{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 28.06361085126286, "eval_steps": 500, "global_step": 30000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "action_query_batch_std": 1.912591528892517, "action_query_norm": 122.23279876708985, "action_relation_loss": 0.06817623265087605, "auxiliary_loss_weight": 1.0, "epoch": 0.009354536950420954, "flow_matching_loss": 1.0699494659900666, "grad_norm": 11.049880981445312, "invalid_tail_samples": 24.4, "learning_rate": 6.000000000000001e-07, "loss": 1.1381, "positive_teacher_pairs": 26709.2, "relation_loss": 0.06817623265087605, "selected_pairs": 26709.2, "step": 10, "student_distance_mean": 107.63986434936524, "teacher_distance_mean": 0.8458072602748871, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.06817623265087605, "weighted_relation_loss": 0.06817623265087605 }, { "action_query_batch_std": 1.8954464077949524, "action_query_norm": 121.25921783447265, "action_relation_loss": 0.06852108426392078, "auxiliary_loss_weight": 1.0, "epoch": 0.018709073900841908, "flow_matching_loss": 1.0575583696365356, "grad_norm": 13.073633193969727, "invalid_tail_samples": 22.4, "learning_rate": 1.2666666666666667e-06, "loss": 1.1261, "positive_teacher_pairs": 27177.8, "relation_loss": 0.06852108426392078, "selected_pairs": 27177.8, "step": 20, "student_distance_mean": 106.92553787231445, "teacher_distance_mean": 0.8513376951217652, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.06852108426392078, "weighted_relation_loss": 0.06852108426392078 }, { "action_query_batch_std": 1.9556469917297363, "action_query_norm": 120.02273712158203, "action_relation_loss": 0.07206994071602821, "auxiliary_loss_weight": 1.0, "epoch": 0.02806361085126286, "flow_matching_loss": 0.8500953912734985, "grad_norm": 7.562002182006836, "invalid_tail_samples": 24.2, "learning_rate": 1.9333333333333336e-06, "loss": 0.9222, "positive_teacher_pairs": 26755.1, "relation_loss": 0.07206994071602821, "selected_pairs": 26755.1, "step": 30, "student_distance_mean": 109.9177017211914, "teacher_distance_mean": 0.8455843806266785, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.07206994071602821, "weighted_relation_loss": 0.07206994071602821 }, { "action_query_batch_std": 2.168392705917358, "action_query_norm": 128.7141441345215, "action_relation_loss": 0.06792716309428215, "auxiliary_loss_weight": 1.0, "epoch": 0.037418147801683815, "flow_matching_loss": 0.60798659324646, "grad_norm": 3.3275556564331055, "invalid_tail_samples": 23.1, "learning_rate": 2.6e-06, "loss": 0.6759, "positive_teacher_pairs": 27012.3, "relation_loss": 0.06792716309428215, "selected_pairs": 27012.3, "step": 40, "student_distance_mean": 124.09095840454101, "teacher_distance_mean": 0.8578713417053223, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.06792716309428215, "weighted_relation_loss": 0.06792716309428215 }, { "action_query_batch_std": 2.37416353225708, "action_query_norm": 143.1913833618164, "action_relation_loss": 0.0665842678397894, "auxiliary_loss_weight": 1.0, "epoch": 0.04677268475210477, "flow_matching_loss": 0.4559076875448227, "grad_norm": 1.6793209314346313, "invalid_tail_samples": 25.8, "learning_rate": 3.2666666666666666e-06, "loss": 0.5225, "positive_teacher_pairs": 26396.6, "relation_loss": 0.0665842678397894, "selected_pairs": 26396.6, "step": 50, "student_distance_mean": 135.95178985595703, "teacher_distance_mean": 0.8490286767482758, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.0665842678397894, "weighted_relation_loss": 0.0665842678397894 }, { "action_query_batch_std": 2.4982990264892577, "action_query_norm": 156.61348724365234, "action_relation_loss": 0.061222634837031366, "auxiliary_loss_weight": 1.0, "epoch": 0.05612722170252572, "flow_matching_loss": 0.3707692980766296, "grad_norm": 1.2340449094772339, "invalid_tail_samples": 21.6, "learning_rate": 3.9333333333333335e-06, "loss": 0.432, "positive_teacher_pairs": 27364.8, "relation_loss": 0.061222634837031366, "selected_pairs": 27364.8, "step": 60, "student_distance_mean": 141.67893829345704, "teacher_distance_mean": 0.8570368528366089, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.061222634837031366, "weighted_relation_loss": 0.061222634837031366 }, { "action_query_batch_std": 2.4792698860168456, "action_query_norm": 162.62819213867186, "action_relation_loss": 0.056347164511680606, "auxiliary_loss_weight": 1.0, "epoch": 0.06548175865294668, "flow_matching_loss": 0.31773262321949003, "grad_norm": 0.9934811592102051, "invalid_tail_samples": 25.5, "learning_rate": 4.6e-06, "loss": 0.3741, "positive_teacher_pairs": 26454.3, "relation_loss": 0.056347164511680606, "selected_pairs": 26454.3, "step": 70, "student_distance_mean": 139.9842758178711, "teacher_distance_mean": 0.8526943862438202, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.056347164511680606, "weighted_relation_loss": 0.056347164511680606 }, { "action_query_batch_std": 2.5468042373657225, "action_query_norm": 168.02757568359374, "action_relation_loss": 0.05257844775915146, "auxiliary_loss_weight": 1.0, "epoch": 0.07483629560336763, "flow_matching_loss": 0.27719379365444186, "grad_norm": 0.6715446710586548, "invalid_tail_samples": 24.8, "learning_rate": 5.266666666666667e-06, "loss": 0.3298, "positive_teacher_pairs": 26614.2, "relation_loss": 0.05257844775915146, "selected_pairs": 26614.2, "step": 80, "student_distance_mean": 143.68640899658203, "teacher_distance_mean": 0.8562870621681213, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.05257844775915146, "weighted_relation_loss": 0.05257844775915146 }, { "action_query_batch_std": 2.52925705909729, "action_query_norm": 160.28639221191406, "action_relation_loss": 0.04784368723630905, "auxiliary_loss_weight": 1.0, "epoch": 0.08419083255378859, "flow_matching_loss": 0.252240301668644, "grad_norm": 0.6869519948959351, "invalid_tail_samples": 23.6, "learning_rate": 5.933333333333334e-06, "loss": 0.3001, "positive_teacher_pairs": 26897.3, "relation_loss": 0.04784368723630905, "selected_pairs": 26897.3, "step": 90, "student_distance_mean": 142.75341796875, "teacher_distance_mean": 0.8514817237854004, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.04784368723630905, "weighted_relation_loss": 0.04784368723630905 }, { "action_query_batch_std": 2.5106595516204835, "action_query_norm": 154.44720916748048, "action_relation_loss": 0.0445989940315485, "auxiliary_loss_weight": 1.0, "epoch": 0.09354536950420954, "flow_matching_loss": 0.22019208073616028, "grad_norm": 0.6758524179458618, "invalid_tail_samples": 23.8, "learning_rate": 6.6e-06, "loss": 0.2648, "positive_teacher_pairs": 26853.0, "relation_loss": 0.0445989940315485, "selected_pairs": 26853.0, "step": 100, "student_distance_mean": 141.1699462890625, "teacher_distance_mean": 0.8571404814720154, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0445989940315485, "weighted_relation_loss": 0.0445989940315485 }, { "action_query_batch_std": 2.580781841278076, "action_query_norm": 157.1111633300781, "action_relation_loss": 0.04071551486849785, "auxiliary_loss_weight": 1.0, "epoch": 0.1028999064546305, "flow_matching_loss": 0.2078786849975586, "grad_norm": 0.6645894050598145, "invalid_tail_samples": 26.6, "learning_rate": 7.266666666666668e-06, "loss": 0.2486, "positive_teacher_pairs": 26207.9, "relation_loss": 0.04071551486849785, "selected_pairs": 26207.9, "step": 110, "student_distance_mean": 145.62954864501953, "teacher_distance_mean": 0.8551790535449981, "valid_action_samples": 229.4, "weighted_auxiliary_loss": 0.04071551486849785, "weighted_relation_loss": 0.04071551486849785 }, { "action_query_batch_std": 2.751747703552246, "action_query_norm": 161.11236572265625, "action_relation_loss": 0.03566614016890526, "auxiliary_loss_weight": 1.0, "epoch": 0.11225444340505145, "flow_matching_loss": 0.1932252362370491, "grad_norm": 0.6238300800323486, "invalid_tail_samples": 24.7, "learning_rate": 7.933333333333334e-06, "loss": 0.2289, "positive_teacher_pairs": 26649.7, "relation_loss": 0.03566614016890526, "selected_pairs": 26649.7, "step": 120, "student_distance_mean": 155.0007522583008, "teacher_distance_mean": 0.8527304410934449, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.03566614016890526, "weighted_relation_loss": 0.03566614016890526 }, { "action_query_batch_std": 2.938173604011536, "action_query_norm": 165.26345977783203, "action_relation_loss": 0.03599611409008503, "auxiliary_loss_weight": 1.0, "epoch": 0.1216089803554724, "flow_matching_loss": 0.1819550409913063, "grad_norm": 0.4981229305267334, "invalid_tail_samples": 21.7, "learning_rate": 8.599999999999999e-06, "loss": 0.218, "positive_teacher_pairs": 27342.7, "relation_loss": 0.03599611409008503, "selected_pairs": 27342.7, "step": 130, "student_distance_mean": 164.9990997314453, "teacher_distance_mean": 0.8566129565238952, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.03599611409008503, "weighted_relation_loss": 0.03599611409008503 }, { "action_query_batch_std": 3.018196177482605, "action_query_norm": 167.10279693603516, "action_relation_loss": 0.03402643725275993, "auxiliary_loss_weight": 1.0, "epoch": 0.13096351730589337, "flow_matching_loss": 0.17340076714754105, "grad_norm": 0.5349473357200623, "invalid_tail_samples": 22.4, "learning_rate": 9.266666666666667e-06, "loss": 0.2074, "positive_teacher_pairs": 27174.7, "relation_loss": 0.03402643725275993, "selected_pairs": 27174.7, "step": 140, "student_distance_mean": 169.8842041015625, "teacher_distance_mean": 0.8592345356941223, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.03402643725275993, "weighted_relation_loss": 0.03402643725275993 }, { "action_query_batch_std": 3.0928674221038817, "action_query_norm": 172.73060455322266, "action_relation_loss": 0.03102922160178423, "auxiliary_loss_weight": 1.0, "epoch": 0.1403180542563143, "flow_matching_loss": 0.1649124339222908, "grad_norm": 0.7145962119102478, "invalid_tail_samples": 23.9, "learning_rate": 9.933333333333334e-06, "loss": 0.1959, "positive_teacher_pairs": 26826.3, "relation_loss": 0.03102922160178423, "selected_pairs": 26826.3, "step": 150, "student_distance_mean": 173.96721496582032, "teacher_distance_mean": 0.8583857834339141, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.03102922160178423, "weighted_relation_loss": 0.03102922160178423 }, { "action_query_batch_std": 3.1232401609420775, "action_query_norm": 173.39476165771484, "action_relation_loss": 0.02957662157714367, "auxiliary_loss_weight": 1.0, "epoch": 0.14967259120673526, "flow_matching_loss": 0.15222562104463577, "grad_norm": 0.5223493576049805, "invalid_tail_samples": 24.8, "learning_rate": 1.06e-05, "loss": 0.1818, "positive_teacher_pairs": 26622.1, "relation_loss": 0.02957662157714367, "selected_pairs": 26622.1, "step": 160, "student_distance_mean": 175.85822143554688, "teacher_distance_mean": 0.8498655676841735, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.02957662157714367, "weighted_relation_loss": 0.02957662157714367 }, { "action_query_batch_std": 3.1262984037399293, "action_query_norm": 172.39686126708983, "action_relation_loss": 0.029181637242436408, "auxiliary_loss_weight": 1.0, "epoch": 0.15902712815715622, "flow_matching_loss": 0.14559588581323624, "grad_norm": 0.5087398886680603, "invalid_tail_samples": 22.0, "learning_rate": 1.1266666666666667e-05, "loss": 0.1748, "positive_teacher_pairs": 27272.6, "relation_loss": 0.029181637242436408, "selected_pairs": 27272.6, "step": 170, "student_distance_mean": 175.71030883789064, "teacher_distance_mean": 0.8486714065074921, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.029181637242436408, "weighted_relation_loss": 0.029181637242436408 }, { "action_query_batch_std": 3.189222264289856, "action_query_norm": 172.14732666015624, "action_relation_loss": 0.028236383199691774, "auxiliary_loss_weight": 1.0, "epoch": 0.16838166510757718, "flow_matching_loss": 0.13952211737632753, "grad_norm": 0.4559570252895355, "invalid_tail_samples": 22.8, "learning_rate": 1.1933333333333333e-05, "loss": 0.1678, "positive_teacher_pairs": 27079.9, "relation_loss": 0.028236383199691774, "selected_pairs": 27079.9, "step": 180, "student_distance_mean": 178.6659927368164, "teacher_distance_mean": 0.8509422183036804, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.028236383199691774, "weighted_relation_loss": 0.028236383199691774 }, { "action_query_batch_std": 3.1658087253570555, "action_query_norm": 170.14852905273438, "action_relation_loss": 0.02836297042667866, "auxiliary_loss_weight": 1.0, "epoch": 0.17773620205799812, "flow_matching_loss": 0.13632603287696837, "grad_norm": 0.48013973236083984, "invalid_tail_samples": 23.7, "learning_rate": 1.2600000000000001e-05, "loss": 0.1647, "positive_teacher_pairs": 26875.0, "relation_loss": 0.02836297042667866, "selected_pairs": 26875.0, "step": 190, "student_distance_mean": 177.2557830810547, "teacher_distance_mean": 0.8458907246589661, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.02836297042667866, "weighted_relation_loss": 0.02836297042667866 }, { "action_query_batch_std": 3.29000186920166, "action_query_norm": 175.99776611328124, "action_relation_loss": 0.02783164884895086, "auxiliary_loss_weight": 1.0, "epoch": 0.18709073900841908, "flow_matching_loss": 0.13707753717899324, "grad_norm": 0.42000335454940796, "invalid_tail_samples": 23.5, "learning_rate": 1.3266666666666666e-05, "loss": 0.1649, "positive_teacher_pairs": 26918.3, "relation_loss": 0.02783164884895086, "selected_pairs": 26918.3, "step": 200, "student_distance_mean": 184.12494049072265, "teacher_distance_mean": 0.8618796646595002, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.02783164884895086, "weighted_relation_loss": 0.02783164884895086 }, { "action_query_batch_std": 3.303533506393433, "action_query_norm": 178.29639282226563, "action_relation_loss": 0.027453589253127575, "auxiliary_loss_weight": 1.0, "epoch": 0.19644527595884004, "flow_matching_loss": 0.12724725008010865, "grad_norm": 0.6304516792297363, "invalid_tail_samples": 22.8, "learning_rate": 1.3933333333333334e-05, "loss": 0.1547, "positive_teacher_pairs": 27081.4, "relation_loss": 0.027453589253127575, "selected_pairs": 27081.4, "step": 210, "student_distance_mean": 185.28952331542968, "teacher_distance_mean": 0.8458437085151672, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.027453589253127575, "weighted_relation_loss": 0.027453589253127575 }, { "action_query_batch_std": 3.302755331993103, "action_query_norm": 176.592529296875, "action_relation_loss": 0.025654416158795358, "auxiliary_loss_weight": 1.0, "epoch": 0.205799812909261, "flow_matching_loss": 0.12997225001454354, "grad_norm": 0.555111825466156, "invalid_tail_samples": 24.5, "learning_rate": 1.4599999999999999e-05, "loss": 0.1556, "positive_teacher_pairs": 26688.9, "relation_loss": 0.025654416158795358, "selected_pairs": 26688.9, "step": 220, "student_distance_mean": 184.9962417602539, "teacher_distance_mean": 0.848963075876236, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.025654416158795358, "weighted_relation_loss": 0.025654416158795358 }, { "action_query_batch_std": 3.4097997665405275, "action_query_norm": 178.2244857788086, "action_relation_loss": 0.025671387277543544, "auxiliary_loss_weight": 1.0, "epoch": 0.21515434985968196, "flow_matching_loss": 0.12258081957697868, "grad_norm": 0.4027562439441681, "invalid_tail_samples": 23.4, "learning_rate": 1.5266666666666667e-05, "loss": 0.1483, "positive_teacher_pairs": 26947.2, "relation_loss": 0.025671387277543544, "selected_pairs": 26947.2, "step": 230, "student_distance_mean": 191.02686004638673, "teacher_distance_mean": 0.8595677196979523, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.025671387277543544, "weighted_relation_loss": 0.025671387277543544 }, { "action_query_batch_std": 3.5026453733444214, "action_query_norm": 183.2259307861328, "action_relation_loss": 0.023777552507817747, "auxiliary_loss_weight": 1.0, "epoch": 0.2245088868101029, "flow_matching_loss": 0.12122728601098061, "grad_norm": 0.4251968562602997, "invalid_tail_samples": 24.6, "learning_rate": 1.5933333333333332e-05, "loss": 0.145, "positive_teacher_pairs": 26659.7, "relation_loss": 0.023777552507817747, "selected_pairs": 26659.7, "step": 240, "student_distance_mean": 196.50845489501953, "teacher_distance_mean": 0.8667687594890594, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.023777552507817747, "weighted_relation_loss": 0.023777552507817747 }, { "action_query_batch_std": 3.507235813140869, "action_query_norm": 183.37318115234376, "action_relation_loss": 0.02374071888625622, "auxiliary_loss_weight": 1.0, "epoch": 0.23386342376052385, "flow_matching_loss": 0.12186196222901344, "grad_norm": 0.3967297077178955, "invalid_tail_samples": 23.5, "learning_rate": 1.66e-05, "loss": 0.1456, "positive_teacher_pairs": 26918.7, "relation_loss": 0.02374071888625622, "selected_pairs": 26918.7, "step": 250, "student_distance_mean": 195.8834976196289, "teacher_distance_mean": 0.8567311465740204, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.02374071888625622, "weighted_relation_loss": 0.02374071888625622 }, { "action_query_batch_std": 3.5464717864990236, "action_query_norm": 185.28692016601562, "action_relation_loss": 0.02403693050146103, "auxiliary_loss_weight": 1.0, "epoch": 0.2432179607109448, "flow_matching_loss": 0.1194988377392292, "grad_norm": 0.7309553027153015, "invalid_tail_samples": 26.7, "learning_rate": 1.726666666666667e-05, "loss": 0.1435, "positive_teacher_pairs": 26196.7, "relation_loss": 0.02403693050146103, "selected_pairs": 26196.7, "step": 260, "student_distance_mean": 199.18551940917968, "teacher_distance_mean": 0.8574040949344635, "valid_action_samples": 229.3, "weighted_auxiliary_loss": 0.02403693050146103, "weighted_relation_loss": 0.02403693050146103 }, { "action_query_batch_std": 3.6302937984466555, "action_query_norm": 189.4575180053711, "action_relation_loss": 0.022687041945755482, "auxiliary_loss_weight": 1.0, "epoch": 0.25257249766136575, "flow_matching_loss": 0.11152774393558502, "grad_norm": 0.5225592851638794, "invalid_tail_samples": 21.1, "learning_rate": 1.7933333333333337e-05, "loss": 0.1342, "positive_teacher_pairs": 27476.1, "relation_loss": 0.022687041945755482, "selected_pairs": 27476.1, "step": 270, "student_distance_mean": 203.74026641845703, "teacher_distance_mean": 0.8486423492431641, "valid_action_samples": 234.9, "weighted_auxiliary_loss": 0.022687041945755482, "weighted_relation_loss": 0.022687041945755482 }, { "action_query_batch_std": 3.727713966369629, "action_query_norm": 192.7791549682617, "action_relation_loss": 0.02351914867758751, "auxiliary_loss_weight": 1.0, "epoch": 0.26192703461178674, "flow_matching_loss": 0.10921182781457901, "grad_norm": 0.522864580154419, "invalid_tail_samples": 22.0, "learning_rate": 1.86e-05, "loss": 0.1327, "positive_teacher_pairs": 27263.9, "relation_loss": 0.02351914867758751, "selected_pairs": 27263.9, "step": 280, "student_distance_mean": 209.12798767089845, "teacher_distance_mean": 0.8574328243732452, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.02351914867758751, "weighted_relation_loss": 0.02351914867758751 }, { "action_query_batch_std": 3.7198429822921755, "action_query_norm": 190.75135345458983, "action_relation_loss": 0.02318516597151756, "auxiliary_loss_weight": 1.0, "epoch": 0.27128157156220767, "flow_matching_loss": 0.11192633360624313, "grad_norm": 0.4600508511066437, "invalid_tail_samples": 27.7, "learning_rate": 1.926666666666667e-05, "loss": 0.1351, "positive_teacher_pairs": 25961.5, "relation_loss": 0.02318516597151756, "selected_pairs": 25961.5, "step": 290, "student_distance_mean": 208.12592315673828, "teacher_distance_mean": 0.8567277014255523, "valid_action_samples": 228.3, "weighted_auxiliary_loss": 0.02318516597151756, "weighted_relation_loss": 0.02318516597151756 }, { "action_query_batch_std": 3.7958707332611086, "action_query_norm": 195.26028900146486, "action_relation_loss": 0.022586559504270555, "auxiliary_loss_weight": 1.0, "epoch": 0.2806361085126286, "flow_matching_loss": 0.109848053753376, "grad_norm": 0.4729570150375366, "invalid_tail_samples": 24.8, "learning_rate": 1.9933333333333334e-05, "loss": 0.1324, "positive_teacher_pairs": 26620.2, "relation_loss": 0.022586559504270555, "selected_pairs": 26620.2, "step": 300, "student_distance_mean": 212.8022018432617, "teacher_distance_mean": 0.8537890136241912, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.022586559504270555, "weighted_relation_loss": 0.022586559504270555 }, { "action_query_batch_std": 3.8364875078201295, "action_query_norm": 198.67525177001954, "action_relation_loss": 0.021388940513134003, "auxiliary_loss_weight": 1.0, "epoch": 0.2899906454630496, "flow_matching_loss": 0.10845717415213585, "grad_norm": 0.3135125935077667, "invalid_tail_samples": 25.5, "learning_rate": 2.06e-05, "loss": 0.1298, "positive_teacher_pairs": 26466.7, "relation_loss": 0.021388940513134003, "selected_pairs": 26466.7, "step": 310, "student_distance_mean": 216.7239227294922, "teacher_distance_mean": 0.852120041847229, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.021388940513134003, "weighted_relation_loss": 0.021388940513134003 }, { "action_query_batch_std": 3.9308857679367066, "action_query_norm": 201.51635284423827, "action_relation_loss": 0.02205349802970886, "auxiliary_loss_weight": 1.0, "epoch": 0.2993451824134705, "flow_matching_loss": 0.10609740689396858, "grad_norm": 0.3777227997779846, "invalid_tail_samples": 22.7, "learning_rate": 2.1266666666666667e-05, "loss": 0.1282, "positive_teacher_pairs": 27105.2, "relation_loss": 0.02205349802970886, "selected_pairs": 27105.2, "step": 320, "student_distance_mean": 220.29512634277344, "teacher_distance_mean": 0.8549017488956452, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.02205349802970886, "weighted_relation_loss": 0.02205349802970886 }, { "action_query_batch_std": 3.9958938360214233, "action_query_norm": 203.020751953125, "action_relation_loss": 0.021906984411180018, "auxiliary_loss_weight": 1.0, "epoch": 0.3086997193638915, "flow_matching_loss": 0.1056068129837513, "grad_norm": 0.4882344901561737, "invalid_tail_samples": 23.3, "learning_rate": 2.1933333333333332e-05, "loss": 0.1275, "positive_teacher_pairs": 26965.0, "relation_loss": 0.021906984411180018, "selected_pairs": 26965.0, "step": 330, "student_distance_mean": 222.571923828125, "teacher_distance_mean": 0.8610243082046509, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.021906984411180018, "weighted_relation_loss": 0.021906984411180018 }, { "action_query_batch_std": 3.9982362747192384, "action_query_norm": 206.47450103759766, "action_relation_loss": 0.02133641969412565, "auxiliary_loss_weight": 1.0, "epoch": 0.31805425631431244, "flow_matching_loss": 0.10679226890206336, "grad_norm": 0.5341958403587341, "invalid_tail_samples": 23.5, "learning_rate": 2.26e-05, "loss": 0.1281, "positive_teacher_pairs": 26916.4, "relation_loss": 0.02133641969412565, "selected_pairs": 26916.4, "step": 340, "student_distance_mean": 224.5735336303711, "teacher_distance_mean": 0.8436944901943206, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.02133641969412565, "weighted_relation_loss": 0.02133641969412565 }, { "action_query_batch_std": 3.993743920326233, "action_query_norm": 204.38870697021486, "action_relation_loss": 0.0208546532317996, "auxiliary_loss_weight": 1.0, "epoch": 0.3274087932647334, "flow_matching_loss": 0.10335411131381989, "grad_norm": 0.4232771396636963, "invalid_tail_samples": 24.1, "learning_rate": 2.326666666666667e-05, "loss": 0.1242, "positive_teacher_pairs": 26783.9, "relation_loss": 0.0208546532317996, "selected_pairs": 26783.9, "step": 350, "student_distance_mean": 223.92751770019532, "teacher_distance_mean": 0.861287534236908, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0208546532317996, "weighted_relation_loss": 0.0208546532317996 }, { "action_query_batch_std": 4.0295493602752686, "action_query_norm": 205.78459777832032, "action_relation_loss": 0.02136755343526602, "auxiliary_loss_weight": 1.0, "epoch": 0.33676333021515437, "flow_matching_loss": 0.10364174023270607, "grad_norm": 0.5512561798095703, "invalid_tail_samples": 25.0, "learning_rate": 2.3933333333333337e-05, "loss": 0.125, "positive_teacher_pairs": 26576.7, "relation_loss": 0.02136755343526602, "selected_pairs": 26576.7, "step": 360, "student_distance_mean": 225.7195266723633, "teacher_distance_mean": 0.8614113867282868, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.02136755343526602, "weighted_relation_loss": 0.02136755343526602 }, { "action_query_batch_std": 4.249338626861572, "action_query_norm": 217.45116119384767, "action_relation_loss": 0.019915934093296526, "auxiliary_loss_weight": 1.0, "epoch": 0.3461178671655753, "flow_matching_loss": 0.10226046442985534, "grad_norm": 0.4511786699295044, "invalid_tail_samples": 23.3, "learning_rate": 2.46e-05, "loss": 0.1222, "positive_teacher_pairs": 26965.0, "relation_loss": 0.019915934093296526, "selected_pairs": 26965.0, "step": 370, "student_distance_mean": 239.53795166015624, "teacher_distance_mean": 0.8600010454654694, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.019915934093296526, "weighted_relation_loss": 0.019915934093296526 }, { "action_query_batch_std": 4.156447076797486, "action_query_norm": 212.5902099609375, "action_relation_loss": 0.02023425083607435, "auxiliary_loss_weight": 1.0, "epoch": 0.35547240411599623, "flow_matching_loss": 0.10050956904888153, "grad_norm": 0.5540117621421814, "invalid_tail_samples": 24.6, "learning_rate": 2.5266666666666666e-05, "loss": 0.1207, "positive_teacher_pairs": 26673.6, "relation_loss": 0.02023425083607435, "selected_pairs": 26673.6, "step": 380, "student_distance_mean": 234.70875244140626, "teacher_distance_mean": 0.8523722171783448, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.02023425083607435, "weighted_relation_loss": 0.02023425083607435 }, { "action_query_batch_std": 4.1234537124633786, "action_query_norm": 210.72919464111328, "action_relation_loss": 0.020051059313118458, "auxiliary_loss_weight": 1.0, "epoch": 0.3648269410664172, "flow_matching_loss": 0.10515229105949402, "grad_norm": 0.46178707480430603, "invalid_tail_samples": 24.5, "learning_rate": 2.5933333333333338e-05, "loss": 0.1252, "positive_teacher_pairs": 26691.8, "relation_loss": 0.020051059313118458, "selected_pairs": 26691.8, "step": 390, "student_distance_mean": 231.69129180908203, "teacher_distance_mean": 0.8537618100643158, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.020051059313118458, "weighted_relation_loss": 0.020051059313118458 }, { "action_query_batch_std": 4.18964786529541, "action_query_norm": 213.20281066894532, "action_relation_loss": 0.019550157897174358, "auxiliary_loss_weight": 1.0, "epoch": 0.37418147801683815, "flow_matching_loss": 0.1026230849325657, "grad_norm": 0.3468194603919983, "invalid_tail_samples": 23.9, "learning_rate": 2.6600000000000003e-05, "loss": 0.1222, "positive_teacher_pairs": 26829.5, "relation_loss": 0.019550157897174358, "selected_pairs": 26829.5, "step": 400, "student_distance_mean": 235.832177734375, "teacher_distance_mean": 0.8585773944854737, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.019550157897174358, "weighted_relation_loss": 0.019550157897174358 }, { "action_query_batch_std": 4.2738532543182375, "action_query_norm": 217.8148971557617, "action_relation_loss": 0.02013334706425667, "auxiliary_loss_weight": 1.0, "epoch": 0.38353601496725914, "flow_matching_loss": 0.09808294996619224, "grad_norm": 0.39833950996398926, "invalid_tail_samples": 22.1, "learning_rate": 2.7266666666666668e-05, "loss": 0.1182, "positive_teacher_pairs": 27249.4, "relation_loss": 0.02013334706425667, "selected_pairs": 27249.4, "step": 410, "student_distance_mean": 241.08030700683594, "teacher_distance_mean": 0.8467832922935485, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.02013334706425667, "weighted_relation_loss": 0.02013334706425667 }, { "action_query_batch_std": 4.390339136123657, "action_query_norm": 222.94143676757812, "action_relation_loss": 0.018668050691485406, "auxiliary_loss_weight": 1.0, "epoch": 0.3928905519176801, "flow_matching_loss": 0.0982811540365219, "grad_norm": 0.4734954833984375, "invalid_tail_samples": 24.0, "learning_rate": 2.7933333333333332e-05, "loss": 0.1169, "positive_teacher_pairs": 26803.8, "relation_loss": 0.018668050691485406, "selected_pairs": 26803.8, "step": 420, "student_distance_mean": 247.9666778564453, "teacher_distance_mean": 0.8591770887374878, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.018668050691485406, "weighted_relation_loss": 0.018668050691485406 }, { "action_query_batch_std": 4.274990797042847, "action_query_norm": 217.10463104248046, "action_relation_loss": 0.019032240286469458, "auxiliary_loss_weight": 1.0, "epoch": 0.402245088868101, "flow_matching_loss": 0.09944747537374496, "grad_norm": 0.3382642865180969, "invalid_tail_samples": 23.2, "learning_rate": 2.86e-05, "loss": 0.1185, "positive_teacher_pairs": 26985.8, "relation_loss": 0.019032240286469458, "selected_pairs": 26985.8, "step": 430, "student_distance_mean": 240.99163818359375, "teacher_distance_mean": 0.8617853462696076, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.019032240286469458, "weighted_relation_loss": 0.019032240286469458 }, { "action_query_batch_std": 4.279836368560791, "action_query_norm": 218.86028289794922, "action_relation_loss": 0.019549339637160303, "auxiliary_loss_weight": 1.0, "epoch": 0.411599625818522, "flow_matching_loss": 0.0993286669254303, "grad_norm": 0.34883013367652893, "invalid_tail_samples": 26.0, "learning_rate": 2.926666666666667e-05, "loss": 0.1189, "positive_teacher_pairs": 26354.5, "relation_loss": 0.019549339637160303, "selected_pairs": 26354.5, "step": 440, "student_distance_mean": 241.34173126220702, "teacher_distance_mean": 0.8463669955730438, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.019549339637160303, "weighted_relation_loss": 0.019549339637160303 }, { "action_query_batch_std": 4.454597043991089, "action_query_norm": 226.6142318725586, "action_relation_loss": 0.01834265235811472, "auxiliary_loss_weight": 1.0, "epoch": 0.42095416276894293, "flow_matching_loss": 0.09961095452308655, "grad_norm": 0.31081536412239075, "invalid_tail_samples": 23.1, "learning_rate": 2.9933333333333337e-05, "loss": 0.118, "positive_teacher_pairs": 27014.6, "relation_loss": 0.01834265235811472, "selected_pairs": 27014.6, "step": 450, "student_distance_mean": 250.8335693359375, "teacher_distance_mean": 0.8585263848304748, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.01834265235811472, "weighted_relation_loss": 0.01834265235811472 }, { "action_query_batch_std": 4.443710422515869, "action_query_norm": 226.0367401123047, "action_relation_loss": 0.01992024164646864, "auxiliary_loss_weight": 1.0, "epoch": 0.4303086997193639, "flow_matching_loss": 0.09696564227342605, "grad_norm": 0.4516272246837616, "invalid_tail_samples": 24.8, "learning_rate": 3.06e-05, "loss": 0.1169, "positive_teacher_pairs": 26617.4, "relation_loss": 0.01992024164646864, "selected_pairs": 26617.4, "step": 460, "student_distance_mean": 249.17134704589844, "teacher_distance_mean": 0.8538972079753876, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.01992024164646864, "weighted_relation_loss": 0.01992024164646864 }, { "action_query_batch_std": 4.369538688659668, "action_query_norm": 220.23301696777344, "action_relation_loss": 0.01897807903587818, "auxiliary_loss_weight": 1.0, "epoch": 0.43966323666978485, "flow_matching_loss": 0.09375459849834442, "grad_norm": 0.4256526529788971, "invalid_tail_samples": 27.6, "learning_rate": 3.126666666666666e-05, "loss": 0.1127, "positive_teacher_pairs": 25988.2, "relation_loss": 0.01897807903587818, "selected_pairs": 25988.2, "step": 470, "student_distance_mean": 245.61532745361328, "teacher_distance_mean": 0.8478752493858337, "valid_action_samples": 228.4, "weighted_auxiliary_loss": 0.01897807903587818, "weighted_relation_loss": 0.01897807903587818 }, { "action_query_batch_std": 4.585294198989868, "action_query_norm": 230.45457458496094, "action_relation_loss": 0.01917589269578457, "auxiliary_loss_weight": 1.0, "epoch": 0.4490177736202058, "flow_matching_loss": 0.09757450819015503, "grad_norm": 0.38343337178230286, "invalid_tail_samples": 25.7, "learning_rate": 3.1933333333333335e-05, "loss": 0.1168, "positive_teacher_pairs": 26416.2, "relation_loss": 0.01917589269578457, "selected_pairs": 26416.2, "step": 480, "student_distance_mean": 258.0065490722656, "teacher_distance_mean": 0.858701741695404, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.01917589269578457, "weighted_relation_loss": 0.01917589269578457 }, { "action_query_batch_std": 4.631412363052368, "action_query_norm": 232.12123260498046, "action_relation_loss": 0.0185067567974329, "auxiliary_loss_weight": 1.0, "epoch": 0.4583723105706268, "flow_matching_loss": 0.09551169797778129, "grad_norm": 0.32808637619018555, "invalid_tail_samples": 25.0, "learning_rate": 3.26e-05, "loss": 0.114, "positive_teacher_pairs": 26572.2, "relation_loss": 0.0185067567974329, "selected_pairs": 26572.2, "step": 490, "student_distance_mean": 260.2520050048828, "teacher_distance_mean": 0.8495366454124451, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0185067567974329, "weighted_relation_loss": 0.0185067567974329 }, { "action_query_batch_std": 4.64166407585144, "action_query_norm": 231.42699584960937, "action_relation_loss": 0.017718618176877497, "auxiliary_loss_weight": 1.0, "epoch": 0.4677268475210477, "flow_matching_loss": 0.09777945727109909, "grad_norm": 0.35714036226272583, "invalid_tail_samples": 25.1, "learning_rate": 3.326666666666667e-05, "loss": 0.1155, "positive_teacher_pairs": 26546.6, "relation_loss": 0.017718618176877497, "selected_pairs": 26546.6, "step": 500, "student_distance_mean": 261.5259979248047, "teacher_distance_mean": 0.8632226824760437, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.017718618176877497, "weighted_relation_loss": 0.017718618176877497 }, { "action_query_batch_std": 4.634678602218628, "action_query_norm": 233.8209197998047, "action_relation_loss": 0.017701963149011134, "auxiliary_loss_weight": 1.0, "epoch": 0.47708138447146864, "flow_matching_loss": 0.09431551396846771, "grad_norm": 0.47436830401420593, "invalid_tail_samples": 22.9, "learning_rate": 3.3933333333333336e-05, "loss": 0.112, "positive_teacher_pairs": 27058.2, "relation_loss": 0.017701963149011134, "selected_pairs": 27058.2, "step": 510, "student_distance_mean": 262.02469940185546, "teacher_distance_mean": 0.8572067856788635, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.017701963149011134, "weighted_relation_loss": 0.017701963149011134 }, { "action_query_batch_std": 4.574918460845947, "action_query_norm": 231.42560272216798, "action_relation_loss": 0.018142166174948217, "auxiliary_loss_weight": 1.0, "epoch": 0.4864359214218896, "flow_matching_loss": 0.09495162963867188, "grad_norm": 0.4766013026237488, "invalid_tail_samples": 21.1, "learning_rate": 3.46e-05, "loss": 0.1131, "positive_teacher_pairs": 27478.1, "relation_loss": 0.018142166174948217, "selected_pairs": 27478.1, "step": 520, "student_distance_mean": 256.79410858154296, "teacher_distance_mean": 0.8518754422664643, "valid_action_samples": 234.9, "weighted_auxiliary_loss": 0.018142166174948217, "weighted_relation_loss": 0.018142166174948217 }, { "action_query_batch_std": 4.612480592727661, "action_query_norm": 233.4261688232422, "action_relation_loss": 0.018377298675477504, "auxiliary_loss_weight": 1.0, "epoch": 0.49579045837231056, "flow_matching_loss": 0.09289046972990037, "grad_norm": 0.49409329891204834, "invalid_tail_samples": 26.2, "learning_rate": 3.526666666666667e-05, "loss": 0.1113, "positive_teacher_pairs": 26298.5, "relation_loss": 0.018377298675477504, "selected_pairs": 26298.5, "step": 530, "student_distance_mean": 260.16479034423827, "teacher_distance_mean": 0.8477982223033905, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.018377298675477504, "weighted_relation_loss": 0.018377298675477504 }, { "action_query_batch_std": 4.729585075378418, "action_query_norm": 233.7132553100586, "action_relation_loss": 0.017598878778517246, "auxiliary_loss_weight": 1.0, "epoch": 0.5051449953227315, "flow_matching_loss": 0.09758690968155861, "grad_norm": 0.5706639885902405, "invalid_tail_samples": 22.9, "learning_rate": 3.593333333333334e-05, "loss": 0.1152, "positive_teacher_pairs": 27060.5, "relation_loss": 0.017598878778517246, "selected_pairs": 27060.5, "step": 540, "student_distance_mean": 264.123388671875, "teacher_distance_mean": 0.8710597097873688, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.017598878778517246, "weighted_relation_loss": 0.017598878778517246 }, { "action_query_batch_std": 4.815340042114258, "action_query_norm": 239.46831665039062, "action_relation_loss": 0.018065017089247702, "auxiliary_loss_weight": 1.0, "epoch": 0.5144995322731525, "flow_matching_loss": 0.09573699906468391, "grad_norm": 0.34826335310935974, "invalid_tail_samples": 26.5, "learning_rate": 3.66e-05, "loss": 0.1138, "positive_teacher_pairs": 26225.1, "relation_loss": 0.018065017089247702, "selected_pairs": 26225.1, "step": 550, "student_distance_mean": 270.57151184082034, "teacher_distance_mean": 0.8591363251209259, "valid_action_samples": 229.5, "weighted_auxiliary_loss": 0.018065017089247702, "weighted_relation_loss": 0.018065017089247702 }, { "action_query_batch_std": 4.741630601882934, "action_query_norm": 238.94192657470703, "action_relation_loss": 0.01778215207159519, "auxiliary_loss_weight": 1.0, "epoch": 0.5238540692235735, "flow_matching_loss": 0.09338715374469757, "grad_norm": 0.40866923332214355, "invalid_tail_samples": 24.7, "learning_rate": 3.726666666666667e-05, "loss": 0.1112, "positive_teacher_pairs": 26645.2, "relation_loss": 0.01778215207159519, "selected_pairs": 26645.2, "step": 560, "student_distance_mean": 267.0246246337891, "teacher_distance_mean": 0.8429630935192108, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.01778215207159519, "weighted_relation_loss": 0.01778215207159519 }, { "action_query_batch_std": 4.78564305305481, "action_query_norm": 239.0897247314453, "action_relation_loss": 0.017794291488826275, "auxiliary_loss_weight": 1.0, "epoch": 0.5332086061739943, "flow_matching_loss": 0.09298616722226143, "grad_norm": 0.5064845085144043, "invalid_tail_samples": 23.8, "learning_rate": 3.793333333333334e-05, "loss": 0.1108, "positive_teacher_pairs": 26852.9, "relation_loss": 0.017794291488826275, "selected_pairs": 26852.9, "step": 570, "student_distance_mean": 269.6378875732422, "teacher_distance_mean": 0.8552877366542816, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.017794291488826275, "weighted_relation_loss": 0.017794291488826275 }, { "action_query_batch_std": 4.818434143066407, "action_query_norm": 240.60321044921875, "action_relation_loss": 0.017581193894147872, "auxiliary_loss_weight": 1.0, "epoch": 0.5425631431244153, "flow_matching_loss": 0.09523181840777398, "grad_norm": 0.35637903213500977, "invalid_tail_samples": 22.3, "learning_rate": 3.86e-05, "loss": 0.1128, "positive_teacher_pairs": 27201.6, "relation_loss": 0.017581193894147872, "selected_pairs": 27201.6, "step": 580, "student_distance_mean": 270.4631713867187, "teacher_distance_mean": 0.8586687326431275, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.017581193894147872, "weighted_relation_loss": 0.017581193894147872 }, { "action_query_batch_std": 4.764396047592163, "action_query_norm": 241.19977569580078, "action_relation_loss": 0.017649205029010774, "auxiliary_loss_weight": 1.0, "epoch": 0.5519176800748363, "flow_matching_loss": 0.09568793475627899, "grad_norm": 0.30014538764953613, "invalid_tail_samples": 23.8, "learning_rate": 3.926666666666667e-05, "loss": 0.1133, "positive_teacher_pairs": 26848.9, "relation_loss": 0.017649205029010774, "selected_pairs": 26848.9, "step": 590, "student_distance_mean": 267.5921203613281, "teacher_distance_mean": 0.8379797995090484, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.017649205029010774, "weighted_relation_loss": 0.017649205029010774 }, { "action_query_batch_std": 4.870819711685181, "action_query_norm": 243.70178985595703, "action_relation_loss": 0.01660277284681797, "auxiliary_loss_weight": 1.0, "epoch": 0.5612722170252572, "flow_matching_loss": 0.09324489459395409, "grad_norm": 0.4089454114437103, "invalid_tail_samples": 25.9, "learning_rate": 3.993333333333333e-05, "loss": 0.1098, "positive_teacher_pairs": 26365.9, "relation_loss": 0.01660277284681797, "selected_pairs": 26365.9, "step": 600, "student_distance_mean": 273.76539306640626, "teacher_distance_mean": 0.8593577206134796, "valid_action_samples": 230.1, "weighted_auxiliary_loss": 0.01660277284681797, "weighted_relation_loss": 0.01660277284681797 }, { "action_query_batch_std": 4.870943975448609, "action_query_norm": 243.02053680419922, "action_relation_loss": 0.01729879816994071, "auxiliary_loss_weight": 1.0, "epoch": 0.5706267539756782, "flow_matching_loss": 0.0930498979985714, "grad_norm": 0.3091792166233063, "invalid_tail_samples": 25.7, "learning_rate": 4.0600000000000004e-05, "loss": 0.1103, "positive_teacher_pairs": 26413.6, "relation_loss": 0.01729879816994071, "selected_pairs": 26413.6, "step": 610, "student_distance_mean": 275.5531707763672, "teacher_distance_mean": 0.8554817795753479, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.01729879816994071, "weighted_relation_loss": 0.01729879816994071 }, { "action_query_batch_std": 4.851469230651856, "action_query_norm": 240.96480407714844, "action_relation_loss": 0.016798316314816476, "auxiliary_loss_weight": 1.0, "epoch": 0.5799812909260992, "flow_matching_loss": 0.08921250551939011, "grad_norm": 0.30739593505859375, "invalid_tail_samples": 22.0, "learning_rate": 4.126666666666667e-05, "loss": 0.106, "positive_teacher_pairs": 27270.6, "relation_loss": 0.016798316314816476, "selected_pairs": 27270.6, "step": 620, "student_distance_mean": 273.2280548095703, "teacher_distance_mean": 0.8501481115818024, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.016798316314816476, "weighted_relation_loss": 0.016798316314816476 }, { "action_query_batch_std": 4.941924381256103, "action_query_norm": 245.58424072265626, "action_relation_loss": 0.016698698792606593, "auxiliary_loss_weight": 1.0, "epoch": 0.5893358278765201, "flow_matching_loss": 0.0920472964644432, "grad_norm": 0.5097075700759888, "invalid_tail_samples": 26.2, "learning_rate": 4.1933333333333334e-05, "loss": 0.1087, "positive_teacher_pairs": 26306.5, "relation_loss": 0.016698698792606593, "selected_pairs": 26306.5, "step": 630, "student_distance_mean": 277.2972106933594, "teacher_distance_mean": 0.8518160104751586, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.016698698792606593, "weighted_relation_loss": 0.016698698792606593 }, { "action_query_batch_std": 4.852025032043457, "action_query_norm": 242.55189056396483, "action_relation_loss": 0.017396665643900633, "auxiliary_loss_weight": 1.0, "epoch": 0.598690364826941, "flow_matching_loss": 0.09254111349582672, "grad_norm": 0.3491365611553192, "invalid_tail_samples": 22.2, "learning_rate": 4.26e-05, "loss": 0.1099, "positive_teacher_pairs": 27222.9, "relation_loss": 0.017396665643900633, "selected_pairs": 27222.9, "step": 640, "student_distance_mean": 273.66802673339845, "teacher_distance_mean": 0.8516839206218719, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.017396665643900633, "weighted_relation_loss": 0.017396665643900633 }, { "action_query_batch_std": 4.932321977615357, "action_query_norm": 245.2572799682617, "action_relation_loss": 0.01585640888661146, "auxiliary_loss_weight": 1.0, "epoch": 0.608044901777362, "flow_matching_loss": 0.08849405199289322, "grad_norm": 0.44555261731147766, "invalid_tail_samples": 24.2, "learning_rate": 4.3266666666666664e-05, "loss": 0.1044, "positive_teacher_pairs": 26754.4, "relation_loss": 0.01585640888661146, "selected_pairs": 26754.4, "step": 650, "student_distance_mean": 277.5366149902344, "teacher_distance_mean": 0.8521072566509247, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.01585640888661146, "weighted_relation_loss": 0.01585640888661146 }, { "action_query_batch_std": 4.985683536529541, "action_query_norm": 247.91678771972656, "action_relation_loss": 0.01645176177844405, "auxiliary_loss_weight": 1.0, "epoch": 0.617399438727783, "flow_matching_loss": 0.09238203689455986, "grad_norm": 0.34168022871017456, "invalid_tail_samples": 24.6, "learning_rate": 4.3933333333333335e-05, "loss": 0.1088, "positive_teacher_pairs": 26672.1, "relation_loss": 0.01645176177844405, "selected_pairs": 26672.1, "step": 660, "student_distance_mean": 280.111767578125, "teacher_distance_mean": 0.8574969232082367, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.01645176177844405, "weighted_relation_loss": 0.01645176177844405 }, { "action_query_batch_std": 5.021868324279785, "action_query_norm": 248.74600372314453, "action_relation_loss": 0.016918748896569014, "auxiliary_loss_weight": 1.0, "epoch": 0.6267539756782039, "flow_matching_loss": 0.09163415506482124, "grad_norm": 0.3770134150981903, "invalid_tail_samples": 21.8, "learning_rate": 4.46e-05, "loss": 0.1086, "positive_teacher_pairs": 27316.5, "relation_loss": 0.016918748896569014, "selected_pairs": 27316.5, "step": 670, "student_distance_mean": 282.67515869140624, "teacher_distance_mean": 0.8672927916049957, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.016918748896569014, "weighted_relation_loss": 0.016918748896569014 }, { "action_query_batch_std": 4.922730398178101, "action_query_norm": 242.04996337890626, "action_relation_loss": 0.017006947565823792, "auxiliary_loss_weight": 1.0, "epoch": 0.6361085126286249, "flow_matching_loss": 0.09539101347327232, "grad_norm": 0.6455338597297668, "invalid_tail_samples": 23.5, "learning_rate": 4.526666666666667e-05, "loss": 0.1124, "positive_teacher_pairs": 26925.6, "relation_loss": 0.017006947565823792, "selected_pairs": 26925.6, "step": 680, "student_distance_mean": 277.6431610107422, "teacher_distance_mean": 0.8570481896400451, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.017006947565823792, "weighted_relation_loss": 0.017006947565823792 }, { "action_query_batch_std": 5.130811595916748, "action_query_norm": 252.6103515625, "action_relation_loss": 0.016640345565974712, "auxiliary_loss_weight": 1.0, "epoch": 0.6454630495790459, "flow_matching_loss": 0.09101317003369332, "grad_norm": 0.47426193952560425, "invalid_tail_samples": 21.5, "learning_rate": 4.5933333333333336e-05, "loss": 0.1077, "positive_teacher_pairs": 27382.9, "relation_loss": 0.016640345565974712, "selected_pairs": 27382.9, "step": 690, "student_distance_mean": 290.12547607421874, "teacher_distance_mean": 0.8531707227230072, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.016640345565974712, "weighted_relation_loss": 0.016640345565974712 }, { "action_query_batch_std": 5.2833899974823, "action_query_norm": 256.99816131591797, "action_relation_loss": 0.01716464664787054, "auxiliary_loss_weight": 1.0, "epoch": 0.6548175865294668, "flow_matching_loss": 0.09063330665230751, "grad_norm": 0.4193283021450043, "invalid_tail_samples": 25.0, "learning_rate": 4.660000000000001e-05, "loss": 0.1078, "positive_teacher_pairs": 26574.2, "relation_loss": 0.01716464664787054, "selected_pairs": 26574.2, "step": 700, "student_distance_mean": 298.55089416503904, "teacher_distance_mean": 0.8632028281688691, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.01716464664787054, "weighted_relation_loss": 0.01716464664787054 }, { "action_query_batch_std": 5.207343006134034, "action_query_norm": 254.1616180419922, "action_relation_loss": 0.01557026244699955, "auxiliary_loss_weight": 1.0, "epoch": 0.6641721234798877, "flow_matching_loss": 0.09162142723798752, "grad_norm": 0.45072633028030396, "invalid_tail_samples": 23.9, "learning_rate": 4.726666666666667e-05, "loss": 0.1072, "positive_teacher_pairs": 26826.8, "relation_loss": 0.01557026244699955, "selected_pairs": 26826.8, "step": 710, "student_distance_mean": 294.2009765625, "teacher_distance_mean": 0.8586376190185547, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.01557026244699955, "weighted_relation_loss": 0.01557026244699955 }, { "action_query_batch_std": 5.332974815368653, "action_query_norm": 262.1114166259766, "action_relation_loss": 0.016024740878492594, "auxiliary_loss_weight": 1.0, "epoch": 0.6735266604303087, "flow_matching_loss": 0.09270400181412697, "grad_norm": 0.546396017074585, "invalid_tail_samples": 21.4, "learning_rate": 4.793333333333334e-05, "loss": 0.1087, "positive_teacher_pairs": 27413.5, "relation_loss": 0.016024740878492594, "selected_pairs": 27413.5, "step": 720, "student_distance_mean": 302.2026611328125, "teacher_distance_mean": 0.8580571472644806, "valid_action_samples": 234.6, "weighted_auxiliary_loss": 0.016024740878492594, "weighted_relation_loss": 0.016024740878492594 }, { "action_query_batch_std": 5.275533819198609, "action_query_norm": 262.13904266357423, "action_relation_loss": 0.015610308479517698, "auxiliary_loss_weight": 1.0, "epoch": 0.6828811973807296, "flow_matching_loss": 0.0890134483575821, "grad_norm": 0.27970701456069946, "invalid_tail_samples": 23.3, "learning_rate": 4.86e-05, "loss": 0.1046, "positive_teacher_pairs": 26964.0, "relation_loss": 0.015610308479517698, "selected_pairs": 26964.0, "step": 730, "student_distance_mean": 298.69325561523436, "teacher_distance_mean": 0.8464121282100677, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.015610308479517698, "weighted_relation_loss": 0.015610308479517698 }, { "action_query_batch_std": 5.179498720169067, "action_query_norm": 254.7204376220703, "action_relation_loss": 0.01595603385940194, "auxiliary_loss_weight": 1.0, "epoch": 0.6922357343311506, "flow_matching_loss": 0.09104391783475876, "grad_norm": 0.3569544553756714, "invalid_tail_samples": 22.1, "learning_rate": 4.926666666666667e-05, "loss": 0.107, "positive_teacher_pairs": 27245.2, "relation_loss": 0.01595603385940194, "selected_pairs": 27245.2, "step": 740, "student_distance_mean": 293.3644958496094, "teacher_distance_mean": 0.8535625696182251, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.01595603385940194, "weighted_relation_loss": 0.01595603385940194 }, { "action_query_batch_std": 5.329921531677246, "action_query_norm": 262.3436553955078, "action_relation_loss": 0.01603262359276414, "auxiliary_loss_weight": 1.0, "epoch": 0.7015902712815716, "flow_matching_loss": 0.08643611147999763, "grad_norm": 0.32468265295028687, "invalid_tail_samples": 22.9, "learning_rate": 4.993333333333334e-05, "loss": 0.1025, "positive_teacher_pairs": 27059.8, "relation_loss": 0.01603262359276414, "selected_pairs": 27059.8, "step": 750, "student_distance_mean": 301.48590698242185, "teacher_distance_mean": 0.8574023485183716, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.01603262359276414, "weighted_relation_loss": 0.01603262359276414 }, { "action_query_batch_std": 5.215629243850708, "action_query_norm": 255.2458251953125, "action_relation_loss": 0.015643595531582833, "auxiliary_loss_weight": 1.0, "epoch": 0.7109448082319925, "flow_matching_loss": 0.08682218790054322, "grad_norm": 0.256466269493103, "invalid_tail_samples": 26.6, "learning_rate": 5.0600000000000003e-05, "loss": 0.1025, "positive_teacher_pairs": 26211.2, "relation_loss": 0.015643595531582833, "selected_pairs": 26211.2, "step": 760, "student_distance_mean": 294.6263946533203, "teacher_distance_mean": 0.8562582790851593, "valid_action_samples": 229.4, "weighted_auxiliary_loss": 0.015643595531582833, "weighted_relation_loss": 0.015643595531582833 }, { "action_query_batch_std": 5.316931867599488, "action_query_norm": 260.0880493164062, "action_relation_loss": 0.01554593788459897, "auxiliary_loss_weight": 1.0, "epoch": 0.7202993451824135, "flow_matching_loss": 0.08374262526631356, "grad_norm": 0.2577996850013733, "invalid_tail_samples": 23.0, "learning_rate": 5.1266666666666675e-05, "loss": 0.0993, "positive_teacher_pairs": 27034.8, "relation_loss": 0.01554593788459897, "selected_pairs": 27034.8, "step": 770, "student_distance_mean": 301.0285217285156, "teacher_distance_mean": 0.8528332710266113, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.01554593788459897, "weighted_relation_loss": 0.01554593788459897 }, { "action_query_batch_std": 5.198346996307373, "action_query_norm": 257.47698669433595, "action_relation_loss": 0.015580863784998655, "auxiliary_loss_weight": 1.0, "epoch": 0.7296538821328344, "flow_matching_loss": 0.0851424716413021, "grad_norm": 0.27716967463493347, "invalid_tail_samples": 22.8, "learning_rate": 5.193333333333333e-05, "loss": 0.1007, "positive_teacher_pairs": 27082.2, "relation_loss": 0.015580863784998655, "selected_pairs": 27082.2, "step": 780, "student_distance_mean": 294.5426300048828, "teacher_distance_mean": 0.8558024168014526, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.015580863784998655, "weighted_relation_loss": 0.015580863784998655 }, { "action_query_batch_std": 5.243866968154907, "action_query_norm": 258.7858917236328, "action_relation_loss": 0.015798735804855822, "auxiliary_loss_weight": 1.0, "epoch": 0.7390084190832554, "flow_matching_loss": 0.08564209043979645, "grad_norm": 0.24821972846984863, "invalid_tail_samples": 22.9, "learning_rate": 5.2600000000000005e-05, "loss": 0.1014, "positive_teacher_pairs": 27058.4, "relation_loss": 0.015798735804855822, "selected_pairs": 27058.4, "step": 790, "student_distance_mean": 295.9865386962891, "teacher_distance_mean": 0.8593971133232117, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.015798735804855822, "weighted_relation_loss": 0.015798735804855822 }, { "action_query_batch_std": 5.416759872436524, "action_query_norm": 267.5557067871094, "action_relation_loss": 0.015984362550079824, "auxiliary_loss_weight": 1.0, "epoch": 0.7483629560336763, "flow_matching_loss": 0.08665185198187828, "grad_norm": 0.2519790530204773, "invalid_tail_samples": 22.7, "learning_rate": 5.326666666666666e-05, "loss": 0.1026, "positive_teacher_pairs": 27107.8, "relation_loss": 0.015984362550079824, "selected_pairs": 27107.8, "step": 800, "student_distance_mean": 307.35413818359376, "teacher_distance_mean": 0.8490899443626404, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.015984362550079824, "weighted_relation_loss": 0.015984362550079824 }, { "action_query_batch_std": 5.33721342086792, "action_query_norm": 260.7020629882812, "action_relation_loss": 0.015282011777162551, "auxiliary_loss_weight": 1.0, "epoch": 0.7577174929840973, "flow_matching_loss": 0.08343541249632835, "grad_norm": 0.2997523844242096, "invalid_tail_samples": 23.0, "learning_rate": 5.3933333333333334e-05, "loss": 0.0987, "positive_teacher_pairs": 27045.8, "relation_loss": 0.015282011777162551, "selected_pairs": 27045.8, "step": 810, "student_distance_mean": 301.3201873779297, "teacher_distance_mean": 0.8540050446987152, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.015282011777162551, "weighted_relation_loss": 0.015282011777162551 }, { "action_query_batch_std": 5.464232158660889, "action_query_norm": 267.65406494140626, "action_relation_loss": 0.01497331103309989, "auxiliary_loss_weight": 1.0, "epoch": 0.7670720299345183, "flow_matching_loss": 0.08723899945616723, "grad_norm": 0.30261775851249695, "invalid_tail_samples": 21.9, "learning_rate": 5.4600000000000006e-05, "loss": 0.1022, "positive_teacher_pairs": 27290.8, "relation_loss": 0.01497331103309989, "selected_pairs": 27290.8, "step": 820, "student_distance_mean": 309.15845947265626, "teacher_distance_mean": 0.8606010735034942, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.01497331103309989, "weighted_relation_loss": 0.01497331103309989 }, { "action_query_batch_std": 5.418412828445435, "action_query_norm": 265.8592102050781, "action_relation_loss": 0.01518045412376523, "auxiliary_loss_weight": 1.0, "epoch": 0.7764265668849392, "flow_matching_loss": 0.08856960535049438, "grad_norm": 0.2799093425273895, "invalid_tail_samples": 24.1, "learning_rate": 5.5266666666666664e-05, "loss": 0.1038, "positive_teacher_pairs": 26780.2, "relation_loss": 0.01518045412376523, "selected_pairs": 26780.2, "step": 830, "student_distance_mean": 306.6482391357422, "teacher_distance_mean": 0.8602522850036621, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.01518045412376523, "weighted_relation_loss": 0.01518045412376523 }, { "action_query_batch_std": 5.354364681243896, "action_query_norm": 261.83213500976564, "action_relation_loss": 0.014724650699645282, "auxiliary_loss_weight": 1.0, "epoch": 0.7857811038353602, "flow_matching_loss": 0.08233556002378464, "grad_norm": 0.28539273142814636, "invalid_tail_samples": 22.4, "learning_rate": 5.5933333333333335e-05, "loss": 0.0971, "positive_teacher_pairs": 27173.0, "relation_loss": 0.014724650699645282, "selected_pairs": 27173.0, "step": 840, "student_distance_mean": 302.9413604736328, "teacher_distance_mean": 0.8439851760864258, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.014724650699645282, "weighted_relation_loss": 0.014724650699645282 }, { "action_query_batch_std": 5.490772771835327, "action_query_norm": 267.6632537841797, "action_relation_loss": 0.01482884380966425, "auxiliary_loss_weight": 1.0, "epoch": 0.7951356407857811, "flow_matching_loss": 0.08616614565253258, "grad_norm": 0.25995370745658875, "invalid_tail_samples": 23.2, "learning_rate": 5.66e-05, "loss": 0.101, "positive_teacher_pairs": 26987.0, "relation_loss": 0.01482884380966425, "selected_pairs": 26987.0, "step": 850, "student_distance_mean": 311.17486572265625, "teacher_distance_mean": 0.857982736825943, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.01482884380966425, "weighted_relation_loss": 0.01482884380966425 }, { "action_query_batch_std": 5.477167797088623, "action_query_norm": 268.9967468261719, "action_relation_loss": 0.015197731833904982, "auxiliary_loss_weight": 1.0, "epoch": 0.804490177736202, "flow_matching_loss": 0.08461062982678413, "grad_norm": 0.31343358755111694, "invalid_tail_samples": 23.2, "learning_rate": 5.726666666666667e-05, "loss": 0.0998, "positive_teacher_pairs": 26989.0, "relation_loss": 0.015197731833904982, "selected_pairs": 26989.0, "step": 860, "student_distance_mean": 309.54148254394534, "teacher_distance_mean": 0.8604804277420044, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.015197731833904982, "weighted_relation_loss": 0.015197731833904982 }, { "action_query_batch_std": 5.396999883651733, "action_query_norm": 264.7397125244141, "action_relation_loss": 0.014559548441320657, "auxiliary_loss_weight": 1.0, "epoch": 0.813844714686623, "flow_matching_loss": 0.08937940299510956, "grad_norm": 0.31960514187812805, "invalid_tail_samples": 24.5, "learning_rate": 5.7933333333333337e-05, "loss": 0.1039, "positive_teacher_pairs": 26689.3, "relation_loss": 0.014559548441320657, "selected_pairs": 26689.3, "step": 870, "student_distance_mean": 304.96461486816406, "teacher_distance_mean": 0.8650976240634918, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.014559548441320657, "weighted_relation_loss": 0.014559548441320657 }, { "action_query_batch_std": 5.376630544662476, "action_query_norm": 264.0845886230469, "action_relation_loss": 0.015391489118337631, "auxiliary_loss_weight": 1.0, "epoch": 0.823199251637044, "flow_matching_loss": 0.08383436501026154, "grad_norm": 0.2700226902961731, "invalid_tail_samples": 24.2, "learning_rate": 5.86e-05, "loss": 0.0992, "positive_teacher_pairs": 26760.4, "relation_loss": 0.015391489118337631, "selected_pairs": 26760.4, "step": 880, "student_distance_mean": 305.3624694824219, "teacher_distance_mean": 0.8410179138183593, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.015391489118337631, "weighted_relation_loss": 0.015391489118337631 }, { "action_query_batch_std": 5.388821172714233, "action_query_norm": 263.62275390625, "action_relation_loss": 0.015140745788812637, "auxiliary_loss_weight": 1.0, "epoch": 0.8325537885874649, "flow_matching_loss": 0.08412848711013794, "grad_norm": 0.24542509019374847, "invalid_tail_samples": 23.6, "learning_rate": 5.926666666666667e-05, "loss": 0.0993, "positive_teacher_pairs": 26894.0, "relation_loss": 0.015140745788812637, "selected_pairs": 26894.0, "step": 890, "student_distance_mean": 304.9043273925781, "teacher_distance_mean": 0.8509200572967529, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.015140745788812637, "weighted_relation_loss": 0.015140745788812637 }, { "action_query_batch_std": 5.4964573860168455, "action_query_norm": 267.28168334960935, "action_relation_loss": 0.015279018599539996, "auxiliary_loss_weight": 1.0, "epoch": 0.8419083255378859, "flow_matching_loss": 0.08584850206971169, "grad_norm": 0.2944795787334442, "invalid_tail_samples": 21.9, "learning_rate": 5.9933333333333345e-05, "loss": 0.1011, "positive_teacher_pairs": 27289.2, "relation_loss": 0.015279018599539996, "selected_pairs": 27289.2, "step": 900, "student_distance_mean": 310.51397399902345, "teacher_distance_mean": 0.8565319061279297, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.015279018599539996, "weighted_relation_loss": 0.015279018599539996 }, { "action_query_batch_std": 5.627483129501343, "action_query_norm": 275.3725128173828, "action_relation_loss": 0.015119998902082443, "auxiliary_loss_weight": 1.0, "epoch": 0.8512628624883068, "flow_matching_loss": 0.08480086177587509, "grad_norm": 0.26865100860595703, "invalid_tail_samples": 23.6, "learning_rate": 6.06e-05, "loss": 0.0999, "positive_teacher_pairs": 26898.3, "relation_loss": 0.015119998902082443, "selected_pairs": 26898.3, "step": 910, "student_distance_mean": 317.6078735351563, "teacher_distance_mean": 0.850821852684021, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.015119998902082443, "weighted_relation_loss": 0.015119998902082443 }, { "action_query_batch_std": 5.602517414093017, "action_query_norm": 274.68547973632815, "action_relation_loss": 0.014109713211655616, "auxiliary_loss_weight": 1.0, "epoch": 0.8606173994387278, "flow_matching_loss": 0.08387444838881493, "grad_norm": 0.3088811933994293, "invalid_tail_samples": 24.6, "learning_rate": 6.126666666666667e-05, "loss": 0.098, "positive_teacher_pairs": 26660.5, "relation_loss": 0.014109713211655616, "selected_pairs": 26660.5, "step": 920, "student_distance_mean": 315.23125915527345, "teacher_distance_mean": 0.8547115445137023, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.014109713211655616, "weighted_relation_loss": 0.014109713211655616 }, { "action_query_batch_std": 5.5141054630279545, "action_query_norm": 273.6205780029297, "action_relation_loss": 0.014714906923472881, "auxiliary_loss_weight": 1.0, "epoch": 0.8699719363891487, "flow_matching_loss": 0.08581111207604408, "grad_norm": 0.385627418756485, "invalid_tail_samples": 22.8, "learning_rate": 6.193333333333333e-05, "loss": 0.1005, "positive_teacher_pairs": 27086.8, "relation_loss": 0.014714906923472881, "selected_pairs": 27086.8, "step": 930, "student_distance_mean": 311.24171447753906, "teacher_distance_mean": 0.8500035166740417, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.014714906923472881, "weighted_relation_loss": 0.014714906923472881 }, { "action_query_batch_std": 5.715878820419311, "action_query_norm": 280.4617492675781, "action_relation_loss": 0.014581979624927044, "auxiliary_loss_weight": 1.0, "epoch": 0.8793264733395697, "flow_matching_loss": 0.0852335698902607, "grad_norm": 0.31146571040153503, "invalid_tail_samples": 20.5, "learning_rate": 6.26e-05, "loss": 0.0998, "positive_teacher_pairs": 27623.5, "relation_loss": 0.014581979624927044, "selected_pairs": 27623.5, "step": 940, "student_distance_mean": 322.3864440917969, "teacher_distance_mean": 0.8509825527667999, "valid_action_samples": 235.5, "weighted_auxiliary_loss": 0.014581979624927044, "weighted_relation_loss": 0.014581979624927044 }, { "action_query_batch_std": 5.728383541107178, "action_query_norm": 278.63169555664064, "action_relation_loss": 0.014553929772228002, "auxiliary_loss_weight": 1.0, "epoch": 0.8886810102899907, "flow_matching_loss": 0.08527024164795875, "grad_norm": 0.22286029160022736, "invalid_tail_samples": 22.0, "learning_rate": 6.326666666666667e-05, "loss": 0.0998, "positive_teacher_pairs": 27269.9, "relation_loss": 0.014553929772228002, "selected_pairs": 27269.9, "step": 950, "student_distance_mean": 323.6655548095703, "teacher_distance_mean": 0.8667896330356598, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.014553929772228002, "weighted_relation_loss": 0.014553929772228002 }, { "action_query_batch_std": 5.828868770599366, "action_query_norm": 286.4430694580078, "action_relation_loss": 0.014512115437537432, "auxiliary_loss_weight": 1.0, "epoch": 0.8980355472404116, "flow_matching_loss": 0.0832817755639553, "grad_norm": 0.33373409509658813, "invalid_tail_samples": 25.4, "learning_rate": 6.393333333333333e-05, "loss": 0.0978, "positive_teacher_pairs": 26485.8, "relation_loss": 0.014512115437537432, "selected_pairs": 26485.8, "step": 960, "student_distance_mean": 329.7289642333984, "teacher_distance_mean": 0.860389792919159, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.014512115437537432, "weighted_relation_loss": 0.014512115437537432 }, { "action_query_batch_std": 5.662932682037353, "action_query_norm": 281.2899627685547, "action_relation_loss": 0.014835766889154911, "auxiliary_loss_weight": 1.0, "epoch": 0.9073900841908326, "flow_matching_loss": 0.08368845358490944, "grad_norm": 0.2989594042301178, "invalid_tail_samples": 25.2, "learning_rate": 6.460000000000001e-05, "loss": 0.0985, "positive_teacher_pairs": 26531.5, "relation_loss": 0.014835766889154911, "selected_pairs": 26531.5, "step": 970, "student_distance_mean": 321.8738586425781, "teacher_distance_mean": 0.8525396347045898, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.014835766889154911, "weighted_relation_loss": 0.014835766889154911 }, { "action_query_batch_std": 5.732227182388305, "action_query_norm": 282.0578918457031, "action_relation_loss": 0.013633608538657426, "auxiliary_loss_weight": 1.0, "epoch": 0.9167446211412535, "flow_matching_loss": 0.08433509320020675, "grad_norm": 0.44581565260887146, "invalid_tail_samples": 23.5, "learning_rate": 6.526666666666666e-05, "loss": 0.098, "positive_teacher_pairs": 26920.1, "relation_loss": 0.013633608538657426, "selected_pairs": 26920.1, "step": 980, "student_distance_mean": 324.54527587890624, "teacher_distance_mean": 0.8592372298240661, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.013633608538657426, "weighted_relation_loss": 0.013633608538657426 }, { "action_query_batch_std": 5.673796129226685, "action_query_norm": 280.8228240966797, "action_relation_loss": 0.014015140291303397, "auxiliary_loss_weight": 1.0, "epoch": 0.9260991580916744, "flow_matching_loss": 0.0858492262661457, "grad_norm": 0.2553304135799408, "invalid_tail_samples": 23.1, "learning_rate": 6.593333333333334e-05, "loss": 0.0999, "positive_teacher_pairs": 27012.6, "relation_loss": 0.014015140291303397, "selected_pairs": 27012.6, "step": 990, "student_distance_mean": 320.6387481689453, "teacher_distance_mean": 0.8498923063278199, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.014015140291303397, "weighted_relation_loss": 0.014015140291303397 }, { "action_query_batch_std": 5.806730127334594, "action_query_norm": 284.3854553222656, "action_relation_loss": 0.014767719898372889, "auxiliary_loss_weight": 1.0, "epoch": 0.9354536950420954, "flow_matching_loss": 0.08785077631473541, "grad_norm": 0.3260240852832794, "invalid_tail_samples": 24.5, "learning_rate": 6.66e-05, "loss": 0.1026, "positive_teacher_pairs": 26686.1, "relation_loss": 0.014767719898372889, "selected_pairs": 26686.1, "step": 1000, "student_distance_mean": 327.60626525878905, "teacher_distance_mean": 0.8574318587779999, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.014767719898372889, "weighted_relation_loss": 0.014767719898372889 }, { "action_query_batch_std": 5.892968416213989, "action_query_norm": 287.7216827392578, "action_relation_loss": 0.014229486975818873, "auxiliary_loss_weight": 1.0, "epoch": 0.9448082319925164, "flow_matching_loss": 0.08476958945393562, "grad_norm": 0.30873581767082214, "invalid_tail_samples": 24.1, "learning_rate": 6.726666666666667e-05, "loss": 0.099, "positive_teacher_pairs": 26782.0, "relation_loss": 0.014229486975818873, "selected_pairs": 26782.0, "step": 1010, "student_distance_mean": 334.3787506103516, "teacher_distance_mean": 0.8578993022441864, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.014229486975818873, "weighted_relation_loss": 0.014229486975818873 }, { "action_query_batch_std": 5.898523950576783, "action_query_norm": 287.4384521484375, "action_relation_loss": 0.014178570080548524, "auxiliary_loss_weight": 1.0, "epoch": 0.9541627689429373, "flow_matching_loss": 0.08209841251373291, "grad_norm": 0.26207298040390015, "invalid_tail_samples": 22.5, "learning_rate": 6.793333333333334e-05, "loss": 0.0963, "positive_teacher_pairs": 27155.1, "relation_loss": 0.014178570080548524, "selected_pairs": 27155.1, "step": 1020, "student_distance_mean": 335.11900024414064, "teacher_distance_mean": 0.849157053232193, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.014178570080548524, "weighted_relation_loss": 0.014178570080548524 }, { "action_query_batch_std": 5.790295171737671, "action_query_norm": 281.8519653320312, "action_relation_loss": 0.014263696316629649, "auxiliary_loss_weight": 1.0, "epoch": 0.9635173058933583, "flow_matching_loss": 0.08502688333392143, "grad_norm": 0.33636802434921265, "invalid_tail_samples": 24.4, "learning_rate": 6.860000000000001e-05, "loss": 0.0993, "positive_teacher_pairs": 26726.0, "relation_loss": 0.014263696316629649, "selected_pairs": 26726.0, "step": 1030, "student_distance_mean": 328.2844299316406, "teacher_distance_mean": 0.8524686574935914, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.014263696316629649, "weighted_relation_loss": 0.014263696316629649 }, { "action_query_batch_std": 5.825967311859131, "action_query_norm": 282.2748596191406, "action_relation_loss": 0.013742216303944588, "auxiliary_loss_weight": 1.0, "epoch": 0.9728718428437793, "flow_matching_loss": 0.08234119564294815, "grad_norm": 0.2712647020816803, "invalid_tail_samples": 22.3, "learning_rate": 6.926666666666667e-05, "loss": 0.0961, "positive_teacher_pairs": 27193.9, "relation_loss": 0.013742216303944588, "selected_pairs": 27193.9, "step": 1040, "student_distance_mean": 329.42043151855466, "teacher_distance_mean": 0.8559509694576264, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.013742216303944588, "weighted_relation_loss": 0.013742216303944588 }, { "action_query_batch_std": 5.913038539886474, "action_query_norm": 285.8617431640625, "action_relation_loss": 0.01410837834700942, "auxiliary_loss_weight": 1.0, "epoch": 0.9822263797942001, "flow_matching_loss": 0.08246059492230415, "grad_norm": 0.254049152135849, "invalid_tail_samples": 27.5, "learning_rate": 6.993333333333334e-05, "loss": 0.0966, "positive_teacher_pairs": 26000.8, "relation_loss": 0.01410837834700942, "selected_pairs": 26000.8, "step": 1050, "student_distance_mean": 335.687060546875, "teacher_distance_mean": 0.8739325344562531, "valid_action_samples": 228.5, "weighted_auxiliary_loss": 0.01410837834700942, "weighted_relation_loss": 0.01410837834700942 }, { "action_query_batch_std": 5.948451232910156, "action_query_norm": 289.0108184814453, "action_relation_loss": 0.013739433791488408, "auxiliary_loss_weight": 1.0, "epoch": 0.9915809167446211, "flow_matching_loss": 0.08207027912139893, "grad_norm": 0.2752748131752014, "invalid_tail_samples": 20.5, "learning_rate": 7.06e-05, "loss": 0.0958, "positive_teacher_pairs": 27615.0, "relation_loss": 0.013739433791488408, "selected_pairs": 27615.0, "step": 1060, "student_distance_mean": 336.6816101074219, "teacher_distance_mean": 0.8545524895191192, "valid_action_samples": 235.5, "weighted_auxiliary_loss": 0.013739433791488408, "weighted_relation_loss": 0.013739433791488408 }, { "action_query_batch_std": 5.810670709609985, "action_query_norm": 285.2886993408203, "action_relation_loss": 0.013453258108347655, "auxiliary_loss_weight": 1.0, "epoch": 1.000935453695042, "flow_matching_loss": 0.08048364222049713, "grad_norm": 0.30194273591041565, "invalid_tail_samples": 22.1, "learning_rate": 7.126666666666667e-05, "loss": 0.0939, "positive_teacher_pairs": 24331.3, "relation_loss": 0.013453258108347655, "selected_pairs": 24331.3, "step": 1070, "student_distance_mean": 330.3103424072266, "teacher_distance_mean": 0.8568814516067504, "valid_action_samples": 214.0, "weighted_auxiliary_loss": 0.013453258108347655, "weighted_relation_loss": 0.013453258108347655 }, { "action_query_batch_std": 5.951973009109497, "action_query_norm": 288.4409637451172, "action_relation_loss": 0.013729339372366667, "auxiliary_loss_weight": 1.0, "epoch": 1.010289990645463, "flow_matching_loss": 0.08458795920014381, "grad_norm": 0.31822100281715393, "invalid_tail_samples": 23.8, "learning_rate": 7.193333333333334e-05, "loss": 0.0983, "positive_teacher_pairs": 26854.3, "relation_loss": 0.013729339372366667, "selected_pairs": 26854.3, "step": 1080, "student_distance_mean": 337.3917572021484, "teacher_distance_mean": 0.8550265669822693, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.013729339372366667, "weighted_relation_loss": 0.013729339372366667 }, { "action_query_batch_std": 5.980794286727905, "action_query_norm": 292.86931762695315, "action_relation_loss": 0.014356639049947263, "auxiliary_loss_weight": 1.0, "epoch": 1.019644527595884, "flow_matching_loss": 0.08192722201347351, "grad_norm": 0.2891424894332886, "invalid_tail_samples": 24.5, "learning_rate": 7.26e-05, "loss": 0.0963, "positive_teacher_pairs": 26685.2, "relation_loss": 0.014356639049947263, "selected_pairs": 26685.2, "step": 1090, "student_distance_mean": 338.6600769042969, "teacher_distance_mean": 0.855253803730011, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.014356639049947263, "weighted_relation_loss": 0.014356639049947263 }, { "action_query_batch_std": 6.085245418548584, "action_query_norm": 295.1039306640625, "action_relation_loss": 0.01389016853645444, "auxiliary_loss_weight": 1.0, "epoch": 1.028999064546305, "flow_matching_loss": 0.08617371618747711, "grad_norm": 0.3481314182281494, "invalid_tail_samples": 21.9, "learning_rate": 7.326666666666667e-05, "loss": 0.1001, "positive_teacher_pairs": 27292.0, "relation_loss": 0.01389016853645444, "selected_pairs": 27292.0, "step": 1100, "student_distance_mean": 344.50917358398436, "teacher_distance_mean": 0.8531495630741119, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.01389016853645444, "weighted_relation_loss": 0.01389016853645444 }, { "action_query_batch_std": 6.258535718917846, "action_query_norm": 306.98407592773435, "action_relation_loss": 0.013696119002997876, "auxiliary_loss_weight": 1.0, "epoch": 1.0383536014967258, "flow_matching_loss": 0.08299609795212745, "grad_norm": 0.24717587232589722, "invalid_tail_samples": 25.6, "learning_rate": 7.393333333333333e-05, "loss": 0.0967, "positive_teacher_pairs": 26446.3, "relation_loss": 0.013696119002997876, "selected_pairs": 26446.3, "step": 1110, "student_distance_mean": 355.65496215820315, "teacher_distance_mean": 0.8546444058418274, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.013696119002997876, "weighted_relation_loss": 0.013696119002997876 }, { "action_query_batch_std": 6.082061147689819, "action_query_norm": 296.2310333251953, "action_relation_loss": 0.013527688384056092, "auxiliary_loss_weight": 1.0, "epoch": 1.047708138447147, "flow_matching_loss": 0.08298024907708168, "grad_norm": 0.23397612571716309, "invalid_tail_samples": 21.1, "learning_rate": 7.46e-05, "loss": 0.0965, "positive_teacher_pairs": 27480.5, "relation_loss": 0.013527688384056092, "selected_pairs": 27480.5, "step": 1120, "student_distance_mean": 344.46608276367186, "teacher_distance_mean": 0.8579326033592224, "valid_action_samples": 234.9, "weighted_auxiliary_loss": 0.013527688384056092, "weighted_relation_loss": 0.013527688384056092 }, { "action_query_batch_std": 6.277023220062256, "action_query_norm": 302.7624481201172, "action_relation_loss": 0.01420425996184349, "auxiliary_loss_weight": 1.0, "epoch": 1.0570626753975678, "flow_matching_loss": 0.0804351732134819, "grad_norm": 0.2730085551738739, "invalid_tail_samples": 23.0, "learning_rate": 7.526666666666668e-05, "loss": 0.0946, "positive_teacher_pairs": 27033.8, "relation_loss": 0.01420425996184349, "selected_pairs": 27033.8, "step": 1130, "student_distance_mean": 355.32244262695315, "teacher_distance_mean": 0.8693834841251373, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.01420425996184349, "weighted_relation_loss": 0.01420425996184349 }, { "action_query_batch_std": 6.1150750637054445, "action_query_norm": 296.6965270996094, "action_relation_loss": 0.013628887478262186, "auxiliary_loss_weight": 1.0, "epoch": 1.0664172123479887, "flow_matching_loss": 0.08204724341630935, "grad_norm": 0.2014453113079071, "invalid_tail_samples": 25.7, "learning_rate": 7.593333333333334e-05, "loss": 0.0957, "positive_teacher_pairs": 26409.6, "relation_loss": 0.013628887478262186, "selected_pairs": 26409.6, "step": 1140, "student_distance_mean": 346.7187438964844, "teacher_distance_mean": 0.8624014377593994, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.013628887478262186, "weighted_relation_loss": 0.013628887478262186 }, { "action_query_batch_std": 6.060169363021851, "action_query_norm": 293.31968994140624, "action_relation_loss": 0.013852603919804096, "auxiliary_loss_weight": 1.0, "epoch": 1.0757717492984098, "flow_matching_loss": 0.08112307712435722, "grad_norm": 0.2842320501804352, "invalid_tail_samples": 20.3, "learning_rate": 7.66e-05, "loss": 0.095, "positive_teacher_pairs": 27662.5, "relation_loss": 0.013852603919804096, "selected_pairs": 27662.5, "step": 1150, "student_distance_mean": 343.0665679931641, "teacher_distance_mean": 0.8590244889259339, "valid_action_samples": 235.7, "weighted_auxiliary_loss": 0.013852603919804096, "weighted_relation_loss": 0.013852603919804096 }, { "action_query_batch_std": 6.206860828399658, "action_query_norm": 303.0013702392578, "action_relation_loss": 0.014117103442549706, "auxiliary_loss_weight": 1.0, "epoch": 1.0851262862488307, "flow_matching_loss": 0.08251656368374824, "grad_norm": 0.28802818059921265, "invalid_tail_samples": 24.8, "learning_rate": 7.726666666666667e-05, "loss": 0.0966, "positive_teacher_pairs": 26627.6, "relation_loss": 0.014117103442549706, "selected_pairs": 26627.6, "step": 1160, "student_distance_mean": 353.7998107910156, "teacher_distance_mean": 0.8621905088424683, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.014117103442549706, "weighted_relation_loss": 0.014117103442549706 }, { "action_query_batch_std": 6.070626306533813, "action_query_norm": 295.3673126220703, "action_relation_loss": 0.013578832149505615, "auxiliary_loss_weight": 1.0, "epoch": 1.0944808231992516, "flow_matching_loss": 0.08257460221648216, "grad_norm": 0.2936771512031555, "invalid_tail_samples": 23.5, "learning_rate": 7.793333333333333e-05, "loss": 0.0962, "positive_teacher_pairs": 26926.1, "relation_loss": 0.013578832149505615, "selected_pairs": 26926.1, "step": 1170, "student_distance_mean": 342.68116149902346, "teacher_distance_mean": 0.8496854722499847, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.013578832149505615, "weighted_relation_loss": 0.013578832149505615 }, { "action_query_batch_std": 6.249606323242188, "action_query_norm": 301.8321105957031, "action_relation_loss": 0.01346318842843175, "auxiliary_loss_weight": 1.0, "epoch": 1.1038353601496727, "flow_matching_loss": 0.08058961480855942, "grad_norm": 0.28090840578079224, "invalid_tail_samples": 24.3, "learning_rate": 7.860000000000001e-05, "loss": 0.0941, "positive_teacher_pairs": 26729.7, "relation_loss": 0.01346318842843175, "selected_pairs": 26729.7, "step": 1180, "student_distance_mean": 353.96583862304686, "teacher_distance_mean": 0.8564692914485932, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.01346318842843175, "weighted_relation_loss": 0.01346318842843175 }, { "action_query_batch_std": 6.030800008773804, "action_query_norm": 296.2656982421875, "action_relation_loss": 0.013918756693601608, "auxiliary_loss_weight": 1.0, "epoch": 1.1131898971000935, "flow_matching_loss": 0.08370478227734565, "grad_norm": 0.19510966539382935, "invalid_tail_samples": 23.0, "learning_rate": 7.926666666666666e-05, "loss": 0.0976, "positive_teacher_pairs": 27038.9, "relation_loss": 0.013918756693601608, "selected_pairs": 27038.9, "step": 1190, "student_distance_mean": 342.25220642089846, "teacher_distance_mean": 0.8424399316310882, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.013918756693601608, "weighted_relation_loss": 0.013918756693601608 }, { "action_query_batch_std": 6.285884094238281, "action_query_norm": 304.0112274169922, "action_relation_loss": 0.013937541935592889, "auxiliary_loss_weight": 1.0, "epoch": 1.1225444340505144, "flow_matching_loss": 0.08267752379179001, "grad_norm": 0.2197481244802475, "invalid_tail_samples": 26.6, "learning_rate": 7.993333333333334e-05, "loss": 0.0966, "positive_teacher_pairs": 26204.3, "relation_loss": 0.013937541935592889, "selected_pairs": 26204.3, "step": 1200, "student_distance_mean": 355.5427001953125, "teacher_distance_mean": 0.8597922265529633, "valid_action_samples": 229.4, "weighted_auxiliary_loss": 0.013937541935592889, "weighted_relation_loss": 0.013937541935592889 }, { "action_query_batch_std": 6.20995602607727, "action_query_norm": 300.3952301025391, "action_relation_loss": 0.013236583303660154, "auxiliary_loss_weight": 1.0, "epoch": 1.1318989710009355, "flow_matching_loss": 0.08336948975920677, "grad_norm": 0.3284875452518463, "invalid_tail_samples": 23.8, "learning_rate": 8.060000000000001e-05, "loss": 0.0966, "positive_teacher_pairs": 26853.9, "relation_loss": 0.013236583303660154, "selected_pairs": 26853.9, "step": 1210, "student_distance_mean": 348.67212829589846, "teacher_distance_mean": 0.8531014382839203, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.013236583303660154, "weighted_relation_loss": 0.013236583303660154 }, { "action_query_batch_std": 6.189349031448364, "action_query_norm": 302.36334228515625, "action_relation_loss": 0.013704653177410365, "auxiliary_loss_weight": 1.0, "epoch": 1.1412535079513564, "flow_matching_loss": 0.07981488555669784, "grad_norm": 0.22152253985404968, "invalid_tail_samples": 23.3, "learning_rate": 8.126666666666667e-05, "loss": 0.0935, "positive_teacher_pairs": 26970.1, "relation_loss": 0.013704653177410365, "selected_pairs": 26970.1, "step": 1220, "student_distance_mean": 351.80096740722655, "teacher_distance_mean": 0.8479903221130372, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.013704653177410365, "weighted_relation_loss": 0.013704653177410365 }, { "action_query_batch_std": 6.183053779602051, "action_query_norm": 300.31493225097654, "action_relation_loss": 0.013948896061629057, "auxiliary_loss_weight": 1.0, "epoch": 1.1506080449017775, "flow_matching_loss": 0.08050061389803886, "grad_norm": 0.24245987832546234, "invalid_tail_samples": 23.6, "learning_rate": 8.193333333333334e-05, "loss": 0.0944, "positive_teacher_pairs": 26903.1, "relation_loss": 0.013948896061629057, "selected_pairs": 26903.1, "step": 1230, "student_distance_mean": 349.4472137451172, "teacher_distance_mean": 0.8530473589897156, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.013948896061629057, "weighted_relation_loss": 0.013948896061629057 }, { "action_query_batch_std": 6.178987121582031, "action_query_norm": 296.2090698242188, "action_relation_loss": 0.013432209193706513, "auxiliary_loss_weight": 1.0, "epoch": 1.1599625818521984, "flow_matching_loss": 0.08093553110957145, "grad_norm": 0.31503456830978394, "invalid_tail_samples": 24.8, "learning_rate": 8.26e-05, "loss": 0.0944, "positive_teacher_pairs": 26621.1, "relation_loss": 0.013432209193706513, "selected_pairs": 26621.1, "step": 1240, "student_distance_mean": 348.1737518310547, "teacher_distance_mean": 0.8497156083583832, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.013432209193706513, "weighted_relation_loss": 0.013432209193706513 }, { "action_query_batch_std": 6.461209774017334, "action_query_norm": 309.7376251220703, "action_relation_loss": 0.01360103404149413, "auxiliary_loss_weight": 1.0, "epoch": 1.1693171188026192, "flow_matching_loss": 0.08330488353967666, "grad_norm": 0.2882491946220398, "invalid_tail_samples": 23.1, "learning_rate": 8.326666666666667e-05, "loss": 0.0969, "positive_teacher_pairs": 27023.8, "relation_loss": 0.01360103404149413, "selected_pairs": 27023.8, "step": 1250, "student_distance_mean": 365.08205261230466, "teacher_distance_mean": 0.8551608204841614, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.01360103404149413, "weighted_relation_loss": 0.01360103404149413 }, { "action_query_batch_std": 6.35383710861206, "action_query_norm": 304.34613342285155, "action_relation_loss": 0.013301718421280384, "auxiliary_loss_weight": 1.0, "epoch": 1.1786716557530403, "flow_matching_loss": 0.08325480595231056, "grad_norm": 0.23038692772388458, "invalid_tail_samples": 23.0, "learning_rate": 8.393333333333335e-05, "loss": 0.0966, "positive_teacher_pairs": 27037.5, "relation_loss": 0.013301718421280384, "selected_pairs": 27037.5, "step": 1260, "student_distance_mean": 359.39988708496094, "teacher_distance_mean": 0.8523586928844452, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.013301718421280384, "weighted_relation_loss": 0.013301718421280384 }, { "action_query_batch_std": 6.288804149627685, "action_query_norm": 307.12884216308595, "action_relation_loss": 0.013835736643522977, "auxiliary_loss_weight": 1.0, "epoch": 1.1880261927034612, "flow_matching_loss": 0.08019229471683502, "grad_norm": 0.313839316368103, "invalid_tail_samples": 22.9, "learning_rate": 8.46e-05, "loss": 0.094, "positive_teacher_pairs": 27059.5, "relation_loss": 0.013835736643522977, "selected_pairs": 27059.5, "step": 1270, "student_distance_mean": 356.9143798828125, "teacher_distance_mean": 0.8493092238903046, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.013835736643522977, "weighted_relation_loss": 0.013835736643522977 }, { "action_query_batch_std": 6.443783712387085, "action_query_norm": 312.365625, "action_relation_loss": 0.01354436231777072, "auxiliary_loss_weight": 1.0, "epoch": 1.197380729653882, "flow_matching_loss": 0.08287939354777336, "grad_norm": 0.360660195350647, "invalid_tail_samples": 24.6, "learning_rate": 8.526666666666667e-05, "loss": 0.0964, "positive_teacher_pairs": 26659.5, "relation_loss": 0.01354436231777072, "selected_pairs": 26659.5, "step": 1280, "student_distance_mean": 365.68133239746095, "teacher_distance_mean": 0.8462124824523926, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.01354436231777072, "weighted_relation_loss": 0.01354436231777072 }, { "action_query_batch_std": 6.387950086593628, "action_query_norm": 310.8820831298828, "action_relation_loss": 0.01320072254166007, "auxiliary_loss_weight": 1.0, "epoch": 1.2067352666043032, "flow_matching_loss": 0.08270650431513786, "grad_norm": 0.2580508887767792, "invalid_tail_samples": 22.7, "learning_rate": 8.593333333333333e-05, "loss": 0.0959, "positive_teacher_pairs": 27108.8, "relation_loss": 0.01320072254166007, "selected_pairs": 27108.8, "step": 1290, "student_distance_mean": 360.2643737792969, "teacher_distance_mean": 0.8469069600105286, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.01320072254166007, "weighted_relation_loss": 0.01320072254166007 }, { "action_query_batch_std": 6.382476949691773, "action_query_norm": 309.968017578125, "action_relation_loss": 0.013362438045442104, "auxiliary_loss_weight": 1.0, "epoch": 1.216089803554724, "flow_matching_loss": 0.07928930297493934, "grad_norm": 0.19579444825649261, "invalid_tail_samples": 24.5, "learning_rate": 8.66e-05, "loss": 0.0927, "positive_teacher_pairs": 26697.4, "relation_loss": 0.013362438045442104, "selected_pairs": 26697.4, "step": 1300, "student_distance_mean": 359.8651916503906, "teacher_distance_mean": 0.8607197284698487, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.013362438045442104, "weighted_relation_loss": 0.013362438045442104 }, { "action_query_batch_std": 6.445230293273926, "action_query_norm": 313.7333618164063, "action_relation_loss": 0.013402472250163555, "auxiliary_loss_weight": 1.0, "epoch": 1.225444340505145, "flow_matching_loss": 0.08152525424957276, "grad_norm": 0.18417982757091522, "invalid_tail_samples": 25.5, "learning_rate": 8.726666666666667e-05, "loss": 0.0949, "positive_teacher_pairs": 26462.9, "relation_loss": 0.013402472250163555, "selected_pairs": 26462.9, "step": 1310, "student_distance_mean": 365.3187255859375, "teacher_distance_mean": 0.8566758096218109, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.013402472250163555, "weighted_relation_loss": 0.013402472250163555 }, { "action_query_batch_std": 6.440150785446167, "action_query_norm": 313.64818115234374, "action_relation_loss": 0.013801176566630602, "auxiliary_loss_weight": 1.0, "epoch": 1.234798877455566, "flow_matching_loss": 0.08017865046858788, "grad_norm": 0.25415846705436707, "invalid_tail_samples": 22.6, "learning_rate": 8.793333333333333e-05, "loss": 0.094, "positive_teacher_pairs": 27136.2, "relation_loss": 0.013801176566630602, "selected_pairs": 27136.2, "step": 1320, "student_distance_mean": 365.3482177734375, "teacher_distance_mean": 0.8545205950736999, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.013801176566630602, "weighted_relation_loss": 0.013801176566630602 }, { "action_query_batch_std": 6.57186369895935, "action_query_norm": 317.760546875, "action_relation_loss": 0.013346442393958569, "auxiliary_loss_weight": 1.0, "epoch": 1.244153414405987, "flow_matching_loss": 0.07930527105927468, "grad_norm": 0.27503502368927, "invalid_tail_samples": 23.3, "learning_rate": 8.86e-05, "loss": 0.0927, "positive_teacher_pairs": 26976.3, "relation_loss": 0.013346442393958569, "selected_pairs": 26976.3, "step": 1330, "student_distance_mean": 371.4205291748047, "teacher_distance_mean": 0.8633258521556855, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.013346442393958569, "weighted_relation_loss": 0.013346442393958569 }, { "action_query_batch_std": 6.642180156707764, "action_query_norm": 323.37489318847656, "action_relation_loss": 0.013373400457203389, "auxiliary_loss_weight": 1.0, "epoch": 1.2535079513564078, "flow_matching_loss": 0.07946289107203483, "grad_norm": 0.2320992797613144, "invalid_tail_samples": 20.6, "learning_rate": 8.926666666666668e-05, "loss": 0.0928, "positive_teacher_pairs": 27592.7, "relation_loss": 0.013373400457203389, "selected_pairs": 27592.7, "step": 1340, "student_distance_mean": 376.5219268798828, "teacher_distance_mean": 0.8554794073104859, "valid_action_samples": 235.4, "weighted_auxiliary_loss": 0.013373400457203389, "weighted_relation_loss": 0.013373400457203389 }, { "action_query_batch_std": 6.699054431915283, "action_query_norm": 320.3262878417969, "action_relation_loss": 0.013418106827884912, "auxiliary_loss_weight": 1.0, "epoch": 1.262862488306829, "flow_matching_loss": 0.07831105664372444, "grad_norm": 0.35835689306259155, "invalid_tail_samples": 23.3, "learning_rate": 8.993333333333334e-05, "loss": 0.0917, "positive_teacher_pairs": 26967.6, "relation_loss": 0.013418106827884912, "selected_pairs": 26967.6, "step": 1350, "student_distance_mean": 379.7442138671875, "teacher_distance_mean": 0.8636923372745514, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.013418106827884912, "weighted_relation_loss": 0.013418106827884912 }, { "action_query_batch_std": 6.64734992980957, "action_query_norm": 318.8267486572266, "action_relation_loss": 0.013378388620913029, "auxiliary_loss_weight": 1.0, "epoch": 1.2722170252572498, "flow_matching_loss": 0.07798447161912918, "grad_norm": 0.33331748843193054, "invalid_tail_samples": 25.0, "learning_rate": 9.06e-05, "loss": 0.0914, "positive_teacher_pairs": 26574.5, "relation_loss": 0.013378388620913029, "selected_pairs": 26574.5, "step": 1360, "student_distance_mean": 374.9155731201172, "teacher_distance_mean": 0.8618788838386535, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.013378388620913029, "weighted_relation_loss": 0.013378388620913029 }, { "action_query_batch_std": 6.765779447555542, "action_query_norm": 323.14043579101565, "action_relation_loss": 0.013192779663950206, "auxiliary_loss_weight": 1.0, "epoch": 1.2815715622076707, "flow_matching_loss": 0.07732647731900215, "grad_norm": 0.2998847961425781, "invalid_tail_samples": 25.3, "learning_rate": 9.126666666666667e-05, "loss": 0.0905, "positive_teacher_pairs": 26501.1, "relation_loss": 0.013192779663950206, "selected_pairs": 26501.1, "step": 1370, "student_distance_mean": 383.48859252929685, "teacher_distance_mean": 0.8600843906402588, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.013192779663950206, "weighted_relation_loss": 0.013192779663950206 }, { "action_query_batch_std": 6.782998895645141, "action_query_norm": 327.9581024169922, "action_relation_loss": 0.012768947798758746, "auxiliary_loss_weight": 1.0, "epoch": 1.2909260991580918, "flow_matching_loss": 0.08242245092988014, "grad_norm": 0.289760559797287, "invalid_tail_samples": 22.0, "learning_rate": 9.193333333333334e-05, "loss": 0.0952, "positive_teacher_pairs": 27263.0, "relation_loss": 0.012768947798758746, "selected_pairs": 27263.0, "step": 1380, "student_distance_mean": 384.8080108642578, "teacher_distance_mean": 0.8605721712112426, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.012768947798758746, "weighted_relation_loss": 0.012768947798758746 }, { "action_query_batch_std": 6.769545793533325, "action_query_norm": 327.8418823242188, "action_relation_loss": 0.014101169165223837, "auxiliary_loss_weight": 1.0, "epoch": 1.3002806361085126, "flow_matching_loss": 0.08292394950985908, "grad_norm": 0.23109829425811768, "invalid_tail_samples": 24.5, "learning_rate": 9.260000000000001e-05, "loss": 0.097, "positive_teacher_pairs": 26693.4, "relation_loss": 0.014101169165223837, "selected_pairs": 26693.4, "step": 1390, "student_distance_mean": 382.09104919433594, "teacher_distance_mean": 0.8571523606777192, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.014101169165223837, "weighted_relation_loss": 0.014101169165223837 }, { "action_query_batch_std": 6.816023921966552, "action_query_norm": 327.6637268066406, "action_relation_loss": 0.013195423781871796, "auxiliary_loss_weight": 1.0, "epoch": 1.3096351730589335, "flow_matching_loss": 0.08415406718850135, "grad_norm": 0.2566090226173401, "invalid_tail_samples": 23.5, "learning_rate": 9.326666666666667e-05, "loss": 0.0973, "positive_teacher_pairs": 26919.3, "relation_loss": 0.013195423781871796, "selected_pairs": 26919.3, "step": 1400, "student_distance_mean": 387.94615478515624, "teacher_distance_mean": 0.8583309769630432, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.013195423781871796, "weighted_relation_loss": 0.013195423781871796 }, { "action_query_batch_std": 6.8868043422698975, "action_query_norm": 332.7694976806641, "action_relation_loss": 0.01383750643581152, "auxiliary_loss_weight": 1.0, "epoch": 1.3189897100093546, "flow_matching_loss": 0.07882940024137497, "grad_norm": 0.25609394907951355, "invalid_tail_samples": 21.7, "learning_rate": 9.393333333333334e-05, "loss": 0.0927, "positive_teacher_pairs": 27339.2, "relation_loss": 0.01383750643581152, "selected_pairs": 27339.2, "step": 1410, "student_distance_mean": 390.4309417724609, "teacher_distance_mean": 0.855209469795227, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.01383750643581152, "weighted_relation_loss": 0.01383750643581152 }, { "action_query_batch_std": 6.892193460464478, "action_query_norm": 329.2400695800781, "action_relation_loss": 0.013168638758361339, "auxiliary_loss_weight": 1.0, "epoch": 1.3283442469597755, "flow_matching_loss": 0.07971258014440537, "grad_norm": 0.2640548050403595, "invalid_tail_samples": 24.6, "learning_rate": 9.46e-05, "loss": 0.0929, "positive_teacher_pairs": 26665.1, "relation_loss": 0.013168638758361339, "selected_pairs": 26665.1, "step": 1420, "student_distance_mean": 391.0892333984375, "teacher_distance_mean": 0.8631888568401337, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.013168638758361339, "weighted_relation_loss": 0.013168638758361339 }, { "action_query_batch_std": 6.729205894470215, "action_query_norm": 322.1756286621094, "action_relation_loss": 0.012587160337716341, "auxiliary_loss_weight": 1.0, "epoch": 1.3376987839101964, "flow_matching_loss": 0.07801647931337356, "grad_norm": 0.32483986020088196, "invalid_tail_samples": 24.7, "learning_rate": 9.526666666666667e-05, "loss": 0.0906, "positive_teacher_pairs": 26660.6, "relation_loss": 0.012587160337716341, "selected_pairs": 26660.6, "step": 1430, "student_distance_mean": 380.1592590332031, "teacher_distance_mean": 0.8511648654937745, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.012587160337716341, "weighted_relation_loss": 0.012587160337716341 }, { "action_query_batch_std": 6.977569198608398, "action_query_norm": 332.7903198242187, "action_relation_loss": 0.012583205569535494, "auxiliary_loss_weight": 1.0, "epoch": 1.3470533208606175, "flow_matching_loss": 0.08134318515658379, "grad_norm": 0.27239683270454407, "invalid_tail_samples": 23.4, "learning_rate": 9.593333333333334e-05, "loss": 0.0939, "positive_teacher_pairs": 26951.2, "relation_loss": 0.012583205569535494, "selected_pairs": 26951.2, "step": 1440, "student_distance_mean": 393.8764678955078, "teacher_distance_mean": 0.864771842956543, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.012583205569535494, "weighted_relation_loss": 0.012583205569535494 }, { "action_query_batch_std": 6.905375576019287, "action_query_norm": 330.08226623535154, "action_relation_loss": 0.012462748866528272, "auxiliary_loss_weight": 1.0, "epoch": 1.3564078578110383, "flow_matching_loss": 0.08175986632704735, "grad_norm": 0.3214185833930969, "invalid_tail_samples": 24.4, "learning_rate": 9.66e-05, "loss": 0.0942, "positive_teacher_pairs": 26723.7, "relation_loss": 0.012462748866528272, "selected_pairs": 26723.7, "step": 1450, "student_distance_mean": 391.17503967285154, "teacher_distance_mean": 0.8553390979766846, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.012462748866528272, "weighted_relation_loss": 0.012462748866528272 }, { "action_query_batch_std": 7.127221965789795, "action_query_norm": 337.6199096679687, "action_relation_loss": 0.013119314052164554, "auxiliary_loss_weight": 1.0, "epoch": 1.3657623947614592, "flow_matching_loss": 0.08047905787825585, "grad_norm": 0.23614630103111267, "invalid_tail_samples": 22.5, "learning_rate": 9.726666666666667e-05, "loss": 0.0936, "positive_teacher_pairs": 27150.1, "relation_loss": 0.013119314052164554, "selected_pairs": 27150.1, "step": 1460, "student_distance_mean": 403.5553375244141, "teacher_distance_mean": 0.8633797943592072, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.013119314052164554, "weighted_relation_loss": 0.013119314052164554 }, { "action_query_batch_std": 7.025757360458374, "action_query_norm": 333.2663238525391, "action_relation_loss": 0.012308477517217397, "auxiliary_loss_weight": 1.0, "epoch": 1.3751169317118803, "flow_matching_loss": 0.07664759457111359, "grad_norm": 0.29586541652679443, "invalid_tail_samples": 22.7, "learning_rate": 9.793333333333333e-05, "loss": 0.089, "positive_teacher_pairs": 27109.4, "relation_loss": 0.012308477517217397, "selected_pairs": 27109.4, "step": 1470, "student_distance_mean": 397.56145629882815, "teacher_distance_mean": 0.8604467213153839, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.012308477517217397, "weighted_relation_loss": 0.012308477517217397 }, { "action_query_batch_std": 6.904181623458863, "action_query_norm": 331.89342346191404, "action_relation_loss": 0.012833608686923981, "auxiliary_loss_weight": 1.0, "epoch": 1.3844714686623012, "flow_matching_loss": 0.07918691113591195, "grad_norm": 0.2904595732688904, "invalid_tail_samples": 23.3, "learning_rate": 9.86e-05, "loss": 0.092, "positive_teacher_pairs": 26978.5, "relation_loss": 0.012833608686923981, "selected_pairs": 26978.5, "step": 1480, "student_distance_mean": 389.7898193359375, "teacher_distance_mean": 0.855737155675888, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.012833608686923981, "weighted_relation_loss": 0.012833608686923981 }, { "action_query_batch_std": 7.038417482376099, "action_query_norm": 336.0210876464844, "action_relation_loss": 0.012761924974620342, "auxiliary_loss_weight": 1.0, "epoch": 1.393826005612722, "flow_matching_loss": 0.08124351873993874, "grad_norm": 0.25942856073379517, "invalid_tail_samples": 24.4, "learning_rate": 9.926666666666668e-05, "loss": 0.094, "positive_teacher_pairs": 26717.2, "relation_loss": 0.012761924974620342, "selected_pairs": 26717.2, "step": 1490, "student_distance_mean": 397.29755249023435, "teacher_distance_mean": 0.8531434416770936, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.012761924974620342, "weighted_relation_loss": 0.012761924974620342 }, { "action_query_batch_std": 6.922738933563233, "action_query_norm": 336.15478515625, "action_relation_loss": 0.012710392475128174, "auxiliary_loss_weight": 1.0, "epoch": 1.4031805425631432, "flow_matching_loss": 0.07861340045928955, "grad_norm": 0.21162176132202148, "invalid_tail_samples": 25.4, "learning_rate": 9.993333333333334e-05, "loss": 0.0913, "positive_teacher_pairs": 26481.1, "relation_loss": 0.012710392475128174, "selected_pairs": 26481.1, "step": 1500, "student_distance_mean": 391.8767333984375, "teacher_distance_mean": 0.8443897724151611, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.012710392475128174, "weighted_relation_loss": 0.012710392475128174 }, { "action_query_batch_std": 6.977701330184937, "action_query_norm": 332.82537536621095, "action_relation_loss": 0.013110181875526905, "auxiliary_loss_weight": 1.0, "epoch": 1.412535079513564, "flow_matching_loss": 0.08136256039142609, "grad_norm": 0.2656700313091278, "invalid_tail_samples": 23.3, "learning_rate": 9.999997539434007e-05, "loss": 0.0945, "positive_teacher_pairs": 26966.8, "relation_loss": 0.013110181875526905, "selected_pairs": 26966.8, "step": 1510, "student_distance_mean": 395.48643493652344, "teacher_distance_mean": 0.8625234723091125, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.013110181875526905, "weighted_relation_loss": 0.013110181875526905 }, { "action_query_batch_std": 7.02873215675354, "action_query_norm": 334.54876708984375, "action_relation_loss": 0.012594263348728419, "auxiliary_loss_weight": 1.0, "epoch": 1.421889616463985, "flow_matching_loss": 0.08186622485518455, "grad_norm": 0.2829800844192505, "invalid_tail_samples": 20.8, "learning_rate": 9.999989033776898e-05, "loss": 0.0945, "positive_teacher_pairs": 27545.6, "relation_loss": 0.012594263348728419, "selected_pairs": 27545.6, "step": 1520, "student_distance_mean": 397.01296081542966, "teacher_distance_mean": 0.8581378996372223, "valid_action_samples": 235.2, "weighted_auxiliary_loss": 0.012594263348728419, "weighted_relation_loss": 0.012594263348728419 }, { "action_query_batch_std": 7.027502870559692, "action_query_norm": 337.6683685302734, "action_relation_loss": 0.012809950765222311, "auxiliary_loss_weight": 1.0, "epoch": 1.431244153414406, "flow_matching_loss": 0.07927987426519394, "grad_norm": 0.2786993086338043, "invalid_tail_samples": 24.4, "learning_rate": 9.999974452661641e-05, "loss": 0.0921, "positive_teacher_pairs": 26709.9, "relation_loss": 0.012809950765222311, "selected_pairs": 26709.9, "step": 1530, "student_distance_mean": 398.5616790771484, "teacher_distance_mean": 0.8593062996864319, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.012809950765222311, "weighted_relation_loss": 0.012809950765222311 }, { "action_query_batch_std": 7.013177347183228, "action_query_norm": 339.9084899902344, "action_relation_loss": 0.012973073869943619, "auxiliary_loss_weight": 1.0, "epoch": 1.440598690364827, "flow_matching_loss": 0.07816641256213189, "grad_norm": 0.34220823645591736, "invalid_tail_samples": 23.4, "learning_rate": 9.999953796105959e-05, "loss": 0.0911, "positive_teacher_pairs": 26944.6, "relation_loss": 0.012973073869943619, "selected_pairs": 26944.6, "step": 1540, "student_distance_mean": 397.4413208007812, "teacher_distance_mean": 0.855421632528305, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.012973073869943619, "weighted_relation_loss": 0.012973073869943619 }, { "action_query_batch_std": 7.0026250839233395, "action_query_norm": 339.4356689453125, "action_relation_loss": 0.013418788835406304, "auxiliary_loss_weight": 1.0, "epoch": 1.4499532273152478, "flow_matching_loss": 0.07777162864804268, "grad_norm": 0.24975328147411346, "invalid_tail_samples": 26.1, "learning_rate": 9.999927064134949e-05, "loss": 0.0912, "positive_teacher_pairs": 26316.8, "relation_loss": 0.013418788835406304, "selected_pairs": 26316.8, "step": 1550, "student_distance_mean": 396.4431671142578, "teacher_distance_mean": 0.8391379117965698, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.013418788835406304, "weighted_relation_loss": 0.013418788835406304 }, { "action_query_batch_std": 7.314692592620849, "action_query_norm": 346.40785522460936, "action_relation_loss": 0.01213080771267414, "auxiliary_loss_weight": 1.0, "epoch": 1.4593077642656689, "flow_matching_loss": 0.08074584156274796, "grad_norm": 0.33374515175819397, "invalid_tail_samples": 23.9, "learning_rate": 9.999894256781095e-05, "loss": 0.0929, "positive_teacher_pairs": 26826.8, "relation_loss": 0.01213080771267414, "selected_pairs": 26826.8, "step": 1560, "student_distance_mean": 414.7841766357422, "teacher_distance_mean": 0.8633062601089477, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.01213080771267414, "weighted_relation_loss": 0.01213080771267414 }, { "action_query_batch_std": 7.277427816390992, "action_query_norm": 345.1303283691406, "action_relation_loss": 0.012964850571006537, "auxiliary_loss_weight": 1.0, "epoch": 1.4686623012160898, "flow_matching_loss": 0.07793425619602204, "grad_norm": 0.28223544359207153, "invalid_tail_samples": 22.8, "learning_rate": 9.99985537408426e-05, "loss": 0.0909, "positive_teacher_pairs": 27079.3, "relation_loss": 0.012964850571006537, "selected_pairs": 27079.3, "step": 1570, "student_distance_mean": 411.8810638427734, "teacher_distance_mean": 0.8577201306819916, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.012964850571006537, "weighted_relation_loss": 0.012964850571006537 }, { "action_query_batch_std": 7.2289040088653564, "action_query_norm": 342.99131469726564, "action_relation_loss": 0.012812991067767144, "auxiliary_loss_weight": 1.0, "epoch": 1.4780168381665106, "flow_matching_loss": 0.07698018997907638, "grad_norm": 0.26159700751304626, "invalid_tail_samples": 23.1, "learning_rate": 9.999810416091688e-05, "loss": 0.0898, "positive_teacher_pairs": 27011.6, "relation_loss": 0.012812991067767144, "selected_pairs": 27011.6, "step": 1580, "student_distance_mean": 410.53891906738284, "teacher_distance_mean": 0.8518498837947845, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.012812991067767144, "weighted_relation_loss": 0.012812991067767144 }, { "action_query_batch_std": 7.2722740650177, "action_query_norm": 345.6647918701172, "action_relation_loss": 0.012412115186452865, "auxiliary_loss_weight": 1.0, "epoch": 1.4873713751169317, "flow_matching_loss": 0.07771048173308373, "grad_norm": 0.20327797532081604, "invalid_tail_samples": 25.8, "learning_rate": 9.99975938285801e-05, "loss": 0.0901, "positive_teacher_pairs": 26389.4, "relation_loss": 0.012412115186452865, "selected_pairs": 26389.4, "step": 1590, "student_distance_mean": 411.9035614013672, "teacher_distance_mean": 0.8571131944656372, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.012412115186452865, "weighted_relation_loss": 0.012412115186452865 }, { "action_query_batch_std": 7.257024812698364, "action_query_norm": 348.1201507568359, "action_relation_loss": 0.012575733009725809, "auxiliary_loss_weight": 1.0, "epoch": 1.4967259120673526, "flow_matching_loss": 0.07858709916472435, "grad_norm": 0.19350598752498627, "invalid_tail_samples": 20.6, "learning_rate": 9.999702274445236e-05, "loss": 0.0912, "positive_teacher_pairs": 27599.6, "relation_loss": 0.012575733009725809, "selected_pairs": 27599.6, "step": 1600, "student_distance_mean": 411.9077850341797, "teacher_distance_mean": 0.8488584697246552, "valid_action_samples": 235.4, "weighted_auxiliary_loss": 0.012575733009725809, "weighted_relation_loss": 0.012575733009725809 }, { "action_query_batch_std": 7.377093076705933, "action_query_norm": 353.6749237060547, "action_relation_loss": 0.011854699067771434, "auxiliary_loss_weight": 1.0, "epoch": 1.5060804490177735, "flow_matching_loss": 0.07733044475317001, "grad_norm": 0.24336904287338257, "invalid_tail_samples": 23.6, "learning_rate": 9.999639090922756e-05, "loss": 0.0892, "positive_teacher_pairs": 26897.9, "relation_loss": 0.011854699067771434, "selected_pairs": 26897.9, "step": 1610, "student_distance_mean": 417.2395263671875, "teacher_distance_mean": 0.86095090508461, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.011854699067771434, "weighted_relation_loss": 0.011854699067771434 }, { "action_query_batch_std": 7.475480651855468, "action_query_norm": 353.71710815429685, "action_relation_loss": 0.012065508775413037, "auxiliary_loss_weight": 1.0, "epoch": 1.5154349859681946, "flow_matching_loss": 0.0743195317685604, "grad_norm": 0.3524872064590454, "invalid_tail_samples": 22.1, "learning_rate": 9.999569832367346e-05, "loss": 0.0864, "positive_teacher_pairs": 27243.8, "relation_loss": 0.012065508775413037, "selected_pairs": 27243.8, "step": 1620, "student_distance_mean": 422.50868530273436, "teacher_distance_mean": 0.8649421334266663, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.012065508775413037, "weighted_relation_loss": 0.012065508775413037 }, { "action_query_batch_std": 7.286542558670044, "action_query_norm": 347.3158447265625, "action_relation_loss": 0.012517304718494415, "auxiliary_loss_weight": 1.0, "epoch": 1.5247895229186157, "flow_matching_loss": 0.07999030873179436, "grad_norm": 0.239640474319458, "invalid_tail_samples": 24.3, "learning_rate": 9.999494498863162e-05, "loss": 0.0925, "positive_teacher_pairs": 26732.0, "relation_loss": 0.012517304718494415, "selected_pairs": 26732.0, "step": 1630, "student_distance_mean": 414.00730590820314, "teacher_distance_mean": 0.8628821492195129, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.012517304718494415, "weighted_relation_loss": 0.012517304718494415 }, { "action_query_batch_std": 7.2369208335876465, "action_query_norm": 350.1357086181641, "action_relation_loss": 0.012540008686482907, "auxiliary_loss_weight": 1.0, "epoch": 1.5341440598690363, "flow_matching_loss": 0.0767799288034439, "grad_norm": 0.3165149390697479, "invalid_tail_samples": 22.8, "learning_rate": 9.99941309050174e-05, "loss": 0.0893, "positive_teacher_pairs": 27085.0, "relation_loss": 0.012540008686482907, "selected_pairs": 27085.0, "step": 1640, "student_distance_mean": 408.4457946777344, "teacher_distance_mean": 0.8494516849517822, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.012540008686482907, "weighted_relation_loss": 0.012540008686482907 }, { "action_query_batch_std": 7.280635213851928, "action_query_norm": 349.07105712890626, "action_relation_loss": 0.012403351347893476, "auxiliary_loss_weight": 1.0, "epoch": 1.5434985968194574, "flow_matching_loss": 0.07868930026888847, "grad_norm": 0.2985949218273163, "invalid_tail_samples": 26.1, "learning_rate": 9.999325607381999e-05, "loss": 0.0911, "positive_teacher_pairs": 26320.7, "relation_loss": 0.012403351347893476, "selected_pairs": 26320.7, "step": 1650, "student_distance_mean": 412.1132476806641, "teacher_distance_mean": 0.8485081672668457, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.012403351347893476, "weighted_relation_loss": 0.012403351347893476 }, { "action_query_batch_std": 7.431552696228027, "action_query_norm": 358.1630859375, "action_relation_loss": 0.012192885018885135, "auxiliary_loss_weight": 1.0, "epoch": 1.5528531337698785, "flow_matching_loss": 0.07964756116271018, "grad_norm": 0.22478695213794708, "invalid_tail_samples": 24.2, "learning_rate": 9.999232049610238e-05, "loss": 0.0918, "positive_teacher_pairs": 26759.7, "relation_loss": 0.012192885018885135, "selected_pairs": 26759.7, "step": 1660, "student_distance_mean": 421.1770935058594, "teacher_distance_mean": 0.8503999054431916, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.012192885018885135, "weighted_relation_loss": 0.012192885018885135 }, { "action_query_batch_std": 7.509901714324951, "action_query_norm": 358.7103698730469, "action_relation_loss": 0.01259373975917697, "auxiliary_loss_weight": 1.0, "epoch": 1.5622076707202992, "flow_matching_loss": 0.07651128768920898, "grad_norm": 0.2921346426010132, "invalid_tail_samples": 24.0, "learning_rate": 9.999132417300142e-05, "loss": 0.0891, "positive_teacher_pairs": 26814.8, "relation_loss": 0.01259373975917697, "selected_pairs": 26814.8, "step": 1670, "student_distance_mean": 425.1151580810547, "teacher_distance_mean": 0.8581283807754516, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.01259373975917697, "weighted_relation_loss": 0.01259373975917697 }, { "action_query_batch_std": 7.312155055999756, "action_query_norm": 348.3176605224609, "action_relation_loss": 0.012346770521253348, "auxiliary_loss_weight": 1.0, "epoch": 1.5715622076707203, "flow_matching_loss": 0.0781780555844307, "grad_norm": 0.29131048917770386, "invalid_tail_samples": 25.0, "learning_rate": 9.99902671057277e-05, "loss": 0.0905, "positive_teacher_pairs": 26572.3, "relation_loss": 0.012346770521253348, "selected_pairs": 26572.3, "step": 1680, "student_distance_mean": 412.9205810546875, "teacher_distance_mean": 0.8616723239421844, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.012346770521253348, "weighted_relation_loss": 0.012346770521253348 }, { "action_query_batch_std": 7.4229700565338135, "action_query_norm": 353.8576202392578, "action_relation_loss": 0.012207405734807253, "auxiliary_loss_weight": 1.0, "epoch": 1.5809167446211414, "flow_matching_loss": 0.07986122816801071, "grad_norm": 0.3235871195793152, "invalid_tail_samples": 23.2, "learning_rate": 9.998914929556569e-05, "loss": 0.0921, "positive_teacher_pairs": 26998.2, "relation_loss": 0.012207405734807253, "selected_pairs": 26998.2, "step": 1690, "student_distance_mean": 419.68992614746094, "teacher_distance_mean": 0.8559258937835693, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.012207405734807253, "weighted_relation_loss": 0.012207405734807253 }, { "action_query_batch_std": 7.647739696502685, "action_query_norm": 359.749462890625, "action_relation_loss": 0.011602048017084598, "auxiliary_loss_weight": 1.0, "epoch": 1.590271281571562, "flow_matching_loss": 0.07952008545398712, "grad_norm": 0.2662928104400635, "invalid_tail_samples": 24.5, "learning_rate": 9.998797074387361e-05, "loss": 0.0911, "positive_teacher_pairs": 26685.9, "relation_loss": 0.011602048017084598, "selected_pairs": 26685.9, "step": 1700, "student_distance_mean": 432.368505859375, "teacher_distance_mean": 0.8513954699039459, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.011602048017084598, "weighted_relation_loss": 0.011602048017084598 }, { "action_query_batch_std": 7.573075008392334, "action_query_norm": 360.3171356201172, "action_relation_loss": 0.012227758020162582, "auxiliary_loss_weight": 1.0, "epoch": 1.5996258185219832, "flow_matching_loss": 0.07871276065707207, "grad_norm": 0.36315545439720154, "invalid_tail_samples": 24.6, "learning_rate": 9.99867314520835e-05, "loss": 0.0909, "positive_teacher_pairs": 26668.3, "relation_loss": 0.012227758020162582, "selected_pairs": 26668.3, "step": 1710, "student_distance_mean": 431.37049255371096, "teacher_distance_mean": 0.8508182823657989, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.012227758020162582, "weighted_relation_loss": 0.012227758020162582 }, { "action_query_batch_std": 7.718354940414429, "action_query_norm": 364.1599365234375, "action_relation_loss": 0.012635661475360393, "auxiliary_loss_weight": 1.0, "epoch": 1.6089803554724043, "flow_matching_loss": 0.07532422095537186, "grad_norm": 0.29948219656944275, "invalid_tail_samples": 25.5, "learning_rate": 9.998543142170126e-05, "loss": 0.088, "positive_teacher_pairs": 26461.7, "relation_loss": 0.012635661475360393, "selected_pairs": 26461.7, "step": 1720, "student_distance_mean": 439.28795166015624, "teacher_distance_mean": 0.8585139513015747, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.012635661475360393, "weighted_relation_loss": 0.012635661475360393 }, { "action_query_batch_std": 7.439778852462768, "action_query_norm": 355.47637939453125, "action_relation_loss": 0.011835044994950295, "auxiliary_loss_weight": 1.0, "epoch": 1.618334892422825, "flow_matching_loss": 0.07892148569226265, "grad_norm": 0.33142390847206116, "invalid_tail_samples": 22.5, "learning_rate": 9.99840706543065e-05, "loss": 0.0908, "positive_teacher_pairs": 27149.7, "relation_loss": 0.011835044994950295, "selected_pairs": 27149.7, "step": 1730, "student_distance_mean": 421.26849365234375, "teacher_distance_mean": 0.8396815836429596, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.011835044994950295, "weighted_relation_loss": 0.011835044994950295 }, { "action_query_batch_std": 7.546114063262939, "action_query_norm": 360.21929321289065, "action_relation_loss": 0.012640104349702596, "auxiliary_loss_weight": 1.0, "epoch": 1.627689429373246, "flow_matching_loss": 0.07554062828421593, "grad_norm": 0.2841711938381195, "invalid_tail_samples": 23.9, "learning_rate": 9.998264915155274e-05, "loss": 0.0882, "positive_teacher_pairs": 26826.4, "relation_loss": 0.012640104349702596, "selected_pairs": 26826.4, "step": 1740, "student_distance_mean": 428.3336883544922, "teacher_distance_mean": 0.8534941732883453, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.012640104349702596, "weighted_relation_loss": 0.012640104349702596 }, { "action_query_batch_std": 7.638364982604981, "action_query_norm": 366.32434997558596, "action_relation_loss": 0.012126391753554344, "auxiliary_loss_weight": 1.0, "epoch": 1.637043966323667, "flow_matching_loss": 0.07847634330391884, "grad_norm": 0.2751025855541229, "invalid_tail_samples": 24.8, "learning_rate": 9.998116691516718e-05, "loss": 0.0906, "positive_teacher_pairs": 26640.6, "relation_loss": 0.012126391753554344, "selected_pairs": 26640.6, "step": 1750, "student_distance_mean": 433.44814453125, "teacher_distance_mean": 0.8532587826251984, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.012126391753554344, "weighted_relation_loss": 0.012126391753554344 }, { "action_query_batch_std": 7.67241678237915, "action_query_norm": 363.81903686523435, "action_relation_loss": 0.012734770867973566, "auxiliary_loss_weight": 1.0, "epoch": 1.646398503274088, "flow_matching_loss": 0.07898509949445724, "grad_norm": 0.213039830327034, "invalid_tail_samples": 24.7, "learning_rate": 9.997962394695091e-05, "loss": 0.0917, "positive_teacher_pairs": 26644.2, "relation_loss": 0.012734770867973566, "selected_pairs": 26644.2, "step": 1760, "student_distance_mean": 433.1340637207031, "teacher_distance_mean": 0.8516146063804626, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.012734770867973566, "weighted_relation_loss": 0.012734770867973566 }, { "action_query_batch_std": 7.636897230148316, "action_query_norm": 359.1812713623047, "action_relation_loss": 0.01155270142480731, "auxiliary_loss_weight": 1.0, "epoch": 1.6557530402245089, "flow_matching_loss": 0.07302806600928306, "grad_norm": 0.22280582785606384, "invalid_tail_samples": 24.7, "learning_rate": 9.997802024877875e-05, "loss": 0.0846, "positive_teacher_pairs": 26640.7, "relation_loss": 0.01155270142480731, "selected_pairs": 26640.7, "step": 1770, "student_distance_mean": 433.97536315917966, "teacher_distance_mean": 0.8575116336345673, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.01155270142480731, "weighted_relation_loss": 0.01155270142480731 }, { "action_query_batch_std": 7.579990196228027, "action_query_norm": 359.43055114746096, "action_relation_loss": 0.011825150158256293, "auxiliary_loss_weight": 1.0, "epoch": 1.66510757717493, "flow_matching_loss": 0.0743702344596386, "grad_norm": 0.18965333700180054, "invalid_tail_samples": 24.7, "learning_rate": 9.99763558225994e-05, "loss": 0.0862, "positive_teacher_pairs": 26638.9, "relation_loss": 0.011825150158256293, "selected_pairs": 26638.9, "step": 1780, "student_distance_mean": 428.3981048583984, "teacher_distance_mean": 0.8488313555717468, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.011825150158256293, "weighted_relation_loss": 0.011825150158256293 }, { "action_query_batch_std": 7.696464204788208, "action_query_norm": 364.54893188476564, "action_relation_loss": 0.012201388273388148, "auxiliary_loss_weight": 1.0, "epoch": 1.6744621141253508, "flow_matching_loss": 0.07462379857897758, "grad_norm": 0.3191966712474823, "invalid_tail_samples": 21.7, "learning_rate": 9.997463067043526e-05, "loss": 0.0868, "positive_teacher_pairs": 27342.1, "relation_loss": 0.012201388273388148, "selected_pairs": 27342.1, "step": 1790, "student_distance_mean": 436.04205017089845, "teacher_distance_mean": 0.8521231830120086, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.012201388273388148, "weighted_relation_loss": 0.012201388273388148 }, { "action_query_batch_std": 7.805192565917968, "action_query_norm": 370.6709716796875, "action_relation_loss": 0.012291827797889709, "auxiliary_loss_weight": 1.0, "epoch": 1.6838166510757717, "flow_matching_loss": 0.07609496116638184, "grad_norm": 0.26660117506980896, "invalid_tail_samples": 22.6, "learning_rate": 9.997284479438253e-05, "loss": 0.0884, "positive_teacher_pairs": 27130.7, "relation_loss": 0.012291827797889709, "selected_pairs": 27130.7, "step": 1800, "student_distance_mean": 443.7105651855469, "teacher_distance_mean": 0.8461378514766693, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.012291827797889709, "weighted_relation_loss": 0.012291827797889709 }, { "action_query_batch_std": 7.721890687942505, "action_query_norm": 366.2240020751953, "action_relation_loss": 0.012440756056457758, "auxiliary_loss_weight": 1.0, "epoch": 1.6931711880261928, "flow_matching_loss": 0.07623371332883835, "grad_norm": 0.1703750640153885, "invalid_tail_samples": 25.4, "learning_rate": 9.997099819661127e-05, "loss": 0.0887, "positive_teacher_pairs": 26480.5, "relation_loss": 0.012440756056457758, "selected_pairs": 26480.5, "step": 1810, "student_distance_mean": 440.10423583984374, "teacher_distance_mean": 0.8522658288478852, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.012440756056457758, "weighted_relation_loss": 0.012440756056457758 }, { "action_query_batch_std": 7.814288854598999, "action_query_norm": 369.7200073242187, "action_relation_loss": 0.012521210126578808, "auxiliary_loss_weight": 1.0, "epoch": 1.7025257249766137, "flow_matching_loss": 0.07829736471176148, "grad_norm": 0.30594512820243835, "invalid_tail_samples": 21.7, "learning_rate": 9.996909087936524e-05, "loss": 0.0908, "positive_teacher_pairs": 27339.8, "relation_loss": 0.012521210126578808, "selected_pairs": 27339.8, "step": 1820, "student_distance_mean": 440.91437072753905, "teacher_distance_mean": 0.8603769779205322, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.012521210126578808, "weighted_relation_loss": 0.012521210126578808 }, { "action_query_batch_std": 7.9600104808807375, "action_query_norm": 377.25587463378906, "action_relation_loss": 0.012198864575475454, "auxiliary_loss_weight": 1.0, "epoch": 1.7118802619270346, "flow_matching_loss": 0.08016830682754517, "grad_norm": 0.2125891000032425, "invalid_tail_samples": 22.6, "learning_rate": 9.996712284496201e-05, "loss": 0.0924, "positive_teacher_pairs": 27126.5, "relation_loss": 0.012198864575475454, "selected_pairs": 27126.5, "step": 1830, "student_distance_mean": 447.75641479492185, "teacher_distance_mean": 0.8587318360805511, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.012198864575475454, "weighted_relation_loss": 0.012198864575475454 }, { "action_query_batch_std": 7.89814248085022, "action_query_norm": 372.47312622070314, "action_relation_loss": 0.011715207435190677, "auxiliary_loss_weight": 1.0, "epoch": 1.7212347988774557, "flow_matching_loss": 0.07506850585341454, "grad_norm": 0.14453527331352234, "invalid_tail_samples": 24.3, "learning_rate": 9.996509409579293e-05, "loss": 0.0868, "positive_teacher_pairs": 26743.6, "relation_loss": 0.011715207435190677, "selected_pairs": 26743.6, "step": 1840, "student_distance_mean": 447.95234375, "teacher_distance_mean": 0.8635297954082489, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.011715207435190677, "weighted_relation_loss": 0.011715207435190677 }, { "action_query_batch_std": 7.674229526519776, "action_query_norm": 367.1763580322266, "action_relation_loss": 0.011930630728602409, "auxiliary_loss_weight": 1.0, "epoch": 1.7305893358278766, "flow_matching_loss": 0.07738547399640083, "grad_norm": 0.1724245250225067, "invalid_tail_samples": 22.3, "learning_rate": 9.996300463432312e-05, "loss": 0.0893, "positive_teacher_pairs": 27202.9, "relation_loss": 0.011930630728602409, "selected_pairs": 27202.9, "step": 1850, "student_distance_mean": 435.53163452148436, "teacher_distance_mean": 0.8517641246318817, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.011930630728602409, "weighted_relation_loss": 0.011930630728602409 }, { "action_query_batch_std": 7.789900588989258, "action_query_norm": 372.8956756591797, "action_relation_loss": 0.012082946486771107, "auxiliary_loss_weight": 1.0, "epoch": 1.7399438727782974, "flow_matching_loss": 0.07187300510704517, "grad_norm": 0.22369007766246796, "invalid_tail_samples": 25.4, "learning_rate": 9.996085446309148e-05, "loss": 0.084, "positive_teacher_pairs": 26477.1, "relation_loss": 0.012082946486771107, "selected_pairs": 26477.1, "step": 1860, "student_distance_mean": 444.2966369628906, "teacher_distance_mean": 0.849731731414795, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.012082946486771107, "weighted_relation_loss": 0.012082946486771107 }, { "action_query_batch_std": 7.839133977890015, "action_query_norm": 375.79547729492185, "action_relation_loss": 0.012273814994841814, "auxiliary_loss_weight": 1.0, "epoch": 1.7492984097287185, "flow_matching_loss": 0.07589468359947205, "grad_norm": 0.21864719688892365, "invalid_tail_samples": 23.7, "learning_rate": 9.995864358471066e-05, "loss": 0.0882, "positive_teacher_pairs": 26878.5, "relation_loss": 0.012273814994841814, "selected_pairs": 26878.5, "step": 1870, "student_distance_mean": 443.88255920410154, "teacher_distance_mean": 0.847928935289383, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.012273814994841814, "weighted_relation_loss": 0.012273814994841814 }, { "action_query_batch_std": 8.100272464752198, "action_query_norm": 385.2171661376953, "action_relation_loss": 0.012207232788205147, "auxiliary_loss_weight": 1.0, "epoch": 1.7586529466791394, "flow_matching_loss": 0.07540271133184433, "grad_norm": 0.19568489491939545, "invalid_tail_samples": 22.5, "learning_rate": 9.99563720018671e-05, "loss": 0.0876, "positive_teacher_pairs": 27152.7, "relation_loss": 0.012207232788205147, "selected_pairs": 27152.7, "step": 1880, "student_distance_mean": 458.586083984375, "teacher_distance_mean": 0.8646112322807312, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.012207232788205147, "weighted_relation_loss": 0.012207232788205147 }, { "action_query_batch_std": 7.914755630493164, "action_query_norm": 376.4857574462891, "action_relation_loss": 0.012069001700729132, "auxiliary_loss_weight": 1.0, "epoch": 1.7680074836295603, "flow_matching_loss": 0.07706857472658157, "grad_norm": 0.22067715227603912, "invalid_tail_samples": 22.5, "learning_rate": 9.995403971732098e-05, "loss": 0.0891, "positive_teacher_pairs": 27152.4, "relation_loss": 0.012069001700729132, "selected_pairs": 27152.4, "step": 1890, "student_distance_mean": 448.3770782470703, "teacher_distance_mean": 0.8561167418956757, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.012069001700729132, "weighted_relation_loss": 0.012069001700729132 }, { "action_query_batch_std": 7.7560042381286625, "action_query_norm": 369.6096557617187, "action_relation_loss": 0.012213116232305764, "auxiliary_loss_weight": 1.0, "epoch": 1.7773620205799814, "flow_matching_loss": 0.07307453528046608, "grad_norm": 0.23668409883975983, "invalid_tail_samples": 23.0, "learning_rate": 9.995164673390625e-05, "loss": 0.0853, "positive_teacher_pairs": 27033.6, "relation_loss": 0.012213116232305764, "selected_pairs": 27033.6, "step": 1900, "student_distance_mean": 439.3253570556641, "teacher_distance_mean": 0.8510109961032868, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.012213116232305764, "weighted_relation_loss": 0.012213116232305764 }, { "action_query_batch_std": 7.881779432296753, "action_query_norm": 376.6009155273438, "action_relation_loss": 0.011573133710771798, "auxiliary_loss_weight": 1.0, "epoch": 1.7867165575304023, "flow_matching_loss": 0.07404428049921989, "grad_norm": 0.2581652104854584, "invalid_tail_samples": 25.4, "learning_rate": 9.994919305453059e-05, "loss": 0.0856, "positive_teacher_pairs": 26486.7, "relation_loss": 0.011573133710771798, "selected_pairs": 26486.7, "step": 1910, "student_distance_mean": 447.71819458007815, "teacher_distance_mean": 0.8620594322681427, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.011573133710771798, "weighted_relation_loss": 0.011573133710771798 }, { "action_query_batch_std": 7.95442008972168, "action_query_norm": 378.2342987060547, "action_relation_loss": 0.011371809430420399, "auxiliary_loss_weight": 1.0, "epoch": 1.7960710944808231, "flow_matching_loss": 0.07519228905439376, "grad_norm": 0.17010532319545746, "invalid_tail_samples": 19.5, "learning_rate": 9.994667868217548e-05, "loss": 0.0866, "positive_teacher_pairs": 27858.6, "relation_loss": 0.011371809430420399, "selected_pairs": 27858.6, "step": 1920, "student_distance_mean": 450.08921813964844, "teacher_distance_mean": 0.8557267785072327, "valid_action_samples": 236.5, "weighted_auxiliary_loss": 0.011371809430420399, "weighted_relation_loss": 0.011371809430420399 }, { "action_query_batch_std": 8.030485916137696, "action_query_norm": 381.50108642578124, "action_relation_loss": 0.01262061633169651, "auxiliary_loss_weight": 1.0, "epoch": 1.8054256314312442, "flow_matching_loss": 0.0768299162387848, "grad_norm": 0.17266544699668884, "invalid_tail_samples": 22.5, "learning_rate": 9.99441036198961e-05, "loss": 0.0895, "positive_teacher_pairs": 27152.7, "relation_loss": 0.01262061633169651, "selected_pairs": 27152.7, "step": 1930, "student_distance_mean": 454.0326843261719, "teacher_distance_mean": 0.8481143653392792, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.01262061633169651, "weighted_relation_loss": 0.01262061633169651 }, { "action_query_batch_std": 8.00507230758667, "action_query_norm": 381.64145812988284, "action_relation_loss": 0.011770842876285315, "auxiliary_loss_weight": 1.0, "epoch": 1.8147801683816651, "flow_matching_loss": 0.0737423799932003, "grad_norm": 0.17633776366710663, "invalid_tail_samples": 27.2, "learning_rate": 9.99414678708214e-05, "loss": 0.0855, "positive_teacher_pairs": 26075.9, "relation_loss": 0.011770842876285315, "selected_pairs": 26075.9, "step": 1940, "student_distance_mean": 455.4341278076172, "teacher_distance_mean": 0.8543880105018615, "valid_action_samples": 228.8, "weighted_auxiliary_loss": 0.011770842876285315, "weighted_relation_loss": 0.011770842876285315 }, { "action_query_batch_std": 7.922230386734009, "action_query_norm": 375.75693359375, "action_relation_loss": 0.011883846949785948, "auxiliary_loss_weight": 1.0, "epoch": 1.824134705332086, "flow_matching_loss": 0.07461657524108886, "grad_norm": 0.2583334147930145, "invalid_tail_samples": 26.6, "learning_rate": 9.993877143815407e-05, "loss": 0.0865, "positive_teacher_pairs": 26204.5, "relation_loss": 0.011883846949785948, "selected_pairs": 26204.5, "step": 1950, "student_distance_mean": 448.38242797851564, "teacher_distance_mean": 0.8536416530609131, "valid_action_samples": 229.4, "weighted_auxiliary_loss": 0.011883846949785948, "weighted_relation_loss": 0.011883846949785948 }, { "action_query_batch_std": 7.859085893630981, "action_query_norm": 372.091796875, "action_relation_loss": 0.012048806250095367, "auxiliary_loss_weight": 1.0, "epoch": 1.833489242282507, "flow_matching_loss": 0.07362382635474204, "grad_norm": 0.2983546257019043, "invalid_tail_samples": 25.9, "learning_rate": 9.993601432517053e-05, "loss": 0.0857, "positive_teacher_pairs": 26369.8, "relation_loss": 0.012048806250095367, "selected_pairs": 26369.8, "step": 1960, "student_distance_mean": 446.0870422363281, "teacher_distance_mean": 0.8458411753177643, "valid_action_samples": 230.1, "weighted_auxiliary_loss": 0.012048806250095367, "weighted_relation_loss": 0.012048806250095367 }, { "action_query_batch_std": 7.7181049346923825, "action_query_norm": 366.95653381347654, "action_relation_loss": 0.01186964837834239, "auxiliary_loss_weight": 1.0, "epoch": 1.842843779232928, "flow_matching_loss": 0.07343735545873642, "grad_norm": 0.25280946493148804, "invalid_tail_samples": 26.6, "learning_rate": 9.993319653522091e-05, "loss": 0.0853, "positive_teacher_pairs": 26216.1, "relation_loss": 0.01186964837834239, "selected_pairs": 26216.1, "step": 1970, "student_distance_mean": 439.35784606933595, "teacher_distance_mean": 0.8504306733608246, "valid_action_samples": 229.4, "weighted_auxiliary_loss": 0.01186964837834239, "weighted_relation_loss": 0.01186964837834239 }, { "action_query_batch_std": 8.039796781539916, "action_query_norm": 378.24139404296875, "action_relation_loss": 0.011839653085917234, "auxiliary_loss_weight": 1.0, "epoch": 1.8521983161833488, "flow_matching_loss": 0.0732967734336853, "grad_norm": 0.2585645616054535, "invalid_tail_samples": 24.6, "learning_rate": 9.993031807172911e-05, "loss": 0.0851, "positive_teacher_pairs": 26673.4, "relation_loss": 0.011839653085917234, "selected_pairs": 26673.4, "step": 1980, "student_distance_mean": 458.44200744628904, "teacher_distance_mean": 0.8552246510982513, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.011839653085917234, "weighted_relation_loss": 0.011839653085917234 }, { "action_query_batch_std": 8.225845623016358, "action_query_norm": 387.23887329101564, "action_relation_loss": 0.011195946484804153, "auxiliary_loss_weight": 1.0, "epoch": 1.86155285313377, "flow_matching_loss": 0.07319524586200714, "grad_norm": 0.20364966988563538, "invalid_tail_samples": 26.2, "learning_rate": 9.992737893819273e-05, "loss": 0.0844, "positive_teacher_pairs": 26311.4, "relation_loss": 0.011195946484804153, "selected_pairs": 26311.4, "step": 1990, "student_distance_mean": 467.25425415039064, "teacher_distance_mean": 0.8612596929073334, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.011195946484804153, "weighted_relation_loss": 0.011195946484804153 }, { "action_query_batch_std": 8.027082920074463, "action_query_norm": 380.2903656005859, "action_relation_loss": 0.011501536704599857, "auxiliary_loss_weight": 1.0, "epoch": 1.8709073900841908, "flow_matching_loss": 0.07401337623596191, "grad_norm": 0.18645130097866058, "invalid_tail_samples": 24.0, "learning_rate": 9.992437913818312e-05, "loss": 0.0855, "positive_teacher_pairs": 26806.5, "relation_loss": 0.011501536704599857, "selected_pairs": 26806.5, "step": 2000, "student_distance_mean": 453.98619689941404, "teacher_distance_mean": 0.8420625746250152, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.011501536704599857, "weighted_relation_loss": 0.011501536704599857 }, { "action_query_batch_std": 8.060087490081788, "action_query_norm": 378.4290405273438, "action_relation_loss": 0.011139441281557083, "auxiliary_loss_weight": 1.0, "epoch": 1.8802619270346117, "flow_matching_loss": 0.07235218361020088, "grad_norm": 0.19897137582302094, "invalid_tail_samples": 21.5, "learning_rate": 9.992131867534526e-05, "loss": 0.0835, "positive_teacher_pairs": 27383.8, "relation_loss": 0.011139441281557083, "selected_pairs": 27383.8, "step": 2010, "student_distance_mean": 456.19239196777346, "teacher_distance_mean": 0.8498137593269348, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.011139441281557083, "weighted_relation_loss": 0.011139441281557083 }, { "action_query_batch_std": 8.032411050796508, "action_query_norm": 375.3441986083984, "action_relation_loss": 0.012032887153327464, "auxiliary_loss_weight": 1.0, "epoch": 1.8896164639850328, "flow_matching_loss": 0.07459945604205132, "grad_norm": 0.2694145441055298, "invalid_tail_samples": 23.8, "learning_rate": 9.991819755339796e-05, "loss": 0.0866, "positive_teacher_pairs": 26844.6, "relation_loss": 0.012032887153327464, "selected_pairs": 26844.6, "step": 2020, "student_distance_mean": 454.85841979980466, "teacher_distance_mean": 0.8449108958244324, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.012032887153327464, "weighted_relation_loss": 0.012032887153327464 }, { "action_query_batch_std": 8.053538084030151, "action_query_norm": 374.2590698242187, "action_relation_loss": 0.012008975725620985, "auxiliary_loss_weight": 1.0, "epoch": 1.8989710009354537, "flow_matching_loss": 0.07464166656136513, "grad_norm": 0.21990491449832916, "invalid_tail_samples": 24.8, "learning_rate": 9.991501577613365e-05, "loss": 0.0867, "positive_teacher_pairs": 26619.7, "relation_loss": 0.012008975725620985, "selected_pairs": 26619.7, "step": 2030, "student_distance_mean": 457.5044647216797, "teacher_distance_mean": 0.855025976896286, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.012008975725620985, "weighted_relation_loss": 0.012008975725620985 }, { "action_query_batch_std": 8.034603023529053, "action_query_norm": 377.45400085449216, "action_relation_loss": 0.011353152524679899, "auxiliary_loss_weight": 1.0, "epoch": 1.9083255378858746, "flow_matching_loss": 0.07441265061497689, "grad_norm": 0.2810445725917816, "invalid_tail_samples": 23.7, "learning_rate": 9.99117733474185e-05, "loss": 0.0858, "positive_teacher_pairs": 26871.5, "relation_loss": 0.011353152524679899, "selected_pairs": 26871.5, "step": 2040, "student_distance_mean": 453.290478515625, "teacher_distance_mean": 0.8520225286483765, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.011353152524679899, "weighted_relation_loss": 0.011353152524679899 }, { "action_query_batch_std": 8.46731424331665, "action_query_norm": 397.9226409912109, "action_relation_loss": 0.011499646492302418, "auxiliary_loss_weight": 1.0, "epoch": 1.9176800748362957, "flow_matching_loss": 0.07608987465500831, "grad_norm": 0.2126709669828415, "invalid_tail_samples": 26.0, "learning_rate": 9.990847027119234e-05, "loss": 0.0876, "positive_teacher_pairs": 26341.8, "relation_loss": 0.011499646492302418, "selected_pairs": 26341.8, "step": 2050, "student_distance_mean": 480.34668884277346, "teacher_distance_mean": 0.8660690903663635, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.011499646492302418, "weighted_relation_loss": 0.011499646492302418 }, { "action_query_batch_std": 8.589781093597413, "action_query_norm": 402.34197387695315, "action_relation_loss": 0.011194588150829077, "auxiliary_loss_weight": 1.0, "epoch": 1.9270346117867165, "flow_matching_loss": 0.07258516699075698, "grad_norm": 0.22477608919143677, "invalid_tail_samples": 23.5, "learning_rate": 9.990510655146877e-05, "loss": 0.0838, "positive_teacher_pairs": 26916.8, "relation_loss": 0.011194588150829077, "selected_pairs": 26916.8, "step": 2060, "student_distance_mean": 484.86378479003906, "teacher_distance_mean": 0.8665591061115265, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.011194588150829077, "weighted_relation_loss": 0.011194588150829077 }, { "action_query_batch_std": 8.336829376220702, "action_query_norm": 394.40668334960935, "action_relation_loss": 0.011267828848212957, "auxiliary_loss_weight": 1.0, "epoch": 1.9363891487371374, "flow_matching_loss": 0.07266712784767151, "grad_norm": 0.30891209840774536, "invalid_tail_samples": 22.4, "learning_rate": 9.990168219233496e-05, "loss": 0.0839, "positive_teacher_pairs": 27174.8, "relation_loss": 0.011267828848212957, "selected_pairs": 27174.8, "step": 2070, "student_distance_mean": 470.3134826660156, "teacher_distance_mean": 0.8529402673244476, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.011267828848212957, "weighted_relation_loss": 0.011267828848212957 }, { "action_query_batch_std": 8.413900566101074, "action_query_norm": 398.1890045166016, "action_relation_loss": 0.011497600562870502, "auxiliary_loss_weight": 1.0, "epoch": 1.9457436856875585, "flow_matching_loss": 0.07338454425334931, "grad_norm": 0.2234109789133072, "invalid_tail_samples": 22.9, "learning_rate": 9.989819719795188e-05, "loss": 0.0849, "positive_teacher_pairs": 27056.8, "relation_loss": 0.011497600562870502, "selected_pairs": 27056.8, "step": 2080, "student_distance_mean": 474.0587097167969, "teacher_distance_mean": 0.8489420056343079, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.011497600562870502, "weighted_relation_loss": 0.011497600562870502 }, { "action_query_batch_std": 8.376276874542237, "action_query_norm": 394.2199005126953, "action_relation_loss": 0.011601857468485832, "auxiliary_loss_weight": 1.0, "epoch": 1.9550982226379794, "flow_matching_loss": 0.07167974635958671, "grad_norm": 0.3216937780380249, "invalid_tail_samples": 24.0, "learning_rate": 9.989465157255412e-05, "loss": 0.0833, "positive_teacher_pairs": 26812.1, "relation_loss": 0.011601857468485832, "selected_pairs": 26812.1, "step": 2090, "student_distance_mean": 473.42890014648435, "teacher_distance_mean": 0.8544936001300811, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.011601857468485832, "weighted_relation_loss": 0.011601857468485832 }, { "action_query_batch_std": 8.422392463684082, "action_query_norm": 397.85528869628905, "action_relation_loss": 0.011189591232687235, "auxiliary_loss_weight": 1.0, "epoch": 1.9644527595884003, "flow_matching_loss": 0.0731152430176735, "grad_norm": 0.17000940442085266, "invalid_tail_samples": 27.3, "learning_rate": 9.989104532044994e-05, "loss": 0.0843, "positive_teacher_pairs": 26047.8, "relation_loss": 0.011189591232687235, "selected_pairs": 26047.8, "step": 2100, "student_distance_mean": 478.5866760253906, "teacher_distance_mean": 0.854183691740036, "valid_action_samples": 228.7, "weighted_auxiliary_loss": 0.011189591232687235, "weighted_relation_loss": 0.011189591232687235 }, { "action_query_batch_std": 8.354833507537842, "action_query_norm": 393.0534362792969, "action_relation_loss": 0.011409569811075927, "auxiliary_loss_weight": 1.0, "epoch": 1.9738072965388214, "flow_matching_loss": 0.0712426871061325, "grad_norm": 0.31431806087493896, "invalid_tail_samples": 22.5, "learning_rate": 9.988737844602128e-05, "loss": 0.0827, "positive_teacher_pairs": 27162.7, "relation_loss": 0.011409569811075927, "selected_pairs": 27162.7, "step": 2110, "student_distance_mean": 470.6171417236328, "teacher_distance_mean": 0.8452260613441467, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.011409569811075927, "weighted_relation_loss": 0.011409569811075927 }, { "action_query_batch_std": 8.44434404373169, "action_query_norm": 396.56138610839844, "action_relation_loss": 0.01105741411447525, "auxiliary_loss_weight": 1.0, "epoch": 1.9831618334892422, "flow_matching_loss": 0.07207595109939575, "grad_norm": 0.20784682035446167, "invalid_tail_samples": 22.4, "learning_rate": 9.988365095372372e-05, "loss": 0.0831, "positive_teacher_pairs": 27179.4, "relation_loss": 0.01105741411447525, "selected_pairs": 27179.4, "step": 2120, "student_distance_mean": 477.0712371826172, "teacher_distance_mean": 0.8593399822711945, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.01105741411447525, "weighted_relation_loss": 0.01105741411447525 }, { "action_query_batch_std": 8.335245132446289, "action_query_norm": 393.7403564453125, "action_relation_loss": 0.011665868479758501, "auxiliary_loss_weight": 1.0, "epoch": 1.9925163704396631, "flow_matching_loss": 0.07367823570966721, "grad_norm": 0.27750536799430847, "invalid_tail_samples": 23.5, "learning_rate": 9.987986284808654e-05, "loss": 0.0853, "positive_teacher_pairs": 26916.4, "relation_loss": 0.011665868479758501, "selected_pairs": 26916.4, "step": 2130, "student_distance_mean": 471.29441223144534, "teacher_distance_mean": 0.8468732237815857, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.011665868479758501, "weighted_relation_loss": 0.011665868479758501 }, { "action_query_batch_std": 8.451801204681397, "action_query_norm": 397.8813537597656, "action_relation_loss": 0.01123599400743842, "auxiliary_loss_weight": 1.0, "epoch": 2.001870907390084, "flow_matching_loss": 0.07446349002420902, "grad_norm": 0.29191333055496216, "invalid_tail_samples": 20.9, "learning_rate": 9.987601413371264e-05, "loss": 0.0857, "positive_teacher_pairs": 24556.9, "relation_loss": 0.01123599400743842, "selected_pairs": 24556.9, "step": 2140, "student_distance_mean": 479.9680938720703, "teacher_distance_mean": 0.8547848343849183, "valid_action_samples": 215.2, "weighted_auxiliary_loss": 0.01123599400743842, "weighted_relation_loss": 0.01123599400743842 }, { "action_query_batch_std": 8.526288795471192, "action_query_norm": 400.9569061279297, "action_relation_loss": 0.011446651630103588, "auxiliary_loss_weight": 1.0, "epoch": 2.0112254443405053, "flow_matching_loss": 0.07784739807248116, "grad_norm": 0.21753163635730743, "invalid_tail_samples": 25.8, "learning_rate": 9.987210481527855e-05, "loss": 0.0893, "positive_teacher_pairs": 26400.0, "relation_loss": 0.011446651630103588, "selected_pairs": 26400.0, "step": 2150, "student_distance_mean": 484.4327789306641, "teacher_distance_mean": 0.8498879849910737, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.011446651630103588, "weighted_relation_loss": 0.011446651630103588 }, { "action_query_batch_std": 8.552843379974366, "action_query_norm": 400.61830749511716, "action_relation_loss": 0.011629880871623755, "auxiliary_loss_weight": 1.0, "epoch": 2.020579981290926, "flow_matching_loss": 0.0740334540605545, "grad_norm": 0.23358701169490814, "invalid_tail_samples": 24.7, "learning_rate": 9.98681348975345e-05, "loss": 0.0857, "positive_teacher_pairs": 26648.1, "relation_loss": 0.011629880871623755, "selected_pairs": 26648.1, "step": 2160, "student_distance_mean": 486.3923828125, "teacher_distance_mean": 0.8566796183586121, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.011629880871623755, "weighted_relation_loss": 0.011629880871623755 }, { "action_query_batch_std": 8.41935863494873, "action_query_norm": 394.0577392578125, "action_relation_loss": 0.01132179144769907, "auxiliary_loss_weight": 1.0, "epoch": 2.029934518241347, "flow_matching_loss": 0.074674042314291, "grad_norm": 0.2097361534833908, "invalid_tail_samples": 22.6, "learning_rate": 9.986410438530427e-05, "loss": 0.086, "positive_teacher_pairs": 27128.4, "relation_loss": 0.01132179144769907, "selected_pairs": 27128.4, "step": 2170, "student_distance_mean": 473.8272644042969, "teacher_distance_mean": 0.8485345363616943, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.01132179144769907, "weighted_relation_loss": 0.01132179144769907 }, { "action_query_batch_std": 8.536952304840089, "action_query_norm": 399.50672302246096, "action_relation_loss": 0.011573130451142787, "auxiliary_loss_weight": 1.0, "epoch": 2.039289055191768, "flow_matching_loss": 0.07330397814512253, "grad_norm": 0.18581995368003845, "invalid_tail_samples": 21.9, "learning_rate": 9.986001328348534e-05, "loss": 0.0849, "positive_teacher_pairs": 27291.6, "relation_loss": 0.011573130451142787, "selected_pairs": 27291.6, "step": 2180, "student_distance_mean": 484.71318969726565, "teacher_distance_mean": 0.8569011330604553, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.011573130451142787, "weighted_relation_loss": 0.011573130451142787 }, { "action_query_batch_std": 8.350082111358642, "action_query_norm": 390.3287078857422, "action_relation_loss": 0.011315055936574937, "auxiliary_loss_weight": 1.0, "epoch": 2.048643592142189, "flow_matching_loss": 0.07163317091763019, "grad_norm": 0.22596217691898346, "invalid_tail_samples": 24.2, "learning_rate": 9.985586159704878e-05, "loss": 0.0829, "positive_teacher_pairs": 26761.1, "relation_loss": 0.011315055936574937, "selected_pairs": 26761.1, "step": 2190, "student_distance_mean": 471.0874908447266, "teacher_distance_mean": 0.8435621798038483, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.011315055936574937, "weighted_relation_loss": 0.011315055936574937 }, { "action_query_batch_std": 8.409004306793213, "action_query_norm": 395.03273315429686, "action_relation_loss": 0.011297750659286976, "auxiliary_loss_weight": 1.0, "epoch": 2.05799812909261, "flow_matching_loss": 0.07470509186387062, "grad_norm": 0.23705437779426575, "invalid_tail_samples": 23.3, "learning_rate": 9.985164933103929e-05, "loss": 0.086, "positive_teacher_pairs": 26971.8, "relation_loss": 0.011297750659286976, "selected_pairs": 26971.8, "step": 2200, "student_distance_mean": 474.5302795410156, "teacher_distance_mean": 0.860341477394104, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.011297750659286976, "weighted_relation_loss": 0.011297750659286976 }, { "action_query_batch_std": 8.379329395294189, "action_query_norm": 398.47723083496095, "action_relation_loss": 0.011222791112959384, "auxiliary_loss_weight": 1.0, "epoch": 2.067352666043031, "flow_matching_loss": 0.07337975278496742, "grad_norm": 0.2123866081237793, "invalid_tail_samples": 23.5, "learning_rate": 9.984737649057513e-05, "loss": 0.0846, "positive_teacher_pairs": 26928.6, "relation_loss": 0.011222791112959384, "selected_pairs": 26928.6, "step": 2210, "student_distance_mean": 472.31598205566405, "teacher_distance_mean": 0.8448000907897949, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.011222791112959384, "weighted_relation_loss": 0.011222791112959384 }, { "action_query_batch_std": 8.676091194152832, "action_query_norm": 407.3606903076172, "action_relation_loss": 0.011613542027771474, "auxiliary_loss_weight": 1.0, "epoch": 2.0767072029934517, "flow_matching_loss": 0.07431945577263832, "grad_norm": 0.2673470377922058, "invalid_tail_samples": 23.9, "learning_rate": 9.984304308084827e-05, "loss": 0.0859, "positive_teacher_pairs": 26822.9, "relation_loss": 0.011613542027771474, "selected_pairs": 26822.9, "step": 2220, "student_distance_mean": 489.3056976318359, "teacher_distance_mean": 0.8476587057113647, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.011613542027771474, "weighted_relation_loss": 0.011613542027771474 }, { "action_query_batch_std": 8.686890602111816, "action_query_norm": 409.9223358154297, "action_relation_loss": 0.011455380078405141, "auxiliary_loss_weight": 1.0, "epoch": 2.086061739943873, "flow_matching_loss": 0.0738326482474804, "grad_norm": 0.2365894466638565, "invalid_tail_samples": 22.5, "learning_rate": 9.983864910712416e-05, "loss": 0.0853, "positive_teacher_pairs": 27156.8, "relation_loss": 0.011455380078405141, "selected_pairs": 27156.8, "step": 2230, "student_distance_mean": 491.9085693359375, "teacher_distance_mean": 0.8543000400066376, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.011455380078405141, "weighted_relation_loss": 0.011455380078405141 }, { "action_query_batch_std": 8.787629699707031, "action_query_norm": 411.8839050292969, "action_relation_loss": 0.010869256779551506, "auxiliary_loss_weight": 1.0, "epoch": 2.095416276894294, "flow_matching_loss": 0.07231393977999687, "grad_norm": 0.2448863387107849, "invalid_tail_samples": 22.4, "learning_rate": 9.98341945747419e-05, "loss": 0.0832, "positive_teacher_pairs": 27174.6, "relation_loss": 0.010869256779551506, "selected_pairs": 27174.6, "step": 2240, "student_distance_mean": 494.6177673339844, "teacher_distance_mean": 0.8554051637649536, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.010869256779551506, "weighted_relation_loss": 0.010869256779551506 }, { "action_query_batch_std": 8.776263904571532, "action_query_norm": 411.2698150634766, "action_relation_loss": 0.010499172937124967, "auxiliary_loss_weight": 1.0, "epoch": 2.1047708138447145, "flow_matching_loss": 0.07312724590301514, "grad_norm": 0.20062966644763947, "invalid_tail_samples": 22.6, "learning_rate": 9.98296794891142e-05, "loss": 0.0836, "positive_teacher_pairs": 27131.5, "relation_loss": 0.010499172937124967, "selected_pairs": 27131.5, "step": 2250, "student_distance_mean": 495.98972778320314, "teacher_distance_mean": 0.8553018629550934, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.010499172937124967, "weighted_relation_loss": 0.010499172937124967 }, { "action_query_batch_std": 8.59710168838501, "action_query_norm": 401.86334838867185, "action_relation_loss": 0.011293986998498439, "auxiliary_loss_weight": 1.0, "epoch": 2.1141253507951356, "flow_matching_loss": 0.07542262524366379, "grad_norm": 0.2020210474729538, "invalid_tail_samples": 23.9, "learning_rate": 9.982510385572725e-05, "loss": 0.0867, "positive_teacher_pairs": 26824.4, "relation_loss": 0.011293986998498439, "selected_pairs": 26824.4, "step": 2260, "student_distance_mean": 485.8135650634766, "teacher_distance_mean": 0.8567930519580841, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.011293986998498439, "weighted_relation_loss": 0.011293986998498439 }, { "action_query_batch_std": 8.695068740844727, "action_query_norm": 401.5216461181641, "action_relation_loss": 0.011058900970965624, "auxiliary_loss_weight": 1.0, "epoch": 2.1234798877455567, "flow_matching_loss": 0.07453663051128387, "grad_norm": 0.25763916969299316, "invalid_tail_samples": 24.1, "learning_rate": 9.982046768014094e-05, "loss": 0.0856, "positive_teacher_pairs": 26792.6, "relation_loss": 0.011058900970965624, "selected_pairs": 26792.6, "step": 2270, "student_distance_mean": 492.78150329589846, "teacher_distance_mean": 0.8519338190555572, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.011058900970965624, "weighted_relation_loss": 0.011058900970965624 }, { "action_query_batch_std": 8.62722396850586, "action_query_norm": 402.6128814697266, "action_relation_loss": 0.011102775111794472, "auxiliary_loss_weight": 1.0, "epoch": 2.1328344246959774, "flow_matching_loss": 0.07150590568780898, "grad_norm": 0.19616787135601044, "invalid_tail_samples": 23.4, "learning_rate": 9.981577096798863e-05, "loss": 0.0826, "positive_teacher_pairs": 26942.0, "relation_loss": 0.011102775111794472, "selected_pairs": 26942.0, "step": 2280, "student_distance_mean": 488.4520233154297, "teacher_distance_mean": 0.8580209195613862, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.011102775111794472, "weighted_relation_loss": 0.011102775111794472 }, { "action_query_batch_std": 8.741319179534912, "action_query_norm": 402.9391723632813, "action_relation_loss": 0.010451782960444689, "auxiliary_loss_weight": 1.0, "epoch": 2.1421889616463985, "flow_matching_loss": 0.07302348427474499, "grad_norm": 0.21914146840572357, "invalid_tail_samples": 24.1, "learning_rate": 9.981101372497727e-05, "loss": 0.0835, "positive_teacher_pairs": 26789.0, "relation_loss": 0.010451782960444689, "selected_pairs": 26789.0, "step": 2290, "student_distance_mean": 496.5298309326172, "teacher_distance_mean": 0.860910427570343, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.010451782960444689, "weighted_relation_loss": 0.010451782960444689 }, { "action_query_batch_std": 8.491642379760743, "action_query_norm": 396.584619140625, "action_relation_loss": 0.010580128617584705, "auxiliary_loss_weight": 1.0, "epoch": 2.1515434985968196, "flow_matching_loss": 0.07058963701128959, "grad_norm": 0.24440427124500275, "invalid_tail_samples": 23.2, "learning_rate": 9.980619595688737e-05, "loss": 0.0812, "positive_teacher_pairs": 26996.1, "relation_loss": 0.010580128617584705, "selected_pairs": 26996.1, "step": 2300, "student_distance_mean": 481.53248291015626, "teacher_distance_mean": 0.8455359697341919, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.010580128617584705, "weighted_relation_loss": 0.010580128617584705 }, { "action_query_batch_std": 8.619925022125244, "action_query_norm": 402.7772186279297, "action_relation_loss": 0.010716603510081768, "auxiliary_loss_weight": 1.0, "epoch": 2.1608980355472402, "flow_matching_loss": 0.07242064103484154, "grad_norm": 0.2642774283885956, "invalid_tail_samples": 25.7, "learning_rate": 9.980131766957295e-05, "loss": 0.0831, "positive_teacher_pairs": 26411.7, "relation_loss": 0.010716603510081768, "selected_pairs": 26411.7, "step": 2310, "student_distance_mean": 488.72649536132815, "teacher_distance_mean": 0.8515179216861725, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.010716603510081768, "weighted_relation_loss": 0.010716603510081768 }, { "action_query_batch_std": 8.604479885101318, "action_query_norm": 404.7857940673828, "action_relation_loss": 0.010877032671123743, "auxiliary_loss_weight": 1.0, "epoch": 2.1702525724976613, "flow_matching_loss": 0.07280837073922157, "grad_norm": 0.2829655110836029, "invalid_tail_samples": 25.5, "learning_rate": 9.979637886896163e-05, "loss": 0.0837, "positive_teacher_pairs": 26457.8, "relation_loss": 0.010877032671123743, "selected_pairs": 26457.8, "step": 2320, "student_distance_mean": 488.7264099121094, "teacher_distance_mean": 0.8499108672142028, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.010877032671123743, "weighted_relation_loss": 0.010877032671123743 }, { "action_query_batch_std": 8.723343563079833, "action_query_norm": 410.2785186767578, "action_relation_loss": 0.010713640414178372, "auxiliary_loss_weight": 1.0, "epoch": 2.1796071094480824, "flow_matching_loss": 0.07427402809262276, "grad_norm": 0.23190978169441223, "invalid_tail_samples": 26.3, "learning_rate": 9.979137956105447e-05, "loss": 0.085, "positive_teacher_pairs": 26272.8, "relation_loss": 0.010713640414178372, "selected_pairs": 26272.8, "step": 2330, "student_distance_mean": 494.5688537597656, "teacher_distance_mean": 0.8552037656307221, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.010713640414178372, "weighted_relation_loss": 0.010713640414178372 }, { "action_query_batch_std": 8.957930946350098, "action_query_norm": 421.9324432373047, "action_relation_loss": 0.011194996349513531, "auxiliary_loss_weight": 1.0, "epoch": 2.188961646398503, "flow_matching_loss": 0.0726882942020893, "grad_norm": 0.17828692495822906, "invalid_tail_samples": 22.4, "learning_rate": 9.978631975192613e-05, "loss": 0.0839, "positive_teacher_pairs": 27174.2, "relation_loss": 0.011194996349513531, "selected_pairs": 27174.2, "step": 2340, "student_distance_mean": 506.1671661376953, "teacher_distance_mean": 0.8592521190643311, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.011194996349513531, "weighted_relation_loss": 0.011194996349513531 }, { "action_query_batch_std": 8.87268123626709, "action_query_norm": 412.8457733154297, "action_relation_loss": 0.01107560945674777, "auxiliary_loss_weight": 1.0, "epoch": 2.198316183348924, "flow_matching_loss": 0.06920578740537167, "grad_norm": 0.18765582144260406, "invalid_tail_samples": 22.7, "learning_rate": 9.978119944772475e-05, "loss": 0.0803, "positive_teacher_pairs": 27102.6, "relation_loss": 0.01107560945674777, "selected_pairs": 27102.6, "step": 2350, "student_distance_mean": 503.2248229980469, "teacher_distance_mean": 0.8545251369476319, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.01107560945674777, "weighted_relation_loss": 0.01107560945674777 }, { "action_query_batch_std": 8.656132698059082, "action_query_norm": 405.37725830078125, "action_relation_loss": 0.01103389197960496, "auxiliary_loss_weight": 1.0, "epoch": 2.2076707202993453, "flow_matching_loss": 0.07300985977053642, "grad_norm": 0.1876729279756546, "invalid_tail_samples": 24.3, "learning_rate": 9.977601865467197e-05, "loss": 0.084, "positive_teacher_pairs": 26735.8, "relation_loss": 0.01103389197960496, "selected_pairs": 26735.8, "step": 2360, "student_distance_mean": 491.9062774658203, "teacher_distance_mean": 0.8605015873908997, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.01103389197960496, "weighted_relation_loss": 0.01103389197960496 }, { "action_query_batch_std": 8.86208143234253, "action_query_norm": 414.6368041992188, "action_relation_loss": 0.010944281332194805, "auxiliary_loss_weight": 1.0, "epoch": 2.217025257249766, "flow_matching_loss": 0.07084929198026657, "grad_norm": 0.22439290583133698, "invalid_tail_samples": 22.4, "learning_rate": 9.977077737906297e-05, "loss": 0.0818, "positive_teacher_pairs": 27174.6, "relation_loss": 0.010944281332194805, "selected_pairs": 27174.6, "step": 2370, "student_distance_mean": 501.225146484375, "teacher_distance_mean": 0.8627536714076995, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.010944281332194805, "weighted_relation_loss": 0.010944281332194805 }, { "action_query_batch_std": 8.994788551330567, "action_query_norm": 421.6114807128906, "action_relation_loss": 0.011000653449445962, "auxiliary_loss_weight": 1.0, "epoch": 2.226379794200187, "flow_matching_loss": 0.07322290688753127, "grad_norm": 0.20611295104026794, "invalid_tail_samples": 24.2, "learning_rate": 9.976547562726636e-05, "loss": 0.0842, "positive_teacher_pairs": 26759.0, "relation_loss": 0.011000653449445962, "selected_pairs": 26759.0, "step": 2380, "student_distance_mean": 506.71221618652345, "teacher_distance_mean": 0.8607861697673798, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.011000653449445962, "weighted_relation_loss": 0.011000653449445962 }, { "action_query_batch_std": 8.877930641174316, "action_query_norm": 414.79619750976565, "action_relation_loss": 0.010497860983014107, "auxiliary_loss_weight": 1.0, "epoch": 2.235734331150608, "flow_matching_loss": 0.06758959181606769, "grad_norm": 0.25231868028640747, "invalid_tail_samples": 22.5, "learning_rate": 9.976011340572429e-05, "loss": 0.0781, "positive_teacher_pairs": 27153.0, "relation_loss": 0.010497860983014107, "selected_pairs": 27153.0, "step": 2390, "student_distance_mean": 503.6494598388672, "teacher_distance_mean": 0.856106412410736, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.010497860983014107, "weighted_relation_loss": 0.010497860983014107 }, { "action_query_batch_std": 8.854407691955567, "action_query_norm": 414.41603088378906, "action_relation_loss": 0.010841759759932757, "auxiliary_loss_weight": 1.0, "epoch": 2.245088868101029, "flow_matching_loss": 0.07098832428455353, "grad_norm": 0.23625975847244263, "invalid_tail_samples": 24.1, "learning_rate": 9.975469072095237e-05, "loss": 0.0818, "positive_teacher_pairs": 26781.3, "relation_loss": 0.010841759759932757, "selected_pairs": 26781.3, "step": 2400, "student_distance_mean": 500.98525085449216, "teacher_distance_mean": 0.8586649656295776, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.010841759759932757, "weighted_relation_loss": 0.010841759759932757 }, { "action_query_batch_std": 8.917078495025635, "action_query_norm": 417.1377716064453, "action_relation_loss": 0.01077620405703783, "auxiliary_loss_weight": 1.0, "epoch": 2.25444340505145, "flow_matching_loss": 0.07095831856131554, "grad_norm": 0.21976281702518463, "invalid_tail_samples": 25.6, "learning_rate": 9.974920757953965e-05, "loss": 0.0817, "positive_teacher_pairs": 26433.6, "relation_loss": 0.01077620405703783, "selected_pairs": 26433.6, "step": 2410, "student_distance_mean": 504.8439514160156, "teacher_distance_mean": 0.8620654046535492, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.01077620405703783, "weighted_relation_loss": 0.01077620405703783 }, { "action_query_batch_std": 9.021456146240235, "action_query_norm": 422.6294342041016, "action_relation_loss": 0.010712660755962134, "auxiliary_loss_weight": 1.0, "epoch": 2.263797942001871, "flow_matching_loss": 0.07070457823574543, "grad_norm": 0.2581172585487366, "invalid_tail_samples": 22.9, "learning_rate": 9.97436639881487e-05, "loss": 0.0814, "positive_teacher_pairs": 27059.9, "relation_loss": 0.010712660755962134, "selected_pairs": 27059.9, "step": 2420, "student_distance_mean": 511.38970947265625, "teacher_distance_mean": 0.864580774307251, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.010712660755962134, "weighted_relation_loss": 0.010712660755962134 }, { "action_query_batch_std": 8.816228771209717, "action_query_norm": 414.5368133544922, "action_relation_loss": 0.011204404290765524, "auxiliary_loss_weight": 1.0, "epoch": 2.2731524789522917, "flow_matching_loss": 0.06964468881487847, "grad_norm": 0.18856000900268555, "invalid_tail_samples": 25.2, "learning_rate": 9.973805995351545e-05, "loss": 0.0808, "positive_teacher_pairs": 26532.1, "relation_loss": 0.011204404290765524, "selected_pairs": 26532.1, "step": 2430, "student_distance_mean": 498.6501739501953, "teacher_distance_mean": 0.8517261981964112, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.011204404290765524, "weighted_relation_loss": 0.011204404290765524 }, { "action_query_batch_std": 8.803187084197997, "action_query_norm": 411.4430389404297, "action_relation_loss": 0.010839175246655942, "auxiliary_loss_weight": 1.0, "epoch": 2.2825070159027128, "flow_matching_loss": 0.07286798357963561, "grad_norm": 0.20806977152824402, "invalid_tail_samples": 25.3, "learning_rate": 9.973239548244939e-05, "loss": 0.0837, "positive_teacher_pairs": 26501.9, "relation_loss": 0.010839175246655942, "selected_pairs": 26501.9, "step": 2440, "student_distance_mean": 498.98511657714846, "teacher_distance_mean": 0.8615609765052795, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.010839175246655942, "weighted_relation_loss": 0.010839175246655942 }, { "action_query_batch_std": 8.960923957824708, "action_query_norm": 420.2246520996094, "action_relation_loss": 0.010716298874467612, "auxiliary_loss_weight": 1.0, "epoch": 2.291861552853134, "flow_matching_loss": 0.07286425530910492, "grad_norm": 0.2024773210287094, "invalid_tail_samples": 26.0, "learning_rate": 9.972667058183333e-05, "loss": 0.0836, "positive_teacher_pairs": 26342.6, "relation_loss": 0.010716298874467612, "selected_pairs": 26342.6, "step": 2450, "student_distance_mean": 508.6462036132813, "teacher_distance_mean": 0.8545688092708588, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.010716298874467612, "weighted_relation_loss": 0.010716298874467612 }, { "action_query_batch_std": 8.850972557067871, "action_query_norm": 416.3748748779297, "action_relation_loss": 0.010807800013571978, "auxiliary_loss_weight": 1.0, "epoch": 2.301216089803555, "flow_matching_loss": 0.06851555891335011, "grad_norm": 0.19386428594589233, "invalid_tail_samples": 24.6, "learning_rate": 9.972088525862362e-05, "loss": 0.0793, "positive_teacher_pairs": 26660.3, "relation_loss": 0.010807800013571978, "selected_pairs": 26660.3, "step": 2460, "student_distance_mean": 502.18780822753905, "teacher_distance_mean": 0.8584686934947967, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.010807800013571978, "weighted_relation_loss": 0.010807800013571978 }, { "action_query_batch_std": 8.872412300109863, "action_query_norm": 416.8495666503906, "action_relation_loss": 0.010818738862872124, "auxiliary_loss_weight": 1.0, "epoch": 2.3105706267539756, "flow_matching_loss": 0.0701764240860939, "grad_norm": 0.21345439553260803, "invalid_tail_samples": 23.2, "learning_rate": 9.971503951984995e-05, "loss": 0.081, "positive_teacher_pairs": 26997.4, "relation_loss": 0.010818738862872124, "selected_pairs": 26997.4, "step": 2470, "student_distance_mean": 500.9537048339844, "teacher_distance_mean": 0.8527155101299286, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.010818738862872124, "weighted_relation_loss": 0.010818738862872124 }, { "action_query_batch_std": 9.02932357788086, "action_query_norm": 422.65155334472655, "action_relation_loss": 0.010729463025927543, "auxiliary_loss_weight": 1.0, "epoch": 2.3199251637043967, "flow_matching_loss": 0.07237340211868286, "grad_norm": 0.18901804089546204, "invalid_tail_samples": 26.1, "learning_rate": 9.970913337261543e-05, "loss": 0.0831, "positive_teacher_pairs": 26327.1, "relation_loss": 0.010729463025927543, "selected_pairs": 26327.1, "step": 2480, "student_distance_mean": 511.33640441894534, "teacher_distance_mean": 0.8549225211143494, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.010729463025927543, "weighted_relation_loss": 0.010729463025927543 }, { "action_query_batch_std": 9.050657367706298, "action_query_norm": 422.62957153320315, "action_relation_loss": 0.01087378580123186, "auxiliary_loss_weight": 1.0, "epoch": 2.3292797006548174, "flow_matching_loss": 0.06997374370694161, "grad_norm": 0.1794978231191635, "invalid_tail_samples": 25.1, "learning_rate": 9.97031668240966e-05, "loss": 0.0808, "positive_teacher_pairs": 26544.0, "relation_loss": 0.01087378580123186, "selected_pairs": 26544.0, "step": 2490, "student_distance_mean": 511.5822784423828, "teacher_distance_mean": 0.8507690489292145, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.01087378580123186, "weighted_relation_loss": 0.01087378580123186 }, { "action_query_batch_std": 8.955254173278808, "action_query_norm": 424.14739685058595, "action_relation_loss": 0.011108957137912512, "auxiliary_loss_weight": 1.0, "epoch": 2.3386342376052385, "flow_matching_loss": 0.07049463763833046, "grad_norm": 0.1938578188419342, "invalid_tail_samples": 23.8, "learning_rate": 9.969713988154339e-05, "loss": 0.0816, "positive_teacher_pairs": 26850.5, "relation_loss": 0.011108957137912512, "selected_pairs": 26850.5, "step": 2500, "student_distance_mean": 507.6938507080078, "teacher_distance_mean": 0.846074104309082, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.011108957137912512, "weighted_relation_loss": 0.011108957137912512 }, { "action_query_batch_std": 9.017176532745362, "action_query_norm": 422.6299255371094, "action_relation_loss": 0.010986237321048975, "auxiliary_loss_weight": 1.0, "epoch": 2.3479887745556596, "flow_matching_loss": 0.06692345589399337, "grad_norm": 0.20429281890392303, "invalid_tail_samples": 21.9, "learning_rate": 9.969105255227906e-05, "loss": 0.0779, "positive_teacher_pairs": 27292.8, "relation_loss": 0.010986237321048975, "selected_pairs": 27292.8, "step": 2510, "student_distance_mean": 505.7627014160156, "teacher_distance_mean": 0.8498829066753387, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.010986237321048975, "weighted_relation_loss": 0.010986237321048975 }, { "action_query_batch_std": 9.077189254760743, "action_query_norm": 426.6125, "action_relation_loss": 0.01091391984373331, "auxiliary_loss_weight": 1.0, "epoch": 2.3573433115060807, "flow_matching_loss": 0.06808374263346195, "grad_norm": 0.2401130050420761, "invalid_tail_samples": 26.4, "learning_rate": 9.968490484370035e-05, "loss": 0.079, "positive_teacher_pairs": 26249.9, "relation_loss": 0.01091391984373331, "selected_pairs": 26249.9, "step": 2520, "student_distance_mean": 514.226708984375, "teacher_distance_mean": 0.8544618487358093, "valid_action_samples": 229.6, "weighted_auxiliary_loss": 0.01091391984373331, "weighted_relation_loss": 0.01091391984373331 }, { "action_query_batch_std": 9.039496326446534, "action_query_norm": 428.5395202636719, "action_relation_loss": 0.01046044658869505, "auxiliary_loss_weight": 1.0, "epoch": 2.3666978484565013, "flow_matching_loss": 0.07024906761944294, "grad_norm": 0.14996090531349182, "invalid_tail_samples": 23.0, "learning_rate": 9.967869676327726e-05, "loss": 0.0807, "positive_teacher_pairs": 27034.6, "relation_loss": 0.01046044658869505, "selected_pairs": 27034.6, "step": 2530, "student_distance_mean": 514.0576263427735, "teacher_distance_mean": 0.8492948114871979, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.01046044658869505, "weighted_relation_loss": 0.01046044658869505 }, { "action_query_batch_std": 9.18730525970459, "action_query_norm": 429.46239318847654, "action_relation_loss": 0.010743972565978765, "auxiliary_loss_weight": 1.0, "epoch": 2.3760523854069224, "flow_matching_loss": 0.06542360410094261, "grad_norm": 0.17865866422653198, "invalid_tail_samples": 23.1, "learning_rate": 9.96724283185532e-05, "loss": 0.0762, "positive_teacher_pairs": 27012.2, "relation_loss": 0.010743972565978765, "selected_pairs": 27012.2, "step": 2540, "student_distance_mean": 519.6923095703125, "teacher_distance_mean": 0.8606425881385803, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.010743972565978765, "weighted_relation_loss": 0.010743972565978765 }, { "action_query_batch_std": 9.204647731781005, "action_query_norm": 429.96460876464846, "action_relation_loss": 0.010466436110436916, "auxiliary_loss_weight": 1.0, "epoch": 2.385406922357343, "flow_matching_loss": 0.06793171465396881, "grad_norm": 0.2129940688610077, "invalid_tail_samples": 22.3, "learning_rate": 9.966609951714494e-05, "loss": 0.0784, "positive_teacher_pairs": 27196.4, "relation_loss": 0.010466436110436916, "selected_pairs": 27196.4, "step": 2550, "student_distance_mean": 522.6418701171875, "teacher_distance_mean": 0.8591488540172577, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.010466436110436916, "weighted_relation_loss": 0.010466436110436916 }, { "action_query_batch_std": 9.078524971008301, "action_query_norm": 423.1674743652344, "action_relation_loss": 0.010840014740824699, "auxiliary_loss_weight": 1.0, "epoch": 2.394761459307764, "flow_matching_loss": 0.06639134027063846, "grad_norm": 0.16757433116436005, "invalid_tail_samples": 22.8, "learning_rate": 9.965971036674255e-05, "loss": 0.0772, "positive_teacher_pairs": 27084.3, "relation_loss": 0.010840014740824699, "selected_pairs": 27084.3, "step": 2560, "student_distance_mean": 514.9233795166016, "teacher_distance_mean": 0.8535837709903717, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.010840014740824699, "weighted_relation_loss": 0.010840014740824699 }, { "action_query_batch_std": 9.27755069732666, "action_query_norm": 430.78533325195315, "action_relation_loss": 0.010693957842886449, "auxiliary_loss_weight": 1.0, "epoch": 2.4041159962581853, "flow_matching_loss": 0.06827091872692108, "grad_norm": 0.16441239416599274, "invalid_tail_samples": 25.4, "learning_rate": 9.965326087510947e-05, "loss": 0.079, "positive_teacher_pairs": 26484.4, "relation_loss": 0.010693957842886449, "selected_pairs": 26484.4, "step": 2570, "student_distance_mean": 526.9243957519532, "teacher_distance_mean": 0.8589366555213929, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.010693957842886449, "weighted_relation_loss": 0.010693957842886449 }, { "action_query_batch_std": 9.319188404083253, "action_query_norm": 435.6939392089844, "action_relation_loss": 0.010729397460818291, "auxiliary_loss_weight": 1.0, "epoch": 2.4134705332086064, "flow_matching_loss": 0.07001055106520652, "grad_norm": 0.17183305323123932, "invalid_tail_samples": 21.9, "learning_rate": 9.964675105008244e-05, "loss": 0.0807, "positive_teacher_pairs": 27292.2, "relation_loss": 0.010729397460818291, "selected_pairs": 27292.2, "step": 2580, "student_distance_mean": 526.96982421875, "teacher_distance_mean": 0.8554266571998597, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.010729397460818291, "weighted_relation_loss": 0.010729397460818291 }, { "action_query_batch_std": 9.2577054977417, "action_query_norm": 429.1572784423828, "action_relation_loss": 0.010556659940630198, "auxiliary_loss_weight": 1.0, "epoch": 2.422825070159027, "flow_matching_loss": 0.07051604352891445, "grad_norm": 0.22678162157535553, "invalid_tail_samples": 23.4, "learning_rate": 9.964018089957147e-05, "loss": 0.0811, "positive_teacher_pairs": 26940.8, "relation_loss": 0.010556659940630198, "selected_pairs": 26940.8, "step": 2590, "student_distance_mean": 523.194711303711, "teacher_distance_mean": 0.856326824426651, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.010556659940630198, "weighted_relation_loss": 0.010556659940630198 }, { "action_query_batch_std": 9.333943176269532, "action_query_norm": 428.3828948974609, "action_relation_loss": 0.009987358283251525, "auxiliary_loss_weight": 1.0, "epoch": 2.432179607109448, "flow_matching_loss": 0.06987108066678047, "grad_norm": 0.20943303406238556, "invalid_tail_samples": 21.0, "learning_rate": 9.963355043155996e-05, "loss": 0.0799, "positive_teacher_pairs": 27510.0, "relation_loss": 0.009987358283251525, "selected_pairs": 27510.0, "step": 2600, "student_distance_mean": 531.6104614257813, "teacher_distance_mean": 0.8668508231639862, "valid_action_samples": 235.0, "weighted_auxiliary_loss": 0.009987358283251525, "weighted_relation_loss": 0.009987358283251525 }, { "action_query_batch_std": 9.012972927093506, "action_query_norm": 421.30942687988284, "action_relation_loss": 0.010807295702397824, "auxiliary_loss_weight": 1.0, "epoch": 2.441534144059869, "flow_matching_loss": 0.06688135303556919, "grad_norm": 0.1884024292230606, "invalid_tail_samples": 23.0, "learning_rate": 9.962685965410455e-05, "loss": 0.0777, "positive_teacher_pairs": 27034.6, "relation_loss": 0.010807295702397824, "selected_pairs": 27034.6, "step": 2610, "student_distance_mean": 510.88002624511716, "teacher_distance_mean": 0.8477510035037994, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.010807295702397824, "weighted_relation_loss": 0.010807295702397824 }, { "action_query_batch_std": 9.185173225402831, "action_query_norm": 430.7807342529297, "action_relation_loss": 0.010651277657598258, "auxiliary_loss_weight": 1.0, "epoch": 2.45088868101029, "flow_matching_loss": 0.06970686912536621, "grad_norm": 0.1693524271249771, "invalid_tail_samples": 22.3, "learning_rate": 9.962010857533514e-05, "loss": 0.0804, "positive_teacher_pairs": 27198.1, "relation_loss": 0.010651277657598258, "selected_pairs": 27198.1, "step": 2620, "student_distance_mean": 518.8926574707032, "teacher_distance_mean": 0.8506654500961304, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.010651277657598258, "weighted_relation_loss": 0.010651277657598258 }, { "action_query_batch_std": 9.14419584274292, "action_query_norm": 422.05726013183596, "action_relation_loss": 0.010974450595676899, "auxiliary_loss_weight": 1.0, "epoch": 2.460243217960711, "flow_matching_loss": 0.07190168425440788, "grad_norm": 0.14925096929073334, "invalid_tail_samples": 24.7, "learning_rate": 9.961329720345493e-05, "loss": 0.0829, "positive_teacher_pairs": 26640.0, "relation_loss": 0.010974450595676899, "selected_pairs": 26640.0, "step": 2630, "student_distance_mean": 516.5640045166016, "teacher_distance_mean": 0.85375816822052, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.010974450595676899, "weighted_relation_loss": 0.010974450595676899 }, { "action_query_batch_std": 9.28924913406372, "action_query_norm": 431.8761779785156, "action_relation_loss": 0.0104580819606781, "auxiliary_loss_weight": 1.0, "epoch": 2.469597754911132, "flow_matching_loss": 0.07124968990683556, "grad_norm": 0.2071225792169571, "invalid_tail_samples": 22.3, "learning_rate": 9.96064255467404e-05, "loss": 0.0817, "positive_teacher_pairs": 27201.6, "relation_loss": 0.0104580819606781, "selected_pairs": 27201.6, "step": 2640, "student_distance_mean": 525.8922607421875, "teacher_distance_mean": 0.85857293009758, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0104580819606781, "weighted_relation_loss": 0.0104580819606781 }, { "action_query_batch_std": 9.405673408508301, "action_query_norm": 434.51320190429686, "action_relation_loss": 0.010328327491879463, "auxiliary_loss_weight": 1.0, "epoch": 2.4789522918615527, "flow_matching_loss": 0.06814789026975632, "grad_norm": 0.18706727027893066, "invalid_tail_samples": 22.2, "learning_rate": 9.959949361354126e-05, "loss": 0.0785, "positive_teacher_pairs": 27217.7, "relation_loss": 0.010328327491879463, "selected_pairs": 27217.7, "step": 2650, "student_distance_mean": 530.6720397949218, "teacher_distance_mean": 0.8559734761714936, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.010328327491879463, "weighted_relation_loss": 0.010328327491879463 }, { "action_query_batch_std": 9.551069641113282, "action_query_norm": 437.9488098144531, "action_relation_loss": 0.010465620551258326, "auxiliary_loss_weight": 1.0, "epoch": 2.488306828811974, "flow_matching_loss": 0.06954067088663578, "grad_norm": 0.21238775551319122, "invalid_tail_samples": 26.3, "learning_rate": 9.959250141228045e-05, "loss": 0.08, "positive_teacher_pairs": 26270.9, "relation_loss": 0.010465620551258326, "selected_pairs": 26270.9, "step": 2660, "student_distance_mean": 540.1966003417969, "teacher_distance_mean": 0.861570131778717, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.010465620551258326, "weighted_relation_loss": 0.010465620551258326 }, { "action_query_batch_std": 9.447887325286866, "action_query_norm": 436.65773010253906, "action_relation_loss": 0.010192689299583436, "auxiliary_loss_weight": 1.0, "epoch": 2.497661365762395, "flow_matching_loss": 0.06873300112783909, "grad_norm": 0.178481787443161, "invalid_tail_samples": 23.5, "learning_rate": 9.958544895145414e-05, "loss": 0.0789, "positive_teacher_pairs": 26920.5, "relation_loss": 0.010192689299583436, "selected_pairs": 26920.5, "step": 2670, "student_distance_mean": 535.2081481933594, "teacher_distance_mean": 0.8573259472846985, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.010192689299583436, "weighted_relation_loss": 0.010192689299583436 }, { "action_query_batch_std": 9.365710353851318, "action_query_norm": 431.18230590820315, "action_relation_loss": 0.010635025706142187, "auxiliary_loss_weight": 1.0, "epoch": 2.5070159027128156, "flow_matching_loss": 0.0682832095772028, "grad_norm": 0.22218520939350128, "invalid_tail_samples": 22.1, "learning_rate": 9.957833623963177e-05, "loss": 0.0789, "positive_teacher_pairs": 27243.8, "relation_loss": 0.010635025706142187, "selected_pairs": 27243.8, "step": 2680, "student_distance_mean": 529.1917907714844, "teacher_distance_mean": 0.8494499027729034, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.010635025706142187, "weighted_relation_loss": 0.010635025706142187 }, { "action_query_batch_std": 9.586129856109618, "action_query_norm": 441.91236267089846, "action_relation_loss": 0.01013027410954237, "auxiliary_loss_weight": 1.0, "epoch": 2.5163704396632367, "flow_matching_loss": 0.06801053211092949, "grad_norm": 0.18866951763629913, "invalid_tail_samples": 21.3, "learning_rate": 9.957116328545593e-05, "loss": 0.0781, "positive_teacher_pairs": 27427.9, "relation_loss": 0.01013027410954237, "selected_pairs": 27427.9, "step": 2690, "student_distance_mean": 543.5324890136719, "teacher_distance_mean": 0.8611037373542786, "valid_action_samples": 234.7, "weighted_auxiliary_loss": 0.01013027410954237, "weighted_relation_loss": 0.01013027410954237 }, { "action_query_batch_std": 9.449714851379394, "action_query_norm": 441.3247039794922, "action_relation_loss": 0.010518714506179094, "auxiliary_loss_weight": 1.0, "epoch": 2.525724976613658, "flow_matching_loss": 0.06863764338195324, "grad_norm": 0.2860105037689209, "invalid_tail_samples": 24.5, "learning_rate": 9.956393009764244e-05, "loss": 0.0792, "positive_teacher_pairs": 26687.0, "relation_loss": 0.010518714506179094, "selected_pairs": 26687.0, "step": 2700, "student_distance_mean": 535.3900573730468, "teacher_distance_mean": 0.852560305595398, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.010518714506179094, "weighted_relation_loss": 0.010518714506179094 }, { "action_query_batch_std": 9.525706005096435, "action_query_norm": 446.1406585693359, "action_relation_loss": 0.010335399303585291, "auxiliary_loss_weight": 1.0, "epoch": 2.5350795135640785, "flow_matching_loss": 0.070658890157938, "grad_norm": 0.2005637139081955, "invalid_tail_samples": 21.9, "learning_rate": 9.955663668498032e-05, "loss": 0.081, "positive_teacher_pairs": 27298.0, "relation_loss": 0.010335399303585291, "selected_pairs": 27298.0, "step": 2710, "student_distance_mean": 540.4940246582031, "teacher_distance_mean": 0.8563046932220459, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.010335399303585291, "weighted_relation_loss": 0.010335399303585291 }, { "action_query_batch_std": 9.361022567749023, "action_query_norm": 436.4105926513672, "action_relation_loss": 0.010547984018921852, "auxiliary_loss_weight": 1.0, "epoch": 2.5444340505144996, "flow_matching_loss": 0.07015922144055367, "grad_norm": 0.17349958419799805, "invalid_tail_samples": 23.6, "learning_rate": 9.954928305633173e-05, "loss": 0.0807, "positive_teacher_pairs": 26898.4, "relation_loss": 0.010547984018921852, "selected_pairs": 26898.4, "step": 2720, "student_distance_mean": 530.2240661621094, "teacher_distance_mean": 0.8555899739265442, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.010547984018921852, "weighted_relation_loss": 0.010547984018921852 }, { "action_query_batch_std": 9.659686374664307, "action_query_norm": 448.2896331787109, "action_relation_loss": 0.010764442011713981, "auxiliary_loss_weight": 1.0, "epoch": 2.55378858746492, "flow_matching_loss": 0.06634327210485935, "grad_norm": 0.18480709195137024, "invalid_tail_samples": 23.6, "learning_rate": 9.954186922063204e-05, "loss": 0.0771, "positive_teacher_pairs": 26890.7, "relation_loss": 0.010764442011713981, "selected_pairs": 26890.7, "step": 2730, "student_distance_mean": 549.0752136230469, "teacher_distance_mean": 0.8625764906406402, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.010764442011713981, "weighted_relation_loss": 0.010764442011713981 }, { "action_query_batch_std": 9.714766120910644, "action_query_norm": 449.68877868652345, "action_relation_loss": 0.010571086127310992, "auxiliary_loss_weight": 1.0, "epoch": 2.5631431244153413, "flow_matching_loss": 0.06714197024703025, "grad_norm": 0.2541513442993164, "invalid_tail_samples": 23.9, "learning_rate": 9.953439518688974e-05, "loss": 0.0777, "positive_teacher_pairs": 26826.6, "relation_loss": 0.010571086127310992, "selected_pairs": 26826.6, "step": 2740, "student_distance_mean": 547.7727416992187, "teacher_distance_mean": 0.8528412163257599, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.010571086127310992, "weighted_relation_loss": 0.010571086127310992 }, { "action_query_batch_std": 9.68304090499878, "action_query_norm": 448.2998291015625, "action_relation_loss": 0.010984602104872464, "auxiliary_loss_weight": 1.0, "epoch": 2.5724976613657624, "flow_matching_loss": 0.07050277777016163, "grad_norm": 0.1820874810218811, "invalid_tail_samples": 25.6, "learning_rate": 9.952686096418652e-05, "loss": 0.0815, "positive_teacher_pairs": 26439.8, "relation_loss": 0.010984602104872464, "selected_pairs": 26439.8, "step": 2750, "student_distance_mean": 550.3870727539063, "teacher_distance_mean": 0.8604168832302094, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.010984602104872464, "weighted_relation_loss": 0.010984602104872464 }, { "action_query_batch_std": 9.359696769714356, "action_query_norm": 435.5222137451172, "action_relation_loss": 0.010417536180466414, "auxiliary_loss_weight": 1.0, "epoch": 2.5818521983161835, "flow_matching_loss": 0.06746739819645882, "grad_norm": 0.21639962494373322, "invalid_tail_samples": 26.6, "learning_rate": 9.951926656167714e-05, "loss": 0.0779, "positive_teacher_pairs": 26209.9, "relation_loss": 0.010417536180466414, "selected_pairs": 26209.9, "step": 2760, "student_distance_mean": 531.4384216308594, "teacher_distance_mean": 0.8552681982517243, "valid_action_samples": 229.4, "weighted_auxiliary_loss": 0.010417536180466414, "weighted_relation_loss": 0.010417536180466414 }, { "action_query_batch_std": 9.28503713607788, "action_query_norm": 433.23256225585936, "action_relation_loss": 0.010187213961035013, "auxiliary_loss_weight": 1.0, "epoch": 2.591206735266604, "flow_matching_loss": 0.06713397987186909, "grad_norm": 0.16764631867408752, "invalid_tail_samples": 22.4, "learning_rate": 9.951161198858953e-05, "loss": 0.0773, "positive_teacher_pairs": 27171.9, "relation_loss": 0.010187213961035013, "selected_pairs": 27171.9, "step": 2770, "student_distance_mean": 526.8660552978515, "teacher_distance_mean": 0.854138720035553, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.010187213961035013, "weighted_relation_loss": 0.010187213961035013 }, { "action_query_batch_std": 9.463657569885253, "action_query_norm": 437.2804809570313, "action_relation_loss": 0.010374708287417888, "auxiliary_loss_weight": 1.0, "epoch": 2.6005612722170253, "flow_matching_loss": 0.06782550215721131, "grad_norm": 0.17964744567871094, "invalid_tail_samples": 25.7, "learning_rate": 9.950389725422471e-05, "loss": 0.0782, "positive_teacher_pairs": 26412.3, "relation_loss": 0.010374708287417888, "selected_pairs": 26412.3, "step": 2780, "student_distance_mean": 538.9919860839843, "teacher_distance_mean": 0.8623916268348694, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.010374708287417888, "weighted_relation_loss": 0.010374708287417888 }, { "action_query_batch_std": 9.474896907806396, "action_query_norm": 439.9205322265625, "action_relation_loss": 0.010196537151932717, "auxiliary_loss_weight": 1.0, "epoch": 2.6099158091674464, "flow_matching_loss": 0.067941714823246, "grad_norm": 0.17822711169719696, "invalid_tail_samples": 25.4, "learning_rate": 9.949612236795682e-05, "loss": 0.0781, "positive_teacher_pairs": 26475.2, "relation_loss": 0.010196537151932717, "selected_pairs": 26475.2, "step": 2790, "student_distance_mean": 537.6175842285156, "teacher_distance_mean": 0.8532963216304779, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.010196537151932717, "weighted_relation_loss": 0.010196537151932717 }, { "action_query_batch_std": 9.622060966491699, "action_query_norm": 445.9388946533203, "action_relation_loss": 0.010317998472601175, "auxiliary_loss_weight": 1.0, "epoch": 2.619270346117867, "flow_matching_loss": 0.0712417408823967, "grad_norm": 0.23082640767097473, "invalid_tail_samples": 23.3, "learning_rate": 9.948828733923305e-05, "loss": 0.0816, "positive_teacher_pairs": 26981.5, "relation_loss": 0.010317998472601175, "selected_pairs": 26981.5, "step": 2800, "student_distance_mean": 543.6850158691407, "teacher_distance_mean": 0.8529873847961426, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.010317998472601175, "weighted_relation_loss": 0.010317998472601175 }, { "action_query_batch_std": 9.585950756072998, "action_query_norm": 445.7609039306641, "action_relation_loss": 0.010772965289652348, "auxiliary_loss_weight": 1.0, "epoch": 2.628624883068288, "flow_matching_loss": 0.07166187651455402, "grad_norm": 0.24784764647483826, "invalid_tail_samples": 24.1, "learning_rate": 9.948039217757374e-05, "loss": 0.0824, "positive_teacher_pairs": 26777.2, "relation_loss": 0.010772965289652348, "selected_pairs": 26777.2, "step": 2810, "student_distance_mean": 542.3987915039063, "teacher_distance_mean": 0.8505622625350953, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.010772965289652348, "weighted_relation_loss": 0.010772965289652348 }, { "action_query_batch_std": 9.479040908813477, "action_query_norm": 439.115185546875, "action_relation_loss": 0.010000360384583473, "auxiliary_loss_weight": 1.0, "epoch": 2.637979420018709, "flow_matching_loss": 0.06969752945005894, "grad_norm": 0.23842446506023407, "invalid_tail_samples": 23.8, "learning_rate": 9.947243689257225e-05, "loss": 0.0797, "positive_teacher_pairs": 26851.5, "relation_loss": 0.010000360384583473, "selected_pairs": 26851.5, "step": 2820, "student_distance_mean": 536.4288787841797, "teacher_distance_mean": 0.842516976594925, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.010000360384583473, "weighted_relation_loss": 0.010000360384583473 }, { "action_query_batch_std": 9.617588901519776, "action_query_norm": 448.1476318359375, "action_relation_loss": 0.010230259131640195, "auxiliary_loss_weight": 1.0, "epoch": 2.64733395696913, "flow_matching_loss": 0.06705829426646233, "grad_norm": 0.20202495157718658, "invalid_tail_samples": 22.7, "learning_rate": 9.946442149389497e-05, "loss": 0.0773, "positive_teacher_pairs": 27103.5, "relation_loss": 0.010230259131640195, "selected_pairs": 27103.5, "step": 2830, "student_distance_mean": 544.1144958496094, "teacher_distance_mean": 0.8510023772716522, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.010230259131640195, "weighted_relation_loss": 0.010230259131640195 }, { "action_query_batch_std": 9.853282642364501, "action_query_norm": 458.55009765625, "action_relation_loss": 0.009923309925943613, "auxiliary_loss_weight": 1.0, "epoch": 2.656688493919551, "flow_matching_loss": 0.06815797165036201, "grad_norm": 0.15226365625858307, "invalid_tail_samples": 23.3, "learning_rate": 9.945634599128139e-05, "loss": 0.0781, "positive_teacher_pairs": 26966.8, "relation_loss": 0.009923309925943613, "selected_pairs": 26966.8, "step": 2840, "student_distance_mean": 557.8621826171875, "teacher_distance_mean": 0.8638333439826965, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.009923309925943613, "weighted_relation_loss": 0.009923309925943613 }, { "action_query_batch_std": 9.59588327407837, "action_query_norm": 444.2348602294922, "action_relation_loss": 0.01021510800346732, "auxiliary_loss_weight": 1.0, "epoch": 2.666043030869972, "flow_matching_loss": 0.07046062424778939, "grad_norm": 0.1779046505689621, "invalid_tail_samples": 23.8, "learning_rate": 9.944821039454402e-05, "loss": 0.0807, "positive_teacher_pairs": 26851.4, "relation_loss": 0.01021510800346732, "selected_pairs": 26851.4, "step": 2850, "student_distance_mean": 543.5665100097656, "teacher_distance_mean": 0.8455385982990264, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.01021510800346732, "weighted_relation_loss": 0.01021510800346732 }, { "action_query_batch_std": 9.75112533569336, "action_query_norm": 448.9607757568359, "action_relation_loss": 0.009868457261472941, "auxiliary_loss_weight": 1.0, "epoch": 2.6753975678203927, "flow_matching_loss": 0.06715695187449455, "grad_norm": 0.1783071607351303, "invalid_tail_samples": 25.7, "learning_rate": 9.944001471356835e-05, "loss": 0.077, "positive_teacher_pairs": 26412.8, "relation_loss": 0.009868457261472941, "selected_pairs": 26412.8, "step": 2860, "student_distance_mean": 554.9674743652344, "teacher_distance_mean": 0.8566486120224, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.009868457261472941, "weighted_relation_loss": 0.009868457261472941 }, { "action_query_batch_std": 9.829680919647217, "action_query_norm": 456.2847045898437, "action_relation_loss": 0.010261150356382132, "auxiliary_loss_weight": 1.0, "epoch": 2.684752104770814, "flow_matching_loss": 0.06985420025885106, "grad_norm": 0.23144537210464478, "invalid_tail_samples": 23.8, "learning_rate": 9.94317589583129e-05, "loss": 0.0801, "positive_teacher_pairs": 26855.5, "relation_loss": 0.010261150356382132, "selected_pairs": 26855.5, "step": 2870, "student_distance_mean": 559.5161560058593, "teacher_distance_mean": 0.8563012778759003, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.010261150356382132, "weighted_relation_loss": 0.010261150356382132 }, { "action_query_batch_std": 9.643744277954102, "action_query_norm": 449.0804870605469, "action_relation_loss": 0.01065946714952588, "auxiliary_loss_weight": 1.0, "epoch": 2.694106641721235, "flow_matching_loss": 0.06684706918895245, "grad_norm": 0.24687650799751282, "invalid_tail_samples": 23.2, "learning_rate": 9.942344313880922e-05, "loss": 0.0775, "positive_teacher_pairs": 26990.4, "relation_loss": 0.01065946714952588, "selected_pairs": 26990.4, "step": 2880, "student_distance_mean": 547.829248046875, "teacher_distance_mean": 0.8522884905338287, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.01065946714952588, "weighted_relation_loss": 0.01065946714952588 }, { "action_query_batch_std": 9.668075370788575, "action_query_norm": 455.7994903564453, "action_relation_loss": 0.010318092815577985, "auxiliary_loss_weight": 1.0, "epoch": 2.703461178671656, "flow_matching_loss": 0.06988479979336262, "grad_norm": 0.23169736564159393, "invalid_tail_samples": 23.8, "learning_rate": 9.941506726516179e-05, "loss": 0.0802, "positive_teacher_pairs": 26854.9, "relation_loss": 0.010318092815577985, "selected_pairs": 26854.9, "step": 2890, "student_distance_mean": 549.5864929199219, "teacher_distance_mean": 0.850574254989624, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.010318092815577985, "weighted_relation_loss": 0.010318092815577985 }, { "action_query_batch_std": 9.765251064300537, "action_query_norm": 457.7448394775391, "action_relation_loss": 0.009902529511600732, "auxiliary_loss_weight": 1.0, "epoch": 2.7128157156220767, "flow_matching_loss": 0.06846042908728123, "grad_norm": 0.1959669440984726, "invalid_tail_samples": 22.5, "learning_rate": 9.94066313475481e-05, "loss": 0.0784, "positive_teacher_pairs": 27153.3, "relation_loss": 0.009902529511600732, "selected_pairs": 27153.3, "step": 2900, "student_distance_mean": 553.8680480957031, "teacher_distance_mean": 0.8560537457466125, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.009902529511600732, "weighted_relation_loss": 0.009902529511600732 }, { "action_query_batch_std": 9.56885747909546, "action_query_norm": 448.81493225097654, "action_relation_loss": 0.010473126173019409, "auxiliary_loss_weight": 1.0, "epoch": 2.722170252572498, "flow_matching_loss": 0.07130044288933277, "grad_norm": 0.18365982174873352, "invalid_tail_samples": 22.8, "learning_rate": 9.939813539621857e-05, "loss": 0.0818, "positive_teacher_pairs": 27087.3, "relation_loss": 0.010473126173019409, "selected_pairs": 27087.3, "step": 2910, "student_distance_mean": 542.8009887695313, "teacher_distance_mean": 0.8467543125152588, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.010473126173019409, "weighted_relation_loss": 0.010473126173019409 }, { "action_query_batch_std": 9.614165592193604, "action_query_norm": 448.44590148925784, "action_relation_loss": 0.01038067927584052, "auxiliary_loss_weight": 1.0, "epoch": 2.7315247895229184, "flow_matching_loss": 0.06884203329682351, "grad_norm": 0.20730169117450714, "invalid_tail_samples": 22.1, "learning_rate": 9.93895794214966e-05, "loss": 0.0792, "positive_teacher_pairs": 27243.4, "relation_loss": 0.01038067927584052, "selected_pairs": 27243.4, "step": 2920, "student_distance_mean": 546.5015075683593, "teacher_distance_mean": 0.8537183940410614, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.01038067927584052, "weighted_relation_loss": 0.01038067927584052 }, { "action_query_batch_std": 9.659425354003906, "action_query_norm": 449.3218078613281, "action_relation_loss": 0.010264295525848866, "auxiliary_loss_weight": 1.0, "epoch": 2.7408793264733395, "flow_matching_loss": 0.06654670760035515, "grad_norm": 0.3302265405654907, "invalid_tail_samples": 20.9, "learning_rate": 9.938096343377852e-05, "loss": 0.0768, "positive_teacher_pairs": 27533.1, "relation_loss": 0.010264295525848866, "selected_pairs": 27533.1, "step": 2930, "student_distance_mean": 548.4728271484375, "teacher_distance_mean": 0.856350588798523, "valid_action_samples": 235.1, "weighted_auxiliary_loss": 0.010264295525848866, "weighted_relation_loss": 0.010264295525848866 }, { "action_query_batch_std": 9.8926362991333, "action_query_norm": 461.3271881103516, "action_relation_loss": 0.010113165341317653, "auxiliary_loss_weight": 1.0, "epoch": 2.7502338634237606, "flow_matching_loss": 0.06670077666640281, "grad_norm": 0.2517249882221222, "invalid_tail_samples": 22.8, "learning_rate": 9.937228744353353e-05, "loss": 0.0768, "positive_teacher_pairs": 27085.0, "relation_loss": 0.010113165341317653, "selected_pairs": 27085.0, "step": 2940, "student_distance_mean": 562.180517578125, "teacher_distance_mean": 0.8527253091335296, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.010113165341317653, "weighted_relation_loss": 0.010113165341317653 }, { "action_query_batch_std": 9.796531295776367, "action_query_norm": 459.49717407226564, "action_relation_loss": 0.01075225118547678, "auxiliary_loss_weight": 1.0, "epoch": 2.7595884003741817, "flow_matching_loss": 0.06722379922866821, "grad_norm": 0.201526939868927, "invalid_tail_samples": 24.4, "learning_rate": 9.936355146130379e-05, "loss": 0.078, "positive_teacher_pairs": 26713.4, "relation_loss": 0.01075225118547678, "selected_pairs": 26713.4, "step": 2950, "student_distance_mean": 555.821875, "teacher_distance_mean": 0.8461726844310761, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.01075225118547678, "weighted_relation_loss": 0.01075225118547678 }, { "action_query_batch_std": 9.8718412399292, "action_query_norm": 460.79994812011716, "action_relation_loss": 0.009473383985459804, "auxiliary_loss_weight": 1.0, "epoch": 2.7689429373246024, "flow_matching_loss": 0.07058334648609162, "grad_norm": 0.18202626705169678, "invalid_tail_samples": 23.8, "learning_rate": 9.935475549770435e-05, "loss": 0.0801, "positive_teacher_pairs": 26845.7, "relation_loss": 0.009473383985459804, "selected_pairs": 26845.7, "step": 2960, "student_distance_mean": 558.1138854980469, "teacher_distance_mean": 0.8578133165836335, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.009473383985459804, "weighted_relation_loss": 0.009473383985459804 }, { "action_query_batch_std": 9.631606101989746, "action_query_norm": 448.10509338378904, "action_relation_loss": 0.010450110863894224, "auxiliary_loss_weight": 1.0, "epoch": 2.7782974742750235, "flow_matching_loss": 0.06807675957679749, "grad_norm": 0.21607163548469543, "invalid_tail_samples": 23.4, "learning_rate": 9.934589956342315e-05, "loss": 0.0785, "positive_teacher_pairs": 26941.4, "relation_loss": 0.010450110863894224, "selected_pairs": 26941.4, "step": 2970, "student_distance_mean": 545.7597045898438, "teacher_distance_mean": 0.8586684823036194, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.010450110863894224, "weighted_relation_loss": 0.010450110863894224 }, { "action_query_batch_std": 9.783702373504639, "action_query_norm": 455.11708068847656, "action_relation_loss": 0.010166362579911947, "auxiliary_loss_weight": 1.0, "epoch": 2.787652011225444, "flow_matching_loss": 0.069898422062397, "grad_norm": 0.24414512515068054, "invalid_tail_samples": 24.8, "learning_rate": 9.933698366922093e-05, "loss": 0.0801, "positive_teacher_pairs": 26626.7, "relation_loss": 0.010166362579911947, "selected_pairs": 26626.7, "step": 2980, "student_distance_mean": 550.9181335449218, "teacher_distance_mean": 0.8479609966278077, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.010166362579911947, "weighted_relation_loss": 0.010166362579911947 }, { "action_query_batch_std": 9.870730686187745, "action_query_norm": 458.4147155761719, "action_relation_loss": 0.010515512246638537, "auxiliary_loss_weight": 1.0, "epoch": 2.7970065481758652, "flow_matching_loss": 0.07111872062087059, "grad_norm": 0.2518541216850281, "invalid_tail_samples": 22.9, "learning_rate": 9.93280078259314e-05, "loss": 0.0816, "positive_teacher_pairs": 27068.2, "relation_loss": 0.010515512246638537, "selected_pairs": 27068.2, "step": 2990, "student_distance_mean": 555.6826965332032, "teacher_distance_mean": 0.8427201211452484, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.010515512246638537, "weighted_relation_loss": 0.010515512246638537 }, { "action_query_batch_std": 10.011138343811036, "action_query_norm": 464.9932037353516, "action_relation_loss": 0.009894659463316201, "auxiliary_loss_weight": 1.0, "epoch": 2.8063610851262863, "flow_matching_loss": 0.06982937902212143, "grad_norm": 0.19373440742492676, "invalid_tail_samples": 22.6, "learning_rate": 9.931897204446104e-05, "loss": 0.0797, "positive_teacher_pairs": 27126.1, "relation_loss": 0.009894659463316201, "selected_pairs": 27126.1, "step": 3000, "student_distance_mean": 565.2856750488281, "teacher_distance_mean": 0.8580991208553315, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.009894659463316201, "weighted_relation_loss": 0.009894659463316201 }, { "action_query_batch_std": 10.049264240264893, "action_query_norm": 466.6423645019531, "action_relation_loss": 0.009984001610428095, "auxiliary_loss_weight": 1.0, "epoch": 2.8157156220767074, "flow_matching_loss": 0.06742947213351727, "grad_norm": 0.21509432792663574, "invalid_tail_samples": 25.0, "learning_rate": 9.930987633578915e-05, "loss": 0.0774, "positive_teacher_pairs": 26575.7, "relation_loss": 0.009984001610428095, "selected_pairs": 26575.7, "step": 3010, "student_distance_mean": 571.9712829589844, "teacher_distance_mean": 0.8693503141403198, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.009984001610428095, "weighted_relation_loss": 0.009984001610428095 }, { "action_query_batch_std": 9.884734630584717, "action_query_norm": 459.4258605957031, "action_relation_loss": 0.010009730514138938, "auxiliary_loss_weight": 1.0, "epoch": 2.825070159027128, "flow_matching_loss": 0.06784634217619896, "grad_norm": 0.15488234162330627, "invalid_tail_samples": 26.2, "learning_rate": 9.93007207109679e-05, "loss": 0.0779, "positive_teacher_pairs": 26312.2, "relation_loss": 0.010009730514138938, "selected_pairs": 26312.2, "step": 3020, "student_distance_mean": 561.4296936035156, "teacher_distance_mean": 0.8579997062683106, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.010009730514138938, "weighted_relation_loss": 0.010009730514138938 }, { "action_query_batch_std": 9.941954231262207, "action_query_norm": 463.954052734375, "action_relation_loss": 0.00993438446894288, "auxiliary_loss_weight": 1.0, "epoch": 2.834424695977549, "flow_matching_loss": 0.06900209486484528, "grad_norm": 0.187167227268219, "invalid_tail_samples": 24.9, "learning_rate": 9.929150518112224e-05, "loss": 0.0789, "positive_teacher_pairs": 26597.0, "relation_loss": 0.00993438446894288, "selected_pairs": 26597.0, "step": 3030, "student_distance_mean": 564.557275390625, "teacher_distance_mean": 0.8588039755821228, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.00993438446894288, "weighted_relation_loss": 0.00993438446894288 }, { "action_query_batch_std": 9.949934673309325, "action_query_norm": 466.6696533203125, "action_relation_loss": 0.009935797378420829, "auxiliary_loss_weight": 1.0, "epoch": 2.84377923292797, "flow_matching_loss": 0.06722557693719863, "grad_norm": 0.16725337505340576, "invalid_tail_samples": 21.4, "learning_rate": 9.928222975744991e-05, "loss": 0.0772, "positive_teacher_pairs": 27404.9, "relation_loss": 0.009935797378420829, "selected_pairs": 27404.9, "step": 3040, "student_distance_mean": 564.1065979003906, "teacher_distance_mean": 0.8489076197147369, "valid_action_samples": 234.6, "weighted_auxiliary_loss": 0.009935797378420829, "weighted_relation_loss": 0.009935797378420829 }, { "action_query_batch_std": 9.900324535369872, "action_query_norm": 461.6391662597656, "action_relation_loss": 0.00938336318358779, "auxiliary_loss_weight": 1.0, "epoch": 2.853133769878391, "flow_matching_loss": 0.06706357412040234, "grad_norm": 0.17995195090770721, "invalid_tail_samples": 23.9, "learning_rate": 9.92728944512214e-05, "loss": 0.0764, "positive_teacher_pairs": 26829.9, "relation_loss": 0.00938336318358779, "selected_pairs": 26829.9, "step": 3050, "student_distance_mean": 563.3787841796875, "teacher_distance_mean": 0.8596603393554687, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.00938336318358779, "weighted_relation_loss": 0.00938336318358779 }, { "action_query_batch_std": 9.928770351409913, "action_query_norm": 461.7056457519531, "action_relation_loss": 0.010162187833338976, "auxiliary_loss_weight": 1.0, "epoch": 2.862488306828812, "flow_matching_loss": 0.06905032023787498, "grad_norm": 0.1421731412410736, "invalid_tail_samples": 24.3, "learning_rate": 9.926349927378001e-05, "loss": 0.0792, "positive_teacher_pairs": 26735.0, "relation_loss": 0.010162187833338976, "selected_pairs": 26735.0, "step": 3060, "student_distance_mean": 562.4447265625, "teacher_distance_mean": 0.8537364482879639, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.010162187833338976, "weighted_relation_loss": 0.010162187833338976 }, { "action_query_batch_std": 10.198553657531738, "action_query_norm": 468.4392059326172, "action_relation_loss": 0.00952435340732336, "auxiliary_loss_weight": 1.0, "epoch": 2.871842843779233, "flow_matching_loss": 0.06523206420242786, "grad_norm": 0.15064100921154022, "invalid_tail_samples": 25.3, "learning_rate": 9.925404423654174e-05, "loss": 0.0748, "positive_teacher_pairs": 26500.2, "relation_loss": 0.00952435340732336, "selected_pairs": 26500.2, "step": 3070, "student_distance_mean": 575.3356506347657, "teacher_distance_mean": 0.8580091118812561, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.00952435340732336, "weighted_relation_loss": 0.00952435340732336 }, { "action_query_batch_std": 10.166518783569336, "action_query_norm": 467.9123016357422, "action_relation_loss": 0.009804924484342337, "auxiliary_loss_weight": 1.0, "epoch": 2.881197380729654, "flow_matching_loss": 0.0686442170292139, "grad_norm": 0.19479478895664215, "invalid_tail_samples": 24.2, "learning_rate": 9.924452935099537e-05, "loss": 0.0784, "positive_teacher_pairs": 26760.8, "relation_loss": 0.009804924484342337, "selected_pairs": 26760.8, "step": 3080, "student_distance_mean": 574.9734313964843, "teacher_distance_mean": 0.8580680906772613, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.009804924484342337, "weighted_relation_loss": 0.009804924484342337 }, { "action_query_batch_std": 10.069078636169433, "action_query_norm": 468.30841064453125, "action_relation_loss": 0.00976940868422389, "auxiliary_loss_weight": 1.0, "epoch": 2.890551917680075, "flow_matching_loss": 0.06470592170953751, "grad_norm": 0.20266903936862946, "invalid_tail_samples": 24.2, "learning_rate": 9.92349546287024e-05, "loss": 0.0745, "positive_teacher_pairs": 26761.6, "relation_loss": 0.00976940868422389, "selected_pairs": 26761.6, "step": 3090, "student_distance_mean": 572.2539916992188, "teacher_distance_mean": 0.8541542410850524, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.00976940868422389, "weighted_relation_loss": 0.00976940868422389 }, { "action_query_batch_std": 10.197695922851562, "action_query_norm": 468.9159454345703, "action_relation_loss": 0.010018527042120695, "auxiliary_loss_weight": 1.0, "epoch": 2.8999064546304956, "flow_matching_loss": 0.06515831798315048, "grad_norm": 0.15134146809577942, "invalid_tail_samples": 24.9, "learning_rate": 9.9225320081297e-05, "loss": 0.0752, "positive_teacher_pairs": 26596.9, "relation_loss": 0.010018527042120695, "selected_pairs": 26596.9, "step": 3100, "student_distance_mean": 578.55048828125, "teacher_distance_mean": 0.8619672238826752, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.010018527042120695, "weighted_relation_loss": 0.010018527042120695 }, { "action_query_batch_std": 10.129713916778565, "action_query_norm": 469.1338134765625, "action_relation_loss": 0.01035372270271182, "auxiliary_loss_weight": 1.0, "epoch": 2.9092609915809167, "flow_matching_loss": 0.06695390492677689, "grad_norm": 0.19944724440574646, "invalid_tail_samples": 23.9, "learning_rate": 9.921562572048606e-05, "loss": 0.0773, "positive_teacher_pairs": 26825.8, "relation_loss": 0.01035372270271182, "selected_pairs": 26825.8, "step": 3110, "student_distance_mean": 572.4380126953125, "teacher_distance_mean": 0.8547627389431, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.01035372270271182, "weighted_relation_loss": 0.01035372270271182 }, { "action_query_batch_std": 10.096638774871826, "action_query_norm": 469.194140625, "action_relation_loss": 0.0095046017318964, "auxiliary_loss_weight": 1.0, "epoch": 2.9186155285313378, "flow_matching_loss": 0.06527426764369011, "grad_norm": 0.18990662693977356, "invalid_tail_samples": 23.5, "learning_rate": 9.920587155804913e-05, "loss": 0.0748, "positive_teacher_pairs": 26923.6, "relation_loss": 0.0095046017318964, "selected_pairs": 26923.6, "step": 3120, "student_distance_mean": 573.110888671875, "teacher_distance_mean": 0.8582189977169037, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0095046017318964, "weighted_relation_loss": 0.0095046017318964 }, { "action_query_batch_std": 10.046384048461913, "action_query_norm": 464.584423828125, "action_relation_loss": 0.009799786191433669, "auxiliary_loss_weight": 1.0, "epoch": 2.927970065481759, "flow_matching_loss": 0.06661862693727016, "grad_norm": 0.1934075653553009, "invalid_tail_samples": 22.5, "learning_rate": 9.919605760583845e-05, "loss": 0.0764, "positive_teacher_pairs": 27149.6, "relation_loss": 0.009799786191433669, "selected_pairs": 27149.6, "step": 3130, "student_distance_mean": 566.1311828613282, "teacher_distance_mean": 0.8549654245376587, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.009799786191433669, "weighted_relation_loss": 0.009799786191433669 }, { "action_query_batch_std": 10.26738338470459, "action_query_norm": 477.8590789794922, "action_relation_loss": 0.01022525541484356, "auxiliary_loss_weight": 1.0, "epoch": 2.9373246024321795, "flow_matching_loss": 0.06394646875560284, "grad_norm": 0.18936826288700104, "invalid_tail_samples": 24.0, "learning_rate": 9.91861838757789e-05, "loss": 0.0742, "positive_teacher_pairs": 26799.0, "relation_loss": 0.01022525541484356, "selected_pairs": 26799.0, "step": 3140, "student_distance_mean": 582.2674133300782, "teacher_distance_mean": 0.848838883638382, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.01022525541484356, "weighted_relation_loss": 0.01022525541484356 }, { "action_query_batch_std": 10.352199077606201, "action_query_norm": 480.55206909179685, "action_relation_loss": 0.010093637835234403, "auxiliary_loss_weight": 1.0, "epoch": 2.9466791393826006, "flow_matching_loss": 0.06637999266386033, "grad_norm": 0.2504115700721741, "invalid_tail_samples": 24.1, "learning_rate": 9.917625037986798e-05, "loss": 0.0765, "positive_teacher_pairs": 26776.1, "relation_loss": 0.010093637835234403, "selected_pairs": 26776.1, "step": 3150, "student_distance_mean": 586.3674682617187, "teacher_distance_mean": 0.8568839013576508, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.010093637835234403, "weighted_relation_loss": 0.010093637835234403 }, { "action_query_batch_std": 10.254201507568359, "action_query_norm": 471.34556579589844, "action_relation_loss": 0.010059550311416388, "auxiliary_loss_weight": 1.0, "epoch": 2.9560336763330213, "flow_matching_loss": 0.06528283730149269, "grad_norm": 0.2013443410396576, "invalid_tail_samples": 24.1, "learning_rate": 9.916625713017583e-05, "loss": 0.0753, "positive_teacher_pairs": 26776.4, "relation_loss": 0.010059550311416388, "selected_pairs": 26776.4, "step": 3160, "student_distance_mean": 582.23212890625, "teacher_distance_mean": 0.8513672113418579, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.010059550311416388, "weighted_relation_loss": 0.010059550311416388 }, { "action_query_batch_std": 10.144214725494384, "action_query_norm": 467.8574157714844, "action_relation_loss": 0.00927608497440815, "auxiliary_loss_weight": 1.0, "epoch": 2.9653882132834424, "flow_matching_loss": 0.06591281481087208, "grad_norm": 0.22637292742729187, "invalid_tail_samples": 24.1, "learning_rate": 9.915620413884519e-05, "loss": 0.0752, "positive_teacher_pairs": 26784.3, "relation_loss": 0.00927608497440815, "selected_pairs": 26784.3, "step": 3170, "student_distance_mean": 576.7920166015625, "teacher_distance_mean": 0.8535195410251617, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.00927608497440815, "weighted_relation_loss": 0.00927608497440815 }, { "action_query_batch_std": 10.078693103790282, "action_query_norm": 466.57728271484376, "action_relation_loss": 0.009514922834932804, "auxiliary_loss_weight": 1.0, "epoch": 2.9747427502338635, "flow_matching_loss": 0.06715216711163521, "grad_norm": 0.22632546722888947, "invalid_tail_samples": 23.5, "learning_rate": 9.914609141809139e-05, "loss": 0.0767, "positive_teacher_pairs": 26921.9, "relation_loss": 0.009514922834932804, "selected_pairs": 26921.9, "step": 3180, "student_distance_mean": 571.4051574707031, "teacher_distance_mean": 0.8482001960277558, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.009514922834932804, "weighted_relation_loss": 0.009514922834932804 }, { "action_query_batch_std": 10.29444465637207, "action_query_norm": 474.23937072753904, "action_relation_loss": 0.01006430946290493, "auxiliary_loss_weight": 1.0, "epoch": 2.9840972871842846, "flow_matching_loss": 0.07146748304367065, "grad_norm": 0.2057710587978363, "invalid_tail_samples": 22.1, "learning_rate": 9.913591898020235e-05, "loss": 0.0815, "positive_teacher_pairs": 27247.1, "relation_loss": 0.01006430946290493, "selected_pairs": 27247.1, "step": 3190, "student_distance_mean": 580.8077331542969, "teacher_distance_mean": 0.8595376431941986, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.01006430946290493, "weighted_relation_loss": 0.01006430946290493 }, { "action_query_batch_std": 10.143955326080322, "action_query_norm": 468.0649017333984, "action_relation_loss": 0.01000894708558917, "auxiliary_loss_weight": 1.0, "epoch": 2.9934518241347052, "flow_matching_loss": 0.06953014880418777, "grad_norm": 0.2426794320344925, "invalid_tail_samples": 24.5, "learning_rate": 9.912568683753853e-05, "loss": 0.0795, "positive_teacher_pairs": 26684.8, "relation_loss": 0.01000894708558917, "selected_pairs": 26684.8, "step": 3200, "student_distance_mean": 574.1711669921875, "teacher_distance_mean": 0.8425423264503479, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.01000894708558917, "weighted_relation_loss": 0.01000894708558917 }, { "action_query_batch_std": 10.444083976745606, "action_query_norm": 478.8743133544922, "action_relation_loss": 0.009585703257471323, "auxiliary_loss_weight": 1.0, "epoch": 3.0028063610851263, "flow_matching_loss": 0.06632637269794942, "grad_norm": 0.21363243460655212, "invalid_tail_samples": 24.6, "learning_rate": 9.911539500253295e-05, "loss": 0.0759, "positive_teacher_pairs": 23666.0, "relation_loss": 0.009585703257471323, "selected_pairs": 23666.0, "step": 3210, "student_distance_mean": 591.5234191894531, "teacher_distance_mean": 0.8711952090263366, "valid_action_samples": 211.5, "weighted_auxiliary_loss": 0.009585703257471323, "weighted_relation_loss": 0.009585703257471323 }, { "action_query_batch_std": 10.160010051727294, "action_query_norm": 465.8601348876953, "action_relation_loss": 0.01001423429697752, "auxiliary_loss_weight": 1.0, "epoch": 3.0121608980355474, "flow_matching_loss": 0.06598403193056583, "grad_norm": 0.20293404161930084, "invalid_tail_samples": 23.7, "learning_rate": 9.910504348769118e-05, "loss": 0.076, "positive_teacher_pairs": 26881.7, "relation_loss": 0.01001423429697752, "selected_pairs": 26881.7, "step": 3220, "student_distance_mean": 576.2977966308594, "teacher_distance_mean": 0.8603328227996826, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.01001423429697752, "weighted_relation_loss": 0.01001423429697752 }, { "action_query_batch_std": 10.40078125, "action_query_norm": 476.84430236816405, "action_relation_loss": 0.009695200342684984, "auxiliary_loss_weight": 1.0, "epoch": 3.021515434985968, "flow_matching_loss": 0.06542261615395546, "grad_norm": 0.2133835256099701, "invalid_tail_samples": 22.3, "learning_rate": 9.909463230559127e-05, "loss": 0.0751, "positive_teacher_pairs": 27205.0, "relation_loss": 0.009695200342684984, "selected_pairs": 27205.0, "step": 3230, "student_distance_mean": 586.9005493164062, "teacher_distance_mean": 0.852055960893631, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.009695200342684984, "weighted_relation_loss": 0.009695200342684984 }, { "action_query_batch_std": 10.213648414611816, "action_query_norm": 473.537939453125, "action_relation_loss": 0.009689631778746844, "auxiliary_loss_weight": 1.0, "epoch": 3.030869971936389, "flow_matching_loss": 0.06843705847859383, "grad_norm": 0.23034901916980743, "invalid_tail_samples": 22.1, "learning_rate": 9.908416146888376e-05, "loss": 0.0781, "positive_teacher_pairs": 27251.6, "relation_loss": 0.009689631778746844, "selected_pairs": 27251.6, "step": 3240, "student_distance_mean": 575.4765869140625, "teacher_distance_mean": 0.8468757092952728, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.009689631778746844, "weighted_relation_loss": 0.009689631778746844 }, { "action_query_batch_std": 10.416471576690673, "action_query_norm": 477.9377105712891, "action_relation_loss": 0.010898146685212851, "auxiliary_loss_weight": 1.0, "epoch": 3.0402245088868103, "flow_matching_loss": 0.06993868090212345, "grad_norm": 0.31854572892189026, "invalid_tail_samples": 26.0, "learning_rate": 9.907363099029175e-05, "loss": 0.0808, "positive_teacher_pairs": 26344.2, "relation_loss": 0.010898146685212851, "selected_pairs": 26344.2, "step": 3250, "student_distance_mean": 587.8264892578125, "teacher_distance_mean": 0.8584413230419159, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.010898146685212851, "weighted_relation_loss": 0.010898146685212851 }, { "action_query_batch_std": 10.239041137695313, "action_query_norm": 473.08575744628905, "action_relation_loss": 0.01061328910291195, "auxiliary_loss_weight": 1.0, "epoch": 3.049579045837231, "flow_matching_loss": 0.0713456466794014, "grad_norm": 0.28451699018478394, "invalid_tail_samples": 22.2, "learning_rate": 9.906304088261073e-05, "loss": 0.082, "positive_teacher_pairs": 27233.9, "relation_loss": 0.01061328910291195, "selected_pairs": 27233.9, "step": 3260, "student_distance_mean": 576.8155578613281, "teacher_distance_mean": 0.8638660430908203, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.01061328910291195, "weighted_relation_loss": 0.01061328910291195 }, { "action_query_batch_std": 10.313683414459229, "action_query_norm": 473.5608764648438, "action_relation_loss": 0.01056930497288704, "auxiliary_loss_weight": 1.0, "epoch": 3.058933582787652, "flow_matching_loss": 0.0709397740662098, "grad_norm": 0.21509379148483276, "invalid_tail_samples": 23.8, "learning_rate": 9.905239115870872e-05, "loss": 0.0815, "positive_teacher_pairs": 26854.1, "relation_loss": 0.01056930497288704, "selected_pairs": 26854.1, "step": 3270, "student_distance_mean": 583.8732604980469, "teacher_distance_mean": 0.8606993377208709, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.01056930497288704, "weighted_relation_loss": 0.01056930497288704 }, { "action_query_batch_std": 10.3933030128479, "action_query_norm": 479.2099365234375, "action_relation_loss": 0.010037598852068185, "auxiliary_loss_weight": 1.0, "epoch": 3.068288119738073, "flow_matching_loss": 0.07161034159362316, "grad_norm": 0.22980904579162598, "invalid_tail_samples": 23.7, "learning_rate": 9.90416818315261e-05, "loss": 0.0816, "positive_teacher_pairs": 26877.9, "relation_loss": 0.010037598852068185, "selected_pairs": 26877.9, "step": 3280, "student_distance_mean": 587.6031127929688, "teacher_distance_mean": 0.8533940613269806, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.010037598852068185, "weighted_relation_loss": 0.010037598852068185 }, { "action_query_batch_std": 10.129660511016846, "action_query_norm": 467.9691925048828, "action_relation_loss": 0.009809680189937353, "auxiliary_loss_weight": 1.0, "epoch": 3.077642656688494, "flow_matching_loss": 0.06598136946558952, "grad_norm": 0.16977721452713013, "invalid_tail_samples": 22.4, "learning_rate": 9.903091291407573e-05, "loss": 0.0758, "positive_teacher_pairs": 27170.2, "relation_loss": 0.009809680189937353, "selected_pairs": 27170.2, "step": 3290, "student_distance_mean": 572.773681640625, "teacher_distance_mean": 0.8505284786224365, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.009809680189937353, "weighted_relation_loss": 0.009809680189937353 }, { "action_query_batch_std": 10.156505489349366, "action_query_norm": 466.4050262451172, "action_relation_loss": 0.010484041832387447, "auxiliary_loss_weight": 1.0, "epoch": 3.086997193638915, "flow_matching_loss": 0.07029794901609421, "grad_norm": 0.18600524961948395, "invalid_tail_samples": 23.3, "learning_rate": 9.902008441944286e-05, "loss": 0.0808, "positive_teacher_pairs": 26972.9, "relation_loss": 0.010484041832387447, "selected_pairs": 26972.9, "step": 3300, "student_distance_mean": 576.6082092285156, "teacher_distance_mean": 0.8576529145240783, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.010484041832387447, "weighted_relation_loss": 0.010484041832387447 }, { "action_query_batch_std": 10.19868631362915, "action_query_norm": 467.39154663085935, "action_relation_loss": 0.010108115058392287, "auxiliary_loss_weight": 1.0, "epoch": 3.096351730589336, "flow_matching_loss": 0.06453034617006778, "grad_norm": 0.22480490803718567, "invalid_tail_samples": 26.5, "learning_rate": 9.900919636078512e-05, "loss": 0.0746, "positive_teacher_pairs": 26237.4, "relation_loss": 0.010108115058392287, "selected_pairs": 26237.4, "step": 3310, "student_distance_mean": 579.1605529785156, "teacher_distance_mean": 0.8495611548423767, "valid_action_samples": 229.5, "weighted_auxiliary_loss": 0.010108115058392287, "weighted_relation_loss": 0.010108115058392287 }, { "action_query_batch_std": 10.591469097137452, "action_query_norm": 484.2051086425781, "action_relation_loss": 0.010092494357377291, "auxiliary_loss_weight": 1.0, "epoch": 3.1057062675397566, "flow_matching_loss": 0.0649992436170578, "grad_norm": 0.185821533203125, "invalid_tail_samples": 23.6, "learning_rate": 9.899824875133255e-05, "loss": 0.0751, "positive_teacher_pairs": 26895.5, "relation_loss": 0.010092494357377291, "selected_pairs": 26895.5, "step": 3320, "student_distance_mean": 600.3386474609375, "teacher_distance_mean": 0.859937185049057, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.010092494357377291, "weighted_relation_loss": 0.010092494357377291 }, { "action_query_batch_std": 10.398225688934327, "action_query_norm": 476.7131866455078, "action_relation_loss": 0.009603939764201642, "auxiliary_loss_weight": 1.0, "epoch": 3.1150608044901777, "flow_matching_loss": 0.06581003181636333, "grad_norm": 0.16856463253498077, "invalid_tail_samples": 23.9, "learning_rate": 9.898724160438749e-05, "loss": 0.0754, "positive_teacher_pairs": 26834.6, "relation_loss": 0.009603939764201642, "selected_pairs": 26834.6, "step": 3330, "student_distance_mean": 588.3423156738281, "teacher_distance_mean": 0.855983418226242, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.009603939764201642, "weighted_relation_loss": 0.009603939764201642 }, { "action_query_batch_std": 10.338820457458496, "action_query_norm": 475.2228149414062, "action_relation_loss": 0.009610612224787474, "auxiliary_loss_weight": 1.0, "epoch": 3.124415341440599, "flow_matching_loss": 0.06705519556999207, "grad_norm": 0.18613722920417786, "invalid_tail_samples": 22.4, "learning_rate": 9.89761749333247e-05, "loss": 0.0767, "positive_teacher_pairs": 27175.2, "relation_loss": 0.009610612224787474, "selected_pairs": 27175.2, "step": 3340, "student_distance_mean": 586.3511108398437, "teacher_distance_mean": 0.8491860032081604, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.009610612224787474, "weighted_relation_loss": 0.009610612224787474 }, { "action_query_batch_std": 10.320244979858398, "action_query_norm": 473.88453979492186, "action_relation_loss": 0.009441908728331328, "auxiliary_loss_weight": 1.0, "epoch": 3.1337698783910195, "flow_matching_loss": 0.06656757965683938, "grad_norm": 0.20633044838905334, "invalid_tail_samples": 22.8, "learning_rate": 9.896504875159122e-05, "loss": 0.076, "positive_teacher_pairs": 27089.8, "relation_loss": 0.009441908728331328, "selected_pairs": 27089.8, "step": 3350, "student_distance_mean": 584.2193603515625, "teacher_distance_mean": 0.84996777176857, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.009441908728331328, "weighted_relation_loss": 0.009441908728331328 }, { "action_query_batch_std": 10.499794292449952, "action_query_norm": 482.9208160400391, "action_relation_loss": 0.009487459622323512, "auxiliary_loss_weight": 1.0, "epoch": 3.1431244153414406, "flow_matching_loss": 0.07069564610719681, "grad_norm": 0.1809207946062088, "invalid_tail_samples": 22.2, "learning_rate": 9.89538630727064e-05, "loss": 0.0802, "positive_teacher_pairs": 27230.4, "relation_loss": 0.009487459622323512, "selected_pairs": 27230.4, "step": 3360, "student_distance_mean": 595.5592651367188, "teacher_distance_mean": 0.8571313560009003, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.009487459622323512, "weighted_relation_loss": 0.009487459622323512 }, { "action_query_batch_std": 10.634636306762696, "action_query_norm": 490.25709533691406, "action_relation_loss": 0.00960159245878458, "auxiliary_loss_weight": 1.0, "epoch": 3.1524789522918617, "flow_matching_loss": 0.06688425838947296, "grad_norm": 0.19943390786647797, "invalid_tail_samples": 26.3, "learning_rate": 9.894261791026189e-05, "loss": 0.0765, "positive_teacher_pairs": 26273.9, "relation_loss": 0.00960159245878458, "selected_pairs": 26273.9, "step": 3370, "student_distance_mean": 602.6541259765625, "teacher_distance_mean": 0.8493212580680847, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.00960159245878458, "weighted_relation_loss": 0.00960159245878458 }, { "action_query_batch_std": 10.525936603546143, "action_query_norm": 484.8138763427734, "action_relation_loss": 0.009173597022891045, "auxiliary_loss_weight": 1.0, "epoch": 3.1618334892422824, "flow_matching_loss": 0.0656782902777195, "grad_norm": 0.2601742446422577, "invalid_tail_samples": 21.5, "learning_rate": 9.893131327792165e-05, "loss": 0.0749, "positive_teacher_pairs": 27385.8, "relation_loss": 0.009173597022891045, "selected_pairs": 27385.8, "step": 3380, "student_distance_mean": 597.9808044433594, "teacher_distance_mean": 0.8537519752979279, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.009173597022891045, "weighted_relation_loss": 0.009173597022891045 }, { "action_query_batch_std": 10.414859676361084, "action_query_norm": 482.6827789306641, "action_relation_loss": 0.009809370897710324, "auxiliary_loss_weight": 1.0, "epoch": 3.1711880261927035, "flow_matching_loss": 0.06620638594031333, "grad_norm": 0.3066995143890381, "invalid_tail_samples": 23.1, "learning_rate": 9.891994918942182e-05, "loss": 0.076, "positive_teacher_pairs": 27008.0, "relation_loss": 0.009809370897710324, "selected_pairs": 27008.0, "step": 3390, "student_distance_mean": 590.7152099609375, "teacher_distance_mean": 0.8435348927974701, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.009809370897710324, "weighted_relation_loss": 0.009809370897710324 }, { "action_query_batch_std": 10.629205417633056, "action_query_norm": 489.7277374267578, "action_relation_loss": 0.009586271364241838, "auxiliary_loss_weight": 1.0, "epoch": 3.1805425631431246, "flow_matching_loss": 0.06755362227559089, "grad_norm": 0.14971159398555756, "invalid_tail_samples": 23.1, "learning_rate": 9.890852565857092e-05, "loss": 0.0771, "positive_teacher_pairs": 27017.3, "relation_loss": 0.009586271364241838, "selected_pairs": 27017.3, "step": 3400, "student_distance_mean": 599.7828186035156, "teacher_distance_mean": 0.8525424063205719, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.009586271364241838, "weighted_relation_loss": 0.009586271364241838 }, { "action_query_batch_std": 10.490101337432861, "action_query_norm": 482.09351501464846, "action_relation_loss": 0.00967160491272807, "auxiliary_loss_weight": 1.0, "epoch": 3.189897100093545, "flow_matching_loss": 0.06336345709860325, "grad_norm": 0.17023077607154846, "invalid_tail_samples": 22.3, "learning_rate": 9.889704269924954e-05, "loss": 0.073, "positive_teacher_pairs": 27201.0, "relation_loss": 0.00967160491272807, "selected_pairs": 27201.0, "step": 3410, "student_distance_mean": 590.9323547363281, "teacher_distance_mean": 0.8470631837844849, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.00967160491272807, "weighted_relation_loss": 0.00967160491272807 }, { "action_query_batch_std": 10.527737045288086, "action_query_norm": 484.7275787353516, "action_relation_loss": 0.00945856710895896, "auxiliary_loss_weight": 1.0, "epoch": 3.1992516370439663, "flow_matching_loss": 0.06574938893318176, "grad_norm": 0.18184131383895874, "invalid_tail_samples": 24.1, "learning_rate": 9.888550032541059e-05, "loss": 0.0752, "positive_teacher_pairs": 26783.7, "relation_loss": 0.00945856710895896, "selected_pairs": 26783.7, "step": 3420, "student_distance_mean": 595.8701293945312, "teacher_distance_mean": 0.8597241044044495, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.00945856710895896, "weighted_relation_loss": 0.00945856710895896 }, { "action_query_batch_std": 10.72214469909668, "action_query_norm": 490.41697998046874, "action_relation_loss": 0.009947104100137948, "auxiliary_loss_weight": 1.0, "epoch": 3.2086061739943874, "flow_matching_loss": 0.0683887965977192, "grad_norm": 0.23712149262428284, "invalid_tail_samples": 23.3, "learning_rate": 9.887389855107916e-05, "loss": 0.0783, "positive_teacher_pairs": 26970.5, "relation_loss": 0.009947104100137948, "selected_pairs": 26970.5, "step": 3430, "student_distance_mean": 608.4749816894531, "teacher_distance_mean": 0.8554693102836609, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.009947104100137948, "weighted_relation_loss": 0.009947104100137948 }, { "action_query_batch_std": 10.849720764160157, "action_query_norm": 496.04254760742185, "action_relation_loss": 0.009618329536169767, "auxiliary_loss_weight": 1.0, "epoch": 3.217960710944808, "flow_matching_loss": 0.0660218719393015, "grad_norm": 0.22114673256874084, "invalid_tail_samples": 24.8, "learning_rate": 9.886223739035248e-05, "loss": 0.0756, "positive_teacher_pairs": 26622.7, "relation_loss": 0.009618329536169767, "selected_pairs": 26622.7, "step": 3440, "student_distance_mean": 614.6430419921875, "teacher_distance_mean": 0.8550926983356476, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.009618329536169767, "weighted_relation_loss": 0.009618329536169767 }, { "action_query_batch_std": 10.571305084228516, "action_query_norm": 484.3988403320312, "action_relation_loss": 0.00956921186298132, "auxiliary_loss_weight": 1.0, "epoch": 3.227315247895229, "flow_matching_loss": 0.06305971629917621, "grad_norm": 0.19742389023303986, "invalid_tail_samples": 25.9, "learning_rate": 9.885051685739997e-05, "loss": 0.0726, "positive_teacher_pairs": 26367.4, "relation_loss": 0.00956921186298132, "selected_pairs": 26367.4, "step": 3450, "student_distance_mean": 600.501416015625, "teacher_distance_mean": 0.8480401992797851, "valid_action_samples": 230.1, "weighted_auxiliary_loss": 0.00956921186298132, "weighted_relation_loss": 0.00956921186298132 }, { "action_query_batch_std": 10.589356708526612, "action_query_norm": 481.3380187988281, "action_relation_loss": 0.009699387568980455, "auxiliary_loss_weight": 1.0, "epoch": 3.2366697848456503, "flow_matching_loss": 0.0644310038536787, "grad_norm": 0.2524200975894928, "invalid_tail_samples": 22.2, "learning_rate": 9.883873696646316e-05, "loss": 0.0741, "positive_teacher_pairs": 27223.7, "relation_loss": 0.009699387568980455, "selected_pairs": 27223.7, "step": 3460, "student_distance_mean": 592.6348754882813, "teacher_distance_mean": 0.847366988658905, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.009699387568980455, "weighted_relation_loss": 0.009699387568980455 }, { "action_query_batch_std": 10.677190399169922, "action_query_norm": 481.57152404785154, "action_relation_loss": 0.009331008791923523, "auxiliary_loss_weight": 1.0, "epoch": 3.246024321796071, "flow_matching_loss": 0.06578377932310105, "grad_norm": 0.2421834021806717, "invalid_tail_samples": 23.5, "learning_rate": 9.882689773185575e-05, "loss": 0.0751, "positive_teacher_pairs": 26931.8, "relation_loss": 0.009331008791923523, "selected_pairs": 26931.8, "step": 3470, "student_distance_mean": 600.3247985839844, "teacher_distance_mean": 0.8628615856170654, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.009331008791923523, "weighted_relation_loss": 0.009331008791923523 }, { "action_query_batch_std": 10.836100578308105, "action_query_norm": 492.8558685302734, "action_relation_loss": 0.009497123770415783, "auxiliary_loss_weight": 1.0, "epoch": 3.255378858746492, "flow_matching_loss": 0.06738731190562249, "grad_norm": 0.24320897459983826, "invalid_tail_samples": 23.0, "learning_rate": 9.881499916796353e-05, "loss": 0.0769, "positive_teacher_pairs": 27037.1, "relation_loss": 0.009497123770415783, "selected_pairs": 27037.1, "step": 3480, "student_distance_mean": 612.5043334960938, "teacher_distance_mean": 0.8491572678089142, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.009497123770415783, "weighted_relation_loss": 0.009497123770415783 }, { "action_query_batch_std": 11.012136840820313, "action_query_norm": 501.33196411132815, "action_relation_loss": 0.009263058751821518, "auxiliary_loss_weight": 1.0, "epoch": 3.264733395696913, "flow_matching_loss": 0.06387542672455311, "grad_norm": 0.20978783071041107, "invalid_tail_samples": 25.0, "learning_rate": 9.880304128924434e-05, "loss": 0.0731, "positive_teacher_pairs": 26569.1, "relation_loss": 0.009263058751821518, "selected_pairs": 26569.1, "step": 3490, "student_distance_mean": 620.6850036621094, "teacher_distance_mean": 0.8524312853813172, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.009263058751821518, "weighted_relation_loss": 0.009263058751821518 }, { "action_query_batch_std": 10.930898952484132, "action_query_norm": 498.6113311767578, "action_relation_loss": 0.009436465054750442, "auxiliary_loss_weight": 1.0, "epoch": 3.2740879326473338, "flow_matching_loss": 0.06506124064326287, "grad_norm": 0.18288950622081757, "invalid_tail_samples": 27.1, "learning_rate": 9.879102411022817e-05, "loss": 0.0745, "positive_teacher_pairs": 26096.5, "relation_loss": 0.009436465054750442, "selected_pairs": 26096.5, "step": 3500, "student_distance_mean": 620.9976745605469, "teacher_distance_mean": 0.8566227793693543, "valid_action_samples": 228.9, "weighted_auxiliary_loss": 0.009436465054750442, "weighted_relation_loss": 0.009436465054750442 }, { "action_query_batch_std": 10.734994506835937, "action_query_norm": 490.96165161132814, "action_relation_loss": 0.00891634039580822, "auxiliary_loss_weight": 1.0, "epoch": 3.283442469597755, "flow_matching_loss": 0.06286763921380042, "grad_norm": 0.1667269766330719, "invalid_tail_samples": 22.5, "learning_rate": 9.877894764551703e-05, "loss": 0.0718, "positive_teacher_pairs": 27153.3, "relation_loss": 0.00891634039580822, "selected_pairs": 27153.3, "step": 3510, "student_distance_mean": 607.0947998046875, "teacher_distance_mean": 0.850921905040741, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.00891634039580822, "weighted_relation_loss": 0.00891634039580822 }, { "action_query_batch_std": 10.817290878295898, "action_query_norm": 494.3103851318359, "action_relation_loss": 0.009765921253710985, "auxiliary_loss_weight": 1.0, "epoch": 3.292797006548176, "flow_matching_loss": 0.06528643518686295, "grad_norm": 0.1894790530204773, "invalid_tail_samples": 24.0, "learning_rate": 9.876681190978494e-05, "loss": 0.0751, "positive_teacher_pairs": 26804.7, "relation_loss": 0.009765921253710985, "selected_pairs": 26804.7, "step": 3520, "student_distance_mean": 615.5501708984375, "teacher_distance_mean": 0.8571419894695282, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.009765921253710985, "weighted_relation_loss": 0.009765921253710985 }, { "action_query_batch_std": 10.920317363739013, "action_query_norm": 500.02459411621095, "action_relation_loss": 0.009364629257470369, "auxiliary_loss_weight": 1.0, "epoch": 3.3021515434985966, "flow_matching_loss": 0.06450496762990951, "grad_norm": 0.19035646319389343, "invalid_tail_samples": 27.0, "learning_rate": 9.875461691777797e-05, "loss": 0.0739, "positive_teacher_pairs": 26123.5, "relation_loss": 0.009364629257470369, "selected_pairs": 26123.5, "step": 3530, "student_distance_mean": 619.0166137695312, "teacher_distance_mean": 0.8495124757289887, "valid_action_samples": 229.0, "weighted_auxiliary_loss": 0.009364629257470369, "weighted_relation_loss": 0.009364629257470369 }, { "action_query_batch_std": 10.888306999206543, "action_query_norm": 498.3343994140625, "action_relation_loss": 0.009325452800840139, "auxiliary_loss_weight": 1.0, "epoch": 3.3115060804490177, "flow_matching_loss": 0.06579267829656602, "grad_norm": 0.15486812591552734, "invalid_tail_samples": 25.0, "learning_rate": 9.874236268431417e-05, "loss": 0.0751, "positive_teacher_pairs": 26579.6, "relation_loss": 0.009325452800840139, "selected_pairs": 26579.6, "step": 3540, "student_distance_mean": 614.640478515625, "teacher_distance_mean": 0.8535836279392243, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.009325452800840139, "weighted_relation_loss": 0.009325452800840139 }, { "action_query_batch_std": 10.783155250549317, "action_query_norm": 490.91721496582034, "action_relation_loss": 0.009170785918831826, "auxiliary_loss_weight": 1.0, "epoch": 3.320860617399439, "flow_matching_loss": 0.0646719541400671, "grad_norm": 0.17172035574913025, "invalid_tail_samples": 24.0, "learning_rate": 9.873004922428361e-05, "loss": 0.0738, "positive_teacher_pairs": 26803.9, "relation_loss": 0.009170785918831826, "selected_pairs": 26803.9, "step": 3550, "student_distance_mean": 609.455908203125, "teacher_distance_mean": 0.8448196709156036, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.009170785918831826, "weighted_relation_loss": 0.009170785918831826 }, { "action_query_batch_std": 11.111705684661866, "action_query_norm": 501.81122131347655, "action_relation_loss": 0.00878364872187376, "auxiliary_loss_weight": 1.0, "epoch": 3.33021515434986, "flow_matching_loss": 0.06415126137435437, "grad_norm": 0.26175495982170105, "invalid_tail_samples": 25.3, "learning_rate": 9.871767655264829e-05, "loss": 0.0729, "positive_teacher_pairs": 26502.2, "relation_loss": 0.00878364872187376, "selected_pairs": 26502.2, "step": 3560, "student_distance_mean": 628.7844787597656, "teacher_distance_mean": 0.8650893807411194, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.00878364872187376, "weighted_relation_loss": 0.00878364872187376 }, { "action_query_batch_std": 10.993505382537842, "action_query_norm": 499.8847290039063, "action_relation_loss": 0.008945634588599205, "auxiliary_loss_weight": 1.0, "epoch": 3.3395696913002806, "flow_matching_loss": 0.06506317965686322, "grad_norm": 0.22930069267749786, "invalid_tail_samples": 20.3, "learning_rate": 9.87052446844422e-05, "loss": 0.074, "positive_teacher_pairs": 27664.0, "relation_loss": 0.008945634588599205, "selected_pairs": 27664.0, "step": 3570, "student_distance_mean": 621.242431640625, "teacher_distance_mean": 0.8562560498714447, "valid_action_samples": 235.7, "weighted_auxiliary_loss": 0.008945634588599205, "weighted_relation_loss": 0.008945634588599205 }, { "action_query_batch_std": 11.150650787353516, "action_query_norm": 506.5787780761719, "action_relation_loss": 0.009297415055334568, "auxiliary_loss_weight": 1.0, "epoch": 3.3489242282507017, "flow_matching_loss": 0.06689276099205017, "grad_norm": 0.21552413702011108, "invalid_tail_samples": 20.6, "learning_rate": 9.869275363477122e-05, "loss": 0.0762, "positive_teacher_pairs": 27594.8, "relation_loss": 0.009297415055334568, "selected_pairs": 27594.8, "step": 3580, "student_distance_mean": 628.9398010253906, "teacher_distance_mean": 0.8611296951770783, "valid_action_samples": 235.4, "weighted_auxiliary_loss": 0.009297415055334568, "weighted_relation_loss": 0.009297415055334568 }, { "action_query_batch_std": 11.065571880340576, "action_query_norm": 501.27585754394534, "action_relation_loss": 0.00960299102589488, "auxiliary_loss_weight": 1.0, "epoch": 3.3582787652011223, "flow_matching_loss": 0.06503602229058743, "grad_norm": 0.19151422381401062, "invalid_tail_samples": 20.9, "learning_rate": 9.868020341881312e-05, "loss": 0.0746, "positive_teacher_pairs": 27530.4, "relation_loss": 0.00960299102589488, "selected_pairs": 27530.4, "step": 3590, "student_distance_mean": 623.8147216796875, "teacher_distance_mean": 0.8567508161067963, "valid_action_samples": 235.1, "weighted_auxiliary_loss": 0.00960299102589488, "weighted_relation_loss": 0.00960299102589488 }, { "action_query_batch_std": 10.903335285186767, "action_query_norm": 497.2985870361328, "action_relation_loss": 0.008864437509328128, "auxiliary_loss_weight": 1.0, "epoch": 3.3676333021515434, "flow_matching_loss": 0.06608579903841019, "grad_norm": 0.2045469880104065, "invalid_tail_samples": 21.8, "learning_rate": 9.866759405181765e-05, "loss": 0.075, "positive_teacher_pairs": 27323.8, "relation_loss": 0.008864437509328128, "selected_pairs": 27323.8, "step": 3600, "student_distance_mean": 617.1291381835938, "teacher_distance_mean": 0.8557819366455078, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.008864437509328128, "weighted_relation_loss": 0.008864437509328128 }, { "action_query_batch_std": 10.80811014175415, "action_query_norm": 492.29883728027346, "action_relation_loss": 0.009162512980401516, "auxiliary_loss_weight": 1.0, "epoch": 3.3769878391019645, "flow_matching_loss": 0.06357503309845924, "grad_norm": 0.18023623526096344, "invalid_tail_samples": 25.9, "learning_rate": 9.865492554910633e-05, "loss": 0.0727, "positive_teacher_pairs": 26366.8, "relation_loss": 0.009162512980401516, "selected_pairs": 26366.8, "step": 3610, "student_distance_mean": 613.117919921875, "teacher_distance_mean": 0.8546540439128876, "valid_action_samples": 230.1, "weighted_auxiliary_loss": 0.009162512980401516, "weighted_relation_loss": 0.009162512980401516 }, { "action_query_batch_std": 10.98538579940796, "action_query_norm": 494.6902160644531, "action_relation_loss": 0.009085317887365819, "auxiliary_loss_weight": 1.0, "epoch": 3.3863423760523856, "flow_matching_loss": 0.06426749341189861, "grad_norm": 0.15121547877788544, "invalid_tail_samples": 23.2, "learning_rate": 9.864219792607262e-05, "loss": 0.0734, "positive_teacher_pairs": 26994.0, "relation_loss": 0.009085317887365819, "selected_pairs": 26994.0, "step": 3620, "student_distance_mean": 619.5362060546875, "teacher_distance_mean": 0.861390370130539, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.009085317887365819, "weighted_relation_loss": 0.009085317887365819 }, { "action_query_batch_std": 10.818570041656494, "action_query_norm": 496.2414520263672, "action_relation_loss": 0.009136772947385907, "auxiliary_loss_weight": 1.0, "epoch": 3.3956969130028063, "flow_matching_loss": 0.06244752444326877, "grad_norm": 0.16810186207294464, "invalid_tail_samples": 22.5, "learning_rate": 9.862941119818177e-05, "loss": 0.0716, "positive_teacher_pairs": 27164.5, "relation_loss": 0.009136772947385907, "selected_pairs": 27164.5, "step": 3630, "student_distance_mean": 611.7423522949218, "teacher_distance_mean": 0.8485789775848389, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.009136772947385907, "weighted_relation_loss": 0.009136772947385907 }, { "action_query_batch_std": 10.890480136871338, "action_query_norm": 501.5595458984375, "action_relation_loss": 0.0093371347989887, "auxiliary_loss_weight": 1.0, "epoch": 3.4050514499532274, "flow_matching_loss": 0.06458198055624961, "grad_norm": 0.1838599592447281, "invalid_tail_samples": 21.6, "learning_rate": 9.861656538097086e-05, "loss": 0.0739, "positive_teacher_pairs": 27365.8, "relation_loss": 0.0093371347989887, "selected_pairs": 27365.8, "step": 3640, "student_distance_mean": 616.9221801757812, "teacher_distance_mean": 0.8466773867607117, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.0093371347989887, "weighted_relation_loss": 0.0093371347989887 }, { "action_query_batch_std": 10.943416595458984, "action_query_norm": 501.33515625, "action_relation_loss": 0.009341242350637912, "auxiliary_loss_weight": 1.0, "epoch": 3.414405986903648, "flow_matching_loss": 0.06299190297722816, "grad_norm": 0.17378078401088715, "invalid_tail_samples": 23.3, "learning_rate": 9.860366049004877e-05, "loss": 0.0723, "positive_teacher_pairs": 26963.9, "relation_loss": 0.009341242350637912, "selected_pairs": 26963.9, "step": 3650, "student_distance_mean": 622.1141723632812, "teacher_distance_mean": 0.8561480700969696, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.009341242350637912, "weighted_relation_loss": 0.009341242350637912 }, { "action_query_batch_std": 10.908739566802979, "action_query_norm": 502.0359313964844, "action_relation_loss": 0.00913118924945593, "auxiliary_loss_weight": 1.0, "epoch": 3.423760523854069, "flow_matching_loss": 0.06337907016277314, "grad_norm": 0.17588648200035095, "invalid_tail_samples": 23.4, "learning_rate": 9.859069654109615e-05, "loss": 0.0725, "positive_teacher_pairs": 26942.7, "relation_loss": 0.00913118924945593, "selected_pairs": 26942.7, "step": 3660, "student_distance_mean": 616.6863830566406, "teacher_distance_mean": 0.8544001579284668, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.00913118924945593, "weighted_relation_loss": 0.00913118924945593 }, { "action_query_batch_std": 11.02485008239746, "action_query_norm": 506.9086151123047, "action_relation_loss": 0.00914623737335205, "auxiliary_loss_weight": 1.0, "epoch": 3.4331150608044902, "flow_matching_loss": 0.061611353605985644, "grad_norm": 0.13978543877601624, "invalid_tail_samples": 25.1, "learning_rate": 9.857767354986545e-05, "loss": 0.0708, "positive_teacher_pairs": 26559.0, "relation_loss": 0.00914623737335205, "selected_pairs": 26559.0, "step": 3670, "student_distance_mean": 624.4624572753906, "teacher_distance_mean": 0.861267375946045, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.00914623737335205, "weighted_relation_loss": 0.00914623737335205 }, { "action_query_batch_std": 10.743500423431396, "action_query_norm": 496.38698425292966, "action_relation_loss": 0.009253010712563991, "auxiliary_loss_weight": 1.0, "epoch": 3.4424695977549113, "flow_matching_loss": 0.06149938777089119, "grad_norm": 0.17525921761989594, "invalid_tail_samples": 24.8, "learning_rate": 9.856459153218078e-05, "loss": 0.0708, "positive_teacher_pairs": 26618.7, "relation_loss": 0.009253010712563991, "selected_pairs": 26618.7, "step": 3680, "student_distance_mean": 608.9984680175781, "teacher_distance_mean": 0.8439852118492126, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.009253010712563991, "weighted_relation_loss": 0.009253010712563991 }, { "action_query_batch_std": 10.929028034210205, "action_query_norm": 501.0648681640625, "action_relation_loss": 0.009458392765372992, "auxiliary_loss_weight": 1.0, "epoch": 3.451824134705332, "flow_matching_loss": 0.06404691301286221, "grad_norm": 0.19609494507312775, "invalid_tail_samples": 25.5, "learning_rate": 9.855145050393808e-05, "loss": 0.0735, "positive_teacher_pairs": 26457.6, "relation_loss": 0.009458392765372992, "selected_pairs": 26457.6, "step": 3690, "student_distance_mean": 618.4272399902344, "teacher_distance_mean": 0.8572499692440033, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.009458392765372992, "weighted_relation_loss": 0.009458392765372992 }, { "action_query_batch_std": 10.996164894104004, "action_query_norm": 502.7755157470703, "action_relation_loss": 0.009024820011109113, "auxiliary_loss_weight": 1.0, "epoch": 3.461178671655753, "flow_matching_loss": 0.06406410001218318, "grad_norm": 0.1744910478591919, "invalid_tail_samples": 23.9, "learning_rate": 9.85382504811049e-05, "loss": 0.0731, "positive_teacher_pairs": 26831.6, "relation_loss": 0.009024820011109113, "selected_pairs": 26831.6, "step": 3700, "student_distance_mean": 623.3551086425781, "teacher_distance_mean": 0.8528892695903778, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.009024820011109113, "weighted_relation_loss": 0.009024820011109113 }, { "action_query_batch_std": 10.943416213989257, "action_query_norm": 499.83798828125, "action_relation_loss": 0.009062350448220968, "auxiliary_loss_weight": 1.0, "epoch": 3.4705332086061738, "flow_matching_loss": 0.06406324170529842, "grad_norm": 0.11332689225673676, "invalid_tail_samples": 22.1, "learning_rate": 9.852499147972054e-05, "loss": 0.0731, "positive_teacher_pairs": 27253.7, "relation_loss": 0.009062350448220968, "selected_pairs": 27253.7, "step": 3710, "student_distance_mean": 615.1633483886719, "teacher_distance_mean": 0.8499199032783509, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.009062350448220968, "weighted_relation_loss": 0.009062350448220968 }, { "action_query_batch_std": 11.17029504776001, "action_query_norm": 505.85182800292966, "action_relation_loss": 0.008728944370523095, "auxiliary_loss_weight": 1.0, "epoch": 3.479887745556595, "flow_matching_loss": 0.061475550010800364, "grad_norm": 0.18672986328601837, "invalid_tail_samples": 23.4, "learning_rate": 9.851167351589592e-05, "loss": 0.0702, "positive_teacher_pairs": 26944.6, "relation_loss": 0.008728944370523095, "selected_pairs": 26944.6, "step": 3720, "student_distance_mean": 629.7603393554688, "teacher_distance_mean": 0.86103395819664, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.008728944370523095, "weighted_relation_loss": 0.008728944370523095 }, { "action_query_batch_std": 11.221687984466552, "action_query_norm": 506.52430114746096, "action_relation_loss": 0.008953563822433352, "auxiliary_loss_weight": 1.0, "epoch": 3.489242282507016, "flow_matching_loss": 0.06556170471012593, "grad_norm": 0.30681341886520386, "invalid_tail_samples": 24.2, "learning_rate": 9.849829660581363e-05, "loss": 0.0745, "positive_teacher_pairs": 26756.8, "relation_loss": 0.008953563822433352, "selected_pairs": 26756.8, "step": 3730, "student_distance_mean": 631.6083679199219, "teacher_distance_mean": 0.8642394661903381, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.008953563822433352, "weighted_relation_loss": 0.008953563822433352 }, { "action_query_batch_std": 11.19305715560913, "action_query_norm": 508.9614318847656, "action_relation_loss": 0.009341660887002945, "auxiliary_loss_weight": 1.0, "epoch": 3.498596819457437, "flow_matching_loss": 0.06745567172765732, "grad_norm": 0.1616632342338562, "invalid_tail_samples": 23.8, "learning_rate": 9.848486076572787e-05, "loss": 0.0768, "positive_teacher_pairs": 26853.2, "relation_loss": 0.009341660887002945, "selected_pairs": 26853.2, "step": 3740, "student_distance_mean": 633.2642333984375, "teacher_distance_mean": 0.8681586503982544, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.009341660887002945, "weighted_relation_loss": 0.009341660887002945 }, { "action_query_batch_std": 11.059050464630127, "action_query_norm": 511.2333526611328, "action_relation_loss": 0.009614897333085537, "auxiliary_loss_weight": 1.0, "epoch": 3.5079513564078577, "flow_matching_loss": 0.06451082415878773, "grad_norm": 0.21574722230434418, "invalid_tail_samples": 22.2, "learning_rate": 9.847136601196446e-05, "loss": 0.0741, "positive_teacher_pairs": 27221.8, "relation_loss": 0.009614897333085537, "selected_pairs": 27221.8, "step": 3750, "student_distance_mean": 625.9608459472656, "teacher_distance_mean": 0.8481390655040741, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.009614897333085537, "weighted_relation_loss": 0.009614897333085537 }, { "action_query_batch_std": 10.944488716125488, "action_query_norm": 500.3837158203125, "action_relation_loss": 0.00911270286887884, "auxiliary_loss_weight": 1.0, "epoch": 3.517305893358279, "flow_matching_loss": 0.06515167541801929, "grad_norm": 0.1797572821378708, "invalid_tail_samples": 24.0, "learning_rate": 9.845781236092078e-05, "loss": 0.0743, "positive_teacher_pairs": 26802.9, "relation_loss": 0.00911270286887884, "selected_pairs": 26802.9, "step": 3760, "student_distance_mean": 618.0296936035156, "teacher_distance_mean": 0.8561072766780853, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.00911270286887884, "weighted_relation_loss": 0.00911270286887884 }, { "action_query_batch_std": 10.928941631317139, "action_query_norm": 497.9414520263672, "action_relation_loss": 0.009564060531556607, "auxiliary_loss_weight": 1.0, "epoch": 3.5266604303086995, "flow_matching_loss": 0.06565916687250137, "grad_norm": 0.15601712465286255, "invalid_tail_samples": 27.1, "learning_rate": 9.844419982906583e-05, "loss": 0.0752, "positive_teacher_pairs": 26096.2, "relation_loss": 0.009564060531556607, "selected_pairs": 26096.2, "step": 3770, "student_distance_mean": 618.8265808105468, "teacher_distance_mean": 0.857233464717865, "valid_action_samples": 228.9, "weighted_auxiliary_loss": 0.009564060531556607, "weighted_relation_loss": 0.009564060531556607 }, { "action_query_batch_std": 11.029979038238526, "action_query_norm": 502.65403442382814, "action_relation_loss": 0.008918979950249196, "auxiliary_loss_weight": 1.0, "epoch": 3.5360149672591206, "flow_matching_loss": 0.06597519069910049, "grad_norm": 0.15870653092861176, "invalid_tail_samples": 24.7, "learning_rate": 9.843052843294008e-05, "loss": 0.0749, "positive_teacher_pairs": 26648.6, "relation_loss": 0.008918979950249196, "selected_pairs": 26648.6, "step": 3780, "student_distance_mean": 623.1559326171875, "teacher_distance_mean": 0.8598987340927124, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.008918979950249196, "weighted_relation_loss": 0.008918979950249196 }, { "action_query_batch_std": 10.841306686401367, "action_query_norm": 499.8896484375, "action_relation_loss": 0.009032377786934376, "auxiliary_loss_weight": 1.0, "epoch": 3.5453695042095417, "flow_matching_loss": 0.06240951679646969, "grad_norm": 0.2540023922920227, "invalid_tail_samples": 24.5, "learning_rate": 9.841679818915559e-05, "loss": 0.0714, "positive_teacher_pairs": 26686.9, "relation_loss": 0.009032377786934376, "selected_pairs": 26686.9, "step": 3790, "student_distance_mean": 615.9367126464844, "teacher_distance_mean": 0.8510994851589203, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.009032377786934376, "weighted_relation_loss": 0.009032377786934376 }, { "action_query_batch_std": 10.890014266967773, "action_query_norm": 499.9611511230469, "action_relation_loss": 0.00956903975456953, "auxiliary_loss_weight": 1.0, "epoch": 3.5547240411599628, "flow_matching_loss": 0.06714712604880332, "grad_norm": 0.1760614663362503, "invalid_tail_samples": 25.8, "learning_rate": 9.840300911439591e-05, "loss": 0.0767, "positive_teacher_pairs": 26385.9, "relation_loss": 0.00956903975456953, "selected_pairs": 26385.9, "step": 3800, "student_distance_mean": 616.5650085449219, "teacher_distance_mean": 0.851911437511444, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.00956903975456953, "weighted_relation_loss": 0.00956903975456953 }, { "action_query_batch_std": 11.17475872039795, "action_query_norm": 510.0329620361328, "action_relation_loss": 0.009375639352947473, "auxiliary_loss_weight": 1.0, "epoch": 3.5640785781103834, "flow_matching_loss": 0.06543456465005874, "grad_norm": 0.17760978639125824, "invalid_tail_samples": 22.6, "learning_rate": 9.838916122541603e-05, "loss": 0.0748, "positive_teacher_pairs": 27129.3, "relation_loss": 0.009375639352947473, "selected_pairs": 27129.3, "step": 3810, "student_distance_mean": 631.7663696289062, "teacher_distance_mean": 0.862323659658432, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.009375639352947473, "weighted_relation_loss": 0.009375639352947473 }, { "action_query_batch_std": 10.941967582702636, "action_query_norm": 503.29900817871095, "action_relation_loss": 0.009409018838778139, "auxiliary_loss_weight": 1.0, "epoch": 3.5734331150608045, "flow_matching_loss": 0.0640040498226881, "grad_norm": 0.20055435597896576, "invalid_tail_samples": 25.0, "learning_rate": 9.837525453904246e-05, "loss": 0.0734, "positive_teacher_pairs": 26584.5, "relation_loss": 0.009409018838778139, "selected_pairs": 26584.5, "step": 3820, "student_distance_mean": 620.0194702148438, "teacher_distance_mean": 0.8469612061977386, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.009409018838778139, "weighted_relation_loss": 0.009409018838778139 }, { "action_query_batch_std": 11.301183223724365, "action_query_norm": 517.475064086914, "action_relation_loss": 0.009346882347017527, "auxiliary_loss_weight": 1.0, "epoch": 3.582787652011225, "flow_matching_loss": 0.0643418613821268, "grad_norm": 0.1724853217601776, "invalid_tail_samples": 23.7, "learning_rate": 9.836128907217314e-05, "loss": 0.0737, "positive_teacher_pairs": 26873.1, "relation_loss": 0.009346882347017527, "selected_pairs": 26873.1, "step": 3830, "student_distance_mean": 643.0377685546875, "teacher_distance_mean": 0.8674036204814911, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.009346882347017527, "weighted_relation_loss": 0.009346882347017527 }, { "action_query_batch_std": 11.161079216003419, "action_query_norm": 507.8258972167969, "action_relation_loss": 0.009284197259694338, "auxiliary_loss_weight": 1.0, "epoch": 3.5921421889616463, "flow_matching_loss": 0.061995310336351396, "grad_norm": 0.16421222686767578, "invalid_tail_samples": 22.9, "learning_rate": 9.834726484177743e-05, "loss": 0.0713, "positive_teacher_pairs": 27064.6, "relation_loss": 0.009284197259694338, "selected_pairs": 27064.6, "step": 3840, "student_distance_mean": 632.2929565429688, "teacher_distance_mean": 0.8484031856060028, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.009284197259694338, "weighted_relation_loss": 0.009284197259694338 }, { "action_query_batch_std": 11.320032405853272, "action_query_norm": 508.61170349121096, "action_relation_loss": 0.008899315819144249, "auxiliary_loss_weight": 1.0, "epoch": 3.6014967259120674, "flow_matching_loss": 0.06536006592214108, "grad_norm": 0.19509375095367432, "invalid_tail_samples": 25.5, "learning_rate": 9.833318186489609e-05, "loss": 0.0743, "positive_teacher_pairs": 26455.8, "relation_loss": 0.008899315819144249, "selected_pairs": 26455.8, "step": 3850, "student_distance_mean": 640.8564575195312, "teacher_distance_mean": 0.8613184511661529, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.008899315819144249, "weighted_relation_loss": 0.008899315819144249 }, { "action_query_batch_std": 11.471273708343507, "action_query_norm": 520.2770233154297, "action_relation_loss": 0.009331653267145157, "auxiliary_loss_weight": 1.0, "epoch": 3.6108512628624885, "flow_matching_loss": 0.06268555223941803, "grad_norm": 0.19188682734966278, "invalid_tail_samples": 22.0, "learning_rate": 9.831904015864126e-05, "loss": 0.072, "positive_teacher_pairs": 27270.3, "relation_loss": 0.009331653267145157, "selected_pairs": 27270.3, "step": 3860, "student_distance_mean": 649.7406921386719, "teacher_distance_mean": 0.8603314578533172, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.009331653267145157, "weighted_relation_loss": 0.009331653267145157 }, { "action_query_batch_std": 11.313276672363282, "action_query_norm": 516.8300048828125, "action_relation_loss": 0.009125166665762663, "auxiliary_loss_weight": 1.0, "epoch": 3.620205799812909, "flow_matching_loss": 0.06257630288600921, "grad_norm": 0.20219260454177856, "invalid_tail_samples": 23.8, "learning_rate": 9.830483974019645e-05, "loss": 0.0717, "positive_teacher_pairs": 26848.1, "relation_loss": 0.009125166665762663, "selected_pairs": 26848.1, "step": 3870, "student_distance_mean": 639.9455444335938, "teacher_distance_mean": 0.8484033107757568, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.009125166665762663, "weighted_relation_loss": 0.009125166665762663 }, { "action_query_batch_std": 11.389143943786621, "action_query_norm": 520.6852600097657, "action_relation_loss": 0.00911708539351821, "auxiliary_loss_weight": 1.0, "epoch": 3.6295603367633302, "flow_matching_loss": 0.0660761334002018, "grad_norm": 0.22057318687438965, "invalid_tail_samples": 22.8, "learning_rate": 9.82905806268165e-05, "loss": 0.0752, "positive_teacher_pairs": 27089.5, "relation_loss": 0.00911708539351821, "selected_pairs": 27089.5, "step": 3880, "student_distance_mean": 645.1115478515625, "teacher_distance_mean": 0.8506798863410949, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.00911708539351821, "weighted_relation_loss": 0.00911708539351821 }, { "action_query_batch_std": 11.464559745788574, "action_query_norm": 519.3201599121094, "action_relation_loss": 0.009082565363496543, "auxiliary_loss_weight": 1.0, "epoch": 3.6389148737137513, "flow_matching_loss": 0.06470117643475533, "grad_norm": 0.18066614866256714, "invalid_tail_samples": 22.3, "learning_rate": 9.82762628358276e-05, "loss": 0.0738, "positive_teacher_pairs": 27197.4, "relation_loss": 0.009082565363496543, "selected_pairs": 27197.4, "step": 3890, "student_distance_mean": 648.1913208007812, "teacher_distance_mean": 0.8552921831607818, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.009082565363496543, "weighted_relation_loss": 0.009082565363496543 }, { "action_query_batch_std": 11.41483964920044, "action_query_norm": 522.9928100585937, "action_relation_loss": 0.008958545606583357, "auxiliary_loss_weight": 1.0, "epoch": 3.648269410664172, "flow_matching_loss": 0.06552073955535889, "grad_norm": 0.1504667103290558, "invalid_tail_samples": 23.1, "learning_rate": 9.826188638462718e-05, "loss": 0.0745, "positive_teacher_pairs": 27010.7, "relation_loss": 0.008958545606583357, "selected_pairs": 27010.7, "step": 3900, "student_distance_mean": 646.6242370605469, "teacher_distance_mean": 0.8569932401180267, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.008958545606583357, "weighted_relation_loss": 0.008958545606583357 }, { "action_query_batch_std": 11.4879940032959, "action_query_norm": 525.4018493652344, "action_relation_loss": 0.009251988772302867, "auxiliary_loss_weight": 1.0, "epoch": 3.657623947614593, "flow_matching_loss": 0.06501507647335529, "grad_norm": 0.1888534128665924, "invalid_tail_samples": 21.6, "learning_rate": 9.824745129068402e-05, "loss": 0.0743, "positive_teacher_pairs": 27371.1, "relation_loss": 0.009251988772302867, "selected_pairs": 27371.1, "step": 3910, "student_distance_mean": 649.4416870117187, "teacher_distance_mean": 0.8559970617294311, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.009251988772302867, "weighted_relation_loss": 0.009251988772302867 }, { "action_query_batch_std": 11.464969444274903, "action_query_norm": 526.812255859375, "action_relation_loss": 0.00935256676748395, "auxiliary_loss_weight": 1.0, "epoch": 3.666978484565014, "flow_matching_loss": 0.06317941732704639, "grad_norm": 0.18228738009929657, "invalid_tail_samples": 22.4, "learning_rate": 9.82329575715381e-05, "loss": 0.0725, "positive_teacher_pairs": 27181.1, "relation_loss": 0.00935256676748395, "selected_pairs": 27181.1, "step": 3920, "student_distance_mean": 646.958349609375, "teacher_distance_mean": 0.852099722623825, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.00935256676748395, "weighted_relation_loss": 0.00935256676748395 }, { "action_query_batch_std": 11.411933994293213, "action_query_norm": 521.0653656005859, "action_relation_loss": 0.009335361327975989, "auxiliary_loss_weight": 1.0, "epoch": 3.676333021515435, "flow_matching_loss": 0.06354930698871612, "grad_norm": 0.22948965430259705, "invalid_tail_samples": 24.0, "learning_rate": 9.821840524480066e-05, "loss": 0.0729, "positive_teacher_pairs": 26801.4, "relation_loss": 0.009335361327975989, "selected_pairs": 26801.4, "step": 3930, "student_distance_mean": 647.0049682617188, "teacher_distance_mean": 0.8567519426345825, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.009335361327975989, "weighted_relation_loss": 0.009335361327975989 }, { "action_query_batch_std": 11.442218780517578, "action_query_norm": 523.0589294433594, "action_relation_loss": 0.00912585686892271, "auxiliary_loss_weight": 1.0, "epoch": 3.685687558465856, "flow_matching_loss": 0.06273225657641887, "grad_norm": 0.22368693351745605, "invalid_tail_samples": 24.3, "learning_rate": 9.820379432815414e-05, "loss": 0.0719, "positive_teacher_pairs": 26735.2, "relation_loss": 0.00912585686892271, "selected_pairs": 26735.2, "step": 3940, "student_distance_mean": 644.1102661132812, "teacher_distance_mean": 0.8521925926208496, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.00912585686892271, "weighted_relation_loss": 0.00912585686892271 }, { "action_query_batch_std": 11.757342529296874, "action_query_norm": 535.0652099609375, "action_relation_loss": 0.009068841114640236, "auxiliary_loss_weight": 1.0, "epoch": 3.695042095416277, "flow_matching_loss": 0.06582744829356671, "grad_norm": 0.27747005224227905, "invalid_tail_samples": 24.0, "learning_rate": 9.81891248393522e-05, "loss": 0.0749, "positive_teacher_pairs": 26802.2, "relation_loss": 0.009068841114640236, "selected_pairs": 26802.2, "step": 3950, "student_distance_mean": 664.9415405273437, "teacher_distance_mean": 0.8720831096172332, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.009068841114640236, "weighted_relation_loss": 0.009068841114640236 }, { "action_query_batch_std": 11.443089389801026, "action_query_norm": 528.0345153808594, "action_relation_loss": 0.00865544336847961, "auxiliary_loss_weight": 1.0, "epoch": 3.7043966323666977, "flow_matching_loss": 0.06311021745204926, "grad_norm": 0.14919711649417877, "invalid_tail_samples": 22.2, "learning_rate": 9.817439679621963e-05, "loss": 0.0718, "positive_teacher_pairs": 27225.0, "relation_loss": 0.00865544336847961, "selected_pairs": 27225.0, "step": 3960, "student_distance_mean": 644.1373229980469, "teacher_distance_mean": 0.8568024277687073, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.00865544336847961, "weighted_relation_loss": 0.00865544336847961 }, { "action_query_batch_std": 11.36579875946045, "action_query_norm": 521.5060546875, "action_relation_loss": 0.008751606941223145, "auxiliary_loss_weight": 1.0, "epoch": 3.713751169317119, "flow_matching_loss": 0.06542240455746651, "grad_norm": 0.183452770113945, "invalid_tail_samples": 24.0, "learning_rate": 9.815961021665243e-05, "loss": 0.0742, "positive_teacher_pairs": 26802.7, "relation_loss": 0.008751606941223145, "selected_pairs": 26802.7, "step": 3970, "student_distance_mean": 647.4305786132812, "teacher_distance_mean": 0.8558969020843505, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.008751606941223145, "weighted_relation_loss": 0.008751606941223145 }, { "action_query_batch_std": 11.521500492095948, "action_query_norm": 527.7269104003906, "action_relation_loss": 0.008873871574178339, "auxiliary_loss_weight": 1.0, "epoch": 3.72310570626754, "flow_matching_loss": 0.063118339702487, "grad_norm": 0.14750096201896667, "invalid_tail_samples": 25.8, "learning_rate": 9.814476511861763e-05, "loss": 0.072, "positive_teacher_pairs": 26387.8, "relation_loss": 0.008873871574178339, "selected_pairs": 26387.8, "step": 3980, "student_distance_mean": 655.2513122558594, "teacher_distance_mean": 0.8586973011493683, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.008873871574178339, "weighted_relation_loss": 0.008873871574178339 }, { "action_query_batch_std": 11.212532901763916, "action_query_norm": 514.1302429199219, "action_relation_loss": 0.008830083766952157, "auxiliary_loss_weight": 1.0, "epoch": 3.7324602432179605, "flow_matching_loss": 0.06279104501008988, "grad_norm": 0.1453801393508911, "invalid_tail_samples": 25.3, "learning_rate": 9.812986152015348e-05, "loss": 0.0716, "positive_teacher_pairs": 26509.3, "relation_loss": 0.008830083766952157, "selected_pairs": 26509.3, "step": 3990, "student_distance_mean": 636.4188903808594, "teacher_distance_mean": 0.8543035745620727, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.008830083766952157, "weighted_relation_loss": 0.008830083766952157 }, { "action_query_batch_std": 11.343321132659913, "action_query_norm": 518.8589691162109, "action_relation_loss": 0.008603299967944622, "auxiliary_loss_weight": 1.0, "epoch": 3.7418147801683816, "flow_matching_loss": 0.06175906173884869, "grad_norm": 0.1887207329273224, "invalid_tail_samples": 23.4, "learning_rate": 9.811489943936922e-05, "loss": 0.0704, "positive_teacher_pairs": 26943.1, "relation_loss": 0.008603299967944622, "selected_pairs": 26943.1, "step": 4000, "student_distance_mean": 642.6680480957032, "teacher_distance_mean": 0.8514031767845154, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.008603299967944622, "weighted_relation_loss": 0.008603299967944622 }, { "action_query_batch_std": 11.513274765014648, "action_query_norm": 527.3817443847656, "action_relation_loss": 0.009064314141869544, "auxiliary_loss_weight": 1.0, "epoch": 3.7511693171188027, "flow_matching_loss": 0.05991838201880455, "grad_norm": 0.20344886183738708, "invalid_tail_samples": 21.7, "learning_rate": 9.809987889444522e-05, "loss": 0.069, "positive_teacher_pairs": 27343.5, "relation_loss": 0.009064314141869544, "selected_pairs": 27343.5, "step": 4010, "student_distance_mean": 652.242236328125, "teacher_distance_mean": 0.854298448562622, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.009064314141869544, "weighted_relation_loss": 0.009064314141869544 }, { "action_query_batch_std": 11.61012659072876, "action_query_norm": 531.0349609375, "action_relation_loss": 0.008726724423468113, "auxiliary_loss_weight": 1.0, "epoch": 3.7605238540692234, "flow_matching_loss": 0.061090200766921045, "grad_norm": 0.21811826527118683, "invalid_tail_samples": 24.7, "learning_rate": 9.808479990363282e-05, "loss": 0.0698, "positive_teacher_pairs": 26659.5, "relation_loss": 0.008726724423468113, "selected_pairs": 26659.5, "step": 4020, "student_distance_mean": 660.4399230957031, "teacher_distance_mean": 0.8535185158252716, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.008726724423468113, "weighted_relation_loss": 0.008726724423468113 }, { "action_query_batch_std": 11.613894653320312, "action_query_norm": 525.3022033691407, "action_relation_loss": 0.00843637720681727, "auxiliary_loss_weight": 1.0, "epoch": 3.7698783910196445, "flow_matching_loss": 0.06406907960772515, "grad_norm": 0.2408963292837143, "invalid_tail_samples": 23.7, "learning_rate": 9.806966248525445e-05, "loss": 0.0725, "positive_teacher_pairs": 26875.0, "relation_loss": 0.00843637720681727, "selected_pairs": 26875.0, "step": 4030, "student_distance_mean": 657.653955078125, "teacher_distance_mean": 0.8642067015171051, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.00843637720681727, "weighted_relation_loss": 0.00843637720681727 }, { "action_query_batch_std": 11.609017944335937, "action_query_norm": 527.795458984375, "action_relation_loss": 0.00868230746127665, "auxiliary_loss_weight": 1.0, "epoch": 3.7792329279700656, "flow_matching_loss": 0.06224278174340725, "grad_norm": 0.20828811824321747, "invalid_tail_samples": 24.1, "learning_rate": 9.805446665770348e-05, "loss": 0.0709, "positive_teacher_pairs": 26783.4, "relation_loss": 0.00868230746127665, "selected_pairs": 26783.4, "step": 4040, "student_distance_mean": 654.7394226074218, "teacher_distance_mean": 0.8530355513095855, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.00868230746127665, "weighted_relation_loss": 0.00868230746127665 }, { "action_query_batch_std": 11.62100944519043, "action_query_norm": 527.8530517578125, "action_relation_loss": 0.008636985393241047, "auxiliary_loss_weight": 1.0, "epoch": 3.7885874649204867, "flow_matching_loss": 0.06426629982888699, "grad_norm": 0.14381836354732513, "invalid_tail_samples": 22.3, "learning_rate": 9.803921243944429e-05, "loss": 0.0729, "positive_teacher_pairs": 27195.7, "relation_loss": 0.008636985393241047, "selected_pairs": 27195.7, "step": 4050, "student_distance_mean": 655.7432495117188, "teacher_distance_mean": 0.8537177801132202, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.008636985393241047, "weighted_relation_loss": 0.008636985393241047 }, { "action_query_batch_std": 11.725759887695313, "action_query_norm": 530.4813232421875, "action_relation_loss": 0.008889113925397396, "auxiliary_loss_weight": 1.0, "epoch": 3.7979420018709074, "flow_matching_loss": 0.067115044221282, "grad_norm": 0.19868247210979462, "invalid_tail_samples": 24.5, "learning_rate": 9.802389984901218e-05, "loss": 0.076, "positive_teacher_pairs": 26687.4, "relation_loss": 0.008889113925397396, "selected_pairs": 26687.4, "step": 4060, "student_distance_mean": 661.3704528808594, "teacher_distance_mean": 0.8590235590934754, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.008889113925397396, "weighted_relation_loss": 0.008889113925397396 }, { "action_query_batch_std": 11.397092247009278, "action_query_norm": 524.3481323242188, "action_relation_loss": 0.008886589948087931, "auxiliary_loss_weight": 1.0, "epoch": 3.8072965388213285, "flow_matching_loss": 0.062447765842080116, "grad_norm": 0.19997991621494293, "invalid_tail_samples": 23.8, "learning_rate": 9.80085289050134e-05, "loss": 0.0713, "positive_teacher_pairs": 26848.1, "relation_loss": 0.008886589948087931, "selected_pairs": 26848.1, "step": 4070, "student_distance_mean": 644.2697937011719, "teacher_distance_mean": 0.8438610851764679, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.008886589948087931, "weighted_relation_loss": 0.008886589948087931 }, { "action_query_batch_std": 11.342367935180665, "action_query_norm": 521.92958984375, "action_relation_loss": 0.00924677224829793, "auxiliary_loss_weight": 1.0, "epoch": 3.816651075771749, "flow_matching_loss": 0.06648588702082633, "grad_norm": 0.1782485544681549, "invalid_tail_samples": 22.1, "learning_rate": 9.799309962612508e-05, "loss": 0.0757, "positive_teacher_pairs": 27242.0, "relation_loss": 0.00924677224829793, "selected_pairs": 27242.0, "step": 4080, "student_distance_mean": 640.6258728027344, "teacher_distance_mean": 0.8461915612220764, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.00924677224829793, "weighted_relation_loss": 0.00924677224829793 }, { "action_query_batch_std": 11.786080646514893, "action_query_norm": 535.1466186523437, "action_relation_loss": 0.008809956256300211, "auxiliary_loss_weight": 1.0, "epoch": 3.82600561272217, "flow_matching_loss": 0.06197243221104145, "grad_norm": 0.22956182062625885, "invalid_tail_samples": 23.7, "learning_rate": 9.797761203109527e-05, "loss": 0.0708, "positive_teacher_pairs": 26869.9, "relation_loss": 0.008809956256300211, "selected_pairs": 26869.9, "step": 4090, "student_distance_mean": 666.7864013671875, "teacher_distance_mean": 0.8660725295543671, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.008809956256300211, "weighted_relation_loss": 0.008809956256300211 }, { "action_query_batch_std": 11.616016292572022, "action_query_norm": 530.0581176757812, "action_relation_loss": 0.008315176609903574, "auxiliary_loss_weight": 1.0, "epoch": 3.8353601496725913, "flow_matching_loss": 0.06221117079257965, "grad_norm": 0.19590112566947937, "invalid_tail_samples": 22.0, "learning_rate": 9.796206613874283e-05, "loss": 0.0705, "positive_teacher_pairs": 27269.9, "relation_loss": 0.008315176609903574, "selected_pairs": 27269.9, "step": 4100, "student_distance_mean": 658.3335632324219, "teacher_distance_mean": 0.8584900915622711, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.008315176609903574, "weighted_relation_loss": 0.008315176609903574 }, { "action_query_batch_std": 11.59937858581543, "action_query_norm": 526.6539184570313, "action_relation_loss": 0.00897711692377925, "auxiliary_loss_weight": 1.0, "epoch": 3.8447146866230124, "flow_matching_loss": 0.06133610121905804, "grad_norm": 0.17817972600460052, "invalid_tail_samples": 22.8, "learning_rate": 9.794646196795754e-05, "loss": 0.0703, "positive_teacher_pairs": 27082.6, "relation_loss": 0.00897711692377925, "selected_pairs": 27082.6, "step": 4110, "student_distance_mean": 655.230712890625, "teacher_distance_mean": 0.8581604957580566, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.00897711692377925, "weighted_relation_loss": 0.00897711692377925 }, { "action_query_batch_std": 11.480801010131836, "action_query_norm": 523.0421447753906, "action_relation_loss": 0.008726261649280786, "auxiliary_loss_weight": 1.0, "epoch": 3.854069223573433, "flow_matching_loss": 0.06347341500222684, "grad_norm": 0.17389321327209473, "invalid_tail_samples": 26.0, "learning_rate": 9.793079953769987e-05, "loss": 0.0722, "positive_teacher_pairs": 26350.1, "relation_loss": 0.008726261649280786, "selected_pairs": 26350.1, "step": 4120, "student_distance_mean": 651.3886901855469, "teacher_distance_mean": 0.8556612491607666, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.008726261649280786, "weighted_relation_loss": 0.008726261649280786 }, { "action_query_batch_std": 11.466103744506835, "action_query_norm": 525.1503479003907, "action_relation_loss": 0.008969072159379721, "auxiliary_loss_weight": 1.0, "epoch": 3.863423760523854, "flow_matching_loss": 0.06300712041556836, "grad_norm": 0.11632765084505081, "invalid_tail_samples": 24.2, "learning_rate": 9.79150788670012e-05, "loss": 0.072, "positive_teacher_pairs": 26756.2, "relation_loss": 0.008969072159379721, "selected_pairs": 26756.2, "step": 4130, "student_distance_mean": 650.1571105957031, "teacher_distance_mean": 0.8467204988002777, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.008969072159379721, "weighted_relation_loss": 0.008969072159379721 }, { "action_query_batch_std": 11.925046062469482, "action_query_norm": 538.6902404785156, "action_relation_loss": 0.008689130423590541, "auxiliary_loss_weight": 1.0, "epoch": 3.872778297474275, "flow_matching_loss": 0.060179611667990685, "grad_norm": 0.1180482879281044, "invalid_tail_samples": 22.8, "learning_rate": 9.78992999749636e-05, "loss": 0.0689, "positive_teacher_pairs": 27103.1, "relation_loss": 0.008689130423590541, "selected_pairs": 27103.1, "step": 4140, "student_distance_mean": 672.8606628417969, "teacher_distance_mean": 0.8560358762741089, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.008689130423590541, "weighted_relation_loss": 0.008689130423590541 }, { "action_query_batch_std": 11.833697605133057, "action_query_norm": 537.6579711914062, "action_relation_loss": 0.00873233238235116, "auxiliary_loss_weight": 1.0, "epoch": 3.882132834424696, "flow_matching_loss": 0.06193920634686947, "grad_norm": 0.1894487738609314, "invalid_tail_samples": 24.6, "learning_rate": 9.788346288075994e-05, "loss": 0.0707, "positive_teacher_pairs": 26664.0, "relation_loss": 0.00873233238235116, "selected_pairs": 26664.0, "step": 4150, "student_distance_mean": 668.5505126953125, "teacher_distance_mean": 0.8560909986495971, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.00873233238235116, "weighted_relation_loss": 0.00873233238235116 }, { "action_query_batch_std": 11.763989353179932, "action_query_norm": 534.6222900390625, "action_relation_loss": 0.009373916499316692, "auxiliary_loss_weight": 1.0, "epoch": 3.891487371375117, "flow_matching_loss": 0.06361658833920955, "grad_norm": 0.19272571802139282, "invalid_tail_samples": 24.6, "learning_rate": 9.786756760363373e-05, "loss": 0.073, "positive_teacher_pairs": 26664.3, "relation_loss": 0.009373916499316692, "selected_pairs": 26664.3, "step": 4160, "student_distance_mean": 665.9774169921875, "teacher_distance_mean": 0.8549234867095947, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.009373916499316692, "weighted_relation_loss": 0.009373916499316692 }, { "action_query_batch_std": 11.442680931091308, "action_query_norm": 521.9003234863281, "action_relation_loss": 0.008694979175925256, "auxiliary_loss_weight": 1.0, "epoch": 3.900841908325538, "flow_matching_loss": 0.06229631416499615, "grad_norm": 0.14524397253990173, "invalid_tail_samples": 24.0, "learning_rate": 9.78516141628993e-05, "loss": 0.071, "positive_teacher_pairs": 26811.7, "relation_loss": 0.008694979175925256, "selected_pairs": 26811.7, "step": 4170, "student_distance_mean": 647.174365234375, "teacher_distance_mean": 0.8499408423900604, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.008694979175925256, "weighted_relation_loss": 0.008694979175925256 }, { "action_query_batch_std": 11.53648796081543, "action_query_norm": 527.6170043945312, "action_relation_loss": 0.008771409606561064, "auxiliary_loss_weight": 1.0, "epoch": 3.9101964452759588, "flow_matching_loss": 0.06198308952152729, "grad_norm": 0.15427744388580322, "invalid_tail_samples": 27.2, "learning_rate": 9.783560257794154e-05, "loss": 0.0708, "positive_teacher_pairs": 26062.4, "relation_loss": 0.008771409606561064, "selected_pairs": 26062.4, "step": 4180, "student_distance_mean": 657.73837890625, "teacher_distance_mean": 0.860990172624588, "valid_action_samples": 228.8, "weighted_auxiliary_loss": 0.008771409606561064, "weighted_relation_loss": 0.008771409606561064 }, { "action_query_batch_std": 11.539818859100341, "action_query_norm": 524.6334594726562, "action_relation_loss": 0.008731224574148655, "auxiliary_loss_weight": 1.0, "epoch": 3.91955098222638, "flow_matching_loss": 0.06288236603140832, "grad_norm": 0.194705531001091, "invalid_tail_samples": 27.4, "learning_rate": 9.781953286821603e-05, "loss": 0.0716, "positive_teacher_pairs": 26019.4, "relation_loss": 0.008731224574148655, "selected_pairs": 26019.4, "step": 4190, "student_distance_mean": 656.2041625976562, "teacher_distance_mean": 0.8541475296020508, "valid_action_samples": 228.6, "weighted_auxiliary_loss": 0.008731224574148655, "weighted_relation_loss": 0.008731224574148655 }, { "action_query_batch_std": 11.649196529388428, "action_query_norm": 530.7073791503906, "action_relation_loss": 0.008860425790771842, "auxiliary_loss_weight": 1.0, "epoch": 3.9289055191768005, "flow_matching_loss": 0.06196849048137665, "grad_norm": 0.14617300033569336, "invalid_tail_samples": 22.6, "learning_rate": 9.780340505324901e-05, "loss": 0.0708, "positive_teacher_pairs": 27131.4, "relation_loss": 0.008860425790771842, "selected_pairs": 27131.4, "step": 4200, "student_distance_mean": 657.0970581054687, "teacher_distance_mean": 0.8545210659503937, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.008860425790771842, "weighted_relation_loss": 0.008860425790771842 }, { "action_query_batch_std": 11.646846389770507, "action_query_norm": 538.2534912109375, "action_relation_loss": 0.008927618246525526, "auxiliary_loss_weight": 1.0, "epoch": 3.9382600561272216, "flow_matching_loss": 0.06352746561169624, "grad_norm": 0.150462344288826, "invalid_tail_samples": 24.3, "learning_rate": 9.778721915263727e-05, "loss": 0.0725, "positive_teacher_pairs": 26735.3, "relation_loss": 0.008927618246525526, "selected_pairs": 26735.3, "step": 4210, "student_distance_mean": 660.6304992675781, "teacher_distance_mean": 0.849684226512909, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.008927618246525526, "weighted_relation_loss": 0.008927618246525526 }, { "action_query_batch_std": 11.929927349090576, "action_query_norm": 541.2610900878906, "action_relation_loss": 0.00881232083775103, "auxiliary_loss_weight": 1.0, "epoch": 3.9476145930776427, "flow_matching_loss": 0.06166811920702457, "grad_norm": 0.22025331854820251, "invalid_tail_samples": 26.0, "learning_rate": 9.777097518604824e-05, "loss": 0.0705, "positive_teacher_pairs": 26348.0, "relation_loss": 0.00881232083775103, "selected_pairs": 26348.0, "step": 4220, "student_distance_mean": 676.1723815917969, "teacher_distance_mean": 0.859817099571228, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.00881232083775103, "weighted_relation_loss": 0.00881232083775103 }, { "action_query_batch_std": 11.778873348236084, "action_query_norm": 535.3246704101563, "action_relation_loss": 0.008354781288653612, "auxiliary_loss_weight": 1.0, "epoch": 3.956969130028064, "flow_matching_loss": 0.05979708880186081, "grad_norm": 0.16188940405845642, "invalid_tail_samples": 26.2, "learning_rate": 9.775467317321984e-05, "loss": 0.0682, "positive_teacher_pairs": 26295.2, "relation_loss": 0.008354781288653612, "selected_pairs": 26295.2, "step": 4230, "student_distance_mean": 669.1353820800781, "teacher_distance_mean": 0.8584621667861938, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.008354781288653612, "weighted_relation_loss": 0.008354781288653612 }, { "action_query_batch_std": 11.72295970916748, "action_query_norm": 533.3174072265625, "action_relation_loss": 0.009031633660197259, "auxiliary_loss_weight": 1.0, "epoch": 3.9663236669784845, "flow_matching_loss": 0.05958803594112396, "grad_norm": 0.1510109007358551, "invalid_tail_samples": 24.3, "learning_rate": 9.773831313396055e-05, "loss": 0.0686, "positive_teacher_pairs": 26737.3, "relation_loss": 0.009031633660197259, "selected_pairs": 26737.3, "step": 4240, "student_distance_mean": 664.0713073730469, "teacher_distance_mean": 0.8500476002693176, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.009031633660197259, "weighted_relation_loss": 0.009031633660197259 }, { "action_query_batch_std": 11.694343566894531, "action_query_norm": 529.82236328125, "action_relation_loss": 0.00854413821361959, "auxiliary_loss_weight": 1.0, "epoch": 3.9756782039289056, "flow_matching_loss": 0.058688294142484665, "grad_norm": 0.14671464264392853, "invalid_tail_samples": 24.2, "learning_rate": 9.77218950881494e-05, "loss": 0.0672, "positive_teacher_pairs": 26757.6, "relation_loss": 0.00854413821361959, "selected_pairs": 26757.6, "step": 4250, "student_distance_mean": 661.8221313476563, "teacher_distance_mean": 0.8525583028793335, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.00854413821361959, "weighted_relation_loss": 0.00854413821361959 }, { "action_query_batch_std": 11.480155754089356, "action_query_norm": 526.7160034179688, "action_relation_loss": 0.009115222375839949, "auxiliary_loss_weight": 1.0, "epoch": 3.9850327408793262, "flow_matching_loss": 0.06206209100782871, "grad_norm": 0.17983391880989075, "invalid_tail_samples": 22.2, "learning_rate": 9.770541905573583e-05, "loss": 0.0712, "positive_teacher_pairs": 27221.4, "relation_loss": 0.009115222375839949, "selected_pairs": 27221.4, "step": 4260, "student_distance_mean": 650.2262268066406, "teacher_distance_mean": 0.8456102311611176, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.009115222375839949, "weighted_relation_loss": 0.009115222375839949 }, { "action_query_batch_std": 11.667091655731202, "action_query_norm": 532.1299560546875, "action_relation_loss": 0.00843229778110981, "auxiliary_loss_weight": 1.0, "epoch": 3.9943872778297473, "flow_matching_loss": 0.06138465143740177, "grad_norm": 0.1489385962486267, "invalid_tail_samples": 23.5, "learning_rate": 9.768888505673976e-05, "loss": 0.0698, "positive_teacher_pairs": 26926.1, "relation_loss": 0.00843229778110981, "selected_pairs": 26926.1, "step": 4270, "student_distance_mean": 662.2837097167969, "teacher_distance_mean": 0.8535879731178284, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.00843229778110981, "weighted_relation_loss": 0.00843229778110981 }, { "action_query_batch_std": 11.900938034057617, "action_query_norm": 542.6484130859375, "action_relation_loss": 0.008447378408163786, "auxiliary_loss_weight": 1.0, "epoch": 4.003741814780168, "flow_matching_loss": 0.05960061028599739, "grad_norm": 0.13511288166046143, "invalid_tail_samples": 22.1, "learning_rate": 9.767229311125162e-05, "loss": 0.068, "positive_teacher_pairs": 24219.5, "relation_loss": 0.008447378408163786, "selected_pairs": 24219.5, "step": 4280, "student_distance_mean": 672.4222961425781, "teacher_distance_mean": 0.8598978579044342, "valid_action_samples": 214.0, "weighted_auxiliary_loss": 0.008447378408163786, "weighted_relation_loss": 0.008447378408163786 }, { "action_query_batch_std": 11.671993827819824, "action_query_norm": 531.60126953125, "action_relation_loss": 0.008803468104451895, "auxiliary_loss_weight": 1.0, "epoch": 4.0130963517305895, "flow_matching_loss": 0.05962501876056194, "grad_norm": 0.1561276763677597, "invalid_tail_samples": 23.0, "learning_rate": 9.765564323943211e-05, "loss": 0.0684, "positive_teacher_pairs": 27033.7, "relation_loss": 0.008803468104451895, "selected_pairs": 27033.7, "step": 4290, "student_distance_mean": 663.286181640625, "teacher_distance_mean": 0.8497637033462524, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.008803468104451895, "weighted_relation_loss": 0.008803468104451895 }, { "action_query_batch_std": 11.960212802886963, "action_query_norm": 543.48369140625, "action_relation_loss": 0.008270103065297008, "auxiliary_loss_weight": 1.0, "epoch": 4.022450888681011, "flow_matching_loss": 0.05966506525874138, "grad_norm": 0.17744751274585724, "invalid_tail_samples": 22.7, "learning_rate": 9.763893546151244e-05, "loss": 0.0679, "positive_teacher_pairs": 27106.7, "relation_loss": 0.008270103065297008, "selected_pairs": 27106.7, "step": 4300, "student_distance_mean": 677.2879943847656, "teacher_distance_mean": 0.8561823725700378, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.008270103065297008, "weighted_relation_loss": 0.008270103065297008 }, { "action_query_batch_std": 12.077787590026855, "action_query_norm": 552.2221069335938, "action_relation_loss": 0.008147026179358363, "auxiliary_loss_weight": 1.0, "epoch": 4.031805425631431, "flow_matching_loss": 0.060899204760789874, "grad_norm": 0.158807173371315, "invalid_tail_samples": 25.2, "learning_rate": 9.762216979779412e-05, "loss": 0.069, "positive_teacher_pairs": 26526.0, "relation_loss": 0.008147026179358363, "selected_pairs": 26526.0, "step": 4310, "student_distance_mean": 683.9251525878906, "teacher_distance_mean": 0.8548923313617707, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.008147026179358363, "weighted_relation_loss": 0.008147026179358363 }, { "action_query_batch_std": 12.080677700042724, "action_query_norm": 548.0977172851562, "action_relation_loss": 0.008108168700709939, "auxiliary_loss_weight": 1.0, "epoch": 4.041159962581852, "flow_matching_loss": 0.059126587584614754, "grad_norm": 0.17925089597702026, "invalid_tail_samples": 23.6, "learning_rate": 9.760534626864902e-05, "loss": 0.0672, "positive_teacher_pairs": 26904.8, "relation_loss": 0.008108168700709939, "selected_pairs": 26904.8, "step": 4320, "student_distance_mean": 682.7647827148437, "teacher_distance_mean": 0.8691844344139099, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.008108168700709939, "weighted_relation_loss": 0.008108168700709939 }, { "action_query_batch_std": 12.01506519317627, "action_query_norm": 547.5630798339844, "action_relation_loss": 0.008084503561258316, "auxiliary_loss_weight": 1.0, "epoch": 4.050514499532273, "flow_matching_loss": 0.06126302070915699, "grad_norm": 0.19939613342285156, "invalid_tail_samples": 22.6, "learning_rate": 9.758846489451931e-05, "loss": 0.0693, "positive_teacher_pairs": 27129.6, "relation_loss": 0.008084503561258316, "selected_pairs": 27129.6, "step": 4330, "student_distance_mean": 680.5261596679687, "teacher_distance_mean": 0.854158878326416, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.008084503561258316, "weighted_relation_loss": 0.008084503561258316 }, { "action_query_batch_std": 11.8937255859375, "action_query_norm": 544.5213806152344, "action_relation_loss": 0.008278994262218476, "auxiliary_loss_weight": 1.0, "epoch": 4.059869036482694, "flow_matching_loss": 0.05807652808725834, "grad_norm": 0.16284272074699402, "invalid_tail_samples": 23.6, "learning_rate": 9.757152569591748e-05, "loss": 0.0664, "positive_teacher_pairs": 26892.2, "relation_loss": 0.008278994262218476, "selected_pairs": 26892.2, "step": 4340, "student_distance_mean": 674.5519958496094, "teacher_distance_mean": 0.8538895905017853, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.008278994262218476, "weighted_relation_loss": 0.008278994262218476 }, { "action_query_batch_std": 11.98679485321045, "action_query_norm": 547.0571655273437, "action_relation_loss": 0.008473299164324998, "auxiliary_loss_weight": 1.0, "epoch": 4.069223573433115, "flow_matching_loss": 0.05968603864312172, "grad_norm": 0.1763816624879837, "invalid_tail_samples": 24.6, "learning_rate": 9.75545286934262e-05, "loss": 0.0682, "positive_teacher_pairs": 26662.3, "relation_loss": 0.008473299164324998, "selected_pairs": 26662.3, "step": 4350, "student_distance_mean": 676.3232238769531, "teacher_distance_mean": 0.8594427227973938, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.008473299164324998, "weighted_relation_loss": 0.008473299164324998 }, { "action_query_batch_std": 11.836299800872803, "action_query_norm": 539.1053588867187, "action_relation_loss": 0.00817043730057776, "auxiliary_loss_weight": 1.0, "epoch": 4.078578110383536, "flow_matching_loss": 0.059566762298345566, "grad_norm": 0.15348635613918304, "invalid_tail_samples": 23.5, "learning_rate": 9.753747390769847e-05, "loss": 0.0677, "positive_teacher_pairs": 26919.9, "relation_loss": 0.00817043730057776, "selected_pairs": 26919.9, "step": 4360, "student_distance_mean": 671.1717529296875, "teacher_distance_mean": 0.8522559344768524, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.00817043730057776, "weighted_relation_loss": 0.00817043730057776 }, { "action_query_batch_std": 11.944089317321778, "action_query_norm": 539.7230407714844, "action_relation_loss": 0.008432523440569639, "auxiliary_loss_weight": 1.0, "epoch": 4.087932647333957, "flow_matching_loss": 0.05810922086238861, "grad_norm": 0.17059172689914703, "invalid_tail_samples": 25.2, "learning_rate": 9.752036135945744e-05, "loss": 0.0665, "positive_teacher_pairs": 26532.4, "relation_loss": 0.008432523440569639, "selected_pairs": 26532.4, "step": 4370, "student_distance_mean": 674.54375, "teacher_distance_mean": 0.8547831535339355, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.008432523440569639, "weighted_relation_loss": 0.008432523440569639 }, { "action_query_batch_std": 12.164586544036865, "action_query_norm": 552.2316162109375, "action_relation_loss": 0.008577777491882443, "auxiliary_loss_weight": 1.0, "epoch": 4.097287184284378, "flow_matching_loss": 0.060071374848484994, "grad_norm": 0.15753722190856934, "invalid_tail_samples": 23.2, "learning_rate": 9.750319106949649e-05, "loss": 0.0686, "positive_teacher_pairs": 26993.3, "relation_loss": 0.008577777491882443, "selected_pairs": 26993.3, "step": 4380, "student_distance_mean": 683.6614624023438, "teacher_distance_mean": 0.8566392600536347, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.008577777491882443, "weighted_relation_loss": 0.008577777491882443 }, { "action_query_batch_std": 12.09965705871582, "action_query_norm": 549.2957153320312, "action_relation_loss": 0.008540068473666906, "auxiliary_loss_weight": 1.0, "epoch": 4.106641721234799, "flow_matching_loss": 0.06358317025005818, "grad_norm": 0.17464850842952728, "invalid_tail_samples": 22.5, "learning_rate": 9.748596305867913e-05, "loss": 0.0721, "positive_teacher_pairs": 27151.0, "relation_loss": 0.008540068473666906, "selected_pairs": 27151.0, "step": 4390, "student_distance_mean": 681.0330627441406, "teacher_distance_mean": 0.8620568454265595, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.008540068473666906, "weighted_relation_loss": 0.008540068473666906 }, { "action_query_batch_std": 11.935565185546874, "action_query_norm": 541.2883728027343, "action_relation_loss": 0.008170740958303214, "auxiliary_loss_weight": 1.0, "epoch": 4.11599625818522, "flow_matching_loss": 0.061221657693386076, "grad_norm": 0.14446017146110535, "invalid_tail_samples": 26.2, "learning_rate": 9.746867734793903e-05, "loss": 0.0694, "positive_teacher_pairs": 26302.5, "relation_loss": 0.008170740958303214, "selected_pairs": 26302.5, "step": 4400, "student_distance_mean": 679.2653625488281, "teacher_distance_mean": 0.8513237237930298, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.008170740958303214, "weighted_relation_loss": 0.008170740958303214 }, { "action_query_batch_std": 11.786076736450195, "action_query_norm": 535.3311157226562, "action_relation_loss": 0.00851702936924994, "auxiliary_loss_weight": 1.0, "epoch": 4.125350795135641, "flow_matching_loss": 0.05995200872421265, "grad_norm": 0.1613791286945343, "invalid_tail_samples": 22.7, "learning_rate": 9.745133395827993e-05, "loss": 0.0685, "positive_teacher_pairs": 27102.3, "relation_loss": 0.00851702936924994, "selected_pairs": 27102.3, "step": 4410, "student_distance_mean": 666.05380859375, "teacher_distance_mean": 0.8472659826278687, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.00851702936924994, "weighted_relation_loss": 0.00851702936924994 }, { "action_query_batch_std": 11.988449096679688, "action_query_norm": 544.2288269042969, "action_relation_loss": 0.00854443134739995, "auxiliary_loss_weight": 1.0, "epoch": 4.134705332086062, "flow_matching_loss": 0.06109824292361736, "grad_norm": 0.1563686579465866, "invalid_tail_samples": 23.5, "learning_rate": 9.743393291077572e-05, "loss": 0.0696, "positive_teacher_pairs": 26930.6, "relation_loss": 0.00854443134739995, "selected_pairs": 26930.6, "step": 4420, "student_distance_mean": 679.5070678710938, "teacher_distance_mean": 0.8570042788982392, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.00854443134739995, "weighted_relation_loss": 0.00854443134739995 }, { "action_query_batch_std": 12.050808525085449, "action_query_norm": 548.8824279785156, "action_relation_loss": 0.00807698369026184, "auxiliary_loss_weight": 1.0, "epoch": 4.144059869036482, "flow_matching_loss": 0.060737207904458045, "grad_norm": 0.15451684594154358, "invalid_tail_samples": 25.2, "learning_rate": 9.741647422657028e-05, "loss": 0.0688, "positive_teacher_pairs": 26530.8, "relation_loss": 0.00807698369026184, "selected_pairs": 26530.8, "step": 4430, "student_distance_mean": 683.3437805175781, "teacher_distance_mean": 0.8581833899021148, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.00807698369026184, "weighted_relation_loss": 0.00807698369026184 }, { "action_query_batch_std": 11.880238723754882, "action_query_norm": 539.6240295410156, "action_relation_loss": 0.008226988837122917, "auxiliary_loss_weight": 1.0, "epoch": 4.153414405986903, "flow_matching_loss": 0.05792598500847816, "grad_norm": 0.1662120372056961, "invalid_tail_samples": 24.2, "learning_rate": 9.739895792687758e-05, "loss": 0.0662, "positive_teacher_pairs": 26760.8, "relation_loss": 0.008226988837122917, "selected_pairs": 26760.8, "step": 4440, "student_distance_mean": 669.9554077148438, "teacher_distance_mean": 0.848652821779251, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.008226988837122917, "weighted_relation_loss": 0.008226988837122917 }, { "action_query_batch_std": 12.061523056030273, "action_query_norm": 549.3589172363281, "action_relation_loss": 0.008112247847020627, "auxiliary_loss_weight": 1.0, "epoch": 4.1627689429373245, "flow_matching_loss": 0.0595002107322216, "grad_norm": 0.19112183153629303, "invalid_tail_samples": 23.4, "learning_rate": 9.738138403298157e-05, "loss": 0.0676, "positive_teacher_pairs": 26949.0, "relation_loss": 0.008112247847020627, "selected_pairs": 26949.0, "step": 4450, "student_distance_mean": 681.8233703613281, "teacher_distance_mean": 0.8586035370826721, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.008112247847020627, "weighted_relation_loss": 0.008112247847020627 }, { "action_query_batch_std": 12.051338958740235, "action_query_norm": 547.9023132324219, "action_relation_loss": 0.007954035140573978, "auxiliary_loss_weight": 1.0, "epoch": 4.172123479887746, "flow_matching_loss": 0.060754455253481866, "grad_norm": 0.18452142179012299, "invalid_tail_samples": 22.4, "learning_rate": 9.736375256623619e-05, "loss": 0.0687, "positive_teacher_pairs": 27174.7, "relation_loss": 0.007954035140573978, "selected_pairs": 27174.7, "step": 4460, "student_distance_mean": 679.0957763671875, "teacher_distance_mean": 0.8532196283340454, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.007954035140573978, "weighted_relation_loss": 0.007954035140573978 }, { "action_query_batch_std": 12.20341625213623, "action_query_norm": 550.4449523925781, "action_relation_loss": 0.00859150062315166, "auxiliary_loss_weight": 1.0, "epoch": 4.181478016838167, "flow_matching_loss": 0.06136949881911278, "grad_norm": 0.15827426314353943, "invalid_tail_samples": 24.8, "learning_rate": 9.734606354806533e-05, "loss": 0.07, "positive_teacher_pairs": 26616.6, "relation_loss": 0.00859150062315166, "selected_pairs": 26616.6, "step": 4470, "student_distance_mean": 693.9561950683594, "teacher_distance_mean": 0.8553594470024108, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.00859150062315166, "weighted_relation_loss": 0.00859150062315166 }, { "action_query_batch_std": 12.369585514068604, "action_query_norm": 555.1101989746094, "action_relation_loss": 0.008346514077857137, "auxiliary_loss_weight": 1.0, "epoch": 4.190832553788588, "flow_matching_loss": 0.05750337317585945, "grad_norm": 0.16128836572170258, "invalid_tail_samples": 23.8, "learning_rate": 9.73283169999628e-05, "loss": 0.0658, "positive_teacher_pairs": 26854.5, "relation_loss": 0.008346514077857137, "selected_pairs": 26854.5, "step": 4480, "student_distance_mean": 698.8798156738281, "teacher_distance_mean": 0.8572259604930877, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.008346514077857137, "weighted_relation_loss": 0.008346514077857137 }, { "action_query_batch_std": 12.248534297943115, "action_query_norm": 550.6796508789063, "action_relation_loss": 0.007712256722152233, "auxiliary_loss_weight": 1.0, "epoch": 4.200187090739009, "flow_matching_loss": 0.057147853448987006, "grad_norm": 0.139438658952713, "invalid_tail_samples": 24.4, "learning_rate": 9.731051294349238e-05, "loss": 0.0649, "positive_teacher_pairs": 26718.2, "relation_loss": 0.007712256722152233, "selected_pairs": 26718.2, "step": 4490, "student_distance_mean": 692.5908447265625, "teacher_distance_mean": 0.8595609426498413, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.007712256722152233, "weighted_relation_loss": 0.007712256722152233 }, { "action_query_batch_std": 12.371457195281982, "action_query_norm": 558.41337890625, "action_relation_loss": 0.008143204776570202, "auxiliary_loss_weight": 1.0, "epoch": 4.209541627689429, "flow_matching_loss": 0.05773521587252617, "grad_norm": 0.12655611336231232, "invalid_tail_samples": 24.3, "learning_rate": 9.729265140028762e-05, "loss": 0.0659, "positive_teacher_pairs": 26734.2, "relation_loss": 0.008143204776570202, "selected_pairs": 26734.2, "step": 4500, "student_distance_mean": 699.8782592773438, "teacher_distance_mean": 0.8598315060138703, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.008143204776570202, "weighted_relation_loss": 0.008143204776570202 }, { "action_query_batch_std": 12.472532367706298, "action_query_norm": 562.1795715332031, "action_relation_loss": 0.007986783143132925, "auxiliary_loss_weight": 1.0, "epoch": 4.21889616463985, "flow_matching_loss": 0.058275171741843226, "grad_norm": 0.1185244545340538, "invalid_tail_samples": 22.2, "learning_rate": 9.727473239205201e-05, "loss": 0.0663, "positive_teacher_pairs": 27220.2, "relation_loss": 0.007986783143132925, "selected_pairs": 27220.2, "step": 4510, "student_distance_mean": 704.4369140625, "teacher_distance_mean": 0.868209844827652, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.007986783143132925, "weighted_relation_loss": 0.007986783143132925 }, { "action_query_batch_std": 12.224381351470948, "action_query_norm": 555.1544128417969, "action_relation_loss": 0.007983820978552103, "auxiliary_loss_weight": 1.0, "epoch": 4.228250701590271, "flow_matching_loss": 0.06267208643257619, "grad_norm": 0.13840679824352264, "invalid_tail_samples": 23.8, "learning_rate": 9.725675594055883e-05, "loss": 0.0707, "positive_teacher_pairs": 26849.1, "relation_loss": 0.007983820978552103, "selected_pairs": 26849.1, "step": 4520, "student_distance_mean": 692.6042114257813, "teacher_distance_mean": 0.8600769460201263, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.007983820978552103, "weighted_relation_loss": 0.007983820978552103 }, { "action_query_batch_std": 12.42706937789917, "action_query_norm": 560.7150695800781, "action_relation_loss": 0.008058831002563238, "auxiliary_loss_weight": 1.0, "epoch": 4.237605238540692, "flow_matching_loss": 0.05967894345521927, "grad_norm": 0.1266200989484787, "invalid_tail_samples": 23.8, "learning_rate": 9.723872206765116e-05, "loss": 0.0677, "positive_teacher_pairs": 26843.8, "relation_loss": 0.008058831002563238, "selected_pairs": 26843.8, "step": 4530, "student_distance_mean": 703.5183898925782, "teacher_distance_mean": 0.8624886691570282, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.008058831002563238, "weighted_relation_loss": 0.008058831002563238 }, { "action_query_batch_std": 12.320631980895996, "action_query_norm": 558.9360534667969, "action_relation_loss": 0.007912500714883208, "auxiliary_loss_weight": 1.0, "epoch": 4.2469597754911135, "flow_matching_loss": 0.06075633466243744, "grad_norm": 0.14556533098220825, "invalid_tail_samples": 25.0, "learning_rate": 9.722063079524185e-05, "loss": 0.0687, "positive_teacher_pairs": 26571.7, "relation_loss": 0.007912500714883208, "selected_pairs": 26571.7, "step": 4540, "student_distance_mean": 696.7991821289063, "teacher_distance_mean": 0.854794156551361, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.007912500714883208, "weighted_relation_loss": 0.007912500714883208 }, { "action_query_batch_std": 12.29130973815918, "action_query_norm": 555.2191223144531, "action_relation_loss": 0.008702426496893168, "auxiliary_loss_weight": 1.0, "epoch": 4.256314312441534, "flow_matching_loss": 0.06138659082353115, "grad_norm": 0.13944193720817566, "invalid_tail_samples": 22.1, "learning_rate": 9.720248214531351e-05, "loss": 0.0701, "positive_teacher_pairs": 27244.9, "relation_loss": 0.008702426496893168, "selected_pairs": 27244.9, "step": 4550, "student_distance_mean": 693.1795532226563, "teacher_distance_mean": 0.8614430844783783, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.008702426496893168, "weighted_relation_loss": 0.008702426496893168 }, { "action_query_batch_std": 12.187449550628662, "action_query_norm": 552.0975891113281, "action_relation_loss": 0.008246382419019937, "auxiliary_loss_weight": 1.0, "epoch": 4.265668849391955, "flow_matching_loss": 0.05881249122321606, "grad_norm": 0.1949227899312973, "invalid_tail_samples": 25.5, "learning_rate": 9.718427613991848e-05, "loss": 0.0671, "positive_teacher_pairs": 26466.5, "relation_loss": 0.008246382419019937, "selected_pairs": 26466.5, "step": 4560, "student_distance_mean": 689.9405578613281, "teacher_distance_mean": 0.8586371839046478, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.008246382419019937, "weighted_relation_loss": 0.008246382419019937 }, { "action_query_batch_std": 12.024177551269531, "action_query_norm": 546.5608093261719, "action_relation_loss": 0.007722750585526228, "auxiliary_loss_weight": 1.0, "epoch": 4.275023386342376, "flow_matching_loss": 0.05970337279140949, "grad_norm": 0.18262989819049835, "invalid_tail_samples": 25.8, "learning_rate": 9.716601280117873e-05, "loss": 0.0674, "positive_teacher_pairs": 26393.0, "relation_loss": 0.007722750585526228, "selected_pairs": 26393.0, "step": 4570, "student_distance_mean": 680.5264282226562, "teacher_distance_mean": 0.858333170413971, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.007722750585526228, "weighted_relation_loss": 0.007722750585526228 }, { "action_query_batch_std": 12.00232629776001, "action_query_norm": 542.8940856933593, "action_relation_loss": 0.008000527787953616, "auxiliary_loss_weight": 1.0, "epoch": 4.284377923292797, "flow_matching_loss": 0.06016770265996456, "grad_norm": 0.23724621534347534, "invalid_tail_samples": 21.9, "learning_rate": 9.714769215128596e-05, "loss": 0.0682, "positive_teacher_pairs": 27292.4, "relation_loss": 0.008000527787953616, "selected_pairs": 27292.4, "step": 4580, "student_distance_mean": 678.5901611328125, "teacher_distance_mean": 0.8537873804569245, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.008000527787953616, "weighted_relation_loss": 0.008000527787953616 }, { "action_query_batch_std": 12.33242483139038, "action_query_norm": 555.2116455078125, "action_relation_loss": 0.00820014444179833, "auxiliary_loss_weight": 1.0, "epoch": 4.293732460243218, "flow_matching_loss": 0.060404497757554056, "grad_norm": 0.22604764997959137, "invalid_tail_samples": 23.9, "learning_rate": 9.712931421250152e-05, "loss": 0.0686, "positive_teacher_pairs": 26826.6, "relation_loss": 0.00820014444179833, "selected_pairs": 26826.6, "step": 4590, "student_distance_mean": 696.3653747558594, "teacher_distance_mean": 0.8575679302215576, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.00820014444179833, "weighted_relation_loss": 0.00820014444179833 }, { "action_query_batch_std": 12.305530071258545, "action_query_norm": 558.0731628417968, "action_relation_loss": 0.007960132788866758, "auxiliary_loss_weight": 1.0, "epoch": 4.303086997193639, "flow_matching_loss": 0.0614156536757946, "grad_norm": 0.1657664179801941, "invalid_tail_samples": 23.0, "learning_rate": 9.711087900715627e-05, "loss": 0.0694, "positive_teacher_pairs": 27035.3, "relation_loss": 0.007960132788866758, "selected_pairs": 27035.3, "step": 4600, "student_distance_mean": 699.276123046875, "teacher_distance_mean": 0.8551149368286133, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.007960132788866758, "weighted_relation_loss": 0.007960132788866758 }, { "action_query_batch_std": 12.383806133270264, "action_query_norm": 557.8954040527344, "action_relation_loss": 0.00790062891319394, "auxiliary_loss_weight": 1.0, "epoch": 4.31244153414406, "flow_matching_loss": 0.060095397382974626, "grad_norm": 0.17684945464134216, "invalid_tail_samples": 22.6, "learning_rate": 9.709238655765078e-05, "loss": 0.068, "positive_teacher_pairs": 27133.0, "relation_loss": 0.00790062891319394, "selected_pairs": 27133.0, "step": 4610, "student_distance_mean": 696.0656677246094, "teacher_distance_mean": 0.8517165899276733, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.00790062891319394, "weighted_relation_loss": 0.00790062891319394 }, { "action_query_batch_std": 12.15020294189453, "action_query_norm": 555.4590759277344, "action_relation_loss": 0.007855398720130325, "auxiliary_loss_weight": 1.0, "epoch": 4.3217960710944805, "flow_matching_loss": 0.05851014107465744, "grad_norm": 0.20802119374275208, "invalid_tail_samples": 21.1, "learning_rate": 9.707383688645511e-05, "loss": 0.0664, "positive_teacher_pairs": 27479.4, "relation_loss": 0.007855398720130325, "selected_pairs": 27479.4, "step": 4620, "student_distance_mean": 686.7403015136719, "teacher_distance_mean": 0.8474745929241181, "valid_action_samples": 234.9, "weighted_auxiliary_loss": 0.007855398720130325, "weighted_relation_loss": 0.007855398720130325 }, { "action_query_batch_std": 12.547698402404786, "action_query_norm": 565.35849609375, "action_relation_loss": 0.008242390910163521, "auxiliary_loss_weight": 1.0, "epoch": 4.331150608044902, "flow_matching_loss": 0.05901707038283348, "grad_norm": 0.2111327350139618, "invalid_tail_samples": 22.4, "learning_rate": 9.705523001610883e-05, "loss": 0.0673, "positive_teacher_pairs": 27172.1, "relation_loss": 0.008242390910163521, "selected_pairs": 27172.1, "step": 4630, "student_distance_mean": 706.8853210449219, "teacher_distance_mean": 0.8648318529129029, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.008242390910163521, "weighted_relation_loss": 0.008242390910163521 }, { "action_query_batch_std": 12.277220439910888, "action_query_norm": 554.6348266601562, "action_relation_loss": 0.008106054598465562, "auxiliary_loss_weight": 1.0, "epoch": 4.340505144995323, "flow_matching_loss": 0.0604857936501503, "grad_norm": 0.1741960644721985, "invalid_tail_samples": 25.8, "learning_rate": 9.703656596922107e-05, "loss": 0.0686, "positive_teacher_pairs": 26385.8, "relation_loss": 0.008106054598465562, "selected_pairs": 26385.8, "step": 4640, "student_distance_mean": 694.1903198242187, "teacher_distance_mean": 0.846158766746521, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.008106054598465562, "weighted_relation_loss": 0.008106054598465562 }, { "action_query_batch_std": 12.374101066589356, "action_query_norm": 558.5419128417968, "action_relation_loss": 0.00825079632923007, "auxiliary_loss_weight": 1.0, "epoch": 4.349859681945744, "flow_matching_loss": 0.06079319380223751, "grad_norm": 0.23592832684516907, "invalid_tail_samples": 23.4, "learning_rate": 9.70178447684704e-05, "loss": 0.069, "positive_teacher_pairs": 26946.1, "relation_loss": 0.00825079632923007, "selected_pairs": 26946.1, "step": 4650, "student_distance_mean": 701.4526733398437, "teacher_distance_mean": 0.8579635083675384, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.00825079632923007, "weighted_relation_loss": 0.00825079632923007 }, { "action_query_batch_std": 12.398934268951416, "action_query_norm": 563.3574645996093, "action_relation_loss": 0.00822641928680241, "auxiliary_loss_weight": 1.0, "epoch": 4.359214218896165, "flow_matching_loss": 0.058083216473460195, "grad_norm": 0.173411563038826, "invalid_tail_samples": 23.7, "learning_rate": 9.699906643660483e-05, "loss": 0.0663, "positive_teacher_pairs": 26876.2, "relation_loss": 0.00822641928680241, "selected_pairs": 26876.2, "step": 4660, "student_distance_mean": 702.9718322753906, "teacher_distance_mean": 0.842037433385849, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.00822641928680241, "weighted_relation_loss": 0.00822641928680241 }, { "action_query_batch_std": 12.22467498779297, "action_query_norm": 554.8631042480469, "action_relation_loss": 0.007944619841873645, "auxiliary_loss_weight": 1.0, "epoch": 4.368568755846586, "flow_matching_loss": 0.056807296723127364, "grad_norm": 0.15895965695381165, "invalid_tail_samples": 22.4, "learning_rate": 9.698023099644185e-05, "loss": 0.0648, "positive_teacher_pairs": 27174.4, "relation_loss": 0.007944619841873645, "selected_pairs": 27174.4, "step": 4670, "student_distance_mean": 692.7747192382812, "teacher_distance_mean": 0.8416971802711487, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.007944619841873645, "weighted_relation_loss": 0.007944619841873645 }, { "action_query_batch_std": 12.550595664978028, "action_query_norm": 567.6669494628907, "action_relation_loss": 0.008131948066875339, "auxiliary_loss_weight": 1.0, "epoch": 4.377923292797006, "flow_matching_loss": 0.06001501902937889, "grad_norm": 0.1941670924425125, "invalid_tail_samples": 24.2, "learning_rate": 9.696133847086823e-05, "loss": 0.0681, "positive_teacher_pairs": 26758.8, "relation_loss": 0.008131948066875339, "selected_pairs": 26758.8, "step": 4680, "student_distance_mean": 707.7985046386718, "teacher_distance_mean": 0.8511555433273316, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.008131948066875339, "weighted_relation_loss": 0.008131948066875339 }, { "action_query_batch_std": 12.611772060394287, "action_query_norm": 569.8890502929687, "action_relation_loss": 0.007990190247073769, "auxiliary_loss_weight": 1.0, "epoch": 4.387277829747427, "flow_matching_loss": 0.05992993339896202, "grad_norm": 0.17995765805244446, "invalid_tail_samples": 22.3, "learning_rate": 9.694238888284022e-05, "loss": 0.0679, "positive_teacher_pairs": 27203.0, "relation_loss": 0.007990190247073769, "selected_pairs": 27203.0, "step": 4690, "student_distance_mean": 711.6671508789062, "teacher_distance_mean": 0.8515803694725037, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.007990190247073769, "weighted_relation_loss": 0.007990190247073769 }, { "action_query_batch_std": 12.606623458862305, "action_query_norm": 569.48056640625, "action_relation_loss": 0.007968629710376263, "auxiliary_loss_weight": 1.0, "epoch": 4.396632366697848, "flow_matching_loss": 0.05663542710244655, "grad_norm": 0.15856783092021942, "invalid_tail_samples": 23.2, "learning_rate": 9.692338225538333e-05, "loss": 0.0646, "positive_teacher_pairs": 26989.5, "relation_loss": 0.007968629710376263, "selected_pairs": 26989.5, "step": 4700, "student_distance_mean": 713.1494201660156, "teacher_distance_mean": 0.859032267332077, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.007968629710376263, "weighted_relation_loss": 0.007968629710376263 }, { "action_query_batch_std": 12.32556095123291, "action_query_norm": 560.7399719238281, "action_relation_loss": 0.008281418913975358, "auxiliary_loss_weight": 1.0, "epoch": 4.4059869036482695, "flow_matching_loss": 0.05808361321687698, "grad_norm": 0.17016245424747467, "invalid_tail_samples": 25.8, "learning_rate": 9.690431861159241e-05, "loss": 0.0664, "positive_teacher_pairs": 26391.4, "relation_loss": 0.008281418913975358, "selected_pairs": 26391.4, "step": 4710, "student_distance_mean": 696.908935546875, "teacher_distance_mean": 0.8513824045658112, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.008281418913975358, "weighted_relation_loss": 0.008281418913975358 }, { "action_query_batch_std": 12.498380661010742, "action_query_norm": 564.7024841308594, "action_relation_loss": 0.008044564444571734, "auxiliary_loss_weight": 1.0, "epoch": 4.415341440598691, "flow_matching_loss": 0.05945386067032814, "grad_norm": 0.16997426748275757, "invalid_tail_samples": 24.8, "learning_rate": 9.688519797463161e-05, "loss": 0.0675, "positive_teacher_pairs": 26615.1, "relation_loss": 0.008044564444571734, "selected_pairs": 26615.1, "step": 4720, "student_distance_mean": 703.3853088378906, "teacher_distance_mean": 0.8550209999084473, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.008044564444571734, "weighted_relation_loss": 0.008044564444571734 }, { "action_query_batch_std": 12.520920372009277, "action_query_norm": 564.4452575683594, "action_relation_loss": 0.007893162965774535, "auxiliary_loss_weight": 1.0, "epoch": 4.424695977549112, "flow_matching_loss": 0.054062669724226, "grad_norm": 0.15692853927612305, "invalid_tail_samples": 25.1, "learning_rate": 9.686602036773426e-05, "loss": 0.062, "positive_teacher_pairs": 26551.4, "relation_loss": 0.007893162965774535, "selected_pairs": 26551.4, "step": 4730, "student_distance_mean": 708.2472961425781, "teacher_distance_mean": 0.8547833263874054, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.007893162965774535, "weighted_relation_loss": 0.007893162965774535 }, { "action_query_batch_std": 12.414472293853759, "action_query_norm": 559.2641235351563, "action_relation_loss": 0.008351048501208425, "auxiliary_loss_weight": 1.0, "epoch": 4.434050514499532, "flow_matching_loss": 0.057379677146673205, "grad_norm": 0.19664670526981354, "invalid_tail_samples": 24.5, "learning_rate": 9.684678581420302e-05, "loss": 0.0657, "positive_teacher_pairs": 26685.8, "relation_loss": 0.008351048501208425, "selected_pairs": 26685.8, "step": 4740, "student_distance_mean": 702.8863464355469, "teacher_distance_mean": 0.8494265258312226, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.008351048501208425, "weighted_relation_loss": 0.008351048501208425 }, { "action_query_batch_std": 12.61052360534668, "action_query_norm": 566.3547058105469, "action_relation_loss": 0.008221445931121707, "auxiliary_loss_weight": 1.0, "epoch": 4.443405051449953, "flow_matching_loss": 0.05777165554463863, "grad_norm": 0.17833580076694489, "invalid_tail_samples": 25.4, "learning_rate": 9.682749433740962e-05, "loss": 0.066, "positive_teacher_pairs": 26479.2, "relation_loss": 0.008221445931121707, "selected_pairs": 26479.2, "step": 4750, "student_distance_mean": 714.2507751464843, "teacher_distance_mean": 0.8615129232406616, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.008221445931121707, "weighted_relation_loss": 0.008221445931121707 }, { "action_query_batch_std": 12.388688564300537, "action_query_norm": 560.198095703125, "action_relation_loss": 0.008292789431288838, "auxiliary_loss_weight": 1.0, "epoch": 4.452759588400374, "flow_matching_loss": 0.05922098644077778, "grad_norm": 0.1407889425754547, "invalid_tail_samples": 26.1, "learning_rate": 9.680814596079507e-05, "loss": 0.0675, "positive_teacher_pairs": 26325.6, "relation_loss": 0.008292789431288838, "selected_pairs": 26325.6, "step": 4760, "student_distance_mean": 701.8825744628906, "teacher_distance_mean": 0.8525031805038452, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.008292789431288838, "weighted_relation_loss": 0.008292789431288838 }, { "action_query_batch_std": 12.596041011810303, "action_query_norm": 567.4397094726562, "action_relation_loss": 0.007788626523688435, "auxiliary_loss_weight": 1.0, "epoch": 4.462114125350795, "flow_matching_loss": 0.06162760257720947, "grad_norm": 0.16360574960708618, "invalid_tail_samples": 25.2, "learning_rate": 9.678874070786945e-05, "loss": 0.0694, "positive_teacher_pairs": 26525.3, "relation_loss": 0.007788626523688435, "selected_pairs": 26525.3, "step": 4770, "student_distance_mean": 708.8593078613281, "teacher_distance_mean": 0.8562284111976624, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.007788626523688435, "weighted_relation_loss": 0.007788626523688435 }, { "action_query_batch_std": 12.519562530517579, "action_query_norm": 562.2070861816406, "action_relation_loss": 0.008034354262053966, "auxiliary_loss_weight": 1.0, "epoch": 4.471468662301216, "flow_matching_loss": 0.061580590531229974, "grad_norm": 0.17205071449279785, "invalid_tail_samples": 23.5, "learning_rate": 9.676927860221199e-05, "loss": 0.0696, "positive_teacher_pairs": 26920.2, "relation_loss": 0.008034354262053966, "selected_pairs": 26920.2, "step": 4780, "student_distance_mean": 710.2412658691406, "teacher_distance_mean": 0.8626834034919739, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.008034354262053966, "weighted_relation_loss": 0.008034354262053966 }, { "action_query_batch_std": 12.617157363891602, "action_query_norm": 573.121533203125, "action_relation_loss": 0.008139216620475054, "auxiliary_loss_weight": 1.0, "epoch": 4.480823199251637, "flow_matching_loss": 0.062107672542333604, "grad_norm": 0.15677566826343536, "invalid_tail_samples": 23.5, "learning_rate": 9.674975966747097e-05, "loss": 0.0702, "positive_teacher_pairs": 26915.8, "relation_loss": 0.008139216620475054, "selected_pairs": 26915.8, "step": 4790, "student_distance_mean": 715.8399108886719, "teacher_distance_mean": 0.8509296298027038, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.008139216620475054, "weighted_relation_loss": 0.008139216620475054 }, { "action_query_batch_std": 12.70328130722046, "action_query_norm": 575.1335327148438, "action_relation_loss": 0.00812817453406751, "auxiliary_loss_weight": 1.0, "epoch": 4.490177736202058, "flow_matching_loss": 0.06194001026451588, "grad_norm": 0.21670442819595337, "invalid_tail_samples": 25.6, "learning_rate": 9.673018392736374e-05, "loss": 0.0701, "positive_teacher_pairs": 26436.9, "relation_loss": 0.00812817453406751, "selected_pairs": 26436.9, "step": 4800, "student_distance_mean": 721.67802734375, "teacher_distance_mean": 0.8617861151695252, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.00812817453406751, "weighted_relation_loss": 0.00812817453406751 }, { "action_query_batch_std": 12.63662347793579, "action_query_norm": 574.7397399902344, "action_relation_loss": 0.007962642656639218, "auxiliary_loss_weight": 1.0, "epoch": 4.499532273152479, "flow_matching_loss": 0.06137738935649395, "grad_norm": 0.20483778417110443, "invalid_tail_samples": 22.8, "learning_rate": 9.671055140567667e-05, "loss": 0.0693, "positive_teacher_pairs": 27087.2, "relation_loss": 0.007962642656639218, "selected_pairs": 27087.2, "step": 4810, "student_distance_mean": 717.2763427734375, "teacher_distance_mean": 0.8558677971363068, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.007962642656639218, "weighted_relation_loss": 0.007962642656639218 }, { "action_query_batch_std": 12.601895999908447, "action_query_norm": 571.6202209472656, "action_relation_loss": 0.0078476055059582, "auxiliary_loss_weight": 1.0, "epoch": 4.5088868101029, "flow_matching_loss": 0.05827457532286644, "grad_norm": 0.22751489281654358, "invalid_tail_samples": 21.7, "learning_rate": 9.669086212626511e-05, "loss": 0.0661, "positive_teacher_pairs": 27337.9, "relation_loss": 0.0078476055059582, "selected_pairs": 27337.9, "step": 4820, "student_distance_mean": 711.1371215820312, "teacher_distance_mean": 0.8533408939838409, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.0078476055059582, "weighted_relation_loss": 0.0078476055059582 }, { "action_query_batch_std": 12.423573875427246, "action_query_norm": 559.0676330566406, "action_relation_loss": 0.0077721294946968555, "auxiliary_loss_weight": 1.0, "epoch": 4.518241347053321, "flow_matching_loss": 0.06075953990221024, "grad_norm": 0.18158382177352905, "invalid_tail_samples": 23.1, "learning_rate": 9.667111611305341e-05, "loss": 0.0685, "positive_teacher_pairs": 27014.6, "relation_loss": 0.0077721294946968555, "selected_pairs": 27014.6, "step": 4830, "student_distance_mean": 702.4255737304687, "teacher_distance_mean": 0.8485257387161255, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0077721294946968555, "weighted_relation_loss": 0.0077721294946968555 }, { "action_query_batch_std": 12.437502765655518, "action_query_norm": 562.1633361816406, "action_relation_loss": 0.007620205171406269, "auxiliary_loss_weight": 1.0, "epoch": 4.527595884003742, "flow_matching_loss": 0.06053567081689835, "grad_norm": 0.15434816479682922, "invalid_tail_samples": 21.8, "learning_rate": 9.665131339003486e-05, "loss": 0.0682, "positive_teacher_pairs": 27315.2, "relation_loss": 0.007620205171406269, "selected_pairs": 27315.2, "step": 4840, "student_distance_mean": 703.8767395019531, "teacher_distance_mean": 0.8546050429344177, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.007620205171406269, "weighted_relation_loss": 0.007620205171406269 }, { "action_query_batch_std": 12.518386363983154, "action_query_norm": 570.9538452148438, "action_relation_loss": 0.008012242149561644, "auxiliary_loss_weight": 1.0, "epoch": 4.536950420954163, "flow_matching_loss": 0.05864864625036716, "grad_norm": 0.17307034134864807, "invalid_tail_samples": 23.4, "learning_rate": 9.663145398127158e-05, "loss": 0.0667, "positive_teacher_pairs": 26943.8, "relation_loss": 0.008012242149561644, "selected_pairs": 26943.8, "step": 4850, "student_distance_mean": 711.0239868164062, "teacher_distance_mean": 0.8466946005821228, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.008012242149561644, "weighted_relation_loss": 0.008012242149561644 }, { "action_query_batch_std": 12.4820725440979, "action_query_norm": 568.3076843261719, "action_relation_loss": 0.007843112386763097, "auxiliary_loss_weight": 1.0, "epoch": 4.546304957904583, "flow_matching_loss": 0.05768636092543602, "grad_norm": 0.10954819619655609, "invalid_tail_samples": 25.9, "learning_rate": 9.661153791089467e-05, "loss": 0.0655, "positive_teacher_pairs": 26363.4, "relation_loss": 0.007843112386763097, "selected_pairs": 26363.4, "step": 4860, "student_distance_mean": 707.4413330078125, "teacher_distance_mean": 0.8519186794757843, "valid_action_samples": 230.1, "weighted_auxiliary_loss": 0.007843112386763097, "weighted_relation_loss": 0.007843112386763097 }, { "action_query_batch_std": 12.599362087249755, "action_query_norm": 571.9240905761719, "action_relation_loss": 0.007573630753904581, "auxiliary_loss_weight": 1.0, "epoch": 4.555659494855004, "flow_matching_loss": 0.056328225508332254, "grad_norm": 0.13935182988643646, "invalid_tail_samples": 26.7, "learning_rate": 9.659156520310402e-05, "loss": 0.0639, "positive_teacher_pairs": 26178.7, "relation_loss": 0.007573630753904581, "selected_pairs": 26178.7, "step": 4870, "student_distance_mean": 714.0578979492187, "teacher_distance_mean": 0.855468612909317, "valid_action_samples": 229.3, "weighted_auxiliary_loss": 0.007573630753904581, "weighted_relation_loss": 0.007573630753904581 }, { "action_query_batch_std": 12.618448734283447, "action_query_norm": 572.46728515625, "action_relation_loss": 0.007576038129627705, "auxiliary_loss_weight": 1.0, "epoch": 4.5650140318054255, "flow_matching_loss": 0.059603733196854594, "grad_norm": 0.13180847465991974, "invalid_tail_samples": 25.6, "learning_rate": 9.657153588216835e-05, "loss": 0.0672, "positive_teacher_pairs": 26435.9, "relation_loss": 0.007576038129627705, "selected_pairs": 26435.9, "step": 4880, "student_distance_mean": 714.3792175292969, "teacher_distance_mean": 0.851275771856308, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.007576038129627705, "weighted_relation_loss": 0.007576038129627705 }, { "action_query_batch_std": 12.49697437286377, "action_query_norm": 571.3718627929687, "action_relation_loss": 0.007928651059046388, "auxiliary_loss_weight": 1.0, "epoch": 4.574368568755847, "flow_matching_loss": 0.05978659577667713, "grad_norm": 0.1282930076122284, "invalid_tail_samples": 22.3, "learning_rate": 9.655144997242516e-05, "loss": 0.0677, "positive_teacher_pairs": 27193.1, "relation_loss": 0.007928651059046388, "selected_pairs": 27193.1, "step": 4890, "student_distance_mean": 705.5660522460937, "teacher_distance_mean": 0.8548653542995452, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.007928651059046388, "weighted_relation_loss": 0.007928651059046388 }, { "action_query_batch_std": 12.529408931732178, "action_query_norm": 573.8530029296875, "action_relation_loss": 0.007815949199721218, "auxiliary_loss_weight": 1.0, "epoch": 4.583723105706268, "flow_matching_loss": 0.058662429079413415, "grad_norm": 0.135674849152565, "invalid_tail_samples": 22.5, "learning_rate": 9.653130749828075e-05, "loss": 0.0665, "positive_teacher_pairs": 27151.5, "relation_loss": 0.007815949199721218, "selected_pairs": 27151.5, "step": 4900, "student_distance_mean": 708.7136962890625, "teacher_distance_mean": 0.8450495004653931, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.007815949199721218, "weighted_relation_loss": 0.007815949199721218 }, { "action_query_batch_std": 12.521563720703124, "action_query_norm": 571.4329040527343, "action_relation_loss": 0.008351161610335112, "auxiliary_loss_weight": 1.0, "epoch": 4.593077642656689, "flow_matching_loss": 0.058170972391963005, "grad_norm": 0.13451777398586273, "invalid_tail_samples": 25.3, "learning_rate": 9.65111084842101e-05, "loss": 0.0665, "positive_teacher_pairs": 26505.1, "relation_loss": 0.008351161610335112, "selected_pairs": 26505.1, "step": 4910, "student_distance_mean": 706.2873657226562, "teacher_distance_mean": 0.8430170536041259, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.008351161610335112, "weighted_relation_loss": 0.008351161610335112 }, { "action_query_batch_std": 12.778299903869629, "action_query_norm": 580.6225708007812, "action_relation_loss": 0.007676599128171801, "auxiliary_loss_weight": 1.0, "epoch": 4.60243217960711, "flow_matching_loss": 0.05938089564442635, "grad_norm": 0.1648557484149933, "invalid_tail_samples": 23.9, "learning_rate": 9.649085295475695e-05, "loss": 0.0671, "positive_teacher_pairs": 26832.7, "relation_loss": 0.007676599128171801, "selected_pairs": 26832.7, "step": 4920, "student_distance_mean": 723.8349487304688, "teacher_distance_mean": 0.8564192950725555, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.007676599128171801, "weighted_relation_loss": 0.007676599128171801 }, { "action_query_batch_std": 12.881189632415772, "action_query_norm": 578.7864807128906, "action_relation_loss": 0.007851715665310621, "auxiliary_loss_weight": 1.0, "epoch": 4.61178671655753, "flow_matching_loss": 0.05478584803640842, "grad_norm": 0.12042558193206787, "invalid_tail_samples": 23.0, "learning_rate": 9.647054093453365e-05, "loss": 0.0626, "positive_teacher_pairs": 27038.6, "relation_loss": 0.007851715665310621, "selected_pairs": 27038.6, "step": 4930, "student_distance_mean": 730.3313415527343, "teacher_distance_mean": 0.8650088012218475, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.007851715665310621, "weighted_relation_loss": 0.007851715665310621 }, { "action_query_batch_std": 12.811984252929687, "action_query_norm": 579.9423400878907, "action_relation_loss": 0.007876319391652942, "auxiliary_loss_weight": 1.0, "epoch": 4.621141253507951, "flow_matching_loss": 0.05870588049292565, "grad_norm": 0.16622009873390198, "invalid_tail_samples": 23.0, "learning_rate": 9.645017244822123e-05, "loss": 0.0666, "positive_teacher_pairs": 27036.7, "relation_loss": 0.007876319391652942, "selected_pairs": 27036.7, "step": 4940, "student_distance_mean": 725.557275390625, "teacher_distance_mean": 0.8473906695842743, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.007876319391652942, "weighted_relation_loss": 0.007876319391652942 }, { "action_query_batch_std": 13.054996967315674, "action_query_norm": 587.5664428710937, "action_relation_loss": 0.007636359892785549, "auxiliary_loss_weight": 1.0, "epoch": 4.630495790458372, "flow_matching_loss": 0.05689567774534225, "grad_norm": 0.16240419447422028, "invalid_tail_samples": 24.4, "learning_rate": 9.642974752056931e-05, "loss": 0.0645, "positive_teacher_pairs": 26715.9, "relation_loss": 0.007636359892785549, "selected_pairs": 26715.9, "step": 4950, "student_distance_mean": 734.5534606933594, "teacher_distance_mean": 0.8540888667106629, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.007636359892785549, "weighted_relation_loss": 0.007636359892785549 }, { "action_query_batch_std": 12.948858737945557, "action_query_norm": 580.8454650878906, "action_relation_loss": 0.008028534101322293, "auxiliary_loss_weight": 1.0, "epoch": 4.639850327408793, "flow_matching_loss": 0.059035253897309306, "grad_norm": 0.1546126753091812, "invalid_tail_samples": 26.3, "learning_rate": 9.640926617639613e-05, "loss": 0.0671, "positive_teacher_pairs": 26277.7, "relation_loss": 0.008028534101322293, "selected_pairs": 26277.7, "step": 4960, "student_distance_mean": 733.6426513671875, "teacher_distance_mean": 0.8560550689697266, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.008028534101322293, "weighted_relation_loss": 0.008028534101322293 }, { "action_query_batch_std": 12.96805191040039, "action_query_norm": 584.524609375, "action_relation_loss": 0.007572944276034832, "auxiliary_loss_weight": 1.0, "epoch": 4.6492048643592145, "flow_matching_loss": 0.05777474045753479, "grad_norm": 0.12229322642087936, "invalid_tail_samples": 24.0, "learning_rate": 9.638872844058843e-05, "loss": 0.0653, "positive_teacher_pairs": 26803.0, "relation_loss": 0.007572944276034832, "selected_pairs": 26803.0, "step": 4970, "student_distance_mean": 733.9008605957031, "teacher_distance_mean": 0.850550377368927, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.007572944276034832, "weighted_relation_loss": 0.007572944276034832 }, { "action_query_batch_std": 13.003592014312744, "action_query_norm": 585.9934692382812, "action_relation_loss": 0.007560801599174738, "auxiliary_loss_weight": 1.0, "epoch": 4.658559401309635, "flow_matching_loss": 0.05765646696090698, "grad_norm": 0.1278841197490692, "invalid_tail_samples": 23.6, "learning_rate": 9.63681343381015e-05, "loss": 0.0652, "positive_teacher_pairs": 26901.1, "relation_loss": 0.007560801599174738, "selected_pairs": 26901.1, "step": 4980, "student_distance_mean": 733.2621154785156, "teacher_distance_mean": 0.8551260471343994, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.007560801599174738, "weighted_relation_loss": 0.007560801599174738 }, { "action_query_batch_std": 12.859586048126221, "action_query_norm": 579.5868469238281, "action_relation_loss": 0.007833396457135678, "auxiliary_loss_weight": 1.0, "epoch": 4.667913938260056, "flow_matching_loss": 0.05929810106754303, "grad_norm": 0.17479373514652252, "invalid_tail_samples": 25.3, "learning_rate": 9.634748389395914e-05, "loss": 0.0671, "positive_teacher_pairs": 26502.4, "relation_loss": 0.007833396457135678, "selected_pairs": 26502.4, "step": 4990, "student_distance_mean": 728.2782287597656, "teacher_distance_mean": 0.857477217912674, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.007833396457135678, "weighted_relation_loss": 0.007833396457135678 }, { "action_query_batch_std": 12.860445594787597, "action_query_norm": 578.9536071777344, "action_relation_loss": 0.007917311368510127, "auxiliary_loss_weight": 1.0, "epoch": 4.677268475210477, "flow_matching_loss": 0.05856610350310802, "grad_norm": 0.17840075492858887, "invalid_tail_samples": 23.0, "learning_rate": 9.632677713325353e-05, "loss": 0.0665, "positive_teacher_pairs": 27039.4, "relation_loss": 0.007917311368510127, "selected_pairs": 27039.4, "step": 5000, "student_distance_mean": 726.5239196777344, "teacher_distance_mean": 0.8576675653457642, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.007917311368510127, "weighted_relation_loss": 0.007917311368510127 }, { "action_query_batch_std": 13.033317279815673, "action_query_norm": 583.5719665527344, "action_relation_loss": 0.007832596264779567, "auxiliary_loss_weight": 1.0, "epoch": 4.686623012160898, "flow_matching_loss": 0.05639016926288605, "grad_norm": 0.16216032207012177, "invalid_tail_samples": 20.9, "learning_rate": 9.63060140811454e-05, "loss": 0.0642, "positive_teacher_pairs": 27536.3, "relation_loss": 0.007832596264779567, "selected_pairs": 27536.3, "step": 5010, "student_distance_mean": 735.4433776855469, "teacher_distance_mean": 0.8532325923442841, "valid_action_samples": 235.1, "weighted_auxiliary_loss": 0.007832596264779567, "weighted_relation_loss": 0.007832596264779567 }, { "action_query_batch_std": 13.004516315460204, "action_query_norm": 586.5894653320313, "action_relation_loss": 0.008175978856161236, "auxiliary_loss_weight": 1.0, "epoch": 4.695977549111319, "flow_matching_loss": 0.05601632297039032, "grad_norm": 0.16632722318172455, "invalid_tail_samples": 23.7, "learning_rate": 9.628519476286379e-05, "loss": 0.0642, "positive_teacher_pairs": 26875.0, "relation_loss": 0.008175978856161236, "selected_pairs": 26875.0, "step": 5020, "student_distance_mean": 735.1625549316407, "teacher_distance_mean": 0.850562858581543, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.008175978856161236, "weighted_relation_loss": 0.008175978856161236 }, { "action_query_batch_std": 13.032559871673584, "action_query_norm": 585.407568359375, "action_relation_loss": 0.007694536074995995, "auxiliary_loss_weight": 1.0, "epoch": 4.70533208606174, "flow_matching_loss": 0.05734288729727268, "grad_norm": 0.14336782693862915, "invalid_tail_samples": 22.5, "learning_rate": 9.626431920370612e-05, "loss": 0.065, "positive_teacher_pairs": 27154.3, "relation_loss": 0.007694536074995995, "selected_pairs": 27154.3, "step": 5030, "student_distance_mean": 738.8558959960938, "teacher_distance_mean": 0.855182284116745, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.007694536074995995, "weighted_relation_loss": 0.007694536074995995 }, { "action_query_batch_std": 12.993583393096923, "action_query_norm": 578.7600036621094, "action_relation_loss": 0.007737476425245404, "auxiliary_loss_weight": 1.0, "epoch": 4.714686623012161, "flow_matching_loss": 0.05825958885252476, "grad_norm": 0.16205060482025146, "invalid_tail_samples": 22.1, "learning_rate": 9.624338742903819e-05, "loss": 0.066, "positive_teacher_pairs": 27257.5, "relation_loss": 0.007737476425245404, "selected_pairs": 27257.5, "step": 5040, "student_distance_mean": 734.4676147460938, "teacher_distance_mean": 0.8637486219406127, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.007737476425245404, "weighted_relation_loss": 0.007737476425245404 }, { "action_query_batch_std": 12.6204345703125, "action_query_norm": 567.6041687011718, "action_relation_loss": 0.008029876928776502, "auxiliary_loss_weight": 1.0, "epoch": 4.724041159962582, "flow_matching_loss": 0.05980735868215561, "grad_norm": 0.1878834366798401, "invalid_tail_samples": 24.5, "learning_rate": 9.622239946429406e-05, "loss": 0.0678, "positive_teacher_pairs": 26686.5, "relation_loss": 0.008029876928776502, "selected_pairs": 26686.5, "step": 5050, "student_distance_mean": 713.4280212402343, "teacher_distance_mean": 0.849944430589676, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.008029876928776502, "weighted_relation_loss": 0.008029876928776502 }, { "action_query_batch_std": 12.703299713134765, "action_query_norm": 572.9424133300781, "action_relation_loss": 0.008091359864920378, "auxiliary_loss_weight": 1.0, "epoch": 4.733395696913003, "flow_matching_loss": 0.0600475586950779, "grad_norm": 0.18721666932106018, "invalid_tail_samples": 24.7, "learning_rate": 9.620135533497609e-05, "loss": 0.0681, "positive_teacher_pairs": 26639.2, "relation_loss": 0.008091359864920378, "selected_pairs": 26639.2, "step": 5060, "student_distance_mean": 716.5522216796875, "teacher_distance_mean": 0.8419934511184692, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.008091359864920378, "weighted_relation_loss": 0.008091359864920378 }, { "action_query_batch_std": 12.631156826019287, "action_query_norm": 571.6971801757812, "action_relation_loss": 0.008158172992989422, "auxiliary_loss_weight": 1.0, "epoch": 4.742750233863424, "flow_matching_loss": 0.056561519578099254, "grad_norm": 0.13892406225204468, "invalid_tail_samples": 24.0, "learning_rate": 9.61802550666549e-05, "loss": 0.0647, "positive_teacher_pairs": 26802.0, "relation_loss": 0.008158172992989422, "selected_pairs": 26802.0, "step": 5070, "student_distance_mean": 719.4254150390625, "teacher_distance_mean": 0.8519473433494568, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.008158172992989422, "weighted_relation_loss": 0.008158172992989422 }, { "action_query_batch_std": 12.91274356842041, "action_query_norm": 579.950927734375, "action_relation_loss": 0.007412909250706434, "auxiliary_loss_weight": 1.0, "epoch": 4.752104770813845, "flow_matching_loss": 0.056812462583184245, "grad_norm": 0.15705955028533936, "invalid_tail_samples": 22.2, "learning_rate": 9.615909868496928e-05, "loss": 0.0642, "positive_teacher_pairs": 27221.0, "relation_loss": 0.007412909250706434, "selected_pairs": 27221.0, "step": 5080, "student_distance_mean": 729.8442138671875, "teacher_distance_mean": 0.8542192816734314, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.007412909250706434, "weighted_relation_loss": 0.007412909250706434 }, { "action_query_batch_std": 12.822709465026856, "action_query_norm": 573.7913757324219, "action_relation_loss": 0.007805826095864177, "auxiliary_loss_weight": 1.0, "epoch": 4.761459307764266, "flow_matching_loss": 0.05932702794671059, "grad_norm": 0.21154546737670898, "invalid_tail_samples": 24.3, "learning_rate": 9.613788621562622e-05, "loss": 0.0671, "positive_teacher_pairs": 26737.6, "relation_loss": 0.007805826095864177, "selected_pairs": 26737.6, "step": 5090, "student_distance_mean": 725.645654296875, "teacher_distance_mean": 0.8538103401660919, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.007805826095864177, "weighted_relation_loss": 0.007805826095864177 }, { "action_query_batch_std": 12.779264736175538, "action_query_norm": 574.3625, "action_relation_loss": 0.007960751419886947, "auxiliary_loss_weight": 1.0, "epoch": 4.770813844714686, "flow_matching_loss": 0.05915798656642437, "grad_norm": 0.20974910259246826, "invalid_tail_samples": 23.2, "learning_rate": 9.611661768440093e-05, "loss": 0.0671, "positive_teacher_pairs": 26997.2, "relation_loss": 0.007960751419886947, "selected_pairs": 26997.2, "step": 5100, "student_distance_mean": 724.8900329589844, "teacher_distance_mean": 0.842427134513855, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.007960751419886947, "weighted_relation_loss": 0.007960751419886947 }, { "action_query_batch_std": 12.855519580841065, "action_query_norm": 582.146630859375, "action_relation_loss": 0.0077153969090431925, "auxiliary_loss_weight": 1.0, "epoch": 4.780168381665107, "flow_matching_loss": 0.05610968396067619, "grad_norm": 0.18272344768047333, "invalid_tail_samples": 22.3, "learning_rate": 9.609529311713661e-05, "loss": 0.0638, "positive_teacher_pairs": 27201.1, "relation_loss": 0.0077153969090431925, "selected_pairs": 27201.1, "step": 5110, "student_distance_mean": 727.6127014160156, "teacher_distance_mean": 0.8490824282169342, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0077153969090431925, "weighted_relation_loss": 0.0077153969090431925 }, { "action_query_batch_std": 12.938071823120117, "action_query_norm": 580.9803588867187, "action_relation_loss": 0.007937473338097334, "auxiliary_loss_weight": 1.0, "epoch": 4.789522918615528, "flow_matching_loss": 0.05776268616318703, "grad_norm": 0.25472259521484375, "invalid_tail_samples": 22.8, "learning_rate": 9.607391253974466e-05, "loss": 0.0657, "positive_teacher_pairs": 27084.9, "relation_loss": 0.007937473338097334, "selected_pairs": 27084.9, "step": 5120, "student_distance_mean": 733.0495483398438, "teacher_distance_mean": 0.8553180038928986, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.007937473338097334, "weighted_relation_loss": 0.007937473338097334 }, { "action_query_batch_std": 12.93872766494751, "action_query_norm": 583.6835266113281, "action_relation_loss": 0.007492513861507177, "auxiliary_loss_weight": 1.0, "epoch": 4.7988774555659495, "flow_matching_loss": 0.058296509087085724, "grad_norm": 0.23524414002895355, "invalid_tail_samples": 24.5, "learning_rate": 9.605247597820448e-05, "loss": 0.0658, "positive_teacher_pairs": 26688.3, "relation_loss": 0.007492513861507177, "selected_pairs": 26688.3, "step": 5130, "student_distance_mean": 736.6823547363281, "teacher_distance_mean": 0.8544264376163483, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.007492513861507177, "weighted_relation_loss": 0.007492513861507177 }, { "action_query_batch_std": 12.790634155273438, "action_query_norm": 578.1257873535156, "action_relation_loss": 0.007921659387648106, "auxiliary_loss_weight": 1.0, "epoch": 4.808231992516371, "flow_matching_loss": 0.05904281213879585, "grad_norm": 0.2293635457754135, "invalid_tail_samples": 23.6, "learning_rate": 9.603098345856354e-05, "loss": 0.067, "positive_teacher_pairs": 26894.6, "relation_loss": 0.007921659387648106, "selected_pairs": 26894.6, "step": 5140, "student_distance_mean": 724.6939086914062, "teacher_distance_mean": 0.849615889787674, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.007921659387648106, "weighted_relation_loss": 0.007921659387648106 }, { "action_query_batch_std": 13.150669288635253, "action_query_norm": 593.0857055664062, "action_relation_loss": 0.0077782433945685625, "auxiliary_loss_weight": 1.0, "epoch": 4.817586529466792, "flow_matching_loss": 0.059050575271248816, "grad_norm": 0.23399387300014496, "invalid_tail_samples": 24.2, "learning_rate": 9.600943500693725e-05, "loss": 0.0668, "positive_teacher_pairs": 26767.9, "relation_loss": 0.0077782433945685625, "selected_pairs": 26767.9, "step": 5150, "student_distance_mean": 747.1485961914062, "teacher_distance_mean": 0.8628664433956146, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0077782433945685625, "weighted_relation_loss": 0.0077782433945685625 }, { "action_query_batch_std": 13.172865200042725, "action_query_norm": 594.4025451660157, "action_relation_loss": 0.007573498785495758, "auxiliary_loss_weight": 1.0, "epoch": 4.826941066417213, "flow_matching_loss": 0.05807885117828846, "grad_norm": 0.18039271235466003, "invalid_tail_samples": 24.3, "learning_rate": 9.598783064950902e-05, "loss": 0.0657, "positive_teacher_pairs": 26736.7, "relation_loss": 0.007573498785495758, "selected_pairs": 26736.7, "step": 5160, "student_distance_mean": 748.0617797851562, "teacher_distance_mean": 0.866655296087265, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.007573498785495758, "weighted_relation_loss": 0.007573498785495758 }, { "action_query_batch_std": 12.879518127441406, "action_query_norm": 584.9187377929687, "action_relation_loss": 0.0076150958891958, "auxiliary_loss_weight": 1.0, "epoch": 4.836295603367633, "flow_matching_loss": 0.05676429122686386, "grad_norm": 0.1976304054260254, "invalid_tail_samples": 24.3, "learning_rate": 9.596617041253018e-05, "loss": 0.0644, "positive_teacher_pairs": 26747.3, "relation_loss": 0.0076150958891958, "selected_pairs": 26747.3, "step": 5170, "student_distance_mean": 732.0709411621094, "teacher_distance_mean": 0.8484009385108948, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0076150958891958, "weighted_relation_loss": 0.0076150958891958 }, { "action_query_batch_std": 13.197955894470216, "action_query_norm": 591.7405151367187, "action_relation_loss": 0.00781849017366767, "auxiliary_loss_weight": 1.0, "epoch": 4.845650140318054, "flow_matching_loss": 0.05775314979255199, "grad_norm": 0.17553669214248657, "invalid_tail_samples": 23.7, "learning_rate": 9.594445432231996e-05, "loss": 0.0656, "positive_teacher_pairs": 26881.2, "relation_loss": 0.00781849017366767, "selected_pairs": 26881.2, "step": 5180, "student_distance_mean": 747.0851379394531, "teacher_distance_mean": 0.8520939767360687, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.00781849017366767, "weighted_relation_loss": 0.00781849017366767 }, { "action_query_batch_std": 13.096281909942627, "action_query_norm": 587.3884704589843, "action_relation_loss": 0.007607648149132729, "auxiliary_loss_weight": 1.0, "epoch": 4.855004677268475, "flow_matching_loss": 0.057871590927243234, "grad_norm": 0.22633793950080872, "invalid_tail_samples": 21.0, "learning_rate": 9.592268240526547e-05, "loss": 0.0655, "positive_teacher_pairs": 27504.2, "relation_loss": 0.007607648149132729, "selected_pairs": 27504.2, "step": 5190, "student_distance_mean": 738.5416381835937, "teacher_distance_mean": 0.8591581821441651, "valid_action_samples": 235.0, "weighted_auxiliary_loss": 0.007607648149132729, "weighted_relation_loss": 0.007607648149132729 }, { "action_query_batch_std": 13.19562463760376, "action_query_norm": 593.8128601074219, "action_relation_loss": 0.007657702593132853, "auxiliary_loss_weight": 1.0, "epoch": 4.864359214218896, "flow_matching_loss": 0.055911460891366005, "grad_norm": 0.1785518229007721, "invalid_tail_samples": 26.2, "learning_rate": 9.590085468782162e-05, "loss": 0.0636, "positive_teacher_pairs": 26300.9, "relation_loss": 0.007657702593132853, "selected_pairs": 26300.9, "step": 5200, "student_distance_mean": 747.990234375, "teacher_distance_mean": 0.8556196630001068, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.007657702593132853, "weighted_relation_loss": 0.007657702593132853 }, { "action_query_batch_std": 13.455115699768067, "action_query_norm": 605.5106262207031, "action_relation_loss": 0.007892385823652148, "auxiliary_loss_weight": 1.0, "epoch": 4.873713751169317, "flow_matching_loss": 0.058968627080321315, "grad_norm": 0.1745312362909317, "invalid_tail_samples": 22.8, "learning_rate": 9.587897119651116e-05, "loss": 0.0669, "positive_teacher_pairs": 27092.1, "relation_loss": 0.007892385823652148, "selected_pairs": 27092.1, "step": 5210, "student_distance_mean": 763.1850524902344, "teacher_distance_mean": 0.8626244604587555, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.007892385823652148, "weighted_relation_loss": 0.007892385823652148 }, { "action_query_batch_std": 13.110801696777344, "action_query_norm": 595.2451721191406, "action_relation_loss": 0.007680736854672432, "auxiliary_loss_weight": 1.0, "epoch": 4.883068288119738, "flow_matching_loss": 0.058925945311784744, "grad_norm": 0.1630302518606186, "invalid_tail_samples": 25.0, "learning_rate": 9.585703195792459e-05, "loss": 0.0666, "positive_teacher_pairs": 26572.1, "relation_loss": 0.007680736854672432, "selected_pairs": 26572.1, "step": 5220, "student_distance_mean": 742.6547424316407, "teacher_distance_mean": 0.8452275097370148, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.007680736854672432, "weighted_relation_loss": 0.007680736854672432 }, { "action_query_batch_std": 13.222741508483887, "action_query_norm": 591.3701293945312, "action_relation_loss": 0.00781246330589056, "auxiliary_loss_weight": 1.0, "epoch": 4.892422825070159, "flow_matching_loss": 0.05702662169933319, "grad_norm": 0.1265415996313095, "invalid_tail_samples": 25.5, "learning_rate": 9.583503699872016e-05, "loss": 0.0648, "positive_teacher_pairs": 26461.9, "relation_loss": 0.00781246330589056, "selected_pairs": 26461.9, "step": 5230, "student_distance_mean": 748.0828796386719, "teacher_distance_mean": 0.8630922675132752, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.00781246330589056, "weighted_relation_loss": 0.00781246330589056 }, { "action_query_batch_std": 13.337376976013184, "action_query_norm": 597.4751770019532, "action_relation_loss": 0.007557666301727295, "auxiliary_loss_weight": 1.0, "epoch": 4.90177736202058, "flow_matching_loss": 0.05666106455028057, "grad_norm": 0.1408938318490982, "invalid_tail_samples": 23.9, "learning_rate": 9.581298634562381e-05, "loss": 0.0642, "positive_teacher_pairs": 26825.0, "relation_loss": 0.007557666301727295, "selected_pairs": 26825.0, "step": 5240, "student_distance_mean": 757.3456115722656, "teacher_distance_mean": 0.8586979329586029, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.007557666301727295, "weighted_relation_loss": 0.007557666301727295 }, { "action_query_batch_std": 13.135890865325928, "action_query_norm": 591.1348388671875, "action_relation_loss": 0.007208696426823735, "auxiliary_loss_weight": 1.0, "epoch": 4.911131898971001, "flow_matching_loss": 0.05895799919962883, "grad_norm": 0.14546839892864227, "invalid_tail_samples": 22.1, "learning_rate": 9.579088002542917e-05, "loss": 0.0662, "positive_teacher_pairs": 27242.4, "relation_loss": 0.007208696426823735, "selected_pairs": 27242.4, "step": 5250, "student_distance_mean": 744.0686889648438, "teacher_distance_mean": 0.8503828704357147, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.007208696426823735, "weighted_relation_loss": 0.007208696426823735 }, { "action_query_batch_std": 13.382974433898926, "action_query_norm": 595.413525390625, "action_relation_loss": 0.007627843599766493, "auxiliary_loss_weight": 1.0, "epoch": 4.920486435921422, "flow_matching_loss": 0.05775411576032639, "grad_norm": 0.11648966372013092, "invalid_tail_samples": 23.7, "learning_rate": 9.57687180649975e-05, "loss": 0.0654, "positive_teacher_pairs": 26881.6, "relation_loss": 0.007627843599766493, "selected_pairs": 26881.6, "step": 5260, "student_distance_mean": 756.9728942871094, "teacher_distance_mean": 0.8583162486553192, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.007627843599766493, "weighted_relation_loss": 0.007627843599766493 }, { "action_query_batch_std": 13.316531372070312, "action_query_norm": 593.2228759765625, "action_relation_loss": 0.0076584193855524065, "auxiliary_loss_weight": 1.0, "epoch": 4.929840972871843, "flow_matching_loss": 0.05581553280353546, "grad_norm": 0.18642495572566986, "invalid_tail_samples": 24.5, "learning_rate": 9.574650049125768e-05, "loss": 0.0635, "positive_teacher_pairs": 26687.0, "relation_loss": 0.0076584193855524065, "selected_pairs": 26687.0, "step": 5270, "student_distance_mean": 752.9483215332032, "teacher_distance_mean": 0.8575884401798248, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0076584193855524065, "weighted_relation_loss": 0.0076584193855524065 }, { "action_query_batch_std": 13.331057071685791, "action_query_norm": 598.3886169433594, "action_relation_loss": 0.007417699415236711, "auxiliary_loss_weight": 1.0, "epoch": 4.939195509822264, "flow_matching_loss": 0.05593580640852451, "grad_norm": 0.1990336924791336, "invalid_tail_samples": 21.7, "learning_rate": 9.572422733120614e-05, "loss": 0.0634, "positive_teacher_pairs": 27336.7, "relation_loss": 0.007417699415236711, "selected_pairs": 27336.7, "step": 5280, "student_distance_mean": 753.1822509765625, "teacher_distance_mean": 0.8600590169429779, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.007417699415236711, "weighted_relation_loss": 0.007417699415236711 }, { "action_query_batch_std": 13.385743141174316, "action_query_norm": 597.1380920410156, "action_relation_loss": 0.00748034561984241, "auxiliary_loss_weight": 1.0, "epoch": 4.948550046772684, "flow_matching_loss": 0.05795916430652141, "grad_norm": 0.19768185913562775, "invalid_tail_samples": 24.0, "learning_rate": 9.570189861190689e-05, "loss": 0.0654, "positive_teacher_pairs": 26801.0, "relation_loss": 0.00748034561984241, "selected_pairs": 26801.0, "step": 5290, "student_distance_mean": 755.4078491210937, "teacher_distance_mean": 0.8572879016399384, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.00748034561984241, "weighted_relation_loss": 0.00748034561984241 }, { "action_query_batch_std": 13.353257083892823, "action_query_norm": 594.9615783691406, "action_relation_loss": 0.007420073682442308, "auxiliary_loss_weight": 1.0, "epoch": 4.9579045837231055, "flow_matching_loss": 0.05564097575843334, "grad_norm": 0.23078958690166473, "invalid_tail_samples": 25.8, "learning_rate": 9.56795143604914e-05, "loss": 0.0631, "positive_teacher_pairs": 26387.4, "relation_loss": 0.007420073682442308, "selected_pairs": 26387.4, "step": 5300, "student_distance_mean": 757.8147827148438, "teacher_distance_mean": 0.8592241823673248, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.007420073682442308, "weighted_relation_loss": 0.007420073682442308 }, { "action_query_batch_std": 13.259716892242432, "action_query_norm": 593.7798828125, "action_relation_loss": 0.007828072924166918, "auxiliary_loss_weight": 1.0, "epoch": 4.967259120673527, "flow_matching_loss": 0.05555474311113358, "grad_norm": 0.12886567413806915, "invalid_tail_samples": 23.6, "learning_rate": 9.565707460415869e-05, "loss": 0.0634, "positive_teacher_pairs": 26897.7, "relation_loss": 0.007828072924166918, "selected_pairs": 26897.7, "step": 5310, "student_distance_mean": 746.0998352050781, "teacher_distance_mean": 0.8477039992809295, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.007828072924166918, "weighted_relation_loss": 0.007828072924166918 }, { "action_query_batch_std": 13.32339506149292, "action_query_norm": 598.7283325195312, "action_relation_loss": 0.007487347861751914, "auxiliary_loss_weight": 1.0, "epoch": 4.976613657623948, "flow_matching_loss": 0.056164948269724846, "grad_norm": 0.1492052525281906, "invalid_tail_samples": 23.8, "learning_rate": 9.563457937017515e-05, "loss": 0.0637, "positive_teacher_pairs": 26850.6, "relation_loss": 0.007487347861751914, "selected_pairs": 26850.6, "step": 5320, "student_distance_mean": 753.8265747070312, "teacher_distance_mean": 0.8510671377182006, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.007487347861751914, "weighted_relation_loss": 0.007487347861751914 }, { "action_query_batch_std": 13.491063404083253, "action_query_norm": 602.6656494140625, "action_relation_loss": 0.007379022799432278, "auxiliary_loss_weight": 1.0, "epoch": 4.985968194574369, "flow_matching_loss": 0.05701272711157799, "grad_norm": 0.16725176572799683, "invalid_tail_samples": 20.6, "learning_rate": 9.56120286858746e-05, "loss": 0.0644, "positive_teacher_pairs": 27596.7, "relation_loss": 0.007379022799432278, "selected_pairs": 27596.7, "step": 5330, "student_distance_mean": 758.6520202636718, "teacher_distance_mean": 0.863540095090866, "valid_action_samples": 235.4, "weighted_auxiliary_loss": 0.007379022799432278, "weighted_relation_loss": 0.007379022799432278 }, { "action_query_batch_std": 13.428126907348632, "action_query_norm": 605.4060546875, "action_relation_loss": 0.007801588065922261, "auxiliary_loss_weight": 1.0, "epoch": 4.99532273152479, "flow_matching_loss": 0.06021732836961746, "grad_norm": 0.19638076424598694, "invalid_tail_samples": 22.9, "learning_rate": 9.558942257865829e-05, "loss": 0.068, "positive_teacher_pairs": 27059.2, "relation_loss": 0.007801588065922261, "selected_pairs": 27059.2, "step": 5340, "student_distance_mean": 759.8815612792969, "teacher_distance_mean": 0.8540811717510224, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.007801588065922261, "weighted_relation_loss": 0.007801588065922261 }, { "action_query_batch_std": 13.274340534210205, "action_query_norm": 597.350439453125, "action_relation_loss": 0.007548433821648359, "auxiliary_loss_weight": 1.0, "epoch": 5.00467726847521, "flow_matching_loss": 0.054662684351205824, "grad_norm": 0.16204990446567535, "invalid_tail_samples": 26.0, "learning_rate": 9.556676107599472e-05, "loss": 0.0622, "positive_teacher_pairs": 23362.0, "relation_loss": 0.007548433821648359, "selected_pairs": 23362.0, "step": 5350, "student_distance_mean": 754.6005126953125, "teacher_distance_mean": 0.8513019919395447, "valid_action_samples": 210.1, "weighted_auxiliary_loss": 0.007548433821648359, "weighted_relation_loss": 0.007548433821648359 }, { "action_query_batch_std": 13.35220193862915, "action_query_norm": 596.093017578125, "action_relation_loss": 0.007334820227697492, "auxiliary_loss_weight": 1.0, "epoch": 5.014031805425631, "flow_matching_loss": 0.05904167778789997, "grad_norm": 0.18845142424106598, "invalid_tail_samples": 24.3, "learning_rate": 9.554404420541978e-05, "loss": 0.0664, "positive_teacher_pairs": 26740.2, "relation_loss": 0.007334820227697492, "selected_pairs": 26740.2, "step": 5360, "student_distance_mean": 754.3320678710937, "teacher_distance_mean": 0.8578934133052826, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.007334820227697492, "weighted_relation_loss": 0.007334820227697492 }, { "action_query_batch_std": 13.470629596710205, "action_query_norm": 604.6179077148438, "action_relation_loss": 0.0074139595031738285, "auxiliary_loss_weight": 1.0, "epoch": 5.023386342376052, "flow_matching_loss": 0.05533906817436218, "grad_norm": 0.16633984446525574, "invalid_tail_samples": 24.6, "learning_rate": 9.55212719945366e-05, "loss": 0.0628, "positive_teacher_pairs": 26661.4, "relation_loss": 0.0074139595031738285, "selected_pairs": 26661.4, "step": 5370, "student_distance_mean": 763.5485168457031, "teacher_distance_mean": 0.856038236618042, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0074139595031738285, "weighted_relation_loss": 0.0074139595031738285 }, { "action_query_batch_std": 13.332397079467773, "action_query_norm": 600.4182312011719, "action_relation_loss": 0.0073380218353122474, "auxiliary_loss_weight": 1.0, "epoch": 5.032740879326473, "flow_matching_loss": 0.05395324118435383, "grad_norm": 0.17837919294834137, "invalid_tail_samples": 22.7, "learning_rate": 9.549844447101559e-05, "loss": 0.0613, "positive_teacher_pairs": 27112.7, "relation_loss": 0.0073380218353122474, "selected_pairs": 27112.7, "step": 5380, "student_distance_mean": 755.3018676757813, "teacher_distance_mean": 0.8519276976585388, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0073380218353122474, "weighted_relation_loss": 0.0073380218353122474 }, { "action_query_batch_std": 13.441190052032471, "action_query_norm": 605.8172729492187, "action_relation_loss": 0.007187769189476967, "auxiliary_loss_weight": 1.0, "epoch": 5.0420954162768945, "flow_matching_loss": 0.05605289340019226, "grad_norm": 0.15646992623806, "invalid_tail_samples": 22.2, "learning_rate": 9.547556166259433e-05, "loss": 0.0632, "positive_teacher_pairs": 27224.7, "relation_loss": 0.007187769189476967, "selected_pairs": 27224.7, "step": 5390, "student_distance_mean": 761.9568786621094, "teacher_distance_mean": 0.8577889621257782, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.007187769189476967, "weighted_relation_loss": 0.007187769189476967 }, { "action_query_batch_std": 13.638681125640868, "action_query_norm": 608.5599243164063, "action_relation_loss": 0.0071676459163427355, "auxiliary_loss_weight": 1.0, "epoch": 5.051449953227316, "flow_matching_loss": 0.053011900186538695, "grad_norm": 0.16588781774044037, "invalid_tail_samples": 25.3, "learning_rate": 9.545262359707756e-05, "loss": 0.0602, "positive_teacher_pairs": 26507.0, "relation_loss": 0.0071676459163427355, "selected_pairs": 26507.0, "step": 5400, "student_distance_mean": 770.8792541503906, "teacher_distance_mean": 0.8597228944301605, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0071676459163427355, "weighted_relation_loss": 0.0071676459163427355 }, { "action_query_batch_std": 13.42047939300537, "action_query_norm": 599.7394592285157, "action_relation_loss": 0.007269756635650992, "auxiliary_loss_weight": 1.0, "epoch": 5.060804490177736, "flow_matching_loss": 0.055691903457045555, "grad_norm": 0.17189258337020874, "invalid_tail_samples": 24.1, "learning_rate": 9.542963030233724e-05, "loss": 0.063, "positive_teacher_pairs": 26779.8, "relation_loss": 0.007269756635650992, "selected_pairs": 26779.8, "step": 5410, "student_distance_mean": 755.2263732910156, "teacher_distance_mean": 0.8540614604949951, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.007269756635650992, "weighted_relation_loss": 0.007269756635650992 }, { "action_query_batch_std": 13.194806003570557, "action_query_norm": 596.0346984863281, "action_relation_loss": 0.0075038410257548096, "auxiliary_loss_weight": 1.0, "epoch": 5.070159027128157, "flow_matching_loss": 0.05511383339762688, "grad_norm": 0.20676948130130768, "invalid_tail_samples": 25.0, "learning_rate": 9.540658180631237e-05, "loss": 0.0626, "positive_teacher_pairs": 26569.3, "relation_loss": 0.0075038410257548096, "selected_pairs": 26569.3, "step": 5420, "student_distance_mean": 748.3352294921875, "teacher_distance_mean": 0.8501707792282105, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0075038410257548096, "weighted_relation_loss": 0.0075038410257548096 }, { "action_query_batch_std": 13.469238376617431, "action_query_norm": 607.056201171875, "action_relation_loss": 0.006811731774359941, "auxiliary_loss_weight": 1.0, "epoch": 5.079513564078578, "flow_matching_loss": 0.05399748906493187, "grad_norm": 0.2194119095802307, "invalid_tail_samples": 23.3, "learning_rate": 9.538347813700904e-05, "loss": 0.0608, "positive_teacher_pairs": 26971.9, "relation_loss": 0.006811731774359941, "selected_pairs": 26971.9, "step": 5430, "student_distance_mean": 762.3446655273438, "teacher_distance_mean": 0.8568255782127381, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.006811731774359941, "weighted_relation_loss": 0.006811731774359941 }, { "action_query_batch_std": 13.26673927307129, "action_query_norm": 601.0958984375, "action_relation_loss": 0.007193393865600228, "auxiliary_loss_weight": 1.0, "epoch": 5.088868101028999, "flow_matching_loss": 0.0571787890046835, "grad_norm": 0.15202723443508148, "invalid_tail_samples": 24.8, "learning_rate": 9.536031932250036e-05, "loss": 0.0644, "positive_teacher_pairs": 26619.8, "relation_loss": 0.007193393865600228, "selected_pairs": 26619.8, "step": 5440, "student_distance_mean": 754.2745361328125, "teacher_distance_mean": 0.8475438714027405, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.007193393865600228, "weighted_relation_loss": 0.007193393865600228 }, { "action_query_batch_std": 13.50142765045166, "action_query_norm": 604.1662292480469, "action_relation_loss": 0.007217951724305749, "auxiliary_loss_weight": 1.0, "epoch": 5.09822263797942, "flow_matching_loss": 0.05556834079325199, "grad_norm": 0.2528911530971527, "invalid_tail_samples": 26.6, "learning_rate": 9.533710539092653e-05, "loss": 0.0628, "positive_teacher_pairs": 26205.6, "relation_loss": 0.007217951724305749, "selected_pairs": 26205.6, "step": 5450, "student_distance_mean": 765.7601684570312, "teacher_distance_mean": 0.8568397521972656, "valid_action_samples": 229.4, "weighted_auxiliary_loss": 0.007217951724305749, "weighted_relation_loss": 0.007217951724305749 }, { "action_query_batch_std": 13.36781349182129, "action_query_norm": 599.9046630859375, "action_relation_loss": 0.00721975308842957, "auxiliary_loss_weight": 1.0, "epoch": 5.107577174929841, "flow_matching_loss": 0.05577995143830776, "grad_norm": 0.18820108473300934, "invalid_tail_samples": 25.3, "learning_rate": 9.531383637049464e-05, "loss": 0.063, "positive_teacher_pairs": 26509.4, "relation_loss": 0.00721975308842957, "selected_pairs": 26509.4, "step": 5460, "student_distance_mean": 759.4730834960938, "teacher_distance_mean": 0.857812124490738, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.00721975308842957, "weighted_relation_loss": 0.00721975308842957 }, { "action_query_batch_std": 13.527851486206055, "action_query_norm": 605.3767639160156, "action_relation_loss": 0.006886099604889751, "auxiliary_loss_weight": 1.0, "epoch": 5.1169317118802615, "flow_matching_loss": 0.057622358575463294, "grad_norm": 0.27055466175079346, "invalid_tail_samples": 24.7, "learning_rate": 9.529051228947875e-05, "loss": 0.0645, "positive_teacher_pairs": 26646.4, "relation_loss": 0.006886099604889751, "selected_pairs": 26646.4, "step": 5470, "student_distance_mean": 762.9156860351562, "teacher_distance_mean": 0.8524903059005737, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.006886099604889751, "weighted_relation_loss": 0.006886099604889751 }, { "action_query_batch_std": 13.474799251556396, "action_query_norm": 606.6561218261719, "action_relation_loss": 0.006878442969173193, "auxiliary_loss_weight": 1.0, "epoch": 5.126286248830683, "flow_matching_loss": 0.05559294335544109, "grad_norm": 0.1447719782590866, "invalid_tail_samples": 21.6, "learning_rate": 9.52671331762198e-05, "loss": 0.0625, "positive_teacher_pairs": 27361.6, "relation_loss": 0.006878442969173193, "selected_pairs": 27361.6, "step": 5480, "student_distance_mean": 761.5662231445312, "teacher_distance_mean": 0.8556136310100555, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.006878442969173193, "weighted_relation_loss": 0.006878442969173193 }, { "action_query_batch_std": 13.476299285888672, "action_query_norm": 605.1425842285156, "action_relation_loss": 0.007358453003689647, "auxiliary_loss_weight": 1.0, "epoch": 5.135640785781104, "flow_matching_loss": 0.05703991651535034, "grad_norm": 0.1539161205291748, "invalid_tail_samples": 26.1, "learning_rate": 9.524369905912565e-05, "loss": 0.0644, "positive_teacher_pairs": 26319.3, "relation_loss": 0.007358453003689647, "selected_pairs": 26319.3, "step": 5490, "student_distance_mean": 763.9696350097656, "teacher_distance_mean": 0.8472604572772979, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.007358453003689647, "weighted_relation_loss": 0.007358453003689647 }, { "action_query_batch_std": 13.535195922851562, "action_query_norm": 607.9943542480469, "action_relation_loss": 0.007415206031873822, "auxiliary_loss_weight": 1.0, "epoch": 5.144995322731525, "flow_matching_loss": 0.05445826016366482, "grad_norm": 0.15881100296974182, "invalid_tail_samples": 23.5, "learning_rate": 9.522020996667092e-05, "loss": 0.0619, "positive_teacher_pairs": 26922.7, "relation_loss": 0.007415206031873822, "selected_pairs": 26922.7, "step": 5500, "student_distance_mean": 768.4290222167969, "teacher_distance_mean": 0.8516034066677094, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.007415206031873822, "weighted_relation_loss": 0.007415206031873822 }, { "action_query_batch_std": 13.441265106201172, "action_query_norm": 601.2410522460938, "action_relation_loss": 0.007207745173946023, "auxiliary_loss_weight": 1.0, "epoch": 5.154349859681946, "flow_matching_loss": 0.055749129876494406, "grad_norm": 0.17208026349544525, "invalid_tail_samples": 21.8, "learning_rate": 9.519666592739709e-05, "loss": 0.063, "positive_teacher_pairs": 27312.2, "relation_loss": 0.007207745173946023, "selected_pairs": 27312.2, "step": 5510, "student_distance_mean": 759.2767822265625, "teacher_distance_mean": 0.8508839786052704, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.007207745173946023, "weighted_relation_loss": 0.007207745173946023 }, { "action_query_batch_std": 13.749523258209228, "action_query_norm": 617.078955078125, "action_relation_loss": 0.007262927852571011, "auxiliary_loss_weight": 1.0, "epoch": 5.163704396632367, "flow_matching_loss": 0.05287961885333061, "grad_norm": 0.11570623517036438, "invalid_tail_samples": 25.7, "learning_rate": 9.517306696991241e-05, "loss": 0.0601, "positive_teacher_pairs": 26408.9, "relation_loss": 0.007262927852571011, "selected_pairs": 26408.9, "step": 5520, "student_distance_mean": 775.8193420410156, "teacher_distance_mean": 0.8579248428344727, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.007262927852571011, "weighted_relation_loss": 0.007262927852571011 }, { "action_query_batch_std": 13.582383918762208, "action_query_norm": 608.9569213867187, "action_relation_loss": 0.006879701558500528, "auxiliary_loss_weight": 1.0, "epoch": 5.173058933582787, "flow_matching_loss": 0.05370512343943119, "grad_norm": 0.17067940533161163, "invalid_tail_samples": 24.6, "learning_rate": 9.51494131228918e-05, "loss": 0.0606, "positive_teacher_pairs": 26663.8, "relation_loss": 0.006879701558500528, "selected_pairs": 26663.8, "step": 5530, "student_distance_mean": 771.2948547363281, "teacher_distance_mean": 0.855718195438385, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.006879701558500528, "weighted_relation_loss": 0.006879701558500528 }, { "action_query_batch_std": 13.302266693115234, "action_query_norm": 595.9442077636719, "action_relation_loss": 0.007227908074855805, "auxiliary_loss_weight": 1.0, "epoch": 5.182413470533208, "flow_matching_loss": 0.05536397770047188, "grad_norm": 0.1726020872592926, "invalid_tail_samples": 22.6, "learning_rate": 9.512570441507695e-05, "loss": 0.0626, "positive_teacher_pairs": 27129.1, "relation_loss": 0.007227908074855805, "selected_pairs": 27129.1, "step": 5540, "student_distance_mean": 752.5469360351562, "teacher_distance_mean": 0.8497236490249633, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.007227908074855805, "weighted_relation_loss": 0.007227908074855805 }, { "action_query_batch_std": 13.51328639984131, "action_query_norm": 608.3333312988282, "action_relation_loss": 0.007098494842648506, "auxiliary_loss_weight": 1.0, "epoch": 5.191768007483629, "flow_matching_loss": 0.0554497379809618, "grad_norm": 0.18465562164783478, "invalid_tail_samples": 25.1, "learning_rate": 9.510194087527615e-05, "loss": 0.0625, "positive_teacher_pairs": 26548.2, "relation_loss": 0.007098494842648506, "selected_pairs": 26548.2, "step": 5550, "student_distance_mean": 769.1176452636719, "teacher_distance_mean": 0.8557537257671356, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.007098494842648506, "weighted_relation_loss": 0.007098494842648506 }, { "action_query_batch_std": 13.536069297790528, "action_query_norm": 606.3245239257812, "action_relation_loss": 0.00724113704636693, "auxiliary_loss_weight": 1.0, "epoch": 5.2011225444340505, "flow_matching_loss": 0.05509053096175194, "grad_norm": 0.2444486916065216, "invalid_tail_samples": 20.7, "learning_rate": 9.507812253236435e-05, "loss": 0.0623, "positive_teacher_pairs": 27571.6, "relation_loss": 0.00724113704636693, "selected_pairs": 27571.6, "step": 5560, "student_distance_mean": 762.6839477539063, "teacher_distance_mean": 0.8554112195968628, "valid_action_samples": 235.3, "weighted_auxiliary_loss": 0.00724113704636693, "weighted_relation_loss": 0.00724113704636693 }, { "action_query_batch_std": 13.417887306213379, "action_query_norm": 598.0452270507812, "action_relation_loss": 0.00730621749535203, "auxiliary_loss_weight": 1.0, "epoch": 5.210477081384472, "flow_matching_loss": 0.055524802580475804, "grad_norm": 0.20076344907283783, "invalid_tail_samples": 25.2, "learning_rate": 9.505424941528309e-05, "loss": 0.0628, "positive_teacher_pairs": 26526.3, "relation_loss": 0.00730621749535203, "selected_pairs": 26526.3, "step": 5570, "student_distance_mean": 759.3187561035156, "teacher_distance_mean": 0.8516004681587219, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.00730621749535203, "weighted_relation_loss": 0.00730621749535203 }, { "action_query_batch_std": 13.317102527618408, "action_query_norm": 597.2972778320312, "action_relation_loss": 0.007700952561572194, "auxiliary_loss_weight": 1.0, "epoch": 5.219831618334893, "flow_matching_loss": 0.056953825801610944, "grad_norm": 0.20890215039253235, "invalid_tail_samples": 23.4, "learning_rate": 9.503032155304046e-05, "loss": 0.0647, "positive_teacher_pairs": 26946.0, "relation_loss": 0.007700952561572194, "selected_pairs": 26946.0, "step": 5580, "student_distance_mean": 757.0588317871094, "teacher_distance_mean": 0.8465550601482391, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.007700952561572194, "weighted_relation_loss": 0.007700952561572194 }, { "action_query_batch_std": 13.630239963531494, "action_query_norm": 614.5479370117188, "action_relation_loss": 0.007599565898999572, "auxiliary_loss_weight": 1.0, "epoch": 5.229186155285314, "flow_matching_loss": 0.05916742086410522, "grad_norm": 0.14162930846214294, "invalid_tail_samples": 22.4, "learning_rate": 9.500633897471106e-05, "loss": 0.0668, "positive_teacher_pairs": 27174.9, "relation_loss": 0.007599565898999572, "selected_pairs": 27174.9, "step": 5590, "student_distance_mean": 772.3117370605469, "teacher_distance_mean": 0.8582954406738281, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.007599565898999572, "weighted_relation_loss": 0.007599565898999572 }, { "action_query_batch_std": 13.724293613433838, "action_query_norm": 618.3954284667968, "action_relation_loss": 0.007213276578113437, "auxiliary_loss_weight": 1.0, "epoch": 5.238540692235734, "flow_matching_loss": 0.05555500276386738, "grad_norm": 0.15578071773052216, "invalid_tail_samples": 23.8, "learning_rate": 9.498230170943596e-05, "loss": 0.0628, "positive_teacher_pairs": 26855.0, "relation_loss": 0.007213276578113437, "selected_pairs": 26855.0, "step": 5600, "student_distance_mean": 777.6493957519531, "teacher_distance_mean": 0.8573739290237427, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.007213276578113437, "weighted_relation_loss": 0.007213276578113437 }, { "action_query_batch_std": 13.713641166687012, "action_query_norm": 612.8508117675781, "action_relation_loss": 0.007014036923646927, "auxiliary_loss_weight": 1.0, "epoch": 5.247895229186155, "flow_matching_loss": 0.05688416436314583, "grad_norm": 0.12527549266815186, "invalid_tail_samples": 22.7, "learning_rate": 9.495820978642275e-05, "loss": 0.0639, "positive_teacher_pairs": 27106.6, "relation_loss": 0.007014036923646927, "selected_pairs": 27106.6, "step": 5610, "student_distance_mean": 776.0135131835938, "teacher_distance_mean": 0.8524515271186829, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.007014036923646927, "weighted_relation_loss": 0.007014036923646927 }, { "action_query_batch_std": 13.97016134262085, "action_query_norm": 624.9058044433593, "action_relation_loss": 0.006993307825177908, "auxiliary_loss_weight": 1.0, "epoch": 5.257249766136576, "flow_matching_loss": 0.05513351112604141, "grad_norm": 0.1451752781867981, "invalid_tail_samples": 23.7, "learning_rate": 9.493406323494535e-05, "loss": 0.0621, "positive_teacher_pairs": 26876.7, "relation_loss": 0.006993307825177908, "selected_pairs": 26876.7, "step": 5620, "student_distance_mean": 791.782080078125, "teacher_distance_mean": 0.8634278893470764, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.006993307825177908, "weighted_relation_loss": 0.006993307825177908 }, { "action_query_batch_std": 13.751214694976806, "action_query_norm": 613.9536682128906, "action_relation_loss": 0.007520127017050982, "auxiliary_loss_weight": 1.0, "epoch": 5.266604303086997, "flow_matching_loss": 0.054373249784111975, "grad_norm": 0.18653526902198792, "invalid_tail_samples": 26.4, "learning_rate": 9.490986208434413e-05, "loss": 0.0619, "positive_teacher_pairs": 26261.9, "relation_loss": 0.007520127017050982, "selected_pairs": 26261.9, "step": 5630, "student_distance_mean": 782.49287109375, "teacher_distance_mean": 0.8597780525684356, "valid_action_samples": 229.6, "weighted_auxiliary_loss": 0.007520127017050982, "weighted_relation_loss": 0.007520127017050982 }, { "action_query_batch_std": 13.694399547576904, "action_query_norm": 614.0503479003906, "action_relation_loss": 0.007076407643035054, "auxiliary_loss_weight": 1.0, "epoch": 5.275958840037418, "flow_matching_loss": 0.05695269666612148, "grad_norm": 0.14702409505844116, "invalid_tail_samples": 22.3, "learning_rate": 9.488560636402577e-05, "loss": 0.064, "positive_teacher_pairs": 27202.2, "relation_loss": 0.007076407643035054, "selected_pairs": 27202.2, "step": 5640, "student_distance_mean": 774.5672058105469, "teacher_distance_mean": 0.8587603509426117, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.007076407643035054, "weighted_relation_loss": 0.007076407643035054 }, { "action_query_batch_std": 13.561741352081299, "action_query_norm": 612.7293762207031, "action_relation_loss": 0.0074540743138641116, "auxiliary_loss_weight": 1.0, "epoch": 5.285313376987839, "flow_matching_loss": 0.05452801398932934, "grad_norm": 0.22800613939762115, "invalid_tail_samples": 22.4, "learning_rate": 9.486129610346321e-05, "loss": 0.062, "positive_teacher_pairs": 27172.4, "relation_loss": 0.0074540743138641116, "selected_pairs": 27172.4, "step": 5650, "student_distance_mean": 768.3717224121094, "teacher_distance_mean": 0.8472028136253357, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.0074540743138641116, "weighted_relation_loss": 0.0074540743138641116 }, { "action_query_batch_std": 13.629422664642334, "action_query_norm": 614.97607421875, "action_relation_loss": 0.007055229274556041, "auxiliary_loss_weight": 1.0, "epoch": 5.29466791393826, "flow_matching_loss": 0.0538902148604393, "grad_norm": 0.13016009330749512, "invalid_tail_samples": 23.9, "learning_rate": 9.483693133219576e-05, "loss": 0.0609, "positive_teacher_pairs": 26824.9, "relation_loss": 0.007055229274556041, "selected_pairs": 26824.9, "step": 5660, "student_distance_mean": 769.9256652832031, "teacher_distance_mean": 0.8477981448173523, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.007055229274556041, "weighted_relation_loss": 0.007055229274556041 }, { "action_query_batch_std": 13.626437377929687, "action_query_norm": 614.50517578125, "action_relation_loss": 0.007529001403599978, "auxiliary_loss_weight": 1.0, "epoch": 5.304022450888681, "flow_matching_loss": 0.05741958916187286, "grad_norm": 0.1568421721458435, "invalid_tail_samples": 25.5, "learning_rate": 9.481251207982888e-05, "loss": 0.0649, "positive_teacher_pairs": 26458.3, "relation_loss": 0.007529001403599978, "selected_pairs": 26458.3, "step": 5670, "student_distance_mean": 772.304345703125, "teacher_distance_mean": 0.854397988319397, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.007529001403599978, "weighted_relation_loss": 0.007529001403599978 }, { "action_query_batch_std": 13.570557403564454, "action_query_norm": 610.1937194824219, "action_relation_loss": 0.00695236618630588, "auxiliary_loss_weight": 1.0, "epoch": 5.313376987839102, "flow_matching_loss": 0.05613969452679157, "grad_norm": 0.14889837801456451, "invalid_tail_samples": 23.3, "learning_rate": 9.47880383760343e-05, "loss": 0.0631, "positive_teacher_pairs": 26971.7, "relation_loss": 0.00695236618630588, "selected_pairs": 26971.7, "step": 5680, "student_distance_mean": 770.0918884277344, "teacher_distance_mean": 0.854418933391571, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.00695236618630588, "weighted_relation_loss": 0.00695236618630588 }, { "action_query_batch_std": 13.490186500549317, "action_query_norm": 607.9477355957031, "action_relation_loss": 0.0072788198478519915, "auxiliary_loss_weight": 1.0, "epoch": 5.322731524789523, "flow_matching_loss": 0.055984356254339215, "grad_norm": 0.13101284205913544, "invalid_tail_samples": 23.1, "learning_rate": 9.476351025054983e-05, "loss": 0.0633, "positive_teacher_pairs": 27018.2, "relation_loss": 0.0072788198478519915, "selected_pairs": 27018.2, "step": 5690, "student_distance_mean": 762.9152099609375, "teacher_distance_mean": 0.8476301014423371, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0072788198478519915, "weighted_relation_loss": 0.0072788198478519915 }, { "action_query_batch_std": 13.797701263427735, "action_query_norm": 619.9428771972656, "action_relation_loss": 0.0073827972635626795, "auxiliary_loss_weight": 1.0, "epoch": 5.332086061739944, "flow_matching_loss": 0.05567741543054581, "grad_norm": 0.15797008574008942, "invalid_tail_samples": 23.7, "learning_rate": 9.473892773317952e-05, "loss": 0.0631, "positive_teacher_pairs": 26873.0, "relation_loss": 0.0073827972635626795, "selected_pairs": 26873.0, "step": 5700, "student_distance_mean": 780.3870300292969, "teacher_distance_mean": 0.8639989137649536, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0073827972635626795, "weighted_relation_loss": 0.0073827972635626795 }, { "action_query_batch_std": 13.513033771514893, "action_query_norm": 609.9706970214844, "action_relation_loss": 0.00757750878110528, "auxiliary_loss_weight": 1.0, "epoch": 5.341440598690365, "flow_matching_loss": 0.05222084149718285, "grad_norm": 0.17843030393123627, "invalid_tail_samples": 26.3, "learning_rate": 9.471429085379338e-05, "loss": 0.0598, "positive_teacher_pairs": 26276.1, "relation_loss": 0.00757750878110528, "selected_pairs": 26276.1, "step": 5710, "student_distance_mean": 765.177587890625, "teacher_distance_mean": 0.8409736752510071, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.00757750878110528, "weighted_relation_loss": 0.00757750878110528 }, { "action_query_batch_std": 13.945691680908203, "action_query_norm": 624.2149719238281, "action_relation_loss": 0.007057943847030401, "auxiliary_loss_weight": 1.0, "epoch": 5.3507951356407855, "flow_matching_loss": 0.05299031175673008, "grad_norm": 0.1533742994070053, "invalid_tail_samples": 22.5, "learning_rate": 9.468959964232757e-05, "loss": 0.06, "positive_teacher_pairs": 27154.9, "relation_loss": 0.007057943847030401, "selected_pairs": 27154.9, "step": 5720, "student_distance_mean": 790.3610534667969, "teacher_distance_mean": 0.86240856051445, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.007057943847030401, "weighted_relation_loss": 0.007057943847030401 }, { "action_query_batch_std": 13.838502120971679, "action_query_norm": 619.9067932128906, "action_relation_loss": 0.007613981747999788, "auxiliary_loss_weight": 1.0, "epoch": 5.360149672591207, "flow_matching_loss": 0.05691146440804005, "grad_norm": 0.13240942358970642, "invalid_tail_samples": 25.1, "learning_rate": 9.466485412878425e-05, "loss": 0.0645, "positive_teacher_pairs": 26553.9, "relation_loss": 0.007613981747999788, "selected_pairs": 26553.9, "step": 5730, "student_distance_mean": 783.2471008300781, "teacher_distance_mean": 0.85621936917305, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.007613981747999788, "weighted_relation_loss": 0.007613981747999788 }, { "action_query_batch_std": 13.96857213973999, "action_query_norm": 623.8596862792969, "action_relation_loss": 0.007189827458932996, "auxiliary_loss_weight": 1.0, "epoch": 5.369504209541628, "flow_matching_loss": 0.05464188121259213, "grad_norm": 0.19504818320274353, "invalid_tail_samples": 24.0, "learning_rate": 9.464005434323154e-05, "loss": 0.0618, "positive_teacher_pairs": 26803.3, "relation_loss": 0.007189827458932996, "selected_pairs": 26803.3, "step": 5740, "student_distance_mean": 784.6742797851563, "teacher_distance_mean": 0.8550743043422699, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.007189827458932996, "weighted_relation_loss": 0.007189827458932996 }, { "action_query_batch_std": 13.888759136199951, "action_query_norm": 623.8095642089844, "action_relation_loss": 0.00750470906496048, "auxiliary_loss_weight": 1.0, "epoch": 5.378858746492049, "flow_matching_loss": 0.05530648455023766, "grad_norm": 0.17729060351848602, "invalid_tail_samples": 22.9, "learning_rate": 9.461520031580352e-05, "loss": 0.0628, "positive_teacher_pairs": 27059.6, "relation_loss": 0.00750470906496048, "selected_pairs": 27059.6, "step": 5750, "student_distance_mean": 786.43408203125, "teacher_distance_mean": 0.8533148527145386, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.00750470906496048, "weighted_relation_loss": 0.00750470906496048 }, { "action_query_batch_std": 14.023475551605225, "action_query_norm": 634.5955871582031, "action_relation_loss": 0.007282687490805984, "auxiliary_loss_weight": 1.0, "epoch": 5.38821328344247, "flow_matching_loss": 0.05458526872098446, "grad_norm": 0.21208757162094116, "invalid_tail_samples": 22.4, "learning_rate": 9.459029207670019e-05, "loss": 0.0619, "positive_teacher_pairs": 27181.1, "relation_loss": 0.007282687490805984, "selected_pairs": 27181.1, "step": 5760, "student_distance_mean": 793.74853515625, "teacher_distance_mean": 0.8608278632164001, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.007282687490805984, "weighted_relation_loss": 0.007282687490805984 }, { "action_query_batch_std": 13.73639965057373, "action_query_norm": 622.427587890625, "action_relation_loss": 0.007048936886712908, "auxiliary_loss_weight": 1.0, "epoch": 5.397567820392891, "flow_matching_loss": 0.05640593506395817, "grad_norm": 0.15900076925754547, "invalid_tail_samples": 24.8, "learning_rate": 9.456532965618737e-05, "loss": 0.0635, "positive_teacher_pairs": 26613.9, "relation_loss": 0.007048936886712908, "selected_pairs": 26613.9, "step": 5770, "student_distance_mean": 778.1683227539063, "teacher_distance_mean": 0.8584268271923066, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.007048936886712908, "weighted_relation_loss": 0.007048936886712908 }, { "action_query_batch_std": 13.894360256195068, "action_query_norm": 624.6501708984375, "action_relation_loss": 0.00733443358913064, "auxiliary_loss_weight": 1.0, "epoch": 5.406922357343311, "flow_matching_loss": 0.057553937658667564, "grad_norm": 0.1910320669412613, "invalid_tail_samples": 22.0, "learning_rate": 9.454031308459681e-05, "loss": 0.0649, "positive_teacher_pairs": 27269.6, "relation_loss": 0.00733443358913064, "selected_pairs": 27269.6, "step": 5780, "student_distance_mean": 785.1164306640625, "teacher_distance_mean": 0.8550061762332917, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.00733443358913064, "weighted_relation_loss": 0.00733443358913064 }, { "action_query_batch_std": 13.861412811279298, "action_query_norm": 626.381689453125, "action_relation_loss": 0.007082986971363425, "auxiliary_loss_weight": 1.0, "epoch": 5.416276894293732, "flow_matching_loss": 0.05341317839920521, "grad_norm": 0.17131049931049347, "invalid_tail_samples": 25.7, "learning_rate": 9.451524239232595e-05, "loss": 0.0605, "positive_teacher_pairs": 26415.6, "relation_loss": 0.007082986971363425, "selected_pairs": 26415.6, "step": 5790, "student_distance_mean": 786.6143005371093, "teacher_distance_mean": 0.857056725025177, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.007082986971363425, "weighted_relation_loss": 0.007082986971363425 }, { "action_query_batch_std": 13.805867576599121, "action_query_norm": 622.8856506347656, "action_relation_loss": 0.006659496109932661, "auxiliary_loss_weight": 1.0, "epoch": 5.425631431244153, "flow_matching_loss": 0.054880644753575326, "grad_norm": 0.16279438138008118, "invalid_tail_samples": 25.4, "learning_rate": 9.449011760983809e-05, "loss": 0.0615, "positive_teacher_pairs": 26490.2, "relation_loss": 0.006659496109932661, "selected_pairs": 26490.2, "step": 5800, "student_distance_mean": 786.35087890625, "teacher_distance_mean": 0.8560605823993683, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.006659496109932661, "weighted_relation_loss": 0.006659496109932661 }, { "action_query_batch_std": 13.871086120605469, "action_query_norm": 621.7814514160157, "action_relation_loss": 0.007055853074416518, "auxiliary_loss_weight": 1.0, "epoch": 5.4349859681945745, "flow_matching_loss": 0.053094587102532384, "grad_norm": 0.1994926780462265, "invalid_tail_samples": 21.9, "learning_rate": 9.446493876766218e-05, "loss": 0.0602, "positive_teacher_pairs": 27287.8, "relation_loss": 0.007055853074416518, "selected_pairs": 27287.8, "step": 5810, "student_distance_mean": 784.0595825195312, "teacher_distance_mean": 0.86078240275383, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.007055853074416518, "weighted_relation_loss": 0.007055853074416518 }, { "action_query_batch_std": 13.781217193603515, "action_query_norm": 616.4867614746094, "action_relation_loss": 0.00715422579087317, "auxiliary_loss_weight": 1.0, "epoch": 5.444340505144996, "flow_matching_loss": 0.05610182508826256, "grad_norm": 0.1709652841091156, "invalid_tail_samples": 22.9, "learning_rate": 9.44397058963929e-05, "loss": 0.0633, "positive_teacher_pairs": 27059.5, "relation_loss": 0.00715422579087317, "selected_pairs": 27059.5, "step": 5820, "student_distance_mean": 781.0665344238281, "teacher_distance_mean": 0.8592698216438294, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.00715422579087317, "weighted_relation_loss": 0.00715422579087317 }, { "action_query_batch_std": 13.809670352935791, "action_query_norm": 618.8268920898438, "action_relation_loss": 0.0069383200723677875, "auxiliary_loss_weight": 1.0, "epoch": 5.453695042095417, "flow_matching_loss": 0.05425047948956489, "grad_norm": 0.14704661071300507, "invalid_tail_samples": 24.9, "learning_rate": 9.441441902669056e-05, "loss": 0.0612, "positive_teacher_pairs": 26595.7, "relation_loss": 0.0069383200723677875, "selected_pairs": 26595.7, "step": 5830, "student_distance_mean": 781.1505920410157, "teacher_distance_mean": 0.852252197265625, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0069383200723677875, "weighted_relation_loss": 0.0069383200723677875 }, { "action_query_batch_std": 13.95989990234375, "action_query_norm": 628.025390625, "action_relation_loss": 0.007497373130172491, "auxiliary_loss_weight": 1.0, "epoch": 5.463049579045837, "flow_matching_loss": 0.05531679093837738, "grad_norm": 0.13197173178195953, "invalid_tail_samples": 23.1, "learning_rate": 9.43890781892811e-05, "loss": 0.0628, "positive_teacher_pairs": 27014.4, "relation_loss": 0.007497373130172491, "selected_pairs": 27014.4, "step": 5840, "student_distance_mean": 789.6153686523437, "teacher_distance_mean": 0.8576492011547089, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.007497373130172491, "weighted_relation_loss": 0.007497373130172491 }, { "action_query_batch_std": 14.009330654144287, "action_query_norm": 630.1172912597656, "action_relation_loss": 0.0070131492335349325, "auxiliary_loss_weight": 1.0, "epoch": 5.472404115996258, "flow_matching_loss": 0.0542121771723032, "grad_norm": 0.17810405790805817, "invalid_tail_samples": 23.4, "learning_rate": 9.436368341495603e-05, "loss": 0.0612, "positive_teacher_pairs": 26949.8, "relation_loss": 0.0070131492335349325, "selected_pairs": 26949.8, "step": 5850, "student_distance_mean": 792.8898559570313, "teacher_distance_mean": 0.8625922679901123, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0070131492335349325, "weighted_relation_loss": 0.0070131492335349325 }, { "action_query_batch_std": 13.894613075256348, "action_query_norm": 628.1130126953125, "action_relation_loss": 0.0073201537132263185, "auxiliary_loss_weight": 1.0, "epoch": 5.481758652946679, "flow_matching_loss": 0.055225181952118875, "grad_norm": 0.1776180863380432, "invalid_tail_samples": 21.7, "learning_rate": 9.43382347345724e-05, "loss": 0.0625, "positive_teacher_pairs": 27335.9, "relation_loss": 0.0073201537132263185, "selected_pairs": 27335.9, "step": 5860, "student_distance_mean": 784.7971618652343, "teacher_distance_mean": 0.84439337849617, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.0073201537132263185, "weighted_relation_loss": 0.0073201537132263185 }, { "action_query_batch_std": 13.585272598266602, "action_query_norm": 614.1277648925782, "action_relation_loss": 0.007509873015806079, "auxiliary_loss_weight": 1.0, "epoch": 5.4911131898971, "flow_matching_loss": 0.055064361169934274, "grad_norm": 0.11935677379369736, "invalid_tail_samples": 23.4, "learning_rate": 9.431273217905273e-05, "loss": 0.0626, "positive_teacher_pairs": 26948.9, "relation_loss": 0.007509873015806079, "selected_pairs": 26948.9, "step": 5870, "student_distance_mean": 772.731201171875, "teacher_distance_mean": 0.8482034087181092, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.007509873015806079, "weighted_relation_loss": 0.007509873015806079 }, { "action_query_batch_std": 13.877599811553955, "action_query_norm": 624.1390441894531, "action_relation_loss": 0.006800603354349732, "auxiliary_loss_weight": 1.0, "epoch": 5.500467726847521, "flow_matching_loss": 0.05412820838391781, "grad_norm": 0.13685984909534454, "invalid_tail_samples": 24.5, "learning_rate": 9.428717577938504e-05, "loss": 0.0609, "positive_teacher_pairs": 26688.4, "relation_loss": 0.006800603354349732, "selected_pairs": 26688.4, "step": 5880, "student_distance_mean": 787.3892517089844, "teacher_distance_mean": 0.8569596529006958, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.006800603354349732, "weighted_relation_loss": 0.006800603354349732 }, { "action_query_batch_std": 13.942207050323486, "action_query_norm": 620.8105407714844, "action_relation_loss": 0.006768537079915404, "auxiliary_loss_weight": 1.0, "epoch": 5.509822263797942, "flow_matching_loss": 0.05573898665606976, "grad_norm": 0.12849342823028564, "invalid_tail_samples": 24.7, "learning_rate": 9.426156556662276e-05, "loss": 0.0625, "positive_teacher_pairs": 26641.6, "relation_loss": 0.006768537079915404, "selected_pairs": 26641.6, "step": 5890, "student_distance_mean": 790.5421447753906, "teacher_distance_mean": 0.8621391654014587, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.006768537079915404, "weighted_relation_loss": 0.006768537079915404 }, { "action_query_batch_std": 13.68750877380371, "action_query_norm": 617.4521667480469, "action_relation_loss": 0.0069921948481351135, "auxiliary_loss_weight": 1.0, "epoch": 5.519176800748363, "flow_matching_loss": 0.054536083713173866, "grad_norm": 0.1847924441099167, "invalid_tail_samples": 23.8, "learning_rate": 9.423590157188474e-05, "loss": 0.0615, "positive_teacher_pairs": 26851.1, "relation_loss": 0.0069921948481351135, "selected_pairs": 26851.1, "step": 5900, "student_distance_mean": 776.7873779296875, "teacher_distance_mean": 0.8449424505233765, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0069921948481351135, "weighted_relation_loss": 0.0069921948481351135 }, { "action_query_batch_std": 13.886480808258057, "action_query_norm": 623.7974426269532, "action_relation_loss": 0.007087680045515299, "auxiliary_loss_weight": 1.0, "epoch": 5.528531337698784, "flow_matching_loss": 0.05622442439198494, "grad_norm": 0.18215449154376984, "invalid_tail_samples": 24.8, "learning_rate": 9.421018382635513e-05, "loss": 0.0633, "positive_teacher_pairs": 26630.4, "relation_loss": 0.007087680045515299, "selected_pairs": 26630.4, "step": 5910, "student_distance_mean": 787.8203125, "teacher_distance_mean": 0.8508593380451203, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.007087680045515299, "weighted_relation_loss": 0.007087680045515299 }, { "action_query_batch_std": 14.157320499420166, "action_query_norm": 630.2516967773438, "action_relation_loss": 0.0068121208809316155, "auxiliary_loss_weight": 1.0, "epoch": 5.537885874649205, "flow_matching_loss": 0.05566430166363716, "grad_norm": 0.12995661795139313, "invalid_tail_samples": 24.4, "learning_rate": 9.418441236128343e-05, "loss": 0.0625, "positive_teacher_pairs": 26711.6, "relation_loss": 0.0068121208809316155, "selected_pairs": 26711.6, "step": 5920, "student_distance_mean": 802.2243896484375, "teacher_distance_mean": 0.8722420156002044, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0068121208809316155, "weighted_relation_loss": 0.0068121208809316155 }, { "action_query_batch_std": 13.97934513092041, "action_query_norm": 631.3638732910156, "action_relation_loss": 0.00745537793263793, "auxiliary_loss_weight": 1.0, "epoch": 5.547240411599626, "flow_matching_loss": 0.05485417209565639, "grad_norm": 0.161187544465065, "invalid_tail_samples": 20.0, "learning_rate": 9.41585872079844e-05, "loss": 0.0623, "positive_teacher_pairs": 27744.1, "relation_loss": 0.00745537793263793, "selected_pairs": 27744.1, "step": 5930, "student_distance_mean": 794.0658508300781, "teacher_distance_mean": 0.8573518812656402, "valid_action_samples": 236.0, "weighted_auxiliary_loss": 0.00745537793263793, "weighted_relation_loss": 0.00745537793263793 }, { "action_query_batch_std": 13.719785499572755, "action_query_norm": 617.9749938964844, "action_relation_loss": 0.007231146469712258, "auxiliary_loss_weight": 1.0, "epoch": 5.556594948550047, "flow_matching_loss": 0.05447305552661419, "grad_norm": 0.15022355318069458, "invalid_tail_samples": 24.3, "learning_rate": 9.413270839783802e-05, "loss": 0.0617, "positive_teacher_pairs": 26741.4, "relation_loss": 0.007231146469712258, "selected_pairs": 26741.4, "step": 5940, "student_distance_mean": 779.4519897460938, "teacher_distance_mean": 0.8511324286460876, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.007231146469712258, "weighted_relation_loss": 0.007231146469712258 }, { "action_query_batch_std": 13.884416103363037, "action_query_norm": 622.7110046386719, "action_relation_loss": 0.006524907704442739, "auxiliary_loss_weight": 1.0, "epoch": 5.565949485500468, "flow_matching_loss": 0.0544683177024126, "grad_norm": 0.16213198006153107, "invalid_tail_samples": 24.1, "learning_rate": 9.41067759622895e-05, "loss": 0.061, "positive_teacher_pairs": 26776.6, "relation_loss": 0.006524907704442739, "selected_pairs": 26776.6, "step": 5950, "student_distance_mean": 788.7061767578125, "teacher_distance_mean": 0.8503491759300232, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.006524907704442739, "weighted_relation_loss": 0.006524907704442739 }, { "action_query_batch_std": 13.934777069091798, "action_query_norm": 628.9301086425781, "action_relation_loss": 0.007087185420095921, "auxiliary_loss_weight": 1.0, "epoch": 5.575304022450888, "flow_matching_loss": 0.055214031413197515, "grad_norm": 0.17611098289489746, "invalid_tail_samples": 25.2, "learning_rate": 9.408078993284917e-05, "loss": 0.0623, "positive_teacher_pairs": 26529.1, "relation_loss": 0.007087185420095921, "selected_pairs": 26529.1, "step": 5960, "student_distance_mean": 788.0182434082031, "teacher_distance_mean": 0.854499101638794, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.007087185420095921, "weighted_relation_loss": 0.007087185420095921 }, { "action_query_batch_std": 14.001750373840332, "action_query_norm": 628.8391235351562, "action_relation_loss": 0.006950820097699761, "auxiliary_loss_weight": 1.0, "epoch": 5.584658559401309, "flow_matching_loss": 0.05537449792027473, "grad_norm": 0.17625091969966888, "invalid_tail_samples": 24.7, "learning_rate": 9.405475034109254e-05, "loss": 0.0623, "positive_teacher_pairs": 26644.7, "relation_loss": 0.006950820097699761, "selected_pairs": 26644.7, "step": 5970, "student_distance_mean": 795.6242004394531, "teacher_distance_mean": 0.8532105088233948, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.006950820097699761, "weighted_relation_loss": 0.006950820097699761 }, { "action_query_batch_std": 14.175667095184327, "action_query_norm": 636.4814208984375, "action_relation_loss": 0.006885630451142788, "auxiliary_loss_weight": 1.0, "epoch": 5.5940130963517305, "flow_matching_loss": 0.05320120379328728, "grad_norm": 0.19490312039852142, "invalid_tail_samples": 26.2, "learning_rate": 9.402865721866015e-05, "loss": 0.0601, "positive_teacher_pairs": 26301.0, "relation_loss": 0.006885630451142788, "selected_pairs": 26301.0, "step": 5980, "student_distance_mean": 803.5849426269531, "teacher_distance_mean": 0.856737595796585, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.006885630451142788, "weighted_relation_loss": 0.006885630451142788 }, { "action_query_batch_std": 14.183108711242676, "action_query_norm": 638.8309143066406, "action_relation_loss": 0.006890122592449188, "auxiliary_loss_weight": 1.0, "epoch": 5.603367633302152, "flow_matching_loss": 0.053840261325240134, "grad_norm": 0.14571094512939453, "invalid_tail_samples": 24.0, "learning_rate": 9.400251059725762e-05, "loss": 0.0607, "positive_teacher_pairs": 26803.1, "relation_loss": 0.006890122592449188, "selected_pairs": 26803.1, "step": 5990, "student_distance_mean": 803.816748046875, "teacher_distance_mean": 0.8650400519371033, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.006890122592449188, "weighted_relation_loss": 0.006890122592449188 }, { "action_query_batch_std": 13.87226848602295, "action_query_norm": 627.8890075683594, "action_relation_loss": 0.007117590028792619, "auxiliary_loss_weight": 1.0, "epoch": 5.612722170252573, "flow_matching_loss": 0.05447879545390606, "grad_norm": 0.16027884185314178, "invalid_tail_samples": 23.5, "learning_rate": 9.397631050865554e-05, "loss": 0.0616, "positive_teacher_pairs": 26915.3, "relation_loss": 0.007117590028792619, "selected_pairs": 26915.3, "step": 6000, "student_distance_mean": 787.0648132324219, "teacher_distance_mean": 0.8534127831459045, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.007117590028792619, "weighted_relation_loss": 0.007117590028792619 }, { "action_query_batch_std": 13.837385177612305, "action_query_norm": 623.0961181640625, "action_relation_loss": 0.007014862447977066, "auxiliary_loss_weight": 1.0, "epoch": 5.622076707202994, "flow_matching_loss": 0.05342728346586227, "grad_norm": 0.1566719263792038, "invalid_tail_samples": 23.1, "learning_rate": 9.395005698468949e-05, "loss": 0.0604, "positive_teacher_pairs": 27026.6, "relation_loss": 0.007014862447977066, "selected_pairs": 27026.6, "step": 6010, "student_distance_mean": 783.9191223144531, "teacher_distance_mean": 0.8463877856731414, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.007014862447977066, "weighted_relation_loss": 0.007014862447977066 }, { "action_query_batch_std": 14.022722530364991, "action_query_norm": 629.7205444335938, "action_relation_loss": 0.007252285815775394, "auxiliary_loss_weight": 1.0, "epoch": 5.631431244153415, "flow_matching_loss": 0.053362160176038745, "grad_norm": 0.17347437143325806, "invalid_tail_samples": 22.3, "learning_rate": 9.392375005726e-05, "loss": 0.0606, "positive_teacher_pairs": 27200.2, "relation_loss": 0.007252285815775394, "selected_pairs": 27200.2, "step": 6020, "student_distance_mean": 794.2074829101563, "teacher_distance_mean": 0.8600810110569, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.007252285815775394, "weighted_relation_loss": 0.007252285815775394 }, { "action_query_batch_std": 14.044410037994385, "action_query_norm": 633.8144714355469, "action_relation_loss": 0.006824387144297362, "auxiliary_loss_weight": 1.0, "epoch": 5.640785781103835, "flow_matching_loss": 0.05170020163059234, "grad_norm": 0.13421791791915894, "invalid_tail_samples": 24.5, "learning_rate": 9.389738975833242e-05, "loss": 0.0585, "positive_teacher_pairs": 26696.7, "relation_loss": 0.006824387144297362, "selected_pairs": 26696.7, "step": 6030, "student_distance_mean": 796.5548034667969, "teacher_distance_mean": 0.850164270401001, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.006824387144297362, "weighted_relation_loss": 0.006824387144297362 }, { "action_query_batch_std": 14.283580493927001, "action_query_norm": 643.16103515625, "action_relation_loss": 0.007272259332239628, "auxiliary_loss_weight": 1.0, "epoch": 5.650140318054256, "flow_matching_loss": 0.05207181796431541, "grad_norm": 0.13704049587249756, "invalid_tail_samples": 23.5, "learning_rate": 9.387097611993707e-05, "loss": 0.0593, "positive_teacher_pairs": 26919.0, "relation_loss": 0.007272259332239628, "selected_pairs": 26919.0, "step": 6040, "student_distance_mean": 808.8964965820312, "teacher_distance_mean": 0.8568325996398926, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.007272259332239628, "weighted_relation_loss": 0.007272259332239628 }, { "action_query_batch_std": 14.27382173538208, "action_query_norm": 637.050830078125, "action_relation_loss": 0.007185416109859943, "auxiliary_loss_weight": 1.0, "epoch": 5.659494855004677, "flow_matching_loss": 0.054381690174341205, "grad_norm": 0.12212732434272766, "invalid_tail_samples": 23.1, "learning_rate": 9.384450917416894e-05, "loss": 0.0616, "positive_teacher_pairs": 27009.5, "relation_loss": 0.007185416109859943, "selected_pairs": 27009.5, "step": 6050, "student_distance_mean": 808.2976928710938, "teacher_distance_mean": 0.8578768312931061, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.007185416109859943, "weighted_relation_loss": 0.007185416109859943 }, { "action_query_batch_std": 14.294675827026367, "action_query_norm": 640.5543212890625, "action_relation_loss": 0.006859307922422886, "auxiliary_loss_weight": 1.0, "epoch": 5.668849391955098, "flow_matching_loss": 0.053890210762619975, "grad_norm": 0.19576284289360046, "invalid_tail_samples": 23.9, "learning_rate": 9.381798895318792e-05, "loss": 0.0607, "positive_teacher_pairs": 26828.1, "relation_loss": 0.006859307922422886, "selected_pairs": 26828.1, "step": 6060, "student_distance_mean": 810.1572998046875, "teacher_distance_mean": 0.8656470656394959, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.006859307922422886, "weighted_relation_loss": 0.006859307922422886 }, { "action_query_batch_std": 14.279448223114013, "action_query_norm": 636.3725708007812, "action_relation_loss": 0.006904137833043933, "auxiliary_loss_weight": 1.0, "epoch": 5.6782039289055195, "flow_matching_loss": 0.052660347893834114, "grad_norm": 0.2053343802690506, "invalid_tail_samples": 22.2, "learning_rate": 9.379141548921853e-05, "loss": 0.0596, "positive_teacher_pairs": 27220.6, "relation_loss": 0.006904137833043933, "selected_pairs": 27220.6, "step": 6070, "student_distance_mean": 802.9817260742187, "teacher_distance_mean": 0.851851636171341, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.006904137833043933, "weighted_relation_loss": 0.006904137833043933 }, { "action_query_batch_std": 14.153242683410644, "action_query_norm": 636.2794189453125, "action_relation_loss": 0.006987565755844116, "auxiliary_loss_weight": 1.0, "epoch": 5.68755846585594, "flow_matching_loss": 0.056231862679123876, "grad_norm": 0.1168292984366417, "invalid_tail_samples": 22.0, "learning_rate": 9.376478881455009e-05, "loss": 0.0632, "positive_teacher_pairs": 27269.6, "relation_loss": 0.006987565755844116, "selected_pairs": 27269.6, "step": 6080, "student_distance_mean": 798.7034851074219, "teacher_distance_mean": 0.8459052443504333, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.006987565755844116, "weighted_relation_loss": 0.006987565755844116 }, { "action_query_batch_std": 14.330132293701173, "action_query_norm": 640.6326904296875, "action_relation_loss": 0.006692096963524819, "auxiliary_loss_weight": 1.0, "epoch": 5.696913002806361, "flow_matching_loss": 0.054401126131415366, "grad_norm": 0.17029336094856262, "invalid_tail_samples": 21.7, "learning_rate": 9.373810896153647e-05, "loss": 0.0611, "positive_teacher_pairs": 27342.2, "relation_loss": 0.006692096963524819, "selected_pairs": 27342.2, "step": 6090, "student_distance_mean": 811.253466796875, "teacher_distance_mean": 0.8596122324466705, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.006692096963524819, "weighted_relation_loss": 0.006692096963524819 }, { "action_query_batch_std": 14.544793510437012, "action_query_norm": 651.1885620117188, "action_relation_loss": 0.006887412490323186, "auxiliary_loss_weight": 1.0, "epoch": 5.706267539756782, "flow_matching_loss": 0.05531417168676853, "grad_norm": 0.16898185014724731, "invalid_tail_samples": 21.7, "learning_rate": 9.371137596259623e-05, "loss": 0.0622, "positive_teacher_pairs": 27346.2, "relation_loss": 0.006887412490323186, "selected_pairs": 27346.2, "step": 6100, "student_distance_mean": 820.5137573242188, "teacher_distance_mean": 0.8575326919555664, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.006887412490323186, "weighted_relation_loss": 0.006887412490323186 }, { "action_query_batch_std": 14.55668830871582, "action_query_norm": 651.25166015625, "action_relation_loss": 0.00685891998000443, "auxiliary_loss_weight": 1.0, "epoch": 5.715622076707203, "flow_matching_loss": 0.05636813566088676, "grad_norm": 0.17083275318145752, "invalid_tail_samples": 26.3, "learning_rate": 9.368458985021248e-05, "loss": 0.0632, "positive_teacher_pairs": 26277.3, "relation_loss": 0.00685891998000443, "selected_pairs": 26277.3, "step": 6110, "student_distance_mean": 827.3696533203125, "teacher_distance_mean": 0.8567015826702118, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.00685891998000443, "weighted_relation_loss": 0.00685891998000443 }, { "action_query_batch_std": 14.325204849243164, "action_query_norm": 641.3421813964844, "action_relation_loss": 0.007238085847347975, "auxiliary_loss_weight": 1.0, "epoch": 5.724976613657624, "flow_matching_loss": 0.05690774582326412, "grad_norm": 0.14518582820892334, "invalid_tail_samples": 24.6, "learning_rate": 9.365775065693287e-05, "loss": 0.0641, "positive_teacher_pairs": 26673.4, "relation_loss": 0.007238085847347975, "selected_pairs": 26673.4, "step": 6120, "student_distance_mean": 812.9261962890625, "teacher_distance_mean": 0.8517943441867828, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.007238085847347975, "weighted_relation_loss": 0.007238085847347975 }, { "action_query_batch_std": 14.391860485076904, "action_query_norm": 645.6037963867187, "action_relation_loss": 0.006739129777997732, "auxiliary_loss_weight": 1.0, "epoch": 5.734331150608045, "flow_matching_loss": 0.05299466177821159, "grad_norm": 0.1882365345954895, "invalid_tail_samples": 22.5, "learning_rate": 9.363085841536957e-05, "loss": 0.0597, "positive_teacher_pairs": 27148.0, "relation_loss": 0.006739129777997732, "selected_pairs": 27148.0, "step": 6130, "student_distance_mean": 815.6767578125, "teacher_distance_mean": 0.8469519674777984, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.006739129777997732, "weighted_relation_loss": 0.006739129777997732 }, { "action_query_batch_std": 14.427900886535644, "action_query_norm": 642.3012817382812, "action_relation_loss": 0.006625579530373215, "auxiliary_loss_weight": 1.0, "epoch": 5.743685687558466, "flow_matching_loss": 0.052230823785066605, "grad_norm": 0.15537388622760773, "invalid_tail_samples": 23.1, "learning_rate": 9.360391315819917e-05, "loss": 0.0589, "positive_teacher_pairs": 27009.9, "relation_loss": 0.006625579530373215, "selected_pairs": 27009.9, "step": 6140, "student_distance_mean": 816.7870666503907, "teacher_distance_mean": 0.8613130033016205, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.006625579530373215, "weighted_relation_loss": 0.006625579530373215 }, { "action_query_batch_std": 14.42003936767578, "action_query_norm": 641.7119934082032, "action_relation_loss": 0.006762376427650452, "auxiliary_loss_weight": 1.0, "epoch": 5.7530402245088865, "flow_matching_loss": 0.05181986130774021, "grad_norm": 0.13624565303325653, "invalid_tail_samples": 22.7, "learning_rate": 9.357691491816269e-05, "loss": 0.0586, "positive_teacher_pairs": 27107.1, "relation_loss": 0.006762376427650452, "selected_pairs": 27107.1, "step": 6150, "student_distance_mean": 813.8839721679688, "teacher_distance_mean": 0.8570758700370789, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.006762376427650452, "weighted_relation_loss": 0.006762376427650452 }, { "action_query_batch_std": 14.59348554611206, "action_query_norm": 648.0725158691406, "action_relation_loss": 0.0066835053730756044, "auxiliary_loss_weight": 1.0, "epoch": 5.762394761459308, "flow_matching_loss": 0.05377751477062702, "grad_norm": 0.18587088584899902, "invalid_tail_samples": 26.8, "learning_rate": 9.354986372806557e-05, "loss": 0.0605, "positive_teacher_pairs": 26159.3, "relation_loss": 0.0066835053730756044, "selected_pairs": 26159.3, "step": 6160, "student_distance_mean": 824.978173828125, "teacher_distance_mean": 0.855550330877304, "valid_action_samples": 229.2, "weighted_auxiliary_loss": 0.0066835053730756044, "weighted_relation_loss": 0.0066835053730756044 }, { "action_query_batch_std": 14.258978939056396, "action_query_norm": 635.2758972167969, "action_relation_loss": 0.00663095829077065, "auxiliary_loss_weight": 1.0, "epoch": 5.771749298409729, "flow_matching_loss": 0.050210357457399366, "grad_norm": 0.17461363971233368, "invalid_tail_samples": 23.7, "learning_rate": 9.352275962077752e-05, "loss": 0.0568, "positive_teacher_pairs": 26877.3, "relation_loss": 0.00663095829077065, "selected_pairs": 26877.3, "step": 6170, "student_distance_mean": 809.8481262207031, "teacher_distance_mean": 0.8516030073165893, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.00663095829077065, "weighted_relation_loss": 0.00663095829077065 }, { "action_query_batch_std": 14.527750587463379, "action_query_norm": 645.7391418457031, "action_relation_loss": 0.006862680986523628, "auxiliary_loss_weight": 1.0, "epoch": 5.78110383536015, "flow_matching_loss": 0.053045005351305005, "grad_norm": 0.14475326240062714, "invalid_tail_samples": 23.6, "learning_rate": 9.349560262923262e-05, "loss": 0.0599, "positive_teacher_pairs": 26895.0, "relation_loss": 0.006862680986523628, "selected_pairs": 26895.0, "step": 6180, "student_distance_mean": 824.5733276367188, "teacher_distance_mean": 0.8568536281585694, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.006862680986523628, "weighted_relation_loss": 0.006862680986523628 }, { "action_query_batch_std": 14.53441801071167, "action_query_norm": 647.0780395507812, "action_relation_loss": 0.007011366030201316, "auxiliary_loss_weight": 1.0, "epoch": 5.790458372310571, "flow_matching_loss": 0.05193967074155807, "grad_norm": 0.1401936411857605, "invalid_tail_samples": 24.7, "learning_rate": 9.346839278642913e-05, "loss": 0.059, "positive_teacher_pairs": 26651.4, "relation_loss": 0.007011366030201316, "selected_pairs": 26651.4, "step": 6190, "student_distance_mean": 826.3287658691406, "teacher_distance_mean": 0.8606139898300171, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.007011366030201316, "weighted_relation_loss": 0.007011366030201316 }, { "action_query_batch_std": 14.50621166229248, "action_query_norm": 646.1082275390625, "action_relation_loss": 0.00682696751318872, "auxiliary_loss_weight": 1.0, "epoch": 5.799812909260991, "flow_matching_loss": 0.05290623567998409, "grad_norm": 0.1264973133802414, "invalid_tail_samples": 24.2, "learning_rate": 9.344113012542963e-05, "loss": 0.0597, "positive_teacher_pairs": 26765.2, "relation_loss": 0.00682696751318872, "selected_pairs": 26765.2, "step": 6200, "student_distance_mean": 822.6007568359375, "teacher_distance_mean": 0.8588486850261688, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.00682696751318872, "weighted_relation_loss": 0.00682696751318872 }, { "action_query_batch_std": 14.518184375762939, "action_query_norm": 647.524755859375, "action_relation_loss": 0.006637630518525839, "auxiliary_loss_weight": 1.0, "epoch": 5.809167446211412, "flow_matching_loss": 0.053859999775886534, "grad_norm": 0.1416151374578476, "invalid_tail_samples": 21.6, "learning_rate": 9.341381467936079e-05, "loss": 0.0605, "positive_teacher_pairs": 27359.0, "relation_loss": 0.006637630518525839, "selected_pairs": 27359.0, "step": 6210, "student_distance_mean": 822.30576171875, "teacher_distance_mean": 0.8604921877384186, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.006637630518525839, "weighted_relation_loss": 0.006637630518525839 }, { "action_query_batch_std": 14.35763177871704, "action_query_norm": 641.7738220214844, "action_relation_loss": 0.006794090522453189, "auxiliary_loss_weight": 1.0, "epoch": 5.818521983161833, "flow_matching_loss": 0.05352163016796112, "grad_norm": 0.1327405720949173, "invalid_tail_samples": 26.0, "learning_rate": 9.338644648141346e-05, "loss": 0.0603, "positive_teacher_pairs": 26343.6, "relation_loss": 0.006794090522453189, "selected_pairs": 26343.6, "step": 6220, "student_distance_mean": 809.3660827636719, "teacher_distance_mean": 0.8498220920562745, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.006794090522453189, "weighted_relation_loss": 0.006794090522453189 }, { "action_query_batch_std": 14.309476852416992, "action_query_norm": 644.4368835449219, "action_relation_loss": 0.006605070689693094, "auxiliary_loss_weight": 1.0, "epoch": 5.827876520112254, "flow_matching_loss": 0.05265726335346699, "grad_norm": 0.11824117600917816, "invalid_tail_samples": 21.7, "learning_rate": 9.335902556484257e-05, "loss": 0.0593, "positive_teacher_pairs": 27335.0, "relation_loss": 0.006605070689693094, "selected_pairs": 27335.0, "step": 6230, "student_distance_mean": 811.8430358886719, "teacher_distance_mean": 0.8549777746200562, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.006605070689693094, "weighted_relation_loss": 0.006605070689693094 }, { "action_query_batch_std": 14.333512306213379, "action_query_norm": 641.6378112792969, "action_relation_loss": 0.006564007280394435, "auxiliary_loss_weight": 1.0, "epoch": 5.8372310570626755, "flow_matching_loss": 0.054834035038948056, "grad_norm": 0.14837685227394104, "invalid_tail_samples": 24.9, "learning_rate": 9.333155196296712e-05, "loss": 0.0614, "positive_teacher_pairs": 26590.5, "relation_loss": 0.006564007280394435, "selected_pairs": 26590.5, "step": 6240, "student_distance_mean": 816.1698913574219, "teacher_distance_mean": 0.8518109023571014, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.006564007280394435, "weighted_relation_loss": 0.006564007280394435 }, { "action_query_batch_std": 14.222785472869873, "action_query_norm": 634.1776184082031, "action_relation_loss": 0.007235536677762866, "auxiliary_loss_weight": 1.0, "epoch": 5.846585594013097, "flow_matching_loss": 0.05399421378970146, "grad_norm": 0.17187529802322388, "invalid_tail_samples": 22.3, "learning_rate": 9.330402570917016e-05, "loss": 0.0612, "positive_teacher_pairs": 27206.4, "relation_loss": 0.007235536677762866, "selected_pairs": 27206.4, "step": 6250, "student_distance_mean": 802.5779296875, "teacher_distance_mean": 0.850264173746109, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.007235536677762866, "weighted_relation_loss": 0.007235536677762866 }, { "action_query_batch_std": 14.403921794891357, "action_query_norm": 638.9991027832032, "action_relation_loss": 0.006461474066600204, "auxiliary_loss_weight": 1.0, "epoch": 5.855940130963518, "flow_matching_loss": 0.05433249548077583, "grad_norm": 0.15709276497364044, "invalid_tail_samples": 23.9, "learning_rate": 9.327644683689865e-05, "loss": 0.0608, "positive_teacher_pairs": 26826.8, "relation_loss": 0.006461474066600204, "selected_pairs": 26826.8, "step": 6260, "student_distance_mean": 817.0077026367187, "teacher_distance_mean": 0.8625324726104736, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.006461474066600204, "weighted_relation_loss": 0.006461474066600204 }, { "action_query_batch_std": 14.449720573425292, "action_query_norm": 643.8697509765625, "action_relation_loss": 0.007041704514995218, "auxiliary_loss_weight": 1.0, "epoch": 5.865294667913938, "flow_matching_loss": 0.052376070991158485, "grad_norm": 0.11190684884786606, "invalid_tail_samples": 24.0, "learning_rate": 9.324881537966354e-05, "loss": 0.0594, "positive_teacher_pairs": 26804.9, "relation_loss": 0.007041704514995218, "selected_pairs": 26804.9, "step": 6270, "student_distance_mean": 818.6626708984375, "teacher_distance_mean": 0.8572137832641602, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.007041704514995218, "weighted_relation_loss": 0.007041704514995218 }, { "action_query_batch_std": 14.605164718627929, "action_query_norm": 646.2505554199219, "action_relation_loss": 0.006834671692922711, "auxiliary_loss_weight": 1.0, "epoch": 5.874649204864359, "flow_matching_loss": 0.05487405396997928, "grad_norm": 0.12632443010807037, "invalid_tail_samples": 23.6, "learning_rate": 9.322113137103964e-05, "loss": 0.0617, "positive_teacher_pairs": 26894.4, "relation_loss": 0.006834671692922711, "selected_pairs": 26894.4, "step": 6280, "student_distance_mean": 825.9123962402343, "teacher_distance_mean": 0.8599928200244904, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.006834671692922711, "weighted_relation_loss": 0.006834671692922711 }, { "action_query_batch_std": 14.426778507232665, "action_query_norm": 643.6463623046875, "action_relation_loss": 0.007083375193178654, "auxiliary_loss_weight": 1.0, "epoch": 5.88400374181478, "flow_matching_loss": 0.05514244437217712, "grad_norm": 0.1682250201702118, "invalid_tail_samples": 23.2, "learning_rate": 9.319339484466564e-05, "loss": 0.0622, "positive_teacher_pairs": 26984.7, "relation_loss": 0.007083375193178654, "selected_pairs": 26984.7, "step": 6290, "student_distance_mean": 820.5504028320313, "teacher_distance_mean": 0.8506622731685638, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.007083375193178654, "weighted_relation_loss": 0.007083375193178654 }, { "action_query_batch_std": 14.264822387695313, "action_query_norm": 636.6290344238281, "action_relation_loss": 0.006822548061609268, "auxiliary_loss_weight": 1.0, "epoch": 5.893358278765201, "flow_matching_loss": 0.05366330705583096, "grad_norm": 0.16250060498714447, "invalid_tail_samples": 23.9, "learning_rate": 9.316560583424403e-05, "loss": 0.0605, "positive_teacher_pairs": 26828.0, "relation_loss": 0.006822548061609268, "selected_pairs": 26828.0, "step": 6300, "student_distance_mean": 810.9742065429688, "teacher_distance_mean": 0.8473630011081695, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.006822548061609268, "weighted_relation_loss": 0.006822548061609268 }, { "action_query_batch_std": 14.340871429443359, "action_query_norm": 637.9686950683594, "action_relation_loss": 0.007050011027604342, "auxiliary_loss_weight": 1.0, "epoch": 5.902712815715622, "flow_matching_loss": 0.054419639706611636, "grad_norm": 0.22293491661548615, "invalid_tail_samples": 22.4, "learning_rate": 9.313776437354108e-05, "loss": 0.0615, "positive_teacher_pairs": 27181.5, "relation_loss": 0.007050011027604342, "selected_pairs": 27181.5, "step": 6310, "student_distance_mean": 814.2043823242187, "teacher_distance_mean": 0.8457733213901519, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.007050011027604342, "weighted_relation_loss": 0.007050011027604342 }, { "action_query_batch_std": 14.405070400238037, "action_query_norm": 642.4329772949219, "action_relation_loss": 0.006915547326207161, "auxiliary_loss_weight": 1.0, "epoch": 5.9120673526660426, "flow_matching_loss": 0.05364744476974011, "grad_norm": 0.16294746100902557, "invalid_tail_samples": 23.3, "learning_rate": 9.31098704963868e-05, "loss": 0.0606, "positive_teacher_pairs": 26965.1, "relation_loss": 0.006915547326207161, "selected_pairs": 26965.1, "step": 6320, "student_distance_mean": 817.8234985351562, "teacher_distance_mean": 0.8556046307086944, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.006915547326207161, "weighted_relation_loss": 0.006915547326207161 }, { "action_query_batch_std": 14.450131225585938, "action_query_norm": 645.7295166015625, "action_relation_loss": 0.0069128389470279215, "auxiliary_loss_weight": 1.0, "epoch": 5.921421889616464, "flow_matching_loss": 0.05299140140414238, "grad_norm": 0.11638505756855011, "invalid_tail_samples": 23.6, "learning_rate": 9.308192423667485e-05, "loss": 0.0599, "positive_teacher_pairs": 26893.4, "relation_loss": 0.0069128389470279215, "selected_pairs": 26893.4, "step": 6330, "student_distance_mean": 818.876220703125, "teacher_distance_mean": 0.8560031950473785, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0069128389470279215, "weighted_relation_loss": 0.0069128389470279215 }, { "action_query_batch_std": 14.491545581817627, "action_query_norm": 647.92255859375, "action_relation_loss": 0.006836830778047443, "auxiliary_loss_weight": 1.0, "epoch": 5.930776426566885, "flow_matching_loss": 0.05383355803787708, "grad_norm": 0.1437690109014511, "invalid_tail_samples": 22.2, "learning_rate": 9.305392562836262e-05, "loss": 0.0607, "positive_teacher_pairs": 27224.4, "relation_loss": 0.006836830778047443, "selected_pairs": 27224.4, "step": 6340, "student_distance_mean": 821.4633911132812, "teacher_distance_mean": 0.8605177998542786, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.006836830778047443, "weighted_relation_loss": 0.006836830778047443 }, { "action_query_batch_std": 14.50757188796997, "action_query_norm": 644.8283935546875, "action_relation_loss": 0.006692310748621822, "auxiliary_loss_weight": 1.0, "epoch": 5.940130963517306, "flow_matching_loss": 0.051625869050621984, "grad_norm": 0.12959042191505432, "invalid_tail_samples": 24.6, "learning_rate": 9.3025874705471e-05, "loss": 0.0583, "positive_teacher_pairs": 26664.6, "relation_loss": 0.006692310748621822, "selected_pairs": 26664.6, "step": 6350, "student_distance_mean": 821.0668395996094, "teacher_distance_mean": 0.8572543323040008, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.006692310748621822, "weighted_relation_loss": 0.006692310748621822 }, { "action_query_batch_std": 14.379586887359618, "action_query_norm": 643.5453369140625, "action_relation_loss": 0.006578366225585342, "auxiliary_loss_weight": 1.0, "epoch": 5.949485500467727, "flow_matching_loss": 0.05173303559422493, "grad_norm": 0.13940231502056122, "invalid_tail_samples": 26.0, "learning_rate": 9.299777150208457e-05, "loss": 0.0583, "positive_teacher_pairs": 26341.9, "relation_loss": 0.006578366225585342, "selected_pairs": 26341.9, "step": 6360, "student_distance_mean": 811.7511352539062, "teacher_distance_mean": 0.8503810644149781, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.006578366225585342, "weighted_relation_loss": 0.006578366225585342 }, { "action_query_batch_std": 14.521267127990722, "action_query_norm": 649.1698364257812, "action_relation_loss": 0.0068271270953118805, "auxiliary_loss_weight": 1.0, "epoch": 5.958840037418148, "flow_matching_loss": 0.05193195641040802, "grad_norm": 0.15547722578048706, "invalid_tail_samples": 21.2, "learning_rate": 9.296961605235133e-05, "loss": 0.0588, "positive_teacher_pairs": 27452.1, "relation_loss": 0.0068271270953118805, "selected_pairs": 27452.1, "step": 6370, "student_distance_mean": 822.0876159667969, "teacher_distance_mean": 0.8527152895927429, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.0068271270953118805, "weighted_relation_loss": 0.0068271270953118805 }, { "action_query_batch_std": 14.35886173248291, "action_query_norm": 646.9143920898438, "action_relation_loss": 0.00711392150260508, "auxiliary_loss_weight": 1.0, "epoch": 5.968194574368569, "flow_matching_loss": 0.053978266194462776, "grad_norm": 0.17626453936100006, "invalid_tail_samples": 21.8, "learning_rate": 9.29414083904828e-05, "loss": 0.0611, "positive_teacher_pairs": 27312.7, "relation_loss": 0.00711392150260508, "selected_pairs": 27312.7, "step": 6380, "student_distance_mean": 813.2507873535156, "teacher_distance_mean": 0.8433324217796325, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.00711392150260508, "weighted_relation_loss": 0.00711392150260508 }, { "action_query_batch_std": 14.353606128692627, "action_query_norm": 645.0748962402344, "action_relation_loss": 0.006498785223811865, "auxiliary_loss_weight": 1.0, "epoch": 5.977549111318989, "flow_matching_loss": 0.055265965312719344, "grad_norm": 0.11318778991699219, "invalid_tail_samples": 24.0, "learning_rate": 9.291314855075397e-05, "loss": 0.0618, "positive_teacher_pairs": 26806.3, "relation_loss": 0.006498785223811865, "selected_pairs": 26806.3, "step": 6390, "student_distance_mean": 810.5850708007813, "teacher_distance_mean": 0.855410385131836, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.006498785223811865, "weighted_relation_loss": 0.006498785223811865 }, { "action_query_batch_std": 14.582754421234132, "action_query_norm": 652.9613342285156, "action_relation_loss": 0.00661947512999177, "auxiliary_loss_weight": 1.0, "epoch": 5.9869036482694105, "flow_matching_loss": 0.05390526130795479, "grad_norm": 0.15460672974586487, "invalid_tail_samples": 24.1, "learning_rate": 9.288483656750322e-05, "loss": 0.0605, "positive_teacher_pairs": 26798.4, "relation_loss": 0.00661947512999177, "selected_pairs": 26798.4, "step": 6400, "student_distance_mean": 821.9504638671875, "teacher_distance_mean": 0.8618562161922455, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.00661947512999177, "weighted_relation_loss": 0.00661947512999177 }, { "action_query_batch_std": 14.772697639465331, "action_query_norm": 659.0311950683594, "action_relation_loss": 0.006810755934566259, "auxiliary_loss_weight": 1.0, "epoch": 5.996258185219832, "flow_matching_loss": 0.05317416600883007, "grad_norm": 0.11301200091838837, "invalid_tail_samples": 24.8, "learning_rate": 9.285647247513225e-05, "loss": 0.06, "positive_teacher_pairs": 26619.8, "relation_loss": 0.006810755934566259, "selected_pairs": 26619.8, "step": 6410, "student_distance_mean": 836.41787109375, "teacher_distance_mean": 0.8590123951435089, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.006810755934566259, "weighted_relation_loss": 0.006810755934566259 }, { "action_query_batch_std": 14.628821754455567, "action_query_norm": 655.1057556152343, "action_relation_loss": 0.006617140304297209, "auxiliary_loss_weight": 1.0, "epoch": 6.005612722170253, "flow_matching_loss": 0.051734543219208715, "grad_norm": 0.1389908641576767, "invalid_tail_samples": 23.4, "learning_rate": 9.282805630810614e-05, "loss": 0.0584, "positive_teacher_pairs": 23926.7, "relation_loss": 0.006617140304297209, "selected_pairs": 23926.7, "step": 6420, "student_distance_mean": 831.3645690917969, "teacher_distance_mean": 0.8479879677295685, "valid_action_samples": 212.7, "weighted_auxiliary_loss": 0.006617140304297209, "weighted_relation_loss": 0.006617140304297209 }, { "action_query_batch_std": 14.586174869537354, "action_query_norm": 656.0067687988281, "action_relation_loss": 0.006647759163752198, "auxiliary_loss_weight": 1.0, "epoch": 6.014967259120674, "flow_matching_loss": 0.052627918869256975, "grad_norm": 0.18842867016792297, "invalid_tail_samples": 24.5, "learning_rate": 9.279958810095317e-05, "loss": 0.0593, "positive_teacher_pairs": 26690.3, "relation_loss": 0.006647759163752198, "selected_pairs": 26690.3, "step": 6430, "student_distance_mean": 826.188916015625, "teacher_distance_mean": 0.841916823387146, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.006647759163752198, "weighted_relation_loss": 0.006647759163752198 }, { "action_query_batch_std": 14.763751125335693, "action_query_norm": 661.1376525878907, "action_relation_loss": 0.006583323376253248, "auxiliary_loss_weight": 1.0, "epoch": 6.024321796071095, "flow_matching_loss": 0.052758068591356275, "grad_norm": 0.13756391406059265, "invalid_tail_samples": 24.3, "learning_rate": 9.277106788826494e-05, "loss": 0.0593, "positive_teacher_pairs": 26732.6, "relation_loss": 0.006583323376253248, "selected_pairs": 26732.6, "step": 6440, "student_distance_mean": 840.0190795898437, "teacher_distance_mean": 0.8517879605293274, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.006583323376253248, "weighted_relation_loss": 0.006583323376253248 }, { "action_query_batch_std": 14.815701389312744, "action_query_norm": 662.0857360839843, "action_relation_loss": 0.00658195149153471, "auxiliary_loss_weight": 1.0, "epoch": 6.033676333021515, "flow_matching_loss": 0.0509986262768507, "grad_norm": 0.16486594080924988, "invalid_tail_samples": 21.9, "learning_rate": 9.274249570469618e-05, "loss": 0.0576, "positive_teacher_pairs": 27291.4, "relation_loss": 0.00658195149153471, "selected_pairs": 27291.4, "step": 6450, "student_distance_mean": 838.3837158203125, "teacher_distance_mean": 0.8495012581348419, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.00658195149153471, "weighted_relation_loss": 0.00658195149153471 }, { "action_query_batch_std": 14.785895442962646, "action_query_norm": 658.4351196289062, "action_relation_loss": 0.006302988575771451, "auxiliary_loss_weight": 1.0, "epoch": 6.043030869971936, "flow_matching_loss": 0.0533006452023983, "grad_norm": 0.124959297478199, "invalid_tail_samples": 22.5, "learning_rate": 9.271387158496476e-05, "loss": 0.0596, "positive_teacher_pairs": 27152.3, "relation_loss": 0.006302988575771451, "selected_pairs": 27152.3, "step": 6460, "student_distance_mean": 834.9094055175781, "teacher_distance_mean": 0.8569265902042389, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.006302988575771451, "weighted_relation_loss": 0.006302988575771451 }, { "action_query_batch_std": 14.808778476715087, "action_query_norm": 659.8097229003906, "action_relation_loss": 0.006284983130171895, "auxiliary_loss_weight": 1.0, "epoch": 6.052385406922357, "flow_matching_loss": 0.051120955497026443, "grad_norm": 0.17083773016929626, "invalid_tail_samples": 22.8, "learning_rate": 9.268519556385173e-05, "loss": 0.0574, "positive_teacher_pairs": 27086.6, "relation_loss": 0.006284983130171895, "selected_pairs": 27086.6, "step": 6470, "student_distance_mean": 833.5052307128906, "teacher_distance_mean": 0.8512375712394714, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.006284983130171895, "weighted_relation_loss": 0.006284983130171895 }, { "action_query_batch_std": 14.705587196350098, "action_query_norm": 658.1302978515625, "action_relation_loss": 0.006208228599280119, "auxiliary_loss_weight": 1.0, "epoch": 6.061739943872778, "flow_matching_loss": 0.05282169505953789, "grad_norm": 0.13837449252605438, "invalid_tail_samples": 22.8, "learning_rate": 9.265646767620113e-05, "loss": 0.059, "positive_teacher_pairs": 27080.1, "relation_loss": 0.006208228599280119, "selected_pairs": 27080.1, "step": 6480, "student_distance_mean": 830.6001525878906, "teacher_distance_mean": 0.8514952301979065, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.006208228599280119, "weighted_relation_loss": 0.006208228599280119 }, { "action_query_batch_std": 14.86418046951294, "action_query_norm": 664.9578857421875, "action_relation_loss": 0.006413292372599244, "auxiliary_loss_weight": 1.0, "epoch": 6.0710944808231995, "flow_matching_loss": 0.05054255239665508, "grad_norm": 0.18040858209133148, "invalid_tail_samples": 23.2, "learning_rate": 9.262768795692006e-05, "loss": 0.057, "positive_teacher_pairs": 26996.7, "relation_loss": 0.006413292372599244, "selected_pairs": 26996.7, "step": 6490, "student_distance_mean": 840.0398498535156, "teacher_distance_mean": 0.8598646581172943, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.006413292372599244, "weighted_relation_loss": 0.006413292372599244 }, { "action_query_batch_std": 14.898026847839356, "action_query_norm": 666.2631530761719, "action_relation_loss": 0.006673080381006002, "auxiliary_loss_weight": 1.0, "epoch": 6.080449017773621, "flow_matching_loss": 0.05100175589323044, "grad_norm": 0.22024884819984436, "invalid_tail_samples": 23.1, "learning_rate": 9.259885644097861e-05, "loss": 0.0577, "positive_teacher_pairs": 27008.8, "relation_loss": 0.006673080381006002, "selected_pairs": 27008.8, "step": 6500, "student_distance_mean": 844.8902038574219, "teacher_distance_mean": 0.8626942038536072, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.006673080381006002, "weighted_relation_loss": 0.006673080381006002 }, { "action_query_batch_std": 14.762003803253174, "action_query_norm": 661.7085205078125, "action_relation_loss": 0.006214948464184999, "auxiliary_loss_weight": 1.0, "epoch": 6.089803554724041, "flow_matching_loss": 0.051701870188117026, "grad_norm": 0.2553153932094574, "invalid_tail_samples": 25.2, "learning_rate": 9.256997316340976e-05, "loss": 0.0579, "positive_teacher_pairs": 26528.5, "relation_loss": 0.006214948464184999, "selected_pairs": 26528.5, "step": 6510, "student_distance_mean": 836.7745056152344, "teacher_distance_mean": 0.8552859127521515, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.006214948464184999, "weighted_relation_loss": 0.006214948464184999 }, { "action_query_batch_std": 14.547068214416504, "action_query_norm": 652.2286437988281, "action_relation_loss": 0.00636867149733007, "auxiliary_loss_weight": 1.0, "epoch": 6.099158091674462, "flow_matching_loss": 0.05040376745164395, "grad_norm": 0.1671326458454132, "invalid_tail_samples": 25.3, "learning_rate": 9.254103815930943e-05, "loss": 0.0568, "positive_teacher_pairs": 26506.6, "relation_loss": 0.00636867149733007, "selected_pairs": 26506.6, "step": 6520, "student_distance_mean": 828.4134582519531, "teacher_distance_mean": 0.8472282290458679, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.00636867149733007, "weighted_relation_loss": 0.00636867149733007 }, { "action_query_batch_std": 14.723042488098145, "action_query_norm": 655.4253356933593, "action_relation_loss": 0.005816814117133617, "auxiliary_loss_weight": 1.0, "epoch": 6.108512628624883, "flow_matching_loss": 0.05023153275251389, "grad_norm": 0.1661129593849182, "invalid_tail_samples": 24.8, "learning_rate": 9.251205146383636e-05, "loss": 0.056, "positive_teacher_pairs": 26625.1, "relation_loss": 0.005816814117133617, "selected_pairs": 26625.1, "step": 6530, "student_distance_mean": 836.3195922851562, "teacher_distance_mean": 0.8602219820022583, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.005816814117133617, "weighted_relation_loss": 0.005816814117133617 }, { "action_query_batch_std": 14.570218944549561, "action_query_norm": 652.5506591796875, "action_relation_loss": 0.006269358517602086, "auxiliary_loss_weight": 1.0, "epoch": 6.117867165575304, "flow_matching_loss": 0.05236674584448338, "grad_norm": 0.15190489590168, "invalid_tail_samples": 21.0, "learning_rate": 9.248301311221216e-05, "loss": 0.0586, "positive_teacher_pairs": 27504.8, "relation_loss": 0.006269358517602086, "selected_pairs": 27504.8, "step": 6540, "student_distance_mean": 827.3183959960937, "teacher_distance_mean": 0.8511854946613312, "valid_action_samples": 235.0, "weighted_auxiliary_loss": 0.006269358517602086, "weighted_relation_loss": 0.006269358517602086 }, { "action_query_batch_std": 14.705756378173827, "action_query_norm": 655.1215759277344, "action_relation_loss": 0.006466745818033815, "auxiliary_loss_weight": 1.0, "epoch": 6.127221702525725, "flow_matching_loss": 0.05139770694077015, "grad_norm": 0.1302507072687149, "invalid_tail_samples": 23.5, "learning_rate": 9.245392313972115e-05, "loss": 0.0579, "positive_teacher_pairs": 26917.4, "relation_loss": 0.006466745818033815, "selected_pairs": 26917.4, "step": 6550, "student_distance_mean": 832.1800598144531, "teacher_distance_mean": 0.8512877702713013, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.006466745818033815, "weighted_relation_loss": 0.006466745818033815 }, { "action_query_batch_std": 14.455609893798828, "action_query_norm": 646.6174194335938, "action_relation_loss": 0.006792945042252541, "auxiliary_loss_weight": 1.0, "epoch": 6.136576239476146, "flow_matching_loss": 0.05275047980248928, "grad_norm": 0.11883188039064407, "invalid_tail_samples": 24.3, "learning_rate": 9.242478158171037e-05, "loss": 0.0595, "positive_teacher_pairs": 26735.5, "relation_loss": 0.006792945042252541, "selected_pairs": 26735.5, "step": 6560, "student_distance_mean": 821.1062561035156, "teacher_distance_mean": 0.8459981083869934, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.006792945042252541, "weighted_relation_loss": 0.006792945042252541 }, { "action_query_batch_std": 14.828782653808593, "action_query_norm": 660.5744445800781, "action_relation_loss": 0.0062730918172746895, "auxiliary_loss_weight": 1.0, "epoch": 6.1459307764265665, "flow_matching_loss": 0.051529424265027046, "grad_norm": 0.15366755425930023, "invalid_tail_samples": 23.6, "learning_rate": 9.239558847358957e-05, "loss": 0.0578, "positive_teacher_pairs": 26903.7, "relation_loss": 0.0062730918172746895, "selected_pairs": 26903.7, "step": 6570, "student_distance_mean": 839.963720703125, "teacher_distance_mean": 0.8596959233283996, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0062730918172746895, "weighted_relation_loss": 0.0062730918172746895 }, { "action_query_batch_std": 14.71257734298706, "action_query_norm": 658.7672180175781, "action_relation_loss": 0.006308539072051644, "auxiliary_loss_weight": 1.0, "epoch": 6.155285313376988, "flow_matching_loss": 0.05060500279068947, "grad_norm": 0.13216650485992432, "invalid_tail_samples": 24.0, "learning_rate": 9.236634385083114e-05, "loss": 0.0569, "positive_teacher_pairs": 26816.6, "relation_loss": 0.006308539072051644, "selected_pairs": 26816.6, "step": 6580, "student_distance_mean": 835.1461608886718, "teacher_distance_mean": 0.849156504869461, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.006308539072051644, "weighted_relation_loss": 0.006308539072051644 }, { "action_query_batch_std": 15.038533782958984, "action_query_norm": 666.9930358886719, "action_relation_loss": 0.006280194269493222, "auxiliary_loss_weight": 1.0, "epoch": 6.164639850327409, "flow_matching_loss": 0.053142597898840904, "grad_norm": 0.1188293918967247, "invalid_tail_samples": 21.9, "learning_rate": 9.233704774897005e-05, "loss": 0.0594, "positive_teacher_pairs": 27292.0, "relation_loss": 0.006280194269493222, "selected_pairs": 27292.0, "step": 6590, "student_distance_mean": 848.7863403320313, "teacher_distance_mean": 0.8634037733078003, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.006280194269493222, "weighted_relation_loss": 0.006280194269493222 }, { "action_query_batch_std": 14.591286659240723, "action_query_norm": 652.788037109375, "action_relation_loss": 0.006225922144949436, "auxiliary_loss_weight": 1.0, "epoch": 6.17399438727783, "flow_matching_loss": 0.051224342361092565, "grad_norm": 0.1541249006986618, "invalid_tail_samples": 24.1, "learning_rate": 9.230770020360382e-05, "loss": 0.0575, "positive_teacher_pairs": 26785.9, "relation_loss": 0.006225922144949436, "selected_pairs": 26785.9, "step": 6600, "student_distance_mean": 828.6154418945313, "teacher_distance_mean": 0.8507076501846313, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.006225922144949436, "weighted_relation_loss": 0.006225922144949436 }, { "action_query_batch_std": 14.561009979248047, "action_query_norm": 652.8111450195313, "action_relation_loss": 0.006541943829506636, "auxiliary_loss_weight": 1.0, "epoch": 6.183348924228251, "flow_matching_loss": 0.05159042440354824, "grad_norm": 0.15627342462539673, "invalid_tail_samples": 22.7, "learning_rate": 9.227830125039247e-05, "loss": 0.0581, "positive_teacher_pairs": 27116.3, "relation_loss": 0.006541943829506636, "selected_pairs": 27116.3, "step": 6610, "student_distance_mean": 821.5236083984375, "teacher_distance_mean": 0.8506549656391144, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.006541943829506636, "weighted_relation_loss": 0.006541943829506636 }, { "action_query_batch_std": 14.809198188781739, "action_query_norm": 662.2953186035156, "action_relation_loss": 0.006258478248491883, "auxiliary_loss_weight": 1.0, "epoch": 6.192703461178672, "flow_matching_loss": 0.049163011088967326, "grad_norm": 0.1198892891407013, "invalid_tail_samples": 23.6, "learning_rate": 9.224885092505853e-05, "loss": 0.0554, "positive_teacher_pairs": 26898.4, "relation_loss": 0.006258478248491883, "selected_pairs": 26898.4, "step": 6620, "student_distance_mean": 841.6772094726563, "teacher_distance_mean": 0.849870240688324, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.006258478248491883, "weighted_relation_loss": 0.006258478248491883 }, { "action_query_batch_std": 14.95904836654663, "action_query_norm": 667.3126647949218, "action_relation_loss": 0.006264349818229676, "auxiliary_loss_weight": 1.0, "epoch": 6.202057998129092, "flow_matching_loss": 0.052703197300434115, "grad_norm": 0.13033251464366913, "invalid_tail_samples": 24.5, "learning_rate": 9.221934926338691e-05, "loss": 0.059, "positive_teacher_pairs": 26701.0, "relation_loss": 0.006264349818229676, "selected_pairs": 26701.0, "step": 6630, "student_distance_mean": 851.6682250976562, "teacher_distance_mean": 0.8683351933956146, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.006264349818229676, "weighted_relation_loss": 0.006264349818229676 }, { "action_query_batch_std": 14.770652961730956, "action_query_norm": 659.4322021484375, "action_relation_loss": 0.0061257991939783095, "auxiliary_loss_weight": 1.0, "epoch": 6.211412535079513, "flow_matching_loss": 0.04884752482175827, "grad_norm": 0.12874619662761688, "invalid_tail_samples": 24.3, "learning_rate": 9.21897963012249e-05, "loss": 0.055, "positive_teacher_pairs": 26737.8, "relation_loss": 0.0061257991939783095, "selected_pairs": 26737.8, "step": 6640, "student_distance_mean": 840.8370666503906, "teacher_distance_mean": 0.8559660732746124, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0061257991939783095, "weighted_relation_loss": 0.0061257991939783095 }, { "action_query_batch_std": 14.667184734344483, "action_query_norm": 656.5693786621093, "action_relation_loss": 0.006337336963042617, "auxiliary_loss_weight": 1.0, "epoch": 6.220767072029934, "flow_matching_loss": 0.05310807228088379, "grad_norm": 0.1465516835451126, "invalid_tail_samples": 26.3, "learning_rate": 9.216019207448217e-05, "loss": 0.0594, "positive_teacher_pairs": 26277.3, "relation_loss": 0.006337336963042617, "selected_pairs": 26277.3, "step": 6650, "student_distance_mean": 829.3346862792969, "teacher_distance_mean": 0.839885151386261, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.006337336963042617, "weighted_relation_loss": 0.006337336963042617 }, { "action_query_batch_std": 14.715821647644043, "action_query_norm": 658.7876892089844, "action_relation_loss": 0.006172384787350893, "auxiliary_loss_weight": 1.0, "epoch": 6.2301216089803555, "flow_matching_loss": 0.0513792309910059, "grad_norm": 0.19430962204933167, "invalid_tail_samples": 23.0, "learning_rate": 9.21305366191306e-05, "loss": 0.0576, "positive_teacher_pairs": 27033.8, "relation_loss": 0.006172384787350893, "selected_pairs": 27033.8, "step": 6660, "student_distance_mean": 832.6307434082031, "teacher_distance_mean": 0.8467274844646454, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.006172384787350893, "weighted_relation_loss": 0.006172384787350893 }, { "action_query_batch_std": 14.805874156951905, "action_query_norm": 655.7118286132812, "action_relation_loss": 0.00595854613929987, "auxiliary_loss_weight": 1.0, "epoch": 6.239476145930777, "flow_matching_loss": 0.053317129611968994, "grad_norm": 0.1570163369178772, "invalid_tail_samples": 25.0, "learning_rate": 9.21008299712044e-05, "loss": 0.0593, "positive_teacher_pairs": 26571.6, "relation_loss": 0.00595854613929987, "selected_pairs": 26571.6, "step": 6670, "student_distance_mean": 840.0702453613281, "teacher_distance_mean": 0.8563144922256469, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.00595854613929987, "weighted_relation_loss": 0.00595854613929987 }, { "action_query_batch_std": 14.66300926208496, "action_query_norm": 656.7398498535156, "action_relation_loss": 0.006203696876764297, "auxiliary_loss_weight": 1.0, "epoch": 6.248830682881198, "flow_matching_loss": 0.051127126812934874, "grad_norm": 0.15327708423137665, "invalid_tail_samples": 24.1, "learning_rate": 9.207107216679993e-05, "loss": 0.0573, "positive_teacher_pairs": 26779.7, "relation_loss": 0.006203696876764297, "selected_pairs": 26779.7, "step": 6680, "student_distance_mean": 832.263330078125, "teacher_distance_mean": 0.84547917842865, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.006203696876764297, "weighted_relation_loss": 0.006203696876764297 }, { "action_query_batch_std": 14.900527572631836, "action_query_norm": 665.9523864746094, "action_relation_loss": 0.006053566187620163, "auxiliary_loss_weight": 1.0, "epoch": 6.258185219831619, "flow_matching_loss": 0.0504581768065691, "grad_norm": 0.1343013346195221, "invalid_tail_samples": 25.7, "learning_rate": 9.204126324207574e-05, "loss": 0.0565, "positive_teacher_pairs": 26410.5, "relation_loss": 0.006053566187620163, "selected_pairs": 26410.5, "step": 6690, "student_distance_mean": 846.5239685058593, "teacher_distance_mean": 0.8483158469200134, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.006053566187620163, "weighted_relation_loss": 0.006053566187620163 }, { "action_query_batch_std": 15.249023246765137, "action_query_norm": 675.7024047851562, "action_relation_loss": 0.005958052026107908, "auxiliary_loss_weight": 1.0, "epoch": 6.267539756782039, "flow_matching_loss": 0.051720616221427915, "grad_norm": 0.14767658710479736, "invalid_tail_samples": 23.8, "learning_rate": 9.201140323325248e-05, "loss": 0.0577, "positive_teacher_pairs": 26851.0, "relation_loss": 0.005958052026107908, "selected_pairs": 26851.0, "step": 6700, "student_distance_mean": 864.9015930175781, "teacher_distance_mean": 0.8693130373954773, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.005958052026107908, "weighted_relation_loss": 0.005958052026107908 }, { "action_query_batch_std": 14.910770416259766, "action_query_norm": 661.8758666992187, "action_relation_loss": 0.0062644349876791235, "auxiliary_loss_weight": 1.0, "epoch": 6.27689429373246, "flow_matching_loss": 0.05265329219400883, "grad_norm": 0.14057233929634094, "invalid_tail_samples": 24.5, "learning_rate": 9.198149217661287e-05, "loss": 0.0589, "positive_teacher_pairs": 26691.3, "relation_loss": 0.0062644349876791235, "selected_pairs": 26691.3, "step": 6710, "student_distance_mean": 842.7237121582032, "teacher_distance_mean": 0.855083417892456, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0062644349876791235, "weighted_relation_loss": 0.0062644349876791235 }, { "action_query_batch_std": 15.158200931549072, "action_query_norm": 673.3440002441406, "action_relation_loss": 0.0060729086864739655, "auxiliary_loss_weight": 1.0, "epoch": 6.286248830682881, "flow_matching_loss": 0.050717495009303094, "grad_norm": 0.14606842398643494, "invalid_tail_samples": 22.7, "learning_rate": 9.195153010850167e-05, "loss": 0.0568, "positive_teacher_pairs": 27102.4, "relation_loss": 0.0060729086864739655, "selected_pairs": 27102.4, "step": 6720, "student_distance_mean": 854.6233154296875, "teacher_distance_mean": 0.8574794054031372, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0060729086864739655, "weighted_relation_loss": 0.0060729086864739655 }, { "action_query_batch_std": 15.364611339569091, "action_query_norm": 682.8723876953125, "action_relation_loss": 0.006268709758296609, "auxiliary_loss_weight": 1.0, "epoch": 6.295603367633302, "flow_matching_loss": 0.05122806876897812, "grad_norm": 0.14003732800483704, "invalid_tail_samples": 21.8, "learning_rate": 9.192151706532562e-05, "loss": 0.0575, "positive_teacher_pairs": 27313.7, "relation_loss": 0.006268709758296609, "selected_pairs": 27313.7, "step": 6730, "student_distance_mean": 868.2000610351563, "teacher_distance_mean": 0.8644701898097992, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.006268709758296609, "weighted_relation_loss": 0.006268709758296609 }, { "action_query_batch_std": 15.03197546005249, "action_query_norm": 670.721826171875, "action_relation_loss": 0.006251487880945206, "auxiliary_loss_weight": 1.0, "epoch": 6.304957904583723, "flow_matching_loss": 0.0490219596773386, "grad_norm": 0.14679664373397827, "invalid_tail_samples": 22.4, "learning_rate": 9.189145308355337e-05, "loss": 0.0553, "positive_teacher_pairs": 27173.3, "relation_loss": 0.006251487880945206, "selected_pairs": 27173.3, "step": 6740, "student_distance_mean": 846.506005859375, "teacher_distance_mean": 0.8457156419754028, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.006251487880945206, "weighted_relation_loss": 0.006251487880945206 }, { "action_query_batch_std": 15.213053131103516, "action_query_norm": 679.7330810546875, "action_relation_loss": 0.0062130490783602, "auxiliary_loss_weight": 1.0, "epoch": 6.314312441534144, "flow_matching_loss": 0.05012758485972881, "grad_norm": 0.15862056612968445, "invalid_tail_samples": 23.4, "learning_rate": 9.186133819971555e-05, "loss": 0.0563, "positive_teacher_pairs": 26939.5, "relation_loss": 0.0062130490783602, "selected_pairs": 26939.5, "step": 6750, "student_distance_mean": 865.077197265625, "teacher_distance_mean": 0.8550687611103058, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0062130490783602, "weighted_relation_loss": 0.0062130490783602 }, { "action_query_batch_std": 15.127758407592774, "action_query_norm": 675.5716247558594, "action_relation_loss": 0.005981644475832581, "auxiliary_loss_weight": 1.0, "epoch": 6.323666978484565, "flow_matching_loss": 0.050794365257024764, "grad_norm": 0.1151505634188652, "invalid_tail_samples": 24.4, "learning_rate": 9.183117245040455e-05, "loss": 0.0568, "positive_teacher_pairs": 26715.1, "relation_loss": 0.005981644475832581, "selected_pairs": 26715.1, "step": 6760, "student_distance_mean": 857.1794006347657, "teacher_distance_mean": 0.8513049781322479, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.005981644475832581, "weighted_relation_loss": 0.005981644475832581 }, { "action_query_batch_std": 15.266908264160156, "action_query_norm": 681.9014587402344, "action_relation_loss": 0.0063453276176005605, "auxiliary_loss_weight": 1.0, "epoch": 6.333021515434986, "flow_matching_loss": 0.05149210505187511, "grad_norm": 0.15734294056892395, "invalid_tail_samples": 22.9, "learning_rate": 9.180095587227458e-05, "loss": 0.0578, "positive_teacher_pairs": 27057.8, "relation_loss": 0.0063453276176005605, "selected_pairs": 27057.8, "step": 6770, "student_distance_mean": 864.1318176269531, "teacher_distance_mean": 0.8549359261989593, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0063453276176005605, "weighted_relation_loss": 0.0063453276176005605 }, { "action_query_batch_std": 15.109162044525146, "action_query_norm": 673.3125244140625, "action_relation_loss": 0.006174324546009302, "auxiliary_loss_weight": 1.0, "epoch": 6.342376052385407, "flow_matching_loss": 0.0515808641910553, "grad_norm": 0.12791621685028076, "invalid_tail_samples": 25.7, "learning_rate": 9.177068850204167e-05, "loss": 0.0578, "positive_teacher_pairs": 26408.9, "relation_loss": 0.006174324546009302, "selected_pairs": 26408.9, "step": 6780, "student_distance_mean": 858.0237731933594, "teacher_distance_mean": 0.854955130815506, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.006174324546009302, "weighted_relation_loss": 0.006174324546009302 }, { "action_query_batch_std": 15.15698595046997, "action_query_norm": 674.33212890625, "action_relation_loss": 0.006156577402725816, "auxiliary_loss_weight": 1.0, "epoch": 6.351730589335828, "flow_matching_loss": 0.0500982541590929, "grad_norm": 0.17601335048675537, "invalid_tail_samples": 23.4, "learning_rate": 9.174037037648351e-05, "loss": 0.0563, "positive_teacher_pairs": 26945.2, "relation_loss": 0.006156577402725816, "selected_pairs": 26945.2, "step": 6790, "student_distance_mean": 860.9067321777344, "teacher_distance_mean": 0.8580003499984741, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.006156577402725816, "weighted_relation_loss": 0.006156577402725816 }, { "action_query_batch_std": 14.968696594238281, "action_query_norm": 663.0143371582031, "action_relation_loss": 0.0060727105010300875, "auxiliary_loss_weight": 1.0, "epoch": 6.361085126286249, "flow_matching_loss": 0.04960654079914093, "grad_norm": 0.1761813908815384, "invalid_tail_samples": 24.4, "learning_rate": 9.171000153243947e-05, "loss": 0.0557, "positive_teacher_pairs": 26706.7, "relation_loss": 0.0060727105010300875, "selected_pairs": 26706.7, "step": 6800, "student_distance_mean": 847.9315124511719, "teacher_distance_mean": 0.8530425488948822, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0060727105010300875, "weighted_relation_loss": 0.0060727105010300875 }, { "action_query_batch_std": 14.990084838867187, "action_query_norm": 659.1294982910156, "action_relation_loss": 0.006401052325963974, "auxiliary_loss_weight": 1.0, "epoch": 6.37043966323667, "flow_matching_loss": 0.052327335625886914, "grad_norm": 0.13189396262168884, "invalid_tail_samples": 24.1, "learning_rate": 9.167958200681057e-05, "loss": 0.0587, "positive_teacher_pairs": 26779.7, "relation_loss": 0.006401052325963974, "selected_pairs": 26779.7, "step": 6810, "student_distance_mean": 844.6089050292969, "teacher_distance_mean": 0.8522985935211181, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.006401052325963974, "weighted_relation_loss": 0.006401052325963974 }, { "action_query_batch_std": 15.181103229522705, "action_query_norm": 670.0578979492187, "action_relation_loss": 0.00619544736109674, "auxiliary_loss_weight": 1.0, "epoch": 6.37979420018709, "flow_matching_loss": 0.050059191137552264, "grad_norm": 0.14681686460971832, "invalid_tail_samples": 23.7, "learning_rate": 9.164911183655943e-05, "loss": 0.0563, "positive_teacher_pairs": 26875.8, "relation_loss": 0.00619544736109674, "selected_pairs": 26875.8, "step": 6820, "student_distance_mean": 863.9533264160157, "teacher_distance_mean": 0.8600635349750518, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.00619544736109674, "weighted_relation_loss": 0.00619544736109674 }, { "action_query_batch_std": 15.270569038391113, "action_query_norm": 673.6052307128906, "action_relation_loss": 0.006086050998419523, "auxiliary_loss_weight": 1.0, "epoch": 6.3891487371375115, "flow_matching_loss": 0.05048317387700081, "grad_norm": 0.1211588904261589, "invalid_tail_samples": 21.2, "learning_rate": 9.161859105871013e-05, "loss": 0.0566, "positive_teacher_pairs": 27458.2, "relation_loss": 0.006086050998419523, "selected_pairs": 27458.2, "step": 6830, "student_distance_mean": 865.6729675292969, "teacher_distance_mean": 0.8695252418518067, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.006086050998419523, "weighted_relation_loss": 0.006086050998419523 }, { "action_query_batch_std": 15.134741687774659, "action_query_norm": 671.2930908203125, "action_relation_loss": 0.006167440023273229, "auxiliary_loss_weight": 1.0, "epoch": 6.398503274087933, "flow_matching_loss": 0.05135255455970764, "grad_norm": 0.12907257676124573, "invalid_tail_samples": 22.9, "learning_rate": 9.158801971034832e-05, "loss": 0.0575, "positive_teacher_pairs": 27055.6, "relation_loss": 0.006167440023273229, "selected_pairs": 27055.6, "step": 6840, "student_distance_mean": 860.7435913085938, "teacher_distance_mean": 0.8576358258724213, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.006167440023273229, "weighted_relation_loss": 0.006167440023273229 }, { "action_query_batch_std": 15.005433750152587, "action_query_norm": 670.8069763183594, "action_relation_loss": 0.006389900669455528, "auxiliary_loss_weight": 1.0, "epoch": 6.407857811038354, "flow_matching_loss": 0.049753238633275035, "grad_norm": 0.16672933101654053, "invalid_tail_samples": 25.1, "learning_rate": 9.155739782862107e-05, "loss": 0.0561, "positive_teacher_pairs": 26551.6, "relation_loss": 0.006389900669455528, "selected_pairs": 26551.6, "step": 6850, "student_distance_mean": 850.3953063964843, "teacher_distance_mean": 0.8486410975456238, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.006389900669455528, "weighted_relation_loss": 0.006389900669455528 }, { "action_query_batch_std": 15.146144104003906, "action_query_norm": 673.8809753417969, "action_relation_loss": 0.0062948314938694235, "auxiliary_loss_weight": 1.0, "epoch": 6.417212347988775, "flow_matching_loss": 0.049931150674819944, "grad_norm": 0.1615762859582901, "invalid_tail_samples": 24.1, "learning_rate": 9.152672545073687e-05, "loss": 0.0562, "positive_teacher_pairs": 26784.5, "relation_loss": 0.0062948314938694235, "selected_pairs": 26784.5, "step": 6860, "student_distance_mean": 858.2484924316407, "teacher_distance_mean": 0.8546960532665253, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0062948314938694235, "weighted_relation_loss": 0.0062948314938694235 }, { "action_query_batch_std": 15.028764057159425, "action_query_norm": 670.4589111328125, "action_relation_loss": 0.006470909342169762, "auxiliary_loss_weight": 1.0, "epoch": 6.426566884939196, "flow_matching_loss": 0.051922450214624404, "grad_norm": 0.1220308467745781, "invalid_tail_samples": 25.1, "learning_rate": 9.149600261396551e-05, "loss": 0.0584, "positive_teacher_pairs": 26546.5, "relation_loss": 0.006470909342169762, "selected_pairs": 26546.5, "step": 6870, "student_distance_mean": 853.3270080566406, "teacher_distance_mean": 0.8486383199691773, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.006470909342169762, "weighted_relation_loss": 0.006470909342169762 }, { "action_query_batch_std": 15.208046150207519, "action_query_norm": 676.2508361816406, "action_relation_loss": 0.00639475965872407, "auxiliary_loss_weight": 1.0, "epoch": 6.435921421889616, "flow_matching_loss": 0.048064276576042175, "grad_norm": 0.14399924874305725, "invalid_tail_samples": 21.3, "learning_rate": 9.146522935563817e-05, "loss": 0.0545, "positive_teacher_pairs": 27434.6, "relation_loss": 0.00639475965872407, "selected_pairs": 27434.6, "step": 6880, "student_distance_mean": 855.3993041992187, "teacher_distance_mean": 0.8474416851997375, "valid_action_samples": 234.7, "weighted_auxiliary_loss": 0.00639475965872407, "weighted_relation_loss": 0.00639475965872407 }, { "action_query_batch_std": 15.310963249206543, "action_query_norm": 682.6743103027344, "action_relation_loss": 0.006134129455313086, "auxiliary_loss_weight": 1.0, "epoch": 6.445275958840037, "flow_matching_loss": 0.04971553571522236, "grad_norm": 0.13540072739124298, "invalid_tail_samples": 24.6, "learning_rate": 9.143440571314723e-05, "loss": 0.0558, "positive_teacher_pairs": 26661.8, "relation_loss": 0.006134129455313086, "selected_pairs": 26661.8, "step": 6890, "student_distance_mean": 869.3177429199219, "teacher_distance_mean": 0.8564040064811707, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.006134129455313086, "weighted_relation_loss": 0.006134129455313086 }, { "action_query_batch_std": 15.208380794525146, "action_query_norm": 675.9145751953125, "action_relation_loss": 0.006277520582079888, "auxiliary_loss_weight": 1.0, "epoch": 6.454630495790458, "flow_matching_loss": 0.0499783530831337, "grad_norm": 0.15026232600212097, "invalid_tail_samples": 24.4, "learning_rate": 9.140353172394636e-05, "loss": 0.0563, "positive_teacher_pairs": 26711.1, "relation_loss": 0.006277520582079888, "selected_pairs": 26711.1, "step": 6900, "student_distance_mean": 860.8579345703125, "teacher_distance_mean": 0.8574673056602478, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.006277520582079888, "weighted_relation_loss": 0.006277520582079888 }, { "action_query_batch_std": 15.132681560516357, "action_query_norm": 674.5673950195312, "action_relation_loss": 0.006445563770830632, "auxiliary_loss_weight": 1.0, "epoch": 6.463985032740879, "flow_matching_loss": 0.0507808618247509, "grad_norm": 0.1571049690246582, "invalid_tail_samples": 22.0, "learning_rate": 9.137260742555032e-05, "loss": 0.0572, "positive_teacher_pairs": 27269.6, "relation_loss": 0.006445563770830632, "selected_pairs": 27269.6, "step": 6910, "student_distance_mean": 858.6242858886719, "teacher_distance_mean": 0.8487402915954589, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.006445563770830632, "weighted_relation_loss": 0.006445563770830632 }, { "action_query_batch_std": 15.420688915252686, "action_query_norm": 682.2985107421875, "action_relation_loss": 0.006413497729226947, "auxiliary_loss_weight": 1.0, "epoch": 6.4733395696913005, "flow_matching_loss": 0.05148705802857876, "grad_norm": 0.13599345088005066, "invalid_tail_samples": 23.3, "learning_rate": 9.13416328555351e-05, "loss": 0.0579, "positive_teacher_pairs": 26964.6, "relation_loss": 0.006413497729226947, "selected_pairs": 26964.6, "step": 6920, "student_distance_mean": 874.0820068359375, "teacher_distance_mean": 0.8639849543571472, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.006413497729226947, "weighted_relation_loss": 0.006413497729226947 }, { "action_query_batch_std": 15.185338592529297, "action_query_norm": 671.60888671875, "action_relation_loss": 0.006011499511078, "auxiliary_loss_weight": 1.0, "epoch": 6.482694106641722, "flow_matching_loss": 0.0492620911449194, "grad_norm": 0.10917933285236359, "invalid_tail_samples": 25.7, "learning_rate": 9.131060805153769e-05, "loss": 0.0553, "positive_teacher_pairs": 26418.6, "relation_loss": 0.006011499511078, "selected_pairs": 26418.6, "step": 6930, "student_distance_mean": 858.4999389648438, "teacher_distance_mean": 0.851640272140503, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.006011499511078, "weighted_relation_loss": 0.006011499511078 }, { "action_query_batch_std": 15.001241493225098, "action_query_norm": 667.6281921386719, "action_relation_loss": 0.006121114967390895, "auxiliary_loss_weight": 1.0, "epoch": 6.492048643592142, "flow_matching_loss": 0.05121059529483318, "grad_norm": 0.1339716762304306, "invalid_tail_samples": 26.4, "learning_rate": 9.127953305125618e-05, "loss": 0.0573, "positive_teacher_pairs": 26249.2, "relation_loss": 0.006121114967390895, "selected_pairs": 26249.2, "step": 6940, "student_distance_mean": 852.4116088867188, "teacher_distance_mean": 0.8458339810371399, "valid_action_samples": 229.6, "weighted_auxiliary_loss": 0.006121114967390895, "weighted_relation_loss": 0.006121114967390895 }, { "action_query_batch_std": 15.002042675018311, "action_query_norm": 664.861181640625, "action_relation_loss": 0.0061778801959007975, "auxiliary_loss_weight": 1.0, "epoch": 6.501403180542563, "flow_matching_loss": 0.049951699748635295, "grad_norm": 0.13161174952983856, "invalid_tail_samples": 24.7, "learning_rate": 9.124840789244958e-05, "loss": 0.0561, "positive_teacher_pairs": 26640.2, "relation_loss": 0.0061778801959007975, "selected_pairs": 26640.2, "step": 6950, "student_distance_mean": 850.3150451660156, "teacher_distance_mean": 0.853215891122818, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0061778801959007975, "weighted_relation_loss": 0.0061778801959007975 }, { "action_query_batch_std": 15.148868846893311, "action_query_norm": 673.1350708007812, "action_relation_loss": 0.006269285874441266, "auxiliary_loss_weight": 1.0, "epoch": 6.510757717492984, "flow_matching_loss": 0.052214748412370685, "grad_norm": 0.17171189188957214, "invalid_tail_samples": 24.0, "learning_rate": 9.121723261293794e-05, "loss": 0.0585, "positive_teacher_pairs": 26802.6, "relation_loss": 0.006269285874441266, "selected_pairs": 26802.6, "step": 6960, "student_distance_mean": 857.1956787109375, "teacher_distance_mean": 0.854384309053421, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.006269285874441266, "weighted_relation_loss": 0.006269285874441266 }, { "action_query_batch_std": 15.318649101257325, "action_query_norm": 682.5612670898438, "action_relation_loss": 0.006165897892788053, "auxiliary_loss_weight": 1.0, "epoch": 6.520112254443405, "flow_matching_loss": 0.04791639372706413, "grad_norm": 0.1346629112958908, "invalid_tail_samples": 22.7, "learning_rate": 9.118600725060214e-05, "loss": 0.0541, "positive_teacher_pairs": 27102.4, "relation_loss": 0.006165897892788053, "selected_pairs": 27102.4, "step": 6970, "student_distance_mean": 871.2234191894531, "teacher_distance_mean": 0.8533631980419158, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.006165897892788053, "weighted_relation_loss": 0.006165897892788053 }, { "action_query_batch_std": 15.31385087966919, "action_query_norm": 679.2359069824219, "action_relation_loss": 0.00589216030202806, "auxiliary_loss_weight": 1.0, "epoch": 6.529466791393826, "flow_matching_loss": 0.050983741879463196, "grad_norm": 0.15070444345474243, "invalid_tail_samples": 22.6, "learning_rate": 9.115473184338392e-05, "loss": 0.0569, "positive_teacher_pairs": 27131.1, "relation_loss": 0.00589216030202806, "selected_pairs": 27131.1, "step": 6980, "student_distance_mean": 869.5462036132812, "teacher_distance_mean": 0.8609455466270447, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.00589216030202806, "weighted_relation_loss": 0.00589216030202806 }, { "action_query_batch_std": 15.492681694030761, "action_query_norm": 684.6732604980468, "action_relation_loss": 0.005982441920787096, "auxiliary_loss_weight": 1.0, "epoch": 6.538821328344247, "flow_matching_loss": 0.051998245716094973, "grad_norm": 0.1896781325340271, "invalid_tail_samples": 26.3, "learning_rate": 9.11234064292859e-05, "loss": 0.058, "positive_teacher_pairs": 26278.2, "relation_loss": 0.005982441920787096, "selected_pairs": 26278.2, "step": 6990, "student_distance_mean": 880.5397399902344, "teacher_distance_mean": 0.8627460360527038, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.005982441920787096, "weighted_relation_loss": 0.005982441920787096 }, { "action_query_batch_std": 15.480856609344482, "action_query_norm": 685.9835693359375, "action_relation_loss": 0.006205671466886997, "auxiliary_loss_weight": 1.0, "epoch": 6.5481758652946676, "flow_matching_loss": 0.05117430500686169, "grad_norm": 0.18224002420902252, "invalid_tail_samples": 23.3, "learning_rate": 9.109203104637137e-05, "loss": 0.0574, "positive_teacher_pairs": 26967.1, "relation_loss": 0.006205671466886997, "selected_pairs": 26967.1, "step": 7000, "student_distance_mean": 875.0997314453125, "teacher_distance_mean": 0.8577425003051757, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.006205671466886997, "weighted_relation_loss": 0.006205671466886997 }, { "action_query_batch_std": 15.479096508026123, "action_query_norm": 686.9046325683594, "action_relation_loss": 0.006378159672021866, "auxiliary_loss_weight": 1.0, "epoch": 6.557530402245089, "flow_matching_loss": 0.053092613071203235, "grad_norm": 0.15059828758239746, "invalid_tail_samples": 22.8, "learning_rate": 9.10606057327644e-05, "loss": 0.0595, "positive_teacher_pairs": 27085.2, "relation_loss": 0.006378159672021866, "selected_pairs": 27085.2, "step": 7010, "student_distance_mean": 875.6100708007813, "teacher_distance_mean": 0.853103518486023, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.006378159672021866, "weighted_relation_loss": 0.006378159672021866 }, { "action_query_batch_std": 15.438053512573243, "action_query_norm": 686.035546875, "action_relation_loss": 0.00606176950968802, "auxiliary_loss_weight": 1.0, "epoch": 6.56688493919551, "flow_matching_loss": 0.049866510555148125, "grad_norm": 0.1566265970468521, "invalid_tail_samples": 25.0, "learning_rate": 9.10291305266497e-05, "loss": 0.0559, "positive_teacher_pairs": 26570.0, "relation_loss": 0.00606176950968802, "selected_pairs": 26570.0, "step": 7020, "student_distance_mean": 875.2469421386719, "teacher_distance_mean": 0.8486098945140839, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.00606176950968802, "weighted_relation_loss": 0.00606176950968802 }, { "action_query_batch_std": 15.57202501296997, "action_query_norm": 689.07509765625, "action_relation_loss": 0.006241921801120043, "auxiliary_loss_weight": 1.0, "epoch": 6.576239476145931, "flow_matching_loss": 0.05314510427415371, "grad_norm": 0.1419631838798523, "invalid_tail_samples": 24.1, "learning_rate": 9.099760546627261e-05, "loss": 0.0594, "positive_teacher_pairs": 26781.5, "relation_loss": 0.006241921801120043, "selected_pairs": 26781.5, "step": 7030, "student_distance_mean": 883.3239624023438, "teacher_distance_mean": 0.8653688728809357, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.006241921801120043, "weighted_relation_loss": 0.006241921801120043 }, { "action_query_batch_std": 15.69923963546753, "action_query_norm": 693.7732238769531, "action_relation_loss": 0.006207583798095584, "auxiliary_loss_weight": 1.0, "epoch": 6.585594013096352, "flow_matching_loss": 0.05033552795648575, "grad_norm": 0.14950014650821686, "invalid_tail_samples": 24.8, "learning_rate": 9.096603058993907e-05, "loss": 0.0565, "positive_teacher_pairs": 26627.0, "relation_loss": 0.006207583798095584, "selected_pairs": 26627.0, "step": 7040, "student_distance_mean": 886.0134399414062, "teacher_distance_mean": 0.8645540356636048, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.006207583798095584, "weighted_relation_loss": 0.006207583798095584 }, { "action_query_batch_std": 15.439647483825684, "action_query_norm": 686.8246948242188, "action_relation_loss": 0.006333314627408981, "auxiliary_loss_weight": 1.0, "epoch": 6.594948550046773, "flow_matching_loss": 0.050898879393935205, "grad_norm": 0.1303601711988449, "invalid_tail_samples": 25.4, "learning_rate": 9.093440593601552e-05, "loss": 0.0572, "positive_teacher_pairs": 26485.3, "relation_loss": 0.006333314627408981, "selected_pairs": 26485.3, "step": 7050, "student_distance_mean": 876.664306640625, "teacher_distance_mean": 0.853467607498169, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.006333314627408981, "weighted_relation_loss": 0.006333314627408981 }, { "action_query_batch_std": 15.32437686920166, "action_query_norm": 678.6159606933594, "action_relation_loss": 0.006053049536421895, "auxiliary_loss_weight": 1.0, "epoch": 6.604303086997193, "flow_matching_loss": 0.048405971750617026, "grad_norm": 0.14238907396793365, "invalid_tail_samples": 23.6, "learning_rate": 9.090273154292889e-05, "loss": 0.0545, "positive_teacher_pairs": 26897.0, "relation_loss": 0.006053049536421895, "selected_pairs": 26897.0, "step": 7060, "student_distance_mean": 868.2250671386719, "teacher_distance_mean": 0.8547001838684082, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.006053049536421895, "weighted_relation_loss": 0.006053049536421895 }, { "action_query_batch_std": 15.174192428588867, "action_query_norm": 671.3865478515625, "action_relation_loss": 0.0061537195462733505, "auxiliary_loss_weight": 1.0, "epoch": 6.613657623947614, "flow_matching_loss": 0.05114432163536549, "grad_norm": 0.14646056294441223, "invalid_tail_samples": 23.5, "learning_rate": 9.087100744916656e-05, "loss": 0.0573, "positive_teacher_pairs": 26925.3, "relation_loss": 0.0061537195462733505, "selected_pairs": 26925.3, "step": 7070, "student_distance_mean": 858.6376342773438, "teacher_distance_mean": 0.8494760572910309, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0061537195462733505, "weighted_relation_loss": 0.0061537195462733505 }, { "action_query_batch_std": 15.37101345062256, "action_query_norm": 681.0320556640625, "action_relation_loss": 0.0064336851239204405, "auxiliary_loss_weight": 1.0, "epoch": 6.6230121608980355, "flow_matching_loss": 0.05019496753811836, "grad_norm": 0.16368548572063446, "invalid_tail_samples": 20.8, "learning_rate": 9.08392336932763e-05, "loss": 0.0566, "positive_teacher_pairs": 27554.9, "relation_loss": 0.0064336851239204405, "selected_pairs": 27554.9, "step": 7080, "student_distance_mean": 870.5246643066406, "teacher_distance_mean": 0.8470839262008667, "valid_action_samples": 235.2, "weighted_auxiliary_loss": 0.0064336851239204405, "weighted_relation_loss": 0.0064336851239204405 }, { "action_query_batch_std": 15.499338531494141, "action_query_norm": 684.90595703125, "action_relation_loss": 0.006286778533831239, "auxiliary_loss_weight": 1.0, "epoch": 6.632366697848457, "flow_matching_loss": 0.05172478519380093, "grad_norm": 0.14473389089107513, "invalid_tail_samples": 23.6, "learning_rate": 9.080741031386619e-05, "loss": 0.058, "positive_teacher_pairs": 26898.2, "relation_loss": 0.006286778533831239, "selected_pairs": 26898.2, "step": 7090, "student_distance_mean": 875.1147094726563, "teacher_distance_mean": 0.8530238330364227, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.006286778533831239, "weighted_relation_loss": 0.006286778533831239 }, { "action_query_batch_std": 15.636297798156738, "action_query_norm": 690.8210998535156, "action_relation_loss": 0.00617686752229929, "auxiliary_loss_weight": 1.0, "epoch": 6.641721234798878, "flow_matching_loss": 0.050824527814984324, "grad_norm": 0.1758521944284439, "invalid_tail_samples": 24.5, "learning_rate": 9.077553734960468e-05, "loss": 0.057, "positive_teacher_pairs": 26696.2, "relation_loss": 0.00617686752229929, "selected_pairs": 26696.2, "step": 7100, "student_distance_mean": 882.7597717285156, "teacher_distance_mean": 0.8603653967380523, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.00617686752229929, "weighted_relation_loss": 0.00617686752229929 }, { "action_query_batch_std": 15.51521282196045, "action_query_norm": 693.8763366699219, "action_relation_loss": 0.006262682331725955, "auxiliary_loss_weight": 1.0, "epoch": 6.651075771749299, "flow_matching_loss": 0.049275970086455345, "grad_norm": 0.17045721411705017, "invalid_tail_samples": 22.5, "learning_rate": 9.074361483922041e-05, "loss": 0.0555, "positive_teacher_pairs": 27149.6, "relation_loss": 0.006262682331725955, "selected_pairs": 27149.6, "step": 7110, "student_distance_mean": 878.4162414550781, "teacher_distance_mean": 0.8527377426624299, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.006262682331725955, "weighted_relation_loss": 0.006262682331725955 }, { "action_query_batch_std": 15.445640087127686, "action_query_norm": 688.9351196289062, "action_relation_loss": 0.0063527405727654696, "auxiliary_loss_weight": 1.0, "epoch": 6.66043030869972, "flow_matching_loss": 0.04979287274181843, "grad_norm": 0.1329263150691986, "invalid_tail_samples": 23.6, "learning_rate": 9.071164282150224e-05, "loss": 0.0561, "positive_teacher_pairs": 26895.7, "relation_loss": 0.0063527405727654696, "selected_pairs": 26895.7, "step": 7120, "student_distance_mean": 871.845361328125, "teacher_distance_mean": 0.8515543282032013, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0063527405727654696, "weighted_relation_loss": 0.0063527405727654696 }, { "action_query_batch_std": 15.381427669525147, "action_query_norm": 681.7149658203125, "action_relation_loss": 0.006198455765843392, "auxiliary_loss_weight": 1.0, "epoch": 6.66978484565014, "flow_matching_loss": 0.049952829629182814, "grad_norm": 0.16192664206027985, "invalid_tail_samples": 24.7, "learning_rate": 9.067962133529919e-05, "loss": 0.0562, "positive_teacher_pairs": 26642.1, "relation_loss": 0.006198455765843392, "selected_pairs": 26642.1, "step": 7130, "student_distance_mean": 869.7023986816406, "teacher_distance_mean": 0.8549824714660644, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.006198455765843392, "weighted_relation_loss": 0.006198455765843392 }, { "action_query_batch_std": 15.414165115356445, "action_query_norm": 683.4470275878906, "action_relation_loss": 0.006207828363403678, "auxiliary_loss_weight": 1.0, "epoch": 6.679139382600561, "flow_matching_loss": 0.04904045425355434, "grad_norm": 0.14635437726974487, "invalid_tail_samples": 23.5, "learning_rate": 9.064755041952036e-05, "loss": 0.0552, "positive_teacher_pairs": 26922.8, "relation_loss": 0.006207828363403678, "selected_pairs": 26922.8, "step": 7140, "student_distance_mean": 868.8963439941406, "teacher_distance_mean": 0.8526542007923126, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.006207828363403678, "weighted_relation_loss": 0.006207828363403678 }, { "action_query_batch_std": 15.239305210113525, "action_query_norm": 682.8203308105469, "action_relation_loss": 0.0063499798066914085, "auxiliary_loss_weight": 1.0, "epoch": 6.688493919550982, "flow_matching_loss": 0.052507972717285155, "grad_norm": 0.1375313103199005, "invalid_tail_samples": 25.8, "learning_rate": 9.061543011313497e-05, "loss": 0.0589, "positive_teacher_pairs": 26389.7, "relation_loss": 0.0063499798066914085, "selected_pairs": 26389.7, "step": 7150, "student_distance_mean": 867.3036987304688, "teacher_distance_mean": 0.8460339367389679, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.0063499798066914085, "weighted_relation_loss": 0.0063499798066914085 }, { "action_query_batch_std": 15.39798994064331, "action_query_norm": 686.401123046875, "action_relation_loss": 0.006201560841873288, "auxiliary_loss_weight": 1.0, "epoch": 6.697848456501403, "flow_matching_loss": 0.051745233684778215, "grad_norm": 0.12573188543319702, "invalid_tail_samples": 21.9, "learning_rate": 9.05832604551722e-05, "loss": 0.0579, "positive_teacher_pairs": 27289.1, "relation_loss": 0.006201560841873288, "selected_pairs": 27289.1, "step": 7160, "student_distance_mean": 869.9331298828125, "teacher_distance_mean": 0.8550559639930725, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.006201560841873288, "weighted_relation_loss": 0.006201560841873288 }, { "action_query_batch_std": 15.396417808532714, "action_query_norm": 683.7271179199219, "action_relation_loss": 0.006105051003396511, "auxiliary_loss_weight": 1.0, "epoch": 6.7072029934518245, "flow_matching_loss": 0.04876309297978878, "grad_norm": 0.16190356016159058, "invalid_tail_samples": 24.4, "learning_rate": 9.055104148472124e-05, "loss": 0.0549, "positive_teacher_pairs": 26709.2, "relation_loss": 0.006105051003396511, "selected_pairs": 26709.2, "step": 7170, "student_distance_mean": 872.4445556640625, "teacher_distance_mean": 0.8607962787151336, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.006105051003396511, "weighted_relation_loss": 0.006105051003396511 }, { "action_query_batch_std": 15.353382968902588, "action_query_norm": 682.5122863769532, "action_relation_loss": 0.006201199721544981, "auxiliary_loss_weight": 1.0, "epoch": 6.716557530402245, "flow_matching_loss": 0.051777205616235736, "grad_norm": 0.172814279794693, "invalid_tail_samples": 23.3, "learning_rate": 9.051877324093114e-05, "loss": 0.058, "positive_teacher_pairs": 26963.6, "relation_loss": 0.006201199721544981, "selected_pairs": 26963.6, "step": 7180, "student_distance_mean": 871.6868896484375, "teacher_distance_mean": 0.8587196946144104, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.006201199721544981, "weighted_relation_loss": 0.006201199721544981 }, { "action_query_batch_std": 15.341513442993165, "action_query_norm": 683.559130859375, "action_relation_loss": 0.00588462040759623, "auxiliary_loss_weight": 1.0, "epoch": 6.725912067352666, "flow_matching_loss": 0.0484731201082468, "grad_norm": 0.20440909266471863, "invalid_tail_samples": 24.8, "learning_rate": 9.04864557630109e-05, "loss": 0.0544, "positive_teacher_pairs": 26618.7, "relation_loss": 0.00588462040759623, "selected_pairs": 26618.7, "step": 7190, "student_distance_mean": 872.9946899414062, "teacher_distance_mean": 0.8560801565647125, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.00588462040759623, "weighted_relation_loss": 0.00588462040759623 }, { "action_query_batch_std": 15.612452411651612, "action_query_norm": 694.2551452636719, "action_relation_loss": 0.006227455288171768, "auxiliary_loss_weight": 1.0, "epoch": 6.735266604303087, "flow_matching_loss": 0.053317158669233325, "grad_norm": 0.1665690839290619, "invalid_tail_samples": 23.2, "learning_rate": 9.045408909022928e-05, "loss": 0.0595, "positive_teacher_pairs": 27004.5, "relation_loss": 0.006227455288171768, "selected_pairs": 27004.5, "step": 7200, "student_distance_mean": 876.9748046875, "teacher_distance_mean": 0.8516120970249176, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.006227455288171768, "weighted_relation_loss": 0.006227455288171768 }, { "action_query_batch_std": 16.03941431045532, "action_query_norm": 707.8824645996094, "action_relation_loss": 0.005931982723996043, "auxiliary_loss_weight": 1.0, "epoch": 6.744621141253508, "flow_matching_loss": 0.05284336358308792, "grad_norm": 0.23828184604644775, "invalid_tail_samples": 23.2, "learning_rate": 9.042167326191484e-05, "loss": 0.0588, "positive_teacher_pairs": 26989.9, "relation_loss": 0.005931982723996043, "selected_pairs": 26989.9, "step": 7210, "student_distance_mean": 906.3455383300782, "teacher_distance_mean": 0.868370521068573, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.005931982723996043, "weighted_relation_loss": 0.005931982723996043 }, { "action_query_batch_std": 15.671708488464356, "action_query_norm": 696.9828247070312, "action_relation_loss": 0.0061178217642009255, "auxiliary_loss_weight": 1.0, "epoch": 6.753975678203929, "flow_matching_loss": 0.050835436582565306, "grad_norm": 0.16844895482063293, "invalid_tail_samples": 22.8, "learning_rate": 9.038920831745587e-05, "loss": 0.057, "positive_teacher_pairs": 27083.9, "relation_loss": 0.0061178217642009255, "selected_pairs": 27083.9, "step": 7220, "student_distance_mean": 886.4067810058593, "teacher_distance_mean": 0.8585586786270142, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0061178217642009255, "weighted_relation_loss": 0.0061178217642009255 }, { "action_query_batch_std": 15.980995559692383, "action_query_norm": 706.3012634277344, "action_relation_loss": 0.005816718516871333, "auxiliary_loss_weight": 1.0, "epoch": 6.76333021515435, "flow_matching_loss": 0.05269625000655651, "grad_norm": 0.12265965342521667, "invalid_tail_samples": 23.9, "learning_rate": 9.035669429630036e-05, "loss": 0.0585, "positive_teacher_pairs": 26840.5, "relation_loss": 0.005816718516871333, "selected_pairs": 26840.5, "step": 7230, "student_distance_mean": 903.9985900878906, "teacher_distance_mean": 0.8658746004104614, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.005816718516871333, "weighted_relation_loss": 0.005816718516871333 }, { "action_query_batch_std": 15.444382476806641, "action_query_norm": 689.7046508789062, "action_relation_loss": 0.00596602214500308, "auxiliary_loss_weight": 1.0, "epoch": 6.772684752104771, "flow_matching_loss": 0.0482146255671978, "grad_norm": 0.15213502943515778, "invalid_tail_samples": 25.4, "learning_rate": 9.032413123795588e-05, "loss": 0.0542, "positive_teacher_pairs": 26490.1, "relation_loss": 0.00596602214500308, "selected_pairs": 26490.1, "step": 7240, "student_distance_mean": 875.2403503417969, "teacher_distance_mean": 0.8435587108135223, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.00596602214500308, "weighted_relation_loss": 0.00596602214500308 }, { "action_query_batch_std": 15.713364791870116, "action_query_norm": 694.6768249511719, "action_relation_loss": 0.005962630873546005, "auxiliary_loss_weight": 1.0, "epoch": 6.7820392890551915, "flow_matching_loss": 0.05011309720575809, "grad_norm": 0.1669682115316391, "invalid_tail_samples": 25.5, "learning_rate": 9.029151918198962e-05, "loss": 0.0561, "positive_teacher_pairs": 26466.0, "relation_loss": 0.005962630873546005, "selected_pairs": 26466.0, "step": 7250, "student_distance_mean": 885.2102661132812, "teacher_distance_mean": 0.8555651009082794, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.005962630873546005, "weighted_relation_loss": 0.005962630873546005 }, { "action_query_batch_std": 15.986658668518066, "action_query_norm": 706.7995483398438, "action_relation_loss": 0.005960956728085875, "auxiliary_loss_weight": 1.0, "epoch": 6.791393826005613, "flow_matching_loss": 0.04931115992367267, "grad_norm": 0.15564340353012085, "invalid_tail_samples": 24.7, "learning_rate": 9.025885816802833e-05, "loss": 0.0553, "positive_teacher_pairs": 26639.9, "relation_loss": 0.005960956728085875, "selected_pairs": 26639.9, "step": 7260, "student_distance_mean": 905.64326171875, "teacher_distance_mean": 0.8731890916824341, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.005960956728085875, "weighted_relation_loss": 0.005960956728085875 }, { "action_query_batch_std": 15.758326244354247, "action_query_norm": 701.5028625488281, "action_relation_loss": 0.006129651609808206, "auxiliary_loss_weight": 1.0, "epoch": 6.800748362956034, "flow_matching_loss": 0.049973007291555405, "grad_norm": 0.13911373913288116, "invalid_tail_samples": 23.9, "learning_rate": 9.02261482357582e-05, "loss": 0.0561, "positive_teacher_pairs": 26826.3, "relation_loss": 0.006129651609808206, "selected_pairs": 26826.3, "step": 7270, "student_distance_mean": 891.3835021972657, "teacher_distance_mean": 0.8575051426887512, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.006129651609808206, "weighted_relation_loss": 0.006129651609808206 }, { "action_query_batch_std": 15.51856803894043, "action_query_norm": 691.344921875, "action_relation_loss": 0.006118192290887237, "auxiliary_loss_weight": 1.0, "epoch": 6.810102899906455, "flow_matching_loss": 0.04925834722816944, "grad_norm": 0.11551155894994736, "invalid_tail_samples": 25.6, "learning_rate": 9.019338942492485e-05, "loss": 0.0554, "positive_teacher_pairs": 26438.1, "relation_loss": 0.006118192290887237, "selected_pairs": 26438.1, "step": 7280, "student_distance_mean": 882.1649719238281, "teacher_distance_mean": 0.8554852068424225, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.006118192290887237, "weighted_relation_loss": 0.006118192290887237 }, { "action_query_batch_std": 15.74363603591919, "action_query_norm": 696.3969482421875, "action_relation_loss": 0.00588038070127368, "auxiliary_loss_weight": 1.0, "epoch": 6.819457436856876, "flow_matching_loss": 0.05139298141002655, "grad_norm": 0.11244609951972961, "invalid_tail_samples": 22.6, "learning_rate": 9.01605817753334e-05, "loss": 0.0573, "positive_teacher_pairs": 27134.6, "relation_loss": 0.00588038070127368, "selected_pairs": 27134.6, "step": 7290, "student_distance_mean": 891.6219848632812, "teacher_distance_mean": 0.8571621119976044, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.00588038070127368, "weighted_relation_loss": 0.00588038070127368 }, { "action_query_batch_std": 15.771368980407715, "action_query_norm": 698.4866577148438, "action_relation_loss": 0.0058536901604384186, "auxiliary_loss_weight": 1.0, "epoch": 6.828811973807296, "flow_matching_loss": 0.05106704533100128, "grad_norm": 0.12189995497465134, "invalid_tail_samples": 23.8, "learning_rate": 9.012772532684818e-05, "loss": 0.0569, "positive_teacher_pairs": 26850.7, "relation_loss": 0.0058536901604384186, "selected_pairs": 26850.7, "step": 7300, "student_distance_mean": 892.9153442382812, "teacher_distance_mean": 0.8628462553024292, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0058536901604384186, "weighted_relation_loss": 0.0058536901604384186 }, { "action_query_batch_std": 15.534633445739747, "action_query_norm": 689.68203125, "action_relation_loss": 0.006243646377697587, "auxiliary_loss_weight": 1.0, "epoch": 6.838166510757717, "flow_matching_loss": 0.04839027039706707, "grad_norm": 0.13198933005332947, "invalid_tail_samples": 24.3, "learning_rate": 9.00948201193929e-05, "loss": 0.0546, "positive_teacher_pairs": 26733.4, "relation_loss": 0.006243646377697587, "selected_pairs": 26733.4, "step": 7310, "student_distance_mean": 879.1844909667968, "teacher_distance_mean": 0.8543272972106933, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.006243646377697587, "weighted_relation_loss": 0.006243646377697587 }, { "action_query_batch_std": 15.592045402526855, "action_query_norm": 694.5349060058594, "action_relation_loss": 0.006149816373363137, "auxiliary_loss_weight": 1.0, "epoch": 6.847521047708138, "flow_matching_loss": 0.050142745673656466, "grad_norm": 0.1290084719657898, "invalid_tail_samples": 23.9, "learning_rate": 9.006186619295047e-05, "loss": 0.0563, "positive_teacher_pairs": 26828.8, "relation_loss": 0.006149816373363137, "selected_pairs": 26828.8, "step": 7320, "student_distance_mean": 883.4422424316406, "teacher_distance_mean": 0.8523162484169007, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.006149816373363137, "weighted_relation_loss": 0.006149816373363137 }, { "action_query_batch_std": 15.566360473632812, "action_query_norm": 690.6857543945313, "action_relation_loss": 0.005973800551146269, "auxiliary_loss_weight": 1.0, "epoch": 6.856875584658559, "flow_matching_loss": 0.04998965561389923, "grad_norm": 0.10705029219388962, "invalid_tail_samples": 20.7, "learning_rate": 9.002886358756305e-05, "loss": 0.056, "positive_teacher_pairs": 27571.3, "relation_loss": 0.005973800551146269, "selected_pairs": 27571.3, "step": 7330, "student_distance_mean": 881.4890258789062, "teacher_distance_mean": 0.851145476102829, "valid_action_samples": 235.3, "weighted_auxiliary_loss": 0.005973800551146269, "weighted_relation_loss": 0.005973800551146269 }, { "action_query_batch_std": 15.944824504852296, "action_query_norm": 705.4959045410156, "action_relation_loss": 0.006085040234029293, "auxiliary_loss_weight": 1.0, "epoch": 6.8662301216089805, "flow_matching_loss": 0.05049765333533287, "grad_norm": 0.11323636025190353, "invalid_tail_samples": 22.9, "learning_rate": 8.999581234333188e-05, "loss": 0.0566, "positive_teacher_pairs": 27056.8, "relation_loss": 0.006085040234029293, "selected_pairs": 27056.8, "step": 7340, "student_distance_mean": 901.0441772460938, "teacher_distance_mean": 0.8561428844928741, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.006085040234029293, "weighted_relation_loss": 0.006085040234029293 }, { "action_query_batch_std": 16.15299549102783, "action_query_norm": 714.3831726074219, "action_relation_loss": 0.00575665794312954, "auxiliary_loss_weight": 1.0, "epoch": 6.875584658559402, "flow_matching_loss": 0.047998666763305664, "grad_norm": 0.14579246938228607, "invalid_tail_samples": 24.0, "learning_rate": 8.996271250041734e-05, "loss": 0.0538, "positive_teacher_pairs": 26802.9, "relation_loss": 0.00575665794312954, "selected_pairs": 26802.9, "step": 7350, "student_distance_mean": 914.1609741210938, "teacher_distance_mean": 0.8626627922058105, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.00575665794312954, "weighted_relation_loss": 0.00575665794312954 }, { "action_query_batch_std": 16.084484577178955, "action_query_norm": 711.7640319824219, "action_relation_loss": 0.005915894126519561, "auxiliary_loss_weight": 1.0, "epoch": 6.884939195509823, "flow_matching_loss": 0.04974271319806576, "grad_norm": 0.12912854552268982, "invalid_tail_samples": 20.6, "learning_rate": 8.99295640990389e-05, "loss": 0.0557, "positive_teacher_pairs": 27599.3, "relation_loss": 0.005915894126519561, "selected_pairs": 27599.3, "step": 7360, "student_distance_mean": 905.8314208984375, "teacher_distance_mean": 0.8593522787094117, "valid_action_samples": 235.4, "weighted_auxiliary_loss": 0.005915894126519561, "weighted_relation_loss": 0.005915894126519561 }, { "action_query_batch_std": 16.176862716674805, "action_query_norm": 711.92861328125, "action_relation_loss": 0.005893581872805953, "auxiliary_loss_weight": 1.0, "epoch": 6.894293732460243, "flow_matching_loss": 0.05081969276070595, "grad_norm": 0.19064129889011383, "invalid_tail_samples": 21.7, "learning_rate": 8.989636717947494e-05, "loss": 0.0567, "positive_teacher_pairs": 27337.1, "relation_loss": 0.005893581872805953, "selected_pairs": 27337.1, "step": 7370, "student_distance_mean": 912.7559387207032, "teacher_distance_mean": 0.8672034978866577, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.005893581872805953, "weighted_relation_loss": 0.005893581872805953 }, { "action_query_batch_std": 15.634506893157958, "action_query_norm": 693.7645568847656, "action_relation_loss": 0.005904108844697475, "auxiliary_loss_weight": 1.0, "epoch": 6.903648269410664, "flow_matching_loss": 0.0487237423658371, "grad_norm": 0.1487424373626709, "invalid_tail_samples": 24.5, "learning_rate": 8.986312178206291e-05, "loss": 0.0546, "positive_teacher_pairs": 26689.2, "relation_loss": 0.005904108844697475, "selected_pairs": 26689.2, "step": 7380, "student_distance_mean": 883.4126953125, "teacher_distance_mean": 0.8453955292701721, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.005904108844697475, "weighted_relation_loss": 0.005904108844697475 }, { "action_query_batch_std": 15.603744792938233, "action_query_norm": 694.5481201171875, "action_relation_loss": 0.005775843001902104, "auxiliary_loss_weight": 1.0, "epoch": 6.913002806361085, "flow_matching_loss": 0.05059928447008133, "grad_norm": 0.18098989129066467, "invalid_tail_samples": 26.5, "learning_rate": 8.982982794719904e-05, "loss": 0.0564, "positive_teacher_pairs": 26234.2, "relation_loss": 0.005775843001902104, "selected_pairs": 26234.2, "step": 7390, "student_distance_mean": 886.1462768554687, "teacher_distance_mean": 0.8474992156028748, "valid_action_samples": 229.5, "weighted_auxiliary_loss": 0.005775843001902104, "weighted_relation_loss": 0.005775843001902104 }, { "action_query_batch_std": 15.948509311676025, "action_query_norm": 710.2495239257812, "action_relation_loss": 0.005451308703050018, "auxiliary_loss_weight": 1.0, "epoch": 6.922357343311506, "flow_matching_loss": 0.04935666993260383, "grad_norm": 0.17183570563793182, "invalid_tail_samples": 21.4, "learning_rate": 8.979648571533852e-05, "loss": 0.0548, "positive_teacher_pairs": 27414.5, "relation_loss": 0.005451308703050018, "selected_pairs": 27414.5, "step": 7400, "student_distance_mean": 902.0503479003906, "teacher_distance_mean": 0.8621039688587189, "valid_action_samples": 234.6, "weighted_auxiliary_loss": 0.005451308703050018, "weighted_relation_loss": 0.005451308703050018 }, { "action_query_batch_std": 15.7195725440979, "action_query_norm": 701.1860290527344, "action_relation_loss": 0.005763487471267581, "auxiliary_loss_weight": 1.0, "epoch": 6.931711880261927, "flow_matching_loss": 0.048288782313466075, "grad_norm": 0.21474693715572357, "invalid_tail_samples": 23.4, "learning_rate": 8.976309512699528e-05, "loss": 0.0541, "positive_teacher_pairs": 26938.9, "relation_loss": 0.005763487471267581, "selected_pairs": 26938.9, "step": 7410, "student_distance_mean": 891.4592529296875, "teacher_distance_mean": 0.8527838170528412, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.005763487471267581, "weighted_relation_loss": 0.005763487471267581 }, { "action_query_batch_std": 15.833297729492188, "action_query_norm": 703.1987731933593, "action_relation_loss": 0.006168094975873828, "auxiliary_loss_weight": 1.0, "epoch": 6.9410664172123475, "flow_matching_loss": 0.04938817732036114, "grad_norm": 0.18101991713047028, "invalid_tail_samples": 24.4, "learning_rate": 8.972965622274205e-05, "loss": 0.0556, "positive_teacher_pairs": 26712.5, "relation_loss": 0.006168094975873828, "selected_pairs": 26712.5, "step": 7420, "student_distance_mean": 899.4349060058594, "teacher_distance_mean": 0.8595913290977478, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.006168094975873828, "weighted_relation_loss": 0.006168094975873828 }, { "action_query_batch_std": 15.76891860961914, "action_query_norm": 698.4628234863281, "action_relation_loss": 0.005878129927441478, "auxiliary_loss_weight": 1.0, "epoch": 6.950420954162769, "flow_matching_loss": 0.04887644574046135, "grad_norm": 0.15422901511192322, "invalid_tail_samples": 23.9, "learning_rate": 8.969616904321026e-05, "loss": 0.0548, "positive_teacher_pairs": 26823.7, "relation_loss": 0.005878129927441478, "selected_pairs": 26823.7, "step": 7430, "student_distance_mean": 890.4539306640625, "teacher_distance_mean": 0.853182464838028, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.005878129927441478, "weighted_relation_loss": 0.005878129927441478 }, { "action_query_batch_std": 15.598863792419433, "action_query_norm": 696.45126953125, "action_relation_loss": 0.0063933773897588255, "auxiliary_loss_weight": 1.0, "epoch": 6.95977549111319, "flow_matching_loss": 0.048595092445611957, "grad_norm": 0.19566918909549713, "invalid_tail_samples": 24.4, "learning_rate": 8.966263362908998e-05, "loss": 0.055, "positive_teacher_pairs": 26712.4, "relation_loss": 0.0063933773897588255, "selected_pairs": 26712.4, "step": 7440, "student_distance_mean": 881.8451721191407, "teacher_distance_mean": 0.8470549046993255, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0063933773897588255, "weighted_relation_loss": 0.0063933773897588255 }, { "action_query_batch_std": 15.53684368133545, "action_query_norm": 700.1459533691407, "action_relation_loss": 0.006000975333154202, "auxiliary_loss_weight": 1.0, "epoch": 6.969130028063611, "flow_matching_loss": 0.05098964609205723, "grad_norm": 0.1514127254486084, "invalid_tail_samples": 24.5, "learning_rate": 8.962905002112989e-05, "loss": 0.057, "positive_teacher_pairs": 26691.8, "relation_loss": 0.006000975333154202, "selected_pairs": 26691.8, "step": 7450, "student_distance_mean": 882.6412963867188, "teacher_distance_mean": 0.8445034801959992, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.006000975333154202, "weighted_relation_loss": 0.006000975333154202 }, { "action_query_batch_std": 15.565508174896241, "action_query_norm": 697.9046325683594, "action_relation_loss": 0.005761418119072914, "auxiliary_loss_weight": 1.0, "epoch": 6.978484565014032, "flow_matching_loss": 0.047837136685848235, "grad_norm": 0.11909069865942001, "invalid_tail_samples": 24.3, "learning_rate": 8.959541826013724e-05, "loss": 0.0536, "positive_teacher_pairs": 26746.0, "relation_loss": 0.005761418119072914, "selected_pairs": 26746.0, "step": 7460, "student_distance_mean": 880.7127380371094, "teacher_distance_mean": 0.8456895530223847, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.005761418119072914, "weighted_relation_loss": 0.005761418119072914 }, { "action_query_batch_std": 15.887327003479005, "action_query_norm": 707.9978820800782, "action_relation_loss": 0.005744302645325661, "auxiliary_loss_weight": 1.0, "epoch": 6.987839101964453, "flow_matching_loss": 0.04838016703724861, "grad_norm": 0.16983726620674133, "invalid_tail_samples": 23.6, "learning_rate": 8.956173838697781e-05, "loss": 0.0541, "positive_teacher_pairs": 26899.5, "relation_loss": 0.005744302645325661, "selected_pairs": 26899.5, "step": 7470, "student_distance_mean": 903.4678466796875, "teacher_distance_mean": 0.857307106256485, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.005744302645325661, "weighted_relation_loss": 0.005744302645325661 }, { "action_query_batch_std": 15.980553722381591, "action_query_norm": 708.2368103027344, "action_relation_loss": 0.0059864017181098465, "auxiliary_loss_weight": 1.0, "epoch": 6.997193638914874, "flow_matching_loss": 0.05059010125696659, "grad_norm": 0.1695217341184616, "invalid_tail_samples": 25.2, "learning_rate": 8.952801044257581e-05, "loss": 0.0566, "positive_teacher_pairs": 26529.9, "relation_loss": 0.0059864017181098465, "selected_pairs": 26529.9, "step": 7480, "student_distance_mean": 903.7196960449219, "teacher_distance_mean": 0.8587952494621277, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0059864017181098465, "weighted_relation_loss": 0.0059864017181098465 }, { "action_query_batch_std": 15.983744621276855, "action_query_norm": 713.2628295898437, "action_relation_loss": 0.006037318566814065, "auxiliary_loss_weight": 1.0, "epoch": 7.006548175865294, "flow_matching_loss": 0.05189389623701572, "grad_norm": 0.15568731725215912, "invalid_tail_samples": 20.9, "learning_rate": 8.949423446791387e-05, "loss": 0.0579, "positive_teacher_pairs": 24532.8, "relation_loss": 0.006037318566814065, "selected_pairs": 24532.8, "step": 7490, "student_distance_mean": 903.8023742675781, "teacher_distance_mean": 0.8570819735527039, "valid_action_samples": 215.2, "weighted_auxiliary_loss": 0.006037318566814065, "weighted_relation_loss": 0.006037318566814065 }, { "action_query_batch_std": 16.081169033050536, "action_query_norm": 712.6594482421875, "action_relation_loss": 0.005534923262894153, "auxiliary_loss_weight": 1.0, "epoch": 7.015902712815715, "flow_matching_loss": 0.04619088508188725, "grad_norm": 0.15055616199970245, "invalid_tail_samples": 24.4, "learning_rate": 8.9460410504033e-05, "loss": 0.0517, "positive_teacher_pairs": 26719.0, "relation_loss": 0.005534923262894153, "selected_pairs": 26719.0, "step": 7500, "student_distance_mean": 908.7170837402343, "teacher_distance_mean": 0.856358277797699, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.005534923262894153, "weighted_relation_loss": 0.005534923262894153 }, { "action_query_batch_std": 16.00672674179077, "action_query_norm": 711.9399475097656, "action_relation_loss": 0.0055073538795113565, "auxiliary_loss_weight": 1.0, "epoch": 7.0252572497661365, "flow_matching_loss": 0.048399630934000015, "grad_norm": 0.16296078264713287, "invalid_tail_samples": 22.9, "learning_rate": 8.942653859203248e-05, "loss": 0.0539, "positive_teacher_pairs": 27063.8, "relation_loss": 0.0055073538795113565, "selected_pairs": 27063.8, "step": 7510, "student_distance_mean": 907.8917053222656, "teacher_distance_mean": 0.8593722403049469, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0055073538795113565, "weighted_relation_loss": 0.0055073538795113565 }, { "action_query_batch_std": 16.04820785522461, "action_query_norm": 716.7385620117187, "action_relation_loss": 0.005782125936821103, "auxiliary_loss_weight": 1.0, "epoch": 7.034611786716558, "flow_matching_loss": 0.046922783553600314, "grad_norm": 0.1776188462972641, "invalid_tail_samples": 20.9, "learning_rate": 8.93926187730699e-05, "loss": 0.0527, "positive_teacher_pairs": 27530.2, "relation_loss": 0.005782125936821103, "selected_pairs": 27530.2, "step": 7520, "student_distance_mean": 908.5742431640625, "teacher_distance_mean": 0.8550886690616608, "valid_action_samples": 235.1, "weighted_auxiliary_loss": 0.005782125936821103, "weighted_relation_loss": 0.005782125936821103 }, { "action_query_batch_std": 16.178525066375734, "action_query_norm": 716.3493408203125, "action_relation_loss": 0.005717647261917591, "auxiliary_loss_weight": 1.0, "epoch": 7.043966323666979, "flow_matching_loss": 0.05038903616368771, "grad_norm": 0.15718679130077362, "invalid_tail_samples": 23.7, "learning_rate": 8.935865108836102e-05, "loss": 0.0561, "positive_teacher_pairs": 26868.9, "relation_loss": 0.005717647261917591, "selected_pairs": 26868.9, "step": 7530, "student_distance_mean": 916.7095947265625, "teacher_distance_mean": 0.8577612221240998, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.005717647261917591, "weighted_relation_loss": 0.005717647261917591 }, { "action_query_batch_std": 16.059367179870605, "action_query_norm": 711.352294921875, "action_relation_loss": 0.0057394738309085366, "auxiliary_loss_weight": 1.0, "epoch": 7.0533208606174, "flow_matching_loss": 0.04875367693603039, "grad_norm": 0.1472635269165039, "invalid_tail_samples": 22.9, "learning_rate": 8.932463557917981e-05, "loss": 0.0545, "positive_teacher_pairs": 27058.6, "relation_loss": 0.0057394738309085366, "selected_pairs": 27058.6, "step": 7540, "student_distance_mean": 907.4214477539062, "teacher_distance_mean": 0.8548420250415802, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0057394738309085366, "weighted_relation_loss": 0.0057394738309085366 }, { "action_query_batch_std": 15.999382209777831, "action_query_norm": 707.1169250488281, "action_relation_loss": 0.005799496127292514, "auxiliary_loss_weight": 1.0, "epoch": 7.06267539756782, "flow_matching_loss": 0.048389916121959684, "grad_norm": 0.13360418379306793, "invalid_tail_samples": 26.8, "learning_rate": 8.929057228685829e-05, "loss": 0.0542, "positive_teacher_pairs": 26162.2, "relation_loss": 0.005799496127292514, "selected_pairs": 26162.2, "step": 7550, "student_distance_mean": 905.9261108398438, "teacher_distance_mean": 0.8587847054004669, "valid_action_samples": 229.2, "weighted_auxiliary_loss": 0.005799496127292514, "weighted_relation_loss": 0.005799496127292514 }, { "action_query_batch_std": 15.99624423980713, "action_query_norm": 707.1467529296875, "action_relation_loss": 0.0056230280548334125, "auxiliary_loss_weight": 1.0, "epoch": 7.072029934518241, "flow_matching_loss": 0.04680492244660854, "grad_norm": 0.15287086367607117, "invalid_tail_samples": 24.5, "learning_rate": 8.925646125278658e-05, "loss": 0.0524, "positive_teacher_pairs": 26683.5, "relation_loss": 0.0056230280548334125, "selected_pairs": 26683.5, "step": 7560, "student_distance_mean": 909.4416870117187, "teacher_distance_mean": 0.8527034282684326, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0056230280548334125, "weighted_relation_loss": 0.0056230280548334125 }, { "action_query_batch_std": 16.209518337249754, "action_query_norm": 716.1498718261719, "action_relation_loss": 0.005665527563542128, "auxiliary_loss_weight": 1.0, "epoch": 7.081384471468662, "flow_matching_loss": 0.04949439577758312, "grad_norm": 0.17483681440353394, "invalid_tail_samples": 23.8, "learning_rate": 8.92223025184128e-05, "loss": 0.0552, "positive_teacher_pairs": 26848.8, "relation_loss": 0.005665527563542128, "selected_pairs": 26848.8, "step": 7570, "student_distance_mean": 921.1834411621094, "teacher_distance_mean": 0.8588057518005371, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.005665527563542128, "weighted_relation_loss": 0.005665527563542128 }, { "action_query_batch_std": 16.098536682128906, "action_query_norm": 710.9912048339844, "action_relation_loss": 0.005766017641872167, "auxiliary_loss_weight": 1.0, "epoch": 7.090739008419083, "flow_matching_loss": 0.0470332682132721, "grad_norm": 0.13410083949565887, "invalid_tail_samples": 25.0, "learning_rate": 8.918809612524303e-05, "loss": 0.0528, "positive_teacher_pairs": 26575.9, "relation_loss": 0.005766017641872167, "selected_pairs": 26575.9, "step": 7580, "student_distance_mean": 915.0801940917969, "teacher_distance_mean": 0.8566790401935578, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.005766017641872167, "weighted_relation_loss": 0.005766017641872167 }, { "action_query_batch_std": 16.18959512710571, "action_query_norm": 716.7378662109375, "action_relation_loss": 0.0056478198617696766, "auxiliary_loss_weight": 1.0, "epoch": 7.100093545369504, "flow_matching_loss": 0.047564738616347316, "grad_norm": 0.12990248203277588, "invalid_tail_samples": 25.7, "learning_rate": 8.91538421148413e-05, "loss": 0.0532, "positive_teacher_pairs": 26421.2, "relation_loss": 0.0056478198617696766, "selected_pairs": 26421.2, "step": 7590, "student_distance_mean": 917.0634887695312, "teacher_distance_mean": 0.8504078447818756, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.0056478198617696766, "weighted_relation_loss": 0.0056478198617696766 }, { "action_query_batch_std": 16.29152889251709, "action_query_norm": 718.4727478027344, "action_relation_loss": 0.005708751501515508, "auxiliary_loss_weight": 1.0, "epoch": 7.1094480823199255, "flow_matching_loss": 0.04816493503749371, "grad_norm": 0.15955252945423126, "invalid_tail_samples": 24.0, "learning_rate": 8.91195405288294e-05, "loss": 0.0539, "positive_teacher_pairs": 26797.9, "relation_loss": 0.005708751501515508, "selected_pairs": 26797.9, "step": 7600, "student_distance_mean": 924.37236328125, "teacher_distance_mean": 0.8709393799304962, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.005708751501515508, "weighted_relation_loss": 0.005708751501515508 }, { "action_query_batch_std": 15.992064094543457, "action_query_norm": 706.6514221191406, "action_relation_loss": 0.005649119662120938, "auxiliary_loss_weight": 1.0, "epoch": 7.118802619270346, "flow_matching_loss": 0.04860041104257107, "grad_norm": 0.15604828298091888, "invalid_tail_samples": 23.5, "learning_rate": 8.908519140888705e-05, "loss": 0.0542, "positive_teacher_pairs": 26929.9, "relation_loss": 0.005649119662120938, "selected_pairs": 26929.9, "step": 7610, "student_distance_mean": 904.9292907714844, "teacher_distance_mean": 0.8508171319961548, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.005649119662120938, "weighted_relation_loss": 0.005649119662120938 }, { "action_query_batch_std": 15.820437049865722, "action_query_norm": 702.244140625, "action_relation_loss": 0.0055736979003995655, "auxiliary_loss_weight": 1.0, "epoch": 7.128157156220767, "flow_matching_loss": 0.04601282104849815, "grad_norm": 0.14085513353347778, "invalid_tail_samples": 26.0, "learning_rate": 8.905079479675164e-05, "loss": 0.0516, "positive_teacher_pairs": 26339.0, "relation_loss": 0.0055736979003995655, "selected_pairs": 26339.0, "step": 7620, "student_distance_mean": 900.1322448730468, "teacher_distance_mean": 0.8481608033180237, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.0055736979003995655, "weighted_relation_loss": 0.0055736979003995655 }, { "action_query_batch_std": 16.03740062713623, "action_query_norm": 707.3896301269531, "action_relation_loss": 0.005822664406150579, "auxiliary_loss_weight": 1.0, "epoch": 7.137511693171188, "flow_matching_loss": 0.046070000156760216, "grad_norm": 0.12373609095811844, "invalid_tail_samples": 22.8, "learning_rate": 8.901635073421831e-05, "loss": 0.0519, "positive_teacher_pairs": 27088.2, "relation_loss": 0.005822664406150579, "selected_pairs": 27088.2, "step": 7630, "student_distance_mean": 908.468505859375, "teacher_distance_mean": 0.8598795354366302, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.005822664406150579, "weighted_relation_loss": 0.005822664406150579 }, { "action_query_batch_std": 16.088643932342528, "action_query_norm": 710.5387878417969, "action_relation_loss": 0.005732842488214374, "auxiliary_loss_weight": 1.0, "epoch": 7.146866230121609, "flow_matching_loss": 0.0484899464994669, "grad_norm": 0.12462546676397324, "invalid_tail_samples": 23.9, "learning_rate": 8.898185926313983e-05, "loss": 0.0542, "positive_teacher_pairs": 26827.2, "relation_loss": 0.005732842488214374, "selected_pairs": 26827.2, "step": 7640, "student_distance_mean": 915.083740234375, "teacher_distance_mean": 0.8600528359413147, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.005732842488214374, "weighted_relation_loss": 0.005732842488214374 }, { "action_query_batch_std": 16.176416301727294, "action_query_norm": 717.2593078613281, "action_relation_loss": 0.005484250886365771, "auxiliary_loss_weight": 1.0, "epoch": 7.15622076707203, "flow_matching_loss": 0.04570759572088719, "grad_norm": 0.09644631296396255, "invalid_tail_samples": 22.0, "learning_rate": 8.894732042542659e-05, "loss": 0.0512, "positive_teacher_pairs": 27271.9, "relation_loss": 0.005484250886365771, "selected_pairs": 27271.9, "step": 7650, "student_distance_mean": 913.4787780761719, "teacher_distance_mean": 0.8574818968772888, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.005484250886365771, "weighted_relation_loss": 0.005484250886365771 }, { "action_query_batch_std": 16.033759117126465, "action_query_norm": 708.4627075195312, "action_relation_loss": 0.005604795878753066, "auxiliary_loss_weight": 1.0, "epoch": 7.165575304022451, "flow_matching_loss": 0.04754188843071461, "grad_norm": 0.14963340759277344, "invalid_tail_samples": 23.4, "learning_rate": 8.891273426304654e-05, "loss": 0.0531, "positive_teacher_pairs": 26946.4, "relation_loss": 0.005604795878753066, "selected_pairs": 26946.4, "step": 7660, "student_distance_mean": 906.4793273925782, "teacher_distance_mean": 0.8527041554450989, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.005604795878753066, "weighted_relation_loss": 0.005604795878753066 }, { "action_query_batch_std": 16.10405902862549, "action_query_norm": 714.9704345703125, "action_relation_loss": 0.0056168610695749525, "auxiliary_loss_weight": 1.0, "epoch": 7.1749298409728715, "flow_matching_loss": 0.04435183443129063, "grad_norm": 0.15037544071674347, "invalid_tail_samples": 24.5, "learning_rate": 8.887810081802515e-05, "loss": 0.05, "positive_teacher_pairs": 26694.4, "relation_loss": 0.0056168610695749525, "selected_pairs": 26694.4, "step": 7670, "student_distance_mean": 913.6489379882812, "teacher_distance_mean": 0.8607877910137176, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0056168610695749525, "weighted_relation_loss": 0.0056168610695749525 }, { "action_query_batch_std": 16.006420135498047, "action_query_norm": 713.2014099121094, "action_relation_loss": 0.0057414462324231865, "auxiliary_loss_weight": 1.0, "epoch": 7.1842843779232926, "flow_matching_loss": 0.0471463680267334, "grad_norm": 0.1290874183177948, "invalid_tail_samples": 21.8, "learning_rate": 8.884342013244529e-05, "loss": 0.0529, "positive_teacher_pairs": 27314.0, "relation_loss": 0.0057414462324231865, "selected_pairs": 27314.0, "step": 7680, "student_distance_mean": 908.5748901367188, "teacher_distance_mean": 0.8511075496673584, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.0057414462324231865, "weighted_relation_loss": 0.0057414462324231865 }, { "action_query_batch_std": 16.061830139160158, "action_query_norm": 713.9417236328125, "action_relation_loss": 0.005533787747845053, "auxiliary_loss_weight": 1.0, "epoch": 7.193638914873714, "flow_matching_loss": 0.04963649436831474, "grad_norm": 0.18644310534000397, "invalid_tail_samples": 23.6, "learning_rate": 8.880869224844725e-05, "loss": 0.0552, "positive_teacher_pairs": 26902.5, "relation_loss": 0.005533787747845053, "selected_pairs": 26902.5, "step": 7690, "student_distance_mean": 911.5863159179687, "teacher_distance_mean": 0.8519628703594208, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.005533787747845053, "weighted_relation_loss": 0.005533787747845053 }, { "action_query_batch_std": 15.974533653259277, "action_query_norm": 711.0440490722656, "action_relation_loss": 0.006032288260757923, "auxiliary_loss_weight": 1.0, "epoch": 7.202993451824135, "flow_matching_loss": 0.04850129820406437, "grad_norm": 0.18108631670475006, "invalid_tail_samples": 23.7, "learning_rate": 8.877391720822875e-05, "loss": 0.0545, "positive_teacher_pairs": 26876.9, "relation_loss": 0.006032288260757923, "selected_pairs": 26876.9, "step": 7700, "student_distance_mean": 905.0551818847656, "teacher_distance_mean": 0.8496497869491577, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.006032288260757923, "weighted_relation_loss": 0.006032288260757923 }, { "action_query_batch_std": 16.221656608581544, "action_query_norm": 720.20205078125, "action_relation_loss": 0.005761515302583575, "auxiliary_loss_weight": 1.0, "epoch": 7.212347988774556, "flow_matching_loss": 0.04732803888618946, "grad_norm": 0.1502184271812439, "invalid_tail_samples": 23.8, "learning_rate": 8.873909505404468e-05, "loss": 0.0531, "positive_teacher_pairs": 26846.2, "relation_loss": 0.005761515302583575, "selected_pairs": 26846.2, "step": 7710, "student_distance_mean": 916.6547729492188, "teacher_distance_mean": 0.8485854625701904, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.005761515302583575, "weighted_relation_loss": 0.005761515302583575 }, { "action_query_batch_std": 16.178278541564943, "action_query_norm": 716.397705078125, "action_relation_loss": 0.005579311260953545, "auxiliary_loss_weight": 1.0, "epoch": 7.221702525724977, "flow_matching_loss": 0.045457911863923076, "grad_norm": 0.13854417204856873, "invalid_tail_samples": 24.0, "learning_rate": 8.870422582820726e-05, "loss": 0.051, "positive_teacher_pairs": 26801.9, "relation_loss": 0.005579311260953545, "selected_pairs": 26801.9, "step": 7720, "student_distance_mean": 914.6382690429688, "teacher_distance_mean": 0.8509435176849365, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.005579311260953545, "weighted_relation_loss": 0.005579311260953545 }, { "action_query_batch_std": 16.39895362854004, "action_query_norm": 724.7875427246094, "action_relation_loss": 0.005517653003334999, "auxiliary_loss_weight": 1.0, "epoch": 7.231057062675397, "flow_matching_loss": 0.047452975809574124, "grad_norm": 0.12662741541862488, "invalid_tail_samples": 23.4, "learning_rate": 8.866930957308588e-05, "loss": 0.053, "positive_teacher_pairs": 26943.4, "relation_loss": 0.005517653003334999, "selected_pairs": 26943.4, "step": 7730, "student_distance_mean": 933.43564453125, "teacher_distance_mean": 0.8618034958839417, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.005517653003334999, "weighted_relation_loss": 0.005517653003334999 }, { "action_query_batch_std": 16.49486427307129, "action_query_norm": 727.3039855957031, "action_relation_loss": 0.005426770728081465, "auxiliary_loss_weight": 1.0, "epoch": 7.240411599625818, "flow_matching_loss": 0.04585037119686604, "grad_norm": 0.12940707802772522, "invalid_tail_samples": 23.2, "learning_rate": 8.86343463311071e-05, "loss": 0.0513, "positive_teacher_pairs": 26987.8, "relation_loss": 0.005426770728081465, "selected_pairs": 26987.8, "step": 7740, "student_distance_mean": 931.682568359375, "teacher_distance_mean": 0.8617575526237488, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.005426770728081465, "weighted_relation_loss": 0.005426770728081465 }, { "action_query_batch_std": 16.310292053222657, "action_query_norm": 718.5880004882813, "action_relation_loss": 0.005441897548735142, "auxiliary_loss_weight": 1.0, "epoch": 7.249766136576239, "flow_matching_loss": 0.04615753628313542, "grad_norm": 0.13090506196022034, "invalid_tail_samples": 22.3, "learning_rate": 8.859933614475452e-05, "loss": 0.0516, "positive_teacher_pairs": 27200.3, "relation_loss": 0.005441897548735142, "selected_pairs": 27200.3, "step": 7750, "student_distance_mean": 920.5965209960938, "teacher_distance_mean": 0.8617521822452545, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.005441897548735142, "weighted_relation_loss": 0.005441897548735142 }, { "action_query_batch_std": 16.009124088287354, "action_query_norm": 709.1328247070312, "action_relation_loss": 0.005563682736828923, "auxiliary_loss_weight": 1.0, "epoch": 7.2591206735266605, "flow_matching_loss": 0.04587619826197624, "grad_norm": 0.12268268316984177, "invalid_tail_samples": 21.8, "learning_rate": 8.85642790565689e-05, "loss": 0.0514, "positive_teacher_pairs": 27312.9, "relation_loss": 0.005563682736828923, "selected_pairs": 27312.9, "step": 7760, "student_distance_mean": 907.1993835449218, "teacher_distance_mean": 0.8386616170406341, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.005563682736828923, "weighted_relation_loss": 0.005563682736828923 }, { "action_query_batch_std": 16.22272148132324, "action_query_norm": 715.8188293457031, "action_relation_loss": 0.005611547594889998, "auxiliary_loss_weight": 1.0, "epoch": 7.268475210477082, "flow_matching_loss": 0.046012047305703165, "grad_norm": 0.1326131671667099, "invalid_tail_samples": 20.8, "learning_rate": 8.852917510914782e-05, "loss": 0.0516, "positive_teacher_pairs": 27549.8, "relation_loss": 0.005611547594889998, "selected_pairs": 27549.8, "step": 7770, "student_distance_mean": 917.1500610351562, "teacher_distance_mean": 0.8384555280208588, "valid_action_samples": 235.2, "weighted_auxiliary_loss": 0.005611547594889998, "weighted_relation_loss": 0.005611547594889998 }, { "action_query_batch_std": 16.314325714111327, "action_query_norm": 721.1653381347656, "action_relation_loss": 0.005675867106765509, "auxiliary_loss_weight": 1.0, "epoch": 7.277829747427503, "flow_matching_loss": 0.04837789796292782, "grad_norm": 0.11505432426929474, "invalid_tail_samples": 22.7, "learning_rate": 8.84940243451459e-05, "loss": 0.0541, "positive_teacher_pairs": 27103.3, "relation_loss": 0.005675867106765509, "selected_pairs": 27103.3, "step": 7780, "student_distance_mean": 920.4301818847656, "teacher_distance_mean": 0.8538496315479278, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.005675867106765509, "weighted_relation_loss": 0.005675867106765509 }, { "action_query_batch_std": 16.563922500610353, "action_query_norm": 729.5155883789063, "action_relation_loss": 0.005519072106108069, "auxiliary_loss_weight": 1.0, "epoch": 7.287184284377924, "flow_matching_loss": 0.050078701227903366, "grad_norm": 0.1273833066225052, "invalid_tail_samples": 22.9, "learning_rate": 8.845882680727469e-05, "loss": 0.0556, "positive_teacher_pairs": 27064.9, "relation_loss": 0.005519072106108069, "selected_pairs": 27064.9, "step": 7790, "student_distance_mean": 938.7092529296875, "teacher_distance_mean": 0.8697809100151062, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.005519072106108069, "weighted_relation_loss": 0.005519072106108069 }, { "action_query_batch_std": 16.221186637878418, "action_query_norm": 718.0181640625, "action_relation_loss": 0.0057255815714597705, "auxiliary_loss_weight": 1.0, "epoch": 7.296538821328344, "flow_matching_loss": 0.04716372527182102, "grad_norm": 0.1454821079969406, "invalid_tail_samples": 24.6, "learning_rate": 8.842358253830246e-05, "loss": 0.0529, "positive_teacher_pairs": 26664.8, "relation_loss": 0.0057255815714597705, "selected_pairs": 26664.8, "step": 7800, "student_distance_mean": 918.9703369140625, "teacher_distance_mean": 0.8543617367744446, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0057255815714597705, "weighted_relation_loss": 0.0057255815714597705 }, { "action_query_batch_std": 16.34643421173096, "action_query_norm": 722.1707153320312, "action_relation_loss": 0.005874883383512497, "auxiliary_loss_weight": 1.0, "epoch": 7.305893358278765, "flow_matching_loss": 0.050308167934417725, "grad_norm": 0.13932321965694427, "invalid_tail_samples": 25.1, "learning_rate": 8.838829158105434e-05, "loss": 0.0562, "positive_teacher_pairs": 26546.3, "relation_loss": 0.005874883383512497, "selected_pairs": 26546.3, "step": 7810, "student_distance_mean": 924.3696166992188, "teacher_distance_mean": 0.8528271198272706, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.005874883383512497, "weighted_relation_loss": 0.005874883383512497 }, { "action_query_batch_std": 16.35685634613037, "action_query_norm": 722.3858093261719, "action_relation_loss": 0.005600332655012608, "auxiliary_loss_weight": 1.0, "epoch": 7.315247895229186, "flow_matching_loss": 0.04713962823152542, "grad_norm": 0.18153293430805206, "invalid_tail_samples": 25.0, "learning_rate": 8.835295397841217e-05, "loss": 0.0527, "positive_teacher_pairs": 26577.2, "relation_loss": 0.005600332655012608, "selected_pairs": 26577.2, "step": 7820, "student_distance_mean": 927.7813659667969, "teacher_distance_mean": 0.8550146818161011, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.005600332655012608, "weighted_relation_loss": 0.005600332655012608 }, { "action_query_batch_std": 16.297806072235108, "action_query_norm": 722.0530395507812, "action_relation_loss": 0.005387011822313071, "auxiliary_loss_weight": 1.0, "epoch": 7.324602432179607, "flow_matching_loss": 0.04625255316495895, "grad_norm": 0.14268633723258972, "invalid_tail_samples": 25.8, "learning_rate": 8.831756977331447e-05, "loss": 0.0516, "positive_teacher_pairs": 26386.2, "relation_loss": 0.005387011822313071, "selected_pairs": 26386.2, "step": 7830, "student_distance_mean": 922.5922607421875, "teacher_distance_mean": 0.8520548164844512, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.005387011822313071, "weighted_relation_loss": 0.005387011822313071 }, { "action_query_batch_std": 16.339284706115723, "action_query_norm": 722.7064025878906, "action_relation_loss": 0.005514457961544395, "auxiliary_loss_weight": 1.0, "epoch": 7.333956969130028, "flow_matching_loss": 0.04966286346316338, "grad_norm": 0.11693858355283737, "invalid_tail_samples": 24.5, "learning_rate": 8.828213900875638e-05, "loss": 0.0552, "positive_teacher_pairs": 26689.0, "relation_loss": 0.005514457961544395, "selected_pairs": 26689.0, "step": 7840, "student_distance_mean": 928.3271301269531, "teacher_distance_mean": 0.8622426629066468, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.005514457961544395, "weighted_relation_loss": 0.005514457961544395 }, { "action_query_batch_std": 16.295226097106934, "action_query_norm": 719.6457885742187, "action_relation_loss": 0.0054033083841204645, "auxiliary_loss_weight": 1.0, "epoch": 7.343311506080449, "flow_matching_loss": 0.04549585059285164, "grad_norm": 0.11566641926765442, "invalid_tail_samples": 24.2, "learning_rate": 8.824666172778964e-05, "loss": 0.0509, "positive_teacher_pairs": 26765.9, "relation_loss": 0.0054033083841204645, "selected_pairs": 26765.9, "step": 7850, "student_distance_mean": 921.895361328125, "teacher_distance_mean": 0.8551561117172242, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0054033083841204645, "weighted_relation_loss": 0.0054033083841204645 }, { "action_query_batch_std": 16.28211841583252, "action_query_norm": 720.8307434082031, "action_relation_loss": 0.005387789383530617, "auxiliary_loss_weight": 1.0, "epoch": 7.35266604303087, "flow_matching_loss": 0.04845552705228329, "grad_norm": 0.14165036380290985, "invalid_tail_samples": 23.8, "learning_rate": 8.821113797352245e-05, "loss": 0.0538, "positive_teacher_pairs": 26852.2, "relation_loss": 0.005387789383530617, "selected_pairs": 26852.2, "step": 7860, "student_distance_mean": 925.3852355957031, "teacher_distance_mean": 0.8552723348140716, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.005387789383530617, "weighted_relation_loss": 0.005387789383530617 }, { "action_query_batch_std": 16.409058570861816, "action_query_norm": 728.3394165039062, "action_relation_loss": 0.005424145050346852, "auxiliary_loss_weight": 1.0, "epoch": 7.362020579981291, "flow_matching_loss": 0.04543875940144062, "grad_norm": 0.13803035020828247, "invalid_tail_samples": 24.6, "learning_rate": 8.817556778911956e-05, "loss": 0.0509, "positive_teacher_pairs": 26671.0, "relation_loss": 0.005424145050346852, "selected_pairs": 26671.0, "step": 7870, "student_distance_mean": 932.5357177734375, "teacher_distance_mean": 0.8564915597438812, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.005424145050346852, "weighted_relation_loss": 0.005424145050346852 }, { "action_query_batch_std": 16.12525815963745, "action_query_norm": 718.5637390136719, "action_relation_loss": 0.005436146818101406, "auxiliary_loss_weight": 1.0, "epoch": 7.371375116931712, "flow_matching_loss": 0.044231648370623586, "grad_norm": 0.13017749786376953, "invalid_tail_samples": 24.2, "learning_rate": 8.81399512178021e-05, "loss": 0.0497, "positive_teacher_pairs": 26755.8, "relation_loss": 0.005436146818101406, "selected_pairs": 26755.8, "step": 7880, "student_distance_mean": 915.0620361328125, "teacher_distance_mean": 0.8499222218990325, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.005436146818101406, "weighted_relation_loss": 0.005436146818101406 }, { "action_query_batch_std": 16.27144145965576, "action_query_norm": 725.0132507324219, "action_relation_loss": 0.005248853052034974, "auxiliary_loss_weight": 1.0, "epoch": 7.380729653882133, "flow_matching_loss": 0.04533675909042358, "grad_norm": 0.11730188876390457, "invalid_tail_samples": 25.3, "learning_rate": 8.810428830284752e-05, "loss": 0.0506, "positive_teacher_pairs": 26500.4, "relation_loss": 0.005248853052034974, "selected_pairs": 26500.4, "step": 7890, "student_distance_mean": 923.8811279296875, "teacher_distance_mean": 0.8555309116840363, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.005248853052034974, "weighted_relation_loss": 0.005248853052034974 }, { "action_query_batch_std": 16.381307792663574, "action_query_norm": 723.807763671875, "action_relation_loss": 0.00524298083037138, "auxiliary_loss_weight": 1.0, "epoch": 7.390084190832554, "flow_matching_loss": 0.046788685768842694, "grad_norm": 0.13461987674236298, "invalid_tail_samples": 25.2, "learning_rate": 8.806857908758967e-05, "loss": 0.052, "positive_teacher_pairs": 26536.6, "relation_loss": 0.00524298083037138, "selected_pairs": 26536.6, "step": 7900, "student_distance_mean": 923.5811401367188, "teacher_distance_mean": 0.8517780601978302, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.00524298083037138, "weighted_relation_loss": 0.00524298083037138 }, { "action_query_batch_std": 16.177599048614503, "action_query_norm": 716.5176086425781, "action_relation_loss": 0.005401681922376156, "auxiliary_loss_weight": 1.0, "epoch": 7.399438727782975, "flow_matching_loss": 0.046488191559910776, "grad_norm": 0.1879006177186966, "invalid_tail_samples": 25.1, "learning_rate": 8.80328236154186e-05, "loss": 0.0519, "positive_teacher_pairs": 26556.1, "relation_loss": 0.005401681922376156, "selected_pairs": 26556.1, "step": 7910, "student_distance_mean": 918.8931640625, "teacher_distance_mean": 0.8528826892375946, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.005401681922376156, "weighted_relation_loss": 0.005401681922376156 }, { "action_query_batch_std": 16.426272106170654, "action_query_norm": 722.0412414550781, "action_relation_loss": 0.005328271584585309, "auxiliary_loss_weight": 1.0, "epoch": 7.408793264733395, "flow_matching_loss": 0.04582333900034428, "grad_norm": 0.15712837874889374, "invalid_tail_samples": 27.6, "learning_rate": 8.799702192978056e-05, "loss": 0.0512, "positive_teacher_pairs": 25996.9, "relation_loss": 0.005328271584585309, "selected_pairs": 25996.9, "step": 7920, "student_distance_mean": 929.8707824707031, "teacher_distance_mean": 0.8616521954536438, "valid_action_samples": 228.4, "weighted_auxiliary_loss": 0.005328271584585309, "weighted_relation_loss": 0.005328271584585309 }, { "action_query_batch_std": 16.42170810699463, "action_query_norm": 725.1541687011719, "action_relation_loss": 0.00557599700987339, "auxiliary_loss_weight": 1.0, "epoch": 7.4181478016838165, "flow_matching_loss": 0.046571682393550876, "grad_norm": 0.1667155772447586, "invalid_tail_samples": 24.4, "learning_rate": 8.7961174074178e-05, "loss": 0.0521, "positive_teacher_pairs": 26708.8, "relation_loss": 0.00557599700987339, "selected_pairs": 26708.8, "step": 7930, "student_distance_mean": 932.7666931152344, "teacher_distance_mean": 0.847359162569046, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.00557599700987339, "weighted_relation_loss": 0.00557599700987339 }, { "action_query_batch_std": 16.49753360748291, "action_query_norm": 727.4067016601563, "action_relation_loss": 0.005477449530735612, "auxiliary_loss_weight": 1.0, "epoch": 7.427502338634238, "flow_matching_loss": 0.04505783617496491, "grad_norm": 0.1613714098930359, "invalid_tail_samples": 24.3, "learning_rate": 8.792528009216942e-05, "loss": 0.0505, "positive_teacher_pairs": 26739.5, "relation_loss": 0.005477449530735612, "selected_pairs": 26739.5, "step": 7940, "student_distance_mean": 927.7586059570312, "teacher_distance_mean": 0.8463572025299072, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.005477449530735612, "weighted_relation_loss": 0.005477449530735612 }, { "action_query_batch_std": 16.531125640869142, "action_query_norm": 729.7266540527344, "action_relation_loss": 0.005401167133823037, "auxiliary_loss_weight": 1.0, "epoch": 7.436856875584659, "flow_matching_loss": 0.04763152115046978, "grad_norm": 0.13421936333179474, "invalid_tail_samples": 24.6, "learning_rate": 8.788934002736943e-05, "loss": 0.053, "positive_teacher_pairs": 26670.3, "relation_loss": 0.005401167133823037, "selected_pairs": 26670.3, "step": 7950, "student_distance_mean": 942.8285949707031, "teacher_distance_mean": 0.8533509850502015, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.005401167133823037, "weighted_relation_loss": 0.005401167133823037 }, { "action_query_batch_std": 16.562927722930908, "action_query_norm": 731.7582275390625, "action_relation_loss": 0.005607564281672239, "auxiliary_loss_weight": 1.0, "epoch": 7.44621141253508, "flow_matching_loss": 0.046969543769955636, "grad_norm": 0.10724177211523056, "invalid_tail_samples": 24.7, "learning_rate": 8.785335392344857e-05, "loss": 0.0526, "positive_teacher_pairs": 26644.4, "relation_loss": 0.005607564281672239, "selected_pairs": 26644.4, "step": 7960, "student_distance_mean": 935.372607421875, "teacher_distance_mean": 0.8493892967700958, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.005607564281672239, "weighted_relation_loss": 0.005607564281672239 }, { "action_query_batch_std": 16.423282623291016, "action_query_norm": 725.5821472167969, "action_relation_loss": 0.005415617162361741, "auxiliary_loss_weight": 1.0, "epoch": 7.4555659494855, "flow_matching_loss": 0.04905649498105049, "grad_norm": 0.11838765442371368, "invalid_tail_samples": 24.1, "learning_rate": 8.781732182413336e-05, "loss": 0.0545, "positive_teacher_pairs": 26787.1, "relation_loss": 0.005415617162361741, "selected_pairs": 26787.1, "step": 7970, "student_distance_mean": 932.1777099609375, "teacher_distance_mean": 0.846110999584198, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.005415617162361741, "weighted_relation_loss": 0.005415617162361741 }, { "action_query_batch_std": 16.614697456359863, "action_query_norm": 729.5420776367188, "action_relation_loss": 0.0053839405532926324, "auxiliary_loss_weight": 1.0, "epoch": 7.464920486435921, "flow_matching_loss": 0.04725270792841911, "grad_norm": 0.12332189083099365, "invalid_tail_samples": 26.3, "learning_rate": 8.778124377320618e-05, "loss": 0.0526, "positive_teacher_pairs": 26275.4, "relation_loss": 0.0053839405532926324, "selected_pairs": 26275.4, "step": 7980, "student_distance_mean": 941.2050659179688, "teacher_distance_mean": 0.8540644109249115, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.0053839405532926324, "weighted_relation_loss": 0.0053839405532926324 }, { "action_query_batch_std": 16.62329444885254, "action_query_norm": 731.0427001953125, "action_relation_loss": 0.00540848933160305, "auxiliary_loss_weight": 1.0, "epoch": 7.474275023386342, "flow_matching_loss": 0.04645646773278713, "grad_norm": 0.11873414367437363, "invalid_tail_samples": 23.2, "learning_rate": 8.774511981450529e-05, "loss": 0.0519, "positive_teacher_pairs": 26989.2, "relation_loss": 0.00540848933160305, "selected_pairs": 26989.2, "step": 7990, "student_distance_mean": 939.7247680664062, "teacher_distance_mean": 0.8646834194660187, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.00540848933160305, "weighted_relation_loss": 0.00540848933160305 }, { "action_query_batch_std": 16.629626655578612, "action_query_norm": 732.7580688476562, "action_relation_loss": 0.005411132657900453, "auxiliary_loss_weight": 1.0, "epoch": 7.483629560336763, "flow_matching_loss": 0.0484673447906971, "grad_norm": 0.18298576772212982, "invalid_tail_samples": 24.3, "learning_rate": 8.770894999192467e-05, "loss": 0.0539, "positive_teacher_pairs": 26742.7, "relation_loss": 0.005411132657900453, "selected_pairs": 26742.7, "step": 8000, "student_distance_mean": 940.7631774902344, "teacher_distance_mean": 0.8639601111412049, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.005411132657900453, "weighted_relation_loss": 0.005411132657900453 }, { "action_query_batch_std": 16.791886711120604, "action_query_norm": 739.1837951660157, "action_relation_loss": 0.005132722342386842, "auxiliary_loss_weight": 1.0, "epoch": 7.492984097287184, "flow_matching_loss": 0.04597201459109783, "grad_norm": 0.14655523002147675, "invalid_tail_samples": 23.3, "learning_rate": 8.767273434941412e-05, "loss": 0.0511, "positive_teacher_pairs": 26966.4, "relation_loss": 0.005132722342386842, "selected_pairs": 26966.4, "step": 8010, "student_distance_mean": 946.2934143066407, "teacher_distance_mean": 0.8618746221065521, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.005132722342386842, "weighted_relation_loss": 0.005132722342386842 }, { "action_query_batch_std": 16.42947635650635, "action_query_norm": 726.509326171875, "action_relation_loss": 0.005238106288015842, "auxiliary_loss_weight": 1.0, "epoch": 7.5023386342376055, "flow_matching_loss": 0.04830494560301304, "grad_norm": 0.13349388539791107, "invalid_tail_samples": 24.3, "learning_rate": 8.7636472930979e-05, "loss": 0.0535, "positive_teacher_pairs": 26736.2, "relation_loss": 0.005238106288015842, "selected_pairs": 26736.2, "step": 8020, "student_distance_mean": 931.7741333007813, "teacher_distance_mean": 0.8548044621944427, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.005238106288015842, "weighted_relation_loss": 0.005238106288015842 }, { "action_query_batch_std": 16.674184226989745, "action_query_norm": 737.2209655761719, "action_relation_loss": 0.005147731071338058, "auxiliary_loss_weight": 1.0, "epoch": 7.511693171188027, "flow_matching_loss": 0.04574839361011982, "grad_norm": 0.13155296444892883, "invalid_tail_samples": 22.8, "learning_rate": 8.76001657806804e-05, "loss": 0.0509, "positive_teacher_pairs": 27082.3, "relation_loss": 0.005147731071338058, "selected_pairs": 27082.3, "step": 8030, "student_distance_mean": 950.4034240722656, "teacher_distance_mean": 0.8633624374866485, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.005147731071338058, "weighted_relation_loss": 0.005147731071338058 }, { "action_query_batch_std": 16.418051528930665, "action_query_norm": 727.1099792480469, "action_relation_loss": 0.005447738105431199, "auxiliary_loss_weight": 1.0, "epoch": 7.521047708138447, "flow_matching_loss": 0.04757486283779144, "grad_norm": 0.17063264548778534, "invalid_tail_samples": 24.9, "learning_rate": 8.756381294263491e-05, "loss": 0.053, "positive_teacher_pairs": 26593.9, "relation_loss": 0.005447738105431199, "selected_pairs": 26593.9, "step": 8040, "student_distance_mean": 927.5401428222656, "teacher_distance_mean": 0.8498658299446106, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.005447738105431199, "weighted_relation_loss": 0.005447738105431199 }, { "action_query_batch_std": 16.586568927764894, "action_query_norm": 732.3350158691406, "action_relation_loss": 0.005465623829513789, "auxiliary_loss_weight": 1.0, "epoch": 7.530402245088868, "flow_matching_loss": 0.04570657201111317, "grad_norm": 0.16964203119277954, "invalid_tail_samples": 23.2, "learning_rate": 8.752741446101464e-05, "loss": 0.0512, "positive_teacher_pairs": 26991.3, "relation_loss": 0.005465623829513789, "selected_pairs": 26991.3, "step": 8050, "student_distance_mean": 940.1717346191406, "teacher_distance_mean": 0.8608804285526276, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.005465623829513789, "weighted_relation_loss": 0.005465623829513789 }, { "action_query_batch_std": 16.515484428405763, "action_query_norm": 729.4392272949219, "action_relation_loss": 0.005379883758723736, "auxiliary_loss_weight": 1.0, "epoch": 7.539756782039289, "flow_matching_loss": 0.04581409767270088, "grad_norm": 0.19714902341365814, "invalid_tail_samples": 21.2, "learning_rate": 8.749097038004722e-05, "loss": 0.0512, "positive_teacher_pairs": 27456.2, "relation_loss": 0.005379883758723736, "selected_pairs": 27456.2, "step": 8060, "student_distance_mean": 939.0197204589844, "teacher_distance_mean": 0.8588360607624054, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.005379883758723736, "weighted_relation_loss": 0.005379883758723736 }, { "action_query_batch_std": 16.449244499206543, "action_query_norm": 723.8856750488281, "action_relation_loss": 0.005375744914636016, "auxiliary_loss_weight": 1.0, "epoch": 7.54911131898971, "flow_matching_loss": 0.046541770175099376, "grad_norm": 0.15692248940467834, "invalid_tail_samples": 24.0, "learning_rate": 8.745448074401561e-05, "loss": 0.0519, "positive_teacher_pairs": 26803.1, "relation_loss": 0.005375744914636016, "selected_pairs": 26803.1, "step": 8070, "student_distance_mean": 931.4992736816406, "teacher_distance_mean": 0.8577327787876129, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.005375744914636016, "weighted_relation_loss": 0.005375744914636016 }, { "action_query_batch_std": 16.565133476257323, "action_query_norm": 733.5111938476563, "action_relation_loss": 0.005542598944157362, "auxiliary_loss_weight": 1.0, "epoch": 7.558465855940131, "flow_matching_loss": 0.048045893758535387, "grad_norm": 0.21530380845069885, "invalid_tail_samples": 20.4, "learning_rate": 8.741794559725818e-05, "loss": 0.0536, "positive_teacher_pairs": 27639.3, "relation_loss": 0.005542598944157362, "selected_pairs": 27639.3, "step": 8080, "student_distance_mean": 939.5259094238281, "teacher_distance_mean": 0.8565585970878601, "valid_action_samples": 235.6, "weighted_auxiliary_loss": 0.005542598944157362, "weighted_relation_loss": 0.005542598944157362 }, { "action_query_batch_std": 16.64531774520874, "action_query_norm": 735.4750549316407, "action_relation_loss": 0.005534841911867261, "auxiliary_loss_weight": 1.0, "epoch": 7.567820392890552, "flow_matching_loss": 0.04768618606030941, "grad_norm": 0.133526012301445, "invalid_tail_samples": 25.7, "learning_rate": 8.738136498416856e-05, "loss": 0.0532, "positive_teacher_pairs": 26410.0, "relation_loss": 0.005534841911867261, "selected_pairs": 26410.0, "step": 8090, "student_distance_mean": 945.6570190429687, "teacher_distance_mean": 0.8579094707965851, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.005534841911867261, "weighted_relation_loss": 0.005534841911867261 }, { "action_query_batch_std": 16.523125648498535, "action_query_norm": 734.1549438476562, "action_relation_loss": 0.00550930043682456, "auxiliary_loss_weight": 1.0, "epoch": 7.5771749298409725, "flow_matching_loss": 0.04718304350972176, "grad_norm": 0.13653115928173065, "invalid_tail_samples": 21.6, "learning_rate": 8.734473894919564e-05, "loss": 0.0527, "positive_teacher_pairs": 27361.5, "relation_loss": 0.00550930043682456, "selected_pairs": 27361.5, "step": 8100, "student_distance_mean": 936.4874084472656, "teacher_distance_mean": 0.8503364622592926, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.00550930043682456, "weighted_relation_loss": 0.00550930043682456 }, { "action_query_batch_std": 16.191379165649415, "action_query_norm": 720.6721374511719, "action_relation_loss": 0.005494385492056608, "auxiliary_loss_weight": 1.0, "epoch": 7.586529466791394, "flow_matching_loss": 0.04671397656202316, "grad_norm": 0.14038118720054626, "invalid_tail_samples": 26.5, "learning_rate": 8.730806753684353e-05, "loss": 0.0522, "positive_teacher_pairs": 26233.7, "relation_loss": 0.005494385492056608, "selected_pairs": 26233.7, "step": 8110, "student_distance_mean": 916.0793762207031, "teacher_distance_mean": 0.842658269405365, "valid_action_samples": 229.5, "weighted_auxiliary_loss": 0.005494385492056608, "weighted_relation_loss": 0.005494385492056608 }, { "action_query_batch_std": 16.538161277770996, "action_query_norm": 729.1035461425781, "action_relation_loss": 0.00545733654871583, "auxiliary_loss_weight": 1.0, "epoch": 7.595884003741815, "flow_matching_loss": 0.047405258566141126, "grad_norm": 0.17429205775260925, "invalid_tail_samples": 24.9, "learning_rate": 8.727135079167144e-05, "loss": 0.0529, "positive_teacher_pairs": 26593.6, "relation_loss": 0.00545733654871583, "selected_pairs": 26593.6, "step": 8120, "student_distance_mean": 940.5585266113281, "teacher_distance_mean": 0.8521535515785217, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.00545733654871583, "weighted_relation_loss": 0.00545733654871583 }, { "action_query_batch_std": 16.39745101928711, "action_query_norm": 726.7526000976562, "action_relation_loss": 0.005424212291836738, "auxiliary_loss_weight": 1.0, "epoch": 7.605238540692236, "flow_matching_loss": 0.04666593447327614, "grad_norm": 0.15911704301834106, "invalid_tail_samples": 21.8, "learning_rate": 8.723458875829368e-05, "loss": 0.0521, "positive_teacher_pairs": 27317.2, "relation_loss": 0.005424212291836738, "selected_pairs": 27317.2, "step": 8130, "student_distance_mean": 927.7567504882812, "teacher_distance_mean": 0.8486208081245422, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.005424212291836738, "weighted_relation_loss": 0.005424212291836738 }, { "action_query_batch_std": 16.655188179016115, "action_query_norm": 732.7173767089844, "action_relation_loss": 0.005734437797218561, "auxiliary_loss_weight": 1.0, "epoch": 7.614593077642657, "flow_matching_loss": 0.04827841930091381, "grad_norm": 0.13339748978614807, "invalid_tail_samples": 22.2, "learning_rate": 8.719778148137958e-05, "loss": 0.054, "positive_teacher_pairs": 27218.6, "relation_loss": 0.005734437797218561, "selected_pairs": 27218.6, "step": 8140, "student_distance_mean": 939.9838073730468, "teacher_distance_mean": 0.853823858499527, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.005734437797218561, "weighted_relation_loss": 0.005734437797218561 }, { "action_query_batch_std": 16.7114688873291, "action_query_norm": 740.9590393066406, "action_relation_loss": 0.0052781881298869845, "auxiliary_loss_weight": 1.0, "epoch": 7.623947614593078, "flow_matching_loss": 0.048316273093223575, "grad_norm": 0.1374814212322235, "invalid_tail_samples": 21.7, "learning_rate": 8.716092900565346e-05, "loss": 0.0536, "positive_teacher_pairs": 27339.6, "relation_loss": 0.0052781881298869845, "selected_pairs": 27339.6, "step": 8150, "student_distance_mean": 946.3029846191406, "teacher_distance_mean": 0.8594342589378356, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.0052781881298869845, "weighted_relation_loss": 0.0052781881298869845 }, { "action_query_batch_std": 16.406660270690917, "action_query_norm": 729.0314453125, "action_relation_loss": 0.005569852888584137, "auxiliary_loss_weight": 1.0, "epoch": 7.633302151543498, "flow_matching_loss": 0.04752497933804989, "grad_norm": 0.1487458199262619, "invalid_tail_samples": 25.6, "learning_rate": 8.712403137589456e-05, "loss": 0.0531, "positive_teacher_pairs": 26443.3, "relation_loss": 0.005569852888584137, "selected_pairs": 26443.3, "step": 8160, "student_distance_mean": 930.92412109375, "teacher_distance_mean": 0.8440684735774994, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.005569852888584137, "weighted_relation_loss": 0.005569852888584137 }, { "action_query_batch_std": 16.46474380493164, "action_query_norm": 729.3068176269531, "action_relation_loss": 0.005359953548759222, "auxiliary_loss_weight": 1.0, "epoch": 7.642656688493919, "flow_matching_loss": 0.04329416751861572, "grad_norm": 0.10256396979093552, "invalid_tail_samples": 24.9, "learning_rate": 8.708708863693697e-05, "loss": 0.0487, "positive_teacher_pairs": 26592.6, "relation_loss": 0.005359953548759222, "selected_pairs": 26592.6, "step": 8170, "student_distance_mean": 934.1507629394531, "teacher_distance_mean": 0.8503333389759063, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.005359953548759222, "weighted_relation_loss": 0.005359953548759222 }, { "action_query_batch_std": 16.76603469848633, "action_query_norm": 742.7506164550781, "action_relation_loss": 0.00532580753788352, "auxiliary_loss_weight": 1.0, "epoch": 7.65201122544434, "flow_matching_loss": 0.04548853635787964, "grad_norm": 0.12013290077447891, "invalid_tail_samples": 24.8, "learning_rate": 8.70501008336696e-05, "loss": 0.0508, "positive_teacher_pairs": 26625.7, "relation_loss": 0.00532580753788352, "selected_pairs": 26625.7, "step": 8180, "student_distance_mean": 954.6119445800781, "teacher_distance_mean": 0.8682703733444214, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.00532580753788352, "weighted_relation_loss": 0.00532580753788352 }, { "action_query_batch_std": 16.679305648803712, "action_query_norm": 738.6167724609375, "action_relation_loss": 0.005621718754991889, "auxiliary_loss_weight": 1.0, "epoch": 7.6613657623947615, "flow_matching_loss": 0.0462061457335949, "grad_norm": 0.14735820889472961, "invalid_tail_samples": 24.5, "learning_rate": 8.701306801103611e-05, "loss": 0.0518, "positive_teacher_pairs": 26687.9, "relation_loss": 0.005621718754991889, "selected_pairs": 26687.9, "step": 8190, "student_distance_mean": 947.8472229003906, "teacher_distance_mean": 0.8569098889827729, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.005621718754991889, "weighted_relation_loss": 0.005621718754991889 }, { "action_query_batch_std": 16.628334999084473, "action_query_norm": 737.6615539550781, "action_relation_loss": 0.005275617307052016, "auxiliary_loss_weight": 1.0, "epoch": 7.670720299345183, "flow_matching_loss": 0.04907307475805282, "grad_norm": 0.14030222594738007, "invalid_tail_samples": 24.2, "learning_rate": 8.697599021403489e-05, "loss": 0.0543, "positive_teacher_pairs": 26757.4, "relation_loss": 0.005275617307052016, "selected_pairs": 26757.4, "step": 8200, "student_distance_mean": 942.4003112792968, "teacher_distance_mean": 0.8611616313457489, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.005275617307052016, "weighted_relation_loss": 0.005275617307052016 }, { "action_query_batch_std": 16.409206295013426, "action_query_norm": 729.7170349121094, "action_relation_loss": 0.005516924848780036, "auxiliary_loss_weight": 1.0, "epoch": 7.680074836295604, "flow_matching_loss": 0.047413647547364234, "grad_norm": 0.15531478822231293, "invalid_tail_samples": 23.8, "learning_rate": 8.693886748771896e-05, "loss": 0.0529, "positive_teacher_pairs": 26844.6, "relation_loss": 0.005516924848780036, "selected_pairs": 26844.6, "step": 8210, "student_distance_mean": 934.5146911621093, "teacher_distance_mean": 0.84745472073555, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.005516924848780036, "weighted_relation_loss": 0.005516924848780036 }, { "action_query_batch_std": 16.603263473510744, "action_query_norm": 737.2647766113281, "action_relation_loss": 0.005406727362424135, "auxiliary_loss_weight": 1.0, "epoch": 7.689429373246024, "flow_matching_loss": 0.0449026208370924, "grad_norm": 0.16615237295627594, "invalid_tail_samples": 24.5, "learning_rate": 8.690169987719593e-05, "loss": 0.0503, "positive_teacher_pairs": 26694.2, "relation_loss": 0.005406727362424135, "selected_pairs": 26694.2, "step": 8220, "student_distance_mean": 944.2526611328125, "teacher_distance_mean": 0.8469603776931762, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.005406727362424135, "weighted_relation_loss": 0.005406727362424135 }, { "action_query_batch_std": 16.73046245574951, "action_query_norm": 739.3903137207031, "action_relation_loss": 0.005578708741813898, "auxiliary_loss_weight": 1.0, "epoch": 7.698783910196445, "flow_matching_loss": 0.04922771565616131, "grad_norm": 0.16325035691261292, "invalid_tail_samples": 21.4, "learning_rate": 8.686448742762791e-05, "loss": 0.0548, "positive_teacher_pairs": 27404.6, "relation_loss": 0.005578708741813898, "selected_pairs": 27404.6, "step": 8230, "student_distance_mean": 946.8957336425781, "teacher_distance_mean": 0.8488977253437042, "valid_action_samples": 234.6, "weighted_auxiliary_loss": 0.005578708741813898, "weighted_relation_loss": 0.005578708741813898 }, { "action_query_batch_std": 16.67452449798584, "action_query_norm": 736.3720397949219, "action_relation_loss": 0.005433280533179641, "auxiliary_loss_weight": 1.0, "epoch": 7.708138447146866, "flow_matching_loss": 0.04556424506008625, "grad_norm": 0.1199025884270668, "invalid_tail_samples": 24.9, "learning_rate": 8.682723018423161e-05, "loss": 0.051, "positive_teacher_pairs": 26593.1, "relation_loss": 0.005433280533179641, "selected_pairs": 26593.1, "step": 8240, "student_distance_mean": 946.5189086914063, "teacher_distance_mean": 0.8615715384483338, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.005433280533179641, "weighted_relation_loss": 0.005433280533179641 }, { "action_query_batch_std": 16.964437103271486, "action_query_norm": 747.2432861328125, "action_relation_loss": 0.005291854543611407, "auxiliary_loss_weight": 1.0, "epoch": 7.717492984097287, "flow_matching_loss": 0.04538375660777092, "grad_norm": 0.144832044839859, "invalid_tail_samples": 23.8, "learning_rate": 8.678992819227804e-05, "loss": 0.0507, "positive_teacher_pairs": 26852.4, "relation_loss": 0.005291854543611407, "selected_pairs": 26852.4, "step": 8250, "student_distance_mean": 966.1373046875, "teacher_distance_mean": 0.8652250468730927, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.005291854543611407, "weighted_relation_loss": 0.005291854543611407 }, { "action_query_batch_std": 16.893624687194823, "action_query_norm": 748.5912902832031, "action_relation_loss": 0.005364300590008498, "auxiliary_loss_weight": 1.0, "epoch": 7.726847521047708, "flow_matching_loss": 0.04494207948446274, "grad_norm": 0.13974131643772125, "invalid_tail_samples": 24.6, "learning_rate": 8.675258149709265e-05, "loss": 0.0503, "positive_teacher_pairs": 26673.4, "relation_loss": 0.005364300590008498, "selected_pairs": 26673.4, "step": 8260, "student_distance_mean": 955.265771484375, "teacher_distance_mean": 0.849784541130066, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.005364300590008498, "weighted_relation_loss": 0.005364300590008498 }, { "action_query_batch_std": 16.819524192810057, "action_query_norm": 740.8507934570313, "action_relation_loss": 0.0050459417514503, "auxiliary_loss_weight": 1.0, "epoch": 7.736202057998129, "flow_matching_loss": 0.04366727620363235, "grad_norm": 0.16278775036334991, "invalid_tail_samples": 24.8, "learning_rate": 8.67151901440552e-05, "loss": 0.0487, "positive_teacher_pairs": 26626.7, "relation_loss": 0.0050459417514503, "selected_pairs": 26626.7, "step": 8270, "student_distance_mean": 954.8569946289062, "teacher_distance_mean": 0.8546716570854187, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0050459417514503, "weighted_relation_loss": 0.0050459417514503 }, { "action_query_batch_std": 16.65582847595215, "action_query_norm": 740.1072692871094, "action_relation_loss": 0.005495285708457231, "auxiliary_loss_weight": 1.0, "epoch": 7.74555659494855, "flow_matching_loss": 0.04561851248145103, "grad_norm": 0.11727631837129593, "invalid_tail_samples": 22.0, "learning_rate": 8.667775417859971e-05, "loss": 0.0511, "positive_teacher_pairs": 27274.3, "relation_loss": 0.005495285708457231, "selected_pairs": 27274.3, "step": 8280, "student_distance_mean": 949.5896423339843, "teacher_distance_mean": 0.8463737189769744, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.005495285708457231, "weighted_relation_loss": 0.005495285708457231 }, { "action_query_batch_std": 16.81796760559082, "action_query_norm": 744.170556640625, "action_relation_loss": 0.005491125537082553, "auxiliary_loss_weight": 1.0, "epoch": 7.754911131898971, "flow_matching_loss": 0.044295217096805575, "grad_norm": 0.14155226945877075, "invalid_tail_samples": 22.4, "learning_rate": 8.664027364621441e-05, "loss": 0.0498, "positive_teacher_pairs": 27181.9, "relation_loss": 0.005491125537082553, "selected_pairs": 27181.9, "step": 8290, "student_distance_mean": 947.1740234375, "teacher_distance_mean": 0.8445720732212066, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.005491125537082553, "weighted_relation_loss": 0.005491125537082553 }, { "action_query_batch_std": 16.75036277770996, "action_query_norm": 741.2319152832031, "action_relation_loss": 0.0052072600927203895, "auxiliary_loss_weight": 1.0, "epoch": 7.764265668849392, "flow_matching_loss": 0.04419127628207207, "grad_norm": 0.13342785835266113, "invalid_tail_samples": 21.4, "learning_rate": 8.660274859244168e-05, "loss": 0.0494, "positive_teacher_pairs": 27406.4, "relation_loss": 0.0052072600927203895, "selected_pairs": 27406.4, "step": 8300, "student_distance_mean": 948.1627624511718, "teacher_distance_mean": 0.8584744453430175, "valid_action_samples": 234.6, "weighted_auxiliary_loss": 0.0052072600927203895, "weighted_relation_loss": 0.0052072600927203895 }, { "action_query_batch_std": 16.712427711486818, "action_query_norm": 739.0756713867188, "action_relation_loss": 0.0053904599510133265, "auxiliary_loss_weight": 1.0, "epoch": 7.773620205799813, "flow_matching_loss": 0.04608294181525707, "grad_norm": 0.12064145505428314, "invalid_tail_samples": 22.8, "learning_rate": 8.656517906287799e-05, "loss": 0.0515, "positive_teacher_pairs": 27082.1, "relation_loss": 0.0053904599510133265, "selected_pairs": 27082.1, "step": 8310, "student_distance_mean": 948.2851257324219, "teacher_distance_mean": 0.8580892503261566, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0053904599510133265, "weighted_relation_loss": 0.0053904599510133265 }, { "action_query_batch_std": 16.69668197631836, "action_query_norm": 738.2128540039063, "action_relation_loss": 0.00535978926345706, "auxiliary_loss_weight": 1.0, "epoch": 7.782974742750234, "flow_matching_loss": 0.04787891209125519, "grad_norm": 0.1352890431880951, "invalid_tail_samples": 22.4, "learning_rate": 8.652756510317387e-05, "loss": 0.0532, "positive_teacher_pairs": 27179.3, "relation_loss": 0.00535978926345706, "selected_pairs": 27179.3, "step": 8320, "student_distance_mean": 947.3011840820312, "teacher_distance_mean": 0.854671961069107, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.00535978926345706, "weighted_relation_loss": 0.00535978926345706 }, { "action_query_batch_std": 16.773043632507324, "action_query_norm": 736.1261657714844, "action_relation_loss": 0.005593094695359469, "auxiliary_loss_weight": 1.0, "epoch": 7.792329279700655, "flow_matching_loss": 0.04527671746909619, "grad_norm": 0.1166524812579155, "invalid_tail_samples": 23.1, "learning_rate": 8.648990675903382e-05, "loss": 0.0509, "positive_teacher_pairs": 27013.8, "relation_loss": 0.005593094695359469, "selected_pairs": 27013.8, "step": 8330, "student_distance_mean": 953.0239868164062, "teacher_distance_mean": 0.855246502161026, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.005593094695359469, "weighted_relation_loss": 0.005593094695359469 }, { "action_query_batch_std": 16.726821899414062, "action_query_norm": 738.8860900878906, "action_relation_loss": 0.005533247627317906, "auxiliary_loss_weight": 1.0, "epoch": 7.801683816651076, "flow_matching_loss": 0.04604523405432701, "grad_norm": 0.10749127715826035, "invalid_tail_samples": 22.4, "learning_rate": 8.64522040762163e-05, "loss": 0.0516, "positive_teacher_pairs": 27175.6, "relation_loss": 0.005533247627317906, "selected_pairs": 27175.6, "step": 8340, "student_distance_mean": 950.8896789550781, "teacher_distance_mean": 0.8550694584846497, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.005533247627317906, "weighted_relation_loss": 0.005533247627317906 }, { "action_query_batch_std": 16.785853767395018, "action_query_norm": 740.4933471679688, "action_relation_loss": 0.005346526112407446, "auxiliary_loss_weight": 1.0, "epoch": 7.8110383536014965, "flow_matching_loss": 0.04443488419055939, "grad_norm": 0.11526905000209808, "invalid_tail_samples": 25.4, "learning_rate": 8.64144571005336e-05, "loss": 0.0498, "positive_teacher_pairs": 26490.7, "relation_loss": 0.005346526112407446, "selected_pairs": 26490.7, "step": 8350, "student_distance_mean": 954.1498901367188, "teacher_distance_mean": 0.8580354869365692, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.005346526112407446, "weighted_relation_loss": 0.005346526112407446 }, { "action_query_batch_std": 16.737857246398924, "action_query_norm": 740.4175415039062, "action_relation_loss": 0.005459546111524105, "auxiliary_loss_weight": 1.0, "epoch": 7.8203928905519176, "flow_matching_loss": 0.044926516711711884, "grad_norm": 0.15155728161334991, "invalid_tail_samples": 25.3, "learning_rate": 8.637666587785184e-05, "loss": 0.0504, "positive_teacher_pairs": 26507.8, "relation_loss": 0.005459546111524105, "selected_pairs": 26507.8, "step": 8360, "student_distance_mean": 946.0385681152344, "teacher_distance_mean": 0.8529709875583649, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.005459546111524105, "weighted_relation_loss": 0.005459546111524105 }, { "action_query_batch_std": 16.88788471221924, "action_query_norm": 745.6711364746094, "action_relation_loss": 0.005276148067787289, "auxiliary_loss_weight": 1.0, "epoch": 7.829747427502339, "flow_matching_loss": 0.0482550285756588, "grad_norm": 0.14991572499275208, "invalid_tail_samples": 23.7, "learning_rate": 8.633883045409096e-05, "loss": 0.0535, "positive_teacher_pairs": 26873.5, "relation_loss": 0.005276148067787289, "selected_pairs": 26873.5, "step": 8370, "student_distance_mean": 954.896484375, "teacher_distance_mean": 0.856433767080307, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.005276148067787289, "weighted_relation_loss": 0.005276148067787289 }, { "action_query_batch_std": 16.817395210266113, "action_query_norm": 746.6791198730468, "action_relation_loss": 0.0053247424308210615, "auxiliary_loss_weight": 1.0, "epoch": 7.83910196445276, "flow_matching_loss": 0.04612730257213116, "grad_norm": 0.15323442220687866, "invalid_tail_samples": 24.1, "learning_rate": 8.630095087522457e-05, "loss": 0.0515, "positive_teacher_pairs": 26778.5, "relation_loss": 0.0053247424308210615, "selected_pairs": 26778.5, "step": 8380, "student_distance_mean": 954.0696838378906, "teacher_distance_mean": 0.8558541357517242, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0053247424308210615, "weighted_relation_loss": 0.0053247424308210615 }, { "action_query_batch_std": 16.786865043640137, "action_query_norm": 741.0075317382813, "action_relation_loss": 0.005509715247899294, "auxiliary_loss_weight": 1.0, "epoch": 7.848456501403181, "flow_matching_loss": 0.04971557557582855, "grad_norm": 0.15355032682418823, "invalid_tail_samples": 26.4, "learning_rate": 8.62630271872799e-05, "loss": 0.0552, "positive_teacher_pairs": 26247.1, "relation_loss": 0.005509715247899294, "selected_pairs": 26247.1, "step": 8390, "student_distance_mean": 951.8791198730469, "teacher_distance_mean": 0.8562076389789581, "valid_action_samples": 229.6, "weighted_auxiliary_loss": 0.005509715247899294, "weighted_relation_loss": 0.005509715247899294 }, { "action_query_batch_std": 16.94209728240967, "action_query_norm": 752.1940795898438, "action_relation_loss": 0.005241656815633178, "auxiliary_loss_weight": 1.0, "epoch": 7.857811038353601, "flow_matching_loss": 0.04388220496475696, "grad_norm": 0.12414519488811493, "invalid_tail_samples": 23.4, "learning_rate": 8.62250594363378e-05, "loss": 0.0491, "positive_teacher_pairs": 26954.1, "relation_loss": 0.005241656815633178, "selected_pairs": 26954.1, "step": 8400, "student_distance_mean": 959.97431640625, "teacher_distance_mean": 0.8546788930892945, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.005241656815633178, "weighted_relation_loss": 0.005241656815633178 }, { "action_query_batch_std": 16.96373291015625, "action_query_norm": 749.2865356445312, "action_relation_loss": 0.005292778555303812, "auxiliary_loss_weight": 1.0, "epoch": 7.867165575304022, "flow_matching_loss": 0.044145699217915536, "grad_norm": 0.15837301313877106, "invalid_tail_samples": 25.6, "learning_rate": 8.61870476685327e-05, "loss": 0.0494, "positive_teacher_pairs": 26431.7, "relation_loss": 0.005292778555303812, "selected_pairs": 26431.7, "step": 8410, "student_distance_mean": 963.9391357421875, "teacher_distance_mean": 0.8629074573516846, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.005292778555303812, "weighted_relation_loss": 0.005292778555303812 }, { "action_query_batch_std": 17.222803688049318, "action_query_norm": 759.3048156738281, "action_relation_loss": 0.004858623491600156, "auxiliary_loss_weight": 1.0, "epoch": 7.876520112254443, "flow_matching_loss": 0.044616840034723285, "grad_norm": 0.15197905898094177, "invalid_tail_samples": 22.6, "learning_rate": 8.614899193005248e-05, "loss": 0.0495, "positive_teacher_pairs": 27131.2, "relation_loss": 0.004858623491600156, "selected_pairs": 27131.2, "step": 8420, "student_distance_mean": 978.1877136230469, "teacher_distance_mean": 0.8633869886398315, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.004858623491600156, "weighted_relation_loss": 0.004858623491600156 }, { "action_query_batch_std": 17.173352241516113, "action_query_norm": 757.9617248535156, "action_relation_loss": 0.004874786548316479, "auxiliary_loss_weight": 1.0, "epoch": 7.885874649204864, "flow_matching_loss": 0.04439086802303791, "grad_norm": 0.1302196979522705, "invalid_tail_samples": 22.8, "learning_rate": 8.611089226713842e-05, "loss": 0.0493, "positive_teacher_pairs": 27084.8, "relation_loss": 0.004874786548316479, "selected_pairs": 27084.8, "step": 8430, "student_distance_mean": 972.4677429199219, "teacher_distance_mean": 0.853873860836029, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.004874786548316479, "weighted_relation_loss": 0.004874786548316479 }, { "action_query_batch_std": 17.07433490753174, "action_query_norm": 756.5564880371094, "action_relation_loss": 0.005181383434683084, "auxiliary_loss_weight": 1.0, "epoch": 7.8952291861552855, "flow_matching_loss": 0.0440480750054121, "grad_norm": 0.14727391302585602, "invalid_tail_samples": 23.1, "learning_rate": 8.607274872608521e-05, "loss": 0.0492, "positive_teacher_pairs": 27010.7, "relation_loss": 0.005181383434683084, "selected_pairs": 27010.7, "step": 8440, "student_distance_mean": 968.1281311035157, "teacher_distance_mean": 0.8569356560707092, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.005181383434683084, "weighted_relation_loss": 0.005181383434683084 }, { "action_query_batch_std": 17.023608207702637, "action_query_norm": 755.0757751464844, "action_relation_loss": 0.005115512805059552, "auxiliary_loss_weight": 1.0, "epoch": 7.904583723105707, "flow_matching_loss": 0.045141595974564554, "grad_norm": 0.1503121554851532, "invalid_tail_samples": 24.0, "learning_rate": 8.603456135324088e-05, "loss": 0.0503, "positive_teacher_pairs": 26807.3, "relation_loss": 0.005115512805059552, "selected_pairs": 26807.3, "step": 8450, "student_distance_mean": 963.6920532226562, "teacher_distance_mean": 0.849487566947937, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.005115512805059552, "weighted_relation_loss": 0.005115512805059552 }, { "action_query_batch_std": 16.783379554748535, "action_query_norm": 745.6797058105469, "action_relation_loss": 0.005143982637673616, "auxiliary_loss_weight": 1.0, "epoch": 7.913938260056128, "flow_matching_loss": 0.04397228248417377, "grad_norm": 0.1311706304550171, "invalid_tail_samples": 25.1, "learning_rate": 8.599633019500665e-05, "loss": 0.0491, "positive_teacher_pairs": 26547.9, "relation_loss": 0.005143982637673616, "selected_pairs": 26547.9, "step": 8460, "student_distance_mean": 953.6616271972656, "teacher_distance_mean": 0.8437596499919892, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.005143982637673616, "weighted_relation_loss": 0.005143982637673616 }, { "action_query_batch_std": 16.75747146606445, "action_query_norm": 741.2063720703125, "action_relation_loss": 0.005045986874029041, "auxiliary_loss_weight": 1.0, "epoch": 7.923292797006548, "flow_matching_loss": 0.04540867544710636, "grad_norm": 0.16627094149589539, "invalid_tail_samples": 20.9, "learning_rate": 8.595805529783702e-05, "loss": 0.0505, "positive_teacher_pairs": 27523.1, "relation_loss": 0.005045986874029041, "selected_pairs": 27523.1, "step": 8470, "student_distance_mean": 951.2112365722656, "teacher_distance_mean": 0.8487771928310395, "valid_action_samples": 235.1, "weighted_auxiliary_loss": 0.005045986874029041, "weighted_relation_loss": 0.005045986874029041 }, { "action_query_batch_std": 16.79695701599121, "action_query_norm": 742.4126403808593, "action_relation_loss": 0.005065256915986538, "auxiliary_loss_weight": 1.0, "epoch": 7.932647333956969, "flow_matching_loss": 0.04668282940983772, "grad_norm": 0.18682847917079926, "invalid_tail_samples": 23.7, "learning_rate": 8.591973670823958e-05, "loss": 0.0517, "positive_teacher_pairs": 26875.1, "relation_loss": 0.005065256915986538, "selected_pairs": 26875.1, "step": 8480, "student_distance_mean": 953.6224365234375, "teacher_distance_mean": 0.8533796668052673, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.005065256915986538, "weighted_relation_loss": 0.005065256915986538 }, { "action_query_batch_std": 16.847380447387696, "action_query_norm": 742.9913879394531, "action_relation_loss": 0.005420351261273026, "auxiliary_loss_weight": 1.0, "epoch": 7.94200187090739, "flow_matching_loss": 0.04520824141800404, "grad_norm": 0.14236238598823547, "invalid_tail_samples": 22.0, "learning_rate": 8.588137447277503e-05, "loss": 0.0506, "positive_teacher_pairs": 27265.4, "relation_loss": 0.005420351261273026, "selected_pairs": 27265.4, "step": 8490, "student_distance_mean": 958.8899658203125, "teacher_distance_mean": 0.8520666539669037, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.005420351261273026, "weighted_relation_loss": 0.005420351261273026 }, { "action_query_batch_std": 17.09238166809082, "action_query_norm": 749.6967407226563, "action_relation_loss": 0.0053194141946733, "auxiliary_loss_weight": 1.0, "epoch": 7.951356407857811, "flow_matching_loss": 0.04647042006254196, "grad_norm": 0.1339569389820099, "invalid_tail_samples": 25.6, "learning_rate": 8.584296863805709e-05, "loss": 0.0518, "positive_teacher_pairs": 26437.1, "relation_loss": 0.0053194141946733, "selected_pairs": 26437.1, "step": 8500, "student_distance_mean": 973.8219543457031, "teacher_distance_mean": 0.8640937507152557, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.0053194141946733, "weighted_relation_loss": 0.0053194141946733 }, { "action_query_batch_std": 17.118500900268554, "action_query_norm": 750.8343322753906, "action_relation_loss": 0.005311863450333476, "auxiliary_loss_weight": 1.0, "epoch": 7.960710944808232, "flow_matching_loss": 0.044265981018543246, "grad_norm": 0.14252373576164246, "invalid_tail_samples": 22.3, "learning_rate": 8.580451925075248e-05, "loss": 0.0496, "positive_teacher_pairs": 27197.1, "relation_loss": 0.005311863450333476, "selected_pairs": 27197.1, "step": 8510, "student_distance_mean": 968.5837219238281, "teacher_distance_mean": 0.8637963175773621, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.005311863450333476, "weighted_relation_loss": 0.005311863450333476 }, { "action_query_batch_std": 16.864927101135255, "action_query_norm": 744.0404968261719, "action_relation_loss": 0.005191950825974345, "auxiliary_loss_weight": 1.0, "epoch": 7.9700654817586525, "flow_matching_loss": 0.04759134165942669, "grad_norm": 0.1579030454158783, "invalid_tail_samples": 24.1, "learning_rate": 8.576602635758085e-05, "loss": 0.0528, "positive_teacher_pairs": 26778.9, "relation_loss": 0.005191950825974345, "selected_pairs": 26778.9, "step": 8520, "student_distance_mean": 952.2849853515625, "teacher_distance_mean": 0.8484537422657012, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.005191950825974345, "weighted_relation_loss": 0.005191950825974345 }, { "action_query_batch_std": 17.022360610961915, "action_query_norm": 753.4866577148438, "action_relation_loss": 0.005074433935806155, "auxiliary_loss_weight": 1.0, "epoch": 7.979420018709074, "flow_matching_loss": 0.04607456736266613, "grad_norm": 0.14995262026786804, "invalid_tail_samples": 23.3, "learning_rate": 8.572749000531469e-05, "loss": 0.0511, "positive_teacher_pairs": 26967.7, "relation_loss": 0.005074433935806155, "selected_pairs": 26967.7, "step": 8530, "student_distance_mean": 964.0490539550781, "teacher_distance_mean": 0.8490293800830842, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.005074433935806155, "weighted_relation_loss": 0.005074433935806155 }, { "action_query_batch_std": 16.949991035461426, "action_query_norm": 752.08134765625, "action_relation_loss": 0.005182030983269215, "auxiliary_loss_weight": 1.0, "epoch": 7.988774555659495, "flow_matching_loss": 0.04410196840763092, "grad_norm": 0.14283280074596405, "invalid_tail_samples": 23.5, "learning_rate": 8.568891024077926e-05, "loss": 0.0493, "positive_teacher_pairs": 26921.0, "relation_loss": 0.005182030983269215, "selected_pairs": 26921.0, "step": 8540, "student_distance_mean": 964.3602172851563, "teacher_distance_mean": 0.8548388659954071, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.005182030983269215, "weighted_relation_loss": 0.005182030983269215 }, { "action_query_batch_std": 16.883115768432617, "action_query_norm": 745.1095153808594, "action_relation_loss": 0.004987817676737905, "auxiliary_loss_weight": 1.0, "epoch": 7.998129092609916, "flow_matching_loss": 0.044638052210211755, "grad_norm": 0.12907494604587555, "invalid_tail_samples": 21.6, "learning_rate": 8.565028711085265e-05, "loss": 0.0496, "positive_teacher_pairs": 27362.5, "relation_loss": 0.004987817676737905, "selected_pairs": 27362.5, "step": 8550, "student_distance_mean": 956.0714111328125, "teacher_distance_mean": 0.8515759885311127, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.004987817676737905, "weighted_relation_loss": 0.004987817676737905 }, { "action_query_batch_std": 16.921880531311036, "action_query_norm": 747.7758056640625, "action_relation_loss": 0.004841357935220003, "auxiliary_loss_weight": 1.0, "epoch": 8.007483629560337, "flow_matching_loss": 0.047036031261086464, "grad_norm": 0.11506932228803635, "invalid_tail_samples": 21.2, "learning_rate": 8.561162066246561e-05, "loss": 0.0519, "positive_teacher_pairs": 24460.0, "relation_loss": 0.004841357935220003, "selected_pairs": 24460.0, "step": 8560, "student_distance_mean": 958.6728149414063, "teacher_distance_mean": 0.8518855214118958, "valid_action_samples": 214.9, "weighted_auxiliary_loss": 0.004841357935220003, "weighted_relation_loss": 0.004841357935220003 }, { "action_query_batch_std": 16.941506576538085, "action_query_norm": 746.2757629394531, "action_relation_loss": 0.005460320878773928, "auxiliary_loss_weight": 1.0, "epoch": 8.016838166510757, "flow_matching_loss": 0.04690858870744705, "grad_norm": 0.14677061140537262, "invalid_tail_samples": 22.6, "learning_rate": 8.557291094260152e-05, "loss": 0.0524, "positive_teacher_pairs": 27131.2, "relation_loss": 0.005460320878773928, "selected_pairs": 27131.2, "step": 8570, "student_distance_mean": 959.0412475585938, "teacher_distance_mean": 0.8629788517951965, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.005460320878773928, "weighted_relation_loss": 0.005460320878773928 }, { "action_query_batch_std": 16.74554100036621, "action_query_norm": 738.9644958496094, "action_relation_loss": 0.005360557045787573, "auxiliary_loss_weight": 1.0, "epoch": 8.026192703461179, "flow_matching_loss": 0.044567167013883593, "grad_norm": 0.13457684218883514, "invalid_tail_samples": 23.6, "learning_rate": 8.553415799829629e-05, "loss": 0.0499, "positive_teacher_pairs": 26905.3, "relation_loss": 0.005360557045787573, "selected_pairs": 26905.3, "step": 8580, "student_distance_mean": 950.449951171875, "teacher_distance_mean": 0.8549827337265015, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.005360557045787573, "weighted_relation_loss": 0.005360557045787573 }, { "action_query_batch_std": 16.698868370056154, "action_query_norm": 736.427099609375, "action_relation_loss": 0.004886423936113715, "auxiliary_loss_weight": 1.0, "epoch": 8.0355472404116, "flow_matching_loss": 0.04837450534105301, "grad_norm": 0.15901103615760803, "invalid_tail_samples": 26.7, "learning_rate": 8.549536187663847e-05, "loss": 0.0533, "positive_teacher_pairs": 26179.7, "relation_loss": 0.004886423936113715, "selected_pairs": 26179.7, "step": 8590, "student_distance_mean": 947.21923828125, "teacher_distance_mean": 0.84943807721138, "valid_action_samples": 229.3, "weighted_auxiliary_loss": 0.004886423936113715, "weighted_relation_loss": 0.004886423936113715 }, { "action_query_batch_std": 16.74092674255371, "action_query_norm": 737.849853515625, "action_relation_loss": 0.004983156500384211, "auxiliary_loss_weight": 1.0, "epoch": 8.044901777362021, "flow_matching_loss": 0.0458533201366663, "grad_norm": 0.11252470314502716, "invalid_tail_samples": 22.5, "learning_rate": 8.545652262476897e-05, "loss": 0.0508, "positive_teacher_pairs": 27154.8, "relation_loss": 0.004983156500384211, "selected_pairs": 27154.8, "step": 8600, "student_distance_mean": 946.1828308105469, "teacher_distance_mean": 0.8434096276760101, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.004983156500384211, "weighted_relation_loss": 0.004983156500384211 }, { "action_query_batch_std": 16.930799674987792, "action_query_norm": 745.6331604003906, "action_relation_loss": 0.005029643047600984, "auxiliary_loss_weight": 1.0, "epoch": 8.054256314312441, "flow_matching_loss": 0.0458845816552639, "grad_norm": 0.12147693336009979, "invalid_tail_samples": 21.7, "learning_rate": 8.541764028988115e-05, "loss": 0.0509, "positive_teacher_pairs": 27336.8, "relation_loss": 0.005029643047600984, "selected_pairs": 27336.8, "step": 8610, "student_distance_mean": 958.6888366699219, "teacher_distance_mean": 0.8477138936519623, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.005029643047600984, "weighted_relation_loss": 0.005029643047600984 }, { "action_query_batch_std": 16.64441547393799, "action_query_norm": 736.9163635253906, "action_relation_loss": 0.005272799311205745, "auxiliary_loss_weight": 1.0, "epoch": 8.063610851262862, "flow_matching_loss": 0.04336593933403492, "grad_norm": 0.15728604793548584, "invalid_tail_samples": 22.2, "learning_rate": 8.537871491922071e-05, "loss": 0.0486, "positive_teacher_pairs": 27225.2, "relation_loss": 0.005272799311205745, "selected_pairs": 27225.2, "step": 8620, "student_distance_mean": 944.5090942382812, "teacher_distance_mean": 0.843720281124115, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.005272799311205745, "weighted_relation_loss": 0.005272799311205745 }, { "action_query_batch_std": 17.154313850402833, "action_query_norm": 754.6863830566406, "action_relation_loss": 0.005140230385586619, "auxiliary_loss_weight": 1.0, "epoch": 8.072965388213284, "flow_matching_loss": 0.045241980254650115, "grad_norm": 0.1579468697309494, "invalid_tail_samples": 23.1, "learning_rate": 8.533974656008566e-05, "loss": 0.0504, "positive_teacher_pairs": 27011.4, "relation_loss": 0.005140230385586619, "selected_pairs": 27011.4, "step": 8630, "student_distance_mean": 978.7319946289062, "teacher_distance_mean": 0.8588936805725098, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.005140230385586619, "weighted_relation_loss": 0.005140230385586619 }, { "action_query_batch_std": 17.16743564605713, "action_query_norm": 755.1545776367187, "action_relation_loss": 0.004981859540566802, "auxiliary_loss_weight": 1.0, "epoch": 8.082319925163704, "flow_matching_loss": 0.04689214751124382, "grad_norm": 0.1283651888370514, "invalid_tail_samples": 23.7, "learning_rate": 8.530073525982621e-05, "loss": 0.0519, "positive_teacher_pairs": 26873.3, "relation_loss": 0.004981859540566802, "selected_pairs": 26873.3, "step": 8640, "student_distance_mean": 973.1932373046875, "teacher_distance_mean": 0.8544857263565063, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.004981859540566802, "weighted_relation_loss": 0.004981859540566802 }, { "action_query_batch_std": 16.843930435180663, "action_query_norm": 745.4012573242187, "action_relation_loss": 0.004988105921074748, "auxiliary_loss_weight": 1.0, "epoch": 8.091674462114126, "flow_matching_loss": 0.04513262137770653, "grad_norm": 0.1447337567806244, "invalid_tail_samples": 25.7, "learning_rate": 8.526168106584476e-05, "loss": 0.0501, "positive_teacher_pairs": 26410.9, "relation_loss": 0.004988105921074748, "selected_pairs": 26410.9, "step": 8650, "student_distance_mean": 952.8644287109375, "teacher_distance_mean": 0.8467743217945098, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.004988105921074748, "weighted_relation_loss": 0.004988105921074748 }, { "action_query_batch_std": 17.225411033630373, "action_query_norm": 760.520947265625, "action_relation_loss": 0.005085930787026882, "auxiliary_loss_weight": 1.0, "epoch": 8.101028999064546, "flow_matching_loss": 0.04521329291164875, "grad_norm": 0.1725817769765854, "invalid_tail_samples": 26.5, "learning_rate": 8.522258402559586e-05, "loss": 0.0503, "positive_teacher_pairs": 26229.1, "relation_loss": 0.005085930787026882, "selected_pairs": 26229.1, "step": 8660, "student_distance_mean": 975.4659545898437, "teacher_distance_mean": 0.8539003133773804, "valid_action_samples": 229.5, "weighted_auxiliary_loss": 0.005085930787026882, "weighted_relation_loss": 0.005085930787026882 }, { "action_query_batch_std": 17.384606742858885, "action_query_norm": 762.3863220214844, "action_relation_loss": 0.004858469543978572, "auxiliary_loss_weight": 1.0, "epoch": 8.110383536014968, "flow_matching_loss": 0.043494663760066034, "grad_norm": 0.14521697163581848, "invalid_tail_samples": 24.3, "learning_rate": 8.518344418658613e-05, "loss": 0.0484, "positive_teacher_pairs": 26738.3, "relation_loss": 0.004858469543978572, "selected_pairs": 26738.3, "step": 8670, "student_distance_mean": 988.0509460449218, "teacher_distance_mean": 0.8648101568222046, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.004858469543978572, "weighted_relation_loss": 0.004858469543978572 }, { "action_query_batch_std": 17.191216468811035, "action_query_norm": 755.8632751464844, "action_relation_loss": 0.005060112895444035, "auxiliary_loss_weight": 1.0, "epoch": 8.119738072965388, "flow_matching_loss": 0.0424694936722517, "grad_norm": 0.13911594450473785, "invalid_tail_samples": 22.9, "learning_rate": 8.51442615963741e-05, "loss": 0.0475, "positive_teacher_pairs": 27067.9, "relation_loss": 0.005060112895444035, "selected_pairs": 27067.9, "step": 8680, "student_distance_mean": 973.2855285644531, "teacher_distance_mean": 0.8526050269603729, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.005060112895444035, "weighted_relation_loss": 0.005060112895444035 }, { "action_query_batch_std": 17.10895519256592, "action_query_norm": 754.3708312988281, "action_relation_loss": 0.004842036729678511, "auxiliary_loss_weight": 1.0, "epoch": 8.129092609915809, "flow_matching_loss": 0.043502173572778705, "grad_norm": 0.09753168374300003, "invalid_tail_samples": 22.0, "learning_rate": 8.510503630257034e-05, "loss": 0.0483, "positive_teacher_pairs": 27263.8, "relation_loss": 0.004842036729678511, "selected_pairs": 27263.8, "step": 8690, "student_distance_mean": 973.5065795898438, "teacher_distance_mean": 0.8489628374576569, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.004842036729678511, "weighted_relation_loss": 0.004842036729678511 }, { "action_query_batch_std": 17.41856231689453, "action_query_norm": 763.0354858398438, "action_relation_loss": 0.004956374363973737, "auxiliary_loss_weight": 1.0, "epoch": 8.13844714686623, "flow_matching_loss": 0.04525947794318199, "grad_norm": 0.10060486197471619, "invalid_tail_samples": 22.4, "learning_rate": 8.50657683528373e-05, "loss": 0.0502, "positive_teacher_pairs": 27174.1, "relation_loss": 0.004956374363973737, "selected_pairs": 27174.1, "step": 8700, "student_distance_mean": 988.2278747558594, "teacher_distance_mean": 0.8669259250164032, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.004956374363973737, "weighted_relation_loss": 0.004956374363973737 }, { "action_query_batch_std": 17.5454460144043, "action_query_norm": 766.5067443847656, "action_relation_loss": 0.004938471224159002, "auxiliary_loss_weight": 1.0, "epoch": 8.14780168381665, "flow_matching_loss": 0.045119984447956084, "grad_norm": 0.13339336216449738, "invalid_tail_samples": 22.9, "learning_rate": 8.502645779488922e-05, "loss": 0.0501, "positive_teacher_pairs": 27053.9, "relation_loss": 0.004938471224159002, "selected_pairs": 27053.9, "step": 8710, "student_distance_mean": 994.9814331054688, "teacher_distance_mean": 0.8687021851539611, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.004938471224159002, "weighted_relation_loss": 0.004938471224159002 }, { "action_query_batch_std": 17.24802303314209, "action_query_norm": 756.7585815429687, "action_relation_loss": 0.004895129986107349, "auxiliary_loss_weight": 1.0, "epoch": 8.157156220767073, "flow_matching_loss": 0.0425168726593256, "grad_norm": 0.10690417885780334, "invalid_tail_samples": 24.5, "learning_rate": 8.498710467649213e-05, "loss": 0.0474, "positive_teacher_pairs": 26684.5, "relation_loss": 0.004895129986107349, "selected_pairs": 26684.5, "step": 8720, "student_distance_mean": 978.6853088378906, "teacher_distance_mean": 0.8560765027999878, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.004895129986107349, "weighted_relation_loss": 0.004895129986107349 }, { "action_query_batch_std": 17.159510231018068, "action_query_norm": 751.5537719726562, "action_relation_loss": 0.005011794297024608, "auxiliary_loss_weight": 1.0, "epoch": 8.166510757717493, "flow_matching_loss": 0.043408863618969916, "grad_norm": 0.1314188838005066, "invalid_tail_samples": 22.4, "learning_rate": 8.494770904546381e-05, "loss": 0.0484, "positive_teacher_pairs": 27179.5, "relation_loss": 0.005011794297024608, "selected_pairs": 27179.5, "step": 8730, "student_distance_mean": 971.5488952636719, "teacher_distance_mean": 0.8550914883613586, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.005011794297024608, "weighted_relation_loss": 0.005011794297024608 }, { "action_query_batch_std": 17.17512454986572, "action_query_norm": 753.8569030761719, "action_relation_loss": 0.0049236234277486805, "auxiliary_loss_weight": 1.0, "epoch": 8.175865294667913, "flow_matching_loss": 0.04452592805027962, "grad_norm": 0.12461898475885391, "invalid_tail_samples": 24.7, "learning_rate": 8.490827094967363e-05, "loss": 0.0494, "positive_teacher_pairs": 26640.7, "relation_loss": 0.0049236234277486805, "selected_pairs": 26640.7, "step": 8740, "student_distance_mean": 975.7724304199219, "teacher_distance_mean": 0.8538088619709014, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0049236234277486805, "weighted_relation_loss": 0.0049236234277486805 }, { "action_query_batch_std": 17.744061851501463, "action_query_norm": 775.7036437988281, "action_relation_loss": 0.004892741097137332, "auxiliary_loss_weight": 1.0, "epoch": 8.185219831618335, "flow_matching_loss": 0.04282814487814903, "grad_norm": 0.12186404317617416, "invalid_tail_samples": 23.5, "learning_rate": 8.486879043704263e-05, "loss": 0.0477, "positive_teacher_pairs": 26914.1, "relation_loss": 0.004892741097137332, "selected_pairs": 26914.1, "step": 8750, "student_distance_mean": 1005.4290222167969, "teacher_distance_mean": 0.8800650715827942, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.004892741097137332, "weighted_relation_loss": 0.004892741097137332 }, { "action_query_batch_std": 17.12177848815918, "action_query_norm": 750.62109375, "action_relation_loss": 0.004780415119603277, "auxiliary_loss_weight": 1.0, "epoch": 8.194574368568755, "flow_matching_loss": 0.04261474013328552, "grad_norm": 0.13268011808395386, "invalid_tail_samples": 24.8, "learning_rate": 8.482926755554332e-05, "loss": 0.0474, "positive_teacher_pairs": 26615.2, "relation_loss": 0.004780415119603277, "selected_pairs": 26615.2, "step": 8760, "student_distance_mean": 971.3707580566406, "teacher_distance_mean": 0.8555474162101746, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.004780415119603277, "weighted_relation_loss": 0.004780415119603277 }, { "action_query_batch_std": 16.898022079467772, "action_query_norm": 748.0070739746094, "action_relation_loss": 0.0050613269675523044, "auxiliary_loss_weight": 1.0, "epoch": 8.203928905519177, "flow_matching_loss": 0.044922278448939326, "grad_norm": 0.14215147495269775, "invalid_tail_samples": 24.2, "learning_rate": 8.478970235319975e-05, "loss": 0.05, "positive_teacher_pairs": 26764.3, "relation_loss": 0.0050613269675523044, "selected_pairs": 26764.3, "step": 8770, "student_distance_mean": 956.3126525878906, "teacher_distance_mean": 0.836435729265213, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0050613269675523044, "weighted_relation_loss": 0.0050613269675523044 }, { "action_query_batch_std": 17.402232551574706, "action_query_norm": 764.9071594238281, "action_relation_loss": 0.004738033562898636, "auxiliary_loss_weight": 1.0, "epoch": 8.213283442469598, "flow_matching_loss": 0.04144250825047493, "grad_norm": 0.1190033033490181, "invalid_tail_samples": 24.8, "learning_rate": 8.475009487808737e-05, "loss": 0.0462, "positive_teacher_pairs": 26619.6, "relation_loss": 0.004738033562898636, "selected_pairs": 26619.6, "step": 8780, "student_distance_mean": 991.4480285644531, "teacher_distance_mean": 0.8552746415138245, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.004738033562898636, "weighted_relation_loss": 0.004738033562898636 }, { "action_query_batch_std": 17.19627456665039, "action_query_norm": 756.0438232421875, "action_relation_loss": 0.00500419489108026, "auxiliary_loss_weight": 1.0, "epoch": 8.22263797942002, "flow_matching_loss": 0.04337537735700607, "grad_norm": 0.1296902298927307, "invalid_tail_samples": 23.0, "learning_rate": 8.471044517833298e-05, "loss": 0.0484, "positive_teacher_pairs": 27043.0, "relation_loss": 0.00500419489108026, "selected_pairs": 27043.0, "step": 8790, "student_distance_mean": 971.2308776855468, "teacher_distance_mean": 0.8426782727241516, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.00500419489108026, "weighted_relation_loss": 0.00500419489108026 }, { "action_query_batch_std": 17.325914573669433, "action_query_norm": 759.3981384277344, "action_relation_loss": 0.004983971081674099, "auxiliary_loss_weight": 1.0, "epoch": 8.23199251637044, "flow_matching_loss": 0.04206796400249004, "grad_norm": 0.1459125429391861, "invalid_tail_samples": 23.7, "learning_rate": 8.467075330211474e-05, "loss": 0.0471, "positive_teacher_pairs": 26878.7, "relation_loss": 0.004983971081674099, "selected_pairs": 26878.7, "step": 8800, "student_distance_mean": 980.9514831542969, "teacher_distance_mean": 0.8576909244060517, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.004983971081674099, "weighted_relation_loss": 0.004983971081674099 }, { "action_query_batch_std": 17.376379776000977, "action_query_norm": 765.556201171875, "action_relation_loss": 0.005131597258150577, "auxiliary_loss_weight": 1.0, "epoch": 8.24134705332086, "flow_matching_loss": 0.04340529218316078, "grad_norm": 0.14963982999324799, "invalid_tail_samples": 22.7, "learning_rate": 8.463101929766198e-05, "loss": 0.0485, "positive_teacher_pairs": 27102.2, "relation_loss": 0.005131597258150577, "selected_pairs": 27102.2, "step": 8810, "student_distance_mean": 982.0608764648438, "teacher_distance_mean": 0.8528629004955292, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.005131597258150577, "weighted_relation_loss": 0.005131597258150577 }, { "action_query_batch_std": 17.333302116394044, "action_query_norm": 766.1490478515625, "action_relation_loss": 0.00503188231959939, "auxiliary_loss_weight": 1.0, "epoch": 8.250701590271282, "flow_matching_loss": 0.04266366921365261, "grad_norm": 0.15684300661087036, "invalid_tail_samples": 25.6, "learning_rate": 8.459124321325528e-05, "loss": 0.0477, "positive_teacher_pairs": 26433.8, "relation_loss": 0.00503188231959939, "selected_pairs": 26433.8, "step": 8820, "student_distance_mean": 986.1942810058594, "teacher_distance_mean": 0.8579978287220001, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.00503188231959939, "weighted_relation_loss": 0.00503188231959939 }, { "action_query_batch_std": 17.21213493347168, "action_query_norm": 760.3487060546875, "action_relation_loss": 0.0047792393248528246, "auxiliary_loss_weight": 1.0, "epoch": 8.260056127221702, "flow_matching_loss": 0.04396522305905819, "grad_norm": 0.12096796184778214, "invalid_tail_samples": 23.3, "learning_rate": 8.455142509722634e-05, "loss": 0.0487, "positive_teacher_pairs": 26970.5, "relation_loss": 0.0047792393248528246, "selected_pairs": 26970.5, "step": 8830, "student_distance_mean": 978.7955383300781, "teacher_distance_mean": 0.8579325318336487, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0047792393248528246, "weighted_relation_loss": 0.0047792393248528246 }, { "action_query_batch_std": 17.441505241394044, "action_query_norm": 766.1494689941406, "action_relation_loss": 0.0048730607144534584, "auxiliary_loss_weight": 1.0, "epoch": 8.269410664172124, "flow_matching_loss": 0.04436870962381363, "grad_norm": 0.16311153769493103, "invalid_tail_samples": 23.9, "learning_rate": 8.451156499795792e-05, "loss": 0.0492, "positive_teacher_pairs": 26829.3, "relation_loss": 0.0048730607144534584, "selected_pairs": 26829.3, "step": 8840, "student_distance_mean": 986.8393249511719, "teacher_distance_mean": 0.8635756433010101, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0048730607144534584, "weighted_relation_loss": 0.0048730607144534584 }, { "action_query_batch_std": 17.25309200286865, "action_query_norm": 756.7574645996094, "action_relation_loss": 0.004796827724203467, "auxiliary_loss_weight": 1.0, "epoch": 8.278765201122544, "flow_matching_loss": 0.04285825714468956, "grad_norm": 0.12438543885946274, "invalid_tail_samples": 26.0, "learning_rate": 8.447166296388381e-05, "loss": 0.0477, "positive_teacher_pairs": 26342.9, "relation_loss": 0.004796827724203467, "selected_pairs": 26342.9, "step": 8850, "student_distance_mean": 980.8547912597656, "teacher_distance_mean": 0.8567080676555634, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.004796827724203467, "weighted_relation_loss": 0.004796827724203467 }, { "action_query_batch_std": 17.199861335754395, "action_query_norm": 755.5229370117188, "action_relation_loss": 0.00507074729539454, "auxiliary_loss_weight": 1.0, "epoch": 8.288119738072965, "flow_matching_loss": 0.045893968641757966, "grad_norm": 0.13174284994602203, "invalid_tail_samples": 21.6, "learning_rate": 8.443171904348872e-05, "loss": 0.051, "positive_teacher_pairs": 27356.5, "relation_loss": 0.00507074729539454, "selected_pairs": 27356.5, "step": 8860, "student_distance_mean": 973.7232055664062, "teacher_distance_mean": 0.8495571970939636, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.00507074729539454, "weighted_relation_loss": 0.00507074729539454 }, { "action_query_batch_std": 17.295103454589842, "action_query_norm": 756.62421875, "action_relation_loss": 0.004795071994885802, "auxiliary_loss_weight": 1.0, "epoch": 8.297474275023387, "flow_matching_loss": 0.044933945685625074, "grad_norm": 0.13738194108009338, "invalid_tail_samples": 22.3, "learning_rate": 8.43917332853083e-05, "loss": 0.0497, "positive_teacher_pairs": 27200.2, "relation_loss": 0.004795071994885802, "selected_pairs": 27200.2, "step": 8870, "student_distance_mean": 978.1890747070313, "teacher_distance_mean": 0.8558946967124939, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.004795071994885802, "weighted_relation_loss": 0.004795071994885802 }, { "action_query_batch_std": 17.272830390930174, "action_query_norm": 757.7506958007813, "action_relation_loss": 0.004918046249076724, "auxiliary_loss_weight": 1.0, "epoch": 8.306828811973807, "flow_matching_loss": 0.04332844503223896, "grad_norm": 0.14467008411884308, "invalid_tail_samples": 24.0, "learning_rate": 8.435170573792901e-05, "loss": 0.0482, "positive_teacher_pairs": 26805.0, "relation_loss": 0.004918046249076724, "selected_pairs": 26805.0, "step": 8880, "student_distance_mean": 979.2407653808593, "teacher_distance_mean": 0.8562002539634704, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.004918046249076724, "weighted_relation_loss": 0.004918046249076724 }, { "action_query_batch_std": 17.19644241333008, "action_query_norm": 753.6810729980468, "action_relation_loss": 0.004833030281588435, "auxiliary_loss_weight": 1.0, "epoch": 8.316183348924229, "flow_matching_loss": 0.04415817968547344, "grad_norm": 0.1756141036748886, "invalid_tail_samples": 22.6, "learning_rate": 8.431163644998808e-05, "loss": 0.049, "positive_teacher_pairs": 27124.4, "relation_loss": 0.004833030281588435, "selected_pairs": 27124.4, "step": 8890, "student_distance_mean": 976.2241516113281, "teacher_distance_mean": 0.8497036218643188, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.004833030281588435, "weighted_relation_loss": 0.004833030281588435 }, { "action_query_batch_std": 17.20566806793213, "action_query_norm": 758.2313598632812, "action_relation_loss": 0.004777212627232075, "auxiliary_loss_weight": 1.0, "epoch": 8.325537885874649, "flow_matching_loss": 0.04247848391532898, "grad_norm": 0.17951281368732452, "invalid_tail_samples": 23.7, "learning_rate": 8.42715254701735e-05, "loss": 0.0473, "positive_teacher_pairs": 26869.0, "relation_loss": 0.004777212627232075, "selected_pairs": 26869.0, "step": 8900, "student_distance_mean": 970.3522216796875, "teacher_distance_mean": 0.85209139585495, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.004777212627232075, "weighted_relation_loss": 0.004777212627232075 }, { "action_query_batch_std": 17.46832408905029, "action_query_norm": 768.63359375, "action_relation_loss": 0.004946235800161958, "auxiliary_loss_weight": 1.0, "epoch": 8.334892422825071, "flow_matching_loss": 0.04535248689353466, "grad_norm": 0.11594191193580627, "invalid_tail_samples": 21.8, "learning_rate": 8.42313728472239e-05, "loss": 0.0503, "positive_teacher_pairs": 27316.6, "relation_loss": 0.004946235800161958, "selected_pairs": 27316.6, "step": 8910, "student_distance_mean": 990.6315979003906, "teacher_distance_mean": 0.8652068138122558, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.004946235800161958, "weighted_relation_loss": 0.004946235800161958 }, { "action_query_batch_std": 17.23044624328613, "action_query_norm": 758.9281433105468, "action_relation_loss": 0.004886017786338926, "auxiliary_loss_weight": 1.0, "epoch": 8.344246959775491, "flow_matching_loss": 0.04385870136320591, "grad_norm": 0.16718241572380066, "invalid_tail_samples": 23.6, "learning_rate": 8.419117862992844e-05, "loss": 0.0487, "positive_teacher_pairs": 26898.3, "relation_loss": 0.004886017786338926, "selected_pairs": 26898.3, "step": 8920, "student_distance_mean": 974.0352478027344, "teacher_distance_mean": 0.8532455027103424, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.004886017786338926, "weighted_relation_loss": 0.004886017786338926 }, { "action_query_batch_std": 17.20205764770508, "action_query_norm": 761.1048645019531, "action_relation_loss": 0.004974221903830766, "auxiliary_loss_weight": 1.0, "epoch": 8.353601496725911, "flow_matching_loss": 0.0421915840357542, "grad_norm": 0.12622827291488647, "invalid_tail_samples": 25.4, "learning_rate": 8.415094286712694e-05, "loss": 0.0472, "positive_teacher_pairs": 26485.4, "relation_loss": 0.004974221903830766, "selected_pairs": 26485.4, "step": 8930, "student_distance_mean": 977.6617858886718, "teacher_distance_mean": 0.8579631745815277, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.004974221903830766, "weighted_relation_loss": 0.004974221903830766 }, { "action_query_batch_std": 17.312606239318846, "action_query_norm": 760.9613891601563, "action_relation_loss": 0.004673887556418776, "auxiliary_loss_weight": 1.0, "epoch": 8.362956033676333, "flow_matching_loss": 0.04174473434686661, "grad_norm": 0.123042993247509, "invalid_tail_samples": 24.2, "learning_rate": 8.411066560770965e-05, "loss": 0.0464, "positive_teacher_pairs": 26767.9, "relation_loss": 0.004673887556418776, "selected_pairs": 26767.9, "step": 8940, "student_distance_mean": 985.0464477539062, "teacher_distance_mean": 0.8607928276062011, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.004673887556418776, "weighted_relation_loss": 0.004673887556418776 }, { "action_query_batch_std": 17.392180061340333, "action_query_norm": 764.3466552734375, "action_relation_loss": 0.005059276474639773, "auxiliary_loss_weight": 1.0, "epoch": 8.372310570626754, "flow_matching_loss": 0.04295647703111172, "grad_norm": 0.14714479446411133, "invalid_tail_samples": 25.4, "learning_rate": 8.407034690061721e-05, "loss": 0.048, "positive_teacher_pairs": 26492.7, "relation_loss": 0.005059276474639773, "selected_pairs": 26492.7, "step": 8950, "student_distance_mean": 989.1251586914062, "teacher_distance_mean": 0.858334481716156, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.005059276474639773, "weighted_relation_loss": 0.005059276474639773 }, { "action_query_batch_std": 17.03566951751709, "action_query_norm": 758.4131103515625, "action_relation_loss": 0.0051578580867499115, "auxiliary_loss_weight": 1.0, "epoch": 8.381665107577176, "flow_matching_loss": 0.04245802164077759, "grad_norm": 0.12387707084417343, "invalid_tail_samples": 20.6, "learning_rate": 8.402998679484067e-05, "loss": 0.0476, "positive_teacher_pairs": 27612.4, "relation_loss": 0.0051578580867499115, "selected_pairs": 27612.4, "step": 8960, "student_distance_mean": 966.7383544921875, "teacher_distance_mean": 0.8451368391513825, "valid_action_samples": 235.4, "weighted_auxiliary_loss": 0.0051578580867499115, "weighted_relation_loss": 0.0051578580867499115 }, { "action_query_batch_std": 17.2705286026001, "action_query_norm": 759.0032653808594, "action_relation_loss": 0.004929303796961904, "auxiliary_loss_weight": 1.0, "epoch": 8.391019644527596, "flow_matching_loss": 0.042594144120812416, "grad_norm": 0.16374525427818298, "invalid_tail_samples": 23.8, "learning_rate": 8.398958533942135e-05, "loss": 0.0475, "positive_teacher_pairs": 26857.1, "relation_loss": 0.004929303796961904, "selected_pairs": 26857.1, "step": 8970, "student_distance_mean": 979.3534118652344, "teacher_distance_mean": 0.8501461029052735, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.004929303796961904, "weighted_relation_loss": 0.004929303796961904 }, { "action_query_batch_std": 17.548104095458985, "action_query_norm": 770.1393371582031, "action_relation_loss": 0.004824549751356244, "auxiliary_loss_weight": 1.0, "epoch": 8.400374181478018, "flow_matching_loss": 0.042164641246199605, "grad_norm": 0.14974071085453033, "invalid_tail_samples": 26.6, "learning_rate": 8.394914258345083e-05, "loss": 0.047, "positive_teacher_pairs": 26212.4, "relation_loss": 0.004824549751356244, "selected_pairs": 26212.4, "step": 8980, "student_distance_mean": 999.1720764160157, "teacher_distance_mean": 0.8493151783943176, "valid_action_samples": 229.4, "weighted_auxiliary_loss": 0.004824549751356244, "weighted_relation_loss": 0.004824549751356244 }, { "action_query_batch_std": 17.54577007293701, "action_query_norm": 773.0007568359375, "action_relation_loss": 0.0050271475221961735, "auxiliary_loss_weight": 1.0, "epoch": 8.409728718428438, "flow_matching_loss": 0.043115508183836936, "grad_norm": 0.17283914983272552, "invalid_tail_samples": 24.5, "learning_rate": 8.390865857607089e-05, "loss": 0.0481, "positive_teacher_pairs": 26691.9, "relation_loss": 0.0050271475221961735, "selected_pairs": 26691.9, "step": 8990, "student_distance_mean": 1001.3197265625, "teacher_distance_mean": 0.8573441565036773, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0050271475221961735, "weighted_relation_loss": 0.0050271475221961735 }, { "action_query_batch_std": 17.486668205261232, "action_query_norm": 766.2301879882813, "action_relation_loss": 0.004959368146955967, "auxiliary_loss_weight": 1.0, "epoch": 8.419083255378858, "flow_matching_loss": 0.04510992243885994, "grad_norm": 0.13208895921707153, "invalid_tail_samples": 24.9, "learning_rate": 8.386813336647339e-05, "loss": 0.0501, "positive_teacher_pairs": 26603.5, "relation_loss": 0.004959368146955967, "selected_pairs": 26603.5, "step": 9000, "student_distance_mean": 989.1415893554688, "teacher_distance_mean": 0.8536613285541534, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.004959368146955967, "weighted_relation_loss": 0.004959368146955967 }, { "action_query_batch_std": 17.605357360839843, "action_query_norm": 773.5289306640625, "action_relation_loss": 0.00484035057015717, "auxiliary_loss_weight": 1.0, "epoch": 8.42843779232928, "flow_matching_loss": 0.04401206374168396, "grad_norm": 0.13809731602668762, "invalid_tail_samples": 24.7, "learning_rate": 8.38275670039003e-05, "loss": 0.0489, "positive_teacher_pairs": 26645.4, "relation_loss": 0.00484035057015717, "selected_pairs": 26645.4, "step": 9010, "student_distance_mean": 999.6059936523437, "teacher_distance_mean": 0.8508257865905762, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.00484035057015717, "weighted_relation_loss": 0.00484035057015717 }, { "action_query_batch_std": 17.4273401260376, "action_query_norm": 766.3163330078125, "action_relation_loss": 0.004991868976503611, "auxiliary_loss_weight": 1.0, "epoch": 8.4377923292797, "flow_matching_loss": 0.04308057203888893, "grad_norm": 0.08981449902057648, "invalid_tail_samples": 24.1, "learning_rate": 8.378695953764356e-05, "loss": 0.0481, "positive_teacher_pairs": 26778.5, "relation_loss": 0.004991868976503611, "selected_pairs": 26778.5, "step": 9020, "student_distance_mean": 987.92294921875, "teacher_distance_mean": 0.8536748230457306, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.004991868976503611, "weighted_relation_loss": 0.004991868976503611 }, { "action_query_batch_std": 17.596302032470703, "action_query_norm": 768.0770751953125, "action_relation_loss": 0.005152039043605327, "auxiliary_loss_weight": 1.0, "epoch": 8.447146866230122, "flow_matching_loss": 0.041859110444784166, "grad_norm": 0.14759708940982819, "invalid_tail_samples": 27.2, "learning_rate": 8.374631101704509e-05, "loss": 0.047, "positive_teacher_pairs": 26071.9, "relation_loss": 0.005152039043605327, "selected_pairs": 26071.9, "step": 9030, "student_distance_mean": 1000.1312866210938, "teacher_distance_mean": 0.8642367660999298, "valid_action_samples": 228.8, "weighted_auxiliary_loss": 0.005152039043605327, "weighted_relation_loss": 0.005152039043605327 }, { "action_query_batch_std": 17.48371868133545, "action_query_norm": 766.9465209960938, "action_relation_loss": 0.004974989732727408, "auxiliary_loss_weight": 1.0, "epoch": 8.456501403180543, "flow_matching_loss": 0.04268182031810284, "grad_norm": 0.15216124057769775, "invalid_tail_samples": 24.6, "learning_rate": 8.370562149149665e-05, "loss": 0.0477, "positive_teacher_pairs": 26664.1, "relation_loss": 0.004974989732727408, "selected_pairs": 26664.1, "step": 9040, "student_distance_mean": 993.5111083984375, "teacher_distance_mean": 0.8568119704723358, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.004974989732727408, "weighted_relation_loss": 0.004974989732727408 }, { "action_query_batch_std": 17.45554084777832, "action_query_norm": 767.6455078125, "action_relation_loss": 0.005021531926468014, "auxiliary_loss_weight": 1.0, "epoch": 8.465855940130963, "flow_matching_loss": 0.04218324422836304, "grad_norm": 0.15070560574531555, "invalid_tail_samples": 23.5, "learning_rate": 8.366489101043989e-05, "loss": 0.0472, "positive_teacher_pairs": 26919.4, "relation_loss": 0.005021531926468014, "selected_pairs": 26919.4, "step": 9050, "student_distance_mean": 993.3388854980469, "teacher_distance_mean": 0.8533543348312378, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.005021531926468014, "weighted_relation_loss": 0.005021531926468014 }, { "action_query_batch_std": 17.79118118286133, "action_query_norm": 777.3313598632812, "action_relation_loss": 0.004684683820232749, "auxiliary_loss_weight": 1.0, "epoch": 8.475210477081385, "flow_matching_loss": 0.040306725353002545, "grad_norm": 0.1273331195116043, "invalid_tail_samples": 25.0, "learning_rate": 8.362411962336614e-05, "loss": 0.045, "positive_teacher_pairs": 26577.9, "relation_loss": 0.004684683820232749, "selected_pairs": 26577.9, "step": 9060, "student_distance_mean": 1015.1434509277344, "teacher_distance_mean": 0.8750076413154602, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.004684683820232749, "weighted_relation_loss": 0.004684683820232749 }, { "action_query_batch_std": 17.35910110473633, "action_query_norm": 762.6971557617187, "action_relation_loss": 0.00520642357878387, "auxiliary_loss_weight": 1.0, "epoch": 8.484565014031805, "flow_matching_loss": 0.045639931410551074, "grad_norm": 0.1602078378200531, "invalid_tail_samples": 25.0, "learning_rate": 8.358330737981651e-05, "loss": 0.0508, "positive_teacher_pairs": 26577.8, "relation_loss": 0.00520642357878387, "selected_pairs": 26577.8, "step": 9070, "student_distance_mean": 991.2833618164062, "teacher_distance_mean": 0.8519914329051972, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.00520642357878387, "weighted_relation_loss": 0.00520642357878387 }, { "action_query_batch_std": 17.182180404663086, "action_query_norm": 754.6646850585937, "action_relation_loss": 0.005136075755581259, "auxiliary_loss_weight": 1.0, "epoch": 8.493919550982227, "flow_matching_loss": 0.04523024521768093, "grad_norm": 0.1846608966588974, "invalid_tail_samples": 22.6, "learning_rate": 8.35424543293817e-05, "loss": 0.0504, "positive_teacher_pairs": 27126.9, "relation_loss": 0.005136075755581259, "selected_pairs": 27126.9, "step": 9080, "student_distance_mean": 976.501806640625, "teacher_distance_mean": 0.8450584411621094, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.005136075755581259, "weighted_relation_loss": 0.005136075755581259 }, { "action_query_batch_std": 17.295233154296874, "action_query_norm": 761.0061889648438, "action_relation_loss": 0.00478698848746717, "auxiliary_loss_weight": 1.0, "epoch": 8.503274087932647, "flow_matching_loss": 0.04349376894533634, "grad_norm": 0.139601469039917, "invalid_tail_samples": 23.9, "learning_rate": 8.350156052170206e-05, "loss": 0.0483, "positive_teacher_pairs": 26829.3, "relation_loss": 0.00478698848746717, "selected_pairs": 26829.3, "step": 9090, "student_distance_mean": 989.44638671875, "teacher_distance_mean": 0.8609326958656311, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.00478698848746717, "weighted_relation_loss": 0.00478698848746717 }, { "action_query_batch_std": 17.548171043395996, "action_query_norm": 769.77080078125, "action_relation_loss": 0.004861015593633056, "auxiliary_loss_weight": 1.0, "epoch": 8.512628624883067, "flow_matching_loss": 0.043650726601481435, "grad_norm": 0.10456525534391403, "invalid_tail_samples": 21.9, "learning_rate": 8.346062600646738e-05, "loss": 0.0485, "positive_teacher_pairs": 27296.8, "relation_loss": 0.004861015593633056, "selected_pairs": 27296.8, "step": 9100, "student_distance_mean": 994.7310974121094, "teacher_distance_mean": 0.8626000165939331, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.004861015593633056, "weighted_relation_loss": 0.004861015593633056 }, { "action_query_batch_std": 17.55210018157959, "action_query_norm": 772.46552734375, "action_relation_loss": 0.004928435618057847, "auxiliary_loss_weight": 1.0, "epoch": 8.52198316183349, "flow_matching_loss": 0.04866744838654995, "grad_norm": 0.15168482065200806, "invalid_tail_samples": 23.6, "learning_rate": 8.341965083341697e-05, "loss": 0.0536, "positive_teacher_pairs": 26893.0, "relation_loss": 0.004928435618057847, "selected_pairs": 26893.0, "step": 9110, "student_distance_mean": 994.5308715820313, "teacher_distance_mean": 0.8504085063934326, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.004928435618057847, "weighted_relation_loss": 0.004928435618057847 }, { "action_query_batch_std": 17.659643363952636, "action_query_norm": 777.666943359375, "action_relation_loss": 0.0049270719289779665, "auxiliary_loss_weight": 1.0, "epoch": 8.53133769878391, "flow_matching_loss": 0.04341127164661884, "grad_norm": 0.11288809776306152, "invalid_tail_samples": 25.4, "learning_rate": 8.337863505233953e-05, "loss": 0.0483, "positive_teacher_pairs": 26481.3, "relation_loss": 0.0049270719289779665, "selected_pairs": 26481.3, "step": 9120, "student_distance_mean": 1000.9054565429688, "teacher_distance_mean": 0.8544484734535217, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.0049270719289779665, "weighted_relation_loss": 0.0049270719289779665 }, { "action_query_batch_std": 17.840275955200195, "action_query_norm": 783.292919921875, "action_relation_loss": 0.004833043413236737, "auxiliary_loss_weight": 1.0, "epoch": 8.540692235734332, "flow_matching_loss": 0.04441035464406014, "grad_norm": 0.18516819179058075, "invalid_tail_samples": 24.5, "learning_rate": 8.33375787130731e-05, "loss": 0.0492, "positive_teacher_pairs": 26686.3, "relation_loss": 0.004833043413236737, "selected_pairs": 26686.3, "step": 9130, "student_distance_mean": 1013.1195922851563, "teacher_distance_mean": 0.8587462544441223, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.004833043413236737, "weighted_relation_loss": 0.004833043413236737 }, { "action_query_batch_std": 17.625177574157714, "action_query_norm": 776.5674133300781, "action_relation_loss": 0.005055912164971232, "auxiliary_loss_weight": 1.0, "epoch": 8.550046772684752, "flow_matching_loss": 0.04371061697602272, "grad_norm": 0.13505376875400543, "invalid_tail_samples": 24.8, "learning_rate": 8.3296481865505e-05, "loss": 0.0488, "positive_teacher_pairs": 26624.9, "relation_loss": 0.005055912164971232, "selected_pairs": 26624.9, "step": 9140, "student_distance_mean": 1002.0677001953125, "teacher_distance_mean": 0.8522750616073609, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.005055912164971232, "weighted_relation_loss": 0.005055912164971232 }, { "action_query_batch_std": 17.556360816955568, "action_query_norm": 772.09208984375, "action_relation_loss": 0.004758896213024855, "auxiliary_loss_weight": 1.0, "epoch": 8.559401309635174, "flow_matching_loss": 0.043210535496473315, "grad_norm": 0.12489351630210876, "invalid_tail_samples": 22.7, "learning_rate": 8.325534455957181e-05, "loss": 0.048, "positive_teacher_pairs": 27106.1, "relation_loss": 0.004758896213024855, "selected_pairs": 27106.1, "step": 9150, "student_distance_mean": 991.3329223632812, "teacher_distance_mean": 0.8575829267501831, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.004758896213024855, "weighted_relation_loss": 0.004758896213024855 }, { "action_query_batch_std": 17.55523624420166, "action_query_norm": 771.2341186523438, "action_relation_loss": 0.004883996630087495, "auxiliary_loss_weight": 1.0, "epoch": 8.568755846585594, "flow_matching_loss": 0.0430248811841011, "grad_norm": 0.12727949023246765, "invalid_tail_samples": 22.8, "learning_rate": 8.321416684525917e-05, "loss": 0.0479, "positive_teacher_pairs": 27087.5, "relation_loss": 0.004883996630087495, "selected_pairs": 27087.5, "step": 9160, "student_distance_mean": 999.368994140625, "teacher_distance_mean": 0.8577404677867889, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.004883996630087495, "weighted_relation_loss": 0.004883996630087495 }, { "action_query_batch_std": 17.77985038757324, "action_query_norm": 778.7915161132812, "action_relation_loss": 0.004638502607122064, "auxiliary_loss_weight": 1.0, "epoch": 8.578110383536014, "flow_matching_loss": 0.04435072578489781, "grad_norm": 0.1409565508365631, "invalid_tail_samples": 22.3, "learning_rate": 8.317294877260193e-05, "loss": 0.049, "positive_teacher_pairs": 27199.0, "relation_loss": 0.004638502607122064, "selected_pairs": 27199.0, "step": 9170, "student_distance_mean": 1008.0934692382813, "teacher_distance_mean": 0.8592587888240815, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.004638502607122064, "weighted_relation_loss": 0.004638502607122064 }, { "action_query_batch_std": 17.744146728515624, "action_query_norm": 779.0669799804688, "action_relation_loss": 0.004866543645039201, "auxiliary_loss_weight": 1.0, "epoch": 8.587464920486436, "flow_matching_loss": 0.042343218252062796, "grad_norm": 0.10783284902572632, "invalid_tail_samples": 21.1, "learning_rate": 8.313169039168394e-05, "loss": 0.0472, "positive_teacher_pairs": 27482.4, "relation_loss": 0.004866543645039201, "selected_pairs": 27482.4, "step": 9180, "student_distance_mean": 1009.9238830566406, "teacher_distance_mean": 0.8564399898052215, "valid_action_samples": 234.9, "weighted_auxiliary_loss": 0.004866543645039201, "weighted_relation_loss": 0.004866543645039201 }, { "action_query_batch_std": 17.7218807220459, "action_query_norm": 779.2007202148437, "action_relation_loss": 0.004768417356535793, "auxiliary_loss_weight": 1.0, "epoch": 8.596819457436856, "flow_matching_loss": 0.04504640512168408, "grad_norm": 0.11604347825050354, "invalid_tail_samples": 24.3, "learning_rate": 8.3090391752638e-05, "loss": 0.0498, "positive_teacher_pairs": 26741.5, "relation_loss": 0.004768417356535793, "selected_pairs": 26741.5, "step": 9190, "student_distance_mean": 1009.8127258300781, "teacher_distance_mean": 0.8654028534889221, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.004768417356535793, "weighted_relation_loss": 0.004768417356535793 }, { "action_query_batch_std": 17.41412944793701, "action_query_norm": 768.1153137207032, "action_relation_loss": 0.004857242340222001, "auxiliary_loss_weight": 1.0, "epoch": 8.606173994387278, "flow_matching_loss": 0.04221646524965763, "grad_norm": 0.11991075426340103, "invalid_tail_samples": 22.0, "learning_rate": 8.304905290564586e-05, "loss": 0.0471, "positive_teacher_pairs": 27266.2, "relation_loss": 0.004857242340222001, "selected_pairs": 27266.2, "step": 9200, "student_distance_mean": 987.3210693359375, "teacher_distance_mean": 0.8390914857387543, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.004857242340222001, "weighted_relation_loss": 0.004857242340222001 }, { "action_query_batch_std": 17.676330947875975, "action_query_norm": 772.4565368652344, "action_relation_loss": 0.004895001091063023, "auxiliary_loss_weight": 1.0, "epoch": 8.615528531337699, "flow_matching_loss": 0.04153027385473251, "grad_norm": 0.14583760499954224, "invalid_tail_samples": 19.1, "learning_rate": 8.300767390093813e-05, "loss": 0.0464, "positive_teacher_pairs": 27952.5, "relation_loss": 0.004895001091063023, "selected_pairs": 27952.5, "step": 9210, "student_distance_mean": 998.5720031738281, "teacher_distance_mean": 0.8545582175254822, "valid_action_samples": 236.9, "weighted_auxiliary_loss": 0.004895001091063023, "weighted_relation_loss": 0.004895001091063023 }, { "action_query_batch_std": 17.485272026062013, "action_query_norm": 772.0916809082031, "action_relation_loss": 0.004817505832761526, "auxiliary_loss_weight": 1.0, "epoch": 8.62488306828812, "flow_matching_loss": 0.042743878439068794, "grad_norm": 0.13036882877349854, "invalid_tail_samples": 24.4, "learning_rate": 8.296625478879417e-05, "loss": 0.0476, "positive_teacher_pairs": 26711.9, "relation_loss": 0.004817505832761526, "selected_pairs": 26711.9, "step": 9220, "student_distance_mean": 992.1524597167969, "teacher_distance_mean": 0.846791785955429, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.004817505832761526, "weighted_relation_loss": 0.004817505832761526 }, { "action_query_batch_std": 17.6129243850708, "action_query_norm": 777.0763854980469, "action_relation_loss": 0.004801349714398384, "auxiliary_loss_weight": 1.0, "epoch": 8.63423760523854, "flow_matching_loss": 0.04371870346367359, "grad_norm": 0.12409282475709915, "invalid_tail_samples": 22.3, "learning_rate": 8.292479561954214e-05, "loss": 0.0485, "positive_teacher_pairs": 27202.2, "relation_loss": 0.004801349714398384, "selected_pairs": 27202.2, "step": 9230, "student_distance_mean": 996.6067504882812, "teacher_distance_mean": 0.85308056473732, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.004801349714398384, "weighted_relation_loss": 0.004801349714398384 }, { "action_query_batch_std": 17.60279541015625, "action_query_norm": 773.69951171875, "action_relation_loss": 0.00494403769262135, "auxiliary_loss_weight": 1.0, "epoch": 8.643592142188961, "flow_matching_loss": 0.04264426790177822, "grad_norm": 0.14482930302619934, "invalid_tail_samples": 23.8, "learning_rate": 8.288329644355883e-05, "loss": 0.0476, "positive_teacher_pairs": 26848.0, "relation_loss": 0.00494403769262135, "selected_pairs": 26848.0, "step": 9240, "student_distance_mean": 996.9481567382812, "teacher_distance_mean": 0.8500030636787415, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.00494403769262135, "weighted_relation_loss": 0.00494403769262135 }, { "action_query_batch_std": 17.634013175964355, "action_query_norm": 776.4008483886719, "action_relation_loss": 0.004896675096824765, "auxiliary_loss_weight": 1.0, "epoch": 8.652946679139383, "flow_matching_loss": 0.04322978593409062, "grad_norm": 0.16761673986911774, "invalid_tail_samples": 22.5, "learning_rate": 8.284175731126965e-05, "loss": 0.0481, "positive_teacher_pairs": 27155.9, "relation_loss": 0.004896675096824765, "selected_pairs": 27155.9, "step": 9250, "student_distance_mean": 1002.9709045410157, "teacher_distance_mean": 0.8554554581642151, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.004896675096824765, "weighted_relation_loss": 0.004896675096824765 }, { "action_query_batch_std": 17.800651359558106, "action_query_norm": 780.8898742675781, "action_relation_loss": 0.004674253286793828, "auxiliary_loss_weight": 1.0, "epoch": 8.662301216089803, "flow_matching_loss": 0.041603457927703855, "grad_norm": 0.142926424741745, "invalid_tail_samples": 23.7, "learning_rate": 8.280017827314854e-05, "loss": 0.0463, "positive_teacher_pairs": 26880.4, "relation_loss": 0.004674253286793828, "selected_pairs": 26880.4, "step": 9260, "student_distance_mean": 1009.0500854492187, "teacher_distance_mean": 0.8544388234615325, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.004674253286793828, "weighted_relation_loss": 0.004674253286793828 }, { "action_query_batch_std": 17.914888191223145, "action_query_norm": 789.5554321289062, "action_relation_loss": 0.0048417178448289635, "auxiliary_loss_weight": 1.0, "epoch": 8.671655753040225, "flow_matching_loss": 0.04594978205859661, "grad_norm": 0.13954345881938934, "invalid_tail_samples": 23.2, "learning_rate": 8.2758559379718e-05, "loss": 0.0508, "positive_teacher_pairs": 26986.5, "relation_loss": 0.0048417178448289635, "selected_pairs": 26986.5, "step": 9270, "student_distance_mean": 1014.0358520507813, "teacher_distance_mean": 0.8508757412433624, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0048417178448289635, "weighted_relation_loss": 0.0048417178448289635 }, { "action_query_batch_std": 17.91329460144043, "action_query_norm": 783.4621215820313, "action_relation_loss": 0.004730718256905675, "auxiliary_loss_weight": 1.0, "epoch": 8.681010289990645, "flow_matching_loss": 0.04414272010326385, "grad_norm": 0.11787647753953934, "invalid_tail_samples": 23.7, "learning_rate": 8.271690068154887e-05, "loss": 0.0489, "positive_teacher_pairs": 26872.2, "relation_loss": 0.004730718256905675, "selected_pairs": 26872.2, "step": 9280, "student_distance_mean": 1016.4918395996094, "teacher_distance_mean": 0.8620408058166504, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.004730718256905675, "weighted_relation_loss": 0.004730718256905675 }, { "action_query_batch_std": 17.892782783508302, "action_query_norm": 784.5421264648437, "action_relation_loss": 0.0048472129739820955, "auxiliary_loss_weight": 1.0, "epoch": 8.690364826941066, "flow_matching_loss": 0.042897018417716024, "grad_norm": 0.14520743489265442, "invalid_tail_samples": 21.9, "learning_rate": 8.26752022292604e-05, "loss": 0.0477, "positive_teacher_pairs": 27291.2, "relation_loss": 0.0048472129739820955, "selected_pairs": 27291.2, "step": 9290, "student_distance_mean": 1013.8661071777344, "teacher_distance_mean": 0.8552644968032836, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.0048472129739820955, "weighted_relation_loss": 0.0048472129739820955 }, { "action_query_batch_std": 17.856900787353517, "action_query_norm": 783.1530578613281, "action_relation_loss": 0.004798829229548574, "auxiliary_loss_weight": 1.0, "epoch": 8.699719363891488, "flow_matching_loss": 0.040765875950455666, "grad_norm": 0.12758754193782806, "invalid_tail_samples": 25.1, "learning_rate": 8.263346407352018e-05, "loss": 0.0456, "positive_teacher_pairs": 26551.2, "relation_loss": 0.004798829229548574, "selected_pairs": 26551.2, "step": 9300, "student_distance_mean": 1010.4160034179688, "teacher_distance_mean": 0.8556943356990814, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.004798829229548574, "weighted_relation_loss": 0.004798829229548574 }, { "action_query_batch_std": 17.629564666748045, "action_query_norm": 775.4398864746094, "action_relation_loss": 0.004668231098912656, "auxiliary_loss_weight": 1.0, "epoch": 8.709073900841908, "flow_matching_loss": 0.04281013570725918, "grad_norm": 0.15131451189517975, "invalid_tail_samples": 21.9, "learning_rate": 8.259168626504395e-05, "loss": 0.0475, "positive_teacher_pairs": 27293.3, "relation_loss": 0.004668231098912656, "selected_pairs": 27293.3, "step": 9310, "student_distance_mean": 997.9408203125, "teacher_distance_mean": 0.8483156025409698, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.004668231098912656, "weighted_relation_loss": 0.004668231098912656 }, { "action_query_batch_std": 17.88732795715332, "action_query_norm": 782.11025390625, "action_relation_loss": 0.004573010001331567, "auxiliary_loss_weight": 1.0, "epoch": 8.71842843779233, "flow_matching_loss": 0.043417370319366454, "grad_norm": 0.12057454884052277, "invalid_tail_samples": 24.6, "learning_rate": 8.254986885459572e-05, "loss": 0.048, "positive_teacher_pairs": 26667.1, "relation_loss": 0.004573010001331567, "selected_pairs": 26667.1, "step": 9320, "student_distance_mean": 1012.7263244628906, "teacher_distance_mean": 0.8559191942214965, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.004573010001331567, "weighted_relation_loss": 0.004573010001331567 }, { "action_query_batch_std": 17.743930053710937, "action_query_norm": 779.901123046875, "action_relation_loss": 0.004736182698979974, "auxiliary_loss_weight": 1.0, "epoch": 8.72778297474275, "flow_matching_loss": 0.043171679601073265, "grad_norm": 0.12393547594547272, "invalid_tail_samples": 24.1, "learning_rate": 8.250801189298757e-05, "loss": 0.0479, "positive_teacher_pairs": 26792.7, "relation_loss": 0.004736182698979974, "selected_pairs": 26792.7, "step": 9330, "student_distance_mean": 1004.1053283691406, "teacher_distance_mean": 0.8536652147769928, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.004736182698979974, "weighted_relation_loss": 0.004736182698979974 }, { "action_query_batch_std": 17.731979370117188, "action_query_norm": 778.6042419433594, "action_relation_loss": 0.0046990904957056046, "auxiliary_loss_weight": 1.0, "epoch": 8.737137511693172, "flow_matching_loss": 0.04104050919413567, "grad_norm": 0.14971128106117249, "invalid_tail_samples": 26.2, "learning_rate": 8.246611543107967e-05, "loss": 0.0457, "positive_teacher_pairs": 26315.6, "relation_loss": 0.0046990904957056046, "selected_pairs": 26315.6, "step": 9340, "student_distance_mean": 1010.4000427246094, "teacher_distance_mean": 0.8641900658607483, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.0046990904957056046, "weighted_relation_loss": 0.0046990904957056046 }, { "action_query_batch_std": 17.65268611907959, "action_query_norm": 776.918212890625, "action_relation_loss": 0.004641690198332072, "auxiliary_loss_weight": 1.0, "epoch": 8.746492048643592, "flow_matching_loss": 0.042679841816425326, "grad_norm": 0.12382392585277557, "invalid_tail_samples": 23.8, "learning_rate": 8.242417951978018e-05, "loss": 0.0473, "positive_teacher_pairs": 26851.8, "relation_loss": 0.004641690198332072, "selected_pairs": 26851.8, "step": 9350, "student_distance_mean": 1003.0869567871093, "teacher_distance_mean": 0.847886073589325, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.004641690198332072, "weighted_relation_loss": 0.004641690198332072 }, { "action_query_batch_std": 17.57143630981445, "action_query_norm": 770.472607421875, "action_relation_loss": 0.004575672326609492, "auxiliary_loss_weight": 1.0, "epoch": 8.755846585594012, "flow_matching_loss": 0.04322341047227383, "grad_norm": 0.16583922505378723, "invalid_tail_samples": 25.7, "learning_rate": 8.238220421004517e-05, "loss": 0.0478, "positive_teacher_pairs": 26414.5, "relation_loss": 0.004575672326609492, "selected_pairs": 26414.5, "step": 9360, "student_distance_mean": 1000.15439453125, "teacher_distance_mean": 0.8575779855251312, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.004575672326609492, "weighted_relation_loss": 0.004575672326609492 }, { "action_query_batch_std": 17.44719524383545, "action_query_norm": 769.3708557128906, "action_relation_loss": 0.004828258138149977, "auxiliary_loss_weight": 1.0, "epoch": 8.765201122544434, "flow_matching_loss": 0.044878016039729116, "grad_norm": 0.15462422370910645, "invalid_tail_samples": 22.8, "learning_rate": 8.234018955287859e-05, "loss": 0.0497, "positive_teacher_pairs": 27082.6, "relation_loss": 0.004828258138149977, "selected_pairs": 27082.6, "step": 9370, "student_distance_mean": 990.3122985839843, "teacher_distance_mean": 0.845087069272995, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.004828258138149977, "weighted_relation_loss": 0.004828258138149977 }, { "action_query_batch_std": 17.633059692382812, "action_query_norm": 775.4857360839844, "action_relation_loss": 0.004941722890362143, "auxiliary_loss_weight": 1.0, "epoch": 8.774555659494855, "flow_matching_loss": 0.04215314462780952, "grad_norm": 0.11121857911348343, "invalid_tail_samples": 22.2, "learning_rate": 8.229813559933224e-05, "loss": 0.0471, "positive_teacher_pairs": 27225.4, "relation_loss": 0.004941722890362143, "selected_pairs": 27225.4, "step": 9380, "student_distance_mean": 1004.5051086425781, "teacher_distance_mean": 0.8554318130016327, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.004941722890362143, "weighted_relation_loss": 0.004941722890362143 }, { "action_query_batch_std": 17.87355270385742, "action_query_norm": 787.2057434082031, "action_relation_loss": 0.0046107228845357895, "auxiliary_loss_weight": 1.0, "epoch": 8.783910196445277, "flow_matching_loss": 0.04520286843180656, "grad_norm": 0.13320128619670868, "invalid_tail_samples": 25.7, "learning_rate": 8.22560424005056e-05, "loss": 0.0498, "positive_teacher_pairs": 26422.0, "relation_loss": 0.0046107228845357895, "selected_pairs": 26422.0, "step": 9390, "student_distance_mean": 1016.7891845703125, "teacher_distance_mean": 0.858987295627594, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.0046107228845357895, "weighted_relation_loss": 0.0046107228845357895 }, { "action_query_batch_std": 17.915514373779295, "action_query_norm": 789.4643615722656, "action_relation_loss": 0.0048456558026373385, "auxiliary_loss_weight": 1.0, "epoch": 8.793264733395697, "flow_matching_loss": 0.04211631678044796, "grad_norm": 0.14901253581047058, "invalid_tail_samples": 22.1, "learning_rate": 8.22139100075459e-05, "loss": 0.047, "positive_teacher_pairs": 27243.0, "relation_loss": 0.0048456558026373385, "selected_pairs": 27243.0, "step": 9400, "student_distance_mean": 1017.871826171875, "teacher_distance_mean": 0.8569692969322205, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0048456558026373385, "weighted_relation_loss": 0.0048456558026373385 }, { "action_query_batch_std": 17.781562995910644, "action_query_norm": 781.540087890625, "action_relation_loss": 0.004889365425333381, "auxiliary_loss_weight": 1.0, "epoch": 8.802619270346117, "flow_matching_loss": 0.04271748848259449, "grad_norm": 0.12017159909009933, "invalid_tail_samples": 25.1, "learning_rate": 8.217173847164799e-05, "loss": 0.0476, "positive_teacher_pairs": 26548.0, "relation_loss": 0.004889365425333381, "selected_pairs": 26548.0, "step": 9410, "student_distance_mean": 1006.1986206054687, "teacher_distance_mean": 0.8524632453918457, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.004889365425333381, "weighted_relation_loss": 0.004889365425333381 }, { "action_query_batch_std": 18.292940139770508, "action_query_norm": 802.7601196289063, "action_relation_loss": 0.004577834019437432, "auxiliary_loss_weight": 1.0, "epoch": 8.811973807296539, "flow_matching_loss": 0.04247496835887432, "grad_norm": 0.1314309537410736, "invalid_tail_samples": 26.7, "learning_rate": 8.212952784405422e-05, "loss": 0.0471, "positive_teacher_pairs": 26180.6, "relation_loss": 0.004577834019437432, "selected_pairs": 26180.6, "step": 9420, "student_distance_mean": 1040.7071838378906, "teacher_distance_mean": 0.8604609131813049, "valid_action_samples": 229.3, "weighted_auxiliary_loss": 0.004577834019437432, "weighted_relation_loss": 0.004577834019437432 }, { "action_query_batch_std": 17.860942840576172, "action_query_norm": 788.9857604980468, "action_relation_loss": 0.004905920336022973, "auxiliary_loss_weight": 1.0, "epoch": 8.82132834424696, "flow_matching_loss": 0.04259691424667835, "grad_norm": 0.13759255409240723, "invalid_tail_samples": 25.4, "learning_rate": 8.208727817605451e-05, "loss": 0.0475, "positive_teacher_pairs": 26478.8, "relation_loss": 0.004905920336022973, "selected_pairs": 26478.8, "step": 9430, "student_distance_mean": 1019.1626586914062, "teacher_distance_mean": 0.8485219478607178, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.004905920336022973, "weighted_relation_loss": 0.004905920336022973 }, { "action_query_batch_std": 17.791611862182616, "action_query_norm": 781.3372863769531, "action_relation_loss": 0.004772931570187211, "auxiliary_loss_weight": 1.0, "epoch": 8.830682881197381, "flow_matching_loss": 0.04388545341789722, "grad_norm": 0.14497241377830505, "invalid_tail_samples": 25.7, "learning_rate": 8.204498951898618e-05, "loss": 0.0487, "positive_teacher_pairs": 26415.1, "relation_loss": 0.004772931570187211, "selected_pairs": 26415.1, "step": 9440, "student_distance_mean": 1011.8204650878906, "teacher_distance_mean": 0.8543251752853394, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.004772931570187211, "weighted_relation_loss": 0.004772931570187211 }, { "action_query_batch_std": 17.800934410095216, "action_query_norm": 781.6152954101562, "action_relation_loss": 0.0046720629092305895, "auxiliary_loss_weight": 1.0, "epoch": 8.840037418147801, "flow_matching_loss": 0.04334899708628655, "grad_norm": 0.11477049440145493, "invalid_tail_samples": 25.7, "learning_rate": 8.200266192423395e-05, "loss": 0.048, "positive_teacher_pairs": 26411.2, "relation_loss": 0.0046720629092305895, "selected_pairs": 26411.2, "step": 9450, "student_distance_mean": 1015.2148620605469, "teacher_distance_mean": 0.8563586354255677, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.0046720629092305895, "weighted_relation_loss": 0.0046720629092305895 }, { "action_query_batch_std": 17.859079551696777, "action_query_norm": 781.9669738769531, "action_relation_loss": 0.004641833947971463, "auxiliary_loss_weight": 1.0, "epoch": 8.849391955098223, "flow_matching_loss": 0.042382979020476344, "grad_norm": 0.14103959500789642, "invalid_tail_samples": 22.8, "learning_rate": 8.196029544322981e-05, "loss": 0.047, "positive_teacher_pairs": 27088.9, "relation_loss": 0.004641833947971463, "selected_pairs": 27088.9, "step": 9460, "student_distance_mean": 1011.9301086425781, "teacher_distance_mean": 0.860787284374237, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.004641833947971463, "weighted_relation_loss": 0.004641833947971463 }, { "action_query_batch_std": 17.89949588775635, "action_query_norm": 784.6552368164063, "action_relation_loss": 0.004785161558538675, "auxiliary_loss_weight": 1.0, "epoch": 8.858746492048644, "flow_matching_loss": 0.04360455498099327, "grad_norm": 0.15607433021068573, "invalid_tail_samples": 23.1, "learning_rate": 8.191789012745305e-05, "loss": 0.0484, "positive_teacher_pairs": 27009.4, "relation_loss": 0.004785161558538675, "selected_pairs": 27009.4, "step": 9470, "student_distance_mean": 1014.7586181640625, "teacher_distance_mean": 0.849185562133789, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.004785161558538675, "weighted_relation_loss": 0.004785161558538675 }, { "action_query_batch_std": 17.821125984191895, "action_query_norm": 786.1292358398438, "action_relation_loss": 0.0047172319144010546, "auxiliary_loss_weight": 1.0, "epoch": 8.868101028999064, "flow_matching_loss": 0.042800988629460336, "grad_norm": 0.16740994155406952, "invalid_tail_samples": 21.4, "learning_rate": 8.187544602843014e-05, "loss": 0.0475, "positive_teacher_pairs": 27410.5, "relation_loss": 0.0047172319144010546, "selected_pairs": 27410.5, "step": 9480, "student_distance_mean": 1013.2242126464844, "teacher_distance_mean": 0.8500980257987976, "valid_action_samples": 234.6, "weighted_auxiliary_loss": 0.0047172319144010546, "weighted_relation_loss": 0.0047172319144010546 }, { "action_query_batch_std": 17.907888221740723, "action_query_norm": 784.6838012695313, "action_relation_loss": 0.004732220899313688, "auxiliary_loss_weight": 1.0, "epoch": 8.877455565949486, "flow_matching_loss": 0.043506179377436636, "grad_norm": 0.12280333787202835, "invalid_tail_samples": 23.8, "learning_rate": 8.183296319773466e-05, "loss": 0.0482, "positive_teacher_pairs": 26856.2, "relation_loss": 0.004732220899313688, "selected_pairs": 26856.2, "step": 9490, "student_distance_mean": 1014.1240783691406, "teacher_distance_mean": 0.8592406749725342, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.004732220899313688, "weighted_relation_loss": 0.004732220899313688 }, { "action_query_batch_std": 18.014872741699218, "action_query_norm": 791.129931640625, "action_relation_loss": 0.004727862868458032, "auxiliary_loss_weight": 1.0, "epoch": 8.886810102899906, "flow_matching_loss": 0.04180227927863598, "grad_norm": 0.13904957473278046, "invalid_tail_samples": 21.2, "learning_rate": 8.179044168698721e-05, "loss": 0.0465, "positive_teacher_pairs": 27456.7, "relation_loss": 0.004727862868458032, "selected_pairs": 27456.7, "step": 9500, "student_distance_mean": 1024.1202575683594, "teacher_distance_mean": 0.8601311206817627, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.004727862868458032, "weighted_relation_loss": 0.004727862868458032 }, { "action_query_batch_std": 17.6209774017334, "action_query_norm": 777.5474792480469, "action_relation_loss": 0.0047277378849685196, "auxiliary_loss_weight": 1.0, "epoch": 8.896164639850328, "flow_matching_loss": 0.04003851637244225, "grad_norm": 0.12253711372613907, "invalid_tail_samples": 24.5, "learning_rate": 8.174788154785548e-05, "loss": 0.0448, "positive_teacher_pairs": 26688.8, "relation_loss": 0.0047277378849685196, "selected_pairs": 26688.8, "step": 9510, "student_distance_mean": 1001.4529357910156, "teacher_distance_mean": 0.847318708896637, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0047277378849685196, "weighted_relation_loss": 0.0047277378849685196 }, { "action_query_batch_std": 17.71300640106201, "action_query_norm": 780.3299133300782, "action_relation_loss": 0.004478917270898819, "auxiliary_loss_weight": 1.0, "epoch": 8.905519176800748, "flow_matching_loss": 0.04008716233074665, "grad_norm": 0.1442602425813675, "invalid_tail_samples": 24.2, "learning_rate": 8.170528283205403e-05, "loss": 0.0446, "positive_teacher_pairs": 26759.9, "relation_loss": 0.004478917270898819, "selected_pairs": 26759.9, "step": 9520, "student_distance_mean": 1005.8528930664063, "teacher_distance_mean": 0.8535420715808868, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.004478917270898819, "weighted_relation_loss": 0.004478917270898819 }, { "action_query_batch_std": 17.915377044677733, "action_query_norm": 788.7976989746094, "action_relation_loss": 0.004580226913094521, "auxiliary_loss_weight": 1.0, "epoch": 8.91487371375117, "flow_matching_loss": 0.043174383044242856, "grad_norm": 0.15367767214775085, "invalid_tail_samples": 24.4, "learning_rate": 8.166264559134435e-05, "loss": 0.0478, "positive_teacher_pairs": 26708.5, "relation_loss": 0.004580226913094521, "selected_pairs": 26708.5, "step": 9530, "student_distance_mean": 1016.4358276367187, "teacher_distance_mean": 0.8594070732593536, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.004580226913094521, "weighted_relation_loss": 0.004580226913094521 }, { "action_query_batch_std": 18.09271869659424, "action_query_norm": 795.9662658691407, "action_relation_loss": 0.00466251908801496, "auxiliary_loss_weight": 1.0, "epoch": 8.92422825070159, "flow_matching_loss": 0.0415020402520895, "grad_norm": 0.11388140916824341, "invalid_tail_samples": 23.3, "learning_rate": 8.161996987753467e-05, "loss": 0.0462, "positive_teacher_pairs": 26968.2, "relation_loss": 0.00466251908801496, "selected_pairs": 26968.2, "step": 9540, "student_distance_mean": 1027.3040466308594, "teacher_distance_mean": 0.8582861006259919, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.00466251908801496, "weighted_relation_loss": 0.00466251908801496 }, { "action_query_batch_std": 18.04876136779785, "action_query_norm": 795.1623107910157, "action_relation_loss": 0.004700808972120285, "auxiliary_loss_weight": 1.0, "epoch": 8.93358278765201, "flow_matching_loss": 0.04392820335924626, "grad_norm": 0.13112598657608032, "invalid_tail_samples": 25.9, "learning_rate": 8.157725574248e-05, "loss": 0.0486, "positive_teacher_pairs": 26371.3, "relation_loss": 0.004700808972120285, "selected_pairs": 26371.3, "step": 9550, "student_distance_mean": 1026.7471008300781, "teacher_distance_mean": 0.8556404113769531, "valid_action_samples": 230.1, "weighted_auxiliary_loss": 0.004700808972120285, "weighted_relation_loss": 0.004700808972120285 }, { "action_query_batch_std": 18.09036178588867, "action_query_norm": 795.6974670410157, "action_relation_loss": 0.004682341264560819, "auxiliary_loss_weight": 1.0, "epoch": 8.942937324602433, "flow_matching_loss": 0.044094428420066833, "grad_norm": 0.11214078962802887, "invalid_tail_samples": 25.1, "learning_rate": 8.153450323808209e-05, "loss": 0.0488, "positive_teacher_pairs": 26551.3, "relation_loss": 0.004682341264560819, "selected_pairs": 26551.3, "step": 9560, "student_distance_mean": 1027.8346740722657, "teacher_distance_mean": 0.8579295158386231, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.004682341264560819, "weighted_relation_loss": 0.004682341264560819 }, { "action_query_batch_std": 17.85380687713623, "action_query_norm": 787.8007385253907, "action_relation_loss": 0.004791607987135649, "auxiliary_loss_weight": 1.0, "epoch": 8.952291861552853, "flow_matching_loss": 0.0396807424724102, "grad_norm": 0.13134562969207764, "invalid_tail_samples": 23.9, "learning_rate": 8.149171241628923e-05, "loss": 0.0445, "positive_teacher_pairs": 26832.9, "relation_loss": 0.004791607987135649, "selected_pairs": 26832.9, "step": 9570, "student_distance_mean": 1015.8295959472656, "teacher_distance_mean": 0.8480618178844452, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.004791607987135649, "weighted_relation_loss": 0.004791607987135649 }, { "action_query_batch_std": 17.901027297973634, "action_query_norm": 783.3072814941406, "action_relation_loss": 0.004562144633382559, "auxiliary_loss_weight": 1.0, "epoch": 8.961646398503275, "flow_matching_loss": 0.04302410632371902, "grad_norm": 0.14775033295154572, "invalid_tail_samples": 24.4, "learning_rate": 8.144888332909631e-05, "loss": 0.0476, "positive_teacher_pairs": 26706.4, "relation_loss": 0.004562144633382559, "selected_pairs": 26706.4, "step": 9580, "student_distance_mean": 1014.6909851074219, "teacher_distance_mean": 0.8566411852836608, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.004562144633382559, "weighted_relation_loss": 0.004562144633382559 }, { "action_query_batch_std": 17.579716682434082, "action_query_norm": 775.2048217773438, "action_relation_loss": 0.004772523371502757, "auxiliary_loss_weight": 1.0, "epoch": 8.971000935453695, "flow_matching_loss": 0.043020155653357504, "grad_norm": 0.16389517486095428, "invalid_tail_samples": 21.9, "learning_rate": 8.14060160285447e-05, "loss": 0.0478, "positive_teacher_pairs": 27293.5, "relation_loss": 0.004772523371502757, "selected_pairs": 27293.5, "step": 9590, "student_distance_mean": 995.5145629882812, "teacher_distance_mean": 0.8483127593994141, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.004772523371502757, "weighted_relation_loss": 0.004772523371502757 }, { "action_query_batch_std": 17.702878952026367, "action_query_norm": 782.4436950683594, "action_relation_loss": 0.004631318664178252, "auxiliary_loss_weight": 1.0, "epoch": 8.980355472404115, "flow_matching_loss": 0.04157202765345573, "grad_norm": 0.1390896886587143, "invalid_tail_samples": 23.0, "learning_rate": 8.136311056672223e-05, "loss": 0.0462, "positive_teacher_pairs": 27040.8, "relation_loss": 0.004631318664178252, "selected_pairs": 27040.8, "step": 9600, "student_distance_mean": 1005.3951965332031, "teacher_distance_mean": 0.8440395653247833, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.004631318664178252, "weighted_relation_loss": 0.004631318664178252 }, { "action_query_batch_std": 18.041372871398927, "action_query_norm": 795.337109375, "action_relation_loss": 0.00495205782353878, "auxiliary_loss_weight": 1.0, "epoch": 8.989710009354537, "flow_matching_loss": 0.04068166427314281, "grad_norm": 0.12655001878738403, "invalid_tail_samples": 23.4, "learning_rate": 8.132016699576308e-05, "loss": 0.0456, "positive_teacher_pairs": 26944.2, "relation_loss": 0.00495205782353878, "selected_pairs": 26944.2, "step": 9610, "student_distance_mean": 1022.3252197265625, "teacher_distance_mean": 0.8556291282176971, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.00495205782353878, "weighted_relation_loss": 0.00495205782353878 }, { "action_query_batch_std": 18.092318725585937, "action_query_norm": 797.2786193847656, "action_relation_loss": 0.0046267412602901455, "auxiliary_loss_weight": 1.0, "epoch": 8.999064546304957, "flow_matching_loss": 0.04317373745143414, "grad_norm": 0.10319627821445465, "invalid_tail_samples": 25.7, "learning_rate": 8.127718536784771e-05, "loss": 0.0478, "positive_teacher_pairs": 26407.7, "relation_loss": 0.0046267412602901455, "selected_pairs": 26407.7, "step": 9620, "student_distance_mean": 1026.5566345214843, "teacher_distance_mean": 0.8562273681163788, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.0046267412602901455, "weighted_relation_loss": 0.0046267412602901455 }, { "action_query_batch_std": 17.89536018371582, "action_query_norm": 789.9556945800781, "action_relation_loss": 0.004421505774371326, "auxiliary_loss_weight": 1.0, "epoch": 9.00841908325538, "flow_matching_loss": 0.04171429648995399, "grad_norm": 0.11046556383371353, "invalid_tail_samples": 20.0, "learning_rate": 8.12341657352029e-05, "loss": 0.0461, "positive_teacher_pairs": 24759.8, "relation_loss": 0.004421505774371326, "selected_pairs": 24759.8, "step": 9630, "student_distance_mean": 1014.7912231445313, "teacher_distance_mean": 0.8503988027572632, "valid_action_samples": 216.1, "weighted_auxiliary_loss": 0.004421505774371326, "weighted_relation_loss": 0.004421505774371326 }, { "action_query_batch_std": 17.92118282318115, "action_query_norm": 789.5955810546875, "action_relation_loss": 0.004488905100151897, "auxiliary_loss_weight": 1.0, "epoch": 9.0177736202058, "flow_matching_loss": 0.04071961604058742, "grad_norm": 0.13444948196411133, "invalid_tail_samples": 24.5, "learning_rate": 8.119110815010151e-05, "loss": 0.0452, "positive_teacher_pairs": 26692.2, "relation_loss": 0.004488905100151897, "selected_pairs": 26692.2, "step": 9640, "student_distance_mean": 1018.1167785644532, "teacher_distance_mean": 0.853518408536911, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.004488905100151897, "weighted_relation_loss": 0.004488905100151897 }, { "action_query_batch_std": 18.195884895324706, "action_query_norm": 800.899365234375, "action_relation_loss": 0.004390545422211289, "auxiliary_loss_weight": 1.0, "epoch": 9.027128157156222, "flow_matching_loss": 0.04230835847556591, "grad_norm": 0.11825926601886749, "invalid_tail_samples": 23.7, "learning_rate": 8.114801266486261e-05, "loss": 0.0467, "positive_teacher_pairs": 26873.4, "relation_loss": 0.004390545422211289, "selected_pairs": 26873.4, "step": 9650, "student_distance_mean": 1031.1830017089844, "teacher_distance_mean": 0.8578909158706665, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.004390545422211289, "weighted_relation_loss": 0.004390545422211289 }, { "action_query_batch_std": 18.066143798828126, "action_query_norm": 795.95107421875, "action_relation_loss": 0.004548689979128539, "auxiliary_loss_weight": 1.0, "epoch": 9.036482694106642, "flow_matching_loss": 0.041939624771475795, "grad_norm": 0.1438911408185959, "invalid_tail_samples": 23.7, "learning_rate": 8.110487933185122e-05, "loss": 0.0465, "positive_teacher_pairs": 26883.5, "relation_loss": 0.004548689979128539, "selected_pairs": 26883.5, "step": 9660, "student_distance_mean": 1021.9403625488281, "teacher_distance_mean": 0.8559792697429657, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.004548689979128539, "weighted_relation_loss": 0.004548689979128539 }, { "action_query_batch_std": 18.059247398376463, "action_query_norm": 794.1515991210938, "action_relation_loss": 0.004655542597174644, "auxiliary_loss_weight": 1.0, "epoch": 9.045837231057062, "flow_matching_loss": 0.04069060198962689, "grad_norm": 0.15337230265140533, "invalid_tail_samples": 23.8, "learning_rate": 8.106170820347847e-05, "loss": 0.0453, "positive_teacher_pairs": 26850.6, "relation_loss": 0.004655542597174644, "selected_pairs": 26850.6, "step": 9670, "student_distance_mean": 1019.1153747558594, "teacher_distance_mean": 0.849178946018219, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.004655542597174644, "weighted_relation_loss": 0.004655542597174644 }, { "action_query_batch_std": 18.14233570098877, "action_query_norm": 797.9141052246093, "action_relation_loss": 0.004432597360573709, "auxiliary_loss_weight": 1.0, "epoch": 9.055191768007484, "flow_matching_loss": 0.04022395238280296, "grad_norm": 0.14005091786384583, "invalid_tail_samples": 23.0, "learning_rate": 8.101849933220132e-05, "loss": 0.0447, "positive_teacher_pairs": 27031.8, "relation_loss": 0.004432597360573709, "selected_pairs": 27031.8, "step": 9680, "student_distance_mean": 1030.9314758300782, "teacher_distance_mean": 0.8557874321937561, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.004432597360573709, "weighted_relation_loss": 0.004432597360573709 }, { "action_query_batch_std": 18.152591133117674, "action_query_norm": 795.7483642578125, "action_relation_loss": 0.004566087294369936, "auxiliary_loss_weight": 1.0, "epoch": 9.064546304957904, "flow_matching_loss": 0.040760114416480066, "grad_norm": 0.12659788131713867, "invalid_tail_samples": 21.3, "learning_rate": 8.097525277052264e-05, "loss": 0.0453, "positive_teacher_pairs": 27428.1, "relation_loss": 0.004566087294369936, "selected_pairs": 27428.1, "step": 9690, "student_distance_mean": 1027.9628479003907, "teacher_distance_mean": 0.8606919765472412, "valid_action_samples": 234.7, "weighted_auxiliary_loss": 0.004566087294369936, "weighted_relation_loss": 0.004566087294369936 }, { "action_query_batch_std": 18.1304349899292, "action_query_norm": 793.9982482910157, "action_relation_loss": 0.004590808553621173, "auxiliary_loss_weight": 1.0, "epoch": 9.073900841908326, "flow_matching_loss": 0.04193824157118797, "grad_norm": 0.11205271631479263, "invalid_tail_samples": 23.0, "learning_rate": 8.093196857099106e-05, "loss": 0.0465, "positive_teacher_pairs": 27039.1, "relation_loss": 0.004590808553621173, "selected_pairs": 27039.1, "step": 9700, "student_distance_mean": 1031.2203735351563, "teacher_distance_mean": 0.8559840500354767, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.004590808553621173, "weighted_relation_loss": 0.004590808553621173 }, { "action_query_batch_std": 17.997236251831055, "action_query_norm": 791.1715515136718, "action_relation_loss": 0.004555564420297742, "auxiliary_loss_weight": 1.0, "epoch": 9.083255378858746, "flow_matching_loss": 0.04141099900007248, "grad_norm": 0.12889380753040314, "invalid_tail_samples": 22.8, "learning_rate": 8.088864678620096e-05, "loss": 0.046, "positive_teacher_pairs": 27078.4, "relation_loss": 0.004555564420297742, "selected_pairs": 27078.4, "step": 9710, "student_distance_mean": 1021.0180114746094, "teacher_distance_mean": 0.8510213673114777, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.004555564420297742, "weighted_relation_loss": 0.004555564420297742 }, { "action_query_batch_std": 18.096975135803223, "action_query_norm": 792.0841552734375, "action_relation_loss": 0.004405293194577098, "auxiliary_loss_weight": 1.0, "epoch": 9.092609915809167, "flow_matching_loss": 0.04014495685696602, "grad_norm": 0.12587757408618927, "invalid_tail_samples": 24.6, "learning_rate": 8.084528746879243e-05, "loss": 0.0446, "positive_teacher_pairs": 26664.5, "relation_loss": 0.004405293194577098, "selected_pairs": 26664.5, "step": 9720, "student_distance_mean": 1027.2598937988282, "teacher_distance_mean": 0.8535687625408173, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.004405293194577098, "weighted_relation_loss": 0.004405293194577098 }, { "action_query_batch_std": 18.20708770751953, "action_query_norm": 798.0659057617188, "action_relation_loss": 0.004486191552132368, "auxiliary_loss_weight": 1.0, "epoch": 9.101964452759589, "flow_matching_loss": 0.04048793688416481, "grad_norm": 0.11331401765346527, "invalid_tail_samples": 22.1, "learning_rate": 8.080189067145108e-05, "loss": 0.045, "positive_teacher_pairs": 27248.0, "relation_loss": 0.004486191552132368, "selected_pairs": 27248.0, "step": 9730, "student_distance_mean": 1032.038525390625, "teacher_distance_mean": 0.8639096915721893, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.004486191552132368, "weighted_relation_loss": 0.004486191552132368 }, { "action_query_batch_std": 17.83088665008545, "action_query_norm": 787.4635009765625, "action_relation_loss": 0.0046089252457022665, "auxiliary_loss_weight": 1.0, "epoch": 9.111318989710009, "flow_matching_loss": 0.041812263801693915, "grad_norm": 0.16029822826385498, "invalid_tail_samples": 23.2, "learning_rate": 8.075845644690813e-05, "loss": 0.0464, "positive_teacher_pairs": 26988.2, "relation_loss": 0.0046089252457022665, "selected_pairs": 26988.2, "step": 9740, "student_distance_mean": 1013.7637512207032, "teacher_distance_mean": 0.8465313851833344, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0046089252457022665, "weighted_relation_loss": 0.0046089252457022665 }, { "action_query_batch_std": 17.952318000793458, "action_query_norm": 788.7181701660156, "action_relation_loss": 0.0044523305259644985, "auxiliary_loss_weight": 1.0, "epoch": 9.12067352666043, "flow_matching_loss": 0.03946783691644669, "grad_norm": 0.13328252732753754, "invalid_tail_samples": 25.5, "learning_rate": 8.07149848479403e-05, "loss": 0.0439, "positive_teacher_pairs": 26454.8, "relation_loss": 0.0044523305259644985, "selected_pairs": 26454.8, "step": 9750, "student_distance_mean": 1022.44638671875, "teacher_distance_mean": 0.8530336201190949, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0044523305259644985, "weighted_relation_loss": 0.0044523305259644985 }, { "action_query_batch_std": 17.909877204895018, "action_query_norm": 786.2180603027343, "action_relation_loss": 0.004599197395145893, "auxiliary_loss_weight": 1.0, "epoch": 9.130028063610851, "flow_matching_loss": 0.04254856966435909, "grad_norm": 0.15723296999931335, "invalid_tail_samples": 22.9, "learning_rate": 8.067147592736962e-05, "loss": 0.0471, "positive_teacher_pairs": 27063.0, "relation_loss": 0.004599197395145893, "selected_pairs": 27063.0, "step": 9760, "student_distance_mean": 1019.5232421875, "teacher_distance_mean": 0.8509238004684448, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.004599197395145893, "weighted_relation_loss": 0.004599197395145893 }, { "action_query_batch_std": 18.08032970428467, "action_query_norm": 791.077734375, "action_relation_loss": 0.004620066145434976, "auxiliary_loss_weight": 1.0, "epoch": 9.139382600561273, "flow_matching_loss": 0.040624509751796725, "grad_norm": 0.17975164949893951, "invalid_tail_samples": 25.5, "learning_rate": 8.062792973806357e-05, "loss": 0.0452, "positive_teacher_pairs": 26458.3, "relation_loss": 0.004620066145434976, "selected_pairs": 26458.3, "step": 9770, "student_distance_mean": 1029.8287353515625, "teacher_distance_mean": 0.8586795508861542, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.004620066145434976, "weighted_relation_loss": 0.004620066145434976 }, { "action_query_batch_std": 18.133933067321777, "action_query_norm": 795.1859069824219, "action_relation_loss": 0.004341484210453927, "auxiliary_loss_weight": 1.0, "epoch": 9.148737137511693, "flow_matching_loss": 0.040032001584768294, "grad_norm": 0.19716669619083405, "invalid_tail_samples": 24.3, "learning_rate": 8.058434633293485e-05, "loss": 0.0444, "positive_teacher_pairs": 26735.5, "relation_loss": 0.004341484210453927, "selected_pairs": 26735.5, "step": 9780, "student_distance_mean": 1033.9900634765625, "teacher_distance_mean": 0.8601351320743561, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.004341484210453927, "weighted_relation_loss": 0.004341484210453927 }, { "action_query_batch_std": 18.103134155273438, "action_query_norm": 793.4372314453125, "action_relation_loss": 0.004282083897851408, "auxiliary_loss_weight": 1.0, "epoch": 9.158091674462113, "flow_matching_loss": 0.039798511564731597, "grad_norm": 0.13457131385803223, "invalid_tail_samples": 25.3, "learning_rate": 8.054072576494143e-05, "loss": 0.0441, "positive_teacher_pairs": 26499.6, "relation_loss": 0.004282083897851408, "selected_pairs": 26499.6, "step": 9790, "student_distance_mean": 1023.8423278808593, "teacher_distance_mean": 0.8533718585968018, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.004282083897851408, "weighted_relation_loss": 0.004282083897851408 }, { "action_query_batch_std": 18.145770645141603, "action_query_norm": 793.8599304199219, "action_relation_loss": 0.004320603585802019, "auxiliary_loss_weight": 1.0, "epoch": 9.167446211412535, "flow_matching_loss": 0.04150369875133038, "grad_norm": 0.1628020852804184, "invalid_tail_samples": 23.1, "learning_rate": 8.04970680870864e-05, "loss": 0.0458, "positive_teacher_pairs": 27030.0, "relation_loss": 0.004320603585802019, "selected_pairs": 27030.0, "step": 9800, "student_distance_mean": 1028.697528076172, "teacher_distance_mean": 0.8572708010673523, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.004320603585802019, "weighted_relation_loss": 0.004320603585802019 }, { "action_query_batch_std": 17.970205307006836, "action_query_norm": 787.1719848632813, "action_relation_loss": 0.004753026086837054, "auxiliary_loss_weight": 1.0, "epoch": 9.176800748362956, "flow_matching_loss": 0.04114764928817749, "grad_norm": 0.1298885941505432, "invalid_tail_samples": 24.0, "learning_rate": 8.045337335241793e-05, "loss": 0.0459, "positive_teacher_pairs": 26800.4, "relation_loss": 0.004753026086837054, "selected_pairs": 26800.4, "step": 9810, "student_distance_mean": 1020.1680847167969, "teacher_distance_mean": 0.8466021120548248, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.004753026086837054, "weighted_relation_loss": 0.004753026086837054 }, { "action_query_batch_std": 18.10704460144043, "action_query_norm": 793.2849609375, "action_relation_loss": 0.004527246858924627, "auxiliary_loss_weight": 1.0, "epoch": 9.186155285313378, "flow_matching_loss": 0.040297366306185724, "grad_norm": 0.17983640730381012, "invalid_tail_samples": 23.2, "learning_rate": 8.040964161402932e-05, "loss": 0.0448, "positive_teacher_pairs": 26989.0, "relation_loss": 0.004527246858924627, "selected_pairs": 26989.0, "step": 9820, "student_distance_mean": 1029.390234375, "teacher_distance_mean": 0.8527725577354431, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.004527246858924627, "weighted_relation_loss": 0.004527246858924627 }, { "action_query_batch_std": 18.030318450927734, "action_query_norm": 792.733642578125, "action_relation_loss": 0.0045441525988280775, "auxiliary_loss_weight": 1.0, "epoch": 9.195509822263798, "flow_matching_loss": 0.04110245518386364, "grad_norm": 0.18179796636104584, "invalid_tail_samples": 22.4, "learning_rate": 8.036587292505869e-05, "loss": 0.0456, "positive_teacher_pairs": 27173.4, "relation_loss": 0.0045441525988280775, "selected_pairs": 27173.4, "step": 9830, "student_distance_mean": 1022.5747741699219, "teacher_distance_mean": 0.846016275882721, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.0045441525988280775, "weighted_relation_loss": 0.0045441525988280775 }, { "action_query_batch_std": 17.904927253723145, "action_query_norm": 787.1803771972657, "action_relation_loss": 0.00445514777675271, "auxiliary_loss_weight": 1.0, "epoch": 9.204864359214218, "flow_matching_loss": 0.04223985150456429, "grad_norm": 0.1354815810918808, "invalid_tail_samples": 23.1, "learning_rate": 8.032206733868912e-05, "loss": 0.0467, "positive_teacher_pairs": 27010.4, "relation_loss": 0.00445514777675271, "selected_pairs": 27010.4, "step": 9840, "student_distance_mean": 1017.6590881347656, "teacher_distance_mean": 0.846471506357193, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.00445514777675271, "weighted_relation_loss": 0.00445514777675271 }, { "action_query_batch_std": 17.92405414581299, "action_query_norm": 788.171142578125, "action_relation_loss": 0.004527379339560866, "auxiliary_loss_weight": 1.0, "epoch": 9.21421889616464, "flow_matching_loss": 0.041872617602348325, "grad_norm": 0.17231230437755585, "invalid_tail_samples": 24.9, "learning_rate": 8.027822490814858e-05, "loss": 0.0464, "positive_teacher_pairs": 26600.0, "relation_loss": 0.004527379339560866, "selected_pairs": 26600.0, "step": 9850, "student_distance_mean": 1021.5788208007813, "teacher_distance_mean": 0.8485131978988647, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.004527379339560866, "weighted_relation_loss": 0.004527379339560866 }, { "action_query_batch_std": 18.16932907104492, "action_query_norm": 797.6992004394531, "action_relation_loss": 0.004513772344216705, "auxiliary_loss_weight": 1.0, "epoch": 9.22357343311506, "flow_matching_loss": 0.042682959139347075, "grad_norm": 0.12287607789039612, "invalid_tail_samples": 23.0, "learning_rate": 8.023434568670972e-05, "loss": 0.0472, "positive_teacher_pairs": 27033.0, "relation_loss": 0.004513772344216705, "selected_pairs": 27033.0, "step": 9860, "student_distance_mean": 1032.6865783691405, "teacher_distance_mean": 0.8528063893318176, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.004513772344216705, "weighted_relation_loss": 0.004513772344216705 }, { "action_query_batch_std": 18.34268856048584, "action_query_norm": 798.5102905273437, "action_relation_loss": 0.0043228124268352985, "auxiliary_loss_weight": 1.0, "epoch": 9.232927970065482, "flow_matching_loss": 0.041658437624573705, "grad_norm": 0.11681770533323288, "invalid_tail_samples": 22.9, "learning_rate": 8.019042972768992e-05, "loss": 0.046, "positive_teacher_pairs": 27059.4, "relation_loss": 0.0043228124268352985, "selected_pairs": 27059.4, "step": 9870, "student_distance_mean": 1046.3730407714843, "teacher_distance_mean": 0.866274493932724, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0043228124268352985, "weighted_relation_loss": 0.0043228124268352985 }, { "action_query_batch_std": 17.907649040222168, "action_query_norm": 784.9083679199218, "action_relation_loss": 0.0046511964406818155, "auxiliary_loss_weight": 1.0, "epoch": 9.242282507015902, "flow_matching_loss": 0.04025122225284576, "grad_norm": 0.11324812471866608, "invalid_tail_samples": 22.6, "learning_rate": 8.014647708445124e-05, "loss": 0.0449, "positive_teacher_pairs": 27130.3, "relation_loss": 0.0046511964406818155, "selected_pairs": 27130.3, "step": 9880, "student_distance_mean": 1015.3407409667968, "teacher_distance_mean": 0.8426767706871032, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0046511964406818155, "weighted_relation_loss": 0.0046511964406818155 }, { "action_query_batch_std": 18.29159622192383, "action_query_norm": 797.0051391601562, "action_relation_loss": 0.0043427682714536784, "auxiliary_loss_weight": 1.0, "epoch": 9.251637043966324, "flow_matching_loss": 0.03869331814348698, "grad_norm": 0.10132317990064621, "invalid_tail_samples": 24.3, "learning_rate": 8.010248781040027e-05, "loss": 0.043, "positive_teacher_pairs": 26738.0, "relation_loss": 0.0043427682714536784, "selected_pairs": 26738.0, "step": 9890, "student_distance_mean": 1034.3788757324219, "teacher_distance_mean": 0.8584299087524414, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0043427682714536784, "weighted_relation_loss": 0.0043427682714536784 }, { "action_query_batch_std": 18.037723350524903, "action_query_norm": 790.5616943359375, "action_relation_loss": 0.004436020134016871, "auxiliary_loss_weight": 1.0, "epoch": 9.260991580916745, "flow_matching_loss": 0.04153507575392723, "grad_norm": 0.13133908808231354, "invalid_tail_samples": 25.8, "learning_rate": 8.005846195898814e-05, "loss": 0.046, "positive_teacher_pairs": 26387.5, "relation_loss": 0.004436020134016871, "selected_pairs": 26387.5, "step": 9900, "student_distance_mean": 1026.0530334472655, "teacher_distance_mean": 0.8450894773006439, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.004436020134016871, "weighted_relation_loss": 0.004436020134016871 }, { "action_query_batch_std": 18.107961463928223, "action_query_norm": 796.5377136230469, "action_relation_loss": 0.004525597812607885, "auxiliary_loss_weight": 1.0, "epoch": 9.270346117867165, "flow_matching_loss": 0.0393491979688406, "grad_norm": 0.1421174257993698, "invalid_tail_samples": 21.6, "learning_rate": 8.00143995837104e-05, "loss": 0.0439, "positive_teacher_pairs": 27361.5, "relation_loss": 0.004525597812607885, "selected_pairs": 27361.5, "step": 9910, "student_distance_mean": 1026.8220642089843, "teacher_distance_mean": 0.851405656337738, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.004525597812607885, "weighted_relation_loss": 0.004525597812607885 }, { "action_query_batch_std": 18.230503463745116, "action_query_norm": 801.5487731933594, "action_relation_loss": 0.004350295756012201, "auxiliary_loss_weight": 1.0, "epoch": 9.279700654817587, "flow_matching_loss": 0.04003994427621364, "grad_norm": 0.17161934077739716, "invalid_tail_samples": 21.5, "learning_rate": 7.997030073810698e-05, "loss": 0.0444, "positive_teacher_pairs": 27387.0, "relation_loss": 0.004350295756012201, "selected_pairs": 27387.0, "step": 9920, "student_distance_mean": 1033.066717529297, "teacher_distance_mean": 0.8527666747570037, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.004350295756012201, "weighted_relation_loss": 0.004350295756012201 }, { "action_query_batch_std": 18.32181453704834, "action_query_norm": 800.4952087402344, "action_relation_loss": 0.004331637918949127, "auxiliary_loss_weight": 1.0, "epoch": 9.289055191768007, "flow_matching_loss": 0.04162886701524258, "grad_norm": 0.15851107239723206, "invalid_tail_samples": 25.7, "learning_rate": 7.992616547576217e-05, "loss": 0.046, "positive_teacher_pairs": 26413.0, "relation_loss": 0.004331637918949127, "selected_pairs": 26413.0, "step": 9930, "student_distance_mean": 1044.89296875, "teacher_distance_mean": 0.8601338505744934, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.004331637918949127, "weighted_relation_loss": 0.004331637918949127 }, { "action_query_batch_std": 18.713458251953124, "action_query_norm": 815.4635437011718, "action_relation_loss": 0.004374272096902132, "auxiliary_loss_weight": 1.0, "epoch": 9.298409728718429, "flow_matching_loss": 0.04141325019299984, "grad_norm": 0.2071489691734314, "invalid_tail_samples": 23.3, "learning_rate": 7.988199385030445e-05, "loss": 0.0458, "positive_teacher_pairs": 26960.3, "relation_loss": 0.004374272096902132, "selected_pairs": 26960.3, "step": 9940, "student_distance_mean": 1061.8286376953124, "teacher_distance_mean": 0.8676073133945466, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.004374272096902132, "weighted_relation_loss": 0.004374272096902132 }, { "action_query_batch_std": 18.331451416015625, "action_query_norm": 801.4079406738281, "action_relation_loss": 0.004278885154053569, "auxiliary_loss_weight": 1.0, "epoch": 9.30776426566885, "flow_matching_loss": 0.04009846150875092, "grad_norm": 0.17096439003944397, "invalid_tail_samples": 24.0, "learning_rate": 7.98377859154065e-05, "loss": 0.0444, "positive_teacher_pairs": 26821.6, "relation_loss": 0.004278885154053569, "selected_pairs": 26821.6, "step": 9950, "student_distance_mean": 1042.1600769042968, "teacher_distance_mean": 0.8541478514671326, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.004278885154053569, "weighted_relation_loss": 0.004278885154053569 }, { "action_query_batch_std": 18.447001647949218, "action_query_norm": 804.4644165039062, "action_relation_loss": 0.004246274009346962, "auxiliary_loss_weight": 1.0, "epoch": 9.31711880261927, "flow_matching_loss": 0.04181676208972931, "grad_norm": 0.1825210005044937, "invalid_tail_samples": 23.5, "learning_rate": 7.979354172478516e-05, "loss": 0.0461, "positive_teacher_pairs": 26922.8, "relation_loss": 0.004246274009346962, "selected_pairs": 26922.8, "step": 9960, "student_distance_mean": 1050.2478515625, "teacher_distance_mean": 0.8559262037277222, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.004246274009346962, "weighted_relation_loss": 0.004246274009346962 }, { "action_query_batch_std": 18.29439353942871, "action_query_norm": 800.8109375, "action_relation_loss": 0.004678040277212858, "auxiliary_loss_weight": 1.0, "epoch": 9.326473339569691, "flow_matching_loss": 0.04181262217462063, "grad_norm": 0.14865517616271973, "invalid_tail_samples": 24.0, "learning_rate": 7.974926133220127e-05, "loss": 0.0465, "positive_teacher_pairs": 26801.1, "relation_loss": 0.004678040277212858, "selected_pairs": 26801.1, "step": 9970, "student_distance_mean": 1043.3688354492188, "teacher_distance_mean": 0.850598955154419, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.004678040277212858, "weighted_relation_loss": 0.004678040277212858 }, { "action_query_batch_std": 18.30525932312012, "action_query_norm": 796.6775817871094, "action_relation_loss": 0.004434858122840524, "auxiliary_loss_weight": 1.0, "epoch": 9.335827876520112, "flow_matching_loss": 0.04322719611227512, "grad_norm": 0.17025132477283478, "invalid_tail_samples": 23.2, "learning_rate": 7.970494479145967e-05, "loss": 0.0477, "positive_teacher_pairs": 26986.7, "relation_loss": 0.004434858122840524, "selected_pairs": 26986.7, "step": 9980, "student_distance_mean": 1035.65078125, "teacher_distance_mean": 0.8517721593379974, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.004434858122840524, "weighted_relation_loss": 0.004434858122840524 }, { "action_query_batch_std": 18.317459297180175, "action_query_norm": 801.470849609375, "action_relation_loss": 0.004440905060619116, "auxiliary_loss_weight": 1.0, "epoch": 9.345182413470534, "flow_matching_loss": 0.040039552748203276, "grad_norm": 0.14602869749069214, "invalid_tail_samples": 23.1, "learning_rate": 7.966059215640919e-05, "loss": 0.0445, "positive_teacher_pairs": 27013.6, "relation_loss": 0.004440905060619116, "selected_pairs": 27013.6, "step": 9990, "student_distance_mean": 1039.1927307128906, "teacher_distance_mean": 0.856253319978714, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.004440905060619116, "weighted_relation_loss": 0.004440905060619116 }, { "action_query_batch_std": 18.414753341674803, "action_query_norm": 806.6541015625, "action_relation_loss": 0.004446364077739418, "auxiliary_loss_weight": 1.0, "epoch": 9.354536950420954, "flow_matching_loss": 0.03895458336919546, "grad_norm": 0.1297345757484436, "invalid_tail_samples": 25.6, "learning_rate": 7.961620348094241e-05, "loss": 0.0434, "positive_teacher_pairs": 26443.5, "relation_loss": 0.004446364077739418, "selected_pairs": 26443.5, "step": 10000, "student_distance_mean": 1045.7764587402344, "teacher_distance_mean": 0.8542515516281128, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.004446364077739418, "weighted_relation_loss": 0.004446364077739418 }, { "action_query_batch_std": 18.489146423339843, "action_query_norm": 811.6247802734375, "action_relation_loss": 0.0046440752688795325, "auxiliary_loss_weight": 1.0, "epoch": 9.363891487371376, "flow_matching_loss": 0.04286549463868141, "grad_norm": 0.1332968920469284, "invalid_tail_samples": 27.7, "learning_rate": 7.957177881899577e-05, "loss": 0.0475, "positive_teacher_pairs": 25962.7, "relation_loss": 0.0046440752688795325, "selected_pairs": 25962.7, "step": 10010, "student_distance_mean": 1054.3515991210938, "teacher_distance_mean": 0.8496267616748809, "valid_action_samples": 228.3, "weighted_auxiliary_loss": 0.0046440752688795325, "weighted_relation_loss": 0.0046440752688795325 }, { "action_query_batch_std": 18.55267448425293, "action_query_norm": 812.1012390136718, "action_relation_loss": 0.004245773050934076, "auxiliary_loss_weight": 1.0, "epoch": 9.373246024321796, "flow_matching_loss": 0.04126765727996826, "grad_norm": 0.12790407240390778, "invalid_tail_samples": 22.9, "learning_rate": 7.952731822454944e-05, "loss": 0.0455, "positive_teacher_pairs": 27070.1, "relation_loss": 0.004245773050934076, "selected_pairs": 27070.1, "step": 10020, "student_distance_mean": 1054.2882568359375, "teacher_distance_mean": 0.8517366468906402, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.004245773050934076, "weighted_relation_loss": 0.004245773050934076 }, { "action_query_batch_std": 18.355102920532225, "action_query_norm": 803.1045104980469, "action_relation_loss": 0.004509062576107681, "auxiliary_loss_weight": 1.0, "epoch": 9.382600561272216, "flow_matching_loss": 0.041473382338881495, "grad_norm": 0.09072991460561752, "invalid_tail_samples": 23.5, "learning_rate": 7.948282175162722e-05, "loss": 0.046, "positive_teacher_pairs": 26922.1, "relation_loss": 0.004509062576107681, "selected_pairs": 26922.1, "step": 10030, "student_distance_mean": 1040.7627807617187, "teacher_distance_mean": 0.8492736339569091, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.004509062576107681, "weighted_relation_loss": 0.004509062576107681 }, { "action_query_batch_std": 18.667510414123534, "action_query_norm": 813.4046813964844, "action_relation_loss": 0.004376119887456298, "auxiliary_loss_weight": 1.0, "epoch": 9.391955098222638, "flow_matching_loss": 0.04050685316324234, "grad_norm": 0.13607849180698395, "invalid_tail_samples": 24.1, "learning_rate": 7.943828945429652e-05, "loss": 0.0449, "positive_teacher_pairs": 26778.7, "relation_loss": 0.004376119887456298, "selected_pairs": 26778.7, "step": 10040, "student_distance_mean": 1059.6261291503906, "teacher_distance_mean": 0.8608789682388306, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.004376119887456298, "weighted_relation_loss": 0.004376119887456298 }, { "action_query_batch_std": 18.631396675109862, "action_query_norm": 808.6065185546875, "action_relation_loss": 0.0042417732998728756, "auxiliary_loss_weight": 1.0, "epoch": 9.401309635173059, "flow_matching_loss": 0.042130536213517186, "grad_norm": 0.15619005262851715, "invalid_tail_samples": 24.9, "learning_rate": 7.939372138666827e-05, "loss": 0.0464, "positive_teacher_pairs": 26604.3, "relation_loss": 0.0042417732998728756, "selected_pairs": 26604.3, "step": 10050, "student_distance_mean": 1053.4525146484375, "teacher_distance_mean": 0.8692049324512482, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0042417732998728756, "weighted_relation_loss": 0.0042417732998728756 }, { "action_query_batch_std": 18.04801387786865, "action_query_norm": 786.1795227050782, "action_relation_loss": 0.004203491588123142, "auxiliary_loss_weight": 1.0, "epoch": 9.41066417212348, "flow_matching_loss": 0.03790455143898726, "grad_norm": 0.11554308980703354, "invalid_tail_samples": 24.2, "learning_rate": 7.934911760289692e-05, "loss": 0.0421, "positive_teacher_pairs": 26763.5, "relation_loss": 0.004203491588123142, "selected_pairs": 26763.5, "step": 10060, "student_distance_mean": 1026.4757995605469, "teacher_distance_mean": 0.8455536544322968, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.004203491588123142, "weighted_relation_loss": 0.004203491588123142 }, { "action_query_batch_std": 18.124407958984374, "action_query_norm": 794.9214477539062, "action_relation_loss": 0.004565122211351991, "auxiliary_loss_weight": 1.0, "epoch": 9.4200187090739, "flow_matching_loss": 0.04175974391400814, "grad_norm": 0.11183740198612213, "invalid_tail_samples": 23.2, "learning_rate": 7.930447815718022e-05, "loss": 0.0463, "positive_teacher_pairs": 26992.9, "relation_loss": 0.004565122211351991, "selected_pairs": 26992.9, "step": 10070, "student_distance_mean": 1027.92919921875, "teacher_distance_mean": 0.8410319685935974, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.004565122211351991, "weighted_relation_loss": 0.004565122211351991 }, { "action_query_batch_std": 18.050928688049318, "action_query_norm": 788.1646667480469, "action_relation_loss": 0.004436571197584271, "auxiliary_loss_weight": 1.0, "epoch": 9.429373246024323, "flow_matching_loss": 0.039197083190083505, "grad_norm": 0.12338180840015411, "invalid_tail_samples": 23.2, "learning_rate": 7.925980310375934e-05, "loss": 0.0436, "positive_teacher_pairs": 26988.3, "relation_loss": 0.004436571197584271, "selected_pairs": 26988.3, "step": 10080, "student_distance_mean": 1023.5570129394531, "teacher_distance_mean": 0.8425539791584015, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.004436571197584271, "weighted_relation_loss": 0.004436571197584271 }, { "action_query_batch_std": 18.386549758911134, "action_query_norm": 804.06484375, "action_relation_loss": 0.0044503791723400354, "auxiliary_loss_weight": 1.0, "epoch": 9.438727782974743, "flow_matching_loss": 0.041426945850253104, "grad_norm": 0.1549443006515503, "invalid_tail_samples": 23.5, "learning_rate": 7.921509249691865e-05, "loss": 0.0459, "positive_teacher_pairs": 26924.7, "relation_loss": 0.0044503791723400354, "selected_pairs": 26924.7, "step": 10090, "student_distance_mean": 1046.4800170898438, "teacher_distance_mean": 0.853213119506836, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0044503791723400354, "weighted_relation_loss": 0.0044503791723400354 }, { "action_query_batch_std": 18.4641263961792, "action_query_norm": 804.2044677734375, "action_relation_loss": 0.004365176241844892, "auxiliary_loss_weight": 1.0, "epoch": 9.448082319925163, "flow_matching_loss": 0.041058003529906274, "grad_norm": 0.15129701793193817, "invalid_tail_samples": 24.2, "learning_rate": 7.917034639098579e-05, "loss": 0.0454, "positive_teacher_pairs": 26757.3, "relation_loss": 0.004365176241844892, "selected_pairs": 26757.3, "step": 10100, "student_distance_mean": 1051.4268005371093, "teacher_distance_mean": 0.8606637954711914, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.004365176241844892, "weighted_relation_loss": 0.004365176241844892 }, { "action_query_batch_std": 18.14414291381836, "action_query_norm": 793.6538635253906, "action_relation_loss": 0.004443860938772559, "auxiliary_loss_weight": 1.0, "epoch": 9.457436856875585, "flow_matching_loss": 0.0407317791134119, "grad_norm": 0.13802863657474518, "invalid_tail_samples": 23.4, "learning_rate": 7.912556484033146e-05, "loss": 0.0452, "positive_teacher_pairs": 26947.2, "relation_loss": 0.004443860938772559, "selected_pairs": 26947.2, "step": 10110, "student_distance_mean": 1032.9321533203124, "teacher_distance_mean": 0.8518133878707885, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.004443860938772559, "weighted_relation_loss": 0.004443860938772559 }, { "action_query_batch_std": 18.47148208618164, "action_query_norm": 806.72548828125, "action_relation_loss": 0.004360317881219089, "auxiliary_loss_weight": 1.0, "epoch": 9.466791393826005, "flow_matching_loss": 0.039713645726442336, "grad_norm": 0.12452513724565506, "invalid_tail_samples": 25.6, "learning_rate": 7.908074789936952e-05, "loss": 0.0441, "positive_teacher_pairs": 26439.1, "relation_loss": 0.004360317881219089, "selected_pairs": 26439.1, "step": 10120, "student_distance_mean": 1054.034600830078, "teacher_distance_mean": 0.8648438572883606, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.004360317881219089, "weighted_relation_loss": 0.004360317881219089 }, { "action_query_batch_std": 18.613816452026366, "action_query_norm": 816.2169616699218, "action_relation_loss": 0.004417826840654016, "auxiliary_loss_weight": 1.0, "epoch": 9.476145930776427, "flow_matching_loss": 0.04011870175600052, "grad_norm": 0.16019529104232788, "invalid_tail_samples": 22.7, "learning_rate": 7.903589562255673e-05, "loss": 0.0445, "positive_teacher_pairs": 27100.8, "relation_loss": 0.004417826840654016, "selected_pairs": 27100.8, "step": 10130, "student_distance_mean": 1060.3080444335938, "teacher_distance_mean": 0.8635322093963623, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.004417826840654016, "weighted_relation_loss": 0.004417826840654016 }, { "action_query_batch_std": 18.35790100097656, "action_query_norm": 803.8862609863281, "action_relation_loss": 0.004326381487771869, "auxiliary_loss_weight": 1.0, "epoch": 9.485500467726848, "flow_matching_loss": 0.03966922499239445, "grad_norm": 0.11479801684617996, "invalid_tail_samples": 24.9, "learning_rate": 7.899100806439285e-05, "loss": 0.044, "positive_teacher_pairs": 26595.2, "relation_loss": 0.004326381487771869, "selected_pairs": 26595.2, "step": 10140, "student_distance_mean": 1044.4829162597657, "teacher_distance_mean": 0.855384373664856, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.004326381487771869, "weighted_relation_loss": 0.004326381487771869 }, { "action_query_batch_std": 18.495576858520508, "action_query_norm": 809.0196899414062, "action_relation_loss": 0.004319495940580964, "auxiliary_loss_weight": 1.0, "epoch": 9.494855004677268, "flow_matching_loss": 0.038647981733083724, "grad_norm": 0.11467880010604858, "invalid_tail_samples": 25.1, "learning_rate": 7.894608527942049e-05, "loss": 0.043, "positive_teacher_pairs": 26553.8, "relation_loss": 0.004319495940580964, "selected_pairs": 26553.8, "step": 10150, "student_distance_mean": 1052.361102294922, "teacher_distance_mean": 0.8540072202682495, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.004319495940580964, "weighted_relation_loss": 0.004319495940580964 }, { "action_query_batch_std": 18.468050956726074, "action_query_norm": 809.9661376953125, "action_relation_loss": 0.00416043393779546, "auxiliary_loss_weight": 1.0, "epoch": 9.50420954162769, "flow_matching_loss": 0.03873856998980045, "grad_norm": 0.11408744007349014, "invalid_tail_samples": 23.2, "learning_rate": 7.89011273222251e-05, "loss": 0.0429, "positive_teacher_pairs": 26991.3, "relation_loss": 0.00416043393779546, "selected_pairs": 26991.3, "step": 10160, "student_distance_mean": 1051.6239990234376, "teacher_distance_mean": 0.8537363827228546, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.00416043393779546, "weighted_relation_loss": 0.00416043393779546 }, { "action_query_batch_std": 18.29402027130127, "action_query_norm": 796.3177307128906, "action_relation_loss": 0.004362594429403543, "auxiliary_loss_weight": 1.0, "epoch": 9.51356407857811, "flow_matching_loss": 0.03999839946627617, "grad_norm": 0.14883729815483093, "invalid_tail_samples": 25.1, "learning_rate": 7.885613424743482e-05, "loss": 0.0444, "positive_teacher_pairs": 26551.2, "relation_loss": 0.004362594429403543, "selected_pairs": 26551.2, "step": 10170, "student_distance_mean": 1042.519219970703, "teacher_distance_mean": 0.8575649619102478, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.004362594429403543, "weighted_relation_loss": 0.004362594429403543 }, { "action_query_batch_std": 18.57221221923828, "action_query_norm": 810.9543579101562, "action_relation_loss": 0.004236205667257309, "auxiliary_loss_weight": 1.0, "epoch": 9.522918615528532, "flow_matching_loss": 0.04082753509283066, "grad_norm": 0.13744662702083588, "invalid_tail_samples": 23.0, "learning_rate": 7.881110610972044e-05, "loss": 0.0451, "positive_teacher_pairs": 27037.7, "relation_loss": 0.004236205667257309, "selected_pairs": 27037.7, "step": 10180, "student_distance_mean": 1059.82626953125, "teacher_distance_mean": 0.8598715007305145, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.004236205667257309, "weighted_relation_loss": 0.004236205667257309 }, { "action_query_batch_std": 18.448686027526854, "action_query_norm": 805.5600341796875, "action_relation_loss": 0.0043063082732260225, "auxiliary_loss_weight": 1.0, "epoch": 9.532273152478952, "flow_matching_loss": 0.04078050963580608, "grad_norm": 0.1335858255624771, "invalid_tail_samples": 23.8, "learning_rate": 7.876604296379544e-05, "loss": 0.0451, "positive_teacher_pairs": 26849.8, "relation_loss": 0.0043063082732260225, "selected_pairs": 26849.8, "step": 10190, "student_distance_mean": 1050.2136840820312, "teacher_distance_mean": 0.854699432849884, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0043063082732260225, "weighted_relation_loss": 0.0043063082732260225 }, { "action_query_batch_std": 18.429803466796876, "action_query_norm": 803.3069152832031, "action_relation_loss": 0.004082078672945499, "auxiliary_loss_weight": 1.0, "epoch": 9.541627689429372, "flow_matching_loss": 0.04275963380932808, "grad_norm": 0.10406224429607391, "invalid_tail_samples": 24.3, "learning_rate": 7.872094486441579e-05, "loss": 0.0468, "positive_teacher_pairs": 26728.3, "relation_loss": 0.004082078672945499, "selected_pairs": 26728.3, "step": 10200, "student_distance_mean": 1046.5940551757812, "teacher_distance_mean": 0.8531465291976928, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.004082078672945499, "weighted_relation_loss": 0.004082078672945499 }, { "action_query_batch_std": 18.637207984924316, "action_query_norm": 810.4648681640625, "action_relation_loss": 0.004407324944622815, "auxiliary_loss_weight": 1.0, "epoch": 9.550982226379794, "flow_matching_loss": 0.039293397963047025, "grad_norm": 0.13638007640838623, "invalid_tail_samples": 21.8, "learning_rate": 7.867581186637991e-05, "loss": 0.0437, "positive_teacher_pairs": 27325.5, "relation_loss": 0.004407324944622815, "selected_pairs": 27325.5, "step": 10210, "student_distance_mean": 1057.5233642578125, "teacher_distance_mean": 0.8588705003261566, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.004407324944622815, "weighted_relation_loss": 0.004407324944622815 }, { "action_query_batch_std": 18.706072044372558, "action_query_norm": 818.3531494140625, "action_relation_loss": 0.004117499990388751, "auxiliary_loss_weight": 1.0, "epoch": 9.560336763330215, "flow_matching_loss": 0.039326539263129234, "grad_norm": 0.14423030614852905, "invalid_tail_samples": 23.7, "learning_rate": 7.863064402452866e-05, "loss": 0.0434, "positive_teacher_pairs": 26875.3, "relation_loss": 0.004117499990388751, "selected_pairs": 26875.3, "step": 10220, "student_distance_mean": 1062.9981018066405, "teacher_distance_mean": 0.8585340321063996, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.004117499990388751, "weighted_relation_loss": 0.004117499990388751 }, { "action_query_batch_std": 18.507438087463377, "action_query_norm": 811.6515686035157, "action_relation_loss": 0.004357712180353701, "auxiliary_loss_weight": 1.0, "epoch": 9.569691300280637, "flow_matching_loss": 0.0403089851140976, "grad_norm": 0.11729325354099274, "invalid_tail_samples": 25.4, "learning_rate": 7.858544139374524e-05, "loss": 0.0447, "positive_teacher_pairs": 26479.4, "relation_loss": 0.004357712180353701, "selected_pairs": 26479.4, "step": 10230, "student_distance_mean": 1056.7577880859376, "teacher_distance_mean": 0.8458316802978516, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.004357712180353701, "weighted_relation_loss": 0.004357712180353701 }, { "action_query_batch_std": 18.76091766357422, "action_query_norm": 818.7215087890625, "action_relation_loss": 0.004305838840082288, "auxiliary_loss_weight": 1.0, "epoch": 9.579045837231057, "flow_matching_loss": 0.039381688460707664, "grad_norm": 0.14396612346172333, "invalid_tail_samples": 21.7, "learning_rate": 7.854020402895508e-05, "loss": 0.0437, "positive_teacher_pairs": 27347.9, "relation_loss": 0.004305838840082288, "selected_pairs": 27347.9, "step": 10240, "student_distance_mean": 1068.7532470703125, "teacher_distance_mean": 0.8548470497131347, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.004305838840082288, "weighted_relation_loss": 0.004305838840082288 }, { "action_query_batch_std": 18.749479866027833, "action_query_norm": 814.5096923828125, "action_relation_loss": 0.004229772230610251, "auxiliary_loss_weight": 1.0, "epoch": 9.588400374181479, "flow_matching_loss": 0.039091401174664496, "grad_norm": 0.12546320259571075, "invalid_tail_samples": 26.5, "learning_rate": 7.849493198512587e-05, "loss": 0.0433, "positive_teacher_pairs": 26225.9, "relation_loss": 0.004229772230610251, "selected_pairs": 26225.9, "step": 10250, "student_distance_mean": 1067.3523315429688, "teacher_distance_mean": 0.8583498656749725, "valid_action_samples": 229.5, "weighted_auxiliary_loss": 0.004229772230610251, "weighted_relation_loss": 0.004229772230610251 }, { "action_query_batch_std": 18.785671615600585, "action_query_norm": 817.0384887695312, "action_relation_loss": 0.004143569525331259, "auxiliary_loss_weight": 1.0, "epoch": 9.597754911131899, "flow_matching_loss": 0.038900966942310336, "grad_norm": 0.10957295447587967, "invalid_tail_samples": 25.7, "learning_rate": 7.84496253172674e-05, "loss": 0.043, "positive_teacher_pairs": 26416.1, "relation_loss": 0.004143569525331259, "selected_pairs": 26416.1, "step": 10260, "student_distance_mean": 1069.7394897460938, "teacher_distance_mean": 0.8655443251132965, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.004143569525331259, "weighted_relation_loss": 0.004143569525331259 }, { "action_query_batch_std": 18.794160270690917, "action_query_norm": 822.13955078125, "action_relation_loss": 0.004257324920035899, "auxiliary_loss_weight": 1.0, "epoch": 9.60710944808232, "flow_matching_loss": 0.03796856366097927, "grad_norm": 0.1218138188123703, "invalid_tail_samples": 23.5, "learning_rate": 7.840428408043155e-05, "loss": 0.0422, "positive_teacher_pairs": 26923.1, "relation_loss": 0.004257324920035899, "selected_pairs": 26923.1, "step": 10270, "student_distance_mean": 1068.611328125, "teacher_distance_mean": 0.8572563052177429, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.004257324920035899, "weighted_relation_loss": 0.004257324920035899 }, { "action_query_batch_std": 18.583856201171876, "action_query_norm": 814.1774841308594, "action_relation_loss": 0.004363533016294241, "auxiliary_loss_weight": 1.0, "epoch": 9.616463985032741, "flow_matching_loss": 0.03812424167990684, "grad_norm": 0.14781339466571808, "invalid_tail_samples": 24.4, "learning_rate": 7.835890832971218e-05, "loss": 0.0425, "positive_teacher_pairs": 26710.8, "relation_loss": 0.004363533016294241, "selected_pairs": 26710.8, "step": 10280, "student_distance_mean": 1058.4248046875, "teacher_distance_mean": 0.8528891623020172, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.004363533016294241, "weighted_relation_loss": 0.004363533016294241 }, { "action_query_batch_std": 18.5497745513916, "action_query_norm": 812.9348876953125, "action_relation_loss": 0.004143301723524928, "auxiliary_loss_weight": 1.0, "epoch": 9.625818521983161, "flow_matching_loss": 0.03998996764421463, "grad_norm": 0.11476024985313416, "invalid_tail_samples": 22.2, "learning_rate": 7.831349812024512e-05, "loss": 0.0441, "positive_teacher_pairs": 27224.6, "relation_loss": 0.004143301723524928, "selected_pairs": 27224.6, "step": 10290, "student_distance_mean": 1051.755352783203, "teacher_distance_mean": 0.8492472290992736, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.004143301723524928, "weighted_relation_loss": 0.004143301723524928 }, { "action_query_batch_std": 18.61192512512207, "action_query_norm": 818.0144775390625, "action_relation_loss": 0.004251721105538309, "auxiliary_loss_weight": 1.0, "epoch": 9.635173058933583, "flow_matching_loss": 0.038563470169901845, "grad_norm": 0.12265376001596451, "invalid_tail_samples": 22.6, "learning_rate": 7.826805350720807e-05, "loss": 0.0428, "positive_teacher_pairs": 27132.2, "relation_loss": 0.004251721105538309, "selected_pairs": 27132.2, "step": 10300, "student_distance_mean": 1060.5812683105469, "teacher_distance_mean": 0.8519443392753601, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.004251721105538309, "weighted_relation_loss": 0.004251721105538309 }, { "action_query_batch_std": 18.601936912536623, "action_query_norm": 817.1183959960938, "action_relation_loss": 0.004198565310798585, "auxiliary_loss_weight": 1.0, "epoch": 9.644527595884004, "flow_matching_loss": 0.04125495590269566, "grad_norm": 0.11484336853027344, "invalid_tail_samples": 22.0, "learning_rate": 7.822257454582049e-05, "loss": 0.0455, "positive_teacher_pairs": 27266.0, "relation_loss": 0.004198565310798585, "selected_pairs": 27266.0, "step": 10310, "student_distance_mean": 1055.7344665527344, "teacher_distance_mean": 0.8531257927417755, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.004198565310798585, "weighted_relation_loss": 0.004198565310798585 }, { "action_query_batch_std": 18.70589237213135, "action_query_norm": 819.4120788574219, "action_relation_loss": 0.004309825785458088, "auxiliary_loss_weight": 1.0, "epoch": 9.653882132834426, "flow_matching_loss": 0.04005354605615139, "grad_norm": 0.13789065182209015, "invalid_tail_samples": 26.2, "learning_rate": 7.817706129134363e-05, "loss": 0.0444, "positive_teacher_pairs": 26299.1, "relation_loss": 0.004309825785458088, "selected_pairs": 26299.1, "step": 10320, "student_distance_mean": 1065.0450744628906, "teacher_distance_mean": 0.8612894892692566, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.004309825785458088, "weighted_relation_loss": 0.004309825785458088 }, { "action_query_batch_std": 18.43561840057373, "action_query_norm": 809.4895324707031, "action_relation_loss": 0.004493516543880105, "auxiliary_loss_weight": 1.0, "epoch": 9.663236669784846, "flow_matching_loss": 0.04109504595398903, "grad_norm": 0.1279434859752655, "invalid_tail_samples": 22.1, "learning_rate": 7.813151379908036e-05, "loss": 0.0456, "positive_teacher_pairs": 27251.1, "relation_loss": 0.004493516543880105, "selected_pairs": 27251.1, "step": 10330, "student_distance_mean": 1048.9006286621093, "teacher_distance_mean": 0.8490405976772308, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.004493516543880105, "weighted_relation_loss": 0.004493516543880105 }, { "action_query_batch_std": 18.71877326965332, "action_query_norm": 817.0672973632812, "action_relation_loss": 0.004168774792924523, "auxiliary_loss_weight": 1.0, "epoch": 9.672591206735266, "flow_matching_loss": 0.040657073631882666, "grad_norm": 0.1353912055492401, "invalid_tail_samples": 21.6, "learning_rate": 7.808593212437523e-05, "loss": 0.0448, "positive_teacher_pairs": 27365.9, "relation_loss": 0.004168774792924523, "selected_pairs": 27365.9, "step": 10340, "student_distance_mean": 1058.2786376953125, "teacher_distance_mean": 0.8576920211315155, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.004168774792924523, "weighted_relation_loss": 0.004168774792924523 }, { "action_query_batch_std": 18.67336959838867, "action_query_norm": 812.6422180175781, "action_relation_loss": 0.0041924153687432405, "auxiliary_loss_weight": 1.0, "epoch": 9.681945743685688, "flow_matching_loss": 0.03759604245424271, "grad_norm": 0.12842963635921478, "invalid_tail_samples": 28.4, "learning_rate": 7.804031632261421e-05, "loss": 0.0418, "positive_teacher_pairs": 25797.4, "relation_loss": 0.0041924153687432405, "selected_pairs": 25797.4, "step": 10350, "student_distance_mean": 1066.873876953125, "teacher_distance_mean": 0.8592258214950561, "valid_action_samples": 227.6, "weighted_auxiliary_loss": 0.0041924153687432405, "weighted_relation_loss": 0.0041924153687432405 }, { "action_query_batch_std": 18.943314933776854, "action_query_norm": 825.7045104980468, "action_relation_loss": 0.004137651924975216, "auxiliary_loss_weight": 1.0, "epoch": 9.691300280636108, "flow_matching_loss": 0.0421401284635067, "grad_norm": 0.12139995396137238, "invalid_tail_samples": 23.2, "learning_rate": 7.799466644922484e-05, "loss": 0.0463, "positive_teacher_pairs": 26994.8, "relation_loss": 0.004137651924975216, "selected_pairs": 26994.8, "step": 10360, "student_distance_mean": 1081.2106811523438, "teacher_distance_mean": 0.8661458551883697, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.004137651924975216, "weighted_relation_loss": 0.004137651924975216 }, { "action_query_batch_std": 18.621745109558105, "action_query_norm": 813.2036193847656, "action_relation_loss": 0.004140054667368531, "auxiliary_loss_weight": 1.0, "epoch": 9.70065481758653, "flow_matching_loss": 0.03968096449971199, "grad_norm": 0.10742487013339996, "invalid_tail_samples": 24.8, "learning_rate": 7.794898255967602e-05, "loss": 0.0438, "positive_teacher_pairs": 26622.7, "relation_loss": 0.004140054667368531, "selected_pairs": 26622.7, "step": 10370, "student_distance_mean": 1061.6387573242187, "teacher_distance_mean": 0.8588145256042481, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.004140054667368531, "weighted_relation_loss": 0.004140054667368531 }, { "action_query_batch_std": 18.571552658081053, "action_query_norm": 807.0925231933594, "action_relation_loss": 0.004231433710083365, "auxiliary_loss_weight": 1.0, "epoch": 9.71000935453695, "flow_matching_loss": 0.039585931971669194, "grad_norm": 0.11843816936016083, "invalid_tail_samples": 22.4, "learning_rate": 7.790326470947795e-05, "loss": 0.0438, "positive_teacher_pairs": 27182.3, "relation_loss": 0.004231433710083365, "selected_pairs": 27182.3, "step": 10380, "student_distance_mean": 1055.4242553710938, "teacher_distance_mean": 0.856687593460083, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.004231433710083365, "weighted_relation_loss": 0.004231433710083365 }, { "action_query_batch_std": 18.53015727996826, "action_query_norm": 808.8046081542968, "action_relation_loss": 0.004296856559813022, "auxiliary_loss_weight": 1.0, "epoch": 9.71936389148737, "flow_matching_loss": 0.04012805260717869, "grad_norm": 0.1311134546995163, "invalid_tail_samples": 20.2, "learning_rate": 7.785751295418217e-05, "loss": 0.0444, "positive_teacher_pairs": 27687.7, "relation_loss": 0.004296856559813022, "selected_pairs": 27687.7, "step": 10390, "student_distance_mean": 1051.2184326171875, "teacher_distance_mean": 0.8506497025489808, "valid_action_samples": 235.8, "weighted_auxiliary_loss": 0.004296856559813022, "weighted_relation_loss": 0.004296856559813022 }, { "action_query_batch_std": 18.520766830444337, "action_query_norm": 804.7738952636719, "action_relation_loss": 0.00450435490347445, "auxiliary_loss_weight": 1.0, "epoch": 9.728718428437793, "flow_matching_loss": 0.04008924551308155, "grad_norm": 0.2511465847492218, "invalid_tail_samples": 24.4, "learning_rate": 7.781172734938136e-05, "loss": 0.0446, "positive_teacher_pairs": 26716.3, "relation_loss": 0.00450435490347445, "selected_pairs": 26716.3, "step": 10400, "student_distance_mean": 1049.1933837890624, "teacher_distance_mean": 0.8530598104000091, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.00450435490347445, "weighted_relation_loss": 0.00450435490347445 }, { "action_query_batch_std": 18.723929977416994, "action_query_norm": 814.7622009277344, "action_relation_loss": 0.004434306127950549, "auxiliary_loss_weight": 1.0, "epoch": 9.738072965388213, "flow_matching_loss": 0.03851842116564512, "grad_norm": 0.12186072021722794, "invalid_tail_samples": 23.4, "learning_rate": 7.776590795070933e-05, "loss": 0.043, "positive_teacher_pairs": 26946.6, "relation_loss": 0.004434306127950549, "selected_pairs": 26946.6, "step": 10410, "student_distance_mean": 1064.0172241210937, "teacher_distance_mean": 0.8541316211223602, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.004434306127950549, "weighted_relation_loss": 0.004434306127950549 }, { "action_query_batch_std": 18.63163013458252, "action_query_norm": 809.283544921875, "action_relation_loss": 0.004451245442032814, "auxiliary_loss_weight": 1.0, "epoch": 9.747427502338635, "flow_matching_loss": 0.040187351033091546, "grad_norm": 0.12033272534608841, "invalid_tail_samples": 23.7, "learning_rate": 7.772005481384099e-05, "loss": 0.0446, "positive_teacher_pairs": 26877.7, "relation_loss": 0.004451245442032814, "selected_pairs": 26877.7, "step": 10420, "student_distance_mean": 1053.4825378417968, "teacher_distance_mean": 0.8629486858844757, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.004451245442032814, "weighted_relation_loss": 0.004451245442032814 }, { "action_query_batch_std": 18.716071701049806, "action_query_norm": 813.5839965820312, "action_relation_loss": 0.0044323096983134745, "auxiliary_loss_weight": 1.0, "epoch": 9.756782039289055, "flow_matching_loss": 0.03851379230618477, "grad_norm": 0.13739128410816193, "invalid_tail_samples": 24.1, "learning_rate": 7.767416799449223e-05, "loss": 0.0429, "positive_teacher_pairs": 26782.8, "relation_loss": 0.0044323096983134745, "selected_pairs": 26782.8, "step": 10430, "student_distance_mean": 1063.3142333984374, "teacher_distance_mean": 0.8598274290561676, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0044323096983134745, "weighted_relation_loss": 0.0044323096983134745 }, { "action_query_batch_std": 18.59801826477051, "action_query_norm": 815.63818359375, "action_relation_loss": 0.004502273164689541, "auxiliary_loss_weight": 1.0, "epoch": 9.766136576239477, "flow_matching_loss": 0.03904284313321114, "grad_norm": 0.12769512832164764, "invalid_tail_samples": 22.3, "learning_rate": 7.762824754841984e-05, "loss": 0.0435, "positive_teacher_pairs": 27200.9, "relation_loss": 0.004502273164689541, "selected_pairs": 27200.9, "step": 10440, "student_distance_mean": 1054.1189086914062, "teacher_distance_mean": 0.8484436392784118, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.004502273164689541, "weighted_relation_loss": 0.004502273164689541 }, { "action_query_batch_std": 18.61103935241699, "action_query_norm": 812.4354858398438, "action_relation_loss": 0.004161244514398277, "auxiliary_loss_weight": 1.0, "epoch": 9.775491113189897, "flow_matching_loss": 0.039401041343808174, "grad_norm": 0.12303298711776733, "invalid_tail_samples": 22.5, "learning_rate": 7.758229353142152e-05, "loss": 0.0436, "positive_teacher_pairs": 27150.5, "relation_loss": 0.004161244514398277, "selected_pairs": 27150.5, "step": 10450, "student_distance_mean": 1057.399676513672, "teacher_distance_mean": 0.8582114398479461, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.004161244514398277, "weighted_relation_loss": 0.004161244514398277 }, { "action_query_batch_std": 18.756196403503417, "action_query_norm": 820.3402954101563, "action_relation_loss": 0.00426892472896725, "auxiliary_loss_weight": 1.0, "epoch": 9.784845650140317, "flow_matching_loss": 0.03925638794898987, "grad_norm": 0.1475251019001007, "invalid_tail_samples": 24.6, "learning_rate": 7.753630599933572e-05, "loss": 0.0435, "positive_teacher_pairs": 26671.7, "relation_loss": 0.00426892472896725, "selected_pairs": 26671.7, "step": 10460, "student_distance_mean": 1067.2073303222655, "teacher_distance_mean": 0.8551178574562073, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.00426892472896725, "weighted_relation_loss": 0.00426892472896725 }, { "action_query_batch_std": 18.832152938842775, "action_query_norm": 828.08310546875, "action_relation_loss": 0.004110275208950043, "auxiliary_loss_weight": 1.0, "epoch": 9.79420018709074, "flow_matching_loss": 0.03965871669352054, "grad_norm": 0.12389081716537476, "invalid_tail_samples": 21.5, "learning_rate": 7.749028500804161e-05, "loss": 0.0438, "positive_teacher_pairs": 27389.4, "relation_loss": 0.004110275208950043, "selected_pairs": 27389.4, "step": 10470, "student_distance_mean": 1069.8488403320312, "teacher_distance_mean": 0.8557397902011872, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.004110275208950043, "weighted_relation_loss": 0.004110275208950043 }, { "action_query_batch_std": 18.88751277923584, "action_query_norm": 822.3482421875, "action_relation_loss": 0.00410932928789407, "auxiliary_loss_weight": 1.0, "epoch": 9.80355472404116, "flow_matching_loss": 0.03877500742673874, "grad_norm": 0.10969012975692749, "invalid_tail_samples": 22.4, "learning_rate": 7.744423061345906e-05, "loss": 0.0429, "positive_teacher_pairs": 27174.5, "relation_loss": 0.00410932928789407, "selected_pairs": 27174.5, "step": 10480, "student_distance_mean": 1073.4153930664063, "teacher_distance_mean": 0.8634011030197144, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.00410932928789407, "weighted_relation_loss": 0.00410932928789407 }, { "action_query_batch_std": 18.741073417663575, "action_query_norm": 816.9694091796875, "action_relation_loss": 0.004273697710596025, "auxiliary_loss_weight": 1.0, "epoch": 9.812909260991582, "flow_matching_loss": 0.039534283056855204, "grad_norm": 0.11357825249433517, "invalid_tail_samples": 23.7, "learning_rate": 7.73981428715485e-05, "loss": 0.0438, "positive_teacher_pairs": 26873.1, "relation_loss": 0.004273697710596025, "selected_pairs": 26873.1, "step": 10490, "student_distance_mean": 1066.0507446289062, "teacher_distance_mean": 0.8587723076343536, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.004273697710596025, "weighted_relation_loss": 0.004273697710596025 }, { "action_query_batch_std": 18.85518913269043, "action_query_norm": 822.3878967285157, "action_relation_loss": 0.004277852061204612, "auxiliary_loss_weight": 1.0, "epoch": 9.822263797942002, "flow_matching_loss": 0.0411938339471817, "grad_norm": 0.1562935709953308, "invalid_tail_samples": 21.6, "learning_rate": 7.735202183831085e-05, "loss": 0.0455, "positive_teacher_pairs": 27359.2, "relation_loss": 0.004277852061204612, "selected_pairs": 27359.2, "step": 10500, "student_distance_mean": 1071.1731323242188, "teacher_distance_mean": 0.8621573328971863, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.004277852061204612, "weighted_relation_loss": 0.004277852061204612 }, { "action_query_batch_std": 18.633230209350586, "action_query_norm": 815.426318359375, "action_relation_loss": 0.004336890392005443, "auxiliary_loss_weight": 1.0, "epoch": 9.831618334892422, "flow_matching_loss": 0.03822638913989067, "grad_norm": 0.15672889351844788, "invalid_tail_samples": 24.5, "learning_rate": 7.730586756978757e-05, "loss": 0.0426, "positive_teacher_pairs": 26695.9, "relation_loss": 0.004336890392005443, "selected_pairs": 26695.9, "step": 10510, "student_distance_mean": 1057.809375, "teacher_distance_mean": 0.8522963941097259, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.004336890392005443, "weighted_relation_loss": 0.004336890392005443 }, { "action_query_batch_std": 18.579136466979982, "action_query_norm": 813.4684936523438, "action_relation_loss": 0.004300229041837156, "auxiliary_loss_weight": 1.0, "epoch": 9.840972871842844, "flow_matching_loss": 0.03722663335502148, "grad_norm": 0.10500762611627579, "invalid_tail_samples": 22.2, "learning_rate": 7.72596801220604e-05, "loss": 0.0415, "positive_teacher_pairs": 27227.3, "relation_loss": 0.004300229041837156, "selected_pairs": 27227.3, "step": 10520, "student_distance_mean": 1055.8186340332031, "teacher_distance_mean": 0.850090378522873, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.004300229041837156, "weighted_relation_loss": 0.004300229041837156 }, { "action_query_batch_std": 18.504804420471192, "action_query_norm": 813.3340698242188, "action_relation_loss": 0.004182728100568056, "auxiliary_loss_weight": 1.0, "epoch": 9.850327408793264, "flow_matching_loss": 0.04002749845385552, "grad_norm": 0.16490937769412994, "invalid_tail_samples": 21.8, "learning_rate": 7.721345955125147e-05, "loss": 0.0442, "positive_teacher_pairs": 27309.7, "relation_loss": 0.004182728100568056, "selected_pairs": 27309.7, "step": 10530, "student_distance_mean": 1053.6160034179688, "teacher_distance_mean": 0.8480269312858582, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.004182728100568056, "weighted_relation_loss": 0.004182728100568056 }, { "action_query_batch_std": 18.74837646484375, "action_query_norm": 817.8022827148437, "action_relation_loss": 0.004094317555427551, "auxiliary_loss_weight": 1.0, "epoch": 9.859681945743686, "flow_matching_loss": 0.03773208148777485, "grad_norm": 0.17271451652050018, "invalid_tail_samples": 24.8, "learning_rate": 7.71672059135231e-05, "loss": 0.0418, "positive_teacher_pairs": 26618.8, "relation_loss": 0.004094317555427551, "selected_pairs": 26618.8, "step": 10540, "student_distance_mean": 1064.9314575195312, "teacher_distance_mean": 0.8570847153663635, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.004094317555427551, "weighted_relation_loss": 0.004094317555427551 }, { "action_query_batch_std": 18.93055648803711, "action_query_norm": 823.4266479492187, "action_relation_loss": 0.004042004118673503, "auxiliary_loss_weight": 1.0, "epoch": 9.869036482694106, "flow_matching_loss": 0.040908809006214145, "grad_norm": 0.11764553934335709, "invalid_tail_samples": 22.3, "learning_rate": 7.712091926507787e-05, "loss": 0.045, "positive_teacher_pairs": 27201.6, "relation_loss": 0.004042004118673503, "selected_pairs": 27201.6, "step": 10550, "student_distance_mean": 1076.6450927734375, "teacher_distance_mean": 0.8613663196563721, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.004042004118673503, "weighted_relation_loss": 0.004042004118673503 }, { "action_query_batch_std": 18.937704277038574, "action_query_norm": 826.2934143066407, "action_relation_loss": 0.004063490382395685, "auxiliary_loss_weight": 1.0, "epoch": 9.878391019644528, "flow_matching_loss": 0.03843921553343534, "grad_norm": 0.15645989775657654, "invalid_tail_samples": 24.3, "learning_rate": 7.70745996621584e-05, "loss": 0.0425, "positive_teacher_pairs": 26745.2, "relation_loss": 0.004063490382395685, "selected_pairs": 26745.2, "step": 10560, "student_distance_mean": 1077.0621337890625, "teacher_distance_mean": 0.8613176703453064, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.004063490382395685, "weighted_relation_loss": 0.004063490382395685 }, { "action_query_batch_std": 18.63053150177002, "action_query_norm": 812.3647705078125, "action_relation_loss": 0.004031572910025716, "auxiliary_loss_weight": 1.0, "epoch": 9.887745556594949, "flow_matching_loss": 0.03963151201605797, "grad_norm": 0.15868723392486572, "invalid_tail_samples": 24.8, "learning_rate": 7.702824716104735e-05, "loss": 0.0437, "positive_teacher_pairs": 26614.4, "relation_loss": 0.004031572910025716, "selected_pairs": 26614.4, "step": 10570, "student_distance_mean": 1062.0195007324219, "teacher_distance_mean": 0.8562812626361846, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.004031572910025716, "weighted_relation_loss": 0.004031572910025716 }, { "action_query_batch_std": 18.480104446411133, "action_query_norm": 804.5780334472656, "action_relation_loss": 0.0042259510373696685, "auxiliary_loss_weight": 1.0, "epoch": 9.897100093545369, "flow_matching_loss": 0.03975297249853611, "grad_norm": 0.15139323472976685, "invalid_tail_samples": 26.2, "learning_rate": 7.698186181806743e-05, "loss": 0.044, "positive_teacher_pairs": 26298.9, "relation_loss": 0.0042259510373696685, "selected_pairs": 26298.9, "step": 10580, "student_distance_mean": 1052.0250244140625, "teacher_distance_mean": 0.8501322150230408, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.0042259510373696685, "weighted_relation_loss": 0.0042259510373696685 }, { "action_query_batch_std": 18.414094734191895, "action_query_norm": 803.659423828125, "action_relation_loss": 0.004410066269338131, "auxiliary_loss_weight": 1.0, "epoch": 9.90645463049579, "flow_matching_loss": 0.04069247357547283, "grad_norm": 0.11548133939504623, "invalid_tail_samples": 25.1, "learning_rate": 7.693544368958116e-05, "loss": 0.0451, "positive_teacher_pairs": 26553.1, "relation_loss": 0.004410066269338131, "selected_pairs": 26553.1, "step": 10590, "student_distance_mean": 1044.588720703125, "teacher_distance_mean": 0.8433753788471222, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.004410066269338131, "weighted_relation_loss": 0.004410066269338131 }, { "action_query_batch_std": 18.63011054992676, "action_query_norm": 812.4701416015625, "action_relation_loss": 0.004396948916837573, "auxiliary_loss_weight": 1.0, "epoch": 9.915809167446211, "flow_matching_loss": 0.04047801196575165, "grad_norm": 0.14697717130184174, "invalid_tail_samples": 23.5, "learning_rate": 7.688899283199096e-05, "loss": 0.0449, "positive_teacher_pairs": 26923.4, "relation_loss": 0.004396948916837573, "selected_pairs": 26923.4, "step": 10600, "student_distance_mean": 1061.9900756835937, "teacher_distance_mean": 0.8498095512390137, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.004396948916837573, "weighted_relation_loss": 0.004396948916837573 }, { "action_query_batch_std": 18.791738510131836, "action_query_norm": 817.3283569335938, "action_relation_loss": 0.004243617225438356, "auxiliary_loss_weight": 1.0, "epoch": 9.925163704396633, "flow_matching_loss": 0.03990762680768967, "grad_norm": 0.13299930095672607, "invalid_tail_samples": 26.0, "learning_rate": 7.684250930173901e-05, "loss": 0.0442, "positive_teacher_pairs": 26340.3, "relation_loss": 0.004243617225438356, "selected_pairs": 26340.3, "step": 10610, "student_distance_mean": 1067.4539184570312, "teacher_distance_mean": 0.8576667428016662, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.004243617225438356, "weighted_relation_loss": 0.004243617225438356 }, { "action_query_batch_std": 18.824908828735353, "action_query_norm": 816.5122741699219, "action_relation_loss": 0.0042193869827315215, "auxiliary_loss_weight": 1.0, "epoch": 9.934518241347053, "flow_matching_loss": 0.04159366302192211, "grad_norm": 0.11602190881967545, "invalid_tail_samples": 24.2, "learning_rate": 7.679599315530718e-05, "loss": 0.0458, "positive_teacher_pairs": 26771.3, "relation_loss": 0.0042193869827315215, "selected_pairs": 26771.3, "step": 10620, "student_distance_mean": 1072.6954833984375, "teacher_distance_mean": 0.8624542355537415, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0042193869827315215, "weighted_relation_loss": 0.0042193869827315215 }, { "action_query_batch_std": 18.47185173034668, "action_query_norm": 806.2523254394531, "action_relation_loss": 0.004161621746607125, "auxiliary_loss_weight": 1.0, "epoch": 9.943872778297475, "flow_matching_loss": 0.03987322524189949, "grad_norm": 0.1365184187889099, "invalid_tail_samples": 26.0, "learning_rate": 7.674944444921695e-05, "loss": 0.044, "positive_teacher_pairs": 26344.7, "relation_loss": 0.004161621746607125, "selected_pairs": 26344.7, "step": 10630, "student_distance_mean": 1050.4643005371095, "teacher_distance_mean": 0.8465651869773865, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.004161621746607125, "weighted_relation_loss": 0.004161621746607125 }, { "action_query_batch_std": 18.98712787628174, "action_query_norm": 825.26865234375, "action_relation_loss": 0.004138190462253988, "auxiliary_loss_weight": 1.0, "epoch": 9.953227315247895, "flow_matching_loss": 0.03779274746775627, "grad_norm": 0.11689234524965286, "invalid_tail_samples": 22.6, "learning_rate": 7.670286324002944e-05, "loss": 0.0419, "positive_teacher_pairs": 27124.6, "relation_loss": 0.004138190462253988, "selected_pairs": 27124.6, "step": 10640, "student_distance_mean": 1072.2299438476562, "teacher_distance_mean": 0.8613380253314972, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.004138190462253988, "weighted_relation_loss": 0.004138190462253988 }, { "action_query_batch_std": 19.0580696105957, "action_query_norm": 830.9481628417968, "action_relation_loss": 0.004174768622033298, "auxiliary_loss_weight": 1.0, "epoch": 9.962581852198316, "flow_matching_loss": 0.04030774459242821, "grad_norm": 0.11573530733585358, "invalid_tail_samples": 23.8, "learning_rate": 7.665624958434514e-05, "loss": 0.0445, "positive_teacher_pairs": 26850.8, "relation_loss": 0.004174768622033298, "selected_pairs": 26850.8, "step": 10650, "student_distance_mean": 1080.2211303710938, "teacher_distance_mean": 0.8540648639202117, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.004174768622033298, "weighted_relation_loss": 0.004174768622033298 }, { "action_query_batch_std": 18.99829845428467, "action_query_norm": 829.57509765625, "action_relation_loss": 0.004213479487225414, "auxiliary_loss_weight": 1.0, "epoch": 9.971936389148738, "flow_matching_loss": 0.04003818407654762, "grad_norm": 0.1070493757724762, "invalid_tail_samples": 22.9, "learning_rate": 7.66096035388041e-05, "loss": 0.0443, "positive_teacher_pairs": 27058.9, "relation_loss": 0.004213479487225414, "selected_pairs": 27058.9, "step": 10660, "student_distance_mean": 1078.9927856445313, "teacher_distance_mean": 0.856555312871933, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.004213479487225414, "weighted_relation_loss": 0.004213479487225414 }, { "action_query_batch_std": 18.988689041137697, "action_query_norm": 826.1646850585937, "action_relation_loss": 0.004235992720350623, "auxiliary_loss_weight": 1.0, "epoch": 9.981290926099158, "flow_matching_loss": 0.03771146945655346, "grad_norm": 0.16043107211589813, "invalid_tail_samples": 27.7, "learning_rate": 7.656292516008563e-05, "loss": 0.0419, "positive_teacher_pairs": 25962.6, "relation_loss": 0.004235992720350623, "selected_pairs": 25962.6, "step": 10670, "student_distance_mean": 1079.3233520507813, "teacher_distance_mean": 0.8555333554744721, "valid_action_samples": 228.3, "weighted_auxiliary_loss": 0.004235992720350623, "weighted_relation_loss": 0.004235992720350623 }, { "action_query_batch_std": 18.958102416992187, "action_query_norm": 828.0656799316406, "action_relation_loss": 0.004048178275115788, "auxiliary_loss_weight": 1.0, "epoch": 9.99064546304958, "flow_matching_loss": 0.03883107379078865, "grad_norm": 0.14323990046977997, "invalid_tail_samples": 22.7, "learning_rate": 7.651621450490837e-05, "loss": 0.0429, "positive_teacher_pairs": 27103.3, "relation_loss": 0.004048178275115788, "selected_pairs": 27103.3, "step": 10680, "student_distance_mean": 1076.437353515625, "teacher_distance_mean": 0.8528829038143158, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.004048178275115788, "weighted_relation_loss": 0.004048178275115788 }, { "action_query_batch_std": 18.842361831665038, "action_query_norm": 818.6911804199219, "action_relation_loss": 0.00425008605234325, "auxiliary_loss_weight": 1.0, "epoch": 10.0, "flow_matching_loss": 0.03902921192348004, "grad_norm": 0.3119277358055115, "invalid_tail_samples": 25.6, "learning_rate": 7.646947163003017e-05, "loss": 0.0433, "positive_teacher_pairs": 23529.8, "relation_loss": 0.00425008605234325, "selected_pairs": 23529.8, "step": 10690, "student_distance_mean": 1074.036865234375, "teacher_distance_mean": 0.8557106494903565, "valid_action_samples": 210.5, "weighted_auxiliary_loss": 0.00425008605234325, "weighted_relation_loss": 0.00425008605234325 }, { "action_query_batch_std": 18.876958465576173, "action_query_norm": 823.2260620117188, "action_relation_loss": 0.004137410479597747, "auxiliary_loss_weight": 1.0, "epoch": 10.00935453695042, "flow_matching_loss": 0.03585330732166767, "grad_norm": 0.1186845526099205, "invalid_tail_samples": 22.6, "learning_rate": 7.642269659224803e-05, "loss": 0.04, "positive_teacher_pairs": 27135.3, "relation_loss": 0.004137410479597747, "selected_pairs": 27135.3, "step": 10700, "student_distance_mean": 1075.656005859375, "teacher_distance_mean": 0.8576485335826873, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.004137410479597747, "weighted_relation_loss": 0.004137410479597747 }, { "action_query_batch_std": 18.61991901397705, "action_query_norm": 815.7474426269531, "action_relation_loss": 0.004176956857554615, "auxiliary_loss_weight": 1.0, "epoch": 10.018709073900842, "flow_matching_loss": 0.037367910891771314, "grad_norm": 0.117101289331913, "invalid_tail_samples": 23.5, "learning_rate": 7.637588944839803e-05, "loss": 0.0415, "positive_teacher_pairs": 26921.8, "relation_loss": 0.004176956857554615, "selected_pairs": 26921.8, "step": 10710, "student_distance_mean": 1060.09365234375, "teacher_distance_mean": 0.850073766708374, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.004176956857554615, "weighted_relation_loss": 0.004176956857554615 }, { "action_query_batch_std": 18.539671897888184, "action_query_norm": 807.3220947265625, "action_relation_loss": 0.003881136770360172, "auxiliary_loss_weight": 1.0, "epoch": 10.028063610851262, "flow_matching_loss": 0.037022626213729384, "grad_norm": 0.09515801072120667, "invalid_tail_samples": 27.3, "learning_rate": 7.632905025535528e-05, "loss": 0.0409, "positive_teacher_pairs": 26046.4, "relation_loss": 0.003881136770360172, "selected_pairs": 26046.4, "step": 10720, "student_distance_mean": 1055.2623107910156, "teacher_distance_mean": 0.8498138427734375, "valid_action_samples": 228.7, "weighted_auxiliary_loss": 0.003881136770360172, "weighted_relation_loss": 0.003881136770360172 }, { "action_query_batch_std": 18.71697425842285, "action_query_norm": 814.5920166015625, "action_relation_loss": 0.004267115332186222, "auxiliary_loss_weight": 1.0, "epoch": 10.037418147801684, "flow_matching_loss": 0.03724839016795158, "grad_norm": 0.1287778615951538, "invalid_tail_samples": 23.8, "learning_rate": 7.628217907003378e-05, "loss": 0.0415, "positive_teacher_pairs": 26847.7, "relation_loss": 0.004267115332186222, "selected_pairs": 26847.7, "step": 10730, "student_distance_mean": 1070.436785888672, "teacher_distance_mean": 0.8556819379329681, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.004267115332186222, "weighted_relation_loss": 0.004267115332186222 }, { "action_query_batch_std": 18.789959335327147, "action_query_norm": 819.821337890625, "action_relation_loss": 0.004097673948854208, "auxiliary_loss_weight": 1.0, "epoch": 10.046772684752105, "flow_matching_loss": 0.03770635146647692, "grad_norm": 0.10257367789745331, "invalid_tail_samples": 24.1, "learning_rate": 7.623527594938649e-05, "loss": 0.0418, "positive_teacher_pairs": 26786.3, "relation_loss": 0.004097673948854208, "selected_pairs": 26786.3, "step": 10740, "student_distance_mean": 1066.7105834960937, "teacher_distance_mean": 0.8522308528423309, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.004097673948854208, "weighted_relation_loss": 0.004097673948854208 }, { "action_query_batch_std": 18.76004409790039, "action_query_norm": 820.1950561523438, "action_relation_loss": 0.004050765605643392, "auxiliary_loss_weight": 1.0, "epoch": 10.056127221702527, "flow_matching_loss": 0.037049459666013716, "grad_norm": 0.12017541378736496, "invalid_tail_samples": 23.6, "learning_rate": 7.618834095040509e-05, "loss": 0.0411, "positive_teacher_pairs": 26896.0, "relation_loss": 0.004050765605643392, "selected_pairs": 26896.0, "step": 10750, "student_distance_mean": 1068.8713989257812, "teacher_distance_mean": 0.8515509784221649, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.004050765605643392, "weighted_relation_loss": 0.004050765605643392 }, { "action_query_batch_std": 18.520470428466798, "action_query_norm": 812.3285583496094, "action_relation_loss": 0.00409027417190373, "auxiliary_loss_weight": 1.0, "epoch": 10.065481758652947, "flow_matching_loss": 0.037151400744915006, "grad_norm": 0.14011341333389282, "invalid_tail_samples": 21.2, "learning_rate": 7.614137413012e-05, "loss": 0.0412, "positive_teacher_pairs": 27458.3, "relation_loss": 0.00409027417190373, "selected_pairs": 27458.3, "step": 10760, "student_distance_mean": 1054.4788696289063, "teacher_distance_mean": 0.8458512544631958, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.00409027417190373, "weighted_relation_loss": 0.00409027417190373 }, { "action_query_batch_std": 18.95227680206299, "action_query_norm": 823.6280944824218, "action_relation_loss": 0.004046695423312485, "auxiliary_loss_weight": 1.0, "epoch": 10.074836295603367, "flow_matching_loss": 0.03976371213793754, "grad_norm": 0.11742360144853592, "invalid_tail_samples": 24.7, "learning_rate": 7.609437554560042e-05, "loss": 0.0438, "positive_teacher_pairs": 26650.3, "relation_loss": 0.004046695423312485, "selected_pairs": 26650.3, "step": 10770, "student_distance_mean": 1077.8593872070312, "teacher_distance_mean": 0.8649433672428131, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.004046695423312485, "weighted_relation_loss": 0.004046695423312485 }, { "action_query_batch_std": 18.730445098876952, "action_query_norm": 818.8128479003906, "action_relation_loss": 0.003904821374453604, "auxiliary_loss_weight": 1.0, "epoch": 10.084190832553789, "flow_matching_loss": 0.03714091703295708, "grad_norm": 0.11811959743499756, "invalid_tail_samples": 24.9, "learning_rate": 7.604734525395398e-05, "loss": 0.041, "positive_teacher_pairs": 26591.3, "relation_loss": 0.003904821374453604, "selected_pairs": 26591.3, "step": 10780, "student_distance_mean": 1064.5578491210938, "teacher_distance_mean": 0.8512816071510315, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.003904821374453604, "weighted_relation_loss": 0.003904821374453604 }, { "action_query_batch_std": 18.892366790771483, "action_query_norm": 824.1775268554687, "action_relation_loss": 0.004119815025478602, "auxiliary_loss_weight": 1.0, "epoch": 10.09354536950421, "flow_matching_loss": 0.037205756083130835, "grad_norm": 0.13739798963069916, "invalid_tail_samples": 23.7, "learning_rate": 7.600028331232699e-05, "loss": 0.0413, "positive_teacher_pairs": 26884.9, "relation_loss": 0.004119815025478602, "selected_pairs": 26884.9, "step": 10790, "student_distance_mean": 1076.8329956054688, "teacher_distance_mean": 0.8588655471801758, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.004119815025478602, "weighted_relation_loss": 0.004119815025478602 }, { "action_query_batch_std": 18.72383632659912, "action_query_norm": 822.3074890136719, "action_relation_loss": 0.0039903184864670035, "auxiliary_loss_weight": 1.0, "epoch": 10.102899906454631, "flow_matching_loss": 0.03966766707599163, "grad_norm": 0.10947223007678986, "invalid_tail_samples": 22.7, "learning_rate": 7.595318977790408e-05, "loss": 0.0437, "positive_teacher_pairs": 27106.9, "relation_loss": 0.0039903184864670035, "selected_pairs": 27106.9, "step": 10800, "student_distance_mean": 1063.387060546875, "teacher_distance_mean": 0.8443946719169617, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0039903184864670035, "weighted_relation_loss": 0.0039903184864670035 }, { "action_query_batch_std": 18.784195327758788, "action_query_norm": 819.5361877441406, "action_relation_loss": 0.004122894257307053, "auxiliary_loss_weight": 1.0, "epoch": 10.112254443405051, "flow_matching_loss": 0.03703464455902576, "grad_norm": 0.10879489034414291, "invalid_tail_samples": 23.3, "learning_rate": 7.590606470790836e-05, "loss": 0.0412, "positive_teacher_pairs": 26969.6, "relation_loss": 0.004122894257307053, "selected_pairs": 26969.6, "step": 10810, "student_distance_mean": 1068.2971435546874, "teacher_distance_mean": 0.8534494161605835, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.004122894257307053, "weighted_relation_loss": 0.004122894257307053 }, { "action_query_batch_std": 19.154513931274415, "action_query_norm": 833.1348815917969, "action_relation_loss": 0.003898995486088097, "auxiliary_loss_weight": 1.0, "epoch": 10.121608980355472, "flow_matching_loss": 0.03948248364031315, "grad_norm": 0.12690798938274384, "invalid_tail_samples": 23.0, "learning_rate": 7.585890815960125e-05, "loss": 0.0434, "positive_teacher_pairs": 27032.6, "relation_loss": 0.003898995486088097, "selected_pairs": 27032.6, "step": 10820, "student_distance_mean": 1087.9450439453126, "teacher_distance_mean": 0.8601637005805969, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.003898995486088097, "weighted_relation_loss": 0.003898995486088097 }, { "action_query_batch_std": 18.938774490356444, "action_query_norm": 831.7921020507813, "action_relation_loss": 0.004150626109912991, "auxiliary_loss_weight": 1.0, "epoch": 10.130963517305894, "flow_matching_loss": 0.0372373640537262, "grad_norm": 0.11037245392799377, "invalid_tail_samples": 22.6, "learning_rate": 7.581172019028238e-05, "loss": 0.0414, "positive_teacher_pairs": 27123.2, "relation_loss": 0.004150626109912991, "selected_pairs": 27123.2, "step": 10830, "student_distance_mean": 1078.2723388671875, "teacher_distance_mean": 0.8467944622039795, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.004150626109912991, "weighted_relation_loss": 0.004150626109912991 }, { "action_query_batch_std": 18.824469757080077, "action_query_norm": 825.8447448730469, "action_relation_loss": 0.004166947002522648, "auxiliary_loss_weight": 1.0, "epoch": 10.140318054256314, "flow_matching_loss": 0.039949764311313626, "grad_norm": 0.13916447758674622, "invalid_tail_samples": 22.5, "learning_rate": 7.576450085728959e-05, "loss": 0.0441, "positive_teacher_pairs": 27161.6, "relation_loss": 0.004166947002522648, "selected_pairs": 27161.6, "step": 10840, "student_distance_mean": 1069.6401611328124, "teacher_distance_mean": 0.8473447620868683, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.004166947002522648, "weighted_relation_loss": 0.004166947002522648 }, { "action_query_batch_std": 19.0638219833374, "action_query_norm": 829.7331176757813, "action_relation_loss": 0.0040913237491622565, "auxiliary_loss_weight": 1.0, "epoch": 10.149672591206736, "flow_matching_loss": 0.0386308379471302, "grad_norm": 0.13142573833465576, "invalid_tail_samples": 23.1, "learning_rate": 7.571725021799885e-05, "loss": 0.0427, "positive_teacher_pairs": 27010.4, "relation_loss": 0.0040913237491622565, "selected_pairs": 27010.4, "step": 10850, "student_distance_mean": 1082.4427368164063, "teacher_distance_mean": 0.8574159979820252, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0040913237491622565, "weighted_relation_loss": 0.0040913237491622565 }, { "action_query_batch_std": 18.983069801330565, "action_query_norm": 826.7672546386718, "action_relation_loss": 0.004027366219088435, "auxiliary_loss_weight": 1.0, "epoch": 10.159027128157156, "flow_matching_loss": 0.03934789076447487, "grad_norm": 0.11578360944986343, "invalid_tail_samples": 24.6, "learning_rate": 7.566996832982409e-05, "loss": 0.0434, "positive_teacher_pairs": 26663.3, "relation_loss": 0.004027366219088435, "selected_pairs": 26663.3, "step": 10860, "student_distance_mean": 1082.9655029296875, "teacher_distance_mean": 0.8552477717399597, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.004027366219088435, "weighted_relation_loss": 0.004027366219088435 }, { "action_query_batch_std": 18.984186363220214, "action_query_norm": 826.3057983398437, "action_relation_loss": 0.004028451396152377, "auxiliary_loss_weight": 1.0, "epoch": 10.168381665107578, "flow_matching_loss": 0.03634592778980732, "grad_norm": 0.10734985023736954, "invalid_tail_samples": 23.5, "learning_rate": 7.56226552502173e-05, "loss": 0.0404, "positive_teacher_pairs": 26916.8, "relation_loss": 0.004028451396152377, "selected_pairs": 26916.8, "step": 10870, "student_distance_mean": 1077.9962524414063, "teacher_distance_mean": 0.8495739459991455, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.004028451396152377, "weighted_relation_loss": 0.004028451396152377 }, { "action_query_batch_std": 18.97074146270752, "action_query_norm": 827.5025268554688, "action_relation_loss": 0.004113542172126472, "auxiliary_loss_weight": 1.0, "epoch": 10.177736202057998, "flow_matching_loss": 0.0374759417027235, "grad_norm": 0.1305457204580307, "invalid_tail_samples": 24.2, "learning_rate": 7.557531103666833e-05, "loss": 0.0416, "positive_teacher_pairs": 26753.4, "relation_loss": 0.004113542172126472, "selected_pairs": 26753.4, "step": 10880, "student_distance_mean": 1079.1825439453125, "teacher_distance_mean": 0.8533388555049897, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.004113542172126472, "weighted_relation_loss": 0.004113542172126472 }, { "action_query_batch_std": 19.325568199157715, "action_query_norm": 841.7022827148437, "action_relation_loss": 0.0040937489829957485, "auxiliary_loss_weight": 1.0, "epoch": 10.187090739008418, "flow_matching_loss": 0.038060346618294716, "grad_norm": 0.10138330608606339, "invalid_tail_samples": 22.6, "learning_rate": 7.552793574670485e-05, "loss": 0.0422, "positive_teacher_pairs": 27129.9, "relation_loss": 0.0040937489829957485, "selected_pairs": 27129.9, "step": 10890, "student_distance_mean": 1100.8535278320312, "teacher_distance_mean": 0.8630773186683655, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0040937489829957485, "weighted_relation_loss": 0.0040937489829957485 }, { "action_query_batch_std": 19.513835144042968, "action_query_norm": 850.21875, "action_relation_loss": 0.003760250308550894, "auxiliary_loss_weight": 1.0, "epoch": 10.19644527595884, "flow_matching_loss": 0.038644567131996155, "grad_norm": 0.15450464189052582, "invalid_tail_samples": 22.3, "learning_rate": 7.54805294378923e-05, "loss": 0.0424, "positive_teacher_pairs": 27207.3, "relation_loss": 0.003760250308550894, "selected_pairs": 27207.3, "step": 10900, "student_distance_mean": 1108.1477294921874, "teacher_distance_mean": 0.8599816262722015, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.003760250308550894, "weighted_relation_loss": 0.003760250308550894 }, { "action_query_batch_std": 19.044888496398926, "action_query_norm": 832.6786437988281, "action_relation_loss": 0.004101914656348527, "auxiliary_loss_weight": 1.0, "epoch": 10.20579981290926, "flow_matching_loss": 0.03982923366129398, "grad_norm": 0.19301262497901917, "invalid_tail_samples": 21.5, "learning_rate": 7.543309216783384e-05, "loss": 0.0439, "positive_teacher_pairs": 27387.4, "relation_loss": 0.004101914656348527, "selected_pairs": 27387.4, "step": 10910, "student_distance_mean": 1080.9630737304688, "teacher_distance_mean": 0.8438433468341827, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.004101914656348527, "weighted_relation_loss": 0.004101914656348527 }, { "action_query_batch_std": 19.49825038909912, "action_query_norm": 844.5120361328125, "action_relation_loss": 0.0038654072443023322, "auxiliary_loss_weight": 1.0, "epoch": 10.215154349859683, "flow_matching_loss": 0.03738938122987747, "grad_norm": 0.19103291630744934, "invalid_tail_samples": 25.0, "learning_rate": 7.53856239941702e-05, "loss": 0.0413, "positive_teacher_pairs": 26578.0, "relation_loss": 0.0038654072443023322, "selected_pairs": 26578.0, "step": 10920, "student_distance_mean": 1112.0886596679688, "teacher_distance_mean": 0.865744686126709, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0038654072443023322, "weighted_relation_loss": 0.0038654072443023322 }, { "action_query_batch_std": 19.371494865417482, "action_query_norm": 844.2703857421875, "action_relation_loss": 0.003965035662986338, "auxiliary_loss_weight": 1.0, "epoch": 10.224508886810103, "flow_matching_loss": 0.03788408227264881, "grad_norm": 0.11831710487604141, "invalid_tail_samples": 24.2, "learning_rate": 7.533812497457972e-05, "loss": 0.0418, "positive_teacher_pairs": 26759.7, "relation_loss": 0.003965035662986338, "selected_pairs": 26759.7, "step": 10930, "student_distance_mean": 1101.5338500976563, "teacher_distance_mean": 0.8549629211425781, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.003965035662986338, "weighted_relation_loss": 0.003965035662986338 }, { "action_query_batch_std": 19.06093101501465, "action_query_norm": 830.6727600097656, "action_relation_loss": 0.003954770206473768, "auxiliary_loss_weight": 1.0, "epoch": 10.233863423760523, "flow_matching_loss": 0.038841909170150755, "grad_norm": 0.12941892445087433, "invalid_tail_samples": 23.0, "learning_rate": 7.529059516677814e-05, "loss": 0.0428, "positive_teacher_pairs": 27034.5, "relation_loss": 0.003954770206473768, "selected_pairs": 27034.5, "step": 10940, "student_distance_mean": 1082.2477905273438, "teacher_distance_mean": 0.8459855616092682, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.003954770206473768, "weighted_relation_loss": 0.003954770206473768 }, { "action_query_batch_std": 19.296997451782225, "action_query_norm": 837.9294006347657, "action_relation_loss": 0.00390015144366771, "auxiliary_loss_weight": 1.0, "epoch": 10.243217960710945, "flow_matching_loss": 0.03882540874183178, "grad_norm": 0.12541735172271729, "invalid_tail_samples": 22.6, "learning_rate": 7.524303462851872e-05, "loss": 0.0427, "positive_teacher_pairs": 27127.5, "relation_loss": 0.00390015144366771, "selected_pairs": 27127.5, "step": 10950, "student_distance_mean": 1099.1407592773437, "teacher_distance_mean": 0.8582009077072144, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.00390015144366771, "weighted_relation_loss": 0.00390015144366771 }, { "action_query_batch_std": 19.317942237854005, "action_query_norm": 840.2214477539062, "action_relation_loss": 0.003994547529146075, "auxiliary_loss_weight": 1.0, "epoch": 10.252572497661365, "flow_matching_loss": 0.03947574812918901, "grad_norm": 0.13786129653453827, "invalid_tail_samples": 23.2, "learning_rate": 7.519544341759192e-05, "loss": 0.0435, "positive_teacher_pairs": 27010.5, "relation_loss": 0.003994547529146075, "selected_pairs": 27010.5, "step": 10960, "student_distance_mean": 1098.8317138671875, "teacher_distance_mean": 0.8612121105194092, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.003994547529146075, "weighted_relation_loss": 0.003994547529146075 }, { "action_query_batch_std": 18.98861789703369, "action_query_norm": 826.9309936523438, "action_relation_loss": 0.004016638919711113, "auxiliary_loss_weight": 1.0, "epoch": 10.261927034611787, "flow_matching_loss": 0.038509277254343034, "grad_norm": 0.11357595026493073, "invalid_tail_samples": 25.3, "learning_rate": 7.514782159182562e-05, "loss": 0.0425, "positive_teacher_pairs": 26504.1, "relation_loss": 0.004016638919711113, "selected_pairs": 26504.1, "step": 10970, "student_distance_mean": 1080.7463012695312, "teacher_distance_mean": 0.8485355913639069, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.004016638919711113, "weighted_relation_loss": 0.004016638919711113 }, { "action_query_batch_std": 18.999153327941894, "action_query_norm": 829.91982421875, "action_relation_loss": 0.004076665709726512, "auxiliary_loss_weight": 1.0, "epoch": 10.271281571562207, "flow_matching_loss": 0.03958294838666916, "grad_norm": 0.14784857630729675, "invalid_tail_samples": 23.0, "learning_rate": 7.510016920908481e-05, "loss": 0.0437, "positive_teacher_pairs": 27034.4, "relation_loss": 0.004076665709726512, "selected_pairs": 27034.4, "step": 10980, "student_distance_mean": 1083.073583984375, "teacher_distance_mean": 0.848150759935379, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.004076665709726512, "weighted_relation_loss": 0.004076665709726512 }, { "action_query_batch_std": 19.119800186157228, "action_query_norm": 833.1955139160157, "action_relation_loss": 0.0038999789394438267, "auxiliary_loss_weight": 1.0, "epoch": 10.28063610851263, "flow_matching_loss": 0.038380485773086545, "grad_norm": 0.12038619816303253, "invalid_tail_samples": 26.4, "learning_rate": 7.505248632727158e-05, "loss": 0.0423, "positive_teacher_pairs": 26257.4, "relation_loss": 0.0038999789394438267, "selected_pairs": 26257.4, "step": 10990, "student_distance_mean": 1092.579296875, "teacher_distance_mean": 0.8582810640335083, "valid_action_samples": 229.6, "weighted_auxiliary_loss": 0.0038999789394438267, "weighted_relation_loss": 0.0038999789394438267 }, { "action_query_batch_std": 18.86530113220215, "action_query_norm": 819.77353515625, "action_relation_loss": 0.004114732169546187, "auxiliary_loss_weight": 1.0, "epoch": 10.28999064546305, "flow_matching_loss": 0.038408170267939565, "grad_norm": 0.14453360438346863, "invalid_tail_samples": 27.1, "learning_rate": 7.50047730043252e-05, "loss": 0.0425, "positive_teacher_pairs": 26094.0, "relation_loss": 0.004114732169546187, "selected_pairs": 26094.0, "step": 11000, "student_distance_mean": 1074.7404418945312, "teacher_distance_mean": 0.8524700999259949, "valid_action_samples": 228.9, "weighted_auxiliary_loss": 0.004114732169546187, "weighted_relation_loss": 0.004114732169546187 }, { "action_query_batch_std": 19.083174896240234, "action_query_norm": 827.4273681640625, "action_relation_loss": 0.0038846662035211922, "auxiliary_loss_weight": 1.0, "epoch": 10.29934518241347, "flow_matching_loss": 0.036691300198435785, "grad_norm": 0.11864857375621796, "invalid_tail_samples": 25.0, "learning_rate": 7.495702929822183e-05, "loss": 0.0406, "positive_teacher_pairs": 26578.5, "relation_loss": 0.0038846662035211922, "selected_pairs": 26578.5, "step": 11010, "student_distance_mean": 1086.3041015625, "teacher_distance_mean": 0.8577611565589904, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0038846662035211922, "weighted_relation_loss": 0.0038846662035211922 }, { "action_query_batch_std": 19.093438720703126, "action_query_norm": 828.7479614257812, "action_relation_loss": 0.004133203905075789, "auxiliary_loss_weight": 1.0, "epoch": 10.308699719363892, "flow_matching_loss": 0.035516800545156005, "grad_norm": 0.10753536224365234, "invalid_tail_samples": 23.1, "learning_rate": 7.490925526697455e-05, "loss": 0.0397, "positive_teacher_pairs": 27011.2, "relation_loss": 0.004133203905075789, "selected_pairs": 27011.2, "step": 11020, "student_distance_mean": 1085.579638671875, "teacher_distance_mean": 0.853117561340332, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.004133203905075789, "weighted_relation_loss": 0.004133203905075789 }, { "action_query_batch_std": 19.005994987487792, "action_query_norm": 827.2363342285156, "action_relation_loss": 0.004002000507898629, "auxiliary_loss_weight": 1.0, "epoch": 10.318054256314312, "flow_matching_loss": 0.03765943981707096, "grad_norm": 0.10284938663244247, "invalid_tail_samples": 23.0, "learning_rate": 7.486145096863334e-05, "loss": 0.0417, "positive_teacher_pairs": 27032.0, "relation_loss": 0.004002000507898629, "selected_pairs": 27032.0, "step": 11030, "student_distance_mean": 1080.0671875, "teacher_distance_mean": 0.8492246210575104, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.004002000507898629, "weighted_relation_loss": 0.004002000507898629 }, { "action_query_batch_std": 19.14349784851074, "action_query_norm": 832.3012817382812, "action_relation_loss": 0.0039798659970983865, "auxiliary_loss_weight": 1.0, "epoch": 10.327408793264734, "flow_matching_loss": 0.03878112733364105, "grad_norm": 0.11779943108558655, "invalid_tail_samples": 24.6, "learning_rate": 7.481361646128491e-05, "loss": 0.0428, "positive_teacher_pairs": 26665.8, "relation_loss": 0.0039798659970983865, "selected_pairs": 26665.8, "step": 11040, "student_distance_mean": 1089.772900390625, "teacher_distance_mean": 0.8562390983104706, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0039798659970983865, "weighted_relation_loss": 0.0039798659970983865 }, { "action_query_batch_std": 19.223915100097656, "action_query_norm": 837.2238891601562, "action_relation_loss": 0.004018572252243757, "auxiliary_loss_weight": 1.0, "epoch": 10.336763330215154, "flow_matching_loss": 0.03954409919679165, "grad_norm": 0.13598991930484772, "invalid_tail_samples": 23.1, "learning_rate": 7.476575180305271e-05, "loss": 0.0436, "positive_teacher_pairs": 27012.6, "relation_loss": 0.004018572252243757, "selected_pairs": 27012.6, "step": 11050, "student_distance_mean": 1092.9428955078124, "teacher_distance_mean": 0.8572866916656494, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.004018572252243757, "weighted_relation_loss": 0.004018572252243757 }, { "action_query_batch_std": 19.155178451538085, "action_query_norm": 833.0334045410157, "action_relation_loss": 0.004057491244748235, "auxiliary_loss_weight": 1.0, "epoch": 10.346117867165574, "flow_matching_loss": 0.03670277372002602, "grad_norm": 0.1259072721004486, "invalid_tail_samples": 24.6, "learning_rate": 7.471785705209682e-05, "loss": 0.0408, "positive_teacher_pairs": 26667.4, "relation_loss": 0.004057491244748235, "selected_pairs": 26667.4, "step": 11060, "student_distance_mean": 1088.0432006835938, "teacher_distance_mean": 0.8599551498889924, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.004057491244748235, "weighted_relation_loss": 0.004057491244748235 }, { "action_query_batch_std": 18.75574951171875, "action_query_norm": 826.9882629394531, "action_relation_loss": 0.004028482385911048, "auxiliary_loss_weight": 1.0, "epoch": 10.355472404115996, "flow_matching_loss": 0.03930259123444557, "grad_norm": 0.13196219503879547, "invalid_tail_samples": 23.6, "learning_rate": 7.466993226661387e-05, "loss": 0.0433, "positive_teacher_pairs": 26899.9, "relation_loss": 0.004028482385911048, "selected_pairs": 26899.9, "step": 11070, "student_distance_mean": 1068.9197143554688, "teacher_distance_mean": 0.8388134479522705, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.004028482385911048, "weighted_relation_loss": 0.004028482385911048 }, { "action_query_batch_std": 19.2409460067749, "action_query_norm": 840.2836059570312, "action_relation_loss": 0.003769870917312801, "auxiliary_loss_weight": 1.0, "epoch": 10.364826941066417, "flow_matching_loss": 0.03831271138042212, "grad_norm": 0.1218516007065773, "invalid_tail_samples": 22.2, "learning_rate": 7.462197750483699e-05, "loss": 0.0421, "positive_teacher_pairs": 27222.4, "relation_loss": 0.003769870917312801, "selected_pairs": 27222.4, "step": 11080, "student_distance_mean": 1098.9151000976562, "teacher_distance_mean": 0.8602357745170593, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.003769870917312801, "weighted_relation_loss": 0.003769870917312801 }, { "action_query_batch_std": 19.236986541748045, "action_query_norm": 839.6497009277343, "action_relation_loss": 0.003841191227547824, "auxiliary_loss_weight": 1.0, "epoch": 10.374181478016839, "flow_matching_loss": 0.03632774334400892, "grad_norm": 0.11931274831295013, "invalid_tail_samples": 23.2, "learning_rate": 7.457399282503574e-05, "loss": 0.0402, "positive_teacher_pairs": 27004.6, "relation_loss": 0.003841191227547824, "selected_pairs": 27004.6, "step": 11090, "student_distance_mean": 1097.1268432617187, "teacher_distance_mean": 0.8552614986896515, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.003841191227547824, "weighted_relation_loss": 0.003841191227547824 }, { "action_query_batch_std": 19.317439842224122, "action_query_norm": 840.8530151367188, "action_relation_loss": 0.0038453704910352826, "auxiliary_loss_weight": 1.0, "epoch": 10.383536014967259, "flow_matching_loss": 0.038111038506031036, "grad_norm": 0.13608919084072113, "invalid_tail_samples": 21.9, "learning_rate": 7.452597828551604e-05, "loss": 0.042, "positive_teacher_pairs": 27295.1, "relation_loss": 0.0038453704910352826, "selected_pairs": 27295.1, "step": 11100, "student_distance_mean": 1097.7586303710937, "teacher_distance_mean": 0.8580511569976806, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.0038453704910352826, "weighted_relation_loss": 0.0038453704910352826 }, { "action_query_batch_std": 19.427139282226562, "action_query_norm": 844.1585083007812, "action_relation_loss": 0.0038848951226100326, "auxiliary_loss_weight": 1.0, "epoch": 10.39289055191768, "flow_matching_loss": 0.03606863804161549, "grad_norm": 0.1386273056268692, "invalid_tail_samples": 24.6, "learning_rate": 7.447793394462006e-05, "loss": 0.04, "positive_teacher_pairs": 26667.7, "relation_loss": 0.0038848951226100326, "selected_pairs": 26667.7, "step": 11110, "student_distance_mean": 1103.3888671875, "teacher_distance_mean": 0.8554830193519593, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0038848951226100326, "weighted_relation_loss": 0.0038848951226100326 }, { "action_query_batch_std": 19.072870445251464, "action_query_norm": 833.8386779785156, "action_relation_loss": 0.003958497266285122, "auxiliary_loss_weight": 1.0, "epoch": 10.402245088868101, "flow_matching_loss": 0.037407441437244414, "grad_norm": 0.17016400396823883, "invalid_tail_samples": 22.1, "learning_rate": 7.442985986072624e-05, "loss": 0.0414, "positive_teacher_pairs": 27247.6, "relation_loss": 0.003958497266285122, "selected_pairs": 27247.6, "step": 11120, "student_distance_mean": 1084.9282470703124, "teacher_distance_mean": 0.8485770404338837, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.003958497266285122, "weighted_relation_loss": 0.003958497266285122 }, { "action_query_batch_std": 18.98274383544922, "action_query_norm": 825.8070678710938, "action_relation_loss": 0.003910316294059158, "auxiliary_loss_weight": 1.0, "epoch": 10.411599625818521, "flow_matching_loss": 0.0364312594756484, "grad_norm": 0.1354350745677948, "invalid_tail_samples": 27.2, "learning_rate": 7.438175609224908e-05, "loss": 0.0403, "positive_teacher_pairs": 26073.2, "relation_loss": 0.003910316294059158, "selected_pairs": 26073.2, "step": 11130, "student_distance_mean": 1075.3693359375, "teacher_distance_mean": 0.8497159421443939, "valid_action_samples": 228.8, "weighted_auxiliary_loss": 0.003910316294059158, "weighted_relation_loss": 0.003910316294059158 }, { "action_query_batch_std": 19.41372146606445, "action_query_norm": 845.0624145507812, "action_relation_loss": 0.004110982641577721, "auxiliary_loss_weight": 1.0, "epoch": 10.420954162768943, "flow_matching_loss": 0.03940621018409729, "grad_norm": 0.14022105932235718, "invalid_tail_samples": 24.2, "learning_rate": 7.433362269763924e-05, "loss": 0.0435, "positive_teacher_pairs": 26759.0, "relation_loss": 0.004110982641577721, "selected_pairs": 26759.0, "step": 11140, "student_distance_mean": 1111.1075927734375, "teacher_distance_mean": 0.8593740284442901, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.004110982641577721, "weighted_relation_loss": 0.004110982641577721 }, { "action_query_batch_std": 19.1335750579834, "action_query_norm": 834.7339233398437, "action_relation_loss": 0.0039873318513855335, "auxiliary_loss_weight": 1.0, "epoch": 10.430308699719363, "flow_matching_loss": 0.04201581291854382, "grad_norm": 0.13119752705097198, "invalid_tail_samples": 23.4, "learning_rate": 7.428545973538329e-05, "loss": 0.046, "positive_teacher_pairs": 26951.3, "relation_loss": 0.0039873318513855335, "selected_pairs": 26951.3, "step": 11150, "student_distance_mean": 1089.0603515625, "teacher_distance_mean": 0.8539914846420288, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0039873318513855335, "weighted_relation_loss": 0.0039873318513855335 }, { "action_query_batch_std": 19.251495361328125, "action_query_norm": 839.3668762207031, "action_relation_loss": 0.004066018387675285, "auxiliary_loss_weight": 1.0, "epoch": 10.439663236669785, "flow_matching_loss": 0.03700944446027279, "grad_norm": 0.12074027210474014, "invalid_tail_samples": 24.5, "learning_rate": 7.42372672640038e-05, "loss": 0.0411, "positive_teacher_pairs": 26686.2, "relation_loss": 0.004066018387675285, "selected_pairs": 26686.2, "step": 11160, "student_distance_mean": 1091.5283203125, "teacher_distance_mean": 0.8515841007232666, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.004066018387675285, "weighted_relation_loss": 0.004066018387675285 }, { "action_query_batch_std": 19.471299934387208, "action_query_norm": 848.844091796875, "action_relation_loss": 0.00408048639073968, "auxiliary_loss_weight": 1.0, "epoch": 10.449017773620206, "flow_matching_loss": 0.037194357626140116, "grad_norm": 0.14957262575626373, "invalid_tail_samples": 23.3, "learning_rate": 7.418904534205917e-05, "loss": 0.0413, "positive_teacher_pairs": 26969.3, "relation_loss": 0.00408048639073968, "selected_pairs": 26969.3, "step": 11170, "student_distance_mean": 1107.3148315429687, "teacher_distance_mean": 0.8621431946754455, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.00408048639073968, "weighted_relation_loss": 0.00408048639073968 }, { "action_query_batch_std": 18.997988128662108, "action_query_norm": 828.5486877441406, "action_relation_loss": 0.004155705054290593, "auxiliary_loss_weight": 1.0, "epoch": 10.458372310570628, "flow_matching_loss": 0.03932621665298939, "grad_norm": 0.12561090290546417, "invalid_tail_samples": 26.1, "learning_rate": 7.414079402814356e-05, "loss": 0.0435, "positive_teacher_pairs": 26328.1, "relation_loss": 0.004155705054290593, "selected_pairs": 26328.1, "step": 11180, "student_distance_mean": 1084.7052978515626, "teacher_distance_mean": 0.8522380232810974, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.004155705054290593, "weighted_relation_loss": 0.004155705054290593 }, { "action_query_batch_std": 19.39213924407959, "action_query_norm": 842.0437683105469, "action_relation_loss": 0.004107620683498681, "auxiliary_loss_weight": 1.0, "epoch": 10.467726847521048, "flow_matching_loss": 0.04021552801132202, "grad_norm": 0.1348923146724701, "invalid_tail_samples": 24.5, "learning_rate": 7.409251338088687e-05, "loss": 0.0443, "positive_teacher_pairs": 26691.4, "relation_loss": 0.004107620683498681, "selected_pairs": 26691.4, "step": 11190, "student_distance_mean": 1099.2758544921876, "teacher_distance_mean": 0.8577737033367157, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.004107620683498681, "weighted_relation_loss": 0.004107620683498681 }, { "action_query_batch_std": 19.211739158630373, "action_query_norm": 836.8212036132812, "action_relation_loss": 0.003943562274798751, "auxiliary_loss_weight": 1.0, "epoch": 10.477081384471468, "flow_matching_loss": 0.037155451253056526, "grad_norm": 0.12525837123394012, "invalid_tail_samples": 23.4, "learning_rate": 7.404420345895467e-05, "loss": 0.0411, "positive_teacher_pairs": 26949.8, "relation_loss": 0.003943562274798751, "selected_pairs": 26949.8, "step": 11200, "student_distance_mean": 1096.520458984375, "teacher_distance_mean": 0.8533223688602447, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.003943562274798751, "weighted_relation_loss": 0.003943562274798751 }, { "action_query_batch_std": 19.261140823364258, "action_query_norm": 833.9345886230469, "action_relation_loss": 0.004048314969986677, "auxiliary_loss_weight": 1.0, "epoch": 10.48643592142189, "flow_matching_loss": 0.0369107473641634, "grad_norm": 0.10998117923736572, "invalid_tail_samples": 24.9, "learning_rate": 7.399586432104804e-05, "loss": 0.041, "positive_teacher_pairs": 26594.2, "relation_loss": 0.004048314969986677, "selected_pairs": 26594.2, "step": 11210, "student_distance_mean": 1094.989501953125, "teacher_distance_mean": 0.8539423048496246, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.004048314969986677, "weighted_relation_loss": 0.004048314969986677 }, { "action_query_batch_std": 19.366279983520506, "action_query_norm": 841.3755187988281, "action_relation_loss": 0.0039403981296345595, "auxiliary_loss_weight": 1.0, "epoch": 10.49579045837231, "flow_matching_loss": 0.0381549209356308, "grad_norm": 0.13149213790893555, "invalid_tail_samples": 22.0, "learning_rate": 7.394749602590358e-05, "loss": 0.0421, "positive_teacher_pairs": 27272.6, "relation_loss": 0.0039403981296345595, "selected_pairs": 27272.6, "step": 11220, "student_distance_mean": 1099.015283203125, "teacher_distance_mean": 0.8540492653846741, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.0039403981296345595, "weighted_relation_loss": 0.0039403981296345595 }, { "action_query_batch_std": 19.50393924713135, "action_query_norm": 846.7190368652343, "action_relation_loss": 0.003825819701887667, "auxiliary_loss_weight": 1.0, "epoch": 10.505144995322732, "flow_matching_loss": 0.03558985218405723, "grad_norm": 0.10002452880144119, "invalid_tail_samples": 22.0, "learning_rate": 7.389909863229336e-05, "loss": 0.0394, "positive_teacher_pairs": 27263.8, "relation_loss": 0.003825819701887667, "selected_pairs": 27263.8, "step": 11230, "student_distance_mean": 1111.1354858398438, "teacher_distance_mean": 0.8640173971652985, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.003825819701887667, "weighted_relation_loss": 0.003825819701887667 }, { "action_query_batch_std": 19.24520263671875, "action_query_norm": 841.2020629882812, "action_relation_loss": 0.0039727374445647, "auxiliary_loss_weight": 1.0, "epoch": 10.514499532273152, "flow_matching_loss": 0.03845681622624397, "grad_norm": 0.11434093862771988, "invalid_tail_samples": 22.0, "learning_rate": 7.385067219902477e-05, "loss": 0.0424, "positive_teacher_pairs": 27270.3, "relation_loss": 0.0039727374445647, "selected_pairs": 27270.3, "step": 11240, "student_distance_mean": 1096.8163818359376, "teacher_distance_mean": 0.847406131029129, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.0039727374445647, "weighted_relation_loss": 0.0039727374445647 }, { "action_query_batch_std": 19.41090679168701, "action_query_norm": 844.6960327148438, "action_relation_loss": 0.003926407778635621, "auxiliary_loss_weight": 1.0, "epoch": 10.523854069223573, "flow_matching_loss": 0.03598197996616363, "grad_norm": 0.14592798054218292, "invalid_tail_samples": 22.9, "learning_rate": 7.380221678494049e-05, "loss": 0.0399, "positive_teacher_pairs": 27061.9, "relation_loss": 0.003926407778635621, "selected_pairs": 27061.9, "step": 11250, "student_distance_mean": 1105.2554321289062, "teacher_distance_mean": 0.855303817987442, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.003926407778635621, "weighted_relation_loss": 0.003926407778635621 }, { "action_query_batch_std": 19.24074058532715, "action_query_norm": 838.8858459472656, "action_relation_loss": 0.004006650974042713, "auxiliary_loss_weight": 1.0, "epoch": 10.533208606173995, "flow_matching_loss": 0.037374241091310975, "grad_norm": 0.13446664810180664, "invalid_tail_samples": 25.0, "learning_rate": 7.37537324489184e-05, "loss": 0.0414, "positive_teacher_pairs": 26575.1, "relation_loss": 0.004006650974042713, "selected_pairs": 26575.1, "step": 11260, "student_distance_mean": 1091.8233520507813, "teacher_distance_mean": 0.8489171624183655, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.004006650974042713, "weighted_relation_loss": 0.004006650974042713 }, { "action_query_batch_std": 19.23240394592285, "action_query_norm": 837.7345886230469, "action_relation_loss": 0.003877313039265573, "auxiliary_loss_weight": 1.0, "epoch": 10.542563143124415, "flow_matching_loss": 0.03812972120940685, "grad_norm": 0.13399669528007507, "invalid_tail_samples": 26.5, "learning_rate": 7.370521924987155e-05, "loss": 0.042, "positive_teacher_pairs": 26226.8, "relation_loss": 0.003877313039265573, "selected_pairs": 26226.8, "step": 11270, "student_distance_mean": 1099.1949340820313, "teacher_distance_mean": 0.8482461750507355, "valid_action_samples": 229.5, "weighted_auxiliary_loss": 0.003877313039265573, "weighted_relation_loss": 0.003877313039265573 }, { "action_query_batch_std": 19.629730415344238, "action_query_norm": 851.3882873535156, "action_relation_loss": 0.003843416995368898, "auxiliary_loss_weight": 1.0, "epoch": 10.551917680074837, "flow_matching_loss": 0.03895445019006729, "grad_norm": 0.12683892250061035, "invalid_tail_samples": 24.6, "learning_rate": 7.365667724674806e-05, "loss": 0.0428, "positive_teacher_pairs": 26668.4, "relation_loss": 0.003843416995368898, "selected_pairs": 26668.4, "step": 11280, "student_distance_mean": 1116.169482421875, "teacher_distance_mean": 0.8651190161705017, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.003843416995368898, "weighted_relation_loss": 0.003843416995368898 }, { "action_query_batch_std": 19.34904327392578, "action_query_norm": 839.1502624511719, "action_relation_loss": 0.0038156176917254923, "auxiliary_loss_weight": 1.0, "epoch": 10.561272217025257, "flow_matching_loss": 0.03894389979541302, "grad_norm": 0.09043149650096893, "invalid_tail_samples": 24.6, "learning_rate": 7.360810649853105e-05, "loss": 0.0428, "positive_teacher_pairs": 26665.5, "relation_loss": 0.0038156176917254923, "selected_pairs": 26665.5, "step": 11290, "student_distance_mean": 1101.6807861328125, "teacher_distance_mean": 0.8588155686855317, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0038156176917254923, "weighted_relation_loss": 0.0038156176917254923 }, { "action_query_batch_std": 19.311090850830077, "action_query_norm": 838.6061767578125, "action_relation_loss": 0.003860958036966622, "auxiliary_loss_weight": 1.0, "epoch": 10.570626753975677, "flow_matching_loss": 0.03658110946416855, "grad_norm": 0.10864190012216568, "invalid_tail_samples": 24.3, "learning_rate": 7.355950706423853e-05, "loss": 0.0404, "positive_teacher_pairs": 26735.5, "relation_loss": 0.003860958036966622, "selected_pairs": 26735.5, "step": 11300, "student_distance_mean": 1099.5499145507813, "teacher_distance_mean": 0.853323882818222, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.003860958036966622, "weighted_relation_loss": 0.003860958036966622 }, { "action_query_batch_std": 19.208900260925294, "action_query_norm": 837.9631896972656, "action_relation_loss": 0.003976526414044201, "auxiliary_loss_weight": 1.0, "epoch": 10.5799812909261, "flow_matching_loss": 0.03707831744104624, "grad_norm": 0.1175537034869194, "invalid_tail_samples": 23.6, "learning_rate": 7.351087900292342e-05, "loss": 0.0411, "positive_teacher_pairs": 26895.8, "relation_loss": 0.003976526414044201, "selected_pairs": 26895.8, "step": 11310, "student_distance_mean": 1093.4138671875, "teacher_distance_mean": 0.850238835811615, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.003976526414044201, "weighted_relation_loss": 0.003976526414044201 }, { "action_query_batch_std": 19.34415473937988, "action_query_norm": 839.1477416992187, "action_relation_loss": 0.003926366381347179, "auxiliary_loss_weight": 1.0, "epoch": 10.58933582787652, "flow_matching_loss": 0.03564899358898401, "grad_norm": 0.11948590725660324, "invalid_tail_samples": 24.2, "learning_rate": 7.346222237367339e-05, "loss": 0.0396, "positive_teacher_pairs": 26762.2, "relation_loss": 0.003926366381347179, "selected_pairs": 26762.2, "step": 11320, "student_distance_mean": 1100.5370849609376, "teacher_distance_mean": 0.8522630512714386, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.003926366381347179, "weighted_relation_loss": 0.003926366381347179 }, { "action_query_batch_std": 19.34030990600586, "action_query_norm": 844.0472473144531, "action_relation_loss": 0.0038121165707707405, "auxiliary_loss_weight": 1.0, "epoch": 10.598690364826941, "flow_matching_loss": 0.037827203050255775, "grad_norm": 0.10097257047891617, "invalid_tail_samples": 22.0, "learning_rate": 7.341353723561081e-05, "loss": 0.0416, "positive_teacher_pairs": 27264.6, "relation_loss": 0.0038121165707707405, "selected_pairs": 27264.6, "step": 11330, "student_distance_mean": 1098.410498046875, "teacher_distance_mean": 0.8512579798698425, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.0038121165707707405, "weighted_relation_loss": 0.0038121165707707405 }, { "action_query_batch_std": 19.297700881958008, "action_query_norm": 838.3241394042968, "action_relation_loss": 0.004105700249783695, "auxiliary_loss_weight": 1.0, "epoch": 10.608044901777362, "flow_matching_loss": 0.03633369002491236, "grad_norm": 0.11369390785694122, "invalid_tail_samples": 23.3, "learning_rate": 7.336482364789277e-05, "loss": 0.0404, "positive_teacher_pairs": 26961.9, "relation_loss": 0.004105700249783695, "selected_pairs": 26961.9, "step": 11340, "student_distance_mean": 1102.7707153320312, "teacher_distance_mean": 0.856107485294342, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.004105700249783695, "weighted_relation_loss": 0.004105700249783695 }, { "action_query_batch_std": 19.316979598999023, "action_query_norm": 838.9129028320312, "action_relation_loss": 0.004016003478318453, "auxiliary_loss_weight": 1.0, "epoch": 10.617399438727784, "flow_matching_loss": 0.0369698878377676, "grad_norm": 0.11907815933227539, "invalid_tail_samples": 25.6, "learning_rate": 7.331608166971082e-05, "loss": 0.041, "positive_teacher_pairs": 26433.9, "relation_loss": 0.004016003478318453, "selected_pairs": 26433.9, "step": 11350, "student_distance_mean": 1103.7412109375, "teacher_distance_mean": 0.8584909200668335, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.004016003478318453, "weighted_relation_loss": 0.004016003478318453 }, { "action_query_batch_std": 19.07782115936279, "action_query_norm": 828.7983459472656, "action_relation_loss": 0.003883725870400667, "auxiliary_loss_weight": 1.0, "epoch": 10.626753975678204, "flow_matching_loss": 0.03626667894423008, "grad_norm": 0.12245266884565353, "invalid_tail_samples": 24.3, "learning_rate": 7.326731136029108e-05, "loss": 0.0402, "positive_teacher_pairs": 26737.2, "relation_loss": 0.003883725870400667, "selected_pairs": 26737.2, "step": 11360, "student_distance_mean": 1088.3731201171875, "teacher_distance_mean": 0.8467535376548767, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.003883725870400667, "weighted_relation_loss": 0.003883725870400667 }, { "action_query_batch_std": 19.20805435180664, "action_query_norm": 835.0614440917968, "action_relation_loss": 0.003991531836800277, "auxiliary_loss_weight": 1.0, "epoch": 10.636108512628624, "flow_matching_loss": 0.03719780966639519, "grad_norm": 0.157253235578537, "invalid_tail_samples": 24.1, "learning_rate": 7.321851277889408e-05, "loss": 0.0412, "positive_teacher_pairs": 26780.4, "relation_loss": 0.003991531836800277, "selected_pairs": 26780.4, "step": 11370, "student_distance_mean": 1094.4283813476563, "teacher_distance_mean": 0.85236074924469, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.003991531836800277, "weighted_relation_loss": 0.003991531836800277 }, { "action_query_batch_std": 19.42613124847412, "action_query_norm": 843.3012756347656, "action_relation_loss": 0.004092916124500334, "auxiliary_loss_weight": 1.0, "epoch": 10.645463049579046, "flow_matching_loss": 0.03909054081887007, "grad_norm": 0.13777318596839905, "invalid_tail_samples": 23.5, "learning_rate": 7.316968598481469e-05, "loss": 0.0432, "positive_teacher_pairs": 26923.5, "relation_loss": 0.004092916124500334, "selected_pairs": 26923.5, "step": 11380, "student_distance_mean": 1103.0126586914062, "teacher_distance_mean": 0.8464615225791932, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.004092916124500334, "weighted_relation_loss": 0.004092916124500334 }, { "action_query_batch_std": 19.561991882324218, "action_query_norm": 847.1665100097656, "action_relation_loss": 0.003909453051164746, "auxiliary_loss_weight": 1.0, "epoch": 10.654817586529466, "flow_matching_loss": 0.03762239124625921, "grad_norm": 0.1131981760263443, "invalid_tail_samples": 23.3, "learning_rate": 7.312083103738206e-05, "loss": 0.0415, "positive_teacher_pairs": 26967.1, "relation_loss": 0.003909453051164746, "selected_pairs": 26967.1, "step": 11390, "student_distance_mean": 1111.137158203125, "teacher_distance_mean": 0.8588544011116028, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.003909453051164746, "weighted_relation_loss": 0.003909453051164746 }, { "action_query_batch_std": 19.697871971130372, "action_query_norm": 854.9812866210938, "action_relation_loss": 0.004102834174409509, "auxiliary_loss_weight": 1.0, "epoch": 10.664172123479888, "flow_matching_loss": 0.04003284052014351, "grad_norm": 0.1433536559343338, "invalid_tail_samples": 25.4, "learning_rate": 7.307194799595958e-05, "loss": 0.0441, "positive_teacher_pairs": 26484.3, "relation_loss": 0.004102834174409509, "selected_pairs": 26484.3, "step": 11400, "student_distance_mean": 1119.8616577148437, "teacher_distance_mean": 0.8608473777770996, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.004102834174409509, "weighted_relation_loss": 0.004102834174409509 }, { "action_query_batch_std": 19.871798515319824, "action_query_norm": 862.9173400878906, "action_relation_loss": 0.0038307390175759794, "auxiliary_loss_weight": 1.0, "epoch": 10.673526660430309, "flow_matching_loss": 0.03611330296844244, "grad_norm": 0.1545165628194809, "invalid_tail_samples": 25.3, "learning_rate": 7.302303691994473e-05, "loss": 0.0399, "positive_teacher_pairs": 26506.0, "relation_loss": 0.0038307390175759794, "selected_pairs": 26506.0, "step": 11410, "student_distance_mean": 1130.4666259765625, "teacher_distance_mean": 0.8692938268184662, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0038307390175759794, "weighted_relation_loss": 0.0038307390175759794 }, { "action_query_batch_std": 19.52755069732666, "action_query_norm": 853.1347045898438, "action_relation_loss": 0.0037433915073052048, "auxiliary_loss_weight": 1.0, "epoch": 10.68288119738073, "flow_matching_loss": 0.03712515123188496, "grad_norm": 0.1283685266971588, "invalid_tail_samples": 25.6, "learning_rate": 7.29740978687691e-05, "loss": 0.0409, "positive_teacher_pairs": 26430.6, "relation_loss": 0.0037433915073052048, "selected_pairs": 26430.6, "step": 11420, "student_distance_mean": 1117.0512329101562, "teacher_distance_mean": 0.8578297555446625, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.0037433915073052048, "weighted_relation_loss": 0.0037433915073052048 }, { "action_query_batch_std": 19.543587684631348, "action_query_norm": 853.2412780761719, "action_relation_loss": 0.004139137966558337, "auxiliary_loss_weight": 1.0, "epoch": 10.69223573433115, "flow_matching_loss": 0.03574118092656135, "grad_norm": 0.15698963403701782, "invalid_tail_samples": 24.6, "learning_rate": 7.292513090189825e-05, "loss": 0.0399, "positive_teacher_pairs": 26664.2, "relation_loss": 0.004139137966558337, "selected_pairs": 26664.2, "step": 11430, "student_distance_mean": 1110.3296997070313, "teacher_distance_mean": 0.8540283203125, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.004139137966558337, "weighted_relation_loss": 0.004139137966558337 }, { "action_query_batch_std": 19.503013610839844, "action_query_norm": 849.7801391601563, "action_relation_loss": 0.003992592240683735, "auxiliary_loss_weight": 1.0, "epoch": 10.701590271281571, "flow_matching_loss": 0.0380033303052187, "grad_norm": 0.12204130738973618, "invalid_tail_samples": 22.9, "learning_rate": 7.287613607883163e-05, "loss": 0.042, "positive_teacher_pairs": 27060.1, "relation_loss": 0.003992592240683735, "selected_pairs": 27060.1, "step": 11440, "student_distance_mean": 1109.1749633789063, "teacher_distance_mean": 0.8544480800628662, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.003992592240683735, "weighted_relation_loss": 0.003992592240683735 }, { "action_query_batch_std": 19.639913177490236, "action_query_norm": 856.0725891113282, "action_relation_loss": 0.0037056429544463755, "auxiliary_loss_weight": 1.0, "epoch": 10.710944808231993, "flow_matching_loss": 0.03498195037245751, "grad_norm": 0.10554630309343338, "invalid_tail_samples": 21.4, "learning_rate": 7.282711345910263e-05, "loss": 0.0387, "positive_teacher_pairs": 27407.9, "relation_loss": 0.0037056429544463755, "selected_pairs": 27407.9, "step": 11450, "student_distance_mean": 1115.1096069335938, "teacher_distance_mean": 0.8588090658187866, "valid_action_samples": 234.6, "weighted_auxiliary_loss": 0.0037056429544463755, "weighted_relation_loss": 0.0037056429544463755 }, { "action_query_batch_std": 19.361509132385255, "action_query_norm": 848.0050903320313, "action_relation_loss": 0.003780751721933484, "auxiliary_loss_weight": 1.0, "epoch": 10.720299345182413, "flow_matching_loss": 0.0356895737349987, "grad_norm": 0.11516878008842468, "invalid_tail_samples": 23.1, "learning_rate": 7.27780631022783e-05, "loss": 0.0395, "positive_teacher_pairs": 27029.1, "relation_loss": 0.003780751721933484, "selected_pairs": 27029.1, "step": 11460, "student_distance_mean": 1105.2053955078125, "teacher_distance_mean": 0.852228581905365, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.003780751721933484, "weighted_relation_loss": 0.003780751721933484 }, { "action_query_batch_std": 19.276550483703613, "action_query_norm": 840.0482666015625, "action_relation_loss": 0.0038331308169290423, "auxiliary_loss_weight": 1.0, "epoch": 10.729653882132835, "flow_matching_loss": 0.03437098413705826, "grad_norm": 0.10624510049819946, "invalid_tail_samples": 24.1, "learning_rate": 7.272898506795948e-05, "loss": 0.0382, "positive_teacher_pairs": 26784.8, "relation_loss": 0.0038331308169290423, "selected_pairs": 26784.8, "step": 11470, "student_distance_mean": 1092.5153564453126, "teacher_distance_mean": 0.8464912354946137, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0038331308169290423, "weighted_relation_loss": 0.0038331308169290423 }, { "action_query_batch_std": 19.38994770050049, "action_query_norm": 839.8337707519531, "action_relation_loss": 0.00377696615178138, "auxiliary_loss_weight": 1.0, "epoch": 10.739008419083255, "flow_matching_loss": 0.03540000319480896, "grad_norm": 0.12856407463550568, "invalid_tail_samples": 24.6, "learning_rate": 7.267987941578058e-05, "loss": 0.0392, "positive_teacher_pairs": 26668.7, "relation_loss": 0.00377696615178138, "selected_pairs": 26668.7, "step": 11480, "student_distance_mean": 1102.0879638671875, "teacher_distance_mean": 0.8543910682201385, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.00377696615178138, "weighted_relation_loss": 0.00377696615178138 }, { "action_query_batch_std": 19.51176815032959, "action_query_norm": 847.5002319335938, "action_relation_loss": 0.0037242350401356815, "auxiliary_loss_weight": 1.0, "epoch": 10.748362956033676, "flow_matching_loss": 0.03761816397309303, "grad_norm": 0.14057587087154388, "invalid_tail_samples": 22.2, "learning_rate": 7.263074620540962e-05, "loss": 0.0413, "positive_teacher_pairs": 27226.3, "relation_loss": 0.0037242350401356815, "selected_pairs": 27226.3, "step": 11490, "student_distance_mean": 1110.6056640625, "teacher_distance_mean": 0.8648564755916596, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.0037242350401356815, "weighted_relation_loss": 0.0037242350401356815 }, { "action_query_batch_std": 19.463156318664552, "action_query_norm": 848.363037109375, "action_relation_loss": 0.0037944611394777894, "auxiliary_loss_weight": 1.0, "epoch": 10.757717492984098, "flow_matching_loss": 0.035327093489468095, "grad_norm": 0.1409652829170227, "invalid_tail_samples": 24.3, "learning_rate": 7.25815854965481e-05, "loss": 0.0391, "positive_teacher_pairs": 26736.3, "relation_loss": 0.0037944611394777894, "selected_pairs": 26736.3, "step": 11500, "student_distance_mean": 1106.3063842773438, "teacher_distance_mean": 0.8544734239578247, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0037944611394777894, "weighted_relation_loss": 0.0037944611394777894 }, { "action_query_batch_std": 19.110064125061037, "action_query_norm": 831.5328308105469, "action_relation_loss": 0.00379356206394732, "auxiliary_loss_weight": 1.0, "epoch": 10.767072029934518, "flow_matching_loss": 0.03638815097510815, "grad_norm": 0.11128930002450943, "invalid_tail_samples": 23.9, "learning_rate": 7.253239734893089e-05, "loss": 0.0402, "positive_teacher_pairs": 26833.8, "relation_loss": 0.00379356206394732, "selected_pairs": 26833.8, "step": 11510, "student_distance_mean": 1089.5796264648438, "teacher_distance_mean": 0.847986352443695, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.00379356206394732, "weighted_relation_loss": 0.00379356206394732 }, { "action_query_batch_std": 19.307451248168945, "action_query_norm": 835.3761047363281, "action_relation_loss": 0.0038395049050450325, "auxiliary_loss_weight": 1.0, "epoch": 10.77642656688494, "flow_matching_loss": 0.03618000689893961, "grad_norm": 0.11472123116254807, "invalid_tail_samples": 25.6, "learning_rate": 7.248318182232623e-05, "loss": 0.04, "positive_teacher_pairs": 26438.2, "relation_loss": 0.0038395049050450325, "selected_pairs": 26438.2, "step": 11520, "student_distance_mean": 1101.4351928710937, "teacher_distance_mean": 0.859623658657074, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.0038395049050450325, "weighted_relation_loss": 0.0038395049050450325 }, { "action_query_batch_std": 19.689790725708008, "action_query_norm": 848.45771484375, "action_relation_loss": 0.0038261823588982224, "auxiliary_loss_weight": 1.0, "epoch": 10.78578110383536, "flow_matching_loss": 0.03655136898159981, "grad_norm": 0.11982350796461105, "invalid_tail_samples": 23.7, "learning_rate": 7.243393897653565e-05, "loss": 0.0404, "positive_teacher_pairs": 26876.3, "relation_loss": 0.0038261823588982224, "selected_pairs": 26876.3, "step": 11530, "student_distance_mean": 1121.5713012695312, "teacher_distance_mean": 0.8685523629188537, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0038261823588982224, "weighted_relation_loss": 0.0038261823588982224 }, { "action_query_batch_std": 19.29053077697754, "action_query_norm": 841.4106384277344, "action_relation_loss": 0.0037340982584282757, "auxiliary_loss_weight": 1.0, "epoch": 10.795135640785782, "flow_matching_loss": 0.03528566751629114, "grad_norm": 0.129978746175766, "invalid_tail_samples": 21.1, "learning_rate": 7.23846688713938e-05, "loss": 0.039, "positive_teacher_pairs": 27482.0, "relation_loss": 0.0037340982584282757, "selected_pairs": 27482.0, "step": 11540, "student_distance_mean": 1099.7869262695312, "teacher_distance_mean": 0.8504108428955078, "valid_action_samples": 234.9, "weighted_auxiliary_loss": 0.0037340982584282757, "weighted_relation_loss": 0.0037340982584282757 }, { "action_query_batch_std": 19.340106391906737, "action_query_norm": 839.1128173828125, "action_relation_loss": 0.0038388516288250683, "auxiliary_loss_weight": 1.0, "epoch": 10.804490177736202, "flow_matching_loss": 0.037210127152502534, "grad_norm": 0.12704378366470337, "invalid_tail_samples": 22.4, "learning_rate": 7.233537156676854e-05, "loss": 0.041, "positive_teacher_pairs": 27172.1, "relation_loss": 0.0038388516288250683, "selected_pairs": 27172.1, "step": 11550, "student_distance_mean": 1094.7482177734375, "teacher_distance_mean": 0.850616317987442, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.0038388516288250683, "weighted_relation_loss": 0.0038388516288250683 }, { "action_query_batch_std": 19.276317024230956, "action_query_norm": 841.6325927734375, "action_relation_loss": 0.0037919589085504413, "auxiliary_loss_weight": 1.0, "epoch": 10.813844714686622, "flow_matching_loss": 0.035180975683033466, "grad_norm": 0.1312384009361267, "invalid_tail_samples": 25.7, "learning_rate": 7.228604712256076e-05, "loss": 0.039, "positive_teacher_pairs": 26418.3, "relation_loss": 0.0037919589085504413, "selected_pairs": 26418.3, "step": 11560, "student_distance_mean": 1102.06083984375, "teacher_distance_mean": 0.8511880815029145, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.0037919589085504413, "weighted_relation_loss": 0.0037919589085504413 }, { "action_query_batch_std": 19.71336212158203, "action_query_norm": 853.9697021484375, "action_relation_loss": 0.003857797523960471, "auxiliary_loss_weight": 1.0, "epoch": 10.823199251637044, "flow_matching_loss": 0.035933489352464675, "grad_norm": 0.11955904215574265, "invalid_tail_samples": 23.6, "learning_rate": 7.223669559870426e-05, "loss": 0.0398, "positive_teacher_pairs": 26900.5, "relation_loss": 0.003857797523960471, "selected_pairs": 26900.5, "step": 11570, "student_distance_mean": 1117.4993408203125, "teacher_distance_mean": 0.8606429159641266, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.003857797523960471, "weighted_relation_loss": 0.003857797523960471 }, { "action_query_batch_std": 19.631724739074706, "action_query_norm": 851.3000610351562, "action_relation_loss": 0.004043110786005855, "auxiliary_loss_weight": 1.0, "epoch": 10.832553788587465, "flow_matching_loss": 0.03656311817467213, "grad_norm": 0.1282818466424942, "invalid_tail_samples": 24.3, "learning_rate": 7.218731705516585e-05, "loss": 0.0406, "positive_teacher_pairs": 26733.7, "relation_loss": 0.004043110786005855, "selected_pairs": 26733.7, "step": 11580, "student_distance_mean": 1116.9013305664062, "teacher_distance_mean": 0.8507877707481384, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.004043110786005855, "weighted_relation_loss": 0.004043110786005855 }, { "action_query_batch_std": 19.687729835510254, "action_query_norm": 851.6370056152343, "action_relation_loss": 0.0038970807334408166, "auxiliary_loss_weight": 1.0, "epoch": 10.841908325537887, "flow_matching_loss": 0.03759505338966847, "grad_norm": 0.14792373776435852, "invalid_tail_samples": 23.2, "learning_rate": 7.21379115519451e-05, "loss": 0.0415, "positive_teacher_pairs": 26987.5, "relation_loss": 0.0038970807334408166, "selected_pairs": 26987.5, "step": 11590, "student_distance_mean": 1123.0904418945313, "teacher_distance_mean": 0.861273729801178, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0038970807334408166, "weighted_relation_loss": 0.0038970807334408166 }, { "action_query_batch_std": 19.717101287841796, "action_query_norm": 858.0677734375, "action_relation_loss": 0.003846771060489118, "auxiliary_loss_weight": 1.0, "epoch": 10.851262862488307, "flow_matching_loss": 0.036873335391283034, "grad_norm": 0.12029203772544861, "invalid_tail_samples": 21.9, "learning_rate": 7.20884791490743e-05, "loss": 0.0407, "positive_teacher_pairs": 27298.1, "relation_loss": 0.003846771060489118, "selected_pairs": 27298.1, "step": 11600, "student_distance_mean": 1126.8802856445313, "teacher_distance_mean": 0.8628146529197693, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.003846771060489118, "weighted_relation_loss": 0.003846771060489118 }, { "action_query_batch_std": 19.46003875732422, "action_query_norm": 845.719970703125, "action_relation_loss": 0.0038103334605693816, "auxiliary_loss_weight": 1.0, "epoch": 10.860617399438727, "flow_matching_loss": 0.036234207451343536, "grad_norm": 0.13767021894454956, "invalid_tail_samples": 23.6, "learning_rate": 7.203901990661857e-05, "loss": 0.04, "positive_teacher_pairs": 26891.0, "relation_loss": 0.0038103334605693816, "selected_pairs": 26891.0, "step": 11610, "student_distance_mean": 1107.937451171875, "teacher_distance_mean": 0.8529490411281586, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0038103334605693816, "weighted_relation_loss": 0.0038103334605693816 }, { "action_query_batch_std": 19.7511625289917, "action_query_norm": 859.9358825683594, "action_relation_loss": 0.0037969858851283787, "auxiliary_loss_weight": 1.0, "epoch": 10.869971936389149, "flow_matching_loss": 0.03608067817986012, "grad_norm": 0.15362921357154846, "invalid_tail_samples": 24.3, "learning_rate": 7.198953388467549e-05, "loss": 0.0399, "positive_teacher_pairs": 26734.3, "relation_loss": 0.0037969858851283787, "selected_pairs": 26734.3, "step": 11620, "student_distance_mean": 1128.1068359375, "teacher_distance_mean": 0.8574946641921997, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0037969858851283787, "weighted_relation_loss": 0.0037969858851283787 }, { "action_query_batch_std": 19.8979585647583, "action_query_norm": 864.4207336425782, "action_relation_loss": 0.0037370648235082625, "auxiliary_loss_weight": 1.0, "epoch": 10.87932647333957, "flow_matching_loss": 0.03815765958279371, "grad_norm": 0.1728043258190155, "invalid_tail_samples": 23.1, "learning_rate": 7.194002114337526e-05, "loss": 0.0419, "positive_teacher_pairs": 27008.5, "relation_loss": 0.0037370648235082625, "selected_pairs": 27008.5, "step": 11630, "student_distance_mean": 1130.9711059570313, "teacher_distance_mean": 0.8608181118965149, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0037370648235082625, "weighted_relation_loss": 0.0037370648235082625 }, { "action_query_batch_std": 19.81254653930664, "action_query_norm": 861.3105712890625, "action_relation_loss": 0.0039005572441965343, "auxiliary_loss_weight": 1.0, "epoch": 10.888681010289991, "flow_matching_loss": 0.03624099940061569, "grad_norm": 0.1408362090587616, "invalid_tail_samples": 23.8, "learning_rate": 7.189048174288054e-05, "loss": 0.0401, "positive_teacher_pairs": 26854.2, "relation_loss": 0.0039005572441965343, "selected_pairs": 26854.2, "step": 11640, "student_distance_mean": 1124.8836669921875, "teacher_distance_mean": 0.8548666894435882, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0039005572441965343, "weighted_relation_loss": 0.0039005572441965343 }, { "action_query_batch_std": 19.65681610107422, "action_query_norm": 853.7799682617188, "action_relation_loss": 0.004018241632729768, "auxiliary_loss_weight": 1.0, "epoch": 10.898035547240411, "flow_matching_loss": 0.03693097550421953, "grad_norm": 0.09344074875116348, "invalid_tail_samples": 26.2, "learning_rate": 7.184091574338636e-05, "loss": 0.0409, "positive_teacher_pairs": 26297.4, "relation_loss": 0.004018241632729768, "selected_pairs": 26297.4, "step": 11650, "student_distance_mean": 1118.9951782226562, "teacher_distance_mean": 0.8543736100196838, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.004018241632729768, "weighted_relation_loss": 0.004018241632729768 }, { "action_query_batch_std": 19.806415176391603, "action_query_norm": 862.1517272949219, "action_relation_loss": 0.0038554339669644834, "auxiliary_loss_weight": 1.0, "epoch": 10.907390084190833, "flow_matching_loss": 0.03524879012256861, "grad_norm": 0.12173207104206085, "invalid_tail_samples": 24.9, "learning_rate": 7.179132320512009e-05, "loss": 0.0391, "positive_teacher_pairs": 26598.3, "relation_loss": 0.0038554339669644834, "selected_pairs": 26598.3, "step": 11660, "student_distance_mean": 1131.1044189453125, "teacher_distance_mean": 0.8550334513187409, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0038554339669644834, "weighted_relation_loss": 0.0038554339669644834 }, { "action_query_batch_std": 19.62492980957031, "action_query_norm": 853.1140014648438, "action_relation_loss": 0.0037782532395794987, "auxiliary_loss_weight": 1.0, "epoch": 10.916744621141254, "flow_matching_loss": 0.0355731263756752, "grad_norm": 0.1070445254445076, "invalid_tail_samples": 21.8, "learning_rate": 7.174170418834134e-05, "loss": 0.0394, "positive_teacher_pairs": 27315.0, "relation_loss": 0.0037782532395794987, "selected_pairs": 27315.0, "step": 11670, "student_distance_mean": 1116.5978149414063, "teacher_distance_mean": 0.8480920016765594, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.0037782532395794987, "weighted_relation_loss": 0.0037782532395794987 }, { "action_query_batch_std": 19.593391609191894, "action_query_norm": 852.0345092773438, "action_relation_loss": 0.0037589608458802105, "auxiliary_loss_weight": 1.0, "epoch": 10.926099158091674, "flow_matching_loss": 0.036557359620928764, "grad_norm": 0.12938062846660614, "invalid_tail_samples": 21.5, "learning_rate": 7.169205875334189e-05, "loss": 0.0403, "positive_teacher_pairs": 27383.0, "relation_loss": 0.0037589608458802105, "selected_pairs": 27383.0, "step": 11680, "student_distance_mean": 1112.1161254882813, "teacher_distance_mean": 0.8554121732711792, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.0037589608458802105, "weighted_relation_loss": 0.0037589608458802105 }, { "action_query_batch_std": 19.792960739135744, "action_query_norm": 859.3683227539062, "action_relation_loss": 0.003714718041010201, "auxiliary_loss_weight": 1.0, "epoch": 10.935453695042096, "flow_matching_loss": 0.03518305104225874, "grad_norm": 0.1342475712299347, "invalid_tail_samples": 23.0, "learning_rate": 7.164238696044562e-05, "loss": 0.0389, "positive_teacher_pairs": 27036.3, "relation_loss": 0.003714718041010201, "selected_pairs": 27036.3, "step": 11690, "student_distance_mean": 1123.5400390625, "teacher_distance_mean": 0.8590748608112335, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.003714718041010201, "weighted_relation_loss": 0.003714718041010201 }, { "action_query_batch_std": 19.55222969055176, "action_query_norm": 851.0132507324219, "action_relation_loss": 0.0037532663205638527, "auxiliary_loss_weight": 1.0, "epoch": 10.944808231992516, "flow_matching_loss": 0.03606428410857916, "grad_norm": 0.11957480758428574, "invalid_tail_samples": 26.0, "learning_rate": 7.159268887000846e-05, "loss": 0.0398, "positive_teacher_pairs": 26338.3, "relation_loss": 0.0037532663205638527, "selected_pairs": 26338.3, "step": 11700, "student_distance_mean": 1117.592431640625, "teacher_distance_mean": 0.8590348958969116, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.0037532663205638527, "weighted_relation_loss": 0.0037532663205638527 }, { "action_query_batch_std": 19.55639591217041, "action_query_norm": 850.4358337402343, "action_relation_loss": 0.003724332177080214, "auxiliary_loss_weight": 1.0, "epoch": 10.954162768942938, "flow_matching_loss": 0.036345669999718666, "grad_norm": 0.11881845444440842, "invalid_tail_samples": 21.9, "learning_rate": 7.154296454241827e-05, "loss": 0.0401, "positive_teacher_pairs": 27289.7, "relation_loss": 0.003724332177080214, "selected_pairs": 27289.7, "step": 11710, "student_distance_mean": 1114.5904907226563, "teacher_distance_mean": 0.8570830762386322, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.003724332177080214, "weighted_relation_loss": 0.003724332177080214 }, { "action_query_batch_std": 19.73123950958252, "action_query_norm": 855.2124450683593, "action_relation_loss": 0.0037638237699866295, "auxiliary_loss_weight": 1.0, "epoch": 10.963517305893358, "flow_matching_loss": 0.03492642566561699, "grad_norm": 0.15764442086219788, "invalid_tail_samples": 22.3, "learning_rate": 7.149321403809479e-05, "loss": 0.0387, "positive_teacher_pairs": 27196.9, "relation_loss": 0.0037638237699866295, "selected_pairs": 27196.9, "step": 11720, "student_distance_mean": 1116.5921875, "teacher_distance_mean": 0.8533395886421203, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0037638237699866295, "weighted_relation_loss": 0.0037638237699866295 }, { "action_query_batch_std": 19.70724697113037, "action_query_norm": 854.9068725585937, "action_relation_loss": 0.0036607994232326748, "auxiliary_loss_weight": 1.0, "epoch": 10.97287184284378, "flow_matching_loss": 0.03495635502040386, "grad_norm": 0.1278272122144699, "invalid_tail_samples": 22.7, "learning_rate": 7.144343741748956e-05, "loss": 0.0386, "positive_teacher_pairs": 27101.6, "relation_loss": 0.0036607994232326748, "selected_pairs": 27101.6, "step": 11730, "student_distance_mean": 1119.4504760742188, "teacher_distance_mean": 0.8548927664756775, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0036607994232326748, "weighted_relation_loss": 0.0036607994232326748 }, { "action_query_batch_std": 19.686514472961427, "action_query_norm": 853.7716979980469, "action_relation_loss": 0.0038045375840738416, "auxiliary_loss_weight": 1.0, "epoch": 10.9822263797942, "flow_matching_loss": 0.03681265376508236, "grad_norm": 0.10045099258422852, "invalid_tail_samples": 26.9, "learning_rate": 7.139363474108589e-05, "loss": 0.0406, "positive_teacher_pairs": 26139.4, "relation_loss": 0.0038045375840738416, "selected_pairs": 26139.4, "step": 11740, "student_distance_mean": 1121.1648559570312, "teacher_distance_mean": 0.8564966440200805, "valid_action_samples": 229.1, "weighted_auxiliary_loss": 0.0038045375840738416, "weighted_relation_loss": 0.0038045375840738416 }, { "action_query_batch_std": 19.82942008972168, "action_query_norm": 858.8892333984375, "action_relation_loss": 0.0037015702575445173, "auxiliary_loss_weight": 1.0, "epoch": 10.99158091674462, "flow_matching_loss": 0.03645938858389854, "grad_norm": 0.14397580921649933, "invalid_tail_samples": 24.5, "learning_rate": 7.134380606939874e-05, "loss": 0.0402, "positive_teacher_pairs": 26686.4, "relation_loss": 0.0037015702575445173, "selected_pairs": 26686.4, "step": 11750, "student_distance_mean": 1129.7499633789062, "teacher_distance_mean": 0.8528771162033081, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0037015702575445173, "weighted_relation_loss": 0.0037015702575445173 }, { "action_query_batch_std": 19.81777420043945, "action_query_norm": 860.5059875488281, "action_relation_loss": 0.0037240376695990562, "auxiliary_loss_weight": 1.0, "epoch": 11.000935453695043, "flow_matching_loss": 0.03636368121951818, "grad_norm": 0.11605534702539444, "invalid_tail_samples": 20.7, "learning_rate": 7.12939514629746e-05, "loss": 0.0401, "positive_teacher_pairs": 24618.5, "relation_loss": 0.0037240376695990562, "selected_pairs": 24618.5, "step": 11760, "student_distance_mean": 1129.1315673828126, "teacher_distance_mean": 0.85646271109581, "valid_action_samples": 215.4, "weighted_auxiliary_loss": 0.0037240376695990562, "weighted_relation_loss": 0.0037240376695990562 }, { "action_query_batch_std": 19.767845344543456, "action_query_norm": 855.8084655761719, "action_relation_loss": 0.003610332706011832, "auxiliary_loss_weight": 1.0, "epoch": 11.010289990645463, "flow_matching_loss": 0.03398111630231142, "grad_norm": 0.12884622812271118, "invalid_tail_samples": 25.0, "learning_rate": 7.124407098239155e-05, "loss": 0.0376, "positive_teacher_pairs": 26585.4, "relation_loss": 0.003610332706011832, "selected_pairs": 26585.4, "step": 11770, "student_distance_mean": 1126.2927490234374, "teacher_distance_mean": 0.8616881668567657, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.003610332706011832, "weighted_relation_loss": 0.003610332706011832 }, { "action_query_batch_std": 19.88124485015869, "action_query_norm": 859.9773620605469, "action_relation_loss": 0.0035667955642566087, "auxiliary_loss_weight": 1.0, "epoch": 11.019644527595885, "flow_matching_loss": 0.035582567751407626, "grad_norm": 0.13445281982421875, "invalid_tail_samples": 25.4, "learning_rate": 7.119416468825908e-05, "loss": 0.0391, "positive_teacher_pairs": 26483.4, "relation_loss": 0.0035667955642566087, "selected_pairs": 26483.4, "step": 11780, "student_distance_mean": 1131.7010986328125, "teacher_distance_mean": 0.8644467175006867, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.0035667955642566087, "weighted_relation_loss": 0.0035667955642566087 }, { "action_query_batch_std": 19.763314628601073, "action_query_norm": 855.6572143554688, "action_relation_loss": 0.0036715045804157852, "auxiliary_loss_weight": 1.0, "epoch": 11.028999064546305, "flow_matching_loss": 0.036234800890088084, "grad_norm": 0.14688582718372345, "invalid_tail_samples": 25.6, "learning_rate": 7.114423264121804e-05, "loss": 0.0399, "positive_teacher_pairs": 26434.3, "relation_loss": 0.0036715045804157852, "selected_pairs": 26434.3, "step": 11790, "student_distance_mean": 1123.4896118164063, "teacher_distance_mean": 0.861061441898346, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.0036715045804157852, "weighted_relation_loss": 0.0036715045804157852 }, { "action_query_batch_std": 19.73280143737793, "action_query_norm": 855.8898010253906, "action_relation_loss": 0.0035697907209396363, "auxiliary_loss_weight": 1.0, "epoch": 11.038353601496725, "flow_matching_loss": 0.035000672563910484, "grad_norm": 0.1192050501704216, "invalid_tail_samples": 23.3, "learning_rate": 7.109427490194056e-05, "loss": 0.0386, "positive_teacher_pairs": 26965.4, "relation_loss": 0.0035697907209396363, "selected_pairs": 26965.4, "step": 11800, "student_distance_mean": 1123.5484497070313, "teacher_distance_mean": 0.8571049630641937, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0035697907209396363, "weighted_relation_loss": 0.0035697907209396363 }, { "action_query_batch_std": 19.42987995147705, "action_query_norm": 844.5158630371094, "action_relation_loss": 0.00378721309825778, "auxiliary_loss_weight": 1.0, "epoch": 11.047708138447147, "flow_matching_loss": 0.03640870675444603, "grad_norm": 0.16940143704414368, "invalid_tail_samples": 23.1, "learning_rate": 7.104429153113001e-05, "loss": 0.0402, "positive_teacher_pairs": 27017.2, "relation_loss": 0.00378721309825778, "selected_pairs": 27017.2, "step": 11810, "student_distance_mean": 1110.5689208984375, "teacher_distance_mean": 0.8491233348846435, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.00378721309825778, "weighted_relation_loss": 0.00378721309825778 }, { "action_query_batch_std": 19.4922513961792, "action_query_norm": 843.4495910644531, "action_relation_loss": 0.003581372299231589, "auxiliary_loss_weight": 1.0, "epoch": 11.057062675397567, "flow_matching_loss": 0.03549900781363249, "grad_norm": 0.12506799399852753, "invalid_tail_samples": 25.6, "learning_rate": 7.099428258952092e-05, "loss": 0.0391, "positive_teacher_pairs": 26448.5, "relation_loss": 0.003581372299231589, "selected_pairs": 26448.5, "step": 11820, "student_distance_mean": 1107.9878540039062, "teacher_distance_mean": 0.8499236583709717, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.003581372299231589, "weighted_relation_loss": 0.003581372299231589 }, { "action_query_batch_std": 19.75840892791748, "action_query_norm": 861.7632995605469, "action_relation_loss": 0.0037208055611699818, "auxiliary_loss_weight": 1.0, "epoch": 11.06641721234799, "flow_matching_loss": 0.03511256277561188, "grad_norm": 0.09861738979816437, "invalid_tail_samples": 21.8, "learning_rate": 7.094424813787883e-05, "loss": 0.0388, "positive_teacher_pairs": 27315.3, "relation_loss": 0.0037208055611699818, "selected_pairs": 27315.3, "step": 11830, "student_distance_mean": 1129.4525390625, "teacher_distance_mean": 0.8595586359500885, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.0037208055611699818, "weighted_relation_loss": 0.0037208055611699818 }, { "action_query_batch_std": 19.63794078826904, "action_query_norm": 854.4648498535156, "action_relation_loss": 0.0036799363093450665, "auxiliary_loss_weight": 1.0, "epoch": 11.07577174929841, "flow_matching_loss": 0.034283690713346006, "grad_norm": 0.11109622567892075, "invalid_tail_samples": 22.7, "learning_rate": 7.089418823700034e-05, "loss": 0.038, "positive_teacher_pairs": 27105.6, "relation_loss": 0.0036799363093450665, "selected_pairs": 27105.6, "step": 11840, "student_distance_mean": 1118.78505859375, "teacher_distance_mean": 0.8474994778633118, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0036799363093450665, "weighted_relation_loss": 0.0036799363093450665 }, { "action_query_batch_std": 19.543481063842773, "action_query_norm": 851.7373107910156, "action_relation_loss": 0.003616274055093527, "auxiliary_loss_weight": 1.0, "epoch": 11.085126286248832, "flow_matching_loss": 0.035198676958680154, "grad_norm": 0.11984161287546158, "invalid_tail_samples": 23.9, "learning_rate": 7.084410294771298e-05, "loss": 0.0388, "positive_teacher_pairs": 26826.0, "relation_loss": 0.003616274055093527, "selected_pairs": 26826.0, "step": 11850, "student_distance_mean": 1109.0802734375, "teacher_distance_mean": 0.8460217475891113, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.003616274055093527, "weighted_relation_loss": 0.003616274055093527 }, { "action_query_batch_std": 19.771706199645998, "action_query_norm": 859.1733703613281, "action_relation_loss": 0.0034811091842129826, "auxiliary_loss_weight": 1.0, "epoch": 11.094480823199252, "flow_matching_loss": 0.03437381237745285, "grad_norm": 0.1251143217086792, "invalid_tail_samples": 23.0, "learning_rate": 7.079399233087504e-05, "loss": 0.0379, "positive_teacher_pairs": 27038.3, "relation_loss": 0.0034811091842129826, "selected_pairs": 27038.3, "step": 11860, "student_distance_mean": 1130.9353271484374, "teacher_distance_mean": 0.8613465607166291, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0034811091842129826, "weighted_relation_loss": 0.0034811091842129826 }, { "action_query_batch_std": 19.9220703125, "action_query_norm": 861.3292419433594, "action_relation_loss": 0.003655771212652326, "auxiliary_loss_weight": 1.0, "epoch": 11.103835360149672, "flow_matching_loss": 0.0342944948002696, "grad_norm": 0.11048227548599243, "invalid_tail_samples": 23.3, "learning_rate": 7.074385644737568e-05, "loss": 0.038, "positive_teacher_pairs": 26963.6, "relation_loss": 0.003655771212652326, "selected_pairs": 26963.6, "step": 11870, "student_distance_mean": 1130.9511352539062, "teacher_distance_mean": 0.8582494497299195, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.003655771212652326, "weighted_relation_loss": 0.003655771212652326 }, { "action_query_batch_std": 19.79836483001709, "action_query_norm": 859.3048828125, "action_relation_loss": 0.003645861172117293, "auxiliary_loss_weight": 1.0, "epoch": 11.113189897100094, "flow_matching_loss": 0.03441818449646235, "grad_norm": 0.12573978304862976, "invalid_tail_samples": 20.0, "learning_rate": 7.069369535813473e-05, "loss": 0.0381, "positive_teacher_pairs": 27737.2, "relation_loss": 0.003645861172117293, "selected_pairs": 27737.2, "step": 11880, "student_distance_mean": 1124.2916625976563, "teacher_distance_mean": 0.8514590561389923, "valid_action_samples": 236.0, "weighted_auxiliary_loss": 0.003645861172117293, "weighted_relation_loss": 0.003645861172117293 }, { "action_query_batch_std": 19.79935073852539, "action_query_norm": 861.469970703125, "action_relation_loss": 0.003601968172006309, "auxiliary_loss_weight": 1.0, "epoch": 11.122544434050514, "flow_matching_loss": 0.03544125277549028, "grad_norm": 0.11341440677642822, "invalid_tail_samples": 24.8, "learning_rate": 7.06435091241026e-05, "loss": 0.039, "positive_teacher_pairs": 26622.0, "relation_loss": 0.003601968172006309, "selected_pairs": 26622.0, "step": 11890, "student_distance_mean": 1131.7326293945312, "teacher_distance_mean": 0.8585293114185333, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.003601968172006309, "weighted_relation_loss": 0.003601968172006309 }, { "action_query_batch_std": 19.828904914855958, "action_query_norm": 857.3643432617188, "action_relation_loss": 0.00368270946200937, "auxiliary_loss_weight": 1.0, "epoch": 11.131898971000936, "flow_matching_loss": 0.03537270650267601, "grad_norm": 0.11375849694013596, "invalid_tail_samples": 25.6, "learning_rate": 7.059329780626034e-05, "loss": 0.0391, "positive_teacher_pairs": 26446.0, "relation_loss": 0.00368270946200937, "selected_pairs": 26446.0, "step": 11900, "student_distance_mean": 1128.7322998046875, "teacher_distance_mean": 0.8582212150096893, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.00368270946200937, "weighted_relation_loss": 0.00368270946200937 }, { "action_query_batch_std": 19.87529048919678, "action_query_norm": 862.9699401855469, "action_relation_loss": 0.0035108813550323247, "auxiliary_loss_weight": 1.0, "epoch": 11.141253507951356, "flow_matching_loss": 0.03542059902101755, "grad_norm": 0.13408416509628296, "invalid_tail_samples": 26.6, "learning_rate": 7.054306146561944e-05, "loss": 0.0389, "positive_teacher_pairs": 26214.8, "relation_loss": 0.0035108813550323247, "selected_pairs": 26214.8, "step": 11910, "student_distance_mean": 1136.7570190429688, "teacher_distance_mean": 0.8596799552440644, "valid_action_samples": 229.4, "weighted_auxiliary_loss": 0.0035108813550323247, "weighted_relation_loss": 0.0035108813550323247 }, { "action_query_batch_std": 20.103442192077637, "action_query_norm": 868.5166687011719, "action_relation_loss": 0.0035380500834435225, "auxiliary_loss_weight": 1.0, "epoch": 11.150608044901777, "flow_matching_loss": 0.037301385030150416, "grad_norm": 0.13772572576999664, "invalid_tail_samples": 24.2, "learning_rate": 7.049280016322178e-05, "loss": 0.0408, "positive_teacher_pairs": 26755.9, "relation_loss": 0.0035380500834435225, "selected_pairs": 26755.9, "step": 11920, "student_distance_mean": 1139.2760131835937, "teacher_distance_mean": 0.864751011133194, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0035380500834435225, "weighted_relation_loss": 0.0035380500834435225 }, { "action_query_batch_std": 19.84789924621582, "action_query_norm": 861.8515991210937, "action_relation_loss": 0.003640122013166547, "auxiliary_loss_weight": 1.0, "epoch": 11.159962581852199, "flow_matching_loss": 0.033499093540012834, "grad_norm": 0.11164628714323044, "invalid_tail_samples": 23.1, "learning_rate": 7.044251396013957e-05, "loss": 0.0371, "positive_teacher_pairs": 27012.8, "relation_loss": 0.003640122013166547, "selected_pairs": 27012.8, "step": 11930, "student_distance_mean": 1131.07646484375, "teacher_distance_mean": 0.8578653573989868, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.003640122013166547, "weighted_relation_loss": 0.003640122013166547 }, { "action_query_batch_std": 20.013276290893554, "action_query_norm": 864.4673767089844, "action_relation_loss": 0.0037116102408617734, "auxiliary_loss_weight": 1.0, "epoch": 11.169317118802619, "flow_matching_loss": 0.03424791265279055, "grad_norm": 0.09240659326314926, "invalid_tail_samples": 24.0, "learning_rate": 7.039220291747528e-05, "loss": 0.038, "positive_teacher_pairs": 26807.0, "relation_loss": 0.0037116102408617734, "selected_pairs": 26807.0, "step": 11940, "student_distance_mean": 1138.025927734375, "teacher_distance_mean": 0.8619182348251343, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0037116102408617734, "weighted_relation_loss": 0.0037116102408617734 }, { "action_query_batch_std": 19.683060264587404, "action_query_norm": 857.1409362792969, "action_relation_loss": 0.003662287723273039, "auxiliary_loss_weight": 1.0, "epoch": 11.17867165575304, "flow_matching_loss": 0.03490371704101562, "grad_norm": 0.13002678751945496, "invalid_tail_samples": 26.9, "learning_rate": 7.034186709636159e-05, "loss": 0.0386, "positive_teacher_pairs": 26144.8, "relation_loss": 0.003662287723273039, "selected_pairs": 26144.8, "step": 11950, "student_distance_mean": 1128.7325073242187, "teacher_distance_mean": 0.8542828261852264, "valid_action_samples": 229.1, "weighted_auxiliary_loss": 0.003662287723273039, "weighted_relation_loss": 0.003662287723273039 }, { "action_query_batch_std": 19.752145195007323, "action_query_norm": 857.3688659667969, "action_relation_loss": 0.003696935740299523, "auxiliary_loss_weight": 1.0, "epoch": 11.188026192703461, "flow_matching_loss": 0.03571320828050375, "grad_norm": 0.11824415624141693, "invalid_tail_samples": 24.1, "learning_rate": 7.029150655796129e-05, "loss": 0.0394, "positive_teacher_pairs": 26782.3, "relation_loss": 0.003696935740299523, "selected_pairs": 26782.3, "step": 11960, "student_distance_mean": 1127.317822265625, "teacher_distance_mean": 0.8489801406860351, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.003696935740299523, "weighted_relation_loss": 0.003696935740299523 }, { "action_query_batch_std": 20.011153602600096, "action_query_norm": 868.2623718261718, "action_relation_loss": 0.003696326515637338, "auxiliary_loss_weight": 1.0, "epoch": 11.197380729653883, "flow_matching_loss": 0.0344573974609375, "grad_norm": 0.11958522349596024, "invalid_tail_samples": 24.6, "learning_rate": 7.024112136346712e-05, "loss": 0.0382, "positive_teacher_pairs": 26667.8, "relation_loss": 0.003696326515637338, "selected_pairs": 26667.8, "step": 11970, "student_distance_mean": 1139.9108276367188, "teacher_distance_mean": 0.8655943691730499, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.003696326515637338, "weighted_relation_loss": 0.003696326515637338 }, { "action_query_batch_std": 19.973539733886717, "action_query_norm": 868.6330505371094, "action_relation_loss": 0.0037071989150717854, "auxiliary_loss_weight": 1.0, "epoch": 11.206735266604303, "flow_matching_loss": 0.034716063924133775, "grad_norm": 0.13306041061878204, "invalid_tail_samples": 23.3, "learning_rate": 7.01907115741019e-05, "loss": 0.0384, "positive_teacher_pairs": 26966.5, "relation_loss": 0.0037071989150717854, "selected_pairs": 26966.5, "step": 11980, "student_distance_mean": 1136.7406982421876, "teacher_distance_mean": 0.856056410074234, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0037071989150717854, "weighted_relation_loss": 0.0037071989150717854 }, { "action_query_batch_std": 19.601347160339355, "action_query_norm": 852.0924438476562, "action_relation_loss": 0.003846734738908708, "auxiliary_loss_weight": 1.0, "epoch": 11.216089803554723, "flow_matching_loss": 0.03667639307677746, "grad_norm": 0.09602325409650803, "invalid_tail_samples": 24.5, "learning_rate": 7.014027725111825e-05, "loss": 0.0405, "positive_teacher_pairs": 26689.1, "relation_loss": 0.003846734738908708, "selected_pairs": 26689.1, "step": 11990, "student_distance_mean": 1113.2761596679688, "teacher_distance_mean": 0.8444814503192901, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.003846734738908708, "weighted_relation_loss": 0.003846734738908708 }, { "action_query_batch_std": 19.846273612976074, "action_query_norm": 857.8639343261718, "action_relation_loss": 0.0035951668163761497, "auxiliary_loss_weight": 1.0, "epoch": 11.225444340505145, "flow_matching_loss": 0.03583308383822441, "grad_norm": 0.13512319326400757, "invalid_tail_samples": 24.8, "learning_rate": 7.008981845579864e-05, "loss": 0.0394, "positive_teacher_pairs": 26622.4, "relation_loss": 0.0035951668163761497, "selected_pairs": 26622.4, "step": 12000, "student_distance_mean": 1132.6480590820313, "teacher_distance_mean": 0.8568101048469543, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0035951668163761497, "weighted_relation_loss": 0.0035951668163761497 }, { "action_query_batch_std": 19.818175506591796, "action_query_norm": 861.3384399414062, "action_relation_loss": 0.0037219722289592028, "auxiliary_loss_weight": 1.0, "epoch": 11.234798877455566, "flow_matching_loss": 0.03415272813290358, "grad_norm": 0.11207976192235947, "invalid_tail_samples": 24.2, "learning_rate": 7.003933524945528e-05, "loss": 0.0379, "positive_teacher_pairs": 26753.4, "relation_loss": 0.0037219722289592028, "selected_pairs": 26753.4, "step": 12010, "student_distance_mean": 1131.5103515625, "teacher_distance_mean": 0.849613219499588, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0037219722289592028, "weighted_relation_loss": 0.0037219722289592028 }, { "action_query_batch_std": 20.341139030456542, "action_query_norm": 876.3923217773438, "action_relation_loss": 0.0035956895211711527, "auxiliary_loss_weight": 1.0, "epoch": 11.244153414405988, "flow_matching_loss": 0.033501374162733556, "grad_norm": 0.10051039606332779, "invalid_tail_samples": 25.9, "learning_rate": 6.998882769342998e-05, "loss": 0.0371, "positive_teacher_pairs": 26365.0, "relation_loss": 0.0035956895211711527, "selected_pairs": 26365.0, "step": 12020, "student_distance_mean": 1162.2376831054687, "teacher_distance_mean": 0.8713494837284088, "valid_action_samples": 230.1, "weighted_auxiliary_loss": 0.0035956895211711527, "weighted_relation_loss": 0.0035956895211711527 }, { "action_query_batch_std": 19.813674545288087, "action_query_norm": 864.5808288574219, "action_relation_loss": 0.0036820488749071956, "auxiliary_loss_weight": 1.0, "epoch": 11.253507951356408, "flow_matching_loss": 0.033294853381812574, "grad_norm": 0.13042421638965607, "invalid_tail_samples": 21.8, "learning_rate": 6.993829584909423e-05, "loss": 0.037, "positive_teacher_pairs": 27320.1, "relation_loss": 0.0036820488749071956, "selected_pairs": 27320.1, "step": 12030, "student_distance_mean": 1130.6643920898437, "teacher_distance_mean": 0.851344245672226, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.0036820488749071956, "weighted_relation_loss": 0.0036820488749071956 }, { "action_query_batch_std": 19.6784366607666, "action_query_norm": 854.4880249023438, "action_relation_loss": 0.003696717880666256, "auxiliary_loss_weight": 1.0, "epoch": 11.262862488306828, "flow_matching_loss": 0.0347249710932374, "grad_norm": 0.0877278670668602, "invalid_tail_samples": 24.6, "learning_rate": 6.988773977784895e-05, "loss": 0.0384, "positive_teacher_pairs": 26660.9, "relation_loss": 0.003696717880666256, "selected_pairs": 26660.9, "step": 12040, "student_distance_mean": 1123.943359375, "teacher_distance_mean": 0.8502229750156403, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.003696717880666256, "weighted_relation_loss": 0.003696717880666256 }, { "action_query_batch_std": 20.055824279785156, "action_query_norm": 868.4546081542969, "action_relation_loss": 0.003672322770580649, "auxiliary_loss_weight": 1.0, "epoch": 11.27221702525725, "flow_matching_loss": 0.03648011721670628, "grad_norm": 0.1690891981124878, "invalid_tail_samples": 23.7, "learning_rate": 6.983715954112454e-05, "loss": 0.0402, "positive_teacher_pairs": 26876.1, "relation_loss": 0.003672322770580649, "selected_pairs": 26876.1, "step": 12050, "student_distance_mean": 1143.2070068359376, "teacher_distance_mean": 0.856883031129837, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.003672322770580649, "weighted_relation_loss": 0.003672322770580649 }, { "action_query_batch_std": 19.87270030975342, "action_query_norm": 859.9679931640625, "action_relation_loss": 0.0035745311994105577, "auxiliary_loss_weight": 1.0, "epoch": 11.28157156220767, "flow_matching_loss": 0.034041513502597806, "grad_norm": 0.16401128470897675, "invalid_tail_samples": 22.9, "learning_rate": 6.978655520038079e-05, "loss": 0.0376, "positive_teacher_pairs": 27069.4, "relation_loss": 0.0035745311994105577, "selected_pairs": 27069.4, "step": 12060, "student_distance_mean": 1129.1328979492187, "teacher_distance_mean": 0.8537349283695221, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0035745311994105577, "weighted_relation_loss": 0.0035745311994105577 }, { "action_query_batch_std": 19.849462890625, "action_query_norm": 863.7140319824218, "action_relation_loss": 0.003530020243488252, "auxiliary_loss_weight": 1.0, "epoch": 11.290926099158092, "flow_matching_loss": 0.03404159918427467, "grad_norm": 0.15551696717739105, "invalid_tail_samples": 22.8, "learning_rate": 6.97359268171067e-05, "loss": 0.0376, "positive_teacher_pairs": 27086.9, "relation_loss": 0.003530020243488252, "selected_pairs": 27086.9, "step": 12070, "student_distance_mean": 1130.3651000976563, "teacher_distance_mean": 0.8534065186977386, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.003530020243488252, "weighted_relation_loss": 0.003530020243488252 }, { "action_query_batch_std": 20.039909172058106, "action_query_norm": 871.0887023925782, "action_relation_loss": 0.0036811029305681585, "auxiliary_loss_weight": 1.0, "epoch": 11.300280636108512, "flow_matching_loss": 0.035772697627544404, "grad_norm": 0.14546173810958862, "invalid_tail_samples": 23.7, "learning_rate": 6.968527445282056e-05, "loss": 0.0395, "positive_teacher_pairs": 26880.7, "relation_loss": 0.0036811029305681585, "selected_pairs": 26880.7, "step": 12080, "student_distance_mean": 1142.9973510742188, "teacher_distance_mean": 0.8522169291973114, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0036811029305681585, "weighted_relation_loss": 0.0036811029305681585 }, { "action_query_batch_std": 20.503231811523438, "action_query_norm": 891.42900390625, "action_relation_loss": 0.003566610557027161, "auxiliary_loss_weight": 1.0, "epoch": 11.309635173058934, "flow_matching_loss": 0.03535003755241632, "grad_norm": 0.13237521052360535, "invalid_tail_samples": 21.8, "learning_rate": 6.963459816906977e-05, "loss": 0.0389, "positive_teacher_pairs": 27314.1, "relation_loss": 0.003566610557027161, "selected_pairs": 27314.1, "step": 12090, "student_distance_mean": 1167.5571166992188, "teacher_distance_mean": 0.8632580935955048, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.003566610557027161, "weighted_relation_loss": 0.003566610557027161 }, { "action_query_batch_std": 20.26471519470215, "action_query_norm": 880.9368957519531, "action_relation_loss": 0.003646136564202607, "auxiliary_loss_weight": 1.0, "epoch": 11.318989710009355, "flow_matching_loss": 0.033593093045055866, "grad_norm": 0.15206728875637054, "invalid_tail_samples": 22.1, "learning_rate": 6.958389802743077e-05, "loss": 0.0372, "positive_teacher_pairs": 27246.4, "relation_loss": 0.003646136564202607, "selected_pairs": 27246.4, "step": 12100, "student_distance_mean": 1153.4449340820313, "teacher_distance_mean": 0.8585791885852814, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.003646136564202607, "weighted_relation_loss": 0.003646136564202607 }, { "action_query_batch_std": 20.23357048034668, "action_query_norm": 874.2318725585938, "action_relation_loss": 0.0037096196319907904, "auxiliary_loss_weight": 1.0, "epoch": 11.328344246959775, "flow_matching_loss": 0.035041497088968754, "grad_norm": 0.13384924829006195, "invalid_tail_samples": 22.4, "learning_rate": 6.953317408950903e-05, "loss": 0.0388, "positive_teacher_pairs": 27183.5, "relation_loss": 0.0037096196319907904, "selected_pairs": 27183.5, "step": 12110, "student_distance_mean": 1152.559912109375, "teacher_distance_mean": 0.8591339409351348, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.0037096196319907904, "weighted_relation_loss": 0.0037096196319907904 }, { "action_query_batch_std": 20.23823013305664, "action_query_norm": 874.5201171875, "action_relation_loss": 0.003549032215960324, "auxiliary_loss_weight": 1.0, "epoch": 11.337698783910197, "flow_matching_loss": 0.03392431288957596, "grad_norm": 0.08744114637374878, "invalid_tail_samples": 24.7, "learning_rate": 6.94824264169389e-05, "loss": 0.0375, "positive_teacher_pairs": 26641.9, "relation_loss": 0.003549032215960324, "selected_pairs": 26641.9, "step": 12120, "student_distance_mean": 1155.3476684570312, "teacher_distance_mean": 0.8639210283756256, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.003549032215960324, "weighted_relation_loss": 0.003549032215960324 }, { "action_query_batch_std": 19.894237899780272, "action_query_norm": 860.7971984863282, "action_relation_loss": 0.0035793780349195003, "auxiliary_loss_weight": 1.0, "epoch": 11.347053320860617, "flow_matching_loss": 0.0352585231885314, "grad_norm": 0.11421428620815277, "invalid_tail_samples": 23.1, "learning_rate": 6.94316550713836e-05, "loss": 0.0388, "positive_teacher_pairs": 27012.4, "relation_loss": 0.0035793780349195003, "selected_pairs": 27012.4, "step": 12130, "student_distance_mean": 1131.3430908203125, "teacher_distance_mean": 0.850759357213974, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0035793780349195003, "weighted_relation_loss": 0.0035793780349195003 }, { "action_query_batch_std": 19.810514831542967, "action_query_norm": 859.3804016113281, "action_relation_loss": 0.003508959198370576, "auxiliary_loss_weight": 1.0, "epoch": 11.356407857811039, "flow_matching_loss": 0.037076497077941896, "grad_norm": 0.14296163618564606, "invalid_tail_samples": 29.0, "learning_rate": 6.938086011453513e-05, "loss": 0.0406, "positive_teacher_pairs": 25660.6, "relation_loss": 0.003508959198370576, "selected_pairs": 25660.6, "step": 12140, "student_distance_mean": 1131.5487915039062, "teacher_distance_mean": 0.8510256111621857, "valid_action_samples": 227.0, "weighted_auxiliary_loss": 0.003508959198370576, "weighted_relation_loss": 0.003508959198370576 }, { "action_query_batch_std": 19.963564491271974, "action_query_norm": 865.3700927734375, "action_relation_loss": 0.0035962529946118593, "auxiliary_loss_weight": 1.0, "epoch": 11.36576239476146, "flow_matching_loss": 0.03541341945528984, "grad_norm": 0.11830812692642212, "invalid_tail_samples": 23.4, "learning_rate": 6.93300416081141e-05, "loss": 0.039, "positive_teacher_pairs": 26953.9, "relation_loss": 0.0035962529946118593, "selected_pairs": 26953.9, "step": 12150, "student_distance_mean": 1141.1962646484376, "teacher_distance_mean": 0.8636250019073486, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0035962529946118593, "weighted_relation_loss": 0.0035962529946118593 }, { "action_query_batch_std": 19.72261791229248, "action_query_norm": 857.8431945800781, "action_relation_loss": 0.0036500929621979595, "auxiliary_loss_weight": 1.0, "epoch": 11.37511693171188, "flow_matching_loss": 0.036139614135026935, "grad_norm": 0.12362220138311386, "invalid_tail_samples": 26.3, "learning_rate": 6.927919961386984e-05, "loss": 0.0398, "positive_teacher_pairs": 26287.6, "relation_loss": 0.0036500929621979595, "selected_pairs": 26287.6, "step": 12160, "student_distance_mean": 1123.4865844726562, "teacher_distance_mean": 0.8609374344348908, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.0036500929621979595, "weighted_relation_loss": 0.0036500929621979595 }, { "action_query_batch_std": 19.592268562316896, "action_query_norm": 849.4358154296875, "action_relation_loss": 0.0038260597037151458, "auxiliary_loss_weight": 1.0, "epoch": 11.384471468662301, "flow_matching_loss": 0.037367946840822695, "grad_norm": 0.12053822726011276, "invalid_tail_samples": 23.5, "learning_rate": 6.922833419358013e-05, "loss": 0.0412, "positive_teacher_pairs": 26914.2, "relation_loss": 0.0038260597037151458, "selected_pairs": 26914.2, "step": 12170, "student_distance_mean": 1108.7703735351563, "teacher_distance_mean": 0.8442794978618622, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0038260597037151458, "weighted_relation_loss": 0.0038260597037151458 }, { "action_query_batch_std": 19.728948020935057, "action_query_norm": 858.0953857421875, "action_relation_loss": 0.003565533482469618, "auxiliary_loss_weight": 1.0, "epoch": 11.393826005612722, "flow_matching_loss": 0.03270389512181282, "grad_norm": 0.15266257524490356, "invalid_tail_samples": 24.1, "learning_rate": 6.917744540905124e-05, "loss": 0.0363, "positive_teacher_pairs": 26782.5, "relation_loss": 0.003565533482469618, "selected_pairs": 26782.5, "step": 12180, "student_distance_mean": 1125.9694091796875, "teacher_distance_mean": 0.8494931817054748, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.003565533482469618, "weighted_relation_loss": 0.003565533482469618 }, { "action_query_batch_std": 20.087641716003418, "action_query_norm": 868.2764892578125, "action_relation_loss": 0.0035447891801595687, "auxiliary_loss_weight": 1.0, "epoch": 11.403180542563144, "flow_matching_loss": 0.03517437800765037, "grad_norm": 0.14064869284629822, "invalid_tail_samples": 23.9, "learning_rate": 6.912653332211787e-05, "loss": 0.0387, "positive_teacher_pairs": 26827.0, "relation_loss": 0.0035447891801595687, "selected_pairs": 26827.0, "step": 12190, "student_distance_mean": 1141.7680419921876, "teacher_distance_mean": 0.8645116329193115, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0035447891801595687, "weighted_relation_loss": 0.0035447891801595687 }, { "action_query_batch_std": 20.004768943786623, "action_query_norm": 867.1450317382812, "action_relation_loss": 0.0034906582441180944, "auxiliary_loss_weight": 1.0, "epoch": 11.412535079513564, "flow_matching_loss": 0.03538722153753042, "grad_norm": 0.1392730325460434, "invalid_tail_samples": 20.2, "learning_rate": 6.9075597994643e-05, "loss": 0.0389, "positive_teacher_pairs": 27693.7, "relation_loss": 0.0034906582441180944, "selected_pairs": 27693.7, "step": 12200, "student_distance_mean": 1139.9645751953126, "teacher_distance_mean": 0.8612628638744354, "valid_action_samples": 235.8, "weighted_auxiliary_loss": 0.0034906582441180944, "weighted_relation_loss": 0.0034906582441180944 }, { "action_query_batch_std": 19.941843032836914, "action_query_norm": 866.6478210449219, "action_relation_loss": 0.003614311502315104, "auxiliary_loss_weight": 1.0, "epoch": 11.421889616463986, "flow_matching_loss": 0.037930891290307044, "grad_norm": 0.13936671614646912, "invalid_tail_samples": 24.6, "learning_rate": 6.902463948851787e-05, "loss": 0.0415, "positive_teacher_pairs": 26669.6, "relation_loss": 0.003614311502315104, "selected_pairs": 26669.6, "step": 12210, "student_distance_mean": 1135.3835571289062, "teacher_distance_mean": 0.8561084032058716, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.003614311502315104, "weighted_relation_loss": 0.003614311502315104 }, { "action_query_batch_std": 19.836786460876464, "action_query_norm": 863.81904296875, "action_relation_loss": 0.00354360428173095, "auxiliary_loss_weight": 1.0, "epoch": 11.431244153414406, "flow_matching_loss": 0.03276624009013176, "grad_norm": 0.11859846115112305, "invalid_tail_samples": 24.1, "learning_rate": 6.897365786566184e-05, "loss": 0.0363, "positive_teacher_pairs": 26777.7, "relation_loss": 0.00354360428173095, "selected_pairs": 26777.7, "step": 12220, "student_distance_mean": 1131.456787109375, "teacher_distance_mean": 0.8530638813972473, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.00354360428173095, "weighted_relation_loss": 0.00354360428173095 }, { "action_query_batch_std": 20.041336059570312, "action_query_norm": 871.5630859375, "action_relation_loss": 0.0035614265827462075, "auxiliary_loss_weight": 1.0, "epoch": 11.440598690364826, "flow_matching_loss": 0.03508584871888161, "grad_norm": 0.1637575924396515, "invalid_tail_samples": 22.6, "learning_rate": 6.892265318802242e-05, "loss": 0.0386, "positive_teacher_pairs": 27125.6, "relation_loss": 0.0035614265827462075, "selected_pairs": 27125.6, "step": 12230, "student_distance_mean": 1142.3512939453126, "teacher_distance_mean": 0.858221036195755, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0035614265827462075, "weighted_relation_loss": 0.0035614265827462075 }, { "action_query_batch_std": 19.75055694580078, "action_query_norm": 860.0511779785156, "action_relation_loss": 0.0038003519177436827, "auxiliary_loss_weight": 1.0, "epoch": 11.449953227315248, "flow_matching_loss": 0.03351971246302128, "grad_norm": 0.12085963785648346, "invalid_tail_samples": 26.6, "learning_rate": 6.887162551757507e-05, "loss": 0.0373, "positive_teacher_pairs": 26224.0, "relation_loss": 0.0038003519177436827, "selected_pairs": 26224.0, "step": 12240, "student_distance_mean": 1125.1704223632812, "teacher_distance_mean": 0.8462480425834655, "valid_action_samples": 229.4, "weighted_auxiliary_loss": 0.0038003519177436827, "weighted_relation_loss": 0.0038003519177436827 }, { "action_query_batch_std": 19.842765045166015, "action_query_norm": 862.7142272949219, "action_relation_loss": 0.003778044763021171, "auxiliary_loss_weight": 1.0, "epoch": 11.459307764265668, "flow_matching_loss": 0.03360791690647602, "grad_norm": 0.12328296154737473, "invalid_tail_samples": 24.4, "learning_rate": 6.882057491632326e-05, "loss": 0.0374, "positive_teacher_pairs": 26712.1, "relation_loss": 0.003778044763021171, "selected_pairs": 26712.1, "step": 12250, "student_distance_mean": 1132.775830078125, "teacher_distance_mean": 0.8552780032157898, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.003778044763021171, "weighted_relation_loss": 0.003778044763021171 }, { "action_query_batch_std": 19.846421432495116, "action_query_norm": 864.2833312988281, "action_relation_loss": 0.0035601594718173146, "auxiliary_loss_weight": 1.0, "epoch": 11.46866230121609, "flow_matching_loss": 0.03498727548867464, "grad_norm": 0.12867142260074615, "invalid_tail_samples": 22.6, "learning_rate": 6.876950144629824e-05, "loss": 0.0385, "positive_teacher_pairs": 27131.5, "relation_loss": 0.0035601594718173146, "selected_pairs": 27131.5, "step": 12260, "student_distance_mean": 1132.135009765625, "teacher_distance_mean": 0.8607246398925781, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0035601594718173146, "weighted_relation_loss": 0.0035601594718173146 }, { "action_query_batch_std": 19.950892066955568, "action_query_norm": 866.29541015625, "action_relation_loss": 0.0036180777940899135, "auxiliary_loss_weight": 1.0, "epoch": 11.47801683816651, "flow_matching_loss": 0.03514015022665262, "grad_norm": 0.1588251143693924, "invalid_tail_samples": 21.7, "learning_rate": 6.87184051695591e-05, "loss": 0.0388, "positive_teacher_pairs": 27336.5, "relation_loss": 0.0036180777940899135, "selected_pairs": 27336.5, "step": 12270, "student_distance_mean": 1134.6786499023438, "teacher_distance_mean": 0.8535094738006592, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.0036180777940899135, "weighted_relation_loss": 0.0036180777940899135 }, { "action_query_batch_std": 19.887385177612305, "action_query_norm": 864.1892578125, "action_relation_loss": 0.003634576266631484, "auxiliary_loss_weight": 1.0, "epoch": 11.487371375116933, "flow_matching_loss": 0.03466218486428261, "grad_norm": 0.1470097303390503, "invalid_tail_samples": 23.6, "learning_rate": 6.866728614819268e-05, "loss": 0.0383, "positive_teacher_pairs": 26895.2, "relation_loss": 0.003634576266631484, "selected_pairs": 26895.2, "step": 12280, "student_distance_mean": 1133.4739990234375, "teacher_distance_mean": 0.8515496909618377, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.003634576266631484, "weighted_relation_loss": 0.003634576266631484 }, { "action_query_batch_std": 19.9694580078125, "action_query_norm": 867.5510803222656, "action_relation_loss": 0.0035171992145478725, "auxiliary_loss_weight": 1.0, "epoch": 11.496725912067353, "flow_matching_loss": 0.033927518874406815, "grad_norm": 0.1445908546447754, "invalid_tail_samples": 22.7, "learning_rate": 6.861614444431337e-05, "loss": 0.0374, "positive_teacher_pairs": 27101.7, "relation_loss": 0.0035171992145478725, "selected_pairs": 27101.7, "step": 12290, "student_distance_mean": 1142.6072998046875, "teacher_distance_mean": 0.8566925942897796, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0035171992145478725, "weighted_relation_loss": 0.0035171992145478725 }, { "action_query_batch_std": 20.06027183532715, "action_query_norm": 872.5844787597656, "action_relation_loss": 0.0034694215282797813, "auxiliary_loss_weight": 1.0, "epoch": 11.506080449017773, "flow_matching_loss": 0.03440530691295862, "grad_norm": 0.09158048778772354, "invalid_tail_samples": 22.5, "learning_rate": 6.856498012006318e-05, "loss": 0.0379, "positive_teacher_pairs": 27151.1, "relation_loss": 0.0034694215282797813, "selected_pairs": 27151.1, "step": 12300, "student_distance_mean": 1143.065380859375, "teacher_distance_mean": 0.8550793647766113, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0034694215282797813, "weighted_relation_loss": 0.0034694215282797813 }, { "action_query_batch_std": 20.064848327636717, "action_query_norm": 868.7032287597656, "action_relation_loss": 0.0037133134203031657, "auxiliary_loss_weight": 1.0, "epoch": 11.515434985968195, "flow_matching_loss": 0.0356368325650692, "grad_norm": 0.10597091913223267, "invalid_tail_samples": 21.9, "learning_rate": 6.851379323761157e-05, "loss": 0.0394, "positive_teacher_pairs": 27295.4, "relation_loss": 0.0037133134203031657, "selected_pairs": 27295.4, "step": 12310, "student_distance_mean": 1140.9710205078125, "teacher_distance_mean": 0.8521512746810913, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.0037133134203031657, "weighted_relation_loss": 0.0037133134203031657 }, { "action_query_batch_std": 20.10515785217285, "action_query_norm": 869.8132507324219, "action_relation_loss": 0.003490565507672727, "auxiliary_loss_weight": 1.0, "epoch": 11.524789522918615, "flow_matching_loss": 0.03342603631317616, "grad_norm": 0.1265384405851364, "invalid_tail_samples": 22.1, "learning_rate": 6.846258385915545e-05, "loss": 0.0369, "positive_teacher_pairs": 27245.4, "relation_loss": 0.003490565507672727, "selected_pairs": 27245.4, "step": 12320, "student_distance_mean": 1148.348486328125, "teacher_distance_mean": 0.8608643233776092, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.003490565507672727, "weighted_relation_loss": 0.003490565507672727 }, { "action_query_batch_std": 20.26618137359619, "action_query_norm": 875.0949584960938, "action_relation_loss": 0.00353124625980854, "auxiliary_loss_weight": 1.0, "epoch": 11.534144059869037, "flow_matching_loss": 0.03635335974395275, "grad_norm": 0.11012443155050278, "invalid_tail_samples": 24.7, "learning_rate": 6.841135204691902e-05, "loss": 0.0399, "positive_teacher_pairs": 26643.9, "relation_loss": 0.00353124625980854, "selected_pairs": 26643.9, "step": 12330, "student_distance_mean": 1154.5697021484375, "teacher_distance_mean": 0.866787600517273, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.00353124625980854, "weighted_relation_loss": 0.00353124625980854 }, { "action_query_batch_std": 19.656435394287108, "action_query_norm": 847.8472290039062, "action_relation_loss": 0.003634561481885612, "auxiliary_loss_weight": 1.0, "epoch": 11.543498596819457, "flow_matching_loss": 0.03444388844072819, "grad_norm": 0.10049665719270706, "invalid_tail_samples": 25.5, "learning_rate": 6.836009786315377e-05, "loss": 0.0381, "positive_teacher_pairs": 26457.6, "relation_loss": 0.003634561481885612, "selected_pairs": 26457.6, "step": 12340, "student_distance_mean": 1120.951220703125, "teacher_distance_mean": 0.8514745652675628, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.003634561481885612, "weighted_relation_loss": 0.003634561481885612 }, { "action_query_batch_std": 20.10824680328369, "action_query_norm": 867.9563232421875, "action_relation_loss": 0.003435571794398129, "auxiliary_loss_weight": 1.0, "epoch": 11.552853133769878, "flow_matching_loss": 0.03554776161909103, "grad_norm": 0.11830152571201324, "invalid_tail_samples": 23.5, "learning_rate": 6.830882137013839e-05, "loss": 0.039, "positive_teacher_pairs": 26918.0, "relation_loss": 0.003435571794398129, "selected_pairs": 26918.0, "step": 12350, "student_distance_mean": 1148.9446411132812, "teacher_distance_mean": 0.8668803215026856, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.003435571794398129, "weighted_relation_loss": 0.003435571794398129 }, { "action_query_batch_std": 19.896030044555665, "action_query_norm": 866.6822509765625, "action_relation_loss": 0.0035547932144254445, "auxiliary_loss_weight": 1.0, "epoch": 11.5622076707203, "flow_matching_loss": 0.03353015296161175, "grad_norm": 0.10580312460660934, "invalid_tail_samples": 24.6, "learning_rate": 6.825752263017863e-05, "loss": 0.0371, "positive_teacher_pairs": 26665.1, "relation_loss": 0.0035547932144254445, "selected_pairs": 26665.1, "step": 12360, "student_distance_mean": 1133.8486206054688, "teacher_distance_mean": 0.8502260863780975, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0035547932144254445, "weighted_relation_loss": 0.0035547932144254445 }, { "action_query_batch_std": 19.989493942260744, "action_query_norm": 868.1291748046875, "action_relation_loss": 0.0034260447369888424, "auxiliary_loss_weight": 1.0, "epoch": 11.57156220767072, "flow_matching_loss": 0.03396244812756777, "grad_norm": 0.1107991486787796, "invalid_tail_samples": 24.1, "learning_rate": 6.820620170560731e-05, "loss": 0.0374, "positive_teacher_pairs": 26782.0, "relation_loss": 0.0034260447369888424, "selected_pairs": 26782.0, "step": 12370, "student_distance_mean": 1139.1149780273438, "teacher_distance_mean": 0.8571113288402558, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0034260447369888424, "weighted_relation_loss": 0.0034260447369888424 }, { "action_query_batch_std": 20.057055473327637, "action_query_norm": 869.9311645507812, "action_relation_loss": 0.003539492073468864, "auxiliary_loss_weight": 1.0, "epoch": 11.580916744621142, "flow_matching_loss": 0.03391555082052946, "grad_norm": 0.14913617074489594, "invalid_tail_samples": 21.9, "learning_rate": 6.815485865878418e-05, "loss": 0.0375, "positive_teacher_pairs": 27293.4, "relation_loss": 0.003539492073468864, "selected_pairs": 27293.4, "step": 12380, "student_distance_mean": 1144.2452514648437, "teacher_distance_mean": 0.8525603771209717, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.003539492073468864, "weighted_relation_loss": 0.003539492073468864 }, { "action_query_batch_std": 19.92283191680908, "action_query_norm": 863.9272705078125, "action_relation_loss": 0.0036675122333690523, "auxiliary_loss_weight": 1.0, "epoch": 11.590271281571562, "flow_matching_loss": 0.0323093393817544, "grad_norm": 0.14256519079208374, "invalid_tail_samples": 23.5, "learning_rate": 6.810349355209588e-05, "loss": 0.036, "positive_teacher_pairs": 26920.8, "relation_loss": 0.0036675122333690523, "selected_pairs": 26920.8, "step": 12390, "student_distance_mean": 1135.3845947265625, "teacher_distance_mean": 0.8506368637084961, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0036675122333690523, "weighted_relation_loss": 0.0036675122333690523 }, { "action_query_batch_std": 20.042276191711426, "action_query_norm": 872.6204650878906, "action_relation_loss": 0.0034607247216627, "auxiliary_loss_weight": 1.0, "epoch": 11.599625818521982, "flow_matching_loss": 0.03497755695134401, "grad_norm": 0.1389300525188446, "invalid_tail_samples": 21.6, "learning_rate": 6.805210644795588e-05, "loss": 0.0384, "positive_teacher_pairs": 27360.9, "relation_loss": 0.0034607247216627, "selected_pairs": 27360.9, "step": 12400, "student_distance_mean": 1145.1877563476562, "teacher_distance_mean": 0.8543310225009918, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.0034607247216627, "weighted_relation_loss": 0.0034607247216627 }, { "action_query_batch_std": 20.160708618164062, "action_query_norm": 875.9082092285156, "action_relation_loss": 0.0035460477229207754, "auxiliary_loss_weight": 1.0, "epoch": 11.608980355472404, "flow_matching_loss": 0.034135378897190094, "grad_norm": 0.12611450254917145, "invalid_tail_samples": 20.5, "learning_rate": 6.800069740880433e-05, "loss": 0.0377, "positive_teacher_pairs": 27626.9, "relation_loss": 0.0035460477229207754, "selected_pairs": 27626.9, "step": 12410, "student_distance_mean": 1149.1613159179688, "teacher_distance_mean": 0.8532103717327117, "valid_action_samples": 235.5, "weighted_auxiliary_loss": 0.0035460477229207754, "weighted_relation_loss": 0.0035460477229207754 }, { "action_query_batch_std": 20.069917678833008, "action_query_norm": 867.0449768066406, "action_relation_loss": 0.003610380692407489, "auxiliary_loss_weight": 1.0, "epoch": 11.618334892422824, "flow_matching_loss": 0.03418232165277004, "grad_norm": 0.14360150694847107, "invalid_tail_samples": 25.0, "learning_rate": 6.794926649710807e-05, "loss": 0.0378, "positive_teacher_pairs": 26575.5, "relation_loss": 0.003610380692407489, "selected_pairs": 26575.5, "step": 12420, "student_distance_mean": 1141.1057006835938, "teacher_distance_mean": 0.8489383459091187, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.003610380692407489, "weighted_relation_loss": 0.003610380692407489 }, { "action_query_batch_std": 20.151052474975586, "action_query_norm": 870.6596252441407, "action_relation_loss": 0.0035852632019668816, "auxiliary_loss_weight": 1.0, "epoch": 11.627689429373246, "flow_matching_loss": 0.03363804686814546, "grad_norm": 0.12778709828853607, "invalid_tail_samples": 23.6, "learning_rate": 6.789781377536052e-05, "loss": 0.0372, "positive_teacher_pairs": 26898.8, "relation_loss": 0.0035852632019668816, "selected_pairs": 26898.8, "step": 12430, "student_distance_mean": 1148.9130859375, "teacher_distance_mean": 0.8564731478691101, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0035852632019668816, "weighted_relation_loss": 0.0035852632019668816 }, { "action_query_batch_std": 20.200103950500488, "action_query_norm": 871.8193603515625, "action_relation_loss": 0.0036239181645214558, "auxiliary_loss_weight": 1.0, "epoch": 11.637043966323667, "flow_matching_loss": 0.03475402481853962, "grad_norm": 0.11928404867649078, "invalid_tail_samples": 23.2, "learning_rate": 6.784633930608158e-05, "loss": 0.0384, "positive_teacher_pairs": 26990.0, "relation_loss": 0.0036239181645214558, "selected_pairs": 26990.0, "step": 12440, "student_distance_mean": 1151.3263061523437, "teacher_distance_mean": 0.8504588544368744, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0036239181645214558, "weighted_relation_loss": 0.0036239181645214558 }, { "action_query_batch_std": 19.952643394470215, "action_query_norm": 863.7609436035157, "action_relation_loss": 0.0036148671293631195, "auxiliary_loss_weight": 1.0, "epoch": 11.646398503274089, "flow_matching_loss": 0.03436301983892918, "grad_norm": 0.1078931987285614, "invalid_tail_samples": 27.0, "learning_rate": 6.779484315181759e-05, "loss": 0.038, "positive_teacher_pairs": 26112.4, "relation_loss": 0.0036148671293631195, "selected_pairs": 26112.4, "step": 12450, "student_distance_mean": 1134.4482299804688, "teacher_distance_mean": 0.8444285988807678, "valid_action_samples": 229.0, "weighted_auxiliary_loss": 0.0036148671293631195, "weighted_relation_loss": 0.0036148671293631195 }, { "action_query_batch_std": 20.29484634399414, "action_query_norm": 876.1017822265625, "action_relation_loss": 0.003763412358239293, "auxiliary_loss_weight": 1.0, "epoch": 11.655753040224509, "flow_matching_loss": 0.03632130678743124, "grad_norm": 0.14654643833637238, "invalid_tail_samples": 23.0, "learning_rate": 6.774332537514122e-05, "loss": 0.0401, "positive_teacher_pairs": 27047.1, "relation_loss": 0.003763412358239293, "selected_pairs": 27047.1, "step": 12460, "student_distance_mean": 1150.556396484375, "teacher_distance_mean": 0.8564913392066955, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.003763412358239293, "weighted_relation_loss": 0.003763412358239293 }, { "action_query_batch_std": 20.035652923583985, "action_query_norm": 867.448291015625, "action_relation_loss": 0.0036906084278598428, "auxiliary_loss_weight": 1.0, "epoch": 11.665107577174929, "flow_matching_loss": 0.034590401686728, "grad_norm": 0.1000538244843483, "invalid_tail_samples": 25.8, "learning_rate": 6.769178603865143e-05, "loss": 0.0383, "positive_teacher_pairs": 26392.8, "relation_loss": 0.0036906084278598428, "selected_pairs": 26392.8, "step": 12470, "student_distance_mean": 1141.3617309570313, "teacher_distance_mean": 0.8426762104034424, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.0036906084278598428, "weighted_relation_loss": 0.0036906084278598428 }, { "action_query_batch_std": 19.936591720581056, "action_query_norm": 861.0172180175781, "action_relation_loss": 0.0035664521157741545, "auxiliary_loss_weight": 1.0, "epoch": 11.674462114125351, "flow_matching_loss": 0.03566032163798809, "grad_norm": 0.10726583003997803, "invalid_tail_samples": 22.1, "learning_rate": 6.764022520497337e-05, "loss": 0.0392, "positive_teacher_pairs": 27253.1, "relation_loss": 0.0035664521157741545, "selected_pairs": 27253.1, "step": 12480, "student_distance_mean": 1136.6508422851562, "teacher_distance_mean": 0.8486266553401947, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0035664521157741545, "weighted_relation_loss": 0.0035664521157741545 }, { "action_query_batch_std": 19.95776710510254, "action_query_norm": 866.7711547851562, "action_relation_loss": 0.0035905800526961685, "auxiliary_loss_weight": 1.0, "epoch": 11.683816651075771, "flow_matching_loss": 0.03396399281919003, "grad_norm": 0.0996968001127243, "invalid_tail_samples": 25.8, "learning_rate": 6.758864293675833e-05, "loss": 0.0376, "positive_teacher_pairs": 26385.2, "relation_loss": 0.0035905800526961685, "selected_pairs": 26385.2, "step": 12490, "student_distance_mean": 1141.9255126953126, "teacher_distance_mean": 0.8500442504882812, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.0035905800526961685, "weighted_relation_loss": 0.0035905800526961685 }, { "action_query_batch_std": 20.270772171020507, "action_query_norm": 877.7870666503907, "action_relation_loss": 0.003560063079930842, "auxiliary_loss_weight": 1.0, "epoch": 11.693171188026193, "flow_matching_loss": 0.035528171434998514, "grad_norm": 0.11384429037570953, "invalid_tail_samples": 23.7, "learning_rate": 6.753703929668362e-05, "loss": 0.0391, "positive_teacher_pairs": 26874.4, "relation_loss": 0.003560063079930842, "selected_pairs": 26874.4, "step": 12500, "student_distance_mean": 1153.2384033203125, "teacher_distance_mean": 0.8551168203353882, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.003560063079930842, "weighted_relation_loss": 0.003560063079930842 }, { "action_query_batch_std": 20.11484851837158, "action_query_norm": 870.4462341308594, "action_relation_loss": 0.003487710515037179, "auxiliary_loss_weight": 1.0, "epoch": 11.702525724976613, "flow_matching_loss": 0.03285953514277935, "grad_norm": 0.11922238767147064, "invalid_tail_samples": 24.1, "learning_rate": 6.748541434745253e-05, "loss": 0.0363, "positive_teacher_pairs": 26785.2, "relation_loss": 0.003487710515037179, "selected_pairs": 26785.2, "step": 12510, "student_distance_mean": 1142.2681274414062, "teacher_distance_mean": 0.8509969055652619, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.003487710515037179, "weighted_relation_loss": 0.003487710515037179 }, { "action_query_batch_std": 20.25206470489502, "action_query_norm": 878.3799499511719, "action_relation_loss": 0.0034298074431717398, "auxiliary_loss_weight": 1.0, "epoch": 11.711880261927035, "flow_matching_loss": 0.033666209876537324, "grad_norm": 0.11113415658473969, "invalid_tail_samples": 21.9, "learning_rate": 6.743376815179424e-05, "loss": 0.0371, "positive_teacher_pairs": 27300.0, "relation_loss": 0.0034298074431717398, "selected_pairs": 27300.0, "step": 12520, "student_distance_mean": 1155.1880615234375, "teacher_distance_mean": 0.8494042336940766, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.0034298074431717398, "weighted_relation_loss": 0.0034298074431717398 }, { "action_query_batch_std": 20.292974090576173, "action_query_norm": 883.5135620117187, "action_relation_loss": 0.0035854173824191094, "auxiliary_loss_weight": 1.0, "epoch": 11.721234798877456, "flow_matching_loss": 0.0354284230619669, "grad_norm": 0.10420054197311401, "invalid_tail_samples": 20.3, "learning_rate": 6.738210077246376e-05, "loss": 0.039, "positive_teacher_pairs": 27669.9, "relation_loss": 0.0035854173824191094, "selected_pairs": 27669.9, "step": 12530, "student_distance_mean": 1154.5589233398437, "teacher_distance_mean": 0.8494055509567261, "valid_action_samples": 235.7, "weighted_auxiliary_loss": 0.0035854173824191094, "weighted_relation_loss": 0.0035854173824191094 }, { "action_query_batch_std": 20.233518028259276, "action_query_norm": 875.1755615234375, "action_relation_loss": 0.003454211074858904, "auxiliary_loss_weight": 1.0, "epoch": 11.730589335827876, "flow_matching_loss": 0.03522449266165495, "grad_norm": 0.12478092312812805, "invalid_tail_samples": 26.0, "learning_rate": 6.733041227224181e-05, "loss": 0.0387, "positive_teacher_pairs": 26340.6, "relation_loss": 0.003454211074858904, "selected_pairs": 26340.6, "step": 12540, "student_distance_mean": 1157.0710327148438, "teacher_distance_mean": 0.8600144147872925, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.003454211074858904, "weighted_relation_loss": 0.003454211074858904 }, { "action_query_batch_std": 20.42604293823242, "action_query_norm": 883.8405700683594, "action_relation_loss": 0.0033581739058718084, "auxiliary_loss_weight": 1.0, "epoch": 11.739943872778298, "flow_matching_loss": 0.0342664510011673, "grad_norm": 0.14495961368083954, "invalid_tail_samples": 20.9, "learning_rate": 6.72787027139348e-05, "loss": 0.0376, "positive_teacher_pairs": 27527.7, "relation_loss": 0.0033581739058718084, "selected_pairs": 27527.7, "step": 12550, "student_distance_mean": 1162.3478271484375, "teacher_distance_mean": 0.8598371744155884, "valid_action_samples": 235.1, "weighted_auxiliary_loss": 0.0033581739058718084, "weighted_relation_loss": 0.0033581739058718084 }, { "action_query_batch_std": 19.96496696472168, "action_query_norm": 863.8044494628906, "action_relation_loss": 0.00359364349860698, "auxiliary_loss_weight": 1.0, "epoch": 11.749298409728718, "flow_matching_loss": 0.03585223518311977, "grad_norm": 0.1315222978591919, "invalid_tail_samples": 26.0, "learning_rate": 6.72269721603747e-05, "loss": 0.0394, "positive_teacher_pairs": 26340.6, "relation_loss": 0.00359364349860698, "selected_pairs": 26340.6, "step": 12560, "student_distance_mean": 1142.0145263671875, "teacher_distance_mean": 0.8561491966247559, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.00359364349860698, "weighted_relation_loss": 0.00359364349860698 }, { "action_query_batch_std": 20.12651309967041, "action_query_norm": 873.99404296875, "action_relation_loss": 0.003678062162362039, "auxiliary_loss_weight": 1.0, "epoch": 11.75865294667914, "flow_matching_loss": 0.032096348516643045, "grad_norm": 0.11687242239713669, "invalid_tail_samples": 22.9, "learning_rate": 6.717522067441904e-05, "loss": 0.0358, "positive_teacher_pairs": 27059.0, "relation_loss": 0.003678062162362039, "selected_pairs": 27059.0, "step": 12570, "student_distance_mean": 1150.4000610351563, "teacher_distance_mean": 0.8545519232749939, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.003678062162362039, "weighted_relation_loss": 0.003678062162362039 }, { "action_query_batch_std": 20.314034461975098, "action_query_norm": 882.1934143066406, "action_relation_loss": 0.003560914960689843, "auxiliary_loss_weight": 1.0, "epoch": 11.76800748362956, "flow_matching_loss": 0.033949909172952174, "grad_norm": 0.10619901120662689, "invalid_tail_samples": 22.3, "learning_rate": 6.712344831895074e-05, "loss": 0.0375, "positive_teacher_pairs": 27197.7, "relation_loss": 0.003560914960689843, "selected_pairs": 27197.7, "step": 12580, "student_distance_mean": 1157.5565185546875, "teacher_distance_mean": 0.8543322265148163, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.003560914960689843, "weighted_relation_loss": 0.003560914960689843 }, { "action_query_batch_std": 20.56369342803955, "action_query_norm": 885.478271484375, "action_relation_loss": 0.0034335532458499075, "auxiliary_loss_weight": 1.0, "epoch": 11.77736202057998, "flow_matching_loss": 0.03401792570948601, "grad_norm": 0.12518924474716187, "invalid_tail_samples": 24.3, "learning_rate": 6.707165515687811e-05, "loss": 0.0375, "positive_teacher_pairs": 26733.8, "relation_loss": 0.0034335532458499075, "selected_pairs": 26733.8, "step": 12590, "student_distance_mean": 1169.8204956054688, "teacher_distance_mean": 0.869545578956604, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0034335532458499075, "weighted_relation_loss": 0.0034335532458499075 }, { "action_query_batch_std": 20.32407703399658, "action_query_norm": 878.5382080078125, "action_relation_loss": 0.003396506514400244, "auxiliary_loss_weight": 1.0, "epoch": 11.786716557530402, "flow_matching_loss": 0.03077902514487505, "grad_norm": 0.09076087176799774, "invalid_tail_samples": 23.2, "learning_rate": 6.70198412511347e-05, "loss": 0.0342, "positive_teacher_pairs": 26995.4, "relation_loss": 0.003396506514400244, "selected_pairs": 26995.4, "step": 12600, "student_distance_mean": 1158.2066650390625, "teacher_distance_mean": 0.8521739065647125, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.003396506514400244, "weighted_relation_loss": 0.003396506514400244 }, { "action_query_batch_std": 20.109100151062012, "action_query_norm": 872.7210571289063, "action_relation_loss": 0.003448120132088661, "auxiliary_loss_weight": 1.0, "epoch": 11.796071094480823, "flow_matching_loss": 0.03395393583923578, "grad_norm": 0.12746863067150116, "invalid_tail_samples": 25.1, "learning_rate": 6.69680066646793e-05, "loss": 0.0374, "positive_teacher_pairs": 26547.1, "relation_loss": 0.003448120132088661, "selected_pairs": 26547.1, "step": 12610, "student_distance_mean": 1146.4806518554688, "teacher_distance_mean": 0.8456077456474305, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.003448120132088661, "weighted_relation_loss": 0.003448120132088661 }, { "action_query_batch_std": 20.07005958557129, "action_query_norm": 869.4145080566407, "action_relation_loss": 0.0037338835652917625, "auxiliary_loss_weight": 1.0, "epoch": 11.805425631431245, "flow_matching_loss": 0.03441344629973173, "grad_norm": 0.1404207944869995, "invalid_tail_samples": 22.1, "learning_rate": 6.691615146049583e-05, "loss": 0.0381, "positive_teacher_pairs": 27256.1, "relation_loss": 0.0037338835652917625, "selected_pairs": 27256.1, "step": 12620, "student_distance_mean": 1143.1009399414063, "teacher_distance_mean": 0.8447196364402771, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0037338835652917625, "weighted_relation_loss": 0.0037338835652917625 }, { "action_query_batch_std": 20.33527355194092, "action_query_norm": 876.9049377441406, "action_relation_loss": 0.0033841901225969196, "auxiliary_loss_weight": 1.0, "epoch": 11.814780168381665, "flow_matching_loss": 0.03499896600842476, "grad_norm": 0.12310444563627243, "invalid_tail_samples": 25.1, "learning_rate": 6.686427570159324e-05, "loss": 0.0384, "positive_teacher_pairs": 26552.8, "relation_loss": 0.0033841901225969196, "selected_pairs": 26552.8, "step": 12630, "student_distance_mean": 1161.082275390625, "teacher_distance_mean": 0.8558188796043396, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0033841901225969196, "weighted_relation_loss": 0.0033841901225969196 }, { "action_query_batch_std": 20.21222839355469, "action_query_norm": 875.2833190917969, "action_relation_loss": 0.0035174625692889093, "auxiliary_loss_weight": 1.0, "epoch": 11.824134705332087, "flow_matching_loss": 0.03302349094301462, "grad_norm": 0.11734389513731003, "invalid_tail_samples": 23.2, "learning_rate": 6.681237945100548e-05, "loss": 0.0365, "positive_teacher_pairs": 26994.9, "relation_loss": 0.0035174625692889093, "selected_pairs": 26994.9, "step": 12640, "student_distance_mean": 1155.3925659179688, "teacher_distance_mean": 0.8528707265853882, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0035174625692889093, "weighted_relation_loss": 0.0035174625692889093 }, { "action_query_batch_std": 19.8882080078125, "action_query_norm": 864.0068237304688, "action_relation_loss": 0.003522750805132091, "auxiliary_loss_weight": 1.0, "epoch": 11.833489242282507, "flow_matching_loss": 0.03324781898409128, "grad_norm": 0.13550719618797302, "invalid_tail_samples": 24.0, "learning_rate": 6.676046277179139e-05, "loss": 0.0368, "positive_teacher_pairs": 26810.6, "relation_loss": 0.003522750805132091, "selected_pairs": 26810.6, "step": 12650, "student_distance_mean": 1133.0189697265625, "teacher_distance_mean": 0.8394081294536591, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.003522750805132091, "weighted_relation_loss": 0.003522750805132091 }, { "action_query_batch_std": 20.21296844482422, "action_query_norm": 874.3970886230469, "action_relation_loss": 0.003511624806560576, "auxiliary_loss_weight": 1.0, "epoch": 11.842843779232927, "flow_matching_loss": 0.03504563383758068, "grad_norm": 0.14898094534873962, "invalid_tail_samples": 22.5, "learning_rate": 6.670852572703462e-05, "loss": 0.0386, "positive_teacher_pairs": 27151.7, "relation_loss": 0.003511624806560576, "selected_pairs": 27151.7, "step": 12660, "student_distance_mean": 1146.4209594726562, "teacher_distance_mean": 0.8494193375110626, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.003511624806560576, "weighted_relation_loss": 0.003511624806560576 }, { "action_query_batch_std": 20.16009941101074, "action_query_norm": 868.4066101074219, "action_relation_loss": 0.003386235982179642, "auxiliary_loss_weight": 1.0, "epoch": 11.85219831618335, "flow_matching_loss": 0.037763493694365026, "grad_norm": 0.14218223094940186, "invalid_tail_samples": 26.1, "learning_rate": 6.665656837984359e-05, "loss": 0.0411, "positive_teacher_pairs": 26317.5, "relation_loss": 0.003386235982179642, "selected_pairs": 26317.5, "step": 12670, "student_distance_mean": 1152.6454345703125, "teacher_distance_mean": 0.8551294147968292, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.003386235982179642, "weighted_relation_loss": 0.003386235982179642 }, { "action_query_batch_std": 20.006982421875, "action_query_norm": 865.7848999023438, "action_relation_loss": 0.00343281552195549, "auxiliary_loss_weight": 1.0, "epoch": 11.86155285313377, "flow_matching_loss": 0.0324074786156416, "grad_norm": 0.15181311964988708, "invalid_tail_samples": 24.6, "learning_rate": 6.660459079335135e-05, "loss": 0.0358, "positive_teacher_pairs": 26664.8, "relation_loss": 0.00343281552195549, "selected_pairs": 26664.8, "step": 12680, "student_distance_mean": 1143.8115356445312, "teacher_distance_mean": 0.8449822902679444, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.00343281552195549, "weighted_relation_loss": 0.00343281552195549 }, { "action_query_batch_std": 19.969949340820314, "action_query_norm": 869.3300415039063, "action_relation_loss": 0.003664081310853362, "auxiliary_loss_weight": 1.0, "epoch": 11.870907390084191, "flow_matching_loss": 0.033410892076790336, "grad_norm": 0.11583514511585236, "invalid_tail_samples": 23.2, "learning_rate": 6.655259303071558e-05, "loss": 0.0371, "positive_teacher_pairs": 26989.2, "relation_loss": 0.003664081310853362, "selected_pairs": 26989.2, "step": 12690, "student_distance_mean": 1140.08349609375, "teacher_distance_mean": 0.8401512026786804, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.003664081310853362, "weighted_relation_loss": 0.003664081310853362 }, { "action_query_batch_std": 20.370188331604005, "action_query_norm": 876.179833984375, "action_relation_loss": 0.0034078781493008135, "auxiliary_loss_weight": 1.0, "epoch": 11.880261927034612, "flow_matching_loss": 0.03361953292042017, "grad_norm": 0.12209655344486237, "invalid_tail_samples": 22.1, "learning_rate": 6.650057515511848e-05, "loss": 0.037, "positive_teacher_pairs": 27255.2, "relation_loss": 0.0034078781493008135, "selected_pairs": 27255.2, "step": 12700, "student_distance_mean": 1164.2224609375, "teacher_distance_mean": 0.8681148290634155, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0034078781493008135, "weighted_relation_loss": 0.0034078781493008135 }, { "action_query_batch_std": 19.961247825622557, "action_query_norm": 864.5279968261718, "action_relation_loss": 0.003531225421465933, "auxiliary_loss_weight": 1.0, "epoch": 11.889616463985032, "flow_matching_loss": 0.035514682345092294, "grad_norm": 0.10922157019376755, "invalid_tail_samples": 23.7, "learning_rate": 6.644853722976667e-05, "loss": 0.039, "positive_teacher_pairs": 26874.4, "relation_loss": 0.003531225421465933, "selected_pairs": 26874.4, "step": 12710, "student_distance_mean": 1133.7438842773438, "teacher_distance_mean": 0.8405336320400238, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.003531225421465933, "weighted_relation_loss": 0.003531225421465933 }, { "action_query_batch_std": 20.15117301940918, "action_query_norm": 873.0894592285156, "action_relation_loss": 0.0034135436872020364, "auxiliary_loss_weight": 1.0, "epoch": 11.898971000935454, "flow_matching_loss": 0.03304608203470707, "grad_norm": 0.15609373152256012, "invalid_tail_samples": 23.6, "learning_rate": 6.639647931789113e-05, "loss": 0.0365, "positive_teacher_pairs": 26895.6, "relation_loss": 0.0034135436872020364, "selected_pairs": 26895.6, "step": 12720, "student_distance_mean": 1152.1751708984375, "teacher_distance_mean": 0.8578393399715424, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0034135436872020364, "weighted_relation_loss": 0.0034135436872020364 }, { "action_query_batch_std": 20.11351776123047, "action_query_norm": 871.0207580566406, "action_relation_loss": 0.003494609030894935, "auxiliary_loss_weight": 1.0, "epoch": 11.908325537885874, "flow_matching_loss": 0.03352668303996324, "grad_norm": 0.11868685483932495, "invalid_tail_samples": 22.7, "learning_rate": 6.634440148274713e-05, "loss": 0.037, "positive_teacher_pairs": 27104.5, "relation_loss": 0.003494609030894935, "selected_pairs": 27104.5, "step": 12730, "student_distance_mean": 1142.0827758789062, "teacher_distance_mean": 0.8491608560085296, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.003494609030894935, "weighted_relation_loss": 0.003494609030894935 }, { "action_query_batch_std": 20.41253547668457, "action_query_norm": 882.0273376464844, "action_relation_loss": 0.0034920216770842672, "auxiliary_loss_weight": 1.0, "epoch": 11.917680074836296, "flow_matching_loss": 0.03361866679042578, "grad_norm": 0.11348108947277069, "invalid_tail_samples": 23.8, "learning_rate": 6.629230378761415e-05, "loss": 0.0371, "positive_teacher_pairs": 26848.5, "relation_loss": 0.0034920216770842672, "selected_pairs": 26848.5, "step": 12740, "student_distance_mean": 1161.3252319335938, "teacher_distance_mean": 0.8555347263813019, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0034920216770842672, "weighted_relation_loss": 0.0034920216770842672 }, { "action_query_batch_std": 20.44229335784912, "action_query_norm": 883.3403625488281, "action_relation_loss": 0.0034778963075950743, "auxiliary_loss_weight": 1.0, "epoch": 11.927034611786716, "flow_matching_loss": 0.032339909486472605, "grad_norm": 0.10198213160037994, "invalid_tail_samples": 25.0, "learning_rate": 6.624018629579581e-05, "loss": 0.0358, "positive_teacher_pairs": 26568.8, "relation_loss": 0.0034778963075950743, "selected_pairs": 26568.8, "step": 12750, "student_distance_mean": 1163.322314453125, "teacher_distance_mean": 0.8539229691028595, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0034778963075950743, "weighted_relation_loss": 0.0034778963075950743 }, { "action_query_batch_std": 20.66932315826416, "action_query_norm": 892.4844604492188, "action_relation_loss": 0.0034522694535553456, "auxiliary_loss_weight": 1.0, "epoch": 11.936389148737138, "flow_matching_loss": 0.03515053186565638, "grad_norm": 0.12846186757087708, "invalid_tail_samples": 23.2, "learning_rate": 6.618804907061976e-05, "loss": 0.0386, "positive_teacher_pairs": 26992.3, "relation_loss": 0.0034522694535553456, "selected_pairs": 26992.3, "step": 12760, "student_distance_mean": 1177.35361328125, "teacher_distance_mean": 0.8688903987407685, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0034522694535553456, "weighted_relation_loss": 0.0034522694535553456 }, { "action_query_batch_std": 20.379445457458495, "action_query_norm": 877.44716796875, "action_relation_loss": 0.003560891165398061, "auxiliary_loss_weight": 1.0, "epoch": 11.945743685687559, "flow_matching_loss": 0.03318620212376118, "grad_norm": 0.12138466536998749, "invalid_tail_samples": 24.4, "learning_rate": 6.613589217543766e-05, "loss": 0.0367, "positive_teacher_pairs": 26709.7, "relation_loss": 0.003560891165398061, "selected_pairs": 26709.7, "step": 12770, "student_distance_mean": 1161.4460083007812, "teacher_distance_mean": 0.8574809849262237, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.003560891165398061, "weighted_relation_loss": 0.003560891165398061 }, { "action_query_batch_std": 20.226174926757814, "action_query_norm": 871.4803161621094, "action_relation_loss": 0.0034502563066780567, "auxiliary_loss_weight": 1.0, "epoch": 11.955098222637979, "flow_matching_loss": 0.033332146145403384, "grad_norm": 0.10164520889520645, "invalid_tail_samples": 25.4, "learning_rate": 6.608371567362504e-05, "loss": 0.0368, "positive_teacher_pairs": 26477.0, "relation_loss": 0.0034502563066780567, "selected_pairs": 26477.0, "step": 12780, "student_distance_mean": 1153.0420654296875, "teacher_distance_mean": 0.8557636618614197, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.0034502563066780567, "weighted_relation_loss": 0.0034502563066780567 }, { "action_query_batch_std": 20.44212989807129, "action_query_norm": 883.8136474609375, "action_relation_loss": 0.003436145791783929, "auxiliary_loss_weight": 1.0, "epoch": 11.9644527595884, "flow_matching_loss": 0.03339252155274153, "grad_norm": 0.13573713600635529, "invalid_tail_samples": 25.2, "learning_rate": 6.60315196285813e-05, "loss": 0.0368, "positive_teacher_pairs": 26526.1, "relation_loss": 0.003436145791783929, "selected_pairs": 26526.1, "step": 12790, "student_distance_mean": 1169.2539184570312, "teacher_distance_mean": 0.8512098848819732, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.003436145791783929, "weighted_relation_loss": 0.003436145791783929 }, { "action_query_batch_std": 20.364150047302246, "action_query_norm": 881.0368835449219, "action_relation_loss": 0.0033836822491139173, "auxiliary_loss_weight": 1.0, "epoch": 11.973807296538821, "flow_matching_loss": 0.03324673939496279, "grad_norm": 0.1524134874343872, "invalid_tail_samples": 26.7, "learning_rate": 6.597930410372954e-05, "loss": 0.0366, "positive_teacher_pairs": 26178.8, "relation_loss": 0.0033836822491139173, "selected_pairs": 26178.8, "step": 12800, "student_distance_mean": 1163.0321411132813, "teacher_distance_mean": 0.8484682381153107, "valid_action_samples": 229.3, "weighted_auxiliary_loss": 0.0033836822491139173, "weighted_relation_loss": 0.0033836822491139173 }, { "action_query_batch_std": 20.412503814697267, "action_query_norm": 876.930224609375, "action_relation_loss": 0.0034043407067656517, "auxiliary_loss_weight": 1.0, "epoch": 11.983161833489243, "flow_matching_loss": 0.03369931727647781, "grad_norm": 0.1376376897096634, "invalid_tail_samples": 24.9, "learning_rate": 6.592706916251653e-05, "loss": 0.0371, "positive_teacher_pairs": 26595.4, "relation_loss": 0.0034043407067656517, "selected_pairs": 26595.4, "step": 12810, "student_distance_mean": 1159.1878784179687, "teacher_distance_mean": 0.8555446863174438, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0034043407067656517, "weighted_relation_loss": 0.0034043407067656517 }, { "action_query_batch_std": 20.603950119018556, "action_query_norm": 888.4771911621094, "action_relation_loss": 0.0033815318951383234, "auxiliary_loss_weight": 1.0, "epoch": 11.992516370439663, "flow_matching_loss": 0.03559381179511547, "grad_norm": 0.13074332475662231, "invalid_tail_samples": 20.6, "learning_rate": 6.587481486841267e-05, "loss": 0.039, "positive_teacher_pairs": 27595.8, "relation_loss": 0.0033815318951383234, "selected_pairs": 27595.8, "step": 12820, "student_distance_mean": 1172.1366455078125, "teacher_distance_mean": 0.8645118772983551, "valid_action_samples": 235.4, "weighted_auxiliary_loss": 0.0033815318951383234, "weighted_relation_loss": 0.0033815318951383234 }, { "action_query_batch_std": 20.28261032104492, "action_query_norm": 876.4689758300781, "action_relation_loss": 0.003519591293297708, "auxiliary_loss_weight": 1.0, "epoch": 12.001870907390083, "flow_matching_loss": 0.03339927364140749, "grad_norm": 0.09833227097988129, "invalid_tail_samples": 21.0, "learning_rate": 6.582254128491184e-05, "loss": 0.0369, "positive_teacher_pairs": 24547.5, "relation_loss": 0.003519591293297708, "selected_pairs": 24547.5, "step": 12830, "student_distance_mean": 1162.7644287109374, "teacher_distance_mean": 0.862897390127182, "valid_action_samples": 215.1, "weighted_auxiliary_loss": 0.003519591293297708, "weighted_relation_loss": 0.003519591293297708 }, { "action_query_batch_std": 20.321905517578124, "action_query_norm": 877.7410217285156, "action_relation_loss": 0.003508942178450525, "auxiliary_loss_weight": 1.0, "epoch": 12.011225444340505, "flow_matching_loss": 0.03283488806337118, "grad_norm": 0.11231353878974915, "invalid_tail_samples": 23.7, "learning_rate": 6.577024847553139e-05, "loss": 0.0363, "positive_teacher_pairs": 26880.0, "relation_loss": 0.003508942178450525, "selected_pairs": 26880.0, "step": 12840, "student_distance_mean": 1159.0980834960938, "teacher_distance_mean": 0.8522614657878875, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.003508942178450525, "weighted_relation_loss": 0.003508942178450525 }, { "action_query_batch_std": 20.36905460357666, "action_query_norm": 880.5125, "action_relation_loss": 0.00353316399268806, "auxiliary_loss_weight": 1.0, "epoch": 12.020579981290926, "flow_matching_loss": 0.0321046132594347, "grad_norm": 0.14604057371616364, "invalid_tail_samples": 22.2, "learning_rate": 6.571793650381201e-05, "loss": 0.0356, "positive_teacher_pairs": 27223.7, "relation_loss": 0.00353316399268806, "selected_pairs": 27223.7, "step": 12850, "student_distance_mean": 1164.1670654296875, "teacher_distance_mean": 0.8572782814502716, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.00353316399268806, "weighted_relation_loss": 0.00353316399268806 }, { "action_query_batch_std": 20.367016410827638, "action_query_norm": 877.7543884277344, "action_relation_loss": 0.003439441253431141, "auxiliary_loss_weight": 1.0, "epoch": 12.029934518241348, "flow_matching_loss": 0.033965341933071616, "grad_norm": 0.17482946813106537, "invalid_tail_samples": 24.0, "learning_rate": 6.566560543331766e-05, "loss": 0.0374, "positive_teacher_pairs": 26802.0, "relation_loss": 0.003439441253431141, "selected_pairs": 26802.0, "step": 12860, "student_distance_mean": 1162.9355590820312, "teacher_distance_mean": 0.8496082186698913, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.003439441253431141, "weighted_relation_loss": 0.003439441253431141 }, { "action_query_batch_std": 20.717203903198243, "action_query_norm": 894.00361328125, "action_relation_loss": 0.0032486631302163006, "auxiliary_loss_weight": 1.0, "epoch": 12.039289055191768, "flow_matching_loss": 0.03235650323331356, "grad_norm": 0.09967228025197983, "invalid_tail_samples": 23.7, "learning_rate": 6.561325532763554e-05, "loss": 0.0356, "positive_teacher_pairs": 26877.0, "relation_loss": 0.0032486631302163006, "selected_pairs": 26877.0, "step": 12870, "student_distance_mean": 1176.7023803710938, "teacher_distance_mean": 0.8593826591968536, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0032486631302163006, "weighted_relation_loss": 0.0032486631302163006 }, { "action_query_batch_std": 20.543979263305665, "action_query_norm": 887.7929443359375, "action_relation_loss": 0.0033239805372431873, "auxiliary_loss_weight": 1.0, "epoch": 12.04864359214219, "flow_matching_loss": 0.03384349066764116, "grad_norm": 0.14654240012168884, "invalid_tail_samples": 23.5, "learning_rate": 6.556088625037597e-05, "loss": 0.0372, "positive_teacher_pairs": 26921.9, "relation_loss": 0.0033239805372431873, "selected_pairs": 26921.9, "step": 12880, "student_distance_mean": 1176.11318359375, "teacher_distance_mean": 0.8600747942924499, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0033239805372431873, "weighted_relation_loss": 0.0033239805372431873 }, { "action_query_batch_std": 20.58436336517334, "action_query_norm": 890.4601989746094, "action_relation_loss": 0.0033626215532422065, "auxiliary_loss_weight": 1.0, "epoch": 12.05799812909261, "flow_matching_loss": 0.03216491062194109, "grad_norm": 0.11057869344949722, "invalid_tail_samples": 24.5, "learning_rate": 6.55084982651723e-05, "loss": 0.0355, "positive_teacher_pairs": 26688.2, "relation_loss": 0.0033626215532422065, "selected_pairs": 26688.2, "step": 12890, "student_distance_mean": 1174.7050170898438, "teacher_distance_mean": 0.8572936415672302, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0033626215532422065, "weighted_relation_loss": 0.0033626215532422065 }, { "action_query_batch_std": 20.347587966918944, "action_query_norm": 884.8257995605469, "action_relation_loss": 0.0032414188608527184, "auxiliary_loss_weight": 1.0, "epoch": 12.06735266604303, "flow_matching_loss": 0.03287655487656593, "grad_norm": 0.091469407081604, "invalid_tail_samples": 22.2, "learning_rate": 6.54560914356809e-05, "loss": 0.0361, "positive_teacher_pairs": 27220.9, "relation_loss": 0.0032414188608527184, "selected_pairs": 27220.9, "step": 12900, "student_distance_mean": 1161.36591796875, "teacher_distance_mean": 0.8473742187023163, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.0032414188608527184, "weighted_relation_loss": 0.0032414188608527184 }, { "action_query_batch_std": 20.539980316162108, "action_query_norm": 889.752490234375, "action_relation_loss": 0.00350376486312598, "auxiliary_loss_weight": 1.0, "epoch": 12.076707202993452, "flow_matching_loss": 0.032161237113177775, "grad_norm": 0.10794071853160858, "invalid_tail_samples": 25.4, "learning_rate": 6.540366582558097e-05, "loss": 0.0357, "positive_teacher_pairs": 26476.0, "relation_loss": 0.00350376486312598, "selected_pairs": 26476.0, "step": 12910, "student_distance_mean": 1173.79658203125, "teacher_distance_mean": 0.8546046793460846, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.00350376486312598, "weighted_relation_loss": 0.00350376486312598 }, { "action_query_batch_std": 20.411302757263183, "action_query_norm": 881.9585754394532, "action_relation_loss": 0.0032978862756863235, "auxiliary_loss_weight": 1.0, "epoch": 12.086061739943872, "flow_matching_loss": 0.03677739500999451, "grad_norm": 0.12007571756839752, "invalid_tail_samples": 25.0, "learning_rate": 6.53512214985746e-05, "loss": 0.0401, "positive_teacher_pairs": 26573.0, "relation_loss": 0.0032978862756863235, "selected_pairs": 26573.0, "step": 12920, "student_distance_mean": 1164.1009887695313, "teacher_distance_mean": 0.8514582991600037, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0032978862756863235, "weighted_relation_loss": 0.0032978862756863235 }, { "action_query_batch_std": 20.666051292419432, "action_query_norm": 894.9750793457031, "action_relation_loss": 0.0033418382285162807, "auxiliary_loss_weight": 1.0, "epoch": 12.095416276894294, "flow_matching_loss": 0.032530890218913554, "grad_norm": 0.11968544870615005, "invalid_tail_samples": 20.6, "learning_rate": 6.529875851838658e-05, "loss": 0.0359, "positive_teacher_pairs": 27602.7, "relation_loss": 0.0033418382285162807, "selected_pairs": 27602.7, "step": 12930, "student_distance_mean": 1180.5067138671875, "teacher_distance_mean": 0.8590914368629455, "valid_action_samples": 235.4, "weighted_auxiliary_loss": 0.0033418382285162807, "weighted_relation_loss": 0.0033418382285162807 }, { "action_query_batch_std": 20.824561882019044, "action_query_norm": 897.608203125, "action_relation_loss": 0.0033804868115112187, "auxiliary_loss_weight": 1.0, "epoch": 12.104770813844715, "flow_matching_loss": 0.03328524641692639, "grad_norm": 0.11506833136081696, "invalid_tail_samples": 21.3, "learning_rate": 6.52462769487644e-05, "loss": 0.0367, "positive_teacher_pairs": 27436.1, "relation_loss": 0.0033804868115112187, "selected_pairs": 27436.1, "step": 12940, "student_distance_mean": 1189.363134765625, "teacher_distance_mean": 0.8584594368934632, "valid_action_samples": 234.7, "weighted_auxiliary_loss": 0.0033804868115112187, "weighted_relation_loss": 0.0033804868115112187 }, { "action_query_batch_std": 20.738944816589356, "action_query_norm": 895.2107666015625, "action_relation_loss": 0.0032924351748079062, "auxiliary_loss_weight": 1.0, "epoch": 12.114125350795135, "flow_matching_loss": 0.03223082404583692, "grad_norm": 0.10049574077129364, "invalid_tail_samples": 21.7, "learning_rate": 6.519377685347807e-05, "loss": 0.0355, "positive_teacher_pairs": 27340.1, "relation_loss": 0.0032924351748079062, "selected_pairs": 27340.1, "step": 12950, "student_distance_mean": 1185.8934326171875, "teacher_distance_mean": 0.8601427674293518, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.0032924351748079062, "weighted_relation_loss": 0.0032924351748079062 }, { "action_query_batch_std": 20.182345390319824, "action_query_norm": 873.6677551269531, "action_relation_loss": 0.003439114219509065, "auxiliary_loss_weight": 1.0, "epoch": 12.123479887745557, "flow_matching_loss": 0.030555295571684838, "grad_norm": 0.10436500608921051, "invalid_tail_samples": 26.4, "learning_rate": 6.514125829632021e-05, "loss": 0.034, "positive_teacher_pairs": 26253.3, "relation_loss": 0.003439114219509065, "selected_pairs": 26253.3, "step": 12960, "student_distance_mean": 1151.510400390625, "teacher_distance_mean": 0.8406302034854889, "valid_action_samples": 229.6, "weighted_auxiliary_loss": 0.003439114219509065, "weighted_relation_loss": 0.003439114219509065 }, { "action_query_batch_std": 20.85886459350586, "action_query_norm": 899.5230407714844, "action_relation_loss": 0.003193001728504896, "auxiliary_loss_weight": 1.0, "epoch": 12.132834424695977, "flow_matching_loss": 0.03185986801981926, "grad_norm": 0.1509115993976593, "invalid_tail_samples": 24.3, "learning_rate": 6.508872134110577e-05, "loss": 0.0351, "positive_teacher_pairs": 26734.1, "relation_loss": 0.003193001728504896, "selected_pairs": 26734.1, "step": 12970, "student_distance_mean": 1184.097265625, "teacher_distance_mean": 0.8559429943561554, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.003193001728504896, "weighted_relation_loss": 0.003193001728504896 }, { "action_query_batch_std": 20.33516025543213, "action_query_norm": 881.729541015625, "action_relation_loss": 0.0032718841917812823, "auxiliary_loss_weight": 1.0, "epoch": 12.142188961646399, "flow_matching_loss": 0.03407932780683041, "grad_norm": 0.08832009881734848, "invalid_tail_samples": 22.0, "learning_rate": 6.503616605167213e-05, "loss": 0.0374, "positive_teacher_pairs": 27276.7, "relation_loss": 0.0032718841917812823, "selected_pairs": 27276.7, "step": 12980, "student_distance_mean": 1160.8949584960938, "teacher_distance_mean": 0.8398965895175934, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.0032718841917812823, "weighted_relation_loss": 0.0032718841917812823 }, { "action_query_batch_std": 20.78995876312256, "action_query_norm": 893.3612976074219, "action_relation_loss": 0.0033415159210562705, "auxiliary_loss_weight": 1.0, "epoch": 12.15154349859682, "flow_matching_loss": 0.03239457178860903, "grad_norm": 0.11879326403141022, "invalid_tail_samples": 23.3, "learning_rate": 6.498359249187893e-05, "loss": 0.0357, "positive_teacher_pairs": 26964.9, "relation_loss": 0.0033415159210562705, "selected_pairs": 26964.9, "step": 12990, "student_distance_mean": 1186.4409912109375, "teacher_distance_mean": 0.8635129392147064, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0033415159210562705, "weighted_relation_loss": 0.0033415159210562705 }, { "action_query_batch_std": 20.483803939819335, "action_query_norm": 888.0366638183593, "action_relation_loss": 0.0032149281818419696, "auxiliary_loss_weight": 1.0, "epoch": 12.160898035547241, "flow_matching_loss": 0.03125240281224251, "grad_norm": 0.10169745981693268, "invalid_tail_samples": 23.0, "learning_rate": 6.493100072560799e-05, "loss": 0.0345, "positive_teacher_pairs": 27036.2, "relation_loss": 0.0032149281818419696, "selected_pairs": 27036.2, "step": 13000, "student_distance_mean": 1170.6435791015624, "teacher_distance_mean": 0.8504546046257019, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0032149281818419696, "weighted_relation_loss": 0.0032149281818419696 }, { "action_query_batch_std": 20.193958854675294, "action_query_norm": 878.8971618652344, "action_relation_loss": 0.003415149240754545, "auxiliary_loss_weight": 1.0, "epoch": 12.170252572497661, "flow_matching_loss": 0.0320002157241106, "grad_norm": 0.09596474468708038, "invalid_tail_samples": 21.8, "learning_rate": 6.487839081676327e-05, "loss": 0.0354, "positive_teacher_pairs": 27311.5, "relation_loss": 0.003415149240754545, "selected_pairs": 27311.5, "step": 13010, "student_distance_mean": 1152.8040405273437, "teacher_distance_mean": 0.8400427341461182, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.003415149240754545, "weighted_relation_loss": 0.003415149240754545 }, { "action_query_batch_std": 20.418687057495116, "action_query_norm": 885.3315612792969, "action_relation_loss": 0.003395830048248172, "auxiliary_loss_weight": 1.0, "epoch": 12.179607109448082, "flow_matching_loss": 0.032242726534605026, "grad_norm": 0.12475771456956863, "invalid_tail_samples": 25.4, "learning_rate": 6.482576282927076e-05, "loss": 0.0356, "positive_teacher_pairs": 26485.3, "relation_loss": 0.003395830048248172, "selected_pairs": 26485.3, "step": 13020, "student_distance_mean": 1163.889794921875, "teacher_distance_mean": 0.8485021829605103, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.003395830048248172, "weighted_relation_loss": 0.003395830048248172 }, { "action_query_batch_std": 20.322066879272462, "action_query_norm": 883.1898864746094, "action_relation_loss": 0.0032425707671791316, "auxiliary_loss_weight": 1.0, "epoch": 12.188961646398504, "flow_matching_loss": 0.030943810380995272, "grad_norm": 0.14712117612361908, "invalid_tail_samples": 24.1, "learning_rate": 6.477311682707845e-05, "loss": 0.0342, "positive_teacher_pairs": 26778.8, "relation_loss": 0.0032425707671791316, "selected_pairs": 26778.8, "step": 13030, "student_distance_mean": 1164.2379150390625, "teacher_distance_mean": 0.8520699143409729, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0032425707671791316, "weighted_relation_loss": 0.0032425707671791316 }, { "action_query_batch_std": 20.32218780517578, "action_query_norm": 880.1274169921875, "action_relation_loss": 0.0031892932718619706, "auxiliary_loss_weight": 1.0, "epoch": 12.198316183348924, "flow_matching_loss": 0.032733823731541635, "grad_norm": 0.12718212604522705, "invalid_tail_samples": 24.2, "learning_rate": 6.472045287415616e-05, "loss": 0.0359, "positive_teacher_pairs": 26755.5, "relation_loss": 0.0031892932718619706, "selected_pairs": 26755.5, "step": 13040, "student_distance_mean": 1163.2827758789062, "teacher_distance_mean": 0.851539534330368, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0031892932718619706, "weighted_relation_loss": 0.0031892932718619706 }, { "action_query_batch_std": 20.474855422973633, "action_query_norm": 884.6267456054687, "action_relation_loss": 0.0031282625393942, "auxiliary_loss_weight": 1.0, "epoch": 12.207670720299346, "flow_matching_loss": 0.030833078548312187, "grad_norm": 0.17684480547904968, "invalid_tail_samples": 22.3, "learning_rate": 6.466777103449558e-05, "loss": 0.034, "positive_teacher_pairs": 27207.5, "relation_loss": 0.0031282625393942, "selected_pairs": 27207.5, "step": 13050, "student_distance_mean": 1164.636962890625, "teacher_distance_mean": 0.8498904824256897, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0031282625393942, "weighted_relation_loss": 0.0031282625393942 }, { "action_query_batch_std": 20.776566314697266, "action_query_norm": 894.9105834960938, "action_relation_loss": 0.003229494672268629, "auxiliary_loss_weight": 1.0, "epoch": 12.217025257249766, "flow_matching_loss": 0.03155078385025263, "grad_norm": 0.13936716318130493, "invalid_tail_samples": 22.4, "learning_rate": 6.461507137211012e-05, "loss": 0.0348, "positive_teacher_pairs": 27175.2, "relation_loss": 0.003229494672268629, "selected_pairs": 27175.2, "step": 13060, "student_distance_mean": 1183.12958984375, "teacher_distance_mean": 0.8623003304004669, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.003229494672268629, "weighted_relation_loss": 0.003229494672268629 }, { "action_query_batch_std": 20.845541381835936, "action_query_norm": 894.8314758300781, "action_relation_loss": 0.003182334289886057, "auxiliary_loss_weight": 1.0, "epoch": 12.226379794200188, "flow_matching_loss": 0.03309846818447113, "grad_norm": 0.14986933767795563, "invalid_tail_samples": 22.1, "learning_rate": 6.456235395103483e-05, "loss": 0.0363, "positive_teacher_pairs": 27244.8, "relation_loss": 0.003182334289886057, "selected_pairs": 27244.8, "step": 13070, "student_distance_mean": 1182.4671142578125, "teacher_distance_mean": 0.8652443170547486, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.003182334289886057, "weighted_relation_loss": 0.003182334289886057 }, { "action_query_batch_std": 20.2530237197876, "action_query_norm": 876.8053527832031, "action_relation_loss": 0.0032377061201259495, "auxiliary_loss_weight": 1.0, "epoch": 12.235734331150608, "flow_matching_loss": 0.03044985868036747, "grad_norm": 0.14318984746932983, "invalid_tail_samples": 24.7, "learning_rate": 6.450961883532634e-05, "loss": 0.0337, "positive_teacher_pairs": 26650.8, "relation_loss": 0.0032377061201259495, "selected_pairs": 26650.8, "step": 13080, "student_distance_mean": 1158.2362182617187, "teacher_distance_mean": 0.8446080625057221, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0032377061201259495, "weighted_relation_loss": 0.0032377061201259495 }, { "action_query_batch_std": 20.450509452819823, "action_query_norm": 880.3805969238281, "action_relation_loss": 0.003280391008593142, "auxiliary_loss_weight": 1.0, "epoch": 12.245088868101028, "flow_matching_loss": 0.032406211271882056, "grad_norm": 0.1455775648355484, "invalid_tail_samples": 26.1, "learning_rate": 6.445686608906283e-05, "loss": 0.0357, "positive_teacher_pairs": 26325.9, "relation_loss": 0.003280391008593142, "selected_pairs": 26325.9, "step": 13090, "student_distance_mean": 1173.0534912109374, "teacher_distance_mean": 0.8583576202392578, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.003280391008593142, "weighted_relation_loss": 0.003280391008593142 }, { "action_query_batch_std": 20.321035385131836, "action_query_norm": 880.7415893554687, "action_relation_loss": 0.0033729909220710395, "auxiliary_loss_weight": 1.0, "epoch": 12.25444340505145, "flow_matching_loss": 0.032859604246914385, "grad_norm": 0.11707647889852524, "invalid_tail_samples": 23.0, "learning_rate": 6.44040957763438e-05, "loss": 0.0362, "positive_teacher_pairs": 27033.9, "relation_loss": 0.0033729909220710395, "selected_pairs": 27033.9, "step": 13100, "student_distance_mean": 1155.637939453125, "teacher_distance_mean": 0.8408303737640381, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0033729909220710395, "weighted_relation_loss": 0.0033729909220710395 }, { "action_query_batch_std": 20.49653606414795, "action_query_norm": 889.0798583984375, "action_relation_loss": 0.0032921819481998684, "auxiliary_loss_weight": 1.0, "epoch": 12.26379794200187, "flow_matching_loss": 0.03305890392512083, "grad_norm": 0.1362442672252655, "invalid_tail_samples": 25.6, "learning_rate": 6.435130796129018e-05, "loss": 0.0364, "positive_teacher_pairs": 26436.6, "relation_loss": 0.0032921819481998684, "selected_pairs": 26436.6, "step": 13110, "student_distance_mean": 1175.5215698242187, "teacher_distance_mean": 0.8560683727264404, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.0032921819481998684, "weighted_relation_loss": 0.0032921819481998684 }, { "action_query_batch_std": 20.546737670898438, "action_query_norm": 886.7660217285156, "action_relation_loss": 0.0031974542886018752, "auxiliary_loss_weight": 1.0, "epoch": 12.273152478952293, "flow_matching_loss": 0.03425378482788801, "grad_norm": 0.12667416036128998, "invalid_tail_samples": 25.3, "learning_rate": 6.429850270804416e-05, "loss": 0.0375, "positive_teacher_pairs": 26513.1, "relation_loss": 0.0031974542886018752, "selected_pairs": 26513.1, "step": 13120, "student_distance_mean": 1175.0760131835937, "teacher_distance_mean": 0.8559604167938233, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0031974542886018752, "weighted_relation_loss": 0.0031974542886018752 }, { "action_query_batch_std": 20.68188190460205, "action_query_norm": 892.1188049316406, "action_relation_loss": 0.003188821952790022, "auxiliary_loss_weight": 1.0, "epoch": 12.282507015902713, "flow_matching_loss": 0.033381787873804566, "grad_norm": 0.13149939477443695, "invalid_tail_samples": 22.7, "learning_rate": 6.424568008076909e-05, "loss": 0.0366, "positive_teacher_pairs": 27102.7, "relation_loss": 0.003188821952790022, "selected_pairs": 27102.7, "step": 13130, "student_distance_mean": 1180.9015380859375, "teacher_distance_mean": 0.8612931966781616, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.003188821952790022, "weighted_relation_loss": 0.003188821952790022 }, { "action_query_batch_std": 20.393787956237794, "action_query_norm": 881.4780090332031, "action_relation_loss": 0.0032948305364698172, "auxiliary_loss_weight": 1.0, "epoch": 12.291861552853133, "flow_matching_loss": 0.03223831243813038, "grad_norm": 0.11093143373727798, "invalid_tail_samples": 24.1, "learning_rate": 6.419284014364943e-05, "loss": 0.0355, "positive_teacher_pairs": 26779.5, "relation_loss": 0.0032948305364698172, "selected_pairs": 26779.5, "step": 13140, "student_distance_mean": 1162.530908203125, "teacher_distance_mean": 0.8564020574092865, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0032948305364698172, "weighted_relation_loss": 0.0032948305364698172 }, { "action_query_batch_std": 20.521364974975587, "action_query_norm": 883.4873901367188, "action_relation_loss": 0.0031581987626850606, "auxiliary_loss_weight": 1.0, "epoch": 12.301216089803555, "flow_matching_loss": 0.030856455862522125, "grad_norm": 0.10583759099245071, "invalid_tail_samples": 24.2, "learning_rate": 6.41399829608907e-05, "loss": 0.034, "positive_teacher_pairs": 26763.6, "relation_loss": 0.0031581987626850606, "selected_pairs": 26763.6, "step": 13150, "student_distance_mean": 1170.2491943359375, "teacher_distance_mean": 0.8663534820079803, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0031581987626850606, "weighted_relation_loss": 0.0031581987626850606 }, { "action_query_batch_std": 20.53639945983887, "action_query_norm": 887.4285583496094, "action_relation_loss": 0.0033676004968583584, "auxiliary_loss_weight": 1.0, "epoch": 12.310570626753975, "flow_matching_loss": 0.032453146763145924, "grad_norm": 0.1422176957130432, "invalid_tail_samples": 21.5, "learning_rate": 6.408710859671938e-05, "loss": 0.0358, "positive_teacher_pairs": 27382.1, "relation_loss": 0.0033676004968583584, "selected_pairs": 27382.1, "step": 13160, "student_distance_mean": 1173.7369018554687, "teacher_distance_mean": 0.8547034144401551, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.0033676004968583584, "weighted_relation_loss": 0.0033676004968583584 }, { "action_query_batch_std": 20.573102760314942, "action_query_norm": 887.8498901367187, "action_relation_loss": 0.0033192568458616733, "auxiliary_loss_weight": 1.0, "epoch": 12.319925163704397, "flow_matching_loss": 0.03484168946743012, "grad_norm": 0.1727461963891983, "invalid_tail_samples": 23.0, "learning_rate": 6.403421711538278e-05, "loss": 0.0382, "positive_teacher_pairs": 27035.4, "relation_loss": 0.0033192568458616733, "selected_pairs": 27035.4, "step": 13170, "student_distance_mean": 1171.2340698242188, "teacher_distance_mean": 0.8515196740627289, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0033192568458616733, "weighted_relation_loss": 0.0033192568458616733 }, { "action_query_batch_std": 20.513948249816895, "action_query_norm": 884.369970703125, "action_relation_loss": 0.0033896447159349917, "auxiliary_loss_weight": 1.0, "epoch": 12.329279700654817, "flow_matching_loss": 0.03384239766746759, "grad_norm": 0.12442847341299057, "invalid_tail_samples": 23.5, "learning_rate": 6.398130858114903e-05, "loss": 0.0372, "positive_teacher_pairs": 26919.8, "relation_loss": 0.0033896447159349917, "selected_pairs": 26919.8, "step": 13180, "student_distance_mean": 1173.5286499023437, "teacher_distance_mean": 0.8583630204200745, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0033896447159349917, "weighted_relation_loss": 0.0033896447159349917 }, { "action_query_batch_std": 20.81293716430664, "action_query_norm": 893.5422485351562, "action_relation_loss": 0.0032406649086624386, "auxiliary_loss_weight": 1.0, "epoch": 12.33863423760524, "flow_matching_loss": 0.03277097176760435, "grad_norm": 0.12104202061891556, "invalid_tail_samples": 23.9, "learning_rate": 6.392838305830701e-05, "loss": 0.036, "positive_teacher_pairs": 26835.9, "relation_loss": 0.0032406649086624386, "selected_pairs": 26835.9, "step": 13190, "student_distance_mean": 1184.7953002929687, "teacher_distance_mean": 0.8657506465911865, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0032406649086624386, "weighted_relation_loss": 0.0032406649086624386 }, { "action_query_batch_std": 20.464466094970703, "action_query_norm": 885.0148986816406, "action_relation_loss": 0.0034428372047841547, "auxiliary_loss_weight": 1.0, "epoch": 12.34798877455566, "flow_matching_loss": 0.03308164719492197, "grad_norm": 0.1271023452281952, "invalid_tail_samples": 23.6, "learning_rate": 6.387544061116621e-05, "loss": 0.0365, "positive_teacher_pairs": 26901.6, "relation_loss": 0.0034428372047841547, "selected_pairs": 26901.6, "step": 13200, "student_distance_mean": 1167.1421752929687, "teacher_distance_mean": 0.8476172685623169, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0034428372047841547, "weighted_relation_loss": 0.0034428372047841547 }, { "action_query_batch_std": 20.20393924713135, "action_query_norm": 875.5506652832031, "action_relation_loss": 0.0033148692222312094, "auxiliary_loss_weight": 1.0, "epoch": 12.35734331150608, "flow_matching_loss": 0.03159365262836218, "grad_norm": 0.10750434547662735, "invalid_tail_samples": 24.1, "learning_rate": 6.382248130405671e-05, "loss": 0.0349, "positive_teacher_pairs": 26781.2, "relation_loss": 0.0033148692222312094, "selected_pairs": 26781.2, "step": 13210, "student_distance_mean": 1158.18330078125, "teacher_distance_mean": 0.8472536385059357, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0033148692222312094, "weighted_relation_loss": 0.0033148692222312094 }, { "action_query_batch_std": 20.48923683166504, "action_query_norm": 883.4708190917969, "action_relation_loss": 0.003367645526304841, "auxiliary_loss_weight": 1.0, "epoch": 12.366697848456502, "flow_matching_loss": 0.031577021814882755, "grad_norm": 0.10492455959320068, "invalid_tail_samples": 27.3, "learning_rate": 6.376950520132905e-05, "loss": 0.0349, "positive_teacher_pairs": 26045.0, "relation_loss": 0.003367645526304841, "selected_pairs": 26045.0, "step": 13220, "student_distance_mean": 1169.3419555664063, "teacher_distance_mean": 0.8525663673877716, "valid_action_samples": 228.7, "weighted_auxiliary_loss": 0.003367645526304841, "weighted_relation_loss": 0.003367645526304841 }, { "action_query_batch_std": 20.59247245788574, "action_query_norm": 889.1714721679688, "action_relation_loss": 0.0032667977269738913, "auxiliary_loss_weight": 1.0, "epoch": 12.376052385406922, "flow_matching_loss": 0.03148736208677292, "grad_norm": 0.1062319278717041, "invalid_tail_samples": 21.3, "learning_rate": 6.371651236735418e-05, "loss": 0.0348, "positive_teacher_pairs": 27433.1, "relation_loss": 0.0032667977269738913, "selected_pairs": 27433.1, "step": 13230, "student_distance_mean": 1175.177099609375, "teacher_distance_mean": 0.8561501860618591, "valid_action_samples": 234.7, "weighted_auxiliary_loss": 0.0032667977269738913, "weighted_relation_loss": 0.0032667977269738913 }, { "action_query_batch_std": 20.758175468444826, "action_query_norm": 889.3065368652344, "action_relation_loss": 0.0032436370849609373, "auxiliary_loss_weight": 1.0, "epoch": 12.385406922357344, "flow_matching_loss": 0.03233881685882807, "grad_norm": 0.10579712688922882, "invalid_tail_samples": 27.0, "learning_rate": 6.366350286652341e-05, "loss": 0.0356, "positive_teacher_pairs": 26117.2, "relation_loss": 0.0032436370849609373, "selected_pairs": 26117.2, "step": 13240, "student_distance_mean": 1179.6757446289062, "teacher_distance_mean": 0.8596866190433502, "valid_action_samples": 229.0, "weighted_auxiliary_loss": 0.0032436370849609373, "weighted_relation_loss": 0.0032436370849609373 }, { "action_query_batch_std": 20.656482124328612, "action_query_norm": 889.0808898925782, "action_relation_loss": 0.0032114753033965827, "auxiliary_loss_weight": 1.0, "epoch": 12.394761459307764, "flow_matching_loss": 0.032274080067873, "grad_norm": 0.11256454139947891, "invalid_tail_samples": 24.6, "learning_rate": 6.361047676324827e-05, "loss": 0.0355, "positive_teacher_pairs": 26666.4, "relation_loss": 0.0032114753033965827, "selected_pairs": 26666.4, "step": 13250, "student_distance_mean": 1177.7515014648438, "teacher_distance_mean": 0.8610926687717437, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0032114753033965827, "weighted_relation_loss": 0.0032114753033965827 }, { "action_query_batch_std": 20.71258373260498, "action_query_norm": 885.9731994628906, "action_relation_loss": 0.003219246119260788, "auxiliary_loss_weight": 1.0, "epoch": 12.404115996258184, "flow_matching_loss": 0.03138664197176695, "grad_norm": 0.1059851199388504, "invalid_tail_samples": 25.5, "learning_rate": 6.355743412196047e-05, "loss": 0.0346, "positive_teacher_pairs": 26467.0, "relation_loss": 0.003219246119260788, "selected_pairs": 26467.0, "step": 13260, "student_distance_mean": 1184.5874755859375, "teacher_distance_mean": 0.8642558217048645, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.003219246119260788, "weighted_relation_loss": 0.003219246119260788 }, { "action_query_batch_std": 20.558775329589842, "action_query_norm": 885.5992065429688, "action_relation_loss": 0.003367033856920898, "auxiliary_loss_weight": 1.0, "epoch": 12.413470533208606, "flow_matching_loss": 0.03387720473110676, "grad_norm": 0.10015164315700531, "invalid_tail_samples": 25.1, "learning_rate": 6.350437500711184e-05, "loss": 0.0372, "positive_teacher_pairs": 26553.9, "relation_loss": 0.003367033856920898, "selected_pairs": 26553.9, "step": 13270, "student_distance_mean": 1173.2837280273438, "teacher_distance_mean": 0.8589188873767852, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.003367033856920898, "weighted_relation_loss": 0.003367033856920898 }, { "action_query_batch_std": 20.40701675415039, "action_query_norm": 882.3299194335938, "action_relation_loss": 0.003414997877553105, "auxiliary_loss_weight": 1.0, "epoch": 12.422825070159027, "flow_matching_loss": 0.032199453376233575, "grad_norm": 0.12674768269062042, "invalid_tail_samples": 23.0, "learning_rate": 6.345129948317418e-05, "loss": 0.0356, "positive_teacher_pairs": 27041.1, "relation_loss": 0.003414997877553105, "selected_pairs": 27041.1, "step": 13280, "student_distance_mean": 1159.1824340820312, "teacher_distance_mean": 0.852505213022232, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.003414997877553105, "weighted_relation_loss": 0.003414997877553105 }, { "action_query_batch_std": 20.557599830627442, "action_query_norm": 886.8914855957031, "action_relation_loss": 0.0032346034655347466, "auxiliary_loss_weight": 1.0, "epoch": 12.432179607109449, "flow_matching_loss": 0.03166639730334282, "grad_norm": 0.10157759487628937, "invalid_tail_samples": 25.1, "learning_rate": 6.33982076146393e-05, "loss": 0.0349, "positive_teacher_pairs": 26554.9, "relation_loss": 0.0032346034655347466, "selected_pairs": 26554.9, "step": 13290, "student_distance_mean": 1173.1536987304687, "teacher_distance_mean": 0.8592599868774414, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0032346034655347466, "weighted_relation_loss": 0.0032346034655347466 }, { "action_query_batch_std": 20.629824256896974, "action_query_norm": 886.1444641113281, "action_relation_loss": 0.0032095237635076045, "auxiliary_loss_weight": 1.0, "epoch": 12.441534144059869, "flow_matching_loss": 0.03200800884515047, "grad_norm": 0.10021866858005524, "invalid_tail_samples": 23.0, "learning_rate": 6.334509946601879e-05, "loss": 0.0352, "positive_teacher_pairs": 27034.5, "relation_loss": 0.0032095237635076045, "selected_pairs": 27034.5, "step": 13300, "student_distance_mean": 1173.8640502929688, "teacher_distance_mean": 0.8551376640796662, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0032095237635076045, "weighted_relation_loss": 0.0032095237635076045 }, { "action_query_batch_std": 20.40135974884033, "action_query_norm": 879.8558227539063, "action_relation_loss": 0.0033242804929614067, "auxiliary_loss_weight": 1.0, "epoch": 12.45088868101029, "flow_matching_loss": 0.0322354007512331, "grad_norm": 0.11791778355836868, "invalid_tail_samples": 24.5, "learning_rate": 6.329197510184406e-05, "loss": 0.0356, "positive_teacher_pairs": 26698.5, "relation_loss": 0.0033242804929614067, "selected_pairs": 26698.5, "step": 13310, "student_distance_mean": 1164.489794921875, "teacher_distance_mean": 0.8459551870822907, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0033242804929614067, "weighted_relation_loss": 0.0033242804929614067 }, { "action_query_batch_std": 20.561758041381836, "action_query_norm": 888.6129760742188, "action_relation_loss": 0.0032325739739462733, "auxiliary_loss_weight": 1.0, "epoch": 12.460243217960711, "flow_matching_loss": 0.032386746071279046, "grad_norm": 0.14605273306369781, "invalid_tail_samples": 25.6, "learning_rate": 6.323883458666624e-05, "loss": 0.0356, "positive_teacher_pairs": 26439.3, "relation_loss": 0.0032325739739462733, "selected_pairs": 26439.3, "step": 13320, "student_distance_mean": 1174.0083251953124, "teacher_distance_mean": 0.8561292827129364, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.0032325739739462733, "weighted_relation_loss": 0.0032325739739462733 }, { "action_query_batch_std": 20.569325065612794, "action_query_norm": 887.9291442871094, "action_relation_loss": 0.0032461675349622966, "auxiliary_loss_weight": 1.0, "epoch": 12.469597754911131, "flow_matching_loss": 0.03221430275589228, "grad_norm": 0.148890420794487, "invalid_tail_samples": 24.5, "learning_rate": 6.318567798505605e-05, "loss": 0.0355, "positive_teacher_pairs": 26685.4, "relation_loss": 0.0032461675349622966, "selected_pairs": 26685.4, "step": 13330, "student_distance_mean": 1172.9192016601562, "teacher_distance_mean": 0.8550348818302155, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0032461675349622966, "weighted_relation_loss": 0.0032461675349622966 }, { "action_query_batch_std": 20.906253623962403, "action_query_norm": 898.8227905273437, "action_relation_loss": 0.003345612925477326, "auxiliary_loss_weight": 1.0, "epoch": 12.478952291861553, "flow_matching_loss": 0.03449531886726618, "grad_norm": 0.14346501231193542, "invalid_tail_samples": 24.8, "learning_rate": 6.313250536160378e-05, "loss": 0.0378, "positive_teacher_pairs": 26621.0, "relation_loss": 0.003345612925477326, "selected_pairs": 26621.0, "step": 13340, "student_distance_mean": 1188.8773559570313, "teacher_distance_mean": 0.8640237271785736, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.003345612925477326, "weighted_relation_loss": 0.003345612925477326 }, { "action_query_batch_std": 20.56527786254883, "action_query_norm": 888.6127807617188, "action_relation_loss": 0.003182476502843201, "auxiliary_loss_weight": 1.0, "epoch": 12.488306828811973, "flow_matching_loss": 0.032497857697308064, "grad_norm": 0.11114102602005005, "invalid_tail_samples": 22.4, "learning_rate": 6.307931678091917e-05, "loss": 0.0357, "positive_teacher_pairs": 27183.3, "relation_loss": 0.003182476502843201, "selected_pairs": 27183.3, "step": 13350, "student_distance_mean": 1176.2593139648438, "teacher_distance_mean": 0.859494811296463, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.003182476502843201, "weighted_relation_loss": 0.003182476502843201 }, { "action_query_batch_std": 20.261274909973146, "action_query_norm": 879.3212951660156, "action_relation_loss": 0.00340457942802459, "auxiliary_loss_weight": 1.0, "epoch": 12.497661365762395, "flow_matching_loss": 0.030541226081550122, "grad_norm": 0.09756018966436386, "invalid_tail_samples": 23.7, "learning_rate": 6.302611230763138e-05, "loss": 0.0339, "positive_teacher_pairs": 26871.9, "relation_loss": 0.00340457942802459, "selected_pairs": 26871.9, "step": 13360, "student_distance_mean": 1159.1996337890625, "teacher_distance_mean": 0.8424903929233551, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.00340457942802459, "weighted_relation_loss": 0.00340457942802459 }, { "action_query_batch_std": 20.6438232421875, "action_query_norm": 892.3975219726562, "action_relation_loss": 0.0032822926063090564, "auxiliary_loss_weight": 1.0, "epoch": 12.507015902712816, "flow_matching_loss": 0.031803864240646365, "grad_norm": 0.11219808459281921, "invalid_tail_samples": 23.4, "learning_rate": 6.297289200638887e-05, "loss": 0.0351, "positive_teacher_pairs": 26944.6, "relation_loss": 0.0032822926063090564, "selected_pairs": 26944.6, "step": 13370, "student_distance_mean": 1182.001904296875, "teacher_distance_mean": 0.8555254220962525, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0032822926063090564, "weighted_relation_loss": 0.0032822926063090564 }, { "action_query_batch_std": 20.642702102661133, "action_query_norm": 890.81806640625, "action_relation_loss": 0.003395073697902262, "auxiliary_loss_weight": 1.0, "epoch": 12.516370439663238, "flow_matching_loss": 0.02978188395500183, "grad_norm": 0.1343659907579422, "invalid_tail_samples": 21.6, "learning_rate": 6.29196559418593e-05, "loss": 0.0332, "positive_teacher_pairs": 27368.6, "relation_loss": 0.003395073697902262, "selected_pairs": 27368.6, "step": 13380, "student_distance_mean": 1179.70087890625, "teacher_distance_mean": 0.855071097612381, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.003395073697902262, "weighted_relation_loss": 0.003395073697902262 }, { "action_query_batch_std": 20.462746238708498, "action_query_norm": 884.7907592773438, "action_relation_loss": 0.0033732427982613444, "auxiliary_loss_weight": 1.0, "epoch": 12.525724976613658, "flow_matching_loss": 0.031784544698894024, "grad_norm": 0.12344609200954437, "invalid_tail_samples": 24.2, "learning_rate": 6.286640417872951e-05, "loss": 0.0352, "positive_teacher_pairs": 26754.9, "relation_loss": 0.0033732427982613444, "selected_pairs": 26754.9, "step": 13390, "student_distance_mean": 1171.7575317382812, "teacher_distance_mean": 0.848039311170578, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0033732427982613444, "weighted_relation_loss": 0.0033732427982613444 }, { "action_query_batch_std": 20.50279483795166, "action_query_norm": 881.3193298339844, "action_relation_loss": 0.003185299807228148, "auxiliary_loss_weight": 1.0, "epoch": 12.535079513564078, "flow_matching_loss": 0.03149601016193628, "grad_norm": 0.09603876620531082, "invalid_tail_samples": 23.3, "learning_rate": 6.281313678170542e-05, "loss": 0.0347, "positive_teacher_pairs": 26960.9, "relation_loss": 0.003185299807228148, "selected_pairs": 26960.9, "step": 13400, "student_distance_mean": 1166.8658935546875, "teacher_distance_mean": 0.8513788700103759, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.003185299807228148, "weighted_relation_loss": 0.003185299807228148 }, { "action_query_batch_std": 20.6245361328125, "action_query_norm": 887.0807495117188, "action_relation_loss": 0.003177252016030252, "auxiliary_loss_weight": 1.0, "epoch": 12.5444340505145, "flow_matching_loss": 0.032861854322254656, "grad_norm": 0.12569038569927216, "invalid_tail_samples": 22.7, "learning_rate": 6.275985381551194e-05, "loss": 0.036, "positive_teacher_pairs": 27107.3, "relation_loss": 0.003177252016030252, "selected_pairs": 27107.3, "step": 13410, "student_distance_mean": 1173.6443115234374, "teacher_distance_mean": 0.8592681586742401, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.003177252016030252, "weighted_relation_loss": 0.003177252016030252 }, { "action_query_batch_std": 20.50970344543457, "action_query_norm": 885.8982788085938, "action_relation_loss": 0.0033293450251221657, "auxiliary_loss_weight": 1.0, "epoch": 12.55378858746492, "flow_matching_loss": 0.03138843812048435, "grad_norm": 0.10711858421564102, "invalid_tail_samples": 23.6, "learning_rate": 6.270655534489292e-05, "loss": 0.0347, "positive_teacher_pairs": 26902.8, "relation_loss": 0.0033293450251221657, "selected_pairs": 26902.8, "step": 13420, "student_distance_mean": 1170.8331787109375, "teacher_distance_mean": 0.8535465657711029, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0033293450251221657, "weighted_relation_loss": 0.0033293450251221657 }, { "action_query_batch_std": 20.57049732208252, "action_query_norm": 890.9430847167969, "action_relation_loss": 0.0034025714732706545, "auxiliary_loss_weight": 1.0, "epoch": 12.563143124415342, "flow_matching_loss": 0.03273202888667583, "grad_norm": 0.1412954330444336, "invalid_tail_samples": 21.5, "learning_rate": 6.265324143461098e-05, "loss": 0.0361, "positive_teacher_pairs": 27383.8, "relation_loss": 0.0034025714732706545, "selected_pairs": 27383.8, "step": 13430, "student_distance_mean": 1172.4616088867188, "teacher_distance_mean": 0.8558097302913665, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.0034025714732706545, "weighted_relation_loss": 0.0034025714732706545 }, { "action_query_batch_std": 20.7128698348999, "action_query_norm": 888.2405822753906, "action_relation_loss": 0.0032994637032970784, "auxiliary_loss_weight": 1.0, "epoch": 12.572497661365762, "flow_matching_loss": 0.03351156320422888, "grad_norm": 0.1092202439904213, "invalid_tail_samples": 24.6, "learning_rate": 6.259991214944758e-05, "loss": 0.0368, "positive_teacher_pairs": 26664.5, "relation_loss": 0.0032994637032970784, "selected_pairs": 26664.5, "step": 13440, "student_distance_mean": 1181.1394165039062, "teacher_distance_mean": 0.8584349989891052, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0032994637032970784, "weighted_relation_loss": 0.0032994637032970784 }, { "action_query_batch_std": 20.73756103515625, "action_query_norm": 892.88212890625, "action_relation_loss": 0.0033602648181840777, "auxiliary_loss_weight": 1.0, "epoch": 12.581852198316183, "flow_matching_loss": 0.0319818127900362, "grad_norm": 0.15410152077674866, "invalid_tail_samples": 24.5, "learning_rate": 6.254656755420283e-05, "loss": 0.0353, "positive_teacher_pairs": 26691.5, "relation_loss": 0.0033602648181840777, "selected_pairs": 26691.5, "step": 13450, "student_distance_mean": 1179.7150268554688, "teacher_distance_mean": 0.8460691034793854, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0033602648181840777, "weighted_relation_loss": 0.0033602648181840777 }, { "action_query_batch_std": 20.990790367126465, "action_query_norm": 902.7429870605469, "action_relation_loss": 0.003173016756772995, "auxiliary_loss_weight": 1.0, "epoch": 12.591206735266605, "flow_matching_loss": 0.032489633001387117, "grad_norm": 0.10582390427589417, "invalid_tail_samples": 23.3, "learning_rate": 6.249320771369545e-05, "loss": 0.0357, "positive_teacher_pairs": 26973.5, "relation_loss": 0.003173016756772995, "selected_pairs": 26973.5, "step": 13460, "student_distance_mean": 1193.5871337890626, "teacher_distance_mean": 0.8615334749221801, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.003173016756772995, "weighted_relation_loss": 0.003173016756772995 }, { "action_query_batch_std": 20.93028316497803, "action_query_norm": 900.1155822753906, "action_relation_loss": 0.0031904242699965835, "auxiliary_loss_weight": 1.0, "epoch": 12.600561272217025, "flow_matching_loss": 0.03147487752139568, "grad_norm": 0.10671041905879974, "invalid_tail_samples": 26.8, "learning_rate": 6.243983269276263e-05, "loss": 0.0347, "positive_teacher_pairs": 26165.8, "relation_loss": 0.0031904242699965835, "selected_pairs": 26165.8, "step": 13470, "student_distance_mean": 1194.2037719726563, "teacher_distance_mean": 0.8636618852615356, "valid_action_samples": 229.2, "weighted_auxiliary_loss": 0.0031904242699965835, "weighted_relation_loss": 0.0031904242699965835 }, { "action_query_batch_std": 20.847140502929687, "action_query_norm": 899.8418151855469, "action_relation_loss": 0.0032814228208735583, "auxiliary_loss_weight": 1.0, "epoch": 12.609915809167447, "flow_matching_loss": 0.03269187733530998, "grad_norm": 0.11632004380226135, "invalid_tail_samples": 24.9, "learning_rate": 6.238644255626012e-05, "loss": 0.036, "positive_teacher_pairs": 26592.1, "relation_loss": 0.0032814228208735583, "selected_pairs": 26592.1, "step": 13480, "student_distance_mean": 1187.507177734375, "teacher_distance_mean": 0.8511119842529297, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0032814228208735583, "weighted_relation_loss": 0.0032814228208735583 }, { "action_query_batch_std": 20.896348571777345, "action_query_norm": 903.2879760742187, "action_relation_loss": 0.003226786316372454, "auxiliary_loss_weight": 1.0, "epoch": 12.619270346117867, "flow_matching_loss": 0.03437794242054224, "grad_norm": 0.15984652936458588, "invalid_tail_samples": 22.9, "learning_rate": 6.233303736906193e-05, "loss": 0.0376, "positive_teacher_pairs": 27061.4, "relation_loss": 0.003226786316372454, "selected_pairs": 27061.4, "step": 13490, "student_distance_mean": 1190.4997924804688, "teacher_distance_mean": 0.8544594764709472, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.003226786316372454, "weighted_relation_loss": 0.003226786316372454 }, { "action_query_batch_std": 20.623766708374024, "action_query_norm": 894.8413024902344, "action_relation_loss": 0.0033984637120738626, "auxiliary_loss_weight": 1.0, "epoch": 12.628624883068287, "flow_matching_loss": 0.033232183568179606, "grad_norm": 0.13542892038822174, "invalid_tail_samples": 22.4, "learning_rate": 6.227961719606039e-05, "loss": 0.0366, "positive_teacher_pairs": 27171.5, "relation_loss": 0.0033984637120738626, "selected_pairs": 27171.5, "step": 13500, "student_distance_mean": 1180.853369140625, "teacher_distance_mean": 0.8488042652606964, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.0033984637120738626, "weighted_relation_loss": 0.0033984637120738626 }, { "action_query_batch_std": 20.88376693725586, "action_query_norm": 898.222119140625, "action_relation_loss": 0.003317148378118873, "auxiliary_loss_weight": 1.0, "epoch": 12.63797942001871, "flow_matching_loss": 0.033921754732728, "grad_norm": 0.10751346498727798, "invalid_tail_samples": 25.1, "learning_rate": 6.222618210216608e-05, "loss": 0.0372, "positive_teacher_pairs": 26555.0, "relation_loss": 0.003317148378118873, "selected_pairs": 26555.0, "step": 13510, "student_distance_mean": 1191.8762329101562, "teacher_distance_mean": 0.8607168555259704, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.003317148378118873, "weighted_relation_loss": 0.003317148378118873 }, { "action_query_batch_std": 20.940952873229982, "action_query_norm": 902.5424133300781, "action_relation_loss": 0.0031785434577614067, "auxiliary_loss_weight": 1.0, "epoch": 12.64733395696913, "flow_matching_loss": 0.031831626407802106, "grad_norm": 0.10376673936843872, "invalid_tail_samples": 24.0, "learning_rate": 6.217273215230767e-05, "loss": 0.035, "positive_teacher_pairs": 26808.8, "relation_loss": 0.0031785434577614067, "selected_pairs": 26808.8, "step": 13520, "student_distance_mean": 1195.9297485351562, "teacher_distance_mean": 0.8677144885063172, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0031785434577614067, "weighted_relation_loss": 0.0031785434577614067 }, { "action_query_batch_std": 20.64681167602539, "action_query_norm": 888.6077880859375, "action_relation_loss": 0.0033811065135523678, "auxiliary_loss_weight": 1.0, "epoch": 12.656688493919551, "flow_matching_loss": 0.0334734907373786, "grad_norm": 0.11340278387069702, "invalid_tail_samples": 22.6, "learning_rate": 6.211926741143188e-05, "loss": 0.0369, "positive_teacher_pairs": 27130.9, "relation_loss": 0.0033811065135523678, "selected_pairs": 27130.9, "step": 13530, "student_distance_mean": 1174.6287109375, "teacher_distance_mean": 0.8526810586452485, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0033811065135523678, "weighted_relation_loss": 0.0033811065135523678 }, { "action_query_batch_std": 20.936175537109374, "action_query_norm": 898.7335083007813, "action_relation_loss": 0.003225732082501054, "auxiliary_loss_weight": 1.0, "epoch": 12.666043030869972, "flow_matching_loss": 0.03273312263190746, "grad_norm": 0.10891025513410568, "invalid_tail_samples": 23.2, "learning_rate": 6.20657879445034e-05, "loss": 0.036, "positive_teacher_pairs": 26985.8, "relation_loss": 0.003225732082501054, "selected_pairs": 26985.8, "step": 13540, "student_distance_mean": 1196.9019165039062, "teacher_distance_mean": 0.8644776582717896, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.003225732082501054, "weighted_relation_loss": 0.003225732082501054 }, { "action_query_batch_std": 20.417363739013673, "action_query_norm": 884.8159851074219, "action_relation_loss": 0.0032031961949542166, "auxiliary_loss_weight": 1.0, "epoch": 12.675397567820394, "flow_matching_loss": 0.03218199610710144, "grad_norm": 0.12955017387866974, "invalid_tail_samples": 24.0, "learning_rate": 6.201229381650485e-05, "loss": 0.0354, "positive_teacher_pairs": 26808.9, "relation_loss": 0.0032031961949542166, "selected_pairs": 26808.9, "step": 13550, "student_distance_mean": 1168.5337890625, "teacher_distance_mean": 0.8409919083118439, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0032031961949542166, "weighted_relation_loss": 0.0032031961949542166 }, { "action_query_batch_std": 21.036376571655275, "action_query_norm": 903.5405456542969, "action_relation_loss": 0.003146142209880054, "auxiliary_loss_weight": 1.0, "epoch": 12.684752104770814, "flow_matching_loss": 0.031069298461079597, "grad_norm": 0.13607469201087952, "invalid_tail_samples": 23.2, "learning_rate": 6.195878509243661e-05, "loss": 0.0342, "positive_teacher_pairs": 26989.8, "relation_loss": 0.003146142209880054, "selected_pairs": 26989.8, "step": 13560, "student_distance_mean": 1195.2885864257812, "teacher_distance_mean": 0.8592975199222564, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.003146142209880054, "weighted_relation_loss": 0.003146142209880054 }, { "action_query_batch_std": 20.82737331390381, "action_query_norm": 895.0284423828125, "action_relation_loss": 0.0033621896291151643, "auxiliary_loss_weight": 1.0, "epoch": 12.694106641721234, "flow_matching_loss": 0.03320027682930231, "grad_norm": 0.1111283078789711, "invalid_tail_samples": 23.0, "learning_rate": 6.190526183731685e-05, "loss": 0.0366, "positive_teacher_pairs": 27036.0, "relation_loss": 0.0033621896291151643, "selected_pairs": 27036.0, "step": 13570, "student_distance_mean": 1191.9249877929688, "teacher_distance_mean": 0.8591034293174744, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0033621896291151643, "weighted_relation_loss": 0.0033621896291151643 }, { "action_query_batch_std": 20.41664562225342, "action_query_norm": 882.7171875, "action_relation_loss": 0.003274732711724937, "auxiliary_loss_weight": 1.0, "epoch": 12.703461178671656, "flow_matching_loss": 0.031106317415833473, "grad_norm": 0.12172337621450424, "invalid_tail_samples": 22.3, "learning_rate": 6.185172411618138e-05, "loss": 0.0344, "positive_teacher_pairs": 27200.5, "relation_loss": 0.003274732711724937, "selected_pairs": 27200.5, "step": 13580, "student_distance_mean": 1159.4806640625, "teacher_distance_mean": 0.8422351717948914, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.003274732711724937, "weighted_relation_loss": 0.003274732711724937 }, { "action_query_batch_std": 20.891917610168456, "action_query_norm": 895.9405639648437, "action_relation_loss": 0.0034338247030973436, "auxiliary_loss_weight": 1.0, "epoch": 12.712815715622076, "flow_matching_loss": 0.03242229763418436, "grad_norm": 0.14236141741275787, "invalid_tail_samples": 24.6, "learning_rate": 6.179817199408355e-05, "loss": 0.0359, "positive_teacher_pairs": 26666.7, "relation_loss": 0.0034338247030973436, "selected_pairs": 26666.7, "step": 13590, "student_distance_mean": 1196.2382080078125, "teacher_distance_mean": 0.8635909795761109, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0034338247030973436, "weighted_relation_loss": 0.0034338247030973436 }, { "action_query_batch_std": 20.503725814819337, "action_query_norm": 885.670068359375, "action_relation_loss": 0.003287665406242013, "auxiliary_loss_weight": 1.0, "epoch": 12.722170252572498, "flow_matching_loss": 0.03295083977282047, "grad_norm": 0.11619540303945541, "invalid_tail_samples": 24.1, "learning_rate": 6.174460553609426e-05, "loss": 0.0362, "positive_teacher_pairs": 26779.6, "relation_loss": 0.003287665406242013, "selected_pairs": 26779.6, "step": 13600, "student_distance_mean": 1180.5941040039063, "teacher_distance_mean": 0.8450697064399719, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.003287665406242013, "weighted_relation_loss": 0.003287665406242013 }, { "action_query_batch_std": 20.927444458007812, "action_query_norm": 901.9536437988281, "action_relation_loss": 0.003229897771961987, "auxiliary_loss_weight": 1.0, "epoch": 12.731524789522918, "flow_matching_loss": 0.031238848343491554, "grad_norm": 0.10198502242565155, "invalid_tail_samples": 21.7, "learning_rate": 6.16910248073018e-05, "loss": 0.0345, "positive_teacher_pairs": 27351.9, "relation_loss": 0.003229897771961987, "selected_pairs": 27351.9, "step": 13610, "student_distance_mean": 1193.2123168945313, "teacher_distance_mean": 0.852106124162674, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.003229897771961987, "weighted_relation_loss": 0.003229897771961987 }, { "action_query_batch_std": 20.721940994262695, "action_query_norm": 895.8887939453125, "action_relation_loss": 0.0032990508479997516, "auxiliary_loss_weight": 1.0, "epoch": 12.74087932647334, "flow_matching_loss": 0.03194182720035314, "grad_norm": 0.10417848080396652, "invalid_tail_samples": 22.8, "learning_rate": 6.16374298728118e-05, "loss": 0.0352, "positive_teacher_pairs": 27082.4, "relation_loss": 0.0032990508479997516, "selected_pairs": 27082.4, "step": 13620, "student_distance_mean": 1179.9105590820313, "teacher_distance_mean": 0.8486816942691803, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0032990508479997516, "weighted_relation_loss": 0.0032990508479997516 }, { "action_query_batch_std": 20.87273826599121, "action_query_norm": 902.1129272460937, "action_relation_loss": 0.003282414865680039, "auxiliary_loss_weight": 1.0, "epoch": 12.75023386342376, "flow_matching_loss": 0.03335847370326519, "grad_norm": 0.14571669697761536, "invalid_tail_samples": 24.4, "learning_rate": 6.158382079774716e-05, "loss": 0.0366, "positive_teacher_pairs": 26715.2, "relation_loss": 0.003282414865680039, "selected_pairs": 26715.2, "step": 13630, "student_distance_mean": 1193.053369140625, "teacher_distance_mean": 0.852534294128418, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.003282414865680039, "weighted_relation_loss": 0.003282414865680039 }, { "action_query_batch_std": 20.70279541015625, "action_query_norm": 896.2337707519531, "action_relation_loss": 0.00332816441077739, "auxiliary_loss_weight": 1.0, "epoch": 12.75958840037418, "flow_matching_loss": 0.0312945568934083, "grad_norm": 0.19188645482063293, "invalid_tail_samples": 24.1, "learning_rate": 6.153019764724799e-05, "loss": 0.0346, "positive_teacher_pairs": 26780.5, "relation_loss": 0.00332816441077739, "selected_pairs": 26780.5, "step": 13640, "student_distance_mean": 1181.5982666015625, "teacher_distance_mean": 0.8497792065143586, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.00332816441077739, "weighted_relation_loss": 0.00332816441077739 }, { "action_query_batch_std": 20.868735313415527, "action_query_norm": 899.2278198242187, "action_relation_loss": 0.0031924903858453037, "auxiliary_loss_weight": 1.0, "epoch": 12.768942937324603, "flow_matching_loss": 0.03198588155210018, "grad_norm": 0.1335832178592682, "invalid_tail_samples": 22.5, "learning_rate": 6.147656048647144e-05, "loss": 0.0352, "positive_teacher_pairs": 27152.0, "relation_loss": 0.0031924903858453037, "selected_pairs": 27152.0, "step": 13650, "student_distance_mean": 1190.2539794921875, "teacher_distance_mean": 0.8614619374275208, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0031924903858453037, "weighted_relation_loss": 0.0031924903858453037 }, { "action_query_batch_std": 20.923794555664063, "action_query_norm": 899.8376525878906, "action_relation_loss": 0.00331047207582742, "auxiliary_loss_weight": 1.0, "epoch": 12.778297474275023, "flow_matching_loss": 0.03222472369670868, "grad_norm": 0.09471395611763, "invalid_tail_samples": 24.6, "learning_rate": 6.142290938059173e-05, "loss": 0.0355, "positive_teacher_pairs": 26666.9, "relation_loss": 0.00331047207582742, "selected_pairs": 26666.9, "step": 13660, "student_distance_mean": 1193.8468872070312, "teacher_distance_mean": 0.8615171134471893, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.00331047207582742, "weighted_relation_loss": 0.00331047207582742 }, { "action_query_batch_std": 20.55175323486328, "action_query_norm": 886.002099609375, "action_relation_loss": 0.0031097795348614455, "auxiliary_loss_weight": 1.0, "epoch": 12.787652011225445, "flow_matching_loss": 0.031279324740171435, "grad_norm": 0.1173953041434288, "invalid_tail_samples": 25.2, "learning_rate": 6.136924439480001e-05, "loss": 0.0344, "positive_teacher_pairs": 26531.1, "relation_loss": 0.0031097795348614455, "selected_pairs": 26531.1, "step": 13670, "student_distance_mean": 1175.7360107421875, "teacher_distance_mean": 0.8486636221408844, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0031097795348614455, "weighted_relation_loss": 0.0031097795348614455 }, { "action_query_batch_std": 20.681551361083983, "action_query_norm": 894.1749755859375, "action_relation_loss": 0.0033834256464615464, "auxiliary_loss_weight": 1.0, "epoch": 12.797006548175865, "flow_matching_loss": 0.031352984718978405, "grad_norm": 0.10962963849306107, "invalid_tail_samples": 24.6, "learning_rate": 6.13155655943043e-05, "loss": 0.0347, "positive_teacher_pairs": 26679.4, "relation_loss": 0.0033834256464615464, "selected_pairs": 26679.4, "step": 13680, "student_distance_mean": 1180.9822143554688, "teacher_distance_mean": 0.8429974853992462, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0033834256464615464, "weighted_relation_loss": 0.0033834256464615464 }, { "action_query_batch_std": 20.824191856384278, "action_query_norm": 900.7593688964844, "action_relation_loss": 0.003074078797362745, "auxiliary_loss_weight": 1.0, "epoch": 12.806361085126285, "flow_matching_loss": 0.02950067091733217, "grad_norm": 0.0937294140458107, "invalid_tail_samples": 23.6, "learning_rate": 6.126187304432941e-05, "loss": 0.0326, "positive_teacher_pairs": 26899.8, "relation_loss": 0.003074078797362745, "selected_pairs": 26899.8, "step": 13690, "student_distance_mean": 1191.5425170898438, "teacher_distance_mean": 0.8521052122116088, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.003074078797362745, "weighted_relation_loss": 0.003074078797362745 }, { "action_query_batch_std": 21.305170631408693, "action_query_norm": 914.8094299316406, "action_relation_loss": 0.003036737465299666, "auxiliary_loss_weight": 1.0, "epoch": 12.815715622076707, "flow_matching_loss": 0.03285083808004856, "grad_norm": 0.11535248905420303, "invalid_tail_samples": 23.7, "learning_rate": 6.120816681011684e-05, "loss": 0.0359, "positive_teacher_pairs": 26870.5, "relation_loss": 0.003036737465299666, "selected_pairs": 26870.5, "step": 13700, "student_distance_mean": 1215.8685180664063, "teacher_distance_mean": 0.8689496517181396, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.003036737465299666, "weighted_relation_loss": 0.003036737465299666 }, { "action_query_batch_std": 20.655129051208498, "action_query_norm": 892.3079040527343, "action_relation_loss": 0.0031933110440149903, "auxiliary_loss_weight": 1.0, "epoch": 12.825070159027128, "flow_matching_loss": 0.03220363762229681, "grad_norm": 0.09402915090322495, "invalid_tail_samples": 24.3, "learning_rate": 6.115444695692474e-05, "loss": 0.0354, "positive_teacher_pairs": 26735.2, "relation_loss": 0.0031933110440149903, "selected_pairs": 26735.2, "step": 13710, "student_distance_mean": 1181.4551879882813, "teacher_distance_mean": 0.8471210360527038, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0031933110440149903, "weighted_relation_loss": 0.0031933110440149903 }, { "action_query_batch_std": 20.79352912902832, "action_query_norm": 900.2258239746094, "action_relation_loss": 0.003208689880557358, "auxiliary_loss_weight": 1.0, "epoch": 12.83442469597755, "flow_matching_loss": 0.03174661844968796, "grad_norm": 0.1194140836596489, "invalid_tail_samples": 22.4, "learning_rate": 6.110071355002779e-05, "loss": 0.035, "positive_teacher_pairs": 27173.6, "relation_loss": 0.003208689880557358, "selected_pairs": 27173.6, "step": 13720, "student_distance_mean": 1191.2872192382813, "teacher_distance_mean": 0.8563750088214874, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.003208689880557358, "weighted_relation_loss": 0.003208689880557358 }, { "action_query_batch_std": 21.018338012695313, "action_query_norm": 908.2107116699219, "action_relation_loss": 0.0031990340212360024, "auxiliary_loss_weight": 1.0, "epoch": 12.84377923292797, "flow_matching_loss": 0.031130877137184144, "grad_norm": 0.14268915355205536, "invalid_tail_samples": 21.8, "learning_rate": 6.104696665471714e-05, "loss": 0.0343, "positive_teacher_pairs": 27318.0, "relation_loss": 0.0031990340212360024, "selected_pairs": 27318.0, "step": 13730, "student_distance_mean": 1194.9003173828125, "teacher_distance_mean": 0.858522641658783, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.0031990340212360024, "weighted_relation_loss": 0.0031990340212360024 }, { "action_query_batch_std": 20.945142364501955, "action_query_norm": 905.4047180175781, "action_relation_loss": 0.003238298324868083, "auxiliary_loss_weight": 1.0, "epoch": 12.853133769878392, "flow_matching_loss": 0.03281331565231085, "grad_norm": 0.10157984495162964, "invalid_tail_samples": 24.6, "learning_rate": 6.099320633630036e-05, "loss": 0.0361, "positive_teacher_pairs": 26666.7, "relation_loss": 0.003238298324868083, "selected_pairs": 26666.7, "step": 13740, "student_distance_mean": 1196.023876953125, "teacher_distance_mean": 0.8556840240955352, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.003238298324868083, "weighted_relation_loss": 0.003238298324868083 }, { "action_query_batch_std": 21.044794273376464, "action_query_norm": 909.028271484375, "action_relation_loss": 0.0032151243649423122, "auxiliary_loss_weight": 1.0, "epoch": 12.862488306828812, "flow_matching_loss": 0.03236220497637987, "grad_norm": 0.12221987545490265, "invalid_tail_samples": 23.5, "learning_rate": 6.093943266010128e-05, "loss": 0.0356, "positive_teacher_pairs": 26918.8, "relation_loss": 0.0032151243649423122, "selected_pairs": 26918.8, "step": 13750, "student_distance_mean": 1205.1378662109375, "teacher_distance_mean": 0.8598865926265716, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0032151243649423122, "weighted_relation_loss": 0.0032151243649423122 }, { "action_query_batch_std": 20.8527587890625, "action_query_norm": 901.7583251953125, "action_relation_loss": 0.0032126048346981404, "auxiliary_loss_weight": 1.0, "epoch": 12.871842843779232, "flow_matching_loss": 0.031006770581007002, "grad_norm": 0.1329997330904007, "invalid_tail_samples": 24.2, "learning_rate": 6.088564569146e-05, "loss": 0.0342, "positive_teacher_pairs": 26756.2, "relation_loss": 0.0032126048346981404, "selected_pairs": 26756.2, "step": 13760, "student_distance_mean": 1193.8541748046875, "teacher_distance_mean": 0.8562843859195709, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0032126048346981404, "weighted_relation_loss": 0.0032126048346981404 }, { "action_query_batch_std": 21.06546974182129, "action_query_norm": 907.8697448730469, "action_relation_loss": 0.0032073725247755646, "auxiliary_loss_weight": 1.0, "epoch": 12.881197380729654, "flow_matching_loss": 0.031764893978834155, "grad_norm": 0.12256436794996262, "invalid_tail_samples": 24.7, "learning_rate": 6.083184549573274e-05, "loss": 0.035, "positive_teacher_pairs": 26640.2, "relation_loss": 0.0032073725247755646, "selected_pairs": 26640.2, "step": 13770, "student_distance_mean": 1198.8029174804688, "teacher_distance_mean": 0.8583155751228333, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0032073725247755646, "weighted_relation_loss": 0.0032073725247755646 }, { "action_query_batch_std": 20.889070129394533, "action_query_norm": 902.2462707519531, "action_relation_loss": 0.0032321835635229943, "auxiliary_loss_weight": 1.0, "epoch": 12.890551917680074, "flow_matching_loss": 0.03098161015659571, "grad_norm": 0.13864704966545105, "invalid_tail_samples": 24.1, "learning_rate": 6.077803213829184e-05, "loss": 0.0342, "positive_teacher_pairs": 26778.2, "relation_loss": 0.0032321835635229943, "selected_pairs": 26778.2, "step": 13780, "student_distance_mean": 1194.95537109375, "teacher_distance_mean": 0.860277658700943, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0032321835635229943, "weighted_relation_loss": 0.0032321835635229943 }, { "action_query_batch_std": 20.635865020751954, "action_query_norm": 893.625634765625, "action_relation_loss": 0.0032327847555279733, "auxiliary_loss_weight": 1.0, "epoch": 12.899906454630496, "flow_matching_loss": 0.031406888738274574, "grad_norm": 0.14318563044071198, "invalid_tail_samples": 24.0, "learning_rate": 6.0724205684525594e-05, "loss": 0.0346, "positive_teacher_pairs": 26803.8, "relation_loss": 0.0032327847555279733, "selected_pairs": 26803.8, "step": 13790, "student_distance_mean": 1176.1986328125, "teacher_distance_mean": 0.8471764326095581, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0032327847555279733, "weighted_relation_loss": 0.0032327847555279733 }, { "action_query_batch_std": 20.768002891540526, "action_query_norm": 895.1839477539063, "action_relation_loss": 0.0031928093172609805, "auxiliary_loss_weight": 1.0, "epoch": 12.909260991580917, "flow_matching_loss": 0.029079096019268037, "grad_norm": 0.11423365026712418, "invalid_tail_samples": 25.7, "learning_rate": 6.0670366199838215e-05, "loss": 0.0323, "positive_teacher_pairs": 26410.9, "relation_loss": 0.0031928093172609805, "selected_pairs": 26410.9, "step": 13800, "student_distance_mean": 1186.0530151367188, "teacher_distance_mean": 0.8551220417022705, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.0031928093172609805, "weighted_relation_loss": 0.0031928093172609805 }, { "action_query_batch_std": 20.780597305297853, "action_query_norm": 900.2337158203125, "action_relation_loss": 0.0031803332502022387, "auxiliary_loss_weight": 1.0, "epoch": 12.918615528531337, "flow_matching_loss": 0.03281013779342175, "grad_norm": 0.11402864754199982, "invalid_tail_samples": 22.4, "learning_rate": 6.061651374964974e-05, "loss": 0.036, "positive_teacher_pairs": 27181.3, "relation_loss": 0.0031803332502022387, "selected_pairs": 27181.3, "step": 13810, "student_distance_mean": 1187.8765747070313, "teacher_distance_mean": 0.8506572365760803, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.0031803332502022387, "weighted_relation_loss": 0.0031803332502022387 }, { "action_query_batch_std": 20.988238906860353, "action_query_norm": 904.3875305175782, "action_relation_loss": 0.0031562297604978084, "auxiliary_loss_weight": 1.0, "epoch": 12.927970065481759, "flow_matching_loss": 0.03049887828528881, "grad_norm": 0.11895376443862915, "invalid_tail_samples": 25.5, "learning_rate": 6.0562648399396004e-05, "loss": 0.0337, "positive_teacher_pairs": 26455.7, "relation_loss": 0.0031562297604978084, "selected_pairs": 26455.7, "step": 13820, "student_distance_mean": 1198.3409545898437, "teacher_distance_mean": 0.855028235912323, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0031562297604978084, "weighted_relation_loss": 0.0031562297604978084 }, { "action_query_batch_std": 20.687253189086913, "action_query_norm": 894.7389221191406, "action_relation_loss": 0.0032526029506698253, "auxiliary_loss_weight": 1.0, "epoch": 12.937324602432179, "flow_matching_loss": 0.03246208261698484, "grad_norm": 0.12916262447834015, "invalid_tail_samples": 24.6, "learning_rate": 6.050877021452845e-05, "loss": 0.0357, "positive_teacher_pairs": 26668.8, "relation_loss": 0.0032526029506698253, "selected_pairs": 26668.8, "step": 13830, "student_distance_mean": 1183.8828979492187, "teacher_distance_mean": 0.8463753223419189, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0032526029506698253, "weighted_relation_loss": 0.0032526029506698253 }, { "action_query_batch_std": 20.936276054382326, "action_query_norm": 900.6726928710938, "action_relation_loss": 0.0031086514471098782, "auxiliary_loss_weight": 1.0, "epoch": 12.946679139382601, "flow_matching_loss": 0.030768714286386965, "grad_norm": 0.1615045815706253, "invalid_tail_samples": 26.4, "learning_rate": 6.04548792605142e-05, "loss": 0.0339, "positive_teacher_pairs": 26260.4, "relation_loss": 0.0031086514471098782, "selected_pairs": 26260.4, "step": 13840, "student_distance_mean": 1195.8513793945312, "teacher_distance_mean": 0.8557541906833649, "valid_action_samples": 229.6, "weighted_auxiliary_loss": 0.0031086514471098782, "weighted_relation_loss": 0.0031086514471098782 }, { "action_query_batch_std": 21.267203712463377, "action_query_norm": 916.223291015625, "action_relation_loss": 0.0030792558565735815, "auxiliary_loss_weight": 1.0, "epoch": 12.956033676333021, "flow_matching_loss": 0.03134002164006233, "grad_norm": 0.1251327395439148, "invalid_tail_samples": 22.2, "learning_rate": 6.04009756028358e-05, "loss": 0.0344, "positive_teacher_pairs": 27220.0, "relation_loss": 0.0030792558565735815, "selected_pairs": 27220.0, "step": 13850, "student_distance_mean": 1211.0113525390625, "teacher_distance_mean": 0.8620552659034729, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.0030792558565735815, "weighted_relation_loss": 0.0030792558565735815 }, { "action_query_batch_std": 21.027334785461427, "action_query_norm": 905.2259155273438, "action_relation_loss": 0.003360361000522971, "auxiliary_loss_weight": 1.0, "epoch": 12.965388213283443, "flow_matching_loss": 0.033027845434844494, "grad_norm": 0.10916145890951157, "invalid_tail_samples": 25.3, "learning_rate": 6.0347059306991294e-05, "loss": 0.0364, "positive_teacher_pairs": 26502.8, "relation_loss": 0.003360361000522971, "selected_pairs": 26502.8, "step": 13860, "student_distance_mean": 1207.0895385742188, "teacher_distance_mean": 0.8638887107372284, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.003360361000522971, "weighted_relation_loss": 0.003360361000522971 }, { "action_query_batch_std": 20.863488960266114, "action_query_norm": 901.8043518066406, "action_relation_loss": 0.0032497371546924116, "auxiliary_loss_weight": 1.0, "epoch": 12.974742750233863, "flow_matching_loss": 0.030949587747454644, "grad_norm": 0.12613870203495026, "invalid_tail_samples": 21.9, "learning_rate": 6.029313043849407e-05, "loss": 0.0342, "positive_teacher_pairs": 27290.1, "relation_loss": 0.0032497371546924116, "selected_pairs": 27290.1, "step": 13870, "student_distance_mean": 1192.326513671875, "teacher_distance_mean": 0.8541031181812286, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.0032497371546924116, "weighted_relation_loss": 0.0032497371546924116 }, { "action_query_batch_std": 20.86889362335205, "action_query_norm": 901.2217590332032, "action_relation_loss": 0.003309417306445539, "auxiliary_loss_weight": 1.0, "epoch": 12.984097287184284, "flow_matching_loss": 0.029880518093705177, "grad_norm": 0.11494328826665878, "invalid_tail_samples": 24.3, "learning_rate": 6.023918906287279e-05, "loss": 0.0332, "positive_teacher_pairs": 26736.5, "relation_loss": 0.003309417306445539, "selected_pairs": 26736.5, "step": 13880, "student_distance_mean": 1192.3132446289062, "teacher_distance_mean": 0.8522013068199158, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.003309417306445539, "weighted_relation_loss": 0.003309417306445539 }, { "action_query_batch_std": 21.062539672851564, "action_query_norm": 906.4812072753906, "action_relation_loss": 0.0031838831957429646, "auxiliary_loss_weight": 1.0, "epoch": 12.993451824134706, "flow_matching_loss": 0.031357608176767825, "grad_norm": 0.13485445082187653, "invalid_tail_samples": 22.7, "learning_rate": 6.01852352456713e-05, "loss": 0.0345, "positive_teacher_pairs": 27106.3, "relation_loss": 0.0031838831957429646, "selected_pairs": 27106.3, "step": 13890, "student_distance_mean": 1204.98798828125, "teacher_distance_mean": 0.8675262153148651, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0031838831957429646, "weighted_relation_loss": 0.0031838831957429646 }, { "action_query_batch_std": 20.755551719665526, "action_query_norm": 898.0363464355469, "action_relation_loss": 0.0032421907410025595, "auxiliary_loss_weight": 1.0, "epoch": 13.002806361085126, "flow_matching_loss": 0.030503959394991398, "grad_norm": 0.13433733582496643, "invalid_tail_samples": 22.2, "learning_rate": 6.013126905244858e-05, "loss": 0.0337, "positive_teacher_pairs": 24235.0, "relation_loss": 0.0032421907410025595, "selected_pairs": 24235.0, "step": 13900, "student_distance_mean": 1185.6594482421874, "teacher_distance_mean": 0.8519642889499665, "valid_action_samples": 213.9, "weighted_auxiliary_loss": 0.0032421907410025595, "weighted_relation_loss": 0.0032421907410025595 }, { "action_query_batch_std": 21.175371170043945, "action_query_norm": 913.2601684570312, "action_relation_loss": 0.003113735909573734, "auxiliary_loss_weight": 1.0, "epoch": 13.012160898035548, "flow_matching_loss": 0.030952491611242295, "grad_norm": 0.1502602994441986, "invalid_tail_samples": 23.3, "learning_rate": 6.007729054877864e-05, "loss": 0.0341, "positive_teacher_pairs": 26963.8, "relation_loss": 0.003113735909573734, "selected_pairs": 26963.8, "step": 13910, "student_distance_mean": 1211.522216796875, "teacher_distance_mean": 0.8599145531654357, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.003113735909573734, "weighted_relation_loss": 0.003113735909573734 }, { "action_query_batch_std": 21.202481269836426, "action_query_norm": 911.3517578125, "action_relation_loss": 0.0030301460064947605, "auxiliary_loss_weight": 1.0, "epoch": 13.021515434985968, "flow_matching_loss": 0.032548324950039384, "grad_norm": 0.12932495772838593, "invalid_tail_samples": 21.3, "learning_rate": 6.0023299800250466e-05, "loss": 0.0356, "positive_teacher_pairs": 27438.0, "relation_loss": 0.0030301460064947605, "selected_pairs": 27438.0, "step": 13920, "student_distance_mean": 1204.2602661132812, "teacher_distance_mean": 0.8572829246520997, "valid_action_samples": 234.7, "weighted_auxiliary_loss": 0.0030301460064947605, "weighted_relation_loss": 0.0030301460064947605 }, { "action_query_batch_std": 20.906589317321778, "action_query_norm": 901.6386047363281, "action_relation_loss": 0.0030434596119448543, "auxiliary_loss_weight": 1.0, "epoch": 13.030869971936388, "flow_matching_loss": 0.029933307878673078, "grad_norm": 0.1404935121536255, "invalid_tail_samples": 20.3, "learning_rate": 5.9969296872467894e-05, "loss": 0.033, "positive_teacher_pairs": 27668.2, "relation_loss": 0.0030434596119448543, "selected_pairs": 27668.2, "step": 13930, "student_distance_mean": 1194.4291259765625, "teacher_distance_mean": 0.8580231130123138, "valid_action_samples": 235.7, "weighted_auxiliary_loss": 0.0030434596119448543, "weighted_relation_loss": 0.0030434596119448543 }, { "action_query_batch_std": 20.88869438171387, "action_query_norm": 902.6823486328125, "action_relation_loss": 0.003022091230377555, "auxiliary_loss_weight": 1.0, "epoch": 13.04022450888681, "flow_matching_loss": 0.029954110085964204, "grad_norm": 0.1323058009147644, "invalid_tail_samples": 22.6, "learning_rate": 5.9915281831049585e-05, "loss": 0.033, "positive_teacher_pairs": 27129.6, "relation_loss": 0.003022091230377555, "selected_pairs": 27129.6, "step": 13940, "student_distance_mean": 1194.1450317382812, "teacher_distance_mean": 0.8497498333454132, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.003022091230377555, "weighted_relation_loss": 0.003022091230377555 }, { "action_query_batch_std": 21.030697631835938, "action_query_norm": 906.7501831054688, "action_relation_loss": 0.003044178965501487, "auxiliary_loss_weight": 1.0, "epoch": 13.04957904583723, "flow_matching_loss": 0.031722009740769865, "grad_norm": 0.10664108395576477, "invalid_tail_samples": 22.5, "learning_rate": 5.98612547416289e-05, "loss": 0.0348, "positive_teacher_pairs": 27150.1, "relation_loss": 0.003044178965501487, "selected_pairs": 27150.1, "step": 13950, "student_distance_mean": 1200.2673095703126, "teacher_distance_mean": 0.8522293031215668, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.003044178965501487, "weighted_relation_loss": 0.003044178965501487 }, { "action_query_batch_std": 20.9673734664917, "action_query_norm": 908.4971618652344, "action_relation_loss": 0.003181143617257476, "auxiliary_loss_weight": 1.0, "epoch": 13.058933582787652, "flow_matching_loss": 0.029899767972528933, "grad_norm": 0.10463012009859085, "invalid_tail_samples": 23.4, "learning_rate": 5.9807215669853855e-05, "loss": 0.0331, "positive_teacher_pairs": 26945.5, "relation_loss": 0.003181143617257476, "selected_pairs": 26945.5, "step": 13960, "student_distance_mean": 1199.4906127929687, "teacher_distance_mean": 0.8515672624111176, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.003181143617257476, "weighted_relation_loss": 0.003181143617257476 }, { "action_query_batch_std": 21.09288635253906, "action_query_norm": 910.5845336914062, "action_relation_loss": 0.003155768383294344, "auxiliary_loss_weight": 1.0, "epoch": 13.068288119738073, "flow_matching_loss": 0.029964029788970947, "grad_norm": 0.09792868793010712, "invalid_tail_samples": 22.6, "learning_rate": 5.9753164681387e-05, "loss": 0.0331, "positive_teacher_pairs": 27126.6, "relation_loss": 0.003155768383294344, "selected_pairs": 27126.6, "step": 13970, "student_distance_mean": 1203.5695190429688, "teacher_distance_mean": 0.85916708111763, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.003155768383294344, "weighted_relation_loss": 0.003155768383294344 }, { "action_query_batch_std": 21.03138999938965, "action_query_norm": 906.2849243164062, "action_relation_loss": 0.003238806314766407, "auxiliary_loss_weight": 1.0, "epoch": 13.077642656688495, "flow_matching_loss": 0.030762533098459242, "grad_norm": 0.09905443340539932, "invalid_tail_samples": 24.4, "learning_rate": 5.969910184190539e-05, "loss": 0.034, "positive_teacher_pairs": 26726.3, "relation_loss": 0.003238806314766407, "selected_pairs": 26726.3, "step": 13980, "student_distance_mean": 1201.6051513671875, "teacher_distance_mean": 0.8616910994052887, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.003238806314766407, "weighted_relation_loss": 0.003238806314766407 }, { "action_query_batch_std": 20.94307098388672, "action_query_norm": 903.4022827148438, "action_relation_loss": 0.0031257797265425323, "auxiliary_loss_weight": 1.0, "epoch": 13.086997193638915, "flow_matching_loss": 0.030791872180998325, "grad_norm": 0.11830098181962967, "invalid_tail_samples": 25.7, "learning_rate": 5.9645027217100477e-05, "loss": 0.0339, "positive_teacher_pairs": 26406.5, "relation_loss": 0.0031257797265425323, "selected_pairs": 26406.5, "step": 13990, "student_distance_mean": 1198.362646484375, "teacher_distance_mean": 0.8538379490375518, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.0031257797265425323, "weighted_relation_loss": 0.0031257797265425323 }, { "action_query_batch_std": 20.8654577255249, "action_query_norm": 899.8489990234375, "action_relation_loss": 0.0030208684504032133, "auxiliary_loss_weight": 1.0, "epoch": 13.096351730589335, "flow_matching_loss": 0.030295890010893344, "grad_norm": 0.12540203332901, "invalid_tail_samples": 23.2, "learning_rate": 5.959094087267804e-05, "loss": 0.0333, "positive_teacher_pairs": 26987.7, "relation_loss": 0.0030208684504032133, "selected_pairs": 26987.7, "step": 14000, "student_distance_mean": 1195.6751220703125, "teacher_distance_mean": 0.8550365090370178, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0030208684504032133, "weighted_relation_loss": 0.0030208684504032133 }, { "action_query_batch_std": 20.91837978363037, "action_query_norm": 900.4097412109375, "action_relation_loss": 0.0030623513972386717, "auxiliary_loss_weight": 1.0, "epoch": 13.105706267539757, "flow_matching_loss": 0.029747775569558144, "grad_norm": 0.1168927401304245, "invalid_tail_samples": 26.5, "learning_rate": 5.9536842874358065e-05, "loss": 0.0328, "positive_teacher_pairs": 26228.4, "relation_loss": 0.0030623513972386717, "selected_pairs": 26228.4, "step": 14010, "student_distance_mean": 1203.98115234375, "teacher_distance_mean": 0.8603272318840027, "valid_action_samples": 229.5, "weighted_auxiliary_loss": 0.0030623513972386717, "weighted_relation_loss": 0.0030623513972386717 }, { "action_query_batch_std": 20.901403999328615, "action_query_norm": 900.9397277832031, "action_relation_loss": 0.0029508247040212154, "auxiliary_loss_weight": 1.0, "epoch": 13.115060804490177, "flow_matching_loss": 0.030995019339025022, "grad_norm": 0.10264366865158081, "invalid_tail_samples": 22.5, "learning_rate": 5.9482733287874734e-05, "loss": 0.0339, "positive_teacher_pairs": 27153.3, "relation_loss": 0.0029508247040212154, "selected_pairs": 27153.3, "step": 14020, "student_distance_mean": 1194.825341796875, "teacher_distance_mean": 0.8541046977043152, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0029508247040212154, "weighted_relation_loss": 0.0029508247040212154 }, { "action_query_batch_std": 21.051938629150392, "action_query_norm": 906.0425842285156, "action_relation_loss": 0.0029483671765774488, "auxiliary_loss_weight": 1.0, "epoch": 13.1244153414406, "flow_matching_loss": 0.031170409359037875, "grad_norm": 0.1151927188038826, "invalid_tail_samples": 23.3, "learning_rate": 5.942861217897631e-05, "loss": 0.0341, "positive_teacher_pairs": 26967.4, "relation_loss": 0.0029483671765774488, "selected_pairs": 26967.4, "step": 14030, "student_distance_mean": 1205.9204467773438, "teacher_distance_mean": 0.8553227722644806, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0029483671765774488, "weighted_relation_loss": 0.0029483671765774488 }, { "action_query_batch_std": 21.1016508102417, "action_query_norm": 908.2793151855469, "action_relation_loss": 0.0030963321682065726, "auxiliary_loss_weight": 1.0, "epoch": 13.13376987839102, "flow_matching_loss": 0.030886268801987173, "grad_norm": 0.11927606910467148, "invalid_tail_samples": 25.2, "learning_rate": 5.9374479613425e-05, "loss": 0.034, "positive_teacher_pairs": 26530.9, "relation_loss": 0.0030963321682065726, "selected_pairs": 26530.9, "step": 14040, "student_distance_mean": 1206.3636108398437, "teacher_distance_mean": 0.858187985420227, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0030963321682065726, "weighted_relation_loss": 0.0030963321682065726 }, { "action_query_batch_std": 21.195286178588866, "action_query_norm": 911.9069580078125, "action_relation_loss": 0.0030109504936262966, "auxiliary_loss_weight": 1.0, "epoch": 13.14312441534144, "flow_matching_loss": 0.031913322396576405, "grad_norm": 0.1095440685749054, "invalid_tail_samples": 27.3, "learning_rate": 5.932033565699704e-05, "loss": 0.0349, "positive_teacher_pairs": 26044.5, "relation_loss": 0.0030109504936262966, "selected_pairs": 26044.5, "step": 14050, "student_distance_mean": 1210.9361694335937, "teacher_distance_mean": 0.8578296601772308, "valid_action_samples": 228.7, "weighted_auxiliary_loss": 0.0030109504936262966, "weighted_relation_loss": 0.0030109504936262966 }, { "action_query_batch_std": 21.469448852539063, "action_query_norm": 922.6944641113281, "action_relation_loss": 0.002962378156371415, "auxiliary_loss_weight": 1.0, "epoch": 13.152478952291862, "flow_matching_loss": 0.03098104428499937, "grad_norm": 0.12005019932985306, "invalid_tail_samples": 26.1, "learning_rate": 5.926618037548237e-05, "loss": 0.0339, "positive_teacher_pairs": 26323.2, "relation_loss": 0.002962378156371415, "selected_pairs": 26323.2, "step": 14060, "student_distance_mean": 1226.3337524414062, "teacher_distance_mean": 0.8634540498256683, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.002962378156371415, "weighted_relation_loss": 0.002962378156371415 }, { "action_query_batch_std": 20.90439853668213, "action_query_norm": 902.6258911132812, "action_relation_loss": 0.002925860835239291, "auxiliary_loss_weight": 1.0, "epoch": 13.161833489242282, "flow_matching_loss": 0.03115726578980684, "grad_norm": 0.12453266978263855, "invalid_tail_samples": 25.4, "learning_rate": 5.9212013834684824e-05, "loss": 0.0341, "positive_teacher_pairs": 26480.9, "relation_loss": 0.002925860835239291, "selected_pairs": 26480.9, "step": 14070, "student_distance_mean": 1194.4642333984375, "teacher_distance_mean": 0.8470171868801117, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.002925860835239291, "weighted_relation_loss": 0.002925860835239291 }, { "action_query_batch_std": 20.869795417785646, "action_query_norm": 899.0337280273437, "action_relation_loss": 0.003078291891142726, "auxiliary_loss_weight": 1.0, "epoch": 13.171188026192704, "flow_matching_loss": 0.030866640619933605, "grad_norm": 0.11314721405506134, "invalid_tail_samples": 23.4, "learning_rate": 5.9157836100421824e-05, "loss": 0.0339, "positive_teacher_pairs": 26952.2, "relation_loss": 0.003078291891142726, "selected_pairs": 26952.2, "step": 14080, "student_distance_mean": 1192.9825439453125, "teacher_distance_mean": 0.845092260837555, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.003078291891142726, "weighted_relation_loss": 0.003078291891142726 }, { "action_query_batch_std": 21.180053329467775, "action_query_norm": 909.7305847167969, "action_relation_loss": 0.0031191704794764517, "auxiliary_loss_weight": 1.0, "epoch": 13.180542563143124, "flow_matching_loss": 0.033345794677734374, "grad_norm": 0.1066761165857315, "invalid_tail_samples": 23.6, "learning_rate": 5.910364723852444e-05, "loss": 0.0365, "positive_teacher_pairs": 26897.0, "relation_loss": 0.0031191704794764517, "selected_pairs": 26897.0, "step": 14090, "student_distance_mean": 1203.5794311523437, "teacher_distance_mean": 0.8552297234535218, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0031191704794764517, "weighted_relation_loss": 0.0031191704794764517 }, { "action_query_batch_std": 21.084671401977538, "action_query_norm": 908.7634460449219, "action_relation_loss": 0.003006347268819809, "auxiliary_loss_weight": 1.0, "epoch": 13.189897100093546, "flow_matching_loss": 0.031278665736317636, "grad_norm": 0.13536547124385834, "invalid_tail_samples": 25.2, "learning_rate": 5.904944731483723e-05, "loss": 0.0343, "positive_teacher_pairs": 26528.1, "relation_loss": 0.003006347268819809, "selected_pairs": 26528.1, "step": 14100, "student_distance_mean": 1199.1730102539063, "teacher_distance_mean": 0.8526037573814392, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.003006347268819809, "weighted_relation_loss": 0.003006347268819809 }, { "action_query_batch_std": 20.830014419555663, "action_query_norm": 898.494873046875, "action_relation_loss": 0.003014687285758555, "auxiliary_loss_weight": 1.0, "epoch": 13.199251637043966, "flow_matching_loss": 0.03155278209596872, "grad_norm": 0.1293599158525467, "invalid_tail_samples": 24.5, "learning_rate": 5.899523639521825e-05, "loss": 0.0346, "positive_teacher_pairs": 26693.0, "relation_loss": 0.003014687285758555, "selected_pairs": 26693.0, "step": 14110, "student_distance_mean": 1189.1151733398438, "teacher_distance_mean": 0.8532336533069611, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.003014687285758555, "weighted_relation_loss": 0.003014687285758555 }, { "action_query_batch_std": 20.9736909866333, "action_query_norm": 902.5091796875, "action_relation_loss": 0.00313880939502269, "auxiliary_loss_weight": 1.0, "epoch": 13.208606173994387, "flow_matching_loss": 0.030937319993972777, "grad_norm": 0.10036126524209976, "invalid_tail_samples": 26.2, "learning_rate": 5.894101454553883e-05, "loss": 0.0341, "positive_teacher_pairs": 26299.5, "relation_loss": 0.00313880939502269, "selected_pairs": 26299.5, "step": 14120, "student_distance_mean": 1205.1204223632812, "teacher_distance_mean": 0.8592589855194092, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.00313880939502269, "weighted_relation_loss": 0.00313880939502269 }, { "action_query_batch_std": 21.07682247161865, "action_query_norm": 904.482373046875, "action_relation_loss": 0.003041559341363609, "auxiliary_loss_weight": 1.0, "epoch": 13.217960710944809, "flow_matching_loss": 0.030704452097415923, "grad_norm": 0.1346980184316635, "invalid_tail_samples": 25.3, "learning_rate": 5.888678183168368e-05, "loss": 0.0337, "positive_teacher_pairs": 26503.4, "relation_loss": 0.003041559341363609, "selected_pairs": 26503.4, "step": 14130, "student_distance_mean": 1206.8011596679687, "teacher_distance_mean": 0.8589671432971955, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.003041559341363609, "weighted_relation_loss": 0.003041559341363609 }, { "action_query_batch_std": 21.226298332214355, "action_query_norm": 910.9376586914062, "action_relation_loss": 0.0030360209988430143, "auxiliary_loss_weight": 1.0, "epoch": 13.227315247895229, "flow_matching_loss": 0.02928310986608267, "grad_norm": 0.1217498928308487, "invalid_tail_samples": 21.4, "learning_rate": 5.883253831955061e-05, "loss": 0.0323, "positive_teacher_pairs": 27409.9, "relation_loss": 0.0030360209988430143, "selected_pairs": 27409.9, "step": 14140, "student_distance_mean": 1207.790625, "teacher_distance_mean": 0.8579809427261352, "valid_action_samples": 234.6, "weighted_auxiliary_loss": 0.0030360209988430143, "weighted_relation_loss": 0.0030360209988430143 }, { "action_query_batch_std": 21.09931182861328, "action_query_norm": 908.3456481933594, "action_relation_loss": 0.00305679754819721, "auxiliary_loss_weight": 1.0, "epoch": 13.23666978484565, "flow_matching_loss": 0.030911459773778915, "grad_norm": 0.13153564929962158, "invalid_tail_samples": 23.2, "learning_rate": 5.8778284075050625e-05, "loss": 0.034, "positive_teacher_pairs": 26997.3, "relation_loss": 0.00305679754819721, "selected_pairs": 26997.3, "step": 14150, "student_distance_mean": 1206.4107421875, "teacher_distance_mean": 0.8586224734783172, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.00305679754819721, "weighted_relation_loss": 0.00305679754819721 }, { "action_query_batch_std": 20.906573867797853, "action_query_norm": 904.3330444335937, "action_relation_loss": 0.0031829931773245334, "auxiliary_loss_weight": 1.0, "epoch": 13.246024321796071, "flow_matching_loss": 0.029660378769040107, "grad_norm": 0.12242907285690308, "invalid_tail_samples": 23.0, "learning_rate": 5.872401916410777e-05, "loss": 0.0328, "positive_teacher_pairs": 27043.7, "relation_loss": 0.0031829931773245334, "selected_pairs": 27043.7, "step": 14160, "student_distance_mean": 1190.7569946289063, "teacher_distance_mean": 0.8471593856811523, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0031829931773245334, "weighted_relation_loss": 0.0031829931773245334 }, { "action_query_batch_std": 21.208576011657716, "action_query_norm": 913.4502380371093, "action_relation_loss": 0.003057685843668878, "auxiliary_loss_weight": 1.0, "epoch": 13.255378858746493, "flow_matching_loss": 0.029968149773776532, "grad_norm": 0.1048436164855957, "invalid_tail_samples": 22.0, "learning_rate": 5.8669743652659014e-05, "loss": 0.033, "positive_teacher_pairs": 27269.7, "relation_loss": 0.003057685843668878, "selected_pairs": 27269.7, "step": 14170, "student_distance_mean": 1211.6409545898437, "teacher_distance_mean": 0.8600100994110107, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.003057685843668878, "weighted_relation_loss": 0.003057685843668878 }, { "action_query_batch_std": 21.03897171020508, "action_query_norm": 906.3256713867188, "action_relation_loss": 0.0031415459467098116, "auxiliary_loss_weight": 1.0, "epoch": 13.264733395696913, "flow_matching_loss": 0.030773648433387278, "grad_norm": 0.11736388504505157, "invalid_tail_samples": 24.0, "learning_rate": 5.86154576066542e-05, "loss": 0.0339, "positive_teacher_pairs": 26804.7, "relation_loss": 0.0031415459467098116, "selected_pairs": 26804.7, "step": 14180, "student_distance_mean": 1197.6404418945312, "teacher_distance_mean": 0.8556435346603394, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0031415459467098116, "weighted_relation_loss": 0.0031415459467098116 }, { "action_query_batch_std": 21.129847908020018, "action_query_norm": 909.0245666503906, "action_relation_loss": 0.002942628646269441, "auxiliary_loss_weight": 1.0, "epoch": 13.274087932647333, "flow_matching_loss": 0.028518519550561904, "grad_norm": 0.09865543991327286, "invalid_tail_samples": 23.6, "learning_rate": 5.856116109205602e-05, "loss": 0.0315, "positive_teacher_pairs": 26897.6, "relation_loss": 0.002942628646269441, "selected_pairs": 26897.6, "step": 14190, "student_distance_mean": 1203.1217529296875, "teacher_distance_mean": 0.8520578563213348, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.002942628646269441, "weighted_relation_loss": 0.002942628646269441 }, { "action_query_batch_std": 20.794790077209473, "action_query_norm": 898.8761840820313, "action_relation_loss": 0.0031143705593422054, "auxiliary_loss_weight": 1.0, "epoch": 13.283442469597755, "flow_matching_loss": 0.029390907660126687, "grad_norm": 0.10633514076471329, "invalid_tail_samples": 23.1, "learning_rate": 5.850685417483983e-05, "loss": 0.0325, "positive_teacher_pairs": 27012.3, "relation_loss": 0.0031143705593422054, "selected_pairs": 27012.3, "step": 14200, "student_distance_mean": 1189.6833251953126, "teacher_distance_mean": 0.8457768499851227, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0031143705593422054, "weighted_relation_loss": 0.0031143705593422054 }, { "action_query_batch_std": 21.15399513244629, "action_query_norm": 909.1578186035156, "action_relation_loss": 0.002872807835228741, "auxiliary_loss_weight": 1.0, "epoch": 13.292797006548176, "flow_matching_loss": 0.028670552372932433, "grad_norm": 0.10203316807746887, "invalid_tail_samples": 25.7, "learning_rate": 5.8452536920993684e-05, "loss": 0.0315, "positive_teacher_pairs": 26422.8, "relation_loss": 0.002872807835228741, "selected_pairs": 26422.8, "step": 14210, "student_distance_mean": 1204.4626831054688, "teacher_distance_mean": 0.8572965562343597, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.002872807835228741, "weighted_relation_loss": 0.002872807835228741 }, { "action_query_batch_std": 21.031172943115234, "action_query_norm": 907.6151062011719, "action_relation_loss": 0.003170311264693737, "auxiliary_loss_weight": 1.0, "epoch": 13.302151543498598, "flow_matching_loss": 0.030256953090429306, "grad_norm": 0.10358598828315735, "invalid_tail_samples": 24.4, "learning_rate": 5.839820939651817e-05, "loss": 0.0334, "positive_teacher_pairs": 26709.5, "relation_loss": 0.003170311264693737, "selected_pairs": 26709.5, "step": 14220, "student_distance_mean": 1197.99873046875, "teacher_distance_mean": 0.852701872587204, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.003170311264693737, "weighted_relation_loss": 0.003170311264693737 }, { "action_query_batch_std": 20.878776168823244, "action_query_norm": 903.2054077148438, "action_relation_loss": 0.003033492551185191, "auxiliary_loss_weight": 1.0, "epoch": 13.311506080449018, "flow_matching_loss": 0.030025980435311794, "grad_norm": 0.09502322226762772, "invalid_tail_samples": 24.5, "learning_rate": 5.834387166742632e-05, "loss": 0.0331, "positive_teacher_pairs": 26697.4, "relation_loss": 0.003033492551185191, "selected_pairs": 26697.4, "step": 14230, "student_distance_mean": 1190.6444458007813, "teacher_distance_mean": 0.850729787349701, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.003033492551185191, "weighted_relation_loss": 0.003033492551185191 }, { "action_query_batch_std": 20.935446548461915, "action_query_norm": 903.4807922363282, "action_relation_loss": 0.003070836653932929, "auxiliary_loss_weight": 1.0, "epoch": 13.320860617399438, "flow_matching_loss": 0.028195539489388466, "grad_norm": 0.07631529867649078, "invalid_tail_samples": 24.7, "learning_rate": 5.828952379974364e-05, "loss": 0.0313, "positive_teacher_pairs": 26657.5, "relation_loss": 0.003070836653932929, "selected_pairs": 26657.5, "step": 14240, "student_distance_mean": 1201.703662109375, "teacher_distance_mean": 0.8542163848876954, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.003070836653932929, "weighted_relation_loss": 0.003070836653932929 }, { "action_query_batch_std": 21.121080589294433, "action_query_norm": 910.8560791015625, "action_relation_loss": 0.003052148735150695, "auxiliary_loss_weight": 1.0, "epoch": 13.33021515434986, "flow_matching_loss": 0.030770627409219743, "grad_norm": 0.10344207286834717, "invalid_tail_samples": 23.0, "learning_rate": 5.8235165859507864e-05, "loss": 0.0338, "positive_teacher_pairs": 27042.5, "relation_loss": 0.003052148735150695, "selected_pairs": 27042.5, "step": 14250, "student_distance_mean": 1207.3380981445312, "teacher_distance_mean": 0.8556453645229339, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.003052148735150695, "weighted_relation_loss": 0.003052148735150695 }, { "action_query_batch_std": 21.220546531677247, "action_query_norm": 911.0009826660156, "action_relation_loss": 0.0029433154501020907, "auxiliary_loss_weight": 1.0, "epoch": 13.33956969130028, "flow_matching_loss": 0.02921273112297058, "grad_norm": 0.09860143810510635, "invalid_tail_samples": 24.4, "learning_rate": 5.818079791276907e-05, "loss": 0.0322, "positive_teacher_pairs": 26709.1, "relation_loss": 0.0029433154501020907, "selected_pairs": 26709.1, "step": 14260, "student_distance_mean": 1209.0811401367187, "teacher_distance_mean": 0.8586938321590424, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0029433154501020907, "weighted_relation_loss": 0.0029433154501020907 }, { "action_query_batch_std": 20.98329849243164, "action_query_norm": 903.24306640625, "action_relation_loss": 0.00291746009606868, "auxiliary_loss_weight": 1.0, "epoch": 13.348924228250702, "flow_matching_loss": 0.030240236967802047, "grad_norm": 0.09844863414764404, "invalid_tail_samples": 26.0, "learning_rate": 5.8126420025589415e-05, "loss": 0.0332, "positive_teacher_pairs": 26344.3, "relation_loss": 0.00291746009606868, "selected_pairs": 26344.3, "step": 14270, "student_distance_mean": 1203.2829223632812, "teacher_distance_mean": 0.8525192081928253, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.00291746009606868, "weighted_relation_loss": 0.00291746009606868 }, { "action_query_batch_std": 20.957768821716307, "action_query_norm": 902.1818481445313, "action_relation_loss": 0.002975944918580353, "auxiliary_loss_weight": 1.0, "epoch": 13.358278765201122, "flow_matching_loss": 0.02721692007035017, "grad_norm": 0.11159870028495789, "invalid_tail_samples": 24.6, "learning_rate": 5.807203226404313e-05, "loss": 0.0302, "positive_teacher_pairs": 26672.0, "relation_loss": 0.002975944918580353, "selected_pairs": 26672.0, "step": 14280, "student_distance_mean": 1193.6228149414062, "teacher_distance_mean": 0.8462829411029815, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.002975944918580353, "weighted_relation_loss": 0.002975944918580353 }, { "action_query_batch_std": 20.922381591796874, "action_query_norm": 901.87685546875, "action_relation_loss": 0.0030714013613760472, "auxiliary_loss_weight": 1.0, "epoch": 13.367633302151544, "flow_matching_loss": 0.030370667949318884, "grad_norm": 0.12806940078735352, "invalid_tail_samples": 23.8, "learning_rate": 5.801763469421652e-05, "loss": 0.0334, "positive_teacher_pairs": 26849.9, "relation_loss": 0.0030714013613760472, "selected_pairs": 26849.9, "step": 14290, "student_distance_mean": 1194.4391357421875, "teacher_distance_mean": 0.8513631343841552, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0030714013613760472, "weighted_relation_loss": 0.0030714013613760472 }, { "action_query_batch_std": 21.16916904449463, "action_query_norm": 910.0763305664062, "action_relation_loss": 0.0031164188403636217, "auxiliary_loss_weight": 1.0, "epoch": 13.376987839101965, "flow_matching_loss": 0.029726553335785867, "grad_norm": 0.1337982416152954, "invalid_tail_samples": 23.1, "learning_rate": 5.796322738220774e-05, "loss": 0.0328, "positive_teacher_pairs": 27014.1, "relation_loss": 0.0031164188403636217, "selected_pairs": 27014.1, "step": 14300, "student_distance_mean": 1206.2910766601562, "teacher_distance_mean": 0.8548417091369629, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0031164188403636217, "weighted_relation_loss": 0.0031164188403636217 }, { "action_query_batch_std": 21.10499801635742, "action_query_norm": 908.5887145996094, "action_relation_loss": 0.0030061632627621294, "auxiliary_loss_weight": 1.0, "epoch": 13.386342376052385, "flow_matching_loss": 0.030194771848618983, "grad_norm": 0.11813928931951523, "invalid_tail_samples": 24.6, "learning_rate": 5.79088103941268e-05, "loss": 0.0332, "positive_teacher_pairs": 26665.7, "relation_loss": 0.0030061632627621294, "selected_pairs": 26665.7, "step": 14310, "student_distance_mean": 1207.1586303710938, "teacher_distance_mean": 0.8520420730113983, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0030061632627621294, "weighted_relation_loss": 0.0030061632627621294 }, { "action_query_batch_std": 20.730379486083983, "action_query_norm": 899.8278686523438, "action_relation_loss": 0.003136357292532921, "auxiliary_loss_weight": 1.0, "epoch": 13.395696913002807, "flow_matching_loss": 0.03165351748466492, "grad_norm": 0.11181087791919708, "invalid_tail_samples": 25.4, "learning_rate": 5.785438379609549e-05, "loss": 0.0348, "positive_teacher_pairs": 26482.2, "relation_loss": 0.003136357292532921, "selected_pairs": 26482.2, "step": 14320, "student_distance_mean": 1188.2551879882812, "teacher_distance_mean": 0.839301061630249, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.003136357292532921, "weighted_relation_loss": 0.003136357292532921 }, { "action_query_batch_std": 21.189084815979005, "action_query_norm": 909.3086730957032, "action_relation_loss": 0.0029140398604795338, "auxiliary_loss_weight": 1.0, "epoch": 13.405051449953227, "flow_matching_loss": 0.03228648882359266, "grad_norm": 0.11068630963563919, "invalid_tail_samples": 24.8, "learning_rate": 5.779994765424724e-05, "loss": 0.0352, "positive_teacher_pairs": 26630.1, "relation_loss": 0.0029140398604795338, "selected_pairs": 26630.1, "step": 14330, "student_distance_mean": 1212.2724487304688, "teacher_distance_mean": 0.8602768898010253, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0029140398604795338, "weighted_relation_loss": 0.0029140398604795338 }, { "action_query_batch_std": 21.324158096313475, "action_query_norm": 911.918896484375, "action_relation_loss": 0.003028898942284286, "auxiliary_loss_weight": 1.0, "epoch": 13.414405986903649, "flow_matching_loss": 0.029717060923576354, "grad_norm": 0.11520341783761978, "invalid_tail_samples": 25.1, "learning_rate": 5.7745502034727114e-05, "loss": 0.0327, "positive_teacher_pairs": 26548.8, "relation_loss": 0.003028898942284286, "selected_pairs": 26548.8, "step": 14340, "student_distance_mean": 1212.1098388671876, "teacher_distance_mean": 0.8622537851333618, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.003028898942284286, "weighted_relation_loss": 0.003028898942284286 }, { "action_query_batch_std": 21.09427127838135, "action_query_norm": 909.7019958496094, "action_relation_loss": 0.0030216566985473035, "auxiliary_loss_weight": 1.0, "epoch": 13.42376052385407, "flow_matching_loss": 0.030553489364683627, "grad_norm": 0.1420345902442932, "invalid_tail_samples": 23.8, "learning_rate": 5.769104700369164e-05, "loss": 0.0336, "positive_teacher_pairs": 26848.3, "relation_loss": 0.0030216566985473035, "selected_pairs": 26848.3, "step": 14350, "student_distance_mean": 1206.4686157226563, "teacher_distance_mean": 0.8480804145336152, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0030216566985473035, "weighted_relation_loss": 0.0030216566985473035 }, { "action_query_batch_std": 21.26530342102051, "action_query_norm": 916.3806396484375, "action_relation_loss": 0.0030228606425225734, "auxiliary_loss_weight": 1.0, "epoch": 13.43311506080449, "flow_matching_loss": 0.030904289707541464, "grad_norm": 0.14138659834861755, "invalid_tail_samples": 24.7, "learning_rate": 5.7636582627308854e-05, "loss": 0.0339, "positive_teacher_pairs": 26644.8, "relation_loss": 0.0030228606425225734, "selected_pairs": 26644.8, "step": 14360, "student_distance_mean": 1219.8882568359375, "teacher_distance_mean": 0.8597558081150055, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0030228606425225734, "weighted_relation_loss": 0.0030228606425225734 }, { "action_query_batch_std": 21.34082450866699, "action_query_norm": 912.8539916992188, "action_relation_loss": 0.003016274678520858, "auxiliary_loss_weight": 1.0, "epoch": 13.442469597754911, "flow_matching_loss": 0.03028734289109707, "grad_norm": 0.12791308760643005, "invalid_tail_samples": 26.7, "learning_rate": 5.7582108971758095e-05, "loss": 0.0333, "positive_teacher_pairs": 26184.2, "relation_loss": 0.003016274678520858, "selected_pairs": 26184.2, "step": 14370, "student_distance_mean": 1218.862548828125, "teacher_distance_mean": 0.8574795246124267, "valid_action_samples": 229.3, "weighted_auxiliary_loss": 0.003016274678520858, "weighted_relation_loss": 0.003016274678520858 }, { "action_query_batch_std": 21.032852745056154, "action_query_norm": 907.1168518066406, "action_relation_loss": 0.003025973658077419, "auxiliary_loss_weight": 1.0, "epoch": 13.451824134705332, "flow_matching_loss": 0.030354331620037554, "grad_norm": 0.1297764927148819, "invalid_tail_samples": 24.0, "learning_rate": 5.752762610322999e-05, "loss": 0.0334, "positive_teacher_pairs": 26801.9, "relation_loss": 0.003025973658077419, "selected_pairs": 26801.9, "step": 14380, "student_distance_mean": 1205.5558715820312, "teacher_distance_mean": 0.8519717991352082, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.003025973658077419, "weighted_relation_loss": 0.003025973658077419 }, { "action_query_batch_std": 20.728552055358886, "action_query_norm": 897.3364135742188, "action_relation_loss": 0.0029562465846538545, "auxiliary_loss_weight": 1.0, "epoch": 13.461178671655754, "flow_matching_loss": 0.02860226798802614, "grad_norm": 0.10581327229738235, "invalid_tail_samples": 24.3, "learning_rate": 5.747313408792636e-05, "loss": 0.0316, "positive_teacher_pairs": 26741.5, "relation_loss": 0.0029562465846538545, "selected_pairs": 26741.5, "step": 14390, "student_distance_mean": 1181.9599365234376, "teacher_distance_mean": 0.8407695353031158, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0029562465846538545, "weighted_relation_loss": 0.0029562465846538545 }, { "action_query_batch_std": 20.920356369018556, "action_query_norm": 902.8196044921875, "action_relation_loss": 0.0030854498967528344, "auxiliary_loss_weight": 1.0, "epoch": 13.470533208606174, "flow_matching_loss": 0.030446811206638814, "grad_norm": 0.16509419679641724, "invalid_tail_samples": 25.1, "learning_rate": 5.741863299206014e-05, "loss": 0.0335, "positive_teacher_pairs": 26550.0, "relation_loss": 0.0030854498967528344, "selected_pairs": 26550.0, "step": 14400, "student_distance_mean": 1198.0838745117187, "teacher_distance_mean": 0.8502983033657074, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0030854498967528344, "weighted_relation_loss": 0.0030854498967528344 }, { "action_query_batch_std": 21.371310234069824, "action_query_norm": 919.0771301269531, "action_relation_loss": 0.003004990215413272, "auxiliary_loss_weight": 1.0, "epoch": 13.479887745556596, "flow_matching_loss": 0.027724551036953926, "grad_norm": 0.12387571483850479, "invalid_tail_samples": 24.2, "learning_rate": 5.73641228818553e-05, "loss": 0.0307, "positive_teacher_pairs": 26754.5, "relation_loss": 0.003004990215413272, "selected_pairs": 26754.5, "step": 14410, "student_distance_mean": 1227.6506958007812, "teacher_distance_mean": 0.8600599825382232, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.003004990215413272, "weighted_relation_loss": 0.003004990215413272 }, { "action_query_batch_std": 20.98091640472412, "action_query_norm": 906.67314453125, "action_relation_loss": 0.0029272859916090964, "auxiliary_loss_weight": 1.0, "epoch": 13.489242282507016, "flow_matching_loss": 0.029600402899086477, "grad_norm": 0.10764086991548538, "invalid_tail_samples": 21.2, "learning_rate": 5.730960382354676e-05, "loss": 0.0325, "positive_teacher_pairs": 27454.1, "relation_loss": 0.0029272859916090964, "selected_pairs": 27454.1, "step": 14420, "student_distance_mean": 1197.9368041992188, "teacher_distance_mean": 0.8504867374897003, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.0029272859916090964, "weighted_relation_loss": 0.0029272859916090964 }, { "action_query_batch_std": 21.141191482543945, "action_query_norm": 909.9994140625, "action_relation_loss": 0.0030367433093488215, "auxiliary_loss_weight": 1.0, "epoch": 13.498596819457436, "flow_matching_loss": 0.028732858411967755, "grad_norm": 0.09541627019643784, "invalid_tail_samples": 21.6, "learning_rate": 5.725507588338035e-05, "loss": 0.0318, "positive_teacher_pairs": 27368.8, "relation_loss": 0.0030367433093488215, "selected_pairs": 27368.8, "step": 14430, "student_distance_mean": 1210.9676635742187, "teacher_distance_mean": 0.8623886644840241, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.0030367433093488215, "weighted_relation_loss": 0.0030367433093488215 }, { "action_query_batch_std": 20.988517189025877, "action_query_norm": 903.6695617675781, "action_relation_loss": 0.0029310818528756498, "auxiliary_loss_weight": 1.0, "epoch": 13.507951356407858, "flow_matching_loss": 0.02784003522247076, "grad_norm": 0.1070350781083107, "invalid_tail_samples": 22.4, "learning_rate": 5.7200539127612604e-05, "loss": 0.0308, "positive_teacher_pairs": 27182.5, "relation_loss": 0.0029310818528756498, "selected_pairs": 27182.5, "step": 14440, "student_distance_mean": 1201.9901611328125, "teacher_distance_mean": 0.8531279981136322, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.0029310818528756498, "weighted_relation_loss": 0.0029310818528756498 }, { "action_query_batch_std": 20.898882484436037, "action_query_norm": 901.912353515625, "action_relation_loss": 0.0029939547646790745, "auxiliary_loss_weight": 1.0, "epoch": 13.517305893358278, "flow_matching_loss": 0.03150506429374218, "grad_norm": 0.1170646920800209, "invalid_tail_samples": 22.9, "learning_rate": 5.714599362251087e-05, "loss": 0.0345, "positive_teacher_pairs": 27060.6, "relation_loss": 0.0029939547646790745, "selected_pairs": 27060.6, "step": 14450, "student_distance_mean": 1197.573486328125, "teacher_distance_mean": 0.8528855621814728, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0029939547646790745, "weighted_relation_loss": 0.0029939547646790745 }, { "action_query_batch_std": 21.214208984375, "action_query_norm": 909.4951721191406, "action_relation_loss": 0.003087754803709686, "auxiliary_loss_weight": 1.0, "epoch": 13.5266604303087, "flow_matching_loss": 0.03133999463170767, "grad_norm": 0.10458499193191528, "invalid_tail_samples": 22.7, "learning_rate": 5.709143943435307e-05, "loss": 0.0344, "positive_teacher_pairs": 27106.4, "relation_loss": 0.003087754803709686, "selected_pairs": 27106.4, "step": 14460, "student_distance_mean": 1209.4234985351563, "teacher_distance_mean": 0.8628775477409363, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.003087754803709686, "weighted_relation_loss": 0.003087754803709686 }, { "action_query_batch_std": 21.146630668640135, "action_query_norm": 910.1722961425781, "action_relation_loss": 0.0030683652264997365, "auxiliary_loss_weight": 1.0, "epoch": 13.53601496725912, "flow_matching_loss": 0.02926539909094572, "grad_norm": 0.11953438818454742, "invalid_tail_samples": 24.7, "learning_rate": 5.7036876629427646e-05, "loss": 0.0323, "positive_teacher_pairs": 26642.5, "relation_loss": 0.0030683652264997365, "selected_pairs": 26642.5, "step": 14470, "student_distance_mean": 1209.8565185546875, "teacher_distance_mean": 0.8593600571155549, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0030683652264997365, "weighted_relation_loss": 0.0030683652264997365 }, { "action_query_batch_std": 21.17704372406006, "action_query_norm": 909.9609252929688, "action_relation_loss": 0.002963961637578905, "auxiliary_loss_weight": 1.0, "epoch": 13.545369504209543, "flow_matching_loss": 0.028692361898720264, "grad_norm": 0.13464152812957764, "invalid_tail_samples": 23.7, "learning_rate": 5.698230527403361e-05, "loss": 0.0317, "positive_teacher_pairs": 26872.1, "relation_loss": 0.002963961637578905, "selected_pairs": 26872.1, "step": 14480, "student_distance_mean": 1208.5633056640625, "teacher_distance_mean": 0.8605400860309601, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.002963961637578905, "weighted_relation_loss": 0.002963961637578905 }, { "action_query_batch_std": 20.83612766265869, "action_query_norm": 898.8544311523438, "action_relation_loss": 0.00281234176363796, "auxiliary_loss_weight": 1.0, "epoch": 13.554724041159963, "flow_matching_loss": 0.030043840408325195, "grad_norm": 0.12099742144346237, "invalid_tail_samples": 25.4, "learning_rate": 5.6927725434480274e-05, "loss": 0.0329, "positive_teacher_pairs": 26482.2, "relation_loss": 0.00281234176363796, "selected_pairs": 26482.2, "step": 14490, "student_distance_mean": 1195.6005615234376, "teacher_distance_mean": 0.8495809257030487, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.00281234176363796, "weighted_relation_loss": 0.00281234176363796 }, { "action_query_batch_std": 21.198474502563478, "action_query_norm": 909.5517761230469, "action_relation_loss": 0.00296785079408437, "auxiliary_loss_weight": 1.0, "epoch": 13.564078578110383, "flow_matching_loss": 0.029071183502674104, "grad_norm": 0.12086360901594162, "invalid_tail_samples": 25.2, "learning_rate": 5.687313717708728e-05, "loss": 0.032, "positive_teacher_pairs": 26522.0, "relation_loss": 0.00296785079408437, "selected_pairs": 26522.0, "step": 14500, "student_distance_mean": 1214.0696166992188, "teacher_distance_mean": 0.860386210680008, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.00296785079408437, "weighted_relation_loss": 0.00296785079408437 }, { "action_query_batch_std": 21.123915672302246, "action_query_norm": 907.9620971679688, "action_relation_loss": 0.003074499871581793, "auxiliary_loss_weight": 1.0, "epoch": 13.573433115060805, "flow_matching_loss": 0.029239821434020995, "grad_norm": 0.12565861642360687, "invalid_tail_samples": 23.5, "learning_rate": 5.681854056818453e-05, "loss": 0.0323, "positive_teacher_pairs": 26919.3, "relation_loss": 0.003074499871581793, "selected_pairs": 26919.3, "step": 14510, "student_distance_mean": 1209.38681640625, "teacher_distance_mean": 0.8555406391620636, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.003074499871581793, "weighted_relation_loss": 0.003074499871581793 }, { "action_query_batch_std": 21.195989418029786, "action_query_norm": 907.5986083984375, "action_relation_loss": 0.0029926891205832363, "auxiliary_loss_weight": 1.0, "epoch": 13.582787652011225, "flow_matching_loss": 0.030126029066741465, "grad_norm": 0.1278664469718933, "invalid_tail_samples": 21.1, "learning_rate": 5.676393567411205e-05, "loss": 0.0331, "positive_teacher_pairs": 27484.0, "relation_loss": 0.0029926891205832363, "selected_pairs": 27484.0, "step": 14520, "student_distance_mean": 1206.2856079101562, "teacher_distance_mean": 0.85482457280159, "valid_action_samples": 234.9, "weighted_auxiliary_loss": 0.0029926891205832363, "weighted_relation_loss": 0.0029926891205832363 }, { "action_query_batch_std": 21.237472152709962, "action_query_norm": 912.7411376953125, "action_relation_loss": 0.002992297033779323, "auxiliary_loss_weight": 1.0, "epoch": 13.592142188961647, "flow_matching_loss": 0.031417895667254926, "grad_norm": 0.11705637723207474, "invalid_tail_samples": 23.4, "learning_rate": 5.670932256121991e-05, "loss": 0.0344, "positive_teacher_pairs": 26943.1, "relation_loss": 0.002992297033779323, "selected_pairs": 26943.1, "step": 14530, "student_distance_mean": 1209.7008056640625, "teacher_distance_mean": 0.8541157066822052, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.002992297033779323, "weighted_relation_loss": 0.002992297033779323 }, { "action_query_batch_std": 21.2546106338501, "action_query_norm": 912.8210083007813, "action_relation_loss": 0.00288533850107342, "auxiliary_loss_weight": 1.0, "epoch": 13.601496725912067, "flow_matching_loss": 0.02989166509360075, "grad_norm": 0.09312086552381516, "invalid_tail_samples": 23.2, "learning_rate": 5.6654701295868216e-05, "loss": 0.0328, "positive_teacher_pairs": 26988.0, "relation_loss": 0.00288533850107342, "selected_pairs": 26988.0, "step": 14540, "student_distance_mean": 1214.4966430664062, "teacher_distance_mean": 0.8585104525089264, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.00288533850107342, "weighted_relation_loss": 0.00288533850107342 }, { "action_query_batch_std": 21.208817863464354, "action_query_norm": 911.8076599121093, "action_relation_loss": 0.00294973193667829, "auxiliary_loss_weight": 1.0, "epoch": 13.610851262862488, "flow_matching_loss": 0.029444769397377966, "grad_norm": 0.1160234585404396, "invalid_tail_samples": 23.5, "learning_rate": 5.660007194442697e-05, "loss": 0.0324, "positive_teacher_pairs": 26924.0, "relation_loss": 0.00294973193667829, "selected_pairs": 26924.0, "step": 14550, "student_distance_mean": 1207.94111328125, "teacher_distance_mean": 0.8512810289859771, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.00294973193667829, "weighted_relation_loss": 0.00294973193667829 }, { "action_query_batch_std": 21.029654121398927, "action_query_norm": 906.3027893066406, "action_relation_loss": 0.0029826949583366515, "auxiliary_loss_weight": 1.0, "epoch": 13.62020579981291, "flow_matching_loss": 0.03101598359644413, "grad_norm": 0.0954645574092865, "invalid_tail_samples": 21.6, "learning_rate": 5.6545434573275946e-05, "loss": 0.034, "positive_teacher_pairs": 27361.7, "relation_loss": 0.0029826949583366515, "selected_pairs": 27361.7, "step": 14560, "student_distance_mean": 1196.0894287109375, "teacher_distance_mean": 0.8415048301219941, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.0029826949583366515, "weighted_relation_loss": 0.0029826949583366515 }, { "action_query_batch_std": 21.232928657531737, "action_query_norm": 913.5438598632812, "action_relation_loss": 0.0030432306695729492, "auxiliary_loss_weight": 1.0, "epoch": 13.62956033676333, "flow_matching_loss": 0.03035280816257, "grad_norm": 0.1339583545923233, "invalid_tail_samples": 22.9, "learning_rate": 5.649078924880472e-05, "loss": 0.0334, "positive_teacher_pairs": 27062.5, "relation_loss": 0.0030432306695729492, "selected_pairs": 27062.5, "step": 14570, "student_distance_mean": 1216.0343383789063, "teacher_distance_mean": 0.8600736439228058, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0030432306695729492, "weighted_relation_loss": 0.0030432306695729492 }, { "action_query_batch_std": 21.457393836975097, "action_query_norm": 919.8310668945312, "action_relation_loss": 0.0030176621628925206, "auxiliary_loss_weight": 1.0, "epoch": 13.638914873713752, "flow_matching_loss": 0.0284288689494133, "grad_norm": 0.12506675720214844, "invalid_tail_samples": 24.0, "learning_rate": 5.643613603741252e-05, "loss": 0.0314, "positive_teacher_pairs": 26802.0, "relation_loss": 0.0030176621628925206, "selected_pairs": 26802.0, "step": 14580, "student_distance_mean": 1224.2495727539062, "teacher_distance_mean": 0.8629280030727386, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0030176621628925206, "weighted_relation_loss": 0.0030176621628925206 }, { "action_query_batch_std": 21.533653831481935, "action_query_norm": 923.4563110351562, "action_relation_loss": 0.0029508905950933694, "auxiliary_loss_weight": 1.0, "epoch": 13.648269410664172, "flow_matching_loss": 0.030204891972243787, "grad_norm": 0.11519184708595276, "invalid_tail_samples": 24.5, "learning_rate": 5.6381475005508154e-05, "loss": 0.0332, "positive_teacher_pairs": 26687.4, "relation_loss": 0.0029508905950933694, "selected_pairs": 26687.4, "step": 14590, "student_distance_mean": 1225.5941528320313, "teacher_distance_mean": 0.8615807473659516, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0029508905950933694, "weighted_relation_loss": 0.0029508905950933694 }, { "action_query_batch_std": 20.948582077026366, "action_query_norm": 902.2205749511719, "action_relation_loss": 0.0030711821746081114, "auxiliary_loss_weight": 1.0, "epoch": 13.657623947614592, "flow_matching_loss": 0.030089784413576126, "grad_norm": 0.12215182930231094, "invalid_tail_samples": 24.9, "learning_rate": 5.632680621950992e-05, "loss": 0.0332, "positive_teacher_pairs": 26598.0, "relation_loss": 0.0030711821746081114, "selected_pairs": 26598.0, "step": 14600, "student_distance_mean": 1199.4656494140625, "teacher_distance_mean": 0.8482327103614807, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0030711821746081114, "weighted_relation_loss": 0.0030711821746081114 }, { "action_query_batch_std": 21.20304298400879, "action_query_norm": 910.7561462402343, "action_relation_loss": 0.0030147148529067634, "auxiliary_loss_weight": 1.0, "epoch": 13.666978484565014, "flow_matching_loss": 0.029350679740309714, "grad_norm": 0.10997838526964188, "invalid_tail_samples": 25.6, "learning_rate": 5.627212974584555e-05, "loss": 0.0324, "positive_teacher_pairs": 26434.8, "relation_loss": 0.0030147148529067634, "selected_pairs": 26434.8, "step": 14610, "student_distance_mean": 1211.9776123046875, "teacher_distance_mean": 0.8542099952697754, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.0030147148529067634, "weighted_relation_loss": 0.0030147148529067634 }, { "action_query_batch_std": 20.848536682128906, "action_query_norm": 899.5171081542969, "action_relation_loss": 0.0031438467325642706, "auxiliary_loss_weight": 1.0, "epoch": 13.676333021515434, "flow_matching_loss": 0.02865844089537859, "grad_norm": 0.1236695945262909, "invalid_tail_samples": 24.4, "learning_rate": 5.62174456509521e-05, "loss": 0.0318, "positive_teacher_pairs": 26718.9, "relation_loss": 0.0031438467325642706, "selected_pairs": 26718.9, "step": 14620, "student_distance_mean": 1192.8822875976562, "teacher_distance_mean": 0.8434093952178955, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0031438467325642706, "weighted_relation_loss": 0.0031438467325642706 }, { "action_query_batch_std": 21.002281379699706, "action_query_norm": 904.989697265625, "action_relation_loss": 0.003163846442475915, "auxiliary_loss_weight": 1.0, "epoch": 13.685687558465856, "flow_matching_loss": 0.029698711074888706, "grad_norm": 0.09876105189323425, "invalid_tail_samples": 24.1, "learning_rate": 5.616275400127594e-05, "loss": 0.0329, "positive_teacher_pairs": 26794.1, "relation_loss": 0.003163846442475915, "selected_pairs": 26794.1, "step": 14630, "student_distance_mean": 1198.5323486328125, "teacher_distance_mean": 0.8515236794948577, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.003163846442475915, "weighted_relation_loss": 0.003163846442475915 }, { "action_query_batch_std": 21.305039978027345, "action_query_norm": 917.621044921875, "action_relation_loss": 0.0030057530151680113, "auxiliary_loss_weight": 1.0, "epoch": 13.695042095416277, "flow_matching_loss": 0.029253643378615378, "grad_norm": 0.10395058244466782, "invalid_tail_samples": 23.0, "learning_rate": 5.610805486327254e-05, "loss": 0.0323, "positive_teacher_pairs": 27032.2, "relation_loss": 0.0030057530151680113, "selected_pairs": 27032.2, "step": 14640, "student_distance_mean": 1218.57470703125, "teacher_distance_mean": 0.8551907241344452, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0030057530151680113, "weighted_relation_loss": 0.0030057530151680113 }, { "action_query_batch_std": 21.487647819519044, "action_query_norm": 923.0299011230469, "action_relation_loss": 0.003073065774515271, "auxiliary_loss_weight": 1.0, "epoch": 13.704396632366699, "flow_matching_loss": 0.0317283870652318, "grad_norm": 0.09725315123796463, "invalid_tail_samples": 21.0, "learning_rate": 5.6053348303406536e-05, "loss": 0.0348, "positive_teacher_pairs": 27504.2, "relation_loss": 0.003073065774515271, "selected_pairs": 27504.2, "step": 14650, "student_distance_mean": 1227.4778442382812, "teacher_distance_mean": 0.861364483833313, "valid_action_samples": 235.0, "weighted_auxiliary_loss": 0.003073065774515271, "weighted_relation_loss": 0.003073065774515271 }, { "action_query_batch_std": 20.88174648284912, "action_query_norm": 899.5912536621094, "action_relation_loss": 0.0029757777461782097, "auxiliary_loss_weight": 1.0, "epoch": 13.713751169317119, "flow_matching_loss": 0.030022672191262246, "grad_norm": 0.08731662482023239, "invalid_tail_samples": 23.4, "learning_rate": 5.599863438815156e-05, "loss": 0.033, "positive_teacher_pairs": 26939.2, "relation_loss": 0.0029757777461782097, "selected_pairs": 26939.2, "step": 14660, "student_distance_mean": 1193.2277587890626, "teacher_distance_mean": 0.840383893251419, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0029757777461782097, "weighted_relation_loss": 0.0029757777461782097 }, { "action_query_batch_std": 21.307144355773925, "action_query_norm": 914.0760437011719, "action_relation_loss": 0.0030252571683377027, "auxiliary_loss_weight": 1.0, "epoch": 13.723105706267539, "flow_matching_loss": 0.02907575685530901, "grad_norm": 0.09451666474342346, "invalid_tail_samples": 25.3, "learning_rate": 5.594391318399017e-05, "loss": 0.0321, "positive_teacher_pairs": 26504.1, "relation_loss": 0.0030252571683377027, "selected_pairs": 26504.1, "step": 14670, "student_distance_mean": 1219.4184448242188, "teacher_distance_mean": 0.8638604760169983, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0030252571683377027, "weighted_relation_loss": 0.0030252571683377027 }, { "action_query_batch_std": 21.256187629699706, "action_query_norm": 916.396484375, "action_relation_loss": 0.00307034773286432, "auxiliary_loss_weight": 1.0, "epoch": 13.732460243217961, "flow_matching_loss": 0.029356572404503824, "grad_norm": 0.1073387861251831, "invalid_tail_samples": 21.8, "learning_rate": 5.588918475741377e-05, "loss": 0.0324, "positive_teacher_pairs": 27316.3, "relation_loss": 0.00307034773286432, "selected_pairs": 27316.3, "step": 14680, "student_distance_mean": 1213.8249267578126, "teacher_distance_mean": 0.8576387822628021, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.00307034773286432, "weighted_relation_loss": 0.00307034773286432 }, { "action_query_batch_std": 21.037270545959473, "action_query_norm": 906.6048828125, "action_relation_loss": 0.002982402639463544, "auxiliary_loss_weight": 1.0, "epoch": 13.741814780168381, "flow_matching_loss": 0.029143095016479492, "grad_norm": 0.1456707864999771, "invalid_tail_samples": 26.1, "learning_rate": 5.5834449174922586e-05, "loss": 0.0321, "positive_teacher_pairs": 26320.7, "relation_loss": 0.002982402639463544, "selected_pairs": 26320.7, "step": 14690, "student_distance_mean": 1210.1425659179688, "teacher_distance_mean": 0.85689976811409, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.002982402639463544, "weighted_relation_loss": 0.002982402639463544 }, { "action_query_batch_std": 21.40889415740967, "action_query_norm": 919.7535095214844, "action_relation_loss": 0.0029688973911106585, "auxiliary_loss_weight": 1.0, "epoch": 13.751169317118803, "flow_matching_loss": 0.028363894671201706, "grad_norm": 0.12640278041362762, "invalid_tail_samples": 23.7, "learning_rate": 5.57797065030255e-05, "loss": 0.0313, "positive_teacher_pairs": 26871.1, "relation_loss": 0.0029688973911106585, "selected_pairs": 26871.1, "step": 14700, "student_distance_mean": 1224.54052734375, "teacher_distance_mean": 0.8647200524806976, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0029688973911106585, "weighted_relation_loss": 0.0029688973911106585 }, { "action_query_batch_std": 21.103541374206543, "action_query_norm": 910.8325866699219, "action_relation_loss": 0.002929518301971257, "auxiliary_loss_weight": 1.0, "epoch": 13.760523854069223, "flow_matching_loss": 0.030133615992963315, "grad_norm": 0.12375102192163467, "invalid_tail_samples": 22.5, "learning_rate": 5.5724956808240016e-05, "loss": 0.0331, "positive_teacher_pairs": 27149.8, "relation_loss": 0.002929518301971257, "selected_pairs": 27149.8, "step": 14710, "student_distance_mean": 1208.6448120117188, "teacher_distance_mean": 0.8489523470401764, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.002929518301971257, "weighted_relation_loss": 0.002929518301971257 }, { "action_query_batch_std": 21.445203399658205, "action_query_norm": 923.5084167480469, "action_relation_loss": 0.0030011964961886408, "auxiliary_loss_weight": 1.0, "epoch": 13.769878391019645, "flow_matching_loss": 0.029257524758577347, "grad_norm": 0.09310116618871689, "invalid_tail_samples": 22.2, "learning_rate": 5.567020015709219e-05, "loss": 0.0323, "positive_teacher_pairs": 27228.4, "relation_loss": 0.0030011964961886408, "selected_pairs": 27228.4, "step": 14720, "student_distance_mean": 1227.1160522460937, "teacher_distance_mean": 0.8592362225055694, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.0030011964961886408, "weighted_relation_loss": 0.0030011964961886408 }, { "action_query_batch_std": 21.456556129455567, "action_query_norm": 922.5895202636718, "action_relation_loss": 0.002950171590782702, "auxiliary_loss_weight": 1.0, "epoch": 13.779232927970066, "flow_matching_loss": 0.027899293042719365, "grad_norm": 0.09664922952651978, "invalid_tail_samples": 20.2, "learning_rate": 5.561543661611649e-05, "loss": 0.0308, "positive_teacher_pairs": 27686.0, "relation_loss": 0.002950171590782702, "selected_pairs": 27686.0, "step": 14730, "student_distance_mean": 1222.2858154296875, "teacher_distance_mean": 0.8588516235351562, "valid_action_samples": 235.8, "weighted_auxiliary_loss": 0.002950171590782702, "weighted_relation_loss": 0.002950171590782702 }, { "action_query_batch_std": 20.96094169616699, "action_query_norm": 902.704833984375, "action_relation_loss": 0.003132996428757906, "auxiliary_loss_weight": 1.0, "epoch": 13.788587464920486, "flow_matching_loss": 0.02943666372448206, "grad_norm": 0.12112318724393845, "invalid_tail_samples": 21.2, "learning_rate": 5.556066625185583e-05, "loss": 0.0326, "positive_teacher_pairs": 27458.2, "relation_loss": 0.003132996428757906, "selected_pairs": 27458.2, "step": 14740, "student_distance_mean": 1200.6476196289063, "teacher_distance_mean": 0.848674887418747, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.003132996428757906, "weighted_relation_loss": 0.003132996428757906 }, { "action_query_batch_std": 21.28333854675293, "action_query_norm": 912.9869323730469, "action_relation_loss": 0.002949489210732281, "auxiliary_loss_weight": 1.0, "epoch": 13.797942001870908, "flow_matching_loss": 0.0313170675188303, "grad_norm": 0.11770796775817871, "invalid_tail_samples": 22.9, "learning_rate": 5.550588913086131e-05, "loss": 0.0343, "positive_teacher_pairs": 27069.3, "relation_loss": 0.002949489210732281, "selected_pairs": 27069.3, "step": 14750, "student_distance_mean": 1215.971923828125, "teacher_distance_mean": 0.8612845838069916, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.002949489210732281, "weighted_relation_loss": 0.002949489210732281 }, { "action_query_batch_std": 21.392570114135744, "action_query_norm": 920.4749816894531, "action_relation_loss": 0.0028097368543967606, "auxiliary_loss_weight": 1.0, "epoch": 13.807296538821328, "flow_matching_loss": 0.027643343061208726, "grad_norm": 0.10955939441919327, "invalid_tail_samples": 21.2, "learning_rate": 5.545110531969234e-05, "loss": 0.0305, "positive_teacher_pairs": 27461.8, "relation_loss": 0.0028097368543967606, "selected_pairs": 27461.8, "step": 14760, "student_distance_mean": 1221.2358032226562, "teacher_distance_mean": 0.8621920943260193, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.0028097368543967606, "weighted_relation_loss": 0.0028097368543967606 }, { "action_query_batch_std": 21.072438621520995, "action_query_norm": 906.8395141601562, "action_relation_loss": 0.002991892979480326, "auxiliary_loss_weight": 1.0, "epoch": 13.81665107577175, "flow_matching_loss": 0.029899776354432105, "grad_norm": 0.11512665450572968, "invalid_tail_samples": 23.2, "learning_rate": 5.539631488491641e-05, "loss": 0.0329, "positive_teacher_pairs": 26993.7, "relation_loss": 0.002991892979480326, "selected_pairs": 26993.7, "step": 14770, "student_distance_mean": 1205.7814453125, "teacher_distance_mean": 0.8523908197879791, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.002991892979480326, "weighted_relation_loss": 0.002991892979480326 }, { "action_query_batch_std": 21.35821533203125, "action_query_norm": 918.5971618652344, "action_relation_loss": 0.0029539041686803104, "auxiliary_loss_weight": 1.0, "epoch": 13.82600561272217, "flow_matching_loss": 0.02970426604151726, "grad_norm": 0.10994391143321991, "invalid_tail_samples": 25.3, "learning_rate": 5.534151789310904e-05, "loss": 0.0327, "positive_teacher_pairs": 26510.3, "relation_loss": 0.0029539041686803104, "selected_pairs": 26510.3, "step": 14780, "student_distance_mean": 1223.979833984375, "teacher_distance_mean": 0.863664448261261, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0029539041686803104, "weighted_relation_loss": 0.0029539041686803104 }, { "action_query_batch_std": 21.369711494445802, "action_query_norm": 916.993115234375, "action_relation_loss": 0.002883579977788031, "auxiliary_loss_weight": 1.0, "epoch": 13.83536014967259, "flow_matching_loss": 0.028028635308146477, "grad_norm": 0.09381107240915298, "invalid_tail_samples": 23.4, "learning_rate": 5.528671441085376e-05, "loss": 0.0309, "positive_teacher_pairs": 26941.6, "relation_loss": 0.002883579977788031, "selected_pairs": 26941.6, "step": 14790, "student_distance_mean": 1223.7978271484376, "teacher_distance_mean": 0.8639601349830628, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.002883579977788031, "weighted_relation_loss": 0.002883579977788031 }, { "action_query_batch_std": 21.17067642211914, "action_query_norm": 911.9748352050781, "action_relation_loss": 0.003056326834484935, "auxiliary_loss_weight": 1.0, "epoch": 13.844714686623012, "flow_matching_loss": 0.030387192219495773, "grad_norm": 0.11603258550167084, "invalid_tail_samples": 26.5, "learning_rate": 5.523190450474197e-05, "loss": 0.0334, "positive_teacher_pairs": 26224.5, "relation_loss": 0.003056326834484935, "selected_pairs": 26224.5, "step": 14800, "student_distance_mean": 1214.2370727539062, "teacher_distance_mean": 0.8483813583850861, "valid_action_samples": 229.5, "weighted_auxiliary_loss": 0.003056326834484935, "weighted_relation_loss": 0.003056326834484935 }, { "action_query_batch_std": 21.174047660827636, "action_query_norm": 913.7631469726563, "action_relation_loss": 0.0029952968237921596, "auxiliary_loss_weight": 1.0, "epoch": 13.854069223573433, "flow_matching_loss": 0.03257732409983873, "grad_norm": 0.11128345876932144, "invalid_tail_samples": 22.5, "learning_rate": 5.5177088241372865e-05, "loss": 0.0356, "positive_teacher_pairs": 27159.1, "relation_loss": 0.0029952968237921596, "selected_pairs": 27159.1, "step": 14810, "student_distance_mean": 1212.1546508789063, "teacher_distance_mean": 0.848833966255188, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0029952968237921596, "weighted_relation_loss": 0.0029952968237921596 }, { "action_query_batch_std": 21.300818252563477, "action_query_norm": 914.4323791503906, "action_relation_loss": 0.0030114943627268078, "auxiliary_loss_weight": 1.0, "epoch": 13.863423760523855, "flow_matching_loss": 0.027566907927393913, "grad_norm": 0.09801476448774338, "invalid_tail_samples": 24.9, "learning_rate": 5.512226568735338e-05, "loss": 0.0306, "positive_teacher_pairs": 26596.8, "relation_loss": 0.0030114943627268078, "selected_pairs": 26596.8, "step": 14820, "student_distance_mean": 1216.4998413085937, "teacher_distance_mean": 0.8592183470726014, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0030114943627268078, "weighted_relation_loss": 0.0030114943627268078 }, { "action_query_batch_std": 21.289302825927734, "action_query_norm": 917.4024658203125, "action_relation_loss": 0.0030398876639083027, "auxiliary_loss_weight": 1.0, "epoch": 13.872778297474275, "flow_matching_loss": 0.02922240737825632, "grad_norm": 0.11929628998041153, "invalid_tail_samples": 24.9, "learning_rate": 5.506743690929809e-05, "loss": 0.0323, "positive_teacher_pairs": 26601.5, "relation_loss": 0.0030398876639083027, "selected_pairs": 26601.5, "step": 14830, "student_distance_mean": 1220.564013671875, "teacher_distance_mean": 0.8555382311344146, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0030398876639083027, "weighted_relation_loss": 0.0030398876639083027 }, { "action_query_batch_std": 21.34521350860596, "action_query_norm": 920.2047485351562, "action_relation_loss": 0.0030311010312289, "auxiliary_loss_weight": 1.0, "epoch": 13.882132834424697, "flow_matching_loss": 0.029535339586436747, "grad_norm": 0.10727470368146896, "invalid_tail_samples": 24.7, "learning_rate": 5.501260197382912e-05, "loss": 0.0326, "positive_teacher_pairs": 26644.9, "relation_loss": 0.0030311010312289, "selected_pairs": 26644.9, "step": 14840, "student_distance_mean": 1221.4083862304688, "teacher_distance_mean": 0.8518848836421966, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0030311010312289, "weighted_relation_loss": 0.0030311010312289 }, { "action_query_batch_std": 21.290390396118163, "action_query_norm": 914.9585754394532, "action_relation_loss": 0.0028943392680957913, "auxiliary_loss_weight": 1.0, "epoch": 13.891487371375117, "flow_matching_loss": 0.03028391357511282, "grad_norm": 0.11196617037057877, "invalid_tail_samples": 24.0, "learning_rate": 5.49577609475761e-05, "loss": 0.0332, "positive_teacher_pairs": 26811.4, "relation_loss": 0.0028943392680957913, "selected_pairs": 26811.4, "step": 14850, "student_distance_mean": 1214.4445190429688, "teacher_distance_mean": 0.8579761922359467, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0028943392680957913, "weighted_relation_loss": 0.0028943392680957913 }, { "action_query_batch_std": 21.208960723876952, "action_query_norm": 910.0389831542968, "action_relation_loss": 0.002941963914781809, "auxiliary_loss_weight": 1.0, "epoch": 13.900841908325537, "flow_matching_loss": 0.029305347613990305, "grad_norm": 0.12153173983097076, "invalid_tail_samples": 23.3, "learning_rate": 5.490291389717603e-05, "loss": 0.0322, "positive_teacher_pairs": 26966.9, "relation_loss": 0.002941963914781809, "selected_pairs": 26966.9, "step": 14860, "student_distance_mean": 1212.1016723632813, "teacher_distance_mean": 0.8570633947849273, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.002941963914781809, "weighted_relation_loss": 0.002941963914781809 }, { "action_query_batch_std": 21.430800247192384, "action_query_norm": 917.8849365234375, "action_relation_loss": 0.00287117341067642, "auxiliary_loss_weight": 1.0, "epoch": 13.91019644527596, "flow_matching_loss": 0.03144941087812185, "grad_norm": 0.11266129463911057, "invalid_tail_samples": 23.1, "learning_rate": 5.484806088927329e-05, "loss": 0.0343, "positive_teacher_pairs": 27011.7, "relation_loss": 0.00287117341067642, "selected_pairs": 27011.7, "step": 14870, "student_distance_mean": 1226.7194702148438, "teacher_distance_mean": 0.8609717428684235, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.00287117341067642, "weighted_relation_loss": 0.00287117341067642 }, { "action_query_batch_std": 21.17875576019287, "action_query_norm": 914.8471008300781, "action_relation_loss": 0.0030580680584535004, "auxiliary_loss_weight": 1.0, "epoch": 13.91955098222638, "flow_matching_loss": 0.028240496665239333, "grad_norm": 0.09713032841682434, "invalid_tail_samples": 23.6, "learning_rate": 5.479320199051942e-05, "loss": 0.0313, "positive_teacher_pairs": 26893.4, "relation_loss": 0.0030580680584535004, "selected_pairs": 26893.4, "step": 14880, "student_distance_mean": 1210.489599609375, "teacher_distance_mean": 0.8504015266895294, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0030580680584535004, "weighted_relation_loss": 0.0030580680584535004 }, { "action_query_batch_std": 21.110936546325682, "action_query_norm": 909.4231811523438, "action_relation_loss": 0.003014455526135862, "auxiliary_loss_weight": 1.0, "epoch": 13.928905519176801, "flow_matching_loss": 0.030398152023553848, "grad_norm": 0.17480096220970154, "invalid_tail_samples": 22.4, "learning_rate": 5.473833726757314e-05, "loss": 0.0334, "positive_teacher_pairs": 27177.7, "relation_loss": 0.003014455526135862, "selected_pairs": 27177.7, "step": 14890, "student_distance_mean": 1204.3403442382812, "teacher_distance_mean": 0.8515190124511719, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.003014455526135862, "weighted_relation_loss": 0.003014455526135862 }, { "action_query_batch_std": 21.019765281677245, "action_query_norm": 905.3154541015625, "action_relation_loss": 0.00293724169023335, "auxiliary_loss_weight": 1.0, "epoch": 13.938260056127222, "flow_matching_loss": 0.03027130551636219, "grad_norm": 0.112086720764637, "invalid_tail_samples": 24.3, "learning_rate": 5.4683466787100304e-05, "loss": 0.0332, "positive_teacher_pairs": 26752.6, "relation_loss": 0.00293724169023335, "selected_pairs": 26752.6, "step": 14900, "student_distance_mean": 1203.7308715820313, "teacher_distance_mean": 0.8472546100616455, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.00293724169023335, "weighted_relation_loss": 0.00293724169023335 }, { "action_query_batch_std": 20.994504547119142, "action_query_norm": 904.2119140625, "action_relation_loss": 0.002847713278606534, "auxiliary_loss_weight": 1.0, "epoch": 13.947614593077642, "flow_matching_loss": 0.029834886081516743, "grad_norm": 0.10827182233333588, "invalid_tail_samples": 25.5, "learning_rate": 5.462859061577369e-05, "loss": 0.0327, "positive_teacher_pairs": 26453.7, "relation_loss": 0.002847713278606534, "selected_pairs": 26453.7, "step": 14910, "student_distance_mean": 1205.3023681640625, "teacher_distance_mean": 0.8468113243579865, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.002847713278606534, "weighted_relation_loss": 0.002847713278606534 }, { "action_query_batch_std": 21.35710620880127, "action_query_norm": 917.270947265625, "action_relation_loss": 0.0032137069618329408, "auxiliary_loss_weight": 1.0, "epoch": 13.956969130028064, "flow_matching_loss": 0.029695227183401583, "grad_norm": 0.1289387345314026, "invalid_tail_samples": 21.9, "learning_rate": 5.4573708820273026e-05, "loss": 0.0329, "positive_teacher_pairs": 27289.4, "relation_loss": 0.0032137069618329408, "selected_pairs": 27289.4, "step": 14920, "student_distance_mean": 1218.3240478515625, "teacher_distance_mean": 0.8549724221229553, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.0032137069618329408, "weighted_relation_loss": 0.0032137069618329408 }, { "action_query_batch_std": 21.183205223083498, "action_query_norm": 912.652587890625, "action_relation_loss": 0.003119019395671785, "auxiliary_loss_weight": 1.0, "epoch": 13.966323666978484, "flow_matching_loss": 0.029396767914295196, "grad_norm": 0.1449262499809265, "invalid_tail_samples": 21.0, "learning_rate": 5.451882146728488e-05, "loss": 0.0325, "positive_teacher_pairs": 27504.0, "relation_loss": 0.003119019395671785, "selected_pairs": 27504.0, "step": 14930, "student_distance_mean": 1215.6433837890625, "teacher_distance_mean": 0.8494069576263428, "valid_action_samples": 235.0, "weighted_auxiliary_loss": 0.003119019395671785, "weighted_relation_loss": 0.003119019395671785 }, { "action_query_batch_std": 21.284714126586913, "action_query_norm": 917.860302734375, "action_relation_loss": 0.002967854030430317, "auxiliary_loss_weight": 1.0, "epoch": 13.975678203928906, "flow_matching_loss": 0.027690965123474597, "grad_norm": 0.115824393928051, "invalid_tail_samples": 24.5, "learning_rate": 5.446392862350255e-05, "loss": 0.0307, "positive_teacher_pairs": 26686.5, "relation_loss": 0.002967854030430317, "selected_pairs": 26686.5, "step": 14940, "student_distance_mean": 1219.3158569335938, "teacher_distance_mean": 0.8533485233783722, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.002967854030430317, "weighted_relation_loss": 0.002967854030430317 }, { "action_query_batch_std": 21.323497009277343, "action_query_norm": 921.0335388183594, "action_relation_loss": 0.003067220258526504, "auxiliary_loss_weight": 1.0, "epoch": 13.985032740879326, "flow_matching_loss": 0.028413469344377516, "grad_norm": 0.11614484339952469, "invalid_tail_samples": 23.1, "learning_rate": 5.440903035562603e-05, "loss": 0.0315, "positive_teacher_pairs": 27024.4, "relation_loss": 0.003067220258526504, "selected_pairs": 27024.4, "step": 14950, "student_distance_mean": 1223.56494140625, "teacher_distance_mean": 0.8540684282779694, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.003067220258526504, "weighted_relation_loss": 0.003067220258526504 }, { "action_query_batch_std": 21.51243152618408, "action_query_norm": 924.1910766601562, "action_relation_loss": 0.0029902531299740077, "auxiliary_loss_weight": 1.0, "epoch": 13.994387277829748, "flow_matching_loss": 0.02953952644020319, "grad_norm": 0.0904003456234932, "invalid_tail_samples": 26.9, "learning_rate": 5.435412673036188e-05, "loss": 0.0325, "positive_teacher_pairs": 26136.1, "relation_loss": 0.0029902531299740077, "selected_pairs": 26136.1, "step": 14960, "student_distance_mean": 1233.2773193359376, "teacher_distance_mean": 0.8583277404308319, "valid_action_samples": 229.1, "weighted_auxiliary_loss": 0.0029902531299740077, "weighted_relation_loss": 0.0029902531299740077 }, { "action_query_batch_std": 21.2326566696167, "action_query_norm": 911.8613220214844, "action_relation_loss": 0.0029427621513605116, "auxiliary_loss_weight": 1.0, "epoch": 14.003741814780168, "flow_matching_loss": 0.03107131402939558, "grad_norm": 0.11480578780174255, "invalid_tail_samples": 21.8, "learning_rate": 5.429921781442318e-05, "loss": 0.034, "positive_teacher_pairs": 24327.9, "relation_loss": 0.0029427621513605116, "selected_pairs": 24327.9, "step": 14970, "student_distance_mean": 1221.5501953125, "teacher_distance_mean": 0.8604766547679901, "valid_action_samples": 214.3, "weighted_auxiliary_loss": 0.0029427621513605116, "weighted_relation_loss": 0.0029427621513605116 }, { "action_query_batch_std": 21.223497772216795, "action_query_norm": 913.2428100585937, "action_relation_loss": 0.002942804200574756, "auxiliary_loss_weight": 1.0, "epoch": 14.013096351730589, "flow_matching_loss": 0.02907483819872141, "grad_norm": 0.109678253531456, "invalid_tail_samples": 22.8, "learning_rate": 5.424430367452945e-05, "loss": 0.032, "positive_teacher_pairs": 27086.2, "relation_loss": 0.002942804200574756, "selected_pairs": 27086.2, "step": 14980, "student_distance_mean": 1216.192822265625, "teacher_distance_mean": 0.8594993114471435, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.002942804200574756, "weighted_relation_loss": 0.002942804200574756 }, { "action_query_batch_std": 21.618952560424805, "action_query_norm": 924.998876953125, "action_relation_loss": 0.002923221350647509, "auxiliary_loss_weight": 1.0, "epoch": 14.02245088868101, "flow_matching_loss": 0.0293972572311759, "grad_norm": 0.09559523314237595, "invalid_tail_samples": 25.3, "learning_rate": 5.418938437740655e-05, "loss": 0.0323, "positive_teacher_pairs": 26500.3, "relation_loss": 0.002923221350647509, "selected_pairs": 26500.3, "step": 14990, "student_distance_mean": 1236.5227783203125, "teacher_distance_mean": 0.8644815683364868, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.002923221350647509, "weighted_relation_loss": 0.002923221350647509 }, { "action_query_batch_std": 21.382566833496092, "action_query_norm": 922.6096069335938, "action_relation_loss": 0.002957919775508344, "auxiliary_loss_weight": 1.0, "epoch": 14.03180542563143, "flow_matching_loss": 0.028707082010805608, "grad_norm": 0.08697057515382767, "invalid_tail_samples": 22.3, "learning_rate": 5.413445998978658e-05, "loss": 0.0317, "positive_teacher_pairs": 27195.5, "relation_loss": 0.002957919775508344, "selected_pairs": 27195.5, "step": 15000, "student_distance_mean": 1224.1443603515625, "teacher_distance_mean": 0.8548851132392883, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.002957919775508344, "weighted_relation_loss": 0.002957919775508344 }, { "action_query_batch_std": 21.30617752075195, "action_query_norm": 916.9500183105469, "action_relation_loss": 0.002919853222556412, "auxiliary_loss_weight": 1.0, "epoch": 14.041159962581853, "flow_matching_loss": 0.02869610730558634, "grad_norm": 0.0883333832025528, "invalid_tail_samples": 25.8, "learning_rate": 5.407953057840789e-05, "loss": 0.0316, "positive_teacher_pairs": 26386.7, "relation_loss": 0.002919853222556412, "selected_pairs": 26386.7, "step": 15010, "student_distance_mean": 1220.448779296875, "teacher_distance_mean": 0.855722713470459, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.002919853222556412, "weighted_relation_loss": 0.002919853222556412 }, { "action_query_batch_std": 21.477096557617188, "action_query_norm": 922.6884765625, "action_relation_loss": 0.002897062315605581, "auxiliary_loss_weight": 1.0, "epoch": 14.050514499532273, "flow_matching_loss": 0.029733995161950588, "grad_norm": 0.09840159118175507, "invalid_tail_samples": 19.2, "learning_rate": 5.4024596210014853e-05, "loss": 0.0326, "positive_teacher_pairs": 27927.0, "relation_loss": 0.002897062315605581, "selected_pairs": 27927.0, "step": 15020, "student_distance_mean": 1226.3237060546876, "teacher_distance_mean": 0.8574491441249847, "valid_action_samples": 236.8, "weighted_auxiliary_loss": 0.002897062315605581, "weighted_relation_loss": 0.002897062315605581 }, { "action_query_batch_std": 21.380831718444824, "action_query_norm": 918.4587463378906, "action_relation_loss": 0.0027622414054349065, "auxiliary_loss_weight": 1.0, "epoch": 14.059869036482693, "flow_matching_loss": 0.02865791358053684, "grad_norm": 0.0938398689031601, "invalid_tail_samples": 25.8, "learning_rate": 5.3969656951357935e-05, "loss": 0.0314, "positive_teacher_pairs": 26389.8, "relation_loss": 0.0027622414054349065, "selected_pairs": 26389.8, "step": 15030, "student_distance_mean": 1226.506982421875, "teacher_distance_mean": 0.8604185879230499, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.0027622414054349065, "weighted_relation_loss": 0.0027622414054349065 }, { "action_query_batch_std": 21.343205642700195, "action_query_norm": 915.1755493164062, "action_relation_loss": 0.002931892964988947, "auxiliary_loss_weight": 1.0, "epoch": 14.069223573433115, "flow_matching_loss": 0.028070041351020335, "grad_norm": 0.10467620939016342, "invalid_tail_samples": 24.7, "learning_rate": 5.3914712869193504e-05, "loss": 0.031, "positive_teacher_pairs": 26648.8, "relation_loss": 0.002931892964988947, "selected_pairs": 26648.8, "step": 15040, "student_distance_mean": 1221.7351684570312, "teacher_distance_mean": 0.858365786075592, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.002931892964988947, "weighted_relation_loss": 0.002931892964988947 }, { "action_query_batch_std": 21.301654434204103, "action_query_norm": 918.13828125, "action_relation_loss": 0.002878850977867842, "auxiliary_loss_weight": 1.0, "epoch": 14.078578110383535, "flow_matching_loss": 0.027002745680510996, "grad_norm": 0.09285281598567963, "invalid_tail_samples": 23.5, "learning_rate": 5.385976403028381e-05, "loss": 0.0299, "positive_teacher_pairs": 26926.5, "relation_loss": 0.002878850977867842, "selected_pairs": 26926.5, "step": 15050, "student_distance_mean": 1220.18994140625, "teacher_distance_mean": 0.8557230949401855, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.002878850977867842, "weighted_relation_loss": 0.002878850977867842 }, { "action_query_batch_std": 21.277304267883302, "action_query_norm": 913.8144165039063, "action_relation_loss": 0.002889090939424932, "auxiliary_loss_weight": 1.0, "epoch": 14.087932647333957, "flow_matching_loss": 0.028122233040630818, "grad_norm": 0.10563187301158905, "invalid_tail_samples": 24.8, "learning_rate": 5.3804810501396875e-05, "loss": 0.031, "positive_teacher_pairs": 26620.7, "relation_loss": 0.002889090939424932, "selected_pairs": 26620.7, "step": 15060, "student_distance_mean": 1214.1154541015626, "teacher_distance_mean": 0.8519750237464905, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.002889090939424932, "weighted_relation_loss": 0.002889090939424932 }, { "action_query_batch_std": 21.318536949157714, "action_query_norm": 916.2740783691406, "action_relation_loss": 0.0028330694185569882, "auxiliary_loss_weight": 1.0, "epoch": 14.097287184284378, "flow_matching_loss": 0.028883256204426288, "grad_norm": 0.10624373704195023, "invalid_tail_samples": 25.3, "learning_rate": 5.374985234930639e-05, "loss": 0.0317, "positive_teacher_pairs": 26509.2, "relation_loss": 0.0028330694185569882, "selected_pairs": 26509.2, "step": 15070, "student_distance_mean": 1222.8943481445312, "teacher_distance_mean": 0.8573721289634705, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0028330694185569882, "weighted_relation_loss": 0.0028330694185569882 }, { "action_query_batch_std": 21.499295234680176, "action_query_norm": 922.6202697753906, "action_relation_loss": 0.002782800770364702, "auxiliary_loss_weight": 1.0, "epoch": 14.1066417212348, "flow_matching_loss": 0.029048054851591586, "grad_norm": 0.16119198501110077, "invalid_tail_samples": 25.0, "learning_rate": 5.3694889640791724e-05, "loss": 0.0318, "positive_teacher_pairs": 26578.4, "relation_loss": 0.002782800770364702, "selected_pairs": 26578.4, "step": 15080, "student_distance_mean": 1229.3185302734375, "teacher_distance_mean": 0.8606893301010132, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.002782800770364702, "weighted_relation_loss": 0.002782800770364702 }, { "action_query_batch_std": 21.380086135864257, "action_query_norm": 915.4032836914063, "action_relation_loss": 0.0029985673958435656, "auxiliary_loss_weight": 1.0, "epoch": 14.11599625818522, "flow_matching_loss": 0.028744842298328875, "grad_norm": 0.12281342595815659, "invalid_tail_samples": 23.0, "learning_rate": 5.3639922442637736e-05, "loss": 0.0317, "positive_teacher_pairs": 27047.6, "relation_loss": 0.0029985673958435656, "selected_pairs": 27047.6, "step": 15090, "student_distance_mean": 1222.3934326171875, "teacher_distance_mean": 0.8589600384235382, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0029985673958435656, "weighted_relation_loss": 0.0029985673958435656 }, { "action_query_batch_std": 21.156496620178224, "action_query_norm": 911.02060546875, "action_relation_loss": 0.0029483657330274583, "auxiliary_loss_weight": 1.0, "epoch": 14.12535079513564, "flow_matching_loss": 0.030420249328017235, "grad_norm": 0.13505922257900238, "invalid_tail_samples": 22.0, "learning_rate": 5.358495082163476e-05, "loss": 0.0334, "positive_teacher_pairs": 27266.9, "relation_loss": 0.0029483657330274583, "selected_pairs": 27266.9, "step": 15100, "student_distance_mean": 1207.6664306640625, "teacher_distance_mean": 0.842194265127182, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.0029483657330274583, "weighted_relation_loss": 0.0029483657330274583 }, { "action_query_batch_std": 21.46593132019043, "action_query_norm": 922.6047485351562, "action_relation_loss": 0.002972193923778832, "auxiliary_loss_weight": 1.0, "epoch": 14.134705332086062, "flow_matching_loss": 0.029979086853563784, "grad_norm": 0.12395896762609482, "invalid_tail_samples": 23.7, "learning_rate": 5.35299748445785e-05, "loss": 0.033, "positive_teacher_pairs": 26875.8, "relation_loss": 0.002972193923778832, "selected_pairs": 26875.8, "step": 15110, "student_distance_mean": 1227.139697265625, "teacher_distance_mean": 0.8581041753292084, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.002972193923778832, "weighted_relation_loss": 0.002972193923778832 }, { "action_query_batch_std": 21.55035285949707, "action_query_norm": 922.4559020996094, "action_relation_loss": 0.002829797426238656, "auxiliary_loss_weight": 1.0, "epoch": 14.144059869036482, "flow_matching_loss": 0.02979671284556389, "grad_norm": 0.1007009819149971, "invalid_tail_samples": 22.8, "learning_rate": 5.3474994578269944e-05, "loss": 0.0326, "positive_teacher_pairs": 27082.0, "relation_loss": 0.002829797426238656, "selected_pairs": 27082.0, "step": 15120, "student_distance_mean": 1230.6275634765625, "teacher_distance_mean": 0.8605375647544861, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.002829797426238656, "weighted_relation_loss": 0.002829797426238656 }, { "action_query_batch_std": 21.01263599395752, "action_query_norm": 902.5155090332031, "action_relation_loss": 0.0029198671225458385, "auxiliary_loss_weight": 1.0, "epoch": 14.153414405986904, "flow_matching_loss": 0.028545390255749224, "grad_norm": 0.1290319859981537, "invalid_tail_samples": 22.0, "learning_rate": 5.34200100895153e-05, "loss": 0.0315, "positive_teacher_pairs": 27270.8, "relation_loss": 0.0029198671225458385, "selected_pairs": 27270.8, "step": 15130, "student_distance_mean": 1203.509765625, "teacher_distance_mean": 0.8485803723335266, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.0029198671225458385, "weighted_relation_loss": 0.0029198671225458385 }, { "action_query_batch_std": 20.962495422363283, "action_query_norm": 902.7762756347656, "action_relation_loss": 0.002844216721132398, "auxiliary_loss_weight": 1.0, "epoch": 14.162768942937324, "flow_matching_loss": 0.03025187235325575, "grad_norm": 0.11672497540712357, "invalid_tail_samples": 25.6, "learning_rate": 5.3365021445125916e-05, "loss": 0.0331, "positive_teacher_pairs": 26434.4, "relation_loss": 0.002844216721132398, "selected_pairs": 26434.4, "step": 15140, "student_distance_mean": 1204.6352172851562, "teacher_distance_mean": 0.8492766976356506, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.002844216721132398, "weighted_relation_loss": 0.002844216721132398 }, { "action_query_batch_std": 21.09450168609619, "action_query_norm": 906.272900390625, "action_relation_loss": 0.0029111542506143452, "auxiliary_loss_weight": 1.0, "epoch": 14.172123479887745, "flow_matching_loss": 0.02799371313303709, "grad_norm": 0.10291369259357452, "invalid_tail_samples": 22.4, "learning_rate": 5.331002871191817e-05, "loss": 0.0309, "positive_teacher_pairs": 27185.7, "relation_loss": 0.0029111542506143452, "selected_pairs": 27185.7, "step": 15150, "student_distance_mean": 1203.1488891601562, "teacher_distance_mean": 0.8437113404273987, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.0029111542506143452, "weighted_relation_loss": 0.0029111542506143452 }, { "action_query_batch_std": 21.598238372802733, "action_query_norm": 923.9851684570312, "action_relation_loss": 0.002845920086838305, "auxiliary_loss_weight": 1.0, "epoch": 14.181478016838167, "flow_matching_loss": 0.02916014418005943, "grad_norm": 0.095955491065979, "invalid_tail_samples": 24.3, "learning_rate": 5.3255031956713443e-05, "loss": 0.032, "positive_teacher_pairs": 26733.3, "relation_loss": 0.002845920086838305, "selected_pairs": 26733.3, "step": 15160, "student_distance_mean": 1231.5788696289062, "teacher_distance_mean": 0.8595671117305755, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.002845920086838305, "weighted_relation_loss": 0.002845920086838305 }, { "action_query_batch_std": 21.42422866821289, "action_query_norm": 922.7368469238281, "action_relation_loss": 0.0028006247710436584, "auxiliary_loss_weight": 1.0, "epoch": 14.190832553788587, "flow_matching_loss": 0.028826844319701193, "grad_norm": 0.10086928308010101, "invalid_tail_samples": 24.6, "learning_rate": 5.320003124633795e-05, "loss": 0.0316, "positive_teacher_pairs": 26667.5, "relation_loss": 0.0028006247710436584, "selected_pairs": 26667.5, "step": 15170, "student_distance_mean": 1227.271484375, "teacher_distance_mean": 0.8596644043922425, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0028006247710436584, "weighted_relation_loss": 0.0028006247710436584 }, { "action_query_batch_std": 21.4642427444458, "action_query_norm": 925.0925598144531, "action_relation_loss": 0.0028652362758293747, "auxiliary_loss_weight": 1.0, "epoch": 14.200187090739009, "flow_matching_loss": 0.02852625586092472, "grad_norm": 0.11348540335893631, "invalid_tail_samples": 21.4, "learning_rate": 5.314502664762274e-05, "loss": 0.0314, "positive_teacher_pairs": 27406.4, "relation_loss": 0.0028652362758293747, "selected_pairs": 27406.4, "step": 15180, "student_distance_mean": 1224.13974609375, "teacher_distance_mean": 0.8527046084403992, "valid_action_samples": 234.6, "weighted_auxiliary_loss": 0.0028652362758293747, "weighted_relation_loss": 0.0028652362758293747 }, { "action_query_batch_std": 21.31359996795654, "action_query_norm": 921.40634765625, "action_relation_loss": 0.0028983092634007335, "auxiliary_loss_weight": 1.0, "epoch": 14.209541627689429, "flow_matching_loss": 0.028279448859393597, "grad_norm": 0.09157642722129822, "invalid_tail_samples": 25.0, "learning_rate": 5.3090018227403604e-05, "loss": 0.0312, "positive_teacher_pairs": 26570.3, "relation_loss": 0.0028983092634007335, "selected_pairs": 26570.3, "step": 15190, "student_distance_mean": 1222.9970703125, "teacher_distance_mean": 0.8523151397705078, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0028983092634007335, "weighted_relation_loss": 0.0028983092634007335 }, { "action_query_batch_std": 21.615308380126955, "action_query_norm": 929.1092834472656, "action_relation_loss": 0.002905694954097271, "auxiliary_loss_weight": 1.0, "epoch": 14.218896164639851, "flow_matching_loss": 0.029717359878122806, "grad_norm": 0.10958455502986908, "invalid_tail_samples": 20.0, "learning_rate": 5.3035006052520955e-05, "loss": 0.0326, "positive_teacher_pairs": 27736.8, "relation_loss": 0.002905694954097271, "selected_pairs": 27736.8, "step": 15200, "student_distance_mean": 1235.7764770507813, "teacher_distance_mean": 0.863695603609085, "valid_action_samples": 236.0, "weighted_auxiliary_loss": 0.002905694954097271, "weighted_relation_loss": 0.002905694954097271 }, { "action_query_batch_std": 21.153731536865234, "action_query_norm": 910.0615356445312, "action_relation_loss": 0.00286033044103533, "auxiliary_loss_weight": 1.0, "epoch": 14.228250701590271, "flow_matching_loss": 0.02890173625200987, "grad_norm": 0.10899358242750168, "invalid_tail_samples": 22.9, "learning_rate": 5.297999018981976e-05, "loss": 0.0318, "positive_teacher_pairs": 27057.3, "relation_loss": 0.00286033044103533, "selected_pairs": 27057.3, "step": 15210, "student_distance_mean": 1211.8790771484375, "teacher_distance_mean": 0.8492531776428223, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.00286033044103533, "weighted_relation_loss": 0.00286033044103533 }, { "action_query_batch_std": 21.248800468444824, "action_query_norm": 913.6830932617188, "action_relation_loss": 0.0028160033049061894, "auxiliary_loss_weight": 1.0, "epoch": 14.237605238540691, "flow_matching_loss": 0.028932970948517323, "grad_norm": 0.09270975738763809, "invalid_tail_samples": 27.1, "learning_rate": 5.2924970706149505e-05, "loss": 0.0317, "positive_teacher_pairs": 26092.1, "relation_loss": 0.0028160033049061894, "selected_pairs": 26092.1, "step": 15220, "student_distance_mean": 1214.4955078125, "teacher_distance_mean": 0.8503003597259522, "valid_action_samples": 228.9, "weighted_auxiliary_loss": 0.0028160033049061894, "weighted_relation_loss": 0.0028160033049061894 }, { "action_query_batch_std": 21.313234710693358, "action_query_norm": 916.0256958007812, "action_relation_loss": 0.0028568352572619915, "auxiliary_loss_weight": 1.0, "epoch": 14.246959775491113, "flow_matching_loss": 0.027438670769333838, "grad_norm": 0.10796602815389633, "invalid_tail_samples": 25.1, "learning_rate": 5.2869947668364014e-05, "loss": 0.0303, "positive_teacher_pairs": 26551.4, "relation_loss": 0.0028568352572619915, "selected_pairs": 26551.4, "step": 15230, "student_distance_mean": 1222.6785766601563, "teacher_distance_mean": 0.8571379959583283, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0028568352572619915, "weighted_relation_loss": 0.0028568352572619915 }, { "action_query_batch_std": 21.61929111480713, "action_query_norm": 926.0120666503906, "action_relation_loss": 0.0027541851857677104, "auxiliary_loss_weight": 1.0, "epoch": 14.256314312441534, "flow_matching_loss": 0.029352952726185322, "grad_norm": 0.11643681675195694, "invalid_tail_samples": 25.5, "learning_rate": 5.2814921143321504e-05, "loss": 0.0321, "positive_teacher_pairs": 26454.3, "relation_loss": 0.0027541851857677104, "selected_pairs": 26454.3, "step": 15240, "student_distance_mean": 1239.0053833007812, "teacher_distance_mean": 0.8648015260696411, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0027541851857677104, "weighted_relation_loss": 0.0027541851857677104 }, { "action_query_batch_std": 21.442184829711913, "action_query_norm": 922.3922912597657, "action_relation_loss": 0.002806873037479818, "auxiliary_loss_weight": 1.0, "epoch": 14.265668849391956, "flow_matching_loss": 0.029299451783299447, "grad_norm": 0.09223029762506485, "invalid_tail_samples": 25.9, "learning_rate": 5.275989119788436e-05, "loss": 0.0321, "positive_teacher_pairs": 26371.2, "relation_loss": 0.002806873037479818, "selected_pairs": 26371.2, "step": 15250, "student_distance_mean": 1230.4607421875, "teacher_distance_mean": 0.8558477580547332, "valid_action_samples": 230.1, "weighted_auxiliary_loss": 0.002806873037479818, "weighted_relation_loss": 0.002806873037479818 }, { "action_query_batch_std": 21.58050193786621, "action_query_norm": 924.2288513183594, "action_relation_loss": 0.002846778184175491, "auxiliary_loss_weight": 1.0, "epoch": 14.275023386342376, "flow_matching_loss": 0.026541389524936676, "grad_norm": 0.11160522699356079, "invalid_tail_samples": 23.5, "learning_rate": 5.270485789891919e-05, "loss": 0.0294, "positive_teacher_pairs": 26929.4, "relation_loss": 0.002846778184175491, "selected_pairs": 26929.4, "step": 15260, "student_distance_mean": 1232.1090209960937, "teacher_distance_mean": 0.8596670627593994, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.002846778184175491, "weighted_relation_loss": 0.002846778184175491 }, { "action_query_batch_std": 21.410533905029297, "action_query_norm": 923.1150451660156, "action_relation_loss": 0.002766282972879708, "auxiliary_loss_weight": 1.0, "epoch": 14.284377923292798, "flow_matching_loss": 0.029891533218324183, "grad_norm": 0.10842641443014145, "invalid_tail_samples": 21.7, "learning_rate": 5.264982131329661e-05, "loss": 0.0327, "positive_teacher_pairs": 27337.0, "relation_loss": 0.002766282972879708, "selected_pairs": 27337.0, "step": 15270, "student_distance_mean": 1224.7405151367188, "teacher_distance_mean": 0.8563940942287445, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.002766282972879708, "weighted_relation_loss": 0.002766282972879708 }, { "action_query_batch_std": 21.6062801361084, "action_query_norm": 927.5806640625, "action_relation_loss": 0.0027553214225918055, "auxiliary_loss_weight": 1.0, "epoch": 14.293732460243218, "flow_matching_loss": 0.027592915296554565, "grad_norm": 0.10479568690061569, "invalid_tail_samples": 24.6, "learning_rate": 5.259478150789128e-05, "loss": 0.0303, "positive_teacher_pairs": 26663.3, "relation_loss": 0.0027553214225918055, "selected_pairs": 26663.3, "step": 15280, "student_distance_mean": 1236.509765625, "teacher_distance_mean": 0.8610250532627106, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0027553214225918055, "weighted_relation_loss": 0.0027553214225918055 }, { "action_query_batch_std": 21.444487380981446, "action_query_norm": 920.9438659667969, "action_relation_loss": 0.002687968290410936, "auxiliary_loss_weight": 1.0, "epoch": 14.303086997193638, "flow_matching_loss": 0.0271960087120533, "grad_norm": 0.09378566592931747, "invalid_tail_samples": 21.7, "learning_rate": 5.253973854958173e-05, "loss": 0.0299, "positive_teacher_pairs": 27337.3, "relation_loss": 0.002687968290410936, "selected_pairs": 27337.3, "step": 15290, "student_distance_mean": 1226.3704833984375, "teacher_distance_mean": 0.8534475445747376, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.002687968290410936, "weighted_relation_loss": 0.002687968290410936 }, { "action_query_batch_std": 21.36146011352539, "action_query_norm": 918.2912170410157, "action_relation_loss": 0.002856403426267207, "auxiliary_loss_weight": 1.0, "epoch": 14.31244153414406, "flow_matching_loss": 0.029065500758588315, "grad_norm": 0.1093636304140091, "invalid_tail_samples": 23.6, "learning_rate": 5.2484692505250376e-05, "loss": 0.0319, "positive_teacher_pairs": 26891.5, "relation_loss": 0.002856403426267207, "selected_pairs": 26891.5, "step": 15300, "student_distance_mean": 1224.4380859375, "teacher_distance_mean": 0.8534066617488861, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.002856403426267207, "weighted_relation_loss": 0.002856403426267207 }, { "action_query_batch_std": 21.498250007629395, "action_query_norm": 926.4837036132812, "action_relation_loss": 0.002895330684259534, "auxiliary_loss_weight": 1.0, "epoch": 14.32179607109448, "flow_matching_loss": 0.028205335699021818, "grad_norm": 0.12340397387742996, "invalid_tail_samples": 22.6, "learning_rate": 5.242964344178333e-05, "loss": 0.0311, "positive_teacher_pairs": 27132.1, "relation_loss": 0.002895330684259534, "selected_pairs": 27132.1, "step": 15310, "student_distance_mean": 1229.6768676757813, "teacher_distance_mean": 0.8489765822887421, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.002895330684259534, "weighted_relation_loss": 0.002895330684259534 }, { "action_query_batch_std": 21.47467746734619, "action_query_norm": 924.1574523925781, "action_relation_loss": 0.0028419893700629474, "auxiliary_loss_weight": 1.0, "epoch": 14.331150608044902, "flow_matching_loss": 0.029914449155330657, "grad_norm": 0.10886330902576447, "invalid_tail_samples": 21.3, "learning_rate": 5.237459142607041e-05, "loss": 0.0328, "positive_teacher_pairs": 27429.6, "relation_loss": 0.0028419893700629474, "selected_pairs": 27429.6, "step": 15320, "student_distance_mean": 1230.4498779296875, "teacher_distance_mean": 0.8509755551815033, "valid_action_samples": 234.7, "weighted_auxiliary_loss": 0.0028419893700629474, "weighted_relation_loss": 0.0028419893700629474 }, { "action_query_batch_std": 21.488834190368653, "action_query_norm": 923.6020385742188, "action_relation_loss": 0.0028662875993177295, "auxiliary_loss_weight": 1.0, "epoch": 14.340505144995323, "flow_matching_loss": 0.027758090011775493, "grad_norm": 0.09293320775032043, "invalid_tail_samples": 26.0, "learning_rate": 5.231953652500498e-05, "loss": 0.0306, "positive_teacher_pairs": 26352.8, "relation_loss": 0.0028662875993177295, "selected_pairs": 26352.8, "step": 15330, "student_distance_mean": 1237.4582275390626, "teacher_distance_mean": 0.8609633266925811, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.0028662875993177295, "weighted_relation_loss": 0.0028662875993177295 }, { "action_query_batch_std": 21.55351848602295, "action_query_norm": 927.3482299804688, "action_relation_loss": 0.002788040670566261, "auxiliary_loss_weight": 1.0, "epoch": 14.349859681945743, "flow_matching_loss": 0.02770982328802347, "grad_norm": 0.0942096933722496, "invalid_tail_samples": 23.2, "learning_rate": 5.2264478805483976e-05, "loss": 0.0305, "positive_teacher_pairs": 26985.5, "relation_loss": 0.002788040670566261, "selected_pairs": 26985.5, "step": 15340, "student_distance_mean": 1228.9331909179687, "teacher_distance_mean": 0.8551229894161224, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.002788040670566261, "weighted_relation_loss": 0.002788040670566261 }, { "action_query_batch_std": 21.37957019805908, "action_query_norm": 920.70986328125, "action_relation_loss": 0.002881347853690386, "auxiliary_loss_weight": 1.0, "epoch": 14.359214218896165, "flow_matching_loss": 0.02896469421684742, "grad_norm": 0.1172638088464737, "invalid_tail_samples": 25.8, "learning_rate": 5.220941833440768e-05, "loss": 0.0318, "positive_teacher_pairs": 26387.7, "relation_loss": 0.002881347853690386, "selected_pairs": 26387.7, "step": 15350, "student_distance_mean": 1224.8203491210938, "teacher_distance_mean": 0.8519615173339844, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.002881347853690386, "weighted_relation_loss": 0.002881347853690386 }, { "action_query_batch_std": 21.427026176452635, "action_query_norm": 924.4472351074219, "action_relation_loss": 0.0026991770602762697, "auxiliary_loss_weight": 1.0, "epoch": 14.368568755846585, "flow_matching_loss": 0.026849438063800336, "grad_norm": 0.09888972342014313, "invalid_tail_samples": 23.2, "learning_rate": 5.215435517867977e-05, "loss": 0.0295, "positive_teacher_pairs": 26984.3, "relation_loss": 0.0026991770602762697, "selected_pairs": 26984.3, "step": 15360, "student_distance_mean": 1225.65615234375, "teacher_distance_mean": 0.8544203460216522, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0026991770602762697, "weighted_relation_loss": 0.0026991770602762697 }, { "action_query_batch_std": 21.628865242004395, "action_query_norm": 929.3874267578125, "action_relation_loss": 0.002823161077685654, "auxiliary_loss_weight": 1.0, "epoch": 14.377923292797007, "flow_matching_loss": 0.02841389011591673, "grad_norm": 0.09614790230989456, "invalid_tail_samples": 23.6, "learning_rate": 5.209928940520719e-05, "loss": 0.0312, "positive_teacher_pairs": 26897.5, "relation_loss": 0.002823161077685654, "selected_pairs": 26897.5, "step": 15370, "student_distance_mean": 1238.2398071289062, "teacher_distance_mean": 0.8574257612228393, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.002823161077685654, "weighted_relation_loss": 0.002823161077685654 }, { "action_query_batch_std": 21.11225128173828, "action_query_norm": 912.4748718261719, "action_relation_loss": 0.0028570756083354356, "auxiliary_loss_weight": 1.0, "epoch": 14.387277829747427, "flow_matching_loss": 0.028280573524534704, "grad_norm": 0.09916195273399353, "invalid_tail_samples": 23.8, "learning_rate": 5.204422108090004e-05, "loss": 0.0311, "positive_teacher_pairs": 26852.0, "relation_loss": 0.0028570756083354356, "selected_pairs": 26852.0, "step": 15380, "student_distance_mean": 1210.3059204101562, "teacher_distance_mean": 0.8417704403400421, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0028570756083354356, "weighted_relation_loss": 0.0028570756083354356 }, { "action_query_batch_std": 21.473857879638672, "action_query_norm": 922.8315795898437, "action_relation_loss": 0.0028621662640944123, "auxiliary_loss_weight": 1.0, "epoch": 14.39663236669785, "flow_matching_loss": 0.02710055336356163, "grad_norm": 0.09173325449228287, "invalid_tail_samples": 22.2, "learning_rate": 5.19891502726715e-05, "loss": 0.03, "positive_teacher_pairs": 27217.9, "relation_loss": 0.0028621662640944123, "selected_pairs": 27217.9, "step": 15390, "student_distance_mean": 1229.9012451171875, "teacher_distance_mean": 0.8579927146434784, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.0028621662640944123, "weighted_relation_loss": 0.0028621662640944123 }, { "action_query_batch_std": 21.409536361694336, "action_query_norm": 918.9976623535156, "action_relation_loss": 0.002883536648005247, "auxiliary_loss_weight": 1.0, "epoch": 14.40598690364827, "flow_matching_loss": 0.02935778200626373, "grad_norm": 0.10771806538105011, "invalid_tail_samples": 22.1, "learning_rate": 5.193407704743782e-05, "loss": 0.0322, "positive_teacher_pairs": 27246.0, "relation_loss": 0.002883536648005247, "selected_pairs": 27246.0, "step": 15400, "student_distance_mean": 1222.9273193359375, "teacher_distance_mean": 0.8520141661167144, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.002883536648005247, "weighted_relation_loss": 0.002883536648005247 }, { "action_query_batch_std": 21.250800704956056, "action_query_norm": 911.559033203125, "action_relation_loss": 0.002719390927813947, "auxiliary_loss_weight": 1.0, "epoch": 14.41534144059869, "flow_matching_loss": 0.027789025008678435, "grad_norm": 0.14319545030593872, "invalid_tail_samples": 23.6, "learning_rate": 5.187900147211815e-05, "loss": 0.0305, "positive_teacher_pairs": 26906.2, "relation_loss": 0.002719390927813947, "selected_pairs": 26906.2, "step": 15410, "student_distance_mean": 1215.518701171875, "teacher_distance_mean": 0.8500774741172791, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.002719390927813947, "weighted_relation_loss": 0.002719390927813947 }, { "action_query_batch_std": 21.548361396789552, "action_query_norm": 922.0160339355468, "action_relation_loss": 0.0028228450333699583, "auxiliary_loss_weight": 1.0, "epoch": 14.424695977549112, "flow_matching_loss": 0.02552344687283039, "grad_norm": 0.08974064141511917, "invalid_tail_samples": 24.2, "learning_rate": 5.182392361363453e-05, "loss": 0.0283, "positive_teacher_pairs": 26757.4, "relation_loss": 0.0028228450333699583, "selected_pairs": 26757.4, "step": 15420, "student_distance_mean": 1228.4140991210938, "teacher_distance_mean": 0.8558978259563446, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0028228450333699583, "weighted_relation_loss": 0.0028228450333699583 }, { "action_query_batch_std": 21.55150451660156, "action_query_norm": 925.3327941894531, "action_relation_loss": 0.0027231041342020033, "auxiliary_loss_weight": 1.0, "epoch": 14.434050514499532, "flow_matching_loss": 0.027337678335607053, "grad_norm": 0.09158007055521011, "invalid_tail_samples": 24.9, "learning_rate": 5.176884353891172e-05, "loss": 0.0301, "positive_teacher_pairs": 26598.6, "relation_loss": 0.0027231041342020033, "selected_pairs": 26598.6, "step": 15430, "student_distance_mean": 1227.322900390625, "teacher_distance_mean": 0.852651983499527, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0027231041342020033, "weighted_relation_loss": 0.0027231041342020033 }, { "action_query_batch_std": 21.550034523010254, "action_query_norm": 925.2903015136719, "action_relation_loss": 0.002761469455435872, "auxiliary_loss_weight": 1.0, "epoch": 14.443405051449954, "flow_matching_loss": 0.027171327173709868, "grad_norm": 0.10445037484169006, "invalid_tail_samples": 23.9, "learning_rate": 5.171376131487722e-05, "loss": 0.0299, "positive_teacher_pairs": 26835.8, "relation_loss": 0.002761469455435872, "selected_pairs": 26835.8, "step": 15440, "student_distance_mean": 1236.1228515625, "teacher_distance_mean": 0.8555058360099792, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.002761469455435872, "weighted_relation_loss": 0.002761469455435872 }, { "action_query_batch_std": 21.21633586883545, "action_query_norm": 913.56396484375, "action_relation_loss": 0.0029463301645591853, "auxiliary_loss_weight": 1.0, "epoch": 14.452759588400374, "flow_matching_loss": 0.028461741656064986, "grad_norm": 0.1166149228811264, "invalid_tail_samples": 25.1, "learning_rate": 5.165867700846113e-05, "loss": 0.0314, "positive_teacher_pairs": 26554.4, "relation_loss": 0.0029463301645591853, "selected_pairs": 26554.4, "step": 15450, "student_distance_mean": 1218.7975463867188, "teacher_distance_mean": 0.8446851074695587, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0029463301645591853, "weighted_relation_loss": 0.0029463301645591853 }, { "action_query_batch_std": 21.220062065124512, "action_query_norm": 913.4297546386719, "action_relation_loss": 0.002990915975533426, "auxiliary_loss_weight": 1.0, "epoch": 14.462114125350794, "flow_matching_loss": 0.027192427404224874, "grad_norm": 0.12545309960842133, "invalid_tail_samples": 22.8, "learning_rate": 5.160359068659606e-05, "loss": 0.0302, "positive_teacher_pairs": 27078.4, "relation_loss": 0.002990915975533426, "selected_pairs": 27078.4, "step": 15460, "student_distance_mean": 1212.8863403320313, "teacher_distance_mean": 0.8474067986011505, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.002990915975533426, "weighted_relation_loss": 0.002990915975533426 }, { "action_query_batch_std": 21.58026180267334, "action_query_norm": 927.1988952636718, "action_relation_loss": 0.002776487241499126, "auxiliary_loss_weight": 1.0, "epoch": 14.471468662301216, "flow_matching_loss": 0.031342510133981705, "grad_norm": 0.10450568795204163, "invalid_tail_samples": 24.0, "learning_rate": 5.154850241621712e-05, "loss": 0.0341, "positive_teacher_pairs": 26806.7, "relation_loss": 0.002776487241499126, "selected_pairs": 26806.7, "step": 15470, "student_distance_mean": 1237.4608154296875, "teacher_distance_mean": 0.8628239750862121, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.002776487241499126, "weighted_relation_loss": 0.002776487241499126 }, { "action_query_batch_std": 21.398212242126466, "action_query_norm": 918.5027954101563, "action_relation_loss": 0.0028057050658389926, "auxiliary_loss_weight": 1.0, "epoch": 14.480823199251637, "flow_matching_loss": 0.02823756095021963, "grad_norm": 0.10442332923412323, "invalid_tail_samples": 23.5, "learning_rate": 5.149341226426172e-05, "loss": 0.031, "positive_teacher_pairs": 26925.2, "relation_loss": 0.0028057050658389926, "selected_pairs": 26925.2, "step": 15480, "student_distance_mean": 1227.3846557617187, "teacher_distance_mean": 0.8513385832309723, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0028057050658389926, "weighted_relation_loss": 0.0028057050658389926 }, { "action_query_batch_std": 21.51050853729248, "action_query_norm": 926.5352722167969, "action_relation_loss": 0.0028279342921450736, "auxiliary_loss_weight": 1.0, "epoch": 14.490177736202059, "flow_matching_loss": 0.026320469006896018, "grad_norm": 0.09939562529325485, "invalid_tail_samples": 22.4, "learning_rate": 5.14383202976696e-05, "loss": 0.0291, "positive_teacher_pairs": 27174.2, "relation_loss": 0.0028279342921450736, "selected_pairs": 27174.2, "step": 15490, "student_distance_mean": 1230.0445678710937, "teacher_distance_mean": 0.853810453414917, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.0028279342921450736, "weighted_relation_loss": 0.0028279342921450736 }, { "action_query_batch_std": 20.924012756347658, "action_query_norm": 903.3102661132813, "action_relation_loss": 0.0028385868761688473, "auxiliary_loss_weight": 1.0, "epoch": 14.499532273152479, "flow_matching_loss": 0.027802561596035957, "grad_norm": 0.09906593710184097, "invalid_tail_samples": 23.9, "learning_rate": 5.1383226583382684e-05, "loss": 0.0306, "positive_teacher_pairs": 26833.9, "relation_loss": 0.0028385868761688473, "selected_pairs": 26833.9, "step": 15500, "student_distance_mean": 1200.69677734375, "teacher_distance_mean": 0.8353751242160797, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0028385868761688473, "weighted_relation_loss": 0.0028385868761688473 }, { "action_query_batch_std": 21.443235206604005, "action_query_norm": 926.8066833496093, "action_relation_loss": 0.0028059519827365875, "auxiliary_loss_weight": 1.0, "epoch": 14.5088868101029, "flow_matching_loss": 0.026145264878869055, "grad_norm": 0.10150397568941116, "invalid_tail_samples": 23.5, "learning_rate": 5.132813118834504e-05, "loss": 0.029, "positive_teacher_pairs": 26923.3, "relation_loss": 0.0028059519827365875, "selected_pairs": 26923.3, "step": 15510, "student_distance_mean": 1229.1732177734375, "teacher_distance_mean": 0.8494824826717376, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0028059519827365875, "weighted_relation_loss": 0.0028059519827365875 }, { "action_query_batch_std": 21.448966789245606, "action_query_norm": 923.0479553222656, "action_relation_loss": 0.0027794197201728823, "auxiliary_loss_weight": 1.0, "epoch": 14.518241347053321, "flow_matching_loss": 0.02823735438287258, "grad_norm": 0.09903775900602341, "invalid_tail_samples": 23.5, "learning_rate": 5.1273034179502777e-05, "loss": 0.031, "positive_teacher_pairs": 26917.3, "relation_loss": 0.0027794197201728823, "selected_pairs": 26917.3, "step": 15520, "student_distance_mean": 1233.9063232421875, "teacher_distance_mean": 0.8582186758518219, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0027794197201728823, "weighted_relation_loss": 0.0027794197201728823 }, { "action_query_batch_std": 21.421209144592286, "action_query_norm": 922.0320556640625, "action_relation_loss": 0.002814653026871383, "auxiliary_loss_weight": 1.0, "epoch": 14.527595884003741, "flow_matching_loss": 0.02820975221693516, "grad_norm": 0.08914224803447723, "invalid_tail_samples": 22.3, "learning_rate": 5.1217935623803945e-05, "loss": 0.031, "positive_teacher_pairs": 27210.1, "relation_loss": 0.002814653026871383, "selected_pairs": 27210.1, "step": 15530, "student_distance_mean": 1229.1744873046875, "teacher_distance_mean": 0.8546329081058502, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.002814653026871383, "weighted_relation_loss": 0.002814653026871383 }, { "action_query_batch_std": 21.627086639404297, "action_query_norm": 926.8576843261719, "action_relation_loss": 0.0027366470312699676, "auxiliary_loss_weight": 1.0, "epoch": 14.536950420954163, "flow_matching_loss": 0.026699374429881573, "grad_norm": 0.11158714443445206, "invalid_tail_samples": 23.2, "learning_rate": 5.1162835588198476e-05, "loss": 0.0294, "positive_teacher_pairs": 26991.9, "relation_loss": 0.0027366470312699676, "selected_pairs": 26991.9, "step": 15540, "student_distance_mean": 1236.6898803710938, "teacher_distance_mean": 0.8591838419437409, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0027366470312699676, "weighted_relation_loss": 0.0027366470312699676 }, { "action_query_batch_std": 21.62427101135254, "action_query_norm": 927.4523376464844, "action_relation_loss": 0.002719797194004059, "auxiliary_loss_weight": 1.0, "epoch": 14.546304957904583, "flow_matching_loss": 0.02635779920965433, "grad_norm": 0.09929116815328598, "invalid_tail_samples": 24.1, "learning_rate": 5.110773413963813e-05, "loss": 0.0291, "positive_teacher_pairs": 26785.5, "relation_loss": 0.002719797194004059, "selected_pairs": 26785.5, "step": 15550, "student_distance_mean": 1242.7561157226562, "teacher_distance_mean": 0.8605045199394226, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.002719797194004059, "weighted_relation_loss": 0.002719797194004059 }, { "action_query_batch_std": 21.194828033447266, "action_query_norm": 916.5478759765625, "action_relation_loss": 0.0028742348542436956, "auxiliary_loss_weight": 1.0, "epoch": 14.555659494855005, "flow_matching_loss": 0.02749203834682703, "grad_norm": 0.10028113424777985, "invalid_tail_samples": 24.0, "learning_rate": 5.105263134507636e-05, "loss": 0.0304, "positive_teacher_pairs": 26803.6, "relation_loss": 0.0028742348542436956, "selected_pairs": 26803.6, "step": 15560, "student_distance_mean": 1215.0896240234374, "teacher_distance_mean": 0.8454653859138489, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0028742348542436956, "weighted_relation_loss": 0.0028742348542436956 }, { "action_query_batch_std": 21.42184066772461, "action_query_norm": 919.8288940429687, "action_relation_loss": 0.002696814411319792, "auxiliary_loss_weight": 1.0, "epoch": 14.565014031805426, "flow_matching_loss": 0.027572604082524776, "grad_norm": 0.1148643046617508, "invalid_tail_samples": 26.0, "learning_rate": 5.099752727146824e-05, "loss": 0.0303, "positive_teacher_pairs": 26345.7, "relation_loss": 0.002696814411319792, "selected_pairs": 26345.7, "step": 15570, "student_distance_mean": 1225.1492431640625, "teacher_distance_mean": 0.8526494860649109, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.002696814411319792, "weighted_relation_loss": 0.002696814411319792 }, { "action_query_batch_std": 21.381021308898926, "action_query_norm": 917.6518188476563, "action_relation_loss": 0.002731518354266882, "auxiliary_loss_weight": 1.0, "epoch": 14.574368568755848, "flow_matching_loss": 0.02902787979692221, "grad_norm": 0.1341719925403595, "invalid_tail_samples": 25.5, "learning_rate": 5.094242198577042e-05, "loss": 0.0318, "positive_teacher_pairs": 26460.5, "relation_loss": 0.002731518354266882, "selected_pairs": 26460.5, "step": 15580, "student_distance_mean": 1218.100439453125, "teacher_distance_mean": 0.8516272962093353, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.002731518354266882, "weighted_relation_loss": 0.002731518354266882 }, { "action_query_batch_std": 21.26472873687744, "action_query_norm": 912.0814208984375, "action_relation_loss": 0.0027328123804181816, "auxiliary_loss_weight": 1.0, "epoch": 14.583723105706268, "flow_matching_loss": 0.027141075395047665, "grad_norm": 0.1438722014427185, "invalid_tail_samples": 23.3, "learning_rate": 5.088731555494102e-05, "loss": 0.0299, "positive_teacher_pairs": 26974.0, "relation_loss": 0.0027328123804181816, "selected_pairs": 26974.0, "step": 15590, "student_distance_mean": 1214.5639404296876, "teacher_distance_mean": 0.8484114646911621, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0027328123804181816, "weighted_relation_loss": 0.0027328123804181816 }, { "action_query_batch_std": 21.526756477355956, "action_query_norm": 922.3526733398437, "action_relation_loss": 0.0027922222623601558, "auxiliary_loss_weight": 1.0, "epoch": 14.593077642656688, "flow_matching_loss": 0.029837075807154178, "grad_norm": 0.10338756442070007, "invalid_tail_samples": 28.2, "learning_rate": 5.0832208045939556e-05, "loss": 0.0326, "positive_teacher_pairs": 25839.1, "relation_loss": 0.0027922222623601558, "selected_pairs": 25839.1, "step": 15600, "student_distance_mean": 1232.1805297851563, "teacher_distance_mean": 0.8575399994850159, "valid_action_samples": 227.8, "weighted_auxiliary_loss": 0.0027922222623601558, "weighted_relation_loss": 0.0027922222623601558 }, { "action_query_batch_std": 21.074230575561522, "action_query_norm": 911.0002075195313, "action_relation_loss": 0.0027817504713311793, "auxiliary_loss_weight": 1.0, "epoch": 14.60243217960711, "flow_matching_loss": 0.02746355887502432, "grad_norm": 0.11266014724969864, "invalid_tail_samples": 24.6, "learning_rate": 5.0777099525726844e-05, "loss": 0.0302, "positive_teacher_pairs": 26663.7, "relation_loss": 0.0027817504713311793, "selected_pairs": 26663.7, "step": 15610, "student_distance_mean": 1210.261279296875, "teacher_distance_mean": 0.8426892936229706, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0027817504713311793, "weighted_relation_loss": 0.0027817504713311793 }, { "action_query_batch_std": 21.513151359558105, "action_query_norm": 920.6837219238281, "action_relation_loss": 0.0027333782520145176, "auxiliary_loss_weight": 1.0, "epoch": 14.61178671655753, "flow_matching_loss": 0.02831205204129219, "grad_norm": 0.10558247566223145, "invalid_tail_samples": 24.0, "learning_rate": 5.072199006126494e-05, "loss": 0.031, "positive_teacher_pairs": 26808.0, "relation_loss": 0.0027333782520145176, "selected_pairs": 26808.0, "step": 15620, "student_distance_mean": 1236.1793579101563, "teacher_distance_mean": 0.8622660636901855, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0027333782520145176, "weighted_relation_loss": 0.0027333782520145176 }, { "action_query_batch_std": 21.382597351074217, "action_query_norm": 917.9253967285156, "action_relation_loss": 0.0028646996477618815, "auxiliary_loss_weight": 1.0, "epoch": 14.621141253507952, "flow_matching_loss": 0.028588126972317697, "grad_norm": 0.10089243948459625, "invalid_tail_samples": 22.2, "learning_rate": 5.0666879719517026e-05, "loss": 0.0315, "positive_teacher_pairs": 27228.9, "relation_loss": 0.0028646996477618815, "selected_pairs": 27228.9, "step": 15630, "student_distance_mean": 1229.9016723632812, "teacher_distance_mean": 0.8538028061389923, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.0028646996477618815, "weighted_relation_loss": 0.0028646996477618815 }, { "action_query_batch_std": 21.643329048156737, "action_query_norm": 927.2338989257812, "action_relation_loss": 0.002825827687047422, "auxiliary_loss_weight": 1.0, "epoch": 14.630495790458372, "flow_matching_loss": 0.02851315550506115, "grad_norm": 0.11588869243860245, "invalid_tail_samples": 24.8, "learning_rate": 5.061176856744737e-05, "loss": 0.0313, "positive_teacher_pairs": 26619.6, "relation_loss": 0.002825827687047422, "selected_pairs": 26619.6, "step": 15640, "student_distance_mean": 1240.8652099609376, "teacher_distance_mean": 0.8608981013298035, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.002825827687047422, "weighted_relation_loss": 0.002825827687047422 }, { "action_query_batch_std": 21.87163600921631, "action_query_norm": 936.7227661132813, "action_relation_loss": 0.002766775130294263, "auxiliary_loss_weight": 1.0, "epoch": 14.639850327408793, "flow_matching_loss": 0.027373983711004257, "grad_norm": 0.12809956073760986, "invalid_tail_samples": 23.1, "learning_rate": 5.0556656672021205e-05, "loss": 0.0301, "positive_teacher_pairs": 27014.6, "relation_loss": 0.002766775130294263, "selected_pairs": 27014.6, "step": 15650, "student_distance_mean": 1249.2963256835938, "teacher_distance_mean": 0.8618495166301727, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.002766775130294263, "weighted_relation_loss": 0.002766775130294263 }, { "action_query_batch_std": 21.791871070861816, "action_query_norm": 933.0516845703125, "action_relation_loss": 0.002690216340124607, "auxiliary_loss_weight": 1.0, "epoch": 14.649204864359215, "flow_matching_loss": 0.026500642858445646, "grad_norm": 0.103389210999012, "invalid_tail_samples": 24.9, "learning_rate": 5.050154410020472e-05, "loss": 0.0292, "positive_teacher_pairs": 26594.3, "relation_loss": 0.002690216340124607, "selected_pairs": 26594.3, "step": 15660, "student_distance_mean": 1251.887158203125, "teacher_distance_mean": 0.8626181781291962, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.002690216340124607, "weighted_relation_loss": 0.002690216340124607 }, { "action_query_batch_std": 21.654616928100587, "action_query_norm": 931.7855163574219, "action_relation_loss": 0.002820132463239133, "auxiliary_loss_weight": 1.0, "epoch": 14.658559401309635, "flow_matching_loss": 0.02852943278849125, "grad_norm": 0.10759888589382172, "invalid_tail_samples": 24.4, "learning_rate": 5.044643091896485e-05, "loss": 0.0313, "positive_teacher_pairs": 26709.2, "relation_loss": 0.002820132463239133, "selected_pairs": 26709.2, "step": 15670, "student_distance_mean": 1237.898046875, "teacher_distance_mean": 0.8551167488098145, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.002820132463239133, "weighted_relation_loss": 0.002820132463239133 }, { "action_query_batch_std": 21.87904930114746, "action_query_norm": 936.6632446289062, "action_relation_loss": 0.0028284398606047033, "auxiliary_loss_weight": 1.0, "epoch": 14.667913938260057, "flow_matching_loss": 0.028047763369977476, "grad_norm": 0.11511658132076263, "invalid_tail_samples": 24.6, "learning_rate": 5.039131719526932e-05, "loss": 0.0309, "positive_teacher_pairs": 26670.7, "relation_loss": 0.0028284398606047033, "selected_pairs": 26670.7, "step": 15680, "student_distance_mean": 1251.8130004882812, "teacher_distance_mean": 0.8671139359474183, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0028284398606047033, "weighted_relation_loss": 0.0028284398606047033 }, { "action_query_batch_std": 21.68942756652832, "action_query_norm": 932.6180297851563, "action_relation_loss": 0.002758005284704268, "auxiliary_loss_weight": 1.0, "epoch": 14.677268475210477, "flow_matching_loss": 0.02751565370708704, "grad_norm": 0.09826423972845078, "invalid_tail_samples": 24.6, "learning_rate": 5.03362029960865e-05, "loss": 0.0303, "positive_teacher_pairs": 26666.3, "relation_loss": 0.002758005284704268, "selected_pairs": 26666.3, "step": 15690, "student_distance_mean": 1240.3953002929688, "teacher_distance_mean": 0.8589360237121582, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.002758005284704268, "weighted_relation_loss": 0.002758005284704268 }, { "action_query_batch_std": 21.84843006134033, "action_query_norm": 933.6779663085938, "action_relation_loss": 0.00274412261787802, "auxiliary_loss_weight": 1.0, "epoch": 14.686623012160897, "flow_matching_loss": 0.029049177281558515, "grad_norm": 0.12380869686603546, "invalid_tail_samples": 21.3, "learning_rate": 5.028108838838533e-05, "loss": 0.0318, "positive_teacher_pairs": 27431.7, "relation_loss": 0.00274412261787802, "selected_pairs": 27431.7, "step": 15700, "student_distance_mean": 1244.514697265625, "teacher_distance_mean": 0.8608365833759308, "valid_action_samples": 234.7, "weighted_auxiliary_loss": 0.00274412261787802, "weighted_relation_loss": 0.00274412261787802 }, { "action_query_batch_std": 21.462580680847168, "action_query_norm": 922.1676025390625, "action_relation_loss": 0.002693793992511928, "auxiliary_loss_weight": 1.0, "epoch": 14.69597754911132, "flow_matching_loss": 0.028581404127180576, "grad_norm": 0.10348918288946152, "invalid_tail_samples": 24.2, "learning_rate": 5.0225973439135276e-05, "loss": 0.0313, "positive_teacher_pairs": 26760.9, "relation_loss": 0.002693793992511928, "selected_pairs": 26760.9, "step": 15710, "student_distance_mean": 1227.2948486328125, "teacher_distance_mean": 0.8481704771518708, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.002693793992511928, "weighted_relation_loss": 0.002693793992511928 }, { "action_query_batch_std": 21.54010467529297, "action_query_norm": 928.1346618652344, "action_relation_loss": 0.0028056310256943107, "auxiliary_loss_weight": 1.0, "epoch": 14.70533208606174, "flow_matching_loss": 0.027319940365850927, "grad_norm": 0.12230084836483002, "invalid_tail_samples": 22.8, "learning_rate": 5.017085821530617e-05, "loss": 0.0301, "positive_teacher_pairs": 27088.1, "relation_loss": 0.0028056310256943107, "selected_pairs": 27088.1, "step": 15720, "student_distance_mean": 1233.821728515625, "teacher_distance_mean": 0.8559103906154633, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0028056310256943107, "weighted_relation_loss": 0.0028056310256943107 }, { "action_query_batch_std": 21.34808483123779, "action_query_norm": 919.5624084472656, "action_relation_loss": 0.0028102716896682978, "auxiliary_loss_weight": 1.0, "epoch": 14.714686623012161, "flow_matching_loss": 0.027006172761321067, "grad_norm": 0.09444285929203033, "invalid_tail_samples": 24.6, "learning_rate": 5.011574278386822e-05, "loss": 0.0298, "positive_teacher_pairs": 26668.7, "relation_loss": 0.0028102716896682978, "selected_pairs": 26668.7, "step": 15730, "student_distance_mean": 1220.694384765625, "teacher_distance_mean": 0.8457450151443482, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0028102716896682978, "weighted_relation_loss": 0.0028102716896682978 }, { "action_query_batch_std": 21.88703384399414, "action_query_norm": 935.2520874023437, "action_relation_loss": 0.002750511188060045, "auxiliary_loss_weight": 1.0, "epoch": 14.724041159962582, "flow_matching_loss": 0.028755470365285873, "grad_norm": 0.11205844581127167, "invalid_tail_samples": 25.0, "learning_rate": 5.006062721179189e-05, "loss": 0.0315, "positive_teacher_pairs": 26573.9, "relation_loss": 0.002750511188060045, "selected_pairs": 26573.9, "step": 15740, "student_distance_mean": 1256.7381591796875, "teacher_distance_mean": 0.869992595911026, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.002750511188060045, "weighted_relation_loss": 0.002750511188060045 }, { "action_query_batch_std": 21.539260864257812, "action_query_norm": 924.3565734863281, "action_relation_loss": 0.002728842734359205, "auxiliary_loss_weight": 1.0, "epoch": 14.733395696913004, "flow_matching_loss": 0.027455173432826996, "grad_norm": 0.09981481730937958, "invalid_tail_samples": 22.1, "learning_rate": 5.000551156604777e-05, "loss": 0.0302, "positive_teacher_pairs": 27247.2, "relation_loss": 0.002728842734359205, "selected_pairs": 27247.2, "step": 15750, "student_distance_mean": 1230.7052124023437, "teacher_distance_mean": 0.8509743630886077, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.002728842734359205, "weighted_relation_loss": 0.002728842734359205 }, { "action_query_batch_std": 21.562621116638184, "action_query_norm": 923.3889038085938, "action_relation_loss": 0.0029075361555442212, "auxiliary_loss_weight": 1.0, "epoch": 14.742750233863424, "flow_matching_loss": 0.02863099779933691, "grad_norm": 0.0934038832783699, "invalid_tail_samples": 23.5, "learning_rate": 4.9950395913606594e-05, "loss": 0.0315, "positive_teacher_pairs": 26918.3, "relation_loss": 0.0029075361555442212, "selected_pairs": 26918.3, "step": 15760, "student_distance_mean": 1230.5442749023437, "teacher_distance_mean": 0.848172789812088, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0029075361555442212, "weighted_relation_loss": 0.0029075361555442212 }, { "action_query_batch_std": 21.47513618469238, "action_query_norm": 923.2845458984375, "action_relation_loss": 0.002801936608739197, "auxiliary_loss_weight": 1.0, "epoch": 14.752104770813844, "flow_matching_loss": 0.02858567424118519, "grad_norm": 0.08500552922487259, "invalid_tail_samples": 26.0, "learning_rate": 4.989528032143903e-05, "loss": 0.0314, "positive_teacher_pairs": 26343.4, "relation_loss": 0.002801936608739197, "selected_pairs": 26343.4, "step": 15770, "student_distance_mean": 1234.5054321289062, "teacher_distance_mean": 0.847814929485321, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.002801936608739197, "weighted_relation_loss": 0.002801936608739197 }, { "action_query_batch_std": 21.644924354553222, "action_query_norm": 928.6617614746094, "action_relation_loss": 0.0028661355609074235, "auxiliary_loss_weight": 1.0, "epoch": 14.761459307764266, "flow_matching_loss": 0.027333442494273184, "grad_norm": 0.13236363232135773, "invalid_tail_samples": 25.3, "learning_rate": 4.984016485651578e-05, "loss": 0.0302, "positive_teacher_pairs": 26507.2, "relation_loss": 0.0028661355609074235, "selected_pairs": 26507.2, "step": 15780, "student_distance_mean": 1236.005615234375, "teacher_distance_mean": 0.8494770228862762, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0028661355609074235, "weighted_relation_loss": 0.0028661355609074235 }, { "action_query_batch_std": 22.000094413757324, "action_query_norm": 941.466796875, "action_relation_loss": 0.002685200818814337, "auxiliary_loss_weight": 1.0, "epoch": 14.770813844714686, "flow_matching_loss": 0.026898351684212684, "grad_norm": 0.10448241978883743, "invalid_tail_samples": 20.7, "learning_rate": 4.9785049585807274e-05, "loss": 0.0296, "positive_teacher_pairs": 27568.6, "relation_loss": 0.002685200818814337, "selected_pairs": 27568.6, "step": 15790, "student_distance_mean": 1261.1169677734374, "teacher_distance_mean": 0.8693042159080505, "valid_action_samples": 235.3, "weighted_auxiliary_loss": 0.002685200818814337, "weighted_relation_loss": 0.002685200818814337 }, { "action_query_batch_std": 21.67979030609131, "action_query_norm": 931.69267578125, "action_relation_loss": 0.0027393373427912595, "auxiliary_loss_weight": 1.0, "epoch": 14.780168381665108, "flow_matching_loss": 0.02838548384606838, "grad_norm": 0.10507633537054062, "invalid_tail_samples": 23.5, "learning_rate": 4.972993457628381e-05, "loss": 0.0311, "positive_teacher_pairs": 26918.4, "relation_loss": 0.0027393373427912595, "selected_pairs": 26918.4, "step": 15800, "student_distance_mean": 1240.2625732421875, "teacher_distance_mean": 0.8501485884189606, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0027393373427912595, "weighted_relation_loss": 0.0027393373427912595 }, { "action_query_batch_std": 21.72621269226074, "action_query_norm": 932.37998046875, "action_relation_loss": 0.002770136808976531, "auxiliary_loss_weight": 1.0, "epoch": 14.789522918615528, "flow_matching_loss": 0.02766386941075325, "grad_norm": 0.11485303193330765, "invalid_tail_samples": 23.7, "learning_rate": 4.9674819894915306e-05, "loss": 0.0304, "positive_teacher_pairs": 26868.7, "relation_loss": 0.002770136808976531, "selected_pairs": 26868.7, "step": 15810, "student_distance_mean": 1243.1386352539062, "teacher_distance_mean": 0.8562114775180817, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.002770136808976531, "weighted_relation_loss": 0.002770136808976531 }, { "action_query_batch_std": 21.779371070861817, "action_query_norm": 929.6510375976562, "action_relation_loss": 0.0026208672439679503, "auxiliary_loss_weight": 1.0, "epoch": 14.79887745556595, "flow_matching_loss": 0.029018434882164, "grad_norm": 0.11415112763643265, "invalid_tail_samples": 25.5, "learning_rate": 4.9619705608671265e-05, "loss": 0.0316, "positive_teacher_pairs": 26462.3, "relation_loss": 0.0026208672439679503, "selected_pairs": 26462.3, "step": 15820, "student_distance_mean": 1247.7427490234375, "teacher_distance_mean": 0.8582633435726166, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0026208672439679503, "weighted_relation_loss": 0.0026208672439679503 }, { "action_query_batch_std": 21.72714767456055, "action_query_norm": 931.7411682128907, "action_relation_loss": 0.0027495715767145157, "auxiliary_loss_weight": 1.0, "epoch": 14.80823199251637, "flow_matching_loss": 0.027152075432240963, "grad_norm": 0.10275137424468994, "invalid_tail_samples": 24.7, "learning_rate": 4.956459178452079e-05, "loss": 0.0299, "positive_teacher_pairs": 26648.6, "relation_loss": 0.0027495715767145157, "selected_pairs": 26648.6, "step": 15830, "student_distance_mean": 1239.8196533203125, "teacher_distance_mean": 0.8567769825458527, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0027495715767145157, "weighted_relation_loss": 0.0027495715767145157 }, { "action_query_batch_std": 21.6420316696167, "action_query_norm": 927.3227294921875, "action_relation_loss": 0.0026447610463947056, "auxiliary_loss_weight": 1.0, "epoch": 14.81758652946679, "flow_matching_loss": 0.026589137874543665, "grad_norm": 0.09118569642305374, "invalid_tail_samples": 22.3, "learning_rate": 4.950947848943235e-05, "loss": 0.0292, "positive_teacher_pairs": 27200.2, "relation_loss": 0.0026447610463947056, "selected_pairs": 27200.2, "step": 15840, "student_distance_mean": 1235.6014404296875, "teacher_distance_mean": 0.8561438739299774, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0026447610463947056, "weighted_relation_loss": 0.0026447610463947056 }, { "action_query_batch_std": 21.58119888305664, "action_query_norm": 923.8560424804688, "action_relation_loss": 0.002783134439960122, "auxiliary_loss_weight": 1.0, "epoch": 14.826941066417213, "flow_matching_loss": 0.027497879602015017, "grad_norm": 0.11015778034925461, "invalid_tail_samples": 23.3, "learning_rate": 4.9454365790373805e-05, "loss": 0.0303, "positive_teacher_pairs": 26966.3, "relation_loss": 0.002783134439960122, "selected_pairs": 26966.3, "step": 15850, "student_distance_mean": 1231.4862670898438, "teacher_distance_mean": 0.8506567656993866, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.002783134439960122, "weighted_relation_loss": 0.002783134439960122 }, { "action_query_batch_std": 21.601576232910155, "action_query_norm": 924.7248962402343, "action_relation_loss": 0.002847340377047658, "auxiliary_loss_weight": 1.0, "epoch": 14.836295603367633, "flow_matching_loss": 0.028117856197059154, "grad_norm": 0.09666959941387177, "invalid_tail_samples": 24.2, "learning_rate": 4.939925375431226e-05, "loss": 0.031, "positive_teacher_pairs": 26754.3, "relation_loss": 0.002847340377047658, "selected_pairs": 26754.3, "step": 15860, "student_distance_mean": 1237.5952270507812, "teacher_distance_mean": 0.8549624502658844, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.002847340377047658, "weighted_relation_loss": 0.002847340377047658 }, { "action_query_batch_std": 21.749921798706055, "action_query_norm": 932.9296081542968, "action_relation_loss": 0.0027608514996245504, "auxiliary_loss_weight": 1.0, "epoch": 14.845650140318055, "flow_matching_loss": 0.028009040653705596, "grad_norm": 0.14366060495376587, "invalid_tail_samples": 21.5, "learning_rate": 4.9344142448214046e-05, "loss": 0.0308, "positive_teacher_pairs": 27386.8, "relation_loss": 0.0027608514996245504, "selected_pairs": 27386.8, "step": 15870, "student_distance_mean": 1244.4904663085938, "teacher_distance_mean": 0.8531561255455017, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.0027608514996245504, "weighted_relation_loss": 0.0027608514996245504 }, { "action_query_batch_std": 21.52900276184082, "action_query_norm": 924.4286315917968, "action_relation_loss": 0.0027261972427368164, "auxiliary_loss_weight": 1.0, "epoch": 14.855004677268475, "flow_matching_loss": 0.026599129289388658, "grad_norm": 0.10939832776784897, "invalid_tail_samples": 21.8, "learning_rate": 4.928903193904461e-05, "loss": 0.0293, "positive_teacher_pairs": 27322.8, "relation_loss": 0.0027261972427368164, "selected_pairs": 27322.8, "step": 15880, "student_distance_mean": 1230.4433837890624, "teacher_distance_mean": 0.8479480385780335, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.0027261972427368164, "weighted_relation_loss": 0.0027261972427368164 }, { "action_query_batch_std": 21.69079418182373, "action_query_norm": 929.8378662109375, "action_relation_loss": 0.002697735978290439, "auxiliary_loss_weight": 1.0, "epoch": 14.864359214218895, "flow_matching_loss": 0.027210380136966705, "grad_norm": 0.12245851010084152, "invalid_tail_samples": 22.8, "learning_rate": 4.923392229376842e-05, "loss": 0.0299, "positive_teacher_pairs": 27087.7, "relation_loss": 0.002697735978290439, "selected_pairs": 27087.7, "step": 15890, "student_distance_mean": 1242.2365844726562, "teacher_distance_mean": 0.8566983222961426, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.002697735978290439, "weighted_relation_loss": 0.002697735978290439 }, { "action_query_batch_std": 21.829817008972167, "action_query_norm": 934.836669921875, "action_relation_loss": 0.002723132842220366, "auxiliary_loss_weight": 1.0, "epoch": 14.873713751169317, "flow_matching_loss": 0.027105480432510376, "grad_norm": 0.10341044515371323, "invalid_tail_samples": 24.5, "learning_rate": 4.9178813579348865e-05, "loss": 0.0298, "positive_teacher_pairs": 26689.0, "relation_loss": 0.002723132842220366, "selected_pairs": 26689.0, "step": 15900, "student_distance_mean": 1251.9032470703125, "teacher_distance_mean": 0.8622668981552124, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.002723132842220366, "weighted_relation_loss": 0.002723132842220366 }, { "action_query_batch_std": 21.691774749755858, "action_query_norm": 930.2051391601562, "action_relation_loss": 0.0026803169399499892, "auxiliary_loss_weight": 1.0, "epoch": 14.883068288119738, "flow_matching_loss": 0.026381395757198334, "grad_norm": 0.105820432305336, "invalid_tail_samples": 22.3, "learning_rate": 4.9123705862748253e-05, "loss": 0.0291, "positive_teacher_pairs": 27201.5, "relation_loss": 0.0026803169399499892, "selected_pairs": 27201.5, "step": 15910, "student_distance_mean": 1238.8520629882812, "teacher_distance_mean": 0.8558797717094422, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0026803169399499892, "weighted_relation_loss": 0.0026803169399499892 }, { "action_query_batch_std": 21.459306526184083, "action_query_norm": 922.0189819335938, "action_relation_loss": 0.00275446199811995, "auxiliary_loss_weight": 1.0, "epoch": 14.89242282507016, "flow_matching_loss": 0.02696255501359701, "grad_norm": 0.09850567579269409, "invalid_tail_samples": 24.1, "learning_rate": 4.9068599210927627e-05, "loss": 0.0297, "positive_teacher_pairs": 26781.0, "relation_loss": 0.00275446199811995, "selected_pairs": 26781.0, "step": 15920, "student_distance_mean": 1231.0932006835938, "teacher_distance_mean": 0.8520523607730865, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.00275446199811995, "weighted_relation_loss": 0.00275446199811995 }, { "action_query_batch_std": 21.945726203918458, "action_query_norm": 939.4024291992188, "action_relation_loss": 0.0028000995283946396, "auxiliary_loss_weight": 1.0, "epoch": 14.90177736202058, "flow_matching_loss": 0.028780340403318404, "grad_norm": 0.10006828606128693, "invalid_tail_samples": 23.8, "learning_rate": 4.901349369084681e-05, "loss": 0.0316, "positive_teacher_pairs": 26867.7, "relation_loss": 0.0028000995283946396, "selected_pairs": 26867.7, "step": 15930, "student_distance_mean": 1255.9296508789062, "teacher_distance_mean": 0.8657507419586181, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0028000995283946396, "weighted_relation_loss": 0.0028000995283946396 }, { "action_query_batch_std": 21.793487548828125, "action_query_norm": 932.8587524414063, "action_relation_loss": 0.0026809737319126725, "auxiliary_loss_weight": 1.0, "epoch": 14.911131898971, "flow_matching_loss": 0.027578430064022542, "grad_norm": 0.09924568980932236, "invalid_tail_samples": 22.2, "learning_rate": 4.8958389369464156e-05, "loss": 0.0303, "positive_teacher_pairs": 27218.8, "relation_loss": 0.0026809737319126725, "selected_pairs": 27218.8, "step": 15940, "student_distance_mean": 1245.820068359375, "teacher_distance_mean": 0.8628336191177368, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.0026809737319126725, "weighted_relation_loss": 0.0026809737319126725 }, { "action_query_batch_std": 21.480237770080567, "action_query_norm": 922.2400024414062, "action_relation_loss": 0.0028301999671384694, "auxiliary_loss_weight": 1.0, "epoch": 14.920486435921422, "flow_matching_loss": 0.02966190315783024, "grad_norm": 0.10770256072282791, "invalid_tail_samples": 23.9, "learning_rate": 4.890328631373666e-05, "loss": 0.0325, "positive_teacher_pairs": 26825.5, "relation_loss": 0.0028301999671384694, "selected_pairs": 26825.5, "step": 15950, "student_distance_mean": 1227.1464965820312, "teacher_distance_mean": 0.8486961424350739, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0028301999671384694, "weighted_relation_loss": 0.0028301999671384694 }, { "action_query_batch_std": 21.383640670776366, "action_query_norm": 918.0284240722656, "action_relation_loss": 0.0027720932150259612, "auxiliary_loss_weight": 1.0, "epoch": 14.929840972871842, "flow_matching_loss": 0.027013534680008888, "grad_norm": 0.10642044991254807, "invalid_tail_samples": 25.1, "learning_rate": 4.88481845906197e-05, "loss": 0.0298, "positive_teacher_pairs": 26560.2, "relation_loss": 0.0027720932150259612, "selected_pairs": 26560.2, "step": 15960, "student_distance_mean": 1226.5896728515625, "teacher_distance_mean": 0.8492038726806641, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0027720932150259612, "weighted_relation_loss": 0.0027720932150259612 }, { "action_query_batch_std": 21.793937301635744, "action_query_norm": 931.3570983886718, "action_relation_loss": 0.002730679139494896, "auxiliary_loss_weight": 1.0, "epoch": 14.939195509822264, "flow_matching_loss": 0.028074264898896216, "grad_norm": 0.11467378586530685, "invalid_tail_samples": 23.7, "learning_rate": 4.879308426706707e-05, "loss": 0.0308, "positive_teacher_pairs": 26880.1, "relation_loss": 0.002730679139494896, "selected_pairs": 26880.1, "step": 15970, "student_distance_mean": 1242.7136840820312, "teacher_distance_mean": 0.8588651120662689, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.002730679139494896, "weighted_relation_loss": 0.002730679139494896 }, { "action_query_batch_std": 21.47414073944092, "action_query_norm": 924.9216064453125, "action_relation_loss": 0.002880202163942158, "auxiliary_loss_weight": 1.0, "epoch": 14.948550046772684, "flow_matching_loss": 0.02776498068124056, "grad_norm": 0.09370090067386627, "invalid_tail_samples": 20.7, "learning_rate": 4.873798541003084e-05, "loss": 0.0306, "positive_teacher_pairs": 27573.8, "relation_loss": 0.002880202163942158, "selected_pairs": 27573.8, "step": 15980, "student_distance_mean": 1230.1294921875, "teacher_distance_mean": 0.851254403591156, "valid_action_samples": 235.3, "weighted_auxiliary_loss": 0.002880202163942158, "weighted_relation_loss": 0.002880202163942158 }, { "action_query_batch_std": 21.458189392089842, "action_query_norm": 919.7761962890625, "action_relation_loss": 0.0027952073607593773, "auxiliary_loss_weight": 1.0, "epoch": 14.957904583723106, "flow_matching_loss": 0.029492870345711707, "grad_norm": 0.10757555067539215, "invalid_tail_samples": 24.4, "learning_rate": 4.868288808646136e-05, "loss": 0.0323, "positive_teacher_pairs": 26729.0, "relation_loss": 0.0027952073607593773, "selected_pairs": 26729.0, "step": 15990, "student_distance_mean": 1226.5484741210937, "teacher_distance_mean": 0.8461026966571807, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0027952073607593773, "weighted_relation_loss": 0.0027952073607593773 }, { "action_query_batch_std": 21.508200454711915, "action_query_norm": 919.7609619140625, "action_relation_loss": 0.0028361596632748842, "auxiliary_loss_weight": 1.0, "epoch": 14.967259120673527, "flow_matching_loss": 0.027176596224308014, "grad_norm": 0.1305890828371048, "invalid_tail_samples": 25.5, "learning_rate": 4.862779236330705e-05, "loss": 0.03, "positive_teacher_pairs": 26467.5, "relation_loss": 0.0028361596632748842, "selected_pairs": 26467.5, "step": 16000, "student_distance_mean": 1232.9594116210938, "teacher_distance_mean": 0.8566137671470642, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0028361596632748842, "weighted_relation_loss": 0.0028361596632748842 }, { "action_query_batch_std": 21.620826530456544, "action_query_norm": 926.6345581054687, "action_relation_loss": 0.0027396226767450573, "auxiliary_loss_weight": 1.0, "epoch": 14.976613657623947, "flow_matching_loss": 0.027917726524174215, "grad_norm": 0.10658732801675797, "invalid_tail_samples": 26.7, "learning_rate": 4.8572698307514395e-05, "loss": 0.0307, "positive_teacher_pairs": 26179.4, "relation_loss": 0.0027396226767450573, "selected_pairs": 26179.4, "step": 16010, "student_distance_mean": 1238.6505615234375, "teacher_distance_mean": 0.8521770775318146, "valid_action_samples": 229.3, "weighted_auxiliary_loss": 0.0027396226767450573, "weighted_relation_loss": 0.0027396226767450573 }, { "action_query_batch_std": 21.399383735656738, "action_query_norm": 921.7839599609375, "action_relation_loss": 0.002753402478992939, "auxiliary_loss_weight": 1.0, "epoch": 14.985968194574369, "flow_matching_loss": 0.026337414234876632, "grad_norm": 0.0965033546090126, "invalid_tail_samples": 23.4, "learning_rate": 4.85176059860279e-05, "loss": 0.0291, "positive_teacher_pairs": 26940.3, "relation_loss": 0.002753402478992939, "selected_pairs": 26940.3, "step": 16020, "student_distance_mean": 1227.7432373046875, "teacher_distance_mean": 0.8496523916721344, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.002753402478992939, "weighted_relation_loss": 0.002753402478992939 }, { "action_query_batch_std": 21.662370491027833, "action_query_norm": 927.7342041015625, "action_relation_loss": 0.0029043664457276464, "auxiliary_loss_weight": 1.0, "epoch": 14.995322731524789, "flow_matching_loss": 0.0290254607796669, "grad_norm": 0.10350127518177032, "invalid_tail_samples": 24.0, "learning_rate": 4.846251546578989e-05, "loss": 0.0319, "positive_teacher_pairs": 26806.9, "relation_loss": 0.0029043664457276464, "selected_pairs": 26806.9, "step": 16030, "student_distance_mean": 1232.8454711914062, "teacher_distance_mean": 0.8524382591247559, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0029043664457276464, "weighted_relation_loss": 0.0029043664457276464 }, { "action_query_batch_std": 21.62014102935791, "action_query_norm": 926.5281799316406, "action_relation_loss": 0.002861104323528707, "auxiliary_loss_weight": 1.0, "epoch": 15.004677268475211, "flow_matching_loss": 0.027453535981476308, "grad_norm": 0.12585605680942535, "invalid_tail_samples": 23.8, "learning_rate": 4.840742681374058e-05, "loss": 0.0303, "positive_teacher_pairs": 23953.5, "relation_loss": 0.002861104323528707, "selected_pairs": 23953.5, "step": 16040, "student_distance_mean": 1240.4241088867188, "teacher_distance_mean": 0.8579780220985412, "valid_action_samples": 212.3, "weighted_auxiliary_loss": 0.002861104323528707, "weighted_relation_loss": 0.002861104323528707 }, { "action_query_batch_std": 21.578114891052245, "action_query_norm": 924.8219421386718, "action_relation_loss": 0.002844993001781404, "auxiliary_loss_weight": 1.0, "epoch": 15.014031805425631, "flow_matching_loss": 0.02610849402844906, "grad_norm": 0.09287761151790619, "invalid_tail_samples": 25.6, "learning_rate": 4.835234009681787e-05, "loss": 0.029, "positive_teacher_pairs": 26436.1, "relation_loss": 0.002844993001781404, "selected_pairs": 26436.1, "step": 16050, "student_distance_mean": 1236.7763305664062, "teacher_distance_mean": 0.8552719354629517, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.002844993001781404, "weighted_relation_loss": 0.002844993001781404 }, { "action_query_batch_std": 21.742399215698242, "action_query_norm": 932.8934204101563, "action_relation_loss": 0.0026856089709326623, "auxiliary_loss_weight": 1.0, "epoch": 15.023386342376053, "flow_matching_loss": 0.028984493389725686, "grad_norm": 0.10586724430322647, "invalid_tail_samples": 22.8, "learning_rate": 4.8297255381957296e-05, "loss": 0.0317, "positive_teacher_pairs": 27079.7, "relation_loss": 0.0026856089709326623, "selected_pairs": 27079.7, "step": 16060, "student_distance_mean": 1246.9840209960937, "teacher_distance_mean": 0.8575641274452209, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0026856089709326623, "weighted_relation_loss": 0.0026856089709326623 }, { "action_query_batch_std": 22.00913848876953, "action_query_norm": 941.3612731933594, "action_relation_loss": 0.0025919900042936208, "auxiliary_loss_weight": 1.0, "epoch": 15.032740879326473, "flow_matching_loss": 0.02719077989459038, "grad_norm": 0.12000707536935806, "invalid_tail_samples": 24.8, "learning_rate": 4.824217273609198e-05, "loss": 0.0298, "positive_teacher_pairs": 26614.3, "relation_loss": 0.0025919900042936208, "selected_pairs": 26614.3, "step": 16070, "student_distance_mean": 1257.350634765625, "teacher_distance_mean": 0.8633100748062134, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0025919900042936208, "weighted_relation_loss": 0.0025919900042936208 }, { "action_query_batch_std": 21.169489097595214, "action_query_norm": 912.3464111328125, "action_relation_loss": 0.002822699141688645, "auxiliary_loss_weight": 1.0, "epoch": 15.042095416276894, "flow_matching_loss": 0.025748582556843758, "grad_norm": 0.12824897468090057, "invalid_tail_samples": 23.9, "learning_rate": 4.8187092226152555e-05, "loss": 0.0286, "positive_teacher_pairs": 26833.3, "relation_loss": 0.002822699141688645, "selected_pairs": 26833.3, "step": 16080, "student_distance_mean": 1214.10126953125, "teacher_distance_mean": 0.8334941744804383, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.002822699141688645, "weighted_relation_loss": 0.002822699141688645 }, { "action_query_batch_std": 21.721557426452637, "action_query_norm": 930.9859680175781, "action_relation_loss": 0.0026761257089674474, "auxiliary_loss_weight": 1.0, "epoch": 15.051449953227316, "flow_matching_loss": 0.026725221239030362, "grad_norm": 0.08357487618923187, "invalid_tail_samples": 24.1, "learning_rate": 4.8132013919067016e-05, "loss": 0.0294, "positive_teacher_pairs": 26782.4, "relation_loss": 0.0026761257089674474, "selected_pairs": 26782.4, "step": 16090, "student_distance_mean": 1234.6742431640625, "teacher_distance_mean": 0.8522696316242218, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0026761257089674474, "weighted_relation_loss": 0.0026761257089674474 }, { "action_query_batch_std": 21.534968185424805, "action_query_norm": 926.1386474609375, "action_relation_loss": 0.0026304125087335704, "auxiliary_loss_weight": 1.0, "epoch": 15.060804490177736, "flow_matching_loss": 0.026120550371706484, "grad_norm": 0.09286938607692719, "invalid_tail_samples": 23.0, "learning_rate": 4.807693788176071e-05, "loss": 0.0288, "positive_teacher_pairs": 27039.5, "relation_loss": 0.0026304125087335704, "selected_pairs": 27039.5, "step": 16100, "student_distance_mean": 1229.530322265625, "teacher_distance_mean": 0.8432645618915557, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0026304125087335704, "weighted_relation_loss": 0.0026304125087335704 }, { "action_query_batch_std": 21.689150619506837, "action_query_norm": 930.0286926269531, "action_relation_loss": 0.00262599834240973, "auxiliary_loss_weight": 1.0, "epoch": 15.070159027128158, "flow_matching_loss": 0.027241843752563, "grad_norm": 0.11275878548622131, "invalid_tail_samples": 25.8, "learning_rate": 4.8021864181156214e-05, "loss": 0.0299, "positive_teacher_pairs": 26386.3, "relation_loss": 0.00262599834240973, "selected_pairs": 26386.3, "step": 16110, "student_distance_mean": 1245.1088745117188, "teacher_distance_mean": 0.859071010351181, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.00262599834240973, "weighted_relation_loss": 0.00262599834240973 }, { "action_query_batch_std": 21.291510772705077, "action_query_norm": 915.4393188476563, "action_relation_loss": 0.002651836141012609, "auxiliary_loss_weight": 1.0, "epoch": 15.079513564078578, "flow_matching_loss": 0.02678303737193346, "grad_norm": 0.09013233333826065, "invalid_tail_samples": 24.8, "learning_rate": 4.796679288417326e-05, "loss": 0.0294, "positive_teacher_pairs": 26623.9, "relation_loss": 0.002651836141012609, "selected_pairs": 26623.9, "step": 16120, "student_distance_mean": 1222.7878540039062, "teacher_distance_mean": 0.8432132422924041, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.002651836141012609, "weighted_relation_loss": 0.002651836141012609 }, { "action_query_batch_std": 21.536182403564453, "action_query_norm": 922.7911254882813, "action_relation_loss": 0.0026609679916873574, "auxiliary_loss_weight": 1.0, "epoch": 15.088868101028998, "flow_matching_loss": 0.024924667179584505, "grad_norm": 0.09294982999563217, "invalid_tail_samples": 23.5, "learning_rate": 4.791172405772866e-05, "loss": 0.0276, "positive_teacher_pairs": 26922.5, "relation_loss": 0.0026609679916873574, "selected_pairs": 26922.5, "step": 16130, "student_distance_mean": 1228.7887329101563, "teacher_distance_mean": 0.8497547209262848, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0026609679916873574, "weighted_relation_loss": 0.0026609679916873574 }, { "action_query_batch_std": 21.866948509216307, "action_query_norm": 935.0359252929687, "action_relation_loss": 0.0026702994713559748, "auxiliary_loss_weight": 1.0, "epoch": 15.09822263797942, "flow_matching_loss": 0.02488714735955, "grad_norm": 0.09527314454317093, "invalid_tail_samples": 25.4, "learning_rate": 4.785665776873625e-05, "loss": 0.0276, "positive_teacher_pairs": 26484.2, "relation_loss": 0.0026702994713559748, "selected_pairs": 26484.2, "step": 16140, "student_distance_mean": 1252.0640380859375, "teacher_distance_mean": 0.859623384475708, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.0026702994713559748, "weighted_relation_loss": 0.0026702994713559748 }, { "action_query_batch_std": 21.722622108459472, "action_query_norm": 932.8647521972656, "action_relation_loss": 0.0026239703875035048, "auxiliary_loss_weight": 1.0, "epoch": 15.10757717492984, "flow_matching_loss": 0.02792726755142212, "grad_norm": 0.09604702889919281, "invalid_tail_samples": 24.9, "learning_rate": 4.7801594084106763e-05, "loss": 0.0306, "positive_teacher_pairs": 26597.9, "relation_loss": 0.0026239703875035048, "selected_pairs": 26597.9, "step": 16150, "student_distance_mean": 1243.7213745117188, "teacher_distance_mean": 0.8540557265281677, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0026239703875035048, "weighted_relation_loss": 0.0026239703875035048 }, { "action_query_batch_std": 21.99790554046631, "action_query_norm": 942.1970947265625, "action_relation_loss": 0.0026154644321650265, "auxiliary_loss_weight": 1.0, "epoch": 15.116931711880262, "flow_matching_loss": 0.02656132485717535, "grad_norm": 0.09871307015419006, "invalid_tail_samples": 22.3, "learning_rate": 4.774653307074775e-05, "loss": 0.0292, "positive_teacher_pairs": 27200.5, "relation_loss": 0.0026154644321650265, "selected_pairs": 27200.5, "step": 16160, "student_distance_mean": 1259.41728515625, "teacher_distance_mean": 0.8685772001743317, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0026154644321650265, "weighted_relation_loss": 0.0026154644321650265 }, { "action_query_batch_std": 21.965167999267578, "action_query_norm": 944.0626586914062, "action_relation_loss": 0.0025978611782193186, "auxiliary_loss_weight": 1.0, "epoch": 15.126286248830683, "flow_matching_loss": 0.025475498661398886, "grad_norm": 0.10037827491760254, "invalid_tail_samples": 24.9, "learning_rate": 4.769147479556355e-05, "loss": 0.0281, "positive_teacher_pairs": 26597.5, "relation_loss": 0.0025978611782193186, "selected_pairs": 26597.5, "step": 16170, "student_distance_mean": 1259.762646484375, "teacher_distance_mean": 0.8617823421955109, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0025978611782193186, "weighted_relation_loss": 0.0025978611782193186 }, { "action_query_batch_std": 21.528256988525392, "action_query_norm": 925.5286376953125, "action_relation_loss": 0.0027977599762380122, "auxiliary_loss_weight": 1.0, "epoch": 15.135640785781105, "flow_matching_loss": 0.02737938202917576, "grad_norm": 0.122737817466259, "invalid_tail_samples": 24.8, "learning_rate": 4.763641932545515e-05, "loss": 0.0302, "positive_teacher_pairs": 26625.3, "relation_loss": 0.0027977599762380122, "selected_pairs": 26625.3, "step": 16180, "student_distance_mean": 1232.4595947265625, "teacher_distance_mean": 0.8498121321201324, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0027977599762380122, "weighted_relation_loss": 0.0027977599762380122 }, { "action_query_batch_std": 21.649168395996092, "action_query_norm": 928.0140319824219, "action_relation_loss": 0.0025336591759696605, "auxiliary_loss_weight": 1.0, "epoch": 15.144995322731525, "flow_matching_loss": 0.026963295601308345, "grad_norm": 0.10931814461946487, "invalid_tail_samples": 24.5, "learning_rate": 4.758136672732013e-05, "loss": 0.0295, "positive_teacher_pairs": 26684.1, "relation_loss": 0.0025336591759696605, "selected_pairs": 26684.1, "step": 16190, "student_distance_mean": 1238.6879760742188, "teacher_distance_mean": 0.858208155632019, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0025336591759696605, "weighted_relation_loss": 0.0025336591759696605 }, { "action_query_batch_std": 21.561619567871094, "action_query_norm": 925.2513916015625, "action_relation_loss": 0.0025763955432921647, "auxiliary_loss_weight": 1.0, "epoch": 15.154349859681945, "flow_matching_loss": 0.026136034913361073, "grad_norm": 0.11781924962997437, "invalid_tail_samples": 25.8, "learning_rate": 4.752631706805261e-05, "loss": 0.0287, "positive_teacher_pairs": 26397.4, "relation_loss": 0.0025763955432921647, "selected_pairs": 26397.4, "step": 16200, "student_distance_mean": 1235.9676391601563, "teacher_distance_mean": 0.8498863101005554, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.0025763955432921647, "weighted_relation_loss": 0.0025763955432921647 }, { "action_query_batch_std": 21.912284088134765, "action_query_norm": 938.6829162597656, "action_relation_loss": 0.0026616316055878995, "auxiliary_loss_weight": 1.0, "epoch": 15.163704396632367, "flow_matching_loss": 0.026973696425557137, "grad_norm": 0.11979392170906067, "invalid_tail_samples": 23.9, "learning_rate": 4.7471270414543114e-05, "loss": 0.0296, "positive_teacher_pairs": 26830.7, "relation_loss": 0.0026616316055878995, "selected_pairs": 26830.7, "step": 16210, "student_distance_mean": 1253.2544067382812, "teacher_distance_mean": 0.864267772436142, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0026616316055878995, "weighted_relation_loss": 0.0026616316055878995 }, { "action_query_batch_std": 21.727012062072752, "action_query_norm": 934.558984375, "action_relation_loss": 0.0025896393693983556, "auxiliary_loss_weight": 1.0, "epoch": 15.173058933582787, "flow_matching_loss": 0.027235766872763634, "grad_norm": 0.11687123030424118, "invalid_tail_samples": 24.0, "learning_rate": 4.741622683367849e-05, "loss": 0.0298, "positive_teacher_pairs": 26804.1, "relation_loss": 0.0025896393693983556, "selected_pairs": 26804.1, "step": 16220, "student_distance_mean": 1246.5683837890624, "teacher_distance_mean": 0.8597762525081635, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0025896393693983556, "weighted_relation_loss": 0.0025896393693983556 }, { "action_query_batch_std": 21.536010932922363, "action_query_norm": 927.0930847167969, "action_relation_loss": 0.0027037547435611485, "auxiliary_loss_weight": 1.0, "epoch": 15.18241347053321, "flow_matching_loss": 0.02810595780611038, "grad_norm": 0.09719140082597733, "invalid_tail_samples": 25.4, "learning_rate": 4.736118639234191e-05, "loss": 0.0308, "positive_teacher_pairs": 26479.2, "relation_loss": 0.0027037547435611485, "selected_pairs": 26479.2, "step": 16230, "student_distance_mean": 1235.7525390625, "teacher_distance_mean": 0.8542441725730896, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.0027037547435611485, "weighted_relation_loss": 0.0027037547435611485 }, { "action_query_batch_std": 21.547694396972656, "action_query_norm": 924.6114135742188, "action_relation_loss": 0.0027555597480386496, "auxiliary_loss_weight": 1.0, "epoch": 15.19176800748363, "flow_matching_loss": 0.02329918909817934, "grad_norm": 0.10864844173192978, "invalid_tail_samples": 24.6, "learning_rate": 4.730614915741267e-05, "loss": 0.0261, "positive_teacher_pairs": 26667.5, "relation_loss": 0.0027555597480386496, "selected_pairs": 26667.5, "step": 16240, "student_distance_mean": 1232.63974609375, "teacher_distance_mean": 0.8489972174167633, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0027555597480386496, "weighted_relation_loss": 0.0027555597480386496 }, { "action_query_batch_std": 21.560448265075685, "action_query_norm": 928.3012084960938, "action_relation_loss": 0.0027082805754616857, "auxiliary_loss_weight": 1.0, "epoch": 15.20112254443405, "flow_matching_loss": 0.025814889557659627, "grad_norm": 0.09065835177898407, "invalid_tail_samples": 23.0, "learning_rate": 4.7251115195766234e-05, "loss": 0.0285, "positive_teacher_pairs": 27042.2, "relation_loss": 0.0027082805754616857, "selected_pairs": 27042.2, "step": 16250, "student_distance_mean": 1235.0220092773438, "teacher_distance_mean": 0.8442302048206329, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0027082805754616857, "weighted_relation_loss": 0.0027082805754616857 }, { "action_query_batch_std": 21.985151481628417, "action_query_norm": 940.746142578125, "action_relation_loss": 0.0025759526295587422, "auxiliary_loss_weight": 1.0, "epoch": 15.210477081384472, "flow_matching_loss": 0.026101153530180454, "grad_norm": 0.0931534394621849, "invalid_tail_samples": 24.9, "learning_rate": 4.719608457427404e-05, "loss": 0.0287, "positive_teacher_pairs": 26597.8, "relation_loss": 0.0025759526295587422, "selected_pairs": 26597.8, "step": 16260, "student_distance_mean": 1257.6457397460938, "teacher_distance_mean": 0.8598739504814148, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0025759526295587422, "weighted_relation_loss": 0.0025759526295587422 }, { "action_query_batch_std": 21.729680442810057, "action_query_norm": 932.4982177734375, "action_relation_loss": 0.0026683860924094915, "auxiliary_loss_weight": 1.0, "epoch": 15.219831618334892, "flow_matching_loss": 0.02747780866920948, "grad_norm": 0.0862787589430809, "invalid_tail_samples": 25.4, "learning_rate": 4.714105735980347e-05, "loss": 0.0301, "positive_teacher_pairs": 26482.7, "relation_loss": 0.0026683860924094915, "selected_pairs": 26482.7, "step": 16270, "student_distance_mean": 1240.6792602539062, "teacher_distance_mean": 0.8472562611103058, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.0026683860924094915, "weighted_relation_loss": 0.0026683860924094915 }, { "action_query_batch_std": 21.793698501586913, "action_query_norm": 934.7573547363281, "action_relation_loss": 0.0025937204016372563, "auxiliary_loss_weight": 1.0, "epoch": 15.229186155285314, "flow_matching_loss": 0.025315620750188828, "grad_norm": 0.1260729432106018, "invalid_tail_samples": 25.8, "learning_rate": 4.70860336192178e-05, "loss": 0.0279, "positive_teacher_pairs": 26388.8, "relation_loss": 0.0025937204016372563, "selected_pairs": 26388.8, "step": 16280, "student_distance_mean": 1240.6301391601562, "teacher_distance_mean": 0.8471508502960206, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.0025937204016372563, "weighted_relation_loss": 0.0025937204016372563 }, { "action_query_batch_std": 21.866431427001952, "action_query_norm": 939.3625732421875, "action_relation_loss": 0.0025667039677500724, "auxiliary_loss_weight": 1.0, "epoch": 15.238540692235734, "flow_matching_loss": 0.024633137881755827, "grad_norm": 0.10779595375061035, "invalid_tail_samples": 23.6, "learning_rate": 4.7031013419376034e-05, "loss": 0.0272, "positive_teacher_pairs": 26894.5, "relation_loss": 0.0025667039677500724, "selected_pairs": 26894.5, "step": 16290, "student_distance_mean": 1248.2310302734375, "teacher_distance_mean": 0.8512989640235901, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0025667039677500724, "weighted_relation_loss": 0.0025667039677500724 }, { "action_query_batch_std": 21.81726837158203, "action_query_norm": 937.8794128417969, "action_relation_loss": 0.0026075609726831316, "auxiliary_loss_weight": 1.0, "epoch": 15.247895229186156, "flow_matching_loss": 0.024547718092799188, "grad_norm": 0.1050351932644844, "invalid_tail_samples": 22.9, "learning_rate": 4.6975996827132926e-05, "loss": 0.0272, "positive_teacher_pairs": 27060.2, "relation_loss": 0.0026075609726831316, "selected_pairs": 27060.2, "step": 16300, "student_distance_mean": 1252.7104858398438, "teacher_distance_mean": 0.8603724837303162, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0026075609726831316, "weighted_relation_loss": 0.0026075609726831316 }, { "action_query_batch_std": 21.503298568725587, "action_query_norm": 928.1763122558593, "action_relation_loss": 0.002613075962290168, "auxiliary_loss_weight": 1.0, "epoch": 15.257249766136576, "flow_matching_loss": 0.02633080929517746, "grad_norm": 0.09847201406955719, "invalid_tail_samples": 24.2, "learning_rate": 4.692098390933883e-05, "loss": 0.0289, "positive_teacher_pairs": 26761.0, "relation_loss": 0.002613075962290168, "selected_pairs": 26761.0, "step": 16310, "student_distance_mean": 1235.8374755859375, "teacher_distance_mean": 0.8520193517208099, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.002613075962290168, "weighted_relation_loss": 0.002613075962290168 }, { "action_query_batch_std": 21.49963836669922, "action_query_norm": 923.9435668945313, "action_relation_loss": 0.002733925450593233, "auxiliary_loss_weight": 1.0, "epoch": 15.266604303086996, "flow_matching_loss": 0.028346950933337212, "grad_norm": 0.09464450180530548, "invalid_tail_samples": 22.3, "learning_rate": 4.6865974732839615e-05, "loss": 0.0311, "positive_teacher_pairs": 27195.6, "relation_loss": 0.002733925450593233, "selected_pairs": 27195.6, "step": 16320, "student_distance_mean": 1234.321240234375, "teacher_distance_mean": 0.8532697856426239, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.002733925450593233, "weighted_relation_loss": 0.002733925450593233 }, { "action_query_batch_std": 21.526290130615234, "action_query_norm": 925.6665466308593, "action_relation_loss": 0.002664920291863382, "auxiliary_loss_weight": 1.0, "epoch": 15.275958840037418, "flow_matching_loss": 0.02874467074871063, "grad_norm": 0.11394532769918442, "invalid_tail_samples": 25.8, "learning_rate": 4.6810969364476615e-05, "loss": 0.0314, "positive_teacher_pairs": 26384.0, "relation_loss": 0.002664920291863382, "selected_pairs": 26384.0, "step": 16330, "student_distance_mean": 1237.5108520507813, "teacher_distance_mean": 0.854115092754364, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.002664920291863382, "weighted_relation_loss": 0.002664920291863382 }, { "action_query_batch_std": 21.745487022399903, "action_query_norm": 934.509033203125, "action_relation_loss": 0.002681471477262676, "auxiliary_loss_weight": 1.0, "epoch": 15.285313376987839, "flow_matching_loss": 0.02792852185666561, "grad_norm": 0.08930335193872452, "invalid_tail_samples": 21.2, "learning_rate": 4.675596787108653e-05, "loss": 0.0306, "positive_teacher_pairs": 27460.7, "relation_loss": 0.002681471477262676, "selected_pairs": 27460.7, "step": 16340, "student_distance_mean": 1247.4005249023437, "teacher_distance_mean": 0.8581232786178589, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.002681471477262676, "weighted_relation_loss": 0.002681471477262676 }, { "action_query_batch_std": 21.510492897033693, "action_query_norm": 923.9351806640625, "action_relation_loss": 0.002706332365050912, "auxiliary_loss_weight": 1.0, "epoch": 15.29466791393826, "flow_matching_loss": 0.02684741225093603, "grad_norm": 0.10541092604398727, "invalid_tail_samples": 21.7, "learning_rate": 4.670097031950139e-05, "loss": 0.0296, "positive_teacher_pairs": 27337.5, "relation_loss": 0.002706332365050912, "selected_pairs": 27337.5, "step": 16350, "student_distance_mean": 1230.025634765625, "teacher_distance_mean": 0.8452439427375793, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.002706332365050912, "weighted_relation_loss": 0.002706332365050912 }, { "action_query_batch_std": 21.696357917785644, "action_query_norm": 934.122412109375, "action_relation_loss": 0.002620282140560448, "auxiliary_loss_weight": 1.0, "epoch": 15.30402245088868, "flow_matching_loss": 0.026314119063317775, "grad_norm": 0.10986039787530899, "invalid_tail_samples": 20.7, "learning_rate": 4.664597677654838e-05, "loss": 0.0289, "positive_teacher_pairs": 27567.8, "relation_loss": 0.002620282140560448, "selected_pairs": 27567.8, "step": 16360, "student_distance_mean": 1245.281201171875, "teacher_distance_mean": 0.8608154714107513, "valid_action_samples": 235.3, "weighted_auxiliary_loss": 0.002620282140560448, "weighted_relation_loss": 0.002620282140560448 }, { "action_query_batch_std": 21.685027503967284, "action_query_norm": 929.998681640625, "action_relation_loss": 0.0027457409305498004, "auxiliary_loss_weight": 1.0, "epoch": 15.313376987839103, "flow_matching_loss": 0.029139906354248523, "grad_norm": 0.10728012025356293, "invalid_tail_samples": 20.6, "learning_rate": 4.659098730904986e-05, "loss": 0.0319, "positive_teacher_pairs": 27596.4, "relation_loss": 0.0027457409305498004, "selected_pairs": 27596.4, "step": 16370, "student_distance_mean": 1243.414892578125, "teacher_distance_mean": 0.8576019644737244, "valid_action_samples": 235.4, "weighted_auxiliary_loss": 0.0027457409305498004, "weighted_relation_loss": 0.0027457409305498004 }, { "action_query_batch_std": 21.85743999481201, "action_query_norm": 938.1434936523438, "action_relation_loss": 0.0027339410968124866, "auxiliary_loss_weight": 1.0, "epoch": 15.322731524789523, "flow_matching_loss": 0.027189492247998714, "grad_norm": 0.12473389506340027, "invalid_tail_samples": 25.0, "learning_rate": 4.6536001983823204e-05, "loss": 0.0299, "positive_teacher_pairs": 26575.6, "relation_loss": 0.0027339410968124866, "selected_pairs": 26575.6, "step": 16380, "student_distance_mean": 1255.307373046875, "teacher_distance_mean": 0.8600112438201905, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0027339410968124866, "weighted_relation_loss": 0.0027339410968124866 }, { "action_query_batch_std": 21.741002464294432, "action_query_norm": 931.7669067382812, "action_relation_loss": 0.0026453729486092927, "auxiliary_loss_weight": 1.0, "epoch": 15.332086061739943, "flow_matching_loss": 0.024884345196187495, "grad_norm": 0.1073332354426384, "invalid_tail_samples": 24.0, "learning_rate": 4.648102086768078e-05, "loss": 0.0275, "positive_teacher_pairs": 26801.4, "relation_loss": 0.0026453729486092927, "selected_pairs": 26801.4, "step": 16390, "student_distance_mean": 1247.1964965820312, "teacher_distance_mean": 0.8568323016166687, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0026453729486092927, "weighted_relation_loss": 0.0026453729486092927 }, { "action_query_batch_std": 21.90314292907715, "action_query_norm": 936.6406188964844, "action_relation_loss": 0.002639118838123977, "auxiliary_loss_weight": 1.0, "epoch": 15.341440598690365, "flow_matching_loss": 0.025811251439154147, "grad_norm": 0.10402783006429672, "invalid_tail_samples": 23.3, "learning_rate": 4.6426044027429786e-05, "loss": 0.0285, "positive_teacher_pairs": 26965.0, "relation_loss": 0.002639118838123977, "selected_pairs": 26965.0, "step": 16400, "student_distance_mean": 1252.1728515625, "teacher_distance_mean": 0.8625072956085205, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.002639118838123977, "weighted_relation_loss": 0.002639118838123977 }, { "action_query_batch_std": 21.539464950561523, "action_query_norm": 923.2509155273438, "action_relation_loss": 0.0027556943241506815, "auxiliary_loss_weight": 1.0, "epoch": 15.350795135640785, "flow_matching_loss": 0.025811915285885334, "grad_norm": 0.11196853965520859, "invalid_tail_samples": 27.0, "learning_rate": 4.637107152987234e-05, "loss": 0.0286, "positive_teacher_pairs": 26121.3, "relation_loss": 0.0027556943241506815, "selected_pairs": 26121.3, "step": 16410, "student_distance_mean": 1241.3590942382812, "teacher_distance_mean": 0.8581142663955689, "valid_action_samples": 229.0, "weighted_auxiliary_loss": 0.0027556943241506815, "weighted_relation_loss": 0.0027556943241506815 }, { "action_query_batch_std": 21.272315216064452, "action_query_norm": 918.3548889160156, "action_relation_loss": 0.0027616543928161265, "auxiliary_loss_weight": 1.0, "epoch": 15.360149672591207, "flow_matching_loss": 0.027842355892062187, "grad_norm": 0.11517369747161865, "invalid_tail_samples": 21.0, "learning_rate": 4.631610344180515e-05, "loss": 0.0306, "positive_teacher_pairs": 27503.0, "relation_loss": 0.0027616543928161265, "selected_pairs": 27503.0, "step": 16420, "student_distance_mean": 1222.3753540039063, "teacher_distance_mean": 0.8370947718620301, "valid_action_samples": 235.0, "weighted_auxiliary_loss": 0.0027616543928161265, "weighted_relation_loss": 0.0027616543928161265 }, { "action_query_batch_std": 21.611105918884277, "action_query_norm": 927.9083190917969, "action_relation_loss": 0.0025847816839814188, "auxiliary_loss_weight": 1.0, "epoch": 15.369504209541628, "flow_matching_loss": 0.025372652523219585, "grad_norm": 0.09055789560079575, "invalid_tail_samples": 23.9, "learning_rate": 4.626113983001965e-05, "loss": 0.028, "positive_teacher_pairs": 26832.9, "relation_loss": 0.0025847816839814188, "selected_pairs": 26832.9, "step": 16430, "student_distance_mean": 1240.8828247070312, "teacher_distance_mean": 0.8534272134304046, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0025847816839814188, "weighted_relation_loss": 0.0025847816839814188 }, { "action_query_batch_std": 21.549332046508788, "action_query_norm": 922.2592834472656, "action_relation_loss": 0.0025850457372143865, "auxiliary_loss_weight": 1.0, "epoch": 15.378858746492048, "flow_matching_loss": 0.02662841249257326, "grad_norm": 0.12384319305419922, "invalid_tail_samples": 23.2, "learning_rate": 4.620618076130182e-05, "loss": 0.0292, "positive_teacher_pairs": 26994.1, "relation_loss": 0.0025850457372143865, "selected_pairs": 26994.1, "step": 16440, "student_distance_mean": 1235.7725952148437, "teacher_distance_mean": 0.8538198649883271, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0025850457372143865, "weighted_relation_loss": 0.0025850457372143865 }, { "action_query_batch_std": 21.74752025604248, "action_query_norm": 931.4421691894531, "action_relation_loss": 0.0026449103141203524, "auxiliary_loss_weight": 1.0, "epoch": 15.38821328344247, "flow_matching_loss": 0.02713516466319561, "grad_norm": 0.0880284309387207, "invalid_tail_samples": 24.8, "learning_rate": 4.6151226302432074e-05, "loss": 0.0298, "positive_teacher_pairs": 26627.0, "relation_loss": 0.0026449103141203524, "selected_pairs": 26627.0, "step": 16450, "student_distance_mean": 1241.8776611328126, "teacher_distance_mean": 0.8544259488582611, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0026449103141203524, "weighted_relation_loss": 0.0026449103141203524 }, { "action_query_batch_std": 22.134097480773924, "action_query_norm": 945.3925720214844, "action_relation_loss": 0.00260642827488482, "auxiliary_loss_weight": 1.0, "epoch": 15.39756782039289, "flow_matching_loss": 0.028056019358336924, "grad_norm": 0.08880104124546051, "invalid_tail_samples": 24.2, "learning_rate": 4.6096276520185304e-05, "loss": 0.0307, "positive_teacher_pairs": 26763.7, "relation_loss": 0.00260642827488482, "selected_pairs": 26763.7, "step": 16460, "student_distance_mean": 1263.730810546875, "teacher_distance_mean": 0.8701772570610047, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.00260642827488482, "weighted_relation_loss": 0.00260642827488482 }, { "action_query_batch_std": 21.32450065612793, "action_query_norm": 919.5616394042969, "action_relation_loss": 0.0027172765228897335, "auxiliary_loss_weight": 1.0, "epoch": 15.406922357343312, "flow_matching_loss": 0.02642226908355951, "grad_norm": 0.09379944950342178, "invalid_tail_samples": 20.7, "learning_rate": 4.604133148133066e-05, "loss": 0.0291, "positive_teacher_pairs": 27572.1, "relation_loss": 0.0027172765228897335, "selected_pairs": 27572.1, "step": 16470, "student_distance_mean": 1221.2809692382812, "teacher_distance_mean": 0.8460890829563141, "valid_action_samples": 235.3, "weighted_auxiliary_loss": 0.0027172765228897335, "weighted_relation_loss": 0.0027172765228897335 }, { "action_query_batch_std": 21.741726684570313, "action_query_norm": 931.6597900390625, "action_relation_loss": 0.002611031848937273, "auxiliary_loss_weight": 1.0, "epoch": 15.416276894293732, "flow_matching_loss": 0.02562277764081955, "grad_norm": 0.11636849492788315, "invalid_tail_samples": 25.2, "learning_rate": 4.598639125263155e-05, "loss": 0.0282, "positive_teacher_pairs": 26531.1, "relation_loss": 0.002611031848937273, "selected_pairs": 26531.1, "step": 16480, "student_distance_mean": 1252.0291015625, "teacher_distance_mean": 0.862420243024826, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.002611031848937273, "weighted_relation_loss": 0.002611031848937273 }, { "action_query_batch_std": 21.465952491760255, "action_query_norm": 923.0034606933593, "action_relation_loss": 0.0027143099810928105, "auxiliary_loss_weight": 1.0, "epoch": 15.425631431244154, "flow_matching_loss": 0.027398231998085977, "grad_norm": 0.11081322282552719, "invalid_tail_samples": 23.4, "learning_rate": 4.593145590084553e-05, "loss": 0.0301, "positive_teacher_pairs": 26943.6, "relation_loss": 0.0027143099810928105, "selected_pairs": 26943.6, "step": 16490, "student_distance_mean": 1233.7223388671875, "teacher_distance_mean": 0.8492116451263427, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0027143099810928105, "weighted_relation_loss": 0.0027143099810928105 }, { "action_query_batch_std": 21.64957904815674, "action_query_norm": 927.6073059082031, "action_relation_loss": 0.00262032353784889, "auxiliary_loss_weight": 1.0, "epoch": 15.434985968194574, "flow_matching_loss": 0.02538294270634651, "grad_norm": 0.11566593497991562, "invalid_tail_samples": 23.2, "learning_rate": 4.58765254927242e-05, "loss": 0.028, "positive_teacher_pairs": 26988.8, "relation_loss": 0.00262032353784889, "selected_pairs": 26988.8, "step": 16500, "student_distance_mean": 1238.9680786132812, "teacher_distance_mean": 0.8539893984794616, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.00262032353784889, "weighted_relation_loss": 0.00262032353784889 }, { "action_query_batch_std": 21.442432403564453, "action_query_norm": 920.7959350585937, "action_relation_loss": 0.0025540539529174565, "auxiliary_loss_weight": 1.0, "epoch": 15.444340505144995, "flow_matching_loss": 0.026240538246929644, "grad_norm": 0.09603170305490494, "invalid_tail_samples": 25.2, "learning_rate": 4.582160009501323e-05, "loss": 0.0288, "positive_teacher_pairs": 26527.6, "relation_loss": 0.0025540539529174565, "selected_pairs": 26527.6, "step": 16510, "student_distance_mean": 1233.600341796875, "teacher_distance_mean": 0.8533028602600098, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0025540539529174565, "weighted_relation_loss": 0.0025540539529174565 }, { "action_query_batch_std": 21.533024024963378, "action_query_norm": 922.3659545898438, "action_relation_loss": 0.0026445439783856274, "auxiliary_loss_weight": 1.0, "epoch": 15.453695042095417, "flow_matching_loss": 0.026027768291532992, "grad_norm": 0.1352209448814392, "invalid_tail_samples": 21.3, "learning_rate": 4.5766679774452143e-05, "loss": 0.0287, "positive_teacher_pairs": 27430.7, "relation_loss": 0.0026445439783856274, "selected_pairs": 27430.7, "step": 16520, "student_distance_mean": 1230.7426635742188, "teacher_distance_mean": 0.850846266746521, "valid_action_samples": 234.7, "weighted_auxiliary_loss": 0.0026445439783856274, "weighted_relation_loss": 0.0026445439783856274 }, { "action_query_batch_std": 21.818088912963866, "action_query_norm": 930.1510192871094, "action_relation_loss": 0.0026798516511917113, "auxiliary_loss_weight": 1.0, "epoch": 15.463049579045837, "flow_matching_loss": 0.026576445810496806, "grad_norm": 0.11999140679836273, "invalid_tail_samples": 26.5, "learning_rate": 4.571176459777431e-05, "loss": 0.0293, "positive_teacher_pairs": 26241.3, "relation_loss": 0.0026798516511917113, "selected_pairs": 26241.3, "step": 16530, "student_distance_mean": 1252.8360473632813, "teacher_distance_mean": 0.8592863261699677, "valid_action_samples": 229.5, "weighted_auxiliary_loss": 0.0026798516511917113, "weighted_relation_loss": 0.0026798516511917113 }, { "action_query_batch_std": 21.779444694519043, "action_query_norm": 934.1583557128906, "action_relation_loss": 0.002718062954954803, "auxiliary_loss_weight": 1.0, "epoch": 15.472404115996259, "flow_matching_loss": 0.025482802465558053, "grad_norm": 0.1233508512377739, "invalid_tail_samples": 23.3, "learning_rate": 4.5656854631706846e-05, "loss": 0.0282, "positive_teacher_pairs": 26967.1, "relation_loss": 0.002718062954954803, "selected_pairs": 26967.1, "step": 16540, "student_distance_mean": 1245.535595703125, "teacher_distance_mean": 0.8488621294498444, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.002718062954954803, "weighted_relation_loss": 0.002718062954954803 }, { "action_query_batch_std": 21.602418899536133, "action_query_norm": 928.9734375, "action_relation_loss": 0.0027416854863986373, "auxiliary_loss_weight": 1.0, "epoch": 15.481758652946679, "flow_matching_loss": 0.026755060628056528, "grad_norm": 0.10964993387460709, "invalid_tail_samples": 21.6, "learning_rate": 4.560194994297054e-05, "loss": 0.0295, "positive_teacher_pairs": 27369.5, "relation_loss": 0.0027416854863986373, "selected_pairs": 27369.5, "step": 16550, "student_distance_mean": 1234.9378051757812, "teacher_distance_mean": 0.8483339965343475, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.0027416854863986373, "weighted_relation_loss": 0.0027416854863986373 }, { "action_query_batch_std": 21.891378974914552, "action_query_norm": 938.8570922851562, "action_relation_loss": 0.002617017924785614, "auxiliary_loss_weight": 1.0, "epoch": 15.4911131898971, "flow_matching_loss": 0.024201536551117897, "grad_norm": 0.08932829648256302, "invalid_tail_samples": 25.5, "learning_rate": 4.554705059827974e-05, "loss": 0.0268, "positive_teacher_pairs": 26457.3, "relation_loss": 0.002617017924785614, "selected_pairs": 26457.3, "step": 16560, "student_distance_mean": 1258.69169921875, "teacher_distance_mean": 0.8604857444763183, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.002617017924785614, "weighted_relation_loss": 0.002617017924785614 }, { "action_query_batch_std": 21.51970863342285, "action_query_norm": 923.976904296875, "action_relation_loss": 0.002682179864495993, "auxiliary_loss_weight": 1.0, "epoch": 15.500467726847521, "flow_matching_loss": 0.025977710634469985, "grad_norm": 0.11258681863546371, "invalid_tail_samples": 23.9, "learning_rate": 4.5492156664342365e-05, "loss": 0.0287, "positive_teacher_pairs": 26831.7, "relation_loss": 0.002682179864495993, "selected_pairs": 26831.7, "step": 16570, "student_distance_mean": 1234.2943481445313, "teacher_distance_mean": 0.844078540802002, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.002682179864495993, "weighted_relation_loss": 0.002682179864495993 }, { "action_query_batch_std": 21.48032627105713, "action_query_norm": 919.3764221191407, "action_relation_loss": 0.0026812596712261438, "auxiliary_loss_weight": 1.0, "epoch": 15.509822263797941, "flow_matching_loss": 0.026992517337203027, "grad_norm": 0.09690718352794647, "invalid_tail_samples": 25.0, "learning_rate": 4.5437268207859695e-05, "loss": 0.0297, "positive_teacher_pairs": 26573.1, "relation_loss": 0.0026812596712261438, "selected_pairs": 26573.1, "step": 16580, "student_distance_mean": 1232.0296630859375, "teacher_distance_mean": 0.8512981414794922, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0026812596712261438, "weighted_relation_loss": 0.0026812596712261438 }, { "action_query_batch_std": 21.603949546813965, "action_query_norm": 923.6817749023437, "action_relation_loss": 0.0026368099730461835, "auxiliary_loss_weight": 1.0, "epoch": 15.519176800748363, "flow_matching_loss": 0.026010257937014104, "grad_norm": 0.1005081981420517, "invalid_tail_samples": 22.0, "learning_rate": 4.538238529552641e-05, "loss": 0.0286, "positive_teacher_pairs": 27269.3, "relation_loss": 0.0026368099730461835, "selected_pairs": 27269.3, "step": 16590, "student_distance_mean": 1233.9508544921875, "teacher_distance_mean": 0.8515370070934296, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.0026368099730461835, "weighted_relation_loss": 0.0026368099730461835 }, { "action_query_batch_std": 21.797780799865723, "action_query_norm": 930.8546142578125, "action_relation_loss": 0.002664329786784947, "auxiliary_loss_weight": 1.0, "epoch": 15.528531337698784, "flow_matching_loss": 0.025995788536965846, "grad_norm": 0.08849512785673141, "invalid_tail_samples": 23.1, "learning_rate": 4.5327507994030394e-05, "loss": 0.0287, "positive_teacher_pairs": 27010.5, "relation_loss": 0.002664329786784947, "selected_pairs": 27010.5, "step": 16600, "student_distance_mean": 1245.3416259765625, "teacher_distance_mean": 0.8563944280147553, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.002664329786784947, "weighted_relation_loss": 0.002664329786784947 }, { "action_query_batch_std": 22.078755569458007, "action_query_norm": 942.2496215820313, "action_relation_loss": 0.0026292602298781274, "auxiliary_loss_weight": 1.0, "epoch": 15.537885874649206, "flow_matching_loss": 0.025115161202847958, "grad_norm": 0.10906285792589188, "invalid_tail_samples": 24.0, "learning_rate": 4.527263637005273e-05, "loss": 0.0277, "positive_teacher_pairs": 26805.8, "relation_loss": 0.0026292602298781274, "selected_pairs": 26805.8, "step": 16610, "student_distance_mean": 1265.3264404296874, "teacher_distance_mean": 0.8672613322734832, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0026292602298781274, "weighted_relation_loss": 0.0026292602298781274 }, { "action_query_batch_std": 21.732130813598634, "action_query_norm": 931.8432006835938, "action_relation_loss": 0.0026451791869476437, "auxiliary_loss_weight": 1.0, "epoch": 15.547240411599626, "flow_matching_loss": 0.025440490432083608, "grad_norm": 0.10455196350812912, "invalid_tail_samples": 24.4, "learning_rate": 4.521777049026766e-05, "loss": 0.0281, "positive_teacher_pairs": 26711.9, "relation_loss": 0.0026451791869476437, "selected_pairs": 26711.9, "step": 16620, "student_distance_mean": 1248.4969848632813, "teacher_distance_mean": 0.8539333522319794, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0026451791869476437, "weighted_relation_loss": 0.0026451791869476437 }, { "action_query_batch_std": 21.77892646789551, "action_query_norm": 932.1449584960938, "action_relation_loss": 0.0026093215448781846, "auxiliary_loss_weight": 1.0, "epoch": 15.556594948550046, "flow_matching_loss": 0.024394426308572293, "grad_norm": 0.09581545740365982, "invalid_tail_samples": 27.3, "learning_rate": 4.5162910421342386e-05, "loss": 0.027, "positive_teacher_pairs": 26051.0, "relation_loss": 0.0026093215448781846, "selected_pairs": 26051.0, "step": 16630, "student_distance_mean": 1250.1587524414062, "teacher_distance_mean": 0.8558913171291351, "valid_action_samples": 228.7, "weighted_auxiliary_loss": 0.0026093215448781846, "weighted_relation_loss": 0.0026093215448781846 }, { "action_query_batch_std": 21.913758277893066, "action_query_norm": 935.1060852050781, "action_relation_loss": 0.0026640537194907664, "auxiliary_loss_weight": 1.0, "epoch": 15.565949485500468, "flow_matching_loss": 0.025334802642464637, "grad_norm": 0.16153714060783386, "invalid_tail_samples": 23.4, "learning_rate": 4.510805622993706e-05, "loss": 0.028, "positive_teacher_pairs": 26943.8, "relation_loss": 0.0026640537194907664, "selected_pairs": 26943.8, "step": 16640, "student_distance_mean": 1254.9220092773437, "teacher_distance_mean": 0.8603367328643798, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0026640537194907664, "weighted_relation_loss": 0.0026640537194907664 }, { "action_query_batch_std": 21.60436420440674, "action_query_norm": 927.5661499023438, "action_relation_loss": 0.0024799985811114313, "auxiliary_loss_weight": 1.0, "epoch": 15.575304022450888, "flow_matching_loss": 0.027431299164891242, "grad_norm": 0.10258298367261887, "invalid_tail_samples": 25.9, "learning_rate": 4.505320798270467e-05, "loss": 0.0299, "positive_teacher_pairs": 26361.5, "relation_loss": 0.0024799985811114313, "selected_pairs": 26361.5, "step": 16650, "student_distance_mean": 1245.6125122070312, "teacher_distance_mean": 0.8583408415317535, "valid_action_samples": 230.1, "weighted_auxiliary_loss": 0.0024799985811114313, "weighted_relation_loss": 0.0024799985811114313 }, { "action_query_batch_std": 21.862345504760743, "action_query_norm": 937.5784606933594, "action_relation_loss": 0.0024980018846690656, "auxiliary_loss_weight": 1.0, "epoch": 15.58465855940131, "flow_matching_loss": 0.024839418567717077, "grad_norm": 0.10207009315490723, "invalid_tail_samples": 22.6, "learning_rate": 4.499836574629105e-05, "loss": 0.0273, "positive_teacher_pairs": 27128.7, "relation_loss": 0.0024980018846690656, "selected_pairs": 27128.7, "step": 16660, "student_distance_mean": 1250.5768310546875, "teacher_distance_mean": 0.8554823100566864, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0024980018846690656, "weighted_relation_loss": 0.0024980018846690656 }, { "action_query_batch_std": 21.836426734924316, "action_query_norm": 938.066064453125, "action_relation_loss": 0.0025481206830590963, "auxiliary_loss_weight": 1.0, "epoch": 15.59401309635173, "flow_matching_loss": 0.02472465727478266, "grad_norm": 0.10302404314279556, "invalid_tail_samples": 22.6, "learning_rate": 4.494352958733465e-05, "loss": 0.0273, "positive_teacher_pairs": 27134.4, "relation_loss": 0.0025481206830590963, "selected_pairs": 27134.4, "step": 16670, "student_distance_mean": 1246.9991333007813, "teacher_distance_mean": 0.8543682098388672, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0025481206830590963, "weighted_relation_loss": 0.0025481206830590963 }, { "action_query_batch_std": 21.68297748565674, "action_query_norm": 927.3290466308594, "action_relation_loss": 0.0026055471040308475, "auxiliary_loss_weight": 1.0, "epoch": 15.603367633302152, "flow_matching_loss": 0.026900718361139296, "grad_norm": 0.0951547622680664, "invalid_tail_samples": 24.2, "learning_rate": 4.488869957246663e-05, "loss": 0.0295, "positive_teacher_pairs": 26765.7, "relation_loss": 0.0026055471040308475, "selected_pairs": 26765.7, "step": 16680, "student_distance_mean": 1243.5146240234376, "teacher_distance_mean": 0.856851464509964, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0026055471040308475, "weighted_relation_loss": 0.0026055471040308475 }, { "action_query_batch_std": 21.64387493133545, "action_query_norm": 928.9622192382812, "action_relation_loss": 0.002679512090981007, "auxiliary_loss_weight": 1.0, "epoch": 15.612722170252573, "flow_matching_loss": 0.024526476860046387, "grad_norm": 0.09821285307407379, "invalid_tail_samples": 27.2, "learning_rate": 4.4833875768310575e-05, "loss": 0.0272, "positive_teacher_pairs": 26068.2, "relation_loss": 0.002679512090981007, "selected_pairs": 26068.2, "step": 16690, "student_distance_mean": 1247.9303833007812, "teacher_distance_mean": 0.8568349421024323, "valid_action_samples": 228.8, "weighted_auxiliary_loss": 0.002679512090981007, "weighted_relation_loss": 0.002679512090981007 }, { "action_query_batch_std": 21.6670352935791, "action_query_norm": 930.7482299804688, "action_relation_loss": 0.002635336061939597, "auxiliary_loss_weight": 1.0, "epoch": 15.622076707202993, "flow_matching_loss": 0.026753986813127996, "grad_norm": 0.09911811351776123, "invalid_tail_samples": 23.5, "learning_rate": 4.47790582414826e-05, "loss": 0.0294, "positive_teacher_pairs": 26926.0, "relation_loss": 0.002635336061939597, "selected_pairs": 26926.0, "step": 16700, "student_distance_mean": 1246.3373657226562, "teacher_distance_mean": 0.8553817808628082, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.002635336061939597, "weighted_relation_loss": 0.002635336061939597 }, { "action_query_batch_std": 21.57974491119385, "action_query_norm": 923.8910827636719, "action_relation_loss": 0.0026047159219160674, "auxiliary_loss_weight": 1.0, "epoch": 15.631431244153415, "flow_matching_loss": 0.02665266301482916, "grad_norm": 0.11635525524616241, "invalid_tail_samples": 21.0, "learning_rate": 4.472424705859114e-05, "loss": 0.0293, "positive_teacher_pairs": 27500.1, "relation_loss": 0.0026047159219160674, "selected_pairs": 27500.1, "step": 16710, "student_distance_mean": 1233.8511474609375, "teacher_distance_mean": 0.8536655128002166, "valid_action_samples": 235.0, "weighted_auxiliary_loss": 0.0026047159219160674, "weighted_relation_loss": 0.0026047159219160674 }, { "action_query_batch_std": 21.678790473937987, "action_query_norm": 929.2163146972656, "action_relation_loss": 0.002631604578346014, "auxiliary_loss_weight": 1.0, "epoch": 15.640785781103835, "flow_matching_loss": 0.026259835995733737, "grad_norm": 0.09040676802396774, "invalid_tail_samples": 25.8, "learning_rate": 4.466944228623701e-05, "loss": 0.0289, "positive_teacher_pairs": 26386.0, "relation_loss": 0.002631604578346014, "selected_pairs": 26386.0, "step": 16720, "student_distance_mean": 1237.8984375, "teacher_distance_mean": 0.8494864344596863, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.002631604578346014, "weighted_relation_loss": 0.002631604578346014 }, { "action_query_batch_std": 21.862153244018554, "action_query_norm": 934.9780456542969, "action_relation_loss": 0.0025177533738315106, "auxiliary_loss_weight": 1.0, "epoch": 15.650140318054257, "flow_matching_loss": 0.026084304973483085, "grad_norm": 0.10557356476783752, "invalid_tail_samples": 26.2, "learning_rate": 4.461464399101312e-05, "loss": 0.0286, "positive_teacher_pairs": 26295.9, "relation_loss": 0.0025177533738315106, "selected_pairs": 26295.9, "step": 16730, "student_distance_mean": 1253.0024536132812, "teacher_distance_mean": 0.859980309009552, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.0025177533738315106, "weighted_relation_loss": 0.0025177533738315106 }, { "action_query_batch_std": 21.74228916168213, "action_query_norm": 930.6002380371094, "action_relation_loss": 0.002648126916028559, "auxiliary_loss_weight": 1.0, "epoch": 15.659494855004677, "flow_matching_loss": 0.026225146651268006, "grad_norm": 0.11142885684967041, "invalid_tail_samples": 22.2, "learning_rate": 4.45598522395046e-05, "loss": 0.0289, "positive_teacher_pairs": 27226.0, "relation_loss": 0.002648126916028559, "selected_pairs": 27226.0, "step": 16740, "student_distance_mean": 1241.5240600585937, "teacher_distance_mean": 0.8586346983909607, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.002648126916028559, "weighted_relation_loss": 0.002648126916028559 }, { "action_query_batch_std": 21.53824653625488, "action_query_norm": 921.15634765625, "action_relation_loss": 0.002551933820359409, "auxiliary_loss_weight": 1.0, "epoch": 15.668849391955098, "flow_matching_loss": 0.026558011211454867, "grad_norm": 0.10674803704023361, "invalid_tail_samples": 23.3, "learning_rate": 4.4505067098288577e-05, "loss": 0.0291, "positive_teacher_pairs": 26974.2, "relation_loss": 0.002551933820359409, "selected_pairs": 26974.2, "step": 16750, "student_distance_mean": 1234.7893798828125, "teacher_distance_mean": 0.8510184526443482, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.002551933820359409, "weighted_relation_loss": 0.002551933820359409 }, { "action_query_batch_std": 21.597773933410643, "action_query_norm": 923.067822265625, "action_relation_loss": 0.002614878094755113, "auxiliary_loss_weight": 1.0, "epoch": 15.67820392890552, "flow_matching_loss": 0.026647168770432474, "grad_norm": 0.13289745151996613, "invalid_tail_samples": 26.1, "learning_rate": 4.445028863393417e-05, "loss": 0.0293, "positive_teacher_pairs": 26320.4, "relation_loss": 0.002614878094755113, "selected_pairs": 26320.4, "step": 16760, "student_distance_mean": 1243.5817993164062, "teacher_distance_mean": 0.8577880144119263, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.002614878094755113, "weighted_relation_loss": 0.002614878094755113 }, { "action_query_batch_std": 21.658009338378907, "action_query_norm": 933.0110473632812, "action_relation_loss": 0.002693855785764754, "auxiliary_loss_weight": 1.0, "epoch": 15.68755846585594, "flow_matching_loss": 0.0250134015455842, "grad_norm": 0.1186618059873581, "invalid_tail_samples": 24.6, "learning_rate": 4.439551691300236e-05, "loss": 0.0277, "positive_teacher_pairs": 26663.1, "relation_loss": 0.002693855785764754, "selected_pairs": 26663.1, "step": 16770, "student_distance_mean": 1243.0684692382813, "teacher_distance_mean": 0.8510065138339996, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.002693855785764754, "weighted_relation_loss": 0.002693855785764754 }, { "action_query_batch_std": 21.568278121948243, "action_query_norm": 926.8448974609375, "action_relation_loss": 0.0026683256961405276, "auxiliary_loss_weight": 1.0, "epoch": 15.696913002806362, "flow_matching_loss": 0.025655256398022176, "grad_norm": 0.11100952327251434, "invalid_tail_samples": 22.2, "learning_rate": 4.434075200204599e-05, "loss": 0.0283, "positive_teacher_pairs": 27221.9, "relation_loss": 0.0026683256961405276, "selected_pairs": 27221.9, "step": 16780, "student_distance_mean": 1236.4070678710937, "teacher_distance_mean": 0.8443813323974609, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.0026683256961405276, "weighted_relation_loss": 0.0026683256961405276 }, { "action_query_batch_std": 22.130329132080078, "action_query_norm": 943.8899719238282, "action_relation_loss": 0.0024473020574077966, "auxiliary_loss_weight": 1.0, "epoch": 15.706267539756782, "flow_matching_loss": 0.025223963148891925, "grad_norm": 0.09556283056735992, "invalid_tail_samples": 23.5, "learning_rate": 4.428599396760956e-05, "loss": 0.0277, "positive_teacher_pairs": 26919.6, "relation_loss": 0.0024473020574077966, "selected_pairs": 26919.6, "step": 16790, "student_distance_mean": 1270.80419921875, "teacher_distance_mean": 0.8757468283176422, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0024473020574077966, "weighted_relation_loss": 0.0024473020574077966 }, { "action_query_batch_std": 21.856596183776855, "action_query_norm": 933.897216796875, "action_relation_loss": 0.0026735566556453706, "auxiliary_loss_weight": 1.0, "epoch": 15.715622076707202, "flow_matching_loss": 0.027029328420758246, "grad_norm": 0.11246542632579803, "invalid_tail_samples": 23.9, "learning_rate": 4.423124287622926e-05, "loss": 0.0297, "positive_teacher_pairs": 26828.6, "relation_loss": 0.0026735566556453706, "selected_pairs": 26828.6, "step": 16800, "student_distance_mean": 1245.8556884765626, "teacher_distance_mean": 0.8567637860774994, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0026735566556453706, "weighted_relation_loss": 0.0026735566556453706 }, { "action_query_batch_std": 21.944247817993165, "action_query_norm": 939.0652099609375, "action_relation_loss": 0.0026095544220879675, "auxiliary_loss_weight": 1.0, "epoch": 15.724976613657624, "flow_matching_loss": 0.02715225238353014, "grad_norm": 0.09520979225635529, "invalid_tail_samples": 22.8, "learning_rate": 4.417649879443282e-05, "loss": 0.0298, "positive_teacher_pairs": 27083.9, "relation_loss": 0.0026095544220879675, "selected_pairs": 27083.9, "step": 16810, "student_distance_mean": 1256.0044799804687, "teacher_distance_mean": 0.8592478811740876, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0026095544220879675, "weighted_relation_loss": 0.0026095544220879675 }, { "action_query_batch_std": 21.76181983947754, "action_query_norm": 931.5492614746094, "action_relation_loss": 0.0025489880237728356, "auxiliary_loss_weight": 1.0, "epoch": 15.734331150608044, "flow_matching_loss": 0.025802585668861865, "grad_norm": 0.08809363096952438, "invalid_tail_samples": 23.9, "learning_rate": 4.4121761788739444e-05, "loss": 0.0284, "positive_teacher_pairs": 26829.6, "relation_loss": 0.0025489880237728356, "selected_pairs": 26829.6, "step": 16820, "student_distance_mean": 1247.0342529296875, "teacher_distance_mean": 0.853325468301773, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0025489880237728356, "weighted_relation_loss": 0.0025489880237728356 }, { "action_query_batch_std": 21.55344581604004, "action_query_norm": 922.6961791992187, "action_relation_loss": 0.0025691949762403966, "auxiliary_loss_weight": 1.0, "epoch": 15.743685687558466, "flow_matching_loss": 0.02601212337613106, "grad_norm": 0.10694776475429535, "invalid_tail_samples": 22.1, "learning_rate": 4.4067031925659805e-05, "loss": 0.0286, "positive_teacher_pairs": 27243.5, "relation_loss": 0.0025691949762403966, "selected_pairs": 27243.5, "step": 16830, "student_distance_mean": 1233.1411865234375, "teacher_distance_mean": 0.8457901239395141, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0025691949762403966, "weighted_relation_loss": 0.0025691949762403966 }, { "action_query_batch_std": 21.786161994934083, "action_query_norm": 933.1070983886718, "action_relation_loss": 0.0027430109912529588, "auxiliary_loss_weight": 1.0, "epoch": 15.753040224508887, "flow_matching_loss": 0.024756461195647717, "grad_norm": 0.09329400956630707, "invalid_tail_samples": 21.5, "learning_rate": 4.4012309271695816e-05, "loss": 0.0275, "positive_teacher_pairs": 27393.9, "relation_loss": 0.0027430109912529588, "selected_pairs": 27393.9, "step": 16840, "student_distance_mean": 1240.9961181640624, "teacher_distance_mean": 0.8488113403320312, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.0027430109912529588, "weighted_relation_loss": 0.0027430109912529588 }, { "action_query_batch_std": 21.678980445861818, "action_query_norm": 926.9872863769531, "action_relation_loss": 0.0025910439901053904, "auxiliary_loss_weight": 1.0, "epoch": 15.762394761459309, "flow_matching_loss": 0.025808231718838216, "grad_norm": 0.09597992897033691, "invalid_tail_samples": 21.1, "learning_rate": 4.395759389334067e-05, "loss": 0.0284, "positive_teacher_pairs": 27478.0, "relation_loss": 0.0025910439901053904, "selected_pairs": 27478.0, "step": 16850, "student_distance_mean": 1243.0081298828125, "teacher_distance_mean": 0.8523328840732575, "valid_action_samples": 234.9, "weighted_auxiliary_loss": 0.0025910439901053904, "weighted_relation_loss": 0.0025910439901053904 }, { "action_query_batch_std": 22.138372039794923, "action_query_norm": 944.1759338378906, "action_relation_loss": 0.00254617661703378, "auxiliary_loss_weight": 1.0, "epoch": 15.771749298409729, "flow_matching_loss": 0.02438094951212406, "grad_norm": 0.12033289670944214, "invalid_tail_samples": 22.8, "learning_rate": 4.3902885857078685e-05, "loss": 0.0269, "positive_teacher_pairs": 27087.4, "relation_loss": 0.00254617661703378, "selected_pairs": 27087.4, "step": 16860, "student_distance_mean": 1269.0712890625, "teacher_distance_mean": 0.8694019675254822, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.00254617661703378, "weighted_relation_loss": 0.00254617661703378 }, { "action_query_batch_std": 21.89519691467285, "action_query_norm": 938.7439453125, "action_relation_loss": 0.0025072841439396144, "auxiliary_loss_weight": 1.0, "epoch": 15.781103835360149, "flow_matching_loss": 0.0262162322178483, "grad_norm": 0.09115336835384369, "invalid_tail_samples": 23.5, "learning_rate": 4.384818522938531e-05, "loss": 0.0287, "positive_teacher_pairs": 26917.1, "relation_loss": 0.0025072841439396144, "selected_pairs": 26917.1, "step": 16870, "student_distance_mean": 1253.356298828125, "teacher_distance_mean": 0.8582234442234039, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0025072841439396144, "weighted_relation_loss": 0.0025072841439396144 }, { "action_query_batch_std": 21.81856174468994, "action_query_norm": 933.0284301757813, "action_relation_loss": 0.0025385989341884852, "auxiliary_loss_weight": 1.0, "epoch": 15.790458372310571, "flow_matching_loss": 0.027408687211573125, "grad_norm": 0.10998111963272095, "invalid_tail_samples": 21.5, "learning_rate": 4.379349207672695e-05, "loss": 0.0299, "positive_teacher_pairs": 27385.7, "relation_loss": 0.0025385989341884852, "selected_pairs": 27385.7, "step": 16880, "student_distance_mean": 1247.7642578125, "teacher_distance_mean": 0.8574559986591339, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.0025385989341884852, "weighted_relation_loss": 0.0025385989341884852 }, { "action_query_batch_std": 21.59075756072998, "action_query_norm": 926.21552734375, "action_relation_loss": 0.0025746508967131377, "auxiliary_loss_weight": 1.0, "epoch": 15.799812909260991, "flow_matching_loss": 0.025394843891263008, "grad_norm": 0.11837410926818848, "invalid_tail_samples": 22.9, "learning_rate": 4.373880646556098e-05, "loss": 0.028, "positive_teacher_pairs": 27061.1, "relation_loss": 0.0025746508967131377, "selected_pairs": 27061.1, "step": 16890, "student_distance_mean": 1236.1425903320312, "teacher_distance_mean": 0.8491452217102051, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0025746508967131377, "weighted_relation_loss": 0.0025746508967131377 }, { "action_query_batch_std": 22.012073135375978, "action_query_norm": 940.6703674316407, "action_relation_loss": 0.002616812917403877, "auxiliary_loss_weight": 1.0, "epoch": 15.809167446211413, "flow_matching_loss": 0.025776714272797107, "grad_norm": 0.11806696653366089, "invalid_tail_samples": 24.5, "learning_rate": 4.3684128462335533e-05, "loss": 0.0284, "positive_teacher_pairs": 26692.7, "relation_loss": 0.002616812917403877, "selected_pairs": 26692.7, "step": 16900, "student_distance_mean": 1263.8796997070312, "teacher_distance_mean": 0.8651179194450378, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.002616812917403877, "weighted_relation_loss": 0.002616812917403877 }, { "action_query_batch_std": 22.056342697143556, "action_query_norm": 939.4750305175781, "action_relation_loss": 0.0025071877054870127, "auxiliary_loss_weight": 1.0, "epoch": 15.818521983161833, "flow_matching_loss": 0.025304041802883148, "grad_norm": 0.09295891970396042, "invalid_tail_samples": 24.8, "learning_rate": 4.362945813348955e-05, "loss": 0.0278, "positive_teacher_pairs": 26625.6, "relation_loss": 0.0025071877054870127, "selected_pairs": 26625.6, "step": 16910, "student_distance_mean": 1261.974560546875, "teacher_distance_mean": 0.8649627506732941, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0025071877054870127, "weighted_relation_loss": 0.0025071877054870127 }, { "action_query_batch_std": 21.827856254577636, "action_query_norm": 934.2207336425781, "action_relation_loss": 0.0025331480661407112, "auxiliary_loss_weight": 1.0, "epoch": 15.827876520112255, "flow_matching_loss": 0.025668345764279364, "grad_norm": 0.08368177711963654, "invalid_tail_samples": 22.3, "learning_rate": 4.357479554545262e-05, "loss": 0.0282, "positive_teacher_pairs": 27200.8, "relation_loss": 0.0025331480661407112, "selected_pairs": 27200.8, "step": 16920, "student_distance_mean": 1252.503369140625, "teacher_distance_mean": 0.8537888944149017, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0025331480661407112, "weighted_relation_loss": 0.0025331480661407112 }, { "action_query_batch_std": 21.37897319793701, "action_query_norm": 917.9097412109375, "action_relation_loss": 0.0025957692880183457, "auxiliary_loss_weight": 1.0, "epoch": 15.837231057062676, "flow_matching_loss": 0.02508258055895567, "grad_norm": 0.09575922042131424, "invalid_tail_samples": 23.6, "learning_rate": 4.352014076464499e-05, "loss": 0.0277, "positive_teacher_pairs": 26894.3, "relation_loss": 0.0025957692880183457, "selected_pairs": 26894.3, "step": 16930, "student_distance_mean": 1226.6601928710938, "teacher_distance_mean": 0.8407330453395844, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0025957692880183457, "weighted_relation_loss": 0.0025957692880183457 }, { "action_query_batch_std": 22.01479320526123, "action_query_norm": 940.69443359375, "action_relation_loss": 0.002503073634579778, "auxiliary_loss_weight": 1.0, "epoch": 15.846585594013096, "flow_matching_loss": 0.02567351683974266, "grad_norm": 0.08997653424739838, "invalid_tail_samples": 23.1, "learning_rate": 4.346549385747734e-05, "loss": 0.0282, "positive_teacher_pairs": 27008.5, "relation_loss": 0.002503073634579778, "selected_pairs": 27008.5, "step": 16940, "student_distance_mean": 1258.4598266601563, "teacher_distance_mean": 0.8637501716613769, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.002503073634579778, "weighted_relation_loss": 0.002503073634579778 }, { "action_query_batch_std": 21.752744674682617, "action_query_norm": 929.647021484375, "action_relation_loss": 0.002474603429436684, "auxiliary_loss_weight": 1.0, "epoch": 15.855940130963518, "flow_matching_loss": 0.026850925385951997, "grad_norm": 0.10237184911966324, "invalid_tail_samples": 23.0, "learning_rate": 4.34108548903508e-05, "loss": 0.0293, "positive_teacher_pairs": 27034.0, "relation_loss": 0.002474603429436684, "selected_pairs": 27034.0, "step": 16950, "student_distance_mean": 1241.3475219726563, "teacher_distance_mean": 0.854862904548645, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.002474603429436684, "weighted_relation_loss": 0.002474603429436684 }, { "action_query_batch_std": 21.878899574279785, "action_query_norm": 934.8526123046875, "action_relation_loss": 0.002544545126147568, "auxiliary_loss_weight": 1.0, "epoch": 15.865294667913938, "flow_matching_loss": 0.025915721245110036, "grad_norm": 0.08922185003757477, "invalid_tail_samples": 24.5, "learning_rate": 4.335622392965689e-05, "loss": 0.0285, "positive_teacher_pairs": 26692.1, "relation_loss": 0.002544545126147568, "selected_pairs": 26692.1, "step": 16960, "student_distance_mean": 1244.8600219726563, "teacher_distance_mean": 0.8532449066638946, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.002544545126147568, "weighted_relation_loss": 0.002544545126147568 }, { "action_query_batch_std": 21.75457305908203, "action_query_norm": 935.4511169433594, "action_relation_loss": 0.0025852905353531243, "auxiliary_loss_weight": 1.0, "epoch": 15.87464920486436, "flow_matching_loss": 0.026326173543930055, "grad_norm": 0.10146642476320267, "invalid_tail_samples": 20.9, "learning_rate": 4.330160104177738e-05, "loss": 0.0289, "positive_teacher_pairs": 27527.9, "relation_loss": 0.0025852905353531243, "selected_pairs": 27527.9, "step": 16970, "student_distance_mean": 1246.76044921875, "teacher_distance_mean": 0.8521814703941345, "valid_action_samples": 235.1, "weighted_auxiliary_loss": 0.0025852905353531243, "weighted_relation_loss": 0.0025852905353531243 }, { "action_query_batch_std": 21.746545600891114, "action_query_norm": 933.2217407226562, "action_relation_loss": 0.0025938799139112235, "auxiliary_loss_weight": 1.0, "epoch": 15.88400374181478, "flow_matching_loss": 0.02577491495758295, "grad_norm": 0.13836349546909332, "invalid_tail_samples": 24.0, "learning_rate": 4.32469862930842e-05, "loss": 0.0284, "positive_teacher_pairs": 26807.5, "relation_loss": 0.0025938799139112235, "selected_pairs": 26807.5, "step": 16980, "student_distance_mean": 1245.5915893554688, "teacher_distance_mean": 0.8541272938251495, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0025938799139112235, "weighted_relation_loss": 0.0025938799139112235 }, { "action_query_batch_std": 21.730109405517577, "action_query_norm": 936.1109619140625, "action_relation_loss": 0.002641383744776249, "auxiliary_loss_weight": 1.0, "epoch": 15.8933582787652, "flow_matching_loss": 0.026375721022486687, "grad_norm": 0.11729937791824341, "invalid_tail_samples": 22.2, "learning_rate": 4.319237974993946e-05, "loss": 0.029, "positive_teacher_pairs": 27216.5, "relation_loss": 0.002641383744776249, "selected_pairs": 27216.5, "step": 16990, "student_distance_mean": 1247.5556640625, "teacher_distance_mean": 0.8507105946540833, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.002641383744776249, "weighted_relation_loss": 0.002641383744776249 }, { "action_query_batch_std": 21.511035537719728, "action_query_norm": 930.0301147460938, "action_relation_loss": 0.002535939263179898, "auxiliary_loss_weight": 1.0, "epoch": 15.902712815715622, "flow_matching_loss": 0.027045794390141965, "grad_norm": 0.08773453533649445, "invalid_tail_samples": 24.8, "learning_rate": 4.3137781478695236e-05, "loss": 0.0296, "positive_teacher_pairs": 26617.3, "relation_loss": 0.002535939263179898, "selected_pairs": 26617.3, "step": 17000, "student_distance_mean": 1235.9578857421875, "teacher_distance_mean": 0.8458852469921112, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.002535939263179898, "weighted_relation_loss": 0.002535939263179898 }, { "action_query_batch_std": 21.673885917663576, "action_query_norm": 929.8327026367188, "action_relation_loss": 0.0025582277914509175, "auxiliary_loss_weight": 1.0, "epoch": 15.912067352666043, "flow_matching_loss": 0.027352720312774182, "grad_norm": 0.12277567386627197, "invalid_tail_samples": 23.2, "learning_rate": 4.308319154569358e-05, "loss": 0.0299, "positive_teacher_pairs": 26991.5, "relation_loss": 0.0025582277914509175, "selected_pairs": 26991.5, "step": 17010, "student_distance_mean": 1240.7508911132813, "teacher_distance_mean": 0.8530342161655426, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0025582277914509175, "weighted_relation_loss": 0.0025582277914509175 }, { "action_query_batch_std": 21.586765480041503, "action_query_norm": 925.4404052734375, "action_relation_loss": 0.0024676966946572064, "auxiliary_loss_weight": 1.0, "epoch": 15.921421889616465, "flow_matching_loss": 0.02463782485574484, "grad_norm": 0.09449666738510132, "invalid_tail_samples": 20.3, "learning_rate": 4.302861001726641e-05, "loss": 0.0271, "positive_teacher_pairs": 27675.7, "relation_loss": 0.0024676966946572064, "selected_pairs": 27675.7, "step": 17020, "student_distance_mean": 1234.442822265625, "teacher_distance_mean": 0.8510075032711029, "valid_action_samples": 235.7, "weighted_auxiliary_loss": 0.0024676966946572064, "weighted_relation_loss": 0.0024676966946572064 }, { "action_query_batch_std": 21.677192878723144, "action_query_norm": 930.8219055175781, "action_relation_loss": 0.0026664279866963625, "auxiliary_loss_weight": 1.0, "epoch": 15.930776426566885, "flow_matching_loss": 0.025769947841763497, "grad_norm": 0.0895533487200737, "invalid_tail_samples": 23.1, "learning_rate": 4.2974036959735415e-05, "loss": 0.0284, "positive_teacher_pairs": 27014.2, "relation_loss": 0.0026664279866963625, "selected_pairs": 27014.2, "step": 17030, "student_distance_mean": 1245.6568481445313, "teacher_distance_mean": 0.8521780848503113, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0026664279866963625, "weighted_relation_loss": 0.0026664279866963625 }, { "action_query_batch_std": 21.947131538391112, "action_query_norm": 939.8671752929688, "action_relation_loss": 0.0025854050181806087, "auxiliary_loss_weight": 1.0, "epoch": 15.940130963517305, "flow_matching_loss": 0.027611350640654564, "grad_norm": 0.11995026469230652, "invalid_tail_samples": 26.3, "learning_rate": 4.2919472439412034e-05, "loss": 0.0302, "positive_teacher_pairs": 26272.7, "relation_loss": 0.0025854050181806087, "selected_pairs": 26272.7, "step": 17040, "student_distance_mean": 1263.139697265625, "teacher_distance_mean": 0.8615656077861786, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.0025854050181806087, "weighted_relation_loss": 0.0025854050181806087 }, { "action_query_batch_std": 21.71754035949707, "action_query_norm": 929.0807495117188, "action_relation_loss": 0.002579561993479729, "auxiliary_loss_weight": 1.0, "epoch": 15.949485500467727, "flow_matching_loss": 0.0248605627566576, "grad_norm": 0.11111277341842651, "invalid_tail_samples": 25.5, "learning_rate": 4.286491652259729e-05, "loss": 0.0274, "positive_teacher_pairs": 26462.8, "relation_loss": 0.002579561993479729, "selected_pairs": 26462.8, "step": 17050, "student_distance_mean": 1243.3769409179688, "teacher_distance_mean": 0.849552047252655, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.002579561993479729, "weighted_relation_loss": 0.002579561993479729 }, { "action_query_batch_std": 21.951092338562013, "action_query_norm": 936.3072326660156, "action_relation_loss": 0.002529705874621868, "auxiliary_loss_weight": 1.0, "epoch": 15.958840037418147, "flow_matching_loss": 0.028239687345921992, "grad_norm": 0.09061557799577713, "invalid_tail_samples": 22.6, "learning_rate": 4.281036927558178e-05, "loss": 0.0308, "positive_teacher_pairs": 27129.1, "relation_loss": 0.002529705874621868, "selected_pairs": 27129.1, "step": 17060, "student_distance_mean": 1257.6969970703126, "teacher_distance_mean": 0.8592657625675202, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.002529705874621868, "weighted_relation_loss": 0.002529705874621868 }, { "action_query_batch_std": 21.812962150573732, "action_query_norm": 936.1775024414062, "action_relation_loss": 0.0026175799779593945, "auxiliary_loss_weight": 1.0, "epoch": 15.96819457436857, "flow_matching_loss": 0.02556562926620245, "grad_norm": 0.09496071189641953, "invalid_tail_samples": 25.6, "learning_rate": 4.275583076464552e-05, "loss": 0.0282, "positive_teacher_pairs": 26433.5, "relation_loss": 0.0026175799779593945, "selected_pairs": 26433.5, "step": 17070, "student_distance_mean": 1252.458154296875, "teacher_distance_mean": 0.8561467111110688, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.0026175799779593945, "weighted_relation_loss": 0.0026175799779593945 }, { "action_query_batch_std": 22.136473655700684, "action_query_norm": 946.1366760253907, "action_relation_loss": 0.0025010400684550406, "auxiliary_loss_weight": 1.0, "epoch": 15.97754911131899, "flow_matching_loss": 0.024493825808167457, "grad_norm": 0.11904382705688477, "invalid_tail_samples": 23.4, "learning_rate": 4.270130105605794e-05, "loss": 0.027, "positive_teacher_pairs": 26940.6, "relation_loss": 0.0025010400684550406, "selected_pairs": 26940.6, "step": 17080, "student_distance_mean": 1270.706201171875, "teacher_distance_mean": 0.8684553384780884, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0025010400684550406, "weighted_relation_loss": 0.0025010400684550406 }, { "action_query_batch_std": 22.0189302444458, "action_query_norm": 940.4577270507813, "action_relation_loss": 0.0026300816563889383, "auxiliary_loss_weight": 1.0, "epoch": 15.986903648269411, "flow_matching_loss": 0.026130710169672965, "grad_norm": 0.08553414791822433, "invalid_tail_samples": 23.7, "learning_rate": 4.264678021607782e-05, "loss": 0.0288, "positive_teacher_pairs": 26878.4, "relation_loss": 0.0026300816563889383, "selected_pairs": 26878.4, "step": 17090, "student_distance_mean": 1257.9538818359374, "teacher_distance_mean": 0.8525933623313904, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0026300816563889383, "weighted_relation_loss": 0.0026300816563889383 }, { "action_query_batch_std": 21.990645980834962, "action_query_norm": 937.6596740722656, "action_relation_loss": 0.0024559831246733664, "auxiliary_loss_weight": 1.0, "epoch": 15.996258185219832, "flow_matching_loss": 0.025362356379628182, "grad_norm": 0.10807880759239197, "invalid_tail_samples": 24.1, "learning_rate": 4.25922683109531e-05, "loss": 0.0278, "positive_teacher_pairs": 26776.8, "relation_loss": 0.0024559831246733664, "selected_pairs": 26776.8, "step": 17100, "student_distance_mean": 1258.6054443359376, "teacher_distance_mean": 0.8633120656013489, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0024559831246733664, "weighted_relation_loss": 0.0024559831246733664 }, { "action_query_batch_std": 21.740498352050782, "action_query_norm": 933.4388610839844, "action_relation_loss": 0.0024355298606678843, "auxiliary_loss_weight": 1.0, "epoch": 16.00561272217025, "flow_matching_loss": 0.0243876900523901, "grad_norm": 0.10443394631147385, "invalid_tail_samples": 21.7, "learning_rate": 4.25377654069209e-05, "loss": 0.0268, "positive_teacher_pairs": 24332.7, "relation_loss": 0.0024355298606678843, "selected_pairs": 24332.7, "step": 17110, "student_distance_mean": 1241.0909790039063, "teacher_distance_mean": 0.8570813536643982, "valid_action_samples": 214.4, "weighted_auxiliary_loss": 0.0024355298606678843, "weighted_relation_loss": 0.0024355298606678843 }, { "action_query_batch_std": 21.73399829864502, "action_query_norm": 931.5035827636718, "action_relation_loss": 0.0025865639792755244, "auxiliary_loss_weight": 1.0, "epoch": 16.014967259120674, "flow_matching_loss": 0.028143777698278426, "grad_norm": 0.14440390467643738, "invalid_tail_samples": 23.8, "learning_rate": 4.248327157020737e-05, "loss": 0.0307, "positive_teacher_pairs": 26858.2, "relation_loss": 0.0025865639792755244, "selected_pairs": 26858.2, "step": 17120, "student_distance_mean": 1243.2154052734375, "teacher_distance_mean": 0.8511475265026093, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0025865639792755244, "weighted_relation_loss": 0.0025865639792755244 }, { "action_query_batch_std": 22.058356094360352, "action_query_norm": 943.2099243164063, "action_relation_loss": 0.0025093234842643143, "auxiliary_loss_weight": 1.0, "epoch": 16.024321796071096, "flow_matching_loss": 0.02438570372760296, "grad_norm": 0.10225965827703476, "invalid_tail_samples": 21.2, "learning_rate": 4.242878686702763e-05, "loss": 0.0269, "positive_teacher_pairs": 27454.4, "relation_loss": 0.0025093234842643143, "selected_pairs": 27454.4, "step": 17130, "student_distance_mean": 1262.214404296875, "teacher_distance_mean": 0.8564788401126862, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.0025093234842643143, "weighted_relation_loss": 0.0025093234842643143 }, { "action_query_batch_std": 21.666040229797364, "action_query_norm": 933.2511535644531, "action_relation_loss": 0.0026129755191504956, "auxiliary_loss_weight": 1.0, "epoch": 16.033676333021514, "flow_matching_loss": 0.024409597925841808, "grad_norm": 0.08924564719200134, "invalid_tail_samples": 24.7, "learning_rate": 4.23743113635858e-05, "loss": 0.027, "positive_teacher_pairs": 26645.1, "relation_loss": 0.0026129755191504956, "selected_pairs": 26645.1, "step": 17140, "student_distance_mean": 1247.0085815429688, "teacher_distance_mean": 0.8488469600677491, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0026129755191504956, "weighted_relation_loss": 0.0026129755191504956 }, { "action_query_batch_std": 21.997793197631836, "action_query_norm": 937.1532958984375, "action_relation_loss": 0.0024992328369989993, "auxiliary_loss_weight": 1.0, "epoch": 16.043030869971936, "flow_matching_loss": 0.025316817872226238, "grad_norm": 0.09949606657028198, "invalid_tail_samples": 24.1, "learning_rate": 4.2319845126074705e-05, "loss": 0.0278, "positive_teacher_pairs": 26788.6, "relation_loss": 0.0024992328369989993, "selected_pairs": 26788.6, "step": 17150, "student_distance_mean": 1261.855322265625, "teacher_distance_mean": 0.8625443637371063, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0024992328369989993, "weighted_relation_loss": 0.0024992328369989993 }, { "action_query_batch_std": 22.161164855957033, "action_query_norm": 945.0114196777344, "action_relation_loss": 0.0024338420946151016, "auxiliary_loss_weight": 1.0, "epoch": 16.052385406922358, "flow_matching_loss": 0.023059369809925557, "grad_norm": 0.12459322810173035, "invalid_tail_samples": 23.8, "learning_rate": 4.226538822067598e-05, "loss": 0.0255, "positive_teacher_pairs": 26862.8, "relation_loss": 0.0024338420946151016, "selected_pairs": 26862.8, "step": 17160, "student_distance_mean": 1268.47744140625, "teacher_distance_mean": 0.8643251538276673, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0024338420946151016, "weighted_relation_loss": 0.0024338420946151016 }, { "action_query_batch_std": 21.891097640991212, "action_query_norm": 936.2067016601562, "action_relation_loss": 0.0024246838409453632, "auxiliary_loss_weight": 1.0, "epoch": 16.061739943872777, "flow_matching_loss": 0.024647181481122972, "grad_norm": 0.08681918680667877, "invalid_tail_samples": 23.7, "learning_rate": 4.2210940713559896e-05, "loss": 0.0271, "positive_teacher_pairs": 26880.3, "relation_loss": 0.0024246838409453632, "selected_pairs": 26880.3, "step": 17170, "student_distance_mean": 1259.1725830078126, "teacher_distance_mean": 0.8598803102970123, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0024246838409453632, "weighted_relation_loss": 0.0024246838409453632 }, { "action_query_batch_std": 22.08957710266113, "action_query_norm": 941.0221069335937, "action_relation_loss": 0.0024651459651067855, "auxiliary_loss_weight": 1.0, "epoch": 16.0710944808232, "flow_matching_loss": 0.024913126789033412, "grad_norm": 0.1028411015868187, "invalid_tail_samples": 25.8, "learning_rate": 4.21565026708853e-05, "loss": 0.0274, "positive_teacher_pairs": 26399.7, "relation_loss": 0.0024651459651067855, "selected_pairs": 26399.7, "step": 17180, "student_distance_mean": 1269.3223022460938, "teacher_distance_mean": 0.865208488702774, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.0024651459651067855, "weighted_relation_loss": 0.0024651459651067855 }, { "action_query_batch_std": 21.94999008178711, "action_query_norm": 939.1166198730468, "action_relation_loss": 0.0024082384072244166, "auxiliary_loss_weight": 1.0, "epoch": 16.08044901777362, "flow_matching_loss": 0.022743703983724117, "grad_norm": 0.10284548252820969, "invalid_tail_samples": 24.0, "learning_rate": 4.2102074158799535e-05, "loss": 0.0252, "positive_teacher_pairs": 26803.0, "relation_loss": 0.0024082384072244166, "selected_pairs": 26803.0, "step": 17190, "student_distance_mean": 1259.7001953125, "teacher_distance_mean": 0.8599130868911743, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0024082384072244166, "weighted_relation_loss": 0.0024082384072244166 }, { "action_query_batch_std": 21.769815826416014, "action_query_norm": 932.3033630371094, "action_relation_loss": 0.0025044871028512715, "auxiliary_loss_weight": 1.0, "epoch": 16.089803554724043, "flow_matching_loss": 0.024965079873800276, "grad_norm": 0.11074265837669373, "invalid_tail_samples": 23.8, "learning_rate": 4.204765524343841e-05, "loss": 0.0275, "positive_teacher_pairs": 26847.7, "relation_loss": 0.0025044871028512715, "selected_pairs": 26847.7, "step": 17200, "student_distance_mean": 1249.358203125, "teacher_distance_mean": 0.8514027655124664, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0025044871028512715, "weighted_relation_loss": 0.0025044871028512715 }, { "action_query_batch_std": 21.94037570953369, "action_query_norm": 938.5500732421875, "action_relation_loss": 0.002519988967105746, "auxiliary_loss_weight": 1.0, "epoch": 16.09915809167446, "flow_matching_loss": 0.024923686869442463, "grad_norm": 0.11479819566011429, "invalid_tail_samples": 26.3, "learning_rate": 4.1993245990926036e-05, "loss": 0.0274, "positive_teacher_pairs": 26280.7, "relation_loss": 0.002519988967105746, "selected_pairs": 26280.7, "step": 17210, "student_distance_mean": 1260.0189697265625, "teacher_distance_mean": 0.8561035752296448, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.002519988967105746, "weighted_relation_loss": 0.002519988967105746 }, { "action_query_batch_std": 21.754179191589355, "action_query_norm": 933.169677734375, "action_relation_loss": 0.0023333196062594653, "auxiliary_loss_weight": 1.0, "epoch": 16.108512628624883, "flow_matching_loss": 0.02664285320788622, "grad_norm": 0.08823798596858978, "invalid_tail_samples": 25.7, "learning_rate": 4.193884646737474e-05, "loss": 0.029, "positive_teacher_pairs": 26422.3, "relation_loss": 0.0023333196062594653, "selected_pairs": 26422.3, "step": 17220, "student_distance_mean": 1246.9869384765625, "teacher_distance_mean": 0.8504813849925995, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.0023333196062594653, "weighted_relation_loss": 0.0023333196062594653 }, { "action_query_batch_std": 22.034343910217284, "action_query_norm": 938.575830078125, "action_relation_loss": 0.002519750641658902, "auxiliary_loss_weight": 1.0, "epoch": 16.117867165575305, "flow_matching_loss": 0.024892411939799786, "grad_norm": 0.10415471345186234, "invalid_tail_samples": 26.5, "learning_rate": 4.1884456738885124e-05, "loss": 0.0274, "positive_teacher_pairs": 26233.6, "relation_loss": 0.002519750641658902, "selected_pairs": 26233.6, "step": 17230, "student_distance_mean": 1260.2649169921874, "teacher_distance_mean": 0.8577429115772247, "valid_action_samples": 229.5, "weighted_auxiliary_loss": 0.002519750641658902, "weighted_relation_loss": 0.002519750641658902 }, { "action_query_batch_std": 22.118631172180176, "action_query_norm": 943.2406188964844, "action_relation_loss": 0.0023797004716470836, "auxiliary_loss_weight": 1.0, "epoch": 16.127221702525723, "flow_matching_loss": 0.024422261863946915, "grad_norm": 0.11900974810123444, "invalid_tail_samples": 22.8, "learning_rate": 4.1830076871545795e-05, "loss": 0.0268, "positive_teacher_pairs": 27080.3, "relation_loss": 0.0023797004716470836, "selected_pairs": 27080.3, "step": 17240, "student_distance_mean": 1270.4685791015625, "teacher_distance_mean": 0.864785087108612, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0023797004716470836, "weighted_relation_loss": 0.0023797004716470836 }, { "action_query_batch_std": 21.982660675048827, "action_query_norm": 942.1212768554688, "action_relation_loss": 0.0024279785109683873, "auxiliary_loss_weight": 1.0, "epoch": 16.136576239476145, "flow_matching_loss": 0.02612751331180334, "grad_norm": 0.08198555558919907, "invalid_tail_samples": 23.1, "learning_rate": 4.177570693143346e-05, "loss": 0.0286, "positive_teacher_pairs": 27015.2, "relation_loss": 0.0024279785109683873, "selected_pairs": 27015.2, "step": 17250, "student_distance_mean": 1262.7919921875, "teacher_distance_mean": 0.8588145077228546, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0024279785109683873, "weighted_relation_loss": 0.0024279785109683873 }, { "action_query_batch_std": 21.873432540893553, "action_query_norm": 935.9868835449219, "action_relation_loss": 0.002534924983046949, "auxiliary_loss_weight": 1.0, "epoch": 16.145930776426567, "flow_matching_loss": 0.02525698971003294, "grad_norm": 0.13486768305301666, "invalid_tail_samples": 25.1, "learning_rate": 4.172134698461271e-05, "loss": 0.0278, "positive_teacher_pairs": 26547.1, "relation_loss": 0.002534924983046949, "selected_pairs": 26547.1, "step": 17260, "student_distance_mean": 1252.3679321289062, "teacher_distance_mean": 0.8534925818443299, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.002534924983046949, "weighted_relation_loss": 0.002534924983046949 }, { "action_query_batch_std": 22.098262214660643, "action_query_norm": 942.7330017089844, "action_relation_loss": 0.002527300361543894, "auxiliary_loss_weight": 1.0, "epoch": 16.15528531337699, "flow_matching_loss": 0.02527320310473442, "grad_norm": 0.10951591283082962, "invalid_tail_samples": 21.8, "learning_rate": 4.166699709713599e-05, "loss": 0.0278, "positive_teacher_pairs": 27318.2, "relation_loss": 0.002527300361543894, "selected_pairs": 27318.2, "step": 17270, "student_distance_mean": 1262.0166381835938, "teacher_distance_mean": 0.8549350798130035, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.002527300361543894, "weighted_relation_loss": 0.002527300361543894 }, { "action_query_batch_std": 21.873772811889648, "action_query_norm": 937.1153381347656, "action_relation_loss": 0.0024544251384213565, "auxiliary_loss_weight": 1.0, "epoch": 16.164639850327408, "flow_matching_loss": 0.025635820627212525, "grad_norm": 0.1025523990392685, "invalid_tail_samples": 23.3, "learning_rate": 4.1612657335043555e-05, "loss": 0.0281, "positive_teacher_pairs": 26962.5, "relation_loss": 0.0024544251384213565, "selected_pairs": 26962.5, "step": 17280, "student_distance_mean": 1254.7776245117188, "teacher_distance_mean": 0.8547489404678345, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0024544251384213565, "weighted_relation_loss": 0.0024544251384213565 }, { "action_query_batch_std": 21.891186714172363, "action_query_norm": 938.0675903320313, "action_relation_loss": 0.0024565886007621883, "auxiliary_loss_weight": 1.0, "epoch": 16.17399438727783, "flow_matching_loss": 0.024404592253267764, "grad_norm": 0.10150459408760071, "invalid_tail_samples": 23.4, "learning_rate": 4.155832776436331e-05, "loss": 0.0269, "positive_teacher_pairs": 26946.3, "relation_loss": 0.0024565886007621883, "selected_pairs": 26946.3, "step": 17290, "student_distance_mean": 1256.4384887695312, "teacher_distance_mean": 0.8559456944465638, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0024565886007621883, "weighted_relation_loss": 0.0024565886007621883 }, { "action_query_batch_std": 21.72960662841797, "action_query_norm": 933.214599609375, "action_relation_loss": 0.002477986481972039, "auxiliary_loss_weight": 1.0, "epoch": 16.18334892422825, "flow_matching_loss": 0.02681289240717888, "grad_norm": 0.09729495644569397, "invalid_tail_samples": 24.0, "learning_rate": 4.1504008451110845e-05, "loss": 0.0293, "positive_teacher_pairs": 26807.3, "relation_loss": 0.002477986481972039, "selected_pairs": 26807.3, "step": 17300, "student_distance_mean": 1246.8148071289063, "teacher_distance_mean": 0.8482035756111145, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.002477986481972039, "weighted_relation_loss": 0.002477986481972039 }, { "action_query_batch_std": 21.67484531402588, "action_query_norm": 927.8458618164062, "action_relation_loss": 0.002484557335264981, "auxiliary_loss_weight": 1.0, "epoch": 16.19270346117867, "flow_matching_loss": 0.02518543880432844, "grad_norm": 0.12885898351669312, "invalid_tail_samples": 24.6, "learning_rate": 4.1449699461289225e-05, "loss": 0.0277, "positive_teacher_pairs": 26669.4, "relation_loss": 0.002484557335264981, "selected_pairs": 26669.4, "step": 17310, "student_distance_mean": 1243.17060546875, "teacher_distance_mean": 0.8501830220222473, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.002484557335264981, "weighted_relation_loss": 0.002484557335264981 }, { "action_query_batch_std": 21.57792224884033, "action_query_norm": 926.9207641601563, "action_relation_loss": 0.0024138142354786394, "auxiliary_loss_weight": 1.0, "epoch": 16.202057998129092, "flow_matching_loss": 0.025585424341261386, "grad_norm": 0.09266634285449982, "invalid_tail_samples": 23.6, "learning_rate": 4.139540086088901e-05, "loss": 0.028, "positive_teacher_pairs": 26893.1, "relation_loss": 0.0024138142354786394, "selected_pairs": 26893.1, "step": 17320, "student_distance_mean": 1235.86884765625, "teacher_distance_mean": 0.8471957564353942, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0024138142354786394, "weighted_relation_loss": 0.0024138142354786394 }, { "action_query_batch_std": 21.870528411865234, "action_query_norm": 934.6960998535156, "action_relation_loss": 0.00247783069498837, "auxiliary_loss_weight": 1.0, "epoch": 16.211412535079514, "flow_matching_loss": 0.02548007182776928, "grad_norm": 0.09697475284337997, "invalid_tail_samples": 24.3, "learning_rate": 4.1341112715888106e-05, "loss": 0.028, "positive_teacher_pairs": 26734.6, "relation_loss": 0.00247783069498837, "selected_pairs": 26734.6, "step": 17330, "student_distance_mean": 1252.5914428710937, "teacher_distance_mean": 0.8549201250076294, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.00247783069498837, "weighted_relation_loss": 0.00247783069498837 }, { "action_query_batch_std": 21.654144859313966, "action_query_norm": 929.7888549804687, "action_relation_loss": 0.0024239524034783246, "auxiliary_loss_weight": 1.0, "epoch": 16.220767072029936, "flow_matching_loss": 0.02420563343912363, "grad_norm": 0.09782213717699051, "invalid_tail_samples": 23.7, "learning_rate": 4.128683509225172e-05, "loss": 0.0266, "positive_teacher_pairs": 26870.3, "relation_loss": 0.0024239524034783246, "selected_pairs": 26870.3, "step": 17340, "student_distance_mean": 1240.8816650390625, "teacher_distance_mean": 0.8460904955863953, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0024239524034783246, "weighted_relation_loss": 0.0024239524034783246 }, { "action_query_batch_std": 21.919100952148437, "action_query_norm": 937.3230773925782, "action_relation_loss": 0.0024860051926225424, "auxiliary_loss_weight": 1.0, "epoch": 16.230121608980355, "flow_matching_loss": 0.025783556140959264, "grad_norm": 0.10993503779172897, "invalid_tail_samples": 20.6, "learning_rate": 4.123256805593231e-05, "loss": 0.0283, "positive_teacher_pairs": 27598.8, "relation_loss": 0.0024860051926225424, "selected_pairs": 27598.8, "step": 17350, "student_distance_mean": 1248.9408203125, "teacher_distance_mean": 0.8548086225986481, "valid_action_samples": 235.4, "weighted_auxiliary_loss": 0.0024860051926225424, "weighted_relation_loss": 0.0024860051926225424 }, { "action_query_batch_std": 21.58098030090332, "action_query_norm": 925.7971984863282, "action_relation_loss": 0.0025042740162461996, "auxiliary_loss_weight": 1.0, "epoch": 16.239476145930777, "flow_matching_loss": 0.023970184102654456, "grad_norm": 0.09111988544464111, "invalid_tail_samples": 25.0, "learning_rate": 4.117831167286943e-05, "loss": 0.0265, "positive_teacher_pairs": 26575.5, "relation_loss": 0.0025042740162461996, "selected_pairs": 26575.5, "step": 17360, "student_distance_mean": 1239.7325805664063, "teacher_distance_mean": 0.844481474161148, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0025042740162461996, "weighted_relation_loss": 0.0025042740162461996 }, { "action_query_batch_std": 21.989025688171388, "action_query_norm": 940.141650390625, "action_relation_loss": 0.0024592940928414462, "auxiliary_loss_weight": 1.0, "epoch": 16.2488306828812, "flow_matching_loss": 0.025443121045827865, "grad_norm": 0.1179361492395401, "invalid_tail_samples": 25.0, "learning_rate": 4.1124066008989685e-05, "loss": 0.0279, "positive_teacher_pairs": 26571.2, "relation_loss": 0.0024592940928414462, "selected_pairs": 26571.2, "step": 17370, "student_distance_mean": 1260.0748901367188, "teacher_distance_mean": 0.8568577289581298, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0024592940928414462, "weighted_relation_loss": 0.0024592940928414462 }, { "action_query_batch_std": 21.837940406799316, "action_query_norm": 934.3680297851563, "action_relation_loss": 0.0024819472339004276, "auxiliary_loss_weight": 1.0, "epoch": 16.258185219831617, "flow_matching_loss": 0.02478481736034155, "grad_norm": 0.11739566177129745, "invalid_tail_samples": 22.9, "learning_rate": 4.106983113020669e-05, "loss": 0.0273, "positive_teacher_pairs": 27059.1, "relation_loss": 0.0024819472339004276, "selected_pairs": 27059.1, "step": 17380, "student_distance_mean": 1252.3630859375, "teacher_distance_mean": 0.8541369199752807, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0024819472339004276, "weighted_relation_loss": 0.0024819472339004276 }, { "action_query_batch_std": 21.993601989746093, "action_query_norm": 937.1766906738281, "action_relation_loss": 0.002401322894729674, "auxiliary_loss_weight": 1.0, "epoch": 16.26753975678204, "flow_matching_loss": 0.025098013691604137, "grad_norm": 0.09233349561691284, "invalid_tail_samples": 21.5, "learning_rate": 4.101560710242094e-05, "loss": 0.0275, "positive_teacher_pairs": 27393.7, "relation_loss": 0.002401322894729674, "selected_pairs": 27393.7, "step": 17390, "student_distance_mean": 1257.9779052734375, "teacher_distance_mean": 0.8613944351673126, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.002401322894729674, "weighted_relation_loss": 0.002401322894729674 }, { "action_query_batch_std": 22.011232757568358, "action_query_norm": 940.9714660644531, "action_relation_loss": 0.0023898327723145484, "auxiliary_loss_weight": 1.0, "epoch": 16.27689429373246, "flow_matching_loss": 0.0257334403693676, "grad_norm": 0.13038943707942963, "invalid_tail_samples": 24.8, "learning_rate": 4.096139399151971e-05, "loss": 0.0281, "positive_teacher_pairs": 26617.4, "relation_loss": 0.0023898327723145484, "selected_pairs": 26617.4, "step": 17400, "student_distance_mean": 1263.1619018554688, "teacher_distance_mean": 0.8568037748336792, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0023898327723145484, "weighted_relation_loss": 0.0023898327723145484 }, { "action_query_batch_std": 21.910300636291502, "action_query_norm": 937.6263366699219, "action_relation_loss": 0.0024991855723783376, "auxiliary_loss_weight": 1.0, "epoch": 16.28624883068288, "flow_matching_loss": 0.02446938045322895, "grad_norm": 0.090094193816185, "invalid_tail_samples": 25.6, "learning_rate": 4.090719186337709e-05, "loss": 0.027, "positive_teacher_pairs": 26439.1, "relation_loss": 0.0024991855723783376, "selected_pairs": 26439.1, "step": 17410, "student_distance_mean": 1259.01416015625, "teacher_distance_mean": 0.8542625844478607, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.0024991855723783376, "weighted_relation_loss": 0.0024991855723783376 }, { "action_query_batch_std": 21.94203987121582, "action_query_norm": 941.6208618164062, "action_relation_loss": 0.0024631087202578784, "auxiliary_loss_weight": 1.0, "epoch": 16.2956033676333, "flow_matching_loss": 0.025547797977924346, "grad_norm": 0.10166274011135101, "invalid_tail_samples": 21.8, "learning_rate": 4.0853000783853746e-05, "loss": 0.028, "positive_teacher_pairs": 27312.6, "relation_loss": 0.0024631087202578784, "selected_pairs": 27312.6, "step": 17420, "student_distance_mean": 1262.7092529296874, "teacher_distance_mean": 0.8604182839393616, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.0024631087202578784, "weighted_relation_loss": 0.0024631087202578784 }, { "action_query_batch_std": 22.055709266662596, "action_query_norm": 940.3174133300781, "action_relation_loss": 0.0024313676403835416, "auxiliary_loss_weight": 1.0, "epoch": 16.304957904583723, "flow_matching_loss": 0.024883175268769264, "grad_norm": 0.1321817934513092, "invalid_tail_samples": 23.9, "learning_rate": 4.0798820818796956e-05, "loss": 0.0273, "positive_teacher_pairs": 26836.7, "relation_loss": 0.0024313676403835416, "selected_pairs": 26836.7, "step": 17430, "student_distance_mean": 1260.5324951171874, "teacher_distance_mean": 0.8572149395942688, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0024313676403835416, "weighted_relation_loss": 0.0024313676403835416 }, { "action_query_batch_std": 21.97862892150879, "action_query_norm": 941.0769653320312, "action_relation_loss": 0.0024912928929552436, "auxiliary_loss_weight": 1.0, "epoch": 16.314312441534145, "flow_matching_loss": 0.023721064440906048, "grad_norm": 0.1029023602604866, "invalid_tail_samples": 23.7, "learning_rate": 4.074465203404048e-05, "loss": 0.0262, "positive_teacher_pairs": 26873.4, "relation_loss": 0.0024912928929552436, "selected_pairs": 26873.4, "step": 17440, "student_distance_mean": 1263.2144775390625, "teacher_distance_mean": 0.8573591947555542, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0024912928929552436, "weighted_relation_loss": 0.0024912928929552436 }, { "action_query_batch_std": 22.105183792114257, "action_query_norm": 944.985595703125, "action_relation_loss": 0.0023862385423853993, "auxiliary_loss_weight": 1.0, "epoch": 16.323666978484564, "flow_matching_loss": 0.026996213383972643, "grad_norm": 0.09986325353384018, "invalid_tail_samples": 22.5, "learning_rate": 4.0690494495404495e-05, "loss": 0.0294, "positive_teacher_pairs": 27151.7, "relation_loss": 0.0023862385423853993, "selected_pairs": 27151.7, "step": 17450, "student_distance_mean": 1264.72216796875, "teacher_distance_mean": 0.863102114200592, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0023862385423853993, "weighted_relation_loss": 0.0023862385423853993 }, { "action_query_batch_std": 21.942440795898438, "action_query_norm": 939.7891235351562, "action_relation_loss": 0.0025994408410042525, "auxiliary_loss_weight": 1.0, "epoch": 16.333021515434986, "flow_matching_loss": 0.022949187085032463, "grad_norm": 0.09787202626466751, "invalid_tail_samples": 22.2, "learning_rate": 4.0636348268695535e-05, "loss": 0.0255, "positive_teacher_pairs": 27220.3, "relation_loss": 0.0025994408410042525, "selected_pairs": 27220.3, "step": 17460, "student_distance_mean": 1256.0650390625, "teacher_distance_mean": 0.8551287651062012, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.0025994408410042525, "weighted_relation_loss": 0.0025994408410042525 }, { "action_query_batch_std": 21.940280532836915, "action_query_norm": 937.716796875, "action_relation_loss": 0.0024005599087104203, "auxiliary_loss_weight": 1.0, "epoch": 16.342376052385408, "flow_matching_loss": 0.02457526307553053, "grad_norm": 0.09595859050750732, "invalid_tail_samples": 23.0, "learning_rate": 4.058221341970637e-05, "loss": 0.027, "positive_teacher_pairs": 27046.9, "relation_loss": 0.0024005599087104203, "selected_pairs": 27046.9, "step": 17470, "student_distance_mean": 1258.2314453125, "teacher_distance_mean": 0.8535286247730255, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0024005599087104203, "weighted_relation_loss": 0.0024005599087104203 }, { "action_query_batch_std": 21.99462718963623, "action_query_norm": 942.4996520996094, "action_relation_loss": 0.0023800414288416504, "auxiliary_loss_weight": 1.0, "epoch": 16.351730589335826, "flow_matching_loss": 0.025260706804692744, "grad_norm": 0.09393178671598434, "invalid_tail_samples": 25.8, "learning_rate": 4.0528090014215945e-05, "loss": 0.0276, "positive_teacher_pairs": 26392.7, "relation_loss": 0.0023800414288416504, "selected_pairs": 26392.7, "step": 17480, "student_distance_mean": 1260.988427734375, "teacher_distance_mean": 0.8562084376811981, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.0023800414288416504, "weighted_relation_loss": 0.0023800414288416504 }, { "action_query_batch_std": 21.969955253601075, "action_query_norm": 942.9561279296875, "action_relation_loss": 0.002473811828531325, "auxiliary_loss_weight": 1.0, "epoch": 16.36108512628625, "flow_matching_loss": 0.025119840912520886, "grad_norm": 0.09459111094474792, "invalid_tail_samples": 18.9, "learning_rate": 4.047397811798929e-05, "loss": 0.0276, "positive_teacher_pairs": 27994.1, "relation_loss": 0.002473811828531325, "selected_pairs": 27994.1, "step": 17490, "student_distance_mean": 1258.5531005859375, "teacher_distance_mean": 0.8554233133792877, "valid_action_samples": 237.1, "weighted_auxiliary_loss": 0.002473811828531325, "weighted_relation_loss": 0.002473811828531325 }, { "action_query_batch_std": 21.948731994628908, "action_query_norm": 941.3585144042969, "action_relation_loss": 0.002501278021372855, "auxiliary_loss_weight": 1.0, "epoch": 16.37043966323667, "flow_matching_loss": 0.02525775171816349, "grad_norm": 0.10013344138860703, "invalid_tail_samples": 22.3, "learning_rate": 4.041987779677745e-05, "loss": 0.0278, "positive_teacher_pairs": 27208.8, "relation_loss": 0.002501278021372855, "selected_pairs": 27208.8, "step": 17500, "student_distance_mean": 1259.8378051757813, "teacher_distance_mean": 0.8513366878032684, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.002501278021372855, "weighted_relation_loss": 0.002501278021372855 }, { "action_query_batch_std": 21.948536682128907, "action_query_norm": 942.2699645996094, "action_relation_loss": 0.0024215464247390626, "auxiliary_loss_weight": 1.0, "epoch": 16.379794200187092, "flow_matching_loss": 0.025831386260688306, "grad_norm": 0.0874897763133049, "invalid_tail_samples": 21.6, "learning_rate": 4.036578911631745e-05, "loss": 0.0283, "positive_teacher_pairs": 27363.2, "relation_loss": 0.0024215464247390626, "selected_pairs": 27363.2, "step": 17510, "student_distance_mean": 1258.5004516601562, "teacher_distance_mean": 0.8496860504150391, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.0024215464247390626, "weighted_relation_loss": 0.0024215464247390626 }, { "action_query_batch_std": 22.025066757202147, "action_query_norm": 943.8166564941406, "action_relation_loss": 0.0024224969791248442, "auxiliary_loss_weight": 1.0, "epoch": 16.38914873713751, "flow_matching_loss": 0.024524899758398534, "grad_norm": 0.08564157783985138, "invalid_tail_samples": 26.1, "learning_rate": 4.031171214233211e-05, "loss": 0.0269, "positive_teacher_pairs": 26322.3, "relation_loss": 0.0024224969791248442, "selected_pairs": 26322.3, "step": 17520, "student_distance_mean": 1265.4259033203125, "teacher_distance_mean": 0.8555191874504089, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.0024224969791248442, "weighted_relation_loss": 0.0024224969791248442 }, { "action_query_batch_std": 21.848056983947753, "action_query_norm": 938.4429321289062, "action_relation_loss": 0.002491554943844676, "auxiliary_loss_weight": 1.0, "epoch": 16.398503274087933, "flow_matching_loss": 0.023586068488657474, "grad_norm": 0.08878984302282333, "invalid_tail_samples": 21.5, "learning_rate": 4.025764694053008e-05, "loss": 0.0261, "positive_teacher_pairs": 27383.6, "relation_loss": 0.002491554943844676, "selected_pairs": 27383.6, "step": 17530, "student_distance_mean": 1250.8546752929688, "teacher_distance_mean": 0.8437394976615906, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.002491554943844676, "weighted_relation_loss": 0.002491554943844676 }, { "action_query_batch_std": 21.817827415466308, "action_query_norm": 935.0105651855469, "action_relation_loss": 0.0024842118844389917, "auxiliary_loss_weight": 1.0, "epoch": 16.407857811038355, "flow_matching_loss": 0.022983921132981776, "grad_norm": 0.1129583939909935, "invalid_tail_samples": 25.1, "learning_rate": 4.020359357660566e-05, "loss": 0.0255, "positive_teacher_pairs": 26552.7, "relation_loss": 0.0024842118844389917, "selected_pairs": 26552.7, "step": 17540, "student_distance_mean": 1251.5726196289063, "teacher_distance_mean": 0.8488347232341766, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0024842118844389917, "weighted_relation_loss": 0.0024842118844389917 }, { "action_query_batch_std": 21.968123626708984, "action_query_norm": 944.0734191894531, "action_relation_loss": 0.0024463665671646596, "auxiliary_loss_weight": 1.0, "epoch": 16.417212347988773, "flow_matching_loss": 0.025232215970754625, "grad_norm": 0.10950496792793274, "invalid_tail_samples": 22.5, "learning_rate": 4.014955211623875e-05, "loss": 0.0277, "positive_teacher_pairs": 27151.7, "relation_loss": 0.0024463665671646596, "selected_pairs": 27151.7, "step": 17550, "student_distance_mean": 1256.7534423828124, "teacher_distance_mean": 0.8491820096969604, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0024463665671646596, "weighted_relation_loss": 0.0024463665671646596 }, { "action_query_batch_std": 22.160049629211425, "action_query_norm": 947.8012084960938, "action_relation_loss": 0.0024222480831667783, "auxiliary_loss_weight": 1.0, "epoch": 16.426566884939195, "flow_matching_loss": 0.02310684770345688, "grad_norm": 0.11264932155609131, "invalid_tail_samples": 23.3, "learning_rate": 4.0095522625094895e-05, "loss": 0.0255, "positive_teacher_pairs": 26967.4, "relation_loss": 0.0024222480831667783, "selected_pairs": 26967.4, "step": 17560, "student_distance_mean": 1278.9063720703125, "teacher_distance_mean": 0.8689408242702484, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0024222480831667783, "weighted_relation_loss": 0.0024222480831667783 }, { "action_query_batch_std": 22.103120613098145, "action_query_norm": 945.4072570800781, "action_relation_loss": 0.002410384104587138, "auxiliary_loss_weight": 1.0, "epoch": 16.435921421889617, "flow_matching_loss": 0.025054928660392762, "grad_norm": 0.11857779324054718, "invalid_tail_samples": 24.3, "learning_rate": 4.004150516882497e-05, "loss": 0.0275, "positive_teacher_pairs": 26732.0, "relation_loss": 0.002410384104587138, "selected_pairs": 26732.0, "step": 17570, "student_distance_mean": 1269.4900756835937, "teacher_distance_mean": 0.8614676773548127, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.002410384104587138, "weighted_relation_loss": 0.002410384104587138 }, { "action_query_batch_std": 22.100795173645018, "action_query_norm": 949.5177856445313, "action_relation_loss": 0.0024356119800359012, "auxiliary_loss_weight": 1.0, "epoch": 16.44527595884004, "flow_matching_loss": 0.02569339331239462, "grad_norm": 0.11943643540143967, "invalid_tail_samples": 23.5, "learning_rate": 3.99874998130653e-05, "loss": 0.0281, "positive_teacher_pairs": 26926.2, "relation_loss": 0.0024356119800359012, "selected_pairs": 26926.2, "step": 17580, "student_distance_mean": 1271.3787475585937, "teacher_distance_mean": 0.8564611375331879, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0024356119800359012, "weighted_relation_loss": 0.0024356119800359012 }, { "action_query_batch_std": 22.18111629486084, "action_query_norm": 947.4678405761719, "action_relation_loss": 0.00244075539521873, "auxiliary_loss_weight": 1.0, "epoch": 16.454630495790457, "flow_matching_loss": 0.024876822717487812, "grad_norm": 0.1152866929769516, "invalid_tail_samples": 22.9, "learning_rate": 3.9933506623437455e-05, "loss": 0.0273, "positive_teacher_pairs": 27055.6, "relation_loss": 0.00244075539521873, "selected_pairs": 27055.6, "step": 17590, "student_distance_mean": 1266.6558227539062, "teacher_distance_mean": 0.8524772465229035, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.00244075539521873, "weighted_relation_loss": 0.00244075539521873 }, { "action_query_batch_std": 22.067501068115234, "action_query_norm": 941.2795959472656, "action_relation_loss": 0.0023302980931475758, "auxiliary_loss_weight": 1.0, "epoch": 16.46398503274088, "flow_matching_loss": 0.02414208874106407, "grad_norm": 0.09353399276733398, "invalid_tail_samples": 27.4, "learning_rate": 3.9879525665548276e-05, "loss": 0.0265, "positive_teacher_pairs": 26026.3, "relation_loss": 0.0023302980931475758, "selected_pairs": 26026.3, "step": 17600, "student_distance_mean": 1269.8048706054688, "teacher_distance_mean": 0.859050965309143, "valid_action_samples": 228.6, "weighted_auxiliary_loss": 0.0023302980931475758, "weighted_relation_loss": 0.0023302980931475758 }, { "action_query_batch_std": 22.085656356811523, "action_query_norm": 944.7994079589844, "action_relation_loss": 0.002342024678364396, "auxiliary_loss_weight": 1.0, "epoch": 16.4733395696913, "flow_matching_loss": 0.024632397666573526, "grad_norm": 0.08987748622894287, "invalid_tail_samples": 22.5, "learning_rate": 3.9825557004989704e-05, "loss": 0.027, "positive_teacher_pairs": 27162.2, "relation_loss": 0.002342024678364396, "selected_pairs": 27162.2, "step": 17610, "student_distance_mean": 1266.4453491210938, "teacher_distance_mean": 0.857507973909378, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.002342024678364396, "weighted_relation_loss": 0.002342024678364396 }, { "action_query_batch_std": 22.384262084960938, "action_query_norm": 955.5268981933593, "action_relation_loss": 0.0024516447680070995, "auxiliary_loss_weight": 1.0, "epoch": 16.48269410664172, "flow_matching_loss": 0.024792665988206862, "grad_norm": 0.09253954142332077, "invalid_tail_samples": 23.4, "learning_rate": 3.977160070733877e-05, "loss": 0.0272, "positive_teacher_pairs": 26940.3, "relation_loss": 0.0024516447680070995, "selected_pairs": 26940.3, "step": 17620, "student_distance_mean": 1282.3978759765625, "teacher_distance_mean": 0.8682787239551544, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0024516447680070995, "weighted_relation_loss": 0.0024516447680070995 }, { "action_query_batch_std": 22.398000526428223, "action_query_norm": 955.986865234375, "action_relation_loss": 0.0023918062215670943, "auxiliary_loss_weight": 1.0, "epoch": 16.492048643592142, "flow_matching_loss": 0.02625927496701479, "grad_norm": 0.1081836074590683, "invalid_tail_samples": 21.1, "learning_rate": 3.971765683815746e-05, "loss": 0.0287, "positive_teacher_pairs": 27475.4, "relation_loss": 0.0023918062215670943, "selected_pairs": 27475.4, "step": 17630, "student_distance_mean": 1286.9686279296875, "teacher_distance_mean": 0.8706569969654083, "valid_action_samples": 234.9, "weighted_auxiliary_loss": 0.0023918062215670943, "weighted_relation_loss": 0.0023918062215670943 }, { "action_query_batch_std": 21.91137752532959, "action_query_norm": 938.2145202636718, "action_relation_loss": 0.002474389155395329, "auxiliary_loss_weight": 1.0, "epoch": 16.501403180542564, "flow_matching_loss": 0.024346221424639224, "grad_norm": 0.09980814903974533, "invalid_tail_samples": 24.0, "learning_rate": 3.966372546299265e-05, "loss": 0.0268, "positive_teacher_pairs": 26815.7, "relation_loss": 0.002474389155395329, "selected_pairs": 26815.7, "step": 17640, "student_distance_mean": 1249.527734375, "teacher_distance_mean": 0.8479695558547974, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.002474389155395329, "weighted_relation_loss": 0.002474389155395329 }, { "action_query_batch_std": 21.918039512634277, "action_query_norm": 939.2920288085937, "action_relation_loss": 0.0023540942929685116, "auxiliary_loss_weight": 1.0, "epoch": 16.510757717492986, "flow_matching_loss": 0.023691220209002495, "grad_norm": 0.0806371346116066, "invalid_tail_samples": 24.6, "learning_rate": 3.960980664737604e-05, "loss": 0.026, "positive_teacher_pairs": 26658.6, "relation_loss": 0.0023540942929685116, "selected_pairs": 26658.6, "step": 17650, "student_distance_mean": 1254.9824340820312, "teacher_distance_mean": 0.8497118353843689, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0023540942929685116, "weighted_relation_loss": 0.0023540942929685116 }, { "action_query_batch_std": 22.07675704956055, "action_query_norm": 946.9495910644531, "action_relation_loss": 0.002432984160259366, "auxiliary_loss_weight": 1.0, "epoch": 16.520112254443404, "flow_matching_loss": 0.024824129603803157, "grad_norm": 0.10242965817451477, "invalid_tail_samples": 23.9, "learning_rate": 3.955590045682408e-05, "loss": 0.0273, "positive_teacher_pairs": 26832.6, "relation_loss": 0.002432984160259366, "selected_pairs": 26832.6, "step": 17660, "student_distance_mean": 1264.635888671875, "teacher_distance_mean": 0.8580476880073548, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.002432984160259366, "weighted_relation_loss": 0.002432984160259366 }, { "action_query_batch_std": 22.266615295410155, "action_query_norm": 949.5333923339844, "action_relation_loss": 0.002551472163759172, "auxiliary_loss_weight": 1.0, "epoch": 16.529466791393826, "flow_matching_loss": 0.023905028030276297, "grad_norm": 0.10667552798986435, "invalid_tail_samples": 22.3, "learning_rate": 3.950200695683788e-05, "loss": 0.0265, "positive_teacher_pairs": 27194.1, "relation_loss": 0.002551472163759172, "selected_pairs": 27194.1, "step": 17670, "student_distance_mean": 1273.70517578125, "teacher_distance_mean": 0.861275565624237, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.002551472163759172, "weighted_relation_loss": 0.002551472163759172 }, { "action_query_batch_std": 21.855059814453124, "action_query_norm": 934.8201782226563, "action_relation_loss": 0.0023467909079045056, "auxiliary_loss_weight": 1.0, "epoch": 16.53882132834425, "flow_matching_loss": 0.02375361043959856, "grad_norm": 0.10185526311397552, "invalid_tail_samples": 22.7, "learning_rate": 3.944812621290314e-05, "loss": 0.0261, "positive_teacher_pairs": 27108.0, "relation_loss": 0.0023467909079045056, "selected_pairs": 27108.0, "step": 17680, "student_distance_mean": 1252.1966064453125, "teacher_distance_mean": 0.8533590197563171, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0023467909079045056, "weighted_relation_loss": 0.0023467909079045056 }, { "action_query_batch_std": 21.9773042678833, "action_query_norm": 938.8286437988281, "action_relation_loss": 0.002402472379617393, "auxiliary_loss_weight": 1.0, "epoch": 16.548175865294667, "flow_matching_loss": 0.02457477692514658, "grad_norm": 0.13065309822559357, "invalid_tail_samples": 21.7, "learning_rate": 3.939425829049002e-05, "loss": 0.027, "positive_teacher_pairs": 27337.5, "relation_loss": 0.002402472379617393, "selected_pairs": 27337.5, "step": 17690, "student_distance_mean": 1255.4489868164062, "teacher_distance_mean": 0.852530962228775, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.002402472379617393, "weighted_relation_loss": 0.002402472379617393 }, { "action_query_batch_std": 22.217499351501466, "action_query_norm": 948.5993286132813, "action_relation_loss": 0.0023982745828107, "auxiliary_loss_weight": 1.0, "epoch": 16.55753040224509, "flow_matching_loss": 0.024795207753777505, "grad_norm": 0.12272525578737259, "invalid_tail_samples": 25.5, "learning_rate": 3.9340403255053135e-05, "loss": 0.0272, "positive_teacher_pairs": 26460.6, "relation_loss": 0.0023982745828107, "selected_pairs": 26460.6, "step": 17700, "student_distance_mean": 1272.1789672851562, "teacher_distance_mean": 0.8591692566871643, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0023982745828107, "weighted_relation_loss": 0.0023982745828107 }, { "action_query_batch_std": 22.110966873168945, "action_query_norm": 946.2356262207031, "action_relation_loss": 0.0024684331845492126, "auxiliary_loss_weight": 1.0, "epoch": 16.56688493919551, "flow_matching_loss": 0.023186959326267242, "grad_norm": 0.09977080672979355, "invalid_tail_samples": 23.3, "learning_rate": 3.9286561172031407e-05, "loss": 0.0257, "positive_teacher_pairs": 26971.5, "relation_loss": 0.0024684331845492126, "selected_pairs": 26971.5, "step": 17710, "student_distance_mean": 1266.4965209960938, "teacher_distance_mean": 0.8551708638668061, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0024684331845492126, "weighted_relation_loss": 0.0024684331845492126 }, { "action_query_batch_std": 21.57770347595215, "action_query_norm": 927.2661682128906, "action_relation_loss": 0.0024057944072410466, "auxiliary_loss_weight": 1.0, "epoch": 16.57623947614593, "flow_matching_loss": 0.024756352044641973, "grad_norm": 0.13143934309482574, "invalid_tail_samples": 24.2, "learning_rate": 3.923273210684809e-05, "loss": 0.0272, "positive_teacher_pairs": 26762.8, "relation_loss": 0.0024057944072410466, "selected_pairs": 26762.8, "step": 17720, "student_distance_mean": 1240.1035400390624, "teacher_distance_mean": 0.8409530520439148, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0024057944072410466, "weighted_relation_loss": 0.0024057944072410466 }, { "action_query_batch_std": 21.958175468444825, "action_query_norm": 937.2106689453125, "action_relation_loss": 0.0024246023036539554, "auxiliary_loss_weight": 1.0, "epoch": 16.58559401309635, "flow_matching_loss": 0.023917152360081673, "grad_norm": 0.0884137749671936, "invalid_tail_samples": 25.1, "learning_rate": 3.9178916124910555e-05, "loss": 0.0263, "positive_teacher_pairs": 26547.8, "relation_loss": 0.0024246023036539554, "selected_pairs": 26547.8, "step": 17730, "student_distance_mean": 1256.760009765625, "teacher_distance_mean": 0.8509639143943787, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0024246023036539554, "weighted_relation_loss": 0.0024246023036539554 }, { "action_query_batch_std": 22.19768867492676, "action_query_norm": 951.1865356445312, "action_relation_loss": 0.002418238646350801, "auxiliary_loss_weight": 1.0, "epoch": 16.594948550046773, "flow_matching_loss": 0.024134644120931626, "grad_norm": 0.10137853026390076, "invalid_tail_samples": 22.1, "learning_rate": 3.9125113291610274e-05, "loss": 0.0266, "positive_teacher_pairs": 27244.7, "relation_loss": 0.002418238646350801, "selected_pairs": 27244.7, "step": 17740, "student_distance_mean": 1275.1559448242188, "teacher_distance_mean": 0.8592665255069732, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.002418238646350801, "weighted_relation_loss": 0.002418238646350801 }, { "action_query_batch_std": 22.18062801361084, "action_query_norm": 947.3184509277344, "action_relation_loss": 0.0024820993887260554, "auxiliary_loss_weight": 1.0, "epoch": 16.604303086997195, "flow_matching_loss": 0.024469625018537045, "grad_norm": 0.11547047644853592, "invalid_tail_samples": 24.3, "learning_rate": 3.907132367232278e-05, "loss": 0.027, "positive_teacher_pairs": 26736.8, "relation_loss": 0.0024820993887260554, "selected_pairs": 26736.8, "step": 17750, "student_distance_mean": 1273.411328125, "teacher_distance_mean": 0.855676805973053, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0024820993887260554, "weighted_relation_loss": 0.0024820993887260554 }, { "action_query_batch_std": 22.17027645111084, "action_query_norm": 946.8494323730469, "action_relation_loss": 0.0024595872964709997, "auxiliary_loss_weight": 1.0, "epoch": 16.613657623947613, "flow_matching_loss": 0.024940937384963037, "grad_norm": 0.1122346892952919, "invalid_tail_samples": 24.8, "learning_rate": 3.901754733240752e-05, "loss": 0.0274, "positive_teacher_pairs": 26618.2, "relation_loss": 0.0024595872964709997, "selected_pairs": 26618.2, "step": 17760, "student_distance_mean": 1266.39296875, "teacher_distance_mean": 0.8492497026920318, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0024595872964709997, "weighted_relation_loss": 0.0024595872964709997 }, { "action_query_batch_std": 22.14741039276123, "action_query_norm": 948.8513549804687, "action_relation_loss": 0.0025029970100149514, "auxiliary_loss_weight": 1.0, "epoch": 16.623012160898035, "flow_matching_loss": 0.02385539785027504, "grad_norm": 0.08539649099111557, "invalid_tail_samples": 24.7, "learning_rate": 3.896378433720785e-05, "loss": 0.0264, "positive_teacher_pairs": 26640.1, "relation_loss": 0.0025029970100149514, "selected_pairs": 26640.1, "step": 17770, "student_distance_mean": 1266.718359375, "teacher_distance_mean": 0.8544222950935364, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0025029970100149514, "weighted_relation_loss": 0.0025029970100149514 }, { "action_query_batch_std": 21.88341236114502, "action_query_norm": 938.6199401855469, "action_relation_loss": 0.0025250261649489405, "auxiliary_loss_weight": 1.0, "epoch": 16.632366697848457, "flow_matching_loss": 0.023916765488684176, "grad_norm": 0.11090555042028427, "invalid_tail_samples": 22.8, "learning_rate": 3.891003475205086e-05, "loss": 0.0264, "positive_teacher_pairs": 27084.0, "relation_loss": 0.0025250261649489405, "selected_pairs": 27084.0, "step": 17780, "student_distance_mean": 1257.3415161132812, "teacher_distance_mean": 0.8513096988201141, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0025250261649489405, "weighted_relation_loss": 0.0025250261649489405 }, { "action_query_batch_std": 22.099228858947754, "action_query_norm": 947.1332824707031, "action_relation_loss": 0.0025139665231108665, "auxiliary_loss_weight": 1.0, "epoch": 16.641721234798876, "flow_matching_loss": 0.026338422484695912, "grad_norm": 0.0880904570221901, "invalid_tail_samples": 23.6, "learning_rate": 3.885629864224736e-05, "loss": 0.0289, "positive_teacher_pairs": 26903.4, "relation_loss": 0.0025139665231108665, "selected_pairs": 26903.4, "step": 17790, "student_distance_mean": 1261.2152954101562, "teacher_distance_mean": 0.8515890419483185, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0025139665231108665, "weighted_relation_loss": 0.0025139665231108665 }, { "action_query_batch_std": 22.352074432373048, "action_query_norm": 951.5153442382813, "action_relation_loss": 0.002505137771368027, "auxiliary_loss_weight": 1.0, "epoch": 16.651075771749298, "flow_matching_loss": 0.02477456945925951, "grad_norm": 0.11787330359220505, "invalid_tail_samples": 23.7, "learning_rate": 3.880257607309178e-05, "loss": 0.0273, "positive_teacher_pairs": 26876.4, "relation_loss": 0.002505137771368027, "selected_pairs": 26876.4, "step": 17800, "student_distance_mean": 1282.4467529296876, "teacher_distance_mean": 0.8674292385578155, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.002505137771368027, "weighted_relation_loss": 0.002505137771368027 }, { "action_query_batch_std": 22.03403377532959, "action_query_norm": 945.2716003417969, "action_relation_loss": 0.0023756832350045444, "auxiliary_loss_weight": 1.0, "epoch": 16.66043030869972, "flow_matching_loss": 0.024664939567446708, "grad_norm": 0.0865754783153534, "invalid_tail_samples": 22.5, "learning_rate": 3.874886710986213e-05, "loss": 0.027, "positive_teacher_pairs": 27157.5, "relation_loss": 0.0023756832350045444, "selected_pairs": 27157.5, "step": 17810, "student_distance_mean": 1262.4401733398438, "teacher_distance_mean": 0.8526267766952514, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0023756832350045444, "weighted_relation_loss": 0.0023756832350045444 }, { "action_query_batch_std": 22.201369094848634, "action_query_norm": 948.3602722167968, "action_relation_loss": 0.0024226100649684668, "auxiliary_loss_weight": 1.0, "epoch": 16.669784845650142, "flow_matching_loss": 0.024634199775755407, "grad_norm": 0.09325557947158813, "invalid_tail_samples": 23.3, "learning_rate": 3.8695171817819834e-05, "loss": 0.0271, "positive_teacher_pairs": 26962.6, "relation_loss": 0.0024226100649684668, "selected_pairs": 26962.6, "step": 17820, "student_distance_mean": 1274.2389770507812, "teacher_distance_mean": 0.8608235418796539, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0024226100649684668, "weighted_relation_loss": 0.0024226100649684668 }, { "action_query_batch_std": 22.01947078704834, "action_query_norm": 942.5678649902344, "action_relation_loss": 0.002385824732482433, "auxiliary_loss_weight": 1.0, "epoch": 16.67913938260056, "flow_matching_loss": 0.02338341474533081, "grad_norm": 0.0905681848526001, "invalid_tail_samples": 24.4, "learning_rate": 3.8641490262209774e-05, "loss": 0.0258, "positive_teacher_pairs": 26708.2, "relation_loss": 0.002385824732482433, "selected_pairs": 26708.2, "step": 17830, "student_distance_mean": 1260.9166381835937, "teacher_distance_mean": 0.8512551367282868, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.002385824732482433, "weighted_relation_loss": 0.002385824732482433 }, { "action_query_batch_std": 21.927360153198244, "action_query_norm": 937.5495239257813, "action_relation_loss": 0.0023998008109629154, "auxiliary_loss_weight": 1.0, "epoch": 16.688493919550982, "flow_matching_loss": 0.023178152553737164, "grad_norm": 0.08811626583337784, "invalid_tail_samples": 23.6, "learning_rate": 3.8587822508260084e-05, "loss": 0.0256, "positive_teacher_pairs": 26896.2, "relation_loss": 0.0023998008109629154, "selected_pairs": 26896.2, "step": 17840, "student_distance_mean": 1254.8092041015625, "teacher_distance_mean": 0.8506120026111603, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0023998008109629154, "weighted_relation_loss": 0.0023998008109629154 }, { "action_query_batch_std": 21.688500213623048, "action_query_norm": 930.2519775390625, "action_relation_loss": 0.0024779797997325657, "auxiliary_loss_weight": 1.0, "epoch": 16.697848456501404, "flow_matching_loss": 0.02325682304799557, "grad_norm": 0.0863918587565422, "invalid_tail_samples": 25.0, "learning_rate": 3.853416862118214e-05, "loss": 0.0257, "positive_teacher_pairs": 26569.2, "relation_loss": 0.0024779797997325657, "selected_pairs": 26569.2, "step": 17850, "student_distance_mean": 1240.160693359375, "teacher_distance_mean": 0.8406519770622254, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0024779797997325657, "weighted_relation_loss": 0.0024779797997325657 }, { "action_query_batch_std": 21.800303649902343, "action_query_norm": 935.7712097167969, "action_relation_loss": 0.0024106027092784645, "auxiliary_loss_weight": 1.0, "epoch": 16.707202993451823, "flow_matching_loss": 0.024634732119739055, "grad_norm": 0.0944509506225586, "invalid_tail_samples": 24.5, "learning_rate": 3.848052866617049e-05, "loss": 0.027, "positive_teacher_pairs": 26688.0, "relation_loss": 0.0024106027092784645, "selected_pairs": 26688.0, "step": 17860, "student_distance_mean": 1251.4094604492188, "teacher_distance_mean": 0.8482271313667298, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0024106027092784645, "weighted_relation_loss": 0.0024106027092784645 }, { "action_query_batch_std": 22.049091339111328, "action_query_norm": 944.712353515625, "action_relation_loss": 0.002413874305784702, "auxiliary_loss_weight": 1.0, "epoch": 16.716557530402245, "flow_matching_loss": 0.02523999959230423, "grad_norm": 0.08784075826406479, "invalid_tail_samples": 22.6, "learning_rate": 3.84269027084027e-05, "loss": 0.0277, "positive_teacher_pairs": 27124.5, "relation_loss": 0.002413874305784702, "selected_pairs": 27124.5, "step": 17870, "student_distance_mean": 1268.5380859375, "teacher_distance_mean": 0.8563400566577911, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.002413874305784702, "weighted_relation_loss": 0.002413874305784702 }, { "action_query_batch_std": 21.945941543579103, "action_query_norm": 937.3025146484375, "action_relation_loss": 0.0024705320363864304, "auxiliary_loss_weight": 1.0, "epoch": 16.725912067352667, "flow_matching_loss": 0.024149120785295963, "grad_norm": 0.08521069586277008, "invalid_tail_samples": 26.8, "learning_rate": 3.83732908130394e-05, "loss": 0.0266, "positive_teacher_pairs": 26163.1, "relation_loss": 0.0024705320363864304, "selected_pairs": 26163.1, "step": 17880, "student_distance_mean": 1257.3701538085938, "teacher_distance_mean": 0.852934592962265, "valid_action_samples": 229.2, "weighted_auxiliary_loss": 0.0024705320363864304, "weighted_relation_loss": 0.0024705320363864304 }, { "action_query_batch_std": 22.305284690856933, "action_query_norm": 951.8530334472656, "action_relation_loss": 0.0024000104051083325, "auxiliary_loss_weight": 1.0, "epoch": 16.73526660430309, "flow_matching_loss": 0.0245771873742342, "grad_norm": 0.10095299780368805, "invalid_tail_samples": 22.6, "learning_rate": 3.831969304522409e-05, "loss": 0.027, "positive_teacher_pairs": 27135.7, "relation_loss": 0.0024000104051083325, "selected_pairs": 27135.7, "step": 17890, "student_distance_mean": 1277.7112426757812, "teacher_distance_mean": 0.8601294696331024, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0024000104051083325, "weighted_relation_loss": 0.0024000104051083325 }, { "action_query_batch_std": 22.344320869445802, "action_query_norm": 953.0181091308593, "action_relation_loss": 0.002488658926449716, "auxiliary_loss_weight": 1.0, "epoch": 16.744621141253507, "flow_matching_loss": 0.024100453965365885, "grad_norm": 0.09111255407333374, "invalid_tail_samples": 24.0, "learning_rate": 3.826610947008312e-05, "loss": 0.0266, "positive_teacher_pairs": 26800.8, "relation_loss": 0.002488658926449716, "selected_pairs": 26800.8, "step": 17900, "student_distance_mean": 1276.564404296875, "teacher_distance_mean": 0.8561338603496551, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.002488658926449716, "weighted_relation_loss": 0.002488658926449716 }, { "action_query_batch_std": 21.964001274108888, "action_query_norm": 941.5561279296875, "action_relation_loss": 0.0023929402465000748, "auxiliary_loss_weight": 1.0, "epoch": 16.75397567820393, "flow_matching_loss": 0.024059299007058145, "grad_norm": 0.11840159446001053, "invalid_tail_samples": 21.5, "learning_rate": 3.821254015272559e-05, "loss": 0.0265, "positive_teacher_pairs": 27391.1, "relation_loss": 0.0023929402465000748, "selected_pairs": 27391.1, "step": 17910, "student_distance_mean": 1258.6999389648438, "teacher_distance_mean": 0.8473030984401703, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.0023929402465000748, "weighted_relation_loss": 0.0023929402465000748 }, { "action_query_batch_std": 22.024653434753418, "action_query_norm": 942.1254455566407, "action_relation_loss": 0.0025394946802407502, "auxiliary_loss_weight": 1.0, "epoch": 16.76333021515435, "flow_matching_loss": 0.022845392860472203, "grad_norm": 0.10888786613941193, "invalid_tail_samples": 22.7, "learning_rate": 3.8158985158243214e-05, "loss": 0.0254, "positive_teacher_pairs": 27115.2, "relation_loss": 0.0025394946802407502, "selected_pairs": 27115.2, "step": 17920, "student_distance_mean": 1259.851123046875, "teacher_distance_mean": 0.8513485372066498, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0025394946802407502, "weighted_relation_loss": 0.0025394946802407502 }, { "action_query_batch_std": 21.901148796081543, "action_query_norm": 938.4832458496094, "action_relation_loss": 0.0024210985749959944, "auxiliary_loss_weight": 1.0, "epoch": 16.77268475210477, "flow_matching_loss": 0.02497209757566452, "grad_norm": 0.11900024861097336, "invalid_tail_samples": 23.6, "learning_rate": 3.810544455171044e-05, "loss": 0.0274, "positive_teacher_pairs": 26901.2, "relation_loss": 0.0024210985749959944, "selected_pairs": 26901.2, "step": 17930, "student_distance_mean": 1261.0130737304687, "teacher_distance_mean": 0.8522762060165405, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0024210985749959944, "weighted_relation_loss": 0.0024210985749959944 }, { "action_query_batch_std": 22.14995403289795, "action_query_norm": 943.4792175292969, "action_relation_loss": 0.0024480462074279786, "auxiliary_loss_weight": 1.0, "epoch": 16.78203928905519, "flow_matching_loss": 0.024058560468256475, "grad_norm": 0.09032439440488815, "invalid_tail_samples": 24.6, "learning_rate": 3.8051918398184114e-05, "loss": 0.0265, "positive_teacher_pairs": 26666.4, "relation_loss": 0.0024480462074279786, "selected_pairs": 26666.4, "step": 17940, "student_distance_mean": 1268.7314453125, "teacher_distance_mean": 0.85942223072052, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0024480462074279786, "weighted_relation_loss": 0.0024480462074279786 }, { "action_query_batch_std": 21.91669578552246, "action_query_norm": 934.544677734375, "action_relation_loss": 0.002363590337336063, "auxiliary_loss_weight": 1.0, "epoch": 16.791393826005613, "flow_matching_loss": 0.023923350870609282, "grad_norm": 0.11189639568328857, "invalid_tail_samples": 23.5, "learning_rate": 3.799840676270356e-05, "loss": 0.0263, "positive_teacher_pairs": 26915.6, "relation_loss": 0.002363590337336063, "selected_pairs": 26915.6, "step": 17950, "student_distance_mean": 1259.0042358398437, "teacher_distance_mean": 0.8521566092967987, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.002363590337336063, "weighted_relation_loss": 0.002363590337336063 }, { "action_query_batch_std": 22.107178115844725, "action_query_norm": 942.4824890136719, "action_relation_loss": 0.002445885166525841, "auxiliary_loss_weight": 1.0, "epoch": 16.800748362956035, "flow_matching_loss": 0.022788561508059503, "grad_norm": 0.11533568799495697, "invalid_tail_samples": 24.4, "learning_rate": 3.794490971029048e-05, "loss": 0.0252, "positive_teacher_pairs": 26718.6, "relation_loss": 0.002445885166525841, "selected_pairs": 26718.6, "step": 17960, "student_distance_mean": 1267.3621704101563, "teacher_distance_mean": 0.8551423490047455, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.002445885166525841, "weighted_relation_loss": 0.002445885166525841 }, { "action_query_batch_std": 22.142399787902832, "action_query_norm": 944.0640258789062, "action_relation_loss": 0.002431097929365933, "auxiliary_loss_weight": 1.0, "epoch": 16.810102899906454, "flow_matching_loss": 0.022464248538017272, "grad_norm": 0.0980461984872818, "invalid_tail_samples": 22.7, "learning_rate": 3.789142730594881e-05, "loss": 0.0249, "positive_teacher_pairs": 27102.6, "relation_loss": 0.002431097929365933, "selected_pairs": 27102.6, "step": 17970, "student_distance_mean": 1268.827294921875, "teacher_distance_mean": 0.8575285196304321, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.002431097929365933, "weighted_relation_loss": 0.002431097929365933 }, { "action_query_batch_std": 22.2233455657959, "action_query_norm": 946.7245239257812, "action_relation_loss": 0.0025453567737713455, "auxiliary_loss_weight": 1.0, "epoch": 16.819457436856876, "flow_matching_loss": 0.024763483367860318, "grad_norm": 0.09090299904346466, "invalid_tail_samples": 22.8, "learning_rate": 3.783795961466471e-05, "loss": 0.0273, "positive_teacher_pairs": 27081.8, "relation_loss": 0.0025453567737713455, "selected_pairs": 27081.8, "step": 17980, "student_distance_mean": 1267.8630126953126, "teacher_distance_mean": 0.8577366948127747, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0025453567737713455, "weighted_relation_loss": 0.0025453567737713455 }, { "action_query_batch_std": 22.262544250488283, "action_query_norm": 951.4274047851562, "action_relation_loss": 0.002340290043503046, "auxiliary_loss_weight": 1.0, "epoch": 16.828811973807298, "flow_matching_loss": 0.023346836864948272, "grad_norm": 0.11498969793319702, "invalid_tail_samples": 22.9, "learning_rate": 3.778450670140651e-05, "loss": 0.0257, "positive_teacher_pairs": 27055.1, "relation_loss": 0.002340290043503046, "selected_pairs": 27055.1, "step": 17990, "student_distance_mean": 1274.3629638671875, "teacher_distance_mean": 0.8596073925495148, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.002340290043503046, "weighted_relation_loss": 0.002340290043503046 }, { "action_query_batch_std": 22.292463874816896, "action_query_norm": 950.9665588378906, "action_relation_loss": 0.0023436603136360646, "auxiliary_loss_weight": 1.0, "epoch": 16.838166510757716, "flow_matching_loss": 0.02249158676713705, "grad_norm": 0.09061736613512039, "invalid_tail_samples": 25.9, "learning_rate": 3.773106863112451e-05, "loss": 0.0248, "positive_teacher_pairs": 26365.2, "relation_loss": 0.0023436603136360646, "selected_pairs": 26365.2, "step": 18000, "student_distance_mean": 1277.571484375, "teacher_distance_mean": 0.8596365213394165, "valid_action_samples": 230.1, "weighted_auxiliary_loss": 0.0023436603136360646, "weighted_relation_loss": 0.0023436603136360646 }, { "action_query_batch_std": 21.972507095336915, "action_query_norm": 938.1348388671875, "action_relation_loss": 0.002507078438065946, "auxiliary_loss_weight": 1.0, "epoch": 16.84752104770814, "flow_matching_loss": 0.025623244047164918, "grad_norm": 0.12377621233463287, "invalid_tail_samples": 23.0, "learning_rate": 3.7677645468751e-05, "loss": 0.0281, "positive_teacher_pairs": 27034.3, "relation_loss": 0.002507078438065946, "selected_pairs": 27034.3, "step": 18010, "student_distance_mean": 1258.9068603515625, "teacher_distance_mean": 0.850350534915924, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.002507078438065946, "weighted_relation_loss": 0.002507078438065946 }, { "action_query_batch_std": 22.131423950195312, "action_query_norm": 945.7545837402344, "action_relation_loss": 0.0024051508866250516, "auxiliary_loss_weight": 1.0, "epoch": 16.85687558465856, "flow_matching_loss": 0.026683938689529896, "grad_norm": 0.09614104777574539, "invalid_tail_samples": 23.2, "learning_rate": 3.762423727920018e-05, "loss": 0.0291, "positive_teacher_pairs": 26987.7, "relation_loss": 0.0024051508866250516, "selected_pairs": 26987.7, "step": 18020, "student_distance_mean": 1271.8251098632813, "teacher_distance_mean": 0.8598633885383606, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0024051508866250516, "weighted_relation_loss": 0.0024051508866250516 }, { "action_query_batch_std": 21.923557090759278, "action_query_norm": 938.0943237304688, "action_relation_loss": 0.002427124744281173, "auxiliary_loss_weight": 1.0, "epoch": 16.86623012160898, "flow_matching_loss": 0.02306712567806244, "grad_norm": 0.1318698674440384, "invalid_tail_samples": 26.1, "learning_rate": 3.7570844127367995e-05, "loss": 0.0255, "positive_teacher_pairs": 26320.8, "relation_loss": 0.002427124744281173, "selected_pairs": 26320.8, "step": 18030, "student_distance_mean": 1261.3594116210938, "teacher_distance_mean": 0.8531546771526337, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.002427124744281173, "weighted_relation_loss": 0.002427124744281173 }, { "action_query_batch_std": 21.933415985107423, "action_query_norm": 939.1406860351562, "action_relation_loss": 0.00240433313883841, "auxiliary_loss_weight": 1.0, "epoch": 16.8755846585594, "flow_matching_loss": 0.024456471763551237, "grad_norm": 0.1258288025856018, "invalid_tail_samples": 24.7, "learning_rate": 3.751746607813221e-05, "loss": 0.0269, "positive_teacher_pairs": 26644.7, "relation_loss": 0.00240433313883841, "selected_pairs": 26644.7, "step": 18040, "student_distance_mean": 1259.4258056640624, "teacher_distance_mean": 0.8497032642364502, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.00240433313883841, "weighted_relation_loss": 0.00240433313883841 }, { "action_query_batch_std": 21.74356327056885, "action_query_norm": 932.7916748046875, "action_relation_loss": 0.0024410215672105553, "auxiliary_loss_weight": 1.0, "epoch": 16.884939195509823, "flow_matching_loss": 0.0247909814119339, "grad_norm": 0.10145192593336105, "invalid_tail_samples": 26.9, "learning_rate": 3.746410319635217e-05, "loss": 0.0272, "positive_teacher_pairs": 26136.2, "relation_loss": 0.0024410215672105553, "selected_pairs": 26136.2, "step": 18050, "student_distance_mean": 1250.7594482421875, "teacher_distance_mean": 0.8476254224777222, "valid_action_samples": 229.1, "weighted_auxiliary_loss": 0.0024410215672105553, "weighted_relation_loss": 0.0024410215672105553 }, { "action_query_batch_std": 22.13175411224365, "action_query_norm": 946.1665344238281, "action_relation_loss": 0.002382827247492969, "auxiliary_loss_weight": 1.0, "epoch": 16.894293732460245, "flow_matching_loss": 0.023696778155863286, "grad_norm": 0.12264612317085266, "invalid_tail_samples": 24.6, "learning_rate": 3.7410755546868806e-05, "loss": 0.0261, "positive_teacher_pairs": 26662.5, "relation_loss": 0.002382827247492969, "selected_pairs": 26662.5, "step": 18060, "student_distance_mean": 1269.8876708984376, "teacher_distance_mean": 0.8561741054058075, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.002382827247492969, "weighted_relation_loss": 0.002382827247492969 }, { "action_query_batch_std": 21.997759056091308, "action_query_norm": 943.1994018554688, "action_relation_loss": 0.0024624031502753496, "auxiliary_loss_weight": 1.0, "epoch": 16.903648269410663, "flow_matching_loss": 0.02420632094144821, "grad_norm": 0.11795061081647873, "invalid_tail_samples": 23.5, "learning_rate": 3.735742319450454e-05, "loss": 0.0267, "positive_teacher_pairs": 26920.2, "relation_loss": 0.0024624031502753496, "selected_pairs": 26920.2, "step": 18070, "student_distance_mean": 1265.1209594726563, "teacher_distance_mean": 0.8519567549228668, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0024624031502753496, "weighted_relation_loss": 0.0024624031502753496 }, { "action_query_batch_std": 21.993998718261718, "action_query_norm": 940.7468933105469, "action_relation_loss": 0.0023687101202085614, "auxiliary_loss_weight": 1.0, "epoch": 16.913002806361085, "flow_matching_loss": 0.024551412649452688, "grad_norm": 0.0873178169131279, "invalid_tail_samples": 23.6, "learning_rate": 3.7304106204063184e-05, "loss": 0.0269, "positive_teacher_pairs": 26907.8, "relation_loss": 0.0023687101202085614, "selected_pairs": 26907.8, "step": 18080, "student_distance_mean": 1259.553271484375, "teacher_distance_mean": 0.853370064496994, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0023687101202085614, "weighted_relation_loss": 0.0023687101202085614 }, { "action_query_batch_std": 21.825898742675783, "action_query_norm": 933.5186828613281, "action_relation_loss": 0.0024207595735788344, "auxiliary_loss_weight": 1.0, "epoch": 16.922357343311507, "flow_matching_loss": 0.024413090944290162, "grad_norm": 0.10241249203681946, "invalid_tail_samples": 21.8, "learning_rate": 3.725080464032996e-05, "loss": 0.0268, "positive_teacher_pairs": 27315.1, "relation_loss": 0.0024207595735788344, "selected_pairs": 27315.1, "step": 18090, "student_distance_mean": 1248.378515625, "teacher_distance_mean": 0.8496035516262055, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.0024207595735788344, "weighted_relation_loss": 0.0024207595735788344 }, { "action_query_batch_std": 21.78958511352539, "action_query_norm": 932.0871826171875, "action_relation_loss": 0.002399345813319087, "auxiliary_loss_weight": 1.0, "epoch": 16.931711880261926, "flow_matching_loss": 0.02346455827355385, "grad_norm": 0.1119963675737381, "invalid_tail_samples": 24.9, "learning_rate": 3.719751856807125e-05, "loss": 0.0259, "positive_teacher_pairs": 26604.6, "relation_loss": 0.002399345813319087, "selected_pairs": 26604.6, "step": 18100, "student_distance_mean": 1242.701513671875, "teacher_distance_mean": 0.8436450481414794, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.002399345813319087, "weighted_relation_loss": 0.002399345813319087 }, { "action_query_batch_std": 21.930124282836914, "action_query_norm": 937.3851379394531, "action_relation_loss": 0.002406960539519787, "auxiliary_loss_weight": 1.0, "epoch": 16.941066417212348, "flow_matching_loss": 0.023556862585246564, "grad_norm": 0.12845997512340546, "invalid_tail_samples": 26.8, "learning_rate": 3.71442480520347e-05, "loss": 0.026, "positive_teacher_pairs": 26166.6, "relation_loss": 0.002406960539519787, "selected_pairs": 26166.6, "step": 18110, "student_distance_mean": 1262.0215698242187, "teacher_distance_mean": 0.855136114358902, "valid_action_samples": 229.2, "weighted_auxiliary_loss": 0.002406960539519787, "weighted_relation_loss": 0.002406960539519787 }, { "action_query_batch_std": 21.970216751098633, "action_query_norm": 940.1822143554688, "action_relation_loss": 0.002532171760685742, "auxiliary_loss_weight": 1.0, "epoch": 16.95042095416277, "flow_matching_loss": 0.026293772272765636, "grad_norm": 0.12202310562133789, "invalid_tail_samples": 24.6, "learning_rate": 3.709099315694897e-05, "loss": 0.0288, "positive_teacher_pairs": 26676.7, "relation_loss": 0.002532171760685742, "selected_pairs": 26676.7, "step": 18120, "student_distance_mean": 1262.14150390625, "teacher_distance_mean": 0.8545642793178558, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.002532171760685742, "weighted_relation_loss": 0.002532171760685742 }, { "action_query_batch_std": 22.16604232788086, "action_query_norm": 946.19599609375, "action_relation_loss": 0.0023538643727079034, "auxiliary_loss_weight": 1.0, "epoch": 16.95977549111319, "flow_matching_loss": 0.02593635693192482, "grad_norm": 0.09954357892274857, "invalid_tail_samples": 25.8, "learning_rate": 3.703775394752378e-05, "loss": 0.0283, "positive_teacher_pairs": 26386.2, "relation_loss": 0.0023538643727079034, "selected_pairs": 26386.2, "step": 18130, "student_distance_mean": 1273.7684204101563, "teacher_distance_mean": 0.8648471117019654, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.0023538643727079034, "weighted_relation_loss": 0.0023538643727079034 }, { "action_query_batch_std": 21.799902534484865, "action_query_norm": 933.9611022949218, "action_relation_loss": 0.002489789156243205, "auxiliary_loss_weight": 1.0, "epoch": 16.96913002806361, "flow_matching_loss": 0.022238739021122455, "grad_norm": 0.10996755212545395, "invalid_tail_samples": 25.1, "learning_rate": 3.698453048844983e-05, "loss": 0.0247, "positive_teacher_pairs": 26548.9, "relation_loss": 0.002489789156243205, "selected_pairs": 26548.9, "step": 18140, "student_distance_mean": 1255.2850952148438, "teacher_distance_mean": 0.8471561431884765, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.002489789156243205, "weighted_relation_loss": 0.002489789156243205 }, { "action_query_batch_std": 22.32123374938965, "action_query_norm": 951.4991271972656, "action_relation_loss": 0.002400895580649376, "auxiliary_loss_weight": 1.0, "epoch": 16.978484565014032, "flow_matching_loss": 0.02464470025151968, "grad_norm": 0.093038409948349, "invalid_tail_samples": 24.8, "learning_rate": 3.693132284439861e-05, "loss": 0.027, "positive_teacher_pairs": 26621.1, "relation_loss": 0.002400895580649376, "selected_pairs": 26621.1, "step": 18150, "student_distance_mean": 1280.0678955078124, "teacher_distance_mean": 0.8641947209835052, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.002400895580649376, "weighted_relation_loss": 0.002400895580649376 }, { "action_query_batch_std": 21.93046646118164, "action_query_norm": 942.008984375, "action_relation_loss": 0.0024972323561087252, "auxiliary_loss_weight": 1.0, "epoch": 16.987839101964454, "flow_matching_loss": 0.024065412394702435, "grad_norm": 0.09263601154088974, "invalid_tail_samples": 23.0, "learning_rate": 3.6878131080022414e-05, "loss": 0.0266, "positive_teacher_pairs": 27038.6, "relation_loss": 0.0024972323561087252, "selected_pairs": 27038.6, "step": 18160, "student_distance_mean": 1256.7162841796876, "teacher_distance_mean": 0.8513702929019928, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0024972323561087252, "weighted_relation_loss": 0.0024972323561087252 }, { "action_query_batch_std": 21.83027763366699, "action_query_norm": 937.14208984375, "action_relation_loss": 0.0024843751220032574, "auxiliary_loss_weight": 1.0, "epoch": 16.997193638914872, "flow_matching_loss": 0.025684784166514874, "grad_norm": 0.10664121061563492, "invalid_tail_samples": 22.5, "learning_rate": 3.682495525995429e-05, "loss": 0.0282, "positive_teacher_pairs": 27161.7, "relation_loss": 0.0024843751220032574, "selected_pairs": 27161.7, "step": 18170, "student_distance_mean": 1254.8345458984375, "teacher_distance_mean": 0.8492787301540374, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0024843751220032574, "weighted_relation_loss": 0.0024843751220032574 }, { "action_query_batch_std": 21.797816848754884, "action_query_norm": 934.7502746582031, "action_relation_loss": 0.0024308994179591537, "auxiliary_loss_weight": 1.0, "epoch": 17.006548175865294, "flow_matching_loss": 0.02549568060785532, "grad_norm": 0.09127624332904816, "invalid_tail_samples": 21.6, "learning_rate": 3.6771795448807846e-05, "loss": 0.0279, "positive_teacher_pairs": 24369.6, "relation_loss": 0.0024308994179591537, "selected_pairs": 24369.6, "step": 18180, "student_distance_mean": 1251.058984375, "teacher_distance_mean": 0.8496906578540802, "valid_action_samples": 214.5, "weighted_auxiliary_loss": 0.0024308994179591537, "weighted_relation_loss": 0.0024308994179591537 }, { "action_query_batch_std": 22.109181213378907, "action_query_norm": 946.50439453125, "action_relation_loss": 0.0023563431575894358, "auxiliary_loss_weight": 1.0, "epoch": 17.015902712815716, "flow_matching_loss": 0.021952995844185353, "grad_norm": 0.0974869579076767, "invalid_tail_samples": 23.1, "learning_rate": 3.671865171117724e-05, "loss": 0.0243, "positive_teacher_pairs": 27020.0, "relation_loss": 0.0023563431575894358, "selected_pairs": 27020.0, "step": 18190, "student_distance_mean": 1269.2939208984376, "teacher_distance_mean": 0.858939653635025, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0023563431575894358, "weighted_relation_loss": 0.0023563431575894358 }, { "action_query_batch_std": 21.887278175354005, "action_query_norm": 939.6433532714843, "action_relation_loss": 0.0023270673118531704, "auxiliary_loss_weight": 1.0, "epoch": 17.02525724976614, "flow_matching_loss": 0.02362983413040638, "grad_norm": 0.08729804307222366, "invalid_tail_samples": 26.3, "learning_rate": 3.666552411163718e-05, "loss": 0.026, "positive_teacher_pairs": 26274.7, "relation_loss": 0.0023270673118531704, "selected_pairs": 26274.7, "step": 18200, "student_distance_mean": 1260.6596923828124, "teacher_distance_mean": 0.8541640400886535, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.0023270673118531704, "weighted_relation_loss": 0.0023270673118531704 }, { "action_query_batch_std": 22.464017486572267, "action_query_norm": 957.0576538085937, "action_relation_loss": 0.002387728914618492, "auxiliary_loss_weight": 1.0, "epoch": 17.034611786716557, "flow_matching_loss": 0.023746778443455695, "grad_norm": 0.10206107795238495, "invalid_tail_samples": 21.2, "learning_rate": 3.661241271474269e-05, "loss": 0.0261, "positive_teacher_pairs": 27469.4, "relation_loss": 0.002387728914618492, "selected_pairs": 27469.4, "step": 18210, "student_distance_mean": 1283.3038696289063, "teacher_distance_mean": 0.872089010477066, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.002387728914618492, "weighted_relation_loss": 0.002387728914618492 }, { "action_query_batch_std": 22.151065254211424, "action_query_norm": 948.0947448730469, "action_relation_loss": 0.002415691199712455, "auxiliary_loss_weight": 1.0, "epoch": 17.04396632366698, "flow_matching_loss": 0.02377883829176426, "grad_norm": 0.09771325439214706, "invalid_tail_samples": 22.3, "learning_rate": 3.6559317585029116e-05, "loss": 0.0262, "positive_teacher_pairs": 27208.8, "relation_loss": 0.002415691199712455, "selected_pairs": 27208.8, "step": 18220, "student_distance_mean": 1272.6925659179688, "teacher_distance_mean": 0.8588692128658295, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.002415691199712455, "weighted_relation_loss": 0.002415691199712455 }, { "action_query_batch_std": 21.933135986328125, "action_query_norm": 941.5944458007813, "action_relation_loss": 0.0023918256862089037, "auxiliary_loss_weight": 1.0, "epoch": 17.0533208606174, "flow_matching_loss": 0.022868394292891024, "grad_norm": 0.09992489963769913, "invalid_tail_samples": 22.2, "learning_rate": 3.650623878701204e-05, "loss": 0.0253, "positive_teacher_pairs": 27229.6, "relation_loss": 0.0023918256862089037, "selected_pairs": 27229.6, "step": 18230, "student_distance_mean": 1259.7536376953126, "teacher_distance_mean": 0.8506628930568695, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.0023918256862089037, "weighted_relation_loss": 0.0023918256862089037 }, { "action_query_batch_std": 22.17139949798584, "action_query_norm": 946.9725402832031, "action_relation_loss": 0.0023150456370785834, "auxiliary_loss_weight": 1.0, "epoch": 17.06267539756782, "flow_matching_loss": 0.023803634755313396, "grad_norm": 0.09390950202941895, "invalid_tail_samples": 23.4, "learning_rate": 3.645317638518721e-05, "loss": 0.0261, "positive_teacher_pairs": 26947.0, "relation_loss": 0.0023150456370785834, "selected_pairs": 26947.0, "step": 18240, "student_distance_mean": 1267.3494995117187, "teacher_distance_mean": 0.8589485883712769, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0023150456370785834, "weighted_relation_loss": 0.0023150456370785834 }, { "action_query_batch_std": 21.86526165008545, "action_query_norm": 936.7776611328125, "action_relation_loss": 0.002333583601284772, "auxiliary_loss_weight": 1.0, "epoch": 17.07202993451824, "flow_matching_loss": 0.02377657424658537, "grad_norm": 0.09500294923782349, "invalid_tail_samples": 25.3, "learning_rate": 3.640013044403046e-05, "loss": 0.0261, "positive_teacher_pairs": 26506.6, "relation_loss": 0.002333583601284772, "selected_pairs": 26506.6, "step": 18250, "student_distance_mean": 1254.728466796875, "teacher_distance_mean": 0.8517720997333527, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.002333583601284772, "weighted_relation_loss": 0.002333583601284772 }, { "action_query_batch_std": 22.026375579833985, "action_query_norm": 939.6924560546875, "action_relation_loss": 0.0023668547859415413, "auxiliary_loss_weight": 1.0, "epoch": 17.081384471468663, "flow_matching_loss": 0.025138232856988907, "grad_norm": 0.09364434331655502, "invalid_tail_samples": 24.3, "learning_rate": 3.634710102799761e-05, "loss": 0.0275, "positive_teacher_pairs": 26735.2, "relation_loss": 0.0023668547859415413, "selected_pairs": 26735.2, "step": 18260, "student_distance_mean": 1256.745947265625, "teacher_distance_mean": 0.8515469789505005, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0023668547859415413, "weighted_relation_loss": 0.0023668547859415413 }, { "action_query_batch_std": 22.139312934875488, "action_query_norm": 945.7221252441407, "action_relation_loss": 0.0023397850804030896, "auxiliary_loss_weight": 1.0, "epoch": 17.09073900841908, "flow_matching_loss": 0.023419759050011636, "grad_norm": 0.1078215166926384, "invalid_tail_samples": 23.3, "learning_rate": 3.6294088201524394e-05, "loss": 0.0258, "positive_teacher_pairs": 26966.8, "relation_loss": 0.0023397850804030896, "selected_pairs": 26966.8, "step": 18270, "student_distance_mean": 1271.2920288085938, "teacher_distance_mean": 0.8632014870643616, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0023397850804030896, "weighted_relation_loss": 0.0023397850804030896 }, { "action_query_batch_std": 22.147435188293457, "action_query_norm": 942.3561401367188, "action_relation_loss": 0.002326888032257557, "auxiliary_loss_weight": 1.0, "epoch": 17.100093545369504, "flow_matching_loss": 0.02475294694304466, "grad_norm": 0.11073967814445496, "invalid_tail_samples": 24.8, "learning_rate": 3.62410920290264e-05, "loss": 0.0271, "positive_teacher_pairs": 26620.9, "relation_loss": 0.002326888032257557, "selected_pairs": 26620.9, "step": 18280, "student_distance_mean": 1262.4556884765625, "teacher_distance_mean": 0.8540900886058808, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.002326888032257557, "weighted_relation_loss": 0.002326888032257557 }, { "action_query_batch_std": 22.003834533691407, "action_query_norm": 941.5980346679687, "action_relation_loss": 0.0024218050297349692, "auxiliary_loss_weight": 1.0, "epoch": 17.109448082319926, "flow_matching_loss": 0.022913404181599616, "grad_norm": 0.10949966311454773, "invalid_tail_samples": 25.0, "learning_rate": 3.6188112574898954e-05, "loss": 0.0253, "positive_teacher_pairs": 26571.9, "relation_loss": 0.0024218050297349692, "selected_pairs": 26571.9, "step": 18290, "student_distance_mean": 1265.6757934570312, "teacher_distance_mean": 0.8533148527145386, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0024218050297349692, "weighted_relation_loss": 0.0024218050297349692 }, { "action_query_batch_std": 21.772609329223634, "action_query_norm": 933.6008605957031, "action_relation_loss": 0.0023431365611031652, "auxiliary_loss_weight": 1.0, "epoch": 17.118802619270348, "flow_matching_loss": 0.025042376853525637, "grad_norm": 0.10069484263658524, "invalid_tail_samples": 23.8, "learning_rate": 3.6135149903517115e-05, "loss": 0.0274, "positive_teacher_pairs": 26864.4, "relation_loss": 0.0023431365611031652, "selected_pairs": 26864.4, "step": 18300, "student_distance_mean": 1251.1209106445312, "teacher_distance_mean": 0.8460357964038849, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0023431365611031652, "weighted_relation_loss": 0.0023431365611031652 }, { "action_query_batch_std": 22.255063247680663, "action_query_norm": 952.4028381347656, "action_relation_loss": 0.002259349171072245, "auxiliary_loss_weight": 1.0, "epoch": 17.128157156220766, "flow_matching_loss": 0.02522369846701622, "grad_norm": 0.09815022349357605, "invalid_tail_samples": 25.0, "learning_rate": 3.608220407923552e-05, "loss": 0.0275, "positive_teacher_pairs": 26574.4, "relation_loss": 0.002259349171072245, "selected_pairs": 26574.4, "step": 18310, "student_distance_mean": 1279.6436645507813, "teacher_distance_mean": 0.8614311277866363, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.002259349171072245, "weighted_relation_loss": 0.002259349171072245 }, { "action_query_batch_std": 22.315909957885744, "action_query_norm": 951.3742065429688, "action_relation_loss": 0.0022616955917328595, "auxiliary_loss_weight": 1.0, "epoch": 17.137511693171188, "flow_matching_loss": 0.02363023888319731, "grad_norm": 0.1142774149775505, "invalid_tail_samples": 22.1, "learning_rate": 3.602927516638833e-05, "loss": 0.0259, "positive_teacher_pairs": 27247.5, "relation_loss": 0.0022616955917328595, "selected_pairs": 27247.5, "step": 18320, "student_distance_mean": 1276.2263793945312, "teacher_distance_mean": 0.8562282681465149, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0022616955917328595, "weighted_relation_loss": 0.0022616955917328595 }, { "action_query_batch_std": 22.032789993286134, "action_query_norm": 945.25673828125, "action_relation_loss": 0.002432816615328193, "auxiliary_loss_weight": 1.0, "epoch": 17.14686623012161, "flow_matching_loss": 0.021308565512299538, "grad_norm": 0.09489293396472931, "invalid_tail_samples": 23.0, "learning_rate": 3.5976363229289165e-05, "loss": 0.0237, "positive_teacher_pairs": 27034.1, "relation_loss": 0.002432816615328193, "selected_pairs": 27034.1, "step": 18330, "student_distance_mean": 1261.7863891601562, "teacher_distance_mean": 0.8467571496963501, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.002432816615328193, "weighted_relation_loss": 0.002432816615328193 }, { "action_query_batch_std": 22.14179344177246, "action_query_norm": 944.9210266113281, "action_relation_loss": 0.0023644560482352973, "auxiliary_loss_weight": 1.0, "epoch": 17.15622076707203, "flow_matching_loss": 0.023014619201421737, "grad_norm": 0.11020918935537338, "invalid_tail_samples": 23.8, "learning_rate": 3.5923468332231e-05, "loss": 0.0254, "positive_teacher_pairs": 26848.3, "relation_loss": 0.0023644560482352973, "selected_pairs": 26848.3, "step": 18340, "student_distance_mean": 1269.9084228515626, "teacher_distance_mean": 0.8564862966537475, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0023644560482352973, "weighted_relation_loss": 0.0023644560482352973 }, { "action_query_batch_std": 22.11515293121338, "action_query_norm": 946.4276489257812, "action_relation_loss": 0.0023227145662531256, "auxiliary_loss_weight": 1.0, "epoch": 17.16557530402245, "flow_matching_loss": 0.022674586810171603, "grad_norm": 0.08334644138813019, "invalid_tail_samples": 23.1, "learning_rate": 3.587059053948616e-05, "loss": 0.025, "positive_teacher_pairs": 27015.3, "relation_loss": 0.0023227145662531256, "selected_pairs": 27015.3, "step": 18350, "student_distance_mean": 1268.7696411132813, "teacher_distance_mean": 0.8527961492538452, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0023227145662531256, "weighted_relation_loss": 0.0023227145662531256 }, { "action_query_batch_std": 22.246997451782228, "action_query_norm": 950.0352722167969, "action_relation_loss": 0.0023015583865344524, "auxiliary_loss_weight": 1.0, "epoch": 17.174929840972872, "flow_matching_loss": 0.024122610129415988, "grad_norm": 0.09539376199245453, "invalid_tail_samples": 25.0, "learning_rate": 3.5817729915306134e-05, "loss": 0.0264, "positive_teacher_pairs": 26570.7, "relation_loss": 0.0023015583865344524, "selected_pairs": 26570.7, "step": 18360, "student_distance_mean": 1273.5727172851562, "teacher_distance_mean": 0.854728764295578, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0023015583865344524, "weighted_relation_loss": 0.0023015583865344524 }, { "action_query_batch_std": 21.982793617248536, "action_query_norm": 940.565673828125, "action_relation_loss": 0.002373660285957158, "auxiliary_loss_weight": 1.0, "epoch": 17.184284377923294, "flow_matching_loss": 0.021504818089306356, "grad_norm": 0.09375004470348358, "invalid_tail_samples": 24.5, "learning_rate": 3.5764886523921566e-05, "loss": 0.0239, "positive_teacher_pairs": 26692.0, "relation_loss": 0.002373660285957158, "selected_pairs": 26692.0, "step": 18370, "student_distance_mean": 1261.2666015625, "teacher_distance_mean": 0.8485233366489411, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.002373660285957158, "weighted_relation_loss": 0.002373660285957158 }, { "action_query_batch_std": 22.16261577606201, "action_query_norm": 946.693310546875, "action_relation_loss": 0.0022850735345855354, "auxiliary_loss_weight": 1.0, "epoch": 17.193638914873713, "flow_matching_loss": 0.023934068344533443, "grad_norm": 0.11136606335639954, "invalid_tail_samples": 22.9, "learning_rate": 3.571206042954214e-05, "loss": 0.0262, "positive_teacher_pairs": 27058.9, "relation_loss": 0.0022850735345855354, "selected_pairs": 27058.9, "step": 18380, "student_distance_mean": 1274.8205200195312, "teacher_distance_mean": 0.8597762644290924, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0022850735345855354, "weighted_relation_loss": 0.0022850735345855354 }, { "action_query_batch_std": 22.09251766204834, "action_query_norm": 941.6856567382813, "action_relation_loss": 0.002352521102875471, "auxiliary_loss_weight": 1.0, "epoch": 17.202993451824135, "flow_matching_loss": 0.02255125641822815, "grad_norm": 0.1092042624950409, "invalid_tail_samples": 23.5, "learning_rate": 3.5659251696356566e-05, "loss": 0.0249, "positive_teacher_pairs": 26925.7, "relation_loss": 0.002352521102875471, "selected_pairs": 26925.7, "step": 18390, "student_distance_mean": 1264.80302734375, "teacher_distance_mean": 0.852979975938797, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.002352521102875471, "weighted_relation_loss": 0.002352521102875471 }, { "action_query_batch_std": 22.33612995147705, "action_query_norm": 954.882958984375, "action_relation_loss": 0.0022575220791622996, "auxiliary_loss_weight": 1.0, "epoch": 17.212347988774557, "flow_matching_loss": 0.022085832618176936, "grad_norm": 0.09411988407373428, "invalid_tail_samples": 24.0, "learning_rate": 3.56064603885324e-05, "loss": 0.0243, "positive_teacher_pairs": 26805.2, "relation_loss": 0.0022575220791622996, "selected_pairs": 26805.2, "step": 18400, "student_distance_mean": 1285.7052001953125, "teacher_distance_mean": 0.8671962976455688, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0022575220791622996, "weighted_relation_loss": 0.0022575220791622996 }, { "action_query_batch_std": 22.176063346862794, "action_query_norm": 945.6706787109375, "action_relation_loss": 0.0022893335670232775, "auxiliary_loss_weight": 1.0, "epoch": 17.221702525724975, "flow_matching_loss": 0.023128698393702508, "grad_norm": 0.10036202520132065, "invalid_tail_samples": 28.2, "learning_rate": 3.5553686570216115e-05, "loss": 0.0254, "positive_teacher_pairs": 25846.2, "relation_loss": 0.0022893335670232775, "selected_pairs": 25846.2, "step": 18410, "student_distance_mean": 1275.3064208984374, "teacher_distance_mean": 0.8588769912719727, "valid_action_samples": 227.8, "weighted_auxiliary_loss": 0.0022893335670232775, "weighted_relation_loss": 0.0022893335670232775 }, { "action_query_batch_std": 22.07143077850342, "action_query_norm": 943.7960510253906, "action_relation_loss": 0.0023240498499944805, "auxiliary_loss_weight": 1.0, "epoch": 17.231057062675397, "flow_matching_loss": 0.023483753204345703, "grad_norm": 0.07704498618841171, "invalid_tail_samples": 23.2, "learning_rate": 3.550093030553284e-05, "loss": 0.0258, "positive_teacher_pairs": 26986.4, "relation_loss": 0.0023240498499944805, "selected_pairs": 26986.4, "step": 18420, "student_distance_mean": 1269.46201171875, "teacher_distance_mean": 0.8565915644168853, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0023240498499944805, "weighted_relation_loss": 0.0023240498499944805 }, { "action_query_batch_std": 22.226730346679688, "action_query_norm": 947.79931640625, "action_relation_loss": 0.002317671896889806, "auxiliary_loss_weight": 1.0, "epoch": 17.24041159962582, "flow_matching_loss": 0.02332350853830576, "grad_norm": 0.10804831981658936, "invalid_tail_samples": 25.4, "learning_rate": 3.544819165858642e-05, "loss": 0.0256, "positive_teacher_pairs": 26486.2, "relation_loss": 0.002317671896889806, "selected_pairs": 26486.2, "step": 18430, "student_distance_mean": 1273.9299560546874, "teacher_distance_mean": 0.8600064158439636, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.002317671896889806, "weighted_relation_loss": 0.002317671896889806 }, { "action_query_batch_std": 22.318727874755858, "action_query_norm": 952.6856384277344, "action_relation_loss": 0.002293025981634855, "auxiliary_loss_weight": 1.0, "epoch": 17.24976613657624, "flow_matching_loss": 0.02315207626670599, "grad_norm": 0.08780645579099655, "invalid_tail_samples": 22.7, "learning_rate": 3.539547069345926e-05, "loss": 0.0254, "positive_teacher_pairs": 27104.0, "relation_loss": 0.002293025981634855, "selected_pairs": 27104.0, "step": 18440, "student_distance_mean": 1277.8091918945313, "teacher_distance_mean": 0.8662505090236664, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.002293025981634855, "weighted_relation_loss": 0.002293025981634855 }, { "action_query_batch_std": 21.813551712036134, "action_query_norm": 936.5949279785157, "action_relation_loss": 0.0022860428784042598, "auxiliary_loss_weight": 1.0, "epoch": 17.25912067352666, "flow_matching_loss": 0.023178747110068797, "grad_norm": 0.09261258691549301, "invalid_tail_samples": 20.4, "learning_rate": 3.5342767474212344e-05, "loss": 0.0255, "positive_teacher_pairs": 27639.2, "relation_loss": 0.0022860428784042598, "selected_pairs": 27639.2, "step": 18450, "student_distance_mean": 1252.8425659179688, "teacher_distance_mean": 0.8445306777954101, "valid_action_samples": 235.6, "weighted_auxiliary_loss": 0.0022860428784042598, "weighted_relation_loss": 0.0022860428784042598 }, { "action_query_batch_std": 22.038407707214354, "action_query_norm": 944.8975830078125, "action_relation_loss": 0.002264251816086471, "auxiliary_loss_weight": 1.0, "epoch": 17.26847521047708, "flow_matching_loss": 0.022732418589293958, "grad_norm": 0.09341088682413101, "invalid_tail_samples": 22.1, "learning_rate": 3.529008206488502e-05, "loss": 0.025, "positive_teacher_pairs": 27262.2, "relation_loss": 0.002264251816086471, "selected_pairs": 27262.2, "step": 18460, "student_distance_mean": 1268.1818115234375, "teacher_distance_mean": 0.8555312275886535, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.002264251816086471, "weighted_relation_loss": 0.002264251816086471 }, { "action_query_batch_std": 21.957398986816408, "action_query_norm": 939.1907775878906, "action_relation_loss": 0.0023092894349247216, "auxiliary_loss_weight": 1.0, "epoch": 17.277829747427504, "flow_matching_loss": 0.021608422696590423, "grad_norm": 0.08709195256233215, "invalid_tail_samples": 24.1, "learning_rate": 3.5237414529495055e-05, "loss": 0.0239, "positive_teacher_pairs": 26790.1, "relation_loss": 0.0023092894349247216, "selected_pairs": 26790.1, "step": 18470, "student_distance_mean": 1261.4738159179688, "teacher_distance_mean": 0.8484342038631439, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0023092894349247216, "weighted_relation_loss": 0.0023092894349247216 }, { "action_query_batch_std": 22.122322845458985, "action_query_norm": 945.1700805664062, "action_relation_loss": 0.0023130379850044847, "auxiliary_loss_weight": 1.0, "epoch": 17.287184284377922, "flow_matching_loss": 0.020838699676096438, "grad_norm": 0.0825456902384758, "invalid_tail_samples": 23.4, "learning_rate": 3.5184764932038454e-05, "loss": 0.0232, "positive_teacher_pairs": 26943.2, "relation_loss": 0.0023130379850044847, "selected_pairs": 26943.2, "step": 18480, "student_distance_mean": 1271.760498046875, "teacher_distance_mean": 0.8564285695552826, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0023130379850044847, "weighted_relation_loss": 0.0023130379850044847 }, { "action_query_batch_std": 22.053440666198732, "action_query_norm": 947.4077941894532, "action_relation_loss": 0.002326903329230845, "auxiliary_loss_weight": 1.0, "epoch": 17.296538821328344, "flow_matching_loss": 0.022662469558417796, "grad_norm": 0.09328250586986542, "invalid_tail_samples": 23.9, "learning_rate": 3.513213333648945e-05, "loss": 0.025, "positive_teacher_pairs": 26824.5, "relation_loss": 0.002326903329230845, "selected_pairs": 26824.5, "step": 18490, "student_distance_mean": 1266.4757568359375, "teacher_distance_mean": 0.85255047082901, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.002326903329230845, "weighted_relation_loss": 0.002326903329230845 }, { "action_query_batch_std": 22.32743434906006, "action_query_norm": 952.9600158691406, "action_relation_loss": 0.0022510827984660864, "auxiliary_loss_weight": 1.0, "epoch": 17.305893358278766, "flow_matching_loss": 0.021164269000291825, "grad_norm": 0.09744391590356827, "invalid_tail_samples": 23.3, "learning_rate": 3.5079519806800374e-05, "loss": 0.0234, "positive_teacher_pairs": 26961.5, "relation_loss": 0.0022510827984660864, "selected_pairs": 26961.5, "step": 18500, "student_distance_mean": 1279.6799926757812, "teacher_distance_mean": 0.8605756461620331, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0022510827984660864, "weighted_relation_loss": 0.0022510827984660864 }, { "action_query_batch_std": 22.084678840637206, "action_query_norm": 945.1017395019531, "action_relation_loss": 0.0022719567408785225, "auxiliary_loss_weight": 1.0, "epoch": 17.315247895229184, "flow_matching_loss": 0.024202031083405018, "grad_norm": 0.08932442218065262, "invalid_tail_samples": 24.4, "learning_rate": 3.502692440690165e-05, "loss": 0.0265, "positive_teacher_pairs": 26711.1, "relation_loss": 0.0022719567408785225, "selected_pairs": 26711.1, "step": 18510, "student_distance_mean": 1266.2991088867188, "teacher_distance_mean": 0.8524319231510162, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0022719567408785225, "weighted_relation_loss": 0.0022719567408785225 }, { "action_query_batch_std": 22.11213912963867, "action_query_norm": 944.7509887695312, "action_relation_loss": 0.002279317774809897, "auxiliary_loss_weight": 1.0, "epoch": 17.324602432179606, "flow_matching_loss": 0.02334465067833662, "grad_norm": 0.106489397585392, "invalid_tail_samples": 22.6, "learning_rate": 3.497434720070165e-05, "loss": 0.0256, "positive_teacher_pairs": 27124.8, "relation_loss": 0.002279317774809897, "selected_pairs": 27124.8, "step": 18520, "student_distance_mean": 1271.096533203125, "teacher_distance_mean": 0.8591370105743408, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.002279317774809897, "weighted_relation_loss": 0.002279317774809897 }, { "action_query_batch_std": 22.05023937225342, "action_query_norm": 942.3794616699219, "action_relation_loss": 0.00226257483009249, "auxiliary_loss_weight": 1.0, "epoch": 17.33395696913003, "flow_matching_loss": 0.023439257591962814, "grad_norm": 0.11084380745887756, "invalid_tail_samples": 24.6, "learning_rate": 3.4921788252086616e-05, "loss": 0.0257, "positive_teacher_pairs": 26673.5, "relation_loss": 0.00226257483009249, "selected_pairs": 26673.5, "step": 18530, "student_distance_mean": 1267.2415161132812, "teacher_distance_mean": 0.8537682354450226, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.00226257483009249, "weighted_relation_loss": 0.00226257483009249 }, { "action_query_batch_std": 21.853496170043947, "action_query_norm": 938.4595825195313, "action_relation_loss": 0.00242486041970551, "auxiliary_loss_weight": 1.0, "epoch": 17.34331150608045, "flow_matching_loss": 0.024264520220458507, "grad_norm": 0.10137201100587845, "invalid_tail_samples": 21.4, "learning_rate": 3.486924762492065e-05, "loss": 0.0267, "positive_teacher_pairs": 27406.1, "relation_loss": 0.00242486041970551, "selected_pairs": 27406.1, "step": 18540, "student_distance_mean": 1256.889501953125, "teacher_distance_mean": 0.8477123320102692, "valid_action_samples": 234.6, "weighted_auxiliary_loss": 0.00242486041970551, "weighted_relation_loss": 0.00242486041970551 }, { "action_query_batch_std": 22.152204513549805, "action_query_norm": 945.3830688476562, "action_relation_loss": 0.002275333064608276, "auxiliary_loss_weight": 1.0, "epoch": 17.35266604303087, "flow_matching_loss": 0.022205820120871068, "grad_norm": 0.11047250032424927, "invalid_tail_samples": 23.1, "learning_rate": 3.4816725383045534e-05, "loss": 0.0245, "positive_teacher_pairs": 27017.8, "relation_loss": 0.002275333064608276, "selected_pairs": 27017.8, "step": 18550, "student_distance_mean": 1273.0335205078125, "teacher_distance_mean": 0.8618335843086242, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.002275333064608276, "weighted_relation_loss": 0.002275333064608276 }, { "action_query_batch_std": 21.994583129882812, "action_query_norm": 940.3215393066406, "action_relation_loss": 0.002312466478906572, "auxiliary_loss_weight": 1.0, "epoch": 17.36202057998129, "flow_matching_loss": 0.023698613233864307, "grad_norm": 0.10132286697626114, "invalid_tail_samples": 23.9, "learning_rate": 3.476422159028079e-05, "loss": 0.026, "positive_teacher_pairs": 26832.8, "relation_loss": 0.002312466478906572, "selected_pairs": 26832.8, "step": 18560, "student_distance_mean": 1260.3030517578125, "teacher_distance_mean": 0.8548852801322937, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.002312466478906572, "weighted_relation_loss": 0.002312466478906572 }, { "action_query_batch_std": 22.113297271728516, "action_query_norm": 947.4818603515625, "action_relation_loss": 0.0022854189155623317, "auxiliary_loss_weight": 1.0, "epoch": 17.371375116931713, "flow_matching_loss": 0.02172988634556532, "grad_norm": 0.1028207316994667, "invalid_tail_samples": 22.1, "learning_rate": 3.471173631042345e-05, "loss": 0.024, "positive_teacher_pairs": 27248.1, "relation_loss": 0.0022854189155623317, "selected_pairs": 27248.1, "step": 18570, "student_distance_mean": 1268.0215087890624, "teacher_distance_mean": 0.8571873545646668, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0022854189155623317, "weighted_relation_loss": 0.0022854189155623317 }, { "action_query_batch_std": 21.940139389038087, "action_query_norm": 937.8932739257813, "action_relation_loss": 0.0024127690121531487, "auxiliary_loss_weight": 1.0, "epoch": 17.38072965388213, "flow_matching_loss": 0.022599237971007824, "grad_norm": 0.10120688378810883, "invalid_tail_samples": 23.4, "learning_rate": 3.465926960724808e-05, "loss": 0.025, "positive_teacher_pairs": 26944.1, "relation_loss": 0.0024127690121531487, "selected_pairs": 26944.1, "step": 18580, "student_distance_mean": 1259.28642578125, "teacher_distance_mean": 0.8488309144973755, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0024127690121531487, "weighted_relation_loss": 0.0024127690121531487 }, { "action_query_batch_std": 22.012177848815917, "action_query_norm": 940.570458984375, "action_relation_loss": 0.0023388381581753493, "auxiliary_loss_weight": 1.0, "epoch": 17.390084190832553, "flow_matching_loss": 0.02244998924434185, "grad_norm": 0.09144514054059982, "invalid_tail_samples": 23.4, "learning_rate": 3.460682154450666e-05, "loss": 0.0248, "positive_teacher_pairs": 26937.2, "relation_loss": 0.0023388381581753493, "selected_pairs": 26937.2, "step": 18590, "student_distance_mean": 1262.5518432617187, "teacher_distance_mean": 0.8517044067382813, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0023388381581753493, "weighted_relation_loss": 0.0023388381581753493 }, { "action_query_batch_std": 22.149958610534668, "action_query_norm": 942.0651000976562, "action_relation_loss": 0.0023118195356801154, "auxiliary_loss_weight": 1.0, "epoch": 17.399438727782975, "flow_matching_loss": 0.02379498481750488, "grad_norm": 0.0906551256775856, "invalid_tail_samples": 24.9, "learning_rate": 3.4554392185928564e-05, "loss": 0.0261, "positive_teacher_pairs": 26597.6, "relation_loss": 0.0023118195356801154, "selected_pairs": 26597.6, "step": 18600, "student_distance_mean": 1269.4692749023438, "teacher_distance_mean": 0.8560985207557679, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0023118195356801154, "weighted_relation_loss": 0.0023118195356801154 }, { "action_query_batch_std": 21.884424018859864, "action_query_norm": 934.7752197265625, "action_relation_loss": 0.0023441158467903734, "auxiliary_loss_weight": 1.0, "epoch": 17.408793264733397, "flow_matching_loss": 0.02338381316512823, "grad_norm": 0.10660773515701294, "invalid_tail_samples": 24.8, "learning_rate": 3.450198159522037e-05, "loss": 0.0257, "positive_teacher_pairs": 26620.9, "relation_loss": 0.0023441158467903734, "selected_pairs": 26620.9, "step": 18610, "student_distance_mean": 1252.4432373046875, "teacher_distance_mean": 0.8441881775856018, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0023441158467903734, "weighted_relation_loss": 0.0023441158467903734 }, { "action_query_batch_std": 22.016912841796874, "action_query_norm": 940.7685363769531, "action_relation_loss": 0.002323336875997484, "auxiliary_loss_weight": 1.0, "epoch": 17.418147801683816, "flow_matching_loss": 0.0217217406257987, "grad_norm": 0.07908537238836288, "invalid_tail_samples": 22.0, "learning_rate": 3.444958983606592e-05, "loss": 0.024, "positive_teacher_pairs": 27264.3, "relation_loss": 0.002323336875997484, "selected_pairs": 27264.3, "step": 18620, "student_distance_mean": 1262.668896484375, "teacher_distance_mean": 0.8499880075454712, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.002323336875997484, "weighted_relation_loss": 0.002323336875997484 }, { "action_query_batch_std": 21.964307022094726, "action_query_norm": 938.1010131835938, "action_relation_loss": 0.0022491790587082505, "auxiliary_loss_weight": 1.0, "epoch": 17.427502338634238, "flow_matching_loss": 0.0225011982023716, "grad_norm": 0.09835638850927353, "invalid_tail_samples": 25.4, "learning_rate": 3.439721697212612e-05, "loss": 0.0248, "positive_teacher_pairs": 26484.2, "relation_loss": 0.0022491790587082505, "selected_pairs": 26484.2, "step": 18630, "student_distance_mean": 1262.259423828125, "teacher_distance_mean": 0.8525522589683533, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.0022491790587082505, "weighted_relation_loss": 0.0022491790587082505 }, { "action_query_batch_std": 21.931546211242676, "action_query_norm": 939.3260375976563, "action_relation_loss": 0.0023983013816177845, "auxiliary_loss_weight": 1.0, "epoch": 17.43685687558466, "flow_matching_loss": 0.02257045153528452, "grad_norm": 0.11835137754678726, "invalid_tail_samples": 23.1, "learning_rate": 3.4344863067038954e-05, "loss": 0.025, "positive_teacher_pairs": 27013.4, "relation_loss": 0.0023983013816177845, "selected_pairs": 27013.4, "step": 18640, "student_distance_mean": 1257.2194580078126, "teacher_distance_mean": 0.8482330143451691, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0023983013816177845, "weighted_relation_loss": 0.0023983013816177845 }, { "action_query_batch_std": 22.05028877258301, "action_query_norm": 943.9709106445313, "action_relation_loss": 0.002349705365486443, "auxiliary_loss_weight": 1.0, "epoch": 17.446211412535078, "flow_matching_loss": 0.023508546128869056, "grad_norm": 0.10325117409229279, "invalid_tail_samples": 22.5, "learning_rate": 3.429252818441935e-05, "loss": 0.0259, "positive_teacher_pairs": 27164.1, "relation_loss": 0.002349705365486443, "selected_pairs": 27164.1, "step": 18650, "student_distance_mean": 1266.172509765625, "teacher_distance_mean": 0.8537384569644928, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.002349705365486443, "weighted_relation_loss": 0.002349705365486443 }, { "action_query_batch_std": 21.90168628692627, "action_query_norm": 939.3360534667969, "action_relation_loss": 0.002241259184665978, "auxiliary_loss_weight": 1.0, "epoch": 17.4555659494855, "flow_matching_loss": 0.02257478181272745, "grad_norm": 0.08619501441717148, "invalid_tail_samples": 23.8, "learning_rate": 3.4240212387859094e-05, "loss": 0.0248, "positive_teacher_pairs": 26848.0, "relation_loss": 0.002241259184665978, "selected_pairs": 26848.0, "step": 18660, "student_distance_mean": 1258.1679565429688, "teacher_distance_mean": 0.8476728141307831, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.002241259184665978, "weighted_relation_loss": 0.002241259184665978 }, { "action_query_batch_std": 22.26291389465332, "action_query_norm": 949.390625, "action_relation_loss": 0.002284754067659378, "auxiliary_loss_weight": 1.0, "epoch": 17.464920486435922, "flow_matching_loss": 0.02391485758125782, "grad_norm": 0.08664640784263611, "invalid_tail_samples": 21.6, "learning_rate": 3.418791574092686e-05, "loss": 0.0262, "positive_teacher_pairs": 27369.4, "relation_loss": 0.002284754067659378, "selected_pairs": 27369.4, "step": 18670, "student_distance_mean": 1272.8196899414063, "teacher_distance_mean": 0.8611822426319122, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.002284754067659378, "weighted_relation_loss": 0.002284754067659378 }, { "action_query_batch_std": 22.09087791442871, "action_query_norm": 944.16943359375, "action_relation_loss": 0.0023412453243508934, "auxiliary_loss_weight": 1.0, "epoch": 17.474275023386344, "flow_matching_loss": 0.022228711657226084, "grad_norm": 0.08934434503316879, "invalid_tail_samples": 23.2, "learning_rate": 3.413563830716796e-05, "loss": 0.0246, "positive_teacher_pairs": 26993.8, "relation_loss": 0.0023412453243508934, "selected_pairs": 26993.8, "step": 18680, "student_distance_mean": 1266.542626953125, "teacher_distance_mean": 0.8535219192504883, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0023412453243508934, "weighted_relation_loss": 0.0023412453243508934 }, { "action_query_batch_std": 21.908369064331055, "action_query_norm": 933.8304748535156, "action_relation_loss": 0.0022924463264644146, "auxiliary_loss_weight": 1.0, "epoch": 17.483629560336762, "flow_matching_loss": 0.023694663122296334, "grad_norm": 0.1047038659453392, "invalid_tail_samples": 25.7, "learning_rate": 3.408338015010445e-05, "loss": 0.026, "positive_teacher_pairs": 26410.1, "relation_loss": 0.0022924463264644146, "selected_pairs": 26410.1, "step": 18690, "student_distance_mean": 1256.6711791992188, "teacher_distance_mean": 0.8454993963241577, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.0022924463264644146, "weighted_relation_loss": 0.0022924463264644146 }, { "action_query_batch_std": 22.24577045440674, "action_query_norm": 951.5693908691406, "action_relation_loss": 0.0022285157348960636, "auxiliary_loss_weight": 1.0, "epoch": 17.492984097287184, "flow_matching_loss": 0.023189207538962364, "grad_norm": 0.11912775784730911, "invalid_tail_samples": 21.6, "learning_rate": 3.40311413332349e-05, "loss": 0.0254, "positive_teacher_pairs": 27367.3, "relation_loss": 0.0022285157348960636, "selected_pairs": 27367.3, "step": 18700, "student_distance_mean": 1280.0566040039062, "teacher_distance_mean": 0.8630158305168152, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.0022285157348960636, "weighted_relation_loss": 0.0022285157348960636 }, { "action_query_batch_std": 21.88529167175293, "action_query_norm": 937.2094116210938, "action_relation_loss": 0.0023080808343365787, "auxiliary_loss_weight": 1.0, "epoch": 17.502338634237606, "flow_matching_loss": 0.022336679883301257, "grad_norm": 0.09447885304689407, "invalid_tail_samples": 24.7, "learning_rate": 3.3978921920034365e-05, "loss": 0.0246, "positive_teacher_pairs": 26653.3, "relation_loss": 0.0023080808343365787, "selected_pairs": 26653.3, "step": 18710, "student_distance_mean": 1253.889453125, "teacher_distance_mean": 0.847247987985611, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0023080808343365787, "weighted_relation_loss": 0.0023080808343365787 }, { "action_query_batch_std": 22.05869255065918, "action_query_norm": 939.9052795410156, "action_relation_loss": 0.0022946490440517663, "auxiliary_loss_weight": 1.0, "epoch": 17.511693171188025, "flow_matching_loss": 0.022017155960202216, "grad_norm": 0.10001955181360245, "invalid_tail_samples": 23.8, "learning_rate": 3.392672197395441e-05, "loss": 0.0243, "positive_teacher_pairs": 26851.6, "relation_loss": 0.0022946490440517663, "selected_pairs": 26851.6, "step": 18720, "student_distance_mean": 1262.2314697265624, "teacher_distance_mean": 0.8552358031272889, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0022946490440517663, "weighted_relation_loss": 0.0022946490440517663 }, { "action_query_batch_std": 21.87356605529785, "action_query_norm": 935.0039916992188, "action_relation_loss": 0.0023599561536684632, "auxiliary_loss_weight": 1.0, "epoch": 17.521047708138447, "flow_matching_loss": 0.02211228236556053, "grad_norm": 0.11600830405950546, "invalid_tail_samples": 24.7, "learning_rate": 3.387454155842287e-05, "loss": 0.0245, "positive_teacher_pairs": 26643.4, "relation_loss": 0.0023599561536684632, "selected_pairs": 26643.4, "step": 18730, "student_distance_mean": 1258.7727172851562, "teacher_distance_mean": 0.8541475236415863, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0023599561536684632, "weighted_relation_loss": 0.0023599561536684632 }, { "action_query_batch_std": 21.9806978225708, "action_query_norm": 939.8634094238281, "action_relation_loss": 0.0023134860442951322, "auxiliary_loss_weight": 1.0, "epoch": 17.53040224508887, "flow_matching_loss": 0.022205814160406588, "grad_norm": 0.08873090893030167, "invalid_tail_samples": 23.3, "learning_rate": 3.382238073684386e-05, "loss": 0.0245, "positive_teacher_pairs": 26969.5, "relation_loss": 0.0023134860442951322, "selected_pairs": 26969.5, "step": 18740, "student_distance_mean": 1262.0383178710938, "teacher_distance_mean": 0.8529600441455841, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0023134860442951322, "weighted_relation_loss": 0.0023134860442951322 }, { "action_query_batch_std": 22.14482479095459, "action_query_norm": 946.2633239746094, "action_relation_loss": 0.0022451029159128665, "auxiliary_loss_weight": 1.0, "epoch": 17.53975678203929, "flow_matching_loss": 0.022038060799241067, "grad_norm": 0.10043387860059738, "invalid_tail_samples": 22.8, "learning_rate": 3.377023957259771e-05, "loss": 0.0243, "positive_teacher_pairs": 27088.0, "relation_loss": 0.0022451029159128665, "selected_pairs": 27088.0, "step": 18750, "student_distance_mean": 1275.6816772460938, "teacher_distance_mean": 0.8624837458133697, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0022451029159128665, "weighted_relation_loss": 0.0022451029159128665 }, { "action_query_batch_std": 22.30107727050781, "action_query_norm": 950.0930114746094, "action_relation_loss": 0.0023119947174564002, "auxiliary_loss_weight": 1.0, "epoch": 17.54911131898971, "flow_matching_loss": 0.022026232443749905, "grad_norm": 0.09137281775474548, "invalid_tail_samples": 22.4, "learning_rate": 3.3718118129040835e-05, "loss": 0.0243, "positive_teacher_pairs": 27180.2, "relation_loss": 0.0023119947174564002, "selected_pairs": 27180.2, "step": 18760, "student_distance_mean": 1281.2825927734375, "teacher_distance_mean": 0.8644888520240783, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.0023119947174564002, "weighted_relation_loss": 0.0023119947174564002 }, { "action_query_batch_std": 22.403169250488283, "action_query_norm": 955.9428588867188, "action_relation_loss": 0.002409216482192278, "auxiliary_loss_weight": 1.0, "epoch": 17.55846585594013, "flow_matching_loss": 0.02123512588441372, "grad_norm": 0.08372647315263748, "invalid_tail_samples": 23.4, "learning_rate": 3.3666016469505724e-05, "loss": 0.0236, "positive_teacher_pairs": 26943.6, "relation_loss": 0.002409216482192278, "selected_pairs": 26943.6, "step": 18770, "student_distance_mean": 1280.65224609375, "teacher_distance_mean": 0.8584478259086609, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.002409216482192278, "weighted_relation_loss": 0.002409216482192278 }, { "action_query_batch_std": 22.201279067993163, "action_query_norm": 946.8098205566406, "action_relation_loss": 0.0023376551922410726, "auxiliary_loss_weight": 1.0, "epoch": 17.567820392890553, "flow_matching_loss": 0.02212263401597738, "grad_norm": 0.1095636636018753, "invalid_tail_samples": 23.7, "learning_rate": 3.361393465730079e-05, "loss": 0.0245, "positive_teacher_pairs": 26875.8, "relation_loss": 0.0023376551922410726, "selected_pairs": 26875.8, "step": 18780, "student_distance_mean": 1268.7035888671876, "teacher_distance_mean": 0.8527871072292328, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0023376551922410726, "weighted_relation_loss": 0.0023376551922410726 }, { "action_query_batch_std": 22.24009304046631, "action_query_norm": 948.8246154785156, "action_relation_loss": 0.0024074798449873923, "auxiliary_loss_weight": 1.0, "epoch": 17.57717492984097, "flow_matching_loss": 0.025296230800449848, "grad_norm": 0.09432826936244965, "invalid_tail_samples": 23.5, "learning_rate": 3.3561872755710366e-05, "loss": 0.0277, "positive_teacher_pairs": 26922.0, "relation_loss": 0.0024074798449873923, "selected_pairs": 26922.0, "step": 18790, "student_distance_mean": 1272.7311767578126, "teacher_distance_mean": 0.8570180416107178, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0024074798449873923, "weighted_relation_loss": 0.0024074798449873923 }, { "action_query_batch_std": 22.063095092773438, "action_query_norm": 941.67548828125, "action_relation_loss": 0.002250664192251861, "auxiliary_loss_weight": 1.0, "epoch": 17.586529466791394, "flow_matching_loss": 0.022162865661084653, "grad_norm": 0.09677230566740036, "invalid_tail_samples": 24.1, "learning_rate": 3.350983082799456e-05, "loss": 0.0244, "positive_teacher_pairs": 26780.2, "relation_loss": 0.002250664192251861, "selected_pairs": 26780.2, "step": 18800, "student_distance_mean": 1268.9886474609375, "teacher_distance_mean": 0.8574211001396179, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.002250664192251861, "weighted_relation_loss": 0.002250664192251861 }, { "action_query_batch_std": 21.955762672424317, "action_query_norm": 937.5555847167968, "action_relation_loss": 0.0023504539858549833, "auxiliary_loss_weight": 1.0, "epoch": 17.595884003741816, "flow_matching_loss": 0.02116559464484453, "grad_norm": 0.10646513849496841, "invalid_tail_samples": 24.2, "learning_rate": 3.34578089373892e-05, "loss": 0.0235, "positive_teacher_pairs": 26756.7, "relation_loss": 0.0023504539858549833, "selected_pairs": 26756.7, "step": 18810, "student_distance_mean": 1259.475634765625, "teacher_distance_mean": 0.848661071062088, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0023504539858549833, "weighted_relation_loss": 0.0023504539858549833 }, { "action_query_batch_std": 22.362020683288574, "action_query_norm": 952.2943603515625, "action_relation_loss": 0.002185577352065593, "auxiliary_loss_weight": 1.0, "epoch": 17.605238540692234, "flow_matching_loss": 0.021463659033179282, "grad_norm": 0.10151122510433197, "invalid_tail_samples": 24.0, "learning_rate": 3.340580714710581e-05, "loss": 0.0236, "positive_teacher_pairs": 26800.5, "relation_loss": 0.002185577352065593, "selected_pairs": 26800.5, "step": 18820, "student_distance_mean": 1282.407568359375, "teacher_distance_mean": 0.8630214631557465, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.002185577352065593, "weighted_relation_loss": 0.002185577352065593 }, { "action_query_batch_std": 22.26302089691162, "action_query_norm": 951.5557678222656, "action_relation_loss": 0.002271068561822176, "auxiliary_loss_weight": 1.0, "epoch": 17.614593077642656, "flow_matching_loss": 0.022936381958425046, "grad_norm": 0.08784370124340057, "invalid_tail_samples": 20.5, "learning_rate": 3.3353825520331466e-05, "loss": 0.0252, "positive_teacher_pairs": 27627.5, "relation_loss": 0.002271068561822176, "selected_pairs": 27627.5, "step": 18830, "student_distance_mean": 1274.4507202148438, "teacher_distance_mean": 0.8551330327987671, "valid_action_samples": 235.5, "weighted_auxiliary_loss": 0.002271068561822176, "weighted_relation_loss": 0.002271068561822176 }, { "action_query_batch_std": 21.94184093475342, "action_query_norm": 937.6661926269531, "action_relation_loss": 0.0022626832593232392, "auxiliary_loss_weight": 1.0, "epoch": 17.623947614593078, "flow_matching_loss": 0.022503905370831488, "grad_norm": 0.08779704570770264, "invalid_tail_samples": 26.8, "learning_rate": 3.330186412022876e-05, "loss": 0.0248, "positive_teacher_pairs": 26158.0, "relation_loss": 0.0022626832593232392, "selected_pairs": 26158.0, "step": 18840, "student_distance_mean": 1265.451513671875, "teacher_distance_mean": 0.8504809737205505, "valid_action_samples": 229.2, "weighted_auxiliary_loss": 0.0022626832593232392, "weighted_relation_loss": 0.0022626832593232392 }, { "action_query_batch_std": 22.036526489257813, "action_query_norm": 942.1683227539063, "action_relation_loss": 0.0023294642101973294, "auxiliary_loss_weight": 1.0, "epoch": 17.6333021515435, "flow_matching_loss": 0.020711878687143324, "grad_norm": 0.10664163529872894, "invalid_tail_samples": 24.8, "learning_rate": 3.324992300993568e-05, "loss": 0.023, "positive_teacher_pairs": 26622.7, "relation_loss": 0.0023294642101973294, "selected_pairs": 26622.7, "step": 18850, "student_distance_mean": 1261.9961791992187, "teacher_distance_mean": 0.8451345086097717, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0023294642101973294, "weighted_relation_loss": 0.0023294642101973294 }, { "action_query_batch_std": 22.11445903778076, "action_query_norm": 946.0960021972656, "action_relation_loss": 0.002354965661652386, "auxiliary_loss_weight": 1.0, "epoch": 17.64265668849392, "flow_matching_loss": 0.022097109723836182, "grad_norm": 0.10198955237865448, "invalid_tail_samples": 24.2, "learning_rate": 3.319800225256556e-05, "loss": 0.0245, "positive_teacher_pairs": 26768.6, "relation_loss": 0.002354965661652386, "selected_pairs": 26768.6, "step": 18860, "student_distance_mean": 1268.3001098632812, "teacher_distance_mean": 0.8524449408054352, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.002354965661652386, "weighted_relation_loss": 0.002354965661652386 }, { "action_query_batch_std": 22.14354305267334, "action_query_norm": 946.4538391113281, "action_relation_loss": 0.002224713494069874, "auxiliary_loss_weight": 1.0, "epoch": 17.65201122544434, "flow_matching_loss": 0.02255515456199646, "grad_norm": 0.12075143307447433, "invalid_tail_samples": 25.4, "learning_rate": 3.314610191120702e-05, "loss": 0.0248, "positive_teacher_pairs": 26481.6, "relation_loss": 0.002224713494069874, "selected_pairs": 26481.6, "step": 18870, "student_distance_mean": 1275.5774780273437, "teacher_distance_mean": 0.8568965256214142, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.002224713494069874, "weighted_relation_loss": 0.002224713494069874 }, { "action_query_batch_std": 22.038986015319825, "action_query_norm": 940.9530090332031, "action_relation_loss": 0.0022748714312911034, "auxiliary_loss_weight": 1.0, "epoch": 17.661365762394762, "flow_matching_loss": 0.023628736659884454, "grad_norm": 0.11354172229766846, "invalid_tail_samples": 23.3, "learning_rate": 3.30942220489239e-05, "loss": 0.0259, "positive_teacher_pairs": 26968.2, "relation_loss": 0.0022748714312911034, "selected_pairs": 26968.2, "step": 18880, "student_distance_mean": 1266.1317138671875, "teacher_distance_mean": 0.8545475721359252, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0022748714312911034, "weighted_relation_loss": 0.0022748714312911034 }, { "action_query_batch_std": 22.038437843322754, "action_query_norm": 940.9446716308594, "action_relation_loss": 0.002315212832763791, "auxiliary_loss_weight": 1.0, "epoch": 17.67072029934518, "flow_matching_loss": 0.02341822236776352, "grad_norm": 0.08570513129234314, "invalid_tail_samples": 26.0, "learning_rate": 3.3042362728755086e-05, "loss": 0.0257, "positive_teacher_pairs": 26341.2, "relation_loss": 0.002315212832763791, "selected_pairs": 26341.2, "step": 18890, "student_distance_mean": 1269.955810546875, "teacher_distance_mean": 0.8570530116558075, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.002315212832763791, "weighted_relation_loss": 0.002315212832763791 }, { "action_query_batch_std": 22.075078201293945, "action_query_norm": 943.524609375, "action_relation_loss": 0.0023138895630836487, "auxiliary_loss_weight": 1.0, "epoch": 17.680074836295603, "flow_matching_loss": 0.02329198345541954, "grad_norm": 0.09222057461738586, "invalid_tail_samples": 23.0, "learning_rate": 3.299052401371456e-05, "loss": 0.0256, "positive_teacher_pairs": 27047.0, "relation_loss": 0.0023138895630836487, "selected_pairs": 27047.0, "step": 18900, "student_distance_mean": 1268.9952392578125, "teacher_distance_mean": 0.859105521440506, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0023138895630836487, "weighted_relation_loss": 0.0023138895630836487 }, { "action_query_batch_std": 22.12918014526367, "action_query_norm": 946.2122619628906, "action_relation_loss": 0.002282424457371235, "auxiliary_loss_weight": 1.0, "epoch": 17.689429373246025, "flow_matching_loss": 0.02218662779778242, "grad_norm": 0.0901310071349144, "invalid_tail_samples": 21.9, "learning_rate": 3.293870596679125e-05, "loss": 0.0245, "positive_teacher_pairs": 27290.8, "relation_loss": 0.002282424457371235, "selected_pairs": 27290.8, "step": 18910, "student_distance_mean": 1268.2707885742188, "teacher_distance_mean": 0.859463506937027, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.002282424457371235, "weighted_relation_loss": 0.002282424457371235 }, { "action_query_batch_std": 22.157795906066895, "action_query_norm": 947.3295776367188, "action_relation_loss": 0.0023934982484206556, "auxiliary_loss_weight": 1.0, "epoch": 17.698783910196447, "flow_matching_loss": 0.023368501290678977, "grad_norm": 0.10917062312364578, "invalid_tail_samples": 22.5, "learning_rate": 3.288690865094895e-05, "loss": 0.0258, "positive_teacher_pairs": 27160.7, "relation_loss": 0.0023934982484206556, "selected_pairs": 27160.7, "step": 18920, "student_distance_mean": 1270.4022583007813, "teacher_distance_mean": 0.8573597371578217, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0023934982484206556, "weighted_relation_loss": 0.0023934982484206556 }, { "action_query_batch_std": 21.94502010345459, "action_query_norm": 936.5212951660156, "action_relation_loss": 0.0023070235969498754, "auxiliary_loss_weight": 1.0, "epoch": 17.708138447146865, "flow_matching_loss": 0.02360998997464776, "grad_norm": 0.09069003909826279, "invalid_tail_samples": 24.9, "learning_rate": 3.283513212912632e-05, "loss": 0.0259, "positive_teacher_pairs": 26593.2, "relation_loss": 0.0023070235969498754, "selected_pairs": 26593.2, "step": 18930, "student_distance_mean": 1260.391357421875, "teacher_distance_mean": 0.8512759149074555, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0023070235969498754, "weighted_relation_loss": 0.0023070235969498754 }, { "action_query_batch_std": 21.82427806854248, "action_query_norm": 933.662255859375, "action_relation_loss": 0.0022530144080519674, "auxiliary_loss_weight": 1.0, "epoch": 17.717492984097287, "flow_matching_loss": 0.023245908506214618, "grad_norm": 0.08312429487705231, "invalid_tail_samples": 24.0, "learning_rate": 3.2783376464236684e-05, "loss": 0.0255, "positive_teacher_pairs": 26803.4, "relation_loss": 0.0022530144080519674, "selected_pairs": 26803.4, "step": 18940, "student_distance_mean": 1257.39970703125, "teacher_distance_mean": 0.8474095225334167, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0022530144080519674, "weighted_relation_loss": 0.0022530144080519674 }, { "action_query_batch_std": 22.03888988494873, "action_query_norm": 940.1950500488281, "action_relation_loss": 0.002277585188858211, "auxiliary_loss_weight": 1.0, "epoch": 17.72684752104771, "flow_matching_loss": 0.02188806664198637, "grad_norm": 0.08793433010578156, "invalid_tail_samples": 23.4, "learning_rate": 3.273164171916806e-05, "loss": 0.0242, "positive_teacher_pairs": 26943.3, "relation_loss": 0.002277585188858211, "selected_pairs": 26943.3, "step": 18950, "student_distance_mean": 1265.6078247070313, "teacher_distance_mean": 0.8561357200145722, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.002277585188858211, "weighted_relation_loss": 0.002277585188858211 }, { "action_query_batch_std": 22.163129615783692, "action_query_norm": 941.6079711914062, "action_relation_loss": 0.002319487277418375, "auxiliary_loss_weight": 1.0, "epoch": 17.736202057998128, "flow_matching_loss": 0.02317783050239086, "grad_norm": 0.08965892344713211, "invalid_tail_samples": 24.8, "learning_rate": 3.267992795678306e-05, "loss": 0.0255, "positive_teacher_pairs": 26634.4, "relation_loss": 0.002319487277418375, "selected_pairs": 26634.4, "step": 18960, "student_distance_mean": 1270.8763549804687, "teacher_distance_mean": 0.8568017423152924, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.002319487277418375, "weighted_relation_loss": 0.002319487277418375 }, { "action_query_batch_std": 22.11108055114746, "action_query_norm": 941.7035949707031, "action_relation_loss": 0.00229856101796031, "auxiliary_loss_weight": 1.0, "epoch": 17.74555659494855, "flow_matching_loss": 0.022356956638395785, "grad_norm": 0.08795558661222458, "invalid_tail_samples": 23.7, "learning_rate": 3.2628235239918744e-05, "loss": 0.0247, "positive_teacher_pairs": 26881.1, "relation_loss": 0.00229856101796031, "selected_pairs": 26881.1, "step": 18970, "student_distance_mean": 1266.7092895507812, "teacher_distance_mean": 0.8502222955226898, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.00229856101796031, "weighted_relation_loss": 0.00229856101796031 }, { "action_query_batch_std": 22.144403076171876, "action_query_norm": 945.8396911621094, "action_relation_loss": 0.002314315736293793, "auxiliary_loss_weight": 1.0, "epoch": 17.75491113189897, "flow_matching_loss": 0.02251996360719204, "grad_norm": 0.08935154229402542, "invalid_tail_samples": 23.4, "learning_rate": 3.2576563631386695e-05, "loss": 0.0248, "positive_teacher_pairs": 26942.5, "relation_loss": 0.002314315736293793, "selected_pairs": 26942.5, "step": 18980, "student_distance_mean": 1266.1849731445313, "teacher_distance_mean": 0.8486142992973328, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.002314315736293793, "weighted_relation_loss": 0.002314315736293793 }, { "action_query_batch_std": 22.048753929138183, "action_query_norm": 941.5473510742188, "action_relation_loss": 0.0023518216796219347, "auxiliary_loss_weight": 1.0, "epoch": 17.764265668849394, "flow_matching_loss": 0.021826678328216075, "grad_norm": 0.1062629371881485, "invalid_tail_samples": 26.1, "learning_rate": 3.252491319397275e-05, "loss": 0.0242, "positive_teacher_pairs": 26335.8, "relation_loss": 0.0023518216796219347, "selected_pairs": 26335.8, "step": 18990, "student_distance_mean": 1264.0545776367187, "teacher_distance_mean": 0.8515005767345428, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.0023518216796219347, "weighted_relation_loss": 0.0023518216796219347 }, { "action_query_batch_std": 22.113010978698732, "action_query_norm": 940.7274536132812, "action_relation_loss": 0.0022906024241819978, "auxiliary_loss_weight": 1.0, "epoch": 17.773620205799812, "flow_matching_loss": 0.022991728596389295, "grad_norm": 0.0991276204586029, "invalid_tail_samples": 24.6, "learning_rate": 3.247328399043706e-05, "loss": 0.0253, "positive_teacher_pairs": 26663.1, "relation_loss": 0.0022906024241819978, "selected_pairs": 26663.1, "step": 19000, "student_distance_mean": 1270.5250122070313, "teacher_distance_mean": 0.8576821208000183, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0022906024241819978, "weighted_relation_loss": 0.0022906024241819978 }, { "action_query_batch_std": 22.1098575592041, "action_query_norm": 945.8235595703125, "action_relation_loss": 0.0023127298336476088, "auxiliary_loss_weight": 1.0, "epoch": 17.782974742750234, "flow_matching_loss": 0.02295073103159666, "grad_norm": 0.09310061484575272, "invalid_tail_samples": 21.6, "learning_rate": 3.242167608351399e-05, "loss": 0.0253, "positive_teacher_pairs": 27358.8, "relation_loss": 0.0023127298336476088, "selected_pairs": 27358.8, "step": 19010, "student_distance_mean": 1271.1153198242187, "teacher_distance_mean": 0.8560178697109222, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.0023127298336476088, "weighted_relation_loss": 0.0023127298336476088 }, { "action_query_batch_std": 22.15542984008789, "action_query_norm": 944.4758483886719, "action_relation_loss": 0.002249259827658534, "auxiliary_loss_weight": 1.0, "epoch": 17.792329279700656, "flow_matching_loss": 0.023115045949816705, "grad_norm": 0.1062416061758995, "invalid_tail_samples": 22.4, "learning_rate": 3.2370089535911986e-05, "loss": 0.0254, "positive_teacher_pairs": 27173.5, "relation_loss": 0.002249259827658534, "selected_pairs": 27173.5, "step": 19020, "student_distance_mean": 1268.9622802734375, "teacher_distance_mean": 0.8555988490581512, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.002249259827658534, "weighted_relation_loss": 0.002249259827658534 }, { "action_query_batch_std": 22.01457576751709, "action_query_norm": 939.5984497070312, "action_relation_loss": 0.002312142797745764, "auxiliary_loss_weight": 1.0, "epoch": 17.801683816651074, "flow_matching_loss": 0.023209425061941145, "grad_norm": 0.1117067039012909, "invalid_tail_samples": 25.0, "learning_rate": 3.23185244103136e-05, "loss": 0.0255, "positive_teacher_pairs": 26572.0, "relation_loss": 0.002312142797745764, "selected_pairs": 26572.0, "step": 19030, "student_distance_mean": 1257.5407470703126, "teacher_distance_mean": 0.8479469001293183, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.002312142797745764, "weighted_relation_loss": 0.002312142797745764 }, { "action_query_batch_std": 22.29561882019043, "action_query_norm": 949.3715576171875, "action_relation_loss": 0.002255982463248074, "auxiliary_loss_weight": 1.0, "epoch": 17.811038353601496, "flow_matching_loss": 0.02266499511897564, "grad_norm": 0.1150205060839653, "invalid_tail_samples": 25.8, "learning_rate": 3.22669807693753e-05, "loss": 0.0249, "positive_teacher_pairs": 26384.6, "relation_loss": 0.002255982463248074, "selected_pairs": 26384.6, "step": 19040, "student_distance_mean": 1272.8273193359375, "teacher_distance_mean": 0.8528661787509918, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.002255982463248074, "weighted_relation_loss": 0.002255982463248074 }, { "action_query_batch_std": 22.646165657043458, "action_query_norm": 960.7354614257813, "action_relation_loss": 0.0022373778047040105, "auxiliary_loss_weight": 1.0, "epoch": 17.82039289055192, "flow_matching_loss": 0.025470929965376855, "grad_norm": 0.11641687154769897, "invalid_tail_samples": 20.7, "learning_rate": 3.2215458675727495e-05, "loss": 0.0277, "positive_teacher_pairs": 27579.6, "relation_loss": 0.0022373778047040105, "selected_pairs": 27579.6, "step": 19050, "student_distance_mean": 1290.7424072265626, "teacher_distance_mean": 0.8675057232379914, "valid_action_samples": 235.3, "weighted_auxiliary_loss": 0.0022373778047040105, "weighted_relation_loss": 0.0022373778047040105 }, { "action_query_batch_std": 22.36363830566406, "action_query_norm": 953.1790344238282, "action_relation_loss": 0.002284126216545701, "auxiliary_loss_weight": 1.0, "epoch": 17.82974742750234, "flow_matching_loss": 0.02329674977809191, "grad_norm": 0.09379934519529343, "invalid_tail_samples": 24.7, "learning_rate": 3.216395819197438e-05, "loss": 0.0256, "positive_teacher_pairs": 26638.7, "relation_loss": 0.002284126216545701, "selected_pairs": 26638.7, "step": 19060, "student_distance_mean": 1284.414990234375, "teacher_distance_mean": 0.8628901720046998, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.002284126216545701, "weighted_relation_loss": 0.002284126216545701 }, { "action_query_batch_std": 22.110658264160158, "action_query_norm": 947.8682739257813, "action_relation_loss": 0.0022832141490653156, "auxiliary_loss_weight": 1.0, "epoch": 17.83910196445276, "flow_matching_loss": 0.021838670969009398, "grad_norm": 0.1073186993598938, "invalid_tail_samples": 23.1, "learning_rate": 3.211247938069387e-05, "loss": 0.0241, "positive_teacher_pairs": 27025.6, "relation_loss": 0.0022832141490653156, "selected_pairs": 27025.6, "step": 19070, "student_distance_mean": 1272.7258178710938, "teacher_distance_mean": 0.8530223488807678, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0022832141490653156, "weighted_relation_loss": 0.0022832141490653156 }, { "action_query_batch_std": 22.30620594024658, "action_query_norm": 951.1643615722656, "action_relation_loss": 0.0022075262386351824, "auxiliary_loss_weight": 1.0, "epoch": 17.84845650140318, "flow_matching_loss": 0.02292448850348592, "grad_norm": 0.09856457263231277, "invalid_tail_samples": 25.6, "learning_rate": 3.206102230443759e-05, "loss": 0.0251, "positive_teacher_pairs": 26436.9, "relation_loss": 0.0022075262386351824, "selected_pairs": 26436.9, "step": 19080, "student_distance_mean": 1280.5221923828126, "teacher_distance_mean": 0.8581237733364105, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.0022075262386351824, "weighted_relation_loss": 0.0022075262386351824 }, { "action_query_batch_std": 22.01375102996826, "action_query_norm": 942.2066772460937, "action_relation_loss": 0.00225494250189513, "auxiliary_loss_weight": 1.0, "epoch": 17.857811038353603, "flow_matching_loss": 0.022127828933298586, "grad_norm": 0.13329412043094635, "invalid_tail_samples": 27.0, "learning_rate": 3.2009587025730764e-05, "loss": 0.0244, "positive_teacher_pairs": 26113.4, "relation_loss": 0.00225494250189513, "selected_pairs": 26113.4, "step": 19090, "student_distance_mean": 1269.2757202148437, "teacher_distance_mean": 0.8547636091709137, "valid_action_samples": 229.0, "weighted_auxiliary_loss": 0.00225494250189513, "weighted_relation_loss": 0.00225494250189513 }, { "action_query_batch_std": 22.26636486053467, "action_query_norm": 948.7797485351563, "action_relation_loss": 0.002299470407888293, "auxiliary_loss_weight": 1.0, "epoch": 17.86716557530402, "flow_matching_loss": 0.022520414739847183, "grad_norm": 0.10141510516405106, "invalid_tail_samples": 22.1, "learning_rate": 3.195817360707207e-05, "loss": 0.0248, "positive_teacher_pairs": 27247.5, "relation_loss": 0.002299470407888293, "selected_pairs": 27247.5, "step": 19100, "student_distance_mean": 1272.4672729492188, "teacher_distance_mean": 0.8567805290222168, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.002299470407888293, "weighted_relation_loss": 0.002299470407888293 }, { "action_query_batch_std": 22.367104530334473, "action_query_norm": 951.7710632324219, "action_relation_loss": 0.00229438291862607, "auxiliary_loss_weight": 1.0, "epoch": 17.876520112254443, "flow_matching_loss": 0.02100059874355793, "grad_norm": 0.09005936235189438, "invalid_tail_samples": 25.2, "learning_rate": 3.19067821109337e-05, "loss": 0.0233, "positive_teacher_pairs": 26526.9, "relation_loss": 0.00229438291862607, "selected_pairs": 26526.9, "step": 19110, "student_distance_mean": 1286.1915405273437, "teacher_distance_mean": 0.8633838295936584, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.00229438291862607, "weighted_relation_loss": 0.00229438291862607 }, { "action_query_batch_std": 22.312145233154297, "action_query_norm": 949.8723205566406, "action_relation_loss": 0.002260094857774675, "auxiliary_loss_weight": 1.0, "epoch": 17.885874649204865, "flow_matching_loss": 0.022031399980187417, "grad_norm": 0.07897331565618515, "invalid_tail_samples": 23.5, "learning_rate": 3.185541259976114e-05, "loss": 0.0243, "positive_teacher_pairs": 26915.6, "relation_loss": 0.002260094857774675, "selected_pairs": 26915.6, "step": 19120, "student_distance_mean": 1277.6934448242187, "teacher_distance_mean": 0.8546323716640473, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.002260094857774675, "weighted_relation_loss": 0.002260094857774675 }, { "action_query_batch_std": 22.04424419403076, "action_query_norm": 944.5898864746093, "action_relation_loss": 0.002242927299812436, "auxiliary_loss_weight": 1.0, "epoch": 17.895229186155284, "flow_matching_loss": 0.02151937335729599, "grad_norm": 0.07867660373449326, "invalid_tail_samples": 22.4, "learning_rate": 3.180406513597316e-05, "loss": 0.0238, "positive_teacher_pairs": 27181.6, "relation_loss": 0.002242927299812436, "selected_pairs": 27181.6, "step": 19130, "student_distance_mean": 1261.7935546875, "teacher_distance_mean": 0.8495950758457184, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.002242927299812436, "weighted_relation_loss": 0.002242927299812436 }, { "action_query_batch_std": 22.273977279663086, "action_query_norm": 945.8162719726563, "action_relation_loss": 0.00228330644313246, "auxiliary_loss_weight": 1.0, "epoch": 17.904583723105706, "flow_matching_loss": 0.023585664667189123, "grad_norm": 0.09591848403215408, "invalid_tail_samples": 22.8, "learning_rate": 3.1752739781961835e-05, "loss": 0.0259, "positive_teacher_pairs": 27081.5, "relation_loss": 0.00228330644313246, "selected_pairs": 27081.5, "step": 19140, "student_distance_mean": 1271.7231689453124, "teacher_distance_mean": 0.8600888133049012, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.00228330644313246, "weighted_relation_loss": 0.00228330644313246 }, { "action_query_batch_std": 21.993515396118163, "action_query_norm": 939.0674438476562, "action_relation_loss": 0.0022634442197158934, "auxiliary_loss_weight": 1.0, "epoch": 17.913938260056128, "flow_matching_loss": 0.023165320791304112, "grad_norm": 0.0934927836060524, "invalid_tail_samples": 26.1, "learning_rate": 3.170143660009228e-05, "loss": 0.0254, "positive_teacher_pairs": 26319.1, "relation_loss": 0.0022634442197158934, "selected_pairs": 26319.1, "step": 19150, "student_distance_mean": 1263.8490478515625, "teacher_distance_mean": 0.8480320274829865, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.0022634442197158934, "weighted_relation_loss": 0.0022634442197158934 }, { "action_query_batch_std": 22.22385654449463, "action_query_norm": 946.5815673828125, "action_relation_loss": 0.0022459704196080565, "auxiliary_loss_weight": 1.0, "epoch": 17.92329279700655, "flow_matching_loss": 0.021377637796103955, "grad_norm": 0.0982813686132431, "invalid_tail_samples": 24.8, "learning_rate": 3.16501556527027e-05, "loss": 0.0236, "positive_teacher_pairs": 26629.6, "relation_loss": 0.0022459704196080565, "selected_pairs": 26629.6, "step": 19160, "student_distance_mean": 1263.300634765625, "teacher_distance_mean": 0.8475718796253204, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0022459704196080565, "weighted_relation_loss": 0.0022459704196080565 }, { "action_query_batch_std": 22.127118873596192, "action_query_norm": 946.1380493164063, "action_relation_loss": 0.0022067716810852287, "auxiliary_loss_weight": 1.0, "epoch": 17.932647333956968, "flow_matching_loss": 0.022147178836166858, "grad_norm": 0.09444110840559006, "invalid_tail_samples": 20.9, "learning_rate": 3.1598897002104265e-05, "loss": 0.0244, "positive_teacher_pairs": 27526.3, "relation_loss": 0.0022067716810852287, "selected_pairs": 27526.3, "step": 19170, "student_distance_mean": 1266.6798828125, "teacher_distance_mean": 0.8486570298671723, "valid_action_samples": 235.1, "weighted_auxiliary_loss": 0.0022067716810852287, "weighted_relation_loss": 0.0022067716810852287 }, { "action_query_batch_std": 22.429685974121092, "action_query_norm": 955.9540771484375, "action_relation_loss": 0.0022315123467706146, "auxiliary_loss_weight": 1.0, "epoch": 17.94200187090739, "flow_matching_loss": 0.021703693829476834, "grad_norm": 0.0872616320848465, "invalid_tail_samples": 25.4, "learning_rate": 3.154766071058108e-05, "loss": 0.0239, "positive_teacher_pairs": 26483.2, "relation_loss": 0.0022315123467706146, "selected_pairs": 26483.2, "step": 19180, "student_distance_mean": 1284.13232421875, "teacher_distance_mean": 0.859505432844162, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.0022315123467706146, "weighted_relation_loss": 0.0022315123467706146 }, { "action_query_batch_std": 22.29389705657959, "action_query_norm": 949.6777893066406, "action_relation_loss": 0.0022587573155760767, "auxiliary_loss_weight": 1.0, "epoch": 17.951356407857812, "flow_matching_loss": 0.021746225096285342, "grad_norm": 0.10867416113615036, "invalid_tail_samples": 23.6, "learning_rate": 3.149644684039008e-05, "loss": 0.024, "positive_teacher_pairs": 26896.1, "relation_loss": 0.0022587573155760767, "selected_pairs": 26896.1, "step": 19190, "student_distance_mean": 1276.5590698242188, "teacher_distance_mean": 0.8509203493595123, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0022587573155760767, "weighted_relation_loss": 0.0022587573155760767 }, { "action_query_batch_std": 22.31080741882324, "action_query_norm": 950.4174194335938, "action_relation_loss": 0.0022808223264291884, "auxiliary_loss_weight": 1.0, "epoch": 17.96071094480823, "flow_matching_loss": 0.022723627090454102, "grad_norm": 0.09431006014347076, "invalid_tail_samples": 26.5, "learning_rate": 3.144525545376095e-05, "loss": 0.025, "positive_teacher_pairs": 26225.4, "relation_loss": 0.0022808223264291884, "selected_pairs": 26225.4, "step": 19200, "student_distance_mean": 1281.9459716796875, "teacher_distance_mean": 0.8552833795547485, "valid_action_samples": 229.5, "weighted_auxiliary_loss": 0.0022808223264291884, "weighted_relation_loss": 0.0022808223264291884 }, { "action_query_batch_std": 22.125913047790526, "action_query_norm": 945.8824523925781, "action_relation_loss": 0.0021915537305176257, "auxiliary_loss_weight": 1.0, "epoch": 17.970065481758652, "flow_matching_loss": 0.021511182002723218, "grad_norm": 0.09774186462163925, "invalid_tail_samples": 25.8, "learning_rate": 3.139408661289603e-05, "loss": 0.0237, "positive_teacher_pairs": 26388.2, "relation_loss": 0.0021915537305176257, "selected_pairs": 26388.2, "step": 19210, "student_distance_mean": 1271.8116333007813, "teacher_distance_mean": 0.8518975794315338, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.0021915537305176257, "weighted_relation_loss": 0.0021915537305176257 }, { "action_query_batch_std": 22.424354362487794, "action_query_norm": 952.1435607910156, "action_relation_loss": 0.0022655131062492726, "auxiliary_loss_weight": 1.0, "epoch": 17.979420018709074, "flow_matching_loss": 0.021169758401811123, "grad_norm": 0.11125623434782028, "invalid_tail_samples": 25.0, "learning_rate": 3.134294037997032e-05, "loss": 0.0234, "positive_teacher_pairs": 26577.9, "relation_loss": 0.0022655131062492726, "selected_pairs": 26577.9, "step": 19220, "student_distance_mean": 1286.5099243164063, "teacher_distance_mean": 0.8646668195724487, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0022655131062492726, "weighted_relation_loss": 0.0022655131062492726 }, { "action_query_batch_std": 22.029029846191406, "action_query_norm": 941.4697631835937, "action_relation_loss": 0.0022310372442007065, "auxiliary_loss_weight": 1.0, "epoch": 17.988774555659496, "flow_matching_loss": 0.021186819672584532, "grad_norm": 0.08357179909944534, "invalid_tail_samples": 22.9, "learning_rate": 3.129181681713127e-05, "loss": 0.0234, "positive_teacher_pairs": 27057.2, "relation_loss": 0.0022310372442007065, "selected_pairs": 27057.2, "step": 19230, "student_distance_mean": 1265.632275390625, "teacher_distance_mean": 0.8520458459854126, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0022310372442007065, "weighted_relation_loss": 0.0022310372442007065 }, { "action_query_batch_std": 21.999347305297853, "action_query_norm": 936.8924011230469, "action_relation_loss": 0.002321977843530476, "auxiliary_loss_weight": 1.0, "epoch": 17.998129092609915, "flow_matching_loss": 0.023238639533519744, "grad_norm": 0.11499476432800293, "invalid_tail_samples": 24.3, "learning_rate": 3.1240715986498855e-05, "loss": 0.0256, "positive_teacher_pairs": 26733.5, "relation_loss": 0.002321977843530476, "selected_pairs": 26733.5, "step": 19240, "student_distance_mean": 1258.1956298828125, "teacher_distance_mean": 0.849436491727829, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.002321977843530476, "weighted_relation_loss": 0.002321977843530476 }, { "action_query_batch_std": 22.080563163757326, "action_query_norm": 945.1486999511719, "action_relation_loss": 0.0024191520642489195, "auxiliary_loss_weight": 1.0, "epoch": 18.007483629560337, "flow_matching_loss": 0.022769251465797426, "grad_norm": 0.10736595094203949, "invalid_tail_samples": 19.1, "learning_rate": 3.1189637950165394e-05, "loss": 0.0252, "positive_teacher_pairs": 24955.9, "relation_loss": 0.0024191520642489195, "selected_pairs": 24955.9, "step": 19250, "student_distance_mean": 1267.8667846679687, "teacher_distance_mean": 0.8541015625, "valid_action_samples": 217.0, "weighted_auxiliary_loss": 0.0024191520642489195, "weighted_relation_loss": 0.0024191520642489195 }, { "action_query_batch_std": 22.449260330200197, "action_query_norm": 954.8887451171875, "action_relation_loss": 0.002218205970712006, "auxiliary_loss_weight": 1.0, "epoch": 18.01683816651076, "flow_matching_loss": 0.022699695266783237, "grad_norm": 0.10075611621141434, "invalid_tail_samples": 21.3, "learning_rate": 3.1138582770195544e-05, "loss": 0.0249, "positive_teacher_pairs": 27433.0, "relation_loss": 0.002218205970712006, "selected_pairs": 27433.0, "step": 19260, "student_distance_mean": 1288.5862060546874, "teacher_distance_mean": 0.8679484009742737, "valid_action_samples": 234.7, "weighted_auxiliary_loss": 0.002218205970712006, "weighted_relation_loss": 0.002218205970712006 }, { "action_query_batch_std": 22.073809814453124, "action_query_norm": 947.9745666503907, "action_relation_loss": 0.0022827507578767835, "auxiliary_loss_weight": 1.0, "epoch": 18.026192703461177, "flow_matching_loss": 0.02247372269630432, "grad_norm": 0.09041912108659744, "invalid_tail_samples": 23.6, "learning_rate": 3.108755050862615e-05, "loss": 0.0248, "positive_teacher_pairs": 26895.0, "relation_loss": 0.0022827507578767835, "selected_pairs": 26895.0, "step": 19270, "student_distance_mean": 1265.7244995117187, "teacher_distance_mean": 0.8464107871055603, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0022827507578767835, "weighted_relation_loss": 0.0022827507578767835 }, { "action_query_batch_std": 22.382887077331542, "action_query_norm": 955.4473815917969, "action_relation_loss": 0.002121674234513193, "auxiliary_loss_weight": 1.0, "epoch": 18.0355472404116, "flow_matching_loss": 0.023653368279337884, "grad_norm": 0.10851926356554031, "invalid_tail_samples": 21.5, "learning_rate": 3.1036541227466204e-05, "loss": 0.0258, "positive_teacher_pairs": 27379.5, "relation_loss": 0.002121674234513193, "selected_pairs": 27379.5, "step": 19280, "student_distance_mean": 1282.911328125, "teacher_distance_mean": 0.8583579957485199, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.002121674234513193, "weighted_relation_loss": 0.002121674234513193 }, { "action_query_batch_std": 22.363624000549315, "action_query_norm": 948.7693908691406, "action_relation_loss": 0.0021937977988272907, "auxiliary_loss_weight": 1.0, "epoch": 18.04490177736202, "flow_matching_loss": 0.021981995925307272, "grad_norm": 0.08940211683511734, "invalid_tail_samples": 24.8, "learning_rate": 3.0985554988696786e-05, "loss": 0.0242, "positive_teacher_pairs": 26622.2, "relation_loss": 0.0021937977988272907, "selected_pairs": 26622.2, "step": 19290, "student_distance_mean": 1286.514404296875, "teacher_distance_mean": 0.8675544619560241, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0021937977988272907, "weighted_relation_loss": 0.0021937977988272907 }, { "action_query_batch_std": 22.261075019836426, "action_query_norm": 948.5249450683593, "action_relation_loss": 0.002194133505690843, "auxiliary_loss_weight": 1.0, "epoch": 18.054256314312443, "flow_matching_loss": 0.022497002407908438, "grad_norm": 0.09883818030357361, "invalid_tail_samples": 22.5, "learning_rate": 3.093459185427102e-05, "loss": 0.0247, "positive_teacher_pairs": 27150.4, "relation_loss": 0.002194133505690843, "selected_pairs": 27150.4, "step": 19300, "student_distance_mean": 1272.684619140625, "teacher_distance_mean": 0.8553444743156433, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.002194133505690843, "weighted_relation_loss": 0.002194133505690843 }, { "action_query_batch_std": 22.149224472045898, "action_query_norm": 944.0490600585938, "action_relation_loss": 0.002195665659382939, "auxiliary_loss_weight": 1.0, "epoch": 18.06361085126286, "flow_matching_loss": 0.02073647119104862, "grad_norm": 0.0933007299900055, "invalid_tail_samples": 25.0, "learning_rate": 3.0883651886113905e-05, "loss": 0.0229, "positive_teacher_pairs": 26582.5, "relation_loss": 0.002195665659382939, "selected_pairs": 26582.5, "step": 19310, "student_distance_mean": 1270.0408447265625, "teacher_distance_mean": 0.8530652940273284, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.002195665659382939, "weighted_relation_loss": 0.002195665659382939 }, { "action_query_batch_std": 22.082393455505372, "action_query_norm": 943.7643249511718, "action_relation_loss": 0.0022239842219278216, "auxiliary_loss_weight": 1.0, "epoch": 18.072965388213284, "flow_matching_loss": 0.022579259239137173, "grad_norm": 0.10960447788238525, "invalid_tail_samples": 24.3, "learning_rate": 3.0832735146122294e-05, "loss": 0.0248, "positive_teacher_pairs": 26733.4, "relation_loss": 0.0022239842219278216, "selected_pairs": 26733.4, "step": 19320, "student_distance_mean": 1269.15810546875, "teacher_distance_mean": 0.8500696539878845, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0022239842219278216, "weighted_relation_loss": 0.0022239842219278216 }, { "action_query_batch_std": 22.32659568786621, "action_query_norm": 952.9384704589844, "action_relation_loss": 0.0022346389479935167, "auxiliary_loss_weight": 1.0, "epoch": 18.082319925163706, "flow_matching_loss": 0.022148428857326506, "grad_norm": 0.10178234428167343, "invalid_tail_samples": 22.7, "learning_rate": 3.078184169616485e-05, "loss": 0.0244, "positive_teacher_pairs": 27105.8, "relation_loss": 0.0022346389479935167, "selected_pairs": 27105.8, "step": 19330, "student_distance_mean": 1284.9916870117188, "teacher_distance_mean": 0.8617388665676117, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0022346389479935167, "weighted_relation_loss": 0.0022346389479935167 }, { "action_query_batch_std": 22.192210388183593, "action_query_norm": 945.017724609375, "action_relation_loss": 0.002135021868161857, "auxiliary_loss_weight": 1.0, "epoch": 18.091674462114124, "flow_matching_loss": 0.021208572946488858, "grad_norm": 0.10359121114015579, "invalid_tail_samples": 25.6, "learning_rate": 3.073097159808187e-05, "loss": 0.0233, "positive_teacher_pairs": 26442.9, "relation_loss": 0.002135021868161857, "selected_pairs": 26442.9, "step": 19340, "student_distance_mean": 1272.9804443359376, "teacher_distance_mean": 0.8542176842689514, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.002135021868161857, "weighted_relation_loss": 0.002135021868161857 }, { "action_query_batch_std": 22.328876113891603, "action_query_norm": 948.6353210449219, "action_relation_loss": 0.002246780367568135, "auxiliary_loss_weight": 1.0, "epoch": 18.101028999064546, "flow_matching_loss": 0.020429171808063983, "grad_norm": 0.09037991613149643, "invalid_tail_samples": 26.7, "learning_rate": 3.068012491368537e-05, "loss": 0.0227, "positive_teacher_pairs": 26190.4, "relation_loss": 0.002246780367568135, "selected_pairs": 26190.4, "step": 19350, "student_distance_mean": 1282.9551025390624, "teacher_distance_mean": 0.8568482577800751, "valid_action_samples": 229.3, "weighted_auxiliary_loss": 0.002246780367568135, "weighted_relation_loss": 0.002246780367568135 }, { "action_query_batch_std": 22.26648063659668, "action_query_norm": 948.6014221191406, "action_relation_loss": 0.002187841315753758, "auxiliary_loss_weight": 1.0, "epoch": 18.110383536014968, "flow_matching_loss": 0.021854417771100997, "grad_norm": 0.06866221874952316, "invalid_tail_samples": 24.4, "learning_rate": 3.062930170475885e-05, "loss": 0.024, "positive_teacher_pairs": 26709.4, "relation_loss": 0.002187841315753758, "selected_pairs": 26709.4, "step": 19360, "student_distance_mean": 1274.5399169921875, "teacher_distance_mean": 0.8473185241222382, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.002187841315753758, "weighted_relation_loss": 0.002187841315753758 }, { "action_query_batch_std": 22.704456901550294, "action_query_norm": 964.2002197265625, "action_relation_loss": 0.00230753836221993, "auxiliary_loss_weight": 1.0, "epoch": 18.119738072965387, "flow_matching_loss": 0.02151756901293993, "grad_norm": 0.0996430441737175, "invalid_tail_samples": 22.6, "learning_rate": 3.057850203305729e-05, "loss": 0.0238, "positive_teacher_pairs": 27129.6, "relation_loss": 0.00230753836221993, "selected_pairs": 27129.6, "step": 19370, "student_distance_mean": 1298.9299438476562, "teacher_distance_mean": 0.8642533183097839, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.00230753836221993, "weighted_relation_loss": 0.00230753836221993 }, { "action_query_batch_std": 22.453570747375487, "action_query_norm": 956.3805419921875, "action_relation_loss": 0.002201410918496549, "auxiliary_loss_weight": 1.0, "epoch": 18.12909260991581, "flow_matching_loss": 0.02208575364202261, "grad_norm": 0.1079552099108696, "invalid_tail_samples": 23.6, "learning_rate": 3.052772596030708e-05, "loss": 0.0243, "positive_teacher_pairs": 26898.7, "relation_loss": 0.002201410918496549, "selected_pairs": 26898.7, "step": 19380, "student_distance_mean": 1290.8301147460938, "teacher_distance_mean": 0.8604044556617737, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.002201410918496549, "weighted_relation_loss": 0.002201410918496549 }, { "action_query_batch_std": 22.632283020019532, "action_query_norm": 961.6267333984375, "action_relation_loss": 0.0021569493226706983, "auxiliary_loss_weight": 1.0, "epoch": 18.13844714686623, "flow_matching_loss": 0.02072338666766882, "grad_norm": 0.08388162404298782, "invalid_tail_samples": 23.3, "learning_rate": 3.0476973548205943e-05, "loss": 0.0229, "positive_teacher_pairs": 26962.1, "relation_loss": 0.0021569493226706983, "selected_pairs": 26962.1, "step": 19390, "student_distance_mean": 1292.3819946289063, "teacher_distance_mean": 0.8590641498565674, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0021569493226706983, "weighted_relation_loss": 0.0021569493226706983 }, { "action_query_batch_std": 22.521720123291015, "action_query_norm": 955.5361083984375, "action_relation_loss": 0.002140521164983511, "auxiliary_loss_weight": 1.0, "epoch": 18.147801683816652, "flow_matching_loss": 0.022396819852292537, "grad_norm": 0.11776747554540634, "invalid_tail_samples": 24.1, "learning_rate": 3.0426244858422847e-05, "loss": 0.0245, "positive_teacher_pairs": 26778.1, "relation_loss": 0.002140521164983511, "selected_pairs": 26778.1, "step": 19400, "student_distance_mean": 1291.7922485351562, "teacher_distance_mean": 0.8601747334003449, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.002140521164983511, "weighted_relation_loss": 0.002140521164983511 }, { "action_query_batch_std": 22.505288314819335, "action_query_norm": 954.9784973144531, "action_relation_loss": 0.002275441202800721, "auxiliary_loss_weight": 1.0, "epoch": 18.15715622076707, "flow_matching_loss": 0.02193051837384701, "grad_norm": 0.09917259961366653, "invalid_tail_samples": 24.6, "learning_rate": 3.0375539952597943e-05, "loss": 0.0242, "positive_teacher_pairs": 26666.9, "relation_loss": 0.002275441202800721, "selected_pairs": 26666.9, "step": 19410, "student_distance_mean": 1288.816455078125, "teacher_distance_mean": 0.8590372681617737, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.002275441202800721, "weighted_relation_loss": 0.002275441202800721 }, { "action_query_batch_std": 22.26490879058838, "action_query_norm": 949.8020874023438, "action_relation_loss": 0.002164289355278015, "auxiliary_loss_weight": 1.0, "epoch": 18.166510757717493, "flow_matching_loss": 0.019295113161206245, "grad_norm": 0.10366791486740112, "invalid_tail_samples": 25.8, "learning_rate": 3.0324858892342468e-05, "loss": 0.0215, "positive_teacher_pairs": 26387.5, "relation_loss": 0.002164289355278015, "selected_pairs": 26387.5, "step": 19420, "student_distance_mean": 1280.9349609375, "teacher_distance_mean": 0.8549656212329865, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.002164289355278015, "weighted_relation_loss": 0.002164289355278015 }, { "action_query_batch_std": 21.90687656402588, "action_query_norm": 935.9755676269531, "action_relation_loss": 0.002122637361753732, "auxiliary_loss_weight": 1.0, "epoch": 18.175865294667915, "flow_matching_loss": 0.0226348627358675, "grad_norm": 0.10231558978557587, "invalid_tail_samples": 25.8, "learning_rate": 3.0274201739238672e-05, "loss": 0.0248, "positive_teacher_pairs": 26388.4, "relation_loss": 0.002122637361753732, "selected_pairs": 26388.4, "step": 19430, "student_distance_mean": 1264.8501586914062, "teacher_distance_mean": 0.8447066426277161, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.002122637361753732, "weighted_relation_loss": 0.002122637361753732 }, { "action_query_batch_std": 22.291809844970704, "action_query_norm": 950.378173828125, "action_relation_loss": 0.0021523972507566215, "auxiliary_loss_weight": 1.0, "epoch": 18.185219831618333, "flow_matching_loss": 0.021395623125135897, "grad_norm": 0.08762234449386597, "invalid_tail_samples": 22.2, "learning_rate": 3.0223568554839786e-05, "loss": 0.0235, "positive_teacher_pairs": 27230.7, "relation_loss": 0.0021523972507566215, "selected_pairs": 27230.7, "step": 19440, "student_distance_mean": 1282.8741088867187, "teacher_distance_mean": 0.8573775887489319, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.0021523972507566215, "weighted_relation_loss": 0.0021523972507566215 }, { "action_query_batch_std": 22.106444358825684, "action_query_norm": 946.1467224121094, "action_relation_loss": 0.0022643536794930696, "auxiliary_loss_weight": 1.0, "epoch": 18.194574368568755, "flow_matching_loss": 0.020435565523803233, "grad_norm": 0.10506930202245712, "invalid_tail_samples": 24.0, "learning_rate": 3.0172959400669886e-05, "loss": 0.0227, "positive_teacher_pairs": 26812.1, "relation_loss": 0.0022643536794930696, "selected_pairs": 26812.1, "step": 19450, "student_distance_mean": 1265.7156616210937, "teacher_distance_mean": 0.8464733242988587, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0022643536794930696, "weighted_relation_loss": 0.0022643536794930696 }, { "action_query_batch_std": 21.98829174041748, "action_query_norm": 939.4532165527344, "action_relation_loss": 0.002260629553347826, "auxiliary_loss_weight": 1.0, "epoch": 18.203928905519177, "flow_matching_loss": 0.021127592585980893, "grad_norm": 0.08376166969537735, "invalid_tail_samples": 24.3, "learning_rate": 3.0122374338223902e-05, "loss": 0.0234, "positive_teacher_pairs": 26732.2, "relation_loss": 0.002260629553347826, "selected_pairs": 26732.2, "step": 19460, "student_distance_mean": 1259.7168212890624, "teacher_distance_mean": 0.845202374458313, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.002260629553347826, "weighted_relation_loss": 0.002260629553347826 }, { "action_query_batch_std": 22.067518615722655, "action_query_norm": 943.5881042480469, "action_relation_loss": 0.002257660194300115, "auxiliary_loss_weight": 1.0, "epoch": 18.2132834424696, "flow_matching_loss": 0.022047645412385464, "grad_norm": 0.08627200871706009, "invalid_tail_samples": 24.9, "learning_rate": 3.0071813428967427e-05, "loss": 0.0243, "positive_teacher_pairs": 26601.3, "relation_loss": 0.002257660194300115, "selected_pairs": 26601.3, "step": 19470, "student_distance_mean": 1264.1973876953125, "teacher_distance_mean": 0.8506606340408325, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.002257660194300115, "weighted_relation_loss": 0.002257660194300115 }, { "action_query_batch_std": 22.383061027526857, "action_query_norm": 951.6063598632812, "action_relation_loss": 0.0021600448992103337, "auxiliary_loss_weight": 1.0, "epoch": 18.222637979420018, "flow_matching_loss": 0.02153970431536436, "grad_norm": 0.0904780849814415, "invalid_tail_samples": 24.3, "learning_rate": 3.0021276734336746e-05, "loss": 0.0237, "positive_teacher_pairs": 26733.7, "relation_loss": 0.0021600448992103337, "selected_pairs": 26733.7, "step": 19480, "student_distance_mean": 1287.4329711914063, "teacher_distance_mean": 0.8625891327857971, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0021600448992103337, "weighted_relation_loss": 0.0021600448992103337 }, { "action_query_batch_std": 22.312944221496583, "action_query_norm": 948.8403686523437, "action_relation_loss": 0.0022003315854817627, "auxiliary_loss_weight": 1.0, "epoch": 18.23199251637044, "flow_matching_loss": 0.020380769576877355, "grad_norm": 0.10986273735761642, "invalid_tail_samples": 24.0, "learning_rate": 2.997076431573871e-05, "loss": 0.0226, "positive_teacher_pairs": 26814.7, "relation_loss": 0.0022003315854817627, "selected_pairs": 26814.7, "step": 19490, "student_distance_mean": 1279.451171875, "teacher_distance_mean": 0.854188597202301, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0022003315854817627, "weighted_relation_loss": 0.0022003315854817627 }, { "action_query_batch_std": 22.389367866516114, "action_query_norm": 952.0704040527344, "action_relation_loss": 0.0021637688158079984, "auxiliary_loss_weight": 1.0, "epoch": 18.24134705332086, "flow_matching_loss": 0.021785862743854523, "grad_norm": 0.09773819148540497, "invalid_tail_samples": 24.6, "learning_rate": 2.9920276234550636e-05, "loss": 0.0239, "positive_teacher_pairs": 26666.1, "relation_loss": 0.0021637688158079984, "selected_pairs": 26666.1, "step": 19500, "student_distance_mean": 1286.7191772460938, "teacher_distance_mean": 0.858772611618042, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0021637688158079984, "weighted_relation_loss": 0.0021637688158079984 }, { "action_query_batch_std": 22.33410987854004, "action_query_norm": 954.9888122558593, "action_relation_loss": 0.002192059741355479, "auxiliary_loss_weight": 1.0, "epoch": 18.25070159027128, "flow_matching_loss": 0.02284827958792448, "grad_norm": 0.10974500328302383, "invalid_tail_samples": 26.1, "learning_rate": 2.986981255212035e-05, "loss": 0.025, "positive_teacher_pairs": 26322.2, "relation_loss": 0.002192059741355479, "selected_pairs": 26322.2, "step": 19510, "student_distance_mean": 1286.5361694335938, "teacher_distance_mean": 0.8560577154159545, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.002192059741355479, "weighted_relation_loss": 0.002192059741355479 }, { "action_query_batch_std": 22.20979824066162, "action_query_norm": 948.6040344238281, "action_relation_loss": 0.0021534301107749344, "auxiliary_loss_weight": 1.0, "epoch": 18.260056127221702, "flow_matching_loss": 0.02333845868706703, "grad_norm": 0.09379568696022034, "invalid_tail_samples": 23.6, "learning_rate": 2.9819373329765977e-05, "loss": 0.0255, "positive_teacher_pairs": 26897.4, "relation_loss": 0.0021534301107749344, "selected_pairs": 26897.4, "step": 19520, "student_distance_mean": 1274.6620483398438, "teacher_distance_mean": 0.8494709014892579, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0021534301107749344, "weighted_relation_loss": 0.0021534301107749344 }, { "action_query_batch_std": 22.375846099853515, "action_query_norm": 954.1105346679688, "action_relation_loss": 0.002157891576644033, "auxiliary_loss_weight": 1.0, "epoch": 18.269410664172124, "flow_matching_loss": 0.019823467172682286, "grad_norm": 0.11296823620796204, "invalid_tail_samples": 23.3, "learning_rate": 2.9768958628775902e-05, "loss": 0.022, "positive_teacher_pairs": 26965.3, "relation_loss": 0.002157891576644033, "selected_pairs": 26965.3, "step": 19530, "student_distance_mean": 1285.1535034179688, "teacher_distance_mean": 0.8549091815948486, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.002157891576644033, "weighted_relation_loss": 0.002157891576644033 }, { "action_query_batch_std": 22.196086120605468, "action_query_norm": 946.2416259765625, "action_relation_loss": 0.002248966530896723, "auxiliary_loss_weight": 1.0, "epoch": 18.278765201122546, "flow_matching_loss": 0.019976740423589944, "grad_norm": 0.08967071026563644, "invalid_tail_samples": 24.9, "learning_rate": 2.9718568510408762e-05, "loss": 0.0222, "positive_teacher_pairs": 26598.2, "relation_loss": 0.002248966530896723, "selected_pairs": 26598.2, "step": 19540, "student_distance_mean": 1274.9140380859376, "teacher_distance_mean": 0.8511991500854492, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.002248966530896723, "weighted_relation_loss": 0.002248966530896723 }, { "action_query_batch_std": 22.096049499511718, "action_query_norm": 944.9390686035156, "action_relation_loss": 0.002185370377264917, "auxiliary_loss_weight": 1.0, "epoch": 18.288119738072965, "flow_matching_loss": 0.022471679747104643, "grad_norm": 0.09730742871761322, "invalid_tail_samples": 22.4, "learning_rate": 2.9668203035893272e-05, "loss": 0.0247, "positive_teacher_pairs": 27171.5, "relation_loss": 0.002185370377264917, "selected_pairs": 27171.5, "step": 19550, "student_distance_mean": 1268.114697265625, "teacher_distance_mean": 0.8483382046222687, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.002185370377264917, "weighted_relation_loss": 0.002185370377264917 }, { "action_query_batch_std": 22.21429023742676, "action_query_norm": 948.1052978515625, "action_relation_loss": 0.0022146680392324926, "auxiliary_loss_weight": 1.0, "epoch": 18.297474275023387, "flow_matching_loss": 0.021895600110292436, "grad_norm": 0.10091843456029892, "invalid_tail_samples": 24.7, "learning_rate": 2.9617862266428287e-05, "loss": 0.0241, "positive_teacher_pairs": 26642.5, "relation_loss": 0.0022146680392324926, "selected_pairs": 26642.5, "step": 19560, "student_distance_mean": 1274.5890625, "teacher_distance_mean": 0.850154447555542, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0022146680392324926, "weighted_relation_loss": 0.0022146680392324926 }, { "action_query_batch_std": 22.27326602935791, "action_query_norm": 951.4461486816406, "action_relation_loss": 0.0022539991652593015, "auxiliary_loss_weight": 1.0, "epoch": 18.30682881197381, "flow_matching_loss": 0.02375091575086117, "grad_norm": 0.10337342321872711, "invalid_tail_samples": 19.8, "learning_rate": 2.9567546263182556e-05, "loss": 0.026, "positive_teacher_pairs": 27784.2, "relation_loss": 0.0022539991652593015, "selected_pairs": 27784.2, "step": 19570, "student_distance_mean": 1276.6451538085937, "teacher_distance_mean": 0.8502439260482788, "valid_action_samples": 236.2, "weighted_auxiliary_loss": 0.0022539991652593015, "weighted_relation_loss": 0.0022539991652593015 }, { "action_query_batch_std": 22.249603843688966, "action_query_norm": 948.2959716796875, "action_relation_loss": 0.0022578914649784565, "auxiliary_loss_weight": 1.0, "epoch": 18.316183348924227, "flow_matching_loss": 0.02320249509066343, "grad_norm": 0.098155677318573, "invalid_tail_samples": 25.5, "learning_rate": 2.951725508729476e-05, "loss": 0.0255, "positive_teacher_pairs": 26463.2, "relation_loss": 0.0022578914649784565, "selected_pairs": 26463.2, "step": 19580, "student_distance_mean": 1280.1535278320312, "teacher_distance_mean": 0.8492608606815338, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0022578914649784565, "weighted_relation_loss": 0.0022578914649784565 }, { "action_query_batch_std": 21.940591049194335, "action_query_norm": 940.0074462890625, "action_relation_loss": 0.0022433413891121746, "auxiliary_loss_weight": 1.0, "epoch": 18.32553788587465, "flow_matching_loss": 0.022000958397984504, "grad_norm": 0.1199265569448471, "invalid_tail_samples": 24.2, "learning_rate": 2.946698879987344e-05, "loss": 0.0242, "positive_teacher_pairs": 26761.1, "relation_loss": 0.0022433413891121746, "selected_pairs": 26761.1, "step": 19590, "student_distance_mean": 1257.04951171875, "teacher_distance_mean": 0.8370276272296906, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0022433413891121746, "weighted_relation_loss": 0.0022433413891121746 }, { "action_query_batch_std": 22.56236801147461, "action_query_norm": 960.4398986816407, "action_relation_loss": 0.0021661690901964904, "auxiliary_loss_weight": 1.0, "epoch": 18.33489242282507, "flow_matching_loss": 0.02234567254781723, "grad_norm": 0.08910170942544937, "invalid_tail_samples": 24.8, "learning_rate": 2.9416747461996853e-05, "loss": 0.0245, "positive_teacher_pairs": 26625.5, "relation_loss": 0.0021661690901964904, "selected_pairs": 26625.5, "step": 19600, "student_distance_mean": 1293.42607421875, "teacher_distance_mean": 0.8621775865554809, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0021661690901964904, "weighted_relation_loss": 0.0021661690901964904 }, { "action_query_batch_std": 22.25848388671875, "action_query_norm": 947.3848449707032, "action_relation_loss": 0.0022964504081755877, "auxiliary_loss_weight": 1.0, "epoch": 18.34424695977549, "flow_matching_loss": 0.021598632633686065, "grad_norm": 0.11959511786699295, "invalid_tail_samples": 25.2, "learning_rate": 2.9366531134712973e-05, "loss": 0.0239, "positive_teacher_pairs": 26521.6, "relation_loss": 0.0022964504081755877, "selected_pairs": 26521.6, "step": 19610, "student_distance_mean": 1273.7461669921875, "teacher_distance_mean": 0.8535040199756623, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0022964504081755877, "weighted_relation_loss": 0.0022964504081755877 }, { "action_query_batch_std": 22.303864860534667, "action_query_norm": 950.2538940429688, "action_relation_loss": 0.0021938261575996875, "auxiliary_loss_weight": 1.0, "epoch": 18.35360149672591, "flow_matching_loss": 0.020750027894973756, "grad_norm": 0.10841990262269974, "invalid_tail_samples": 23.3, "learning_rate": 2.9316339879039367e-05, "loss": 0.0229, "positive_teacher_pairs": 26971.1, "relation_loss": 0.0021938261575996875, "selected_pairs": 26971.1, "step": 19620, "student_distance_mean": 1282.58408203125, "teacher_distance_mean": 0.8578187227249146, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0021938261575996875, "weighted_relation_loss": 0.0021938261575996875 }, { "action_query_batch_std": 22.067174911499023, "action_query_norm": 940.8328125, "action_relation_loss": 0.00227159708738327, "auxiliary_loss_weight": 1.0, "epoch": 18.362956033676333, "flow_matching_loss": 0.021156198531389236, "grad_norm": 0.09197483956813812, "invalid_tail_samples": 22.5, "learning_rate": 2.9266173755963167e-05, "loss": 0.0234, "positive_teacher_pairs": 27152.3, "relation_loss": 0.00227159708738327, "selected_pairs": 27152.3, "step": 19630, "student_distance_mean": 1264.3013427734375, "teacher_distance_mean": 0.8456463754177094, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.00227159708738327, "weighted_relation_loss": 0.00227159708738327 }, { "action_query_batch_std": 22.06715202331543, "action_query_norm": 942.42216796875, "action_relation_loss": 0.0021710199769586326, "auxiliary_loss_weight": 1.0, "epoch": 18.372310570626755, "flow_matching_loss": 0.02001576218754053, "grad_norm": 0.09413336962461472, "invalid_tail_samples": 23.3, "learning_rate": 2.9216032826440926e-05, "loss": 0.0222, "positive_teacher_pairs": 26963.2, "relation_loss": 0.0021710199769586326, "selected_pairs": 26963.2, "step": 19640, "student_distance_mean": 1266.5830200195312, "teacher_distance_mean": 0.8437573075294494, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0021710199769586326, "weighted_relation_loss": 0.0021710199769586326 }, { "action_query_batch_std": 22.587112998962404, "action_query_norm": 962.2348937988281, "action_relation_loss": 0.0021806353237479926, "auxiliary_loss_weight": 1.0, "epoch": 18.381665107577174, "flow_matching_loss": 0.021050899103283883, "grad_norm": 0.10408319532871246, "invalid_tail_samples": 24.0, "learning_rate": 2.9165917151398592e-05, "loss": 0.0232, "positive_teacher_pairs": 26805.9, "relation_loss": 0.0021806353237479926, "selected_pairs": 26805.9, "step": 19650, "student_distance_mean": 1296.9133544921874, "teacher_distance_mean": 0.8637557208538056, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0021806353237479926, "weighted_relation_loss": 0.0021806353237479926 }, { "action_query_batch_std": 22.685263442993165, "action_query_norm": 962.7735961914062, "action_relation_loss": 0.002100236830301583, "auxiliary_loss_weight": 1.0, "epoch": 18.391019644527596, "flow_matching_loss": 0.021759011410176755, "grad_norm": 0.09481988102197647, "invalid_tail_samples": 22.8, "learning_rate": 2.9115826791731428e-05, "loss": 0.0239, "positive_teacher_pairs": 27093.6, "relation_loss": 0.002100236830301583, "selected_pairs": 27093.6, "step": 19660, "student_distance_mean": 1297.077294921875, "teacher_distance_mean": 0.8645600199699401, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.002100236830301583, "weighted_relation_loss": 0.002100236830301583 }, { "action_query_batch_std": 22.394241333007812, "action_query_norm": 953.6055603027344, "action_relation_loss": 0.0021866460447199643, "auxiliary_loss_weight": 1.0, "epoch": 18.400374181478018, "flow_matching_loss": 0.02199536096304655, "grad_norm": 0.09570712596178055, "invalid_tail_samples": 23.9, "learning_rate": 2.906576180830398e-05, "loss": 0.0242, "positive_teacher_pairs": 26831.8, "relation_loss": 0.0021866460447199643, "selected_pairs": 26831.8, "step": 19670, "student_distance_mean": 1291.0900390625, "teacher_distance_mean": 0.8607929170131683, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0021866460447199643, "weighted_relation_loss": 0.0021866460447199643 }, { "action_query_batch_std": 22.144581985473632, "action_query_norm": 949.0113891601562, "action_relation_loss": 0.0021975029609166085, "auxiliary_loss_weight": 1.0, "epoch": 18.409728718428436, "flow_matching_loss": 0.020043743215501307, "grad_norm": 0.09787897765636444, "invalid_tail_samples": 24.4, "learning_rate": 2.9015722261949917e-05, "loss": 0.0222, "positive_teacher_pairs": 26712.5, "relation_loss": 0.0021975029609166085, "selected_pairs": 26712.5, "step": 19680, "student_distance_mean": 1271.3595458984375, "teacher_distance_mean": 0.8486388802528382, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0021975029609166085, "weighted_relation_loss": 0.0021975029609166085 }, { "action_query_batch_std": 22.272714042663573, "action_query_norm": 949.311279296875, "action_relation_loss": 0.002167564199771732, "auxiliary_loss_weight": 1.0, "epoch": 18.419083255378858, "flow_matching_loss": 0.0220116401091218, "grad_norm": 0.11559562385082245, "invalid_tail_samples": 23.2, "learning_rate": 2.8965708213471986e-05, "loss": 0.0242, "positive_teacher_pairs": 26984.7, "relation_loss": 0.002167564199771732, "selected_pairs": 26984.7, "step": 19690, "student_distance_mean": 1277.8715087890625, "teacher_distance_mean": 0.8547618389129639, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.002167564199771732, "weighted_relation_loss": 0.002167564199771732 }, { "action_query_batch_std": 22.25947151184082, "action_query_norm": 950.4169006347656, "action_relation_loss": 0.0022203736705705525, "auxiliary_loss_weight": 1.0, "epoch": 18.42843779232928, "flow_matching_loss": 0.021980374306440353, "grad_norm": 0.13123081624507904, "invalid_tail_samples": 24.0, "learning_rate": 2.8915719723641975e-05, "loss": 0.0242, "positive_teacher_pairs": 26802.2, "relation_loss": 0.0022203736705705525, "selected_pairs": 26802.2, "step": 19700, "student_distance_mean": 1269.597314453125, "teacher_distance_mean": 0.84865021109581, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0022203736705705525, "weighted_relation_loss": 0.0022203736705705525 }, { "action_query_batch_std": 22.430014610290527, "action_query_norm": 954.0366271972656, "action_relation_loss": 0.002331631490960717, "auxiliary_loss_weight": 1.0, "epoch": 18.437792329279702, "flow_matching_loss": 0.021980582550168038, "grad_norm": 0.10942772030830383, "invalid_tail_samples": 23.3, "learning_rate": 2.8865756853200604e-05, "loss": 0.0243, "positive_teacher_pairs": 26972.9, "relation_loss": 0.002331631490960717, "selected_pairs": 26972.9, "step": 19710, "student_distance_mean": 1287.7578857421875, "teacher_distance_mean": 0.8594668686389924, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.002331631490960717, "weighted_relation_loss": 0.002331631490960717 }, { "action_query_batch_std": 22.288331604003908, "action_query_norm": 950.3813293457031, "action_relation_loss": 0.002188185625709593, "auxiliary_loss_weight": 1.0, "epoch": 18.44714686623012, "flow_matching_loss": 0.020417193975299598, "grad_norm": 0.11831976473331451, "invalid_tail_samples": 26.0, "learning_rate": 2.8815819662857503e-05, "loss": 0.0226, "positive_teacher_pairs": 26343.1, "relation_loss": 0.002188185625709593, "selected_pairs": 26343.1, "step": 19720, "student_distance_mean": 1288.803857421875, "teacher_distance_mean": 0.8570678651332855, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.002188185625709593, "weighted_relation_loss": 0.002188185625709593 }, { "action_query_batch_std": 22.421968269348145, "action_query_norm": 953.5296020507812, "action_relation_loss": 0.0022211677744053302, "auxiliary_loss_weight": 1.0, "epoch": 18.456501403180543, "flow_matching_loss": 0.022770129702985288, "grad_norm": 0.09868737310171127, "invalid_tail_samples": 22.3, "learning_rate": 2.876590821329105e-05, "loss": 0.025, "positive_teacher_pairs": 27195.8, "relation_loss": 0.0022211677744053302, "selected_pairs": 27195.8, "step": 19730, "student_distance_mean": 1285.72958984375, "teacher_distance_mean": 0.8560385882854462, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0022211677744053302, "weighted_relation_loss": 0.0022211677744053302 }, { "action_query_batch_std": 22.4810302734375, "action_query_norm": 955.84765625, "action_relation_loss": 0.0021969803608953955, "auxiliary_loss_weight": 1.0, "epoch": 18.465855940130965, "flow_matching_loss": 0.022857123240828513, "grad_norm": 0.0759829506278038, "invalid_tail_samples": 23.3, "learning_rate": 2.871602256514836e-05, "loss": 0.0251, "positive_teacher_pairs": 26966.2, "relation_loss": 0.0021969803608953955, "selected_pairs": 26966.2, "step": 19740, "student_distance_mean": 1292.4406616210938, "teacher_distance_mean": 0.863780802488327, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0021969803608953955, "weighted_relation_loss": 0.0021969803608953955 }, { "action_query_batch_std": 22.394734954833986, "action_query_norm": 954.8136169433594, "action_relation_loss": 0.0022236990043893456, "auxiliary_loss_weight": 1.0, "epoch": 18.475210477081383, "flow_matching_loss": 0.01983726564794779, "grad_norm": 0.10318934917449951, "invalid_tail_samples": 23.0, "learning_rate": 2.8666162779045203e-05, "loss": 0.0221, "positive_teacher_pairs": 27036.5, "relation_loss": 0.0022236990043893456, "selected_pairs": 27036.5, "step": 19750, "student_distance_mean": 1288.0540405273437, "teacher_distance_mean": 0.8592106580734253, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0022236990043893456, "weighted_relation_loss": 0.0022236990043893456 }, { "action_query_batch_std": 22.28502502441406, "action_query_norm": 945.9573669433594, "action_relation_loss": 0.002186007075943053, "auxiliary_loss_weight": 1.0, "epoch": 18.484565014031805, "flow_matching_loss": 0.021826305240392686, "grad_norm": 0.09760360419750214, "invalid_tail_samples": 22.0, "learning_rate": 2.8616328915565904e-05, "loss": 0.024, "positive_teacher_pairs": 27267.6, "relation_loss": 0.002186007075943053, "selected_pairs": 27267.6, "step": 19760, "student_distance_mean": 1278.5565185546875, "teacher_distance_mean": 0.8537887811660767, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.002186007075943053, "weighted_relation_loss": 0.002186007075943053 }, { "action_query_batch_std": 22.557155990600585, "action_query_norm": 956.8310913085937, "action_relation_loss": 0.002196540194563568, "auxiliary_loss_weight": 1.0, "epoch": 18.493919550982227, "flow_matching_loss": 0.023455033265054225, "grad_norm": 0.09191596508026123, "invalid_tail_samples": 24.7, "learning_rate": 2.856652103526334e-05, "loss": 0.0257, "positive_teacher_pairs": 26648.7, "relation_loss": 0.002196540194563568, "selected_pairs": 26648.7, "step": 19770, "student_distance_mean": 1291.0263549804688, "teacher_distance_mean": 0.8601207256317138, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.002196540194563568, "weighted_relation_loss": 0.002196540194563568 }, { "action_query_batch_std": 22.489799880981444, "action_query_norm": 958.057373046875, "action_relation_loss": 0.0021715355687774718, "auxiliary_loss_weight": 1.0, "epoch": 18.50327408793265, "flow_matching_loss": 0.021134616713970898, "grad_norm": 0.11177122592926025, "invalid_tail_samples": 23.1, "learning_rate": 2.8516739198658755e-05, "loss": 0.0233, "positive_teacher_pairs": 27010.2, "relation_loss": 0.0021715355687774718, "selected_pairs": 27010.2, "step": 19780, "student_distance_mean": 1292.7947631835937, "teacher_distance_mean": 0.8561775147914886, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0021715355687774718, "weighted_relation_loss": 0.0021715355687774718 }, { "action_query_batch_std": 22.83746757507324, "action_query_norm": 969.3184936523437, "action_relation_loss": 0.002186005236580968, "auxiliary_loss_weight": 1.0, "epoch": 18.512628624883067, "flow_matching_loss": 0.020857050083577633, "grad_norm": 0.09457916766405106, "invalid_tail_samples": 22.3, "learning_rate": 2.846698346624177e-05, "loss": 0.023, "positive_teacher_pairs": 27197.8, "relation_loss": 0.002186005236580968, "selected_pairs": 27197.8, "step": 19790, "student_distance_mean": 1308.937548828125, "teacher_distance_mean": 0.8694282591342926, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.002186005236580968, "weighted_relation_loss": 0.002186005236580968 }, { "action_query_batch_std": 22.220551109313966, "action_query_norm": 945.7005187988282, "action_relation_loss": 0.002201530523598194, "auxiliary_loss_weight": 1.0, "epoch": 18.52198316183349, "flow_matching_loss": 0.01961846025660634, "grad_norm": 0.10041534155607224, "invalid_tail_samples": 22.0, "learning_rate": 2.841725389847032e-05, "loss": 0.0218, "positive_teacher_pairs": 27264.6, "relation_loss": 0.002201530523598194, "selected_pairs": 27264.6, "step": 19800, "student_distance_mean": 1273.2857055664062, "teacher_distance_mean": 0.8536351382732391, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.002201530523598194, "weighted_relation_loss": 0.002201530523598194 }, { "action_query_batch_std": 22.324165725708006, "action_query_norm": 950.0904296875, "action_relation_loss": 0.0021168709034100177, "auxiliary_loss_weight": 1.0, "epoch": 18.53133769878391, "flow_matching_loss": 0.021349932998418808, "grad_norm": 0.07908222079277039, "invalid_tail_samples": 24.8, "learning_rate": 2.8367550555770506e-05, "loss": 0.0235, "positive_teacher_pairs": 26622.3, "relation_loss": 0.0021168709034100177, "selected_pairs": 26622.3, "step": 19810, "student_distance_mean": 1282.9621704101562, "teacher_distance_mean": 0.8602001070976257, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0021168709034100177, "weighted_relation_loss": 0.0021168709034100177 }, { "action_query_batch_std": 22.867401695251466, "action_query_norm": 965.5198852539063, "action_relation_loss": 0.002070956549141556, "auxiliary_loss_weight": 1.0, "epoch": 18.54069223573433, "flow_matching_loss": 0.02121305214241147, "grad_norm": 0.11211192607879639, "invalid_tail_samples": 22.7, "learning_rate": 2.831787349853655e-05, "loss": 0.0233, "positive_teacher_pairs": 27105.9, "relation_loss": 0.002070956549141556, "selected_pairs": 27105.9, "step": 19820, "student_distance_mean": 1307.754345703125, "teacher_distance_mean": 0.874002856016159, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.002070956549141556, "weighted_relation_loss": 0.002070956549141556 }, { "action_query_batch_std": 22.195831298828125, "action_query_norm": 944.9685913085938, "action_relation_loss": 0.002226291224360466, "auxiliary_loss_weight": 1.0, "epoch": 18.55004677268475, "flow_matching_loss": 0.020709678158164026, "grad_norm": 0.09104809910058975, "invalid_tail_samples": 22.8, "learning_rate": 2.8268222787130806e-05, "loss": 0.0229, "positive_teacher_pairs": 27079.4, "relation_loss": 0.002226291224360466, "selected_pairs": 27079.4, "step": 19830, "student_distance_mean": 1272.1091430664062, "teacher_distance_mean": 0.8480593204498291, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.002226291224360466, "weighted_relation_loss": 0.002226291224360466 }, { "action_query_batch_std": 22.59560890197754, "action_query_norm": 962.3220092773438, "action_relation_loss": 0.0021000292617827654, "auxiliary_loss_weight": 1.0, "epoch": 18.559401309635174, "flow_matching_loss": 0.022418305091559888, "grad_norm": 0.10763407498598099, "invalid_tail_samples": 23.9, "learning_rate": 2.821859848188355e-05, "loss": 0.0245, "positive_teacher_pairs": 26827.1, "relation_loss": 0.0021000292617827654, "selected_pairs": 26827.1, "step": 19840, "student_distance_mean": 1302.53349609375, "teacher_distance_mean": 0.8670372843742371, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0021000292617827654, "weighted_relation_loss": 0.0021000292617827654 }, { "action_query_batch_std": 22.257001686096192, "action_query_norm": 949.7154357910156, "action_relation_loss": 0.0021697202697396278, "auxiliary_loss_weight": 1.0, "epoch": 18.568755846585596, "flow_matching_loss": 0.021802443079650402, "grad_norm": 0.11808571964502335, "invalid_tail_samples": 25.5, "learning_rate": 2.816900064309299e-05, "loss": 0.024, "positive_teacher_pairs": 26459.3, "relation_loss": 0.0021697202697396278, "selected_pairs": 26459.3, "step": 19850, "student_distance_mean": 1280.0859375, "teacher_distance_mean": 0.8545915007591247, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0021697202697396278, "weighted_relation_loss": 0.0021697202697396278 }, { "action_query_batch_std": 22.353591537475587, "action_query_norm": 954.6235778808593, "action_relation_loss": 0.0021088335546664894, "auxiliary_loss_weight": 1.0, "epoch": 18.578110383536014, "flow_matching_loss": 0.023401215486228467, "grad_norm": 0.09593494981527328, "invalid_tail_samples": 23.7, "learning_rate": 2.811942933102517e-05, "loss": 0.0255, "positive_teacher_pairs": 26871.9, "relation_loss": 0.0021088335546664894, "selected_pairs": 26871.9, "step": 19860, "student_distance_mean": 1285.132080078125, "teacher_distance_mean": 0.8565112113952636, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0021088335546664894, "weighted_relation_loss": 0.0021088335546664894 }, { "action_query_batch_std": 22.26026859283447, "action_query_norm": 949.8589660644532, "action_relation_loss": 0.002114211046136916, "auxiliary_loss_weight": 1.0, "epoch": 18.587464920486436, "flow_matching_loss": 0.02093223240226507, "grad_norm": 0.09550724923610687, "invalid_tail_samples": 23.5, "learning_rate": 2.806988460591391e-05, "loss": 0.023, "positive_teacher_pairs": 26916.6, "relation_loss": 0.002114211046136916, "selected_pairs": 26916.6, "step": 19870, "student_distance_mean": 1278.5772705078125, "teacher_distance_mean": 0.8534242689609528, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.002114211046136916, "weighted_relation_loss": 0.002114211046136916 }, { "action_query_batch_std": 22.71415481567383, "action_query_norm": 963.4366149902344, "action_relation_loss": 0.0021460224641487004, "auxiliary_loss_weight": 1.0, "epoch": 18.596819457436858, "flow_matching_loss": 0.021687872521579266, "grad_norm": 0.11518912017345428, "invalid_tail_samples": 21.4, "learning_rate": 2.802036652796074e-05, "loss": 0.0238, "positive_teacher_pairs": 27410.0, "relation_loss": 0.0021460224641487004, "selected_pairs": 27410.0, "step": 19880, "student_distance_mean": 1297.3107421875, "teacher_distance_mean": 0.8655130565166473, "valid_action_samples": 234.6, "weighted_auxiliary_loss": 0.0021460224641487004, "weighted_relation_loss": 0.0021460224641487004 }, { "action_query_batch_std": 22.313366317749022, "action_query_norm": 951.6586303710938, "action_relation_loss": 0.0022196026053279637, "auxiliary_loss_weight": 1.0, "epoch": 18.606173994387277, "flow_matching_loss": 0.02111403439193964, "grad_norm": 0.10165621340274811, "invalid_tail_samples": 26.5, "learning_rate": 2.797087515733478e-05, "loss": 0.0233, "positive_teacher_pairs": 26227.0, "relation_loss": 0.0022196026053279637, "selected_pairs": 26227.0, "step": 19890, "student_distance_mean": 1285.1833740234374, "teacher_distance_mean": 0.8617952525615692, "valid_action_samples": 229.5, "weighted_auxiliary_loss": 0.0022196026053279637, "weighted_relation_loss": 0.0022196026053279637 }, { "action_query_batch_std": 22.421722984313966, "action_query_norm": 954.1569396972657, "action_relation_loss": 0.00221367918420583, "auxiliary_loss_weight": 1.0, "epoch": 18.6155285313377, "flow_matching_loss": 0.021746286004781724, "grad_norm": 0.10168755799531937, "invalid_tail_samples": 22.4, "learning_rate": 2.7921410554172723e-05, "loss": 0.024, "positive_teacher_pairs": 27180.8, "relation_loss": 0.00221367918420583, "selected_pairs": 27180.8, "step": 19900, "student_distance_mean": 1284.9076538085938, "teacher_distance_mean": 0.8594145834445953, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.00221367918420583, "weighted_relation_loss": 0.00221367918420583 }, { "action_query_batch_std": 22.27300968170166, "action_query_norm": 948.6626403808593, "action_relation_loss": 0.0021930640912614765, "auxiliary_loss_weight": 1.0, "epoch": 18.62488306828812, "flow_matching_loss": 0.02280327267944813, "grad_norm": 0.10127381980419159, "invalid_tail_samples": 24.6, "learning_rate": 2.787197277857871e-05, "loss": 0.025, "positive_teacher_pairs": 26676.2, "relation_loss": 0.0021930640912614765, "selected_pairs": 26676.2, "step": 19910, "student_distance_mean": 1280.7348388671876, "teacher_distance_mean": 0.8576735079288482, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0021930640912614765, "weighted_relation_loss": 0.0021930640912614765 }, { "action_query_batch_std": 22.00358638763428, "action_query_norm": 942.1524963378906, "action_relation_loss": 0.0022141973488032816, "auxiliary_loss_weight": 1.0, "epoch": 18.63423760523854, "flow_matching_loss": 0.02197022419422865, "grad_norm": 0.1008976548910141, "invalid_tail_samples": 23.2, "learning_rate": 2.782256189062429e-05, "loss": 0.0242, "positive_teacher_pairs": 26990.8, "relation_loss": 0.0022141973488032816, "selected_pairs": 26990.8, "step": 19920, "student_distance_mean": 1265.0140869140625, "teacher_distance_mean": 0.8463195502758026, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0022141973488032816, "weighted_relation_loss": 0.0022141973488032816 }, { "action_query_batch_std": 22.047609519958495, "action_query_norm": 942.3532348632813, "action_relation_loss": 0.0021973080467432736, "auxiliary_loss_weight": 1.0, "epoch": 18.64359214218896, "flow_matching_loss": 0.021358858421444894, "grad_norm": 0.09465456753969193, "invalid_tail_samples": 23.1, "learning_rate": 2.777317795034839e-05, "loss": 0.0236, "positive_teacher_pairs": 27018.5, "relation_loss": 0.0021973080467432736, "selected_pairs": 27018.5, "step": 19930, "student_distance_mean": 1267.5758544921875, "teacher_distance_mean": 0.8496235430240631, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0021973080467432736, "weighted_relation_loss": 0.0021973080467432736 }, { "action_query_batch_std": 22.2876314163208, "action_query_norm": 949.0816223144532, "action_relation_loss": 0.0020837588352151217, "auxiliary_loss_weight": 1.0, "epoch": 18.652946679139383, "flow_matching_loss": 0.02117961011826992, "grad_norm": 0.09900498390197754, "invalid_tail_samples": 21.2, "learning_rate": 2.7723821017757112e-05, "loss": 0.0233, "positive_teacher_pairs": 27455.1, "relation_loss": 0.0020837588352151217, "selected_pairs": 27455.1, "step": 19940, "student_distance_mean": 1275.5947875976562, "teacher_distance_mean": 0.8568404614925385, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.0020837588352151217, "weighted_relation_loss": 0.0020837588352151217 }, { "action_query_batch_std": 22.588721466064452, "action_query_norm": 959.1376159667968, "action_relation_loss": 0.0022176508093252776, "auxiliary_loss_weight": 1.0, "epoch": 18.662301216089805, "flow_matching_loss": 0.021674894355237485, "grad_norm": 0.11338886618614197, "invalid_tail_samples": 24.2, "learning_rate": 2.7674491152823822e-05, "loss": 0.0239, "positive_teacher_pairs": 26758.1, "relation_loss": 0.0022176508093252776, "selected_pairs": 26758.1, "step": 19950, "student_distance_mean": 1295.3846435546875, "teacher_distance_mean": 0.8664376616477967, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0022176508093252776, "weighted_relation_loss": 0.0022176508093252776 }, { "action_query_batch_std": 22.02473430633545, "action_query_norm": 942.1172241210937, "action_relation_loss": 0.0021751016611233354, "auxiliary_loss_weight": 1.0, "epoch": 18.671655753040223, "flow_matching_loss": 0.01992396228015423, "grad_norm": 0.09438621997833252, "invalid_tail_samples": 23.0, "learning_rate": 2.7625188415488944e-05, "loss": 0.0221, "positive_teacher_pairs": 27031.6, "relation_loss": 0.0021751016611233354, "selected_pairs": 27031.6, "step": 19960, "student_distance_mean": 1263.4282104492188, "teacher_distance_mean": 0.8465493261814118, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0021751016611233354, "weighted_relation_loss": 0.0021751016611233354 }, { "action_query_batch_std": 22.455921936035157, "action_query_norm": 953.2598205566406, "action_relation_loss": 0.002286650997120887, "auxiliary_loss_weight": 1.0, "epoch": 18.681010289990645, "flow_matching_loss": 0.021802389807999135, "grad_norm": 0.1010078713297844, "invalid_tail_samples": 25.4, "learning_rate": 2.7575912865659924e-05, "loss": 0.0241, "positive_teacher_pairs": 26490.1, "relation_loss": 0.002286650997120887, "selected_pairs": 26490.1, "step": 19970, "student_distance_mean": 1292.3858276367187, "teacher_distance_mean": 0.8656992077827453, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.002286650997120887, "weighted_relation_loss": 0.002286650997120887 }, { "action_query_batch_std": 22.40279140472412, "action_query_norm": 953.7941650390625, "action_relation_loss": 0.002230350184254348, "auxiliary_loss_weight": 1.0, "epoch": 18.690364826941067, "flow_matching_loss": 0.02302881460636854, "grad_norm": 0.08077170699834824, "invalid_tail_samples": 25.0, "learning_rate": 2.7526664563211245e-05, "loss": 0.0253, "positive_teacher_pairs": 26576.1, "relation_loss": 0.002230350184254348, "selected_pairs": 26576.1, "step": 19980, "student_distance_mean": 1289.6291137695312, "teacher_distance_mean": 0.8626927077770233, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.002230350184254348, "weighted_relation_loss": 0.002230350184254348 }, { "action_query_batch_std": 22.054176330566406, "action_query_norm": 940.7045349121094, "action_relation_loss": 0.0021285692346282303, "auxiliary_loss_weight": 1.0, "epoch": 18.699719363891486, "flow_matching_loss": 0.02177685983479023, "grad_norm": 0.09821019321680069, "invalid_tail_samples": 23.3, "learning_rate": 2.7477443567984224e-05, "loss": 0.0239, "positive_teacher_pairs": 26978.5, "relation_loss": 0.0021285692346282303, "selected_pairs": 26978.5, "step": 19990, "student_distance_mean": 1269.2823120117187, "teacher_distance_mean": 0.8480072379112243, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0021285692346282303, "weighted_relation_loss": 0.0021285692346282303 }, { "action_query_batch_std": 22.115279769897462, "action_query_norm": 947.0041625976562, "action_relation_loss": 0.002208221913315356, "auxiliary_loss_weight": 1.0, "epoch": 18.709073900841908, "flow_matching_loss": 0.021466767881065607, "grad_norm": 0.07569620758295059, "invalid_tail_samples": 21.5, "learning_rate": 2.7428249939787e-05, "loss": 0.0237, "positive_teacher_pairs": 27381.1, "relation_loss": 0.002208221913315356, "selected_pairs": 27381.1, "step": 20000, "student_distance_mean": 1267.2409301757812, "teacher_distance_mean": 0.8440041184425354, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.002208221913315356, "weighted_relation_loss": 0.002208221913315356 }, { "action_query_batch_std": 22.314865112304688, "action_query_norm": 953.2791198730469, "action_relation_loss": 0.002277629729360342, "auxiliary_loss_weight": 1.0, "epoch": 18.71842843779233, "flow_matching_loss": 0.021128532476723194, "grad_norm": 0.09568293392658234, "invalid_tail_samples": 21.0, "learning_rate": 2.7379083738394484e-05, "loss": 0.0234, "positive_teacher_pairs": 27512.7, "relation_loss": 0.002277629729360342, "selected_pairs": 27512.7, "step": 20010, "student_distance_mean": 1275.6725708007812, "teacher_distance_mean": 0.8519261658191681, "valid_action_samples": 235.0, "weighted_auxiliary_loss": 0.002277629729360342, "weighted_relation_loss": 0.002277629729360342 }, { "action_query_batch_std": 22.1079402923584, "action_query_norm": 944.716552734375, "action_relation_loss": 0.0021913871867582204, "auxiliary_loss_weight": 1.0, "epoch": 18.72778297474275, "flow_matching_loss": 0.02239001225680113, "grad_norm": 0.11906712502241135, "invalid_tail_samples": 24.6, "learning_rate": 2.732994502354823e-05, "loss": 0.0246, "positive_teacher_pairs": 26662.0, "relation_loss": 0.0021913871867582204, "selected_pairs": 26662.0, "step": 20020, "student_distance_mean": 1269.6506469726562, "teacher_distance_mean": 0.8431577920913697, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0021913871867582204, "weighted_relation_loss": 0.0021913871867582204 }, { "action_query_batch_std": 22.344511032104492, "action_query_norm": 952.5336364746094, "action_relation_loss": 0.002221143082715571, "auxiliary_loss_weight": 1.0, "epoch": 18.73713751169317, "flow_matching_loss": 0.021363269817084075, "grad_norm": 0.09987364709377289, "invalid_tail_samples": 25.0, "learning_rate": 2.72808338549564e-05, "loss": 0.0236, "positive_teacher_pairs": 26573.9, "relation_loss": 0.002221143082715571, "selected_pairs": 26573.9, "step": 20030, "student_distance_mean": 1284.5808471679688, "teacher_distance_mean": 0.8563238024711609, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.002221143082715571, "weighted_relation_loss": 0.002221143082715571 }, { "action_query_batch_std": 22.27861957550049, "action_query_norm": 948.6253051757812, "action_relation_loss": 0.0022334472509101034, "auxiliary_loss_weight": 1.0, "epoch": 18.746492048643592, "flow_matching_loss": 0.020434636622667313, "grad_norm": 0.08577970415353775, "invalid_tail_samples": 23.8, "learning_rate": 2.723175029229374e-05, "loss": 0.0227, "positive_teacher_pairs": 26844.8, "relation_loss": 0.0022334472509101034, "selected_pairs": 26844.8, "step": 20040, "student_distance_mean": 1276.52607421875, "teacher_distance_mean": 0.8492612302303314, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0022334472509101034, "weighted_relation_loss": 0.0022334472509101034 }, { "action_query_batch_std": 22.227894401550294, "action_query_norm": 947.6836059570312, "action_relation_loss": 0.0022081115283071997, "auxiliary_loss_weight": 1.0, "epoch": 18.755846585594014, "flow_matching_loss": 0.02052064221352339, "grad_norm": 0.10006846487522125, "invalid_tail_samples": 23.7, "learning_rate": 2.718269439520138e-05, "loss": 0.0227, "positive_teacher_pairs": 26881.7, "relation_loss": 0.0022081115283071997, "selected_pairs": 26881.7, "step": 20050, "student_distance_mean": 1276.1179931640625, "teacher_distance_mean": 0.8476019024848938, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0022081115283071997, "weighted_relation_loss": 0.0022081115283071997 }, { "action_query_batch_std": 22.309241676330565, "action_query_norm": 949.705615234375, "action_relation_loss": 0.0021385110798291863, "auxiliary_loss_weight": 1.0, "epoch": 18.765201122544433, "flow_matching_loss": 0.020506474934518338, "grad_norm": 0.07605456560850143, "invalid_tail_samples": 27.5, "learning_rate": 2.7133666223286858e-05, "loss": 0.0226, "positive_teacher_pairs": 26004.6, "relation_loss": 0.0021385110798291863, "selected_pairs": 26004.6, "step": 20060, "student_distance_mean": 1286.0190063476562, "teacher_distance_mean": 0.8590044736862182, "valid_action_samples": 228.5, "weighted_auxiliary_loss": 0.0021385110798291863, "weighted_relation_loss": 0.0021385110798291863 }, { "action_query_batch_std": 21.9485013961792, "action_query_norm": 937.9708923339844, "action_relation_loss": 0.002231857320293784, "auxiliary_loss_weight": 1.0, "epoch": 18.774555659494855, "flow_matching_loss": 0.020744382031261922, "grad_norm": 0.0992598757147789, "invalid_tail_samples": 22.3, "learning_rate": 2.7084665836124006e-05, "loss": 0.023, "positive_teacher_pairs": 27195.3, "relation_loss": 0.002231857320293784, "selected_pairs": 27195.3, "step": 20070, "student_distance_mean": 1260.9086547851562, "teacher_distance_mean": 0.8443916440010071, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.002231857320293784, "weighted_relation_loss": 0.002231857320293784 }, { "action_query_batch_std": 22.401653861999513, "action_query_norm": 952.1504272460937, "action_relation_loss": 0.002135039446875453, "auxiliary_loss_weight": 1.0, "epoch": 18.783910196445277, "flow_matching_loss": 0.0200602101162076, "grad_norm": 0.10342909395694733, "invalid_tail_samples": 21.8, "learning_rate": 2.703569329325296e-05, "loss": 0.0222, "positive_teacher_pairs": 27321.4, "relation_loss": 0.002135039446875453, "selected_pairs": 27321.4, "step": 20080, "student_distance_mean": 1284.686083984375, "teacher_distance_mean": 0.8572917997837066, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.002135039446875453, "weighted_relation_loss": 0.002135039446875453 }, { "action_query_batch_std": 22.486417388916017, "action_query_norm": 954.3729858398438, "action_relation_loss": 0.0021359492791816594, "auxiliary_loss_weight": 1.0, "epoch": 18.7932647333957, "flow_matching_loss": 0.019732006639242173, "grad_norm": 0.08436279743909836, "invalid_tail_samples": 23.1, "learning_rate": 2.698674865417994e-05, "loss": 0.0219, "positive_teacher_pairs": 27007.5, "relation_loss": 0.0021359492791816594, "selected_pairs": 27007.5, "step": 20090, "student_distance_mean": 1284.7102905273437, "teacher_distance_mean": 0.8556505441665649, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0021359492791816594, "weighted_relation_loss": 0.0021359492791816594 }, { "action_query_batch_std": 22.39070072174072, "action_query_norm": 952.4709350585938, "action_relation_loss": 0.0021421130048111083, "auxiliary_loss_weight": 1.0, "epoch": 18.802619270346117, "flow_matching_loss": 0.020907854475080968, "grad_norm": 0.08363451808691025, "invalid_tail_samples": 25.1, "learning_rate": 2.6937831978377325e-05, "loss": 0.023, "positive_teacher_pairs": 26550.1, "relation_loss": 0.0021421130048111083, "selected_pairs": 26550.1, "step": 20100, "student_distance_mean": 1285.0931030273437, "teacher_distance_mean": 0.8589517951011658, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0021421130048111083, "weighted_relation_loss": 0.0021421130048111083 }, { "action_query_batch_std": 22.04660415649414, "action_query_norm": 939.2703063964843, "action_relation_loss": 0.0022139750653877854, "auxiliary_loss_weight": 1.0, "epoch": 18.81197380729654, "flow_matching_loss": 0.021577252075076103, "grad_norm": 0.08705374598503113, "invalid_tail_samples": 23.8, "learning_rate": 2.6888943325283485e-05, "loss": 0.0238, "positive_teacher_pairs": 26858.8, "relation_loss": 0.0022139750653877854, "selected_pairs": 26858.8, "step": 20110, "student_distance_mean": 1266.7159301757813, "teacher_distance_mean": 0.8447826206684113, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0022139750653877854, "weighted_relation_loss": 0.0022139750653877854 }, { "action_query_batch_std": 22.162836265563964, "action_query_norm": 944.7814025878906, "action_relation_loss": 0.0021818608860485257, "auxiliary_loss_weight": 1.0, "epoch": 18.82132834424696, "flow_matching_loss": 0.02221436332911253, "grad_norm": 0.08662775903940201, "invalid_tail_samples": 23.7, "learning_rate": 2.6840082754302733e-05, "loss": 0.0244, "positive_teacher_pairs": 26878.1, "relation_loss": 0.0021818608860485257, "selected_pairs": 26878.1, "step": 20120, "student_distance_mean": 1268.766845703125, "teacher_distance_mean": 0.8463830411434173, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0021818608860485257, "weighted_relation_loss": 0.0021818608860485257 }, { "action_query_batch_std": 22.211140441894532, "action_query_norm": 945.4799255371094, "action_relation_loss": 0.0021822597365826367, "auxiliary_loss_weight": 1.0, "epoch": 18.83068288119738, "flow_matching_loss": 0.021579641662538052, "grad_norm": 0.08500583469867706, "invalid_tail_samples": 24.4, "learning_rate": 2.679125032480525e-05, "loss": 0.0238, "positive_teacher_pairs": 26710.1, "relation_loss": 0.0021822597365826367, "selected_pairs": 26710.1, "step": 20130, "student_distance_mean": 1277.1121337890625, "teacher_distance_mean": 0.8528085052967072, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0021822597365826367, "weighted_relation_loss": 0.0021822597365826367 }, { "action_query_batch_std": 22.37690200805664, "action_query_norm": 954.7100341796875, "action_relation_loss": 0.002128519571851939, "auxiliary_loss_weight": 1.0, "epoch": 18.8400374181478, "flow_matching_loss": 0.020860282704234123, "grad_norm": 0.096904456615448, "invalid_tail_samples": 22.5, "learning_rate": 2.674244609612708e-05, "loss": 0.023, "positive_teacher_pairs": 27152.8, "relation_loss": 0.002128519571851939, "selected_pairs": 27152.8, "step": 20140, "student_distance_mean": 1283.9688232421875, "teacher_distance_mean": 0.8606077253818512, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.002128519571851939, "weighted_relation_loss": 0.002128519571851939 }, { "action_query_batch_std": 22.316172218322755, "action_query_norm": 950.1812744140625, "action_relation_loss": 0.00211504491744563, "auxiliary_loss_weight": 1.0, "epoch": 18.849391955098223, "flow_matching_loss": 0.019624086562544107, "grad_norm": 0.1000906303524971, "invalid_tail_samples": 23.1, "learning_rate": 2.6693670127569958e-05, "loss": 0.0217, "positive_teacher_pairs": 27010.9, "relation_loss": 0.00211504491744563, "selected_pairs": 27010.9, "step": 20150, "student_distance_mean": 1276.3135131835938, "teacher_distance_mean": 0.8550749301910401, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.00211504491744563, "weighted_relation_loss": 0.00211504491744563 }, { "action_query_batch_std": 22.047749519348145, "action_query_norm": 940.8037536621093, "action_relation_loss": 0.0023195239249616862, "auxiliary_loss_weight": 1.0, "epoch": 18.858746492048645, "flow_matching_loss": 0.020490841940045357, "grad_norm": 0.0981680303812027, "invalid_tail_samples": 25.7, "learning_rate": 2.6644922478401268e-05, "loss": 0.0228, "positive_teacher_pairs": 26413.8, "relation_loss": 0.0023195239249616862, "selected_pairs": 26413.8, "step": 20160, "student_distance_mean": 1263.8960571289062, "teacher_distance_mean": 0.847030633687973, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.0023195239249616862, "weighted_relation_loss": 0.0023195239249616862 }, { "action_query_batch_std": 22.43544158935547, "action_query_norm": 954.3707458496094, "action_relation_loss": 0.0021136467694304883, "auxiliary_loss_weight": 1.0, "epoch": 18.868101028999064, "flow_matching_loss": 0.021386080794036387, "grad_norm": 0.09599034488201141, "invalid_tail_samples": 23.3, "learning_rate": 2.6596203207854004e-05, "loss": 0.0235, "positive_teacher_pairs": 26964.3, "relation_loss": 0.0021136467694304883, "selected_pairs": 26964.3, "step": 20170, "student_distance_mean": 1281.783251953125, "teacher_distance_mean": 0.858119684457779, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0021136467694304883, "weighted_relation_loss": 0.0021136467694304883 }, { "action_query_batch_std": 22.43397960662842, "action_query_norm": 953.9755615234375, "action_relation_loss": 0.0021170156192965805, "auxiliary_loss_weight": 1.0, "epoch": 18.877455565949486, "flow_matching_loss": 0.02091138157993555, "grad_norm": 0.07726938277482986, "invalid_tail_samples": 24.2, "learning_rate": 2.654751237512666e-05, "loss": 0.023, "positive_teacher_pairs": 26754.7, "relation_loss": 0.0021170156192965805, "selected_pairs": 26754.7, "step": 20180, "student_distance_mean": 1289.2718017578125, "teacher_distance_mean": 0.8584266543388367, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0021170156192965805, "weighted_relation_loss": 0.0021170156192965805 }, { "action_query_batch_std": 22.362841033935545, "action_query_norm": 949.4773681640625, "action_relation_loss": 0.002149199228733778, "auxiliary_loss_weight": 1.0, "epoch": 18.886810102899908, "flow_matching_loss": 0.021320006996393203, "grad_norm": 0.11614726483821869, "invalid_tail_samples": 23.1, "learning_rate": 2.649885003938323e-05, "loss": 0.0235, "positive_teacher_pairs": 27019.8, "relation_loss": 0.002149199228733778, "selected_pairs": 27019.8, "step": 20190, "student_distance_mean": 1284.6464721679688, "teacher_distance_mean": 0.857443916797638, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.002149199228733778, "weighted_relation_loss": 0.002149199228733778 }, { "action_query_batch_std": 22.503324890136717, "action_query_norm": 957.1410766601563, "action_relation_loss": 0.00218363746535033, "auxiliary_loss_weight": 1.0, "epoch": 18.896164639850326, "flow_matching_loss": 0.020028057042509317, "grad_norm": 0.09882040321826935, "invalid_tail_samples": 25.6, "learning_rate": 2.6450216259753e-05, "loss": 0.0222, "positive_teacher_pairs": 26439.1, "relation_loss": 0.00218363746535033, "selected_pairs": 26439.1, "step": 20200, "student_distance_mean": 1290.0340209960937, "teacher_distance_mean": 0.8612808465957642, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.00218363746535033, "weighted_relation_loss": 0.00218363746535033 }, { "action_query_batch_std": 22.296728515625, "action_query_norm": 948.8269897460938, "action_relation_loss": 0.0021768663660623132, "auxiliary_loss_weight": 1.0, "epoch": 18.90551917680075, "flow_matching_loss": 0.019575341045856474, "grad_norm": 0.09828917682170868, "invalid_tail_samples": 22.3, "learning_rate": 2.640161109533063e-05, "loss": 0.0218, "positive_teacher_pairs": 27197.3, "relation_loss": 0.0021768663660623132, "selected_pairs": 27197.3, "step": 20210, "student_distance_mean": 1273.0197998046874, "teacher_distance_mean": 0.851829570531845, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0021768663660623132, "weighted_relation_loss": 0.0021768663660623132 }, { "action_query_batch_std": 22.19030590057373, "action_query_norm": 944.9096130371094, "action_relation_loss": 0.002204729011282325, "auxiliary_loss_weight": 1.0, "epoch": 18.91487371375117, "flow_matching_loss": 0.020887649059295653, "grad_norm": 0.09277846664190292, "invalid_tail_samples": 23.5, "learning_rate": 2.6353034605175936e-05, "loss": 0.0231, "positive_teacher_pairs": 26914.6, "relation_loss": 0.002204729011282325, "selected_pairs": 26914.6, "step": 20220, "student_distance_mean": 1275.73671875, "teacher_distance_mean": 0.8522580564022064, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.002204729011282325, "weighted_relation_loss": 0.002204729011282325 }, { "action_query_batch_std": 22.236682510375978, "action_query_norm": 948.4267578125, "action_relation_loss": 0.0021870646392926573, "auxiliary_loss_weight": 1.0, "epoch": 18.92422825070159, "flow_matching_loss": 0.024257959425449373, "grad_norm": 0.10108739882707596, "invalid_tail_samples": 24.4, "learning_rate": 2.630448684831398e-05, "loss": 0.0264, "positive_teacher_pairs": 26709.7, "relation_loss": 0.0021870646392926573, "selected_pairs": 26709.7, "step": 20230, "student_distance_mean": 1280.4688842773437, "teacher_distance_mean": 0.8548310935497284, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0021870646392926573, "weighted_relation_loss": 0.0021870646392926573 }, { "action_query_batch_std": 22.033872413635255, "action_query_norm": 941.7787780761719, "action_relation_loss": 0.0021676629083231093, "auxiliary_loss_weight": 1.0, "epoch": 18.93358278765201, "flow_matching_loss": 0.02187464889138937, "grad_norm": 0.10481422394514084, "invalid_tail_samples": 22.9, "learning_rate": 2.625596788373482e-05, "loss": 0.024, "positive_teacher_pairs": 27075.3, "relation_loss": 0.0021676629083231093, "selected_pairs": 27075.3, "step": 20240, "student_distance_mean": 1262.4161499023437, "teacher_distance_mean": 0.8414458096027374, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0021676629083231093, "weighted_relation_loss": 0.0021676629083231093 }, { "action_query_batch_std": 22.47818374633789, "action_query_norm": 958.0154663085938, "action_relation_loss": 0.0021616955986246468, "auxiliary_loss_weight": 1.0, "epoch": 18.942937324602433, "flow_matching_loss": 0.022414709068834783, "grad_norm": 0.08939041942358017, "invalid_tail_samples": 23.2, "learning_rate": 2.620747777039363e-05, "loss": 0.0246, "positive_teacher_pairs": 26990.8, "relation_loss": 0.0021616955986246468, "selected_pairs": 26990.8, "step": 20250, "student_distance_mean": 1288.3050048828125, "teacher_distance_mean": 0.8590226113796234, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0021616955986246468, "weighted_relation_loss": 0.0021616955986246468 }, { "action_query_batch_std": 21.972647666931152, "action_query_norm": 935.8031982421875, "action_relation_loss": 0.002197518921457231, "auxiliary_loss_weight": 1.0, "epoch": 18.952291861552855, "flow_matching_loss": 0.0200802612118423, "grad_norm": 0.1370171308517456, "invalid_tail_samples": 25.7, "learning_rate": 2.6159016567210424e-05, "loss": 0.0223, "positive_teacher_pairs": 26409.9, "relation_loss": 0.002197518921457231, "selected_pairs": 26409.9, "step": 20260, "student_distance_mean": 1259.6172485351562, "teacher_distance_mean": 0.8397339403629303, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.002197518921457231, "weighted_relation_loss": 0.002197518921457231 }, { "action_query_batch_std": 22.034142303466798, "action_query_norm": 939.7450561523438, "action_relation_loss": 0.0022485314402729273, "auxiliary_loss_weight": 1.0, "epoch": 18.961646398503273, "flow_matching_loss": 0.019830659683793782, "grad_norm": 0.0970216691493988, "invalid_tail_samples": 26.3, "learning_rate": 2.6110584333070153e-05, "loss": 0.0221, "positive_teacher_pairs": 26270.4, "relation_loss": 0.0022485314402729273, "selected_pairs": 26270.4, "step": 20270, "student_distance_mean": 1267.9539306640625, "teacher_distance_mean": 0.8463076233863831, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.0022485314402729273, "weighted_relation_loss": 0.0022485314402729273 }, { "action_query_batch_std": 22.36791076660156, "action_query_norm": 949.8893920898438, "action_relation_loss": 0.0021916784113273024, "auxiliary_loss_weight": 1.0, "epoch": 18.971000935453695, "flow_matching_loss": 0.02058310192078352, "grad_norm": 0.08174348622560501, "invalid_tail_samples": 24.9, "learning_rate": 2.6062181126822537e-05, "loss": 0.0228, "positive_teacher_pairs": 26590.9, "relation_loss": 0.0021916784113273024, "selected_pairs": 26590.9, "step": 20280, "student_distance_mean": 1280.0218383789063, "teacher_distance_mean": 0.8561300277709961, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0021916784113273024, "weighted_relation_loss": 0.0021916784113273024 }, { "action_query_batch_std": 22.31101474761963, "action_query_norm": 950.3813049316407, "action_relation_loss": 0.0021082958672195675, "auxiliary_loss_weight": 1.0, "epoch": 18.980355472404117, "flow_matching_loss": 0.021993013098835945, "grad_norm": 0.10902194678783417, "invalid_tail_samples": 24.8, "learning_rate": 2.601380700728203e-05, "loss": 0.0241, "positive_teacher_pairs": 26617.1, "relation_loss": 0.0021082958672195675, "selected_pairs": 26617.1, "step": 20290, "student_distance_mean": 1281.2807861328124, "teacher_distance_mean": 0.8568740427494049, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0021082958672195675, "weighted_relation_loss": 0.0021082958672195675 }, { "action_query_batch_std": 21.96624622344971, "action_query_norm": 940.3319519042968, "action_relation_loss": 0.0022370632737874984, "auxiliary_loss_weight": 1.0, "epoch": 18.989710009354535, "flow_matching_loss": 0.02123659960925579, "grad_norm": 0.08928204327821732, "invalid_tail_samples": 21.9, "learning_rate": 2.596546203322777e-05, "loss": 0.0235, "positive_teacher_pairs": 27290.2, "relation_loss": 0.0022370632737874984, "selected_pairs": 27290.2, "step": 20300, "student_distance_mean": 1264.2212158203124, "teacher_distance_mean": 0.8454155027866364, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.0022370632737874984, "weighted_relation_loss": 0.0022370632737874984 }, { "action_query_batch_std": 22.180934715270997, "action_query_norm": 944.7429016113281, "action_relation_loss": 0.0020969243603758516, "auxiliary_loss_weight": 1.0, "epoch": 18.999064546304957, "flow_matching_loss": 0.019555195420980453, "grad_norm": 0.10963714867830276, "invalid_tail_samples": 24.7, "learning_rate": 2.5917146263403457e-05, "loss": 0.0217, "positive_teacher_pairs": 26641.6, "relation_loss": 0.0020969243603758516, "selected_pairs": 26641.6, "step": 20310, "student_distance_mean": 1274.4487548828124, "teacher_distance_mean": 0.8523175418376923, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0020969243603758516, "weighted_relation_loss": 0.0020969243603758516 }, { "action_query_batch_std": 22.164703369140625, "action_query_norm": 945.614697265625, "action_relation_loss": 0.0020491233677603304, "auxiliary_loss_weight": 1.0, "epoch": 19.00841908325538, "flow_matching_loss": 0.019576780311763287, "grad_norm": 0.08030744642019272, "invalid_tail_samples": 20.1, "learning_rate": 2.5868859756517296e-05, "loss": 0.0216, "positive_teacher_pairs": 24783.1, "relation_loss": 0.0020491233677603304, "selected_pairs": 24783.1, "step": 20320, "student_distance_mean": 1276.9156860351563, "teacher_distance_mean": 0.8545320928096771, "valid_action_samples": 216.0, "weighted_auxiliary_loss": 0.0020491233677603304, "weighted_relation_loss": 0.0020491233677603304 }, { "action_query_batch_std": 22.163652610778808, "action_query_norm": 944.517529296875, "action_relation_loss": 0.0022027343977242706, "auxiliary_loss_weight": 1.0, "epoch": 19.0177736202058, "flow_matching_loss": 0.021797933802008628, "grad_norm": 0.1060241311788559, "invalid_tail_samples": 23.6, "learning_rate": 2.5820602571241947e-05, "loss": 0.024, "positive_teacher_pairs": 26899.7, "relation_loss": 0.0022027343977242706, "selected_pairs": 26899.7, "step": 20330, "student_distance_mean": 1272.90400390625, "teacher_distance_mean": 0.8486927092075348, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0022027343977242706, "weighted_relation_loss": 0.0022027343977242706 }, { "action_query_batch_std": 22.189874839782714, "action_query_norm": 946.5261901855469, "action_relation_loss": 0.0021704997634515166, "auxiliary_loss_weight": 1.0, "epoch": 19.02712815715622, "flow_matching_loss": 0.020119704864919187, "grad_norm": 0.09616836160421371, "invalid_tail_samples": 22.5, "learning_rate": 2.577237476621442e-05, "loss": 0.0223, "positive_teacher_pairs": 27153.6, "relation_loss": 0.0021704997634515166, "selected_pairs": 27153.6, "step": 20340, "student_distance_mean": 1270.1052124023438, "teacher_distance_mean": 0.846642130613327, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0021704997634515166, "weighted_relation_loss": 0.0021704997634515166 }, { "action_query_batch_std": 22.568373107910155, "action_query_norm": 959.7058471679687, "action_relation_loss": 0.002089074742980301, "auxiliary_loss_weight": 1.0, "epoch": 19.036482694106642, "flow_matching_loss": 0.020856552943587302, "grad_norm": 0.09695179760456085, "invalid_tail_samples": 23.0, "learning_rate": 2.572417640003609e-05, "loss": 0.0229, "positive_teacher_pairs": 27034.5, "relation_loss": 0.002089074742980301, "selected_pairs": 27034.5, "step": 20350, "student_distance_mean": 1294.4365234375, "teacher_distance_mean": 0.8649242460727692, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.002089074742980301, "weighted_relation_loss": 0.002089074742980301 }, { "action_query_batch_std": 22.004064559936523, "action_query_norm": 937.3656921386719, "action_relation_loss": 0.002075885480735451, "auxiliary_loss_weight": 1.0, "epoch": 19.045837231057064, "flow_matching_loss": 0.01937079504132271, "grad_norm": 0.09606984257698059, "invalid_tail_samples": 25.8, "learning_rate": 2.5676007531272473e-05, "loss": 0.0214, "positive_teacher_pairs": 26386.6, "relation_loss": 0.002075885480735451, "selected_pairs": 26386.6, "step": 20360, "student_distance_mean": 1263.0527709960938, "teacher_distance_mean": 0.8467443466186524, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.002075885480735451, "weighted_relation_loss": 0.002075885480735451 }, { "action_query_batch_std": 22.068198585510252, "action_query_norm": 942.6824829101563, "action_relation_loss": 0.002110830170568079, "auxiliary_loss_weight": 1.0, "epoch": 19.055191768007482, "flow_matching_loss": 0.02159094512462616, "grad_norm": 0.0953102633357048, "invalid_tail_samples": 25.3, "learning_rate": 2.5627868218453332e-05, "loss": 0.0237, "positive_teacher_pairs": 26512.9, "relation_loss": 0.002110830170568079, "selected_pairs": 26512.9, "step": 20370, "student_distance_mean": 1268.4570922851562, "teacher_distance_mean": 0.8488598346710206, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.002110830170568079, "weighted_relation_loss": 0.002110830170568079 }, { "action_query_batch_std": 22.352153015136718, "action_query_norm": 949.9739440917969, "action_relation_loss": 0.002026369678787887, "auxiliary_loss_weight": 1.0, "epoch": 19.064546304957904, "flow_matching_loss": 0.020000757835805415, "grad_norm": 0.09373245388269424, "invalid_tail_samples": 24.3, "learning_rate": 2.5579758520072443e-05, "loss": 0.022, "positive_teacher_pairs": 26735.2, "relation_loss": 0.002026369678787887, "selected_pairs": 26735.2, "step": 20380, "student_distance_mean": 1284.3642822265624, "teacher_distance_mean": 0.8581943571567535, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.002026369678787887, "weighted_relation_loss": 0.002026369678787887 }, { "action_query_batch_std": 22.45515842437744, "action_query_norm": 954.6043640136719, "action_relation_loss": 0.0020720369298942386, "auxiliary_loss_weight": 1.0, "epoch": 19.073900841908326, "flow_matching_loss": 0.02099747583270073, "grad_norm": 0.09635228663682938, "invalid_tail_samples": 24.3, "learning_rate": 2.5531678494587615e-05, "loss": 0.0231, "positive_teacher_pairs": 26735.0, "relation_loss": 0.0020720369298942386, "selected_pairs": 26735.0, "step": 20390, "student_distance_mean": 1289.4098876953126, "teacher_distance_mean": 0.8620216310024261, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0020720369298942386, "weighted_relation_loss": 0.0020720369298942386 }, { "action_query_batch_std": 22.309767723083496, "action_query_norm": 948.3715087890625, "action_relation_loss": 0.0021787433652207255, "auxiliary_loss_weight": 1.0, "epoch": 19.08325537885875, "flow_matching_loss": 0.020914646424353124, "grad_norm": 0.12017671763896942, "invalid_tail_samples": 24.4, "learning_rate": 2.5483628200420644e-05, "loss": 0.0231, "positive_teacher_pairs": 26723.0, "relation_loss": 0.0021787433652207255, "selected_pairs": 26723.0, "step": 20400, "student_distance_mean": 1280.4959106445312, "teacher_distance_mean": 0.8568553626537323, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0021787433652207255, "weighted_relation_loss": 0.0021787433652207255 }, { "action_query_batch_std": 22.35077667236328, "action_query_norm": 950.9471069335938, "action_relation_loss": 0.002052273426670581, "auxiliary_loss_weight": 1.0, "epoch": 19.092609915809167, "flow_matching_loss": 0.02069624587893486, "grad_norm": 0.10155847668647766, "invalid_tail_samples": 23.6, "learning_rate": 2.5435607695957154e-05, "loss": 0.0227, "positive_teacher_pairs": 26894.4, "relation_loss": 0.002052273426670581, "selected_pairs": 26894.4, "step": 20410, "student_distance_mean": 1285.9796508789063, "teacher_distance_mean": 0.8607842147350311, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.002052273426670581, "weighted_relation_loss": 0.002052273426670581 }, { "action_query_batch_std": 22.316502380371094, "action_query_norm": 951.9857604980468, "action_relation_loss": 0.0020598397706635295, "auxiliary_loss_weight": 1.0, "epoch": 19.10196445275959, "flow_matching_loss": 0.019690763019025326, "grad_norm": 0.10465936362743378, "invalid_tail_samples": 21.8, "learning_rate": 2.5387617039546586e-05, "loss": 0.0218, "positive_teacher_pairs": 27322.6, "relation_loss": 0.0020598397706635295, "selected_pairs": 27322.6, "step": 20420, "student_distance_mean": 1283.930810546875, "teacher_distance_mean": 0.8582909345626831, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.0020598397706635295, "weighted_relation_loss": 0.0020598397706635295 }, { "action_query_batch_std": 22.309426689147948, "action_query_norm": 950.1691345214844, "action_relation_loss": 0.0021060742205008865, "auxiliary_loss_weight": 1.0, "epoch": 19.11131898971001, "flow_matching_loss": 0.01966056991368532, "grad_norm": 0.0916939526796341, "invalid_tail_samples": 24.1, "learning_rate": 2.5339656289502106e-05, "loss": 0.0218, "positive_teacher_pairs": 26778.8, "relation_loss": 0.0021060742205008865, "selected_pairs": 26778.8, "step": 20430, "student_distance_mean": 1283.93251953125, "teacher_distance_mean": 0.8599696815013885, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0021060742205008865, "weighted_relation_loss": 0.0021060742205008865 }, { "action_query_batch_std": 22.258788871765137, "action_query_norm": 947.3017639160156, "action_relation_loss": 0.0020848897867836056, "auxiliary_loss_weight": 1.0, "epoch": 19.12067352666043, "flow_matching_loss": 0.02004640270024538, "grad_norm": 0.08454388380050659, "invalid_tail_samples": 24.1, "learning_rate": 2.529172550410056e-05, "loss": 0.0221, "positive_teacher_pairs": 26789.0, "relation_loss": 0.0020848897867836056, "selected_pairs": 26789.0, "step": 20440, "student_distance_mean": 1276.4115600585938, "teacher_distance_mean": 0.8517818331718445, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0020848897867836056, "weighted_relation_loss": 0.0020848897867836056 }, { "action_query_batch_std": 22.298249816894533, "action_query_norm": 951.2433776855469, "action_relation_loss": 0.0021387447952292858, "auxiliary_loss_weight": 1.0, "epoch": 19.13002806361085, "flow_matching_loss": 0.020549324341118336, "grad_norm": 0.08364652097225189, "invalid_tail_samples": 22.8, "learning_rate": 2.524382474158234e-05, "loss": 0.0227, "positive_teacher_pairs": 27079.8, "relation_loss": 0.0021387447952292858, "selected_pairs": 27079.8, "step": 20450, "student_distance_mean": 1281.9441040039062, "teacher_distance_mean": 0.8519168078899384, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0021387447952292858, "weighted_relation_loss": 0.0021387447952292858 }, { "action_query_batch_std": 22.341749382019042, "action_query_norm": 951.8542846679687, "action_relation_loss": 0.002103697566781193, "auxiliary_loss_weight": 1.0, "epoch": 19.139382600561273, "flow_matching_loss": 0.020985233411192895, "grad_norm": 0.08853878080844879, "invalid_tail_samples": 23.6, "learning_rate": 2.5195954060151433e-05, "loss": 0.0231, "positive_teacher_pairs": 26898.7, "relation_loss": 0.002103697566781193, "selected_pairs": 26898.7, "step": 20460, "student_distance_mean": 1282.997021484375, "teacher_distance_mean": 0.8554010391235352, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.002103697566781193, "weighted_relation_loss": 0.002103697566781193 }, { "action_query_batch_std": 22.376399040222168, "action_query_norm": 951.5213806152344, "action_relation_loss": 0.00214456079993397, "auxiliary_loss_weight": 1.0, "epoch": 19.14873713751169, "flow_matching_loss": 0.02126947194337845, "grad_norm": 0.10715170204639435, "invalid_tail_samples": 25.7, "learning_rate": 2.5148113517975212e-05, "loss": 0.0234, "positive_teacher_pairs": 26411.9, "relation_loss": 0.00214456079993397, "selected_pairs": 26411.9, "step": 20470, "student_distance_mean": 1287.5680297851563, "teacher_distance_mean": 0.8617434084415436, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.00214456079993397, "weighted_relation_loss": 0.00214456079993397 }, { "action_query_batch_std": 22.222747230529784, "action_query_norm": 948.7681396484375, "action_relation_loss": 0.0021188676590099932, "auxiliary_loss_weight": 1.0, "epoch": 19.158091674462113, "flow_matching_loss": 0.020970593765378, "grad_norm": 0.08991224318742752, "invalid_tail_samples": 22.9, "learning_rate": 2.5100303173184447e-05, "loss": 0.0231, "positive_teacher_pairs": 27056.8, "relation_loss": 0.0021188676590099932, "selected_pairs": 27056.8, "step": 20480, "student_distance_mean": 1275.0509033203125, "teacher_distance_mean": 0.8485614359378815, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0021188676590099932, "weighted_relation_loss": 0.0021188676590099932 }, { "action_query_batch_std": 22.38515911102295, "action_query_norm": 952.8095581054688, "action_relation_loss": 0.002098955074325204, "auxiliary_loss_weight": 1.0, "epoch": 19.167446211412535, "flow_matching_loss": 0.019455944001674653, "grad_norm": 0.09201129525899887, "invalid_tail_samples": 26.4, "learning_rate": 2.5052523083873196e-05, "loss": 0.0216, "positive_teacher_pairs": 26247.3, "relation_loss": 0.002098955074325204, "selected_pairs": 26247.3, "step": 20490, "student_distance_mean": 1286.6966064453125, "teacher_distance_mean": 0.8538908660411835, "valid_action_samples": 229.6, "weighted_auxiliary_loss": 0.002098955074325204, "weighted_relation_loss": 0.002098955074325204 }, { "action_query_batch_std": 22.333172416687013, "action_query_norm": 952.8152099609375, "action_relation_loss": 0.00209315501851961, "auxiliary_loss_weight": 1.0, "epoch": 19.176800748362957, "flow_matching_loss": 0.020242260582745076, "grad_norm": 0.08786506205797195, "invalid_tail_samples": 24.9, "learning_rate": 2.500477330809881e-05, "loss": 0.0223, "positive_teacher_pairs": 26597.2, "relation_loss": 0.00209315501851961, "selected_pairs": 26597.2, "step": 20500, "student_distance_mean": 1288.6051879882812, "teacher_distance_mean": 0.8566208600997924, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.00209315501851961, "weighted_relation_loss": 0.00209315501851961 }, { "action_query_batch_std": 22.299782752990723, "action_query_norm": 950.175927734375, "action_relation_loss": 0.0020507854293100535, "auxiliary_loss_weight": 1.0, "epoch": 19.186155285313376, "flow_matching_loss": 0.02082236800342798, "grad_norm": 0.08323273062705994, "invalid_tail_samples": 24.7, "learning_rate": 2.4957053903881733e-05, "loss": 0.0229, "positive_teacher_pairs": 26641.8, "relation_loss": 0.0020507854293100535, "selected_pairs": 26641.8, "step": 20510, "student_distance_mean": 1283.9885009765626, "teacher_distance_mean": 0.8536025285720825, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0020507854293100535, "weighted_relation_loss": 0.0020507854293100535 }, { "action_query_batch_std": 22.595708465576173, "action_query_norm": 958.1727478027344, "action_relation_loss": 0.00207469230517745, "auxiliary_loss_weight": 1.0, "epoch": 19.195509822263798, "flow_matching_loss": 0.022828453220427036, "grad_norm": 0.08530622720718384, "invalid_tail_samples": 25.5, "learning_rate": 2.4909364929205576e-05, "loss": 0.0249, "positive_teacher_pairs": 26461.8, "relation_loss": 0.00207469230517745, "selected_pairs": 26461.8, "step": 20520, "student_distance_mean": 1299.578369140625, "teacher_distance_mean": 0.8640811979770661, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.00207469230517745, "weighted_relation_loss": 0.00207469230517745 }, { "action_query_batch_std": 22.346298599243163, "action_query_norm": 951.4680358886719, "action_relation_loss": 0.002036874007899314, "auxiliary_loss_weight": 1.0, "epoch": 19.20486435921422, "flow_matching_loss": 0.019940730091184376, "grad_norm": 0.09452806413173676, "invalid_tail_samples": 27.3, "learning_rate": 2.4861706442016923e-05, "loss": 0.022, "positive_teacher_pairs": 26049.9, "relation_loss": 0.002036874007899314, "selected_pairs": 26049.9, "step": 20530, "student_distance_mean": 1286.266259765625, "teacher_distance_mean": 0.8568997383117676, "valid_action_samples": 228.7, "weighted_auxiliary_loss": 0.002036874007899314, "weighted_relation_loss": 0.002036874007899314 }, { "action_query_batch_std": 22.349088859558105, "action_query_norm": 950.2015441894531, "action_relation_loss": 0.0020731777185574174, "auxiliary_loss_weight": 1.0, "epoch": 19.21421889616464, "flow_matching_loss": 0.02052573310211301, "grad_norm": 0.08508586883544922, "invalid_tail_samples": 23.9, "learning_rate": 2.481407850022533e-05, "loss": 0.0226, "positive_teacher_pairs": 26840.1, "relation_loss": 0.0020731777185574174, "selected_pairs": 26840.1, "step": 20540, "student_distance_mean": 1278.8543579101563, "teacher_distance_mean": 0.8540429949760437, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0020731777185574174, "weighted_relation_loss": 0.0020731777185574174 }, { "action_query_batch_std": 22.194543647766114, "action_query_norm": 946.798046875, "action_relation_loss": 0.0021387475309893487, "auxiliary_loss_weight": 1.0, "epoch": 19.22357343311506, "flow_matching_loss": 0.02086179917678237, "grad_norm": 0.10205880552530289, "invalid_tail_samples": 25.2, "learning_rate": 2.4766481161703213e-05, "loss": 0.023, "positive_teacher_pairs": 26528.2, "relation_loss": 0.0021387475309893487, "selected_pairs": 26528.2, "step": 20550, "student_distance_mean": 1275.7208129882813, "teacher_distance_mean": 0.8546782195568084, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0021387475309893487, "weighted_relation_loss": 0.0021387475309893487 }, { "action_query_batch_std": 22.00074234008789, "action_query_norm": 941.0763305664062, "action_relation_loss": 0.002102346532046795, "auxiliary_loss_weight": 1.0, "epoch": 19.232927970065482, "flow_matching_loss": 0.020207997784018515, "grad_norm": 0.08267146348953247, "invalid_tail_samples": 24.0, "learning_rate": 2.4718914484285876e-05, "loss": 0.0223, "positive_teacher_pairs": 26800.8, "relation_loss": 0.002102346532046795, "selected_pairs": 26800.8, "step": 20560, "student_distance_mean": 1266.4888427734375, "teacher_distance_mean": 0.8462191581726074, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.002102346532046795, "weighted_relation_loss": 0.002102346532046795 }, { "action_query_batch_std": 22.2654167175293, "action_query_norm": 951.3609619140625, "action_relation_loss": 0.0020027236780151723, "auxiliary_loss_weight": 1.0, "epoch": 19.242282507015904, "flow_matching_loss": 0.01894485894590616, "grad_norm": 0.0748477354645729, "invalid_tail_samples": 24.1, "learning_rate": 2.467137852577129e-05, "loss": 0.0209, "positive_teacher_pairs": 26780.2, "relation_loss": 0.0020027236780151723, "selected_pairs": 26780.2, "step": 20570, "student_distance_mean": 1278.08291015625, "teacher_distance_mean": 0.8526998579502105, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0020027236780151723, "weighted_relation_loss": 0.0020027236780151723 }, { "action_query_batch_std": 22.326354217529296, "action_query_norm": 949.785546875, "action_relation_loss": 0.0021657816134393213, "auxiliary_loss_weight": 1.0, "epoch": 19.251637043966323, "flow_matching_loss": 0.02044271267950535, "grad_norm": 0.0879271849989891, "invalid_tail_samples": 24.8, "learning_rate": 2.4623873343920123e-05, "loss": 0.0226, "positive_teacher_pairs": 26623.3, "relation_loss": 0.0021657816134393213, "selected_pairs": 26623.3, "step": 20580, "student_distance_mean": 1282.4315673828125, "teacher_distance_mean": 0.8544344186782837, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0021657816134393213, "weighted_relation_loss": 0.0021657816134393213 }, { "action_query_batch_std": 22.45078239440918, "action_query_norm": 954.892822265625, "action_relation_loss": 0.0020428407122381033, "auxiliary_loss_weight": 1.0, "epoch": 19.260991580916745, "flow_matching_loss": 0.020033320970833303, "grad_norm": 0.09252467006444931, "invalid_tail_samples": 21.7, "learning_rate": 2.4576398996455656e-05, "loss": 0.0221, "positive_teacher_pairs": 27343.1, "relation_loss": 0.0020428407122381033, "selected_pairs": 27343.1, "step": 20590, "student_distance_mean": 1287.0646606445312, "teacher_distance_mean": 0.8579456984996796, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.0020428407122381033, "weighted_relation_loss": 0.0020428407122381033 }, { "action_query_batch_std": 22.477164459228515, "action_query_norm": 956.8245483398438, "action_relation_loss": 0.00206905126105994, "auxiliary_loss_weight": 1.0, "epoch": 19.270346117867167, "flow_matching_loss": 0.021490028686821462, "grad_norm": 0.1050940603017807, "invalid_tail_samples": 20.8, "learning_rate": 2.452895554106368e-05, "loss": 0.0236, "positive_teacher_pairs": 27548.9, "relation_loss": 0.00206905126105994, "selected_pairs": 27548.9, "step": 20600, "student_distance_mean": 1290.543994140625, "teacher_distance_mean": 0.8588152766227722, "valid_action_samples": 235.2, "weighted_auxiliary_loss": 0.00206905126105994, "weighted_relation_loss": 0.00206905126105994 }, { "action_query_batch_std": 22.31289291381836, "action_query_norm": 950.5759033203125, "action_relation_loss": 0.002166407194454223, "auxiliary_loss_weight": 1.0, "epoch": 19.279700654817585, "flow_matching_loss": 0.021178411785513163, "grad_norm": 0.07930298149585724, "invalid_tail_samples": 22.3, "learning_rate": 2.4481543035392506e-05, "loss": 0.0233, "positive_teacher_pairs": 27197.5, "relation_loss": 0.002166407194454223, "selected_pairs": 27197.5, "step": 20610, "student_distance_mean": 1279.3195922851562, "teacher_distance_mean": 0.8495869576931, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.002166407194454223, "weighted_relation_loss": 0.002166407194454223 }, { "action_query_batch_std": 21.970814895629882, "action_query_norm": 938.3430725097656, "action_relation_loss": 0.0021536461426876485, "auxiliary_loss_weight": 1.0, "epoch": 19.289055191768007, "flow_matching_loss": 0.02053016293793917, "grad_norm": 0.09443394839763641, "invalid_tail_samples": 25.0, "learning_rate": 2.4434161537052774e-05, "loss": 0.0227, "positive_teacher_pairs": 26575.2, "relation_loss": 0.0021536461426876485, "selected_pairs": 26575.2, "step": 20620, "student_distance_mean": 1266.3505737304688, "teacher_distance_mean": 0.8437453627586364, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0021536461426876485, "weighted_relation_loss": 0.0021536461426876485 }, { "action_query_batch_std": 22.218122673034667, "action_query_norm": 946.1566345214844, "action_relation_loss": 0.0021190094295889137, "auxiliary_loss_weight": 1.0, "epoch": 19.29840972871843, "flow_matching_loss": 0.019511574320495127, "grad_norm": 0.08792440593242645, "invalid_tail_samples": 24.0, "learning_rate": 2.4386811103617474e-05, "loss": 0.0216, "positive_teacher_pairs": 26802.2, "relation_loss": 0.0021190094295889137, "selected_pairs": 26802.2, "step": 20630, "student_distance_mean": 1271.1360595703125, "teacher_distance_mean": 0.8488773167133331, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0021190094295889137, "weighted_relation_loss": 0.0021190094295889137 }, { "action_query_batch_std": 22.33192367553711, "action_query_norm": 949.85673828125, "action_relation_loss": 0.0021312885684892533, "auxiliary_loss_weight": 1.0, "epoch": 19.30776426566885, "flow_matching_loss": 0.01970334369689226, "grad_norm": 0.08657386153936386, "invalid_tail_samples": 22.8, "learning_rate": 2.4339491792621833e-05, "loss": 0.0218, "positive_teacher_pairs": 27085.8, "relation_loss": 0.0021312885684892533, "selected_pairs": 27085.8, "step": 20640, "student_distance_mean": 1280.2757568359375, "teacher_distance_mean": 0.8541159510612488, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0021312885684892533, "weighted_relation_loss": 0.0021312885684892533 }, { "action_query_batch_std": 22.47519245147705, "action_query_norm": 955.8676147460938, "action_relation_loss": 0.0021409038454294205, "auxiliary_loss_weight": 1.0, "epoch": 19.31711880261927, "flow_matching_loss": 0.01937789125367999, "grad_norm": 0.11768782138824463, "invalid_tail_samples": 23.5, "learning_rate": 2.4292203661563312e-05, "loss": 0.0215, "positive_teacher_pairs": 26920.3, "relation_loss": 0.0021409038454294205, "selected_pairs": 26920.3, "step": 20650, "student_distance_mean": 1287.4499389648438, "teacher_distance_mean": 0.856582760810852, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0021409038454294205, "weighted_relation_loss": 0.0021409038454294205 }, { "action_query_batch_std": 22.47429370880127, "action_query_norm": 954.9591857910157, "action_relation_loss": 0.002152661490254104, "auxiliary_loss_weight": 1.0, "epoch": 19.32647333956969, "flow_matching_loss": 0.020120614487677813, "grad_norm": 0.09885042905807495, "invalid_tail_samples": 21.9, "learning_rate": 2.424494676790141e-05, "loss": 0.0223, "positive_teacher_pairs": 27289.7, "relation_loss": 0.002152661490254104, "selected_pairs": 27289.7, "step": 20660, "student_distance_mean": 1285.6985961914063, "teacher_distance_mean": 0.8541265368461609, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.002152661490254104, "weighted_relation_loss": 0.002152661490254104 }, { "action_query_batch_std": 22.56331672668457, "action_query_norm": 959.2784362792969, "action_relation_loss": 0.0020987104740925132, "auxiliary_loss_weight": 1.0, "epoch": 19.335827876520113, "flow_matching_loss": 0.02089834976941347, "grad_norm": 0.09155106544494629, "invalid_tail_samples": 25.2, "learning_rate": 2.4197721169057745e-05, "loss": 0.023, "positive_teacher_pairs": 26524.0, "relation_loss": 0.0020987104740925132, "selected_pairs": 26524.0, "step": 20670, "student_distance_mean": 1301.0266479492188, "teacher_distance_mean": 0.864881831407547, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0020987104740925132, "weighted_relation_loss": 0.0020987104740925132 }, { "action_query_batch_std": 22.529273223876952, "action_query_norm": 956.2882629394531, "action_relation_loss": 0.0020412071025930345, "auxiliary_loss_weight": 1.0, "epoch": 19.345182413470532, "flow_matching_loss": 0.01996322236955166, "grad_norm": 0.09787873923778534, "invalid_tail_samples": 22.7, "learning_rate": 2.4150526922415857e-05, "loss": 0.022, "positive_teacher_pairs": 27110.4, "relation_loss": 0.0020412071025930345, "selected_pairs": 27110.4, "step": 20680, "student_distance_mean": 1288.375537109375, "teacher_distance_mean": 0.8588218510150909, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0020412071025930345, "weighted_relation_loss": 0.0020412071025930345 }, { "action_query_batch_std": 22.0370454788208, "action_query_norm": 941.0744506835938, "action_relation_loss": 0.0021970700239762665, "auxiliary_loss_weight": 1.0, "epoch": 19.354536950420954, "flow_matching_loss": 0.021273213531821968, "grad_norm": 0.10177291929721832, "invalid_tail_samples": 23.4, "learning_rate": 2.41033640853212e-05, "loss": 0.0235, "positive_teacher_pairs": 26951.1, "relation_loss": 0.0021970700239762665, "selected_pairs": 26951.1, "step": 20690, "student_distance_mean": 1269.0168212890626, "teacher_distance_mean": 0.8439264595508575, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0021970700239762665, "weighted_relation_loss": 0.0021970700239762665 }, { "action_query_batch_std": 22.169189643859863, "action_query_norm": 942.9964233398438, "action_relation_loss": 0.002109976252540946, "auxiliary_loss_weight": 1.0, "epoch": 19.363891487371376, "flow_matching_loss": 0.018539256136864423, "grad_norm": 0.10734459012746811, "invalid_tail_samples": 23.7, "learning_rate": 2.405623271508108e-05, "loss": 0.0206, "positive_teacher_pairs": 26876.6, "relation_loss": 0.002109976252540946, "selected_pairs": 26876.6, "step": 20700, "student_distance_mean": 1270.4211669921874, "teacher_distance_mean": 0.8498884081840515, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.002109976252540946, "weighted_relation_loss": 0.002109976252540946 }, { "action_query_batch_std": 22.089976501464843, "action_query_norm": 943.7234191894531, "action_relation_loss": 0.002089816832449287, "auxiliary_loss_weight": 1.0, "epoch": 19.373246024321794, "flow_matching_loss": 0.018678454868495464, "grad_norm": 0.07328066229820251, "invalid_tail_samples": 24.2, "learning_rate": 2.4009132868964522e-05, "loss": 0.0208, "positive_teacher_pairs": 26755.6, "relation_loss": 0.002089816832449287, "selected_pairs": 26755.6, "step": 20710, "student_distance_mean": 1269.320751953125, "teacher_distance_mean": 0.847421008348465, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.002089816832449287, "weighted_relation_loss": 0.002089816832449287 }, { "action_query_batch_std": 22.021712493896484, "action_query_norm": 941.1527893066407, "action_relation_loss": 0.00204882042016834, "auxiliary_loss_weight": 1.0, "epoch": 19.382600561272216, "flow_matching_loss": 0.021137769520282745, "grad_norm": 0.08755327761173248, "invalid_tail_samples": 25.7, "learning_rate": 2.3962064604202327e-05, "loss": 0.0232, "positive_teacher_pairs": 26416.6, "relation_loss": 0.00204882042016834, "selected_pairs": 26416.6, "step": 20720, "student_distance_mean": 1263.9052856445312, "teacher_distance_mean": 0.8431564331054687, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.00204882042016834, "weighted_relation_loss": 0.00204882042016834 }, { "action_query_batch_std": 22.483244323730467, "action_query_norm": 955.1073425292968, "action_relation_loss": 0.0020699978806078432, "auxiliary_loss_weight": 1.0, "epoch": 19.39195509822264, "flow_matching_loss": 0.019444617629051208, "grad_norm": 0.08957633376121521, "invalid_tail_samples": 24.5, "learning_rate": 2.3915027977986858e-05, "loss": 0.0215, "positive_teacher_pairs": 26696.2, "relation_loss": 0.0020699978806078432, "selected_pairs": 26696.2, "step": 20730, "student_distance_mean": 1291.5651977539062, "teacher_distance_mean": 0.8611415743827819, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0020699978806078432, "weighted_relation_loss": 0.0020699978806078432 }, { "action_query_batch_std": 22.206303787231445, "action_query_norm": 944.9088012695313, "action_relation_loss": 0.0021435090457089245, "auxiliary_loss_weight": 1.0, "epoch": 19.40130963517306, "flow_matching_loss": 0.022027582861483097, "grad_norm": 0.0984937995672226, "invalid_tail_samples": 22.4, "learning_rate": 2.386802304747205e-05, "loss": 0.0242, "positive_teacher_pairs": 27178.0, "relation_loss": 0.0021435090457089245, "selected_pairs": 27178.0, "step": 20740, "student_distance_mean": 1275.0797973632812, "teacher_distance_mean": 0.8479250907897949, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.0021435090457089245, "weighted_relation_loss": 0.0021435090457089245 }, { "action_query_batch_std": 22.18553771972656, "action_query_norm": 940.9890380859375, "action_relation_loss": 0.0020049784565344454, "auxiliary_loss_weight": 1.0, "epoch": 19.41066417212348, "flow_matching_loss": 0.020683228224515914, "grad_norm": 0.09870896488428116, "invalid_tail_samples": 23.4, "learning_rate": 2.382104986977332e-05, "loss": 0.0227, "positive_teacher_pairs": 26940.8, "relation_loss": 0.0020049784565344454, "selected_pairs": 26940.8, "step": 20750, "student_distance_mean": 1273.5482788085938, "teacher_distance_mean": 0.8499489605426789, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0020049784565344454, "weighted_relation_loss": 0.0020049784565344454 }, { "action_query_batch_std": 22.522411155700684, "action_query_norm": 955.5280090332031, "action_relation_loss": 0.002110145753249526, "auxiliary_loss_weight": 1.0, "epoch": 19.4200187090739, "flow_matching_loss": 0.020018833223730326, "grad_norm": 0.07916577905416489, "invalid_tail_samples": 20.9, "learning_rate": 2.377410850196749e-05, "loss": 0.0221, "positive_teacher_pairs": 27525.3, "relation_loss": 0.002110145753249526, "selected_pairs": 27525.3, "step": 20760, "student_distance_mean": 1287.4030395507812, "teacher_distance_mean": 0.8604134678840637, "valid_action_samples": 235.1, "weighted_auxiliary_loss": 0.002110145753249526, "weighted_relation_loss": 0.002110145753249526 }, { "action_query_batch_std": 22.55166015625, "action_query_norm": 955.762841796875, "action_relation_loss": 0.002026264229789376, "auxiliary_loss_weight": 1.0, "epoch": 19.429373246024323, "flow_matching_loss": 0.021173245366662742, "grad_norm": 0.08469458669424057, "invalid_tail_samples": 23.5, "learning_rate": 2.3727199001092797e-05, "loss": 0.0232, "positive_teacher_pairs": 26920.2, "relation_loss": 0.002026264229789376, "selected_pairs": 26920.2, "step": 20770, "student_distance_mean": 1291.401904296875, "teacher_distance_mean": 0.8621614813804627, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.002026264229789376, "weighted_relation_loss": 0.002026264229789376 }, { "action_query_batch_std": 22.23253402709961, "action_query_norm": 949.3723571777343, "action_relation_loss": 0.0021091665606945754, "auxiliary_loss_weight": 1.0, "epoch": 19.43872778297474, "flow_matching_loss": 0.018960294499993324, "grad_norm": 0.09079952538013458, "invalid_tail_samples": 22.2, "learning_rate": 2.3680321424148677e-05, "loss": 0.0211, "positive_teacher_pairs": 27217.7, "relation_loss": 0.0021091665606945754, "selected_pairs": 27217.7, "step": 20780, "student_distance_mean": 1279.6633666992188, "teacher_distance_mean": 0.8535641729831696, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.0021091665606945754, "weighted_relation_loss": 0.0021091665606945754 }, { "action_query_batch_std": 22.08823928833008, "action_query_norm": 942.254345703125, "action_relation_loss": 0.0021985865896567702, "auxiliary_loss_weight": 1.0, "epoch": 19.448082319925163, "flow_matching_loss": 0.02071390338242054, "grad_norm": 0.09648872911930084, "invalid_tail_samples": 21.2, "learning_rate": 2.3633475828095793e-05, "loss": 0.0229, "positive_teacher_pairs": 27456.6, "relation_loss": 0.0021985865896567702, "selected_pairs": 27456.6, "step": 20790, "student_distance_mean": 1270.7337158203125, "teacher_distance_mean": 0.8485074043273926, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.0021985865896567702, "weighted_relation_loss": 0.0021985865896567702 }, { "action_query_batch_std": 22.18319625854492, "action_query_norm": 944.1929931640625, "action_relation_loss": 0.002126066875644028, "auxiliary_loss_weight": 1.0, "epoch": 19.457436856875585, "flow_matching_loss": 0.021699861250817777, "grad_norm": 0.0845547765493393, "invalid_tail_samples": 23.3, "learning_rate": 2.358666226985599e-05, "loss": 0.0238, "positive_teacher_pairs": 26966.4, "relation_loss": 0.002126066875644028, "selected_pairs": 26966.4, "step": 20800, "student_distance_mean": 1275.1241821289063, "teacher_distance_mean": 0.8529497385025024, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.002126066875644028, "weighted_relation_loss": 0.002126066875644028 }, { "action_query_batch_std": 22.373240280151368, "action_query_norm": 948.3392761230468, "action_relation_loss": 0.002096883300691843, "auxiliary_loss_weight": 1.0, "epoch": 19.466791393826007, "flow_matching_loss": 0.02034260965883732, "grad_norm": 0.09533639997243881, "invalid_tail_samples": 26.7, "learning_rate": 2.353988080631213e-05, "loss": 0.0224, "positive_teacher_pairs": 26176.7, "relation_loss": 0.002096883300691843, "selected_pairs": 26176.7, "step": 20810, "student_distance_mean": 1283.0983276367188, "teacher_distance_mean": 0.8578766822814942, "valid_action_samples": 229.3, "weighted_auxiliary_loss": 0.002096883300691843, "weighted_relation_loss": 0.002096883300691843 }, { "action_query_batch_std": 22.362766647338866, "action_query_norm": 948.5400390625, "action_relation_loss": 0.0020134258083999157, "auxiliary_loss_weight": 1.0, "epoch": 19.476145930776426, "flow_matching_loss": 0.019444257952272892, "grad_norm": 0.08963415026664734, "invalid_tail_samples": 23.0, "learning_rate": 2.3493131494308142e-05, "loss": 0.0215, "positive_teacher_pairs": 27035.6, "relation_loss": 0.0020134258083999157, "selected_pairs": 27035.6, "step": 20820, "student_distance_mean": 1286.0174438476563, "teacher_distance_mean": 0.8579287111759186, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0020134258083999157, "weighted_relation_loss": 0.0020134258083999157 }, { "action_query_batch_std": 22.570209312438966, "action_query_norm": 956.0581787109375, "action_relation_loss": 0.0020630639512091873, "auxiliary_loss_weight": 1.0, "epoch": 19.485500467726848, "flow_matching_loss": 0.02008782811462879, "grad_norm": 0.09029372036457062, "invalid_tail_samples": 23.9, "learning_rate": 2.344641439064881e-05, "loss": 0.0222, "positive_teacher_pairs": 26828.2, "relation_loss": 0.0020630639512091873, "selected_pairs": 26828.2, "step": 20830, "student_distance_mean": 1290.9813110351563, "teacher_distance_mean": 0.8623341858386994, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0020630639512091873, "weighted_relation_loss": 0.0020630639512091873 }, { "action_query_batch_std": 22.264657402038573, "action_query_norm": 948.2647399902344, "action_relation_loss": 0.0021028740564361216, "auxiliary_loss_weight": 1.0, "epoch": 19.49485500467727, "flow_matching_loss": 0.019916604459285735, "grad_norm": 0.09324391186237335, "invalid_tail_samples": 24.0, "learning_rate": 2.339972955209984e-05, "loss": 0.022, "positive_teacher_pairs": 26813.1, "relation_loss": 0.0021028740564361216, "selected_pairs": 26813.1, "step": 20840, "student_distance_mean": 1278.635546875, "teacher_distance_mean": 0.853520268201828, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0021028740564361216, "weighted_relation_loss": 0.0021028740564361216 }, { "action_query_batch_std": 22.29204864501953, "action_query_norm": 947.7332153320312, "action_relation_loss": 0.0020539446733891962, "auxiliary_loss_weight": 1.0, "epoch": 19.504209541627688, "flow_matching_loss": 0.022447685338556768, "grad_norm": 0.13192836940288544, "invalid_tail_samples": 21.8, "learning_rate": 2.335307703538771e-05, "loss": 0.0245, "positive_teacher_pairs": 27317.5, "relation_loss": 0.0020539446733891962, "selected_pairs": 27317.5, "step": 20850, "student_distance_mean": 1277.6578491210937, "teacher_distance_mean": 0.8532798409461975, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.0020539446733891962, "weighted_relation_loss": 0.0020539446733891962 }, { "action_query_batch_std": 22.656213569641114, "action_query_norm": 961.5328369140625, "action_relation_loss": 0.002011221868451685, "auxiliary_loss_weight": 1.0, "epoch": 19.51356407857811, "flow_matching_loss": 0.02128519117832184, "grad_norm": 0.09019207954406738, "invalid_tail_samples": 23.2, "learning_rate": 2.330645689719962e-05, "loss": 0.0233, "positive_teacher_pairs": 26987.8, "relation_loss": 0.002011221868451685, "selected_pairs": 26987.8, "step": 20860, "student_distance_mean": 1295.7047241210937, "teacher_distance_mean": 0.8673037886619568, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.002011221868451685, "weighted_relation_loss": 0.002011221868451685 }, { "action_query_batch_std": 22.36670207977295, "action_query_norm": 952.5652038574219, "action_relation_loss": 0.0021014335798099637, "auxiliary_loss_weight": 1.0, "epoch": 19.522918615528532, "flow_matching_loss": 0.020132710784673692, "grad_norm": 0.11535367369651794, "invalid_tail_samples": 22.5, "learning_rate": 2.3259869194183414e-05, "loss": 0.0222, "positive_teacher_pairs": 27150.1, "relation_loss": 0.0021014335798099637, "selected_pairs": 27150.1, "step": 20870, "student_distance_mean": 1289.3151245117188, "teacher_distance_mean": 0.8588767766952514, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0021014335798099637, "weighted_relation_loss": 0.0021014335798099637 }, { "action_query_batch_std": 22.3257719039917, "action_query_norm": 952.949462890625, "action_relation_loss": 0.002059219335205853, "auxiliary_loss_weight": 1.0, "epoch": 19.532273152478954, "flow_matching_loss": 0.01881658285856247, "grad_norm": 0.11407796293497086, "invalid_tail_samples": 25.4, "learning_rate": 2.321331398294759e-05, "loss": 0.0209, "positive_teacher_pairs": 26482.7, "relation_loss": 0.002059219335205853, "selected_pairs": 26482.7, "step": 20880, "student_distance_mean": 1285.2987060546875, "teacher_distance_mean": 0.8566109657287597, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.002059219335205853, "weighted_relation_loss": 0.002059219335205853 }, { "action_query_batch_std": 22.1506778717041, "action_query_norm": 946.124267578125, "action_relation_loss": 0.002144718437921256, "auxiliary_loss_weight": 1.0, "epoch": 19.541627689429372, "flow_matching_loss": 0.01995417904108763, "grad_norm": 0.09231316298246384, "invalid_tail_samples": 22.9, "learning_rate": 2.3166791320061094e-05, "loss": 0.0221, "positive_teacher_pairs": 27058.6, "relation_loss": 0.002144718437921256, "selected_pairs": 27058.6, "step": 20890, "student_distance_mean": 1266.7341064453126, "teacher_distance_mean": 0.8449335157871246, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.002144718437921256, "weighted_relation_loss": 0.002144718437921256 }, { "action_query_batch_std": 22.56476173400879, "action_query_norm": 959.5664367675781, "action_relation_loss": 0.0020944396150298417, "auxiliary_loss_weight": 1.0, "epoch": 19.550982226379794, "flow_matching_loss": 0.019725806172937156, "grad_norm": 0.10723908990621567, "invalid_tail_samples": 23.0, "learning_rate": 2.312030126205335e-05, "loss": 0.0218, "positive_teacher_pairs": 27041.8, "relation_loss": 0.0020944396150298417, "selected_pairs": 27041.8, "step": 20900, "student_distance_mean": 1297.534326171875, "teacher_distance_mean": 0.8720930397510529, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0020944396150298417, "weighted_relation_loss": 0.0020944396150298417 }, { "action_query_batch_std": 21.92911148071289, "action_query_norm": 934.8435852050782, "action_relation_loss": 0.0021273600170388816, "auxiliary_loss_weight": 1.0, "epoch": 19.560336763330216, "flow_matching_loss": 0.019017407204955816, "grad_norm": 0.14779706299304962, "invalid_tail_samples": 24.6, "learning_rate": 2.3073843865414162e-05, "loss": 0.0211, "positive_teacher_pairs": 26666.1, "relation_loss": 0.0021273600170388816, "selected_pairs": 26666.1, "step": 20910, "student_distance_mean": 1262.6927368164063, "teacher_distance_mean": 0.8464496970176697, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0021273600170388816, "weighted_relation_loss": 0.0021273600170388816 }, { "action_query_batch_std": 22.414098930358886, "action_query_norm": 950.437158203125, "action_relation_loss": 0.0020488774054683743, "auxiliary_loss_weight": 1.0, "epoch": 19.569691300280635, "flow_matching_loss": 0.02056475169956684, "grad_norm": 0.10188518464565277, "invalid_tail_samples": 24.8, "learning_rate": 2.302741918659363e-05, "loss": 0.0226, "positive_teacher_pairs": 26618.1, "relation_loss": 0.0020488774054683743, "selected_pairs": 26618.1, "step": 20920, "student_distance_mean": 1282.5092407226562, "teacher_distance_mean": 0.8589855194091797, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0020488774054683743, "weighted_relation_loss": 0.0020488774054683743 }, { "action_query_batch_std": 22.273894119262696, "action_query_norm": 947.8972717285156, "action_relation_loss": 0.002105646242853254, "auxiliary_loss_weight": 1.0, "epoch": 19.579045837231057, "flow_matching_loss": 0.01964832954108715, "grad_norm": 0.08815477043390274, "invalid_tail_samples": 24.0, "learning_rate": 2.2981027282002154e-05, "loss": 0.0218, "positive_teacher_pairs": 26803.9, "relation_loss": 0.002105646242853254, "selected_pairs": 26803.9, "step": 20930, "student_distance_mean": 1282.589990234375, "teacher_distance_mean": 0.8595274269580842, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.002105646242853254, "weighted_relation_loss": 0.002105646242853254 }, { "action_query_batch_std": 22.120883178710937, "action_query_norm": 942.1145874023438, "action_relation_loss": 0.0020981722278520464, "auxiliary_loss_weight": 1.0, "epoch": 19.58840037418148, "flow_matching_loss": 0.019270909298211337, "grad_norm": 0.08855152875185013, "invalid_tail_samples": 25.1, "learning_rate": 2.2934668208010236e-05, "loss": 0.0214, "positive_teacher_pairs": 26559.1, "relation_loss": 0.0020981722278520464, "selected_pairs": 26559.1, "step": 20940, "student_distance_mean": 1275.2824584960938, "teacher_distance_mean": 0.8525089502334595, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0020981722278520464, "weighted_relation_loss": 0.0020981722278520464 }, { "action_query_batch_std": 22.11801948547363, "action_query_norm": 944.5007568359375, "action_relation_loss": 0.0021644851425662638, "auxiliary_loss_weight": 1.0, "epoch": 19.5977549111319, "flow_matching_loss": 0.021414318680763246, "grad_norm": 0.08294928073883057, "invalid_tail_samples": 23.5, "learning_rate": 2.2888342020948555e-05, "loss": 0.0236, "positive_teacher_pairs": 26922.7, "relation_loss": 0.0021644851425662638, "selected_pairs": 26922.7, "step": 20950, "student_distance_mean": 1272.1933959960938, "teacher_distance_mean": 0.8513484418392181, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0021644851425662638, "weighted_relation_loss": 0.0021644851425662638 }, { "action_query_batch_std": 22.143287467956544, "action_query_norm": 942.8944396972656, "action_relation_loss": 0.0020266150822862983, "auxiliary_loss_weight": 1.0, "epoch": 19.60710944808232, "flow_matching_loss": 0.018826641235500575, "grad_norm": 0.09314969927072525, "invalid_tail_samples": 22.4, "learning_rate": 2.2842048777107783e-05, "loss": 0.0209, "positive_teacher_pairs": 27180.3, "relation_loss": 0.0020266150822862983, "selected_pairs": 27180.3, "step": 20960, "student_distance_mean": 1274.1758056640624, "teacher_distance_mean": 0.8531110465526581, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.0020266150822862983, "weighted_relation_loss": 0.0020266150822862983 }, { "action_query_batch_std": 22.319227981567384, "action_query_norm": 946.9246032714843, "action_relation_loss": 0.0021163406083360313, "auxiliary_loss_weight": 1.0, "epoch": 19.61646398503274, "flow_matching_loss": 0.01886400720104575, "grad_norm": 0.09705325961112976, "invalid_tail_samples": 23.1, "learning_rate": 2.2795788532738553e-05, "loss": 0.021, "positive_teacher_pairs": 27013.6, "relation_loss": 0.0021163406083360313, "selected_pairs": 27013.6, "step": 20970, "student_distance_mean": 1274.7911987304688, "teacher_distance_mean": 0.8526619911193848, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0021163406083360313, "weighted_relation_loss": 0.0021163406083360313 }, { "action_query_batch_std": 22.19091968536377, "action_query_norm": 946.6708984375, "action_relation_loss": 0.002137807640247047, "auxiliary_loss_weight": 1.0, "epoch": 19.625818521983163, "flow_matching_loss": 0.019972036592662334, "grad_norm": 0.10449255257844925, "invalid_tail_samples": 23.9, "learning_rate": 2.2749561344051468e-05, "loss": 0.0221, "positive_teacher_pairs": 26831.8, "relation_loss": 0.002137807640247047, "selected_pairs": 26831.8, "step": 20980, "student_distance_mean": 1275.025439453125, "teacher_distance_mean": 0.8498416423797608, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.002137807640247047, "weighted_relation_loss": 0.002137807640247047 }, { "action_query_batch_std": 22.396218299865723, "action_query_norm": 952.6847961425781, "action_relation_loss": 0.002075492637231946, "auxiliary_loss_weight": 1.0, "epoch": 19.63517305893358, "flow_matching_loss": 0.020098602585494518, "grad_norm": 0.0912373811006546, "invalid_tail_samples": 23.3, "learning_rate": 2.2703367267216896e-05, "loss": 0.0222, "positive_teacher_pairs": 26964.2, "relation_loss": 0.002075492637231946, "selected_pairs": 26964.2, "step": 20990, "student_distance_mean": 1278.0538330078125, "teacher_distance_mean": 0.8534628987312317, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.002075492637231946, "weighted_relation_loss": 0.002075492637231946 }, { "action_query_batch_std": 22.310226249694825, "action_query_norm": 950.3006896972656, "action_relation_loss": 0.002101869066245854, "auxiliary_loss_weight": 1.0, "epoch": 19.644527595884004, "flow_matching_loss": 0.019297417998313905, "grad_norm": 0.0939326211810112, "invalid_tail_samples": 22.4, "learning_rate": 2.2657206358364997e-05, "loss": 0.0214, "positive_teacher_pairs": 27180.4, "relation_loss": 0.002101869066245854, "selected_pairs": 27180.4, "step": 21000, "student_distance_mean": 1280.9553955078125, "teacher_distance_mean": 0.8563460767269134, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.002101869066245854, "weighted_relation_loss": 0.002101869066245854 }, { "action_query_batch_std": 22.09360694885254, "action_query_norm": 946.6057006835938, "action_relation_loss": 0.002118829474784434, "auxiliary_loss_weight": 1.0, "epoch": 19.653882132834426, "flow_matching_loss": 0.020683438703417777, "grad_norm": 0.10988438129425049, "invalid_tail_samples": 23.3, "learning_rate": 2.261107867358563e-05, "loss": 0.0228, "positive_teacher_pairs": 26969.9, "relation_loss": 0.002118829474784434, "selected_pairs": 26969.9, "step": 21010, "student_distance_mean": 1270.49921875, "teacher_distance_mean": 0.8459058821201324, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.002118829474784434, "weighted_relation_loss": 0.002118829474784434 }, { "action_query_batch_std": 22.336612510681153, "action_query_norm": 952.3679260253906, "action_relation_loss": 0.002068251045420766, "auxiliary_loss_weight": 1.0, "epoch": 19.663236669784844, "flow_matching_loss": 0.019953708350658416, "grad_norm": 0.10546424984931946, "invalid_tail_samples": 23.4, "learning_rate": 2.2564984268928263e-05, "loss": 0.022, "positive_teacher_pairs": 26945.5, "relation_loss": 0.002068251045420766, "selected_pairs": 26945.5, "step": 21020, "student_distance_mean": 1283.5209350585938, "teacher_distance_mean": 0.8603592813014984, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.002068251045420766, "weighted_relation_loss": 0.002068251045420766 }, { "action_query_batch_std": 21.991773986816405, "action_query_norm": 936.6068542480468, "action_relation_loss": 0.0021340959472581746, "auxiliary_loss_weight": 1.0, "epoch": 19.672591206735266, "flow_matching_loss": 0.022629563882946967, "grad_norm": 0.10850420594215393, "invalid_tail_samples": 25.6, "learning_rate": 2.251892320040198e-05, "loss": 0.0248, "positive_teacher_pairs": 26432.8, "relation_loss": 0.0021340959472581746, "selected_pairs": 26432.8, "step": 21030, "student_distance_mean": 1262.276220703125, "teacher_distance_mean": 0.8482008814811707, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.0021340959472581746, "weighted_relation_loss": 0.0021340959472581746 }, { "action_query_batch_std": 22.372297859191896, "action_query_norm": 949.1844787597656, "action_relation_loss": 0.0021052529918961227, "auxiliary_loss_weight": 1.0, "epoch": 19.681945743685688, "flow_matching_loss": 0.019733772799372672, "grad_norm": 0.09615866839885712, "invalid_tail_samples": 22.5, "learning_rate": 2.2472895523975312e-05, "loss": 0.0218, "positive_teacher_pairs": 27149.0, "relation_loss": 0.0021052529918961227, "selected_pairs": 27149.0, "step": 21040, "student_distance_mean": 1279.3749755859376, "teacher_distance_mean": 0.8537565886974334, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0021052529918961227, "weighted_relation_loss": 0.0021052529918961227 }, { "action_query_batch_std": 22.353743934631346, "action_query_norm": 950.5071899414063, "action_relation_loss": 0.002129322336986661, "auxiliary_loss_weight": 1.0, "epoch": 19.69130028063611, "flow_matching_loss": 0.019351894315332175, "grad_norm": 0.09919029474258423, "invalid_tail_samples": 23.4, "learning_rate": 2.2426901295576212e-05, "loss": 0.0215, "positive_teacher_pairs": 26943.2, "relation_loss": 0.002129322336986661, "selected_pairs": 26943.2, "step": 21050, "student_distance_mean": 1282.2914916992188, "teacher_distance_mean": 0.8577932715415955, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.002129322336986661, "weighted_relation_loss": 0.002129322336986661 }, { "action_query_batch_std": 22.05440311431885, "action_query_norm": 940.0649597167969, "action_relation_loss": 0.0020922908675856887, "auxiliary_loss_weight": 1.0, "epoch": 19.70065481758653, "flow_matching_loss": 0.019426336977630854, "grad_norm": 0.10150203853845596, "invalid_tail_samples": 21.6, "learning_rate": 2.2380940571092013e-05, "loss": 0.0215, "positive_teacher_pairs": 27365.3, "relation_loss": 0.0020922908675856887, "selected_pairs": 27365.3, "step": 21060, "student_distance_mean": 1261.2245483398438, "teacher_distance_mean": 0.8447649538516998, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.0020922908675856887, "weighted_relation_loss": 0.0020922908675856887 }, { "action_query_batch_std": 22.25159435272217, "action_query_norm": 949.6860595703125, "action_relation_loss": 0.0020759416511282325, "auxiliary_loss_weight": 1.0, "epoch": 19.71000935453695, "flow_matching_loss": 0.021239122934639455, "grad_norm": 0.08204666525125504, "invalid_tail_samples": 21.7, "learning_rate": 2.2335013406369302e-05, "loss": 0.0233, "positive_teacher_pairs": 27344.0, "relation_loss": 0.0020759416511282325, "selected_pairs": 27344.0, "step": 21070, "student_distance_mean": 1281.0905883789062, "teacher_distance_mean": 0.8575551033020019, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.0020759416511282325, "weighted_relation_loss": 0.0020759416511282325 }, { "action_query_batch_std": 22.182526969909667, "action_query_norm": 945.459326171875, "action_relation_loss": 0.00206214995123446, "auxiliary_loss_weight": 1.0, "epoch": 19.719363891487372, "flow_matching_loss": 0.01994943181052804, "grad_norm": 0.10371734946966171, "invalid_tail_samples": 25.7, "learning_rate": 2.228911985721397e-05, "loss": 0.022, "positive_teacher_pairs": 26414.5, "relation_loss": 0.00206214995123446, "selected_pairs": 26414.5, "step": 21080, "student_distance_mean": 1277.8988525390625, "teacher_distance_mean": 0.8538690447807312, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.00206214995123446, "weighted_relation_loss": 0.00206214995123446 }, { "action_query_batch_std": 22.294440269470215, "action_query_norm": 946.0306274414063, "action_relation_loss": 0.0021088063018396496, "auxiliary_loss_weight": 1.0, "epoch": 19.72871842843779, "flow_matching_loss": 0.019256265740841626, "grad_norm": 0.12159755080938339, "invalid_tail_samples": 22.8, "learning_rate": 2.224325997939095e-05, "loss": 0.0214, "positive_teacher_pairs": 27083.4, "relation_loss": 0.0021088063018396496, "selected_pairs": 27083.4, "step": 21090, "student_distance_mean": 1279.1386962890624, "teacher_distance_mean": 0.8558204114437103, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0021088063018396496, "weighted_relation_loss": 0.0021088063018396496 }, { "action_query_batch_std": 22.18364028930664, "action_query_norm": 942.8632080078125, "action_relation_loss": 0.0020785561413504184, "auxiliary_loss_weight": 1.0, "epoch": 19.738072965388213, "flow_matching_loss": 0.020744919404387475, "grad_norm": 0.095530666410923, "invalid_tail_samples": 24.2, "learning_rate": 2.219743382862437e-05, "loss": 0.0228, "positive_teacher_pairs": 26762.6, "relation_loss": 0.0020785561413504184, "selected_pairs": 26762.6, "step": 21100, "student_distance_mean": 1278.1614379882812, "teacher_distance_mean": 0.855107432603836, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0020785561413504184, "weighted_relation_loss": 0.0020785561413504184 }, { "action_query_batch_std": 22.216246032714842, "action_query_norm": 947.6401123046875, "action_relation_loss": 0.0021308176685124634, "auxiliary_loss_weight": 1.0, "epoch": 19.747427502338635, "flow_matching_loss": 0.01960646715015173, "grad_norm": 0.08853248506784439, "invalid_tail_samples": 25.9, "learning_rate": 2.2151641460597294e-05, "loss": 0.0217, "positive_teacher_pairs": 26363.2, "relation_loss": 0.0021308176685124634, "selected_pairs": 26363.2, "step": 21110, "student_distance_mean": 1275.6912841796875, "teacher_distance_mean": 0.8523089528083801, "valid_action_samples": 230.1, "weighted_auxiliary_loss": 0.0021308176685124634, "weighted_relation_loss": 0.0021308176685124634 }, { "action_query_batch_std": 22.102004623413087, "action_query_norm": 943.4574157714844, "action_relation_loss": 0.0020698888576589523, "auxiliary_loss_weight": 1.0, "epoch": 19.756782039289057, "flow_matching_loss": 0.017512001935392617, "grad_norm": 0.09600474685430527, "invalid_tail_samples": 21.0, "learning_rate": 2.210588293095177e-05, "loss": 0.0196, "positive_teacher_pairs": 27502.1, "relation_loss": 0.0020698888576589523, "selected_pairs": 27502.1, "step": 21120, "student_distance_mean": 1269.4017944335938, "teacher_distance_mean": 0.8468704044818878, "valid_action_samples": 235.0, "weighted_auxiliary_loss": 0.0020698888576589523, "weighted_relation_loss": 0.0020698888576589523 }, { "action_query_batch_std": 22.201640129089355, "action_query_norm": 946.7142578125, "action_relation_loss": 0.0021097865188494324, "auxiliary_loss_weight": 1.0, "epoch": 19.766136576239475, "flow_matching_loss": 0.02035949397832155, "grad_norm": 0.10366032272577286, "invalid_tail_samples": 23.1, "learning_rate": 2.2060158295288714e-05, "loss": 0.0225, "positive_teacher_pairs": 27009.7, "relation_loss": 0.0021097865188494324, "selected_pairs": 27009.7, "step": 21130, "student_distance_mean": 1281.2233520507812, "teacher_distance_mean": 0.8532328605651855, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0021097865188494324, "weighted_relation_loss": 0.0021097865188494324 }, { "action_query_batch_std": 22.675136375427247, "action_query_norm": 962.3106140136719, "action_relation_loss": 0.0020775872515514495, "auxiliary_loss_weight": 1.0, "epoch": 19.775491113189897, "flow_matching_loss": 0.019875551201403142, "grad_norm": 0.0861181691288948, "invalid_tail_samples": 22.1, "learning_rate": 2.2014467609167905e-05, "loss": 0.022, "positive_teacher_pairs": 27247.0, "relation_loss": 0.0020775872515514495, "selected_pairs": 27247.0, "step": 21140, "student_distance_mean": 1296.570947265625, "teacher_distance_mean": 0.8654014825820923, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0020775872515514495, "weighted_relation_loss": 0.0020775872515514495 }, { "action_query_batch_std": 22.113833808898924, "action_query_norm": 940.6710998535157, "action_relation_loss": 0.0021046075969934465, "auxiliary_loss_weight": 1.0, "epoch": 19.78484565014032, "flow_matching_loss": 0.020067593641579153, "grad_norm": 0.09726160019636154, "invalid_tail_samples": 24.6, "learning_rate": 2.1968810928107806e-05, "loss": 0.0222, "positive_teacher_pairs": 26671.1, "relation_loss": 0.0021046075969934465, "selected_pairs": 26671.1, "step": 21150, "student_distance_mean": 1272.3635375976562, "teacher_distance_mean": 0.8492263615131378, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0021046075969934465, "weighted_relation_loss": 0.0021046075969934465 }, { "action_query_batch_std": 22.25244140625, "action_query_norm": 944.3441711425781, "action_relation_loss": 0.002072299201972783, "auxiliary_loss_weight": 1.0, "epoch": 19.794200187090738, "flow_matching_loss": 0.019213184155523776, "grad_norm": 0.09541474282741547, "invalid_tail_samples": 26.3, "learning_rate": 2.1923188307585606e-05, "loss": 0.0213, "positive_teacher_pairs": 26278.6, "relation_loss": 0.002072299201972783, "selected_pairs": 26278.6, "step": 21160, "student_distance_mean": 1274.3960083007812, "teacher_distance_mean": 0.8507069826126099, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.002072299201972783, "weighted_relation_loss": 0.002072299201972783 }, { "action_query_batch_std": 22.424263763427735, "action_query_norm": 954.1222900390625, "action_relation_loss": 0.0020725098554976286, "auxiliary_loss_weight": 1.0, "epoch": 19.80355472404116, "flow_matching_loss": 0.019971031695604324, "grad_norm": 0.0950024202466011, "invalid_tail_samples": 22.3, "learning_rate": 2.187759980303708e-05, "loss": 0.022, "positive_teacher_pairs": 27202.0, "relation_loss": 0.0020725098554976286, "selected_pairs": 27202.0, "step": 21170, "student_distance_mean": 1289.227734375, "teacher_distance_mean": 0.8606051564216614, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0020725098554976286, "weighted_relation_loss": 0.0020725098554976286 }, { "action_query_batch_std": 22.316848754882812, "action_query_norm": 948.3299743652344, "action_relation_loss": 0.0020103894057683647, "auxiliary_loss_weight": 1.0, "epoch": 19.81290926099158, "flow_matching_loss": 0.021141666546463968, "grad_norm": 0.13745537400245667, "invalid_tail_samples": 24.9, "learning_rate": 2.1832045469856545e-05, "loss": 0.0232, "positive_teacher_pairs": 26600.1, "relation_loss": 0.0020103894057683647, "selected_pairs": 26600.1, "step": 21180, "student_distance_mean": 1282.100244140625, "teacher_distance_mean": 0.8545000076293945, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0020103894057683647, "weighted_relation_loss": 0.0020103894057683647 }, { "action_query_batch_std": 22.20943088531494, "action_query_norm": 946.2809204101562, "action_relation_loss": 0.0020015696645714343, "auxiliary_loss_weight": 1.0, "epoch": 19.822263797942004, "flow_matching_loss": 0.019356653187423946, "grad_norm": 0.10453809052705765, "invalid_tail_samples": 23.2, "learning_rate": 2.1786525363396844e-05, "loss": 0.0214, "positive_teacher_pairs": 26992.0, "relation_loss": 0.0020015696645714343, "selected_pairs": 26992.0, "step": 21190, "student_distance_mean": 1278.1983520507813, "teacher_distance_mean": 0.8534283995628357, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0020015696645714343, "weighted_relation_loss": 0.0020015696645714343 }, { "action_query_batch_std": 22.307444953918456, "action_query_norm": 944.2637390136719, "action_relation_loss": 0.002062300860416144, "auxiliary_loss_weight": 1.0, "epoch": 19.831618334892422, "flow_matching_loss": 0.02049744352698326, "grad_norm": 0.0931628867983818, "invalid_tail_samples": 25.5, "learning_rate": 2.1741039538969183e-05, "loss": 0.0226, "positive_teacher_pairs": 26465.1, "relation_loss": 0.002062300860416144, "selected_pairs": 26465.1, "step": 21200, "student_distance_mean": 1281.2811279296875, "teacher_distance_mean": 0.8579222977161407, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.002062300860416144, "weighted_relation_loss": 0.002062300860416144 }, { "action_query_batch_std": 21.909806632995604, "action_query_norm": 935.8569885253906, "action_relation_loss": 0.002119052177295089, "auxiliary_loss_weight": 1.0, "epoch": 19.840972871842844, "flow_matching_loss": 0.020814773440361024, "grad_norm": 0.14735014736652374, "invalid_tail_samples": 24.5, "learning_rate": 2.169558805184313e-05, "loss": 0.0229, "positive_teacher_pairs": 26685.3, "relation_loss": 0.002119052177295089, "selected_pairs": 26685.3, "step": 21210, "student_distance_mean": 1258.9236206054688, "teacher_distance_mean": 0.8431875348091126, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.002119052177295089, "weighted_relation_loss": 0.002119052177295089 }, { "action_query_batch_std": 22.338857460021973, "action_query_norm": 948.3690490722656, "action_relation_loss": 0.00208240516949445, "auxiliary_loss_weight": 1.0, "epoch": 19.850327408793266, "flow_matching_loss": 0.020666353311389683, "grad_norm": 0.09315481781959534, "invalid_tail_samples": 24.7, "learning_rate": 2.165017095724651e-05, "loss": 0.0227, "positive_teacher_pairs": 26649.2, "relation_loss": 0.00208240516949445, "selected_pairs": 26649.2, "step": 21220, "student_distance_mean": 1286.2495483398438, "teacher_distance_mean": 0.8606465458869934, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.00208240516949445, "weighted_relation_loss": 0.00208240516949445 }, { "action_query_batch_std": 22.118919372558594, "action_query_norm": 944.7332214355469, "action_relation_loss": 0.0021064392291009425, "auxiliary_loss_weight": 1.0, "epoch": 19.859681945743684, "flow_matching_loss": 0.019224178791046143, "grad_norm": 0.09258623421192169, "invalid_tail_samples": 24.9, "learning_rate": 2.1604788310365405e-05, "loss": 0.0213, "positive_teacher_pairs": 26599.7, "relation_loss": 0.0021064392291009425, "selected_pairs": 26599.7, "step": 21230, "student_distance_mean": 1275.9705322265625, "teacher_distance_mean": 0.8519236147403717, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0021064392291009425, "weighted_relation_loss": 0.0021064392291009425 }, { "action_query_batch_std": 21.90610694885254, "action_query_norm": 939.2117736816406, "action_relation_loss": 0.0022568809101358054, "auxiliary_loss_weight": 1.0, "epoch": 19.869036482694106, "flow_matching_loss": 0.019180713593959807, "grad_norm": 0.09353594481945038, "invalid_tail_samples": 25.7, "learning_rate": 2.155944016634398e-05, "loss": 0.0214, "positive_teacher_pairs": 26420.0, "relation_loss": 0.0022568809101358054, "selected_pairs": 26420.0, "step": 21240, "student_distance_mean": 1259.151220703125, "teacher_distance_mean": 0.8422824919223786, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.0022568809101358054, "weighted_relation_loss": 0.0022568809101358054 }, { "action_query_batch_std": 22.122643280029298, "action_query_norm": 946.5809875488281, "action_relation_loss": 0.002056599163915962, "auxiliary_loss_weight": 1.0, "epoch": 19.87839101964453, "flow_matching_loss": 0.01788112036883831, "grad_norm": 0.08769967406988144, "invalid_tail_samples": 23.9, "learning_rate": 2.1514126580284538e-05, "loss": 0.0199, "positive_teacher_pairs": 26823.3, "relation_loss": 0.002056599163915962, "selected_pairs": 26823.3, "step": 21250, "student_distance_mean": 1272.0539916992188, "teacher_distance_mean": 0.8513802528381348, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.002056599163915962, "weighted_relation_loss": 0.002056599163915962 }, { "action_query_batch_std": 22.260349464416503, "action_query_norm": 948.0856750488281, "action_relation_loss": 0.002073584799654782, "auxiliary_loss_weight": 1.0, "epoch": 19.88774555659495, "flow_matching_loss": 0.018824477773159744, "grad_norm": 0.10083837062120438, "invalid_tail_samples": 21.4, "learning_rate": 2.1468847607247344e-05, "loss": 0.0209, "positive_teacher_pairs": 27406.0, "relation_loss": 0.002073584799654782, "selected_pairs": 27406.0, "step": 21260, "student_distance_mean": 1277.5836303710937, "teacher_distance_mean": 0.8561869978904724, "valid_action_samples": 234.6, "weighted_auxiliary_loss": 0.002073584799654782, "weighted_relation_loss": 0.002073584799654782 }, { "action_query_batch_std": 22.569198036193846, "action_query_norm": 956.4925109863282, "action_relation_loss": 0.002098038699477911, "auxiliary_loss_weight": 1.0, "epoch": 19.89710009354537, "flow_matching_loss": 0.019850379042327403, "grad_norm": 0.08540580421686172, "invalid_tail_samples": 22.4, "learning_rate": 2.1423603302250623e-05, "loss": 0.0219, "positive_teacher_pairs": 27173.8, "relation_loss": 0.002098038699477911, "selected_pairs": 27173.8, "step": 21270, "student_distance_mean": 1296.4303344726563, "teacher_distance_mean": 0.8644936978816986, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.002098038699477911, "weighted_relation_loss": 0.002098038699477911 }, { "action_query_batch_std": 22.48919849395752, "action_query_norm": 956.1009399414063, "action_relation_loss": 0.0020638503250665964, "auxiliary_loss_weight": 1.0, "epoch": 19.90645463049579, "flow_matching_loss": 0.02108903508633375, "grad_norm": 0.11374976485967636, "invalid_tail_samples": 23.6, "learning_rate": 2.1378393720270468e-05, "loss": 0.0232, "positive_teacher_pairs": 26893.0, "relation_loss": 0.0020638503250665964, "selected_pairs": 26893.0, "step": 21280, "student_distance_mean": 1293.3240478515625, "teacher_distance_mean": 0.860652619600296, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0020638503250665964, "weighted_relation_loss": 0.0020638503250665964 }, { "action_query_batch_std": 22.247692680358888, "action_query_norm": 951.6907531738282, "action_relation_loss": 0.001999786065425724, "auxiliary_loss_weight": 1.0, "epoch": 19.915809167446213, "flow_matching_loss": 0.020404163189232348, "grad_norm": 0.08034329116344452, "invalid_tail_samples": 23.4, "learning_rate": 2.133321891624076e-05, "loss": 0.0224, "positive_teacher_pairs": 26942.4, "relation_loss": 0.001999786065425724, "selected_pairs": 26942.4, "step": 21290, "student_distance_mean": 1272.5696533203125, "teacher_distance_mean": 0.8502300918102265, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.001999786065425724, "weighted_relation_loss": 0.001999786065425724 }, { "action_query_batch_std": 22.366637802124025, "action_query_norm": 950.2546203613281, "action_relation_loss": 0.0020525920554064214, "auxiliary_loss_weight": 1.0, "epoch": 19.92516370439663, "flow_matching_loss": 0.019238171447068454, "grad_norm": 0.09291880577802658, "invalid_tail_samples": 25.3, "learning_rate": 2.1288078945053193e-05, "loss": 0.0213, "positive_teacher_pairs": 26506.7, "relation_loss": 0.0020525920554064214, "selected_pairs": 26506.7, "step": 21300, "student_distance_mean": 1288.3168701171876, "teacher_distance_mean": 0.8636962234973907, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0020525920554064214, "weighted_relation_loss": 0.0020525920554064214 }, { "action_query_batch_std": 21.886949157714845, "action_query_norm": 935.9964782714844, "action_relation_loss": 0.0020802990533411504, "auxiliary_loss_weight": 1.0, "epoch": 19.934518241347053, "flow_matching_loss": 0.01791303977370262, "grad_norm": 0.1090271919965744, "invalid_tail_samples": 25.2, "learning_rate": 2.1242973861557064e-05, "loss": 0.02, "positive_teacher_pairs": 26523.8, "relation_loss": 0.0020802990533411504, "selected_pairs": 26523.8, "step": 21310, "student_distance_mean": 1259.9265258789062, "teacher_distance_mean": 0.8453199684619903, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0020802990533411504, "weighted_relation_loss": 0.0020802990533411504 }, { "action_query_batch_std": 22.404022216796875, "action_query_norm": 954.8610168457031, "action_relation_loss": 0.002036134270019829, "auxiliary_loss_weight": 1.0, "epoch": 19.943872778297475, "flow_matching_loss": 0.018130838125944137, "grad_norm": 0.08167170733213425, "invalid_tail_samples": 22.5, "learning_rate": 2.1197903720559304e-05, "loss": 0.0202, "positive_teacher_pairs": 27152.9, "relation_loss": 0.002036134270019829, "selected_pairs": 27152.9, "step": 21320, "student_distance_mean": 1292.0028076171875, "teacher_distance_mean": 0.8659355103969574, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.002036134270019829, "weighted_relation_loss": 0.002036134270019829 }, { "action_query_batch_std": 22.369313430786132, "action_query_norm": 949.2115783691406, "action_relation_loss": 0.0021505378652364017, "auxiliary_loss_weight": 1.0, "epoch": 19.953227315247894, "flow_matching_loss": 0.019615001603960992, "grad_norm": 0.10488496720790863, "invalid_tail_samples": 26.4, "learning_rate": 2.115286857682438e-05, "loss": 0.0218, "positive_teacher_pairs": 26255.2, "relation_loss": 0.0021505378652364017, "selected_pairs": 26255.2, "step": 21330, "student_distance_mean": 1288.6161010742187, "teacher_distance_mean": 0.8625416815280914, "valid_action_samples": 229.6, "weighted_auxiliary_loss": 0.0021505378652364017, "weighted_relation_loss": 0.0021505378652364017 }, { "action_query_batch_std": 22.249976348876952, "action_query_norm": 949.3011535644531, "action_relation_loss": 0.0020503408391959964, "auxiliary_loss_weight": 1.0, "epoch": 19.962581852198316, "flow_matching_loss": 0.020764285512268544, "grad_norm": 0.08292660117149353, "invalid_tail_samples": 24.3, "learning_rate": 2.1107868485074228e-05, "loss": 0.0228, "positive_teacher_pairs": 26736.3, "relation_loss": 0.0020503408391959964, "selected_pairs": 26736.3, "step": 21340, "student_distance_mean": 1280.0886474609374, "teacher_distance_mean": 0.8567478835582734, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0020503408391959964, "weighted_relation_loss": 0.0020503408391959964 }, { "action_query_batch_std": 22.28941955566406, "action_query_norm": 947.4351257324219, "action_relation_loss": 0.0020669385441578923, "auxiliary_loss_weight": 1.0, "epoch": 19.971936389148738, "flow_matching_loss": 0.02140307631343603, "grad_norm": 0.10053684562444687, "invalid_tail_samples": 22.0, "learning_rate": 2.1062903499988234e-05, "loss": 0.0235, "positive_teacher_pairs": 27263.0, "relation_loss": 0.0020669385441578923, "selected_pairs": 27263.0, "step": 21350, "student_distance_mean": 1277.4997802734374, "teacher_distance_mean": 0.856287705898285, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.0020669385441578923, "weighted_relation_loss": 0.0020669385441578923 }, { "action_query_batch_std": 22.387170028686523, "action_query_norm": 948.2435607910156, "action_relation_loss": 0.002008288272190839, "auxiliary_loss_weight": 1.0, "epoch": 19.98129092609916, "flow_matching_loss": 0.018231190741062164, "grad_norm": 0.08013216406106949, "invalid_tail_samples": 26.9, "learning_rate": 2.101797367620308e-05, "loss": 0.0202, "positive_teacher_pairs": 26132.5, "relation_loss": 0.002008288272190839, "selected_pairs": 26132.5, "step": 21360, "student_distance_mean": 1288.4667114257813, "teacher_distance_mean": 0.8639300227165222, "valid_action_samples": 229.1, "weighted_auxiliary_loss": 0.002008288272190839, "weighted_relation_loss": 0.002008288272190839 }, { "action_query_batch_std": 22.30434341430664, "action_query_norm": 946.2783142089844, "action_relation_loss": 0.002042909630108625, "auxiliary_loss_weight": 1.0, "epoch": 19.990645463049578, "flow_matching_loss": 0.019442891329526903, "grad_norm": 0.08492705971002579, "invalid_tail_samples": 23.4, "learning_rate": 2.0973079068312713e-05, "loss": 0.0215, "positive_teacher_pairs": 26946.2, "relation_loss": 0.002042909630108625, "selected_pairs": 26946.2, "step": 21370, "student_distance_mean": 1283.1635864257812, "teacher_distance_mean": 0.857511454820633, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.002042909630108625, "weighted_relation_loss": 0.002042909630108625 }, { "action_query_batch_std": 22.416506004333495, "action_query_norm": 954.9585021972656, "action_relation_loss": 0.00208210195414722, "auxiliary_loss_weight": 1.0, "epoch": 20.0, "flow_matching_loss": 0.021108248457312583, "grad_norm": 0.19518929719924927, "invalid_tail_samples": 22.2, "learning_rate": 2.0928219730868358e-05, "loss": 0.0232, "positive_teacher_pairs": 24176.4, "relation_loss": 0.00208210195414722, "selected_pairs": 24176.4, "step": 21380, "student_distance_mean": 1293.5230102539062, "teacher_distance_mean": 0.8634997725486755, "valid_action_samples": 213.9, "weighted_auxiliary_loss": 0.00208210195414722, "weighted_relation_loss": 0.00208210195414722 }, { "action_query_batch_std": 21.918511581420898, "action_query_norm": 935.357666015625, "action_relation_loss": 0.0020597218186594545, "auxiliary_loss_weight": 1.0, "epoch": 20.009354536950422, "flow_matching_loss": 0.020467629097402094, "grad_norm": 0.13681334257125854, "invalid_tail_samples": 24.3, "learning_rate": 2.0883395718378302e-05, "loss": 0.0225, "positive_teacher_pairs": 26738.5, "relation_loss": 0.0020597218186594545, "selected_pairs": 26738.5, "step": 21390, "student_distance_mean": 1264.4131225585938, "teacher_distance_mean": 0.8456033170223236, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0020597218186594545, "weighted_relation_loss": 0.0020597218186594545 }, { "action_query_batch_std": 22.23735179901123, "action_query_norm": 945.7842712402344, "action_relation_loss": 0.0019638681435026227, "auxiliary_loss_weight": 1.0, "epoch": 20.01870907390084, "flow_matching_loss": 0.018840792868286372, "grad_norm": 0.09684118628501892, "invalid_tail_samples": 21.6, "learning_rate": 2.083860708530798e-05, "loss": 0.0208, "positive_teacher_pairs": 27358.8, "relation_loss": 0.0019638681435026227, "selected_pairs": 27358.8, "step": 21400, "student_distance_mean": 1273.791357421875, "teacher_distance_mean": 0.8532844603061676, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.0019638681435026227, "weighted_relation_loss": 0.0019638681435026227 }, { "action_query_batch_std": 22.179870796203613, "action_query_norm": 944.3577697753906, "action_relation_loss": 0.00196272226748988, "auxiliary_loss_weight": 1.0, "epoch": 20.028063610851262, "flow_matching_loss": 0.020216717943549158, "grad_norm": 0.10692822933197021, "invalid_tail_samples": 21.4, "learning_rate": 2.0793853886079796e-05, "loss": 0.0222, "positive_teacher_pairs": 27408.7, "relation_loss": 0.00196272226748988, "selected_pairs": 27408.7, "step": 21410, "student_distance_mean": 1273.3898559570312, "teacher_distance_mean": 0.8520319998264313, "valid_action_samples": 234.6, "weighted_auxiliary_loss": 0.00196272226748988, "weighted_relation_loss": 0.00196272226748988 }, { "action_query_batch_std": 22.332177734375, "action_query_norm": 950.0040893554688, "action_relation_loss": 0.001925481460057199, "auxiliary_loss_weight": 1.0, "epoch": 20.037418147801684, "flow_matching_loss": 0.01829658607020974, "grad_norm": 0.0866965502500534, "invalid_tail_samples": 26.0, "learning_rate": 2.074913617507309e-05, "loss": 0.0202, "positive_teacher_pairs": 26354.4, "relation_loss": 0.001925481460057199, "selected_pairs": 26354.4, "step": 21420, "student_distance_mean": 1286.113427734375, "teacher_distance_mean": 0.8614849925041199, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.001925481460057199, "weighted_relation_loss": 0.001925481460057199 }, { "action_query_batch_std": 22.04364929199219, "action_query_norm": 945.8037536621093, "action_relation_loss": 0.0019704869482666254, "auxiliary_loss_weight": 1.0, "epoch": 20.046772684752106, "flow_matching_loss": 0.019800679851323368, "grad_norm": 0.09443920850753784, "invalid_tail_samples": 21.8, "learning_rate": 2.070445400662411e-05, "loss": 0.0218, "positive_teacher_pairs": 27312.9, "relation_loss": 0.0019704869482666254, "selected_pairs": 27312.9, "step": 21430, "student_distance_mean": 1269.88623046875, "teacher_distance_mean": 0.848334151506424, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.0019704869482666254, "weighted_relation_loss": 0.0019704869482666254 }, { "action_query_batch_std": 22.147771072387695, "action_query_norm": 944.9763427734375, "action_relation_loss": 0.0021551801357418297, "auxiliary_loss_weight": 1.0, "epoch": 20.056127221702525, "flow_matching_loss": 0.018661631364375354, "grad_norm": 0.09373766928911209, "invalid_tail_samples": 21.2, "learning_rate": 2.0659807435025907e-05, "loss": 0.0208, "positive_teacher_pairs": 27452.7, "relation_loss": 0.0021551801357418297, "selected_pairs": 27452.7, "step": 21440, "student_distance_mean": 1274.6594360351562, "teacher_distance_mean": 0.8506998181343078, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.0021551801357418297, "weighted_relation_loss": 0.0021551801357418297 }, { "action_query_batch_std": 22.493736267089844, "action_query_norm": 956.9697448730469, "action_relation_loss": 0.0019650337286293506, "auxiliary_loss_weight": 1.0, "epoch": 20.065481758652947, "flow_matching_loss": 0.018186983186751604, "grad_norm": 0.1375260055065155, "invalid_tail_samples": 25.0, "learning_rate": 2.061519651452825e-05, "loss": 0.0202, "positive_teacher_pairs": 26577.0, "relation_loss": 0.0019650337286293506, "selected_pairs": 26577.0, "step": 21450, "student_distance_mean": 1294.8231201171875, "teacher_distance_mean": 0.8634220242500306, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0019650337286293506, "weighted_relation_loss": 0.0019650337286293506 }, { "action_query_batch_std": 22.417857360839843, "action_query_norm": 954.9541198730469, "action_relation_loss": 0.002012642903719097, "auxiliary_loss_weight": 1.0, "epoch": 20.07483629560337, "flow_matching_loss": 0.01892473055049777, "grad_norm": 0.08141415566205978, "invalid_tail_samples": 21.5, "learning_rate": 2.0570621299337656e-05, "loss": 0.0209, "positive_teacher_pairs": 27388.4, "relation_loss": 0.002012642903719097, "selected_pairs": 27388.4, "step": 21460, "student_distance_mean": 1286.3984375, "teacher_distance_mean": 0.8582565307617187, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.002012642903719097, "weighted_relation_loss": 0.002012642903719097 }, { "action_query_batch_std": 22.375008964538573, "action_query_norm": 952.5180725097656, "action_relation_loss": 0.002043431636411697, "auxiliary_loss_weight": 1.0, "epoch": 20.084190832553787, "flow_matching_loss": 0.019950352050364016, "grad_norm": 0.09275038540363312, "invalid_tail_samples": 25.1, "learning_rate": 2.0526081843617183e-05, "loss": 0.022, "positive_teacher_pairs": 26558.4, "relation_loss": 0.002043431636411697, "selected_pairs": 26558.4, "step": 21470, "student_distance_mean": 1292.4890625, "teacher_distance_mean": 0.8597387671470642, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.002043431636411697, "weighted_relation_loss": 0.002043431636411697 }, { "action_query_batch_std": 22.13297805786133, "action_query_norm": 943.0744812011719, "action_relation_loss": 0.002096910250838846, "auxiliary_loss_weight": 1.0, "epoch": 20.09354536950421, "flow_matching_loss": 0.01986378412693739, "grad_norm": 0.08835117518901825, "invalid_tail_samples": 23.2, "learning_rate": 2.0481578201486485e-05, "loss": 0.022, "positive_teacher_pairs": 26984.8, "relation_loss": 0.002096910250838846, "selected_pairs": 26984.8, "step": 21480, "student_distance_mean": 1272.9144653320313, "teacher_distance_mean": 0.8502972424030304, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.002096910250838846, "weighted_relation_loss": 0.002096910250838846 }, { "action_query_batch_std": 22.073208808898926, "action_query_norm": 941.750732421875, "action_relation_loss": 0.0019514322513714433, "auxiliary_loss_weight": 1.0, "epoch": 20.10289990645463, "flow_matching_loss": 0.017497047036886215, "grad_norm": 0.09925609827041626, "invalid_tail_samples": 25.9, "learning_rate": 2.0437110427021677e-05, "loss": 0.0194, "positive_teacher_pairs": 26360.7, "relation_loss": 0.0019514322513714433, "selected_pairs": 26360.7, "step": 21490, "student_distance_mean": 1266.2754760742187, "teacher_distance_mean": 0.8449884593486786, "valid_action_samples": 230.1, "weighted_auxiliary_loss": 0.0019514322513714433, "weighted_relation_loss": 0.0019514322513714433 }, { "action_query_batch_std": 22.18943386077881, "action_query_norm": 943.7580627441406, "action_relation_loss": 0.002111282246187329, "auxiliary_loss_weight": 1.0, "epoch": 20.112254443405053, "flow_matching_loss": 0.018174355290830134, "grad_norm": 0.08089398592710495, "invalid_tail_samples": 24.7, "learning_rate": 2.0392678574255282e-05, "loss": 0.0203, "positive_teacher_pairs": 26643.8, "relation_loss": 0.002111282246187329, "selected_pairs": 26643.8, "step": 21500, "student_distance_mean": 1277.6803833007812, "teacher_distance_mean": 0.8528348207473755, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.002111282246187329, "weighted_relation_loss": 0.002111282246187329 }, { "action_query_batch_std": 22.30557174682617, "action_query_norm": 950.0873596191407, "action_relation_loss": 0.0020177783910185097, "auxiliary_loss_weight": 1.0, "epoch": 20.12160898035547, "flow_matching_loss": 0.019496440328657626, "grad_norm": 0.08268909156322479, "invalid_tail_samples": 22.1, "learning_rate": 2.0348282697176217e-05, "loss": 0.0215, "positive_teacher_pairs": 27246.9, "relation_loss": 0.0020177783910185097, "selected_pairs": 27246.9, "step": 21510, "student_distance_mean": 1278.997412109375, "teacher_distance_mean": 0.8552718877792358, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0020177783910185097, "weighted_relation_loss": 0.0020177783910185097 }, { "action_query_batch_std": 22.14440460205078, "action_query_norm": 942.3492309570313, "action_relation_loss": 0.0021043197601102294, "auxiliary_loss_weight": 1.0, "epoch": 20.130963517305894, "flow_matching_loss": 0.019467940926551817, "grad_norm": 0.09855017811059952, "invalid_tail_samples": 22.3, "learning_rate": 2.030392284972964e-05, "loss": 0.0216, "positive_teacher_pairs": 27201.9, "relation_loss": 0.0021043197601102294, "selected_pairs": 27201.9, "step": 21520, "student_distance_mean": 1270.6098022460938, "teacher_distance_mean": 0.849888551235199, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0021043197601102294, "weighted_relation_loss": 0.0021043197601102294 }, { "action_query_batch_std": 22.107786178588867, "action_query_norm": 943.6138122558593, "action_relation_loss": 0.0020658474531956017, "auxiliary_loss_weight": 1.0, "epoch": 20.140318054256316, "flow_matching_loss": 0.0184158724732697, "grad_norm": 0.08113007247447968, "invalid_tail_samples": 23.4, "learning_rate": 2.0259599085816973e-05, "loss": 0.0205, "positive_teacher_pairs": 26943.3, "relation_loss": 0.0020658474531956017, "selected_pairs": 26943.3, "step": 21530, "student_distance_mean": 1273.494970703125, "teacher_distance_mean": 0.8501653790473938, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0020658474531956017, "weighted_relation_loss": 0.0020658474531956017 }, { "action_query_batch_std": 22.21673755645752, "action_query_norm": 944.0871704101562, "action_relation_loss": 0.0019991892855614423, "auxiliary_loss_weight": 1.0, "epoch": 20.149672591206734, "flow_matching_loss": 0.019284153915941717, "grad_norm": 0.08337847143411636, "invalid_tail_samples": 24.9, "learning_rate": 2.0215311459295755e-05, "loss": 0.0213, "positive_teacher_pairs": 26604.4, "relation_loss": 0.0019991892855614423, "selected_pairs": 26604.4, "step": 21540, "student_distance_mean": 1281.4326782226562, "teacher_distance_mean": 0.8552115499973297, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0019991892855614423, "weighted_relation_loss": 0.0019991892855614423 }, { "action_query_batch_std": 22.106894111633302, "action_query_norm": 939.8852783203125, "action_relation_loss": 0.002022516157012433, "auxiliary_loss_weight": 1.0, "epoch": 20.159027128157156, "flow_matching_loss": 0.020560820959508418, "grad_norm": 0.08237851411104202, "invalid_tail_samples": 25.7, "learning_rate": 2.0171060023979606e-05, "loss": 0.0226, "positive_teacher_pairs": 26413.9, "relation_loss": 0.002022516157012433, "selected_pairs": 26413.9, "step": 21550, "student_distance_mean": 1278.5516479492187, "teacher_distance_mean": 0.8554230749607086, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.002022516157012433, "weighted_relation_loss": 0.002022516157012433 }, { "action_query_batch_std": 22.090570068359376, "action_query_norm": 943.5902526855468, "action_relation_loss": 0.0019685218576341867, "auxiliary_loss_weight": 1.0, "epoch": 20.168381665107578, "flow_matching_loss": 0.019512231834232806, "grad_norm": 0.10152199119329453, "invalid_tail_samples": 25.1, "learning_rate": 2.012684483363823e-05, "loss": 0.0215, "positive_teacher_pairs": 26552.2, "relation_loss": 0.0019685218576341867, "selected_pairs": 26552.2, "step": 21560, "student_distance_mean": 1271.1682373046874, "teacher_distance_mean": 0.8524809360504151, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0019685218576341867, "weighted_relation_loss": 0.0019685218576341867 }, { "action_query_batch_std": 22.370088005065917, "action_query_norm": 952.728466796875, "action_relation_loss": 0.0020192212658002974, "auxiliary_loss_weight": 1.0, "epoch": 20.177736202057996, "flow_matching_loss": 0.017695668432861567, "grad_norm": 0.08732243627309799, "invalid_tail_samples": 24.4, "learning_rate": 2.0082665941997237e-05, "loss": 0.0197, "positive_teacher_pairs": 26717.2, "relation_loss": 0.0020192212658002974, "selected_pairs": 26717.2, "step": 21570, "student_distance_mean": 1280.8930297851562, "teacher_distance_mean": 0.8561842918395997, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0020192212658002974, "weighted_relation_loss": 0.0020192212658002974 }, { "action_query_batch_std": 22.30410270690918, "action_query_norm": 950.4925048828125, "action_relation_loss": 0.0020071820006705822, "auxiliary_loss_weight": 1.0, "epoch": 20.18709073900842, "flow_matching_loss": 0.018301854003220798, "grad_norm": 0.09569777548313141, "invalid_tail_samples": 23.1, "learning_rate": 2.0038523402738146e-05, "loss": 0.0203, "positive_teacher_pairs": 27012.1, "relation_loss": 0.0020071820006705822, "selected_pairs": 27012.1, "step": 21580, "student_distance_mean": 1280.3774291992188, "teacher_distance_mean": 0.8544401943683624, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0020071820006705822, "weighted_relation_loss": 0.0020071820006705822 }, { "action_query_batch_std": 22.288763999938965, "action_query_norm": 952.11083984375, "action_relation_loss": 0.002008497971110046, "auxiliary_loss_weight": 1.0, "epoch": 20.19644527595884, "flow_matching_loss": 0.018436440080404282, "grad_norm": 0.0894063413143158, "invalid_tail_samples": 24.0, "learning_rate": 1.99944172694983e-05, "loss": 0.0204, "positive_teacher_pairs": 26811.3, "relation_loss": 0.002008497971110046, "selected_pairs": 26811.3, "step": 21590, "student_distance_mean": 1283.572607421875, "teacher_distance_mean": 0.8543040752410889, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.002008497971110046, "weighted_relation_loss": 0.002008497971110046 }, { "action_query_batch_std": 22.256801414489747, "action_query_norm": 946.7035400390625, "action_relation_loss": 0.001984647347126156, "auxiliary_loss_weight": 1.0, "epoch": 20.205799812909262, "flow_matching_loss": 0.019717648159712553, "grad_norm": 0.08487717807292938, "invalid_tail_samples": 22.8, "learning_rate": 1.99503475958708e-05, "loss": 0.0217, "positive_teacher_pairs": 27094.4, "relation_loss": 0.001984647347126156, "selected_pairs": 27094.4, "step": 21600, "student_distance_mean": 1278.8186645507812, "teacher_distance_mean": 0.8546176552772522, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.001984647347126156, "weighted_relation_loss": 0.001984647347126156 }, { "action_query_batch_std": 22.393817901611328, "action_query_norm": 949.4072265625, "action_relation_loss": 0.0020007499610073865, "auxiliary_loss_weight": 1.0, "epoch": 20.21515434985968, "flow_matching_loss": 0.018394697178155183, "grad_norm": 0.08350597321987152, "invalid_tail_samples": 24.7, "learning_rate": 1.9906314435404484e-05, "loss": 0.0204, "positive_teacher_pairs": 26645.8, "relation_loss": 0.0020007499610073865, "selected_pairs": 26645.8, "step": 21610, "student_distance_mean": 1282.5830078125, "teacher_distance_mean": 0.8569809019565582, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0020007499610073865, "weighted_relation_loss": 0.0020007499610073865 }, { "action_query_batch_std": 22.058971214294434, "action_query_norm": 940.7090515136719, "action_relation_loss": 0.0019785337033681573, "auxiliary_loss_weight": 1.0, "epoch": 20.224508886810103, "flow_matching_loss": 0.018589366879314183, "grad_norm": 0.07724657654762268, "invalid_tail_samples": 22.2, "learning_rate": 1.986231784160378e-05, "loss": 0.0206, "positive_teacher_pairs": 27220.9, "relation_loss": 0.0019785337033681573, "selected_pairs": 27220.9, "step": 21620, "student_distance_mean": 1268.6732055664063, "teacher_distance_mean": 0.8488250315189362, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.0019785337033681573, "weighted_relation_loss": 0.0019785337033681573 }, { "action_query_batch_std": 22.325962829589844, "action_query_norm": 949.2072875976562, "action_relation_loss": 0.0019244618597440422, "auxiliary_loss_weight": 1.0, "epoch": 20.233863423760525, "flow_matching_loss": 0.019295578822493553, "grad_norm": 0.07451549917459488, "invalid_tail_samples": 24.5, "learning_rate": 1.9818357867928693e-05, "loss": 0.0212, "positive_teacher_pairs": 26689.7, "relation_loss": 0.0019244618597440422, "selected_pairs": 26689.7, "step": 21630, "student_distance_mean": 1281.27685546875, "teacher_distance_mean": 0.8578679919242859, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0019244618597440422, "weighted_relation_loss": 0.0019244618597440422 }, { "action_query_batch_std": 22.204563522338866, "action_query_norm": 946.0602416992188, "action_relation_loss": 0.0019839320331811903, "auxiliary_loss_weight": 1.0, "epoch": 20.243217960710943, "flow_matching_loss": 0.020702486764639615, "grad_norm": 0.09121248126029968, "invalid_tail_samples": 24.2, "learning_rate": 1.977443456779474e-05, "loss": 0.0227, "positive_teacher_pairs": 26761.5, "relation_loss": 0.0019839320331811903, "selected_pairs": 26761.5, "step": 21640, "student_distance_mean": 1275.8649169921875, "teacher_distance_mean": 0.8533181846141815, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0019839320331811903, "weighted_relation_loss": 0.0019839320331811903 }, { "action_query_batch_std": 22.29629554748535, "action_query_norm": 944.4791137695313, "action_relation_loss": 0.002063962817192078, "auxiliary_loss_weight": 1.0, "epoch": 20.252572497661365, "flow_matching_loss": 0.01969581050798297, "grad_norm": 0.09773951023817062, "invalid_tail_samples": 24.9, "learning_rate": 1.9730547994572858e-05, "loss": 0.0218, "positive_teacher_pairs": 26594.9, "relation_loss": 0.002063962817192078, "selected_pairs": 26594.9, "step": 21650, "student_distance_mean": 1276.6929321289062, "teacher_distance_mean": 0.855999332666397, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.002063962817192078, "weighted_relation_loss": 0.002063962817192078 }, { "action_query_batch_std": 22.16299648284912, "action_query_norm": 943.8648193359375, "action_relation_loss": 0.002040904469322413, "auxiliary_loss_weight": 1.0, "epoch": 20.261927034611787, "flow_matching_loss": 0.01905249198898673, "grad_norm": 0.08924154192209244, "invalid_tail_samples": 26.2, "learning_rate": 1.9686698201589393e-05, "loss": 0.0211, "positive_teacher_pairs": 26300.7, "relation_loss": 0.002040904469322413, "selected_pairs": 26300.7, "step": 21660, "student_distance_mean": 1271.1699951171875, "teacher_distance_mean": 0.8517269551753998, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.002040904469322413, "weighted_relation_loss": 0.002040904469322413 }, { "action_query_batch_std": 22.176495170593263, "action_query_norm": 943.6534118652344, "action_relation_loss": 0.002024960110429674, "auxiliary_loss_weight": 1.0, "epoch": 20.27128157156221, "flow_matching_loss": 0.02068406865000725, "grad_norm": 0.10499516874551773, "invalid_tail_samples": 22.7, "learning_rate": 1.9642885242125964e-05, "loss": 0.0227, "positive_teacher_pairs": 27103.9, "relation_loss": 0.002024960110429674, "selected_pairs": 27103.9, "step": 21670, "student_distance_mean": 1273.1028930664063, "teacher_distance_mean": 0.8498983800411224, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.002024960110429674, "weighted_relation_loss": 0.002024960110429674 }, { "action_query_batch_std": 22.121498107910156, "action_query_norm": 942.1112426757812, "action_relation_loss": 0.002019676275085658, "auxiliary_loss_weight": 1.0, "epoch": 20.280636108512628, "flow_matching_loss": 0.019019265286624433, "grad_norm": 0.07808542996644974, "invalid_tail_samples": 26.6, "learning_rate": 1.9599109169419466e-05, "loss": 0.021, "positive_teacher_pairs": 26213.2, "relation_loss": 0.002019676275085658, "selected_pairs": 26213.2, "step": 21680, "student_distance_mean": 1273.9186767578126, "teacher_distance_mean": 0.8503220736980438, "valid_action_samples": 229.4, "weighted_auxiliary_loss": 0.002019676275085658, "weighted_relation_loss": 0.002019676275085658 }, { "action_query_batch_std": 22.57171630859375, "action_query_norm": 955.7450439453125, "action_relation_loss": 0.002038531971629709, "auxiliary_loss_weight": 1.0, "epoch": 20.28999064546305, "flow_matching_loss": 0.0185938686132431, "grad_norm": 0.0912238359451294, "invalid_tail_samples": 26.0, "learning_rate": 1.9555370036661948e-05, "loss": 0.0206, "positive_teacher_pairs": 26351.1, "relation_loss": 0.002038531971629709, "selected_pairs": 26351.1, "step": 21690, "student_distance_mean": 1299.1066528320312, "teacher_distance_mean": 0.8657501876354218, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.002038531971629709, "weighted_relation_loss": 0.002038531971629709 }, { "action_query_batch_std": 22.50217456817627, "action_query_norm": 958.0766174316407, "action_relation_loss": 0.0019388267653994262, "auxiliary_loss_weight": 1.0, "epoch": 20.29934518241347, "flow_matching_loss": 0.018343265913426877, "grad_norm": 0.1255768984556198, "invalid_tail_samples": 20.0, "learning_rate": 1.9511667897000574e-05, "loss": 0.0203, "positive_teacher_pairs": 27743.2, "relation_loss": 0.0019388267653994262, "selected_pairs": 27743.2, "step": 21700, "student_distance_mean": 1289.8281127929688, "teacher_distance_mean": 0.8618841886520385, "valid_action_samples": 236.0, "weighted_auxiliary_loss": 0.0019388267653994262, "weighted_relation_loss": 0.0019388267653994262 }, { "action_query_batch_std": 22.202587890625, "action_query_norm": 945.7427734375, "action_relation_loss": 0.0020882894983515143, "auxiliary_loss_weight": 1.0, "epoch": 20.30869971936389, "flow_matching_loss": 0.01936996281147003, "grad_norm": 0.11356290429830551, "invalid_tail_samples": 23.5, "learning_rate": 1.946800280353755e-05, "loss": 0.0215, "positive_teacher_pairs": 26919.3, "relation_loss": 0.0020882894983515143, "selected_pairs": 26919.3, "step": 21710, "student_distance_mean": 1274.8866333007813, "teacher_distance_mean": 0.8516731142997742, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0020882894983515143, "weighted_relation_loss": 0.0020882894983515143 }, { "action_query_batch_std": 22.121955490112306, "action_query_norm": 941.8001281738282, "action_relation_loss": 0.00199866509065032, "auxiliary_loss_weight": 1.0, "epoch": 20.318054256314312, "flow_matching_loss": 0.017611832544207572, "grad_norm": 0.09139951318502426, "invalid_tail_samples": 25.0, "learning_rate": 1.9424374809330114e-05, "loss": 0.0196, "positive_teacher_pairs": 26574.7, "relation_loss": 0.00199866509065032, "selected_pairs": 26574.7, "step": 21720, "student_distance_mean": 1265.9221435546874, "teacher_distance_mean": 0.8465249598026275, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.00199866509065032, "weighted_relation_loss": 0.00199866509065032 }, { "action_query_batch_std": 22.4973051071167, "action_query_norm": 956.0172485351562, "action_relation_loss": 0.0020096784690395, "auxiliary_loss_weight": 1.0, "epoch": 20.327408793264734, "flow_matching_loss": 0.01960328808054328, "grad_norm": 0.09821899980306625, "invalid_tail_samples": 23.9, "learning_rate": 1.9380783967390382e-05, "loss": 0.0216, "positive_teacher_pairs": 26828.6, "relation_loss": 0.0020096784690395, "selected_pairs": 26828.6, "step": 21730, "student_distance_mean": 1293.8352172851562, "teacher_distance_mean": 0.8682154417037964, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0020096784690395, "weighted_relation_loss": 0.0020096784690395 }, { "action_query_batch_std": 22.411667251586913, "action_query_norm": 951.8436767578125, "action_relation_loss": 0.0020029204548336565, "auxiliary_loss_weight": 1.0, "epoch": 20.336763330215156, "flow_matching_loss": 0.01822349913418293, "grad_norm": 0.09049632400274277, "invalid_tail_samples": 23.2, "learning_rate": 1.933723033068533e-05, "loss": 0.0202, "positive_teacher_pairs": 26989.8, "relation_loss": 0.0020029204548336565, "selected_pairs": 26989.8, "step": 21740, "student_distance_mean": 1285.4441040039062, "teacher_distance_mean": 0.8581591308116913, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0020029204548336565, "weighted_relation_loss": 0.0020029204548336565 }, { "action_query_batch_std": 22.300507926940917, "action_query_norm": 945.73115234375, "action_relation_loss": 0.0020971683785319327, "auxiliary_loss_weight": 1.0, "epoch": 20.346117867165574, "flow_matching_loss": 0.019080874603241683, "grad_norm": 0.1262696087360382, "invalid_tail_samples": 25.4, "learning_rate": 1.929371395213674e-05, "loss": 0.0212, "positive_teacher_pairs": 26476.8, "relation_loss": 0.0020971683785319327, "selected_pairs": 26476.8, "step": 21750, "student_distance_mean": 1280.92265625, "teacher_distance_mean": 0.8539641201496124, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.0020971683785319327, "weighted_relation_loss": 0.0020971683785319327 }, { "action_query_batch_std": 22.12002811431885, "action_query_norm": 945.7798950195313, "action_relation_loss": 0.0019955500843934714, "auxiliary_loss_weight": 1.0, "epoch": 20.355472404115996, "flow_matching_loss": 0.017887652572244405, "grad_norm": 0.09671838581562042, "invalid_tail_samples": 23.6, "learning_rate": 1.9250234884621092e-05, "loss": 0.0199, "positive_teacher_pairs": 26893.6, "relation_loss": 0.0019955500843934714, "selected_pairs": 26893.6, "step": 21760, "student_distance_mean": 1275.0406616210937, "teacher_distance_mean": 0.8489976823329926, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0019955500843934714, "weighted_relation_loss": 0.0019955500843934714 }, { "action_query_batch_std": 22.373046493530275, "action_query_norm": 950.9794128417968, "action_relation_loss": 0.0020733615849167107, "auxiliary_loss_weight": 1.0, "epoch": 20.36482694106642, "flow_matching_loss": 0.017503493186086416, "grad_norm": 0.08896316587924957, "invalid_tail_samples": 24.1, "learning_rate": 1.920679318096959e-05, "loss": 0.0196, "positive_teacher_pairs": 26781.5, "relation_loss": 0.0020733615849167107, "selected_pairs": 26781.5, "step": 21770, "student_distance_mean": 1290.567333984375, "teacher_distance_mean": 0.8607537090778351, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0020733615849167107, "weighted_relation_loss": 0.0020733615849167107 }, { "action_query_batch_std": 22.01260108947754, "action_query_norm": 943.7194702148438, "action_relation_loss": 0.0020454385317862033, "auxiliary_loss_weight": 1.0, "epoch": 20.374181478016837, "flow_matching_loss": 0.019270361959934236, "grad_norm": 0.08639887720346451, "invalid_tail_samples": 24.3, "learning_rate": 1.9163388893967982e-05, "loss": 0.0213, "positive_teacher_pairs": 26751.3, "relation_loss": 0.0020454385317862033, "selected_pairs": 26751.3, "step": 21780, "student_distance_mean": 1269.1415771484376, "teacher_distance_mean": 0.8490921020507812, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0020454385317862033, "weighted_relation_loss": 0.0020454385317862033 }, { "action_query_batch_std": 22.54957046508789, "action_query_norm": 954.2089904785156, "action_relation_loss": 0.0019851383985951543, "auxiliary_loss_weight": 1.0, "epoch": 20.38353601496726, "flow_matching_loss": 0.019181977957487106, "grad_norm": 0.09349925071001053, "invalid_tail_samples": 25.0, "learning_rate": 1.9120022076356575e-05, "loss": 0.0212, "positive_teacher_pairs": 26578.3, "relation_loss": 0.0019851383985951543, "selected_pairs": 26578.3, "step": 21790, "student_distance_mean": 1292.7480590820312, "teacher_distance_mean": 0.8667750298976898, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0019851383985951543, "weighted_relation_loss": 0.0019851383985951543 }, { "action_query_batch_std": 22.2074914932251, "action_query_norm": 945.1986633300781, "action_relation_loss": 0.0019977005547843875, "auxiliary_loss_weight": 1.0, "epoch": 20.39289055191768, "flow_matching_loss": 0.019376896042376756, "grad_norm": 0.08881894499063492, "invalid_tail_samples": 23.7, "learning_rate": 1.9076692780830114e-05, "loss": 0.0214, "positive_teacher_pairs": 26872.9, "relation_loss": 0.0019977005547843875, "selected_pairs": 26872.9, "step": 21800, "student_distance_mean": 1272.9183227539063, "teacher_distance_mean": 0.8549434959888458, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0019977005547843875, "weighted_relation_loss": 0.0019977005547843875 }, { "action_query_batch_std": 22.552952766418457, "action_query_norm": 957.86142578125, "action_relation_loss": 0.0019586004666052757, "auxiliary_loss_weight": 1.0, "epoch": 20.4022450888681, "flow_matching_loss": 0.018271316029131412, "grad_norm": 0.08313920348882675, "invalid_tail_samples": 22.7, "learning_rate": 1.903340106003782e-05, "loss": 0.0202, "positive_teacher_pairs": 27103.6, "relation_loss": 0.0019586004666052757, "selected_pairs": 27103.6, "step": 21810, "student_distance_mean": 1292.3931274414062, "teacher_distance_mean": 0.8646336793899536, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0019586004666052757, "weighted_relation_loss": 0.0019586004666052757 }, { "action_query_batch_std": 22.056601142883302, "action_query_norm": 940.4127624511718, "action_relation_loss": 0.0020641920622438193, "auxiliary_loss_weight": 1.0, "epoch": 20.41159962581852, "flow_matching_loss": 0.01862187562510371, "grad_norm": 0.08459270000457764, "invalid_tail_samples": 25.3, "learning_rate": 1.8990146966583183e-05, "loss": 0.0207, "positive_teacher_pairs": 26508.3, "relation_loss": 0.0020641920622438193, "selected_pairs": 26508.3, "step": 21820, "student_distance_mean": 1272.41181640625, "teacher_distance_mean": 0.8525031805038452, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0020641920622438193, "weighted_relation_loss": 0.0020641920622438193 }, { "action_query_batch_std": 22.081666564941408, "action_query_norm": 939.6692687988282, "action_relation_loss": 0.0019945543841458856, "auxiliary_loss_weight": 1.0, "epoch": 20.420954162768943, "flow_matching_loss": 0.019867461547255515, "grad_norm": 0.10933467000722885, "invalid_tail_samples": 23.9, "learning_rate": 1.8946930553024035e-05, "loss": 0.0219, "positive_teacher_pairs": 26831.3, "relation_loss": 0.0019945543841458856, "selected_pairs": 26831.3, "step": 21830, "student_distance_mean": 1265.7591430664063, "teacher_distance_mean": 0.8478293538093566, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0019945543841458856, "weighted_relation_loss": 0.0019945543841458856 }, { "action_query_batch_std": 22.151384353637695, "action_query_norm": 942.6279113769531, "action_relation_loss": 0.002053091174457222, "auxiliary_loss_weight": 1.0, "epoch": 20.430308699719365, "flow_matching_loss": 0.01964434813708067, "grad_norm": 0.09126132726669312, "invalid_tail_samples": 22.8, "learning_rate": 1.8903751871872378e-05, "loss": 0.0217, "positive_teacher_pairs": 27083.6, "relation_loss": 0.002053091174457222, "selected_pairs": 27083.6, "step": 21840, "student_distance_mean": 1273.6771362304687, "teacher_distance_mean": 0.8534398913383484, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.002053091174457222, "weighted_relation_loss": 0.002053091174457222 }, { "action_query_batch_std": 22.058621978759767, "action_query_norm": 940.7381225585938, "action_relation_loss": 0.0019820301793515684, "auxiliary_loss_weight": 1.0, "epoch": 20.439663236669784, "flow_matching_loss": 0.018885707855224608, "grad_norm": 0.07325825095176697, "invalid_tail_samples": 22.3, "learning_rate": 1.8860610975594382e-05, "loss": 0.0209, "positive_teacher_pairs": 27196.7, "relation_loss": 0.0019820301793515684, "selected_pairs": 27196.7, "step": 21850, "student_distance_mean": 1269.207958984375, "teacher_distance_mean": 0.8529504060745239, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0019820301793515684, "weighted_relation_loss": 0.0019820301793515684 }, { "action_query_batch_std": 22.21773204803467, "action_query_norm": 946.1246643066406, "action_relation_loss": 0.002015245531219989, "auxiliary_loss_weight": 1.0, "epoch": 20.449017773620206, "flow_matching_loss": 0.019043934624642135, "grad_norm": 0.10201743245124817, "invalid_tail_samples": 23.6, "learning_rate": 1.8817507916610307e-05, "loss": 0.0211, "positive_teacher_pairs": 26897.6, "relation_loss": 0.002015245531219989, "selected_pairs": 26897.6, "step": 21860, "student_distance_mean": 1276.1952270507813, "teacher_distance_mean": 0.855341249704361, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.002015245531219989, "weighted_relation_loss": 0.002015245531219989 }, { "action_query_batch_std": 22.05737934112549, "action_query_norm": 938.6169738769531, "action_relation_loss": 0.002029749669600278, "auxiliary_loss_weight": 1.0, "epoch": 20.458372310570628, "flow_matching_loss": 0.020235623791813852, "grad_norm": 0.12154240161180496, "invalid_tail_samples": 23.6, "learning_rate": 1.8774442747294407e-05, "loss": 0.0223, "positive_teacher_pairs": 26890.6, "relation_loss": 0.002029749669600278, "selected_pairs": 26890.6, "step": 21870, "student_distance_mean": 1263.6795532226563, "teacher_distance_mean": 0.8434747755527496, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.002029749669600278, "weighted_relation_loss": 0.002029749669600278 }, { "action_query_batch_std": 22.22020568847656, "action_query_norm": 946.1273315429687, "action_relation_loss": 0.0019244563998654484, "auxiliary_loss_weight": 1.0, "epoch": 20.467726847521046, "flow_matching_loss": 0.020090863294899463, "grad_norm": 0.09099425375461578, "invalid_tail_samples": 22.9, "learning_rate": 1.8731415519974965e-05, "loss": 0.022, "positive_teacher_pairs": 27057.9, "relation_loss": 0.0019244563998654484, "selected_pairs": 27057.9, "step": 21880, "student_distance_mean": 1276.3135864257813, "teacher_distance_mean": 0.8541561841964722, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0019244563998654484, "weighted_relation_loss": 0.0019244563998654484 }, { "action_query_batch_std": 22.20000228881836, "action_query_norm": 944.1781555175781, "action_relation_loss": 0.0019858989981003106, "auxiliary_loss_weight": 1.0, "epoch": 20.477081384471468, "flow_matching_loss": 0.018815642781555654, "grad_norm": 0.09694872051477432, "invalid_tail_samples": 24.0, "learning_rate": 1.86884262869341e-05, "loss": 0.0208, "positive_teacher_pairs": 26800.1, "relation_loss": 0.0019858989981003106, "selected_pairs": 26800.1, "step": 21890, "student_distance_mean": 1269.6415771484376, "teacher_distance_mean": 0.8481038689613343, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0019858989981003106, "weighted_relation_loss": 0.0019858989981003106 }, { "action_query_batch_std": 22.540007209777833, "action_query_norm": 956.000732421875, "action_relation_loss": 0.0019631057512015104, "auxiliary_loss_weight": 1.0, "epoch": 20.48643592142189, "flow_matching_loss": 0.019460334349423646, "grad_norm": 0.10685083270072937, "invalid_tail_samples": 21.6, "learning_rate": 1.8645475100407788e-05, "loss": 0.0214, "positive_teacher_pairs": 27361.3, "relation_loss": 0.0019631057512015104, "selected_pairs": 27361.3, "step": 21900, "student_distance_mean": 1293.1815063476563, "teacher_distance_mean": 0.8653329849243164, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.0019631057512015104, "weighted_relation_loss": 0.0019631057512015104 }, { "action_query_batch_std": 22.55755443572998, "action_query_norm": 957.5947143554688, "action_relation_loss": 0.0019629228045232594, "auxiliary_loss_weight": 1.0, "epoch": 20.495790458372312, "flow_matching_loss": 0.01820445852354169, "grad_norm": 0.08927012234926224, "invalid_tail_samples": 25.9, "learning_rate": 1.8602562012585768e-05, "loss": 0.0202, "positive_teacher_pairs": 26368.4, "relation_loss": 0.0019629228045232594, "selected_pairs": 26368.4, "step": 21910, "student_distance_mean": 1300.7650512695313, "teacher_distance_mean": 0.8695890307426453, "valid_action_samples": 230.1, "weighted_auxiliary_loss": 0.0019629228045232594, "weighted_relation_loss": 0.0019629228045232594 }, { "action_query_batch_std": 22.048509407043458, "action_query_norm": 939.9222534179687, "action_relation_loss": 0.001967531268019229, "auxiliary_loss_weight": 1.0, "epoch": 20.50514499532273, "flow_matching_loss": 0.019638556893914937, "grad_norm": 0.10076922178268433, "invalid_tail_samples": 22.9, "learning_rate": 1.8559687075611466e-05, "loss": 0.0216, "positive_teacher_pairs": 27059.1, "relation_loss": 0.001967531268019229, "selected_pairs": 27059.1, "step": 21920, "student_distance_mean": 1264.851416015625, "teacher_distance_mean": 0.843986839056015, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.001967531268019229, "weighted_relation_loss": 0.001967531268019229 }, { "action_query_batch_std": 22.192836952209472, "action_query_norm": 946.5304626464844, "action_relation_loss": 0.0020508354180492462, "auxiliary_loss_weight": 1.0, "epoch": 20.514499532273152, "flow_matching_loss": 0.020170059986412525, "grad_norm": 0.09361784160137177, "invalid_tail_samples": 26.2, "learning_rate": 1.8516850341582017e-05, "loss": 0.0222, "positive_teacher_pairs": 26295.7, "relation_loss": 0.0020508354180492462, "selected_pairs": 26295.7, "step": 21930, "student_distance_mean": 1281.09189453125, "teacher_distance_mean": 0.8569990634918213, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.0020508354180492462, "weighted_relation_loss": 0.0020508354180492462 }, { "action_query_batch_std": 22.429195213317872, "action_query_norm": 952.2073913574219, "action_relation_loss": 0.0018929359037429094, "auxiliary_loss_weight": 1.0, "epoch": 20.523854069223574, "flow_matching_loss": 0.01769104544073343, "grad_norm": 0.09025285392999649, "invalid_tail_samples": 23.0, "learning_rate": 1.847405186254807e-05, "loss": 0.0196, "positive_teacher_pairs": 27030.2, "relation_loss": 0.0018929359037429094, "selected_pairs": 27030.2, "step": 21940, "student_distance_mean": 1290.3254638671874, "teacher_distance_mean": 0.8639645993709564, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0018929359037429094, "weighted_relation_loss": 0.0018929359037429094 }, { "action_query_batch_std": 22.439830780029297, "action_query_norm": 953.4247802734375, "action_relation_loss": 0.0019718347932212053, "auxiliary_loss_weight": 1.0, "epoch": 20.533208606173993, "flow_matching_loss": 0.018326465599238874, "grad_norm": 0.08432745188474655, "invalid_tail_samples": 20.8, "learning_rate": 1.843129169051379e-05, "loss": 0.0203, "positive_teacher_pairs": 27551.2, "relation_loss": 0.0019718347932212053, "selected_pairs": 27551.2, "step": 21950, "student_distance_mean": 1283.003369140625, "teacher_distance_mean": 0.8588447511196137, "valid_action_samples": 235.2, "weighted_auxiliary_loss": 0.0019718347932212053, "weighted_relation_loss": 0.0019718347932212053 }, { "action_query_batch_std": 22.35652885437012, "action_query_norm": 948.6025573730469, "action_relation_loss": 0.0019630053429864347, "auxiliary_loss_weight": 1.0, "epoch": 20.542563143124415, "flow_matching_loss": 0.018000306747853755, "grad_norm": 0.09065902978181839, "invalid_tail_samples": 22.7, "learning_rate": 1.8388569877436863e-05, "loss": 0.02, "positive_teacher_pairs": 27107.6, "relation_loss": 0.0019630053429864347, "selected_pairs": 27107.6, "step": 21960, "student_distance_mean": 1282.7758666992188, "teacher_distance_mean": 0.8580171883106231, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0019630053429864347, "weighted_relation_loss": 0.0019630053429864347 }, { "action_query_batch_std": 22.313251495361328, "action_query_norm": 946.6256896972657, "action_relation_loss": 0.0019325408386066556, "auxiliary_loss_weight": 1.0, "epoch": 20.551917680074837, "flow_matching_loss": 0.018463293183594943, "grad_norm": 0.08235964924097061, "invalid_tail_samples": 24.3, "learning_rate": 1.834588647522828e-05, "loss": 0.0204, "positive_teacher_pairs": 26734.5, "relation_loss": 0.0019325408386066556, "selected_pairs": 26734.5, "step": 21970, "student_distance_mean": 1283.0802368164063, "teacher_distance_mean": 0.8609029829502106, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0019325408386066556, "weighted_relation_loss": 0.0019325408386066556 }, { "action_query_batch_std": 22.067509841918945, "action_query_norm": 938.8344787597656, "action_relation_loss": 0.0021008309442549942, "auxiliary_loss_weight": 1.0, "epoch": 20.56127221702526, "flow_matching_loss": 0.017947463598102332, "grad_norm": 0.08461683243513107, "invalid_tail_samples": 25.1, "learning_rate": 1.8303241535752435e-05, "loss": 0.02, "positive_teacher_pairs": 26545.4, "relation_loss": 0.0021008309442549942, "selected_pairs": 26545.4, "step": 21980, "student_distance_mean": 1265.5921020507812, "teacher_distance_mean": 0.8488863050937653, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0021008309442549942, "weighted_relation_loss": 0.0021008309442549942 }, { "action_query_batch_std": 22.302746200561522, "action_query_norm": 948.1547058105468, "action_relation_loss": 0.0020111834397539496, "auxiliary_loss_weight": 1.0, "epoch": 20.570626753975677, "flow_matching_loss": 0.018425618298351765, "grad_norm": 0.08782678842544556, "invalid_tail_samples": 24.0, "learning_rate": 1.8260635110826934e-05, "loss": 0.0204, "positive_teacher_pairs": 26805.9, "relation_loss": 0.0020111834397539496, "selected_pairs": 26805.9, "step": 21990, "student_distance_mean": 1285.4762939453126, "teacher_distance_mean": 0.8634514749050141, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0020111834397539496, "weighted_relation_loss": 0.0020111834397539496 }, { "action_query_batch_std": 22.230410194396974, "action_query_norm": 945.2651428222656, "action_relation_loss": 0.001977643312420696, "auxiliary_loss_weight": 1.0, "epoch": 20.5799812909261, "flow_matching_loss": 0.019005900155752896, "grad_norm": 0.11616086214780807, "invalid_tail_samples": 22.9, "learning_rate": 1.8218067252222597e-05, "loss": 0.021, "positive_teacher_pairs": 27059.3, "relation_loss": 0.001977643312420696, "selected_pairs": 27059.3, "step": 22000, "student_distance_mean": 1283.5981201171876, "teacher_distance_mean": 0.8597420692443848, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.001977643312420696, "weighted_relation_loss": 0.001977643312420696 }, { "action_query_batch_std": 22.10950813293457, "action_query_norm": 940.0086975097656, "action_relation_loss": 0.0019601535168476403, "auxiliary_loss_weight": 1.0, "epoch": 20.58933582787652, "flow_matching_loss": 0.018457743525505065, "grad_norm": 0.09703834354877472, "invalid_tail_samples": 23.8, "learning_rate": 1.817553801166339e-05, "loss": 0.0204, "positive_teacher_pairs": 26858.9, "relation_loss": 0.0019601535168476403, "selected_pairs": 26858.9, "step": 22010, "student_distance_mean": 1273.54208984375, "teacher_distance_mean": 0.8536525905132294, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0019601535168476403, "weighted_relation_loss": 0.0019601535168476403 }, { "action_query_batch_std": 22.07763042449951, "action_query_norm": 938.2600708007812, "action_relation_loss": 0.002014386502560228, "auxiliary_loss_weight": 1.0, "epoch": 20.59869036482694, "flow_matching_loss": 0.018970430269837378, "grad_norm": 0.13258787989616394, "invalid_tail_samples": 23.6, "learning_rate": 1.8133047440826333e-05, "loss": 0.021, "positive_teacher_pairs": 26898.8, "relation_loss": 0.002014386502560228, "selected_pairs": 26898.8, "step": 22020, "student_distance_mean": 1265.1757202148438, "teacher_distance_mean": 0.8521599471569061, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.002014386502560228, "weighted_relation_loss": 0.002014386502560228 }, { "action_query_batch_std": 22.085430335998534, "action_query_norm": 942.1844299316406, "action_relation_loss": 0.002056519710458815, "auxiliary_loss_weight": 1.0, "epoch": 20.60804490177736, "flow_matching_loss": 0.01802540011703968, "grad_norm": 0.10097366571426392, "invalid_tail_samples": 22.1, "learning_rate": 1.809059559134151e-05, "loss": 0.0201, "positive_teacher_pairs": 27251.2, "relation_loss": 0.002056519710458815, "selected_pairs": 27251.2, "step": 22030, "student_distance_mean": 1270.6040893554687, "teacher_distance_mean": 0.8534752070903778, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.002056519710458815, "weighted_relation_loss": 0.002056519710458815 }, { "action_query_batch_std": 22.114322090148924, "action_query_norm": 941.9053588867188, "action_relation_loss": 0.0019095325376838445, "auxiliary_loss_weight": 1.0, "epoch": 20.617399438727784, "flow_matching_loss": 0.020340575464069845, "grad_norm": 0.09204313904047012, "invalid_tail_samples": 24.6, "learning_rate": 1.80481825147919e-05, "loss": 0.0223, "positive_teacher_pairs": 26663.5, "relation_loss": 0.0019095325376838445, "selected_pairs": 26663.5, "step": 22040, "student_distance_mean": 1269.5223510742187, "teacher_distance_mean": 0.8512354791164398, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0019095325376838445, "weighted_relation_loss": 0.0019095325376838445 }, { "action_query_batch_std": 22.317783737182616, "action_query_norm": 948.4087646484375, "action_relation_loss": 0.001969315984752029, "auxiliary_loss_weight": 1.0, "epoch": 20.626753975678206, "flow_matching_loss": 0.019530060049146414, "grad_norm": 0.09771167486906052, "invalid_tail_samples": 25.6, "learning_rate": 1.8005808262713396e-05, "loss": 0.0215, "positive_teacher_pairs": 26439.1, "relation_loss": 0.001969315984752029, "selected_pairs": 26439.1, "step": 22050, "student_distance_mean": 1279.6161865234376, "teacher_distance_mean": 0.8552681088447571, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.001969315984752029, "weighted_relation_loss": 0.001969315984752029 }, { "action_query_batch_std": 22.07935199737549, "action_query_norm": 943.729931640625, "action_relation_loss": 0.0021711983601562677, "auxiliary_loss_weight": 1.0, "epoch": 20.636108512628624, "flow_matching_loss": 0.018338555842638014, "grad_norm": 0.09485941380262375, "invalid_tail_samples": 24.3, "learning_rate": 1.7963472886594714e-05, "loss": 0.0205, "positive_teacher_pairs": 26734.3, "relation_loss": 0.0021711983601562677, "selected_pairs": 26734.3, "step": 22060, "student_distance_mean": 1272.24677734375, "teacher_distance_mean": 0.8498256921768188, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0021711983601562677, "weighted_relation_loss": 0.0021711983601562677 }, { "action_query_batch_std": 21.956402206420897, "action_query_norm": 938.909423828125, "action_relation_loss": 0.002079278219025582, "auxiliary_loss_weight": 1.0, "epoch": 20.645463049579046, "flow_matching_loss": 0.018461085762828587, "grad_norm": 0.08604435622692108, "invalid_tail_samples": 22.5, "learning_rate": 1.7921176437877302e-05, "loss": 0.0205, "positive_teacher_pairs": 27153.4, "relation_loss": 0.002079278219025582, "selected_pairs": 27153.4, "step": 22070, "student_distance_mean": 1262.2415893554687, "teacher_distance_mean": 0.8484510779380798, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.002079278219025582, "weighted_relation_loss": 0.002079278219025582 }, { "action_query_batch_std": 22.101497650146484, "action_query_norm": 939.7334411621093, "action_relation_loss": 0.0020384326810017226, "auxiliary_loss_weight": 1.0, "epoch": 20.654817586529468, "flow_matching_loss": 0.019783557020127775, "grad_norm": 0.09781737625598907, "invalid_tail_samples": 23.1, "learning_rate": 1.7878918967955366e-05, "loss": 0.0218, "positive_teacher_pairs": 27012.4, "relation_loss": 0.0020384326810017226, "selected_pairs": 27012.4, "step": 22080, "student_distance_mean": 1266.3029296875, "teacher_distance_mean": 0.8507722377777099, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0020384326810017226, "weighted_relation_loss": 0.0020384326810017226 }, { "action_query_batch_std": 22.213552284240723, "action_query_norm": 944.133056640625, "action_relation_loss": 0.001994321052916348, "auxiliary_loss_weight": 1.0, "epoch": 20.664172123479887, "flow_matching_loss": 0.019115991424769163, "grad_norm": 0.07912846654653549, "invalid_tail_samples": 21.9, "learning_rate": 1.7836700528175693e-05, "loss": 0.0211, "positive_teacher_pairs": 27285.6, "relation_loss": 0.001994321052916348, "selected_pairs": 27285.6, "step": 22090, "student_distance_mean": 1273.374755859375, "teacher_distance_mean": 0.853682941198349, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.001994321052916348, "weighted_relation_loss": 0.001994321052916348 }, { "action_query_batch_std": 22.215533447265624, "action_query_norm": 944.7297058105469, "action_relation_loss": 0.0019733177963644267, "auxiliary_loss_weight": 1.0, "epoch": 20.67352666043031, "flow_matching_loss": 0.01890630889683962, "grad_norm": 0.09747890383005142, "invalid_tail_samples": 26.8, "learning_rate": 1.779452116983769e-05, "loss": 0.0209, "positive_teacher_pairs": 26159.4, "relation_loss": 0.0019733177963644267, "selected_pairs": 26159.4, "step": 22100, "student_distance_mean": 1278.9377197265626, "teacher_distance_mean": 0.8557725846767426, "valid_action_samples": 229.2, "weighted_auxiliary_loss": 0.0019733177963644267, "weighted_relation_loss": 0.0019733177963644267 }, { "action_query_batch_std": 22.219726371765137, "action_query_norm": 944.9345153808594, "action_relation_loss": 0.002070157346315682, "auxiliary_loss_weight": 1.0, "epoch": 20.68288119738073, "flow_matching_loss": 0.01889238180592656, "grad_norm": 0.10838049650192261, "invalid_tail_samples": 20.7, "learning_rate": 1.775238094419325e-05, "loss": 0.021, "positive_teacher_pairs": 27571.0, "relation_loss": 0.002070157346315682, "selected_pairs": 27571.0, "step": 22110, "student_distance_mean": 1274.0557739257813, "teacher_distance_mean": 0.8528156995773315, "valid_action_samples": 235.3, "weighted_auxiliary_loss": 0.002070157346315682, "weighted_relation_loss": 0.002070157346315682 }, { "action_query_batch_std": 22.30299072265625, "action_query_norm": 948.7343566894531, "action_relation_loss": 0.0020180405117571354, "auxiliary_loss_weight": 1.0, "epoch": 20.69223573433115, "flow_matching_loss": 0.018901081569492818, "grad_norm": 0.11174692213535309, "invalid_tail_samples": 23.4, "learning_rate": 1.7710279902446708e-05, "loss": 0.0209, "positive_teacher_pairs": 26951.5, "relation_loss": 0.0020180405117571354, "selected_pairs": 26951.5, "step": 22120, "student_distance_mean": 1276.4412963867187, "teacher_distance_mean": 0.8533107161521911, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0020180405117571354, "weighted_relation_loss": 0.0020180405117571354 }, { "action_query_batch_std": 22.050841331481934, "action_query_norm": 937.6658630371094, "action_relation_loss": 0.001997414161451161, "auxiliary_loss_weight": 1.0, "epoch": 20.70159027128157, "flow_matching_loss": 0.018679165933281183, "grad_norm": 0.09010645747184753, "invalid_tail_samples": 25.5, "learning_rate": 1.7668218095754795e-05, "loss": 0.0207, "positive_teacher_pairs": 26456.8, "relation_loss": 0.001997414161451161, "selected_pairs": 26456.8, "step": 22130, "student_distance_mean": 1266.6767333984376, "teacher_distance_mean": 0.8481730103492737, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.001997414161451161, "weighted_relation_loss": 0.001997414161451161 }, { "action_query_batch_std": 22.344008445739746, "action_query_norm": 946.2046020507812, "action_relation_loss": 0.0019727508071810005, "auxiliary_loss_weight": 1.0, "epoch": 20.710944808231993, "flow_matching_loss": 0.018179237190634013, "grad_norm": 0.08366207778453827, "invalid_tail_samples": 23.6, "learning_rate": 1.7626195575226594e-05, "loss": 0.0202, "positive_teacher_pairs": 26898.1, "relation_loss": 0.0019727508071810005, "selected_pairs": 26898.1, "step": 22140, "student_distance_mean": 1281.0581787109375, "teacher_distance_mean": 0.8585481703281402, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0019727508071810005, "weighted_relation_loss": 0.0019727508071810005 }, { "action_query_batch_std": 22.148232078552248, "action_query_norm": 940.1074523925781, "action_relation_loss": 0.0020631545688956977, "auxiliary_loss_weight": 1.0, "epoch": 20.720299345182415, "flow_matching_loss": 0.019602998346090316, "grad_norm": 0.08635769784450531, "invalid_tail_samples": 23.9, "learning_rate": 1.758421239192343e-05, "loss": 0.0217, "positive_teacher_pairs": 26824.9, "relation_loss": 0.0020631545688956977, "selected_pairs": 26824.9, "step": 22150, "student_distance_mean": 1269.3911865234375, "teacher_distance_mean": 0.8505948185920715, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0020631545688956977, "weighted_relation_loss": 0.0020631545688956977 }, { "action_query_batch_std": 22.297443389892578, "action_query_norm": 946.4688171386719, "action_relation_loss": 0.001984725205693394, "auxiliary_loss_weight": 1.0, "epoch": 20.729653882132833, "flow_matching_loss": 0.02011874094605446, "grad_norm": 0.0909326821565628, "invalid_tail_samples": 22.4, "learning_rate": 1.7542268596858814e-05, "loss": 0.0221, "positive_teacher_pairs": 27184.2, "relation_loss": 0.001984725205693394, "selected_pairs": 27184.2, "step": 22160, "student_distance_mean": 1281.0797119140625, "teacher_distance_mean": 0.8574661016464233, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.001984725205693394, "weighted_relation_loss": 0.001984725205693394 }, { "action_query_batch_std": 22.292680740356445, "action_query_norm": 948.6766296386719, "action_relation_loss": 0.0020021689357236027, "auxiliary_loss_weight": 1.0, "epoch": 20.739008419083255, "flow_matching_loss": 0.01946705672889948, "grad_norm": 0.07501013576984406, "invalid_tail_samples": 23.5, "learning_rate": 1.750036424099841e-05, "loss": 0.0215, "positive_teacher_pairs": 26924.0, "relation_loss": 0.0020021689357236027, "selected_pairs": 26924.0, "step": 22170, "student_distance_mean": 1281.3817260742187, "teacher_distance_mean": 0.85691978931427, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0020021689357236027, "weighted_relation_loss": 0.0020021689357236027 }, { "action_query_batch_std": 22.153629493713378, "action_query_norm": 941.7322387695312, "action_relation_loss": 0.001972990552894771, "auxiliary_loss_weight": 1.0, "epoch": 20.748362956033677, "flow_matching_loss": 0.018131955061107874, "grad_norm": 0.1105211079120636, "invalid_tail_samples": 25.7, "learning_rate": 1.7458499375259956e-05, "loss": 0.0201, "positive_teacher_pairs": 26410.8, "relation_loss": 0.001972990552894771, "selected_pairs": 26410.8, "step": 22180, "student_distance_mean": 1276.2954467773438, "teacher_distance_mean": 0.8581580936908721, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.001972990552894771, "weighted_relation_loss": 0.001972990552894771 }, { "action_query_batch_std": 22.385453987121583, "action_query_norm": 950.405126953125, "action_relation_loss": 0.001968074915930629, "auxiliary_loss_weight": 1.0, "epoch": 20.757717492984096, "flow_matching_loss": 0.01893516117706895, "grad_norm": 0.08162903785705566, "invalid_tail_samples": 23.9, "learning_rate": 1.7416674050513245e-05, "loss": 0.0209, "positive_teacher_pairs": 26833.5, "relation_loss": 0.001968074915930629, "selected_pairs": 26833.5, "step": 22190, "student_distance_mean": 1284.7708374023437, "teacher_distance_mean": 0.8637134492397308, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.001968074915930629, "weighted_relation_loss": 0.001968074915930629 }, { "action_query_batch_std": 21.92085418701172, "action_query_norm": 934.1018127441406, "action_relation_loss": 0.002000755281187594, "auxiliary_loss_weight": 1.0, "epoch": 20.767072029934518, "flow_matching_loss": 0.019910115003585815, "grad_norm": 0.07458135485649109, "invalid_tail_samples": 21.1, "learning_rate": 1.737488831757997e-05, "loss": 0.0219, "positive_teacher_pairs": 27476.9, "relation_loss": 0.002000755281187594, "selected_pairs": 27476.9, "step": 22200, "student_distance_mean": 1257.1172119140624, "teacher_distance_mean": 0.8424690186977386, "valid_action_samples": 234.9, "weighted_auxiliary_loss": 0.002000755281187594, "weighted_relation_loss": 0.002000755281187594 }, { "action_query_batch_std": 22.105106925964357, "action_query_norm": 940.153125, "action_relation_loss": 0.0019860081491060557, "auxiliary_loss_weight": 1.0, "epoch": 20.77642656688494, "flow_matching_loss": 0.019225710444152354, "grad_norm": 0.09756224602460861, "invalid_tail_samples": 22.8, "learning_rate": 1.733314222723373e-05, "loss": 0.0212, "positive_teacher_pairs": 27080.9, "relation_loss": 0.0019860081491060557, "selected_pairs": 27080.9, "step": 22210, "student_distance_mean": 1274.7479125976563, "teacher_distance_mean": 0.8545158565044403, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0019860081491060557, "weighted_relation_loss": 0.0019860081491060557 }, { "action_query_batch_std": 22.141444778442384, "action_query_norm": 943.3401123046875, "action_relation_loss": 0.0020429982454515994, "auxiliary_loss_weight": 1.0, "epoch": 20.78578110383536, "flow_matching_loss": 0.018649390246719123, "grad_norm": 0.11504821479320526, "invalid_tail_samples": 23.2, "learning_rate": 1.7291435830199954e-05, "loss": 0.0207, "positive_teacher_pairs": 26988.9, "relation_loss": 0.0020429982454515994, "selected_pairs": 26988.9, "step": 22220, "student_distance_mean": 1267.5132690429687, "teacher_distance_mean": 0.8488244891166687, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0020429982454515994, "weighted_relation_loss": 0.0020429982454515994 }, { "action_query_batch_std": 22.633176040649413, "action_query_norm": 959.4602416992187, "action_relation_loss": 0.0019646497210487725, "auxiliary_loss_weight": 1.0, "epoch": 20.79513564078578, "flow_matching_loss": 0.01994104851037264, "grad_norm": 0.0755845457315445, "invalid_tail_samples": 22.8, "learning_rate": 1.7249769177155878e-05, "loss": 0.0219, "positive_teacher_pairs": 27081.1, "relation_loss": 0.0019646497210487725, "selected_pairs": 27081.1, "step": 22230, "student_distance_mean": 1303.5983154296875, "teacher_distance_mean": 0.8738548815250397, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0019646497210487725, "weighted_relation_loss": 0.0019646497210487725 }, { "action_query_batch_std": 22.466776275634764, "action_query_norm": 956.0990905761719, "action_relation_loss": 0.0019698401563800873, "auxiliary_loss_weight": 1.0, "epoch": 20.804490177736202, "flow_matching_loss": 0.021010693907737733, "grad_norm": 0.08515478670597076, "invalid_tail_samples": 23.9, "learning_rate": 1.720814231873038e-05, "loss": 0.023, "positive_teacher_pairs": 26829.7, "relation_loss": 0.0019698401563800873, "selected_pairs": 26829.7, "step": 22240, "student_distance_mean": 1294.61318359375, "teacher_distance_mean": 0.8653818726539612, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0019698401563800873, "weighted_relation_loss": 0.0019698401563800873 }, { "action_query_batch_std": 22.333088874816895, "action_query_norm": 949.0620727539062, "action_relation_loss": 0.0020527189481072128, "auxiliary_loss_weight": 1.0, "epoch": 20.813844714686624, "flow_matching_loss": 0.019878464750945568, "grad_norm": 0.10182816535234451, "invalid_tail_samples": 21.8, "learning_rate": 1.716655530550405e-05, "loss": 0.0219, "positive_teacher_pairs": 27316.2, "relation_loss": 0.0020527189481072128, "selected_pairs": 27316.2, "step": 22250, "student_distance_mean": 1286.9423461914062, "teacher_distance_mean": 0.8586272478103638, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.0020527189481072128, "weighted_relation_loss": 0.0020527189481072128 }, { "action_query_batch_std": 22.41475887298584, "action_query_norm": 952.4745849609375, "action_relation_loss": 0.0020078041357919573, "auxiliary_loss_weight": 1.0, "epoch": 20.823199251637043, "flow_matching_loss": 0.019283332116901874, "grad_norm": 0.10502446442842484, "invalid_tail_samples": 21.7, "learning_rate": 1.7125008188009017e-05, "loss": 0.0213, "positive_teacher_pairs": 27339.7, "relation_loss": 0.0020078041357919573, "selected_pairs": 27339.7, "step": 22260, "student_distance_mean": 1286.4187133789062, "teacher_distance_mean": 0.8615343570709229, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.0020078041357919573, "weighted_relation_loss": 0.0020078041357919573 }, { "action_query_batch_std": 22.142078399658203, "action_query_norm": 942.9607604980469, "action_relation_loss": 0.0019847216783091424, "auxiliary_loss_weight": 1.0, "epoch": 20.832553788587465, "flow_matching_loss": 0.0182150655426085, "grad_norm": 0.09681861102581024, "invalid_tail_samples": 24.2, "learning_rate": 1.708350101672894e-05, "loss": 0.0202, "positive_teacher_pairs": 26755.1, "relation_loss": 0.0019847216783091424, "selected_pairs": 26755.1, "step": 22270, "student_distance_mean": 1275.6190551757813, "teacher_distance_mean": 0.8533702909946441, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0019847216783091424, "weighted_relation_loss": 0.0019847216783091424 }, { "action_query_batch_std": 22.26791477203369, "action_query_norm": 946.480859375, "action_relation_loss": 0.001874041638802737, "auxiliary_loss_weight": 1.0, "epoch": 20.841908325537887, "flow_matching_loss": 0.019515538960695265, "grad_norm": 0.0938214510679245, "invalid_tail_samples": 23.9, "learning_rate": 1.7042033842098957e-05, "loss": 0.0214, "positive_teacher_pairs": 26828.5, "relation_loss": 0.001874041638802737, "selected_pairs": 26828.5, "step": 22280, "student_distance_mean": 1278.7192993164062, "teacher_distance_mean": 0.8527722597122193, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.001874041638802737, "weighted_relation_loss": 0.001874041638802737 }, { "action_query_batch_std": 22.182025909423828, "action_query_norm": 945.5292358398438, "action_relation_loss": 0.0020355435088276865, "auxiliary_loss_weight": 1.0, "epoch": 20.85126286248831, "flow_matching_loss": 0.020451082661747933, "grad_norm": 0.0962975025177002, "invalid_tail_samples": 24.8, "learning_rate": 1.7000606714505567e-05, "loss": 0.0225, "positive_teacher_pairs": 26630.9, "relation_loss": 0.0020355435088276865, "selected_pairs": 26630.9, "step": 22290, "student_distance_mean": 1277.2310180664062, "teacher_distance_mean": 0.8525071322917939, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0020355435088276865, "weighted_relation_loss": 0.0020355435088276865 }, { "action_query_batch_std": 22.37157917022705, "action_query_norm": 950.3865051269531, "action_relation_loss": 0.001989210653118789, "auxiliary_loss_weight": 1.0, "epoch": 20.860617399438727, "flow_matching_loss": 0.019762005470693112, "grad_norm": 0.0978027805685997, "invalid_tail_samples": 23.1, "learning_rate": 1.695921968428668e-05, "loss": 0.0218, "positive_teacher_pairs": 27014.8, "relation_loss": 0.001989210653118789, "selected_pairs": 27014.8, "step": 22300, "student_distance_mean": 1286.2038940429688, "teacher_distance_mean": 0.858293479681015, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.001989210653118789, "weighted_relation_loss": 0.001989210653118789 }, { "action_query_batch_std": 22.40815086364746, "action_query_norm": 950.6721740722656, "action_relation_loss": 0.0020281594130210578, "auxiliary_loss_weight": 1.0, "epoch": 20.86997193638915, "flow_matching_loss": 0.017129632737487556, "grad_norm": 0.10683616995811462, "invalid_tail_samples": 25.7, "learning_rate": 1.6917872801731416e-05, "loss": 0.0192, "positive_teacher_pairs": 26419.6, "relation_loss": 0.0020281594130210578, "selected_pairs": 26419.6, "step": 22310, "student_distance_mean": 1284.8375244140625, "teacher_distance_mean": 0.8599628210067749, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.0020281594130210578, "weighted_relation_loss": 0.0020281594130210578 }, { "action_query_batch_std": 21.990639877319335, "action_query_norm": 935.9518981933594, "action_relation_loss": 0.0020061583258211614, "auxiliary_loss_weight": 1.0, "epoch": 20.87932647333957, "flow_matching_loss": 0.018861713539808988, "grad_norm": 0.07804092019796371, "invalid_tail_samples": 25.3, "learning_rate": 1.687656611708014e-05, "loss": 0.0209, "positive_teacher_pairs": 26506.9, "relation_loss": 0.0020061583258211614, "selected_pairs": 26506.9, "step": 22320, "student_distance_mean": 1264.4228515625, "teacher_distance_mean": 0.848354059457779, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0020061583258211614, "weighted_relation_loss": 0.0020061583258211614 }, { "action_query_batch_std": 22.185181427001954, "action_query_norm": 942.3591857910156, "action_relation_loss": 0.001960818667430431, "auxiliary_loss_weight": 1.0, "epoch": 20.88868101028999, "flow_matching_loss": 0.01898003863170743, "grad_norm": 0.09218402951955795, "invalid_tail_samples": 24.6, "learning_rate": 1.6835299680524368e-05, "loss": 0.0209, "positive_teacher_pairs": 26667.1, "relation_loss": 0.001960818667430431, "selected_pairs": 26667.1, "step": 22330, "student_distance_mean": 1275.8922729492188, "teacher_distance_mean": 0.8556691944599152, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.001960818667430431, "weighted_relation_loss": 0.001960818667430431 }, { "action_query_batch_std": 22.11744613647461, "action_query_norm": 943.1111755371094, "action_relation_loss": 0.0019830719102174044, "auxiliary_loss_weight": 1.0, "epoch": 20.89803554724041, "flow_matching_loss": 0.017395978327840567, "grad_norm": 0.09050488471984863, "invalid_tail_samples": 24.9, "learning_rate": 1.679407354220669e-05, "loss": 0.0194, "positive_teacher_pairs": 26601.8, "relation_loss": 0.0019830719102174044, "selected_pairs": 26601.8, "step": 22340, "student_distance_mean": 1271.0459838867187, "teacher_distance_mean": 0.8514031410217285, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0019830719102174044, "weighted_relation_loss": 0.0019830719102174044 }, { "action_query_batch_std": 22.35364933013916, "action_query_norm": 949.6376159667968, "action_relation_loss": 0.0019543621921911834, "auxiliary_loss_weight": 1.0, "epoch": 20.907390084190833, "flow_matching_loss": 0.01718797953799367, "grad_norm": 0.08824615925550461, "invalid_tail_samples": 25.2, "learning_rate": 1.6752887752220793e-05, "loss": 0.0191, "positive_teacher_pairs": 26535.4, "relation_loss": 0.0019543621921911834, "selected_pairs": 26535.4, "step": 22350, "student_distance_mean": 1285.6965942382812, "teacher_distance_mean": 0.8595798730850219, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0019543621921911834, "weighted_relation_loss": 0.0019543621921911834 }, { "action_query_batch_std": 22.125555419921874, "action_query_norm": 941.7202819824219, "action_relation_loss": 0.001982521323952824, "auxiliary_loss_weight": 1.0, "epoch": 20.916744621141255, "flow_matching_loss": 0.016665541101247072, "grad_norm": 0.07958618551492691, "invalid_tail_samples": 24.3, "learning_rate": 1.6711742360611277e-05, "loss": 0.0186, "positive_teacher_pairs": 26734.7, "relation_loss": 0.001982521323952824, "selected_pairs": 26734.7, "step": 22360, "student_distance_mean": 1271.1859619140625, "teacher_distance_mean": 0.8479538261890411, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.001982521323952824, "weighted_relation_loss": 0.001982521323952824 }, { "action_query_batch_std": 22.335022735595704, "action_query_norm": 947.5761047363281, "action_relation_loss": 0.0020184947759844364, "auxiliary_loss_weight": 1.0, "epoch": 20.926099158091674, "flow_matching_loss": 0.017725690454244613, "grad_norm": 0.07864335179328918, "invalid_tail_samples": 24.3, "learning_rate": 1.6670637417373652e-05, "loss": 0.0197, "positive_teacher_pairs": 26741.2, "relation_loss": 0.0020184947759844364, "selected_pairs": 26741.2, "step": 22370, "student_distance_mean": 1282.9344604492187, "teacher_distance_mean": 0.8550454199314117, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0020184947759844364, "weighted_relation_loss": 0.0020184947759844364 }, { "action_query_batch_std": 22.35134162902832, "action_query_norm": 948.7322082519531, "action_relation_loss": 0.002022425422910601, "auxiliary_loss_weight": 1.0, "epoch": 20.935453695042096, "flow_matching_loss": 0.01922214115038514, "grad_norm": 0.10210204869508743, "invalid_tail_samples": 20.3, "learning_rate": 1.6629572972454333e-05, "loss": 0.0212, "positive_teacher_pairs": 27665.1, "relation_loss": 0.002022425422910601, "selected_pairs": 27665.1, "step": 22380, "student_distance_mean": 1281.104248046875, "teacher_distance_mean": 0.8544592797756195, "valid_action_samples": 235.7, "weighted_auxiliary_loss": 0.002022425422910601, "weighted_relation_loss": 0.002022425422910601 }, { "action_query_batch_std": 22.008676719665527, "action_query_norm": 936.7025207519531, "action_relation_loss": 0.0019402782083489001, "auxiliary_loss_weight": 1.0, "epoch": 20.944808231992518, "flow_matching_loss": 0.01781441131606698, "grad_norm": 0.08783790469169617, "invalid_tail_samples": 25.5, "learning_rate": 1.6588549075750464e-05, "loss": 0.0198, "positive_teacher_pairs": 26462.8, "relation_loss": 0.0019402782083489001, "selected_pairs": 26462.8, "step": 22390, "student_distance_mean": 1267.2388061523438, "teacher_distance_mean": 0.8458777129650116, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0019402782083489001, "weighted_relation_loss": 0.0019402782083489001 }, { "action_query_batch_std": 22.149729537963868, "action_query_norm": 939.7499267578125, "action_relation_loss": 0.0020026941085234283, "auxiliary_loss_weight": 1.0, "epoch": 20.954162768942936, "flow_matching_loss": 0.017321220226585866, "grad_norm": 0.12153582274913788, "invalid_tail_samples": 23.7, "learning_rate": 1.6547565777109976e-05, "loss": 0.0193, "positive_teacher_pairs": 26876.1, "relation_loss": 0.0020026941085234283, "selected_pairs": 26876.1, "step": 22400, "student_distance_mean": 1275.3262329101562, "teacher_distance_mean": 0.8541008412837983, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0020026941085234283, "weighted_relation_loss": 0.0020026941085234283 }, { "action_query_batch_std": 22.185194206237792, "action_query_norm": 942.4126708984375, "action_relation_loss": 0.0020066679106093945, "auxiliary_loss_weight": 1.0, "epoch": 20.963517305893358, "flow_matching_loss": 0.017728505469858647, "grad_norm": 0.09694703668355942, "invalid_tail_samples": 24.9, "learning_rate": 1.650662312633143e-05, "loss": 0.0197, "positive_teacher_pairs": 26590.7, "relation_loss": 0.0020066679106093945, "selected_pairs": 26590.7, "step": 22410, "student_distance_mean": 1270.5253051757813, "teacher_distance_mean": 0.8528976678848267, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0020066679106093945, "weighted_relation_loss": 0.0020066679106093945 }, { "action_query_batch_std": 22.202774429321288, "action_query_norm": 941.9021057128906, "action_relation_loss": 0.002014611382037401, "auxiliary_loss_weight": 1.0, "epoch": 20.97287184284378, "flow_matching_loss": 0.017844904121011494, "grad_norm": 0.10375078022480011, "invalid_tail_samples": 26.7, "learning_rate": 1.6465721173164002e-05, "loss": 0.0199, "positive_teacher_pairs": 26179.4, "relation_loss": 0.002014611382037401, "selected_pairs": 26179.4, "step": 22420, "student_distance_mean": 1276.3092041015625, "teacher_distance_mean": 0.8565963208675385, "valid_action_samples": 229.3, "weighted_auxiliary_loss": 0.002014611382037401, "weighted_relation_loss": 0.002014611382037401 }, { "action_query_batch_std": 22.154630661010742, "action_query_norm": 942.0230102539062, "action_relation_loss": 0.0020391658879816534, "auxiliary_loss_weight": 1.0, "epoch": 20.9822263797942, "flow_matching_loss": 0.01810734551399946, "grad_norm": 0.09075820446014404, "invalid_tail_samples": 24.3, "learning_rate": 1.6424859967307428e-05, "loss": 0.0201, "positive_teacher_pairs": 26741.2, "relation_loss": 0.0020391658879816534, "selected_pairs": 26741.2, "step": 22430, "student_distance_mean": 1275.200390625, "teacher_distance_mean": 0.8517954170703887, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0020391658879816534, "weighted_relation_loss": 0.0020391658879816534 }, { "action_query_batch_std": 22.294237899780274, "action_query_norm": 951.0380920410156, "action_relation_loss": 0.0019513224833644927, "auxiliary_loss_weight": 1.0, "epoch": 20.99158091674462, "flow_matching_loss": 0.017441572900861502, "grad_norm": 0.09196490049362183, "invalid_tail_samples": 22.4, "learning_rate": 1.6384039558411903e-05, "loss": 0.0194, "positive_teacher_pairs": 27182.4, "relation_loss": 0.0019513224833644927, "selected_pairs": 27182.4, "step": 22440, "student_distance_mean": 1282.7928833007813, "teacher_distance_mean": 0.8572915852069855, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.0019513224833644927, "weighted_relation_loss": 0.0019513224833644927 }, { "action_query_batch_std": 22.007654190063477, "action_query_norm": 939.3041076660156, "action_relation_loss": 0.0020155222504399718, "auxiliary_loss_weight": 1.0, "epoch": 21.000935453695043, "flow_matching_loss": 0.01805010810494423, "grad_norm": 0.11884912848472595, "invalid_tail_samples": 22.1, "learning_rate": 1.634325999607811e-05, "loss": 0.0201, "positive_teacher_pairs": 24271.0, "relation_loss": 0.0020155222504399718, "selected_pairs": 24271.0, "step": 22450, "student_distance_mean": 1259.466259765625, "teacher_distance_mean": 0.844015383720398, "valid_action_samples": 214.0, "weighted_auxiliary_loss": 0.0020155222504399718, "weighted_relation_loss": 0.0020155222504399718 }, { "action_query_batch_std": 22.366760635375975, "action_query_norm": 948.9051574707031, "action_relation_loss": 0.001912779314443469, "auxiliary_loss_weight": 1.0, "epoch": 21.010289990645465, "flow_matching_loss": 0.019514850061386823, "grad_norm": 0.10973506420850754, "invalid_tail_samples": 22.8, "learning_rate": 1.6302521329857045e-05, "loss": 0.0214, "positive_teacher_pairs": 27089.3, "relation_loss": 0.001912779314443469, "selected_pairs": 27089.3, "step": 22460, "student_distance_mean": 1283.033203125, "teacher_distance_mean": 0.857388299703598, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.001912779314443469, "weighted_relation_loss": 0.001912779314443469 }, { "action_query_batch_std": 22.48508472442627, "action_query_norm": 954.4180725097656, "action_relation_loss": 0.0018993067089468241, "auxiliary_loss_weight": 1.0, "epoch": 21.019644527595883, "flow_matching_loss": 0.019396192766726016, "grad_norm": 0.09369882196187973, "invalid_tail_samples": 23.1, "learning_rate": 1.6261823609250027e-05, "loss": 0.0213, "positive_teacher_pairs": 27010.6, "relation_loss": 0.0018993067089468241, "selected_pairs": 27010.6, "step": 22470, "student_distance_mean": 1291.406494140625, "teacher_distance_mean": 0.860969877243042, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0018993067089468241, "weighted_relation_loss": 0.0018993067089468241 }, { "action_query_batch_std": 22.453743553161623, "action_query_norm": 950.9005493164062, "action_relation_loss": 0.001937001955229789, "auxiliary_loss_weight": 1.0, "epoch": 21.028999064546305, "flow_matching_loss": 0.01810504598543048, "grad_norm": 0.09495582431554794, "invalid_tail_samples": 22.2, "learning_rate": 1.6221166883708627e-05, "loss": 0.02, "positive_teacher_pairs": 27222.1, "relation_loss": 0.001937001955229789, "selected_pairs": 27222.1, "step": 22480, "student_distance_mean": 1285.67421875, "teacher_distance_mean": 0.8579420566558837, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.001937001955229789, "weighted_relation_loss": 0.001937001955229789 }, { "action_query_batch_std": 22.20933380126953, "action_query_norm": 947.6124694824218, "action_relation_loss": 0.0019995693815872072, "auxiliary_loss_weight": 1.0, "epoch": 21.038353601496727, "flow_matching_loss": 0.018475637957453727, "grad_norm": 0.07467286288738251, "invalid_tail_samples": 23.6, "learning_rate": 1.6180551202634603e-05, "loss": 0.0205, "positive_teacher_pairs": 26906.2, "relation_loss": 0.0019995693815872072, "selected_pairs": 26906.2, "step": 22490, "student_distance_mean": 1275.1347534179688, "teacher_distance_mean": 0.8498268187046051, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0019995693815872072, "weighted_relation_loss": 0.0019995693815872072 }, { "action_query_batch_std": 22.40287342071533, "action_query_norm": 952.8287841796875, "action_relation_loss": 0.0019963923143222926, "auxiliary_loss_weight": 1.0, "epoch": 21.047708138447145, "flow_matching_loss": 0.017543497122824193, "grad_norm": 0.10150358825922012, "invalid_tail_samples": 23.2, "learning_rate": 1.613997661537981e-05, "loss": 0.0195, "positive_teacher_pairs": 26996.3, "relation_loss": 0.0019963923143222926, "selected_pairs": 26996.3, "step": 22500, "student_distance_mean": 1286.8851196289063, "teacher_distance_mean": 0.8583734571933747, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0019963923143222926, "weighted_relation_loss": 0.0019963923143222926 }, { "action_query_batch_std": 22.16248950958252, "action_query_norm": 941.4030395507813, "action_relation_loss": 0.0019845952629111707, "auxiliary_loss_weight": 1.0, "epoch": 21.057062675397567, "flow_matching_loss": 0.017907170206308366, "grad_norm": 0.08023818582296371, "invalid_tail_samples": 22.9, "learning_rate": 1.609944317124624e-05, "loss": 0.0199, "positive_teacher_pairs": 27057.3, "relation_loss": 0.0019845952629111707, "selected_pairs": 27057.3, "step": 22510, "student_distance_mean": 1275.8190673828126, "teacher_distance_mean": 0.8511442601680755, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0019845952629111707, "weighted_relation_loss": 0.0019845952629111707 }, { "action_query_batch_std": 22.510306739807127, "action_query_norm": 956.2168212890625, "action_relation_loss": 0.001937813579570502, "auxiliary_loss_weight": 1.0, "epoch": 21.06641721234799, "flow_matching_loss": 0.017492661997675896, "grad_norm": 0.0944414809346199, "invalid_tail_samples": 24.7, "learning_rate": 1.605895091948582e-05, "loss": 0.0194, "positive_teacher_pairs": 26638.9, "relation_loss": 0.001937813579570502, "selected_pairs": 26638.9, "step": 22520, "student_distance_mean": 1286.48798828125, "teacher_distance_mean": 0.8578325390815735, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.001937813579570502, "weighted_relation_loss": 0.001937813579570502 }, { "action_query_batch_std": 22.322066688537596, "action_query_norm": 947.7117736816406, "action_relation_loss": 0.0019249270786531269, "auxiliary_loss_weight": 1.0, "epoch": 21.07577174929841, "flow_matching_loss": 0.017571236379444598, "grad_norm": 0.07404652237892151, "invalid_tail_samples": 22.7, "learning_rate": 1.6018499909300477e-05, "loss": 0.0195, "positive_teacher_pairs": 27110.1, "relation_loss": 0.0019249270786531269, "selected_pairs": 27110.1, "step": 22530, "student_distance_mean": 1279.2605102539062, "teacher_distance_mean": 0.8524871408939362, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0019249270786531269, "weighted_relation_loss": 0.0019249270786531269 }, { "action_query_batch_std": 22.19982967376709, "action_query_norm": 944.0577575683594, "action_relation_loss": 0.0019741108757443727, "auxiliary_loss_weight": 1.0, "epoch": 21.08512628624883, "flow_matching_loss": 0.017242513503879307, "grad_norm": 0.08359820395708084, "invalid_tail_samples": 22.5, "learning_rate": 1.597809018984199e-05, "loss": 0.0192, "positive_teacher_pairs": 27153.8, "relation_loss": 0.0019741108757443727, "selected_pairs": 27153.8, "step": 22540, "student_distance_mean": 1275.9410766601563, "teacher_distance_mean": 0.8515476763248444, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0019741108757443727, "weighted_relation_loss": 0.0019741108757443727 }, { "action_query_batch_std": 22.03860397338867, "action_query_norm": 942.9559387207031, "action_relation_loss": 0.0019294658792205154, "auxiliary_loss_weight": 1.0, "epoch": 21.09448082319925, "flow_matching_loss": 0.018110630009323357, "grad_norm": 0.0902070477604866, "invalid_tail_samples": 22.5, "learning_rate": 1.593772181021196e-05, "loss": 0.02, "positive_teacher_pairs": 27152.7, "relation_loss": 0.0019294658792205154, "selected_pairs": 27152.7, "step": 22550, "student_distance_mean": 1266.8453125, "teacher_distance_mean": 0.8447019338607789, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0019294658792205154, "weighted_relation_loss": 0.0019294658792205154 }, { "action_query_batch_std": 22.447211456298827, "action_query_norm": 953.9780578613281, "action_relation_loss": 0.0018875708570703863, "auxiliary_loss_weight": 1.0, "epoch": 21.103835360149674, "flow_matching_loss": 0.01829135585576296, "grad_norm": 0.07511214911937714, "invalid_tail_samples": 23.1, "learning_rate": 1.5897394819461813e-05, "loss": 0.0202, "positive_teacher_pairs": 27009.7, "relation_loss": 0.0018875708570703863, "selected_pairs": 27009.7, "step": 22560, "student_distance_mean": 1288.354638671875, "teacher_distance_mean": 0.8585618019104004, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0018875708570703863, "weighted_relation_loss": 0.0018875708570703863 }, { "action_query_batch_std": 22.500183486938475, "action_query_norm": 957.3042541503906, "action_relation_loss": 0.0019119638483971358, "auxiliary_loss_weight": 1.0, "epoch": 21.113189897100092, "flow_matching_loss": 0.01715996442362666, "grad_norm": 0.10979878157377243, "invalid_tail_samples": 22.7, "learning_rate": 1.5857109266592625e-05, "loss": 0.0191, "positive_teacher_pairs": 27103.4, "relation_loss": 0.0019119638483971358, "selected_pairs": 27103.4, "step": 22570, "student_distance_mean": 1290.3842651367188, "teacher_distance_mean": 0.858489853143692, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0019119638483971358, "weighted_relation_loss": 0.0019119638483971358 }, { "action_query_batch_std": 22.25309066772461, "action_query_norm": 942.0725280761719, "action_relation_loss": 0.0019266504910774528, "auxiliary_loss_weight": 1.0, "epoch": 21.122544434050514, "flow_matching_loss": 0.01937809297814965, "grad_norm": 0.10954047739505768, "invalid_tail_samples": 26.5, "learning_rate": 1.581686520055514e-05, "loss": 0.0213, "positive_teacher_pairs": 26226.8, "relation_loss": 0.0019266504910774528, "selected_pairs": 26226.8, "step": 22580, "student_distance_mean": 1279.7784790039063, "teacher_distance_mean": 0.8551080346107482, "valid_action_samples": 229.5, "weighted_auxiliary_loss": 0.0019266504910774528, "weighted_relation_loss": 0.0019266504910774528 }, { "action_query_batch_std": 22.480732345581053, "action_query_norm": 953.2905334472656, "action_relation_loss": 0.0019732865621335804, "auxiliary_loss_weight": 1.0, "epoch": 21.131898971000936, "flow_matching_loss": 0.01899576438590884, "grad_norm": 0.0828867107629776, "invalid_tail_samples": 25.0, "learning_rate": 1.5776662670249704e-05, "loss": 0.021, "positive_teacher_pairs": 26575.8, "relation_loss": 0.0019732865621335804, "selected_pairs": 26575.8, "step": 22590, "student_distance_mean": 1294.5727661132812, "teacher_distance_mean": 0.862355375289917, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0019732865621335804, "weighted_relation_loss": 0.0019732865621335804 }, { "action_query_batch_std": 22.6262487411499, "action_query_norm": 959.7574157714844, "action_relation_loss": 0.0019000582513399422, "auxiliary_loss_weight": 1.0, "epoch": 21.141253507951358, "flow_matching_loss": 0.018645606096833946, "grad_norm": 0.08920585364103317, "invalid_tail_samples": 24.3, "learning_rate": 1.573650172452615e-05, "loss": 0.0205, "positive_teacher_pairs": 26731.9, "relation_loss": 0.0019000582513399422, "selected_pairs": 26731.9, "step": 22600, "student_distance_mean": 1298.1781616210938, "teacher_distance_mean": 0.8660019338130951, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0019000582513399422, "weighted_relation_loss": 0.0019000582513399422 }, { "action_query_batch_std": 22.211568450927736, "action_query_norm": 944.7395080566406, "action_relation_loss": 0.001946911122649908, "auxiliary_loss_weight": 1.0, "epoch": 21.150608044901777, "flow_matching_loss": 0.016821679566055535, "grad_norm": 0.08523078262805939, "invalid_tail_samples": 22.6, "learning_rate": 1.5696382412183852e-05, "loss": 0.0188, "positive_teacher_pairs": 27125.9, "relation_loss": 0.001946911122649908, "selected_pairs": 27125.9, "step": 22610, "student_distance_mean": 1280.5518188476562, "teacher_distance_mean": 0.8560261487960815, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.001946911122649908, "weighted_relation_loss": 0.001946911122649908 }, { "action_query_batch_std": 22.07113151550293, "action_query_norm": 940.236328125, "action_relation_loss": 0.0018747628666460515, "auxiliary_loss_weight": 1.0, "epoch": 21.1599625818522, "flow_matching_loss": 0.018380918353796006, "grad_norm": 0.08073857426643372, "invalid_tail_samples": 23.3, "learning_rate": 1.565630478197155e-05, "loss": 0.0203, "positive_teacher_pairs": 26965.0, "relation_loss": 0.0018747628666460515, "selected_pairs": 26965.0, "step": 22620, "student_distance_mean": 1268.8523681640625, "teacher_distance_mean": 0.8477884113788605, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0018747628666460515, "weighted_relation_loss": 0.0018747628666460515 }, { "action_query_batch_std": 22.280902099609374, "action_query_norm": 949.8831115722656, "action_relation_loss": 0.0018938806722871959, "auxiliary_loss_weight": 1.0, "epoch": 21.16931711880262, "flow_matching_loss": 0.018253284972161055, "grad_norm": 0.1096373051404953, "invalid_tail_samples": 20.2, "learning_rate": 1.5616268882587332e-05, "loss": 0.0201, "positive_teacher_pairs": 27688.0, "relation_loss": 0.0018938806722871959, "selected_pairs": 27688.0, "step": 22630, "student_distance_mean": 1277.8985229492187, "teacher_distance_mean": 0.8505739867687225, "valid_action_samples": 235.8, "weighted_auxiliary_loss": 0.0018938806722871959, "weighted_relation_loss": 0.0018938806722871959 }, { "action_query_batch_std": 22.155724716186523, "action_query_norm": 941.8482543945313, "action_relation_loss": 0.001903281465638429, "auxiliary_loss_weight": 1.0, "epoch": 21.17867165575304, "flow_matching_loss": 0.017777665611356498, "grad_norm": 0.10312631726264954, "invalid_tail_samples": 23.7, "learning_rate": 1.5576274762678594e-05, "loss": 0.0197, "positive_teacher_pairs": 26874.7, "relation_loss": 0.001903281465638429, "selected_pairs": 26874.7, "step": 22640, "student_distance_mean": 1273.978857421875, "teacher_distance_mean": 0.8487162470817566, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.001903281465638429, "weighted_relation_loss": 0.001903281465638429 }, { "action_query_batch_std": 22.10259094238281, "action_query_norm": 942.6876953125, "action_relation_loss": 0.001962422812357545, "auxiliary_loss_weight": 1.0, "epoch": 21.18802619270346, "flow_matching_loss": 0.016774088609963655, "grad_norm": 0.08438664674758911, "invalid_tail_samples": 25.0, "learning_rate": 1.5536322470841952e-05, "loss": 0.0187, "positive_teacher_pairs": 26579.3, "relation_loss": 0.001962422812357545, "selected_pairs": 26579.3, "step": 22650, "student_distance_mean": 1272.3799926757813, "teacher_distance_mean": 0.850579684972763, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.001962422812357545, "weighted_relation_loss": 0.001962422812357545 }, { "action_query_batch_std": 22.066519737243652, "action_query_norm": 939.7735473632813, "action_relation_loss": 0.0019152212073095143, "auxiliary_loss_weight": 1.0, "epoch": 21.197380729653883, "flow_matching_loss": 0.01960983853787184, "grad_norm": 0.0806402638554573, "invalid_tail_samples": 24.6, "learning_rate": 1.549641205562324e-05, "loss": 0.0215, "positive_teacher_pairs": 26673.1, "relation_loss": 0.0019152212073095143, "selected_pairs": 26673.1, "step": 22660, "student_distance_mean": 1274.3310791015624, "teacher_distance_mean": 0.8532684981822968, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0019152212073095143, "weighted_relation_loss": 0.0019152212073095143 }, { "action_query_batch_std": 22.209299850463868, "action_query_norm": 942.2576782226563, "action_relation_loss": 0.0019267424009740352, "auxiliary_loss_weight": 1.0, "epoch": 21.2067352666043, "flow_matching_loss": 0.01804568599909544, "grad_norm": 0.08585788309574127, "invalid_tail_samples": 23.7, "learning_rate": 1.5456543565517334e-05, "loss": 0.02, "positive_teacher_pairs": 26879.4, "relation_loss": 0.0019267424009740352, "selected_pairs": 26879.4, "step": 22670, "student_distance_mean": 1276.66142578125, "teacher_distance_mean": 0.8536933779716491, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0019267424009740352, "weighted_relation_loss": 0.0019267424009740352 }, { "action_query_batch_std": 22.251672172546385, "action_query_norm": 943.5929077148437, "action_relation_loss": 0.0019468395155854523, "auxiliary_loss_weight": 1.0, "epoch": 21.216089803554723, "flow_matching_loss": 0.01707450682297349, "grad_norm": 0.08076257258653641, "invalid_tail_samples": 26.8, "learning_rate": 1.541671704896825e-05, "loss": 0.019, "positive_teacher_pairs": 26164.2, "relation_loss": 0.0019468395155854523, "selected_pairs": 26164.2, "step": 22680, "student_distance_mean": 1280.9334106445312, "teacher_distance_mean": 0.8543808698654175, "valid_action_samples": 229.2, "weighted_auxiliary_loss": 0.0019468395155854523, "weighted_relation_loss": 0.0019468395155854523 }, { "action_query_batch_std": 22.11947536468506, "action_query_norm": 940.9400634765625, "action_relation_loss": 0.0019304185872897506, "auxiliary_loss_weight": 1.0, "epoch": 21.225444340505145, "flow_matching_loss": 0.018803184758871792, "grad_norm": 0.08300910145044327, "invalid_tail_samples": 23.1, "learning_rate": 1.5376932554368938e-05, "loss": 0.0207, "positive_teacher_pairs": 27015.0, "relation_loss": 0.0019304185872897506, "selected_pairs": 27015.0, "step": 22690, "student_distance_mean": 1270.7311279296875, "teacher_distance_mean": 0.8490243494510651, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0019304185872897506, "weighted_relation_loss": 0.0019304185872897506 }, { "action_query_batch_std": 22.041391944885255, "action_query_norm": 939.6322082519531, "action_relation_loss": 0.0018909762613475323, "auxiliary_loss_weight": 1.0, "epoch": 21.234798877455567, "flow_matching_loss": 0.01732396110892296, "grad_norm": 0.09208271652460098, "invalid_tail_samples": 21.4, "learning_rate": 1.5337190130061318e-05, "loss": 0.0192, "positive_teacher_pairs": 27407.3, "relation_loss": 0.0018909762613475323, "selected_pairs": 27407.3, "step": 22700, "student_distance_mean": 1264.5483764648438, "teacher_distance_mean": 0.8454705774784088, "valid_action_samples": 234.6, "weighted_auxiliary_loss": 0.0018909762613475323, "weighted_relation_loss": 0.0018909762613475323 }, { "action_query_batch_std": 22.388059425354005, "action_query_norm": 948.7575988769531, "action_relation_loss": 0.0019133978523314, "auxiliary_loss_weight": 1.0, "epoch": 21.244153414405986, "flow_matching_loss": 0.01788235316053033, "grad_norm": 0.08769705891609192, "invalid_tail_samples": 25.3, "learning_rate": 1.5297489824336165e-05, "loss": 0.0198, "positive_teacher_pairs": 26504.0, "relation_loss": 0.0019133978523314, "selected_pairs": 26504.0, "step": 22710, "student_distance_mean": 1283.1683349609375, "teacher_distance_mean": 0.8603722155094147, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0019133978523314, "weighted_relation_loss": 0.0019133978523314 }, { "action_query_batch_std": 22.05839099884033, "action_query_norm": 939.9555725097656, "action_relation_loss": 0.0019246947253122927, "auxiliary_loss_weight": 1.0, "epoch": 21.253507951356408, "flow_matching_loss": 0.016534237749874593, "grad_norm": 0.09439956396818161, "invalid_tail_samples": 23.1, "learning_rate": 1.5257831685433121e-05, "loss": 0.0185, "positive_teacher_pairs": 27012.1, "relation_loss": 0.0019246947253122927, "selected_pairs": 27012.1, "step": 22720, "student_distance_mean": 1271.058837890625, "teacher_distance_mean": 0.8520468533039093, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0019246947253122927, "weighted_relation_loss": 0.0019246947253122927 }, { "action_query_batch_std": 22.01537094116211, "action_query_norm": 938.07763671875, "action_relation_loss": 0.0019095799303613602, "auxiliary_loss_weight": 1.0, "epoch": 21.26286248830683, "flow_matching_loss": 0.016978944838047027, "grad_norm": 0.11382406949996948, "invalid_tail_samples": 25.0, "learning_rate": 1.521821576154055e-05, "loss": 0.0189, "positive_teacher_pairs": 26580.1, "relation_loss": 0.0019095799303613602, "selected_pairs": 26580.1, "step": 22730, "student_distance_mean": 1266.30888671875, "teacher_distance_mean": 0.8469596922397613, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0019095799303613602, "weighted_relation_loss": 0.0019095799303613602 }, { "action_query_batch_std": 22.454895210266113, "action_query_norm": 949.3011901855468, "action_relation_loss": 0.0019831960205920042, "auxiliary_loss_weight": 1.0, "epoch": 21.27221702525725, "flow_matching_loss": 0.017244263924658297, "grad_norm": 0.11150293797254562, "invalid_tail_samples": 24.0, "learning_rate": 1.5178642100795542e-05, "loss": 0.0192, "positive_teacher_pairs": 26806.9, "relation_loss": 0.0019831960205920042, "selected_pairs": 26806.9, "step": 22740, "student_distance_mean": 1284.8860107421874, "teacher_distance_mean": 0.8576762735843658, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0019831960205920042, "weighted_relation_loss": 0.0019831960205920042 }, { "action_query_batch_std": 22.184135246276856, "action_query_norm": 943.7343322753907, "action_relation_loss": 0.0019032745622098446, "auxiliary_loss_weight": 1.0, "epoch": 21.28157156220767, "flow_matching_loss": 0.01717663574963808, "grad_norm": 0.09266695380210876, "invalid_tail_samples": 23.8, "learning_rate": 1.5139110751283819e-05, "loss": 0.0191, "positive_teacher_pairs": 26852.8, "relation_loss": 0.0019032745622098446, "selected_pairs": 26852.8, "step": 22750, "student_distance_mean": 1276.7272338867188, "teacher_distance_mean": 0.8533592879772186, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0019032745622098446, "weighted_relation_loss": 0.0019032745622098446 }, { "action_query_batch_std": 21.999705505371093, "action_query_norm": 938.1571838378907, "action_relation_loss": 0.001955613063182682, "auxiliary_loss_weight": 1.0, "epoch": 21.290926099158092, "flow_matching_loss": 0.020678805746138097, "grad_norm": 0.0808633342385292, "invalid_tail_samples": 22.7, "learning_rate": 1.5099621761039683e-05, "loss": 0.0226, "positive_teacher_pairs": 27105.1, "relation_loss": 0.001955613063182682, "selected_pairs": 27105.1, "step": 22760, "student_distance_mean": 1261.684423828125, "teacher_distance_mean": 0.8437100291252136, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.001955613063182682, "weighted_relation_loss": 0.001955613063182682 }, { "action_query_batch_std": 22.18889389038086, "action_query_norm": 945.1367065429688, "action_relation_loss": 0.0018888761871494353, "auxiliary_loss_weight": 1.0, "epoch": 21.300280636108514, "flow_matching_loss": 0.018871753104031087, "grad_norm": 0.08655041456222534, "invalid_tail_samples": 21.2, "learning_rate": 1.5060175178046016e-05, "loss": 0.0208, "positive_teacher_pairs": 27452.8, "relation_loss": 0.0018888761871494353, "selected_pairs": 27452.8, "step": 22770, "student_distance_mean": 1272.9025390625, "teacher_distance_mean": 0.8515381217002869, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.0018888761871494353, "weighted_relation_loss": 0.0018888761871494353 }, { "action_query_batch_std": 22.51042423248291, "action_query_norm": 953.7416137695312, "action_relation_loss": 0.0018784254789352417, "auxiliary_loss_weight": 1.0, "epoch": 21.309635173058933, "flow_matching_loss": 0.019920130725950003, "grad_norm": 0.10240380465984344, "invalid_tail_samples": 23.6, "learning_rate": 1.5020771050234117e-05, "loss": 0.0218, "positive_teacher_pairs": 26911.3, "relation_loss": 0.0018784254789352417, "selected_pairs": 26911.3, "step": 22780, "student_distance_mean": 1291.7452758789063, "teacher_distance_mean": 0.863712626695633, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0018784254789352417, "weighted_relation_loss": 0.0018784254789352417 }, { "action_query_batch_std": 22.21799259185791, "action_query_norm": 942.2702697753906, "action_relation_loss": 0.0019444139790721238, "auxiliary_loss_weight": 1.0, "epoch": 21.318989710009355, "flow_matching_loss": 0.01780981747433543, "grad_norm": 0.09096547961235046, "invalid_tail_samples": 26.9, "learning_rate": 1.4981409425483716e-05, "loss": 0.0198, "positive_teacher_pairs": 26138.1, "relation_loss": 0.0019444139790721238, "selected_pairs": 26138.1, "step": 22790, "student_distance_mean": 1277.8990966796875, "teacher_distance_mean": 0.8521228432655334, "valid_action_samples": 229.1, "weighted_auxiliary_loss": 0.0019444139790721238, "weighted_relation_loss": 0.0019444139790721238 }, { "action_query_batch_std": 22.17033996582031, "action_query_norm": 944.5119934082031, "action_relation_loss": 0.0018852007458917796, "auxiliary_loss_weight": 1.0, "epoch": 21.328344246959777, "flow_matching_loss": 0.015649604611098766, "grad_norm": 0.08080732822418213, "invalid_tail_samples": 24.6, "learning_rate": 1.4942090351622883e-05, "loss": 0.0175, "positive_teacher_pairs": 26670.9, "relation_loss": 0.0018852007458917796, "selected_pairs": 26670.9, "step": 22800, "student_distance_mean": 1281.7935668945313, "teacher_distance_mean": 0.8547110676765441, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0018852007458917796, "weighted_relation_loss": 0.0018852007458917796 }, { "action_query_batch_std": 22.112478828430177, "action_query_norm": 940.4507202148437, "action_relation_loss": 0.0019772342522628604, "auxiliary_loss_weight": 1.0, "epoch": 21.337698783910195, "flow_matching_loss": 0.017212731204926966, "grad_norm": 0.09085889905691147, "invalid_tail_samples": 25.5, "learning_rate": 1.490281387642804e-05, "loss": 0.0192, "positive_teacher_pairs": 26455.4, "relation_loss": 0.0019772342522628604, "selected_pairs": 26455.4, "step": 22810, "student_distance_mean": 1269.1282348632812, "teacher_distance_mean": 0.849175900220871, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0019772342522628604, "weighted_relation_loss": 0.0019772342522628604 }, { "action_query_batch_std": 22.03443603515625, "action_query_norm": 939.0878356933594, "action_relation_loss": 0.0018851307919248938, "auxiliary_loss_weight": 1.0, "epoch": 21.347053320860617, "flow_matching_loss": 0.017254481464624404, "grad_norm": 0.09654656052589417, "invalid_tail_samples": 23.7, "learning_rate": 1.4863580047623765e-05, "loss": 0.0191, "positive_teacher_pairs": 26869.5, "relation_loss": 0.0018851307919248938, "selected_pairs": 26869.5, "step": 22820, "student_distance_mean": 1268.6563598632813, "teacher_distance_mean": 0.8484698235988617, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0018851307919248938, "weighted_relation_loss": 0.0018851307919248938 }, { "action_query_batch_std": 22.19716625213623, "action_query_norm": 943.071923828125, "action_relation_loss": 0.0019134614733047784, "auxiliary_loss_weight": 1.0, "epoch": 21.35640785781104, "flow_matching_loss": 0.01605207649990916, "grad_norm": 0.09311921894550323, "invalid_tail_samples": 24.9, "learning_rate": 1.4824388912882897e-05, "loss": 0.018, "positive_teacher_pairs": 26595.4, "relation_loss": 0.0019134614733047784, "selected_pairs": 26595.4, "step": 22830, "student_distance_mean": 1276.1773559570313, "teacher_distance_mean": 0.854604172706604, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0019134614733047784, "weighted_relation_loss": 0.0019134614733047784 }, { "action_query_batch_std": 22.095860481262207, "action_query_norm": 937.663330078125, "action_relation_loss": 0.0019060276099480689, "auxiliary_loss_weight": 1.0, "epoch": 21.36576239476146, "flow_matching_loss": 0.017776318546384572, "grad_norm": 0.11035005748271942, "invalid_tail_samples": 22.1, "learning_rate": 1.4785240519826344e-05, "loss": 0.0197, "positive_teacher_pairs": 27242.7, "relation_loss": 0.0019060276099480689, "selected_pairs": 27242.7, "step": 22840, "student_distance_mean": 1264.741064453125, "teacher_distance_mean": 0.8468108654022217, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0019060276099480689, "weighted_relation_loss": 0.0019060276099480689 }, { "action_query_batch_std": 22.245897483825683, "action_query_norm": 943.7501037597656, "action_relation_loss": 0.0019514222396537662, "auxiliary_loss_weight": 1.0, "epoch": 21.37511693171188, "flow_matching_loss": 0.01576925441622734, "grad_norm": 0.09036348015069962, "invalid_tail_samples": 24.2, "learning_rate": 1.4746134916023097e-05, "loss": 0.0177, "positive_teacher_pairs": 26755.4, "relation_loss": 0.0019514222396537662, "selected_pairs": 26755.4, "step": 22850, "student_distance_mean": 1274.9650390625, "teacher_distance_mean": 0.8531951546669007, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0019514222396537662, "weighted_relation_loss": 0.0019514222396537662 }, { "action_query_batch_std": 22.01339054107666, "action_query_norm": 935.1289367675781, "action_relation_loss": 0.0019700515898875893, "auxiliary_loss_weight": 1.0, "epoch": 21.3844714686623, "flow_matching_loss": 0.01794739505276084, "grad_norm": 0.10043670237064362, "invalid_tail_samples": 25.6, "learning_rate": 1.4707072148990141e-05, "loss": 0.0199, "positive_teacher_pairs": 26438.2, "relation_loss": 0.0019700515898875893, "selected_pairs": 26438.2, "step": 22860, "student_distance_mean": 1266.327490234375, "teacher_distance_mean": 0.8463808774948121, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.0019700515898875893, "weighted_relation_loss": 0.0019700515898875893 }, { "action_query_batch_std": 22.20395679473877, "action_query_norm": 944.1100646972657, "action_relation_loss": 0.0019296774524264037, "auxiliary_loss_weight": 1.0, "epoch": 21.393826005612723, "flow_matching_loss": 0.018321989849209786, "grad_norm": 0.10606163740158081, "invalid_tail_samples": 24.8, "learning_rate": 1.4668052266192423e-05, "loss": 0.0203, "positive_teacher_pairs": 26616.0, "relation_loss": 0.0019296774524264037, "selected_pairs": 26616.0, "step": 22870, "student_distance_mean": 1276.7773193359376, "teacher_distance_mean": 0.8514677226543427, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0019296774524264037, "weighted_relation_loss": 0.0019296774524264037 }, { "action_query_batch_std": 22.29680690765381, "action_query_norm": 947.9667297363281, "action_relation_loss": 0.0019370767869986594, "auxiliary_loss_weight": 1.0, "epoch": 21.403180542563142, "flow_matching_loss": 0.01943707773461938, "grad_norm": 0.09949313849210739, "invalid_tail_samples": 21.1, "learning_rate": 1.4629075315042795e-05, "loss": 0.0214, "positive_teacher_pairs": 27481.5, "relation_loss": 0.0019370767869986594, "selected_pairs": 27481.5, "step": 22880, "student_distance_mean": 1286.4427612304687, "teacher_distance_mean": 0.8572475194931031, "valid_action_samples": 234.9, "weighted_auxiliary_loss": 0.0019370767869986594, "weighted_relation_loss": 0.0019370767869986594 }, { "action_query_batch_std": 22.219954872131346, "action_query_norm": 941.7267211914062, "action_relation_loss": 0.001877264236100018, "auxiliary_loss_weight": 1.0, "epoch": 21.412535079513564, "flow_matching_loss": 0.01929735401645303, "grad_norm": 0.09852389991283417, "invalid_tail_samples": 23.0, "learning_rate": 1.4590141342901925e-05, "loss": 0.0212, "positive_teacher_pairs": 27038.0, "relation_loss": 0.001877264236100018, "selected_pairs": 27038.0, "step": 22890, "student_distance_mean": 1278.061376953125, "teacher_distance_mean": 0.8523436665534974, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.001877264236100018, "weighted_relation_loss": 0.001877264236100018 }, { "action_query_batch_std": 22.58671417236328, "action_query_norm": 956.446826171875, "action_relation_loss": 0.0018797788652591407, "auxiliary_loss_weight": 1.0, "epoch": 21.421889616463986, "flow_matching_loss": 0.019247570261359214, "grad_norm": 0.0904431864619255, "invalid_tail_samples": 23.4, "learning_rate": 1.4551250397078253e-05, "loss": 0.0211, "positive_teacher_pairs": 26945.3, "relation_loss": 0.0018797788652591407, "selected_pairs": 26945.3, "step": 22900, "student_distance_mean": 1300.9496704101562, "teacher_distance_mean": 0.8691042780876159, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0018797788652591407, "weighted_relation_loss": 0.0018797788652591407 }, { "action_query_batch_std": 22.573829650878906, "action_query_norm": 957.3370056152344, "action_relation_loss": 0.0019133066409267486, "auxiliary_loss_weight": 1.0, "epoch": 21.431244153414404, "flow_matching_loss": 0.017350361868739127, "grad_norm": 0.0874180793762207, "invalid_tail_samples": 23.6, "learning_rate": 1.4512402524827945e-05, "loss": 0.0193, "positive_teacher_pairs": 26899.5, "relation_loss": 0.0019133066409267486, "selected_pairs": 26899.5, "step": 22910, "student_distance_mean": 1299.7683349609374, "teacher_distance_mean": 0.8660071969032288, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0019133066409267486, "weighted_relation_loss": 0.0019133066409267486 }, { "action_query_batch_std": 22.59210147857666, "action_query_norm": 957.5097717285156, "action_relation_loss": 0.0019089098437689244, "auxiliary_loss_weight": 1.0, "epoch": 21.440598690364826, "flow_matching_loss": 0.01705157607793808, "grad_norm": 0.09544668346643448, "invalid_tail_samples": 23.0, "learning_rate": 1.447359777335482e-05, "loss": 0.019, "positive_teacher_pairs": 27034.0, "relation_loss": 0.0019089098437689244, "selected_pairs": 27034.0, "step": 22920, "student_distance_mean": 1295.384375, "teacher_distance_mean": 0.8613941669464111, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0019089098437689244, "weighted_relation_loss": 0.0019089098437689244 }, { "action_query_batch_std": 22.468247413635254, "action_query_norm": 949.8215637207031, "action_relation_loss": 0.001910807762760669, "auxiliary_loss_weight": 1.0, "epoch": 21.44995322731525, "flow_matching_loss": 0.01720120748504996, "grad_norm": 0.11261390149593353, "invalid_tail_samples": 24.3, "learning_rate": 1.4434836189810335e-05, "loss": 0.0191, "positive_teacher_pairs": 26735.0, "relation_loss": 0.001910807762760669, "selected_pairs": 26735.0, "step": 22930, "student_distance_mean": 1289.6009887695313, "teacher_distance_mean": 0.8580859303474426, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.001910807762760669, "weighted_relation_loss": 0.001910807762760669 }, { "action_query_batch_std": 22.416132545471193, "action_query_norm": 948.8356628417969, "action_relation_loss": 0.0019186440738849341, "auxiliary_loss_weight": 1.0, "epoch": 21.45930776426567, "flow_matching_loss": 0.017764626257121562, "grad_norm": 0.10474973917007446, "invalid_tail_samples": 24.2, "learning_rate": 1.4396117821293453e-05, "loss": 0.0197, "positive_teacher_pairs": 26759.8, "relation_loss": 0.0019186440738849341, "selected_pairs": 26759.8, "step": 22940, "student_distance_mean": 1286.8660278320312, "teacher_distance_mean": 0.8574157238006592, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0019186440738849341, "weighted_relation_loss": 0.0019186440738849341 }, { "action_query_batch_std": 22.247661590576172, "action_query_norm": 944.5519348144531, "action_relation_loss": 0.001898894109763205, "auxiliary_loss_weight": 1.0, "epoch": 21.46866230121609, "flow_matching_loss": 0.018994479440152645, "grad_norm": 0.09021515399217606, "invalid_tail_samples": 25.8, "learning_rate": 1.4357442714850633e-05, "loss": 0.0209, "positive_teacher_pairs": 26393.2, "relation_loss": 0.001898894109763205, "selected_pairs": 26393.2, "step": 22950, "student_distance_mean": 1275.937890625, "teacher_distance_mean": 0.8535067737102509, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.001898894109763205, "weighted_relation_loss": 0.001898894109763205 }, { "action_query_batch_std": 22.320562171936036, "action_query_norm": 950.0372314453125, "action_relation_loss": 0.001886125560849905, "auxiliary_loss_weight": 1.0, "epoch": 21.47801683816651, "flow_matching_loss": 0.017466880008578302, "grad_norm": 0.09550022333860397, "invalid_tail_samples": 23.1, "learning_rate": 1.43188109174758e-05, "loss": 0.0194, "positive_teacher_pairs": 27010.7, "relation_loss": 0.001886125560849905, "selected_pairs": 27010.7, "step": 22960, "student_distance_mean": 1287.3435302734374, "teacher_distance_mean": 0.8578958332538604, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.001886125560849905, "weighted_relation_loss": 0.001886125560849905 }, { "action_query_batch_std": 22.355527687072755, "action_query_norm": 947.2782836914063, "action_relation_loss": 0.0019739151932299135, "auxiliary_loss_weight": 1.0, "epoch": 21.487371375116933, "flow_matching_loss": 0.019404458906501533, "grad_norm": 0.12056703120470047, "invalid_tail_samples": 25.9, "learning_rate": 1.4280222476110206e-05, "loss": 0.0214, "positive_teacher_pairs": 26364.4, "relation_loss": 0.0019739151932299135, "selected_pairs": 26364.4, "step": 22970, "student_distance_mean": 1289.1327026367187, "teacher_distance_mean": 0.8575498819351196, "valid_action_samples": 230.1, "weighted_auxiliary_loss": 0.0019739151932299135, "weighted_relation_loss": 0.0019739151932299135 }, { "action_query_batch_std": 22.25756130218506, "action_query_norm": 943.3015808105469, "action_relation_loss": 0.0018912595580331982, "auxiliary_loss_weight": 1.0, "epoch": 21.49672591206735, "flow_matching_loss": 0.017862549144774677, "grad_norm": 0.08729347586631775, "invalid_tail_samples": 24.3, "learning_rate": 1.4241677437642469e-05, "loss": 0.0198, "positive_teacher_pairs": 26737.7, "relation_loss": 0.0018912595580331982, "selected_pairs": 26737.7, "step": 22980, "student_distance_mean": 1282.3276733398438, "teacher_distance_mean": 0.8570938885211945, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0018912595580331982, "weighted_relation_loss": 0.0018912595580331982 }, { "action_query_batch_std": 22.259647178649903, "action_query_norm": 945.0190673828125, "action_relation_loss": 0.0019751021987758576, "auxiliary_loss_weight": 1.0, "epoch": 21.506080449017773, "flow_matching_loss": 0.017653318494558333, "grad_norm": 0.09671542793512344, "invalid_tail_samples": 24.0, "learning_rate": 1.420317584890844e-05, "loss": 0.0196, "positive_teacher_pairs": 26805.0, "relation_loss": 0.0019751021987758576, "selected_pairs": 26805.0, "step": 22990, "student_distance_mean": 1277.3542846679688, "teacher_distance_mean": 0.8536903560161591, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0019751021987758576, "weighted_relation_loss": 0.0019751021987758576 }, { "action_query_batch_std": 22.09800968170166, "action_query_norm": 938.3167724609375, "action_relation_loss": 0.0018772723153233529, "auxiliary_loss_weight": 1.0, "epoch": 21.515434985968195, "flow_matching_loss": 0.01781307961791754, "grad_norm": 0.10486394912004471, "invalid_tail_samples": 22.8, "learning_rate": 1.4164717756691176e-05, "loss": 0.0197, "positive_teacher_pairs": 27086.5, "relation_loss": 0.0018772723153233529, "selected_pairs": 27086.5, "step": 23000, "student_distance_mean": 1271.0022094726562, "teacher_distance_mean": 0.847283661365509, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0018772723153233529, "weighted_relation_loss": 0.0018772723153233529 }, { "action_query_batch_std": 22.48952980041504, "action_query_norm": 954.6693237304687, "action_relation_loss": 0.0019178285961970686, "auxiliary_loss_weight": 1.0, "epoch": 21.524789522918617, "flow_matching_loss": 0.019094304740428926, "grad_norm": 0.0888957753777504, "invalid_tail_samples": 22.8, "learning_rate": 1.4126303207720882e-05, "loss": 0.021, "positive_teacher_pairs": 27081.2, "relation_loss": 0.0019178285961970686, "selected_pairs": 27081.2, "step": 23010, "student_distance_mean": 1290.932373046875, "teacher_distance_mean": 0.8617390334606171, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0019178285961970686, "weighted_relation_loss": 0.0019178285961970686 }, { "action_query_batch_std": 22.246250724792482, "action_query_norm": 944.214794921875, "action_relation_loss": 0.0019163926248438657, "auxiliary_loss_weight": 1.0, "epoch": 21.534144059869035, "flow_matching_loss": 0.0201274904422462, "grad_norm": 0.09056004136800766, "invalid_tail_samples": 24.4, "learning_rate": 1.408793224867484e-05, "loss": 0.022, "positive_teacher_pairs": 26716.1, "relation_loss": 0.0019163926248438657, "selected_pairs": 26716.1, "step": 23020, "student_distance_mean": 1279.069873046875, "teacher_distance_mean": 0.8543200135231018, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0019163926248438657, "weighted_relation_loss": 0.0019163926248438657 }, { "action_query_batch_std": 22.25941982269287, "action_query_norm": 945.9526306152344, "action_relation_loss": 0.001972773135639727, "auxiliary_loss_weight": 1.0, "epoch": 21.543498596819457, "flow_matching_loss": 0.01921234354376793, "grad_norm": 0.09158018231391907, "invalid_tail_samples": 24.9, "learning_rate": 1.4049604926177423e-05, "loss": 0.0212, "positive_teacher_pairs": 26599.0, "relation_loss": 0.001972773135639727, "selected_pairs": 26599.0, "step": 23030, "student_distance_mean": 1280.1385009765625, "teacher_distance_mean": 0.8548133671283722, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.001972773135639727, "weighted_relation_loss": 0.001972773135639727 }, { "action_query_batch_std": 22.11415500640869, "action_query_norm": 939.3442504882812, "action_relation_loss": 0.0019618925522081553, "auxiliary_loss_weight": 1.0, "epoch": 21.55285313376988, "flow_matching_loss": 0.019385550543665885, "grad_norm": 0.08542070537805557, "invalid_tail_samples": 22.5, "learning_rate": 1.4011321286799916e-05, "loss": 0.0213, "positive_teacher_pairs": 27154.9, "relation_loss": 0.0019618925522081553, "selected_pairs": 27154.9, "step": 23040, "student_distance_mean": 1267.1888916015625, "teacher_distance_mean": 0.8492319762706757, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0019618925522081553, "weighted_relation_loss": 0.0019618925522081553 }, { "action_query_batch_std": 22.084085845947264, "action_query_norm": 938.0882873535156, "action_relation_loss": 0.0018676525447517633, "auxiliary_loss_weight": 1.0, "epoch": 21.562207670720298, "flow_matching_loss": 0.016781082190573216, "grad_norm": 0.07226589322090149, "invalid_tail_samples": 26.0, "learning_rate": 1.3973081377060565e-05, "loss": 0.0186, "positive_teacher_pairs": 26348.0, "relation_loss": 0.0018676525447517633, "selected_pairs": 26348.0, "step": 23050, "student_distance_mean": 1272.8717163085937, "teacher_distance_mean": 0.8540005505084991, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.0018676525447517633, "weighted_relation_loss": 0.0018676525447517633 }, { "action_query_batch_std": 22.14216556549072, "action_query_norm": 940.9515563964844, "action_relation_loss": 0.0019176918780431152, "auxiliary_loss_weight": 1.0, "epoch": 21.57156220767072, "flow_matching_loss": 0.019304659869521856, "grad_norm": 0.09782475233078003, "invalid_tail_samples": 22.7, "learning_rate": 1.393488524342445e-05, "loss": 0.0212, "positive_teacher_pairs": 27112.2, "relation_loss": 0.0019176918780431152, "selected_pairs": 27112.2, "step": 23060, "student_distance_mean": 1272.7790283203126, "teacher_distance_mean": 0.8522536396980286, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0019176918780431152, "weighted_relation_loss": 0.0019176918780431152 }, { "action_query_batch_std": 22.123388290405273, "action_query_norm": 938.1794189453125, "action_relation_loss": 0.0018303972436115145, "auxiliary_loss_weight": 1.0, "epoch": 21.580916744621142, "flow_matching_loss": 0.019671717286109926, "grad_norm": 0.0914139449596405, "invalid_tail_samples": 26.5, "learning_rate": 1.3896732932303486e-05, "loss": 0.0215, "positive_teacher_pairs": 26231.7, "relation_loss": 0.0018303972436115145, "selected_pairs": 26231.7, "step": 23070, "student_distance_mean": 1280.4453491210938, "teacher_distance_mean": 0.8577911078929901, "valid_action_samples": 229.5, "weighted_auxiliary_loss": 0.0018303972436115145, "weighted_relation_loss": 0.0018303972436115145 }, { "action_query_batch_std": 22.317103767395018, "action_query_norm": 946.4508544921875, "action_relation_loss": 0.0018897957750596106, "auxiliary_loss_weight": 1.0, "epoch": 21.590271281571564, "flow_matching_loss": 0.01738174054771662, "grad_norm": 0.11712466180324554, "invalid_tail_samples": 22.9, "learning_rate": 1.3858624490056304e-05, "loss": 0.0193, "positive_teacher_pairs": 27064.2, "relation_loss": 0.0018897957750596106, "selected_pairs": 27064.2, "step": 23080, "student_distance_mean": 1278.5284423828125, "teacher_distance_mean": 0.8555888950824737, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0018897957750596106, "weighted_relation_loss": 0.0018897957750596106 }, { "action_query_batch_std": 22.35606155395508, "action_query_norm": 945.6355163574219, "action_relation_loss": 0.0019029095768928529, "auxiliary_loss_weight": 1.0, "epoch": 21.599625818521982, "flow_matching_loss": 0.016767805255949498, "grad_norm": 0.09580551087856293, "invalid_tail_samples": 23.5, "learning_rate": 1.3820559962988299e-05, "loss": 0.0187, "positive_teacher_pairs": 26916.9, "relation_loss": 0.0019029095768928529, "selected_pairs": 26916.9, "step": 23090, "student_distance_mean": 1285.1463989257813, "teacher_distance_mean": 0.8593064248561859, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0019029095768928529, "weighted_relation_loss": 0.0019029095768928529 }, { "action_query_batch_std": 22.141687393188477, "action_query_norm": 939.0511596679687, "action_relation_loss": 0.0019800747162662447, "auxiliary_loss_weight": 1.0, "epoch": 21.608980355472404, "flow_matching_loss": 0.018545290175825357, "grad_norm": 0.106790691614151, "invalid_tail_samples": 24.8, "learning_rate": 1.3782539397351418e-05, "loss": 0.0205, "positive_teacher_pairs": 26618.8, "relation_loss": 0.0019800747162662447, "selected_pairs": 26618.8, "step": 23100, "student_distance_mean": 1273.68203125, "teacher_distance_mean": 0.8528796970844269, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0019800747162662447, "weighted_relation_loss": 0.0019800747162662447 }, { "action_query_batch_std": 22.31107063293457, "action_query_norm": 947.5544921875, "action_relation_loss": 0.001848907466046512, "auxiliary_loss_weight": 1.0, "epoch": 21.618334892422826, "flow_matching_loss": 0.018750933464616537, "grad_norm": 0.09318966418504715, "invalid_tail_samples": 21.8, "learning_rate": 1.3744562839344266e-05, "loss": 0.0206, "positive_teacher_pairs": 27317.3, "relation_loss": 0.001848907466046512, "selected_pairs": 27317.3, "step": 23110, "student_distance_mean": 1282.4603759765625, "teacher_distance_mean": 0.8571161389350891, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.001848907466046512, "weighted_relation_loss": 0.001848907466046512 }, { "action_query_batch_std": 22.217416954040527, "action_query_norm": 943.1967224121094, "action_relation_loss": 0.001879122096579522, "auxiliary_loss_weight": 1.0, "epoch": 21.627689429373245, "flow_matching_loss": 0.018541838694363832, "grad_norm": 0.08988306671380997, "invalid_tail_samples": 23.7, "learning_rate": 1.370663033511193e-05, "loss": 0.0204, "positive_teacher_pairs": 26872.3, "relation_loss": 0.001879122096579522, "selected_pairs": 26872.3, "step": 23120, "student_distance_mean": 1276.4067993164062, "teacher_distance_mean": 0.8523586332798004, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.001879122096579522, "weighted_relation_loss": 0.001879122096579522 }, { "action_query_batch_std": 22.274967002868653, "action_query_norm": 943.16015625, "action_relation_loss": 0.0018999954336322844, "auxiliary_loss_weight": 1.0, "epoch": 21.637043966323667, "flow_matching_loss": 0.018013288266956806, "grad_norm": 0.07783696800470352, "invalid_tail_samples": 23.2, "learning_rate": 1.3668741930745964e-05, "loss": 0.0199, "positive_teacher_pairs": 26998.6, "relation_loss": 0.0018999954336322844, "selected_pairs": 26998.6, "step": 23130, "student_distance_mean": 1279.4120239257813, "teacher_distance_mean": 0.8554975330829621, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0018999954336322844, "weighted_relation_loss": 0.0018999954336322844 }, { "action_query_batch_std": 22.2416353225708, "action_query_norm": 944.6770202636719, "action_relation_loss": 0.0019046868081204593, "auxiliary_loss_weight": 1.0, "epoch": 21.64639850327409, "flow_matching_loss": 0.01697738831862807, "grad_norm": 0.09098250418901443, "invalid_tail_samples": 23.5, "learning_rate": 1.3630897672284382e-05, "loss": 0.0189, "positive_teacher_pairs": 26917.9, "relation_loss": 0.0019046868081204593, "selected_pairs": 26917.9, "step": 23140, "student_distance_mean": 1278.023486328125, "teacher_distance_mean": 0.8544784009456634, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0019046868081204593, "weighted_relation_loss": 0.0019046868081204593 }, { "action_query_batch_std": 22.159375190734863, "action_query_norm": 942.5858947753907, "action_relation_loss": 0.001868525124154985, "auxiliary_loss_weight": 1.0, "epoch": 21.65575304022451, "flow_matching_loss": 0.016853239946067335, "grad_norm": 0.08528830856084824, "invalid_tail_samples": 26.9, "learning_rate": 1.3593097605711508e-05, "loss": 0.0187, "positive_teacher_pairs": 26144.3, "relation_loss": 0.001868525124154985, "selected_pairs": 26144.3, "step": 23150, "student_distance_mean": 1275.8884155273438, "teacher_distance_mean": 0.8533890604972839, "valid_action_samples": 229.1, "weighted_auxiliary_loss": 0.001868525124154985, "weighted_relation_loss": 0.001868525124154985 }, { "action_query_batch_std": 22.086765861511232, "action_query_norm": 939.9292602539062, "action_relation_loss": 0.0019524681381881237, "auxiliary_loss_weight": 1.0, "epoch": 21.66510757717493, "flow_matching_loss": 0.01883589746430516, "grad_norm": 0.08191444724798203, "invalid_tail_samples": 23.3, "learning_rate": 1.3555341776957992e-05, "loss": 0.0208, "positive_teacher_pairs": 26964.3, "relation_loss": 0.0019524681381881237, "selected_pairs": 26964.3, "step": 23160, "student_distance_mean": 1266.1895263671875, "teacher_distance_mean": 0.8463043570518494, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0019524681381881237, "weighted_relation_loss": 0.0019524681381881237 }, { "action_query_batch_std": 22.270207023620607, "action_query_norm": 945.0220031738281, "action_relation_loss": 0.0019315206329338253, "auxiliary_loss_weight": 1.0, "epoch": 21.67446211412535, "flow_matching_loss": 0.01733557917177677, "grad_norm": 0.08850011229515076, "invalid_tail_samples": 24.2, "learning_rate": 1.3517630231900724e-05, "loss": 0.0193, "positive_teacher_pairs": 26755.4, "relation_loss": 0.0019315206329338253, "selected_pairs": 26755.4, "step": 23170, "student_distance_mean": 1279.8324951171876, "teacher_distance_mean": 0.8562601506710052, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0019315206329338253, "weighted_relation_loss": 0.0019315206329338253 }, { "action_query_batch_std": 22.44996280670166, "action_query_norm": 953.2227355957032, "action_relation_loss": 0.001869243534747511, "auxiliary_loss_weight": 1.0, "epoch": 21.683816651075773, "flow_matching_loss": 0.01659094151109457, "grad_norm": 0.09272860735654831, "invalid_tail_samples": 24.0, "learning_rate": 1.3479963016362767e-05, "loss": 0.0185, "positive_teacher_pairs": 26801.5, "relation_loss": 0.001869243534747511, "selected_pairs": 26801.5, "step": 23180, "student_distance_mean": 1289.1750732421874, "teacher_distance_mean": 0.8620006740093231, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.001869243534747511, "weighted_relation_loss": 0.001869243534747511 }, { "action_query_batch_std": 22.258788681030275, "action_query_norm": 942.5167114257813, "action_relation_loss": 0.001920616952702403, "auxiliary_loss_weight": 1.0, "epoch": 21.69317118802619, "flow_matching_loss": 0.018057071045041083, "grad_norm": 0.0857718288898468, "invalid_tail_samples": 22.6, "learning_rate": 1.3442340176113377e-05, "loss": 0.02, "positive_teacher_pairs": 27126.0, "relation_loss": 0.001920616952702403, "selected_pairs": 27126.0, "step": 23190, "student_distance_mean": 1279.6048095703125, "teacher_distance_mean": 0.8556494593620301, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.001920616952702403, "weighted_relation_loss": 0.001920616952702403 }, { "action_query_batch_std": 22.07289218902588, "action_query_norm": 939.7807250976563, "action_relation_loss": 0.001984126341994852, "auxiliary_loss_weight": 1.0, "epoch": 21.702525724976613, "flow_matching_loss": 0.01896198224276304, "grad_norm": 0.08240851014852524, "invalid_tail_samples": 23.1, "learning_rate": 1.340476175686784e-05, "loss": 0.0209, "positive_teacher_pairs": 27014.2, "relation_loss": 0.001984126341994852, "selected_pairs": 27014.2, "step": 23200, "student_distance_mean": 1270.0599731445313, "teacher_distance_mean": 0.8509067952632904, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.001984126341994852, "weighted_relation_loss": 0.001984126341994852 }, { "action_query_batch_std": 22.23866214752197, "action_query_norm": 942.6987548828125, "action_relation_loss": 0.0019982643658295273, "auxiliary_loss_weight": 1.0, "epoch": 21.711880261927035, "flow_matching_loss": 0.018063855916261674, "grad_norm": 0.10895044356584549, "invalid_tail_samples": 24.2, "learning_rate": 1.3367227804287469e-05, "loss": 0.0201, "positive_teacher_pairs": 26758.7, "relation_loss": 0.0019982643658295273, "selected_pairs": 26758.7, "step": 23210, "student_distance_mean": 1282.9078491210937, "teacher_distance_mean": 0.8586019515991211, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0019982643658295273, "weighted_relation_loss": 0.0019982643658295273 }, { "action_query_batch_std": 22.550998878479003, "action_query_norm": 955.702734375, "action_relation_loss": 0.001904560870025307, "auxiliary_loss_weight": 1.0, "epoch": 21.721234798877454, "flow_matching_loss": 0.018295131158083677, "grad_norm": 0.09011593461036682, "invalid_tail_samples": 22.3, "learning_rate": 1.332973836397956e-05, "loss": 0.0202, "positive_teacher_pairs": 27199.2, "relation_loss": 0.001904560870025307, "selected_pairs": 27199.2, "step": 23220, "student_distance_mean": 1294.0942504882812, "teacher_distance_mean": 0.8661631107330322, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.001904560870025307, "weighted_relation_loss": 0.001904560870025307 }, { "action_query_batch_std": 22.140773582458497, "action_query_norm": 940.4457824707031, "action_relation_loss": 0.0019256467814557255, "auxiliary_loss_weight": 1.0, "epoch": 21.730589335827876, "flow_matching_loss": 0.018550913035869598, "grad_norm": 0.08527299761772156, "invalid_tail_samples": 22.1, "learning_rate": 1.329229348149731e-05, "loss": 0.0205, "positive_teacher_pairs": 27246.6, "relation_loss": 0.0019256467814557255, "selected_pairs": 27246.6, "step": 23230, "student_distance_mean": 1273.6721069335938, "teacher_distance_mean": 0.8508980929851532, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0019256467814557255, "weighted_relation_loss": 0.0019256467814557255 }, { "action_query_batch_std": 22.14676876068115, "action_query_norm": 939.3612976074219, "action_relation_loss": 0.00197994455229491, "auxiliary_loss_weight": 1.0, "epoch": 21.739943872778298, "flow_matching_loss": 0.017831495404243468, "grad_norm": 0.10573651641607285, "invalid_tail_samples": 22.9, "learning_rate": 1.3254893202339796e-05, "loss": 0.0198, "positive_teacher_pairs": 27058.4, "relation_loss": 0.00197994455229491, "selected_pairs": 27058.4, "step": 23240, "student_distance_mean": 1275.7391479492187, "teacher_distance_mean": 0.8535291910171509, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.00197994455229491, "weighted_relation_loss": 0.00197994455229491 }, { "action_query_batch_std": 22.024975395202638, "action_query_norm": 932.3148193359375, "action_relation_loss": 0.0019054479547776283, "auxiliary_loss_weight": 1.0, "epoch": 21.74929840972872, "flow_matching_loss": 0.018878530990332366, "grad_norm": 0.09720728546380997, "invalid_tail_samples": 24.8, "learning_rate": 1.3217537571951872e-05, "loss": 0.0208, "positive_teacher_pairs": 26618.5, "relation_loss": 0.0019054479547776283, "selected_pairs": 26618.5, "step": 23250, "student_distance_mean": 1267.3682373046875, "teacher_distance_mean": 0.8483159661293029, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0019054479547776283, "weighted_relation_loss": 0.0019054479547776283 }, { "action_query_batch_std": 22.403048706054687, "action_query_norm": 950.8052124023437, "action_relation_loss": 0.0018889385741204024, "auxiliary_loss_weight": 1.0, "epoch": 21.75865294667914, "flow_matching_loss": 0.017553178034722804, "grad_norm": 0.09551780670881271, "invalid_tail_samples": 24.3, "learning_rate": 1.3180226635724169e-05, "loss": 0.0194, "positive_teacher_pairs": 26738.3, "relation_loss": 0.0018889385741204024, "selected_pairs": 26738.3, "step": 23260, "student_distance_mean": 1286.3943725585937, "teacher_distance_mean": 0.8605891466140747, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0018889385741204024, "weighted_relation_loss": 0.0018889385741204024 }, { "action_query_batch_std": 22.430231666564943, "action_query_norm": 949.3279113769531, "action_relation_loss": 0.0019025744870305062, "auxiliary_loss_weight": 1.0, "epoch": 21.76800748362956, "flow_matching_loss": 0.01810723338276148, "grad_norm": 0.10011479258537292, "invalid_tail_samples": 21.7, "learning_rate": 1.314296043899298e-05, "loss": 0.02, "positive_teacher_pairs": 27341.7, "relation_loss": 0.0019025744870305062, "selected_pairs": 27341.7, "step": 23270, "student_distance_mean": 1286.9553833007812, "teacher_distance_mean": 0.8613059461116791, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.0019025744870305062, "weighted_relation_loss": 0.0019025744870305062 }, { "action_query_batch_std": 22.40211772918701, "action_query_norm": 949.186962890625, "action_relation_loss": 0.0019433531910181046, "auxiliary_loss_weight": 1.0, "epoch": 21.777362020579982, "flow_matching_loss": 0.017675197031348944, "grad_norm": 0.10054313391447067, "invalid_tail_samples": 23.2, "learning_rate": 1.3105739027040248e-05, "loss": 0.0196, "positive_teacher_pairs": 26989.5, "relation_loss": 0.0019433531910181046, "selected_pairs": 26989.5, "step": 23280, "student_distance_mean": 1285.163330078125, "teacher_distance_mean": 0.8602680206298828, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0019433531910181046, "weighted_relation_loss": 0.0019433531910181046 }, { "action_query_batch_std": 22.181264305114745, "action_query_norm": 942.9048217773437, "action_relation_loss": 0.0018859678297303618, "auxiliary_loss_weight": 1.0, "epoch": 21.7867165575304, "flow_matching_loss": 0.01750590279698372, "grad_norm": 0.09389296919107437, "invalid_tail_samples": 25.4, "learning_rate": 1.3068562445093491e-05, "loss": 0.0194, "positive_teacher_pairs": 26484.2, "relation_loss": 0.0018859678297303618, "selected_pairs": 26484.2, "step": 23290, "student_distance_mean": 1278.9259765625, "teacher_distance_mean": 0.8554937720298768, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.0018859678297303618, "weighted_relation_loss": 0.0018859678297303618 }, { "action_query_batch_std": 22.568489456176756, "action_query_norm": 956.1626342773437, "action_relation_loss": 0.0018960912711918354, "auxiliary_loss_weight": 1.0, "epoch": 21.796071094480823, "flow_matching_loss": 0.018735936377197504, "grad_norm": 0.09046823531389236, "invalid_tail_samples": 24.3, "learning_rate": 1.3031430738325778e-05, "loss": 0.0206, "positive_teacher_pairs": 26737.0, "relation_loss": 0.0018960912711918354, "selected_pairs": 26737.0, "step": 23300, "student_distance_mean": 1298.5425903320313, "teacher_distance_mean": 0.8681683242321014, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0018960912711918354, "weighted_relation_loss": 0.0018960912711918354 }, { "action_query_batch_std": 22.12491397857666, "action_query_norm": 939.0250732421875, "action_relation_loss": 0.001922078465577215, "auxiliary_loss_weight": 1.0, "epoch": 21.805425631431245, "flow_matching_loss": 0.01739031421020627, "grad_norm": 0.1054985448718071, "invalid_tail_samples": 25.9, "learning_rate": 1.299434395185563e-05, "loss": 0.0193, "positive_teacher_pairs": 26374.4, "relation_loss": 0.001922078465577215, "selected_pairs": 26374.4, "step": 23310, "student_distance_mean": 1278.2406005859375, "teacher_distance_mean": 0.8547684967517852, "valid_action_samples": 230.1, "weighted_auxiliary_loss": 0.001922078465577215, "weighted_relation_loss": 0.001922078465577215 }, { "action_query_batch_std": 22.111947059631348, "action_query_norm": 939.8976013183594, "action_relation_loss": 0.0019217662513256073, "auxiliary_loss_weight": 1.0, "epoch": 21.814780168381667, "flow_matching_loss": 0.016713535599410533, "grad_norm": 0.07436733692884445, "invalid_tail_samples": 24.2, "learning_rate": 1.295730213074699e-05, "loss": 0.0186, "positive_teacher_pairs": 26757.3, "relation_loss": 0.0019217662513256073, "selected_pairs": 26757.3, "step": 23320, "student_distance_mean": 1271.8947509765626, "teacher_distance_mean": 0.8511657953262329, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0019217662513256073, "weighted_relation_loss": 0.0019217662513256073 }, { "action_query_batch_std": 22.444906616210936, "action_query_norm": 949.9570373535156, "action_relation_loss": 0.0019076998578384519, "auxiliary_loss_weight": 1.0, "epoch": 21.824134705332085, "flow_matching_loss": 0.017678228300064804, "grad_norm": 0.08715120702981949, "invalid_tail_samples": 25.0, "learning_rate": 1.2920305320009152e-05, "loss": 0.0196, "positive_teacher_pairs": 26567.8, "relation_loss": 0.0019076998578384519, "selected_pairs": 26567.8, "step": 23330, "student_distance_mean": 1290.9330200195313, "teacher_distance_mean": 0.8628508269786834, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0019076998578384519, "weighted_relation_loss": 0.0019076998578384519 }, { "action_query_batch_std": 22.093133544921876, "action_query_norm": 939.1713745117188, "action_relation_loss": 0.001973096572328359, "auxiliary_loss_weight": 1.0, "epoch": 21.833489242282507, "flow_matching_loss": 0.017155379801988602, "grad_norm": 0.08777730166912079, "invalid_tail_samples": 23.5, "learning_rate": 1.2883353564596729e-05, "loss": 0.0191, "positive_teacher_pairs": 26917.6, "relation_loss": 0.001973096572328359, "selected_pairs": 26917.6, "step": 23340, "student_distance_mean": 1269.7228515625, "teacher_distance_mean": 0.8484084844589234, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.001973096572328359, "weighted_relation_loss": 0.001973096572328359 }, { "action_query_batch_std": 22.1094482421875, "action_query_norm": 940.6966247558594, "action_relation_loss": 0.0019217644585296512, "auxiliary_loss_weight": 1.0, "epoch": 21.84284377923293, "flow_matching_loss": 0.019080048147588968, "grad_norm": 0.08947362750768661, "invalid_tail_samples": 24.0, "learning_rate": 1.2846446909409604e-05, "loss": 0.021, "positive_teacher_pairs": 26803.6, "relation_loss": 0.0019217644585296512, "selected_pairs": 26803.6, "step": 23350, "student_distance_mean": 1275.34599609375, "teacher_distance_mean": 0.8523203790187835, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0019217644585296512, "weighted_relation_loss": 0.0019217644585296512 }, { "action_query_batch_std": 22.417426681518556, "action_query_norm": 951.3415466308594, "action_relation_loss": 0.0018622936680912972, "auxiliary_loss_weight": 1.0, "epoch": 21.852198316183348, "flow_matching_loss": 0.01745161823928356, "grad_norm": 0.07974876463413239, "invalid_tail_samples": 24.8, "learning_rate": 1.280958539929284e-05, "loss": 0.0193, "positive_teacher_pairs": 26615.1, "relation_loss": 0.0018622936680912972, "selected_pairs": 26615.1, "step": 23360, "student_distance_mean": 1294.4359619140625, "teacher_distance_mean": 0.8622651517391204, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0018622936680912972, "weighted_relation_loss": 0.0018622936680912972 }, { "action_query_batch_std": 22.43687915802002, "action_query_norm": 948.7642456054688, "action_relation_loss": 0.0019122123485431075, "auxiliary_loss_weight": 1.0, "epoch": 21.86155285313377, "flow_matching_loss": 0.01718152277171612, "grad_norm": 0.08607176691293716, "invalid_tail_samples": 23.7, "learning_rate": 1.277276907903664e-05, "loss": 0.0191, "positive_teacher_pairs": 26872.7, "relation_loss": 0.0019122123485431075, "selected_pairs": 26872.7, "step": 23370, "student_distance_mean": 1289.4549194335937, "teacher_distance_mean": 0.8617159605026246, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0019122123485431075, "weighted_relation_loss": 0.0019122123485431075 }, { "action_query_batch_std": 22.038347816467287, "action_query_norm": 936.0381530761719, "action_relation_loss": 0.0018800231628119946, "auxiliary_loss_weight": 1.0, "epoch": 21.87090739008419, "flow_matching_loss": 0.01866087792441249, "grad_norm": 0.07957293093204498, "invalid_tail_samples": 25.2, "learning_rate": 1.2735997993376298e-05, "loss": 0.0205, "positive_teacher_pairs": 26530.6, "relation_loss": 0.0018800231628119946, "selected_pairs": 26530.6, "step": 23380, "student_distance_mean": 1268.6788696289063, "teacher_distance_mean": 0.8470286905765534, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0018800231628119946, "weighted_relation_loss": 0.0018800231628119946 }, { "action_query_batch_std": 22.34163875579834, "action_query_norm": 946.6263244628906, "action_relation_loss": 0.0018625868717208505, "auxiliary_loss_weight": 1.0, "epoch": 21.880261927034613, "flow_matching_loss": 0.017186270281672477, "grad_norm": 0.06877579540014267, "invalid_tail_samples": 24.0, "learning_rate": 1.2699272186992166e-05, "loss": 0.019, "positive_teacher_pairs": 26803.8, "relation_loss": 0.0018625868717208505, "selected_pairs": 26803.8, "step": 23390, "student_distance_mean": 1287.9130859375, "teacher_distance_mean": 0.8611633896827697, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0018625868717208505, "weighted_relation_loss": 0.0018625868717208505 }, { "action_query_batch_std": 22.26778202056885, "action_query_norm": 946.5037109375, "action_relation_loss": 0.0019497606204822659, "auxiliary_loss_weight": 1.0, "epoch": 21.889616463985032, "flow_matching_loss": 0.016561306733638047, "grad_norm": 0.09994830936193466, "invalid_tail_samples": 25.2, "learning_rate": 1.2662591704509547e-05, "loss": 0.0185, "positive_teacher_pairs": 26523.3, "relation_loss": 0.0019497606204822659, "selected_pairs": 26523.3, "step": 23400, "student_distance_mean": 1286.35576171875, "teacher_distance_mean": 0.8606972992420197, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0019497606204822659, "weighted_relation_loss": 0.0019497606204822659 }, { "action_query_batch_std": 22.050317764282227, "action_query_norm": 937.5409240722656, "action_relation_loss": 0.0018761885119602084, "auxiliary_loss_weight": 1.0, "epoch": 21.898971000935454, "flow_matching_loss": 0.019280481897294522, "grad_norm": 0.09664443135261536, "invalid_tail_samples": 25.3, "learning_rate": 1.2625956590498711e-05, "loss": 0.0212, "positive_teacher_pairs": 26500.1, "relation_loss": 0.0018761885119602084, "selected_pairs": 26500.1, "step": 23410, "student_distance_mean": 1269.66064453125, "teacher_distance_mean": 0.8516542434692382, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0018761885119602084, "weighted_relation_loss": 0.0018761885119602084 }, { "action_query_batch_std": 22.325354385375977, "action_query_norm": 946.101611328125, "action_relation_loss": 0.0018917127978056668, "auxiliary_loss_weight": 1.0, "epoch": 21.908325537885876, "flow_matching_loss": 0.016744655277580022, "grad_norm": 0.09255236387252808, "invalid_tail_samples": 23.4, "learning_rate": 1.2589366889474757e-05, "loss": 0.0186, "positive_teacher_pairs": 26940.0, "relation_loss": 0.0018917127978056668, "selected_pairs": 26940.0, "step": 23420, "student_distance_mean": 1285.2772583007813, "teacher_distance_mean": 0.8606866657733917, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0018917127978056668, "weighted_relation_loss": 0.0018917127978056668 }, { "action_query_batch_std": 22.39577159881592, "action_query_norm": 949.4722473144532, "action_relation_loss": 0.00186050123302266, "auxiliary_loss_weight": 1.0, "epoch": 21.917680074836294, "flow_matching_loss": 0.01821424616500735, "grad_norm": 0.08635302633047104, "invalid_tail_samples": 22.4, "learning_rate": 1.2552822645897621e-05, "loss": 0.0201, "positive_teacher_pairs": 27174.7, "relation_loss": 0.00186050123302266, "selected_pairs": 27174.7, "step": 23430, "student_distance_mean": 1285.4473999023437, "teacher_distance_mean": 0.8617683351039886, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.00186050123302266, "weighted_relation_loss": 0.00186050123302266 }, { "action_query_batch_std": 22.29349727630615, "action_query_norm": 945.3050537109375, "action_relation_loss": 0.0018684933427721262, "auxiliary_loss_weight": 1.0, "epoch": 21.927034611786716, "flow_matching_loss": 0.01809295518323779, "grad_norm": 0.10968060791492462, "invalid_tail_samples": 21.8, "learning_rate": 1.2516323904172e-05, "loss": 0.02, "positive_teacher_pairs": 27317.0, "relation_loss": 0.0018684933427721262, "selected_pairs": 27317.0, "step": 23440, "student_distance_mean": 1278.868701171875, "teacher_distance_mean": 0.8581844627857208, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.0018684933427721262, "weighted_relation_loss": 0.0018684933427721262 }, { "action_query_batch_std": 22.106142044067383, "action_query_norm": 938.0364685058594, "action_relation_loss": 0.0018868276965804398, "auxiliary_loss_weight": 1.0, "epoch": 21.93638914873714, "flow_matching_loss": 0.018443734850734472, "grad_norm": 0.0930594727396965, "invalid_tail_samples": 22.1, "learning_rate": 1.2479870708647324e-05, "loss": 0.0203, "positive_teacher_pairs": 27244.7, "relation_loss": 0.0018868276965804398, "selected_pairs": 27244.7, "step": 23450, "student_distance_mean": 1267.0421508789063, "teacher_distance_mean": 0.8488706409931183, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0018868276965804398, "weighted_relation_loss": 0.0018868276965804398 }, { "action_query_batch_std": 21.925830459594728, "action_query_norm": 933.6350158691406, "action_relation_loss": 0.0019484811928123236, "auxiliary_loss_weight": 1.0, "epoch": 21.94574368568756, "flow_matching_loss": 0.017795476876199246, "grad_norm": 0.07958007603883743, "invalid_tail_samples": 23.0, "learning_rate": 1.2443463103617658e-05, "loss": 0.0197, "positive_teacher_pairs": 27040.2, "relation_loss": 0.0019484811928123236, "selected_pairs": 27040.2, "step": 23460, "student_distance_mean": 1262.06650390625, "teacher_distance_mean": 0.8469535052776337, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0019484811928123236, "weighted_relation_loss": 0.0019484811928123236 }, { "action_query_batch_std": 22.18797912597656, "action_query_norm": 941.0810363769531, "action_relation_loss": 0.001860541058704257, "auxiliary_loss_weight": 1.0, "epoch": 21.95509822263798, "flow_matching_loss": 0.016189327090978624, "grad_norm": 0.0846407413482666, "invalid_tail_samples": 24.6, "learning_rate": 1.240710113332167e-05, "loss": 0.018, "positive_teacher_pairs": 26668.8, "relation_loss": 0.001860541058704257, "selected_pairs": 26668.8, "step": 23470, "student_distance_mean": 1281.5281127929688, "teacher_distance_mean": 0.8579237222671509, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.001860541058704257, "weighted_relation_loss": 0.001860541058704257 }, { "action_query_batch_std": 22.320803260803224, "action_query_norm": 946.8110046386719, "action_relation_loss": 0.0019473031861707568, "auxiliary_loss_weight": 1.0, "epoch": 21.9644527595884, "flow_matching_loss": 0.01800492275506258, "grad_norm": 0.09603564441204071, "invalid_tail_samples": 22.4, "learning_rate": 1.2370784841942584e-05, "loss": 0.02, "positive_teacher_pairs": 27175.5, "relation_loss": 0.0019473031861707568, "selected_pairs": 27175.5, "step": 23480, "student_distance_mean": 1276.0748168945313, "teacher_distance_mean": 0.8549975335597992, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.0019473031861707568, "weighted_relation_loss": 0.0019473031861707568 }, { "action_query_batch_std": 22.21295738220215, "action_query_norm": 942.1690551757813, "action_relation_loss": 0.0019658821751363576, "auxiliary_loss_weight": 1.0, "epoch": 21.973807296538823, "flow_matching_loss": 0.01779426299035549, "grad_norm": 0.10343004763126373, "invalid_tail_samples": 25.6, "learning_rate": 1.2334514273608117e-05, "loss": 0.0198, "positive_teacher_pairs": 26445.2, "relation_loss": 0.0019658821751363576, "selected_pairs": 26445.2, "step": 23490, "student_distance_mean": 1273.8203247070312, "teacher_distance_mean": 0.8546140730381012, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.0019658821751363576, "weighted_relation_loss": 0.0019658821751363576 }, { "action_query_batch_std": 21.97128849029541, "action_query_norm": 933.8013916015625, "action_relation_loss": 0.002028863015584648, "auxiliary_loss_weight": 1.0, "epoch": 21.98316183348924, "flow_matching_loss": 0.018298844061791896, "grad_norm": 0.09052915126085281, "invalid_tail_samples": 23.7, "learning_rate": 1.2298289472390417e-05, "loss": 0.0203, "positive_teacher_pairs": 26881.2, "relation_loss": 0.002028863015584648, "selected_pairs": 26881.2, "step": 23500, "student_distance_mean": 1263.2542846679687, "teacher_distance_mean": 0.8471233963966369, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.002028863015584648, "weighted_relation_loss": 0.002028863015584648 }, { "action_query_batch_std": 22.172669982910158, "action_query_norm": 943.3122985839843, "action_relation_loss": 0.001962123066186905, "auxiliary_loss_weight": 1.0, "epoch": 21.992516370439663, "flow_matching_loss": 0.017860955093055964, "grad_norm": 0.10995017737150192, "invalid_tail_samples": 21.2, "learning_rate": 1.226211048230606e-05, "loss": 0.0198, "positive_teacher_pairs": 27470.3, "relation_loss": 0.001962123066186905, "selected_pairs": 27470.3, "step": 23510, "student_distance_mean": 1271.4690795898437, "teacher_distance_mean": 0.8514962911605835, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.001962123066186905, "weighted_relation_loss": 0.001962123066186905 }, { "action_query_batch_std": 22.115260314941406, "action_query_norm": 939.5091369628906, "action_relation_loss": 0.0019392229965887963, "auxiliary_loss_weight": 1.0, "epoch": 22.001870907390085, "flow_matching_loss": 0.016178732551634312, "grad_norm": 0.09575486928224564, "invalid_tail_samples": 22.8, "learning_rate": 1.2225977347315921e-05, "loss": 0.0181, "positive_teacher_pairs": 24058.7, "relation_loss": 0.0019392229965887963, "selected_pairs": 24058.7, "step": 23520, "student_distance_mean": 1266.520068359375, "teacher_distance_mean": 0.8477723836898804, "valid_action_samples": 213.3, "weighted_auxiliary_loss": 0.0019392229965887963, "weighted_relation_loss": 0.0019392229965887963 }, { "action_query_batch_std": 22.010629081726073, "action_query_norm": 936.4859985351562, "action_relation_loss": 0.0018892479361966251, "auxiliary_loss_weight": 1.0, "epoch": 22.011225444340504, "flow_matching_loss": 0.018387025222182274, "grad_norm": 0.09047640860080719, "invalid_tail_samples": 28.0, "learning_rate": 1.2189890111325148e-05, "loss": 0.0203, "positive_teacher_pairs": 25891.5, "relation_loss": 0.0018892479361966251, "selected_pairs": 25891.5, "step": 23530, "student_distance_mean": 1269.0130859375, "teacher_distance_mean": 0.85164195895195, "valid_action_samples": 228.0, "weighted_auxiliary_loss": 0.0018892479361966251, "weighted_relation_loss": 0.0018892479361966251 }, { "action_query_batch_std": 21.96222553253174, "action_query_norm": 934.9270385742187, "action_relation_loss": 0.0017871280666440724, "auxiliary_loss_weight": 1.0, "epoch": 22.020579981290926, "flow_matching_loss": 0.01821801355108619, "grad_norm": 0.09581871330738068, "invalid_tail_samples": 27.1, "learning_rate": 1.2153848818183161e-05, "loss": 0.02, "positive_teacher_pairs": 26090.6, "relation_loss": 0.0017871280666440724, "selected_pairs": 26090.6, "step": 23540, "student_distance_mean": 1269.0556518554688, "teacher_distance_mean": 0.8503153681755066, "valid_action_samples": 228.9, "weighted_auxiliary_loss": 0.0017871280666440724, "weighted_relation_loss": 0.0017871280666440724 }, { "action_query_batch_std": 22.530129623413085, "action_query_norm": 953.1419250488282, "action_relation_loss": 0.0018051668419502675, "auxiliary_loss_weight": 1.0, "epoch": 22.029934518241348, "flow_matching_loss": 0.01708598555997014, "grad_norm": 0.1079859584569931, "invalid_tail_samples": 23.7, "learning_rate": 1.2117853511683507e-05, "loss": 0.0189, "positive_teacher_pairs": 26874.1, "relation_loss": 0.0018051668419502675, "selected_pairs": 26874.1, "step": 23550, "student_distance_mean": 1286.5053100585938, "teacher_distance_mean": 0.8596763372421264, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0018051668419502675, "weighted_relation_loss": 0.0018051668419502675 }, { "action_query_batch_std": 22.349189949035644, "action_query_norm": 949.3794555664062, "action_relation_loss": 0.0018792880116961896, "auxiliary_loss_weight": 1.0, "epoch": 22.03928905519177, "flow_matching_loss": 0.01646581953391433, "grad_norm": 0.07623400539159775, "invalid_tail_samples": 21.7, "learning_rate": 1.2081904235563906e-05, "loss": 0.0183, "positive_teacher_pairs": 27342.8, "relation_loss": 0.0018792880116961896, "selected_pairs": 27342.8, "step": 23560, "student_distance_mean": 1286.1970825195312, "teacher_distance_mean": 0.8590806543827056, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.0018792880116961896, "weighted_relation_loss": 0.0018792880116961896 }, { "action_query_batch_std": 22.175822257995605, "action_query_norm": 942.8071960449219, "action_relation_loss": 0.0018405603594146668, "auxiliary_loss_weight": 1.0, "epoch": 22.048643592142188, "flow_matching_loss": 0.017146931029856205, "grad_norm": 0.07618595659732819, "invalid_tail_samples": 24.1, "learning_rate": 1.20460010335061e-05, "loss": 0.019, "positive_teacher_pairs": 26782.3, "relation_loss": 0.0018405603594146668, "selected_pairs": 26782.3, "step": 23570, "student_distance_mean": 1273.398779296875, "teacher_distance_mean": 0.8512828946113586, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0018405603594146668, "weighted_relation_loss": 0.0018405603594146668 }, { "action_query_batch_std": 22.434873008728026, "action_query_norm": 952.7062683105469, "action_relation_loss": 0.0018760907929390668, "auxiliary_loss_weight": 1.0, "epoch": 22.05799812909261, "flow_matching_loss": 0.017127082217484713, "grad_norm": 0.10061272233724594, "invalid_tail_samples": 25.1, "learning_rate": 1.2010143949135865e-05, "loss": 0.019, "positive_teacher_pairs": 26564.5, "relation_loss": 0.0018760907929390668, "selected_pairs": 26564.5, "step": 23580, "student_distance_mean": 1293.792529296875, "teacher_distance_mean": 0.8636395275592804, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0018760907929390668, "weighted_relation_loss": 0.0018760907929390668 }, { "action_query_batch_std": 22.6886775970459, "action_query_norm": 960.726318359375, "action_relation_loss": 0.0018519000383093952, "auxiliary_loss_weight": 1.0, "epoch": 22.067352666043032, "flow_matching_loss": 0.017480016965419055, "grad_norm": 0.10096344351768494, "invalid_tail_samples": 21.2, "learning_rate": 1.1974333026022938e-05, "loss": 0.0193, "positive_teacher_pairs": 27461.7, "relation_loss": 0.0018519000383093952, "selected_pairs": 27461.7, "step": 23590, "student_distance_mean": 1303.72431640625, "teacher_distance_mean": 0.8694544672966004, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.0018519000383093952, "weighted_relation_loss": 0.0018519000383093952 }, { "action_query_batch_std": 22.391575431823732, "action_query_norm": 950.5832824707031, "action_relation_loss": 0.001825925800949335, "auxiliary_loss_weight": 1.0, "epoch": 22.07670720299345, "flow_matching_loss": 0.018595483154058456, "grad_norm": 0.11342426389455795, "invalid_tail_samples": 22.4, "learning_rate": 1.1938568307680964e-05, "loss": 0.0204, "positive_teacher_pairs": 27181.0, "relation_loss": 0.001825925800949335, "selected_pairs": 27181.0, "step": 23600, "student_distance_mean": 1282.5377075195313, "teacher_distance_mean": 0.8568421840667725, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.001825925800949335, "weighted_relation_loss": 0.001825925800949335 }, { "action_query_batch_std": 22.371949768066408, "action_query_norm": 946.326220703125, "action_relation_loss": 0.0018864886951632798, "auxiliary_loss_weight": 1.0, "epoch": 22.086061739943872, "flow_matching_loss": 0.0168945481069386, "grad_norm": 0.08391274511814117, "invalid_tail_samples": 24.6, "learning_rate": 1.1902849837567464e-05, "loss": 0.0188, "positive_teacher_pairs": 26660.5, "relation_loss": 0.0018864886951632798, "selected_pairs": 26660.5, "step": 23610, "student_distance_mean": 1289.8650024414062, "teacher_distance_mean": 0.8624653458595276, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0018864886951632798, "weighted_relation_loss": 0.0018864886951632798 }, { "action_query_batch_std": 22.17430763244629, "action_query_norm": 938.6895141601562, "action_relation_loss": 0.0019245813367888332, "auxiliary_loss_weight": 1.0, "epoch": 22.095416276894294, "flow_matching_loss": 0.017500998824834822, "grad_norm": 0.09778256714344025, "invalid_tail_samples": 25.0, "learning_rate": 1.1867177659083739e-05, "loss": 0.0194, "positive_teacher_pairs": 26571.1, "relation_loss": 0.0019245813367888332, "selected_pairs": 26571.1, "step": 23620, "student_distance_mean": 1274.856005859375, "teacher_distance_mean": 0.852611380815506, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0019245813367888332, "weighted_relation_loss": 0.0019245813367888332 }, { "action_query_batch_std": 22.21619243621826, "action_query_norm": 945.3793762207031, "action_relation_loss": 0.0018864296143874526, "auxiliary_loss_weight": 1.0, "epoch": 22.104770813844716, "flow_matching_loss": 0.01833817195147276, "grad_norm": 0.12451442331075668, "invalid_tail_samples": 20.0, "learning_rate": 1.1831551815574848e-05, "loss": 0.0202, "positive_teacher_pairs": 27736.0, "relation_loss": 0.0018864296143874526, "selected_pairs": 27736.0, "step": 23630, "student_distance_mean": 1276.4900146484374, "teacher_distance_mean": 0.8554836869239807, "valid_action_samples": 236.0, "weighted_auxiliary_loss": 0.0018864296143874526, "weighted_relation_loss": 0.0018864296143874526 }, { "action_query_batch_std": 22.183524703979494, "action_query_norm": 942.8824462890625, "action_relation_loss": 0.0019055590149946512, "auxiliary_loss_weight": 1.0, "epoch": 22.114125350795135, "flow_matching_loss": 0.01797236194834113, "grad_norm": 0.11000411957502365, "invalid_tail_samples": 25.0, "learning_rate": 1.1795972350329554e-05, "loss": 0.0199, "positive_teacher_pairs": 26579.5, "relation_loss": 0.0019055590149946512, "selected_pairs": 26579.5, "step": 23640, "student_distance_mean": 1274.3007934570312, "teacher_distance_mean": 0.853944593667984, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0019055590149946512, "weighted_relation_loss": 0.0019055590149946512 }, { "action_query_batch_std": 21.95078945159912, "action_query_norm": 934.1998596191406, "action_relation_loss": 0.0019156526308506728, "auxiliary_loss_weight": 1.0, "epoch": 22.123479887745557, "flow_matching_loss": 0.017663555406033992, "grad_norm": 0.09756153076887131, "invalid_tail_samples": 23.3, "learning_rate": 1.176043930658024e-05, "loss": 0.0196, "positive_teacher_pairs": 26965.6, "relation_loss": 0.0019156526308506728, "selected_pairs": 26965.6, "step": 23650, "student_distance_mean": 1264.8275756835938, "teacher_distance_mean": 0.84664067029953, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0019156526308506728, "weighted_relation_loss": 0.0019156526308506728 }, { "action_query_batch_std": 22.134899520874022, "action_query_norm": 941.5468627929688, "action_relation_loss": 0.0018721093190833926, "auxiliary_loss_weight": 1.0, "epoch": 22.13283442469598, "flow_matching_loss": 0.0170493233948946, "grad_norm": 0.08321863412857056, "invalid_tail_samples": 24.6, "learning_rate": 1.1724952727502942e-05, "loss": 0.0189, "positive_teacher_pairs": 26669.5, "relation_loss": 0.0018721093190833926, "selected_pairs": 26669.5, "step": 23660, "student_distance_mean": 1277.1747192382813, "teacher_distance_mean": 0.8559212267398835, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0018721093190833926, "weighted_relation_loss": 0.0018721093190833926 }, { "action_query_batch_std": 22.249623489379882, "action_query_norm": 943.4426391601562, "action_relation_loss": 0.0018368356046266853, "auxiliary_loss_weight": 1.0, "epoch": 22.142188961646397, "flow_matching_loss": 0.017536814138293267, "grad_norm": 0.1065530925989151, "invalid_tail_samples": 23.4, "learning_rate": 1.1689512656217178e-05, "loss": 0.0194, "positive_teacher_pairs": 26948.6, "relation_loss": 0.0018368356046266853, "selected_pairs": 26948.6, "step": 23670, "student_distance_mean": 1277.57001953125, "teacher_distance_mean": 0.8560546994209289, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0018368356046266853, "weighted_relation_loss": 0.0018368356046266853 }, { "action_query_batch_std": 22.180420112609863, "action_query_norm": 942.4885070800781, "action_relation_loss": 0.0017924942425452174, "auxiliary_loss_weight": 1.0, "epoch": 22.15154349859682, "flow_matching_loss": 0.01782900160178542, "grad_norm": 0.08411131799221039, "invalid_tail_samples": 25.1, "learning_rate": 1.1654119135785962e-05, "loss": 0.0196, "positive_teacher_pairs": 26555.9, "relation_loss": 0.0017924942425452174, "selected_pairs": 26555.9, "step": 23680, "student_distance_mean": 1278.5947387695312, "teacher_distance_mean": 0.8550256669521332, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0017924942425452174, "weighted_relation_loss": 0.0017924942425452174 }, { "action_query_batch_std": 22.039714431762697, "action_query_norm": 937.1269653320312, "action_relation_loss": 0.0018668889068067073, "auxiliary_loss_weight": 1.0, "epoch": 22.16089803554724, "flow_matching_loss": 0.017393996380269526, "grad_norm": 0.10070561617612839, "invalid_tail_samples": 23.1, "learning_rate": 1.1618772209215794e-05, "loss": 0.0193, "positive_teacher_pairs": 27019.2, "relation_loss": 0.0018668889068067073, "selected_pairs": 27019.2, "step": 23690, "student_distance_mean": 1266.1863403320312, "teacher_distance_mean": 0.8487030029296875, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0018668889068067073, "weighted_relation_loss": 0.0018668889068067073 }, { "action_query_batch_std": 22.165472793579102, "action_query_norm": 939.8462036132812, "action_relation_loss": 0.0018571870285086333, "auxiliary_loss_weight": 1.0, "epoch": 22.170252572497663, "flow_matching_loss": 0.016966107487678527, "grad_norm": 0.08395359665155411, "invalid_tail_samples": 22.6, "learning_rate": 1.1583471919456506e-05, "loss": 0.0188, "positive_teacher_pairs": 27126.0, "relation_loss": 0.0018571870285086333, "selected_pairs": 27126.0, "step": 23700, "student_distance_mean": 1272.2674560546875, "teacher_distance_mean": 0.8545035779476166, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0018571870285086333, "weighted_relation_loss": 0.0018571870285086333 }, { "action_query_batch_std": 22.027366638183594, "action_query_norm": 934.6633117675781, "action_relation_loss": 0.0018418364226818085, "auxiliary_loss_weight": 1.0, "epoch": 22.17960710944808, "flow_matching_loss": 0.016745060589164494, "grad_norm": 0.09941799193620682, "invalid_tail_samples": 25.4, "learning_rate": 1.1548218309401266e-05, "loss": 0.0186, "positive_teacher_pairs": 26476.7, "relation_loss": 0.0018418364226818085, "selected_pairs": 26476.7, "step": 23710, "student_distance_mean": 1261.2072875976562, "teacher_distance_mean": 0.846165931224823, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.0018418364226818085, "weighted_relation_loss": 0.0018418364226818085 }, { "action_query_batch_std": 22.207390975952148, "action_query_norm": 940.3536682128906, "action_relation_loss": 0.001865271886344999, "auxiliary_loss_weight": 1.0, "epoch": 22.188961646398504, "flow_matching_loss": 0.017298252508044242, "grad_norm": 0.10154519230127335, "invalid_tail_samples": 25.1, "learning_rate": 1.1513011421886555e-05, "loss": 0.0192, "positive_teacher_pairs": 26556.4, "relation_loss": 0.001865271886344999, "selected_pairs": 26556.4, "step": 23720, "student_distance_mean": 1275.9994750976562, "teacher_distance_mean": 0.8566198825836182, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.001865271886344999, "weighted_relation_loss": 0.001865271886344999 }, { "action_query_batch_std": 22.20262794494629, "action_query_norm": 939.3975769042969, "action_relation_loss": 0.0018562474171631039, "auxiliary_loss_weight": 1.0, "epoch": 22.198316183348926, "flow_matching_loss": 0.015611274912953377, "grad_norm": 0.09332463890314102, "invalid_tail_samples": 21.8, "learning_rate": 1.1477851299692056e-05, "loss": 0.0175, "positive_teacher_pairs": 27320.2, "relation_loss": 0.0018562474171631039, "selected_pairs": 27320.2, "step": 23730, "student_distance_mean": 1270.9905639648437, "teacher_distance_mean": 0.8551732838153839, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.0018562474171631039, "weighted_relation_loss": 0.0018562474171631039 }, { "action_query_batch_std": 22.08846378326416, "action_query_norm": 938.4248901367188, "action_relation_loss": 0.0019738144241273404, "auxiliary_loss_weight": 1.0, "epoch": 22.207670720299344, "flow_matching_loss": 0.016544748935848473, "grad_norm": 0.10379493981599808, "invalid_tail_samples": 21.9, "learning_rate": 1.144273798554063e-05, "loss": 0.0185, "positive_teacher_pairs": 27289.5, "relation_loss": 0.0019738144241273404, "selected_pairs": 27289.5, "step": 23740, "student_distance_mean": 1268.196875, "teacher_distance_mean": 0.8521166265010833, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.0019738144241273404, "weighted_relation_loss": 0.0019738144241273404 }, { "action_query_batch_std": 22.3575647354126, "action_query_norm": 943.6672973632812, "action_relation_loss": 0.0019154833280481398, "auxiliary_loss_weight": 1.0, "epoch": 22.217025257249766, "flow_matching_loss": 0.01679798373952508, "grad_norm": 0.07037226855754852, "invalid_tail_samples": 23.8, "learning_rate": 1.1407671522098262e-05, "loss": 0.0187, "positive_teacher_pairs": 26846.0, "relation_loss": 0.0019154833280481398, "selected_pairs": 26846.0, "step": 23750, "student_distance_mean": 1283.0328735351563, "teacher_distance_mean": 0.861338347196579, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0019154833280481398, "weighted_relation_loss": 0.0019154833280481398 }, { "action_query_batch_std": 22.18560657501221, "action_query_norm": 939.140673828125, "action_relation_loss": 0.0018200962455011903, "auxiliary_loss_weight": 1.0, "epoch": 22.226379794200188, "flow_matching_loss": 0.016866377834230662, "grad_norm": 0.09550957381725311, "invalid_tail_samples": 22.5, "learning_rate": 1.1372651951974e-05, "loss": 0.0187, "positive_teacher_pairs": 27152.3, "relation_loss": 0.0018200962455011903, "selected_pairs": 27152.3, "step": 23760, "student_distance_mean": 1278.2931762695312, "teacher_distance_mean": 0.8581305623054505, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0018200962455011903, "weighted_relation_loss": 0.0018200962455011903 }, { "action_query_batch_std": 22.042694664001466, "action_query_norm": 940.2362976074219, "action_relation_loss": 0.0018735165940597653, "auxiliary_loss_weight": 1.0, "epoch": 22.235734331150606, "flow_matching_loss": 0.015984317194670437, "grad_norm": 0.08821813017129898, "invalid_tail_samples": 23.6, "learning_rate": 1.1337679317719952e-05, "loss": 0.0179, "positive_teacher_pairs": 26909.5, "relation_loss": 0.0018735165940597653, "selected_pairs": 26909.5, "step": 23770, "student_distance_mean": 1268.0062622070313, "teacher_distance_mean": 0.8480682730674743, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0018735165940597653, "weighted_relation_loss": 0.0018735165940597653 }, { "action_query_batch_std": 22.15288562774658, "action_query_norm": 937.5504516601562, "action_relation_loss": 0.0018893712782301008, "auxiliary_loss_weight": 1.0, "epoch": 22.24508886810103, "flow_matching_loss": 0.01569579876959324, "grad_norm": 0.08577115833759308, "invalid_tail_samples": 26.2, "learning_rate": 1.1302753661831151e-05, "loss": 0.0176, "positive_teacher_pairs": 26299.2, "relation_loss": 0.0018893712782301008, "selected_pairs": 26299.2, "step": 23780, "student_distance_mean": 1269.0383056640626, "teacher_distance_mean": 0.8506523907184601, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.0018893712782301008, "weighted_relation_loss": 0.0018893712782301008 }, { "action_query_batch_std": 21.88147735595703, "action_query_norm": 934.2357666015625, "action_relation_loss": 0.0019156691618263722, "auxiliary_loss_weight": 1.0, "epoch": 22.25444340505145, "flow_matching_loss": 0.016808061767369507, "grad_norm": 0.08541884273290634, "invalid_tail_samples": 24.0, "learning_rate": 1.1267875026745561e-05, "loss": 0.0187, "positive_teacher_pairs": 26805.6, "relation_loss": 0.0019156691618263722, "selected_pairs": 26805.6, "step": 23790, "student_distance_mean": 1260.251953125, "teacher_distance_mean": 0.847198623418808, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0019156691618263722, "weighted_relation_loss": 0.0019156691618263722 }, { "action_query_batch_std": 22.638283729553223, "action_query_norm": 956.6585205078125, "action_relation_loss": 0.0018388594849966466, "auxiliary_loss_weight": 1.0, "epoch": 22.263797942001872, "flow_matching_loss": 0.016745438519865274, "grad_norm": 0.08129547536373138, "invalid_tail_samples": 23.3, "learning_rate": 1.1233043454844016e-05, "loss": 0.0186, "positive_teacher_pairs": 26963.9, "relation_loss": 0.0018388594849966466, "selected_pairs": 26963.9, "step": 23800, "student_distance_mean": 1299.54541015625, "teacher_distance_mean": 0.8721794664859772, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0018388594849966466, "weighted_relation_loss": 0.0018388594849966466 }, { "action_query_batch_std": 22.56167335510254, "action_query_norm": 952.3222595214844, "action_relation_loss": 0.0019244878552854062, "auxiliary_loss_weight": 1.0, "epoch": 22.27315247895229, "flow_matching_loss": 0.018657656852155924, "grad_norm": 0.09366513043642044, "invalid_tail_samples": 23.1, "learning_rate": 1.1198258988450144e-05, "loss": 0.0206, "positive_teacher_pairs": 27015.4, "relation_loss": 0.0019244878552854062, "selected_pairs": 27015.4, "step": 23810, "student_distance_mean": 1295.1849243164063, "teacher_distance_mean": 0.8694539546966553, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0019244878552854062, "weighted_relation_loss": 0.0019244878552854062 }, { "action_query_batch_std": 22.1803258895874, "action_query_norm": 942.1449035644531, "action_relation_loss": 0.0019045276567339897, "auxiliary_loss_weight": 1.0, "epoch": 22.282507015902713, "flow_matching_loss": 0.016498704068362714, "grad_norm": 0.09244156628847122, "invalid_tail_samples": 21.4, "learning_rate": 1.1163521669830368e-05, "loss": 0.0184, "positive_teacher_pairs": 27405.1, "relation_loss": 0.0019045276567339897, "selected_pairs": 27405.1, "step": 23820, "student_distance_mean": 1272.5505981445312, "teacher_distance_mean": 0.8559471309185028, "valid_action_samples": 234.6, "weighted_auxiliary_loss": 0.0019045276567339897, "weighted_relation_loss": 0.0019045276567339897 }, { "action_query_batch_std": 21.92754135131836, "action_query_norm": 931.4316040039063, "action_relation_loss": 0.0018769814167171716, "auxiliary_loss_weight": 1.0, "epoch": 22.291861552853135, "flow_matching_loss": 0.0185872838832438, "grad_norm": 0.08956751972436905, "invalid_tail_samples": 27.3, "learning_rate": 1.1128831541193818e-05, "loss": 0.0205, "positive_teacher_pairs": 26051.9, "relation_loss": 0.0018769814167171716, "selected_pairs": 26051.9, "step": 23830, "student_distance_mean": 1266.8484375, "teacher_distance_mean": 0.8502493321895599, "valid_action_samples": 228.7, "weighted_auxiliary_loss": 0.0018769814167171716, "weighted_relation_loss": 0.0018769814167171716 }, { "action_query_batch_std": 22.333373069763184, "action_query_norm": 945.3489440917969, "action_relation_loss": 0.001982247014530003, "auxiliary_loss_weight": 1.0, "epoch": 22.301216089803553, "flow_matching_loss": 0.017661500349640848, "grad_norm": 0.12302086502313614, "invalid_tail_samples": 23.1, "learning_rate": 1.1094188644692255e-05, "loss": 0.0196, "positive_teacher_pairs": 27009.0, "relation_loss": 0.001982247014530003, "selected_pairs": 27009.0, "step": 23840, "student_distance_mean": 1280.3179809570313, "teacher_distance_mean": 0.8565351903438568, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.001982247014530003, "weighted_relation_loss": 0.001982247014530003 }, { "action_query_batch_std": 22.126571464538575, "action_query_norm": 939.5608215332031, "action_relation_loss": 0.0019320872146636249, "auxiliary_loss_weight": 1.0, "epoch": 22.310570626753975, "flow_matching_loss": 0.0172539752908051, "grad_norm": 0.08553806692361832, "invalid_tail_samples": 26.7, "learning_rate": 1.1059593022420067e-05, "loss": 0.0192, "positive_teacher_pairs": 26184.5, "relation_loss": 0.0019320872146636249, "selected_pairs": 26184.5, "step": 23850, "student_distance_mean": 1278.5432250976562, "teacher_distance_mean": 0.8580619692802429, "valid_action_samples": 229.3, "weighted_auxiliary_loss": 0.0019320872146636249, "weighted_relation_loss": 0.0019320872146636249 }, { "action_query_batch_std": 22.291829681396486, "action_query_norm": 945.062353515625, "action_relation_loss": 0.00190964974462986, "auxiliary_loss_weight": 1.0, "epoch": 22.319925163704397, "flow_matching_loss": 0.017167274467647077, "grad_norm": 0.08935713022947311, "invalid_tail_samples": 24.2, "learning_rate": 1.1025044716414184e-05, "loss": 0.0191, "positive_teacher_pairs": 26757.7, "relation_loss": 0.00190964974462986, "selected_pairs": 26757.7, "step": 23860, "student_distance_mean": 1285.1333740234375, "teacher_distance_mean": 0.8608139157295227, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.00190964974462986, "weighted_relation_loss": 0.00190964974462986 }, { "action_query_batch_std": 22.277416801452638, "action_query_norm": 942.828955078125, "action_relation_loss": 0.0018542167614214121, "auxiliary_loss_weight": 1.0, "epoch": 22.32927970065482, "flow_matching_loss": 0.016317069716751575, "grad_norm": 0.10499043762683868, "invalid_tail_samples": 24.0, "learning_rate": 1.0990543768654082e-05, "loss": 0.0182, "positive_teacher_pairs": 26804.4, "relation_loss": 0.0018542167614214121, "selected_pairs": 26804.4, "step": 23870, "student_distance_mean": 1279.73662109375, "teacher_distance_mean": 0.8588102400302887, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0018542167614214121, "weighted_relation_loss": 0.0018542167614214121 }, { "action_query_batch_std": 22.00105400085449, "action_query_norm": 931.019970703125, "action_relation_loss": 0.0019228502409532667, "auxiliary_loss_weight": 1.0, "epoch": 22.338634237605238, "flow_matching_loss": 0.016785395331680775, "grad_norm": 0.08624427020549774, "invalid_tail_samples": 24.5, "learning_rate": 1.0956090221061655e-05, "loss": 0.0187, "positive_teacher_pairs": 26689.7, "relation_loss": 0.0019228502409532667, "selected_pairs": 26689.7, "step": 23880, "student_distance_mean": 1268.863427734375, "teacher_distance_mean": 0.8518024265766144, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0019228502409532667, "weighted_relation_loss": 0.0019228502409532667 }, { "action_query_batch_std": 22.175077629089355, "action_query_norm": 938.9834838867188, "action_relation_loss": 0.001903625507839024, "auxiliary_loss_weight": 1.0, "epoch": 22.34798877455566, "flow_matching_loss": 0.017639412824064494, "grad_norm": 0.08831905573606491, "invalid_tail_samples": 23.8, "learning_rate": 1.0921684115501208e-05, "loss": 0.0195, "positive_teacher_pairs": 26859.9, "relation_loss": 0.001903625507839024, "selected_pairs": 26859.9, "step": 23890, "student_distance_mean": 1275.8353881835938, "teacher_distance_mean": 0.8553228437900543, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.001903625507839024, "weighted_relation_loss": 0.001903625507839024 }, { "action_query_batch_std": 22.06284523010254, "action_query_norm": 937.5268371582031, "action_relation_loss": 0.001883826800622046, "auxiliary_loss_weight": 1.0, "epoch": 22.35734331150608, "flow_matching_loss": 0.017542561702430248, "grad_norm": 0.12094350159168243, "invalid_tail_samples": 23.9, "learning_rate": 1.0887325493779405e-05, "loss": 0.0194, "positive_teacher_pairs": 26838.5, "relation_loss": 0.001883826800622046, "selected_pairs": 26838.5, "step": 23900, "student_distance_mean": 1272.789599609375, "teacher_distance_mean": 0.8536721050739289, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.001883826800622046, "weighted_relation_loss": 0.001883826800622046 }, { "action_query_batch_std": 22.2648832321167, "action_query_norm": 940.649658203125, "action_relation_loss": 0.0018325677956454456, "auxiliary_loss_weight": 1.0, "epoch": 22.3666978484565, "flow_matching_loss": 0.015808550361543893, "grad_norm": 0.07698916643857956, "invalid_tail_samples": 24.5, "learning_rate": 1.0853014397645207e-05, "loss": 0.0176, "positive_teacher_pairs": 26695.7, "relation_loss": 0.0018325677956454456, "selected_pairs": 26695.7, "step": 23910, "student_distance_mean": 1277.140576171875, "teacher_distance_mean": 0.8573339462280274, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0018325677956454456, "weighted_relation_loss": 0.0018325677956454456 }, { "action_query_batch_std": 22.071311378479002, "action_query_norm": 935.6100769042969, "action_relation_loss": 0.0018668425967916847, "auxiliary_loss_weight": 1.0, "epoch": 22.376052385406922, "flow_matching_loss": 0.01738312980160117, "grad_norm": 0.09400862455368042, "invalid_tail_samples": 25.6, "learning_rate": 1.0818750868789829e-05, "loss": 0.0192, "positive_teacher_pairs": 26433.6, "relation_loss": 0.0018668425967916847, "selected_pairs": 26433.6, "step": 23920, "student_distance_mean": 1267.2100341796875, "teacher_distance_mean": 0.8489904463291168, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.0018668425967916847, "weighted_relation_loss": 0.0018668425967916847 }, { "action_query_batch_std": 22.406292343139647, "action_query_norm": 948.26103515625, "action_relation_loss": 0.001801696082111448, "auxiliary_loss_weight": 1.0, "epoch": 22.385406922357344, "flow_matching_loss": 0.017276554182171822, "grad_norm": 0.09929052740335464, "invalid_tail_samples": 22.1, "learning_rate": 1.0784534948846703e-05, "loss": 0.0191, "positive_teacher_pairs": 27245.9, "relation_loss": 0.001801696082111448, "selected_pairs": 27245.9, "step": 23930, "student_distance_mean": 1287.0588623046874, "teacher_distance_mean": 0.8632162034511566, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.001801696082111448, "weighted_relation_loss": 0.001801696082111448 }, { "action_query_batch_std": 22.334196472167967, "action_query_norm": 943.3527282714844, "action_relation_loss": 0.0018543855636380612, "auxiliary_loss_weight": 1.0, "epoch": 22.394761459307766, "flow_matching_loss": 0.01778694847598672, "grad_norm": 0.09245990216732025, "invalid_tail_samples": 25.6, "learning_rate": 1.0750366679391393e-05, "loss": 0.0196, "positive_teacher_pairs": 26440.8, "relation_loss": 0.0018543855636380612, "selected_pairs": 26440.8, "step": 23940, "student_distance_mean": 1284.6509521484375, "teacher_distance_mean": 0.8619961440563202, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.0018543855636380612, "weighted_relation_loss": 0.0018543855636380612 }, { "action_query_batch_std": 22.11331901550293, "action_query_norm": 941.8908386230469, "action_relation_loss": 0.0018001802847720683, "auxiliary_loss_weight": 1.0, "epoch": 22.404115996258184, "flow_matching_loss": 0.017546935752034188, "grad_norm": 0.11119509488344193, "invalid_tail_samples": 22.5, "learning_rate": 1.0716246101941557e-05, "loss": 0.0193, "positive_teacher_pairs": 27157.4, "relation_loss": 0.0018001802847720683, "selected_pairs": 27157.4, "step": 23950, "student_distance_mean": 1268.0856811523438, "teacher_distance_mean": 0.850716894865036, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0018001802847720683, "weighted_relation_loss": 0.0018001802847720683 }, { "action_query_batch_std": 22.149073600769043, "action_query_norm": 937.0615905761719, "action_relation_loss": 0.001917680713813752, "auxiliary_loss_weight": 1.0, "epoch": 22.413470533208606, "flow_matching_loss": 0.016420093737542628, "grad_norm": 0.09471148252487183, "invalid_tail_samples": 24.4, "learning_rate": 1.0682173257956934e-05, "loss": 0.0183, "positive_teacher_pairs": 26709.9, "relation_loss": 0.001917680713813752, "selected_pairs": 26709.9, "step": 23960, "student_distance_mean": 1272.9914184570312, "teacher_distance_mean": 0.852373731136322, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.001917680713813752, "weighted_relation_loss": 0.001917680713813752 }, { "action_query_batch_std": 22.16941318511963, "action_query_norm": 940.6948608398437, "action_relation_loss": 0.001844485814217478, "auxiliary_loss_weight": 1.0, "epoch": 22.42282507015903, "flow_matching_loss": 0.015474616270512342, "grad_norm": 0.09498226642608643, "invalid_tail_samples": 25.3, "learning_rate": 1.064814818883922e-05, "loss": 0.0173, "positive_teacher_pairs": 26502.5, "relation_loss": 0.001844485814217478, "selected_pairs": 26502.5, "step": 23970, "student_distance_mean": 1279.2290283203124, "teacher_distance_mean": 0.8569958508014679, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.001844485814217478, "weighted_relation_loss": 0.001844485814217478 }, { "action_query_batch_std": 22.28204174041748, "action_query_norm": 942.9873596191406, "action_relation_loss": 0.0018767853965982796, "auxiliary_loss_weight": 1.0, "epoch": 22.432179607109447, "flow_matching_loss": 0.017049788683652877, "grad_norm": 0.09582481533288956, "invalid_tail_samples": 23.9, "learning_rate": 1.06141709359321e-05, "loss": 0.0189, "positive_teacher_pairs": 26835.2, "relation_loss": 0.0018767853965982796, "selected_pairs": 26835.2, "step": 23980, "student_distance_mean": 1279.89990234375, "teacher_distance_mean": 0.8574924468994141, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0018767853965982796, "weighted_relation_loss": 0.0018767853965982796 }, { "action_query_batch_std": 22.05512180328369, "action_query_norm": 934.7718078613282, "action_relation_loss": 0.0018127735471352934, "auxiliary_loss_weight": 1.0, "epoch": 22.44153414405987, "flow_matching_loss": 0.0156018091365695, "grad_norm": 0.09478883445262909, "invalid_tail_samples": 25.4, "learning_rate": 1.058024154052114e-05, "loss": 0.0174, "positive_teacher_pairs": 26475.9, "relation_loss": 0.0018127735471352934, "selected_pairs": 26475.9, "step": 23990, "student_distance_mean": 1265.9274658203126, "teacher_distance_mean": 0.849645984172821, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.0018127735471352934, "weighted_relation_loss": 0.0018127735471352934 }, { "action_query_batch_std": 22.262675094604493, "action_query_norm": 945.5616271972656, "action_relation_loss": 0.0018634476931765676, "auxiliary_loss_weight": 1.0, "epoch": 22.45088868101029, "flow_matching_loss": 0.015398337878286839, "grad_norm": 0.09042072296142578, "invalid_tail_samples": 22.6, "learning_rate": 1.0546360043833747e-05, "loss": 0.0173, "positive_teacher_pairs": 27126.5, "relation_loss": 0.0018634476931765676, "selected_pairs": 27126.5, "step": 24000, "student_distance_mean": 1283.692919921875, "teacher_distance_mean": 0.8591970384120942, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0018634476931765676, "weighted_relation_loss": 0.0018634476931765676 }, { "action_query_batch_std": 21.92255210876465, "action_query_norm": 933.1717895507812, "action_relation_loss": 0.0019171495572663844, "auxiliary_loss_weight": 1.0, "epoch": 22.46024321796071, "flow_matching_loss": 0.01812119549140334, "grad_norm": 0.09527384489774704, "invalid_tail_samples": 21.7, "learning_rate": 1.0512526487039138e-05, "loss": 0.02, "positive_teacher_pairs": 27335.3, "relation_loss": 0.0019171495572663844, "selected_pairs": 27335.3, "step": 24010, "student_distance_mean": 1261.2407348632812, "teacher_distance_mean": 0.8427047371864319, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.0019171495572663844, "weighted_relation_loss": 0.0019171495572663844 }, { "action_query_batch_std": 22.36772346496582, "action_query_norm": 944.9035400390625, "action_relation_loss": 0.0018238890334032476, "auxiliary_loss_weight": 1.0, "epoch": 22.46959775491113, "flow_matching_loss": 0.015730895288288593, "grad_norm": 0.09839972108602524, "invalid_tail_samples": 23.1, "learning_rate": 1.0478740911248258e-05, "loss": 0.0176, "positive_teacher_pairs": 27018.1, "relation_loss": 0.0018238890334032476, "selected_pairs": 27018.1, "step": 24020, "student_distance_mean": 1275.9374633789062, "teacher_distance_mean": 0.8529518127441407, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0018238890334032476, "weighted_relation_loss": 0.0018238890334032476 }, { "action_query_batch_std": 22.331407165527345, "action_query_norm": 946.9097595214844, "action_relation_loss": 0.001891106169205159, "auxiliary_loss_weight": 1.0, "epoch": 22.478952291861553, "flow_matching_loss": 0.01633249120786786, "grad_norm": 0.09908267110586166, "invalid_tail_samples": 22.7, "learning_rate": 1.0445003357513793e-05, "loss": 0.0182, "positive_teacher_pairs": 27104.7, "relation_loss": 0.001891106169205159, "selected_pairs": 27104.7, "step": 24030, "student_distance_mean": 1281.4473876953125, "teacher_distance_mean": 0.8573908507823944, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.001891106169205159, "weighted_relation_loss": 0.001891106169205159 }, { "action_query_batch_std": 22.194568252563478, "action_query_norm": 941.0278259277344, "action_relation_loss": 0.001826578623149544, "auxiliary_loss_weight": 1.0, "epoch": 22.488306828811975, "flow_matching_loss": 0.01614540461450815, "grad_norm": 0.09588246047496796, "invalid_tail_samples": 22.4, "learning_rate": 1.0411313866830042e-05, "loss": 0.018, "positive_teacher_pairs": 27182.1, "relation_loss": 0.001826578623149544, "selected_pairs": 27182.1, "step": 24040, "student_distance_mean": 1279.9065795898437, "teacher_distance_mean": 0.8568706572055816, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.001826578623149544, "weighted_relation_loss": 0.001826578623149544 }, { "action_query_batch_std": 22.1605583190918, "action_query_norm": 940.94658203125, "action_relation_loss": 0.0018560273689217865, "auxiliary_loss_weight": 1.0, "epoch": 22.497661365762394, "flow_matching_loss": 0.014721910376101733, "grad_norm": 0.08132357150316238, "invalid_tail_samples": 22.8, "learning_rate": 1.0377672480132915e-05, "loss": 0.0166, "positive_teacher_pairs": 27081.9, "relation_loss": 0.0018560273689217865, "selected_pairs": 27081.9, "step": 24050, "student_distance_mean": 1271.7745971679688, "teacher_distance_mean": 0.8495422303676605, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0018560273689217865, "weighted_relation_loss": 0.0018560273689217865 }, { "action_query_batch_std": 22.213246726989745, "action_query_norm": 942.4820983886718, "action_relation_loss": 0.0019101278041489423, "auxiliary_loss_weight": 1.0, "epoch": 22.507015902712816, "flow_matching_loss": 0.01619226597249508, "grad_norm": 0.08796326816082001, "invalid_tail_samples": 20.9, "learning_rate": 1.0344079238299864e-05, "loss": 0.0181, "positive_teacher_pairs": 27527.0, "relation_loss": 0.0019101278041489423, "selected_pairs": 27527.0, "step": 24060, "student_distance_mean": 1270.479736328125, "teacher_distance_mean": 0.8507800161838531, "valid_action_samples": 235.1, "weighted_auxiliary_loss": 0.0019101278041489423, "weighted_relation_loss": 0.0019101278041489423 }, { "action_query_batch_std": 22.29813575744629, "action_query_norm": 942.5441345214844, "action_relation_loss": 0.0018523287842981517, "auxiliary_loss_weight": 1.0, "epoch": 22.516370439663238, "flow_matching_loss": 0.016290871985256673, "grad_norm": 0.07203798741102219, "invalid_tail_samples": 25.4, "learning_rate": 1.0310534182149833e-05, "loss": 0.0181, "positive_teacher_pairs": 26483.9, "relation_loss": 0.0018523287842981517, "selected_pairs": 26483.9, "step": 24070, "student_distance_mean": 1283.6464477539062, "teacher_distance_mean": 0.8612770140171051, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.0018523287842981517, "weighted_relation_loss": 0.0018523287842981517 }, { "action_query_batch_std": 22.01175136566162, "action_query_norm": 933.7410705566406, "action_relation_loss": 0.001878435886465013, "auxiliary_loss_weight": 1.0, "epoch": 22.525724976613656, "flow_matching_loss": 0.016212789062410592, "grad_norm": 0.09035955369472504, "invalid_tail_samples": 24.8, "learning_rate": 1.0277037352443258e-05, "loss": 0.0181, "positive_teacher_pairs": 26625.2, "relation_loss": 0.001878435886465013, "selected_pairs": 26625.2, "step": 24080, "student_distance_mean": 1266.4955078125, "teacher_distance_mean": 0.850798225402832, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.001878435886465013, "weighted_relation_loss": 0.001878435886465013 }, { "action_query_batch_std": 22.09306106567383, "action_query_norm": 938.3867797851562, "action_relation_loss": 0.001890573720447719, "auxiliary_loss_weight": 1.0, "epoch": 22.535079513564078, "flow_matching_loss": 0.01679408932104707, "grad_norm": 0.0775647908449173, "invalid_tail_samples": 21.6, "learning_rate": 1.024358878988193e-05, "loss": 0.0187, "positive_teacher_pairs": 27366.9, "relation_loss": 0.001890573720447719, "selected_pairs": 27366.9, "step": 24090, "student_distance_mean": 1268.7890380859376, "teacher_distance_mean": 0.8527596354484558, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.001890573720447719, "weighted_relation_loss": 0.001890573720447719 }, { "action_query_batch_std": 21.990266036987304, "action_query_norm": 934.4323974609375, "action_relation_loss": 0.0018936445820145309, "auxiliary_loss_weight": 1.0, "epoch": 22.5444340505145, "flow_matching_loss": 0.016930113732814788, "grad_norm": 0.08531288057565689, "invalid_tail_samples": 26.1, "learning_rate": 1.0210188535108995e-05, "loss": 0.0188, "positive_teacher_pairs": 26328.0, "relation_loss": 0.0018936445820145309, "selected_pairs": 26328.0, "step": 24100, "student_distance_mean": 1261.7283325195312, "teacher_distance_mean": 0.8485282361507416, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.0018936445820145309, "weighted_relation_loss": 0.0018936445820145309 }, { "action_query_batch_std": 22.392936134338377, "action_query_norm": 947.7021789550781, "action_relation_loss": 0.0018205255968496204, "auxiliary_loss_weight": 1.0, "epoch": 22.553788587464922, "flow_matching_loss": 0.015686481539160014, "grad_norm": 0.08039593696594238, "invalid_tail_samples": 22.6, "learning_rate": 1.0176836628708935e-05, "loss": 0.0175, "positive_teacher_pairs": 27130.6, "relation_loss": 0.0018205255968496204, "selected_pairs": 27130.6, "step": 24110, "student_distance_mean": 1288.0401245117187, "teacher_distance_mean": 0.8670444846153259, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0018205255968496204, "weighted_relation_loss": 0.0018205255968496204 }, { "action_query_batch_std": 22.346224212646483, "action_query_norm": 946.8975402832032, "action_relation_loss": 0.0018548473832197486, "auxiliary_loss_weight": 1.0, "epoch": 22.56314312441534, "flow_matching_loss": 0.016540659964084624, "grad_norm": 0.08786047250032425, "invalid_tail_samples": 23.7, "learning_rate": 1.0143533111207454e-05, "loss": 0.0184, "positive_teacher_pairs": 26878.9, "relation_loss": 0.0018548473832197486, "selected_pairs": 26878.9, "step": 24120, "student_distance_mean": 1286.6760986328125, "teacher_distance_mean": 0.8619843065738678, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0018548473832197486, "weighted_relation_loss": 0.0018548473832197486 }, { "action_query_batch_std": 22.22713680267334, "action_query_norm": 942.7506896972657, "action_relation_loss": 0.0018862284952774644, "auxiliary_loss_weight": 1.0, "epoch": 22.572497661365762, "flow_matching_loss": 0.017539078556001186, "grad_norm": 0.10200285911560059, "invalid_tail_samples": 23.4, "learning_rate": 1.0110278023071446e-05, "loss": 0.0194, "positive_teacher_pairs": 26956.0, "relation_loss": 0.0018862284952774644, "selected_pairs": 26956.0, "step": 24130, "student_distance_mean": 1276.2914916992188, "teacher_distance_mean": 0.8538169026374817, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0018862284952774644, "weighted_relation_loss": 0.0018862284952774644 }, { "action_query_batch_std": 21.831526374816896, "action_query_norm": 930.4551391601562, "action_relation_loss": 0.0018827770603820682, "auxiliary_loss_weight": 1.0, "epoch": 22.581852198316184, "flow_matching_loss": 0.016736244410276414, "grad_norm": 0.08844036608934402, "invalid_tail_samples": 23.1, "learning_rate": 1.007707140470901e-05, "loss": 0.0186, "positive_teacher_pairs": 27023.3, "relation_loss": 0.0018827770603820682, "selected_pairs": 27023.3, "step": 24140, "student_distance_mean": 1257.7735473632813, "teacher_distance_mean": 0.8428349375724793, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0018827770603820682, "weighted_relation_loss": 0.0018827770603820682 }, { "action_query_batch_std": 22.027639961242677, "action_query_norm": 939.4213439941407, "action_relation_loss": 0.0018057988956570626, "auxiliary_loss_weight": 1.0, "epoch": 22.591206735266603, "flow_matching_loss": 0.01621503382921219, "grad_norm": 0.0926814153790474, "invalid_tail_samples": 24.3, "learning_rate": 1.0043913296469298e-05, "loss": 0.018, "positive_teacher_pairs": 26734.7, "relation_loss": 0.0018057988956570626, "selected_pairs": 26734.7, "step": 24150, "student_distance_mean": 1270.0503173828124, "teacher_distance_mean": 0.8502480864524842, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0018057988956570626, "weighted_relation_loss": 0.0018057988956570626 }, { "action_query_batch_std": 22.164865493774414, "action_query_norm": 940.9392578125, "action_relation_loss": 0.0018522665253840388, "auxiliary_loss_weight": 1.0, "epoch": 22.600561272217025, "flow_matching_loss": 0.01602793363854289, "grad_norm": 0.08855590969324112, "invalid_tail_samples": 24.2, "learning_rate": 1.001080373864255e-05, "loss": 0.0179, "positive_teacher_pairs": 26760.6, "relation_loss": 0.0018522665253840388, "selected_pairs": 26760.6, "step": 24160, "student_distance_mean": 1273.0026733398438, "teacher_distance_mean": 0.852543169260025, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0018522665253840388, "weighted_relation_loss": 0.0018522665253840388 }, { "action_query_batch_std": 22.152935791015626, "action_query_norm": 939.0213317871094, "action_relation_loss": 0.0019046731060370803, "auxiliary_loss_weight": 1.0, "epoch": 22.609915809167447, "flow_matching_loss": 0.016755121853202583, "grad_norm": 0.08004173636436462, "invalid_tail_samples": 24.5, "learning_rate": 9.977742771459991e-06, "loss": 0.0187, "positive_teacher_pairs": 26699.1, "relation_loss": 0.0019046731060370803, "selected_pairs": 26699.1, "step": 24170, "student_distance_mean": 1271.3571044921875, "teacher_distance_mean": 0.8507328987121582, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0019046731060370803, "weighted_relation_loss": 0.0019046731060370803 }, { "action_query_batch_std": 22.167742347717287, "action_query_norm": 941.8689025878906, "action_relation_loss": 0.0018885371042415499, "auxiliary_loss_weight": 1.0, "epoch": 22.61927034611787, "flow_matching_loss": 0.01720419218763709, "grad_norm": 0.09180199354887009, "invalid_tail_samples": 21.1, "learning_rate": 9.944730435093802e-06, "loss": 0.0191, "positive_teacher_pairs": 27487.1, "relation_loss": 0.0018885371042415499, "selected_pairs": 27487.1, "step": 24180, "student_distance_mean": 1276.5540893554687, "teacher_distance_mean": 0.8534013748168945, "valid_action_samples": 234.9, "weighted_auxiliary_loss": 0.0018885371042415499, "weighted_relation_loss": 0.0018885371042415499 }, { "action_query_batch_std": 22.161895179748534, "action_query_norm": 941.4852600097656, "action_relation_loss": 0.0019058751757256686, "auxiliary_loss_weight": 1.0, "epoch": 22.628624883068287, "flow_matching_loss": 0.016666427068412305, "grad_norm": 0.10058264434337616, "invalid_tail_samples": 23.2, "learning_rate": 9.911766769657115e-06, "loss": 0.0186, "positive_teacher_pairs": 26993.2, "relation_loss": 0.0019058751757256686, "selected_pairs": 26993.2, "step": 24190, "student_distance_mean": 1277.742822265625, "teacher_distance_mean": 0.8552118599414825, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0019058751757256686, "weighted_relation_loss": 0.0019058751757256686 }, { "action_query_batch_std": 22.333989715576173, "action_query_norm": 945.6515930175781, "action_relation_loss": 0.001879026391543448, "auxiliary_loss_weight": 1.0, "epoch": 22.63797942001871, "flow_matching_loss": 0.017824374511837958, "grad_norm": 0.08058987557888031, "invalid_tail_samples": 22.8, "learning_rate": 9.878851815203882e-06, "loss": 0.0197, "positive_teacher_pairs": 27096.7, "relation_loss": 0.001879026391543448, "selected_pairs": 27096.7, "step": 24200, "student_distance_mean": 1283.3170288085937, "teacher_distance_mean": 0.8588520467281342, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.001879026391543448, "weighted_relation_loss": 0.001879026391543448 }, { "action_query_batch_std": 22.239539337158202, "action_query_norm": 943.3910522460938, "action_relation_loss": 0.0019039546605199575, "auxiliary_loss_weight": 1.0, "epoch": 22.64733395696913, "flow_matching_loss": 0.01672901092097163, "grad_norm": 0.10002274066209793, "invalid_tail_samples": 24.8, "learning_rate": 9.845985611728864e-06, "loss": 0.0186, "positive_teacher_pairs": 26617.4, "relation_loss": 0.0019039546605199575, "selected_pairs": 26617.4, "step": 24210, "student_distance_mean": 1280.0608520507812, "teacher_distance_mean": 0.8565591633319855, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0019039546605199575, "weighted_relation_loss": 0.0019039546605199575 }, { "action_query_batch_std": 22.26578884124756, "action_query_norm": 943.579638671875, "action_relation_loss": 0.0019100977224297822, "auxiliary_loss_weight": 1.0, "epoch": 22.65668849391955, "flow_matching_loss": 0.018347993306815625, "grad_norm": 0.10391444712877274, "invalid_tail_samples": 23.9, "learning_rate": 9.813168199167606e-06, "loss": 0.0203, "positive_teacher_pairs": 26825.5, "relation_loss": 0.0019100977224297822, "selected_pairs": 26825.5, "step": 24220, "student_distance_mean": 1278.86201171875, "teacher_distance_mean": 0.8566284716129303, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0019100977224297822, "weighted_relation_loss": 0.0019100977224297822 }, { "action_query_batch_std": 22.058491897583007, "action_query_norm": 936.8247314453125, "action_relation_loss": 0.001857643120456487, "auxiliary_loss_weight": 1.0, "epoch": 22.66604303086997, "flow_matching_loss": 0.0191678480245173, "grad_norm": 0.09723131358623505, "invalid_tail_samples": 24.1, "learning_rate": 9.780399617396341e-06, "loss": 0.021, "positive_teacher_pairs": 26780.5, "relation_loss": 0.001857643120456487, "selected_pairs": 26780.5, "step": 24230, "student_distance_mean": 1267.958935546875, "teacher_distance_mean": 0.8502298176288605, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.001857643120456487, "weighted_relation_loss": 0.001857643120456487 }, { "action_query_batch_std": 22.281302452087402, "action_query_norm": 943.65390625, "action_relation_loss": 0.001897174515761435, "auxiliary_loss_weight": 1.0, "epoch": 22.675397567820394, "flow_matching_loss": 0.017446107137948273, "grad_norm": 0.10155219584703445, "invalid_tail_samples": 23.7, "learning_rate": 9.747679906232016e-06, "loss": 0.0193, "positive_teacher_pairs": 26877.4, "relation_loss": 0.001897174515761435, "selected_pairs": 26877.4, "step": 24240, "student_distance_mean": 1279.7871704101562, "teacher_distance_mean": 0.8577432453632354, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.001897174515761435, "weighted_relation_loss": 0.001897174515761435 }, { "action_query_batch_std": 22.071585655212402, "action_query_norm": 938.9169799804688, "action_relation_loss": 0.0018380363704636692, "auxiliary_loss_weight": 1.0, "epoch": 22.684752104770816, "flow_matching_loss": 0.016414748132228853, "grad_norm": 0.09163988381624222, "invalid_tail_samples": 21.2, "learning_rate": 9.715009105432138e-06, "loss": 0.0183, "positive_teacher_pairs": 27467.2, "relation_loss": 0.0018380363704636692, "selected_pairs": 27467.2, "step": 24250, "student_distance_mean": 1267.8624145507813, "teacher_distance_mean": 0.8477605104446411, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.0018380363704636692, "weighted_relation_loss": 0.0018380363704636692 }, { "action_query_batch_std": 22.486179924011232, "action_query_norm": 952.3458923339844, "action_relation_loss": 0.0018728647148236633, "auxiliary_loss_weight": 1.0, "epoch": 22.694106641721234, "flow_matching_loss": 0.017334269173443318, "grad_norm": 0.08873856067657471, "invalid_tail_samples": 25.4, "learning_rate": 9.682387254694835e-06, "loss": 0.0192, "positive_teacher_pairs": 26482.2, "relation_loss": 0.0018728647148236633, "selected_pairs": 26482.2, "step": 24260, "student_distance_mean": 1292.69609375, "teacher_distance_mean": 0.8660654067993164, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.0018728647148236633, "weighted_relation_loss": 0.0018728647148236633 }, { "action_query_batch_std": 22.176626205444336, "action_query_norm": 938.3247192382812, "action_relation_loss": 0.0018578168819658458, "auxiliary_loss_weight": 1.0, "epoch": 22.703461178671656, "flow_matching_loss": 0.017284391354769467, "grad_norm": 0.08839883655309677, "invalid_tail_samples": 25.2, "learning_rate": 9.649814393658723e-06, "loss": 0.0191, "positive_teacher_pairs": 26526.5, "relation_loss": 0.0018578168819658458, "selected_pairs": 26526.5, "step": 24270, "student_distance_mean": 1272.2821655273438, "teacher_distance_mean": 0.852258950471878, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0018578168819658458, "weighted_relation_loss": 0.0018578168819658458 }, { "action_query_batch_std": 22.278114128112794, "action_query_norm": 945.2629638671875, "action_relation_loss": 0.0018423313624225557, "auxiliary_loss_weight": 1.0, "epoch": 22.712815715622078, "flow_matching_loss": 0.017958861868828536, "grad_norm": 0.11019794642925262, "invalid_tail_samples": 22.2, "learning_rate": 9.617290561902881e-06, "loss": 0.0198, "positive_teacher_pairs": 27218.8, "relation_loss": 0.0018423313624225557, "selected_pairs": 27218.8, "step": 24280, "student_distance_mean": 1280.6626586914062, "teacher_distance_mean": 0.8579918205738067, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.0018423313624225557, "weighted_relation_loss": 0.0018423313624225557 }, { "action_query_batch_std": 22.114841651916503, "action_query_norm": 941.4514892578125, "action_relation_loss": 0.0018510063760913908, "auxiliary_loss_weight": 1.0, "epoch": 22.722170252572496, "flow_matching_loss": 0.018087602872401475, "grad_norm": 0.08717158436775208, "invalid_tail_samples": 23.2, "learning_rate": 9.584815798946861e-06, "loss": 0.0199, "positive_teacher_pairs": 26989.9, "relation_loss": 0.0018510063760913908, "selected_pairs": 26989.9, "step": 24290, "student_distance_mean": 1273.8433715820313, "teacher_distance_mean": 0.8526827692985535, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0018510063760913908, "weighted_relation_loss": 0.0018510063760913908 }, { "action_query_batch_std": 22.292797660827638, "action_query_norm": 946.6104125976562, "action_relation_loss": 0.0018350895261391997, "auxiliary_loss_weight": 1.0, "epoch": 22.73152478952292, "flow_matching_loss": 0.01584935123100877, "grad_norm": 0.07884243875741959, "invalid_tail_samples": 23.3, "learning_rate": 9.55239014425055e-06, "loss": 0.0177, "positive_teacher_pairs": 26968.6, "relation_loss": 0.0018350895261391997, "selected_pairs": 26968.6, "step": 24300, "student_distance_mean": 1281.429345703125, "teacher_distance_mean": 0.8578994631767273, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0018350895261391997, "weighted_relation_loss": 0.0018350895261391997 }, { "action_query_batch_std": 22.103751564025877, "action_query_norm": 938.7939331054688, "action_relation_loss": 0.0018323064083233475, "auxiliary_loss_weight": 1.0, "epoch": 22.74087932647334, "flow_matching_loss": 0.01789183709770441, "grad_norm": 0.10776082426309586, "invalid_tail_samples": 23.6, "learning_rate": 9.520013637214176e-06, "loss": 0.0197, "positive_teacher_pairs": 26895.7, "relation_loss": 0.0018323064083233475, "selected_pairs": 26895.7, "step": 24310, "student_distance_mean": 1272.5333129882813, "teacher_distance_mean": 0.8506321966648102, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0018323064083233475, "weighted_relation_loss": 0.0018323064083233475 }, { "action_query_batch_std": 22.273189544677734, "action_query_norm": 944.0910949707031, "action_relation_loss": 0.0018439637264236809, "auxiliary_loss_weight": 1.0, "epoch": 22.75023386342376, "flow_matching_loss": 0.017124523874372244, "grad_norm": 0.09764957427978516, "invalid_tail_samples": 21.1, "learning_rate": 9.48768631717824e-06, "loss": 0.019, "positive_teacher_pairs": 27479.5, "relation_loss": 0.0018439637264236809, "selected_pairs": 27479.5, "step": 24320, "student_distance_mean": 1272.3694946289063, "teacher_distance_mean": 0.849378091096878, "valid_action_samples": 234.9, "weighted_auxiliary_loss": 0.0018439637264236809, "weighted_relation_loss": 0.0018439637264236809 }, { "action_query_batch_std": 22.16495418548584, "action_query_norm": 938.0232543945312, "action_relation_loss": 0.0018424022011458874, "auxiliary_loss_weight": 1.0, "epoch": 22.75958840037418, "flow_matching_loss": 0.015856179129332303, "grad_norm": 0.08950512856245041, "invalid_tail_samples": 27.3, "learning_rate": 9.455408223423496e-06, "loss": 0.0177, "positive_teacher_pairs": 26052.3, "relation_loss": 0.0018424022011458874, "selected_pairs": 26052.3, "step": 24330, "student_distance_mean": 1278.9303833007812, "teacher_distance_mean": 0.8559616327285766, "valid_action_samples": 228.7, "weighted_auxiliary_loss": 0.0018424022011458874, "weighted_relation_loss": 0.0018424022011458874 }, { "action_query_batch_std": 22.14007453918457, "action_query_norm": 938.7337219238282, "action_relation_loss": 0.0018443501787260175, "auxiliary_loss_weight": 1.0, "epoch": 22.768942937324603, "flow_matching_loss": 0.017933447379618883, "grad_norm": 0.0907721221446991, "invalid_tail_samples": 23.8, "learning_rate": 9.423179395170845e-06, "loss": 0.0198, "positive_teacher_pairs": 26851.1, "relation_loss": 0.0018443501787260175, "selected_pairs": 26851.1, "step": 24340, "student_distance_mean": 1273.3981811523438, "teacher_distance_mean": 0.8511699616909028, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0018443501787260175, "weighted_relation_loss": 0.0018443501787260175 }, { "action_query_batch_std": 22.370472145080566, "action_query_norm": 950.1756958007812, "action_relation_loss": 0.0018264126032590867, "auxiliary_loss_weight": 1.0, "epoch": 22.778297474275025, "flow_matching_loss": 0.016795328445732595, "grad_norm": 0.08856984227895737, "invalid_tail_samples": 19.2, "learning_rate": 9.390999871581391e-06, "loss": 0.0186, "positive_teacher_pairs": 27927.1, "relation_loss": 0.0018264126032590867, "selected_pairs": 27927.1, "step": 24350, "student_distance_mean": 1282.5781127929688, "teacher_distance_mean": 0.8596964716911316, "valid_action_samples": 236.8, "weighted_auxiliary_loss": 0.0018264126032590867, "weighted_relation_loss": 0.0018264126032590867 }, { "action_query_batch_std": 22.449703407287597, "action_query_norm": 949.9816284179688, "action_relation_loss": 0.0018449915922246873, "auxiliary_loss_weight": 1.0, "epoch": 22.787652011225443, "flow_matching_loss": 0.018337343540042638, "grad_norm": 0.09708856791257858, "invalid_tail_samples": 24.4, "learning_rate": 9.358869691756273e-06, "loss": 0.0202, "positive_teacher_pairs": 26719.0, "relation_loss": 0.0018449915922246873, "selected_pairs": 26719.0, "step": 24360, "student_distance_mean": 1284.3653076171875, "teacher_distance_mean": 0.8596248149871826, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0018449915922246873, "weighted_relation_loss": 0.0018449915922246873 }, { "action_query_batch_std": 21.95033950805664, "action_query_norm": 936.7144165039062, "action_relation_loss": 0.001918168761767447, "auxiliary_loss_weight": 1.0, "epoch": 22.797006548175865, "flow_matching_loss": 0.016769342962652443, "grad_norm": 0.11313027888536453, "invalid_tail_samples": 26.1, "learning_rate": 9.326788894736688e-06, "loss": 0.0187, "positive_teacher_pairs": 26320.1, "relation_loss": 0.001918168761767447, "selected_pairs": 26320.1, "step": 24370, "student_distance_mean": 1265.7626342773438, "teacher_distance_mean": 0.8488696813583374, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.001918168761767447, "weighted_relation_loss": 0.001918168761767447 }, { "action_query_batch_std": 22.070027542114257, "action_query_norm": 940.1711059570313, "action_relation_loss": 0.0018769121845252812, "auxiliary_loss_weight": 1.0, "epoch": 22.806361085126287, "flow_matching_loss": 0.016515914537012576, "grad_norm": 0.08573164790868759, "invalid_tail_samples": 23.8, "learning_rate": 9.294757519503811e-06, "loss": 0.0184, "positive_teacher_pairs": 26846.6, "relation_loss": 0.0018769121845252812, "selected_pairs": 26846.6, "step": 24380, "student_distance_mean": 1269.9947509765625, "teacher_distance_mean": 0.8503986895084381, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0018769121845252812, "weighted_relation_loss": 0.0018769121845252812 }, { "action_query_batch_std": 22.03489170074463, "action_query_norm": 938.1968017578125, "action_relation_loss": 0.0018672573263756932, "auxiliary_loss_weight": 1.0, "epoch": 22.815715622076706, "flow_matching_loss": 0.015569752361625434, "grad_norm": 0.09573909640312195, "invalid_tail_samples": 23.5, "learning_rate": 9.262775604978819e-06, "loss": 0.0174, "positive_teacher_pairs": 26919.4, "relation_loss": 0.0018672573263756932, "selected_pairs": 26919.4, "step": 24390, "student_distance_mean": 1268.9685302734374, "teacher_distance_mean": 0.8490934491157531, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0018672573263756932, "weighted_relation_loss": 0.0018672573263756932 }, { "action_query_batch_std": 22.19264087677002, "action_query_norm": 943.6408508300781, "action_relation_loss": 0.001897019858006388, "auxiliary_loss_weight": 1.0, "epoch": 22.825070159027128, "flow_matching_loss": 0.01753599038347602, "grad_norm": 0.10326217859983444, "invalid_tail_samples": 24.3, "learning_rate": 9.230843190022725e-06, "loss": 0.0194, "positive_teacher_pairs": 26739.8, "relation_loss": 0.001897019858006388, "selected_pairs": 26739.8, "step": 24400, "student_distance_mean": 1280.1892822265625, "teacher_distance_mean": 0.8556721270084381, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.001897019858006388, "weighted_relation_loss": 0.001897019858006388 }, { "action_query_batch_std": 21.948167037963866, "action_query_norm": 933.8876525878907, "action_relation_loss": 0.0018866654252633452, "auxiliary_loss_weight": 1.0, "epoch": 22.83442469597755, "flow_matching_loss": 0.016238388139754534, "grad_norm": 0.08392997831106186, "invalid_tail_samples": 24.2, "learning_rate": 9.198960313436445e-06, "loss": 0.0181, "positive_teacher_pairs": 26754.1, "relation_loss": 0.0018866654252633452, "selected_pairs": 26754.1, "step": 24410, "student_distance_mean": 1266.7885864257812, "teacher_distance_mean": 0.8483922421932221, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0018866654252633452, "weighted_relation_loss": 0.0018866654252633452 }, { "action_query_batch_std": 22.54792003631592, "action_query_norm": 951.4618225097656, "action_relation_loss": 0.0018332263105548918, "auxiliary_loss_weight": 1.0, "epoch": 22.84377923292797, "flow_matching_loss": 0.01590792778879404, "grad_norm": 0.10182452201843262, "invalid_tail_samples": 22.1, "learning_rate": 9.16712701396067e-06, "loss": 0.0177, "positive_teacher_pairs": 27244.9, "relation_loss": 0.0018332263105548918, "selected_pairs": 27244.9, "step": 24420, "student_distance_mean": 1290.8280517578125, "teacher_distance_mean": 0.8618566691875458, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0018332263105548918, "weighted_relation_loss": 0.0018332263105548918 }, { "action_query_batch_std": 22.17110424041748, "action_query_norm": 942.0655029296875, "action_relation_loss": 0.0018950570258311928, "auxiliary_loss_weight": 1.0, "epoch": 22.85313376987839, "flow_matching_loss": 0.015367972105741501, "grad_norm": 0.09736794233322144, "invalid_tail_samples": 24.3, "learning_rate": 9.135343330275864e-06, "loss": 0.0173, "positive_teacher_pairs": 26730.6, "relation_loss": 0.0018950570258311928, "selected_pairs": 26730.6, "step": 24430, "student_distance_mean": 1277.359228515625, "teacher_distance_mean": 0.8547436356544494, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0018950570258311928, "weighted_relation_loss": 0.0018950570258311928 }, { "action_query_batch_std": 22.238895606994628, "action_query_norm": 941.50576171875, "action_relation_loss": 0.0017903036088682712, "auxiliary_loss_weight": 1.0, "epoch": 22.862488306828812, "flow_matching_loss": 0.015186705254018306, "grad_norm": 0.06608270853757858, "invalid_tail_samples": 22.3, "learning_rate": 9.10360930100218e-06, "loss": 0.017, "positive_teacher_pairs": 27199.3, "relation_loss": 0.0017903036088682712, "selected_pairs": 27199.3, "step": 24440, "student_distance_mean": 1272.2772583007813, "teacher_distance_mean": 0.8535149216651916, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0017903036088682712, "weighted_relation_loss": 0.0017903036088682712 }, { "action_query_batch_std": 22.453249168395995, "action_query_norm": 950.0784851074219, "action_relation_loss": 0.0018110660137608647, "auxiliary_loss_weight": 1.0, "epoch": 22.871842843779234, "flow_matching_loss": 0.016310480237007142, "grad_norm": 0.0957678034901619, "invalid_tail_samples": 24.7, "learning_rate": 9.07192496469949e-06, "loss": 0.0181, "positive_teacher_pairs": 26649.6, "relation_loss": 0.0018110660137608647, "selected_pairs": 26649.6, "step": 24450, "student_distance_mean": 1290.232177734375, "teacher_distance_mean": 0.8668935060501098, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0018110660137608647, "weighted_relation_loss": 0.0018110660137608647 }, { "action_query_batch_std": 22.43241081237793, "action_query_norm": 947.2155151367188, "action_relation_loss": 0.001879314484540373, "auxiliary_loss_weight": 1.0, "epoch": 22.881197380729652, "flow_matching_loss": 0.015292021725326777, "grad_norm": 0.07856220006942749, "invalid_tail_samples": 23.5, "learning_rate": 9.040290359867231e-06, "loss": 0.0172, "positive_teacher_pairs": 26925.1, "relation_loss": 0.001879314484540373, "selected_pairs": 26925.1, "step": 24460, "student_distance_mean": 1293.3341064453125, "teacher_distance_mean": 0.8674599707126618, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.001879314484540373, "weighted_relation_loss": 0.001879314484540373 }, { "action_query_batch_std": 22.19705295562744, "action_query_norm": 941.0907592773438, "action_relation_loss": 0.0018298298818990588, "auxiliary_loss_weight": 1.0, "epoch": 22.890551917680074, "flow_matching_loss": 0.01742779351770878, "grad_norm": 0.10462686419487, "invalid_tail_samples": 22.4, "learning_rate": 9.008705524944438e-06, "loss": 0.0193, "positive_teacher_pairs": 27174.9, "relation_loss": 0.0018298298818990588, "selected_pairs": 27174.9, "step": 24470, "student_distance_mean": 1274.3257934570313, "teacher_distance_mean": 0.8546174168586731, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.0018298298818990588, "weighted_relation_loss": 0.0018298298818990588 }, { "action_query_batch_std": 21.886500549316406, "action_query_norm": 932.2424011230469, "action_relation_loss": 0.0018392441212199627, "auxiliary_loss_weight": 1.0, "epoch": 22.899906454630496, "flow_matching_loss": 0.017290742229670288, "grad_norm": 0.0945788323879242, "invalid_tail_samples": 24.2, "learning_rate": 8.977170498309651e-06, "loss": 0.0191, "positive_teacher_pairs": 26758.1, "relation_loss": 0.0018392441212199627, "selected_pairs": 26758.1, "step": 24480, "student_distance_mean": 1260.0737915039062, "teacher_distance_mean": 0.8423701405525208, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0018392441212199627, "weighted_relation_loss": 0.0018392441212199627 }, { "action_query_batch_std": 21.983722496032716, "action_query_norm": 933.4400268554688, "action_relation_loss": 0.0018537380965426564, "auxiliary_loss_weight": 1.0, "epoch": 22.90926099158092, "flow_matching_loss": 0.01598612731322646, "grad_norm": 0.09897206723690033, "invalid_tail_samples": 23.4, "learning_rate": 8.945685318280916e-06, "loss": 0.0178, "positive_teacher_pairs": 26942.2, "relation_loss": 0.0018537380965426564, "selected_pairs": 26942.2, "step": 24490, "student_distance_mean": 1263.3926879882813, "teacher_distance_mean": 0.8451205134391785, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0018537380965426564, "weighted_relation_loss": 0.0018537380965426564 }, { "action_query_batch_std": 22.182452583312987, "action_query_norm": 942.7951965332031, "action_relation_loss": 0.0019205486285500228, "auxiliary_loss_weight": 1.0, "epoch": 22.918615528531337, "flow_matching_loss": 0.017075222544372083, "grad_norm": 0.09147959202528, "invalid_tail_samples": 21.9, "learning_rate": 8.914250023115672e-06, "loss": 0.019, "positive_teacher_pairs": 27293.2, "relation_loss": 0.0019205486285500228, "selected_pairs": 27293.2, "step": 24500, "student_distance_mean": 1276.2165649414062, "teacher_distance_mean": 0.8535805821418763, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.0019205486285500228, "weighted_relation_loss": 0.0019205486285500228 }, { "action_query_batch_std": 22.315951347351074, "action_query_norm": 943.8957763671875, "action_relation_loss": 0.0018081994727253913, "auxiliary_loss_weight": 1.0, "epoch": 22.92797006548176, "flow_matching_loss": 0.01549788573756814, "grad_norm": 0.07870540022850037, "invalid_tail_samples": 24.9, "learning_rate": 8.882864651010798e-06, "loss": 0.0173, "positive_teacher_pairs": 26600.5, "relation_loss": 0.0018081994727253913, "selected_pairs": 26600.5, "step": 24510, "student_distance_mean": 1283.4470703125, "teacher_distance_mean": 0.8592985391616821, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0018081994727253913, "weighted_relation_loss": 0.0018081994727253913 }, { "action_query_batch_std": 22.075880813598634, "action_query_norm": 937.631640625, "action_relation_loss": 0.0018655415973626078, "auxiliary_loss_weight": 1.0, "epoch": 22.93732460243218, "flow_matching_loss": 0.01602987041696906, "grad_norm": 0.08898462355136871, "invalid_tail_samples": 25.1, "learning_rate": 8.851529240102462e-06, "loss": 0.0179, "positive_teacher_pairs": 26551.2, "relation_loss": 0.0018655415973626078, "selected_pairs": 26551.2, "step": 24520, "student_distance_mean": 1268.216015625, "teacher_distance_mean": 0.850022429227829, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0018655415973626078, "weighted_relation_loss": 0.0018655415973626078 }, { "action_query_batch_std": 22.056415939331053, "action_query_norm": 936.0148498535157, "action_relation_loss": 0.0018297997070476414, "auxiliary_loss_weight": 1.0, "epoch": 22.9466791393826, "flow_matching_loss": 0.016757895052433015, "grad_norm": 0.1008932888507843, "invalid_tail_samples": 24.8, "learning_rate": 8.820243828466134e-06, "loss": 0.0186, "positive_teacher_pairs": 26626.4, "relation_loss": 0.0018297997070476414, "selected_pairs": 26626.4, "step": 24530, "student_distance_mean": 1270.9695678710937, "teacher_distance_mean": 0.8505248427391052, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0018297997070476414, "weighted_relation_loss": 0.0018297997070476414 }, { "action_query_batch_std": 22.336621856689455, "action_query_norm": 944.6816284179688, "action_relation_loss": 0.0018860253971070052, "auxiliary_loss_weight": 1.0, "epoch": 22.95603367633302, "flow_matching_loss": 0.016117825359106063, "grad_norm": 0.08650494366884232, "invalid_tail_samples": 22.6, "learning_rate": 8.789008454116566e-06, "loss": 0.018, "positive_teacher_pairs": 27127.0, "relation_loss": 0.0018860253971070052, "selected_pairs": 27127.0, "step": 24540, "student_distance_mean": 1282.1265991210937, "teacher_distance_mean": 0.8588224649429321, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0018860253971070052, "weighted_relation_loss": 0.0018860253971070052 }, { "action_query_batch_std": 22.186682510375977, "action_query_norm": 941.3506042480469, "action_relation_loss": 0.001847858796827495, "auxiliary_loss_weight": 1.0, "epoch": 22.965388213283443, "flow_matching_loss": 0.016237834375351666, "grad_norm": 0.12641315162181854, "invalid_tail_samples": 25.0, "learning_rate": 8.757823155007655e-06, "loss": 0.0181, "positive_teacher_pairs": 26574.6, "relation_loss": 0.001847858796827495, "selected_pairs": 26574.6, "step": 24550, "student_distance_mean": 1275.39736328125, "teacher_distance_mean": 0.8544678926467896, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.001847858796827495, "weighted_relation_loss": 0.001847858796827495 }, { "action_query_batch_std": 22.00042018890381, "action_query_norm": 937.6486877441406, "action_relation_loss": 0.0018494908814318477, "auxiliary_loss_weight": 1.0, "epoch": 22.974742750233865, "flow_matching_loss": 0.015167632605880499, "grad_norm": 0.09088797122240067, "invalid_tail_samples": 23.3, "learning_rate": 8.72668796903251e-06, "loss": 0.017, "positive_teacher_pairs": 26961.0, "relation_loss": 0.0018494908814318477, "selected_pairs": 26961.0, "step": 24560, "student_distance_mean": 1265.6844360351563, "teacher_distance_mean": 0.8486080408096314, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0018494908814318477, "weighted_relation_loss": 0.0018494908814318477 }, { "action_query_batch_std": 22.027565002441406, "action_query_norm": 936.7673095703125, "action_relation_loss": 0.0018524380633607508, "auxiliary_loss_weight": 1.0, "epoch": 22.984097287184284, "flow_matching_loss": 0.016798293963074685, "grad_norm": 0.086367666721344, "invalid_tail_samples": 25.1, "learning_rate": 8.695602934023301e-06, "loss": 0.0187, "positive_teacher_pairs": 26544.5, "relation_loss": 0.0018524380633607508, "selected_pairs": 26544.5, "step": 24570, "student_distance_mean": 1267.64638671875, "teacher_distance_mean": 0.8498486697673797, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0018524380633607508, "weighted_relation_loss": 0.0018524380633607508 }, { "action_query_batch_std": 22.297780799865723, "action_query_norm": 943.3020935058594, "action_relation_loss": 0.0019144445308484138, "auxiliary_loss_weight": 1.0, "epoch": 22.993451824134706, "flow_matching_loss": 0.015674807876348496, "grad_norm": 0.08967795968055725, "invalid_tail_samples": 25.8, "learning_rate": 8.664568087751274e-06, "loss": 0.0176, "positive_teacher_pairs": 26387.5, "relation_loss": 0.0019144445308484138, "selected_pairs": 26387.5, "step": 24580, "student_distance_mean": 1282.8987426757812, "teacher_distance_mean": 0.8596825420856475, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.0019144445308484138, "weighted_relation_loss": 0.0019144445308484138 }, { "action_query_batch_std": 22.217528915405275, "action_query_norm": 945.4774719238281, "action_relation_loss": 0.0018504705163650214, "auxiliary_loss_weight": 1.0, "epoch": 23.002806361085128, "flow_matching_loss": 0.016333404742181302, "grad_norm": 0.07411081343889236, "invalid_tail_samples": 21.4, "learning_rate": 8.633583467926697e-06, "loss": 0.0182, "positive_teacher_pairs": 24489.3, "relation_loss": 0.0018504705163650214, "selected_pairs": 24489.3, "step": 24590, "student_distance_mean": 1286.8969116210938, "teacher_distance_mean": 0.8614144921302795, "valid_action_samples": 214.7, "weighted_auxiliary_loss": 0.0018504705163650214, "weighted_relation_loss": 0.0018504705163650214 }, { "action_query_batch_std": 22.223465347290038, "action_query_norm": 941.936962890625, "action_relation_loss": 0.0018462569452822209, "auxiliary_loss_weight": 1.0, "epoch": 23.012160898035546, "flow_matching_loss": 0.017415314074605705, "grad_norm": 0.08715928345918655, "invalid_tail_samples": 23.7, "learning_rate": 8.602649112198796e-06, "loss": 0.0193, "positive_teacher_pairs": 26872.9, "relation_loss": 0.0018462569452822209, "selected_pairs": 26872.9, "step": 24600, "student_distance_mean": 1275.3497680664063, "teacher_distance_mean": 0.8546447157859802, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0018462569452822209, "weighted_relation_loss": 0.0018462569452822209 }, { "action_query_batch_std": 22.163937759399413, "action_query_norm": 940.0298767089844, "action_relation_loss": 0.0018396742991171778, "auxiliary_loss_weight": 1.0, "epoch": 23.021515434985968, "flow_matching_loss": 0.017578543443232775, "grad_norm": 0.09394970536231995, "invalid_tail_samples": 23.5, "learning_rate": 8.571765058155745e-06, "loss": 0.0194, "positive_teacher_pairs": 26931.1, "relation_loss": 0.0018396742991171778, "selected_pairs": 26931.1, "step": 24610, "student_distance_mean": 1273.0219116210938, "teacher_distance_mean": 0.8547844529151917, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0018396742991171778, "weighted_relation_loss": 0.0018396742991171778 }, { "action_query_batch_std": 21.929753875732423, "action_query_norm": 930.7815002441406, "action_relation_loss": 0.001874685799703002, "auxiliary_loss_weight": 1.0, "epoch": 23.03086997193639, "flow_matching_loss": 0.016926496103405953, "grad_norm": 0.10614575445652008, "invalid_tail_samples": 23.2, "learning_rate": 8.540931343324583e-06, "loss": 0.0188, "positive_teacher_pairs": 26990.8, "relation_loss": 0.001874685799703002, "selected_pairs": 26990.8, "step": 24620, "student_distance_mean": 1261.5838256835937, "teacher_distance_mean": 0.8456320583820343, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.001874685799703002, "weighted_relation_loss": 0.001874685799703002 }, { "action_query_batch_std": 22.172439765930175, "action_query_norm": 941.2328369140625, "action_relation_loss": 0.001841529889497906, "auxiliary_loss_weight": 1.0, "epoch": 23.04022450888681, "flow_matching_loss": 0.016277361381798982, "grad_norm": 0.08099618554115295, "invalid_tail_samples": 24.0, "learning_rate": 8.51014800517117e-06, "loss": 0.0181, "positive_teacher_pairs": 26803.9, "relation_loss": 0.001841529889497906, "selected_pairs": 26803.9, "step": 24630, "student_distance_mean": 1279.4756225585938, "teacher_distance_mean": 0.8587874352931977, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.001841529889497906, "weighted_relation_loss": 0.001841529889497906 }, { "action_query_batch_std": 22.17193431854248, "action_query_norm": 940.7799865722657, "action_relation_loss": 0.0018408737960271537, "auxiliary_loss_weight": 1.0, "epoch": 23.04957904583723, "flow_matching_loss": 0.01529149552807212, "grad_norm": 0.07628229260444641, "invalid_tail_samples": 21.9, "learning_rate": 8.479415081100167e-06, "loss": 0.0171, "positive_teacher_pairs": 27299.5, "relation_loss": 0.0018408737960271537, "selected_pairs": 27299.5, "step": 24640, "student_distance_mean": 1274.0105834960937, "teacher_distance_mean": 0.8555600583553314, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.0018408737960271537, "weighted_relation_loss": 0.0018408737960271537 }, { "action_query_batch_std": 22.184402847290038, "action_query_norm": 939.8893493652344, "action_relation_loss": 0.0018629215308465063, "auxiliary_loss_weight": 1.0, "epoch": 23.058933582787652, "flow_matching_loss": 0.017245033383369447, "grad_norm": 0.07708277553319931, "invalid_tail_samples": 22.6, "learning_rate": 8.448732608454967e-06, "loss": 0.0191, "positive_teacher_pairs": 27127.9, "relation_loss": 0.0018629215308465063, "selected_pairs": 27127.9, "step": 24650, "student_distance_mean": 1280.1369750976562, "teacher_distance_mean": 0.8605577051639557, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0018629215308465063, "weighted_relation_loss": 0.0018629215308465063 }, { "action_query_batch_std": 21.753096199035646, "action_query_norm": 925.6304504394532, "action_relation_loss": 0.0018664857489056885, "auxiliary_loss_weight": 1.0, "epoch": 23.068288119738074, "flow_matching_loss": 0.016341534070670606, "grad_norm": 0.08822412043809891, "invalid_tail_samples": 24.7, "learning_rate": 8.418100624517688e-06, "loss": 0.0182, "positive_teacher_pairs": 26635.6, "relation_loss": 0.0018664857489056885, "selected_pairs": 26635.6, "step": 24660, "student_distance_mean": 1250.1859619140625, "teacher_distance_mean": 0.838535475730896, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0018664857489056885, "weighted_relation_loss": 0.0018664857489056885 }, { "action_query_batch_std": 22.027122497558594, "action_query_norm": 934.3197998046875, "action_relation_loss": 0.0018991792458109558, "auxiliary_loss_weight": 1.0, "epoch": 23.077642656688493, "flow_matching_loss": 0.016215164586901663, "grad_norm": 0.11943022906780243, "invalid_tail_samples": 24.0, "learning_rate": 8.387519166509062e-06, "loss": 0.0181, "positive_teacher_pairs": 26813.1, "relation_loss": 0.0018991792458109558, "selected_pairs": 26813.1, "step": 24670, "student_distance_mean": 1272.8921020507812, "teacher_distance_mean": 0.853293526172638, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0018991792458109558, "weighted_relation_loss": 0.0018991792458109558 }, { "action_query_batch_std": 22.069745826721192, "action_query_norm": 936.7646179199219, "action_relation_loss": 0.001834438380319625, "auxiliary_loss_weight": 1.0, "epoch": 23.086997193638915, "flow_matching_loss": 0.016237742826342584, "grad_norm": 0.13939258456230164, "invalid_tail_samples": 22.2, "learning_rate": 8.356988271588445e-06, "loss": 0.0181, "positive_teacher_pairs": 27224.4, "relation_loss": 0.001834438380319625, "selected_pairs": 27224.4, "step": 24680, "student_distance_mean": 1268.0549926757812, "teacher_distance_mean": 0.850665706396103, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.001834438380319625, "weighted_relation_loss": 0.001834438380319625 }, { "action_query_batch_std": 22.379763793945312, "action_query_norm": 946.6117431640625, "action_relation_loss": 0.0017756307614035904, "auxiliary_loss_weight": 1.0, "epoch": 23.096351730589337, "flow_matching_loss": 0.017363474238663912, "grad_norm": 0.07348480075597763, "invalid_tail_samples": 25.4, "learning_rate": 8.326507976853765e-06, "loss": 0.0191, "positive_teacher_pairs": 26491.7, "relation_loss": 0.0017756307614035904, "selected_pairs": 26491.7, "step": 24690, "student_distance_mean": 1282.9662841796876, "teacher_distance_mean": 0.8608135402202606, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.0017756307614035904, "weighted_relation_loss": 0.0017756307614035904 }, { "action_query_batch_std": 22.173168182373047, "action_query_norm": 939.9726318359375, "action_relation_loss": 0.001827836816664785, "auxiliary_loss_weight": 1.0, "epoch": 23.105706267539755, "flow_matching_loss": 0.01588473850861192, "grad_norm": 0.10105060786008835, "invalid_tail_samples": 22.7, "learning_rate": 8.296078319341443e-06, "loss": 0.0177, "positive_teacher_pairs": 27105.7, "relation_loss": 0.001827836816664785, "selected_pairs": 27105.7, "step": 24700, "student_distance_mean": 1267.3505615234376, "teacher_distance_mean": 0.8480458498001099, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.001827836816664785, "weighted_relation_loss": 0.001827836816664785 }, { "action_query_batch_std": 22.375841331481933, "action_query_norm": 947.0645812988281, "action_relation_loss": 0.0018307127174921334, "auxiliary_loss_weight": 1.0, "epoch": 23.115060804490177, "flow_matching_loss": 0.01620501121506095, "grad_norm": 0.1308700293302536, "invalid_tail_samples": 23.3, "learning_rate": 8.265699336026383e-06, "loss": 0.018, "positive_teacher_pairs": 26964.4, "relation_loss": 0.0018307127174921334, "selected_pairs": 26964.4, "step": 24710, "student_distance_mean": 1283.07685546875, "teacher_distance_mean": 0.8621327579021454, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0018307127174921334, "weighted_relation_loss": 0.0018307127174921334 }, { "action_query_batch_std": 22.083106994628906, "action_query_norm": 935.2766296386719, "action_relation_loss": 0.0018452673335559665, "auxiliary_loss_weight": 1.0, "epoch": 23.1244153414406, "flow_matching_loss": 0.016617551259696484, "grad_norm": 0.09019831568002701, "invalid_tail_samples": 23.5, "learning_rate": 8.235371063821923e-06, "loss": 0.0185, "positive_teacher_pairs": 26925.7, "relation_loss": 0.0018452673335559665, "selected_pairs": 26925.7, "step": 24720, "student_distance_mean": 1265.8903564453126, "teacher_distance_mean": 0.8507194697856904, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0018452673335559665, "weighted_relation_loss": 0.0018452673335559665 }, { "action_query_batch_std": 22.043456268310546, "action_query_norm": 935.9185607910156, "action_relation_loss": 0.0018222138634882868, "auxiliary_loss_weight": 1.0, "epoch": 23.13376987839102, "flow_matching_loss": 0.016200970485806467, "grad_norm": 0.08992455899715424, "invalid_tail_samples": 22.8, "learning_rate": 8.205093539579767e-06, "loss": 0.018, "positive_teacher_pairs": 27083.4, "relation_loss": 0.0018222138634882868, "selected_pairs": 27083.4, "step": 24730, "student_distance_mean": 1267.0798950195312, "teacher_distance_mean": 0.8512308239936829, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0018222138634882868, "weighted_relation_loss": 0.0018222138634882868 }, { "action_query_batch_std": 22.130886459350585, "action_query_norm": 940.1846435546875, "action_relation_loss": 0.0017816830426454545, "auxiliary_loss_weight": 1.0, "epoch": 23.14312441534144, "flow_matching_loss": 0.0167783223092556, "grad_norm": 0.082344651222229, "invalid_tail_samples": 22.6, "learning_rate": 8.174866800089963e-06, "loss": 0.0186, "positive_teacher_pairs": 27128.5, "relation_loss": 0.0017816830426454545, "selected_pairs": 27128.5, "step": 24740, "student_distance_mean": 1271.4408935546876, "teacher_distance_mean": 0.855720865726471, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0017816830426454545, "weighted_relation_loss": 0.0017816830426454545 }, { "action_query_batch_std": 22.278558921813964, "action_query_norm": 944.2612487792969, "action_relation_loss": 0.0017849026364274323, "auxiliary_loss_weight": 1.0, "epoch": 23.15247895229186, "flow_matching_loss": 0.0167543888092041, "grad_norm": 0.07522960752248764, "invalid_tail_samples": 23.4, "learning_rate": 8.144690882080853e-06, "loss": 0.0185, "positive_teacher_pairs": 26945.2, "relation_loss": 0.0017849026364274323, "selected_pairs": 26945.2, "step": 24750, "student_distance_mean": 1283.0326171875, "teacher_distance_mean": 0.8614963114261627, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0017849026364274323, "weighted_relation_loss": 0.0017849026364274323 }, { "action_query_batch_std": 22.16164608001709, "action_query_norm": 939.1534912109375, "action_relation_loss": 0.0018364853924140335, "auxiliary_loss_weight": 1.0, "epoch": 23.161833489242284, "flow_matching_loss": 0.016565304063260556, "grad_norm": 0.07391071319580078, "invalid_tail_samples": 25.5, "learning_rate": 8.114565822219006e-06, "loss": 0.0184, "positive_teacher_pairs": 26463.0, "relation_loss": 0.0018364853924140335, "selected_pairs": 26463.0, "step": 24760, "student_distance_mean": 1268.4805908203125, "teacher_distance_mean": 0.8527036786079407, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0018364853924140335, "weighted_relation_loss": 0.0018364853924140335 }, { "action_query_batch_std": 22.242879104614257, "action_query_norm": 941.972412109375, "action_relation_loss": 0.0018128013121895491, "auxiliary_loss_weight": 1.0, "epoch": 23.171188026192702, "flow_matching_loss": 0.016081675980240108, "grad_norm": 0.10209142416715622, "invalid_tail_samples": 23.7, "learning_rate": 8.084491657109233e-06, "loss": 0.0179, "positive_teacher_pairs": 26872.1, "relation_loss": 0.0018128013121895491, "selected_pairs": 26872.1, "step": 24770, "student_distance_mean": 1277.29990234375, "teacher_distance_mean": 0.8588464856147766, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0018128013121895491, "weighted_relation_loss": 0.0018128013121895491 }, { "action_query_batch_std": 21.929576683044434, "action_query_norm": 933.7500061035156, "action_relation_loss": 0.0018598933005705477, "auxiliary_loss_weight": 1.0, "epoch": 23.180542563143124, "flow_matching_loss": 0.015519405156373978, "grad_norm": 0.09114482253789902, "invalid_tail_samples": 26.3, "learning_rate": 8.054468423294476e-06, "loss": 0.0174, "positive_teacher_pairs": 26274.3, "relation_loss": 0.0018598933005705477, "selected_pairs": 26274.3, "step": 24780, "student_distance_mean": 1259.8935791015624, "teacher_distance_mean": 0.8449669897556304, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.0018598933005705477, "weighted_relation_loss": 0.0018598933005705477 }, { "action_query_batch_std": 22.334686851501466, "action_query_norm": 943.35029296875, "action_relation_loss": 0.001860190718434751, "auxiliary_loss_weight": 1.0, "epoch": 23.189897100093546, "flow_matching_loss": 0.014750297367572784, "grad_norm": 0.08203164488077164, "invalid_tail_samples": 24.6, "learning_rate": 8.024496157255785e-06, "loss": 0.0166, "positive_teacher_pairs": 26669.2, "relation_loss": 0.001860190718434751, "selected_pairs": 26669.2, "step": 24790, "student_distance_mean": 1283.608984375, "teacher_distance_mean": 0.8604507565498352, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.001860190718434751, "weighted_relation_loss": 0.001860190718434751 }, { "action_query_batch_std": 22.07809543609619, "action_query_norm": 938.068359375, "action_relation_loss": 0.0019099849625490606, "auxiliary_loss_weight": 1.0, "epoch": 23.199251637043965, "flow_matching_loss": 0.017364519648253918, "grad_norm": 0.08216963708400726, "invalid_tail_samples": 24.5, "learning_rate": 7.994574895412293e-06, "loss": 0.0193, "positive_teacher_pairs": 26687.5, "relation_loss": 0.0019099849625490606, "selected_pairs": 26687.5, "step": 24800, "student_distance_mean": 1274.3155639648437, "teacher_distance_mean": 0.8533102333545685, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0019099849625490606, "weighted_relation_loss": 0.0019099849625490606 }, { "action_query_batch_std": 22.23726921081543, "action_query_norm": 944.6358093261719, "action_relation_loss": 0.0018200069782324136, "auxiliary_loss_weight": 1.0, "epoch": 23.208606173994387, "flow_matching_loss": 0.016886166576296092, "grad_norm": 0.09985258430242538, "invalid_tail_samples": 24.0, "learning_rate": 7.964704674121149e-06, "loss": 0.0187, "positive_teacher_pairs": 26806.3, "relation_loss": 0.0018200069782324136, "selected_pairs": 26806.3, "step": 24810, "student_distance_mean": 1282.523779296875, "teacher_distance_mean": 0.8585955798625946, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0018200069782324136, "weighted_relation_loss": 0.0018200069782324136 }, { "action_query_batch_std": 22.491440963745116, "action_query_norm": 949.1848693847656, "action_relation_loss": 0.0017583796987310051, "auxiliary_loss_weight": 1.0, "epoch": 23.21796071094481, "flow_matching_loss": 0.014735332410782575, "grad_norm": 0.08783343434333801, "invalid_tail_samples": 24.2, "learning_rate": 7.934885529677505e-06, "loss": 0.0165, "positive_teacher_pairs": 26762.7, "relation_loss": 0.0017583796987310051, "selected_pairs": 26762.7, "step": 24820, "student_distance_mean": 1292.9702758789062, "teacher_distance_mean": 0.8659135282039643, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0017583796987310051, "weighted_relation_loss": 0.0017583796987310051 }, { "action_query_batch_std": 22.1133731842041, "action_query_norm": 939.8104064941406, "action_relation_loss": 0.0018177073216065764, "auxiliary_loss_weight": 1.0, "epoch": 23.22731524789523, "flow_matching_loss": 0.01800379008054733, "grad_norm": 0.09598225355148315, "invalid_tail_samples": 24.5, "learning_rate": 7.905117498314412e-06, "loss": 0.0198, "positive_teacher_pairs": 26683.5, "relation_loss": 0.0018177073216065764, "selected_pairs": 26683.5, "step": 24830, "student_distance_mean": 1272.9452026367187, "teacher_distance_mean": 0.8521635830402374, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0018177073216065764, "weighted_relation_loss": 0.0018177073216065764 }, { "action_query_batch_std": 22.14463520050049, "action_query_norm": 939.582568359375, "action_relation_loss": 0.0018260870245285332, "auxiliary_loss_weight": 1.0, "epoch": 23.23666978484565, "flow_matching_loss": 0.01597917415201664, "grad_norm": 0.08914404362440109, "invalid_tail_samples": 22.2, "learning_rate": 7.87540061620286e-06, "loss": 0.0178, "positive_teacher_pairs": 27226.3, "relation_loss": 0.0018260870245285332, "selected_pairs": 27226.3, "step": 24840, "student_distance_mean": 1270.6425415039062, "teacher_distance_mean": 0.8538430154323577, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.0018260870245285332, "weighted_relation_loss": 0.0018260870245285332 }, { "action_query_batch_std": 22.112700843811034, "action_query_norm": 939.3531555175781, "action_relation_loss": 0.0018185640452429651, "auxiliary_loss_weight": 1.0, "epoch": 23.24602432179607, "flow_matching_loss": 0.01695610862225294, "grad_norm": 0.11831092089414597, "invalid_tail_samples": 24.5, "learning_rate": 7.845734919451647e-06, "loss": 0.0188, "positive_teacher_pairs": 26690.9, "relation_loss": 0.0018185640452429651, "selected_pairs": 26690.9, "step": 24850, "student_distance_mean": 1272.4327514648437, "teacher_distance_mean": 0.8543524026870728, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0018185640452429651, "weighted_relation_loss": 0.0018185640452429651 }, { "action_query_batch_std": 22.159849548339842, "action_query_norm": 939.8872253417969, "action_relation_loss": 0.0018455304089002311, "auxiliary_loss_weight": 1.0, "epoch": 23.255378858746493, "flow_matching_loss": 0.016045077331364156, "grad_norm": 0.09605288505554199, "invalid_tail_samples": 25.1, "learning_rate": 7.816120444107383e-06, "loss": 0.0179, "positive_teacher_pairs": 26548.6, "relation_loss": 0.0018455304089002311, "selected_pairs": 26548.6, "step": 24860, "student_distance_mean": 1277.5666870117188, "teacher_distance_mean": 0.8571955502033234, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0018455304089002311, "weighted_relation_loss": 0.0018455304089002311 }, { "action_query_batch_std": 22.159616661071777, "action_query_norm": 942.3919677734375, "action_relation_loss": 0.0018749875831417739, "auxiliary_loss_weight": 1.0, "epoch": 23.26473339569691, "flow_matching_loss": 0.016553455591201784, "grad_norm": 0.09055368602275848, "invalid_tail_samples": 24.1, "learning_rate": 7.786557226154473e-06, "loss": 0.0184, "positive_teacher_pairs": 26778.5, "relation_loss": 0.0018749875831417739, "selected_pairs": 26778.5, "step": 24870, "student_distance_mean": 1276.176708984375, "teacher_distance_mean": 0.8541529655456543, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0018749875831417739, "weighted_relation_loss": 0.0018749875831417739 }, { "action_query_batch_std": 22.026701164245605, "action_query_norm": 935.5243957519531, "action_relation_loss": 0.001825798861682415, "auxiliary_loss_weight": 1.0, "epoch": 23.274087932647333, "flow_matching_loss": 0.017313226871192456, "grad_norm": 0.08549469709396362, "invalid_tail_samples": 26.4, "learning_rate": 7.757045301514998e-06, "loss": 0.0191, "positive_teacher_pairs": 26249.9, "relation_loss": 0.001825798861682415, "selected_pairs": 26249.9, "step": 24880, "student_distance_mean": 1264.6733032226562, "teacher_distance_mean": 0.8475408613681793, "valid_action_samples": 229.6, "weighted_auxiliary_loss": 0.001825798861682415, "weighted_relation_loss": 0.001825798861682415 }, { "action_query_batch_std": 22.118984985351563, "action_query_norm": 939.693896484375, "action_relation_loss": 0.0018840914592146874, "auxiliary_loss_weight": 1.0, "epoch": 23.283442469597755, "flow_matching_loss": 0.016738577652722596, "grad_norm": 0.08369741588830948, "invalid_tail_samples": 23.8, "learning_rate": 7.727584706048735e-06, "loss": 0.0186, "positive_teacher_pairs": 26849.3, "relation_loss": 0.0018840914592146874, "selected_pairs": 26849.3, "step": 24890, "student_distance_mean": 1273.9092895507813, "teacher_distance_mean": 0.8540769279003143, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0018840914592146874, "weighted_relation_loss": 0.0018840914592146874 }, { "action_query_batch_std": 22.126198959350585, "action_query_norm": 939.7651428222656, "action_relation_loss": 0.001843171287328005, "auxiliary_loss_weight": 1.0, "epoch": 23.292797006548177, "flow_matching_loss": 0.01654304889962077, "grad_norm": 0.08533813059329987, "invalid_tail_samples": 24.1, "learning_rate": 7.698175475553077e-06, "loss": 0.0184, "positive_teacher_pairs": 26786.7, "relation_loss": 0.001843171287328005, "selected_pairs": 26786.7, "step": 24900, "student_distance_mean": 1272.947802734375, "teacher_distance_mean": 0.854044783115387, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.001843171287328005, "weighted_relation_loss": 0.001843171287328005 }, { "action_query_batch_std": 22.410510063171387, "action_query_norm": 951.3367248535156, "action_relation_loss": 0.0018192274146713316, "auxiliary_loss_weight": 1.0, "epoch": 23.302151543498596, "flow_matching_loss": 0.017132631968706846, "grad_norm": 0.08013084530830383, "invalid_tail_samples": 22.3, "learning_rate": 7.668817645763021e-06, "loss": 0.019, "positive_teacher_pairs": 27193.4, "relation_loss": 0.0018192274146713316, "selected_pairs": 27193.4, "step": 24910, "student_distance_mean": 1287.7784545898437, "teacher_distance_mean": 0.8632689654827118, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0018192274146713316, "weighted_relation_loss": 0.0018192274146713316 }, { "action_query_batch_std": 22.160313987731932, "action_query_norm": 941.1125122070313, "action_relation_loss": 0.0018287692917510867, "auxiliary_loss_weight": 1.0, "epoch": 23.311506080449018, "flow_matching_loss": 0.01673715515062213, "grad_norm": 0.08258896321058273, "invalid_tail_samples": 24.0, "learning_rate": 7.639511252351088e-06, "loss": 0.0186, "positive_teacher_pairs": 26798.3, "relation_loss": 0.0018287692917510867, "selected_pairs": 26798.3, "step": 24920, "student_distance_mean": 1275.441552734375, "teacher_distance_mean": 0.8541198790073394, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0018287692917510867, "weighted_relation_loss": 0.0018287692917510867 }, { "action_query_batch_std": 22.22050037384033, "action_query_norm": 940.7260375976563, "action_relation_loss": 0.001842889515683055, "auxiliary_loss_weight": 1.0, "epoch": 23.32086061739944, "flow_matching_loss": 0.01692796926945448, "grad_norm": 0.08627624809741974, "invalid_tail_samples": 24.5, "learning_rate": 7.610256330927324e-06, "loss": 0.0188, "positive_teacher_pairs": 26691.1, "relation_loss": 0.001842889515683055, "selected_pairs": 26691.1, "step": 24930, "student_distance_mean": 1279.15439453125, "teacher_distance_mean": 0.8558902740478516, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.001842889515683055, "weighted_relation_loss": 0.001842889515683055 }, { "action_query_batch_std": 21.681710624694823, "action_query_norm": 926.6500671386718, "action_relation_loss": 0.0018928870791569351, "auxiliary_loss_weight": 1.0, "epoch": 23.330215154349858, "flow_matching_loss": 0.015177822392433881, "grad_norm": 0.08458898961544037, "invalid_tail_samples": 25.9, "learning_rate": 7.581052917039211e-06, "loss": 0.0171, "positive_teacher_pairs": 26368.4, "relation_loss": 0.0018928870791569351, "selected_pairs": 26368.4, "step": 24940, "student_distance_mean": 1250.317236328125, "teacher_distance_mean": 0.8364940047264099, "valid_action_samples": 230.1, "weighted_auxiliary_loss": 0.0018928870791569351, "weighted_relation_loss": 0.0018928870791569351 }, { "action_query_batch_std": 22.22159595489502, "action_query_norm": 940.9997009277344, "action_relation_loss": 0.0017495572566986084, "auxiliary_loss_weight": 1.0, "epoch": 23.33956969130028, "flow_matching_loss": 0.01626146351918578, "grad_norm": 0.0945097804069519, "invalid_tail_samples": 23.5, "learning_rate": 7.551901046171645e-06, "loss": 0.018, "positive_teacher_pairs": 26924.3, "relation_loss": 0.0017495572566986084, "selected_pairs": 26924.3, "step": 24950, "student_distance_mean": 1278.4710571289063, "teacher_distance_mean": 0.8571976661682129, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0017495572566986084, "weighted_relation_loss": 0.0017495572566986084 }, { "action_query_batch_std": 22.14193000793457, "action_query_norm": 939.1692260742187, "action_relation_loss": 0.0018384614260867238, "auxiliary_loss_weight": 1.0, "epoch": 23.348924228250702, "flow_matching_loss": 0.015264274924993515, "grad_norm": 0.08167912811040878, "invalid_tail_samples": 25.6, "learning_rate": 7.522800753746895e-06, "loss": 0.0171, "positive_teacher_pairs": 26442.2, "relation_loss": 0.0018384614260867238, "selected_pairs": 26442.2, "step": 24960, "student_distance_mean": 1278.7123168945313, "teacher_distance_mean": 0.8561252772808075, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.0018384614260867238, "weighted_relation_loss": 0.0018384614260867238 }, { "action_query_batch_std": 22.237505149841308, "action_query_norm": 941.3164672851562, "action_relation_loss": 0.0018511262605898082, "auxiliary_loss_weight": 1.0, "epoch": 23.358278765201124, "flow_matching_loss": 0.016478685196489096, "grad_norm": 0.09715712070465088, "invalid_tail_samples": 24.3, "learning_rate": 7.493752075124577e-06, "loss": 0.0183, "positive_teacher_pairs": 26739.0, "relation_loss": 0.0018511262605898082, "selected_pairs": 26739.0, "step": 24970, "student_distance_mean": 1282.3734497070313, "teacher_distance_mean": 0.8601784944534302, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0018511262605898082, "weighted_relation_loss": 0.0018511262605898082 }, { "action_query_batch_std": 21.7915620803833, "action_query_norm": 926.1956237792969, "action_relation_loss": 0.0018191437469795347, "auxiliary_loss_weight": 1.0, "epoch": 23.367633302151543, "flow_matching_loss": 0.016161592956632376, "grad_norm": 0.09655242413282394, "invalid_tail_samples": 25.4, "learning_rate": 7.464755045601557e-06, "loss": 0.018, "positive_teacher_pairs": 26484.2, "relation_loss": 0.0018191437469795347, "selected_pairs": 26484.2, "step": 24980, "student_distance_mean": 1257.0470581054688, "teacher_distance_mean": 0.8436359584331512, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.0018191437469795347, "weighted_relation_loss": 0.0018191437469795347 }, { "action_query_batch_std": 22.2242525100708, "action_query_norm": 943.5749267578125, "action_relation_loss": 0.0018049191916361452, "auxiliary_loss_weight": 1.0, "epoch": 23.376987839101965, "flow_matching_loss": 0.014938457030802965, "grad_norm": 0.0963616669178009, "invalid_tail_samples": 23.7, "learning_rate": 7.435809700411972e-06, "loss": 0.0167, "positive_teacher_pairs": 26875.9, "relation_loss": 0.0018049191916361452, "selected_pairs": 26875.9, "step": 24990, "student_distance_mean": 1276.83251953125, "teacher_distance_mean": 0.8558652102947235, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0018049191916361452, "weighted_relation_loss": 0.0018049191916361452 }, { "action_query_batch_std": 22.399708366394044, "action_query_norm": 946.4535461425781, "action_relation_loss": 0.0018376770662143827, "auxiliary_loss_weight": 1.0, "epoch": 23.386342376052387, "flow_matching_loss": 0.016196015942841768, "grad_norm": 0.10073453933000565, "invalid_tail_samples": 21.8, "learning_rate": 7.40691607472715e-06, "loss": 0.018, "positive_teacher_pairs": 27314.7, "relation_loss": 0.0018376770662143827, "selected_pairs": 27314.7, "step": 25000, "student_distance_mean": 1286.9049438476563, "teacher_distance_mean": 0.8619038224220276, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.0018376770662143827, "weighted_relation_loss": 0.0018376770662143827 }, { "action_query_batch_std": 21.781400299072267, "action_query_norm": 929.5612915039062, "action_relation_loss": 0.0018818810931406915, "auxiliary_loss_weight": 1.0, "epoch": 23.395696913002805, "flow_matching_loss": 0.015345095656812191, "grad_norm": 0.07857916504144669, "invalid_tail_samples": 23.1, "learning_rate": 7.3780742036555606e-06, "loss": 0.0172, "positive_teacher_pairs": 27018.6, "relation_loss": 0.0018818810931406915, "selected_pairs": 27018.6, "step": 25010, "student_distance_mean": 1252.3462280273438, "teacher_distance_mean": 0.837670648097992, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0018818810931406915, "weighted_relation_loss": 0.0018818810931406915 }, { "action_query_batch_std": 22.241942596435546, "action_query_norm": 943.2455505371094, "action_relation_loss": 0.0017458710703067482, "auxiliary_loss_weight": 1.0, "epoch": 23.405051449953227, "flow_matching_loss": 0.016166389174759387, "grad_norm": 0.08954720199108124, "invalid_tail_samples": 23.0, "learning_rate": 7.349284122242783e-06, "loss": 0.0179, "positive_teacher_pairs": 27034.2, "relation_loss": 0.0017458710703067482, "selected_pairs": 27034.2, "step": 25020, "student_distance_mean": 1274.4147705078126, "teacher_distance_mean": 0.8518600404262543, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0017458710703067482, "weighted_relation_loss": 0.0017458710703067482 }, { "action_query_batch_std": 22.007204627990724, "action_query_norm": 936.2477233886718, "action_relation_loss": 0.001883078645914793, "auxiliary_loss_weight": 1.0, "epoch": 23.41440598690365, "flow_matching_loss": 0.01588985463604331, "grad_norm": 0.08420503884553909, "invalid_tail_samples": 26.2, "learning_rate": 7.320545865471512e-06, "loss": 0.0178, "positive_teacher_pairs": 26298.4, "relation_loss": 0.001883078645914793, "selected_pairs": 26298.4, "step": 25030, "student_distance_mean": 1267.5727783203124, "teacher_distance_mean": 0.8490740776062011, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.001883078645914793, "weighted_relation_loss": 0.001883078645914793 }, { "action_query_batch_std": 22.049134063720704, "action_query_norm": 939.3518493652343, "action_relation_loss": 0.0018297341652214528, "auxiliary_loss_weight": 1.0, "epoch": 23.42376052385407, "flow_matching_loss": 0.015465691220015287, "grad_norm": 0.08358434587717056, "invalid_tail_samples": 22.6, "learning_rate": 7.291859468261425e-06, "loss": 0.0173, "positive_teacher_pairs": 27138.2, "relation_loss": 0.0018297341652214528, "selected_pairs": 27138.2, "step": 25040, "student_distance_mean": 1268.835546875, "teacher_distance_mean": 0.8482806086540222, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0018297341652214528, "weighted_relation_loss": 0.0018297341652214528 }, { "action_query_batch_std": 22.243811225891115, "action_query_norm": 944.576318359375, "action_relation_loss": 0.0018212796072475611, "auxiliary_loss_weight": 1.0, "epoch": 23.43311506080449, "flow_matching_loss": 0.015092315152287483, "grad_norm": 0.10433545708656311, "invalid_tail_samples": 24.4, "learning_rate": 7.263224965469195e-06, "loss": 0.0169, "positive_teacher_pairs": 26711.3, "relation_loss": 0.0018212796072475611, "selected_pairs": 26711.3, "step": 25050, "student_distance_mean": 1276.3160888671875, "teacher_distance_mean": 0.8531992137432098, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0018212796072475611, "weighted_relation_loss": 0.0018212796072475611 }, { "action_query_batch_std": 22.259966468811037, "action_query_norm": 942.6034240722656, "action_relation_loss": 0.001827550621237606, "auxiliary_loss_weight": 1.0, "epoch": 23.44246959775491, "flow_matching_loss": 0.016685374174267055, "grad_norm": 0.09508757293224335, "invalid_tail_samples": 24.8, "learning_rate": 7.234642391888446e-06, "loss": 0.0185, "positive_teacher_pairs": 26623.0, "relation_loss": 0.001827550621237606, "selected_pairs": 26623.0, "step": 25060, "student_distance_mean": 1286.6953735351562, "teacher_distance_mean": 0.8610044360160828, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.001827550621237606, "weighted_relation_loss": 0.001827550621237606 }, { "action_query_batch_std": 22.120360946655275, "action_query_norm": 937.4982482910157, "action_relation_loss": 0.0018531724577769636, "auxiliary_loss_weight": 1.0, "epoch": 23.451824134705333, "flow_matching_loss": 0.01687236800789833, "grad_norm": 0.09613420069217682, "invalid_tail_samples": 24.0, "learning_rate": 7.206111782249697e-06, "loss": 0.0187, "positive_teacher_pairs": 26804.4, "relation_loss": 0.0018531724577769636, "selected_pairs": 26804.4, "step": 25070, "student_distance_mean": 1269.2867919921875, "teacher_distance_mean": 0.8511164486408234, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0018531724577769636, "weighted_relation_loss": 0.0018531724577769636 }, { "action_query_batch_std": 22.28568229675293, "action_query_norm": 943.1231872558594, "action_relation_loss": 0.0018197202822193503, "auxiliary_loss_weight": 1.0, "epoch": 23.46117867165575, "flow_matching_loss": 0.016316348686814308, "grad_norm": 0.09085766226053238, "invalid_tail_samples": 23.2, "learning_rate": 7.1776331712203385e-06, "loss": 0.0181, "positive_teacher_pairs": 26987.8, "relation_loss": 0.0018197202822193503, "selected_pairs": 26987.8, "step": 25080, "student_distance_mean": 1281.5327880859375, "teacher_distance_mean": 0.8602640450000762, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0018197202822193503, "weighted_relation_loss": 0.0018197202822193503 }, { "action_query_batch_std": 22.28453884124756, "action_query_norm": 942.4286865234375, "action_relation_loss": 0.0017620490631088614, "auxiliary_loss_weight": 1.0, "epoch": 23.470533208606174, "flow_matching_loss": 0.015753413457423447, "grad_norm": 0.09419969469308853, "invalid_tail_samples": 23.7, "learning_rate": 7.149206593404561e-06, "loss": 0.0175, "positive_teacher_pairs": 26871.2, "relation_loss": 0.0017620490631088614, "selected_pairs": 26871.2, "step": 25090, "student_distance_mean": 1281.9514282226562, "teacher_distance_mean": 0.862037068605423, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0017620490631088614, "weighted_relation_loss": 0.0017620490631088614 }, { "action_query_batch_std": 22.124917221069335, "action_query_norm": 935.6393127441406, "action_relation_loss": 0.00182382419006899, "auxiliary_loss_weight": 1.0, "epoch": 23.479887745556596, "flow_matching_loss": 0.01615153029561043, "grad_norm": 0.08497174084186554, "invalid_tail_samples": 24.7, "learning_rate": 7.120832083343337e-06, "loss": 0.018, "positive_teacher_pairs": 26639.2, "relation_loss": 0.00182382419006899, "selected_pairs": 26639.2, "step": 25100, "student_distance_mean": 1269.2105590820313, "teacher_distance_mean": 0.8525038421154022, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.00182382419006899, "weighted_relation_loss": 0.00182382419006899 }, { "action_query_batch_std": 22.124965286254884, "action_query_norm": 939.7210876464844, "action_relation_loss": 0.0018069213605485857, "auxiliary_loss_weight": 1.0, "epoch": 23.489242282507014, "flow_matching_loss": 0.014124931301921606, "grad_norm": 0.0985042080283165, "invalid_tail_samples": 22.9, "learning_rate": 7.092509675514369e-06, "loss": 0.0159, "positive_teacher_pairs": 27055.6, "relation_loss": 0.0018069213605485857, "selected_pairs": 27055.6, "step": 25110, "student_distance_mean": 1277.6143676757813, "teacher_distance_mean": 0.8569399237632751, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0018069213605485857, "weighted_relation_loss": 0.0018069213605485857 }, { "action_query_batch_std": 22.169658660888672, "action_query_norm": 940.3323181152343, "action_relation_loss": 0.001834302255883813, "auxiliary_loss_weight": 1.0, "epoch": 23.498596819457436, "flow_matching_loss": 0.01631707027554512, "grad_norm": 0.09745928645133972, "invalid_tail_samples": 23.1, "learning_rate": 7.064239404332063e-06, "loss": 0.0182, "positive_teacher_pairs": 27012.7, "relation_loss": 0.001834302255883813, "selected_pairs": 27012.7, "step": 25120, "student_distance_mean": 1273.5120239257812, "teacher_distance_mean": 0.8545400619506835, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.001834302255883813, "weighted_relation_loss": 0.001834302255883813 }, { "action_query_batch_std": 22.159202766418456, "action_query_norm": 941.3821472167969, "action_relation_loss": 0.0018548166495747863, "auxiliary_loss_weight": 1.0, "epoch": 23.507951356407858, "flow_matching_loss": 0.01625147871673107, "grad_norm": 0.09306689351797104, "invalid_tail_samples": 22.2, "learning_rate": 7.03602130414745e-06, "loss": 0.0181, "positive_teacher_pairs": 27225.8, "relation_loss": 0.0018548166495747863, "selected_pairs": 27225.8, "step": 25130, "student_distance_mean": 1275.3853881835937, "teacher_distance_mean": 0.8570019364356994, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.0018548166495747863, "weighted_relation_loss": 0.0018548166495747863 }, { "action_query_batch_std": 22.15911293029785, "action_query_norm": 938.8249145507813, "action_relation_loss": 0.0018462654086761176, "auxiliary_loss_weight": 1.0, "epoch": 23.51730589335828, "flow_matching_loss": 0.016878879349678754, "grad_norm": 0.09287315607070923, "invalid_tail_samples": 23.1, "learning_rate": 7.007855409248198e-06, "loss": 0.0187, "positive_teacher_pairs": 27010.0, "relation_loss": 0.0018462654086761176, "selected_pairs": 27010.0, "step": 25140, "student_distance_mean": 1270.4291137695313, "teacher_distance_mean": 0.8534028589725494, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0018462654086761176, "weighted_relation_loss": 0.0018462654086761176 }, { "action_query_batch_std": 22.244082069396974, "action_query_norm": 947.0979187011719, "action_relation_loss": 0.0017821941175498069, "auxiliary_loss_weight": 1.0, "epoch": 23.5266604303087, "flow_matching_loss": 0.015367137081921101, "grad_norm": 0.0771617591381073, "invalid_tail_samples": 22.7, "learning_rate": 6.979741753858521e-06, "loss": 0.0171, "positive_teacher_pairs": 27117.5, "relation_loss": 0.0017821941175498069, "selected_pairs": 27117.5, "step": 25150, "student_distance_mean": 1282.0864990234375, "teacher_distance_mean": 0.8620621621608734, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0017821941175498069, "weighted_relation_loss": 0.0017821941175498069 }, { "action_query_batch_std": 22.030488204956054, "action_query_norm": 936.3713256835938, "action_relation_loss": 0.0018043427611701191, "auxiliary_loss_weight": 1.0, "epoch": 23.53601496725912, "flow_matching_loss": 0.016753938887268303, "grad_norm": 0.09513752162456512, "invalid_tail_samples": 24.4, "learning_rate": 6.951680372139158e-06, "loss": 0.0186, "positive_teacher_pairs": 26711.1, "relation_loss": 0.0018043427611701191, "selected_pairs": 26711.1, "step": 25160, "student_distance_mean": 1268.615966796875, "teacher_distance_mean": 0.852127081155777, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0018043427611701191, "weighted_relation_loss": 0.0018043427611701191 }, { "action_query_batch_std": 21.866772842407226, "action_query_norm": 929.858203125, "action_relation_loss": 0.0018323801225051284, "auxiliary_loss_weight": 1.0, "epoch": 23.545369504209543, "flow_matching_loss": 0.01745021007955074, "grad_norm": 0.10590063780546188, "invalid_tail_samples": 23.2, "learning_rate": 6.923671298187334e-06, "loss": 0.0193, "positive_teacher_pairs": 26988.1, "relation_loss": 0.0018323801225051284, "selected_pairs": 26988.1, "step": 25170, "student_distance_mean": 1255.2921997070312, "teacher_distance_mean": 0.8429591476917266, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0018323801225051284, "weighted_relation_loss": 0.0018323801225051284 }, { "action_query_batch_std": 22.109529304504395, "action_query_norm": 940.0903930664062, "action_relation_loss": 0.0017985297716222703, "auxiliary_loss_weight": 1.0, "epoch": 23.55472404115996, "flow_matching_loss": 0.014507029857486486, "grad_norm": 0.08024866133928299, "invalid_tail_samples": 23.5, "learning_rate": 6.895714566036704e-06, "loss": 0.0163, "positive_teacher_pairs": 26915.5, "relation_loss": 0.0017985297716222703, "selected_pairs": 26915.5, "step": 25180, "student_distance_mean": 1265.6993774414063, "teacher_distance_mean": 0.8523014485836029, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0017985297716222703, "weighted_relation_loss": 0.0017985297716222703 }, { "action_query_batch_std": 22.299501609802245, "action_query_norm": 943.3630493164062, "action_relation_loss": 0.0017755298875272274, "auxiliary_loss_weight": 1.0, "epoch": 23.564078578110383, "flow_matching_loss": 0.015431160107254982, "grad_norm": 0.11707131564617157, "invalid_tail_samples": 22.3, "learning_rate": 6.86781020965736e-06, "loss": 0.0172, "positive_teacher_pairs": 27198.2, "relation_loss": 0.0017755298875272274, "selected_pairs": 27198.2, "step": 25190, "student_distance_mean": 1277.142041015625, "teacher_distance_mean": 0.8594076454639434, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0017755298875272274, "weighted_relation_loss": 0.0017755298875272274 }, { "action_query_batch_std": 22.171307182312013, "action_query_norm": 942.0033447265625, "action_relation_loss": 0.0018427095026709139, "auxiliary_loss_weight": 1.0, "epoch": 23.573433115060805, "flow_matching_loss": 0.015815034694969653, "grad_norm": 0.09463321417570114, "invalid_tail_samples": 24.2, "learning_rate": 6.839958262955709e-06, "loss": 0.0177, "positive_teacher_pairs": 26762.5, "relation_loss": 0.0018427095026709139, "selected_pairs": 26762.5, "step": 25200, "student_distance_mean": 1276.3328857421875, "teacher_distance_mean": 0.8574173092842102, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0018427095026709139, "weighted_relation_loss": 0.0018427095026709139 }, { "action_query_batch_std": 22.315861892700195, "action_query_norm": 945.3705078125, "action_relation_loss": 0.0017991083906963468, "auxiliary_loss_weight": 1.0, "epoch": 23.582787652011227, "flow_matching_loss": 0.01612467849627137, "grad_norm": 0.09196314215660095, "invalid_tail_samples": 21.6, "learning_rate": 6.8121587597744894e-06, "loss": 0.0179, "positive_teacher_pairs": 27359.0, "relation_loss": 0.0017991083906963468, "selected_pairs": 27359.0, "step": 25210, "student_distance_mean": 1283.7565795898438, "teacher_distance_mean": 0.8614673972129822, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.0017991083906963468, "weighted_relation_loss": 0.0017991083906963468 }, { "action_query_batch_std": 22.241204452514648, "action_query_norm": 942.2562133789063, "action_relation_loss": 0.0017929825000464917, "auxiliary_loss_weight": 1.0, "epoch": 23.592142188961645, "flow_matching_loss": 0.016054367087781428, "grad_norm": 0.09305454790592194, "invalid_tail_samples": 26.0, "learning_rate": 6.784411733892732e-06, "loss": 0.0178, "positive_teacher_pairs": 26344.1, "relation_loss": 0.0017929825000464917, "selected_pairs": 26344.1, "step": 25220, "student_distance_mean": 1277.6255126953124, "teacher_distance_mean": 0.8575632810592652, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.0017929825000464917, "weighted_relation_loss": 0.0017929825000464917 }, { "action_query_batch_std": 22.202534103393553, "action_query_norm": 939.3240295410156, "action_relation_loss": 0.0018163939588703216, "auxiliary_loss_weight": 1.0, "epoch": 23.601496725912067, "flow_matching_loss": 0.014383386634290219, "grad_norm": 0.099675253033638, "invalid_tail_samples": 22.0, "learning_rate": 6.756717219025666e-06, "loss": 0.0162, "positive_teacher_pairs": 27274.5, "relation_loss": 0.0018163939588703216, "selected_pairs": 27274.5, "step": 25230, "student_distance_mean": 1273.9852661132813, "teacher_distance_mean": 0.8550836324691773, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.0018163939588703216, "weighted_relation_loss": 0.0018163939588703216 }, { "action_query_batch_std": 21.99821243286133, "action_query_norm": 935.3088562011719, "action_relation_loss": 0.0018284297664649784, "auxiliary_loss_weight": 1.0, "epoch": 23.61085126286249, "flow_matching_loss": 0.015368403866887093, "grad_norm": 0.08474962413311005, "invalid_tail_samples": 21.6, "learning_rate": 6.729075248824762e-06, "loss": 0.0172, "positive_teacher_pairs": 27363.7, "relation_loss": 0.0018284297664649784, "selected_pairs": 27363.7, "step": 25240, "student_distance_mean": 1266.23564453125, "teacher_distance_mean": 0.8501187860965729, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.0018284297664649784, "weighted_relation_loss": 0.0018284297664649784 }, { "action_query_batch_std": 22.05908946990967, "action_query_norm": 937.8899291992187, "action_relation_loss": 0.0018014764646068215, "auxiliary_loss_weight": 1.0, "epoch": 23.620205799812908, "flow_matching_loss": 0.01578011503443122, "grad_norm": 0.10224226117134094, "invalid_tail_samples": 22.9, "learning_rate": 6.701485856877615e-06, "loss": 0.0176, "positive_teacher_pairs": 27063.2, "relation_loss": 0.0018014764646068215, "selected_pairs": 27063.2, "step": 25250, "student_distance_mean": 1273.4464599609375, "teacher_distance_mean": 0.8541735887527466, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0018014764646068215, "weighted_relation_loss": 0.0018014764646068215 }, { "action_query_batch_std": 22.174966621398926, "action_query_norm": 938.346044921875, "action_relation_loss": 0.0017354430281557142, "auxiliary_loss_weight": 1.0, "epoch": 23.62956033676333, "flow_matching_loss": 0.01683595050126314, "grad_norm": 0.07824978977441788, "invalid_tail_samples": 26.2, "learning_rate": 6.673949076707925e-06, "loss": 0.0186, "positive_teacher_pairs": 26298.0, "relation_loss": 0.0017354430281557142, "selected_pairs": 26298.0, "step": 25260, "student_distance_mean": 1272.6821166992188, "teacher_distance_mean": 0.8533273279666901, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.0017354430281557142, "weighted_relation_loss": 0.0017354430281557142 }, { "action_query_batch_std": 22.353773880004884, "action_query_norm": 946.9124206542969, "action_relation_loss": 0.0017766937613487243, "auxiliary_loss_weight": 1.0, "epoch": 23.63891487371375, "flow_matching_loss": 0.016078580729663373, "grad_norm": 0.09174448996782303, "invalid_tail_samples": 25.2, "learning_rate": 6.646464941775499e-06, "loss": 0.0179, "positive_teacher_pairs": 26523.9, "relation_loss": 0.0017766937613487243, "selected_pairs": 26523.9, "step": 25270, "student_distance_mean": 1289.290185546875, "teacher_distance_mean": 0.8642933785915374, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0017766937613487243, "weighted_relation_loss": 0.0017766937613487243 }, { "action_query_batch_std": 22.04238090515137, "action_query_norm": 935.7156616210938, "action_relation_loss": 0.0017633070121519268, "auxiliary_loss_weight": 1.0, "epoch": 23.648269410664174, "flow_matching_loss": 0.013831307087093592, "grad_norm": 0.08358601480722427, "invalid_tail_samples": 23.9, "learning_rate": 6.619033485476128e-06, "loss": 0.0156, "positive_teacher_pairs": 26828.6, "relation_loss": 0.0017633070121519268, "selected_pairs": 26828.6, "step": 25280, "student_distance_mean": 1268.1832275390625, "teacher_distance_mean": 0.8521145522594452, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0017633070121519268, "weighted_relation_loss": 0.0017633070121519268 }, { "action_query_batch_std": 22.10028076171875, "action_query_norm": 938.3593811035156, "action_relation_loss": 0.0018008165643550456, "auxiliary_loss_weight": 1.0, "epoch": 23.657623947614592, "flow_matching_loss": 0.016231103893369438, "grad_norm": 0.08827579021453857, "invalid_tail_samples": 23.1, "learning_rate": 6.59165474114164e-06, "loss": 0.018, "positive_teacher_pairs": 27009.3, "relation_loss": 0.0018008165643550456, "selected_pairs": 27009.3, "step": 25290, "student_distance_mean": 1276.1938720703124, "teacher_distance_mean": 0.8544628262519837, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0018008165643550456, "weighted_relation_loss": 0.0018008165643550456 }, { "action_query_batch_std": 22.248405838012694, "action_query_norm": 939.939208984375, "action_relation_loss": 0.0017520173685625195, "auxiliary_loss_weight": 1.0, "epoch": 23.666978484565014, "flow_matching_loss": 0.015348510537296533, "grad_norm": 0.06924594193696976, "invalid_tail_samples": 25.3, "learning_rate": 6.564328742039783e-06, "loss": 0.0171, "positive_teacher_pairs": 26507.6, "relation_loss": 0.0017520173685625195, "selected_pairs": 26507.6, "step": 25300, "student_distance_mean": 1280.6222900390626, "teacher_distance_mean": 0.8608613610267639, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0017520173685625195, "weighted_relation_loss": 0.0017520173685625195 }, { "action_query_batch_std": 22.08845748901367, "action_query_norm": 936.03232421875, "action_relation_loss": 0.00184304085560143, "auxiliary_loss_weight": 1.0, "epoch": 23.676333021515436, "flow_matching_loss": 0.015869936998933555, "grad_norm": 0.10293327271938324, "invalid_tail_samples": 24.6, "learning_rate": 6.537055521374219e-06, "loss": 0.0177, "positive_teacher_pairs": 26662.2, "relation_loss": 0.00184304085560143, "selected_pairs": 26662.2, "step": 25310, "student_distance_mean": 1271.1925048828125, "teacher_distance_mean": 0.8551479160785675, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.00184304085560143, "weighted_relation_loss": 0.00184304085560143 }, { "action_query_batch_std": 22.111224746704103, "action_query_norm": 935.2836853027344, "action_relation_loss": 0.001851055270526558, "auxiliary_loss_weight": 1.0, "epoch": 23.685687558465855, "flow_matching_loss": 0.016576215904206038, "grad_norm": 0.082497738301754, "invalid_tail_samples": 25.7, "learning_rate": 6.509835112284485e-06, "loss": 0.0184, "positive_teacher_pairs": 26413.3, "relation_loss": 0.001851055270526558, "selected_pairs": 26413.3, "step": 25320, "student_distance_mean": 1273.4200561523437, "teacher_distance_mean": 0.8562312662601471, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.001851055270526558, "weighted_relation_loss": 0.001851055270526558 }, { "action_query_batch_std": 21.818549156188965, "action_query_norm": 927.6651733398437, "action_relation_loss": 0.001813706732355058, "auxiliary_loss_weight": 1.0, "epoch": 23.695042095416277, "flow_matching_loss": 0.015594248753041029, "grad_norm": 0.08908206969499588, "invalid_tail_samples": 23.5, "learning_rate": 6.482667547845944e-06, "loss": 0.0174, "positive_teacher_pairs": 26928.2, "relation_loss": 0.001813706732355058, "selected_pairs": 26928.2, "step": 25330, "student_distance_mean": 1255.4444946289063, "teacher_distance_mean": 0.8429404199123383, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.001813706732355058, "weighted_relation_loss": 0.001813706732355058 }, { "action_query_batch_std": 21.85966262817383, "action_query_norm": 929.5366455078125, "action_relation_loss": 0.0018151622614823281, "auxiliary_loss_weight": 1.0, "epoch": 23.7043966323667, "flow_matching_loss": 0.01591399610042572, "grad_norm": 0.10660485178232193, "invalid_tail_samples": 24.9, "learning_rate": 6.455552861069736e-06, "loss": 0.0177, "positive_teacher_pairs": 26608.2, "relation_loss": 0.0018151622614823281, "selected_pairs": 26608.2, "step": 25340, "student_distance_mean": 1265.8705078125, "teacher_distance_mean": 0.8509035408496857, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0018151622614823281, "weighted_relation_loss": 0.0018151622614823281 }, { "action_query_batch_std": 22.146798515319823, "action_query_norm": 939.0877807617187, "action_relation_loss": 0.0018199499347247184, "auxiliary_loss_weight": 1.0, "epoch": 23.71375116931712, "flow_matching_loss": 0.016833561658859252, "grad_norm": 0.09433749318122864, "invalid_tail_samples": 24.2, "learning_rate": 6.428491084902788e-06, "loss": 0.0187, "positive_teacher_pairs": 26758.3, "relation_loss": 0.0018199499347247184, "selected_pairs": 26758.3, "step": 25350, "student_distance_mean": 1276.12080078125, "teacher_distance_mean": 0.8587798416614533, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0018199499347247184, "weighted_relation_loss": 0.0018199499347247184 }, { "action_query_batch_std": 22.010514068603516, "action_query_norm": 934.7322998046875, "action_relation_loss": 0.001846899196971208, "auxiliary_loss_weight": 1.0, "epoch": 23.72310570626754, "flow_matching_loss": 0.01527231177315116, "grad_norm": 0.07906192541122437, "invalid_tail_samples": 22.9, "learning_rate": 6.401482252227698e-06, "loss": 0.0171, "positive_teacher_pairs": 27056.5, "relation_loss": 0.001846899196971208, "selected_pairs": 27056.5, "step": 25360, "student_distance_mean": 1264.9164184570313, "teacher_distance_mean": 0.8500539839267731, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.001846899196971208, "weighted_relation_loss": 0.001846899196971208 }, { "action_query_batch_std": 22.15907802581787, "action_query_norm": 938.5503479003906, "action_relation_loss": 0.0017964007682166993, "auxiliary_loss_weight": 1.0, "epoch": 23.73246024321796, "flow_matching_loss": 0.013827166240662336, "grad_norm": 0.07454440742731094, "invalid_tail_samples": 23.5, "learning_rate": 6.37452639586274e-06, "loss": 0.0156, "positive_teacher_pairs": 26917.3, "relation_loss": 0.0017964007682166993, "selected_pairs": 26917.3, "step": 25370, "student_distance_mean": 1271.03232421875, "teacher_distance_mean": 0.8543863475322724, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0017964007682166993, "weighted_relation_loss": 0.0017964007682166993 }, { "action_query_batch_std": 22.239138221740724, "action_query_norm": 941.9878723144532, "action_relation_loss": 0.0018017549766227603, "auxiliary_loss_weight": 1.0, "epoch": 23.741814780168383, "flow_matching_loss": 0.014755924232304096, "grad_norm": 0.0821191817522049, "invalid_tail_samples": 23.5, "learning_rate": 6.347623548561826e-06, "loss": 0.0166, "positive_teacher_pairs": 26919.8, "relation_loss": 0.0018017549766227603, "selected_pairs": 26919.8, "step": 25380, "student_distance_mean": 1275.29755859375, "teacher_distance_mean": 0.8581567645072937, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0018017549766227603, "weighted_relation_loss": 0.0018017549766227603 }, { "action_query_batch_std": 22.23569812774658, "action_query_norm": 940.7569946289062, "action_relation_loss": 0.0017875217483378947, "auxiliary_loss_weight": 1.0, "epoch": 23.7511693171188, "flow_matching_loss": 0.015865239873528482, "grad_norm": 0.06872659921646118, "invalid_tail_samples": 23.4, "learning_rate": 6.320773743014441e-06, "loss": 0.0177, "positive_teacher_pairs": 26946.2, "relation_loss": 0.0017875217483378947, "selected_pairs": 26946.2, "step": 25390, "student_distance_mean": 1275.7987670898438, "teacher_distance_mean": 0.8573069274425507, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0017875217483378947, "weighted_relation_loss": 0.0017875217483378947 }, { "action_query_batch_std": 22.316682052612304, "action_query_norm": 945.9628356933594, "action_relation_loss": 0.0017742979805916547, "auxiliary_loss_weight": 1.0, "epoch": 23.760523854069223, "flow_matching_loss": 0.015722373221069574, "grad_norm": 0.07194793224334717, "invalid_tail_samples": 23.5, "learning_rate": 6.293977011845648e-06, "loss": 0.0175, "positive_teacher_pairs": 26923.0, "relation_loss": 0.0017742979805916547, "selected_pairs": 26923.0, "step": 25400, "student_distance_mean": 1289.7569458007813, "teacher_distance_mean": 0.8643244743347168, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0017742979805916547, "weighted_relation_loss": 0.0017742979805916547 }, { "action_query_batch_std": 22.057850646972657, "action_query_norm": 935.7562194824219, "action_relation_loss": 0.0017720210598781705, "auxiliary_loss_weight": 1.0, "epoch": 23.769878391019645, "flow_matching_loss": 0.014782472979277372, "grad_norm": 0.10220646113157272, "invalid_tail_samples": 25.2, "learning_rate": 6.2672333876159835e-06, "loss": 0.0166, "positive_teacher_pairs": 26533.1, "relation_loss": 0.0017720210598781705, "selected_pairs": 26533.1, "step": 25410, "student_distance_mean": 1266.702294921875, "teacher_distance_mean": 0.8491647601127624, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0017720210598781705, "weighted_relation_loss": 0.0017720210598781705 }, { "action_query_batch_std": 22.175879669189452, "action_query_norm": 938.4290161132812, "action_relation_loss": 0.00182309317169711, "auxiliary_loss_weight": 1.0, "epoch": 23.779232927970064, "flow_matching_loss": 0.016199867613613604, "grad_norm": 0.0954524353146553, "invalid_tail_samples": 22.5, "learning_rate": 6.2405429028215e-06, "loss": 0.018, "positive_teacher_pairs": 27150.1, "relation_loss": 0.00182309317169711, "selected_pairs": 27150.1, "step": 25420, "student_distance_mean": 1278.72998046875, "teacher_distance_mean": 0.8573266923427582, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.00182309317169711, "weighted_relation_loss": 0.00182309317169711 }, { "action_query_batch_std": 21.968259620666505, "action_query_norm": 932.3322509765625, "action_relation_loss": 0.0017611304065212607, "auxiliary_loss_weight": 1.0, "epoch": 23.788587464920486, "flow_matching_loss": 0.016600245051085948, "grad_norm": 0.08784239739179611, "invalid_tail_samples": 25.5, "learning_rate": 6.213905589893631e-06, "loss": 0.0184, "positive_teacher_pairs": 26458.2, "relation_loss": 0.0017611304065212607, "selected_pairs": 26458.2, "step": 25430, "student_distance_mean": 1268.3833374023438, "teacher_distance_mean": 0.8517082035541534, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0017611304065212607, "weighted_relation_loss": 0.0017611304065212607 }, { "action_query_batch_std": 22.3005090713501, "action_query_norm": 943.9110534667968, "action_relation_loss": 0.0018719815299846232, "auxiliary_loss_weight": 1.0, "epoch": 23.797942001870908, "flow_matching_loss": 0.015081565454602241, "grad_norm": 0.0834413543343544, "invalid_tail_samples": 23.3, "learning_rate": 6.187321481199221e-06, "loss": 0.017, "positive_teacher_pairs": 26967.1, "relation_loss": 0.0018719815299846232, "selected_pairs": 26967.1, "step": 25440, "student_distance_mean": 1285.456298828125, "teacher_distance_mean": 0.8642821550369263, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0018719815299846232, "weighted_relation_loss": 0.0018719815299846232 }, { "action_query_batch_std": 22.177320671081542, "action_query_norm": 941.4417663574219, "action_relation_loss": 0.0017726245452649892, "auxiliary_loss_weight": 1.0, "epoch": 23.80729653882133, "flow_matching_loss": 0.017446244601160288, "grad_norm": 0.09624958783388138, "invalid_tail_samples": 23.9, "learning_rate": 6.1607906090404895e-06, "loss": 0.0192, "positive_teacher_pairs": 26824.3, "relation_loss": 0.0017726245452649892, "selected_pairs": 26824.3, "step": 25450, "student_distance_mean": 1275.098876953125, "teacher_distance_mean": 0.8573077023029327, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0017726245452649892, "weighted_relation_loss": 0.0017726245452649892 }, { "action_query_batch_std": 22.051131439208984, "action_query_norm": 935.4091003417968, "action_relation_loss": 0.0017603260115720333, "auxiliary_loss_weight": 1.0, "epoch": 23.81665107577175, "flow_matching_loss": 0.016669325157999994, "grad_norm": 0.0887170284986496, "invalid_tail_samples": 23.2, "learning_rate": 6.134313005654929e-06, "loss": 0.0184, "positive_teacher_pairs": 27002.4, "relation_loss": 0.0017603260115720333, "selected_pairs": 27002.4, "step": 25460, "student_distance_mean": 1272.0886962890625, "teacher_distance_mean": 0.8550746977329254, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0017603260115720333, "weighted_relation_loss": 0.0017603260115720333 }, { "action_query_batch_std": 22.017108535766603, "action_query_norm": 932.9759155273438, "action_relation_loss": 0.0018441354273818432, "auxiliary_loss_weight": 1.0, "epoch": 23.82600561272217, "flow_matching_loss": 0.016834800038486718, "grad_norm": 0.09348328411579132, "invalid_tail_samples": 24.9, "learning_rate": 6.107888703215337e-06, "loss": 0.0187, "positive_teacher_pairs": 26602.2, "relation_loss": 0.0018441354273818432, "selected_pairs": 26602.2, "step": 25470, "student_distance_mean": 1260.8411254882812, "teacher_distance_mean": 0.8469401121139526, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0018441354273818432, "weighted_relation_loss": 0.0018441354273818432 }, { "action_query_batch_std": 21.984386253356934, "action_query_norm": 933.5970336914063, "action_relation_loss": 0.0018445236259140075, "auxiliary_loss_weight": 1.0, "epoch": 23.835360149672592, "flow_matching_loss": 0.016056306287646295, "grad_norm": 0.10841255635023117, "invalid_tail_samples": 25.1, "learning_rate": 6.081517733829722e-06, "loss": 0.0179, "positive_teacher_pairs": 26549.8, "relation_loss": 0.0018445236259140075, "selected_pairs": 26549.8, "step": 25480, "student_distance_mean": 1267.058740234375, "teacher_distance_mean": 0.8493653535842896, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0018445236259140075, "weighted_relation_loss": 0.0018445236259140075 }, { "action_query_batch_std": 22.167781639099122, "action_query_norm": 940.0411682128906, "action_relation_loss": 0.0018264707643538714, "auxiliary_loss_weight": 1.0, "epoch": 23.84471468662301, "flow_matching_loss": 0.015137238427996635, "grad_norm": 0.08742012083530426, "invalid_tail_samples": 20.8, "learning_rate": 6.055200129541294e-06, "loss": 0.017, "positive_teacher_pairs": 27551.4, "relation_loss": 0.0018264707643538714, "selected_pairs": 27551.4, "step": 25490, "student_distance_mean": 1273.8508666992188, "teacher_distance_mean": 0.8546085596084595, "valid_action_samples": 235.2, "weighted_auxiliary_loss": 0.0018264707643538714, "weighted_relation_loss": 0.0018264707643538714 }, { "action_query_batch_std": 21.921037101745604, "action_query_norm": 932.0503234863281, "action_relation_loss": 0.0017755592241883277, "auxiliary_loss_weight": 1.0, "epoch": 23.854069223573433, "flow_matching_loss": 0.01591810043901205, "grad_norm": 0.1242055892944336, "invalid_tail_samples": 24.8, "learning_rate": 6.0289359223284434e-06, "loss": 0.0177, "positive_teacher_pairs": 26616.7, "relation_loss": 0.0017755592241883277, "selected_pairs": 26616.7, "step": 25500, "student_distance_mean": 1262.3786499023438, "teacher_distance_mean": 0.848243910074234, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0017755592241883277, "weighted_relation_loss": 0.0017755592241883277 }, { "action_query_batch_std": 22.46374855041504, "action_query_norm": 949.1365112304687, "action_relation_loss": 0.0018175548408180474, "auxiliary_loss_weight": 1.0, "epoch": 23.863423760523855, "flow_matching_loss": 0.015836260002106427, "grad_norm": 0.08606043457984924, "invalid_tail_samples": 22.1, "learning_rate": 6.002725144104648e-06, "loss": 0.0177, "positive_teacher_pairs": 27244.8, "relation_loss": 0.0018175548408180474, "selected_pairs": 27244.8, "step": 25510, "student_distance_mean": 1287.325048828125, "teacher_distance_mean": 0.8631963133811951, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0018175548408180474, "weighted_relation_loss": 0.0018175548408180474 }, { "action_query_batch_std": 22.001044273376465, "action_query_norm": 935.6329223632813, "action_relation_loss": 0.0017952987342141568, "auxiliary_loss_weight": 1.0, "epoch": 23.872778297474277, "flow_matching_loss": 0.016568905767053367, "grad_norm": 0.07874246686697006, "invalid_tail_samples": 24.0, "learning_rate": 5.976567826718477e-06, "loss": 0.0184, "positive_teacher_pairs": 26802.6, "relation_loss": 0.0017952987342141568, "selected_pairs": 26802.6, "step": 25520, "student_distance_mean": 1261.8986572265626, "teacher_distance_mean": 0.8483396530151367, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0017952987342141568, "weighted_relation_loss": 0.0017952987342141568 }, { "action_query_batch_std": 22.296627235412597, "action_query_norm": 943.6848815917969, "action_relation_loss": 0.0018151567899622023, "auxiliary_loss_weight": 1.0, "epoch": 23.882132834424695, "flow_matching_loss": 0.016935376357287167, "grad_norm": 0.0783505067229271, "invalid_tail_samples": 23.1, "learning_rate": 5.9504640019535315e-06, "loss": 0.0188, "positive_teacher_pairs": 27007.7, "relation_loss": 0.0018151567899622023, "selected_pairs": 27007.7, "step": 25530, "student_distance_mean": 1283.1025512695312, "teacher_distance_mean": 0.8622898459434509, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0018151567899622023, "weighted_relation_loss": 0.0018151567899622023 }, { "action_query_batch_std": 22.143511962890624, "action_query_norm": 939.5610900878906, "action_relation_loss": 0.0018454666715115309, "auxiliary_loss_weight": 1.0, "epoch": 23.891487371375117, "flow_matching_loss": 0.014835096523165702, "grad_norm": 0.08871153742074966, "invalid_tail_samples": 23.4, "learning_rate": 5.924413701528414e-06, "loss": 0.0167, "positive_teacher_pairs": 26937.4, "relation_loss": 0.0018454666715115309, "selected_pairs": 26937.4, "step": 25540, "student_distance_mean": 1271.8310668945312, "teacher_distance_mean": 0.8544721662998199, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0018454666715115309, "weighted_relation_loss": 0.0018454666715115309 }, { "action_query_batch_std": 22.1390661239624, "action_query_norm": 938.8838623046875, "action_relation_loss": 0.0018321251031011344, "auxiliary_loss_weight": 1.0, "epoch": 23.90084190832554, "flow_matching_loss": 0.016792484745383262, "grad_norm": 0.07326790690422058, "invalid_tail_samples": 24.4, "learning_rate": 5.898416957096703e-06, "loss": 0.0186, "positive_teacher_pairs": 26711.8, "relation_loss": 0.0018321251031011344, "selected_pairs": 26711.8, "step": 25550, "student_distance_mean": 1271.6882568359374, "teacher_distance_mean": 0.8529676735401154, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0018321251031011344, "weighted_relation_loss": 0.0018321251031011344 }, { "action_query_batch_std": 22.13315906524658, "action_query_norm": 938.1961364746094, "action_relation_loss": 0.001850014564115554, "auxiliary_loss_weight": 1.0, "epoch": 23.910196445275957, "flow_matching_loss": 0.015214305836707354, "grad_norm": 0.09458249062299728, "invalid_tail_samples": 22.7, "learning_rate": 5.872473800246913e-06, "loss": 0.0171, "positive_teacher_pairs": 27112.2, "relation_loss": 0.001850014564115554, "selected_pairs": 27112.2, "step": 25560, "student_distance_mean": 1273.7437866210937, "teacher_distance_mean": 0.855935400724411, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.001850014564115554, "weighted_relation_loss": 0.001850014564115554 }, { "action_query_batch_std": 21.979886054992676, "action_query_norm": 931.5182678222657, "action_relation_loss": 0.0018702120753005147, "auxiliary_loss_weight": 1.0, "epoch": 23.91955098222638, "flow_matching_loss": 0.013986685033887624, "grad_norm": 0.09531241655349731, "invalid_tail_samples": 26.3, "learning_rate": 5.846584262502402e-06, "loss": 0.0159, "positive_teacher_pairs": 26278.7, "relation_loss": 0.0018702120753005147, "selected_pairs": 26278.7, "step": 25570, "student_distance_mean": 1261.8943725585937, "teacher_distance_mean": 0.846331512928009, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.0018702120753005147, "weighted_relation_loss": 0.0018702120753005147 }, { "action_query_batch_std": 22.06626033782959, "action_query_norm": 935.6242736816406, "action_relation_loss": 0.0017913763178512454, "auxiliary_loss_weight": 1.0, "epoch": 23.9289055191768, "flow_matching_loss": 0.014697975479066372, "grad_norm": 0.09842517226934433, "invalid_tail_samples": 23.0, "learning_rate": 5.820748375321411e-06, "loss": 0.0165, "positive_teacher_pairs": 27037.7, "relation_loss": 0.0017913763178512454, "selected_pairs": 27037.7, "step": 25580, "student_distance_mean": 1265.656640625, "teacher_distance_mean": 0.8504914283752442, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0017913763178512454, "weighted_relation_loss": 0.0017913763178512454 }, { "action_query_batch_std": 22.07336597442627, "action_query_norm": 935.0776794433593, "action_relation_loss": 0.0018239831435494125, "auxiliary_loss_weight": 1.0, "epoch": 23.938260056127223, "flow_matching_loss": 0.015592980198562145, "grad_norm": 0.11021454632282257, "invalid_tail_samples": 22.8, "learning_rate": 5.794966170096977e-06, "loss": 0.0174, "positive_teacher_pairs": 27087.0, "relation_loss": 0.0018239831435494125, "selected_pairs": 27087.0, "step": 25590, "student_distance_mean": 1265.6484497070312, "teacher_distance_mean": 0.8511089026927948, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0018239831435494125, "weighted_relation_loss": 0.0018239831435494125 }, { "action_query_batch_std": 22.420217514038086, "action_query_norm": 945.352587890625, "action_relation_loss": 0.001817570545244962, "auxiliary_loss_weight": 1.0, "epoch": 23.947614593077642, "flow_matching_loss": 0.015376676898449659, "grad_norm": 0.08155015856027603, "invalid_tail_samples": 22.9, "learning_rate": 5.769237678156897e-06, "loss": 0.0172, "positive_teacher_pairs": 27060.3, "relation_loss": 0.001817570545244962, "selected_pairs": 27060.3, "step": 25600, "student_distance_mean": 1286.3162231445312, "teacher_distance_mean": 0.8650133550167084, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.001817570545244962, "weighted_relation_loss": 0.001817570545244962 }, { "action_query_batch_std": 22.267118835449217, "action_query_norm": 947.0476196289062, "action_relation_loss": 0.0017547728610225021, "auxiliary_loss_weight": 1.0, "epoch": 23.956969130028064, "flow_matching_loss": 0.01532912915572524, "grad_norm": 0.08010932803153992, "invalid_tail_samples": 21.8, "learning_rate": 5.743562930763735e-06, "loss": 0.0171, "positive_teacher_pairs": 27312.3, "relation_loss": 0.0017547728610225021, "selected_pairs": 27312.3, "step": 25610, "student_distance_mean": 1280.3304321289063, "teacher_distance_mean": 0.8625989258289337, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.0017547728610225021, "weighted_relation_loss": 0.0017547728610225021 }, { "action_query_batch_std": 22.165256309509278, "action_query_norm": 939.8709838867187, "action_relation_loss": 0.001769314834382385, "auxiliary_loss_weight": 1.0, "epoch": 23.966323666978486, "flow_matching_loss": 0.015688745491206645, "grad_norm": 0.09230536967515945, "invalid_tail_samples": 23.3, "learning_rate": 5.717941959114726e-06, "loss": 0.0175, "positive_teacher_pairs": 26976.4, "relation_loss": 0.001769314834382385, "selected_pairs": 26976.4, "step": 25620, "student_distance_mean": 1274.2457397460937, "teacher_distance_mean": 0.8557830631732941, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.001769314834382385, "weighted_relation_loss": 0.001769314834382385 }, { "action_query_batch_std": 22.03087673187256, "action_query_norm": 935.9262939453125, "action_relation_loss": 0.0017715685651637613, "auxiliary_loss_weight": 1.0, "epoch": 23.975678203928904, "flow_matching_loss": 0.015389614459127187, "grad_norm": 0.08238145709037781, "invalid_tail_samples": 23.2, "learning_rate": 5.69237479434176e-06, "loss": 0.0172, "positive_teacher_pairs": 26990.2, "relation_loss": 0.0017715685651637613, "selected_pairs": 26990.2, "step": 25630, "student_distance_mean": 1271.2021118164062, "teacher_distance_mean": 0.8535255134105683, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0017715685651637613, "weighted_relation_loss": 0.0017715685651637613 }, { "action_query_batch_std": 22.472886085510254, "action_query_norm": 946.4751770019532, "action_relation_loss": 0.0018076073261909186, "auxiliary_loss_weight": 1.0, "epoch": 23.985032740879326, "flow_matching_loss": 0.018563689664006233, "grad_norm": 0.10972640663385391, "invalid_tail_samples": 22.0, "learning_rate": 5.666861467511353e-06, "loss": 0.0204, "positive_teacher_pairs": 27268.8, "relation_loss": 0.0018076073261909186, "selected_pairs": 27268.8, "step": 25640, "student_distance_mean": 1289.025, "teacher_distance_mean": 0.8645212650299072, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.0018076073261909186, "weighted_relation_loss": 0.0018076073261909186 }, { "action_query_batch_std": 22.148752403259277, "action_query_norm": 938.5848327636719, "action_relation_loss": 0.0018100479966960848, "auxiliary_loss_weight": 1.0, "epoch": 23.99438727782975, "flow_matching_loss": 0.016634631995111705, "grad_norm": 0.09442004561424255, "invalid_tail_samples": 24.4, "learning_rate": 5.641402009624591e-06, "loss": 0.0184, "positive_teacher_pairs": 26721.6, "relation_loss": 0.0018100479966960848, "selected_pairs": 26721.6, "step": 25650, "student_distance_mean": 1272.0686401367188, "teacher_distance_mean": 0.8540994584560394, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0018100479966960848, "weighted_relation_loss": 0.0018100479966960848 }, { "action_query_batch_std": 22.195590209960937, "action_query_norm": 940.3795166015625, "action_relation_loss": 0.0017840978573076427, "auxiliary_loss_weight": 1.0, "epoch": 24.003741814780167, "flow_matching_loss": 0.017271858267486097, "grad_norm": 0.09391497820615768, "invalid_tail_samples": 22.6, "learning_rate": 5.615996451617145e-06, "loss": 0.0191, "positive_teacher_pairs": 24154.5, "relation_loss": 0.0017840978573076427, "selected_pairs": 24154.5, "step": 25660, "student_distance_mean": 1280.3504516601563, "teacher_distance_mean": 0.8605303823947906, "valid_action_samples": 213.5, "weighted_auxiliary_loss": 0.0017840978573076427, "weighted_relation_loss": 0.0017840978573076427 }, { "action_query_batch_std": 22.346811485290527, "action_query_norm": 946.6165649414063, "action_relation_loss": 0.0017947510816156865, "auxiliary_loss_weight": 1.0, "epoch": 24.01309635173059, "flow_matching_loss": 0.01643684096634388, "grad_norm": 0.10833168029785156, "invalid_tail_samples": 23.2, "learning_rate": 5.590644824359148e-06, "loss": 0.0182, "positive_teacher_pairs": 26990.7, "relation_loss": 0.0017947510816156865, "selected_pairs": 26990.7, "step": 25670, "student_distance_mean": 1287.9359252929687, "teacher_distance_mean": 0.8648000299930573, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0017947510816156865, "weighted_relation_loss": 0.0017947510816156865 }, { "action_query_batch_std": 21.831356048583984, "action_query_norm": 930.1907653808594, "action_relation_loss": 0.0017631878959946333, "auxiliary_loss_weight": 1.0, "epoch": 24.02245088868101, "flow_matching_loss": 0.015994393546134234, "grad_norm": 0.07838913798332214, "invalid_tail_samples": 23.4, "learning_rate": 5.56534715865521e-06, "loss": 0.0178, "positive_teacher_pairs": 26950.9, "relation_loss": 0.0017631878959946333, "selected_pairs": 26950.9, "step": 25680, "student_distance_mean": 1258.705908203125, "teacher_distance_mean": 0.8440729796886444, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0017631878959946333, "weighted_relation_loss": 0.0017631878959946333 }, { "action_query_batch_std": 22.021473503112794, "action_query_norm": 935.0357727050781, "action_relation_loss": 0.001790854532737285, "auxiliary_loss_weight": 1.0, "epoch": 24.031805425631433, "flow_matching_loss": 0.01590829063206911, "grad_norm": 0.08362612873315811, "invalid_tail_samples": 23.7, "learning_rate": 5.5401034852443965e-06, "loss": 0.0177, "positive_teacher_pairs": 26873.9, "relation_loss": 0.001790854532737285, "selected_pairs": 26873.9, "step": 25690, "student_distance_mean": 1267.5246826171874, "teacher_distance_mean": 0.8506939768791199, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.001790854532737285, "weighted_relation_loss": 0.001790854532737285 }, { "action_query_batch_std": 22.324139976501463, "action_query_norm": 943.1261047363281, "action_relation_loss": 0.001790607743896544, "auxiliary_loss_weight": 1.0, "epoch": 24.04115996258185, "flow_matching_loss": 0.01495203012600541, "grad_norm": 0.0925140455365181, "invalid_tail_samples": 26.3, "learning_rate": 5.514913834800134e-06, "loss": 0.0167, "positive_teacher_pairs": 26285.0, "relation_loss": 0.001790607743896544, "selected_pairs": 26285.0, "step": 25700, "student_distance_mean": 1285.8858154296875, "teacher_distance_mean": 0.8630145847797394, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.001790607743896544, "weighted_relation_loss": 0.001790607743896544 }, { "action_query_batch_std": 22.36765651702881, "action_query_norm": 948.4026550292969, "action_relation_loss": 0.0017982843099161982, "auxiliary_loss_weight": 1.0, "epoch": 24.050514499532273, "flow_matching_loss": 0.01665439074859023, "grad_norm": 0.08266276866197586, "invalid_tail_samples": 23.1, "learning_rate": 5.489778237930238e-06, "loss": 0.0185, "positive_teacher_pairs": 27012.2, "relation_loss": 0.0017982843099161982, "selected_pairs": 27012.2, "step": 25710, "student_distance_mean": 1288.6883911132813, "teacher_distance_mean": 0.8656353533267975, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0017982843099161982, "weighted_relation_loss": 0.0017982843099161982 }, { "action_query_batch_std": 22.083182525634765, "action_query_norm": 937.86845703125, "action_relation_loss": 0.0017607376794330776, "auxiliary_loss_weight": 1.0, "epoch": 24.059869036482695, "flow_matching_loss": 0.015235859993845224, "grad_norm": 0.08518078178167343, "invalid_tail_samples": 25.6, "learning_rate": 5.464696725176827e-06, "loss": 0.017, "positive_teacher_pairs": 26459.1, "relation_loss": 0.0017607376794330776, "selected_pairs": 26459.1, "step": 25720, "student_distance_mean": 1275.7202758789062, "teacher_distance_mean": 0.8549070119857788, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.0017607376794330776, "weighted_relation_loss": 0.0017607376794330776 }, { "action_query_batch_std": 22.337347793579102, "action_query_norm": 947.7135314941406, "action_relation_loss": 0.0018167660338804126, "auxiliary_loss_weight": 1.0, "epoch": 24.069223573433113, "flow_matching_loss": 0.01432913364842534, "grad_norm": 0.10519744455814362, "invalid_tail_samples": 21.2, "learning_rate": 5.439669327016294e-06, "loss": 0.0161, "positive_teacher_pairs": 27454.3, "relation_loss": 0.0018167660338804126, "selected_pairs": 27454.3, "step": 25730, "student_distance_mean": 1284.3887329101562, "teacher_distance_mean": 0.8614897072315216, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.0018167660338804126, "weighted_relation_loss": 0.0018167660338804126 }, { "action_query_batch_std": 21.937952041625977, "action_query_norm": 931.398779296875, "action_relation_loss": 0.0017926629749126731, "auxiliary_loss_weight": 1.0, "epoch": 24.078578110383535, "flow_matching_loss": 0.015074306074529887, "grad_norm": 0.07685591280460358, "invalid_tail_samples": 22.8, "learning_rate": 5.4146960738592985e-06, "loss": 0.0169, "positive_teacher_pairs": 27090.9, "relation_loss": 0.0017926629749126731, "selected_pairs": 27090.9, "step": 25740, "student_distance_mean": 1262.64677734375, "teacher_distance_mean": 0.8463819861412049, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0017926629749126731, "weighted_relation_loss": 0.0017926629749126731 }, { "action_query_batch_std": 22.333081436157226, "action_query_norm": 945.5763305664062, "action_relation_loss": 0.001787800167221576, "auxiliary_loss_weight": 1.0, "epoch": 24.087932647333957, "flow_matching_loss": 0.014949838072061539, "grad_norm": 0.08153226226568222, "invalid_tail_samples": 25.9, "learning_rate": 5.389776996050694e-06, "loss": 0.0167, "positive_teacher_pairs": 26375.8, "relation_loss": 0.001787800167221576, "selected_pairs": 26375.8, "step": 25750, "student_distance_mean": 1290.7614624023438, "teacher_distance_mean": 0.8673052668571473, "valid_action_samples": 230.1, "weighted_auxiliary_loss": 0.001787800167221576, "weighted_relation_loss": 0.001787800167221576 }, { "action_query_batch_std": 22.09912452697754, "action_query_norm": 934.9224853515625, "action_relation_loss": 0.0018151517724618316, "auxiliary_loss_weight": 1.0, "epoch": 24.09728718428438, "flow_matching_loss": 0.015753115061670542, "grad_norm": 0.08490786701440811, "invalid_tail_samples": 24.4, "learning_rate": 5.364912123869492e-06, "loss": 0.0176, "positive_teacher_pairs": 26707.1, "relation_loss": 0.0018151517724618316, "selected_pairs": 26707.1, "step": 25760, "student_distance_mean": 1267.3721923828125, "teacher_distance_mean": 0.8522765278816223, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0018151517724618316, "weighted_relation_loss": 0.0018151517724618316 }, { "action_query_batch_std": 21.805605316162108, "action_query_norm": 927.0901184082031, "action_relation_loss": 0.0018398624029941856, "auxiliary_loss_weight": 1.0, "epoch": 24.106641721234798, "flow_matching_loss": 0.013661116920411586, "grad_norm": 0.07181894779205322, "invalid_tail_samples": 25.3, "learning_rate": 5.3401014875288864e-06, "loss": 0.0155, "positive_teacher_pairs": 26504.7, "relation_loss": 0.0018398624029941856, "selected_pairs": 26504.7, "step": 25770, "student_distance_mean": 1253.8121459960937, "teacher_distance_mean": 0.8424722671508789, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0018398624029941856, "weighted_relation_loss": 0.0018398624029941856 }, { "action_query_batch_std": 22.164433097839357, "action_query_norm": 939.3347595214843, "action_relation_loss": 0.0017871034680865705, "auxiliary_loss_weight": 1.0, "epoch": 24.11599625818522, "flow_matching_loss": 0.01785101303830743, "grad_norm": 0.09734104573726654, "invalid_tail_samples": 21.0, "learning_rate": 5.315345117176129e-06, "loss": 0.0196, "positive_teacher_pairs": 27503.5, "relation_loss": 0.0017871034680865705, "selected_pairs": 27503.5, "step": 25780, "student_distance_mean": 1267.2795288085938, "teacher_distance_mean": 0.8513547897338867, "valid_action_samples": 235.0, "weighted_auxiliary_loss": 0.0017871034680865705, "weighted_relation_loss": 0.0017871034680865705 }, { "action_query_batch_std": 22.207840728759766, "action_query_norm": 941.946728515625, "action_relation_loss": 0.001744750700891018, "auxiliary_loss_weight": 1.0, "epoch": 24.125350795135642, "flow_matching_loss": 0.016399373952299356, "grad_norm": 0.086257703602314, "invalid_tail_samples": 25.6, "learning_rate": 5.2906430428925405e-06, "loss": 0.0181, "positive_teacher_pairs": 26430.9, "relation_loss": 0.001744750700891018, "selected_pairs": 26430.9, "step": 25790, "student_distance_mean": 1280.4123779296874, "teacher_distance_mean": 0.8587824761867523, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.001744750700891018, "weighted_relation_loss": 0.001744750700891018 }, { "action_query_batch_std": 21.97726974487305, "action_query_norm": 935.7466796875, "action_relation_loss": 0.0017935769283212721, "auxiliary_loss_weight": 1.0, "epoch": 24.13470533208606, "flow_matching_loss": 0.016323681082576515, "grad_norm": 0.09672167152166367, "invalid_tail_samples": 23.1, "learning_rate": 5.265995294693471e-06, "loss": 0.0181, "positive_teacher_pairs": 27016.5, "relation_loss": 0.0017935769283212721, "selected_pairs": 27016.5, "step": 25800, "student_distance_mean": 1268.1598999023438, "teacher_distance_mean": 0.848939198255539, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0017935769283212721, "weighted_relation_loss": 0.0017935769283212721 }, { "action_query_batch_std": 22.027171897888184, "action_query_norm": 934.8544799804688, "action_relation_loss": 0.001794966624584049, "auxiliary_loss_weight": 1.0, "epoch": 24.144059869036482, "flow_matching_loss": 0.014074446354061364, "grad_norm": 0.09782817959785461, "invalid_tail_samples": 25.9, "learning_rate": 5.241401902528254e-06, "loss": 0.0159, "positive_teacher_pairs": 26362.7, "relation_loss": 0.001794966624584049, "selected_pairs": 26362.7, "step": 25810, "student_distance_mean": 1267.9917724609375, "teacher_distance_mean": 0.8507691502571106, "valid_action_samples": 230.1, "weighted_auxiliary_loss": 0.001794966624584049, "weighted_relation_loss": 0.001794966624584049 }, { "action_query_batch_std": 22.372980880737305, "action_query_norm": 945.7513488769531, "action_relation_loss": 0.0017727922415360809, "auxiliary_loss_weight": 1.0, "epoch": 24.153414405986904, "flow_matching_loss": 0.016511558927595614, "grad_norm": 0.09081496298313141, "invalid_tail_samples": 23.8, "learning_rate": 5.216862896280189e-06, "loss": 0.0183, "positive_teacher_pairs": 26848.0, "relation_loss": 0.0017727922415360809, "selected_pairs": 26848.0, "step": 25820, "student_distance_mean": 1286.2465698242188, "teacher_distance_mean": 0.8640395522117614, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0017727922415360809, "weighted_relation_loss": 0.0017727922415360809 }, { "action_query_batch_std": 22.005777740478514, "action_query_norm": 934.0878356933594, "action_relation_loss": 0.0017725567216984929, "auxiliary_loss_weight": 1.0, "epoch": 24.162768942937326, "flow_matching_loss": 0.015075101796537638, "grad_norm": 0.11262837797403336, "invalid_tail_samples": 24.3, "learning_rate": 5.192378305766471e-06, "loss": 0.0168, "positive_teacher_pairs": 26735.3, "relation_loss": 0.0017725567216984929, "selected_pairs": 26735.3, "step": 25830, "student_distance_mean": 1267.8310180664062, "teacher_distance_mean": 0.8521020889282227, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0017725567216984929, "weighted_relation_loss": 0.0017725567216984929 }, { "action_query_batch_std": 21.990510177612304, "action_query_norm": 934.5094421386718, "action_relation_loss": 0.0017686073784716426, "auxiliary_loss_weight": 1.0, "epoch": 24.172123479887745, "flow_matching_loss": 0.01653413735330105, "grad_norm": 0.10890992730855942, "invalid_tail_samples": 24.8, "learning_rate": 5.1679481607382065e-06, "loss": 0.0183, "positive_teacher_pairs": 26625.9, "relation_loss": 0.0017686073784716426, "selected_pairs": 26625.9, "step": 25840, "student_distance_mean": 1266.6263549804687, "teacher_distance_mean": 0.8503529310226441, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0017686073784716426, "weighted_relation_loss": 0.0017686073784716426 }, { "action_query_batch_std": 21.921764755249022, "action_query_norm": 934.0849182128907, "action_relation_loss": 0.0017701596370898187, "auxiliary_loss_weight": 1.0, "epoch": 24.181478016838167, "flow_matching_loss": 0.01448363596573472, "grad_norm": 0.08313363790512085, "invalid_tail_samples": 25.3, "learning_rate": 5.1435724908803105e-06, "loss": 0.0163, "positive_teacher_pairs": 26507.2, "relation_loss": 0.0017701596370898187, "selected_pairs": 26507.2, "step": 25850, "student_distance_mean": 1269.8046630859376, "teacher_distance_mean": 0.853841507434845, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0017701596370898187, "weighted_relation_loss": 0.0017701596370898187 }, { "action_query_batch_std": 21.86606960296631, "action_query_norm": 929.1674377441407, "action_relation_loss": 0.00179841173812747, "auxiliary_loss_weight": 1.0, "epoch": 24.19083255378859, "flow_matching_loss": 0.016701601911336184, "grad_norm": 0.0864887461066246, "invalid_tail_samples": 25.5, "learning_rate": 5.119251325811514e-06, "loss": 0.0185, "positive_teacher_pairs": 26467.7, "relation_loss": 0.00179841173812747, "selected_pairs": 26467.7, "step": 25860, "student_distance_mean": 1258.250537109375, "teacher_distance_mean": 0.8454391241073609, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.00179841173812747, "weighted_relation_loss": 0.00179841173812747 }, { "action_query_batch_std": 22.37712707519531, "action_query_norm": 943.4347412109375, "action_relation_loss": 0.0017448478960432113, "auxiliary_loss_weight": 1.0, "epoch": 24.200187090739007, "flow_matching_loss": 0.015220671612769365, "grad_norm": 0.0770246759057045, "invalid_tail_samples": 22.1, "learning_rate": 5.094984695084348e-06, "loss": 0.017, "positive_teacher_pairs": 27246.6, "relation_loss": 0.0017448478960432113, "selected_pairs": 27246.6, "step": 25870, "student_distance_mean": 1284.2822631835938, "teacher_distance_mean": 0.8655564248561859, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0017448478960432113, "weighted_relation_loss": 0.0017448478960432113 }, { "action_query_batch_std": 22.317688369750975, "action_query_norm": 942.3525207519531, "action_relation_loss": 0.001789119397290051, "auxiliary_loss_weight": 1.0, "epoch": 24.20954162768943, "flow_matching_loss": 0.01624531960114837, "grad_norm": 0.09671639651060104, "invalid_tail_samples": 25.2, "learning_rate": 5.070772628185039e-06, "loss": 0.018, "positive_teacher_pairs": 26524.4, "relation_loss": 0.001789119397290051, "selected_pairs": 26524.4, "step": 25880, "student_distance_mean": 1277.1076538085938, "teacher_distance_mean": 0.8591930329799652, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.001789119397290051, "weighted_relation_loss": 0.001789119397290051 }, { "action_query_batch_std": 22.314767837524414, "action_query_norm": 944.683642578125, "action_relation_loss": 0.0017263479763641953, "auxiliary_loss_weight": 1.0, "epoch": 24.21889616463985, "flow_matching_loss": 0.015622786246240139, "grad_norm": 0.11911678314208984, "invalid_tail_samples": 23.2, "learning_rate": 5.046615154533535e-06, "loss": 0.0173, "positive_teacher_pairs": 26999.5, "relation_loss": 0.0017263479763641953, "selected_pairs": 26999.5, "step": 25890, "student_distance_mean": 1281.4600463867187, "teacher_distance_mean": 0.8622937560081482, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0017263479763641953, "weighted_relation_loss": 0.0017263479763641953 }, { "action_query_batch_std": 22.285342979431153, "action_query_norm": 942.4738342285157, "action_relation_loss": 0.0018058338784612716, "auxiliary_loss_weight": 1.0, "epoch": 24.22825070159027, "flow_matching_loss": 0.01588792968541384, "grad_norm": 0.09685259312391281, "invalid_tail_samples": 25.4, "learning_rate": 5.022512303483451e-06, "loss": 0.0177, "positive_teacher_pairs": 26480.8, "relation_loss": 0.0018058338784612716, "selected_pairs": 26480.8, "step": 25900, "student_distance_mean": 1276.4307373046875, "teacher_distance_mean": 0.8589461863040924, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.0018058338784612716, "weighted_relation_loss": 0.0018058338784612716 }, { "action_query_batch_std": 21.91462287902832, "action_query_norm": 927.2240234375, "action_relation_loss": 0.0017899879487231374, "auxiliary_loss_weight": 1.0, "epoch": 24.23760523854069, "flow_matching_loss": 0.016790056135505438, "grad_norm": 0.08759225159883499, "invalid_tail_samples": 24.2, "learning_rate": 4.998464104322015e-06, "loss": 0.0186, "positive_teacher_pairs": 26760.8, "relation_loss": 0.0017899879487231374, "selected_pairs": 26760.8, "step": 25910, "student_distance_mean": 1258.1970947265625, "teacher_distance_mean": 0.8461904644966125, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0017899879487231374, "weighted_relation_loss": 0.0017899879487231374 }, { "action_query_batch_std": 22.131266593933105, "action_query_norm": 938.3109252929687, "action_relation_loss": 0.0017991735134273768, "auxiliary_loss_weight": 1.0, "epoch": 24.246959775491113, "flow_matching_loss": 0.015073999483138322, "grad_norm": 0.09404326230287552, "invalid_tail_samples": 24.6, "learning_rate": 4.974470586270047e-06, "loss": 0.0169, "positive_teacher_pairs": 26667.5, "relation_loss": 0.0017991735134273768, "selected_pairs": 26667.5, "step": 25920, "student_distance_mean": 1272.7711059570313, "teacher_distance_mean": 0.8562030851840973, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0017991735134273768, "weighted_relation_loss": 0.0017991735134273768 }, { "action_query_batch_std": 22.211331367492676, "action_query_norm": 937.7250549316407, "action_relation_loss": 0.0017797455191612243, "auxiliary_loss_weight": 1.0, "epoch": 24.256314312441535, "flow_matching_loss": 0.01493118554353714, "grad_norm": 0.08945437520742416, "invalid_tail_samples": 21.7, "learning_rate": 4.950531778481965e-06, "loss": 0.0167, "positive_teacher_pairs": 27333.7, "relation_loss": 0.0017797455191612243, "selected_pairs": 27333.7, "step": 25930, "student_distance_mean": 1277.4352416992188, "teacher_distance_mean": 0.8590570867061615, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.0017797455191612243, "weighted_relation_loss": 0.0017797455191612243 }, { "action_query_batch_std": 22.00302047729492, "action_query_norm": 935.1574768066406, "action_relation_loss": 0.0018080875393934547, "auxiliary_loss_weight": 1.0, "epoch": 24.265668849391954, "flow_matching_loss": 0.015651243552565575, "grad_norm": 0.0901845172047615, "invalid_tail_samples": 23.2, "learning_rate": 4.926647710045651e-06, "loss": 0.0175, "positive_teacher_pairs": 27007.0, "relation_loss": 0.0018080875393934547, "selected_pairs": 27007.0, "step": 25940, "student_distance_mean": 1265.9271606445313, "teacher_distance_mean": 0.8521972894668579, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0018080875393934547, "weighted_relation_loss": 0.0018080875393934547 }, { "action_query_batch_std": 22.000124168395995, "action_query_norm": 930.3746704101562, "action_relation_loss": 0.001785322988871485, "auxiliary_loss_weight": 1.0, "epoch": 24.275023386342376, "flow_matching_loss": 0.015138811804354191, "grad_norm": 0.0750843808054924, "invalid_tail_samples": 25.1, "learning_rate": 4.9028184099825125e-06, "loss": 0.0169, "positive_teacher_pairs": 26547.5, "relation_loss": 0.001785322988871485, "selected_pairs": 26547.5, "step": 25950, "student_distance_mean": 1266.28623046875, "teacher_distance_mean": 0.8535877704620362, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.001785322988871485, "weighted_relation_loss": 0.001785322988871485 }, { "action_query_batch_std": 21.925282287597657, "action_query_norm": 929.8757141113281, "action_relation_loss": 0.0017572539858520032, "auxiliary_loss_weight": 1.0, "epoch": 24.284377923292798, "flow_matching_loss": 0.015900408383458853, "grad_norm": 0.09519418329000473, "invalid_tail_samples": 23.8, "learning_rate": 4.879043907247382e-06, "loss": 0.0177, "positive_teacher_pairs": 26857.4, "relation_loss": 0.0017572539858520032, "selected_pairs": 26857.4, "step": 25960, "student_distance_mean": 1258.4716796875, "teacher_distance_mean": 0.8483340620994568, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0017572539858520032, "weighted_relation_loss": 0.0017572539858520032 }, { "action_query_batch_std": 22.084410667419434, "action_query_norm": 934.556884765625, "action_relation_loss": 0.0017604844644665719, "auxiliary_loss_weight": 1.0, "epoch": 24.293732460243216, "flow_matching_loss": 0.01647983128204942, "grad_norm": 0.0973334014415741, "invalid_tail_samples": 23.2, "learning_rate": 4.8553242307285414e-06, "loss": 0.0182, "positive_teacher_pairs": 26987.7, "relation_loss": 0.0017604844644665719, "selected_pairs": 26987.7, "step": 25970, "student_distance_mean": 1268.559619140625, "teacher_distance_mean": 0.8549225747585296, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0017604844644665719, "weighted_relation_loss": 0.0017604844644665719 }, { "action_query_batch_std": 22.130218505859375, "action_query_norm": 937.3685791015625, "action_relation_loss": 0.0018259710050188005, "auxiliary_loss_weight": 1.0, "epoch": 24.30308699719364, "flow_matching_loss": 0.01440051207318902, "grad_norm": 0.06098714843392372, "invalid_tail_samples": 25.7, "learning_rate": 4.8316594092476185e-06, "loss": 0.0162, "positive_teacher_pairs": 26414.4, "relation_loss": 0.0018259710050188005, "selected_pairs": 26414.4, "step": 25980, "student_distance_mean": 1275.7962524414063, "teacher_distance_mean": 0.8590709149837494, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.0018259710050188005, "weighted_relation_loss": 0.0018259710050188005 }, { "action_query_batch_std": 22.188556480407716, "action_query_norm": 938.6670715332032, "action_relation_loss": 0.0017754296772181989, "auxiliary_loss_weight": 1.0, "epoch": 24.31244153414406, "flow_matching_loss": 0.015561904944479465, "grad_norm": 0.10386712849140167, "invalid_tail_samples": 22.3, "learning_rate": 4.808049471559617e-06, "loss": 0.0173, "positive_teacher_pairs": 27194.8, "relation_loss": 0.0017754296772181989, "selected_pairs": 27194.8, "step": 25990, "student_distance_mean": 1271.7042358398437, "teacher_distance_mean": 0.8564530551433563, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0017754296772181989, "weighted_relation_loss": 0.0017754296772181989 }, { "action_query_batch_std": 21.841557693481445, "action_query_norm": 927.4349060058594, "action_relation_loss": 0.001860981248319149, "auxiliary_loss_weight": 1.0, "epoch": 24.321796071094482, "flow_matching_loss": 0.015476320032030344, "grad_norm": 0.1026100367307663, "invalid_tail_samples": 21.9, "learning_rate": 4.784494446352833e-06, "loss": 0.0173, "positive_teacher_pairs": 27298.0, "relation_loss": 0.001860981248319149, "selected_pairs": 27298.0, "step": 26000, "student_distance_mean": 1252.0128051757813, "teacher_distance_mean": 0.8424726307392121, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.001860981248319149, "weighted_relation_loss": 0.001860981248319149 }, { "action_query_batch_std": 21.911865234375, "action_query_norm": 931.4575744628906, "action_relation_loss": 0.001753135654143989, "auxiliary_loss_weight": 1.0, "epoch": 24.3311506080449, "flow_matching_loss": 0.015462968405336142, "grad_norm": 0.07585755735635757, "invalid_tail_samples": 25.5, "learning_rate": 4.760994362248833e-06, "loss": 0.0172, "positive_teacher_pairs": 26464.2, "relation_loss": 0.001753135654143989, "selected_pairs": 26464.2, "step": 26010, "student_distance_mean": 1259.8532104492188, "teacher_distance_mean": 0.8459527432918549, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.001753135654143989, "weighted_relation_loss": 0.001753135654143989 }, { "action_query_batch_std": 22.08640613555908, "action_query_norm": 936.0938903808594, "action_relation_loss": 0.0017792313359677792, "auxiliary_loss_weight": 1.0, "epoch": 24.340505144995323, "flow_matching_loss": 0.014267656113952398, "grad_norm": 0.10051383078098297, "invalid_tail_samples": 22.8, "learning_rate": 4.737549247802442e-06, "loss": 0.016, "positive_teacher_pairs": 27081.7, "relation_loss": 0.0017792313359677792, "selected_pairs": 27081.7, "step": 26020, "student_distance_mean": 1269.5234252929688, "teacher_distance_mean": 0.8539652526378632, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0017792313359677792, "weighted_relation_loss": 0.0017792313359677792 }, { "action_query_batch_std": 22.43147430419922, "action_query_norm": 944.15185546875, "action_relation_loss": 0.0017785605858080089, "auxiliary_loss_weight": 1.0, "epoch": 24.349859681945745, "flow_matching_loss": 0.015125491935759783, "grad_norm": 0.078263059258461, "invalid_tail_samples": 25.8, "learning_rate": 4.714159131501689e-06, "loss": 0.0169, "positive_teacher_pairs": 26393.5, "relation_loss": 0.0017785605858080089, "selected_pairs": 26393.5, "step": 26030, "student_distance_mean": 1294.5610717773438, "teacher_distance_mean": 0.8706495463848114, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.0017785605858080089, "weighted_relation_loss": 0.0017785605858080089 }, { "action_query_batch_std": 22.230880165100096, "action_query_norm": 941.3548400878906, "action_relation_loss": 0.001743289129808545, "auxiliary_loss_weight": 1.0, "epoch": 24.359214218896163, "flow_matching_loss": 0.014721464645117522, "grad_norm": 0.07291147112846375, "invalid_tail_samples": 24.0, "learning_rate": 4.690824041767766e-06, "loss": 0.0165, "positive_teacher_pairs": 26807.1, "relation_loss": 0.001743289129808545, "selected_pairs": 26807.1, "step": 26040, "student_distance_mean": 1281.4880859375, "teacher_distance_mean": 0.8628329813480378, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.001743289129808545, "weighted_relation_loss": 0.001743289129808545 }, { "action_query_batch_std": 22.29035472869873, "action_query_norm": 943.2166870117187, "action_relation_loss": 0.001762925845105201, "auxiliary_loss_weight": 1.0, "epoch": 24.368568755846585, "flow_matching_loss": 0.014640404470264911, "grad_norm": 0.09871462732553482, "invalid_tail_samples": 22.9, "learning_rate": 4.6675440069550105e-06, "loss": 0.0164, "positive_teacher_pairs": 27058.9, "relation_loss": 0.001762925845105201, "selected_pairs": 27058.9, "step": 26050, "student_distance_mean": 1286.0731689453125, "teacher_distance_mean": 0.8653549134731293, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.001762925845105201, "weighted_relation_loss": 0.001762925845105201 }, { "action_query_batch_std": 22.051283836364746, "action_query_norm": 936.3113403320312, "action_relation_loss": 0.001784419419709593, "auxiliary_loss_weight": 1.0, "epoch": 24.377923292797007, "flow_matching_loss": 0.015592670068144798, "grad_norm": 0.09104006737470627, "invalid_tail_samples": 23.0, "learning_rate": 4.64431905535086e-06, "loss": 0.0174, "positive_teacher_pairs": 27034.8, "relation_loss": 0.001784419419709593, "selected_pairs": 27034.8, "step": 26060, "student_distance_mean": 1265.2085083007812, "teacher_distance_mean": 0.852598637342453, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.001784419419709593, "weighted_relation_loss": 0.001784419419709593 }, { "action_query_batch_std": 22.134690856933595, "action_query_norm": 935.4239685058594, "action_relation_loss": 0.0018241747049614788, "auxiliary_loss_weight": 1.0, "epoch": 24.38727782974743, "flow_matching_loss": 0.016302168369293213, "grad_norm": 0.10085013508796692, "invalid_tail_samples": 22.3, "learning_rate": 4.621149215175808e-06, "loss": 0.0181, "positive_teacher_pairs": 27197.5, "relation_loss": 0.0018241747049614788, "selected_pairs": 27197.5, "step": 26070, "student_distance_mean": 1276.7854858398437, "teacher_distance_mean": 0.8595598101615906, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0018241747049614788, "weighted_relation_loss": 0.0018241747049614788 }, { "action_query_batch_std": 22.237466430664064, "action_query_norm": 940.9007202148438, "action_relation_loss": 0.0017240218119695782, "auxiliary_loss_weight": 1.0, "epoch": 24.396632366697848, "flow_matching_loss": 0.014963329397141933, "grad_norm": 0.08437462896108627, "invalid_tail_samples": 21.6, "learning_rate": 4.5980345145834154e-06, "loss": 0.0167, "positive_teacher_pairs": 27361.6, "relation_loss": 0.0017240218119695782, "selected_pairs": 27361.6, "step": 26080, "student_distance_mean": 1279.1681396484375, "teacher_distance_mean": 0.8594091951847076, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.0017240218119695782, "weighted_relation_loss": 0.0017240218119695782 }, { "action_query_batch_std": 21.920906829833985, "action_query_norm": 931.50712890625, "action_relation_loss": 0.00179231510264799, "auxiliary_loss_weight": 1.0, "epoch": 24.40598690364827, "flow_matching_loss": 0.01538388356566429, "grad_norm": 0.10412533581256866, "invalid_tail_samples": 23.3, "learning_rate": 4.574974981660213e-06, "loss": 0.0172, "positive_teacher_pairs": 26965.4, "relation_loss": 0.00179231510264799, "selected_pairs": 26965.4, "step": 26090, "student_distance_mean": 1260.478173828125, "teacher_distance_mean": 0.8457883358001709, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.00179231510264799, "weighted_relation_loss": 0.00179231510264799 }, { "action_query_batch_std": 22.100391960144044, "action_query_norm": 939.5549438476562, "action_relation_loss": 0.001744721841532737, "auxiliary_loss_weight": 1.0, "epoch": 24.41534144059869, "flow_matching_loss": 0.014963783416897058, "grad_norm": 0.07676827907562256, "invalid_tail_samples": 22.3, "learning_rate": 4.551970644425707e-06, "loss": 0.0167, "positive_teacher_pairs": 27200.8, "relation_loss": 0.001744721841532737, "selected_pairs": 27200.8, "step": 26100, "student_distance_mean": 1270.769091796875, "teacher_distance_mean": 0.8549024999141693, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.001744721841532737, "weighted_relation_loss": 0.001744721841532737 }, { "action_query_batch_std": 22.161452865600587, "action_query_norm": 936.611669921875, "action_relation_loss": 0.0017750278813764453, "auxiliary_loss_weight": 1.0, "epoch": 24.42469597754911, "flow_matching_loss": 0.014156876876950265, "grad_norm": 0.0807139202952385, "invalid_tail_samples": 21.9, "learning_rate": 4.529021530832328e-06, "loss": 0.0159, "positive_teacher_pairs": 27288.5, "relation_loss": 0.0017750278813764453, "selected_pairs": 27288.5, "step": 26110, "student_distance_mean": 1266.3063720703126, "teacher_distance_mean": 0.8534591555595398, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.0017750278813764453, "weighted_relation_loss": 0.0017750278813764453 }, { "action_query_batch_std": 22.282995986938477, "action_query_norm": 943.180126953125, "action_relation_loss": 0.0018084496958181262, "auxiliary_loss_weight": 1.0, "epoch": 24.434050514499532, "flow_matching_loss": 0.016072316188365222, "grad_norm": 0.08775492757558823, "invalid_tail_samples": 25.5, "learning_rate": 4.5061276687654306e-06, "loss": 0.0179, "positive_teacher_pairs": 26460.5, "relation_loss": 0.0018084496958181262, "selected_pairs": 26460.5, "step": 26120, "student_distance_mean": 1284.53916015625, "teacher_distance_mean": 0.864560866355896, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0018084496958181262, "weighted_relation_loss": 0.0018084496958181262 }, { "action_query_batch_std": 21.83486404418945, "action_query_norm": 928.1166442871094, "action_relation_loss": 0.001751887216232717, "auxiliary_loss_weight": 1.0, "epoch": 24.443405051449954, "flow_matching_loss": 0.01457809591665864, "grad_norm": 0.09670177102088928, "invalid_tail_samples": 26.0, "learning_rate": 4.4832890860431965e-06, "loss": 0.0163, "positive_teacher_pairs": 26351.5, "relation_loss": 0.001751887216232717, "selected_pairs": 26351.5, "step": 26130, "student_distance_mean": 1257.769482421875, "teacher_distance_mean": 0.8457066357135773, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.001751887216232717, "weighted_relation_loss": 0.001751887216232717 }, { "action_query_batch_std": 21.776988220214843, "action_query_norm": 926.5630981445313, "action_relation_loss": 0.0017921135760843754, "auxiliary_loss_weight": 1.0, "epoch": 24.452759588400376, "flow_matching_loss": 0.01478646444156766, "grad_norm": 0.0772659182548523, "invalid_tail_samples": 23.8, "learning_rate": 4.460505810416682e-06, "loss": 0.0166, "positive_teacher_pairs": 26860.1, "relation_loss": 0.0017921135760843754, "selected_pairs": 26860.1, "step": 26140, "student_distance_mean": 1251.1846557617187, "teacher_distance_mean": 0.8414897561073303, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0017921135760843754, "weighted_relation_loss": 0.0017921135760843754 }, { "action_query_batch_std": 22.40620288848877, "action_query_norm": 943.8849548339844, "action_relation_loss": 0.0017608709284104406, "auxiliary_loss_weight": 1.0, "epoch": 24.462114125350794, "flow_matching_loss": 0.015069427154958247, "grad_norm": 0.08368659019470215, "invalid_tail_samples": 21.4, "learning_rate": 4.4377778695696984e-06, "loss": 0.0168, "positive_teacher_pairs": 27406.5, "relation_loss": 0.0017608709284104406, "selected_pairs": 27406.5, "step": 26150, "student_distance_mean": 1281.3023803710937, "teacher_distance_mean": 0.861279284954071, "valid_action_samples": 234.6, "weighted_auxiliary_loss": 0.0017608709284104406, "weighted_relation_loss": 0.0017608709284104406 }, { "action_query_batch_std": 22.309359741210937, "action_query_norm": 945.1062683105469, "action_relation_loss": 0.001738185028079897, "auxiliary_loss_weight": 1.0, "epoch": 24.471468662301216, "flow_matching_loss": 0.015496709570288657, "grad_norm": 0.08140894770622253, "invalid_tail_samples": 21.6, "learning_rate": 4.415105291118843e-06, "loss": 0.0172, "positive_teacher_pairs": 27360.8, "relation_loss": 0.001738185028079897, "selected_pairs": 27360.8, "step": 26160, "student_distance_mean": 1283.4908569335937, "teacher_distance_mean": 0.8622393429279327, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.001738185028079897, "weighted_relation_loss": 0.001738185028079897 }, { "action_query_batch_std": 22.079040145874025, "action_query_norm": 935.5319152832031, "action_relation_loss": 0.001800048688892275, "auxiliary_loss_weight": 1.0, "epoch": 24.48082319925164, "flow_matching_loss": 0.013933368120342493, "grad_norm": 0.09762981534004211, "invalid_tail_samples": 21.5, "learning_rate": 4.392488102613435e-06, "loss": 0.0157, "positive_teacher_pairs": 27388.4, "relation_loss": 0.001800048688892275, "selected_pairs": 27388.4, "step": 26170, "student_distance_mean": 1266.9245971679688, "teacher_distance_mean": 0.8507429182529449, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.001800048688892275, "weighted_relation_loss": 0.001800048688892275 }, { "action_query_batch_std": 22.209885025024413, "action_query_norm": 939.48466796875, "action_relation_loss": 0.0017806361662223934, "auxiliary_loss_weight": 1.0, "epoch": 24.490177736202057, "flow_matching_loss": 0.014194201584905386, "grad_norm": 0.10397090017795563, "invalid_tail_samples": 24.6, "learning_rate": 4.369926331535473e-06, "loss": 0.016, "positive_teacher_pairs": 26666.3, "relation_loss": 0.0017806361662223934, "selected_pairs": 26666.3, "step": 26180, "student_distance_mean": 1280.483984375, "teacher_distance_mean": 0.8616195976734161, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0017806361662223934, "weighted_relation_loss": 0.0017806361662223934 }, { "action_query_batch_std": 22.02183589935303, "action_query_norm": 933.545068359375, "action_relation_loss": 0.0018153623561374844, "auxiliary_loss_weight": 1.0, "epoch": 24.49953227315248, "flow_matching_loss": 0.01510216873139143, "grad_norm": 0.08740319311618805, "invalid_tail_samples": 23.0, "learning_rate": 4.347420005299668e-06, "loss": 0.0169, "positive_teacher_pairs": 27031.0, "relation_loss": 0.0018153623561374844, "selected_pairs": 27031.0, "step": 26190, "student_distance_mean": 1266.4758544921874, "teacher_distance_mean": 0.852333790063858, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0018153623561374844, "weighted_relation_loss": 0.0018153623561374844 }, { "action_query_batch_std": 22.2458854675293, "action_query_norm": 942.6056457519531, "action_relation_loss": 0.0017472153180278839, "auxiliary_loss_weight": 1.0, "epoch": 24.5088868101029, "flow_matching_loss": 0.017042942438274623, "grad_norm": 0.1257733404636383, "invalid_tail_samples": 22.7, "learning_rate": 4.324969151253317e-06, "loss": 0.0188, "positive_teacher_pairs": 27108.0, "relation_loss": 0.0017472153180278839, "selected_pairs": 27108.0, "step": 26200, "student_distance_mean": 1280.408447265625, "teacher_distance_mean": 0.8619442999362945, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0017472153180278839, "weighted_relation_loss": 0.0017472153180278839 }, { "action_query_batch_std": 22.014680099487304, "action_query_norm": 932.7343566894531, "action_relation_loss": 0.0017963143996894359, "auxiliary_loss_weight": 1.0, "epoch": 24.51824134705332, "flow_matching_loss": 0.015814008936285973, "grad_norm": 0.10414807498455048, "invalid_tail_samples": 25.1, "learning_rate": 4.302573796676312e-06, "loss": 0.0176, "positive_teacher_pairs": 26549.1, "relation_loss": 0.0017963143996894359, "selected_pairs": 26549.1, "step": 26210, "student_distance_mean": 1265.3246215820313, "teacher_distance_mean": 0.85024134516716, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0017963143996894359, "weighted_relation_loss": 0.0017963143996894359 }, { "action_query_batch_std": 22.043898391723634, "action_query_norm": 938.5079467773437, "action_relation_loss": 0.0018453040742315353, "auxiliary_loss_weight": 1.0, "epoch": 24.52759588400374, "flow_matching_loss": 0.014650644082576037, "grad_norm": 0.08949218690395355, "invalid_tail_samples": 23.1, "learning_rate": 4.2802339687811385e-06, "loss": 0.0165, "positive_teacher_pairs": 27013.8, "relation_loss": 0.0018453040742315353, "selected_pairs": 27013.8, "step": 26220, "student_distance_mean": 1269.525927734375, "teacher_distance_mean": 0.8533636152744293, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0018453040742315353, "weighted_relation_loss": 0.0018453040742315353 }, { "action_query_batch_std": 22.108831024169923, "action_query_norm": 936.2573425292969, "action_relation_loss": 0.0017941580736078322, "auxiliary_loss_weight": 1.0, "epoch": 24.536950420954163, "flow_matching_loss": 0.015004530269652604, "grad_norm": 0.07864411920309067, "invalid_tail_samples": 25.8, "learning_rate": 4.257949694712771e-06, "loss": 0.0168, "positive_teacher_pairs": 26383.0, "relation_loss": 0.0017941580736078322, "selected_pairs": 26383.0, "step": 26230, "student_distance_mean": 1271.8404907226563, "teacher_distance_mean": 0.8545526087284088, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.0017941580736078322, "weighted_relation_loss": 0.0017941580736078322 }, { "action_query_batch_std": 22.14615592956543, "action_query_norm": 936.5018249511719, "action_relation_loss": 0.0018527360749430954, "auxiliary_loss_weight": 1.0, "epoch": 24.546304957904585, "flow_matching_loss": 0.016219406481832267, "grad_norm": 0.08373499661684036, "invalid_tail_samples": 24.6, "learning_rate": 4.235721001548726e-06, "loss": 0.0181, "positive_teacher_pairs": 26667.5, "relation_loss": 0.0018527360749430954, "selected_pairs": 26667.5, "step": 26240, "student_distance_mean": 1269.1927856445313, "teacher_distance_mean": 0.8539424955844879, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0018527360749430954, "weighted_relation_loss": 0.0018527360749430954 }, { "action_query_batch_std": 22.164158058166503, "action_query_norm": 938.1687194824219, "action_relation_loss": 0.0017334607895463706, "auxiliary_loss_weight": 1.0, "epoch": 24.555659494855004, "flow_matching_loss": 0.016234321985393763, "grad_norm": 0.07974627614021301, "invalid_tail_samples": 21.5, "learning_rate": 4.21354791629896e-06, "loss": 0.018, "positive_teacher_pairs": 27389.7, "relation_loss": 0.0017334607895463706, "selected_pairs": 27389.7, "step": 26250, "student_distance_mean": 1266.552001953125, "teacher_distance_mean": 0.8522831857204437, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.0017334607895463706, "weighted_relation_loss": 0.0017334607895463706 }, { "action_query_batch_std": 21.65542526245117, "action_query_norm": 920.2538330078125, "action_relation_loss": 0.001774301123805344, "auxiliary_loss_weight": 1.0, "epoch": 24.565014031805426, "flow_matching_loss": 0.014670583046972751, "grad_norm": 0.091864213347435, "invalid_tail_samples": 24.0, "learning_rate": 4.191430465905843e-06, "loss": 0.0164, "positive_teacher_pairs": 26804.6, "relation_loss": 0.001774301123805344, "selected_pairs": 26804.6, "step": 26260, "student_distance_mean": 1246.0560424804687, "teacher_distance_mean": 0.837384831905365, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.001774301123805344, "weighted_relation_loss": 0.001774301123805344 }, { "action_query_batch_std": 21.916575622558593, "action_query_norm": 928.6658203125, "action_relation_loss": 0.0018066123826429247, "auxiliary_loss_weight": 1.0, "epoch": 24.574368568755848, "flow_matching_loss": 0.01740266177803278, "grad_norm": 0.07977577298879623, "invalid_tail_samples": 25.5, "learning_rate": 4.169368677244184e-06, "loss": 0.0192, "positive_teacher_pairs": 26458.5, "relation_loss": 0.0018066123826429247, "selected_pairs": 26458.5, "step": 26270, "student_distance_mean": 1253.9782348632812, "teacher_distance_mean": 0.8442013382911682, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0018066123826429247, "weighted_relation_loss": 0.0018066123826429247 }, { "action_query_batch_std": 22.320702362060548, "action_query_norm": 942.0172607421875, "action_relation_loss": 0.0017227824428118765, "auxiliary_loss_weight": 1.0, "epoch": 24.583723105706266, "flow_matching_loss": 0.01421529883518815, "grad_norm": 0.0868590772151947, "invalid_tail_samples": 24.1, "learning_rate": 4.147362577121122e-06, "loss": 0.0159, "positive_teacher_pairs": 26782.5, "relation_loss": 0.0017227824428118765, "selected_pairs": 26782.5, "step": 26280, "student_distance_mean": 1287.7324096679688, "teacher_distance_mean": 0.8668675124645233, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0017227824428118765, "weighted_relation_loss": 0.0017227824428118765 }, { "action_query_batch_std": 22.000647354125977, "action_query_norm": 932.7893493652343, "action_relation_loss": 0.0017873262986540794, "auxiliary_loss_weight": 1.0, "epoch": 24.593077642656688, "flow_matching_loss": 0.014301943592727184, "grad_norm": 0.08098223060369492, "invalid_tail_samples": 24.4, "learning_rate": 4.125412192276157e-06, "loss": 0.0161, "positive_teacher_pairs": 26708.4, "relation_loss": 0.0017873262986540794, "selected_pairs": 26708.4, "step": 26290, "student_distance_mean": 1266.2258178710938, "teacher_distance_mean": 0.8519282639026642, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.0017873262986540794, "weighted_relation_loss": 0.0017873262986540794 }, { "action_query_batch_std": 22.33780918121338, "action_query_norm": 942.0145202636719, "action_relation_loss": 0.0017783622490242124, "auxiliary_loss_weight": 1.0, "epoch": 24.60243217960711, "flow_matching_loss": 0.01646456429734826, "grad_norm": 0.09361705929040909, "invalid_tail_samples": 22.6, "learning_rate": 4.10351754938107e-06, "loss": 0.0182, "positive_teacher_pairs": 27131.7, "relation_loss": 0.0017783622490242124, "selected_pairs": 27131.7, "step": 26300, "student_distance_mean": 1280.6344482421875, "teacher_distance_mean": 0.8624108612537384, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0017783622490242124, "weighted_relation_loss": 0.0017783622490242124 }, { "action_query_batch_std": 21.884060859680176, "action_query_norm": 930.0330383300782, "action_relation_loss": 0.0017831783508881927, "auxiliary_loss_weight": 1.0, "epoch": 24.611786716557532, "flow_matching_loss": 0.014327207766473293, "grad_norm": 0.08264926820993423, "invalid_tail_samples": 22.1, "learning_rate": 4.081678675039913e-06, "loss": 0.0161, "positive_teacher_pairs": 27249.3, "relation_loss": 0.0017831783508881927, "selected_pairs": 27249.3, "step": 26310, "student_distance_mean": 1252.228173828125, "teacher_distance_mean": 0.8432863116264343, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0017831783508881927, "weighted_relation_loss": 0.0017831783508881927 }, { "action_query_batch_std": 22.355397605895995, "action_query_norm": 946.5692626953125, "action_relation_loss": 0.001756399788428098, "auxiliary_loss_weight": 1.0, "epoch": 24.62114125350795, "flow_matching_loss": 0.01738814152777195, "grad_norm": 0.09944380074739456, "invalid_tail_samples": 21.4, "learning_rate": 4.0598955957889876e-06, "loss": 0.0191, "positive_teacher_pairs": 27407.5, "relation_loss": 0.001756399788428098, "selected_pairs": 27407.5, "step": 26320, "student_distance_mean": 1281.5949096679688, "teacher_distance_mean": 0.8656389772891998, "valid_action_samples": 234.6, "weighted_auxiliary_loss": 0.001756399788428098, "weighted_relation_loss": 0.001756399788428098 }, { "action_query_batch_std": 21.72991199493408, "action_query_norm": 925.4007446289063, "action_relation_loss": 0.0017513962928205728, "auxiliary_loss_weight": 1.0, "epoch": 24.630495790458372, "flow_matching_loss": 0.01530267409980297, "grad_norm": 0.09661949425935745, "invalid_tail_samples": 21.6, "learning_rate": 4.038168338096776e-06, "loss": 0.0171, "positive_teacher_pairs": 27360.3, "relation_loss": 0.0017513962928205728, "selected_pairs": 27360.3, "step": 26330, "student_distance_mean": 1252.1312377929687, "teacher_distance_mean": 0.8444082736968994, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.0017513962928205728, "weighted_relation_loss": 0.0017513962928205728 }, { "action_query_batch_std": 22.082351875305175, "action_query_norm": 935.6666748046875, "action_relation_loss": 0.0018012198503129183, "auxiliary_loss_weight": 1.0, "epoch": 24.639850327408794, "flow_matching_loss": 0.015264722425490618, "grad_norm": 0.07583962380886078, "invalid_tail_samples": 25.5, "learning_rate": 4.016496928363944e-06, "loss": 0.0171, "positive_teacher_pairs": 26462.4, "relation_loss": 0.0018012198503129183, "selected_pairs": 26462.4, "step": 26340, "student_distance_mean": 1270.2432373046875, "teacher_distance_mean": 0.8556677103042603, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0018012198503129183, "weighted_relation_loss": 0.0018012198503129183 }, { "action_query_batch_std": 22.21110954284668, "action_query_norm": 941.19697265625, "action_relation_loss": 0.0018183843581937253, "auxiliary_loss_weight": 1.0, "epoch": 24.649204864359213, "flow_matching_loss": 0.01411315705627203, "grad_norm": 0.07817959040403366, "invalid_tail_samples": 22.1, "learning_rate": 3.994881392923317e-06, "loss": 0.0159, "positive_teacher_pairs": 27248.1, "relation_loss": 0.0018183843581937253, "selected_pairs": 27248.1, "step": 26350, "student_distance_mean": 1271.8934692382813, "teacher_distance_mean": 0.8560960471630097, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0018183843581937253, "weighted_relation_loss": 0.0018183843581937253 }, { "action_query_batch_std": 22.03198699951172, "action_query_norm": 936.2908203125, "action_relation_loss": 0.0017424278426915406, "auxiliary_loss_weight": 1.0, "epoch": 24.658559401309635, "flow_matching_loss": 0.016340749990195035, "grad_norm": 0.08352337032556534, "invalid_tail_samples": 25.3, "learning_rate": 3.9733217580397945e-06, "loss": 0.0181, "positive_teacher_pairs": 26503.0, "relation_loss": 0.0017424278426915406, "selected_pairs": 26503.0, "step": 26360, "student_distance_mean": 1274.459423828125, "teacher_distance_mean": 0.8573636949062348, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0017424278426915406, "weighted_relation_loss": 0.0017424278426915406 }, { "action_query_batch_std": 21.86466293334961, "action_query_norm": 928.3883422851562, "action_relation_loss": 0.001802528277039528, "auxiliary_loss_weight": 1.0, "epoch": 24.667913938260057, "flow_matching_loss": 0.01603640094399452, "grad_norm": 0.07862168550491333, "invalid_tail_samples": 25.0, "learning_rate": 3.951818049910366e-06, "loss": 0.0178, "positive_teacher_pairs": 26573.6, "relation_loss": 0.001802528277039528, "selected_pairs": 26573.6, "step": 26370, "student_distance_mean": 1257.125244140625, "teacher_distance_mean": 0.8468840897083283, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.001802528277039528, "weighted_relation_loss": 0.001802528277039528 }, { "action_query_batch_std": 21.765341186523436, "action_query_norm": 927.4801025390625, "action_relation_loss": 0.0017406575731001793, "auxiliary_loss_weight": 1.0, "epoch": 24.67726847521048, "flow_matching_loss": 0.014447541628032922, "grad_norm": 0.10488202422857285, "invalid_tail_samples": 24.9, "learning_rate": 3.930370294664071e-06, "loss": 0.0162, "positive_teacher_pairs": 26597.9, "relation_loss": 0.0017406575731001793, "selected_pairs": 26597.9, "step": 26380, "student_distance_mean": 1260.5262573242187, "teacher_distance_mean": 0.8466160535812378, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0017406575731001793, "weighted_relation_loss": 0.0017406575731001793 }, { "action_query_batch_std": 22.067233848571778, "action_query_norm": 936.3261352539063, "action_relation_loss": 0.0017549653188325466, "auxiliary_loss_weight": 1.0, "epoch": 24.686623012160897, "flow_matching_loss": 0.014418445900082589, "grad_norm": 0.07381510734558105, "invalid_tail_samples": 21.9, "learning_rate": 3.908978518361938e-06, "loss": 0.0162, "positive_teacher_pairs": 27296.2, "relation_loss": 0.0017549653188325466, "selected_pairs": 27296.2, "step": 26390, "student_distance_mean": 1267.6211669921875, "teacher_distance_mean": 0.8531278252601624, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.0017549653188325466, "weighted_relation_loss": 0.0017549653188325466 }, { "action_query_batch_std": 22.181888771057128, "action_query_norm": 940.3683532714844, "action_relation_loss": 0.0017600743914954365, "auxiliary_loss_weight": 1.0, "epoch": 24.69597754911132, "flow_matching_loss": 0.015957724675536154, "grad_norm": 0.09294839948415756, "invalid_tail_samples": 23.6, "learning_rate": 3.887642746997017e-06, "loss": 0.0177, "positive_teacher_pairs": 26890.6, "relation_loss": 0.0017600743914954365, "selected_pairs": 26890.6, "step": 26400, "student_distance_mean": 1270.28427734375, "teacher_distance_mean": 0.8567950189113617, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0017600743914954365, "weighted_relation_loss": 0.0017600743914954365 }, { "action_query_batch_std": 22.113859176635742, "action_query_norm": 932.2232116699219, "action_relation_loss": 0.001908629888202995, "auxiliary_loss_weight": 1.0, "epoch": 24.70533208606174, "flow_matching_loss": 0.015352807193994521, "grad_norm": 0.09681423753499985, "invalid_tail_samples": 25.1, "learning_rate": 3.866363006494255e-06, "loss": 0.0173, "positive_teacher_pairs": 26556.2, "relation_loss": 0.001908629888202995, "selected_pairs": 26556.2, "step": 26410, "student_distance_mean": 1269.2815307617188, "teacher_distance_mean": 0.855964207649231, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.001908629888202995, "weighted_relation_loss": 0.001908629888202995 }, { "action_query_batch_std": 22.152140426635743, "action_query_norm": 937.7559326171875, "action_relation_loss": 0.0017876491765491664, "auxiliary_loss_weight": 1.0, "epoch": 24.71468662301216, "flow_matching_loss": 0.01629184065386653, "grad_norm": 0.07590235024690628, "invalid_tail_samples": 22.1, "learning_rate": 3.8451393227105725e-06, "loss": 0.0181, "positive_teacher_pairs": 27245.9, "relation_loss": 0.0017876491765491664, "selected_pairs": 27245.9, "step": 26420, "student_distance_mean": 1276.52939453125, "teacher_distance_mean": 0.8599147200584412, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0017876491765491664, "weighted_relation_loss": 0.0017876491765491664 }, { "action_query_batch_std": 22.05778102874756, "action_query_norm": 935.5545471191406, "action_relation_loss": 0.0017886561807245016, "auxiliary_loss_weight": 1.0, "epoch": 24.72404115996258, "flow_matching_loss": 0.014602304622530937, "grad_norm": 0.09724484384059906, "invalid_tail_samples": 23.8, "learning_rate": 3.823971721434727e-06, "loss": 0.0164, "positive_teacher_pairs": 26847.8, "relation_loss": 0.0017886561807245016, "selected_pairs": 26847.8, "step": 26430, "student_distance_mean": 1270.2901611328125, "teacher_distance_mean": 0.8540280401706696, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0017886561807245016, "weighted_relation_loss": 0.0017886561807245016 }, { "action_query_batch_std": 21.964140701293946, "action_query_norm": 933.7874145507812, "action_relation_loss": 0.001768311799969524, "auxiliary_loss_weight": 1.0, "epoch": 24.733395696913004, "flow_matching_loss": 0.014646526426076889, "grad_norm": 0.06978937238454819, "invalid_tail_samples": 23.3, "learning_rate": 3.8028602283873505e-06, "loss": 0.0164, "positive_teacher_pairs": 26970.7, "relation_loss": 0.001768311799969524, "selected_pairs": 26970.7, "step": 26440, "student_distance_mean": 1265.16787109375, "teacher_distance_mean": 0.8519418597221374, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.001768311799969524, "weighted_relation_loss": 0.001768311799969524 }, { "action_query_batch_std": 22.14183692932129, "action_query_norm": 936.4266174316406, "action_relation_loss": 0.0018170218449085952, "auxiliary_loss_weight": 1.0, "epoch": 24.742750233863426, "flow_matching_loss": 0.015782774332910775, "grad_norm": 0.07430503517389297, "invalid_tail_samples": 25.3, "learning_rate": 3.781804869220912e-06, "loss": 0.0176, "positive_teacher_pairs": 26505.4, "relation_loss": 0.0018170218449085952, "selected_pairs": 26505.4, "step": 26450, "student_distance_mean": 1278.869970703125, "teacher_distance_mean": 0.8622684121131897, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0018170218449085952, "weighted_relation_loss": 0.0018170218449085952 }, { "action_query_batch_std": 21.915075302124023, "action_query_norm": 931.3369873046875, "action_relation_loss": 0.0018389960867352783, "auxiliary_loss_weight": 1.0, "epoch": 24.752104770813844, "flow_matching_loss": 0.01498579615727067, "grad_norm": 0.09471356123685837, "invalid_tail_samples": 23.3, "learning_rate": 3.760805669519646e-06, "loss": 0.0168, "positive_teacher_pairs": 26966.3, "relation_loss": 0.0018389960867352783, "selected_pairs": 26966.3, "step": 26460, "student_distance_mean": 1263.3632690429688, "teacher_distance_mean": 0.8506422460079193, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0018389960867352783, "weighted_relation_loss": 0.0018389960867352783 }, { "action_query_batch_std": 21.9535774230957, "action_query_norm": 927.7124572753906, "action_relation_loss": 0.0017624630010686815, "auxiliary_loss_weight": 1.0, "epoch": 24.761459307764266, "flow_matching_loss": 0.015937043353915215, "grad_norm": 0.09660971909761429, "invalid_tail_samples": 26.6, "learning_rate": 3.7398626547995587e-06, "loss": 0.0177, "positive_teacher_pairs": 26209.0, "relation_loss": 0.0017624630010686815, "selected_pairs": 26209.0, "step": 26470, "student_distance_mean": 1261.125732421875, "teacher_distance_mean": 0.8504232704639435, "valid_action_samples": 229.4, "weighted_auxiliary_loss": 0.0017624630010686815, "weighted_relation_loss": 0.0017624630010686815 }, { "action_query_batch_std": 21.73618679046631, "action_query_norm": 924.20810546875, "action_relation_loss": 0.001829108688980341, "auxiliary_loss_weight": 1.0, "epoch": 24.770813844714688, "flow_matching_loss": 0.014373281411826611, "grad_norm": 0.08749188482761383, "invalid_tail_samples": 22.3, "learning_rate": 3.7189758505083995e-06, "loss": 0.0162, "positive_teacher_pairs": 27201.9, "relation_loss": 0.001829108688980341, "selected_pairs": 27201.9, "step": 26480, "student_distance_mean": 1252.0712646484376, "teacher_distance_mean": 0.843765264749527, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.001829108688980341, "weighted_relation_loss": 0.001829108688980341 }, { "action_query_batch_std": 21.852705574035646, "action_query_norm": 926.6580993652344, "action_relation_loss": 0.0017912273528054357, "auxiliary_loss_weight": 1.0, "epoch": 24.780168381665106, "flow_matching_loss": 0.016158902272582053, "grad_norm": 0.0871034637093544, "invalid_tail_samples": 24.3, "learning_rate": 3.6981452820255837e-06, "loss": 0.018, "positive_teacher_pairs": 26734.9, "relation_loss": 0.0017912273528054357, "selected_pairs": 26734.9, "step": 26490, "student_distance_mean": 1253.3938842773437, "teacher_distance_mean": 0.8450819492340088, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0017912273528054357, "weighted_relation_loss": 0.0017912273528054357 }, { "action_query_batch_std": 21.862408256530763, "action_query_norm": 929.9294921875, "action_relation_loss": 0.0017476388602517545, "auxiliary_loss_weight": 1.0, "epoch": 24.78952291861553, "flow_matching_loss": 0.015653406921774148, "grad_norm": 0.07707181572914124, "invalid_tail_samples": 24.8, "learning_rate": 3.6773709746622363e-06, "loss": 0.0174, "positive_teacher_pairs": 26624.0, "relation_loss": 0.0017476388602517545, "selected_pairs": 26624.0, "step": 26500, "student_distance_mean": 1265.41376953125, "teacher_distance_mean": 0.8528895795345306, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0017476388602517545, "weighted_relation_loss": 0.0017476388602517545 }, { "action_query_batch_std": 22.224050521850586, "action_query_norm": 940.1999633789062, "action_relation_loss": 0.0017689852858893574, "auxiliary_loss_weight": 1.0, "epoch": 24.79887745556595, "flow_matching_loss": 0.014241054467856885, "grad_norm": 0.09489816427230835, "invalid_tail_samples": 25.3, "learning_rate": 3.6566529536610995e-06, "loss": 0.016, "positive_teacher_pairs": 26500.9, "relation_loss": 0.0017689852858893574, "selected_pairs": 26500.9, "step": 26510, "student_distance_mean": 1279.5756958007812, "teacher_distance_mean": 0.8626170575618743, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0017689852858893574, "weighted_relation_loss": 0.0017689852858893574 }, { "action_query_batch_std": 22.207673263549804, "action_query_norm": 937.7142822265625, "action_relation_loss": 0.001755839551333338, "auxiliary_loss_weight": 1.0, "epoch": 24.80823199251637, "flow_matching_loss": 0.013545804377645253, "grad_norm": 0.10554123669862747, "invalid_tail_samples": 23.2, "learning_rate": 3.635991244196513e-06, "loss": 0.0153, "positive_teacher_pairs": 26987.8, "relation_loss": 0.001755839551333338, "selected_pairs": 26987.8, "step": 26520, "student_distance_mean": 1280.8520874023438, "teacher_distance_mean": 0.8635007858276367, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.001755839551333338, "weighted_relation_loss": 0.001755839551333338 }, { "action_query_batch_std": 22.14139747619629, "action_query_norm": 936.6120422363281, "action_relation_loss": 0.0017515841289423406, "auxiliary_loss_weight": 1.0, "epoch": 24.81758652946679, "flow_matching_loss": 0.01818838994950056, "grad_norm": 0.0896487906575203, "invalid_tail_samples": 23.9, "learning_rate": 3.615385871374405e-06, "loss": 0.0199, "positive_teacher_pairs": 26823.8, "relation_loss": 0.0017515841289423406, "selected_pairs": 26823.8, "step": 26530, "student_distance_mean": 1268.1613525390626, "teacher_distance_mean": 0.8536558747291565, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0017515841289423406, "weighted_relation_loss": 0.0017515841289423406 }, { "action_query_batch_std": 22.13288230895996, "action_query_norm": 934.7111328125, "action_relation_loss": 0.0017672143294475973, "auxiliary_loss_weight": 1.0, "epoch": 24.826941066417213, "flow_matching_loss": 0.016111449897289278, "grad_norm": 0.0855112299323082, "invalid_tail_samples": 22.8, "learning_rate": 3.5948368602322367e-06, "loss": 0.0179, "positive_teacher_pairs": 27078.5, "relation_loss": 0.0017672143294475973, "selected_pairs": 27078.5, "step": 26540, "student_distance_mean": 1276.002587890625, "teacher_distance_mean": 0.8604686617851257, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0017672143294475973, "weighted_relation_loss": 0.0017672143294475973 }, { "action_query_batch_std": 22.387205123901367, "action_query_norm": 946.3779357910156, "action_relation_loss": 0.0018036452936939895, "auxiliary_loss_weight": 1.0, "epoch": 24.836295603367635, "flow_matching_loss": 0.01631225077435374, "grad_norm": 0.08544410765171051, "invalid_tail_samples": 24.3, "learning_rate": 3.5743442357390187e-06, "loss": 0.0181, "positive_teacher_pairs": 26732.4, "relation_loss": 0.0018036452936939895, "selected_pairs": 26732.4, "step": 26550, "student_distance_mean": 1286.0109619140626, "teacher_distance_mean": 0.8665674388408661, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0018036452936939895, "weighted_relation_loss": 0.0018036452936939895 }, { "action_query_batch_std": 22.01680278778076, "action_query_norm": 934.6552978515625, "action_relation_loss": 0.0017801705631427466, "auxiliary_loss_weight": 1.0, "epoch": 24.845650140318053, "flow_matching_loss": 0.014877013955265283, "grad_norm": 0.08322256058454514, "invalid_tail_samples": 21.5, "learning_rate": 3.5539080227951937e-06, "loss": 0.0167, "positive_teacher_pairs": 27386.1, "relation_loss": 0.0017801705631427466, "selected_pairs": 27386.1, "step": 26560, "student_distance_mean": 1260.0756591796876, "teacher_distance_mean": 0.8472756683826447, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.0017801705631427466, "weighted_relation_loss": 0.0017801705631427466 }, { "action_query_batch_std": 21.845001220703125, "action_query_norm": 928.6236450195313, "action_relation_loss": 0.0017684565740637482, "auxiliary_loss_weight": 1.0, "epoch": 24.855004677268475, "flow_matching_loss": 0.015285946894437075, "grad_norm": 0.06829164177179337, "invalid_tail_samples": 24.8, "learning_rate": 3.533528246232709e-06, "loss": 0.0171, "positive_teacher_pairs": 26621.6, "relation_loss": 0.0017684565740637482, "selected_pairs": 26621.6, "step": 26570, "student_distance_mean": 1256.7986938476563, "teacher_distance_mean": 0.8457021832466125, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0017684565740637482, "weighted_relation_loss": 0.0017684565740637482 }, { "action_query_batch_std": 21.971162033081054, "action_query_norm": 932.9687683105469, "action_relation_loss": 0.0017636118573136628, "auxiliary_loss_weight": 1.0, "epoch": 24.864359214218897, "flow_matching_loss": 0.013535660691559315, "grad_norm": 0.09079352021217346, "invalid_tail_samples": 22.5, "learning_rate": 3.5132049308149117e-06, "loss": 0.0153, "positive_teacher_pairs": 27155.4, "relation_loss": 0.0017636118573136628, "selected_pairs": 27155.4, "step": 26580, "student_distance_mean": 1264.5283081054688, "teacher_distance_mean": 0.8507469356060028, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0017636118573136628, "weighted_relation_loss": 0.0017636118573136628 }, { "action_query_batch_std": 22.297175407409668, "action_query_norm": 940.362109375, "action_relation_loss": 0.001796121778897941, "auxiliary_loss_weight": 1.0, "epoch": 24.873713751169316, "flow_matching_loss": 0.015466044656932354, "grad_norm": 0.08728625625371933, "invalid_tail_samples": 24.2, "learning_rate": 3.4929381012365425e-06, "loss": 0.0173, "positive_teacher_pairs": 26755.4, "relation_loss": 0.001796121778897941, "selected_pairs": 26755.4, "step": 26590, "student_distance_mean": 1282.72900390625, "teacher_distance_mean": 0.8645830392837525, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.001796121778897941, "weighted_relation_loss": 0.001796121778897941 }, { "action_query_batch_std": 22.09181365966797, "action_query_norm": 936.9421508789062, "action_relation_loss": 0.0017466021701693535, "auxiliary_loss_weight": 1.0, "epoch": 24.883068288119738, "flow_matching_loss": 0.015364805981516839, "grad_norm": 0.10011204332113266, "invalid_tail_samples": 21.1, "learning_rate": 3.472727782123697e-06, "loss": 0.0171, "positive_teacher_pairs": 27486.0, "relation_loss": 0.0017466021701693535, "selected_pairs": 27486.0, "step": 26600, "student_distance_mean": 1265.0357177734375, "teacher_distance_mean": 0.8521816432476044, "valid_action_samples": 234.9, "weighted_auxiliary_loss": 0.0017466021701693535, "weighted_relation_loss": 0.0017466021701693535 }, { "action_query_batch_std": 21.807025337219237, "action_query_norm": 929.2329772949219, "action_relation_loss": 0.0018279701354913414, "auxiliary_loss_weight": 1.0, "epoch": 24.89242282507016, "flow_matching_loss": 0.013876318093389272, "grad_norm": 0.09883598238229752, "invalid_tail_samples": 23.2, "learning_rate": 3.4525739980338425e-06, "loss": 0.0157, "positive_teacher_pairs": 26988.9, "relation_loss": 0.0018279701354913414, "selected_pairs": 26988.9, "step": 26610, "student_distance_mean": 1256.5562133789062, "teacher_distance_mean": 0.8475111067295075, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0018279701354913414, "weighted_relation_loss": 0.0018279701354913414 }, { "action_query_batch_std": 21.93004913330078, "action_query_norm": 931.4258361816406, "action_relation_loss": 0.0017589193303138018, "auxiliary_loss_weight": 1.0, "epoch": 24.90177736202058, "flow_matching_loss": 0.015215079300105572, "grad_norm": 0.09472040086984634, "invalid_tail_samples": 22.9, "learning_rate": 3.432476773455712e-06, "loss": 0.017, "positive_teacher_pairs": 27061.7, "relation_loss": 0.0017589193303138018, "selected_pairs": 27061.7, "step": 26620, "student_distance_mean": 1262.212939453125, "teacher_distance_mean": 0.8501305937767029, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0017589193303138018, "weighted_relation_loss": 0.0017589193303138018 }, { "action_query_batch_std": 22.115729904174806, "action_query_norm": 936.5011596679688, "action_relation_loss": 0.0017768342630006372, "auxiliary_loss_weight": 1.0, "epoch": 24.911131898971, "flow_matching_loss": 0.014606885705143213, "grad_norm": 0.1020302027463913, "invalid_tail_samples": 23.5, "learning_rate": 3.4124361328093378e-06, "loss": 0.0164, "positive_teacher_pairs": 26921.1, "relation_loss": 0.0017768342630006372, "selected_pairs": 26921.1, "step": 26630, "student_distance_mean": 1275.1577392578124, "teacher_distance_mean": 0.8595704674720764, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0017768342630006372, "weighted_relation_loss": 0.0017768342630006372 }, { "action_query_batch_std": 22.03239498138428, "action_query_norm": 933.7553771972656, "action_relation_loss": 0.001742169342469424, "auxiliary_loss_weight": 1.0, "epoch": 24.920486435921422, "flow_matching_loss": 0.016525528393685818, "grad_norm": 0.08168385177850723, "invalid_tail_samples": 26.8, "learning_rate": 3.392452100445975e-06, "loss": 0.0183, "positive_teacher_pairs": 26167.9, "relation_loss": 0.001742169342469424, "selected_pairs": 26167.9, "step": 26640, "student_distance_mean": 1271.816650390625, "teacher_distance_mean": 0.8579560041427612, "valid_action_samples": 229.2, "weighted_auxiliary_loss": 0.001742169342469424, "weighted_relation_loss": 0.001742169342469424 }, { "action_query_batch_std": 22.08936767578125, "action_query_norm": 937.2784790039062, "action_relation_loss": 0.0017671745154075325, "auxiliary_loss_weight": 1.0, "epoch": 24.929840972871844, "flow_matching_loss": 0.017261523753404617, "grad_norm": 0.07573994994163513, "invalid_tail_samples": 24.0, "learning_rate": 3.3725247006481163e-06, "loss": 0.019, "positive_teacher_pairs": 26805.8, "relation_loss": 0.0017671745154075325, "selected_pairs": 26805.8, "step": 26650, "student_distance_mean": 1271.2197143554688, "teacher_distance_mean": 0.8569309413433075, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0017671745154075325, "weighted_relation_loss": 0.0017671745154075325 }, { "action_query_batch_std": 22.20042266845703, "action_query_norm": 938.0475219726562, "action_relation_loss": 0.0018067354802042245, "auxiliary_loss_weight": 1.0, "epoch": 24.939195509822262, "flow_matching_loss": 0.015596389025449752, "grad_norm": 0.09280914813280106, "invalid_tail_samples": 23.9, "learning_rate": 3.3526539576294313e-06, "loss": 0.0174, "positive_teacher_pairs": 26824.6, "relation_loss": 0.0018067354802042245, "selected_pairs": 26824.6, "step": 26660, "student_distance_mean": 1279.2159545898437, "teacher_distance_mean": 0.8621124148368835, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0018067354802042245, "weighted_relation_loss": 0.0018067354802042245 }, { "action_query_batch_std": 21.94965534210205, "action_query_norm": 931.8775817871094, "action_relation_loss": 0.0017892614123411477, "auxiliary_loss_weight": 1.0, "epoch": 24.948550046772684, "flow_matching_loss": 0.013899321854114532, "grad_norm": 0.08178909122943878, "invalid_tail_samples": 25.1, "learning_rate": 3.332839895534745e-06, "loss": 0.0157, "positive_teacher_pairs": 26559.0, "relation_loss": 0.0017892614123411477, "selected_pairs": 26559.0, "step": 26670, "student_distance_mean": 1265.8868286132813, "teacher_distance_mean": 0.8539897322654724, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0017892614123411477, "weighted_relation_loss": 0.0017892614123411477 }, { "action_query_batch_std": 22.14352951049805, "action_query_norm": 937.3851623535156, "action_relation_loss": 0.0017742278170771897, "auxiliary_loss_weight": 1.0, "epoch": 24.957904583723106, "flow_matching_loss": 0.014426902588456868, "grad_norm": 0.08845193684101105, "invalid_tail_samples": 22.1, "learning_rate": 3.3130825384400155e-06, "loss": 0.0162, "positive_teacher_pairs": 27244.6, "relation_loss": 0.0017742278170771897, "selected_pairs": 27244.6, "step": 26680, "student_distance_mean": 1274.1912841796875, "teacher_distance_mean": 0.8576843738555908, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0017742278170771897, "weighted_relation_loss": 0.0017742278170771897 }, { "action_query_batch_std": 22.050894737243652, "action_query_norm": 935.6030944824219, "action_relation_loss": 0.0017793699051253497, "auxiliary_loss_weight": 1.0, "epoch": 24.96725912067353, "flow_matching_loss": 0.015886369813233613, "grad_norm": 0.0970141664147377, "invalid_tail_samples": 23.0, "learning_rate": 3.293381910352278e-06, "loss": 0.0177, "positive_teacher_pairs": 27035.9, "relation_loss": 0.0017793699051253497, "selected_pairs": 27035.9, "step": 26690, "student_distance_mean": 1269.7019409179688, "teacher_distance_mean": 0.8549809157848358, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0017793699051253497, "weighted_relation_loss": 0.0017793699051253497 }, { "action_query_batch_std": 22.085286140441895, "action_query_norm": 935.3622009277344, "action_relation_loss": 0.001709809899330139, "auxiliary_loss_weight": 1.0, "epoch": 24.976613657623947, "flow_matching_loss": 0.016229134052991867, "grad_norm": 0.07591570168733597, "invalid_tail_samples": 24.4, "learning_rate": 3.273738035209678e-06, "loss": 0.0179, "positive_teacher_pairs": 26709.1, "relation_loss": 0.001709809899330139, "selected_pairs": 26709.1, "step": 26700, "student_distance_mean": 1270.7783935546875, "teacher_distance_mean": 0.8558022916316986, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.001709809899330139, "weighted_relation_loss": 0.001709809899330139 }, { "action_query_batch_std": 22.022582626342775, "action_query_norm": 934.7790222167969, "action_relation_loss": 0.0017419561045244336, "auxiliary_loss_weight": 1.0, "epoch": 24.98596819457437, "flow_matching_loss": 0.015396211761981249, "grad_norm": 0.10254230350255966, "invalid_tail_samples": 25.4, "learning_rate": 3.254150936881356e-06, "loss": 0.0171, "positive_teacher_pairs": 26479.0, "relation_loss": 0.0017419561045244336, "selected_pairs": 26479.0, "step": 26710, "student_distance_mean": 1267.5427734375, "teacher_distance_mean": 0.8531536757946014, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.0017419561045244336, "weighted_relation_loss": 0.0017419561045244336 }, { "action_query_batch_std": 22.080075645446776, "action_query_norm": 934.9103515625, "action_relation_loss": 0.0017992060747928917, "auxiliary_loss_weight": 1.0, "epoch": 24.99532273152479, "flow_matching_loss": 0.014018019754439592, "grad_norm": 0.07838134467601776, "invalid_tail_samples": 26.3, "learning_rate": 3.234620639167496e-06, "loss": 0.0158, "positive_teacher_pairs": 26271.5, "relation_loss": 0.0017992060747928917, "selected_pairs": 26271.5, "step": 26720, "student_distance_mean": 1274.168994140625, "teacher_distance_mean": 0.8584648728370666, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.0017992060747928917, "weighted_relation_loss": 0.0017992060747928917 }, { "action_query_batch_std": 22.19609889984131, "action_query_norm": 938.04375, "action_relation_loss": 0.0017102035810239613, "auxiliary_loss_weight": 1.0, "epoch": 25.00467726847521, "flow_matching_loss": 0.014491321798413993, "grad_norm": 0.1554470658302307, "invalid_tail_samples": 21.2, "learning_rate": 3.2151471657992482e-06, "loss": 0.0162, "positive_teacher_pairs": 24424.8, "relation_loss": 0.0017102035810239613, "selected_pairs": 24424.8, "step": 26730, "student_distance_mean": 1276.2428344726563, "teacher_distance_mean": 0.8599992752075195, "valid_action_samples": 214.9, "weighted_auxiliary_loss": 0.0017102035810239613, "weighted_relation_loss": 0.0017102035810239613 }, { "action_query_batch_std": 22.23836898803711, "action_query_norm": 939.60205078125, "action_relation_loss": 0.0018101776717230678, "auxiliary_loss_weight": 1.0, "epoch": 25.01403180542563, "flow_matching_loss": 0.016357090789824724, "grad_norm": 0.08783845603466034, "invalid_tail_samples": 25.2, "learning_rate": 3.195730540438718e-06, "loss": 0.0182, "positive_teacher_pairs": 26532.7, "relation_loss": 0.0018101776717230678, "selected_pairs": 26532.7, "step": 26740, "student_distance_mean": 1282.4650024414063, "teacher_distance_mean": 0.8633697330951691, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0018101776717230678, "weighted_relation_loss": 0.0018101776717230678 }, { "action_query_batch_std": 21.919247436523438, "action_query_norm": 927.8304077148438, "action_relation_loss": 0.0017631897237151862, "auxiliary_loss_weight": 1.0, "epoch": 25.023386342376053, "flow_matching_loss": 0.017179823480546474, "grad_norm": 0.0749955028295517, "invalid_tail_samples": 23.7, "learning_rate": 3.1763707866789336e-06, "loss": 0.0189, "positive_teacher_pairs": 26872.2, "relation_loss": 0.0017631897237151862, "selected_pairs": 26872.2, "step": 26750, "student_distance_mean": 1259.9388061523437, "teacher_distance_mean": 0.8482341170310974, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0017631897237151862, "weighted_relation_loss": 0.0017631897237151862 }, { "action_query_batch_std": 22.255242919921876, "action_query_norm": 943.3276428222656, "action_relation_loss": 0.00174820008687675, "auxiliary_loss_weight": 1.0, "epoch": 25.03274087932647, "flow_matching_loss": 0.014675568882375955, "grad_norm": 0.10298152267932892, "invalid_tail_samples": 21.7, "learning_rate": 3.1570679280438165e-06, "loss": 0.0164, "positive_teacher_pairs": 27334.5, "relation_loss": 0.00174820008687675, "selected_pairs": 27334.5, "step": 26760, "student_distance_mean": 1279.4932373046875, "teacher_distance_mean": 0.8601479887962341, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.00174820008687675, "weighted_relation_loss": 0.00174820008687675 }, { "action_query_batch_std": 21.998232078552245, "action_query_norm": 934.6589721679687, "action_relation_loss": 0.0017544729402288795, "auxiliary_loss_weight": 1.0, "epoch": 25.042095416276894, "flow_matching_loss": 0.015054570510983467, "grad_norm": 0.11432966589927673, "invalid_tail_samples": 24.2, "learning_rate": 3.1378219879881767e-06, "loss": 0.0168, "positive_teacher_pairs": 26759.2, "relation_loss": 0.0017544729402288795, "selected_pairs": 26759.2, "step": 26770, "student_distance_mean": 1268.3336059570313, "teacher_distance_mean": 0.8541248261928558, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0017544729402288795, "weighted_relation_loss": 0.0017544729402288795 }, { "action_query_batch_std": 22.38538589477539, "action_query_norm": 944.524462890625, "action_relation_loss": 0.0017251254757866263, "auxiliary_loss_weight": 1.0, "epoch": 25.051449953227316, "flow_matching_loss": 0.016740670334547757, "grad_norm": 0.0683324933052063, "invalid_tail_samples": 21.9, "learning_rate": 3.11863298989763e-06, "loss": 0.0185, "positive_teacher_pairs": 27291.6, "relation_loss": 0.0017251254757866263, "selected_pairs": 27291.6, "step": 26780, "student_distance_mean": 1286.7795654296874, "teacher_distance_mean": 0.8670066177845002, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.0017251254757866263, "weighted_relation_loss": 0.0017251254757866263 }, { "action_query_batch_std": 22.327783584594727, "action_query_norm": 946.7477905273438, "action_relation_loss": 0.001749597885645926, "auxiliary_loss_weight": 1.0, "epoch": 25.060804490177738, "flow_matching_loss": 0.014876305125653744, "grad_norm": 0.080985888838768, "invalid_tail_samples": 21.7, "learning_rate": 3.0995009570886303e-06, "loss": 0.0166, "positive_teacher_pairs": 27340.9, "relation_loss": 0.001749597885645926, "selected_pairs": 27340.9, "step": 26790, "student_distance_mean": 1279.8364501953124, "teacher_distance_mean": 0.8618344008922577, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.001749597885645926, "weighted_relation_loss": 0.001749597885645926 }, { "action_query_batch_std": 22.0400821685791, "action_query_norm": 935.3673217773437, "action_relation_loss": 0.0017599400831386446, "auxiliary_loss_weight": 1.0, "epoch": 25.070159027128156, "flow_matching_loss": 0.01375854229554534, "grad_norm": 0.1103539988398552, "invalid_tail_samples": 23.0, "learning_rate": 3.0804259128083936e-06, "loss": 0.0155, "positive_teacher_pairs": 27036.1, "relation_loss": 0.0017599400831386446, "selected_pairs": 27036.1, "step": 26800, "student_distance_mean": 1268.2280151367188, "teacher_distance_mean": 0.8528465867042542, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0017599400831386446, "weighted_relation_loss": 0.0017599400831386446 }, { "action_query_batch_std": 22.176136207580566, "action_query_norm": 939.0643798828125, "action_relation_loss": 0.0016866722726263106, "auxiliary_loss_weight": 1.0, "epoch": 25.079513564078578, "flow_matching_loss": 0.015451317187398672, "grad_norm": 0.09255452454090118, "invalid_tail_samples": 20.5, "learning_rate": 3.06140788023489e-06, "loss": 0.0171, "positive_teacher_pairs": 27618.5, "relation_loss": 0.0016866722726263106, "selected_pairs": 27618.5, "step": 26810, "student_distance_mean": 1274.6447998046874, "teacher_distance_mean": 0.8567586123943329, "valid_action_samples": 235.5, "weighted_auxiliary_loss": 0.0016866722726263106, "weighted_relation_loss": 0.0016866722726263106 }, { "action_query_batch_std": 21.95777282714844, "action_query_norm": 931.0373352050781, "action_relation_loss": 0.0018130580196157099, "auxiliary_loss_weight": 1.0, "epoch": 25.088868101029, "flow_matching_loss": 0.015064088441431523, "grad_norm": 0.07641462236642838, "invalid_tail_samples": 20.6, "learning_rate": 3.042446882476846e-06, "loss": 0.0169, "positive_teacher_pairs": 27602.7, "relation_loss": 0.0018130580196157099, "selected_pairs": 27602.7, "step": 26820, "student_distance_mean": 1259.91435546875, "teacher_distance_mean": 0.8488270342350006, "valid_action_samples": 235.4, "weighted_auxiliary_loss": 0.0018130580196157099, "weighted_relation_loss": 0.0018130580196157099 }, { "action_query_batch_std": 21.75416851043701, "action_query_norm": 925.3642028808594, "action_relation_loss": 0.0017170433886349202, "auxiliary_loss_weight": 1.0, "epoch": 25.09822263797942, "flow_matching_loss": 0.015273272711783647, "grad_norm": 0.13646389544010162, "invalid_tail_samples": 24.0, "learning_rate": 3.023542942573643e-06, "loss": 0.017, "positive_teacher_pairs": 26807.6, "relation_loss": 0.0017170433886349202, "selected_pairs": 26807.6, "step": 26830, "student_distance_mean": 1253.227587890625, "teacher_distance_mean": 0.8456153273582458, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0017170433886349202, "weighted_relation_loss": 0.0017170433886349202 }, { "action_query_batch_std": 22.298534965515138, "action_query_norm": 942.0638061523438, "action_relation_loss": 0.0017984982929192483, "auxiliary_loss_weight": 1.0, "epoch": 25.10757717492984, "flow_matching_loss": 0.01366884857416153, "grad_norm": 0.0917869284749031, "invalid_tail_samples": 22.6, "learning_rate": 3.004696083495351e-06, "loss": 0.0155, "positive_teacher_pairs": 27126.7, "relation_loss": 0.0017984982929192483, "selected_pairs": 27126.7, "step": 26840, "student_distance_mean": 1285.9157348632812, "teacher_distance_mean": 0.8667202532291413, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0017984982929192483, "weighted_relation_loss": 0.0017984982929192483 }, { "action_query_batch_std": 21.92764530181885, "action_query_norm": 929.4036560058594, "action_relation_loss": 0.0018079253495670855, "auxiliary_loss_weight": 1.0, "epoch": 25.116931711880262, "flow_matching_loss": 0.016004174016416073, "grad_norm": 0.08451709896326065, "invalid_tail_samples": 22.9, "learning_rate": 2.98590632814269e-06, "loss": 0.0178, "positive_teacher_pairs": 27054.0, "relation_loss": 0.0018079253495670855, "selected_pairs": 27054.0, "step": 26850, "student_distance_mean": 1262.8486572265624, "teacher_distance_mean": 0.8503017246723175, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0018079253495670855, "weighted_relation_loss": 0.0018079253495670855 }, { "action_query_batch_std": 21.99635543823242, "action_query_norm": 927.9649291992188, "action_relation_loss": 0.0018039038870483637, "auxiliary_loss_weight": 1.0, "epoch": 25.126286248830684, "flow_matching_loss": 0.016897031012922524, "grad_norm": 0.08687346428632736, "invalid_tail_samples": 26.6, "learning_rate": 2.9671736993469702e-06, "loss": 0.0187, "positive_teacher_pairs": 26206.7, "relation_loss": 0.0018039038870483637, "selected_pairs": 26206.7, "step": 26860, "student_distance_mean": 1270.7732055664062, "teacher_distance_mean": 0.8546272993087769, "valid_action_samples": 229.4, "weighted_auxiliary_loss": 0.0018039038870483637, "weighted_relation_loss": 0.0018039038870483637 }, { "action_query_batch_std": 22.144195747375488, "action_query_norm": 936.5819030761719, "action_relation_loss": 0.001751373615115881, "auxiliary_loss_weight": 1.0, "epoch": 25.135640785781103, "flow_matching_loss": 0.01402470376342535, "grad_norm": 0.09417479485273361, "invalid_tail_samples": 24.3, "learning_rate": 2.9484982198701216e-06, "loss": 0.0158, "positive_teacher_pairs": 26733.7, "relation_loss": 0.001751373615115881, "selected_pairs": 26733.7, "step": 26870, "student_distance_mean": 1267.3074951171875, "teacher_distance_mean": 0.8525093376636506, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.001751373615115881, "weighted_relation_loss": 0.001751373615115881 }, { "action_query_batch_std": 21.87849063873291, "action_query_norm": 929.6405578613281, "action_relation_loss": 0.0017511245328933, "auxiliary_loss_weight": 1.0, "epoch": 25.144995322731525, "flow_matching_loss": 0.014612146187573671, "grad_norm": 0.08387511223554611, "invalid_tail_samples": 22.5, "learning_rate": 2.929879912404604e-06, "loss": 0.0164, "positive_teacher_pairs": 27156.1, "relation_loss": 0.0017511245328933, "selected_pairs": 27156.1, "step": 26880, "student_distance_mean": 1263.6972045898438, "teacher_distance_mean": 0.8497180342674255, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0017511245328933, "weighted_relation_loss": 0.0017511245328933 }, { "action_query_batch_std": 22.31566753387451, "action_query_norm": 941.9368286132812, "action_relation_loss": 0.001736555143725127, "auxiliary_loss_weight": 1.0, "epoch": 25.154349859681947, "flow_matching_loss": 0.015669064503163098, "grad_norm": 0.11417412012815475, "invalid_tail_samples": 21.6, "learning_rate": 2.9113187995734147e-06, "loss": 0.0174, "positive_teacher_pairs": 27372.3, "relation_loss": 0.001736555143725127, "selected_pairs": 27372.3, "step": 26890, "student_distance_mean": 1280.7409423828126, "teacher_distance_mean": 0.8623098790645599, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.001736555143725127, "weighted_relation_loss": 0.001736555143725127 }, { "action_query_batch_std": 22.067696952819823, "action_query_norm": 937.1677612304687, "action_relation_loss": 0.0017503468436188996, "auxiliary_loss_weight": 1.0, "epoch": 25.163704396632365, "flow_matching_loss": 0.01395658841356635, "grad_norm": 0.07475391030311584, "invalid_tail_samples": 21.3, "learning_rate": 2.8928149039300524e-06, "loss": 0.0157, "positive_teacher_pairs": 27436.6, "relation_loss": 0.0017503468436188996, "selected_pairs": 27436.6, "step": 26900, "student_distance_mean": 1269.2793212890624, "teacher_distance_mean": 0.8545122385025025, "valid_action_samples": 234.7, "weighted_auxiliary_loss": 0.0017503468436188996, "weighted_relation_loss": 0.0017503468436188996 }, { "action_query_batch_std": 22.08402214050293, "action_query_norm": 935.1173706054688, "action_relation_loss": 0.00173498714575544, "auxiliary_loss_weight": 1.0, "epoch": 25.173058933582787, "flow_matching_loss": 0.014871513843536377, "grad_norm": 0.0984577015042305, "invalid_tail_samples": 22.9, "learning_rate": 2.8743682479584975e-06, "loss": 0.0166, "positive_teacher_pairs": 27062.2, "relation_loss": 0.00173498714575544, "selected_pairs": 27062.2, "step": 26910, "student_distance_mean": 1266.250390625, "teacher_distance_mean": 0.851270443201065, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.00173498714575544, "weighted_relation_loss": 0.00173498714575544 }, { "action_query_batch_std": 22.011371231079103, "action_query_norm": 936.027978515625, "action_relation_loss": 0.0017305243643932044, "auxiliary_loss_weight": 1.0, "epoch": 25.18241347053321, "flow_matching_loss": 0.015759831946343183, "grad_norm": 0.09313178062438965, "invalid_tail_samples": 23.3, "learning_rate": 2.8559788540731824e-06, "loss": 0.0175, "positive_teacher_pairs": 26963.9, "relation_loss": 0.0017305243643932044, "selected_pairs": 26963.9, "step": 26920, "student_distance_mean": 1265.5316162109375, "teacher_distance_mean": 0.8519084513187408, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0017305243643932044, "weighted_relation_loss": 0.0017305243643932044 }, { "action_query_batch_std": 22.112524223327636, "action_query_norm": 936.9484130859375, "action_relation_loss": 0.0017912291106767953, "auxiliary_loss_weight": 1.0, "epoch": 25.19176800748363, "flow_matching_loss": 0.015547420736402274, "grad_norm": 0.09081395715475082, "invalid_tail_samples": 23.7, "learning_rate": 2.8376467446189493e-06, "loss": 0.0173, "positive_teacher_pairs": 26874.1, "relation_loss": 0.0017912291106767953, "selected_pairs": 26874.1, "step": 26930, "student_distance_mean": 1270.6096557617188, "teacher_distance_mean": 0.8545173525810241, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0017912291106767953, "weighted_relation_loss": 0.0017912291106767953 }, { "action_query_batch_std": 22.15972843170166, "action_query_norm": 938.1523193359375, "action_relation_loss": 0.0017896539182402193, "auxiliary_loss_weight": 1.0, "epoch": 25.20112254443405, "flow_matching_loss": 0.014638410042971372, "grad_norm": 0.09631871432065964, "invalid_tail_samples": 24.5, "learning_rate": 2.8193719418710406e-06, "loss": 0.0164, "positive_teacher_pairs": 26698.5, "relation_loss": 0.0017896539182402193, "selected_pairs": 26698.5, "step": 26940, "student_distance_mean": 1275.5178833007812, "teacher_distance_mean": 0.8573425769805908, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0017896539182402193, "weighted_relation_loss": 0.0017896539182402193 }, { "action_query_batch_std": 21.992830276489258, "action_query_norm": 932.6356872558594, "action_relation_loss": 0.0017955099465325475, "auxiliary_loss_weight": 1.0, "epoch": 25.21047708138447, "flow_matching_loss": 0.015242727566510439, "grad_norm": 0.07673841714859009, "invalid_tail_samples": 23.5, "learning_rate": 2.8011544680350667e-06, "loss": 0.017, "positive_teacher_pairs": 26916.6, "relation_loss": 0.0017955099465325475, "selected_pairs": 26916.6, "step": 26950, "student_distance_mean": 1261.0413940429687, "teacher_distance_mean": 0.847713416814804, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0017955099465325475, "weighted_relation_loss": 0.0017955099465325475 }, { "action_query_batch_std": 22.117218589782716, "action_query_norm": 933.8799560546875, "action_relation_loss": 0.0017416160902939738, "auxiliary_loss_weight": 1.0, "epoch": 25.219831618334894, "flow_matching_loss": 0.015039836894720793, "grad_norm": 0.0739903673529625, "invalid_tail_samples": 26.4, "learning_rate": 2.7829943452469753e-06, "loss": 0.0168, "positive_teacher_pairs": 26252.4, "relation_loss": 0.0017416160902939738, "selected_pairs": 26252.4, "step": 26960, "student_distance_mean": 1277.2177124023438, "teacher_distance_mean": 0.8591368079185486, "valid_action_samples": 229.6, "weighted_auxiliary_loss": 0.0017416160902939738, "weighted_relation_loss": 0.0017416160902939738 }, { "action_query_batch_std": 21.985490608215333, "action_query_norm": 934.3421875, "action_relation_loss": 0.0017840476939454675, "auxiliary_loss_weight": 1.0, "epoch": 25.229186155285312, "flow_matching_loss": 0.014352164417505264, "grad_norm": 0.09162618964910507, "invalid_tail_samples": 22.1, "learning_rate": 2.7648915955730213e-06, "loss": 0.0161, "positive_teacher_pairs": 27243.6, "relation_loss": 0.0017840476939454675, "selected_pairs": 27243.6, "step": 26970, "student_distance_mean": 1262.2969116210938, "teacher_distance_mean": 0.8480069100856781, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0017840476939454675, "weighted_relation_loss": 0.0017840476939454675 }, { "action_query_batch_std": 22.191815757751463, "action_query_norm": 939.8288024902344, "action_relation_loss": 0.0017842098488472403, "auxiliary_loss_weight": 1.0, "epoch": 25.238540692235734, "flow_matching_loss": 0.013617129251360893, "grad_norm": 0.08380734175443649, "invalid_tail_samples": 21.3, "learning_rate": 2.746846241009765e-06, "loss": 0.0154, "positive_teacher_pairs": 27429.0, "relation_loss": 0.0017842098488472403, "selected_pairs": 27429.0, "step": 26980, "student_distance_mean": 1277.6513305664062, "teacher_distance_mean": 0.8603223741054535, "valid_action_samples": 234.7, "weighted_auxiliary_loss": 0.0017842098488472403, "weighted_relation_loss": 0.0017842098488472403 }, { "action_query_batch_std": 22.042360687255858, "action_query_norm": 936.4398986816407, "action_relation_loss": 0.001710014883428812, "auxiliary_loss_weight": 1.0, "epoch": 25.247895229186156, "flow_matching_loss": 0.015601099096238613, "grad_norm": 0.07968396693468094, "invalid_tail_samples": 24.2, "learning_rate": 2.7288583034839945e-06, "loss": 0.0173, "positive_teacher_pairs": 26765.5, "relation_loss": 0.001710014883428812, "selected_pairs": 26765.5, "step": 26990, "student_distance_mean": 1269.4654541015625, "teacher_distance_mean": 0.8549090027809143, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.001710014883428812, "weighted_relation_loss": 0.001710014883428812 }, { "action_query_batch_std": 22.267090225219725, "action_query_norm": 942.1419494628906, "action_relation_loss": 0.001784689084161073, "auxiliary_loss_weight": 1.0, "epoch": 25.257249766136574, "flow_matching_loss": 0.01597087914124131, "grad_norm": 0.07950634509325027, "invalid_tail_samples": 22.8, "learning_rate": 2.7109278048527752e-06, "loss": 0.0178, "positive_teacher_pairs": 27078.4, "relation_loss": 0.001784689084161073, "selected_pairs": 27078.4, "step": 27000, "student_distance_mean": 1282.5294555664063, "teacher_distance_mean": 0.8628093361854553, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.001784689084161073, "weighted_relation_loss": 0.001784689084161073 }, { "action_query_batch_std": 21.93658866882324, "action_query_norm": 929.2868835449219, "action_relation_loss": 0.0018657786189578474, "auxiliary_loss_weight": 1.0, "epoch": 25.266604303086996, "flow_matching_loss": 0.014140963926911354, "grad_norm": 0.07332833111286163, "invalid_tail_samples": 25.3, "learning_rate": 2.6930547669033413e-06, "loss": 0.016, "positive_teacher_pairs": 26503.1, "relation_loss": 0.0018657786189578474, "selected_pairs": 26503.1, "step": 27010, "student_distance_mean": 1259.7593994140625, "teacher_distance_mean": 0.8484947085380554, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0018657786189578474, "weighted_relation_loss": 0.0018657786189578474 }, { "action_query_batch_std": 22.20063133239746, "action_query_norm": 938.1430480957031, "action_relation_loss": 0.0017616439727135003, "auxiliary_loss_weight": 1.0, "epoch": 25.27595884003742, "flow_matching_loss": 0.015591865964233875, "grad_norm": 0.08350059390068054, "invalid_tail_samples": 23.5, "learning_rate": 2.675239211353109e-06, "loss": 0.0174, "positive_teacher_pairs": 26916.3, "relation_loss": 0.0017616439727135003, "selected_pairs": 26916.3, "step": 27020, "student_distance_mean": 1273.8234252929688, "teacher_distance_mean": 0.8582277595996857, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0017616439727135003, "weighted_relation_loss": 0.0017616439727135003 }, { "action_query_batch_std": 22.329557991027833, "action_query_norm": 943.8257690429688, "action_relation_loss": 0.0017317532328888774, "auxiliary_loss_weight": 1.0, "epoch": 25.28531337698784, "flow_matching_loss": 0.014356133434921503, "grad_norm": 0.08046063780784607, "invalid_tail_samples": 24.7, "learning_rate": 2.6574811598496786e-06, "loss": 0.0161, "positive_teacher_pairs": 26648.8, "relation_loss": 0.0017317532328888774, "selected_pairs": 26648.8, "step": 27030, "student_distance_mean": 1289.3564453125, "teacher_distance_mean": 0.8689804315567017, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0017317532328888774, "weighted_relation_loss": 0.0017317532328888774 }, { "action_query_batch_std": 22.234914207458495, "action_query_norm": 940.513720703125, "action_relation_loss": 0.0017497708788141609, "auxiliary_loss_weight": 1.0, "epoch": 25.29466791393826, "flow_matching_loss": 0.015791431069374084, "grad_norm": 0.08004062622785568, "invalid_tail_samples": 26.0, "learning_rate": 2.6397806339707456e-06, "loss": 0.0175, "positive_teacher_pairs": 26339.6, "relation_loss": 0.0017497708788141609, "selected_pairs": 26339.6, "step": 27040, "student_distance_mean": 1277.4930908203125, "teacher_distance_mean": 0.861409479379654, "valid_action_samples": 230.0, "weighted_auxiliary_loss": 0.0017497708788141609, "weighted_relation_loss": 0.0017497708788141609 }, { "action_query_batch_std": 22.06261577606201, "action_query_norm": 933.5587036132813, "action_relation_loss": 0.0017799093038775027, "auxiliary_loss_weight": 1.0, "epoch": 25.30402245088868, "flow_matching_loss": 0.014657803531736135, "grad_norm": 0.08010400086641312, "invalid_tail_samples": 25.0, "learning_rate": 2.6221376552241217e-06, "loss": 0.0164, "positive_teacher_pairs": 26583.7, "relation_loss": 0.0017799093038775027, "selected_pairs": 26583.7, "step": 27050, "student_distance_mean": 1269.301318359375, "teacher_distance_mean": 0.8542539477348328, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0017799093038775027, "weighted_relation_loss": 0.0017799093038775027 }, { "action_query_batch_std": 21.86358757019043, "action_query_norm": 927.2799011230469, "action_relation_loss": 0.0017524425988085569, "auxiliary_loss_weight": 1.0, "epoch": 25.313376987839103, "flow_matching_loss": 0.014062974881380797, "grad_norm": 0.09805714339017868, "invalid_tail_samples": 24.5, "learning_rate": 2.604552245047681e-06, "loss": 0.0158, "positive_teacher_pairs": 26685.0, "relation_loss": 0.0017524425988085569, "selected_pairs": 26685.0, "step": 27060, "student_distance_mean": 1262.6940307617188, "teacher_distance_mean": 0.8518096685409546, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0017524425988085569, "weighted_relation_loss": 0.0017524425988085569 }, { "action_query_batch_std": 21.68565216064453, "action_query_norm": 921.330029296875, "action_relation_loss": 0.0017582711996510624, "auxiliary_loss_weight": 1.0, "epoch": 25.32273152478952, "flow_matching_loss": 0.015336626023054124, "grad_norm": 0.08799406886100769, "invalid_tail_samples": 25.2, "learning_rate": 2.587024424809359e-06, "loss": 0.0171, "positive_teacher_pairs": 26525.5, "relation_loss": 0.0017582711996510624, "selected_pairs": 26525.5, "step": 27070, "student_distance_mean": 1251.7137084960937, "teacher_distance_mean": 0.8435228109359741, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0017582711996510624, "weighted_relation_loss": 0.0017582711996510624 }, { "action_query_batch_std": 21.98322925567627, "action_query_norm": 930.7196716308594, "action_relation_loss": 0.0017236780375242233, "auxiliary_loss_weight": 1.0, "epoch": 25.332086061739943, "flow_matching_loss": 0.014486936014145612, "grad_norm": 0.10314252972602844, "invalid_tail_samples": 23.5, "learning_rate": 2.5695542158071186e-06, "loss": 0.0162, "positive_teacher_pairs": 26923.0, "relation_loss": 0.0017236780375242233, "selected_pairs": 26923.0, "step": 27080, "student_distance_mean": 1260.84833984375, "teacher_distance_mean": 0.8505742609500885, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0017236780375242233, "weighted_relation_loss": 0.0017236780375242233 }, { "action_query_batch_std": 21.919336318969727, "action_query_norm": 929.7744873046875, "action_relation_loss": 0.0017974759684875607, "auxiliary_loss_weight": 1.0, "epoch": 25.341440598690365, "flow_matching_loss": 0.01481621228158474, "grad_norm": 0.07938530296087265, "invalid_tail_samples": 27.3, "learning_rate": 2.5521416392689068e-06, "loss": 0.0166, "positive_teacher_pairs": 26053.7, "relation_loss": 0.0017974759684875607, "selected_pairs": 26053.7, "step": 27090, "student_distance_mean": 1264.179345703125, "teacher_distance_mean": 0.851618093252182, "valid_action_samples": 228.7, "weighted_auxiliary_loss": 0.0017974759684875607, "weighted_relation_loss": 0.0017974759684875607 }, { "action_query_batch_std": 22.18486804962158, "action_query_norm": 936.8003479003906, "action_relation_loss": 0.001706937572453171, "auxiliary_loss_weight": 1.0, "epoch": 25.350795135640787, "flow_matching_loss": 0.014387524127960205, "grad_norm": 0.0758831724524498, "invalid_tail_samples": 24.7, "learning_rate": 2.5347867163526384e-06, "loss": 0.0161, "positive_teacher_pairs": 26646.4, "relation_loss": 0.001706937572453171, "selected_pairs": 26646.4, "step": 27100, "student_distance_mean": 1275.491455078125, "teacher_distance_mean": 0.8586500942707062, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.001706937572453171, "weighted_relation_loss": 0.001706937572453171 }, { "action_query_batch_std": 21.823355293273927, "action_query_norm": 926.3033508300781, "action_relation_loss": 0.001771096931770444, "auxiliary_loss_weight": 1.0, "epoch": 25.360149672591206, "flow_matching_loss": 0.015200095996260644, "grad_norm": 0.09983471781015396, "invalid_tail_samples": 26.1, "learning_rate": 2.517489468146189e-06, "loss": 0.017, "positive_teacher_pairs": 26331.1, "relation_loss": 0.001771096931770444, "selected_pairs": 26331.1, "step": 27110, "student_distance_mean": 1257.9614990234375, "teacher_distance_mean": 0.8470806658267975, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.001771096931770444, "weighted_relation_loss": 0.001771096931770444 }, { "action_query_batch_std": 22.32350101470947, "action_query_norm": 942.5975830078125, "action_relation_loss": 0.0017937679309397935, "auxiliary_loss_weight": 1.0, "epoch": 25.369504209541628, "flow_matching_loss": 0.015368693787604571, "grad_norm": 0.10157562047243118, "invalid_tail_samples": 23.0, "learning_rate": 2.500249915667341e-06, "loss": 0.0172, "positive_teacher_pairs": 27032.1, "relation_loss": 0.0017937679309397935, "selected_pairs": 27032.1, "step": 27120, "student_distance_mean": 1281.9263671875, "teacher_distance_mean": 0.8634238302707672, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0017937679309397935, "weighted_relation_loss": 0.0017937679309397935 }, { "action_query_batch_std": 22.19168643951416, "action_query_norm": 939.0296813964844, "action_relation_loss": 0.0017717599868774414, "auxiliary_loss_weight": 1.0, "epoch": 25.37885874649205, "flow_matching_loss": 0.014849749952554702, "grad_norm": 0.08068526536226273, "invalid_tail_samples": 23.6, "learning_rate": 2.4830680798637817e-06, "loss": 0.0166, "positive_teacher_pairs": 26896.3, "relation_loss": 0.0017717599868774414, "selected_pairs": 26896.3, "step": 27130, "student_distance_mean": 1274.242724609375, "teacher_distance_mean": 0.8586519896984101, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0017717599868774414, "weighted_relation_loss": 0.0017717599868774414 }, { "action_query_batch_std": 22.056397247314454, "action_query_norm": 934.6712524414063, "action_relation_loss": 0.0016820563818328083, "auxiliary_loss_weight": 1.0, "epoch": 25.388213283442468, "flow_matching_loss": 0.015077614411711692, "grad_norm": 0.08842575550079346, "invalid_tail_samples": 21.7, "learning_rate": 2.465943981613056e-06, "loss": 0.0168, "positive_teacher_pairs": 27339.1, "relation_loss": 0.0016820563818328083, "selected_pairs": 27339.1, "step": 27140, "student_distance_mean": 1265.7891357421875, "teacher_distance_mean": 0.8521281659603119, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.0016820563818328083, "weighted_relation_loss": 0.0016820563818328083 }, { "action_query_batch_std": 22.03115291595459, "action_query_norm": 933.7250793457031, "action_relation_loss": 0.0017580450396053493, "auxiliary_loss_weight": 1.0, "epoch": 25.39756782039289, "flow_matching_loss": 0.015831975266337395, "grad_norm": 0.09933219850063324, "invalid_tail_samples": 22.4, "learning_rate": 2.448877641722569e-06, "loss": 0.0176, "positive_teacher_pairs": 27184.9, "relation_loss": 0.0017580450396053493, "selected_pairs": 27184.9, "step": 27150, "student_distance_mean": 1264.6014892578125, "teacher_distance_mean": 0.8509602844715118, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.0017580450396053493, "weighted_relation_loss": 0.0017580450396053493 }, { "action_query_batch_std": 22.092910385131837, "action_query_norm": 934.9949401855469, "action_relation_loss": 0.0017646667314693333, "auxiliary_loss_weight": 1.0, "epoch": 25.406922357343312, "flow_matching_loss": 0.015997285023331642, "grad_norm": 0.06664054840803146, "invalid_tail_samples": 21.7, "learning_rate": 2.431869080929522e-06, "loss": 0.0178, "positive_teacher_pairs": 27335.9, "relation_loss": 0.0017646667314693333, "selected_pairs": 27335.9, "step": 27160, "student_distance_mean": 1271.3451049804687, "teacher_distance_mean": 0.8553396344184876, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.0017646667314693333, "weighted_relation_loss": 0.0017646667314693333 }, { "action_query_batch_std": 22.27198314666748, "action_query_norm": 941.7995361328125, "action_relation_loss": 0.0017040425329469145, "auxiliary_loss_weight": 1.0, "epoch": 25.416276894293734, "flow_matching_loss": 0.015311318822205067, "grad_norm": 0.10032878071069717, "invalid_tail_samples": 23.7, "learning_rate": 2.4149183199009216e-06, "loss": 0.017, "positive_teacher_pairs": 26875.0, "relation_loss": 0.0017040425329469145, "selected_pairs": 26875.0, "step": 27170, "student_distance_mean": 1279.5061645507812, "teacher_distance_mean": 0.8618137419223786, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0017040425329469145, "weighted_relation_loss": 0.0017040425329469145 }, { "action_query_batch_std": 21.922084045410156, "action_query_norm": 934.0557922363281, "action_relation_loss": 0.0017609383328817784, "auxiliary_loss_weight": 1.0, "epoch": 25.425631431244152, "flow_matching_loss": 0.01434200033545494, "grad_norm": 0.07857723534107208, "invalid_tail_samples": 24.1, "learning_rate": 2.3980253792335427e-06, "loss": 0.0161, "positive_teacher_pairs": 26785.0, "relation_loss": 0.0017609383328817784, "selected_pairs": 26785.0, "step": 27180, "student_distance_mean": 1266.3384155273438, "teacher_distance_mean": 0.8519021689891815, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0017609383328817784, "weighted_relation_loss": 0.0017609383328817784 }, { "action_query_batch_std": 21.87796745300293, "action_query_norm": 928.2452941894531, "action_relation_loss": 0.0017741886083967983, "auxiliary_loss_weight": 1.0, "epoch": 25.434985968194574, "flow_matching_loss": 0.014526804070919752, "grad_norm": 0.07841843366622925, "invalid_tail_samples": 24.2, "learning_rate": 2.381190279453899e-06, "loss": 0.0163, "positive_teacher_pairs": 26754.7, "relation_loss": 0.0017741886083967983, "selected_pairs": 26754.7, "step": 27190, "student_distance_mean": 1257.6830444335938, "teacher_distance_mean": 0.8475596606731415, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0017741886083967983, "weighted_relation_loss": 0.0017741886083967983 }, { "action_query_batch_std": 21.740967750549316, "action_query_norm": 925.3753479003906, "action_relation_loss": 0.0017705720267258585, "auxiliary_loss_weight": 1.0, "epoch": 25.444340505144996, "flow_matching_loss": 0.014233506750315428, "grad_norm": 0.09963583946228027, "invalid_tail_samples": 24.6, "learning_rate": 2.364413041018232e-06, "loss": 0.016, "positive_teacher_pairs": 26662.0, "relation_loss": 0.0017705720267258585, "selected_pairs": 26662.0, "step": 27200, "student_distance_mean": 1252.6401977539062, "teacher_distance_mean": 0.8434945046901703, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0017705720267258585, "weighted_relation_loss": 0.0017705720267258585 }, { "action_query_batch_std": 22.143595123291014, "action_query_norm": 936.6782043457031, "action_relation_loss": 0.001797690661624074, "auxiliary_loss_weight": 1.0, "epoch": 25.453695042095415, "flow_matching_loss": 0.015607545804232358, "grad_norm": 0.0908794179558754, "invalid_tail_samples": 21.8, "learning_rate": 2.347693684312463e-06, "loss": 0.0174, "positive_teacher_pairs": 27317.7, "relation_loss": 0.001797690661624074, "selected_pairs": 27317.7, "step": 27210, "student_distance_mean": 1271.910693359375, "teacher_distance_mean": 0.8561914145946503, "valid_action_samples": 234.2, "weighted_auxiliary_loss": 0.001797690661624074, "weighted_relation_loss": 0.001797690661624074 }, { "action_query_batch_std": 21.96249656677246, "action_query_norm": 931.0507751464844, "action_relation_loss": 0.0017241360270418226, "auxiliary_loss_weight": 1.0, "epoch": 25.463049579045837, "flow_matching_loss": 0.014742238819599152, "grad_norm": 0.08394777029752731, "invalid_tail_samples": 24.6, "learning_rate": 2.331032229652186e-06, "loss": 0.0165, "positive_teacher_pairs": 26672.8, "relation_loss": 0.0017241360270418226, "selected_pairs": 26672.8, "step": 27220, "student_distance_mean": 1261.4947631835937, "teacher_distance_mean": 0.8498398244380951, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0017241360270418226, "weighted_relation_loss": 0.0017241360270418226 }, { "action_query_batch_std": 22.211061668395995, "action_query_norm": 941.2206420898438, "action_relation_loss": 0.0017547512194141745, "auxiliary_loss_weight": 1.0, "epoch": 25.47240411599626, "flow_matching_loss": 0.014406598266214132, "grad_norm": 0.08284163475036621, "invalid_tail_samples": 25.0, "learning_rate": 2.314428697282628e-06, "loss": 0.0162, "positive_teacher_pairs": 26569.9, "relation_loss": 0.0017547512194141745, "selected_pairs": 26569.9, "step": 27230, "student_distance_mean": 1277.4453002929688, "teacher_distance_mean": 0.8617422223091126, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0017547512194141745, "weighted_relation_loss": 0.0017547512194141745 }, { "action_query_batch_std": 21.887386131286622, "action_query_norm": 930.9721984863281, "action_relation_loss": 0.0017371995607391, "auxiliary_loss_weight": 1.0, "epoch": 25.48175865294668, "flow_matching_loss": 0.014966104552149773, "grad_norm": 0.08387277275323868, "invalid_tail_samples": 25.3, "learning_rate": 2.297883107378673e-06, "loss": 0.0167, "positive_teacher_pairs": 26504.0, "relation_loss": 0.0017371995607391, "selected_pairs": 26504.0, "step": 27240, "student_distance_mean": 1257.5642333984374, "teacher_distance_mean": 0.8464844405651093, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0017371995607391, "weighted_relation_loss": 0.0017371995607391 }, { "action_query_batch_std": 22.295161247253418, "action_query_norm": 942.4428161621094, "action_relation_loss": 0.0017420822870917619, "auxiliary_loss_weight": 1.0, "epoch": 25.4911131898971, "flow_matching_loss": 0.015105817280709744, "grad_norm": 0.1230277419090271, "invalid_tail_samples": 23.8, "learning_rate": 2.2813954800447513e-06, "loss": 0.0168, "positive_teacher_pairs": 26848.6, "relation_loss": 0.0017420822870917619, "selected_pairs": 26848.6, "step": 27250, "student_distance_mean": 1281.77900390625, "teacher_distance_mean": 0.8650087714195251, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0017420822870917619, "weighted_relation_loss": 0.0017420822870917619 }, { "action_query_batch_std": 22.145705032348634, "action_query_norm": 937.0494995117188, "action_relation_loss": 0.0017854595324024558, "auxiliary_loss_weight": 1.0, "epoch": 25.50046772684752, "flow_matching_loss": 0.01535089686512947, "grad_norm": 0.09265723079442978, "invalid_tail_samples": 22.3, "learning_rate": 2.2649658353148974e-06, "loss": 0.0171, "positive_teacher_pairs": 27200.8, "relation_loss": 0.0017854595324024558, "selected_pairs": 27200.8, "step": 27260, "student_distance_mean": 1275.1188354492188, "teacher_distance_mean": 0.8588058054447174, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0017854595324024558, "weighted_relation_loss": 0.0017854595324024558 }, { "action_query_batch_std": 21.972471046447755, "action_query_norm": 931.1322265625, "action_relation_loss": 0.0017248502117581666, "auxiliary_loss_weight": 1.0, "epoch": 25.509822263797943, "flow_matching_loss": 0.01462261015549302, "grad_norm": 0.08687656372785568, "invalid_tail_samples": 23.6, "learning_rate": 2.2485941931526645e-06, "loss": 0.0163, "positive_teacher_pairs": 26897.3, "relation_loss": 0.0017248502117581666, "selected_pairs": 26897.3, "step": 27270, "student_distance_mean": 1264.093603515625, "teacher_distance_mean": 0.8533783793449402, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0017248502117581666, "weighted_relation_loss": 0.0017248502117581666 }, { "action_query_batch_std": 21.91220932006836, "action_query_norm": 926.9298461914062, "action_relation_loss": 0.0016905734897591173, "auxiliary_loss_weight": 1.0, "epoch": 25.51917680074836, "flow_matching_loss": 0.015070871915668249, "grad_norm": 0.08804012089967728, "invalid_tail_samples": 23.0, "learning_rate": 2.232280573451151e-06, "loss": 0.0168, "positive_teacher_pairs": 27030.8, "relation_loss": 0.0016905734897591173, "selected_pairs": 27030.8, "step": 27280, "student_distance_mean": 1257.4871337890625, "teacher_distance_mean": 0.8479676723480225, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0016905734897591173, "weighted_relation_loss": 0.0016905734897591173 }, { "action_query_batch_std": 21.85243453979492, "action_query_norm": 925.9024475097656, "action_relation_loss": 0.0017664513667114078, "auxiliary_loss_weight": 1.0, "epoch": 25.528531337698784, "flow_matching_loss": 0.016296919621527194, "grad_norm": 0.08216314017772675, "invalid_tail_samples": 25.5, "learning_rate": 2.216024996032945e-06, "loss": 0.0181, "positive_teacher_pairs": 26465.1, "relation_loss": 0.0017664513667114078, "selected_pairs": 26465.1, "step": 27290, "student_distance_mean": 1261.6505126953125, "teacher_distance_mean": 0.849332070350647, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0017664513667114078, "weighted_relation_loss": 0.0017664513667114078 }, { "action_query_batch_std": 22.09446430206299, "action_query_norm": 936.9036437988282, "action_relation_loss": 0.0018432298791594803, "auxiliary_loss_weight": 1.0, "epoch": 25.537885874649206, "flow_matching_loss": 0.014490529149770736, "grad_norm": 0.0713718831539154, "invalid_tail_samples": 22.6, "learning_rate": 2.1998274806501074e-06, "loss": 0.0163, "positive_teacher_pairs": 27131.8, "relation_loss": 0.0018432298791594803, "selected_pairs": 27131.8, "step": 27300, "student_distance_mean": 1269.7288818359375, "teacher_distance_mean": 0.8571480274200439, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0018432298791594803, "weighted_relation_loss": 0.0018432298791594803 }, { "action_query_batch_std": 22.110097694396973, "action_query_norm": 935.8277587890625, "action_relation_loss": 0.001748658053111285, "auxiliary_loss_weight": 1.0, "epoch": 25.547240411599624, "flow_matching_loss": 0.015453389193862677, "grad_norm": 0.09641299396753311, "invalid_tail_samples": 24.4, "learning_rate": 2.183688046984139e-06, "loss": 0.0172, "positive_teacher_pairs": 26712.3, "relation_loss": 0.001748658053111285, "selected_pairs": 26712.3, "step": 27310, "student_distance_mean": 1271.2837158203124, "teacher_distance_mean": 0.8571777224540711, "valid_action_samples": 231.6, "weighted_auxiliary_loss": 0.001748658053111285, "weighted_relation_loss": 0.001748658053111285 }, { "action_query_batch_std": 21.611816215515137, "action_query_norm": 923.1872741699219, "action_relation_loss": 0.0017891870578750969, "auxiliary_loss_weight": 1.0, "epoch": 25.556594948550046, "flow_matching_loss": 0.01475843321532011, "grad_norm": 0.07727105915546417, "invalid_tail_samples": 22.3, "learning_rate": 2.167606714645981e-06, "loss": 0.0165, "positive_teacher_pairs": 27203.6, "relation_loss": 0.0017891870578750969, "selected_pairs": 27203.6, "step": 27320, "student_distance_mean": 1247.373828125, "teacher_distance_mean": 0.8424164295196533, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0017891870578750969, "weighted_relation_loss": 0.0017891870578750969 }, { "action_query_batch_std": 21.887507247924805, "action_query_norm": 928.4416625976562, "action_relation_loss": 0.0018028972088359296, "auxiliary_loss_weight": 1.0, "epoch": 25.565949485500468, "flow_matching_loss": 0.015998787339776756, "grad_norm": 0.12716332077980042, "invalid_tail_samples": 25.8, "learning_rate": 2.151583503175958e-06, "loss": 0.0178, "positive_teacher_pairs": 26394.5, "relation_loss": 0.0018028972088359296, "selected_pairs": 26394.5, "step": 27330, "student_distance_mean": 1263.5111206054687, "teacher_distance_mean": 0.852581912279129, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.0018028972088359296, "weighted_relation_loss": 0.0018028972088359296 }, { "action_query_batch_std": 21.988334274291994, "action_query_norm": 933.1771911621094, "action_relation_loss": 0.0017147540464065969, "auxiliary_loss_weight": 1.0, "epoch": 25.57530402245089, "flow_matching_loss": 0.013133617583662271, "grad_norm": 0.0754517987370491, "invalid_tail_samples": 23.8, "learning_rate": 2.1356184320437957e-06, "loss": 0.0148, "positive_teacher_pairs": 26857.3, "relation_loss": 0.0017147540464065969, "selected_pairs": 26857.3, "step": 27340, "student_distance_mean": 1269.6354736328126, "teacher_distance_mean": 0.8569000601768494, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0017147540464065969, "weighted_relation_loss": 0.0017147540464065969 }, { "action_query_batch_std": 22.08392791748047, "action_query_norm": 936.4101806640625, "action_relation_loss": 0.0018228699336759746, "auxiliary_loss_weight": 1.0, "epoch": 25.58465855940131, "flow_matching_loss": 0.014434927608817816, "grad_norm": 0.08558816462755203, "invalid_tail_samples": 24.3, "learning_rate": 2.119711520648554e-06, "loss": 0.0163, "positive_teacher_pairs": 26735.5, "relation_loss": 0.0018228699336759746, "selected_pairs": 26735.5, "step": 27350, "student_distance_mean": 1269.3953857421875, "teacher_distance_mean": 0.8559800982475281, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0018228699336759746, "weighted_relation_loss": 0.0018228699336759746 }, { "action_query_batch_std": 21.981118965148926, "action_query_norm": 929.4430603027344, "action_relation_loss": 0.0017856240971013903, "auxiliary_loss_weight": 1.0, "epoch": 25.59401309635173, "flow_matching_loss": 0.01490594083443284, "grad_norm": 0.08746448159217834, "invalid_tail_samples": 24.6, "learning_rate": 2.103862788318628e-06, "loss": 0.0167, "positive_teacher_pairs": 26667.0, "relation_loss": 0.0017856240971013903, "selected_pairs": 26667.0, "step": 27360, "student_distance_mean": 1263.078466796875, "teacher_distance_mean": 0.8518382549285889, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0017856240971013903, "weighted_relation_loss": 0.0017856240971013903 }, { "action_query_batch_std": 22.05352611541748, "action_query_norm": 936.1667541503906, "action_relation_loss": 0.0017984218662604689, "auxiliary_loss_weight": 1.0, "epoch": 25.603367633302152, "flow_matching_loss": 0.015506312437355518, "grad_norm": 0.09931056946516037, "invalid_tail_samples": 21.5, "learning_rate": 2.088072254311729e-06, "loss": 0.0173, "positive_teacher_pairs": 27383.4, "relation_loss": 0.0017984218662604689, "selected_pairs": 27383.4, "step": 27370, "student_distance_mean": 1261.931494140625, "teacher_distance_mean": 0.8513988018035888, "valid_action_samples": 234.5, "weighted_auxiliary_loss": 0.0017984218662604689, "weighted_relation_loss": 0.0017984218662604689 }, { "action_query_batch_std": 22.305628967285156, "action_query_norm": 942.9185668945313, "action_relation_loss": 0.0017637020093388856, "auxiliary_loss_weight": 1.0, "epoch": 25.61272217025257, "flow_matching_loss": 0.014289519283920527, "grad_norm": 0.08043752610683441, "invalid_tail_samples": 20.4, "learning_rate": 2.0723399378148435e-06, "loss": 0.0161, "positive_teacher_pairs": 27645.2, "relation_loss": 0.0017637020093388856, "selected_pairs": 27645.2, "step": 27380, "student_distance_mean": 1279.7216186523438, "teacher_distance_mean": 0.863320791721344, "valid_action_samples": 235.6, "weighted_auxiliary_loss": 0.0017637020093388856, "weighted_relation_loss": 0.0017637020093388856 }, { "action_query_batch_std": 21.962013816833498, "action_query_norm": 929.874755859375, "action_relation_loss": 0.0016905959113501013, "auxiliary_loss_weight": 1.0, "epoch": 25.622076707202993, "flow_matching_loss": 0.014430724177509546, "grad_norm": 0.1012088879942894, "invalid_tail_samples": 21.4, "learning_rate": 2.0566658579442065e-06, "loss": 0.0161, "positive_teacher_pairs": 27403.9, "relation_loss": 0.0016905959113501013, "selected_pairs": 27403.9, "step": 27390, "student_distance_mean": 1261.3057373046875, "teacher_distance_mean": 0.8509093761444092, "valid_action_samples": 234.6, "weighted_auxiliary_loss": 0.0016905959113501013, "weighted_relation_loss": 0.0016905959113501013 }, { "action_query_batch_std": 21.89755802154541, "action_query_norm": 928.9334350585938, "action_relation_loss": 0.0017730892170220614, "auxiliary_loss_weight": 1.0, "epoch": 25.631431244153415, "flow_matching_loss": 0.015182409342378378, "grad_norm": 0.07712145894765854, "invalid_tail_samples": 24.6, "learning_rate": 2.0410500337453176e-06, "loss": 0.017, "positive_teacher_pairs": 26668.3, "relation_loss": 0.0017730892170220614, "selected_pairs": 26668.3, "step": 27400, "student_distance_mean": 1263.304248046875, "teacher_distance_mean": 0.8528038382530212, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0017730892170220614, "weighted_relation_loss": 0.0017730892170220614 }, { "action_query_batch_std": 22.09182186126709, "action_query_norm": 934.8496337890625, "action_relation_loss": 0.0017300021718256176, "auxiliary_loss_weight": 1.0, "epoch": 25.640785781103837, "flow_matching_loss": 0.013475491758435964, "grad_norm": 0.08407997339963913, "invalid_tail_samples": 25.2, "learning_rate": 2.0254924841928645e-06, "loss": 0.0152, "positive_teacher_pairs": 26539.0, "relation_loss": 0.0017300021718256176, "selected_pairs": 26539.0, "step": 27410, "student_distance_mean": 1272.65693359375, "teacher_distance_mean": 0.860043340921402, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0017300021718256176, "weighted_relation_loss": 0.0017300021718256176 }, { "action_query_batch_std": 22.09964942932129, "action_query_norm": 935.6076293945313, "action_relation_loss": 0.0017263985821045936, "auxiliary_loss_weight": 1.0, "epoch": 25.650140318054255, "flow_matching_loss": 0.014112326689064503, "grad_norm": 0.08312984555959702, "invalid_tail_samples": 25.2, "learning_rate": 2.009993228190754e-06, "loss": 0.0158, "positive_teacher_pairs": 26538.6, "relation_loss": 0.0017263985821045936, "selected_pairs": 26538.6, "step": 27420, "student_distance_mean": 1269.973388671875, "teacher_distance_mean": 0.8571206033229828, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0017263985821045936, "weighted_relation_loss": 0.0017263985821045936 }, { "action_query_batch_std": 22.023448371887206, "action_query_norm": 932.4200805664062, "action_relation_loss": 0.0017201252281665801, "auxiliary_loss_weight": 1.0, "epoch": 25.659494855004677, "flow_matching_loss": 0.015393982827663421, "grad_norm": 0.09785771369934082, "invalid_tail_samples": 29.2, "learning_rate": 1.9945522845720323e-06, "loss": 0.0171, "positive_teacher_pairs": 25618.6, "relation_loss": 0.0017201252281665801, "selected_pairs": 25618.6, "step": 27430, "student_distance_mean": 1264.7132080078125, "teacher_distance_mean": 0.8543327510356903, "valid_action_samples": 226.8, "weighted_auxiliary_loss": 0.0017201252281665801, "weighted_relation_loss": 0.0017201252281665801 }, { "action_query_batch_std": 22.195019149780272, "action_query_norm": 938.5926940917968, "action_relation_loss": 0.0017918074503540994, "auxiliary_loss_weight": 1.0, "epoch": 25.6688493919551, "flow_matching_loss": 0.014759880490601063, "grad_norm": 0.06923588365316391, "invalid_tail_samples": 22.6, "learning_rate": 1.9791696720988963e-06, "loss": 0.0166, "positive_teacher_pairs": 27127.9, "relation_loss": 0.0017918074503540994, "selected_pairs": 27127.9, "step": 27440, "student_distance_mean": 1275.4877807617188, "teacher_distance_mean": 0.8610141038894653, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0017918074503540994, "weighted_relation_loss": 0.0017918074503540994 }, { "action_query_batch_std": 21.82890033721924, "action_query_norm": 926.3649108886718, "action_relation_loss": 0.0018017700989730657, "auxiliary_loss_weight": 1.0, "epoch": 25.678203928905518, "flow_matching_loss": 0.015248588472604751, "grad_norm": 0.10297922044992447, "invalid_tail_samples": 23.3, "learning_rate": 1.9638454094626833e-06, "loss": 0.0171, "positive_teacher_pairs": 26978.1, "relation_loss": 0.0018017700989730657, "selected_pairs": 26978.1, "step": 27450, "student_distance_mean": 1256.0149047851562, "teacher_distance_mean": 0.8481356918811798, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0018017700989730657, "weighted_relation_loss": 0.0018017700989730657 }, { "action_query_batch_std": 22.12423458099365, "action_query_norm": 936.4416259765625, "action_relation_loss": 0.0017902996856719255, "auxiliary_loss_weight": 1.0, "epoch": 25.68755846585594, "flow_matching_loss": 0.015011179354041814, "grad_norm": 0.07326282560825348, "invalid_tail_samples": 24.2, "learning_rate": 1.9485795152838104e-06, "loss": 0.0168, "positive_teacher_pairs": 26769.2, "relation_loss": 0.0017902996856719255, "selected_pairs": 26769.2, "step": 27460, "student_distance_mean": 1275.006591796875, "teacher_distance_mean": 0.8596313059329986, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0017902996856719255, "weighted_relation_loss": 0.0017902996856719255 }, { "action_query_batch_std": 22.105243492126466, "action_query_norm": 937.2066345214844, "action_relation_loss": 0.001768245780840516, "auxiliary_loss_weight": 1.0, "epoch": 25.69691300280636, "flow_matching_loss": 0.013606194127351045, "grad_norm": 0.07639392465353012, "invalid_tail_samples": 21.2, "learning_rate": 1.933372008111778e-06, "loss": 0.0154, "positive_teacher_pairs": 27462.2, "relation_loss": 0.001768245780840516, "selected_pairs": 27462.2, "step": 27470, "student_distance_mean": 1267.1545043945312, "teacher_distance_mean": 0.8567264437675476, "valid_action_samples": 234.8, "weighted_auxiliary_loss": 0.001768245780840516, "weighted_relation_loss": 0.001768245780840516 }, { "action_query_batch_std": 22.132416915893554, "action_query_norm": 934.1461059570313, "action_relation_loss": 0.0017339226556941866, "auxiliary_loss_weight": 1.0, "epoch": 25.706267539756784, "flow_matching_loss": 0.0148035092279315, "grad_norm": 0.08710316568613052, "invalid_tail_samples": 23.3, "learning_rate": 1.918222906425143e-06, "loss": 0.0165, "positive_teacher_pairs": 26966.5, "relation_loss": 0.0017339226556941866, "selected_pairs": 26966.5, "step": 27480, "student_distance_mean": 1266.3009887695312, "teacher_distance_mean": 0.8545786619186402, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0017339226556941866, "weighted_relation_loss": 0.0017339226556941866 }, { "action_query_batch_std": 22.1082612991333, "action_query_norm": 937.069970703125, "action_relation_loss": 0.0017373740207403897, "auxiliary_loss_weight": 1.0, "epoch": 25.715622076707202, "flow_matching_loss": 0.015490955486893655, "grad_norm": 0.07673422992229462, "invalid_tail_samples": 24.0, "learning_rate": 1.903132228631488e-06, "loss": 0.0172, "positive_teacher_pairs": 26807.4, "relation_loss": 0.0017373740207403897, "selected_pairs": 26807.4, "step": 27490, "student_distance_mean": 1271.6789916992188, "teacher_distance_mean": 0.8582633793354034, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0017373740207403897, "weighted_relation_loss": 0.0017373740207403897 }, { "action_query_batch_std": 21.781480026245116, "action_query_norm": 925.0461669921875, "action_relation_loss": 0.0018361505470238626, "auxiliary_loss_weight": 1.0, "epoch": 25.724976613657624, "flow_matching_loss": 0.01579260127618909, "grad_norm": 0.10242850333452225, "invalid_tail_samples": 24.2, "learning_rate": 1.8880999930674215e-06, "loss": 0.0176, "positive_teacher_pairs": 26761.1, "relation_loss": 0.0018361505470238626, "selected_pairs": 26761.1, "step": 27500, "student_distance_mean": 1249.2442504882813, "teacher_distance_mean": 0.8426270961761475, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0018361505470238626, "weighted_relation_loss": 0.0018361505470238626 }, { "action_query_batch_std": 21.569737052917482, "action_query_norm": 920.5282165527344, "action_relation_loss": 0.0017605211818590761, "auxiliary_loss_weight": 1.0, "epoch": 25.734331150608046, "flow_matching_loss": 0.014553113281726838, "grad_norm": 0.07636088132858276, "invalid_tail_samples": 22.1, "learning_rate": 1.8731262179985166e-06, "loss": 0.0163, "positive_teacher_pairs": 27240.0, "relation_loss": 0.0017605211818590761, "selected_pairs": 27240.0, "step": 27510, "student_distance_mean": 1240.8510009765625, "teacher_distance_mean": 0.8373531103134155, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0017605211818590761, "weighted_relation_loss": 0.0017605211818590761 }, { "action_query_batch_std": 21.98900623321533, "action_query_norm": 933.6090637207031, "action_relation_loss": 0.0017743657459504901, "auxiliary_loss_weight": 1.0, "epoch": 25.743685687558465, "flow_matching_loss": 0.013315497431904078, "grad_norm": 0.0869726911187172, "invalid_tail_samples": 24.1, "learning_rate": 1.8582109216193244e-06, "loss": 0.0151, "positive_teacher_pairs": 26778.9, "relation_loss": 0.0017743657459504901, "selected_pairs": 26778.9, "step": 27520, "student_distance_mean": 1268.8432373046876, "teacher_distance_mean": 0.8551554203033447, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0017743657459504901, "weighted_relation_loss": 0.0017743657459504901 }, { "action_query_batch_std": 22.01534309387207, "action_query_norm": 934.3222595214844, "action_relation_loss": 0.0017144424258731306, "auxiliary_loss_weight": 1.0, "epoch": 25.753040224508887, "flow_matching_loss": 0.014959329087287188, "grad_norm": 0.08727827668190002, "invalid_tail_samples": 24.2, "learning_rate": 1.8433541220533368e-06, "loss": 0.0167, "positive_teacher_pairs": 26755.4, "relation_loss": 0.0017144424258731306, "selected_pairs": 26755.4, "step": 27530, "student_distance_mean": 1270.9286254882813, "teacher_distance_mean": 0.8558400094509124, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0017144424258731306, "weighted_relation_loss": 0.0017144424258731306 }, { "action_query_batch_std": 22.212020492553712, "action_query_norm": 938.5279052734375, "action_relation_loss": 0.0017260282183997333, "auxiliary_loss_weight": 1.0, "epoch": 25.76239476145931, "flow_matching_loss": 0.014506951905786991, "grad_norm": 0.14629386365413666, "invalid_tail_samples": 22.9, "learning_rate": 1.8285558373529577e-06, "loss": 0.0162, "positive_teacher_pairs": 27057.7, "relation_loss": 0.0017260282183997333, "selected_pairs": 27057.7, "step": 27540, "student_distance_mean": 1277.7254272460937, "teacher_distance_mean": 0.8612569332122803, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0017260282183997333, "weighted_relation_loss": 0.0017260282183997333 }, { "action_query_batch_std": 22.034398078918457, "action_query_norm": 932.5798706054687, "action_relation_loss": 0.001752381364349276, "auxiliary_loss_weight": 1.0, "epoch": 25.77174929840973, "flow_matching_loss": 0.014514123741537332, "grad_norm": 0.09928999841213226, "invalid_tail_samples": 23.1, "learning_rate": 1.8138160854995145e-06, "loss": 0.0163, "positive_teacher_pairs": 27013.4, "relation_loss": 0.001752381364349276, "selected_pairs": 27013.4, "step": 27550, "student_distance_mean": 1266.542919921875, "teacher_distance_mean": 0.853718489408493, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.001752381364349276, "weighted_relation_loss": 0.001752381364349276 }, { "action_query_batch_std": 21.91145267486572, "action_query_norm": 928.4232177734375, "action_relation_loss": 0.001700515253469348, "auxiliary_loss_weight": 1.0, "epoch": 25.78110383536015, "flow_matching_loss": 0.015688138082623482, "grad_norm": 0.0918671041727066, "invalid_tail_samples": 23.7, "learning_rate": 1.7991348844031864e-06, "loss": 0.0174, "positive_teacher_pairs": 26875.3, "relation_loss": 0.001700515253469348, "selected_pairs": 26875.3, "step": 27560, "student_distance_mean": 1261.1771240234375, "teacher_distance_mean": 0.8498208940029144, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.001700515253469348, "weighted_relation_loss": 0.001700515253469348 }, { "action_query_batch_std": 22.209893035888673, "action_query_norm": 940.1218688964843, "action_relation_loss": 0.0017302477499470115, "auxiliary_loss_weight": 1.0, "epoch": 25.79045837231057, "flow_matching_loss": 0.014652934111654758, "grad_norm": 0.10208603739738464, "invalid_tail_samples": 24.9, "learning_rate": 1.78451225190302e-06, "loss": 0.0164, "positive_teacher_pairs": 26593.5, "relation_loss": 0.0017302477499470115, "selected_pairs": 26593.5, "step": 27570, "student_distance_mean": 1281.95048828125, "teacher_distance_mean": 0.8642394483089447, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0017302477499470115, "weighted_relation_loss": 0.0017302477499470115 }, { "action_query_batch_std": 21.880270385742186, "action_query_norm": 927.4834411621093, "action_relation_loss": 0.0017163725919090212, "auxiliary_loss_weight": 1.0, "epoch": 25.799812909260993, "flow_matching_loss": 0.014639976061880588, "grad_norm": 0.08066337555646896, "invalid_tail_samples": 26.2, "learning_rate": 1.7699482057668914e-06, "loss": 0.0164, "positive_teacher_pairs": 26303.4, "relation_loss": 0.0017163725919090212, "selected_pairs": 26303.4, "step": 27580, "student_distance_mean": 1262.6523681640624, "teacher_distance_mean": 0.8515571236610413, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.0017163725919090212, "weighted_relation_loss": 0.0017163725919090212 }, { "action_query_batch_std": 22.092142868041993, "action_query_norm": 937.2061157226562, "action_relation_loss": 0.0016599992639385163, "auxiliary_loss_weight": 1.0, "epoch": 25.80916744621141, "flow_matching_loss": 0.014403460361063481, "grad_norm": 0.08912211656570435, "invalid_tail_samples": 23.2, "learning_rate": 1.7554427636914895e-06, "loss": 0.0161, "positive_teacher_pairs": 26986.1, "relation_loss": 0.0016599992639385163, "selected_pairs": 26986.1, "step": 27590, "student_distance_mean": 1277.481494140625, "teacher_distance_mean": 0.860962551832199, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0016599992639385163, "weighted_relation_loss": 0.0016599992639385163 }, { "action_query_batch_std": 21.965666007995605, "action_query_norm": 932.7555847167969, "action_relation_loss": 0.0017320848186500371, "auxiliary_loss_weight": 1.0, "epoch": 25.818521983161833, "flow_matching_loss": 0.014724448323249817, "grad_norm": 0.09141966700553894, "invalid_tail_samples": 25.3, "learning_rate": 1.7409959433022871e-06, "loss": 0.0165, "positive_teacher_pairs": 26508.6, "relation_loss": 0.0017320848186500371, "selected_pairs": 26508.6, "step": 27600, "student_distance_mean": 1268.4748046875, "teacher_distance_mean": 0.8558596909046173, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0017320848186500371, "weighted_relation_loss": 0.0017320848186500371 }, { "action_query_batch_std": 21.8349515914917, "action_query_norm": 925.8057739257813, "action_relation_loss": 0.0017552103963680565, "auxiliary_loss_weight": 1.0, "epoch": 25.827876520112255, "flow_matching_loss": 0.015068535227328539, "grad_norm": 0.07125731557607651, "invalid_tail_samples": 22.6, "learning_rate": 1.7266077621535481e-06, "loss": 0.0168, "positive_teacher_pairs": 27127.3, "relation_loss": 0.0017552103963680565, "selected_pairs": 27127.3, "step": 27610, "student_distance_mean": 1255.4517578125, "teacher_distance_mean": 0.8468204855918884, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0017552103963680565, "weighted_relation_loss": 0.0017552103963680565 }, { "action_query_batch_std": 22.036064910888673, "action_query_norm": 932.56181640625, "action_relation_loss": 0.0017199636553414167, "auxiliary_loss_weight": 1.0, "epoch": 25.837231057062674, "flow_matching_loss": 0.015597732085734606, "grad_norm": 0.0847802683711052, "invalid_tail_samples": 22.6, "learning_rate": 1.7122782377282597e-06, "loss": 0.0173, "positive_teacher_pairs": 27129.8, "relation_loss": 0.0017199636553414167, "selected_pairs": 27129.8, "step": 27620, "student_distance_mean": 1267.30625, "teacher_distance_mean": 0.8549609899520874, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0017199636553414167, "weighted_relation_loss": 0.0017199636553414167 }, { "action_query_batch_std": 22.21866455078125, "action_query_norm": 938.2890747070312, "action_relation_loss": 0.0017933966242708265, "auxiliary_loss_weight": 1.0, "epoch": 25.846585594013096, "flow_matching_loss": 0.01546245040372014, "grad_norm": 0.08083321899175644, "invalid_tail_samples": 25.7, "learning_rate": 1.6980073874381497e-06, "loss": 0.0173, "positive_teacher_pairs": 26411.4, "relation_loss": 0.0017933966242708265, "selected_pairs": 26411.4, "step": 27630, "student_distance_mean": 1278.8211303710937, "teacher_distance_mean": 0.8621093928813934, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.0017933966242708265, "weighted_relation_loss": 0.0017933966242708265 }, { "action_query_batch_std": 21.741967582702635, "action_query_norm": 923.9624694824219, "action_relation_loss": 0.0017146635218523443, "auxiliary_loss_weight": 1.0, "epoch": 25.855940130963518, "flow_matching_loss": 0.014813883788883686, "grad_norm": 0.08600457012653351, "invalid_tail_samples": 26.1, "learning_rate": 1.6837952286236413e-06, "loss": 0.0165, "positive_teacher_pairs": 26317.5, "relation_loss": 0.0017146635218523443, "selected_pairs": 26317.5, "step": 27640, "student_distance_mean": 1256.618798828125, "teacher_distance_mean": 0.8490593671798706, "valid_action_samples": 229.9, "weighted_auxiliary_loss": 0.0017146635218523443, "weighted_relation_loss": 0.0017146635218523443 }, { "action_query_batch_std": 22.066746139526366, "action_query_norm": 934.2070068359375, "action_relation_loss": 0.0017058015335351228, "auxiliary_loss_weight": 1.0, "epoch": 25.86529466791394, "flow_matching_loss": 0.014045785926282407, "grad_norm": 0.07067347317934036, "invalid_tail_samples": 22.7, "learning_rate": 1.6696417785538488e-06, "loss": 0.0158, "positive_teacher_pairs": 27108.6, "relation_loss": 0.0017058015335351228, "selected_pairs": 27108.6, "step": 27650, "student_distance_mean": 1267.2443969726562, "teacher_distance_mean": 0.8557172834873199, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0017058015335351228, "weighted_relation_loss": 0.0017058015335351228 }, { "action_query_batch_std": 21.92446365356445, "action_query_norm": 929.5953369140625, "action_relation_loss": 0.0017924364074133337, "auxiliary_loss_weight": 1.0, "epoch": 25.874649204864358, "flow_matching_loss": 0.017749490775167943, "grad_norm": 0.10525128990411758, "invalid_tail_samples": 24.7, "learning_rate": 1.6555470544265538e-06, "loss": 0.0195, "positive_teacher_pairs": 26638.3, "relation_loss": 0.0017924364074133337, "selected_pairs": 26638.3, "step": 27660, "student_distance_mean": 1260.81357421875, "teacher_distance_mean": 0.8495086193084717, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0017924364074133337, "weighted_relation_loss": 0.0017924364074133337 }, { "action_query_batch_std": 22.19715347290039, "action_query_norm": 938.8430297851562, "action_relation_loss": 0.0017381998244673015, "auxiliary_loss_weight": 1.0, "epoch": 25.88400374181478, "flow_matching_loss": 0.013805689942091703, "grad_norm": 0.06644206494092941, "invalid_tail_samples": 24.2, "learning_rate": 1.6415110733681738e-06, "loss": 0.0155, "positive_teacher_pairs": 26759.9, "relation_loss": 0.0017381998244673015, "selected_pairs": 26759.9, "step": 27670, "student_distance_mean": 1273.8469360351562, "teacher_distance_mean": 0.8586301922798156, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0017381998244673015, "weighted_relation_loss": 0.0017381998244673015 }, { "action_query_batch_std": 22.004512977600097, "action_query_norm": 933.2792724609375, "action_relation_loss": 0.0016996346064843237, "auxiliary_loss_weight": 1.0, "epoch": 25.893358278765202, "flow_matching_loss": 0.013897591643035412, "grad_norm": 0.06804246455430984, "invalid_tail_samples": 22.9, "learning_rate": 1.6275338524337436e-06, "loss": 0.0156, "positive_teacher_pairs": 27058.3, "relation_loss": 0.0016996346064843237, "selected_pairs": 27058.3, "step": 27680, "student_distance_mean": 1262.8057983398437, "teacher_distance_mean": 0.8515997648239135, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0016996346064843237, "weighted_relation_loss": 0.0016996346064843237 }, { "action_query_batch_std": 22.1217924118042, "action_query_norm": 939.1220336914063, "action_relation_loss": 0.001757020503282547, "auxiliary_loss_weight": 1.0, "epoch": 25.90271281571562, "flow_matching_loss": 0.015213413629680872, "grad_norm": 0.08996257930994034, "invalid_tail_samples": 24.3, "learning_rate": 1.6136154086069056e-06, "loss": 0.017, "positive_teacher_pairs": 26735.9, "relation_loss": 0.001757020503282547, "selected_pairs": 26735.9, "step": 27690, "student_distance_mean": 1273.1563598632813, "teacher_distance_mean": 0.8599176526069641, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.001757020503282547, "weighted_relation_loss": 0.001757020503282547 }, { "action_query_batch_std": 22.0753080368042, "action_query_norm": 934.8862182617188, "action_relation_loss": 0.001758301188237965, "auxiliary_loss_weight": 1.0, "epoch": 25.912067352666043, "flow_matching_loss": 0.015084516536444426, "grad_norm": 0.07909268140792847, "invalid_tail_samples": 25.4, "learning_rate": 1.5997557587998868e-06, "loss": 0.0168, "positive_teacher_pairs": 26480.1, "relation_loss": 0.001758301188237965, "selected_pairs": 26480.1, "step": 27700, "student_distance_mean": 1275.4341552734375, "teacher_distance_mean": 0.8592385947704315, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.001758301188237965, "weighted_relation_loss": 0.001758301188237965 }, { "action_query_batch_std": 21.92765712738037, "action_query_norm": 930.2566772460938, "action_relation_loss": 0.0017873555072583259, "auxiliary_loss_weight": 1.0, "epoch": 25.921421889616465, "flow_matching_loss": 0.013684897404164075, "grad_norm": 0.07795505970716476, "invalid_tail_samples": 22.7, "learning_rate": 1.5859549198534606e-06, "loss": 0.0155, "positive_teacher_pairs": 27104.8, "relation_loss": 0.0017873555072583259, "selected_pairs": 27104.8, "step": 27710, "student_distance_mean": 1259.4549072265625, "teacher_distance_mean": 0.850192004442215, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0017873555072583259, "weighted_relation_loss": 0.0017873555072583259 }, { "action_query_batch_std": 22.223955154418945, "action_query_norm": 939.3664184570313, "action_relation_loss": 0.00177933347877115, "auxiliary_loss_weight": 1.0, "epoch": 25.930776426566887, "flow_matching_loss": 0.016858451440930365, "grad_norm": 0.08905822038650513, "invalid_tail_samples": 24.9, "learning_rate": 1.572212908536963e-06, "loss": 0.0186, "positive_teacher_pairs": 26603.9, "relation_loss": 0.00177933347877115, "selected_pairs": 26603.9, "step": 27720, "student_distance_mean": 1280.44052734375, "teacher_distance_mean": 0.8635348558425904, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.00177933347877115, "weighted_relation_loss": 0.00177933347877115 }, { "action_query_batch_std": 21.7992805480957, "action_query_norm": 926.939208984375, "action_relation_loss": 0.0017467944882810116, "auxiliary_loss_weight": 1.0, "epoch": 25.940130963517305, "flow_matching_loss": 0.0159317497164011, "grad_norm": 0.07709112763404846, "invalid_tail_samples": 22.1, "learning_rate": 1.5585297415482202e-06, "loss": 0.0177, "positive_teacher_pairs": 27251.4, "relation_loss": 0.0017467944882810116, "selected_pairs": 27251.4, "step": 27730, "student_distance_mean": 1257.3727661132812, "teacher_distance_mean": 0.8472377181053161, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0017467944882810116, "weighted_relation_loss": 0.0017467944882810116 }, { "action_query_batch_std": 22.11167163848877, "action_query_norm": 935.2738464355468, "action_relation_loss": 0.0017660967423580587, "auxiliary_loss_weight": 1.0, "epoch": 25.949485500467727, "flow_matching_loss": 0.015323476772755385, "grad_norm": 0.10889696329832077, "invalid_tail_samples": 22.5, "learning_rate": 1.5449054355135717e-06, "loss": 0.0171, "positive_teacher_pairs": 27147.6, "relation_loss": 0.0017660967423580587, "selected_pairs": 27147.6, "step": 27740, "student_distance_mean": 1269.7051513671875, "teacher_distance_mean": 0.8557334005832672, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.0017660967423580587, "weighted_relation_loss": 0.0017660967423580587 }, { "action_query_batch_std": 22.237180709838867, "action_query_norm": 939.7856079101563, "action_relation_loss": 0.0017428857274353505, "auxiliary_loss_weight": 1.0, "epoch": 25.95884003741815, "flow_matching_loss": 0.01405638437718153, "grad_norm": 0.07068019360303879, "invalid_tail_samples": 23.4, "learning_rate": 1.5313400069878415e-06, "loss": 0.0158, "positive_teacher_pairs": 26940.9, "relation_loss": 0.0017428857274353505, "selected_pairs": 26940.9, "step": 27750, "student_distance_mean": 1279.9438354492188, "teacher_distance_mean": 0.8624405026435852, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0017428857274353505, "weighted_relation_loss": 0.0017428857274353505 }, { "action_query_batch_std": 22.101079177856445, "action_query_norm": 933.7994995117188, "action_relation_loss": 0.00173831406282261, "auxiliary_loss_weight": 1.0, "epoch": 25.968194574368567, "flow_matching_loss": 0.014941896311938763, "grad_norm": 0.10882823169231415, "invalid_tail_samples": 24.0, "learning_rate": 1.5178334724542887e-06, "loss": 0.0167, "positive_teacher_pairs": 26800.9, "relation_loss": 0.00173831406282261, "selected_pairs": 26800.9, "step": 27760, "student_distance_mean": 1276.37763671875, "teacher_distance_mean": 0.862733519077301, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.00173831406282261, "weighted_relation_loss": 0.00173831406282261 }, { "action_query_batch_std": 22.08721866607666, "action_query_norm": 936.0521606445312, "action_relation_loss": 0.001744965824764222, "auxiliary_loss_weight": 1.0, "epoch": 25.97754911131899, "flow_matching_loss": 0.014547034539282322, "grad_norm": 0.08002718538045883, "invalid_tail_samples": 25.3, "learning_rate": 1.504385848324641e-06, "loss": 0.0163, "positive_teacher_pairs": 26500.4, "relation_loss": 0.001744965824764222, "selected_pairs": 26500.4, "step": 27770, "student_distance_mean": 1271.7182006835938, "teacher_distance_mean": 0.8582752406597137, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.001744965824764222, "weighted_relation_loss": 0.001744965824764222 }, { "action_query_batch_std": 21.84779796600342, "action_query_norm": 926.2247802734375, "action_relation_loss": 0.0017829535878263413, "auxiliary_loss_weight": 1.0, "epoch": 25.98690364826941, "flow_matching_loss": 0.015416853129863739, "grad_norm": 0.08366122841835022, "invalid_tail_samples": 25.8, "learning_rate": 1.490997150939033e-06, "loss": 0.0172, "positive_teacher_pairs": 26393.8, "relation_loss": 0.0017829535878263413, "selected_pairs": 26393.8, "step": 27780, "student_distance_mean": 1260.2302001953126, "teacher_distance_mean": 0.8496857762336731, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.0017829535878263413, "weighted_relation_loss": 0.0017829535878263413 }, { "action_query_batch_std": 22.209695053100585, "action_query_norm": 937.7260986328125, "action_relation_loss": 0.0017532336642034352, "auxiliary_loss_weight": 1.0, "epoch": 25.996258185219833, "flow_matching_loss": 0.015175593178719282, "grad_norm": 0.09198649972677231, "invalid_tail_samples": 26.5, "learning_rate": 1.4776673965659793e-06, "loss": 0.0169, "positive_teacher_pairs": 26226.8, "relation_loss": 0.0017532336642034352, "selected_pairs": 26226.8, "step": 27790, "student_distance_mean": 1273.5512451171876, "teacher_distance_mean": 0.8611262500286102, "valid_action_samples": 229.5, "weighted_auxiliary_loss": 0.0017532336642034352, "weighted_relation_loss": 0.0017532336642034352 }, { "action_query_batch_std": 22.115505981445313, "action_query_norm": 936.6867614746094, "action_relation_loss": 0.0016972498851828277, "auxiliary_loss_weight": 1.0, "epoch": 26.00561272217025, "flow_matching_loss": 0.014989164844155311, "grad_norm": 0.09679614752531052, "invalid_tail_samples": 25.6, "learning_rate": 1.4643966014023957e-06, "loss": 0.0167, "positive_teacher_pairs": 23525.5, "relation_loss": 0.0016972498851828277, "selected_pairs": 23525.5, "step": 27800, "student_distance_mean": 1282.3327758789062, "teacher_distance_mean": 0.8657264351844788, "valid_action_samples": 210.5, "weighted_auxiliary_loss": 0.0016972498851828277, "weighted_relation_loss": 0.0016972498851828277 }, { "action_query_batch_std": 22.028594779968262, "action_query_norm": 932.7619018554688, "action_relation_loss": 0.001735056354664266, "auxiliary_loss_weight": 1.0, "epoch": 26.014967259120674, "flow_matching_loss": 0.01545813661068678, "grad_norm": 0.08510981500148773, "invalid_tail_samples": 25.6, "learning_rate": 1.4511847815735503e-06, "loss": 0.0172, "positive_teacher_pairs": 26433.4, "relation_loss": 0.001735056354664266, "selected_pairs": 26433.4, "step": 27810, "student_distance_mean": 1270.5672241210937, "teacher_distance_mean": 0.8567986607551574, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.001735056354664266, "weighted_relation_loss": 0.001735056354664266 }, { "action_query_batch_std": 22.11850643157959, "action_query_norm": 935.2385009765625, "action_relation_loss": 0.0017609881004318594, "auxiliary_loss_weight": 1.0, "epoch": 26.024321796071096, "flow_matching_loss": 0.013766136579215526, "grad_norm": 0.07204218953847885, "invalid_tail_samples": 23.6, "learning_rate": 1.438031953133051e-06, "loss": 0.0155, "positive_teacher_pairs": 26899.3, "relation_loss": 0.0017609881004318594, "selected_pairs": 26899.3, "step": 27820, "student_distance_mean": 1272.5854736328124, "teacher_distance_mean": 0.8582377970218659, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0017609881004318594, "weighted_relation_loss": 0.0017609881004318594 }, { "action_query_batch_std": 22.06788578033447, "action_query_norm": 935.1530700683594, "action_relation_loss": 0.001808623701799661, "auxiliary_loss_weight": 1.0, "epoch": 26.033676333021514, "flow_matching_loss": 0.014086757693439722, "grad_norm": 0.07617924362421036, "invalid_tail_samples": 24.3, "learning_rate": 1.4249381320628197e-06, "loss": 0.0159, "positive_teacher_pairs": 26736.4, "relation_loss": 0.001808623701799661, "selected_pairs": 26736.4, "step": 27830, "student_distance_mean": 1266.5546630859376, "teacher_distance_mean": 0.8535449981689454, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.001808623701799661, "weighted_relation_loss": 0.001808623701799661 }, { "action_query_batch_std": 22.084819984436034, "action_query_norm": 933.8680847167968, "action_relation_loss": 0.0017329003079794348, "auxiliary_loss_weight": 1.0, "epoch": 26.043030869971936, "flow_matching_loss": 0.0149141994304955, "grad_norm": 0.07273352891206741, "invalid_tail_samples": 25.8, "learning_rate": 1.4119033342730902e-06, "loss": 0.0166, "positive_teacher_pairs": 26393.2, "relation_loss": 0.0017329003079794348, "selected_pairs": 26393.2, "step": 27840, "student_distance_mean": 1268.00458984375, "teacher_distance_mean": 0.8549577295780182, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.0017329003079794348, "weighted_relation_loss": 0.0017329003079794348 }, { "action_query_batch_std": 22.094438362121583, "action_query_norm": 938.4420654296875, "action_relation_loss": 0.0017893955227918923, "auxiliary_loss_weight": 1.0, "epoch": 26.052385406922358, "flow_matching_loss": 0.015066208876669407, "grad_norm": 0.07179579883813858, "invalid_tail_samples": 24.3, "learning_rate": 1.3989275756023656e-06, "loss": 0.0169, "positive_teacher_pairs": 26730.6, "relation_loss": 0.0017893955227918923, "selected_pairs": 26730.6, "step": 27850, "student_distance_mean": 1272.53681640625, "teacher_distance_mean": 0.8573049783706665, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0017893955227918923, "weighted_relation_loss": 0.0017893955227918923 }, { "action_query_batch_std": 21.922883796691895, "action_query_norm": 930.6421691894532, "action_relation_loss": 0.001750769536010921, "auxiliary_loss_weight": 1.0, "epoch": 26.061739943872777, "flow_matching_loss": 0.014415558148175477, "grad_norm": 0.09672480821609497, "invalid_tail_samples": 24.2, "learning_rate": 1.386010871817417e-06, "loss": 0.0162, "positive_teacher_pairs": 26758.3, "relation_loss": 0.001750769536010921, "selected_pairs": 26758.3, "step": 27860, "student_distance_mean": 1262.1378662109375, "teacher_distance_mean": 0.8505372166633606, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.001750769536010921, "weighted_relation_loss": 0.001750769536010921 }, { "action_query_batch_std": 21.793410301208496, "action_query_norm": 923.834765625, "action_relation_loss": 0.0017840927233919502, "auxiliary_loss_weight": 1.0, "epoch": 26.0710944808232, "flow_matching_loss": 0.014532670564949512, "grad_norm": 0.0934009775519371, "invalid_tail_samples": 21.3, "learning_rate": 1.3731532386132616e-06, "loss": 0.0163, "positive_teacher_pairs": 27431.0, "relation_loss": 0.0017840927233919502, "selected_pairs": 27431.0, "step": 27870, "student_distance_mean": 1252.2536254882812, "teacher_distance_mean": 0.843695592880249, "valid_action_samples": 234.7, "weighted_auxiliary_loss": 0.0017840927233919502, "weighted_relation_loss": 0.0017840927233919502 }, { "action_query_batch_std": 22.176140213012694, "action_query_norm": 939.2483215332031, "action_relation_loss": 0.0017372715868987144, "auxiliary_loss_weight": 1.0, "epoch": 26.08044901777362, "flow_matching_loss": 0.01663670251145959, "grad_norm": 0.0756528452038765, "invalid_tail_samples": 24.9, "learning_rate": 1.360354691613136e-06, "loss": 0.0184, "positive_teacher_pairs": 26596.1, "relation_loss": 0.0017372715868987144, "selected_pairs": 26596.1, "step": 27880, "student_distance_mean": 1282.1276977539062, "teacher_distance_mean": 0.8644738376140595, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0017372715868987144, "weighted_relation_loss": 0.0017372715868987144 }, { "action_query_batch_std": 21.96464099884033, "action_query_norm": 931.3227233886719, "action_relation_loss": 0.0017493157181888818, "auxiliary_loss_weight": 1.0, "epoch": 26.089803554724043, "flow_matching_loss": 0.014048536028712987, "grad_norm": 0.08803185075521469, "invalid_tail_samples": 20.4, "learning_rate": 1.3476152463684776e-06, "loss": 0.0158, "positive_teacher_pairs": 27646.8, "relation_loss": 0.0017493157181888818, "selected_pairs": 27646.8, "step": 27890, "student_distance_mean": 1264.263623046875, "teacher_distance_mean": 0.851783037185669, "valid_action_samples": 235.6, "weighted_auxiliary_loss": 0.0017493157181888818, "weighted_relation_loss": 0.0017493157181888818 }, { "action_query_batch_std": 21.81600856781006, "action_query_norm": 924.7462219238281, "action_relation_loss": 0.00181538067990914, "auxiliary_loss_weight": 1.0, "epoch": 26.09915809167446, "flow_matching_loss": 0.015612759441137315, "grad_norm": 0.09587051719427109, "invalid_tail_samples": 27.9, "learning_rate": 1.3349349183589155e-06, "loss": 0.0174, "positive_teacher_pairs": 25914.5, "relation_loss": 0.00181538067990914, "selected_pairs": 25914.5, "step": 27900, "student_distance_mean": 1259.2139526367187, "teacher_distance_mean": 0.8486063539981842, "valid_action_samples": 228.1, "weighted_auxiliary_loss": 0.00181538067990914, "weighted_relation_loss": 0.00181538067990914 }, { "action_query_batch_std": 22.027494621276855, "action_query_norm": 934.4166015625, "action_relation_loss": 0.0017266737413592637, "auxiliary_loss_weight": 1.0, "epoch": 26.108512628624883, "flow_matching_loss": 0.015732795093208553, "grad_norm": 0.08813376724720001, "invalid_tail_samples": 23.8, "learning_rate": 1.3223137229922356e-06, "loss": 0.0175, "positive_teacher_pairs": 26860.2, "relation_loss": 0.0017266737413592637, "selected_pairs": 26860.2, "step": 27910, "student_distance_mean": 1268.4798706054687, "teacher_distance_mean": 0.8557035803794861, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0017266737413592637, "weighted_relation_loss": 0.0017266737413592637 }, { "action_query_batch_std": 21.99722557067871, "action_query_norm": 933.0706604003906, "action_relation_loss": 0.0017336672521196307, "auxiliary_loss_weight": 1.0, "epoch": 26.117867165575305, "flow_matching_loss": 0.01550649655982852, "grad_norm": 0.06897362321615219, "invalid_tail_samples": 22.2, "learning_rate": 1.3097516756043981e-06, "loss": 0.0172, "positive_teacher_pairs": 27218.2, "relation_loss": 0.0017336672521196307, "selected_pairs": 27218.2, "step": 27920, "student_distance_mean": 1268.6306274414062, "teacher_distance_mean": 0.8559043824672699, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.0017336672521196307, "weighted_relation_loss": 0.0017336672521196307 }, { "action_query_batch_std": 22.04006996154785, "action_query_norm": 933.2371032714843, "action_relation_loss": 0.0017223744885995983, "auxiliary_loss_weight": 1.0, "epoch": 26.127221702525723, "flow_matching_loss": 0.014784186799079179, "grad_norm": 0.08196693658828735, "invalid_tail_samples": 22.3, "learning_rate": 1.29724879145946e-06, "loss": 0.0165, "positive_teacher_pairs": 27204.3, "relation_loss": 0.0017223744885995983, "selected_pairs": 27204.3, "step": 27930, "student_distance_mean": 1271.3477416992187, "teacher_distance_mean": 0.8595836937427521, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0017223744885995983, "weighted_relation_loss": 0.0017223744885995983 }, { "action_query_batch_std": 21.816603088378905, "action_query_norm": 927.0048583984375, "action_relation_loss": 0.0017069434863515199, "auxiliary_loss_weight": 1.0, "epoch": 26.136576239476145, "flow_matching_loss": 0.014266493450850248, "grad_norm": 0.0983891561627388, "invalid_tail_samples": 24.8, "learning_rate": 1.284805085749613e-06, "loss": 0.016, "positive_teacher_pairs": 26619.8, "relation_loss": 0.0017069434863515199, "selected_pairs": 26619.8, "step": 27940, "student_distance_mean": 1259.3657592773438, "teacher_distance_mean": 0.850050288438797, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0017069434863515199, "weighted_relation_loss": 0.0017069434863515199 }, { "action_query_batch_std": 22.025584030151368, "action_query_norm": 934.4125854492188, "action_relation_loss": 0.0018207598128356039, "auxiliary_loss_weight": 1.0, "epoch": 26.145930776426567, "flow_matching_loss": 0.014982567075639963, "grad_norm": 0.11105622351169586, "invalid_tail_samples": 23.5, "learning_rate": 1.2724205735951288e-06, "loss": 0.0168, "positive_teacher_pairs": 26919.6, "relation_loss": 0.0018207598128356039, "selected_pairs": 26919.6, "step": 27950, "student_distance_mean": 1264.1712646484375, "teacher_distance_mean": 0.8518655359745025, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0018207598128356039, "weighted_relation_loss": 0.0018207598128356039 }, { "action_query_batch_std": 21.881784439086914, "action_query_norm": 926.7197448730469, "action_relation_loss": 0.0017791135469451547, "auxiliary_loss_weight": 1.0, "epoch": 26.15528531337699, "flow_matching_loss": 0.01483310516923666, "grad_norm": 0.09154702723026276, "invalid_tail_samples": 23.6, "learning_rate": 1.2600952700443591e-06, "loss": 0.0166, "positive_teacher_pairs": 26902.0, "relation_loss": 0.0017791135469451547, "selected_pairs": 26902.0, "step": 27960, "student_distance_mean": 1256.9367797851562, "teacher_distance_mean": 0.8472964465618134, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0017791135469451547, "weighted_relation_loss": 0.0017791135469451547 }, { "action_query_batch_std": 22.207971382141114, "action_query_norm": 938.6752136230468, "action_relation_loss": 0.0017386345192790032, "auxiliary_loss_weight": 1.0, "epoch": 26.164639850327408, "flow_matching_loss": 0.013552536070346833, "grad_norm": 0.08498984575271606, "invalid_tail_samples": 23.8, "learning_rate": 1.247829190073707e-06, "loss": 0.0153, "positive_teacher_pairs": 26850.0, "relation_loss": 0.0017386345192790032, "selected_pairs": 26850.0, "step": 27970, "student_distance_mean": 1275.9488403320313, "teacher_distance_mean": 0.8597489595413208, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0017386345192790032, "weighted_relation_loss": 0.0017386345192790032 }, { "action_query_batch_std": 22.09634609222412, "action_query_norm": 937.1425537109375, "action_relation_loss": 0.0017219452653080224, "auxiliary_loss_weight": 1.0, "epoch": 26.17399438727783, "flow_matching_loss": 0.01370289521291852, "grad_norm": 0.07724679261445999, "invalid_tail_samples": 23.9, "learning_rate": 1.2356223485876173e-06, "loss": 0.0154, "positive_teacher_pairs": 26825.6, "relation_loss": 0.0017219452653080224, "selected_pairs": 26825.6, "step": 27980, "student_distance_mean": 1275.4686767578125, "teacher_distance_mean": 0.8609384298324585, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0017219452653080224, "weighted_relation_loss": 0.0017219452653080224 }, { "action_query_batch_std": 22.13835048675537, "action_query_norm": 934.7602416992188, "action_relation_loss": 0.0017274393467232585, "auxiliary_loss_weight": 1.0, "epoch": 26.18334892422825, "flow_matching_loss": 0.013473499566316605, "grad_norm": 0.07888161391019821, "invalid_tail_samples": 23.5, "learning_rate": 1.2234747604185526e-06, "loss": 0.0152, "positive_teacher_pairs": 26924.3, "relation_loss": 0.0017274393467232585, "selected_pairs": 26924.3, "step": 27990, "student_distance_mean": 1273.5530151367188, "teacher_distance_mean": 0.8593181252479554, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0017274393467232585, "weighted_relation_loss": 0.0017274393467232585 }, { "action_query_batch_std": 22.131457328796387, "action_query_norm": 937.0954284667969, "action_relation_loss": 0.0017589803668670357, "auxiliary_loss_weight": 1.0, "epoch": 26.19270346117867, "flow_matching_loss": 0.014875488821417093, "grad_norm": 0.0866316556930542, "invalid_tail_samples": 24.3, "learning_rate": 1.2113864403269836e-06, "loss": 0.0166, "positive_teacher_pairs": 26739.9, "relation_loss": 0.0017589803668670357, "selected_pairs": 26739.9, "step": 28000, "student_distance_mean": 1273.177734375, "teacher_distance_mean": 0.8585870504379273, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0017589803668670357, "weighted_relation_loss": 0.0017589803668670357 }, { "action_query_batch_std": 21.89630241394043, "action_query_norm": 929.1313720703125, "action_relation_loss": 0.0017139058327302337, "auxiliary_loss_weight": 1.0, "epoch": 26.202057998129092, "flow_matching_loss": 0.01597169050946832, "grad_norm": 0.10980040580034256, "invalid_tail_samples": 24.2, "learning_rate": 1.1993574030013555e-06, "loss": 0.0177, "positive_teacher_pairs": 26754.3, "relation_loss": 0.0017139058327302337, "selected_pairs": 26754.3, "step": 28010, "student_distance_mean": 1252.7075927734375, "teacher_distance_mean": 0.8444019854068756, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0017139058327302337, "weighted_relation_loss": 0.0017139058327302337 }, { "action_query_batch_std": 21.93691463470459, "action_query_norm": 931.7547424316406, "action_relation_loss": 0.001760065509006381, "auxiliary_loss_weight": 1.0, "epoch": 26.211412535079514, "flow_matching_loss": 0.014913010224699975, "grad_norm": 0.0803387239575386, "invalid_tail_samples": 23.7, "learning_rate": 1.1873876630580816e-06, "loss": 0.0167, "positive_teacher_pairs": 26880.9, "relation_loss": 0.001760065509006381, "selected_pairs": 26880.9, "step": 28020, "student_distance_mean": 1263.858544921875, "teacher_distance_mean": 0.8527510106563568, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.001760065509006381, "weighted_relation_loss": 0.001760065509006381 }, { "action_query_batch_std": 22.04626350402832, "action_query_norm": 935.1173400878906, "action_relation_loss": 0.0017425696598365903, "auxiliary_loss_weight": 1.0, "epoch": 26.220767072029936, "flow_matching_loss": 0.015568509697914124, "grad_norm": 0.1015830859541893, "invalid_tail_samples": 20.8, "learning_rate": 1.1754772350415278e-06, "loss": 0.0173, "positive_teacher_pairs": 27549.8, "relation_loss": 0.0017425696598365903, "selected_pairs": 27549.8, "step": 28030, "student_distance_mean": 1264.0043090820313, "teacher_distance_mean": 0.853096854686737, "valid_action_samples": 235.2, "weighted_auxiliary_loss": 0.0017425696598365903, "weighted_relation_loss": 0.0017425696598365903 }, { "action_query_batch_std": 22.009919738769533, "action_query_norm": 930.3710021972656, "action_relation_loss": 0.0017191950464621186, "auxiliary_loss_weight": 1.0, "epoch": 26.230121608980355, "flow_matching_loss": 0.015292255394160747, "grad_norm": 0.09390949457883835, "invalid_tail_samples": 23.9, "learning_rate": 1.163626133423984e-06, "loss": 0.017, "positive_teacher_pairs": 26825.9, "relation_loss": 0.0017191950464621186, "selected_pairs": 26825.9, "step": 28040, "student_distance_mean": 1260.4920532226563, "teacher_distance_mean": 0.8503889918327332, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0017191950464621186, "weighted_relation_loss": 0.0017191950464621186 }, { "action_query_batch_std": 22.141932868957518, "action_query_norm": 936.9626220703125, "action_relation_loss": 0.001734209863934666, "auxiliary_loss_weight": 1.0, "epoch": 26.239476145930777, "flow_matching_loss": 0.014858725201338529, "grad_norm": 0.097919762134552, "invalid_tail_samples": 25.3, "learning_rate": 1.1518343726056591e-06, "loss": 0.0166, "positive_teacher_pairs": 26512.2, "relation_loss": 0.001734209863934666, "selected_pairs": 26512.2, "step": 28050, "student_distance_mean": 1277.23623046875, "teacher_distance_mean": 0.8615305066108704, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.001734209863934666, "weighted_relation_loss": 0.001734209863934666 }, { "action_query_batch_std": 22.091930198669434, "action_query_norm": 936.2855895996094, "action_relation_loss": 0.0017265709582716226, "auxiliary_loss_weight": 1.0, "epoch": 26.2488306828812, "flow_matching_loss": 0.014668677747249604, "grad_norm": 0.07691451907157898, "invalid_tail_samples": 21.6, "learning_rate": 1.1401019669146474e-06, "loss": 0.0164, "positive_teacher_pairs": 27363.8, "relation_loss": 0.0017265709582716226, "selected_pairs": 27363.8, "step": 28060, "student_distance_mean": 1266.1169311523438, "teacher_distance_mean": 0.8541577756404877, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.0017265709582716226, "weighted_relation_loss": 0.0017265709582716226 }, { "action_query_batch_std": 22.24433765411377, "action_query_norm": 942.1208374023438, "action_relation_loss": 0.0018022008473053575, "auxiliary_loss_weight": 1.0, "epoch": 26.258185219831617, "flow_matching_loss": 0.014466434251517057, "grad_norm": 0.08626635372638702, "invalid_tail_samples": 22.7, "learning_rate": 1.128428930606934e-06, "loss": 0.0163, "positive_teacher_pairs": 27109.1, "relation_loss": 0.0018022008473053575, "selected_pairs": 27109.1, "step": 28070, "student_distance_mean": 1282.0709838867188, "teacher_distance_mean": 0.8668529093265533, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0018022008473053575, "weighted_relation_loss": 0.0018022008473053575 }, { "action_query_batch_std": 22.07067451477051, "action_query_norm": 934.4377075195313, "action_relation_loss": 0.0017128711915574968, "auxiliary_loss_weight": 1.0, "epoch": 26.26753975678204, "flow_matching_loss": 0.014401288423687219, "grad_norm": 0.07103107124567032, "invalid_tail_samples": 22.8, "learning_rate": 1.1168152778663621e-06, "loss": 0.0161, "positive_teacher_pairs": 27081.4, "relation_loss": 0.0017128711915574968, "selected_pairs": 27081.4, "step": 28080, "student_distance_mean": 1271.1651733398437, "teacher_distance_mean": 0.8581295669078827, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0017128711915574968, "weighted_relation_loss": 0.0017128711915574968 }, { "action_query_batch_std": 22.093898582458497, "action_query_norm": 933.6440673828125, "action_relation_loss": 0.0016975854872725905, "auxiliary_loss_weight": 1.0, "epoch": 26.27689429373246, "flow_matching_loss": 0.014572957158088684, "grad_norm": 0.07780583202838898, "invalid_tail_samples": 21.1, "learning_rate": 1.10526102280461e-06, "loss": 0.0163, "positive_teacher_pairs": 27477.3, "relation_loss": 0.0016975854872725905, "selected_pairs": 27477.3, "step": 28090, "student_distance_mean": 1269.7936157226563, "teacher_distance_mean": 0.8571509778499603, "valid_action_samples": 234.9, "weighted_auxiliary_loss": 0.0016975854872725905, "weighted_relation_loss": 0.0016975854872725905 }, { "action_query_batch_std": 22.05659770965576, "action_query_norm": 937.42822265625, "action_relation_loss": 0.0017001446918584406, "auxiliary_loss_weight": 1.0, "epoch": 26.28624883068288, "flow_matching_loss": 0.01420102482661605, "grad_norm": 0.07394302636384964, "invalid_tail_samples": 22.9, "learning_rate": 1.0937661794611864e-06, "loss": 0.0159, "positive_teacher_pairs": 27060.9, "relation_loss": 0.0017001446918584406, "selected_pairs": 27060.9, "step": 28100, "student_distance_mean": 1270.3754638671876, "teacher_distance_mean": 0.8584912240505218, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0017001446918584406, "weighted_relation_loss": 0.0017001446918584406 }, { "action_query_batch_std": 21.82477512359619, "action_query_norm": 924.2431091308594, "action_relation_loss": 0.001736739301122725, "auxiliary_loss_weight": 1.0, "epoch": 26.2956033676333, "flow_matching_loss": 0.01356441928073764, "grad_norm": 0.08200538903474808, "invalid_tail_samples": 26.2, "learning_rate": 1.082330761803413e-06, "loss": 0.0153, "positive_teacher_pairs": 26294.4, "relation_loss": 0.001736739301122725, "selected_pairs": 26294.4, "step": 28110, "student_distance_mean": 1259.5440551757813, "teacher_distance_mean": 0.8486299812793732, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.001736739301122725, "weighted_relation_loss": 0.001736739301122725 }, { "action_query_batch_std": 22.111034774780272, "action_query_norm": 936.7121032714844, "action_relation_loss": 0.0016724006738513709, "auxiliary_loss_weight": 1.0, "epoch": 26.304957904583723, "flow_matching_loss": 0.013278836850076914, "grad_norm": 0.09718681871891022, "invalid_tail_samples": 23.3, "learning_rate": 1.0709547837263966e-06, "loss": 0.015, "positive_teacher_pairs": 26966.2, "relation_loss": 0.0016724006738513709, "selected_pairs": 26966.2, "step": 28120, "student_distance_mean": 1270.572119140625, "teacher_distance_mean": 0.8568882942199707, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0016724006738513709, "weighted_relation_loss": 0.0016724006738513709 }, { "action_query_batch_std": 22.04680061340332, "action_query_norm": 934.7401000976563, "action_relation_loss": 0.0017643000464886427, "auxiliary_loss_weight": 1.0, "epoch": 26.314312441534145, "flow_matching_loss": 0.014259573072195053, "grad_norm": 0.07502679526805878, "invalid_tail_samples": 23.0, "learning_rate": 1.059638259053025e-06, "loss": 0.016, "positive_teacher_pairs": 27038.1, "relation_loss": 0.0017643000464886427, "selected_pairs": 27038.1, "step": 28130, "student_distance_mean": 1268.5383178710938, "teacher_distance_mean": 0.8557204842567444, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0017643000464886427, "weighted_relation_loss": 0.0017643000464886427 }, { "action_query_batch_std": 22.22454204559326, "action_query_norm": 937.7334045410156, "action_relation_loss": 0.001755807874724269, "auxiliary_loss_weight": 1.0, "epoch": 26.323666978484564, "flow_matching_loss": 0.013926723040640354, "grad_norm": 0.09171310812234879, "invalid_tail_samples": 23.9, "learning_rate": 1.0483812015339434e-06, "loss": 0.0157, "positive_teacher_pairs": 26833.2, "relation_loss": 0.001755807874724269, "selected_pairs": 26833.2, "step": 28140, "student_distance_mean": 1273.9900146484374, "teacher_distance_mean": 0.8598420321941376, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.001755807874724269, "weighted_relation_loss": 0.001755807874724269 }, { "action_query_batch_std": 21.855150032043458, "action_query_norm": 928.9313049316406, "action_relation_loss": 0.0017701192758977414, "auxiliary_loss_weight": 1.0, "epoch": 26.333021515434986, "flow_matching_loss": 0.013520626537501811, "grad_norm": 0.08246807754039764, "invalid_tail_samples": 22.7, "learning_rate": 1.037183624847543e-06, "loss": 0.0153, "positive_teacher_pairs": 27104.8, "relation_loss": 0.0017701192758977414, "selected_pairs": 27104.8, "step": 28150, "student_distance_mean": 1257.4037475585938, "teacher_distance_mean": 0.8492944478988648, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0017701192758977414, "weighted_relation_loss": 0.0017701192758977414 }, { "action_query_batch_std": 22.068871688842773, "action_query_norm": 935.0831237792969, "action_relation_loss": 0.0017474299645982682, "auxiliary_loss_weight": 1.0, "epoch": 26.342376052385408, "flow_matching_loss": 0.01446393234655261, "grad_norm": 0.0931159108877182, "invalid_tail_samples": 23.4, "learning_rate": 1.0260455425999238e-06, "loss": 0.0162, "positive_teacher_pairs": 26944.4, "relation_loss": 0.0017474299645982682, "selected_pairs": 26944.4, "step": 28160, "student_distance_mean": 1269.0766357421876, "teacher_distance_mean": 0.8561046659946442, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0017474299645982682, "weighted_relation_loss": 0.0017474299645982682 }, { "action_query_batch_std": 21.927839851379396, "action_query_norm": 928.078076171875, "action_relation_loss": 0.0016948775271885097, "auxiliary_loss_weight": 1.0, "epoch": 26.351730589335826, "flow_matching_loss": 0.013919076044112444, "grad_norm": 0.10148085653781891, "invalid_tail_samples": 22.7, "learning_rate": 1.0149669683249208e-06, "loss": 0.0156, "positive_teacher_pairs": 27103.4, "relation_loss": 0.0016948775271885097, "selected_pairs": 27103.4, "step": 28170, "student_distance_mean": 1259.225927734375, "teacher_distance_mean": 0.8499638974666596, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0016948775271885097, "weighted_relation_loss": 0.0016948775271885097 }, { "action_query_batch_std": 21.826562881469727, "action_query_norm": 924.8061218261719, "action_relation_loss": 0.0017692892928607763, "auxiliary_loss_weight": 1.0, "epoch": 26.36108512628625, "flow_matching_loss": 0.012980389688163996, "grad_norm": 0.07191100716590881, "invalid_tail_samples": 24.0, "learning_rate": 1.003947915484027e-06, "loss": 0.0147, "positive_teacher_pairs": 26802.4, "relation_loss": 0.0017692892928607763, "selected_pairs": 26802.4, "step": 28180, "student_distance_mean": 1254.3049072265626, "teacher_distance_mean": 0.8469112753868103, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0017692892928607763, "weighted_relation_loss": 0.0017692892928607763 }, { "action_query_batch_std": 21.920362663269042, "action_query_norm": 931.2502868652343, "action_relation_loss": 0.001754000666551292, "auxiliary_loss_weight": 1.0, "epoch": 26.37043966323667, "flow_matching_loss": 0.014209140930324793, "grad_norm": 0.09835370630025864, "invalid_tail_samples": 22.9, "learning_rate": 9.92988397466449e-07, "loss": 0.016, "positive_teacher_pairs": 27061.0, "relation_loss": 0.001754000666551292, "selected_pairs": 27061.0, "step": 28190, "student_distance_mean": 1263.7870361328125, "teacher_distance_mean": 0.8543682515621185, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.001754000666551292, "weighted_relation_loss": 0.001754000666551292 }, { "action_query_batch_std": 21.826428413391113, "action_query_norm": 924.8939025878906, "action_relation_loss": 0.0017396723851561546, "auxiliary_loss_weight": 1.0, "epoch": 26.379794200187092, "flow_matching_loss": 0.01432113004848361, "grad_norm": 0.08928351104259491, "invalid_tail_samples": 26.2, "learning_rate": 9.820884275890286e-07, "loss": 0.0161, "positive_teacher_pairs": 26301.3, "relation_loss": 0.0017396723851561546, "selected_pairs": 26301.3, "step": 28200, "student_distance_mean": 1257.088134765625, "teacher_distance_mean": 0.8480534613132477, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.0017396723851561546, "weighted_relation_loss": 0.0017396723851561546 }, { "action_query_batch_std": 22.183051681518556, "action_query_norm": 937.0984130859375, "action_relation_loss": 0.001803249097429216, "auxiliary_loss_weight": 1.0, "epoch": 26.38914873713751, "flow_matching_loss": 0.016464320942759514, "grad_norm": 0.07529358565807343, "invalid_tail_samples": 23.4, "learning_rate": 9.712480190962546e-07, "loss": 0.0183, "positive_teacher_pairs": 26941.7, "relation_loss": 0.001803249097429216, "selected_pairs": 26941.7, "step": 28210, "student_distance_mean": 1272.7899047851563, "teacher_distance_mean": 0.8588350296020508, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.001803249097429216, "weighted_relation_loss": 0.001803249097429216 }, { "action_query_batch_std": 21.81907501220703, "action_query_norm": 925.2806091308594, "action_relation_loss": 0.00177132812095806, "auxiliary_loss_weight": 1.0, "epoch": 26.398503274087933, "flow_matching_loss": 0.014469965267926455, "grad_norm": 0.11320450156927109, "invalid_tail_samples": 25.6, "learning_rate": 9.604671851602464e-07, "loss": 0.0162, "positive_teacher_pairs": 26439.2, "relation_loss": 0.00177132812095806, "selected_pairs": 26439.2, "step": 28220, "student_distance_mean": 1256.8671020507813, "teacher_distance_mean": 0.8485673666000366, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.00177132812095806, "weighted_relation_loss": 0.00177132812095806 }, { "action_query_batch_std": 22.349852752685546, "action_query_norm": 945.3798217773438, "action_relation_loss": 0.0017195884021930397, "auxiliary_loss_weight": 1.0, "epoch": 26.407857811038355, "flow_matching_loss": 0.013187674060463905, "grad_norm": 0.08137933909893036, "invalid_tail_samples": 24.2, "learning_rate": 9.497459388807306e-07, "loss": 0.0149, "positive_teacher_pairs": 26755.4, "relation_loss": 0.0017195884021930397, "selected_pairs": 26755.4, "step": 28230, "student_distance_mean": 1286.5756103515625, "teacher_distance_mean": 0.8681500256061554, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0017195884021930397, "weighted_relation_loss": 0.0017195884021930397 }, { "action_query_batch_std": 22.229493713378908, "action_query_norm": 937.7018188476562, "action_relation_loss": 0.0017013388453051448, "auxiliary_loss_weight": 1.0, "epoch": 26.417212347988773, "flow_matching_loss": 0.014866517670452595, "grad_norm": 0.06950823217630386, "invalid_tail_samples": 23.3, "learning_rate": 9.390842932850364e-07, "loss": 0.0166, "positive_teacher_pairs": 26965.5, "relation_loss": 0.0017013388453051448, "selected_pairs": 26965.5, "step": 28240, "student_distance_mean": 1272.0695678710938, "teacher_distance_mean": 0.8591656625270844, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0017013388453051448, "weighted_relation_loss": 0.0017013388453051448 }, { "action_query_batch_std": 22.091140937805175, "action_query_norm": 935.5204467773438, "action_relation_loss": 0.0017782107344828546, "auxiliary_loss_weight": 1.0, "epoch": 26.426566884939195, "flow_matching_loss": 0.013600124698132276, "grad_norm": 0.08491780608892441, "invalid_tail_samples": 24.2, "learning_rate": 9.28482261328073e-07, "loss": 0.0154, "positive_teacher_pairs": 26763.9, "relation_loss": 0.0017782107344828546, "selected_pairs": 26763.9, "step": 28250, "student_distance_mean": 1272.0508911132813, "teacher_distance_mean": 0.8579949617385865, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0017782107344828546, "weighted_relation_loss": 0.0017782107344828546 }, { "action_query_batch_std": 22.0751895904541, "action_query_norm": 936.9464965820313, "action_relation_loss": 0.0017381883109919727, "auxiliary_loss_weight": 1.0, "epoch": 26.435921421889617, "flow_matching_loss": 0.014781868271529674, "grad_norm": 0.08141031861305237, "invalid_tail_samples": 24.9, "learning_rate": 9.179398558923025e-07, "loss": 0.0165, "positive_teacher_pairs": 26596.3, "relation_loss": 0.0017381883109919727, "selected_pairs": 26596.3, "step": 28260, "student_distance_mean": 1273.379150390625, "teacher_distance_mean": 0.8584149181842804, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0017381883109919727, "weighted_relation_loss": 0.0017381883109919727 }, { "action_query_batch_std": 21.834735488891603, "action_query_norm": 925.1118408203125, "action_relation_loss": 0.0017728778766468167, "auxiliary_loss_weight": 1.0, "epoch": 26.44527595884004, "flow_matching_loss": 0.014955113176256418, "grad_norm": 0.07377288490533829, "invalid_tail_samples": 23.9, "learning_rate": 9.074570897877388e-07, "loss": 0.0167, "positive_teacher_pairs": 26827.6, "relation_loss": 0.0017728778766468167, "selected_pairs": 26827.6, "step": 28270, "student_distance_mean": 1255.5128051757813, "teacher_distance_mean": 0.8475736498832702, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0017728778766468167, "weighted_relation_loss": 0.0017728778766468167 }, { "action_query_batch_std": 22.1002405166626, "action_query_norm": 933.7845764160156, "action_relation_loss": 0.0017460821545682847, "auxiliary_loss_weight": 1.0, "epoch": 26.454630495790457, "flow_matching_loss": 0.014412230625748635, "grad_norm": 0.0876106321811676, "invalid_tail_samples": 25.5, "learning_rate": 8.970339757519375e-07, "loss": 0.0162, "positive_teacher_pairs": 26453.5, "relation_loss": 0.0017460821545682847, "selected_pairs": 26453.5, "step": 28280, "student_distance_mean": 1269.218896484375, "teacher_distance_mean": 0.8563388228416443, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0017460821545682847, "weighted_relation_loss": 0.0017460821545682847 }, { "action_query_batch_std": 21.949305915832518, "action_query_norm": 930.4407592773438, "action_relation_loss": 0.0017218048684298991, "auxiliary_loss_weight": 1.0, "epoch": 26.46398503274088, "flow_matching_loss": 0.013869933132082225, "grad_norm": 0.06637308746576309, "invalid_tail_samples": 21.7, "learning_rate": 8.866705264499619e-07, "loss": 0.0156, "positive_teacher_pairs": 27339.7, "relation_loss": 0.0017218048684298991, "selected_pairs": 27339.7, "step": 28290, "student_distance_mean": 1263.9141479492187, "teacher_distance_mean": 0.8530316948890686, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.0017218048684298991, "weighted_relation_loss": 0.0017218048684298991 }, { "action_query_batch_std": 22.189781951904298, "action_query_norm": 936.23974609375, "action_relation_loss": 0.001717081794049591, "auxiliary_loss_weight": 1.0, "epoch": 26.4733395696913, "flow_matching_loss": 0.014804766047745943, "grad_norm": 0.08491020649671555, "invalid_tail_samples": 23.6, "learning_rate": 8.763667544743836e-07, "loss": 0.0165, "positive_teacher_pairs": 26894.4, "relation_loss": 0.001717081794049591, "selected_pairs": 26894.4, "step": 28300, "student_distance_mean": 1270.1611206054688, "teacher_distance_mean": 0.8569600880146027, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.001717081794049591, "weighted_relation_loss": 0.001717081794049591 }, { "action_query_batch_std": 21.968427658081055, "action_query_norm": 929.4067504882812, "action_relation_loss": 0.001742037502117455, "auxiliary_loss_weight": 1.0, "epoch": 26.48269410664172, "flow_matching_loss": 0.016604742035269737, "grad_norm": 0.09730804711580276, "invalid_tail_samples": 22.8, "learning_rate": 8.661226723452543e-07, "loss": 0.0183, "positive_teacher_pairs": 27079.4, "relation_loss": 0.001742037502117455, "selected_pairs": 27079.4, "step": 28310, "student_distance_mean": 1259.999072265625, "teacher_distance_mean": 0.8499829590320587, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.001742037502117455, "weighted_relation_loss": 0.001742037502117455 }, { "action_query_batch_std": 21.957876014709473, "action_query_norm": 931.8934020996094, "action_relation_loss": 0.0017448694794438778, "auxiliary_loss_weight": 1.0, "epoch": 26.492048643592142, "flow_matching_loss": 0.014662677701562644, "grad_norm": 0.10085617750883102, "invalid_tail_samples": 25.0, "learning_rate": 8.559382925101001e-07, "loss": 0.0164, "positive_teacher_pairs": 26578.0, "relation_loss": 0.0017448694794438778, "selected_pairs": 26578.0, "step": 28320, "student_distance_mean": 1262.2897338867188, "teacher_distance_mean": 0.8517216801643371, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0017448694794438778, "weighted_relation_loss": 0.0017448694794438778 }, { "action_query_batch_std": 22.067710876464844, "action_query_norm": 935.2189270019531, "action_relation_loss": 0.0018186901463195682, "auxiliary_loss_weight": 1.0, "epoch": 26.501403180542564, "flow_matching_loss": 0.013901229482144117, "grad_norm": 0.09581685811281204, "invalid_tail_samples": 21.0, "learning_rate": 8.458136273438943e-07, "loss": 0.0157, "positive_teacher_pairs": 27505.6, "relation_loss": 0.0018186901463195682, "selected_pairs": 27505.6, "step": 28330, "student_distance_mean": 1269.7802124023438, "teacher_distance_mean": 0.8562718331813812, "valid_action_samples": 235.0, "weighted_auxiliary_loss": 0.0018186901463195682, "weighted_relation_loss": 0.0018186901463195682 }, { "action_query_batch_std": 22.054762077331542, "action_query_norm": 932.2026123046875, "action_relation_loss": 0.0017280733212828637, "auxiliary_loss_weight": 1.0, "epoch": 26.510757717492986, "flow_matching_loss": 0.014610279444605112, "grad_norm": 0.0693918839097023, "invalid_tail_samples": 24.6, "learning_rate": 8.357486891490795e-07, "loss": 0.0163, "positive_teacher_pairs": 26677.5, "relation_loss": 0.0017280733212828637, "selected_pairs": 26677.5, "step": 28340, "student_distance_mean": 1265.8352783203125, "teacher_distance_mean": 0.8554877758026123, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0017280733212828637, "weighted_relation_loss": 0.0017280733212828637 }, { "action_query_batch_std": 21.821931076049804, "action_query_norm": 922.6934814453125, "action_relation_loss": 0.0018027548678219319, "auxiliary_loss_weight": 1.0, "epoch": 26.520112254443404, "flow_matching_loss": 0.014012675639241934, "grad_norm": 0.08678964525461197, "invalid_tail_samples": 26.6, "learning_rate": 8.257434901554895e-07, "loss": 0.0158, "positive_teacher_pairs": 26203.8, "relation_loss": 0.0018027548678219319, "selected_pairs": 26203.8, "step": 28350, "student_distance_mean": 1255.6241577148437, "teacher_distance_mean": 0.8471720695495606, "valid_action_samples": 229.4, "weighted_auxiliary_loss": 0.0018027548678219319, "weighted_relation_loss": 0.0018027548678219319 }, { "action_query_batch_std": 22.389207458496095, "action_query_norm": 946.6212585449218, "action_relation_loss": 0.0017406379920430481, "auxiliary_loss_weight": 1.0, "epoch": 26.529466791393826, "flow_matching_loss": 0.015105514880269766, "grad_norm": 0.1087772324681282, "invalid_tail_samples": 19.7, "learning_rate": 8.157980425203937e-07, "loss": 0.0168, "positive_teacher_pairs": 27811.4, "relation_loss": 0.0017406379920430481, "selected_pairs": 27811.4, "step": 28360, "student_distance_mean": 1283.9909790039062, "teacher_distance_mean": 0.8673199236392974, "valid_action_samples": 236.3, "weighted_auxiliary_loss": 0.0017406379920430481, "weighted_relation_loss": 0.0017406379920430481 }, { "action_query_batch_std": 22.003735160827638, "action_query_norm": 932.1245666503906, "action_relation_loss": 0.0017480513895861804, "auxiliary_loss_weight": 1.0, "epoch": 26.53882132834425, "flow_matching_loss": 0.014802244491875172, "grad_norm": 0.08444834500551224, "invalid_tail_samples": 23.4, "learning_rate": 8.059123583284367e-07, "loss": 0.0166, "positive_teacher_pairs": 26949.1, "relation_loss": 0.0017480513895861804, "selected_pairs": 26949.1, "step": 28370, "student_distance_mean": 1264.5114868164062, "teacher_distance_mean": 0.855192244052887, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0017480513895861804, "weighted_relation_loss": 0.0017480513895861804 }, { "action_query_batch_std": 21.990195655822752, "action_query_norm": 930.297900390625, "action_relation_loss": 0.0017555001424625516, "auxiliary_loss_weight": 1.0, "epoch": 26.548175865294667, "flow_matching_loss": 0.017006028909236193, "grad_norm": 0.08782338351011276, "invalid_tail_samples": 24.2, "learning_rate": 7.960864495916654e-07, "loss": 0.0188, "positive_teacher_pairs": 26763.2, "relation_loss": 0.0017555001424625516, "selected_pairs": 26763.2, "step": 28380, "student_distance_mean": 1267.3469970703125, "teacher_distance_mean": 0.8548388957977295, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0017555001424625516, "weighted_relation_loss": 0.0017555001424625516 }, { "action_query_batch_std": 21.973613739013672, "action_query_norm": 930.9300537109375, "action_relation_loss": 0.0017395791248418391, "auxiliary_loss_weight": 1.0, "epoch": 26.55753040224509, "flow_matching_loss": 0.01273983558639884, "grad_norm": 0.0787339136004448, "invalid_tail_samples": 24.2, "learning_rate": 7.863203282494847e-07, "loss": 0.0145, "positive_teacher_pairs": 26762.7, "relation_loss": 0.0017395791248418391, "selected_pairs": 26762.7, "step": 28390, "student_distance_mean": 1260.0770874023438, "teacher_distance_mean": 0.8504279732704163, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0017395791248418391, "weighted_relation_loss": 0.0017395791248418391 }, { "action_query_batch_std": 22.10638599395752, "action_query_norm": 934.6028625488282, "action_relation_loss": 0.0017389524495229126, "auxiliary_loss_weight": 1.0, "epoch": 26.56688493919551, "flow_matching_loss": 0.016151142958551645, "grad_norm": 0.08748574554920197, "invalid_tail_samples": 23.0, "learning_rate": 7.766140061686522e-07, "loss": 0.0179, "positive_teacher_pairs": 27036.6, "relation_loss": 0.0017389524495229126, "selected_pairs": 27036.6, "step": 28400, "student_distance_mean": 1266.7311279296875, "teacher_distance_mean": 0.8548456370830536, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0017389524495229126, "weighted_relation_loss": 0.0017389524495229126 }, { "action_query_batch_std": 22.049454307556154, "action_query_norm": 934.2513305664063, "action_relation_loss": 0.0016846227925270795, "auxiliary_loss_weight": 1.0, "epoch": 26.57623947614593, "flow_matching_loss": 0.015786763094365597, "grad_norm": 0.08685217797756195, "invalid_tail_samples": 23.4, "learning_rate": 7.669674951432615e-07, "loss": 0.0175, "positive_teacher_pairs": 26948.5, "relation_loss": 0.0016846227925270795, "selected_pairs": 26948.5, "step": 28410, "student_distance_mean": 1271.9754760742187, "teacher_distance_mean": 0.8581543505191803, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0016846227925270795, "weighted_relation_loss": 0.0016846227925270795 }, { "action_query_batch_std": 21.995772743225096, "action_query_norm": 932.7986083984375, "action_relation_loss": 0.001738746534101665, "auxiliary_loss_weight": 1.0, "epoch": 26.58559401309635, "flow_matching_loss": 0.013999431114643811, "grad_norm": 0.08425811678171158, "invalid_tail_samples": 23.7, "learning_rate": 7.573808068947363e-07, "loss": 0.0157, "positive_teacher_pairs": 26869.9, "relation_loss": 0.001738746534101665, "selected_pairs": 26869.9, "step": 28420, "student_distance_mean": 1269.6142211914062, "teacher_distance_mean": 0.8575934290885925, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.001738746534101665, "weighted_relation_loss": 0.001738746534101665 }, { "action_query_batch_std": 21.925975036621093, "action_query_norm": 930.1608825683594, "action_relation_loss": 0.0017694690730422735, "auxiliary_loss_weight": 1.0, "epoch": 26.594948550046773, "flow_matching_loss": 0.016057191789150237, "grad_norm": 0.09596932679414749, "invalid_tail_samples": 23.7, "learning_rate": 7.478539530718087e-07, "loss": 0.0178, "positive_teacher_pairs": 26874.9, "relation_loss": 0.0017694690730422735, "selected_pairs": 26874.9, "step": 28430, "student_distance_mean": 1259.3025146484374, "teacher_distance_mean": 0.850175416469574, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0017694690730422735, "weighted_relation_loss": 0.0017694690730422735 }, { "action_query_batch_std": 22.19678020477295, "action_query_norm": 939.2386413574219, "action_relation_loss": 0.001742966752499342, "auxiliary_loss_weight": 1.0, "epoch": 26.604303086997195, "flow_matching_loss": 0.015498829912394286, "grad_norm": 0.07117843627929688, "invalid_tail_samples": 25.1, "learning_rate": 7.383869452504965e-07, "loss": 0.0172, "positive_teacher_pairs": 26556.0, "relation_loss": 0.001742966752499342, "selected_pairs": 26556.0, "step": 28440, "student_distance_mean": 1275.512646484375, "teacher_distance_mean": 0.8607399702072144, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.001742966752499342, "weighted_relation_loss": 0.001742966752499342 }, { "action_query_batch_std": 21.949707984924316, "action_query_norm": 929.6269287109375, "action_relation_loss": 0.0017046713386662305, "auxiliary_loss_weight": 1.0, "epoch": 26.613657623947613, "flow_matching_loss": 0.014310219138860703, "grad_norm": 0.07718439400196075, "invalid_tail_samples": 24.0, "learning_rate": 7.289797949341204e-07, "loss": 0.016, "positive_teacher_pairs": 26809.8, "relation_loss": 0.0017046713386662305, "selected_pairs": 26809.8, "step": 28450, "student_distance_mean": 1262.5762084960938, "teacher_distance_mean": 0.8531899094581604, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0017046713386662305, "weighted_relation_loss": 0.0017046713386662305 }, { "action_query_batch_std": 21.990625, "action_query_norm": 930.6033264160156, "action_relation_loss": 0.0017070923815481365, "auxiliary_loss_weight": 1.0, "epoch": 26.623012160898035, "flow_matching_loss": 0.013691087439656257, "grad_norm": 0.09567002952098846, "invalid_tail_samples": 23.0, "learning_rate": 7.196325135532423e-07, "loss": 0.0154, "positive_teacher_pairs": 27050.9, "relation_loss": 0.0017070923815481365, "selected_pairs": 27050.9, "step": 28460, "student_distance_mean": 1267.332470703125, "teacher_distance_mean": 0.8555469512939453, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0017070923815481365, "weighted_relation_loss": 0.0017070923815481365 }, { "action_query_batch_std": 21.800903511047363, "action_query_norm": 924.5756530761719, "action_relation_loss": 0.0017551174969412386, "auxiliary_loss_weight": 1.0, "epoch": 26.632366697848457, "flow_matching_loss": 0.016055432613939047, "grad_norm": 0.09602320939302444, "invalid_tail_samples": 25.1, "learning_rate": 7.10345112465699e-07, "loss": 0.0178, "positive_teacher_pairs": 26548.4, "relation_loss": 0.0017551174969412386, "selected_pairs": 26548.4, "step": 28470, "student_distance_mean": 1255.946630859375, "teacher_distance_mean": 0.8468271970748902, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0017551174969412386, "weighted_relation_loss": 0.0017551174969412386 }, { "action_query_batch_std": 22.064410400390624, "action_query_norm": 932.795751953125, "action_relation_loss": 0.00181916116271168, "auxiliary_loss_weight": 1.0, "epoch": 26.641721234798876, "flow_matching_loss": 0.015221171826124192, "grad_norm": 0.0743211954832077, "invalid_tail_samples": 23.5, "learning_rate": 7.011176029565525e-07, "loss": 0.017, "positive_teacher_pairs": 26919.3, "relation_loss": 0.00181916116271168, "selected_pairs": 26919.3, "step": 28480, "student_distance_mean": 1266.2048461914062, "teacher_distance_mean": 0.8534184396266937, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.00181916116271168, "weighted_relation_loss": 0.00181916116271168 }, { "action_query_batch_std": 21.81975326538086, "action_query_norm": 927.5097717285156, "action_relation_loss": 0.0017250499222427607, "auxiliary_loss_weight": 1.0, "epoch": 26.651075771749298, "flow_matching_loss": 0.012995591945946216, "grad_norm": 0.09882580488920212, "invalid_tail_samples": 23.8, "learning_rate": 6.919499962381004e-07, "loss": 0.0147, "positive_teacher_pairs": 26856.5, "relation_loss": 0.0017250499222427607, "selected_pairs": 26856.5, "step": 28490, "student_distance_mean": 1256.3405395507812, "teacher_distance_mean": 0.8486289858818055, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0017250499222427607, "weighted_relation_loss": 0.0017250499222427607 }, { "action_query_batch_std": 21.817020988464357, "action_query_norm": 928.2533081054687, "action_relation_loss": 0.0016946792602539062, "auxiliary_loss_weight": 1.0, "epoch": 26.66043030869972, "flow_matching_loss": 0.015353055763989687, "grad_norm": 0.09546934813261032, "invalid_tail_samples": 25.7, "learning_rate": 6.828423034498488e-07, "loss": 0.017, "positive_teacher_pairs": 26417.8, "relation_loss": 0.0016946792602539062, "selected_pairs": 26417.8, "step": 28500, "student_distance_mean": 1256.5147705078125, "teacher_distance_mean": 0.8477632701396942, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.0016946792602539062, "weighted_relation_loss": 0.0016946792602539062 }, { "action_query_batch_std": 22.00230255126953, "action_query_norm": 931.2010803222656, "action_relation_loss": 0.0017251637880690395, "auxiliary_loss_weight": 1.0, "epoch": 26.669784845650142, "flow_matching_loss": 0.014875272568315268, "grad_norm": 0.07710343599319458, "invalid_tail_samples": 24.3, "learning_rate": 6.737945356585007e-07, "loss": 0.0166, "positive_teacher_pairs": 26731.4, "relation_loss": 0.0017251637880690395, "selected_pairs": 26731.4, "step": 28510, "student_distance_mean": 1268.4050048828126, "teacher_distance_mean": 0.8567954659461975, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0017251637880690395, "weighted_relation_loss": 0.0017251637880690395 }, { "action_query_batch_std": 21.883008575439455, "action_query_norm": 924.7856811523437, "action_relation_loss": 0.0017958274926058947, "auxiliary_loss_weight": 1.0, "epoch": 26.67913938260056, "flow_matching_loss": 0.015002189297229051, "grad_norm": 0.10016948729753494, "invalid_tail_samples": 26.2, "learning_rate": 6.648067038579508e-07, "loss": 0.0168, "positive_teacher_pairs": 26295.4, "relation_loss": 0.0017958274926058947, "selected_pairs": 26295.4, "step": 28520, "student_distance_mean": 1262.0040771484375, "teacher_distance_mean": 0.8512162327766418, "valid_action_samples": 229.8, "weighted_auxiliary_loss": 0.0017958274926058947, "weighted_relation_loss": 0.0017958274926058947 }, { "action_query_batch_std": 22.092893409729005, "action_query_norm": 934.9529968261719, "action_relation_loss": 0.0017223102971911431, "auxiliary_loss_weight": 1.0, "epoch": 26.688493919550982, "flow_matching_loss": 0.014616480469703675, "grad_norm": 0.09168258309364319, "invalid_tail_samples": 25.5, "learning_rate": 6.558788189692578e-07, "loss": 0.0163, "positive_teacher_pairs": 26465.6, "relation_loss": 0.0017223102971911431, "selected_pairs": 26465.6, "step": 28530, "student_distance_mean": 1270.9039794921875, "teacher_distance_mean": 0.8580532133579254, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0017223102971911431, "weighted_relation_loss": 0.0017223102971911431 }, { "action_query_batch_std": 22.18940124511719, "action_query_norm": 938.7766418457031, "action_relation_loss": 0.0018218271434307098, "auxiliary_loss_weight": 1.0, "epoch": 26.697848456501404, "flow_matching_loss": 0.016058725584298373, "grad_norm": 0.06508318334817886, "invalid_tail_samples": 23.3, "learning_rate": 6.470108918406492e-07, "loss": 0.0179, "positive_teacher_pairs": 26969.8, "relation_loss": 0.0018218271434307098, "selected_pairs": 26969.8, "step": 28540, "student_distance_mean": 1277.91630859375, "teacher_distance_mean": 0.8623511373996735, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0018218271434307098, "weighted_relation_loss": 0.0018218271434307098 }, { "action_query_batch_std": 22.051679420471192, "action_query_norm": 935.5005615234375, "action_relation_loss": 0.001770177553407848, "auxiliary_loss_weight": 1.0, "epoch": 26.707202993451823, "flow_matching_loss": 0.015156630892306566, "grad_norm": 0.08215329051017761, "invalid_tail_samples": 25.5, "learning_rate": 6.382029332474893e-07, "loss": 0.0169, "positive_teacher_pairs": 26464.8, "relation_loss": 0.001770177553407848, "selected_pairs": 26464.8, "step": 28550, "student_distance_mean": 1273.0552734375, "teacher_distance_mean": 0.8584609389305115, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.001770177553407848, "weighted_relation_loss": 0.001770177553407848 }, { "action_query_batch_std": 21.890616607666015, "action_query_norm": 929.1240966796875, "action_relation_loss": 0.0017913712770678103, "auxiliary_loss_weight": 1.0, "epoch": 26.716557530402245, "flow_matching_loss": 0.015265167411416768, "grad_norm": 0.0888749286532402, "invalid_tail_samples": 22.2, "learning_rate": 6.294549538922778e-07, "loss": 0.0171, "positive_teacher_pairs": 27220.1, "relation_loss": 0.0017913712770678103, "selected_pairs": 27220.1, "step": 28560, "student_distance_mean": 1257.8769653320312, "teacher_distance_mean": 0.850541865825653, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.0017913712770678103, "weighted_relation_loss": 0.0017913712770678103 }, { "action_query_batch_std": 21.699788665771486, "action_query_norm": 924.6985290527343, "action_relation_loss": 0.0017243270296603442, "auxiliary_loss_weight": 1.0, "epoch": 26.725912067352667, "flow_matching_loss": 0.014888664148747921, "grad_norm": 0.08919785171747208, "invalid_tail_samples": 26.3, "learning_rate": 6.207669644046344e-07, "loss": 0.0166, "positive_teacher_pairs": 26270.6, "relation_loss": 0.0017243270296603442, "selected_pairs": 26270.6, "step": 28570, "student_distance_mean": 1248.1522338867187, "teacher_distance_mean": 0.8431589782238007, "valid_action_samples": 229.7, "weighted_auxiliary_loss": 0.0017243270296603442, "weighted_relation_loss": 0.0017243270296603442 }, { "action_query_batch_std": 22.00729103088379, "action_query_norm": 932.0309265136718, "action_relation_loss": 0.001748629950452596, "auxiliary_loss_weight": 1.0, "epoch": 26.73526660430309, "flow_matching_loss": 0.014648799225687981, "grad_norm": 0.07033279538154602, "invalid_tail_samples": 25.2, "learning_rate": 6.121389753412865e-07, "loss": 0.0164, "positive_teacher_pairs": 26530.8, "relation_loss": 0.001748629950452596, "selected_pairs": 26530.8, "step": 28580, "student_distance_mean": 1272.5657470703125, "teacher_distance_mean": 0.8585484027862549, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.001748629950452596, "weighted_relation_loss": 0.001748629950452596 }, { "action_query_batch_std": 22.01999168395996, "action_query_norm": 934.9580993652344, "action_relation_loss": 0.0017174859647639095, "auxiliary_loss_weight": 1.0, "epoch": 26.744621141253507, "flow_matching_loss": 0.01507976297289133, "grad_norm": 0.06679099798202515, "invalid_tail_samples": 22.3, "learning_rate": 6.035709971860592e-07, "loss": 0.0168, "positive_teacher_pairs": 27202.7, "relation_loss": 0.0017174859647639095, "selected_pairs": 27202.7, "step": 28590, "student_distance_mean": 1268.8133544921875, "teacher_distance_mean": 0.8577908873558044, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0017174859647639095, "weighted_relation_loss": 0.0017174859647639095 }, { "action_query_batch_std": 21.63624515533447, "action_query_norm": 920.8581481933594, "action_relation_loss": 0.0017909977934323252, "auxiliary_loss_weight": 1.0, "epoch": 26.75397567820393, "flow_matching_loss": 0.014868701621890069, "grad_norm": 0.08486922830343246, "invalid_tail_samples": 25.2, "learning_rate": 5.950630403498469e-07, "loss": 0.0167, "positive_teacher_pairs": 26524.3, "relation_loss": 0.0017909977934323252, "selected_pairs": 26524.3, "step": 28600, "student_distance_mean": 1247.5503051757812, "teacher_distance_mean": 0.8417169392108917, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0017909977934323252, "weighted_relation_loss": 0.0017909977934323252 }, { "action_query_batch_std": 22.355427742004395, "action_query_norm": 944.5071105957031, "action_relation_loss": 0.0016953455051407218, "auxiliary_loss_weight": 1.0, "epoch": 26.76333021515435, "flow_matching_loss": 0.013743357267230749, "grad_norm": 0.09317535161972046, "invalid_tail_samples": 23.5, "learning_rate": 5.866151151706189e-07, "loss": 0.0154, "positive_teacher_pairs": 26920.2, "relation_loss": 0.0016953455051407218, "selected_pairs": 26920.2, "step": 28610, "student_distance_mean": 1284.3800537109375, "teacher_distance_mean": 0.8678649067878723, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.0016953455051407218, "weighted_relation_loss": 0.0016953455051407218 }, { "action_query_batch_std": 22.127802848815918, "action_query_norm": 936.2061096191406, "action_relation_loss": 0.0017345255706459283, "auxiliary_loss_weight": 1.0, "epoch": 26.77268475210477, "flow_matching_loss": 0.015054200682789088, "grad_norm": 0.08161993324756622, "invalid_tail_samples": 25.2, "learning_rate": 5.782272319134086e-07, "loss": 0.0168, "positive_teacher_pairs": 26525.9, "relation_loss": 0.0017345255706459283, "selected_pairs": 26525.9, "step": 28620, "student_distance_mean": 1274.6777221679688, "teacher_distance_mean": 0.860746318101883, "valid_action_samples": 230.8, "weighted_auxiliary_loss": 0.0017345255706459283, "weighted_relation_loss": 0.0017345255706459283 }, { "action_query_batch_std": 22.356770706176757, "action_query_norm": 944.5687072753906, "action_relation_loss": 0.0017524089897051453, "auxiliary_loss_weight": 1.0, "epoch": 26.78203928905519, "flow_matching_loss": 0.01591927921399474, "grad_norm": 0.09935256838798523, "invalid_tail_samples": 20.5, "learning_rate": 5.698994007702796e-07, "loss": 0.0177, "positive_teacher_pairs": 27614.9, "relation_loss": 0.0017524089897051453, "selected_pairs": 27614.9, "step": 28630, "student_distance_mean": 1284.8161010742188, "teacher_distance_mean": 0.865999561548233, "valid_action_samples": 235.5, "weighted_auxiliary_loss": 0.0017524089897051453, "weighted_relation_loss": 0.0017524089897051453 }, { "action_query_batch_std": 21.98647861480713, "action_query_norm": 932.305224609375, "action_relation_loss": 0.0017142278025858103, "auxiliary_loss_weight": 1.0, "epoch": 26.791393826005613, "flow_matching_loss": 0.01586419129744172, "grad_norm": 0.0778624564409256, "invalid_tail_samples": 23.2, "learning_rate": 5.616316318603321e-07, "loss": 0.0176, "positive_teacher_pairs": 26989.4, "relation_loss": 0.0017142278025858103, "selected_pairs": 26989.4, "step": 28640, "student_distance_mean": 1265.2531372070312, "teacher_distance_mean": 0.8547655522823334, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0017142278025858103, "weighted_relation_loss": 0.0017142278025858103 }, { "action_query_batch_std": 22.045440864562988, "action_query_norm": 932.0273986816406, "action_relation_loss": 0.0017301623011007905, "auxiliary_loss_weight": 1.0, "epoch": 26.800748362956035, "flow_matching_loss": 0.015026297327131033, "grad_norm": 0.09766492992639542, "invalid_tail_samples": 23.0, "learning_rate": 5.534239352296799e-07, "loss": 0.0168, "positive_teacher_pairs": 27045.7, "relation_loss": 0.0017301623011007905, "selected_pairs": 27045.7, "step": 28650, "student_distance_mean": 1268.8859375, "teacher_distance_mean": 0.8579043328762055, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0017301623011007905, "weighted_relation_loss": 0.0017301623011007905 }, { "action_query_batch_std": 22.10621585845947, "action_query_norm": 936.3283935546875, "action_relation_loss": 0.0017067439155653119, "auxiliary_loss_weight": 1.0, "epoch": 26.810102899906454, "flow_matching_loss": 0.014666600432246924, "grad_norm": 0.08666574954986572, "invalid_tail_samples": 22.8, "learning_rate": 5.452763208514621e-07, "loss": 0.0164, "positive_teacher_pairs": 27084.3, "relation_loss": 0.0017067439155653119, "selected_pairs": 27084.3, "step": 28660, "student_distance_mean": 1272.5649658203124, "teacher_distance_mean": 0.8595351696014404, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0017067439155653119, "weighted_relation_loss": 0.0017067439155653119 }, { "action_query_batch_std": 21.88460178375244, "action_query_norm": 928.412158203125, "action_relation_loss": 0.0017563701956532895, "auxiliary_loss_weight": 1.0, "epoch": 26.819457436856876, "flow_matching_loss": 0.014639397244900465, "grad_norm": 0.09032993018627167, "invalid_tail_samples": 25.7, "learning_rate": 5.371887986257873e-07, "loss": 0.0164, "positive_teacher_pairs": 26415.9, "relation_loss": 0.0017563701956532895, "selected_pairs": 26415.9, "step": 28670, "student_distance_mean": 1259.0330322265625, "teacher_distance_mean": 0.8499682664871215, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.0017563701956532895, "weighted_relation_loss": 0.0017563701956532895 }, { "action_query_batch_std": 22.18865833282471, "action_query_norm": 939.1677062988281, "action_relation_loss": 0.0017227393109351397, "auxiliary_loss_weight": 1.0, "epoch": 26.828811973807298, "flow_matching_loss": 0.014437037613242864, "grad_norm": 0.09591605514287949, "invalid_tail_samples": 23.7, "learning_rate": 5.291613783797611e-07, "loss": 0.0162, "positive_teacher_pairs": 26874.0, "relation_loss": 0.0017227393109351397, "selected_pairs": 26874.0, "step": 28680, "student_distance_mean": 1276.5769897460937, "teacher_distance_mean": 0.8619510054588317, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0017227393109351397, "weighted_relation_loss": 0.0017227393109351397 }, { "action_query_batch_std": 21.95105400085449, "action_query_norm": 929.4617797851563, "action_relation_loss": 0.0017472126754000783, "auxiliary_loss_weight": 1.0, "epoch": 26.838166510757716, "flow_matching_loss": 0.014945036172866822, "grad_norm": 0.1132126972079277, "invalid_tail_samples": 22.7, "learning_rate": 5.211940698674534e-07, "loss": 0.0167, "positive_teacher_pairs": 27107.9, "relation_loss": 0.0017472126754000783, "selected_pairs": 27107.9, "step": 28690, "student_distance_mean": 1268.7015258789063, "teacher_distance_mean": 0.8573776960372925, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0017472126754000783, "weighted_relation_loss": 0.0017472126754000783 }, { "action_query_batch_std": 22.151080703735353, "action_query_norm": 938.5216918945313, "action_relation_loss": 0.0017275823163799941, "auxiliary_loss_weight": 1.0, "epoch": 26.84752104770814, "flow_matching_loss": 0.015219480264931917, "grad_norm": 0.06992719322443008, "invalid_tail_samples": 20.5, "learning_rate": 5.132868827698978e-07, "loss": 0.0169, "positive_teacher_pairs": 27614.3, "relation_loss": 0.0017275823163799941, "selected_pairs": 27614.3, "step": 28700, "student_distance_mean": 1274.4787963867188, "teacher_distance_mean": 0.8616655707359314, "valid_action_samples": 235.5, "weighted_auxiliary_loss": 0.0017275823163799941, "weighted_relation_loss": 0.0017275823163799941 }, { "action_query_batch_std": 21.892973327636717, "action_query_norm": 928.9809204101563, "action_relation_loss": 0.0017524102120660245, "auxiliary_loss_weight": 1.0, "epoch": 26.85687558465856, "flow_matching_loss": 0.015681121684610843, "grad_norm": 0.09192954748868942, "invalid_tail_samples": 23.3, "learning_rate": 5.054398266950755e-07, "loss": 0.0174, "positive_teacher_pairs": 26969.0, "relation_loss": 0.0017524102120660245, "selected_pairs": 26969.0, "step": 28710, "student_distance_mean": 1262.6282592773437, "teacher_distance_mean": 0.8527831256389617, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0017524102120660245, "weighted_relation_loss": 0.0017524102120660245 }, { "action_query_batch_std": 21.996470642089843, "action_query_norm": 931.72353515625, "action_relation_loss": 0.001719200238585472, "auxiliary_loss_weight": 1.0, "epoch": 26.86623012160898, "flow_matching_loss": 0.0162790697067976, "grad_norm": 0.07581213861703873, "invalid_tail_samples": 21.6, "learning_rate": 4.976529111778872e-07, "loss": 0.018, "positive_teacher_pairs": 27363.5, "relation_loss": 0.001719200238585472, "selected_pairs": 27363.5, "step": 28720, "student_distance_mean": 1264.6417114257813, "teacher_distance_mean": 0.8525619328022003, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.001719200238585472, "weighted_relation_loss": 0.001719200238585472 }, { "action_query_batch_std": 21.959973526000976, "action_query_norm": 932.2363220214844, "action_relation_loss": 0.0017099970602430404, "auxiliary_loss_weight": 1.0, "epoch": 26.8755846585594, "flow_matching_loss": 0.01460346495732665, "grad_norm": 0.08190636336803436, "invalid_tail_samples": 22.4, "learning_rate": 4.899261456801862e-07, "loss": 0.0163, "positive_teacher_pairs": 27175.2, "relation_loss": 0.0017099970602430404, "selected_pairs": 27175.2, "step": 28730, "student_distance_mean": 1265.5051391601562, "teacher_distance_mean": 0.8545255720615387, "valid_action_samples": 233.6, "weighted_auxiliary_loss": 0.0017099970602430404, "weighted_relation_loss": 0.0017099970602430404 }, { "action_query_batch_std": 22.012094688415527, "action_query_norm": 931.3703796386719, "action_relation_loss": 0.0017537988955155016, "auxiliary_loss_weight": 1.0, "epoch": 26.884939195509823, "flow_matching_loss": 0.01471982691437006, "grad_norm": 0.09222865849733353, "invalid_tail_samples": 24.9, "learning_rate": 4.822595395907126e-07, "loss": 0.0165, "positive_teacher_pairs": 26594.9, "relation_loss": 0.0017537988955155016, "selected_pairs": 26594.9, "step": 28740, "student_distance_mean": 1266.7915771484375, "teacher_distance_mean": 0.8541071772575378, "valid_action_samples": 231.1, "weighted_auxiliary_loss": 0.0017537988955155016, "weighted_relation_loss": 0.0017537988955155016 }, { "action_query_batch_std": 22.03380584716797, "action_query_norm": 934.2581359863282, "action_relation_loss": 0.00177396823419258, "auxiliary_loss_weight": 1.0, "epoch": 26.894293732460245, "flow_matching_loss": 0.014280693139880896, "grad_norm": 0.08930162340402603, "invalid_tail_samples": 21.7, "learning_rate": 4.7465310222510886e-07, "loss": 0.0161, "positive_teacher_pairs": 27334.8, "relation_loss": 0.00177396823419258, "selected_pairs": 27334.8, "step": 28750, "student_distance_mean": 1266.8563110351563, "teacher_distance_mean": 0.8548985064029694, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.00177396823419258, "weighted_relation_loss": 0.00177396823419258 }, { "action_query_batch_std": 21.980736923217773, "action_query_norm": 932.9650024414062, "action_relation_loss": 0.001735357823781669, "auxiliary_loss_weight": 1.0, "epoch": 26.903648269410663, "flow_matching_loss": 0.015186154842376709, "grad_norm": 0.08389348536729813, "invalid_tail_samples": 23.4, "learning_rate": 4.6710684282593175e-07, "loss": 0.0169, "positive_teacher_pairs": 26942.0, "relation_loss": 0.001735357823781669, "selected_pairs": 26942.0, "step": 28760, "student_distance_mean": 1266.1421142578124, "teacher_distance_mean": 0.8537512123584747, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.001735357823781669, "weighted_relation_loss": 0.001735357823781669 }, { "action_query_batch_std": 21.791565704345704, "action_query_norm": 923.7768981933593, "action_relation_loss": 0.0017535691382363438, "auxiliary_loss_weight": 1.0, "epoch": 26.913002806361085, "flow_matching_loss": 0.014454603753983974, "grad_norm": 0.10470130294561386, "invalid_tail_samples": 24.6, "learning_rate": 4.5962077056257993e-07, "loss": 0.0162, "positive_teacher_pairs": 26663.3, "relation_loss": 0.0017535691382363438, "selected_pairs": 26663.3, "step": 28770, "student_distance_mean": 1256.4267944335938, "teacher_distance_mean": 0.84829261302948, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0017535691382363438, "weighted_relation_loss": 0.0017535691382363438 }, { "action_query_batch_std": 22.016214752197264, "action_query_norm": 932.9101623535156, "action_relation_loss": 0.0017564750974997877, "auxiliary_loss_weight": 1.0, "epoch": 26.922357343311507, "flow_matching_loss": 0.013842362817376852, "grad_norm": 0.08747130632400513, "invalid_tail_samples": 23.6, "learning_rate": 4.521948945313492e-07, "loss": 0.0156, "positive_teacher_pairs": 26896.0, "relation_loss": 0.0017564750974997877, "selected_pairs": 26896.0, "step": 28780, "student_distance_mean": 1269.4099975585937, "teacher_distance_mean": 0.85729221701622, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0017564750974997877, "weighted_relation_loss": 0.0017564750974997877 }, { "action_query_batch_std": 21.965213584899903, "action_query_norm": 929.2748229980468, "action_relation_loss": 0.0017190742772072553, "auxiliary_loss_weight": 1.0, "epoch": 26.931711880261926, "flow_matching_loss": 0.015510042943060399, "grad_norm": 0.07765968143939972, "invalid_tail_samples": 28.2, "learning_rate": 4.4482922375537195e-07, "loss": 0.0172, "positive_teacher_pairs": 25845.2, "relation_loss": 0.0017190742772072553, "selected_pairs": 25845.2, "step": 28790, "student_distance_mean": 1264.7520385742187, "teacher_distance_mean": 0.8534460604190827, "valid_action_samples": 227.8, "weighted_auxiliary_loss": 0.0017190742772072553, "weighted_relation_loss": 0.0017190742772072553 }, { "action_query_batch_std": 22.11687889099121, "action_query_norm": 936.6803100585937, "action_relation_loss": 0.0017153894528746604, "auxiliary_loss_weight": 1.0, "epoch": 26.941066417212348, "flow_matching_loss": 0.01467419546097517, "grad_norm": 0.08858143538236618, "invalid_tail_samples": 25.9, "learning_rate": 4.375237671846333e-07, "loss": 0.0164, "positive_teacher_pairs": 26368.6, "relation_loss": 0.0017153894528746604, "selected_pairs": 26368.6, "step": 28800, "student_distance_mean": 1271.7005737304687, "teacher_distance_mean": 0.8573513150215148, "valid_action_samples": 230.1, "weighted_auxiliary_loss": 0.0017153894528746604, "weighted_relation_loss": 0.0017153894528746604 }, { "action_query_batch_std": 21.786696243286134, "action_query_norm": 924.913916015625, "action_relation_loss": 0.0017573078512214124, "auxiliary_loss_weight": 1.0, "epoch": 26.95042095416277, "flow_matching_loss": 0.013779959082603455, "grad_norm": 0.08303772658109665, "invalid_tail_samples": 26.4, "learning_rate": 4.302785336959547e-07, "loss": 0.0155, "positive_teacher_pairs": 26246.3, "relation_loss": 0.0017573078512214124, "selected_pairs": 26246.3, "step": 28810, "student_distance_mean": 1254.595361328125, "teacher_distance_mean": 0.8468885838985443, "valid_action_samples": 229.6, "weighted_auxiliary_loss": 0.0017573078512214124, "weighted_relation_loss": 0.0017573078512214124 }, { "action_query_batch_std": 21.901719856262208, "action_query_norm": 928.2269592285156, "action_relation_loss": 0.0017572855809703468, "auxiliary_loss_weight": 1.0, "epoch": 26.95977549111319, "flow_matching_loss": 0.015020410902798176, "grad_norm": 0.11551517993211746, "invalid_tail_samples": 25.3, "learning_rate": 4.2309353209297744e-07, "loss": 0.0168, "positive_teacher_pairs": 26515.1, "relation_loss": 0.0017572855809703468, "selected_pairs": 26515.1, "step": 28820, "student_distance_mean": 1258.221142578125, "teacher_distance_mean": 0.8493692994117736, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0017572855809703468, "weighted_relation_loss": 0.0017572855809703468 }, { "action_query_batch_std": 22.01502456665039, "action_query_norm": 933.3083190917969, "action_relation_loss": 0.0017380241421051323, "auxiliary_loss_weight": 1.0, "epoch": 26.96913002806361, "flow_matching_loss": 0.01369008468464017, "grad_norm": 0.07029544562101364, "invalid_tail_samples": 20.3, "learning_rate": 4.159687711061566e-07, "loss": 0.0154, "positive_teacher_pairs": 27667.7, "relation_loss": 0.0017380241421051323, "selected_pairs": 27667.7, "step": 28830, "student_distance_mean": 1264.6169921875, "teacher_distance_mean": 0.8518456935882568, "valid_action_samples": 235.7, "weighted_auxiliary_loss": 0.0017380241421051323, "weighted_relation_loss": 0.0017380241421051323 }, { "action_query_batch_std": 22.032570457458498, "action_query_norm": 932.34599609375, "action_relation_loss": 0.0017790545243769884, "auxiliary_loss_weight": 1.0, "epoch": 26.978484565014032, "flow_matching_loss": 0.016188556887209417, "grad_norm": 0.09388240426778793, "invalid_tail_samples": 21.6, "learning_rate": 4.0890425939275055e-07, "loss": 0.018, "positive_teacher_pairs": 27366.7, "relation_loss": 0.0017790545243769884, "selected_pairs": 27366.7, "step": 28840, "student_distance_mean": 1260.897802734375, "teacher_distance_mean": 0.8516728281974792, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.0017790545243769884, "weighted_relation_loss": 0.0017790545243769884 }, { "action_query_batch_std": 22.023710823059083, "action_query_norm": 932.4005432128906, "action_relation_loss": 0.0017471366096287965, "auxiliary_loss_weight": 1.0, "epoch": 26.987839101964454, "flow_matching_loss": 0.013777884561568499, "grad_norm": 0.09721806645393372, "invalid_tail_samples": 21.6, "learning_rate": 4.0190000553679827e-07, "loss": 0.0155, "positive_teacher_pairs": 27371.7, "relation_loss": 0.0017471366096287965, "selected_pairs": 27371.7, "step": 28850, "student_distance_mean": 1264.2370971679688, "teacher_distance_mean": 0.8524950206279754, "valid_action_samples": 234.4, "weighted_auxiliary_loss": 0.0017471366096287965, "weighted_relation_loss": 0.0017471366096287965 }, { "action_query_batch_std": 22.062938499450684, "action_query_norm": 932.2682434082031, "action_relation_loss": 0.001711255090776831, "auxiliary_loss_weight": 1.0, "epoch": 26.997193638914872, "flow_matching_loss": 0.0150176920928061, "grad_norm": 0.07219240814447403, "invalid_tail_samples": 24.3, "learning_rate": 3.9495601804913627e-07, "loss": 0.0167, "positive_teacher_pairs": 26738.6, "relation_loss": 0.001711255090776831, "selected_pairs": 26738.6, "step": 28860, "student_distance_mean": 1267.4486083984375, "teacher_distance_mean": 0.8561433792114258, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.001711255090776831, "weighted_relation_loss": 0.001711255090776831 }, { "action_query_batch_std": 22.010852241516112, "action_query_norm": 930.8360229492188, "action_relation_loss": 0.0018639732734300196, "auxiliary_loss_weight": 1.0, "epoch": 27.006548175865294, "flow_matching_loss": 0.014316958095878362, "grad_norm": 0.08570920675992966, "invalid_tail_samples": 21.6, "learning_rate": 3.880723053673652e-07, "loss": 0.0162, "positive_teacher_pairs": 24389.7, "relation_loss": 0.0018639732734300196, "selected_pairs": 24389.7, "step": 28870, "student_distance_mean": 1268.9489868164062, "teacher_distance_mean": 0.8552198231220245, "valid_action_samples": 214.5, "weighted_auxiliary_loss": 0.0018639732734300196, "weighted_relation_loss": 0.0018639732734300196 }, { "action_query_batch_std": 21.837992477416993, "action_query_norm": 925.52548828125, "action_relation_loss": 0.0017368197324685753, "auxiliary_loss_weight": 1.0, "epoch": 27.015902712815716, "flow_matching_loss": 0.015297103859484195, "grad_norm": 0.0736212357878685, "invalid_tail_samples": 24.8, "learning_rate": 3.812488758558386e-07, "loss": 0.017, "positive_teacher_pairs": 26616.7, "relation_loss": 0.0017368197324685753, "selected_pairs": 26616.7, "step": 28880, "student_distance_mean": 1250.6701293945312, "teacher_distance_mean": 0.8430625140666962, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0017368197324685753, "weighted_relation_loss": 0.0017368197324685753 }, { "action_query_batch_std": 21.945429420471193, "action_query_norm": 928.373095703125, "action_relation_loss": 0.0017261752276681364, "auxiliary_loss_weight": 1.0, "epoch": 27.02525724976614, "flow_matching_loss": 0.014852218609303237, "grad_norm": 0.07736758142709732, "invalid_tail_samples": 28.6, "learning_rate": 3.744857378056743e-07, "loss": 0.0166, "positive_teacher_pairs": 25756.0, "relation_loss": 0.0017261752276681364, "selected_pairs": 25756.0, "step": 28890, "student_distance_mean": 1268.57197265625, "teacher_distance_mean": 0.8566320896148681, "valid_action_samples": 227.4, "weighted_auxiliary_loss": 0.0017261752276681364, "weighted_relation_loss": 0.0017261752276681364 }, { "action_query_batch_std": 21.611188316345213, "action_query_norm": 918.0017639160156, "action_relation_loss": 0.0017303717671893538, "auxiliary_loss_weight": 1.0, "epoch": 27.034611786716557, "flow_matching_loss": 0.015292377956211568, "grad_norm": 0.0887884572148323, "invalid_tail_samples": 21.9, "learning_rate": 3.677828994347154e-07, "loss": 0.017, "positive_teacher_pairs": 27298.1, "relation_loss": 0.0017303717671893538, "selected_pairs": 27298.1, "step": 28900, "student_distance_mean": 1239.188525390625, "teacher_distance_mean": 0.8365091979503632, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.0017303717671893538, "weighted_relation_loss": 0.0017303717671893538 }, { "action_query_batch_std": 21.96474094390869, "action_query_norm": 927.8262390136719, "action_relation_loss": 0.0017842257278971375, "auxiliary_loss_weight": 1.0, "epoch": 27.04396632366698, "flow_matching_loss": 0.014789404347538948, "grad_norm": 0.09851595014333725, "invalid_tail_samples": 24.0, "learning_rate": 3.61140368887547e-07, "loss": 0.0166, "positive_teacher_pairs": 26803.4, "relation_loss": 0.0017842257278971375, "selected_pairs": 26803.4, "step": 28910, "student_distance_mean": 1264.5842651367188, "teacher_distance_mean": 0.8535025835037231, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0017842257278971375, "weighted_relation_loss": 0.0017842257278971375 }, { "action_query_batch_std": 21.964543533325195, "action_query_norm": 930.1550720214843, "action_relation_loss": 0.0017496783519163727, "auxiliary_loss_weight": 1.0, "epoch": 27.0533208606174, "flow_matching_loss": 0.014225527830421924, "grad_norm": 0.08220011740922928, "invalid_tail_samples": 24.5, "learning_rate": 3.545581542354681e-07, "loss": 0.016, "positive_teacher_pairs": 26695.0, "relation_loss": 0.0017496783519163727, "selected_pairs": 26695.0, "step": 28920, "student_distance_mean": 1265.6295654296875, "teacher_distance_mean": 0.8545563578605652, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0017496783519163727, "weighted_relation_loss": 0.0017496783519163727 }, { "action_query_batch_std": 22.13835906982422, "action_query_norm": 934.9024841308594, "action_relation_loss": 0.0017107818857766688, "auxiliary_loss_weight": 1.0, "epoch": 27.06267539756782, "flow_matching_loss": 0.014601287152618169, "grad_norm": 0.09028583765029907, "invalid_tail_samples": 24.1, "learning_rate": 3.480362634764922e-07, "loss": 0.0163, "positive_teacher_pairs": 26777.4, "relation_loss": 0.0017107818857766688, "selected_pairs": 26777.4, "step": 28930, "student_distance_mean": 1269.0662231445312, "teacher_distance_mean": 0.856304270029068, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0017107818857766688, "weighted_relation_loss": 0.0017107818857766688 }, { "action_query_batch_std": 22.01262836456299, "action_query_norm": 932.7254150390625, "action_relation_loss": 0.0017634736024774611, "auxiliary_loss_weight": 1.0, "epoch": 27.07202993451824, "flow_matching_loss": 0.01429307321086526, "grad_norm": 0.1021118089556694, "invalid_tail_samples": 23.9, "learning_rate": 3.4157470453533014e-07, "loss": 0.0161, "positive_teacher_pairs": 26833.5, "relation_loss": 0.0017634736024774611, "selected_pairs": 26833.5, "step": 28940, "student_distance_mean": 1268.1796020507813, "teacher_distance_mean": 0.8565811932086944, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0017634736024774611, "weighted_relation_loss": 0.0017634736024774611 }, { "action_query_batch_std": 22.039422225952148, "action_query_norm": 930.6466186523437, "action_relation_loss": 0.001728057162836194, "auxiliary_loss_weight": 1.0, "epoch": 27.081384471468663, "flow_matching_loss": 0.015441073570400476, "grad_norm": 0.10951163619756699, "invalid_tail_samples": 23.7, "learning_rate": 3.3517348526339034e-07, "loss": 0.0172, "positive_teacher_pairs": 26879.9, "relation_loss": 0.001728057162836194, "selected_pairs": 26879.9, "step": 28950, "student_distance_mean": 1265.9422729492187, "teacher_distance_mean": 0.8534647464752197, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.001728057162836194, "weighted_relation_loss": 0.001728057162836194 }, { "action_query_batch_std": 21.968582344055175, "action_query_norm": 929.1511352539062, "action_relation_loss": 0.0017187760444357992, "auxiliary_loss_weight": 1.0, "epoch": 27.09073900841908, "flow_matching_loss": 0.015812303870916367, "grad_norm": 0.07273297011852264, "invalid_tail_samples": 24.5, "learning_rate": 3.288326134387454e-07, "loss": 0.0175, "positive_teacher_pairs": 26700.1, "relation_loss": 0.0017187760444357992, "selected_pairs": 26700.1, "step": 28960, "student_distance_mean": 1262.66943359375, "teacher_distance_mean": 0.8520882070064545, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0017187760444357992, "weighted_relation_loss": 0.0017187760444357992 }, { "action_query_batch_std": 22.11381607055664, "action_query_norm": 936.0850280761719, "action_relation_loss": 0.0017394753522239625, "auxiliary_loss_weight": 1.0, "epoch": 27.100093545369504, "flow_matching_loss": 0.016113010328263046, "grad_norm": 0.10418514162302017, "invalid_tail_samples": 27.8, "learning_rate": 3.225520967661655e-07, "loss": 0.0179, "positive_teacher_pairs": 25933.8, "relation_loss": 0.0017394753522239625, "selected_pairs": 25933.8, "step": 28970, "student_distance_mean": 1274.4111206054688, "teacher_distance_mean": 0.8593230485916138, "valid_action_samples": 228.2, "weighted_auxiliary_loss": 0.0017394753522239625, "weighted_relation_loss": 0.0017394753522239625 }, { "action_query_batch_std": 22.018489265441893, "action_query_norm": 933.1903564453125, "action_relation_loss": 0.001778680901043117, "auxiliary_loss_weight": 1.0, "epoch": 27.109448082319926, "flow_matching_loss": 0.013849571999162435, "grad_norm": 0.07899554073810577, "invalid_tail_samples": 23.8, "learning_rate": 3.163319428770628e-07, "loss": 0.0156, "positive_teacher_pairs": 26861.3, "relation_loss": 0.001778680901043117, "selected_pairs": 26861.3, "step": 28980, "student_distance_mean": 1267.2690063476562, "teacher_distance_mean": 0.8542381167411804, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.001778680901043117, "weighted_relation_loss": 0.001778680901043117 }, { "action_query_batch_std": 21.952157402038573, "action_query_norm": 928.9464477539062, "action_relation_loss": 0.0017295574420131744, "auxiliary_loss_weight": 1.0, "epoch": 27.118802619270348, "flow_matching_loss": 0.015843843668699266, "grad_norm": 0.09381762892007828, "invalid_tail_samples": 28.0, "learning_rate": 3.1017215932951374e-07, "loss": 0.0176, "positive_teacher_pairs": 25896.5, "relation_loss": 0.0017295574420131744, "selected_pairs": 25896.5, "step": 28990, "student_distance_mean": 1268.0625244140624, "teacher_distance_mean": 0.854913306236267, "valid_action_samples": 228.0, "weighted_auxiliary_loss": 0.0017295574420131744, "weighted_relation_loss": 0.0017295574420131744 }, { "action_query_batch_std": 22.286191558837892, "action_query_norm": 941.9787719726562, "action_relation_loss": 0.0017099933582358062, "auxiliary_loss_weight": 1.0, "epoch": 27.128157156220766, "flow_matching_loss": 0.015701039414852857, "grad_norm": 0.08134733885526657, "invalid_tail_samples": 23.1, "learning_rate": 3.040727536082366e-07, "loss": 0.0174, "positive_teacher_pairs": 27011.8, "relation_loss": 0.0017099933582358062, "selected_pairs": 27011.8, "step": 29000, "student_distance_mean": 1281.5066284179688, "teacher_distance_mean": 0.8644352555274963, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0017099933582358062, "weighted_relation_loss": 0.0017099933582358062 }, { "action_query_batch_std": 22.258172225952148, "action_query_norm": 940.8303649902343, "action_relation_loss": 0.001709272840525955, "auxiliary_loss_weight": 1.0, "epoch": 27.137511693171188, "flow_matching_loss": 0.013525819778442383, "grad_norm": 0.09572356194257736, "invalid_tail_samples": 24.5, "learning_rate": 2.980337331245864e-07, "loss": 0.0152, "positive_teacher_pairs": 26690.9, "relation_loss": 0.001709272840525955, "selected_pairs": 26690.9, "step": 29010, "student_distance_mean": 1281.84736328125, "teacher_distance_mean": 0.8662551820278168, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.001709272840525955, "weighted_relation_loss": 0.001709272840525955 }, { "action_query_batch_std": 22.110525131225586, "action_query_norm": 935.1158935546875, "action_relation_loss": 0.0017055890988558532, "auxiliary_loss_weight": 1.0, "epoch": 27.14686623012161, "flow_matching_loss": 0.014605835638940334, "grad_norm": 0.08951320499181747, "invalid_tail_samples": 25.7, "learning_rate": 2.9205510521653213e-07, "loss": 0.0163, "positive_teacher_pairs": 26415.2, "relation_loss": 0.0017055890988558532, "selected_pairs": 26415.2, "step": 29020, "student_distance_mean": 1273.3173583984376, "teacher_distance_mean": 0.8598312318325043, "valid_action_samples": 230.3, "weighted_auxiliary_loss": 0.0017055890988558532, "weighted_relation_loss": 0.0017055890988558532 }, { "action_query_batch_std": 22.15684394836426, "action_query_norm": 938.8126098632813, "action_relation_loss": 0.001779492711648345, "auxiliary_loss_weight": 1.0, "epoch": 27.15622076707203, "flow_matching_loss": 0.014923736918717623, "grad_norm": 0.10958413779735565, "invalid_tail_samples": 22.1, "learning_rate": 2.86136877148685e-07, "loss": 0.0167, "positive_teacher_pairs": 27251.0, "relation_loss": 0.001779492711648345, "selected_pairs": 27251.0, "step": 29030, "student_distance_mean": 1277.932080078125, "teacher_distance_mean": 0.863145262002945, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.001779492711648345, "weighted_relation_loss": 0.001779492711648345 }, { "action_query_batch_std": 22.29297046661377, "action_query_norm": 942.9227905273438, "action_relation_loss": 0.0017522679641842841, "auxiliary_loss_weight": 1.0, "epoch": 27.16557530402245, "flow_matching_loss": 0.014507441408932209, "grad_norm": 0.07194062322378159, "invalid_tail_samples": 22.1, "learning_rate": 2.8027905611223704e-07, "loss": 0.0163, "positive_teacher_pairs": 27244.7, "relation_loss": 0.0017522679641842841, "selected_pairs": 27244.7, "step": 29040, "student_distance_mean": 1280.9743286132812, "teacher_distance_mean": 0.8641137659549714, "valid_action_samples": 233.9, "weighted_auxiliary_loss": 0.0017522679641842841, "weighted_relation_loss": 0.0017522679641842841 }, { "action_query_batch_std": 22.160548210144043, "action_query_norm": 936.99111328125, "action_relation_loss": 0.0016920403460972012, "auxiliary_loss_weight": 1.0, "epoch": 27.174929840972872, "flow_matching_loss": 0.014549112785607577, "grad_norm": 0.07097848504781723, "invalid_tail_samples": 23.7, "learning_rate": 2.7448164922500573e-07, "loss": 0.0162, "positive_teacher_pairs": 26881.1, "relation_loss": 0.0016920403460972012, "selected_pairs": 26881.1, "step": 29050, "student_distance_mean": 1273.9996826171875, "teacher_distance_mean": 0.8603982567787171, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0016920403460972012, "weighted_relation_loss": 0.0016920403460972012 }, { "action_query_batch_std": 22.171784019470216, "action_query_norm": 937.9202270507812, "action_relation_loss": 0.0017018011538311839, "auxiliary_loss_weight": 1.0, "epoch": 27.184284377923294, "flow_matching_loss": 0.015335789788514376, "grad_norm": 0.052102118730545044, "invalid_tail_samples": 24.3, "learning_rate": 2.687446635313784e-07, "loss": 0.017, "positive_teacher_pairs": 26736.4, "relation_loss": 0.0017018011538311839, "selected_pairs": 26736.4, "step": 29060, "student_distance_mean": 1277.1625244140625, "teacher_distance_mean": 0.8619286835193634, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0017018011538311839, "weighted_relation_loss": 0.0017018011538311839 }, { "action_query_batch_std": 22.285105514526368, "action_query_norm": 942.3030029296875, "action_relation_loss": 0.001691897911950946, "auxiliary_loss_weight": 1.0, "epoch": 27.193638914873713, "flow_matching_loss": 0.0156579471193254, "grad_norm": 0.08405080437660217, "invalid_tail_samples": 23.3, "learning_rate": 2.630681060023343e-07, "loss": 0.0173, "positive_teacher_pairs": 26973.5, "relation_loss": 0.001691897911950946, "selected_pairs": 26973.5, "step": 29070, "student_distance_mean": 1286.9026245117188, "teacher_distance_mean": 0.8680238962173462, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.001691897911950946, "weighted_relation_loss": 0.001691897911950946 }, { "action_query_batch_std": 22.381500053405762, "action_query_norm": 944.5240356445313, "action_relation_loss": 0.0017387247644364834, "auxiliary_loss_weight": 1.0, "epoch": 27.202993451824135, "flow_matching_loss": 0.01531369611620903, "grad_norm": 0.07000478357076645, "invalid_tail_samples": 21.9, "learning_rate": 2.5745198353542833e-07, "loss": 0.0171, "positive_teacher_pairs": 27291.9, "relation_loss": 0.0017387247644364834, "selected_pairs": 27291.9, "step": 29080, "student_distance_mean": 1282.2319580078124, "teacher_distance_mean": 0.8654094934463501, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.0017387247644364834, "weighted_relation_loss": 0.0017387247644364834 }, { "action_query_batch_std": 21.69605598449707, "action_query_norm": 922.06884765625, "action_relation_loss": 0.0017593119875527919, "auxiliary_loss_weight": 1.0, "epoch": 27.212347988774557, "flow_matching_loss": 0.012369035929441451, "grad_norm": 0.07143616676330566, "invalid_tail_samples": 23.9, "learning_rate": 2.518963029547794e-07, "loss": 0.0141, "positive_teacher_pairs": 26821.9, "relation_loss": 0.0017593119875527919, "selected_pairs": 26821.9, "step": 29090, "student_distance_mean": 1243.1734619140625, "teacher_distance_mean": 0.8390437543392182, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0017593119875527919, "weighted_relation_loss": 0.0017593119875527919 }, { "action_query_batch_std": 22.169916534423827, "action_query_norm": 938.3633972167969, "action_relation_loss": 0.0017318214988335967, "auxiliary_loss_weight": 1.0, "epoch": 27.221702525724975, "flow_matching_loss": 0.012992742471396923, "grad_norm": 0.06429094821214676, "invalid_tail_samples": 24.5, "learning_rate": 2.464010710110598e-07, "loss": 0.0147, "positive_teacher_pairs": 26685.8, "relation_loss": 0.0017318214988335967, "selected_pairs": 26685.8, "step": 29100, "student_distance_mean": 1279.0053100585938, "teacher_distance_mean": 0.8634848415851593, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0017318214988335967, "weighted_relation_loss": 0.0017318214988335967 }, { "action_query_batch_std": 21.773703193664552, "action_query_norm": 925.1068298339844, "action_relation_loss": 0.0017296470468863845, "auxiliary_loss_weight": 1.0, "epoch": 27.231057062675397, "flow_matching_loss": 0.01388101391494274, "grad_norm": 0.08903191238641739, "invalid_tail_samples": 22.8, "learning_rate": 2.4096629438150054e-07, "loss": 0.0156, "positive_teacher_pairs": 27080.2, "relation_loss": 0.0017296470468863845, "selected_pairs": 27080.2, "step": 29110, "student_distance_mean": 1255.3820190429688, "teacher_distance_mean": 0.8477736115455627, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0017296470468863845, "weighted_relation_loss": 0.0017296470468863845 }, { "action_query_batch_std": 22.070476531982422, "action_query_norm": 936.1170532226563, "action_relation_loss": 0.001807808713056147, "auxiliary_loss_weight": 1.0, "epoch": 27.24041159962582, "flow_matching_loss": 0.015657263062894344, "grad_norm": 0.09150610119104385, "invalid_tail_samples": 24.6, "learning_rate": 2.3559197966985802e-07, "loss": 0.0175, "positive_teacher_pairs": 26675.5, "relation_loss": 0.001807808713056147, "selected_pairs": 26675.5, "step": 29120, "student_distance_mean": 1264.583544921875, "teacher_distance_mean": 0.8520877957344055, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.001807808713056147, "weighted_relation_loss": 0.001807808713056147 }, { "action_query_batch_std": 22.263773727416993, "action_query_norm": 939.29111328125, "action_relation_loss": 0.0016897305846214294, "auxiliary_loss_weight": 1.0, "epoch": 27.24976613657624, "flow_matching_loss": 0.013918354827910661, "grad_norm": 0.12362281233072281, "invalid_tail_samples": 22.0, "learning_rate": 2.3027813340644188e-07, "loss": 0.0156, "positive_teacher_pairs": 27268.6, "relation_loss": 0.0016897305846214294, "selected_pairs": 27268.6, "step": 29130, "student_distance_mean": 1272.0939208984375, "teacher_distance_mean": 0.8581798732280731, "valid_action_samples": 234.0, "weighted_auxiliary_loss": 0.0016897305846214294, "weighted_relation_loss": 0.0016897305846214294 }, { "action_query_batch_std": 22.121941757202148, "action_query_norm": 938.7457214355469, "action_relation_loss": 0.001751662965398282, "auxiliary_loss_weight": 1.0, "epoch": 27.25912067352666, "flow_matching_loss": 0.015493628103286028, "grad_norm": 0.10401855409145355, "invalid_tail_samples": 21.1, "learning_rate": 2.2502476204807055e-07, "loss": 0.0172, "positive_teacher_pairs": 27477.1, "relation_loss": 0.001751662965398282, "selected_pairs": 27477.1, "step": 29140, "student_distance_mean": 1270.0080932617188, "teacher_distance_mean": 0.8564531624317169, "valid_action_samples": 234.9, "weighted_auxiliary_loss": 0.001751662965398282, "weighted_relation_loss": 0.001751662965398282 }, { "action_query_batch_std": 21.64848384857178, "action_query_norm": 918.2103820800781, "action_relation_loss": 0.0017334379837848247, "auxiliary_loss_weight": 1.0, "epoch": 27.26847521047708, "flow_matching_loss": 0.014104163367301225, "grad_norm": 0.08797837793827057, "invalid_tail_samples": 25.3, "learning_rate": 2.1983187197808786e-07, "loss": 0.0158, "positive_teacher_pairs": 26501.6, "relation_loss": 0.0017334379837848247, "selected_pairs": 26501.6, "step": 29150, "student_distance_mean": 1246.515576171875, "teacher_distance_mean": 0.8411959111690521, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.0017334379837848247, "weighted_relation_loss": 0.0017334379837848247 }, { "action_query_batch_std": 21.94000301361084, "action_query_norm": 929.9963012695313, "action_relation_loss": 0.0017642678692936897, "auxiliary_loss_weight": 1.0, "epoch": 27.277829747427504, "flow_matching_loss": 0.013798925559967756, "grad_norm": 0.09343211352825165, "invalid_tail_samples": 24.6, "learning_rate": 2.1469946950634644e-07, "loss": 0.0156, "positive_teacher_pairs": 26661.5, "relation_loss": 0.0017642678692936897, "selected_pairs": 26661.5, "step": 29160, "student_distance_mean": 1262.8714477539063, "teacher_distance_mean": 0.8515038430690766, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0017642678692936897, "weighted_relation_loss": 0.0017642678692936897 }, { "action_query_batch_std": 21.976473999023437, "action_query_norm": 931.5956298828125, "action_relation_loss": 0.0017482221825048327, "auxiliary_loss_weight": 1.0, "epoch": 27.287184284377922, "flow_matching_loss": 0.016311352886259557, "grad_norm": 0.0801696628332138, "invalid_tail_samples": 23.9, "learning_rate": 2.096275608691911e-07, "loss": 0.0181, "positive_teacher_pairs": 26831.2, "relation_loss": 0.0017482221825048327, "selected_pairs": 26831.2, "step": 29170, "student_distance_mean": 1264.1501586914062, "teacher_distance_mean": 0.8531807482242584, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0017482221825048327, "weighted_relation_loss": 0.0017482221825048327 }, { "action_query_batch_std": 22.15258617401123, "action_query_norm": 937.5276977539063, "action_relation_loss": 0.0017258868203498424, "auxiliary_loss_weight": 1.0, "epoch": 27.296538821328344, "flow_matching_loss": 0.013496877998113633, "grad_norm": 0.09998594224452972, "invalid_tail_samples": 25.5, "learning_rate": 2.046161522294754e-07, "loss": 0.0152, "positive_teacher_pairs": 26462.4, "relation_loss": 0.0017258868203498424, "selected_pairs": 26462.4, "step": 29180, "student_distance_mean": 1275.6248413085937, "teacher_distance_mean": 0.8605956912040711, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0017258868203498424, "weighted_relation_loss": 0.0017258868203498424 }, { "action_query_batch_std": 22.116931533813478, "action_query_norm": 936.6433532714843, "action_relation_loss": 0.0017630102927796542, "auxiliary_loss_weight": 1.0, "epoch": 27.305893358278766, "flow_matching_loss": 0.01359571423381567, "grad_norm": 0.09314251691102982, "invalid_tail_samples": 22.8, "learning_rate": 1.9966524967653944e-07, "loss": 0.0154, "positive_teacher_pairs": 27080.7, "relation_loss": 0.0017630102927796542, "selected_pairs": 27080.7, "step": 29190, "student_distance_mean": 1270.3890502929687, "teacher_distance_mean": 0.8558631181716919, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0017630102927796542, "weighted_relation_loss": 0.0017630102927796542 }, { "action_query_batch_std": 22.084984970092773, "action_query_norm": 936.5005981445313, "action_relation_loss": 0.001718242873903364, "auxiliary_loss_weight": 1.0, "epoch": 27.315247895229184, "flow_matching_loss": 0.015110631100833416, "grad_norm": 0.0810505598783493, "invalid_tail_samples": 23.5, "learning_rate": 1.9477485922618222e-07, "loss": 0.0168, "positive_teacher_pairs": 26930.0, "relation_loss": 0.001718242873903364, "selected_pairs": 26930.0, "step": 29200, "student_distance_mean": 1271.5451782226562, "teacher_distance_mean": 0.8562844872474671, "valid_action_samples": 232.5, "weighted_auxiliary_loss": 0.001718242873903364, "weighted_relation_loss": 0.001718242873903364 }, { "action_query_batch_std": 22.152133178710937, "action_query_norm": 937.7463623046875, "action_relation_loss": 0.0017507563112303614, "auxiliary_loss_weight": 1.0, "epoch": 27.324602432179606, "flow_matching_loss": 0.014914889633655549, "grad_norm": 0.08684976398944855, "invalid_tail_samples": 22.2, "learning_rate": 1.899449868207004e-07, "loss": 0.0167, "positive_teacher_pairs": 27219.7, "relation_loss": 0.0017507563112303614, "selected_pairs": 27219.7, "step": 29210, "student_distance_mean": 1269.96943359375, "teacher_distance_mean": 0.8564445734024048, "valid_action_samples": 233.8, "weighted_auxiliary_loss": 0.0017507563112303614, "weighted_relation_loss": 0.0017507563112303614 }, { "action_query_batch_std": 21.934140014648438, "action_query_norm": 929.5020446777344, "action_relation_loss": 0.0017345672473311423, "auxiliary_loss_weight": 1.0, "epoch": 27.33395696913003, "flow_matching_loss": 0.013859385624527931, "grad_norm": 0.06691520661115646, "invalid_tail_samples": 23.1, "learning_rate": 1.851756383288439e-07, "loss": 0.0156, "positive_teacher_pairs": 27020.5, "relation_loss": 0.0017345672473311423, "selected_pairs": 27020.5, "step": 29220, "student_distance_mean": 1262.4649169921875, "teacher_distance_mean": 0.8518693149089813, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0017345672473311423, "weighted_relation_loss": 0.0017345672473311423 }, { "action_query_batch_std": 22.199144172668458, "action_query_norm": 935.7912658691406, "action_relation_loss": 0.0017073157825507224, "auxiliary_loss_weight": 1.0, "epoch": 27.34331150608045, "flow_matching_loss": 0.013910177815705537, "grad_norm": 0.07821695506572723, "invalid_tail_samples": 24.8, "learning_rate": 1.8046681954581035e-07, "loss": 0.0156, "positive_teacher_pairs": 26618.3, "relation_loss": 0.0017073157825507224, "selected_pairs": 26618.3, "step": 29230, "student_distance_mean": 1273.2003662109375, "teacher_distance_mean": 0.8604408800601959, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.0017073157825507224, "weighted_relation_loss": 0.0017073157825507224 }, { "action_query_batch_std": 22.008499336242675, "action_query_norm": 937.4072265625, "action_relation_loss": 0.0017107989871874452, "auxiliary_loss_weight": 1.0, "epoch": 27.35266604303087, "flow_matching_loss": 0.014184916578233241, "grad_norm": 0.08904179185628891, "invalid_tail_samples": 24.2, "learning_rate": 1.7581853619327294e-07, "loss": 0.0159, "positive_teacher_pairs": 26754.3, "relation_loss": 0.0017107989871874452, "selected_pairs": 26754.3, "step": 29240, "student_distance_mean": 1273.238720703125, "teacher_distance_mean": 0.8573582291603088, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0017107989871874452, "weighted_relation_loss": 0.0017107989871874452 }, { "action_query_batch_std": 21.903410148620605, "action_query_norm": 927.8657775878906, "action_relation_loss": 0.0017556274659000337, "auxiliary_loss_weight": 1.0, "epoch": 27.36202057998129, "flow_matching_loss": 0.013462769892066717, "grad_norm": 0.06875241547822952, "invalid_tail_samples": 22.7, "learning_rate": 1.7123079391932472e-07, "loss": 0.0152, "positive_teacher_pairs": 27107.3, "relation_loss": 0.0017556274659000337, "selected_pairs": 27107.3, "step": 29250, "student_distance_mean": 1258.5403442382812, "teacher_distance_mean": 0.8487218499183655, "valid_action_samples": 233.3, "weighted_auxiliary_loss": 0.0017556274659000337, "weighted_relation_loss": 0.0017556274659000337 }, { "action_query_batch_std": 22.20403938293457, "action_query_norm": 939.4424621582032, "action_relation_loss": 0.0017183074611239134, "auxiliary_loss_weight": 1.0, "epoch": 27.371375116931713, "flow_matching_loss": 0.014179009106010198, "grad_norm": 0.08873556554317474, "invalid_tail_samples": 23.4, "learning_rate": 1.6670359829850657e-07, "loss": 0.0159, "positive_teacher_pairs": 26942.3, "relation_loss": 0.0017183074611239134, "selected_pairs": 26942.3, "step": 29260, "student_distance_mean": 1280.4982788085938, "teacher_distance_mean": 0.8628111481666565, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0017183074611239134, "weighted_relation_loss": 0.0017183074611239134 }, { "action_query_batch_std": 21.963683319091796, "action_query_norm": 933.5319641113281, "action_relation_loss": 0.001715703122317791, "auxiliary_loss_weight": 1.0, "epoch": 27.38072965388213, "flow_matching_loss": 0.013582091126590968, "grad_norm": 0.11066167801618576, "invalid_tail_samples": 23.7, "learning_rate": 1.6223695483179037e-07, "loss": 0.0153, "positive_teacher_pairs": 26880.1, "relation_loss": 0.001715703122317791, "selected_pairs": 26880.1, "step": 29270, "student_distance_mean": 1263.5341796875, "teacher_distance_mean": 0.8519785165786743, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.001715703122317791, "weighted_relation_loss": 0.001715703122317791 }, { "action_query_batch_std": 21.872927093505858, "action_query_norm": 926.0965637207031, "action_relation_loss": 0.0017520119086839258, "auxiliary_loss_weight": 1.0, "epoch": 27.390084190832553, "flow_matching_loss": 0.0157511567696929, "grad_norm": 0.08489692211151123, "invalid_tail_samples": 23.3, "learning_rate": 1.5783086894656795e-07, "loss": 0.0175, "positive_teacher_pairs": 26976.1, "relation_loss": 0.0017520119086839258, "selected_pairs": 26976.1, "step": 29280, "student_distance_mean": 1262.4282958984375, "teacher_distance_mean": 0.8515621483325958, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0017520119086839258, "weighted_relation_loss": 0.0017520119086839258 }, { "action_query_batch_std": 22.378908348083495, "action_query_norm": 944.8617980957031, "action_relation_loss": 0.0016771324211731554, "auxiliary_loss_weight": 1.0, "epoch": 27.399438727782975, "flow_matching_loss": 0.015076756849884987, "grad_norm": 0.08195332437753677, "invalid_tail_samples": 27.4, "learning_rate": 1.5348534599665121e-07, "loss": 0.0168, "positive_teacher_pairs": 26027.0, "relation_loss": 0.0016771324211731554, "selected_pairs": 26027.0, "step": 29290, "student_distance_mean": 1292.043603515625, "teacher_distance_mean": 0.8710382163524628, "valid_action_samples": 228.6, "weighted_auxiliary_loss": 0.0016771324211731554, "weighted_relation_loss": 0.0016771324211731554 }, { "action_query_batch_std": 22.083482360839845, "action_query_norm": 932.6843933105469, "action_relation_loss": 0.0017294952413067222, "auxiliary_loss_weight": 1.0, "epoch": 27.408793264733397, "flow_matching_loss": 0.01334139471873641, "grad_norm": 0.1031450629234314, "invalid_tail_samples": 23.0, "learning_rate": 1.4920039126225527e-07, "loss": 0.0151, "positive_teacher_pairs": 27033.8, "relation_loss": 0.0017294952413067222, "selected_pairs": 27033.8, "step": 29300, "student_distance_mean": 1265.344482421875, "teacher_distance_mean": 0.8530788421630859, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0017294952413067222, "weighted_relation_loss": 0.0017294952413067222 }, { "action_query_batch_std": 22.062010192871092, "action_query_norm": 936.8612487792968, "action_relation_loss": 0.0017982755205594003, "auxiliary_loss_weight": 1.0, "epoch": 27.418147801683816, "flow_matching_loss": 0.014716108608990908, "grad_norm": 0.06407757103443146, "invalid_tail_samples": 25.8, "learning_rate": 1.449760099500097e-07, "loss": 0.0165, "positive_teacher_pairs": 26390.8, "relation_loss": 0.0017982755205594003, "selected_pairs": 26390.8, "step": 29310, "student_distance_mean": 1271.707861328125, "teacher_distance_mean": 0.8567094385623932, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.0017982755205594003, "weighted_relation_loss": 0.0017982755205594003 }, { "action_query_batch_std": 21.916267585754394, "action_query_norm": 928.5158996582031, "action_relation_loss": 0.0017619410646148026, "auxiliary_loss_weight": 1.0, "epoch": 27.427502338634238, "flow_matching_loss": 0.015154446288943291, "grad_norm": 0.07770028710365295, "invalid_tail_samples": 22.3, "learning_rate": 1.4081220719293075e-07, "loss": 0.0169, "positive_teacher_pairs": 27198.1, "relation_loss": 0.0017619410646148026, "selected_pairs": 27198.1, "step": 29320, "student_distance_mean": 1261.5847778320312, "teacher_distance_mean": 0.8508605480194091, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0017619410646148026, "weighted_relation_loss": 0.0017619410646148026 }, { "action_query_batch_std": 22.12656593322754, "action_query_norm": 934.7416320800781, "action_relation_loss": 0.0017220249632373453, "auxiliary_loss_weight": 1.0, "epoch": 27.43685687558466, "flow_matching_loss": 0.012990978080779314, "grad_norm": 0.08196607977151871, "invalid_tail_samples": 23.6, "learning_rate": 1.3670898805043797e-07, "loss": 0.0147, "positive_teacher_pairs": 26898.8, "relation_loss": 0.0017220249632373453, "selected_pairs": 26898.8, "step": 29330, "student_distance_mean": 1271.7595336914062, "teacher_distance_mean": 0.857498687505722, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0017220249632373453, "weighted_relation_loss": 0.0017220249632373453 }, { "action_query_batch_std": 21.69081554412842, "action_query_norm": 922.5375305175781, "action_relation_loss": 0.0017533864360302688, "auxiliary_loss_weight": 1.0, "epoch": 27.446211412535078, "flow_matching_loss": 0.014337560534477234, "grad_norm": 0.06522196531295776, "invalid_tail_samples": 23.4, "learning_rate": 1.326663575083209e-07, "loss": 0.0161, "positive_teacher_pairs": 26940.5, "relation_loss": 0.0017533864360302688, "selected_pairs": 26940.5, "step": 29340, "student_distance_mean": 1253.7225219726563, "teacher_distance_mean": 0.8461718201637268, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.0017533864360302688, "weighted_relation_loss": 0.0017533864360302688 }, { "action_query_batch_std": 22.171848106384278, "action_query_norm": 936.38876953125, "action_relation_loss": 0.0018166859517805278, "auxiliary_loss_weight": 1.0, "epoch": 27.4555659494855, "flow_matching_loss": 0.016438171453773975, "grad_norm": 0.06902216374874115, "invalid_tail_samples": 23.6, "learning_rate": 1.2868432047876688e-07, "loss": 0.0183, "positive_teacher_pairs": 26902.1, "relation_loss": 0.0018166859517805278, "selected_pairs": 26902.1, "step": 29350, "student_distance_mean": 1272.0639892578124, "teacher_distance_mean": 0.859024441242218, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0018166859517805278, "weighted_relation_loss": 0.0018166859517805278 }, { "action_query_batch_std": 22.147333717346193, "action_query_norm": 937.4030029296875, "action_relation_loss": 0.0016918897279538214, "auxiliary_loss_weight": 1.0, "epoch": 27.464920486435922, "flow_matching_loss": 0.014981246832758189, "grad_norm": 0.09637246280908585, "invalid_tail_samples": 22.6, "learning_rate": 1.2476288180032213e-07, "loss": 0.0167, "positive_teacher_pairs": 27131.4, "relation_loss": 0.0016918897279538214, "selected_pairs": 27131.4, "step": 29360, "student_distance_mean": 1275.4068481445313, "teacher_distance_mean": 0.861458820104599, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0016918897279538214, "weighted_relation_loss": 0.0016918897279538214 }, { "action_query_batch_std": 21.886715126037597, "action_query_norm": 929.664111328125, "action_relation_loss": 0.0017649557790718972, "auxiliary_loss_weight": 1.0, "epoch": 27.474275023386344, "flow_matching_loss": 0.014676214940845967, "grad_norm": 0.09782323986291885, "invalid_tail_samples": 23.9, "learning_rate": 1.209020462379029e-07, "loss": 0.0164, "positive_teacher_pairs": 26826.4, "relation_loss": 0.0017649557790718972, "selected_pairs": 26826.4, "step": 29370, "student_distance_mean": 1265.023583984375, "teacher_distance_mean": 0.8529768109321594, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0017649557790718972, "weighted_relation_loss": 0.0017649557790718972 }, { "action_query_batch_std": 22.224475860595703, "action_query_norm": 939.2877746582031, "action_relation_loss": 0.001791565236635506, "auxiliary_loss_weight": 1.0, "epoch": 27.483629560336762, "flow_matching_loss": 0.014834208600223064, "grad_norm": 0.08381320536136627, "invalid_tail_samples": 21.4, "learning_rate": 1.1710181848278435e-07, "loss": 0.0166, "positive_teacher_pairs": 27408.3, "relation_loss": 0.001791565236635506, "selected_pairs": 27408.3, "step": 29380, "student_distance_mean": 1272.8251586914062, "teacher_distance_mean": 0.8587408721446991, "valid_action_samples": 234.6, "weighted_auxiliary_loss": 0.001791565236635506, "weighted_relation_loss": 0.001791565236635506 }, { "action_query_batch_std": 21.941571998596192, "action_query_norm": 930.5131896972656, "action_relation_loss": 0.0017004178022034465, "auxiliary_loss_weight": 1.0, "epoch": 27.492984097287184, "flow_matching_loss": 0.013553320616483688, "grad_norm": 0.07941862940788269, "invalid_tail_samples": 24.0, "learning_rate": 1.133622031526116e-07, "loss": 0.0153, "positive_teacher_pairs": 26802.8, "relation_loss": 0.0017004178022034465, "selected_pairs": 26802.8, "step": 29390, "student_distance_mean": 1265.836962890625, "teacher_distance_mean": 0.8533502757549286, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0017004178022034465, "weighted_relation_loss": 0.0017004178022034465 }, { "action_query_batch_std": 22.3005163192749, "action_query_norm": 941.1558166503906, "action_relation_loss": 0.001739680045284331, "auxiliary_loss_weight": 1.0, "epoch": 27.502338634237606, "flow_matching_loss": 0.013611620664596558, "grad_norm": 0.126067653298378, "invalid_tail_samples": 23.9, "learning_rate": 1.0968320479136095e-07, "loss": 0.0154, "positive_teacher_pairs": 26826.5, "relation_loss": 0.001739680045284331, "selected_pairs": 26826.5, "step": 29400, "student_distance_mean": 1277.721875, "teacher_distance_mean": 0.86236732006073, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.001739680045284331, "weighted_relation_loss": 0.001739680045284331 }, { "action_query_batch_std": 21.967385864257814, "action_query_norm": 930.1918823242188, "action_relation_loss": 0.0017565028625540434, "auxiliary_loss_weight": 1.0, "epoch": 27.511693171188025, "flow_matching_loss": 0.014161595609039068, "grad_norm": 0.08496759831905365, "invalid_tail_samples": 23.7, "learning_rate": 1.0606482786936767e-07, "loss": 0.0159, "positive_teacher_pairs": 26880.6, "relation_loss": 0.0017565028625540434, "selected_pairs": 26880.6, "step": 29410, "student_distance_mean": 1263.9394409179688, "teacher_distance_mean": 0.8527771949768066, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0017565028625540434, "weighted_relation_loss": 0.0017565028625540434 }, { "action_query_batch_std": 22.017626762390137, "action_query_norm": 935.8529418945312, "action_relation_loss": 0.0016963252448476851, "auxiliary_loss_weight": 1.0, "epoch": 27.521047708138447, "flow_matching_loss": 0.015924818441271783, "grad_norm": 0.0640605092048645, "invalid_tail_samples": 26.6, "learning_rate": 1.0250707678329808e-07, "loss": 0.0176, "positive_teacher_pairs": 26209.2, "relation_loss": 0.0016963252448476851, "selected_pairs": 26209.2, "step": 29420, "student_distance_mean": 1268.7268798828125, "teacher_distance_mean": 0.8558191239833832, "valid_action_samples": 229.4, "weighted_auxiliary_loss": 0.0016963252448476851, "weighted_relation_loss": 0.0016963252448476851 }, { "action_query_batch_std": 21.95266819000244, "action_query_norm": 929.6299499511719, "action_relation_loss": 0.0017474520835094153, "auxiliary_loss_weight": 1.0, "epoch": 27.53040224508887, "flow_matching_loss": 0.015284015517681836, "grad_norm": 0.12174472212791443, "invalid_tail_samples": 24.0, "learning_rate": 9.900995585615525e-08, "loss": 0.017, "positive_teacher_pairs": 26810.7, "relation_loss": 0.0017474520835094153, "selected_pairs": 26810.7, "step": 29430, "student_distance_mean": 1265.6501342773438, "teacher_distance_mean": 0.8537345647811889, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.0017474520835094153, "weighted_relation_loss": 0.0017474520835094153 }, { "action_query_batch_std": 21.985964584350587, "action_query_norm": 932.5635986328125, "action_relation_loss": 0.0017028515692800283, "auxiliary_loss_weight": 1.0, "epoch": 27.53975678203929, "flow_matching_loss": 0.015396773722022772, "grad_norm": 0.092641681432724, "invalid_tail_samples": 25.5, "learning_rate": 9.55734693372734e-08, "loss": 0.0171, "positive_teacher_pairs": 26461.8, "relation_loss": 0.0017028515692800283, "selected_pairs": 26461.8, "step": 29440, "student_distance_mean": 1268.1362060546876, "teacher_distance_mean": 0.8558795809745788, "valid_action_samples": 230.5, "weighted_auxiliary_loss": 0.0017028515692800283, "weighted_relation_loss": 0.0017028515692800283 }, { "action_query_batch_std": 21.97667827606201, "action_query_norm": 930.5380065917968, "action_relation_loss": 0.0017462315619923175, "auxiliary_loss_weight": 1.0, "epoch": 27.54911131898971, "flow_matching_loss": 0.014073413796722889, "grad_norm": 0.08656048029661179, "invalid_tail_samples": 24.1, "learning_rate": 9.219762140231236e-08, "loss": 0.0158, "positive_teacher_pairs": 26781.2, "relation_loss": 0.0017462315619923175, "selected_pairs": 26781.2, "step": 29450, "student_distance_mean": 1261.3586059570312, "teacher_distance_mean": 0.8515130281448364, "valid_action_samples": 231.9, "weighted_auxiliary_loss": 0.0017462315619923175, "weighted_relation_loss": 0.0017462315619923175 }, { "action_query_batch_std": 21.638333129882813, "action_query_norm": 921.084521484375, "action_relation_loss": 0.0017759977956302464, "auxiliary_loss_weight": 1.0, "epoch": 27.55846585594013, "flow_matching_loss": 0.014240937028080224, "grad_norm": 0.09237684309482574, "invalid_tail_samples": 22.9, "learning_rate": 8.888241615322978e-08, "loss": 0.016, "positive_teacher_pairs": 27061.8, "relation_loss": 0.0017759977956302464, "selected_pairs": 27061.8, "step": 29460, "student_distance_mean": 1242.6375244140625, "teacher_distance_mean": 0.837987071275711, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0017759977956302464, "weighted_relation_loss": 0.0017759977956302464 }, { "action_query_batch_std": 21.980984687805176, "action_query_norm": 930.3905334472656, "action_relation_loss": 0.001766393694560975, "auxiliary_loss_weight": 1.0, "epoch": 27.567820392890553, "flow_matching_loss": 0.014975980669260026, "grad_norm": 0.08352421224117279, "invalid_tail_samples": 25.0, "learning_rate": 8.562785761833114e-08, "loss": 0.0167, "positive_teacher_pairs": 26577.7, "relation_loss": 0.001766393694560975, "selected_pairs": 26577.7, "step": 29470, "student_distance_mean": 1262.9109130859374, "teacher_distance_mean": 0.8519108235836029, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.001766393694560975, "weighted_relation_loss": 0.001766393694560975 }, { "action_query_batch_std": 21.99444923400879, "action_query_norm": 932.2700744628906, "action_relation_loss": 0.0017152476124465466, "auxiliary_loss_weight": 1.0, "epoch": 27.57717492984097, "flow_matching_loss": 0.012791530415415763, "grad_norm": 0.08695793896913528, "invalid_tail_samples": 21.7, "learning_rate": 8.243394975219753e-08, "loss": 0.0145, "positive_teacher_pairs": 27336.7, "relation_loss": 0.0017152476124465466, "selected_pairs": 27336.7, "step": 29480, "student_distance_mean": 1261.1621948242187, "teacher_distance_mean": 0.8514366269111633, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.0017152476124465466, "weighted_relation_loss": 0.0017152476124465466 }, { "action_query_batch_std": 21.827548027038574, "action_query_norm": 927.40927734375, "action_relation_loss": 0.0017356861499138176, "auxiliary_loss_weight": 1.0, "epoch": 27.586529466791394, "flow_matching_loss": 0.015139586292207241, "grad_norm": 0.10632643103599548, "invalid_tail_samples": 21.7, "learning_rate": 7.930069643573568e-08, "loss": 0.0169, "positive_teacher_pairs": 27339.0, "relation_loss": 0.0017356861499138176, "selected_pairs": 27339.0, "step": 29490, "student_distance_mean": 1253.1204345703125, "teacher_distance_mean": 0.8442297041416168, "valid_action_samples": 234.3, "weighted_auxiliary_loss": 0.0017356861499138176, "weighted_relation_loss": 0.0017356861499138176 }, { "action_query_batch_std": 21.832317352294922, "action_query_norm": 926.2167297363281, "action_relation_loss": 0.0017528029158711434, "auxiliary_loss_weight": 1.0, "epoch": 27.595884003741816, "flow_matching_loss": 0.014370499085634947, "grad_norm": 0.07712339609861374, "invalid_tail_samples": 24.3, "learning_rate": 7.622810147614456e-08, "loss": 0.0161, "positive_teacher_pairs": 26743.2, "relation_loss": 0.0017528029158711434, "selected_pairs": 26743.2, "step": 29500, "student_distance_mean": 1259.1155029296874, "teacher_distance_mean": 0.849542647600174, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0017528029158711434, "weighted_relation_loss": 0.0017528029158711434 }, { "action_query_batch_std": 21.796008110046387, "action_query_norm": 926.9439208984375, "action_relation_loss": 0.0017330010421574115, "auxiliary_loss_weight": 1.0, "epoch": 27.605238540692234, "flow_matching_loss": 0.014241245388984681, "grad_norm": 0.08515283465385437, "invalid_tail_samples": 23.0, "learning_rate": 7.321616860690995e-08, "loss": 0.016, "positive_teacher_pairs": 27046.2, "relation_loss": 0.0017330010421574115, "selected_pairs": 27046.2, "step": 29510, "student_distance_mean": 1250.3743530273437, "teacher_distance_mean": 0.8433170437812805, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0017330010421574115, "weighted_relation_loss": 0.0017330010421574115 }, { "action_query_batch_std": 21.699891662597658, "action_query_norm": 921.5156860351562, "action_relation_loss": 0.0017807778087444604, "auxiliary_loss_weight": 1.0, "epoch": 27.614593077642656, "flow_matching_loss": 0.01587967565283179, "grad_norm": 0.07710114121437073, "invalid_tail_samples": 24.5, "learning_rate": 7.026490148782095e-08, "loss": 0.0177, "positive_teacher_pairs": 26688.2, "relation_loss": 0.0017807778087444604, "selected_pairs": 26688.2, "step": 29520, "student_distance_mean": 1252.0348022460937, "teacher_distance_mean": 0.8443889021873474, "valid_action_samples": 231.5, "weighted_auxiliary_loss": 0.0017807778087444604, "weighted_relation_loss": 0.0017807778087444604 }, { "action_query_batch_std": 21.929752922058107, "action_query_norm": 930.7819458007813, "action_relation_loss": 0.001783438411075622, "auxiliary_loss_weight": 1.0, "epoch": 27.623947614593078, "flow_matching_loss": 0.014525003172457219, "grad_norm": 0.07838176935911179, "invalid_tail_samples": 21.9, "learning_rate": 6.737430370494236e-08, "loss": 0.0163, "positive_teacher_pairs": 27292.7, "relation_loss": 0.001783438411075622, "selected_pairs": 27292.7, "step": 29530, "student_distance_mean": 1263.4864013671875, "teacher_distance_mean": 0.8519434452056884, "valid_action_samples": 234.1, "weighted_auxiliary_loss": 0.001783438411075622, "weighted_relation_loss": 0.001783438411075622 }, { "action_query_batch_std": 22.193814086914063, "action_query_norm": 938.5053649902344, "action_relation_loss": 0.0017288665752857924, "auxiliary_loss_weight": 1.0, "epoch": 27.6333021515435, "flow_matching_loss": 0.014740849751979113, "grad_norm": 0.09926457703113556, "invalid_tail_samples": 25.6, "learning_rate": 6.454437877062569e-08, "loss": 0.0165, "positive_teacher_pairs": 26433.9, "relation_loss": 0.0017288665752857924, "selected_pairs": 26433.9, "step": 29540, "student_distance_mean": 1282.8269409179688, "teacher_distance_mean": 0.8651415288448334, "valid_action_samples": 230.4, "weighted_auxiliary_loss": 0.0017288665752857924, "weighted_relation_loss": 0.0017288665752857924 }, { "action_query_batch_std": 22.022603607177736, "action_query_norm": 930.7313842773438, "action_relation_loss": 0.001711661380250007, "auxiliary_loss_weight": 1.0, "epoch": 27.64265668849392, "flow_matching_loss": 0.014432934392243624, "grad_norm": 0.13902348279953003, "invalid_tail_samples": 23.2, "learning_rate": 6.177513012349256e-08, "loss": 0.0161, "positive_teacher_pairs": 26987.9, "relation_loss": 0.001711661380250007, "selected_pairs": 26987.9, "step": 29550, "student_distance_mean": 1268.7902099609375, "teacher_distance_mean": 0.8556109368801117, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.001711661380250007, "weighted_relation_loss": 0.001711661380250007 }, { "action_query_batch_std": 21.882773017883302, "action_query_norm": 927.197265625, "action_relation_loss": 0.0017227861797437071, "auxiliary_loss_weight": 1.0, "epoch": 27.65201122544434, "flow_matching_loss": 0.013782821130007505, "grad_norm": 0.08990520238876343, "invalid_tail_samples": 22.3, "learning_rate": 5.9066561128445775e-08, "loss": 0.0155, "positive_teacher_pairs": 27199.1, "relation_loss": 0.0017227861797437071, "selected_pairs": 27199.1, "step": 29560, "student_distance_mean": 1256.643310546875, "teacher_distance_mean": 0.8478014767169952, "valid_action_samples": 233.7, "weighted_auxiliary_loss": 0.0017227861797437071, "weighted_relation_loss": 0.0017227861797437071 }, { "action_query_batch_std": 22.103564834594728, "action_query_norm": 932.824462890625, "action_relation_loss": 0.0017127752886153757, "auxiliary_loss_weight": 1.0, "epoch": 27.661365762394762, "flow_matching_loss": 0.01411461979150772, "grad_norm": 0.07470640540122986, "invalid_tail_samples": 23.6, "learning_rate": 5.6418675076641556e-08, "loss": 0.0158, "positive_teacher_pairs": 26895.2, "relation_loss": 0.0017127752886153757, "selected_pairs": 26895.2, "step": 29570, "student_distance_mean": 1269.7975952148438, "teacher_distance_mean": 0.8569369673728943, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.0017127752886153757, "weighted_relation_loss": 0.0017127752886153757 }, { "action_query_batch_std": 22.38096103668213, "action_query_norm": 944.6858703613282, "action_relation_loss": 0.0016844567260704934, "auxiliary_loss_weight": 1.0, "epoch": 27.67072029934518, "flow_matching_loss": 0.014601108245551586, "grad_norm": 0.06379657238721848, "invalid_tail_samples": 21.1, "learning_rate": 5.383147518552845e-08, "loss": 0.0163, "positive_teacher_pairs": 27481.5, "relation_loss": 0.0016844567260704934, "selected_pairs": 27481.5, "step": 29580, "student_distance_mean": 1277.5551391601562, "teacher_distance_mean": 0.8627241432666779, "valid_action_samples": 234.9, "weighted_auxiliary_loss": 0.0016844567260704934, "weighted_relation_loss": 0.0016844567260704934 }, { "action_query_batch_std": 22.245436096191405, "action_query_norm": 940.8132385253906, "action_relation_loss": 0.0017034543678164482, "auxiliary_loss_weight": 1.0, "epoch": 27.680074836295603, "flow_matching_loss": 0.015179119538515806, "grad_norm": 0.11289644986391068, "invalid_tail_samples": 25.0, "learning_rate": 5.1304964598786196e-08, "loss": 0.0169, "positive_teacher_pairs": 26572.2, "relation_loss": 0.0017034543678164482, "selected_pairs": 26572.2, "step": 29590, "student_distance_mean": 1282.0441162109375, "teacher_distance_mean": 0.8636237859725953, "valid_action_samples": 231.0, "weighted_auxiliary_loss": 0.0017034543678164482, "weighted_relation_loss": 0.0017034543678164482 }, { "action_query_batch_std": 21.812541007995605, "action_query_norm": 927.6699035644531, "action_relation_loss": 0.0017031349707394838, "auxiliary_loss_weight": 1.0, "epoch": 27.689429373246025, "flow_matching_loss": 0.014023513440042734, "grad_norm": 0.08443664014339447, "invalid_tail_samples": 25.4, "learning_rate": 4.883914638636467e-08, "loss": 0.0157, "positive_teacher_pairs": 26477.0, "relation_loss": 0.0017031349707394838, "selected_pairs": 26477.0, "step": 29600, "student_distance_mean": 1257.19580078125, "teacher_distance_mean": 0.8489549458026886, "valid_action_samples": 230.6, "weighted_auxiliary_loss": 0.0017031349707394838, "weighted_relation_loss": 0.0017031349707394838 }, { "action_query_batch_std": 22.040370750427247, "action_query_norm": 934.5110290527343, "action_relation_loss": 0.0016988725401461124, "auxiliary_loss_weight": 1.0, "epoch": 27.698783910196447, "flow_matching_loss": 0.01390089662745595, "grad_norm": 0.07425909489393234, "invalid_tail_samples": 22.8, "learning_rate": 4.643402354446713e-08, "loss": 0.0156, "positive_teacher_pairs": 27080.7, "relation_loss": 0.0016988725401461124, "selected_pairs": 27080.7, "step": 29610, "student_distance_mean": 1267.995849609375, "teacher_distance_mean": 0.8545102655887604, "valid_action_samples": 233.2, "weighted_auxiliary_loss": 0.0016988725401461124, "weighted_relation_loss": 0.0016988725401461124 }, { "action_query_batch_std": 22.205657386779784, "action_query_norm": 939.6778442382813, "action_relation_loss": 0.0017338861827738584, "auxiliary_loss_weight": 1.0, "epoch": 27.708138447146865, "flow_matching_loss": 0.015121655631810426, "grad_norm": 0.10656613856554031, "invalid_tail_samples": 23.1, "learning_rate": 4.4089598995544766e-08, "loss": 0.0169, "positive_teacher_pairs": 27015.6, "relation_loss": 0.0017338861827738584, "selected_pairs": 27015.6, "step": 29620, "student_distance_mean": 1274.3273559570312, "teacher_distance_mean": 0.8605853974819183, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.0017338861827738584, "weighted_relation_loss": 0.0017338861827738584 }, { "action_query_batch_std": 22.063256454467773, "action_query_norm": 934.3002136230468, "action_relation_loss": 0.001759824377950281, "auxiliary_loss_weight": 1.0, "epoch": 27.717492984097287, "flow_matching_loss": 0.013095973897725344, "grad_norm": 0.08066322654485703, "invalid_tail_samples": 23.7, "learning_rate": 4.180587558829663e-08, "loss": 0.0149, "positive_teacher_pairs": 26874.9, "relation_loss": 0.001759824377950281, "selected_pairs": 26874.9, "step": 29630, "student_distance_mean": 1270.0100952148437, "teacher_distance_mean": 0.8570815920829773, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.001759824377950281, "weighted_relation_loss": 0.001759824377950281 }, { "action_query_batch_std": 21.918530082702638, "action_query_norm": 929.2615234375, "action_relation_loss": 0.0017868056311272085, "auxiliary_loss_weight": 1.0, "epoch": 27.72684752104771, "flow_matching_loss": 0.016146472562104462, "grad_norm": 0.12348508089780807, "invalid_tail_samples": 23.9, "learning_rate": 3.958285609765855e-08, "loss": 0.0179, "positive_teacher_pairs": 26825.2, "relation_loss": 0.0017868056311272085, "selected_pairs": 26825.2, "step": 29640, "student_distance_mean": 1263.9096069335938, "teacher_distance_mean": 0.8526329517364502, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0017868056311272085, "weighted_relation_loss": 0.0017868056311272085 }, { "action_query_batch_std": 21.988274383544923, "action_query_norm": 933.0316833496094, "action_relation_loss": 0.0017198070185258985, "auxiliary_loss_weight": 1.0, "epoch": 27.736202057998128, "flow_matching_loss": 0.013705622218549252, "grad_norm": 0.09586029499769211, "invalid_tail_samples": 24.3, "learning_rate": 3.74205432248087e-08, "loss": 0.0154, "positive_teacher_pairs": 26736.3, "relation_loss": 0.0017198070185258985, "selected_pairs": 26736.3, "step": 29650, "student_distance_mean": 1264.2486572265625, "teacher_distance_mean": 0.8519802629947663, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0017198070185258985, "weighted_relation_loss": 0.0017198070185258985 }, { "action_query_batch_std": 21.605890846252443, "action_query_norm": 920.4463439941406, "action_relation_loss": 0.0017700741067528726, "auxiliary_loss_weight": 1.0, "epoch": 27.74555659494855, "flow_matching_loss": 0.013939045742154122, "grad_norm": 0.10007119923830032, "invalid_tail_samples": 24.2, "learning_rate": 3.531893959716204e-08, "loss": 0.0157, "positive_teacher_pairs": 26763.2, "relation_loss": 0.0017700741067528726, "selected_pairs": 26763.2, "step": 29660, "student_distance_mean": 1241.0139282226562, "teacher_distance_mean": 0.8367544889450074, "valid_action_samples": 231.8, "weighted_auxiliary_loss": 0.0017700741067528726, "weighted_relation_loss": 0.0017700741067528726 }, { "action_query_batch_std": 22.099031066894533, "action_query_norm": 935.3648620605469, "action_relation_loss": 0.0017221127054654062, "auxiliary_loss_weight": 1.0, "epoch": 27.75491113189897, "flow_matching_loss": 0.015680888295173646, "grad_norm": 0.08502696454524994, "invalid_tail_samples": 23.9, "learning_rate": 3.327804776837029e-08, "loss": 0.0174, "positive_teacher_pairs": 26829.4, "relation_loss": 0.0017221127054654062, "selected_pairs": 26829.4, "step": 29670, "student_distance_mean": 1275.4865844726562, "teacher_distance_mean": 0.8606666564941406, "valid_action_samples": 232.1, "weighted_auxiliary_loss": 0.0017221127054654062, "weighted_relation_loss": 0.0017221127054654062 }, { "action_query_batch_std": 21.881020927429198, "action_query_norm": 928.1545104980469, "action_relation_loss": 0.0017519523156806827, "auxiliary_loss_weight": 1.0, "epoch": 27.764265668849394, "flow_matching_loss": 0.013913367595523595, "grad_norm": 0.07369309663772583, "invalid_tail_samples": 22.6, "learning_rate": 3.129787021829977e-08, "loss": 0.0157, "positive_teacher_pairs": 27131.7, "relation_loss": 0.0017519523156806827, "selected_pairs": 27131.7, "step": 29680, "student_distance_mean": 1258.3430541992188, "teacher_distance_mean": 0.8477837264537811, "valid_action_samples": 233.4, "weighted_auxiliary_loss": 0.0017519523156806827, "weighted_relation_loss": 0.0017519523156806827 }, { "action_query_batch_std": 21.754586029052735, "action_query_norm": 927.4845153808594, "action_relation_loss": 0.0017641178681515157, "auxiliary_loss_weight": 1.0, "epoch": 27.773620205799812, "flow_matching_loss": 0.014105310849845409, "grad_norm": 0.07407518476247787, "invalid_tail_samples": 23.2, "learning_rate": 2.9378409353059133e-08, "loss": 0.0159, "positive_teacher_pairs": 26986.1, "relation_loss": 0.0017641178681515157, "selected_pairs": 26986.1, "step": 29690, "student_distance_mean": 1256.74970703125, "teacher_distance_mean": 0.8483591854572297, "valid_action_samples": 232.8, "weighted_auxiliary_loss": 0.0017641178681515157, "weighted_relation_loss": 0.0017641178681515157 }, { "action_query_batch_std": 21.851467323303222, "action_query_norm": 927.8584777832032, "action_relation_loss": 0.001711980951949954, "auxiliary_loss_weight": 1.0, "epoch": 27.782974742750234, "flow_matching_loss": 0.015546879824250936, "grad_norm": 0.08001038432121277, "invalid_tail_samples": 22.5, "learning_rate": 2.7519667504971593e-08, "loss": 0.0173, "positive_teacher_pairs": 27147.4, "relation_loss": 0.001711980951949954, "selected_pairs": 27147.4, "step": 29700, "student_distance_mean": 1253.9442260742187, "teacher_distance_mean": 0.8459338366985321, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.001711980951949954, "weighted_relation_loss": 0.001711980951949954 }, { "action_query_batch_std": 22.254670715332033, "action_query_norm": 938.3911315917969, "action_relation_loss": 0.001686203619465232, "auxiliary_loss_weight": 1.0, "epoch": 27.792329279700656, "flow_matching_loss": 0.01420272346585989, "grad_norm": 0.0750046968460083, "invalid_tail_samples": 24.8, "learning_rate": 2.572164693258605e-08, "loss": 0.0159, "positive_teacher_pairs": 26616.7, "relation_loss": 0.001686203619465232, "selected_pairs": 26616.7, "step": 29710, "student_distance_mean": 1275.89765625, "teacher_distance_mean": 0.8612178981304168, "valid_action_samples": 231.2, "weighted_auxiliary_loss": 0.001686203619465232, "weighted_relation_loss": 0.001686203619465232 }, { "action_query_batch_std": 21.81895294189453, "action_query_norm": 927.8649169921875, "action_relation_loss": 0.0018029983970336617, "auxiliary_loss_weight": 1.0, "epoch": 27.801683816651074, "flow_matching_loss": 0.013598269131034613, "grad_norm": 0.07316421717405319, "invalid_tail_samples": 25.8, "learning_rate": 2.3984349820665996e-08, "loss": 0.0154, "positive_teacher_pairs": 26397.5, "relation_loss": 0.0018029983970336617, "selected_pairs": 26397.5, "step": 29720, "student_distance_mean": 1263.7435546875, "teacher_distance_mean": 0.853032261133194, "valid_action_samples": 230.2, "weighted_auxiliary_loss": 0.0018029983970336617, "weighted_relation_loss": 0.0018029983970336617 }, { "action_query_batch_std": 22.185910034179688, "action_query_norm": 937.2789123535156, "action_relation_loss": 0.0017413867521099747, "auxiliary_loss_weight": 1.0, "epoch": 27.811038353601496, "flow_matching_loss": 0.015628468338400127, "grad_norm": 0.09622379392385483, "invalid_tail_samples": 24.3, "learning_rate": 2.2307778280189485e-08, "loss": 0.0174, "positive_teacher_pairs": 26730.5, "relation_loss": 0.0017413867521099747, "selected_pairs": 26730.5, "step": 29730, "student_distance_mean": 1269.4586303710937, "teacher_distance_mean": 0.8557639122009277, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0017413867521099747, "weighted_relation_loss": 0.0017413867521099747 }, { "action_query_batch_std": 21.80807228088379, "action_query_norm": 926.6265014648437, "action_relation_loss": 0.001755677629262209, "auxiliary_loss_weight": 1.0, "epoch": 27.82039289055192, "flow_matching_loss": 0.014395400136709213, "grad_norm": 0.09356653690338135, "invalid_tail_samples": 23.4, "learning_rate": 2.0691934348354704e-08, "loss": 0.0162, "positive_teacher_pairs": 26941.9, "relation_loss": 0.001755677629262209, "selected_pairs": 26941.9, "step": 29740, "student_distance_mean": 1259.2136962890625, "teacher_distance_mean": 0.8490984976291657, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.001755677629262209, "weighted_relation_loss": 0.001755677629262209 }, { "action_query_batch_std": 22.058902168273924, "action_query_norm": 934.499267578125, "action_relation_loss": 0.0017652357812039555, "auxiliary_loss_weight": 1.0, "epoch": 27.82974742750234, "flow_matching_loss": 0.01402304256334901, "grad_norm": 0.07552497833967209, "invalid_tail_samples": 23.0, "learning_rate": 1.9136819988557763e-08, "loss": 0.0158, "positive_teacher_pairs": 27041.0, "relation_loss": 0.0017652357812039555, "selected_pairs": 27041.0, "step": 29750, "student_distance_mean": 1272.3167358398437, "teacher_distance_mean": 0.858797574043274, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.0017652357812039555, "weighted_relation_loss": 0.0017652357812039555 }, { "action_query_batch_std": 21.931501579284667, "action_query_norm": 929.4395202636719, "action_relation_loss": 0.0017248423770070075, "auxiliary_loss_weight": 1.0, "epoch": 27.83910196445276, "flow_matching_loss": 0.01465848246589303, "grad_norm": 0.09755803644657135, "invalid_tail_samples": 23.8, "learning_rate": 1.7642437090414908e-08, "loss": 0.0164, "positive_teacher_pairs": 26848.6, "relation_loss": 0.0017248423770070075, "selected_pairs": 26848.6, "step": 29760, "student_distance_mean": 1262.6969116210937, "teacher_distance_mean": 0.8514629423618316, "valid_action_samples": 232.2, "weighted_auxiliary_loss": 0.0017248423770070075, "weighted_relation_loss": 0.0017248423770070075 }, { "action_query_batch_std": 22.044759368896486, "action_query_norm": 934.4522399902344, "action_relation_loss": 0.001780195243190974, "auxiliary_loss_weight": 1.0, "epoch": 27.84845650140318, "flow_matching_loss": 0.014011899195611476, "grad_norm": 0.09069061279296875, "invalid_tail_samples": 23.0, "learning_rate": 1.6208787469734755e-08, "loss": 0.0158, "positive_teacher_pairs": 27035.4, "relation_loss": 0.001780195243190974, "selected_pairs": 27035.4, "step": 29770, "student_distance_mean": 1267.4557495117188, "teacher_distance_mean": 0.854973566532135, "valid_action_samples": 233.0, "weighted_auxiliary_loss": 0.001780195243190974, "weighted_relation_loss": 0.001780195243190974 }, { "action_query_batch_std": 22.201713943481444, "action_query_norm": 937.8564025878907, "action_relation_loss": 0.001785230590030551, "auxiliary_loss_weight": 1.0, "epoch": 27.857811038353603, "flow_matching_loss": 0.013854040578007699, "grad_norm": 0.0800781399011612, "invalid_tail_samples": 25.3, "learning_rate": 1.483587286854604e-08, "loss": 0.0156, "positive_teacher_pairs": 26507.4, "relation_loss": 0.001785230590030551, "selected_pairs": 26507.4, "step": 29780, "student_distance_mean": 1270.7829467773438, "teacher_distance_mean": 0.8578691482543945, "valid_action_samples": 230.7, "weighted_auxiliary_loss": 0.001785230590030551, "weighted_relation_loss": 0.001785230590030551 }, { "action_query_batch_std": 22.032797241210936, "action_query_norm": 932.2096435546875, "action_relation_loss": 0.001715031056664884, "auxiliary_loss_weight": 1.0, "epoch": 27.86716557530402, "flow_matching_loss": 0.014423512946814298, "grad_norm": 0.10887026786804199, "invalid_tail_samples": 23.6, "learning_rate": 1.3523694955064336e-08, "loss": 0.0161, "positive_teacher_pairs": 26895.5, "relation_loss": 0.001715031056664884, "selected_pairs": 26895.5, "step": 29790, "student_distance_mean": 1268.4073852539063, "teacher_distance_mean": 0.8555575609207153, "valid_action_samples": 232.4, "weighted_auxiliary_loss": 0.001715031056664884, "weighted_relation_loss": 0.001715031056664884 }, { "action_query_batch_std": 22.1559196472168, "action_query_norm": 938.1764770507813, "action_relation_loss": 0.0017349314992316067, "auxiliary_loss_weight": 1.0, "epoch": 27.876520112254443, "flow_matching_loss": 0.014440679457038641, "grad_norm": 0.05803079158067703, "invalid_tail_samples": 21.1, "learning_rate": 1.2272255323708681e-08, "loss": 0.0162, "positive_teacher_pairs": 27479.5, "relation_loss": 0.0017349314992316067, "selected_pairs": 27479.5, "step": 29800, "student_distance_mean": 1276.9026977539063, "teacher_distance_mean": 0.8608908712863922, "valid_action_samples": 234.9, "weighted_auxiliary_loss": 0.0017349314992316067, "weighted_relation_loss": 0.0017349314992316067 }, { "action_query_batch_std": 21.97595157623291, "action_query_norm": 929.9289916992187, "action_relation_loss": 0.0017496985732577742, "auxiliary_loss_weight": 1.0, "epoch": 27.885874649204865, "flow_matching_loss": 0.015924660209566354, "grad_norm": 0.07397548854351044, "invalid_tail_samples": 22.9, "learning_rate": 1.1081555495096042e-08, "loss": 0.0177, "positive_teacher_pairs": 27056.0, "relation_loss": 0.0017496985732577742, "selected_pairs": 27056.0, "step": 29810, "student_distance_mean": 1265.1114013671875, "teacher_distance_mean": 0.8541914939880371, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.0017496985732577742, "weighted_relation_loss": 0.0017496985732577742 }, { "action_query_batch_std": 22.071398162841795, "action_query_norm": 934.6842468261718, "action_relation_loss": 0.0016933437203988434, "auxiliary_loss_weight": 1.0, "epoch": 27.895229186155284, "flow_matching_loss": 0.014290082361549139, "grad_norm": 0.08847682923078537, "invalid_tail_samples": 24.7, "learning_rate": 9.951596916041306e-09, "loss": 0.016, "positive_teacher_pairs": 26649.5, "relation_loss": 0.0016933437203988434, "selected_pairs": 26649.5, "step": 29820, "student_distance_mean": 1267.75986328125, "teacher_distance_mean": 0.855498480796814, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0016933437203988434, "weighted_relation_loss": 0.0016933437203988434 }, { "action_query_batch_std": 21.91108455657959, "action_query_norm": 928.1366516113281, "action_relation_loss": 0.001738959306385368, "auxiliary_loss_weight": 1.0, "epoch": 27.904583723105706, "flow_matching_loss": 0.014170486945658922, "grad_norm": 0.0916019082069397, "invalid_tail_samples": 23.4, "learning_rate": 8.882380959551739e-09, "loss": 0.0159, "positive_teacher_pairs": 26952.6, "relation_loss": 0.001738959306385368, "selected_pairs": 26952.6, "step": 29830, "student_distance_mean": 1254.5084594726563, "teacher_distance_mean": 0.8454032599925995, "valid_action_samples": 232.6, "weighted_auxiliary_loss": 0.001738959306385368, "weighted_relation_loss": 0.001738959306385368 }, { "action_query_batch_std": 21.956829261779784, "action_query_norm": 931.77744140625, "action_relation_loss": 0.0016640458023175597, "auxiliary_loss_weight": 1.0, "epoch": 27.913938260056128, "flow_matching_loss": 0.01373831145465374, "grad_norm": 0.07551641762256622, "invalid_tail_samples": 23.7, "learning_rate": 7.873908924821428e-09, "loss": 0.0154, "positive_teacher_pairs": 26874.9, "relation_loss": 0.0016640458023175597, "selected_pairs": 26874.9, "step": 29840, "student_distance_mean": 1267.3849853515626, "teacher_distance_mean": 0.854653924703598, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0016640458023175597, "weighted_relation_loss": 0.0016640458023175597 }, { "action_query_batch_std": 22.06707649230957, "action_query_norm": 933.1578796386718, "action_relation_loss": 0.001721266855020076, "auxiliary_loss_weight": 1.0, "epoch": 27.92329279700655, "flow_matching_loss": 0.015547428000718354, "grad_norm": 0.08943187445402145, "invalid_tail_samples": 22.9, "learning_rate": 6.926182037242379e-09, "loss": 0.0173, "positive_teacher_pairs": 27057.3, "relation_loss": 0.001721266855020076, "selected_pairs": 27057.3, "step": 29850, "student_distance_mean": 1264.9134765625, "teacher_distance_mean": 0.8540675580501557, "valid_action_samples": 233.1, "weighted_auxiliary_loss": 0.001721266855020076, "weighted_relation_loss": 0.001721266855020076 }, { "action_query_batch_std": 22.152928352355957, "action_query_norm": 939.5382873535157, "action_relation_loss": 0.0017445168225094676, "auxiliary_loss_weight": 1.0, "epoch": 27.932647333956968, "flow_matching_loss": 0.014148536510765553, "grad_norm": 0.07718367129564285, "invalid_tail_samples": 21.0, "learning_rate": 6.039201448387876e-09, "loss": 0.0159, "positive_teacher_pairs": 27502.6, "relation_loss": 0.0017445168225094676, "selected_pairs": 27502.6, "step": 29860, "student_distance_mean": 1272.85859375, "teacher_distance_mean": 0.8592040240764618, "valid_action_samples": 235.0, "weighted_auxiliary_loss": 0.0017445168225094676, "weighted_relation_loss": 0.0017445168225094676 }, { "action_query_batch_std": 21.836517906188966, "action_query_norm": 927.3145935058594, "action_relation_loss": 0.001782728382386267, "auxiliary_loss_weight": 1.0, "epoch": 27.94200187090739, "flow_matching_loss": 0.016427494958043097, "grad_norm": 0.11432889103889465, "invalid_tail_samples": 20.4, "learning_rate": 5.212968236029125e-09, "loss": 0.0182, "positive_teacher_pairs": 27643.9, "relation_loss": 0.001782728382386267, "selected_pairs": 27643.9, "step": 29870, "student_distance_mean": 1254.9906372070313, "teacher_distance_mean": 0.8466277778148651, "valid_action_samples": 235.6, "weighted_auxiliary_loss": 0.001782728382386267, "weighted_relation_loss": 0.001782728382386267 }, { "action_query_batch_std": 22.459233665466307, "action_query_norm": 946.3840026855469, "action_relation_loss": 0.0017033780342899263, "auxiliary_loss_weight": 1.0, "epoch": 27.951356407857812, "flow_matching_loss": 0.014825744181871414, "grad_norm": 0.07738694548606873, "invalid_tail_samples": 23.7, "learning_rate": 4.447483404118602e-09, "loss": 0.0165, "positive_teacher_pairs": 26883.5, "relation_loss": 0.0017033780342899263, "selected_pairs": 26883.5, "step": 29880, "student_distance_mean": 1291.7508544921875, "teacher_distance_mean": 0.8721532940864563, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0017033780342899263, "weighted_relation_loss": 0.0017033780342899263 }, { "action_query_batch_std": 21.821408843994142, "action_query_norm": 924.3088806152343, "action_relation_loss": 0.001883336273021996, "auxiliary_loss_weight": 1.0, "epoch": 27.96071094480823, "flow_matching_loss": 0.015821829717606307, "grad_norm": 0.09362196922302246, "invalid_tail_samples": 26.7, "learning_rate": 3.742747882784503e-09, "loss": 0.0177, "positive_teacher_pairs": 26183.9, "relation_loss": 0.001883336273021996, "selected_pairs": 26183.9, "step": 29890, "student_distance_mean": 1263.795458984375, "teacher_distance_mean": 0.8529690742492676, "valid_action_samples": 229.3, "weighted_auxiliary_loss": 0.001883336273021996, "weighted_relation_loss": 0.001883336273021996 }, { "action_query_batch_std": 22.180299758911133, "action_query_norm": 937.935546875, "action_relation_loss": 0.0016951761092059315, "auxiliary_loss_weight": 1.0, "epoch": 27.970065481758652, "flow_matching_loss": 0.01416535945609212, "grad_norm": 0.06154535710811615, "invalid_tail_samples": 23.3, "learning_rate": 3.0987625283473987e-09, "loss": 0.0159, "positive_teacher_pairs": 26968.3, "relation_loss": 0.0016951761092059315, "selected_pairs": 26968.3, "step": 29900, "student_distance_mean": 1281.2049560546875, "teacher_distance_mean": 0.8643620312213898, "valid_action_samples": 232.7, "weighted_auxiliary_loss": 0.0016951761092059315, "weighted_relation_loss": 0.0016951761092059315 }, { "action_query_batch_std": 22.072142028808592, "action_query_norm": 936.1207275390625, "action_relation_loss": 0.0017231531324796378, "auxiliary_loss_weight": 1.0, "epoch": 27.979420018709074, "flow_matching_loss": 0.014848039392381907, "grad_norm": 0.089378222823143, "invalid_tail_samples": 24.7, "learning_rate": 2.515528123320232e-09, "loss": 0.0166, "positive_teacher_pairs": 26639.2, "relation_loss": 0.0017231531324796378, "selected_pairs": 26639.2, "step": 29910, "student_distance_mean": 1272.4785278320312, "teacher_distance_mean": 0.8590325891971589, "valid_action_samples": 231.3, "weighted_auxiliary_loss": 0.0017231531324796378, "weighted_relation_loss": 0.0017231531324796378 }, { "action_query_batch_std": 21.999908256530762, "action_query_norm": 933.1412414550781, "action_relation_loss": 0.0017430506180971862, "auxiliary_loss_weight": 1.0, "epoch": 27.988774555659496, "flow_matching_loss": 0.014079730492085218, "grad_norm": 0.08693593740463257, "invalid_tail_samples": 24.3, "learning_rate": 1.9930453763750133e-09, "loss": 0.0158, "positive_teacher_pairs": 26734.2, "relation_loss": 0.0017430506180971862, "selected_pairs": 26734.2, "step": 29920, "student_distance_mean": 1269.2790893554688, "teacher_distance_mean": 0.8551995635032654, "valid_action_samples": 231.7, "weighted_auxiliary_loss": 0.0017430506180971862, "weighted_relation_loss": 0.0017430506180971862 }, { "action_query_batch_std": 22.020097923278808, "action_query_norm": 932.0262268066406, "action_relation_loss": 0.0017300609266385435, "auxiliary_loss_weight": 1.0, "epoch": 27.998129092609915, "flow_matching_loss": 0.015246427617967129, "grad_norm": 0.07633975893259048, "invalid_tail_samples": 24.6, "learning_rate": 1.5313149223872281e-09, "loss": 0.017, "positive_teacher_pairs": 26664.9, "relation_loss": 0.0017300609266385435, "selected_pairs": 26664.9, "step": 29930, "student_distance_mean": 1266.7284545898438, "teacher_distance_mean": 0.8543819487094879, "valid_action_samples": 231.4, "weighted_auxiliary_loss": 0.0017300609266385435, "weighted_relation_loss": 0.0017300609266385435 }, { "action_query_batch_std": 22.0088830947876, "action_query_norm": 936.7771850585938, "action_relation_loss": 0.001740728400181979, "auxiliary_loss_weight": 1.0, "epoch": 28.007483629560337, "flow_matching_loss": 0.01448399294167757, "grad_norm": 0.09357314556837082, "invalid_tail_samples": 20.6, "learning_rate": 1.1303373224025305e-09, "loss": 0.0162, "positive_teacher_pairs": 24608.7, "relation_loss": 0.001740728400181979, "selected_pairs": 24608.7, "step": 29940, "student_distance_mean": 1269.8177001953125, "teacher_distance_mean": 0.8572041511535644, "valid_action_samples": 215.5, "weighted_auxiliary_loss": 0.001740728400181979, "weighted_relation_loss": 0.001740728400181979 }, { "action_query_batch_std": 22.144318771362304, "action_query_norm": 936.4758239746094, "action_relation_loss": 0.0017123606405220926, "auxiliary_loss_weight": 1.0, "epoch": 28.01683816651076, "flow_matching_loss": 0.014313843566924334, "grad_norm": 0.09036807715892792, "invalid_tail_samples": 25.1, "learning_rate": 7.901130636367438e-10, "loss": 0.016, "positive_teacher_pairs": 26558.4, "relation_loss": 0.0017123606405220926, "selected_pairs": 26558.4, "step": 29950, "student_distance_mean": 1274.8627807617188, "teacher_distance_mean": 0.8593349933624268, "valid_action_samples": 230.9, "weighted_auxiliary_loss": 0.0017123606405220926, "weighted_relation_loss": 0.0017123606405220926 }, { "action_query_batch_std": 21.814156913757323, "action_query_norm": 924.3799926757813, "action_relation_loss": 0.001730853656772524, "auxiliary_loss_weight": 1.0, "epoch": 28.026192703461177, "flow_matching_loss": 0.015143449138849973, "grad_norm": 0.07830667495727539, "invalid_tail_samples": 26.5, "learning_rate": 5.106425595036158e-10, "loss": 0.0169, "positive_teacher_pairs": 26233.1, "relation_loss": 0.001730853656772524, "selected_pairs": 26233.1, "step": 29960, "student_distance_mean": 1251.4041137695312, "teacher_distance_mean": 0.8441360831260681, "valid_action_samples": 229.5, "weighted_auxiliary_loss": 0.001730853656772524, "weighted_relation_loss": 0.001730853656772524 }, { "action_query_batch_std": 21.89515438079834, "action_query_norm": 929.9698364257813, "action_relation_loss": 0.0017213037819601596, "auxiliary_loss_weight": 1.0, "epoch": 28.0355472404116, "flow_matching_loss": 0.014121380820870399, "grad_norm": 0.0917702168226242, "invalid_tail_samples": 23.7, "learning_rate": 2.9192614958706286e-10, "loss": 0.0158, "positive_teacher_pairs": 26875.3, "relation_loss": 0.0017213037819601596, "selected_pairs": 26875.3, "step": 29970, "student_distance_mean": 1266.2725463867187, "teacher_distance_mean": 0.8534406065940857, "valid_action_samples": 232.3, "weighted_auxiliary_loss": 0.0017213037819601596, "weighted_relation_loss": 0.0017213037819601596 }, { "action_query_batch_std": 22.273439788818358, "action_query_norm": 941.7827392578125, "action_relation_loss": 0.001686085422988981, "auxiliary_loss_weight": 1.0, "epoch": 28.04490177736202, "flow_matching_loss": 0.014362641796469688, "grad_norm": 0.09084833413362503, "invalid_tail_samples": 24.0, "learning_rate": 1.3396409964117064e-10, "loss": 0.016, "positive_teacher_pairs": 26808.6, "relation_loss": 0.001686085422988981, "selected_pairs": 26808.6, "step": 29980, "student_distance_mean": 1286.021435546875, "teacher_distance_mean": 0.868180763721466, "valid_action_samples": 232.0, "weighted_auxiliary_loss": 0.001686085422988981, "weighted_relation_loss": 0.001686085422988981 }, { "action_query_batch_std": 22.057555198669434, "action_query_norm": 934.7302612304687, "action_relation_loss": 0.001701758790295571, "auxiliary_loss_weight": 1.0, "epoch": 28.054256314312443, "flow_matching_loss": 0.01361939162015915, "grad_norm": 0.07112231850624084, "invalid_tail_samples": 22.5, "learning_rate": 3.6756601606846574e-11, "loss": 0.0153, "positive_teacher_pairs": 27151.3, "relation_loss": 0.001701758790295571, "selected_pairs": 27151.3, "step": 29990, "student_distance_mean": 1268.7133911132812, "teacher_distance_mean": 0.8565080225467682, "valid_action_samples": 233.5, "weighted_auxiliary_loss": 0.001701758790295571, "weighted_relation_loss": 0.001701758790295571 }, { "action_query_batch_std": 21.98136348724365, "action_query_norm": 930.8185363769531, "action_relation_loss": 0.001831626461353153, "auxiliary_loss_weight": 1.0, "epoch": 28.06361085126286, "flow_matching_loss": 0.01525414725765586, "grad_norm": 0.09926923364400864, "invalid_tail_samples": 23.1, "learning_rate": 3.0377360626943076e-13, "loss": 0.0171, "positive_teacher_pairs": 27014.0, "relation_loss": 0.001831626461353153, "selected_pairs": 27014.0, "step": 30000, "student_distance_mean": 1263.6744262695313, "teacher_distance_mean": 0.8537414073944092, "valid_action_samples": 232.9, "weighted_auxiliary_loss": 0.001831626461353153, "weighted_relation_loss": 0.001831626461353153 }, { "epoch": 28.06361085126286, "step": 30000, "total_flos": 0.0, "train_loss": 0.04247494149804115, "train_runtime": 58456.8409, "train_samples_per_second": 131.379, "train_steps_per_second": 0.513 } ], "logging_steps": 10, "max_steps": 30000, "num_input_tokens_seen": 0, "num_train_epochs": 29, "save_steps": 10000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 256, "trial_name": null, "trial_params": null }