| { |
| "results": { |
| "unseen_lanes": { |
| "accuracy": 0.9304995345950977, |
| "random_baseline": 0.2137126998901743, |
| "n": 3223, |
| "by_n_routes": { |
| "2": { |
| "acc": 0.954954954954955, |
| "n": 111 |
| }, |
| "4": { |
| "acc": 0.9449877750611247, |
| "n": 818 |
| }, |
| "5": { |
| "acc": 0.9423076923076923, |
| "n": 624 |
| }, |
| "8": { |
| "acc": 0.9341317365269461, |
| "n": 334 |
| }, |
| "3": { |
| "acc": 0.9104938271604939, |
| "n": 324 |
| }, |
| "7": { |
| "acc": 0.907928388746803, |
| "n": 391 |
| }, |
| "6": { |
| "acc": 0.9224952741020794, |
| "n": 529 |
| }, |
| "9": { |
| "acc": 0.8913043478260869, |
| "n": 92 |
| } |
| }, |
| "by_difficulty": { |
| "easy": { |
| "acc": 0.9478603049680275, |
| "n": 2033 |
| }, |
| "hard": { |
| "acc": 0.9008403361344538, |
| "n": 1190 |
| } |
| }, |
| "by_mode": { |
| "topical": { |
| "acc": 0.884, |
| "n": 1500 |
| }, |
| "mixed": { |
| "acc": 0.9772549019607844, |
| "n": 1275 |
| }, |
| "axis": { |
| "acc": 0.953125, |
| "n": 448 |
| } |
| } |
| }, |
| "unseen_domain": { |
| "accuracy": 0.6976068889556424, |
| "random_baseline": 0.25206113185236045, |
| "n": 9987, |
| "by_n_routes": { |
| "5": { |
| "acc": 0.6869671132764921, |
| "n": 1642 |
| }, |
| "4": { |
| "acc": 0.727150084317032, |
| "n": 2965 |
| }, |
| "3": { |
| "acc": 0.7427476737821566, |
| "n": 1827 |
| }, |
| "2": { |
| "acc": 0.7923497267759563, |
| "n": 915 |
| }, |
| "6": { |
| "acc": 0.6202393906420022, |
| "n": 919 |
| }, |
| "7": { |
| "acc": 0.5959595959595959, |
| "n": 792 |
| }, |
| "8": { |
| "acc": 0.5976608187134503, |
| "n": 855 |
| }, |
| "9": { |
| "acc": 0.6666666666666666, |
| "n": 72 |
| } |
| }, |
| "by_difficulty": { |
| "easy": { |
| "acc": 0.6926144520657203, |
| "n": 6269 |
| }, |
| "hard": { |
| "acc": 0.7060247444862829, |
| "n": 3718 |
| } |
| }, |
| "by_mode": { |
| "topical": { |
| "acc": 0.6976068889556424, |
| "n": 9987 |
| } |
| } |
| }, |
| "unseen_axis": { |
| "accuracy": 0.6129888942539836, |
| "random_baseline": 0.23578575644002975, |
| "n": 12426, |
| "by_n_routes": { |
| "4": { |
| "acc": 0.541494632535095, |
| "n": 4844 |
| }, |
| "5": { |
| "acc": 0.6220699603317706, |
| "n": 2773 |
| }, |
| "3": { |
| "acc": 0.6389937106918239, |
| "n": 2385 |
| }, |
| "6": { |
| "acc": 0.7419898819561551, |
| "n": 1186 |
| }, |
| "7": { |
| "acc": 0.7033898305084746, |
| "n": 944 |
| }, |
| "8": { |
| "acc": 0.6836734693877551, |
| "n": 294 |
| } |
| }, |
| "by_difficulty": { |
| "hard": { |
| "acc": 0.6019339242546333, |
| "n": 4964 |
| }, |
| "easy": { |
| "acc": 0.6203430715625837, |
| "n": 7462 |
| } |
| }, |
| "by_mode": { |
| "axis": { |
| "acc": 0.6129888942539836, |
| "n": 12426 |
| } |
| } |
| }, |
| "hard": { |
| "accuracy": 0.9008403361344538, |
| "random_baseline": 0.21085734293717487, |
| "n": 1190, |
| "by_n_routes": { |
| "4": { |
| "acc": 0.9182156133828996, |
| "n": 269 |
| }, |
| "5": { |
| "acc": 0.9043824701195219, |
| "n": 251 |
| }, |
| "8": { |
| "acc": 0.9291338582677166, |
| "n": 127 |
| }, |
| "3": { |
| "acc": 0.8571428571428571, |
| "n": 126 |
| }, |
| "7": { |
| "acc": 0.8662420382165605, |
| "n": 157 |
| }, |
| "6": { |
| "acc": 0.9045226130653267, |
| "n": 199 |
| }, |
| "2": { |
| "acc": 1.0, |
| "n": 34 |
| }, |
| "9": { |
| "acc": 0.8148148148148148, |
| "n": 27 |
| } |
| }, |
| "by_difficulty": { |
| "hard": { |
| "acc": 0.9008403361344538, |
| "n": 1190 |
| } |
| }, |
| "by_mode": { |
| "topical": { |
| "acc": 0.8300180831826401, |
| "n": 553 |
| }, |
| "mixed": { |
| "acc": 0.9680851063829787, |
| "n": 470 |
| }, |
| "axis": { |
| "acc": 0.9461077844311377, |
| "n": 167 |
| } |
| } |
| } |
| }, |
| "base_model": "oddadmix/50M-2048-Emhotob", |
| "formulation": "routing_head", |
| "log_history": [ |
| { |
| "loss": 0.8975238800048828, |
| "grad_norm": 11.03390121459961, |
| "learning_rate": 7.4625e-05, |
| "epoch": 0.030902348578491966, |
| "step": 200 |
| }, |
| { |
| "loss": 0.47223701477050783, |
| "grad_norm": 11.903738975524902, |
| "learning_rate": 0.000149625, |
| "epoch": 0.06180469715698393, |
| "step": 400 |
| }, |
| { |
| "loss": 0.4622153091430664, |
| "grad_norm": 6.198873996734619, |
| "learning_rate": 0.000224625, |
| "epoch": 0.09270704573547589, |
| "step": 600 |
| }, |
| { |
| "loss": 0.49717689514160157, |
| "grad_norm": 4.740701198577881, |
| "learning_rate": 0.000299625, |
| "epoch": 0.12360939431396786, |
| "step": 800 |
| }, |
| { |
| "loss": 0.4837868118286133, |
| "grad_norm": 3.6331026554107666, |
| "learning_rate": 0.0002998012771863284, |
| "epoch": 0.15451174289245984, |
| "step": 1000 |
| }, |
| { |
| "eval_unseen_lanes_loss": 0.5073266625404358, |
| "eval_unseen_lanes_accuracy": 0.8163201985727583, |
| "eval_unseen_lanes_runtime": 0.5548, |
| "eval_unseen_lanes_samples_per_second": 5809.493, |
| "eval_unseen_lanes_steps_per_second": 91.928, |
| "epoch": 0.15451174289245984, |
| "step": 1000 |
| }, |
| { |
| "eval_unseen_domain_loss": 0.9687234163284302, |
| "eval_unseen_domain_accuracy": 0.6065885651346751, |
| "eval_unseen_domain_runtime": 1.5808, |
| "eval_unseen_domain_samples_per_second": 6317.746, |
| "eval_unseen_domain_steps_per_second": 99.318, |
| "epoch": 0.15451174289245984, |
| "step": 1000 |
| }, |
| { |
| "eval_unseen_axis_loss": 1.1325784921646118, |
| "eval_unseen_axis_accuracy": 0.5135200386286818, |
| "eval_unseen_axis_runtime": 1.2551, |
| "eval_unseen_axis_samples_per_second": 9900.252, |
| "eval_unseen_axis_steps_per_second": 155.364, |
| "epoch": 0.15451174289245984, |
| "step": 1000 |
| }, |
| { |
| "eval_hard_loss": 0.5369061231613159, |
| "eval_hard_accuracy": 0.807563025210084, |
| "eval_hard_runtime": 0.2574, |
| "eval_hard_samples_per_second": 4623.428, |
| "eval_hard_steps_per_second": 73.819, |
| "epoch": 0.15451174289245984, |
| "step": 1000 |
| }, |
| { |
| "loss": 0.4474765396118164, |
| "grad_norm": 9.281235694885254, |
| "learning_rate": 0.00029920164204065217, |
| "epoch": 0.18541409147095178, |
| "step": 1200 |
| }, |
| { |
| "loss": 0.4180959320068359, |
| "grad_norm": 6.990286827087402, |
| "learning_rate": 0.00029820269436406154, |
| "epoch": 0.21631644004944375, |
| "step": 1400 |
| }, |
| { |
| "loss": 0.4012123489379883, |
| "grad_norm": 2.00594425201416, |
| "learning_rate": 0.00029680710766818503, |
| "epoch": 0.24721878862793573, |
| "step": 1600 |
| }, |
| { |
| "loss": 0.39807247161865233, |
| "grad_norm": 4.734849452972412, |
| "learning_rate": 0.0002950186170007609, |
| "epoch": 0.27812113720642767, |
| "step": 1800 |
| }, |
| { |
| "loss": 0.37501571655273436, |
| "grad_norm": 2.752845048904419, |
| "learning_rate": 0.0002928420089494242, |
| "epoch": 0.30902348578491967, |
| "step": 2000 |
| }, |
| { |
| "eval_unseen_lanes_loss": 0.406538724899292, |
| "eval_unseen_lanes_accuracy": 0.8569655600372323, |
| "eval_unseen_lanes_runtime": 0.5556, |
| "eval_unseen_lanes_samples_per_second": 5801.001, |
| "eval_unseen_lanes_steps_per_second": 91.794, |
| "epoch": 0.30902348578491967, |
| "step": 2000 |
| }, |
| { |
| "eval_unseen_domain_loss": 1.1472351551055908, |
| "eval_unseen_domain_accuracy": 0.5958746370281366, |
| "eval_unseen_domain_runtime": 1.575, |
| "eval_unseen_domain_samples_per_second": 6340.999, |
| "eval_unseen_domain_steps_per_second": 99.683, |
| "epoch": 0.30902348578491967, |
| "step": 2000 |
| }, |
| { |
| "eval_unseen_axis_loss": 1.353710412979126, |
| "eval_unseen_axis_accuracy": 0.49806856591018833, |
| "eval_unseen_axis_runtime": 1.3077, |
| "eval_unseen_axis_samples_per_second": 9502.1, |
| "eval_unseen_axis_steps_per_second": 149.116, |
| "epoch": 0.30902348578491967, |
| "step": 2000 |
| }, |
| { |
| "eval_hard_loss": 0.4623798727989197, |
| "eval_hard_accuracy": 0.8378151260504202, |
| "eval_hard_runtime": 0.2506, |
| "eval_hard_samples_per_second": 4749.401, |
| "eval_hard_steps_per_second": 75.831, |
| "epoch": 0.30902348578491967, |
| "step": 2000 |
| }, |
| { |
| "loss": 0.3629868316650391, |
| "grad_norm": 3.957963228225708, |
| "learning_rate": 0.0002902831088312284, |
| "epoch": 0.3399258343634116, |
| "step": 2200 |
| }, |
| { |
| "loss": 0.3620159912109375, |
| "grad_norm": 2.070098638534546, |
| "learning_rate": 0.00028734876510218624, |
| "epoch": 0.37082818294190356, |
| "step": 2400 |
| }, |
| { |
| "loss": 0.33227527618408204, |
| "grad_norm": 3.895007371902466, |
| "learning_rate": 0.00028404683102855547, |
| "epoch": 0.40173053152039556, |
| "step": 2600 |
| }, |
| { |
| "loss": 0.3365111541748047, |
| "grad_norm": 3.198639154434204, |
| "learning_rate": 0.0002803861436689221, |
| "epoch": 0.4326328800988875, |
| "step": 2800 |
| }, |
| { |
| "loss": 0.31873382568359376, |
| "grad_norm": 2.5327401161193848, |
| "learning_rate": 0.0002763765002233335, |
| "epoch": 0.4635352286773795, |
| "step": 3000 |
| }, |
| { |
| "eval_unseen_lanes_loss": 0.34330183267593384, |
| "eval_unseen_lanes_accuracy": 0.8836487744337573, |
| "eval_unseen_lanes_runtime": 0.553, |
| "eval_unseen_lanes_samples_per_second": 5828.318, |
| "eval_unseen_lanes_steps_per_second": 92.226, |
| "epoch": 0.4635352286773795, |
| "step": 3000 |
| }, |
| { |
| "eval_unseen_domain_loss": 0.9895414113998413, |
| "eval_unseen_domain_accuracy": 0.6378291779313107, |
| "eval_unseen_domain_runtime": 1.5853, |
| "eval_unseen_domain_samples_per_second": 6299.774, |
| "eval_unseen_domain_steps_per_second": 99.035, |
| "epoch": 0.4635352286773795, |
| "step": 3000 |
| }, |
| { |
| "eval_unseen_axis_loss": 1.0701825618743896, |
| "eval_unseen_axis_accuracy": 0.5737164010944793, |
| "eval_unseen_axis_runtime": 1.2712, |
| "eval_unseen_axis_samples_per_second": 9774.846, |
| "eval_unseen_axis_steps_per_second": 153.396, |
| "epoch": 0.4635352286773795, |
| "step": 3000 |
| }, |
| { |
| "eval_hard_loss": 0.38013485074043274, |
| "eval_hard_accuracy": 0.873109243697479, |
| "eval_hard_runtime": 0.2542, |
| "eval_hard_samples_per_second": 4681.85, |
| "eval_hard_steps_per_second": 74.752, |
| "epoch": 0.4635352286773795, |
| "step": 3000 |
| }, |
| { |
| "loss": 0.29870388031005857, |
| "grad_norm": 2.18878173828125, |
| "learning_rate": 0.00027202863181277745, |
| "epoch": 0.49443757725587145, |
| "step": 3200 |
| }, |
| { |
| "loss": 0.30184398651123046, |
| "grad_norm": 3.0138494968414307, |
| "learning_rate": 0.00026735417475918285, |
| "epoch": 0.5253399258343634, |
| "step": 3400 |
| }, |
| { |
| "loss": 0.32383251190185547, |
| "grad_norm": 7.008852005004883, |
| "learning_rate": 0.00026236563944280554, |
| "epoch": 0.5562422744128553, |
| "step": 3600 |
| }, |
| { |
| "loss": 0.3035639762878418, |
| "grad_norm": 2.690004825592041, |
| "learning_rate": 0.0002570763768203474, |
| "epoch": 0.5871446229913473, |
| "step": 3800 |
| }, |
| { |
| "loss": 0.2934083366394043, |
| "grad_norm": 1.9328616857528687, |
| "learning_rate": 0.0002515005426934173, |
| "epoch": 0.6180469715698393, |
| "step": 4000 |
| }, |
| { |
| "eval_unseen_lanes_loss": 0.30602237582206726, |
| "eval_unseen_lanes_accuracy": 0.8920260626745269, |
| "eval_unseen_lanes_runtime": 0.5511, |
| "eval_unseen_lanes_samples_per_second": 5848.268, |
| "eval_unseen_lanes_steps_per_second": 92.542, |
| "epoch": 0.6180469715698393, |
| "step": 4000 |
| }, |
| { |
| "eval_unseen_domain_loss": 0.983905553817749, |
| "eval_unseen_domain_accuracy": 0.6368278762391109, |
| "eval_unseen_domain_runtime": 1.5835, |
| "eval_unseen_domain_samples_per_second": 6306.791, |
| "eval_unseen_domain_steps_per_second": 99.146, |
| "epoch": 0.6180469715698393, |
| "step": 4000 |
| }, |
| { |
| "eval_unseen_axis_loss": 1.2108259201049805, |
| "eval_unseen_axis_accuracy": 0.5799130854659584, |
| "eval_unseen_axis_runtime": 1.2562, |
| "eval_unseen_axis_samples_per_second": 9891.534, |
| "eval_unseen_axis_steps_per_second": 155.227, |
| "epoch": 0.6180469715698393, |
| "step": 4000 |
| }, |
| { |
| "eval_hard_loss": 0.3655548691749573, |
| "eval_hard_accuracy": 0.8756302521008403, |
| "eval_hard_runtime": 0.2592, |
| "eval_hard_samples_per_second": 4591.918, |
| "eval_hard_steps_per_second": 73.316, |
| "epoch": 0.6180469715698393, |
| "step": 4000 |
| }, |
| { |
| "loss": 0.2829387664794922, |
| "grad_norm": 2.094444513320923, |
| "learning_rate": 0.00024565305982296296, |
| "epoch": 0.6489493201483313, |
| "step": 4200 |
| }, |
| { |
| "loss": 0.2714531135559082, |
| "grad_norm": 2.0051519870758057, |
| "learning_rate": 0.00023954957799106823, |
| "epoch": 0.6798516687268232, |
| "step": 4400 |
| }, |
| { |
| "loss": 0.26623159408569336, |
| "grad_norm": 2.2412750720977783, |
| "learning_rate": 0.00023320643211700308, |
| "epoch": 0.7107540173053152, |
| "step": 4600 |
| }, |
| { |
| "loss": 0.2522362518310547, |
| "grad_norm": 1.7817517518997192, |
| "learning_rate": 0.000226640598539622, |
| "epoch": 0.7416563658838071, |
| "step": 4800 |
| }, |
| { |
| "loss": 0.2480511474609375, |
| "grad_norm": 5.033050537109375, |
| "learning_rate": 0.00021986964958311316, |
| "epoch": 0.7725587144622992, |
| "step": 5000 |
| }, |
| { |
| "eval_unseen_lanes_loss": 0.27606716752052307, |
| "eval_unseen_lanes_accuracy": 0.9053676698727893, |
| "eval_unseen_lanes_runtime": 0.552, |
| "eval_unseen_lanes_samples_per_second": 5838.329, |
| "eval_unseen_lanes_steps_per_second": 92.384, |
| "epoch": 0.7725587144622992, |
| "step": 5000 |
| }, |
| { |
| "eval_unseen_domain_loss": 0.96076899766922, |
| "eval_unseen_domain_accuracy": 0.6541503955141684, |
| "eval_unseen_domain_runtime": 1.5806, |
| "eval_unseen_domain_samples_per_second": 6318.291, |
| "eval_unseen_domain_steps_per_second": 99.326, |
| "epoch": 0.7725587144622992, |
| "step": 5000 |
| }, |
| { |
| "eval_unseen_axis_loss": 1.4210246801376343, |
| "eval_unseen_axis_accuracy": 0.5544825366167713, |
| "eval_unseen_axis_runtime": 1.2599, |
| "eval_unseen_axis_samples_per_second": 9862.704, |
| "eval_unseen_axis_steps_per_second": 154.774, |
| "epoch": 0.7725587144622992, |
| "step": 5000 |
| }, |
| { |
| "eval_hard_loss": 0.3613678812980652, |
| "eval_hard_accuracy": 0.8857142857142857, |
| "eval_hard_runtime": 0.2606, |
| "eval_hard_samples_per_second": 4565.623, |
| "eval_hard_steps_per_second": 72.897, |
| "epoch": 0.7725587144622992, |
| "step": 5000 |
| }, |
| { |
| "loss": 0.24242013931274414, |
| "grad_norm": 2.4511566162109375, |
| "learning_rate": 0.00021291170652769533, |
| "epoch": 0.8034610630407911, |
| "step": 5200 |
| }, |
| { |
| "loss": 0.2558748817443848, |
| "grad_norm": 1.6439733505249023, |
| "learning_rate": 0.00020578539111112834, |
| "epoch": 0.8343634116192831, |
| "step": 5400 |
| }, |
| { |
| "loss": 0.24663785934448243, |
| "grad_norm": 3.4409291744232178, |
| "learning_rate": 0.00019850977569083514, |
| "epoch": 0.865265760197775, |
| "step": 5600 |
| }, |
| { |
| "loss": 0.24483919143676758, |
| "grad_norm": 3.071554183959961, |
| "learning_rate": 0.00019110433220001754, |
| "epoch": 0.896168108776267, |
| "step": 5800 |
| }, |
| { |
| "loss": 0.23662748336791992, |
| "grad_norm": 2.491429567337036, |
| "learning_rate": 0.0001835888800343768, |
| "epoch": 0.927070457354759, |
| "step": 6000 |
| }, |
| { |
| "eval_unseen_lanes_loss": 0.2571614384651184, |
| "eval_unseen_lanes_accuracy": 0.9081600992863792, |
| "eval_unseen_lanes_runtime": 0.5519, |
| "eval_unseen_lanes_samples_per_second": 5839.58, |
| "eval_unseen_lanes_steps_per_second": 92.404, |
| "epoch": 0.927070457354759, |
| "step": 6000 |
| }, |
| { |
| "eval_unseen_domain_loss": 0.9326336979866028, |
| "eval_unseen_domain_accuracy": 0.6525483128066486, |
| "eval_unseen_domain_runtime": 1.5742, |
| "eval_unseen_domain_samples_per_second": 6344.232, |
| "eval_unseen_domain_steps_per_second": 99.734, |
| "epoch": 0.927070457354759, |
| "step": 6000 |
| }, |
| { |
| "eval_unseen_axis_loss": 1.3221510648727417, |
| "eval_unseen_axis_accuracy": 0.5856269113149847, |
| "eval_unseen_axis_runtime": 1.2492, |
| "eval_unseen_axis_samples_per_second": 9946.782, |
| "eval_unseen_axis_steps_per_second": 156.094, |
| "epoch": 0.927070457354759, |
| "step": 6000 |
| }, |
| { |
| "eval_hard_loss": 0.33343571424484253, |
| "eval_hard_accuracy": 0.888235294117647, |
| "eval_hard_runtime": 0.2587, |
| "eval_hard_samples_per_second": 4600.467, |
| "eval_hard_steps_per_second": 73.453, |
| "epoch": 0.927070457354759, |
| "step": 6000 |
| }, |
| { |
| "loss": 0.23579851150512696, |
| "grad_norm": 2.5624895095825195, |
| "learning_rate": 0.00017598353300890969, |
| "epoch": 0.957972805933251, |
| "step": 6200 |
| }, |
| { |
| "loss": 0.21076148986816406, |
| "grad_norm": 0.9841051697731018, |
| "learning_rate": 0.00016830864552674267, |
| "epoch": 0.9888751545117429, |
| "step": 6400 |
| }, |
| { |
| "loss": 0.17771633148193358, |
| "grad_norm": 0.9096925258636475, |
| "learning_rate": 0.00016058475810407297, |
| "epoch": 1.019777503090235, |
| "step": 6600 |
| }, |
| { |
| "loss": 0.14182785034179687, |
| "grad_norm": 3.3751485347747803, |
| "learning_rate": 0.00015283254239701005, |
| "epoch": 1.0506798516687268, |
| "step": 6800 |
| }, |
| { |
| "loss": 0.1347336483001709, |
| "grad_norm": 0.5445594787597656, |
| "learning_rate": 0.00014507274587744398, |
| "epoch": 1.0815822002472189, |
| "step": 7000 |
| }, |
| { |
| "eval_unseen_lanes_loss": 0.2655007839202881, |
| "eval_unseen_lanes_accuracy": 0.9162271175923054, |
| "eval_unseen_lanes_runtime": 0.5535, |
| "eval_unseen_lanes_samples_per_second": 5823.011, |
| "eval_unseen_lanes_steps_per_second": 92.142, |
| "epoch": 1.0815822002472189, |
| "step": 7000 |
| }, |
| { |
| "eval_unseen_domain_loss": 1.0792171955108643, |
| "eval_unseen_domain_accuracy": 0.6691699208971663, |
| "eval_unseen_domain_runtime": 1.5827, |
| "eval_unseen_domain_samples_per_second": 6310.28, |
| "eval_unseen_domain_steps_per_second": 99.2, |
| "epoch": 1.0815822002472189, |
| "step": 7000 |
| }, |
| { |
| "eval_unseen_axis_loss": 1.5451632738113403, |
| "eval_unseen_axis_accuracy": 0.5832930951231289, |
| "eval_unseen_axis_runtime": 1.2555, |
| "eval_unseen_axis_samples_per_second": 9897.184, |
| "eval_unseen_axis_steps_per_second": 155.316, |
| "epoch": 1.0815822002472189, |
| "step": 7000 |
| }, |
| { |
| "eval_hard_loss": 0.3464004695415497, |
| "eval_hard_accuracy": 0.8966386554621849, |
| "eval_hard_runtime": 0.2591, |
| "eval_hard_samples_per_second": 4593.088, |
| "eval_hard_steps_per_second": 73.335, |
| "epoch": 1.0815822002472189, |
| "step": 7000 |
| }, |
| { |
| "loss": 0.13339081764221192, |
| "grad_norm": 2.522960901260376, |
| "learning_rate": 0.00013732613630600555, |
| "epoch": 1.1124845488257107, |
| "step": 7200 |
| }, |
| { |
| "loss": 0.11780735015869141, |
| "grad_norm": 1.1648684740066528, |
| "learning_rate": 0.0001296134461507269, |
| "epoch": 1.1433868974042027, |
| "step": 7400 |
| }, |
| { |
| "loss": 0.13406469345092772, |
| "grad_norm": 1.038225531578064, |
| "learning_rate": 0.00012195531710015758, |
| "epoch": 1.1742892459826946, |
| "step": 7600 |
| }, |
| { |
| "loss": 0.1309179973602295, |
| "grad_norm": 1.6545023918151855, |
| "learning_rate": 0.00011437224481943516, |
| "epoch": 1.2051915945611866, |
| "step": 7800 |
| }, |
| { |
| "loss": 0.13036264419555665, |
| "grad_norm": 1.7858803272247314, |
| "learning_rate": 0.00010688452409716325, |
| "epoch": 1.2360939431396787, |
| "step": 8000 |
| }, |
| { |
| "eval_unseen_lanes_loss": 0.26563557982444763, |
| "eval_unseen_lanes_accuracy": 0.9162271175923054, |
| "eval_unseen_lanes_runtime": 0.5528, |
| "eval_unseen_lanes_samples_per_second": 5830.741, |
| "eval_unseen_lanes_steps_per_second": 92.264, |
| "epoch": 1.2360939431396787, |
| "step": 8000 |
| }, |
| { |
| "eval_unseen_domain_loss": 1.1347131729125977, |
| "eval_unseen_domain_accuracy": 0.6633623710824071, |
| "eval_unseen_domain_runtime": 1.5784, |
| "eval_unseen_domain_samples_per_second": 6327.271, |
| "eval_unseen_domain_steps_per_second": 99.467, |
| "epoch": 1.2360939431396787, |
| "step": 8000 |
| }, |
| { |
| "eval_unseen_axis_loss": 1.7664040327072144, |
| "eval_unseen_axis_accuracy": 0.5963302752293578, |
| "eval_unseen_axis_runtime": 1.2484, |
| "eval_unseen_axis_samples_per_second": 9953.248, |
| "eval_unseen_axis_steps_per_second": 156.195, |
| "epoch": 1.2360939431396787, |
| "step": 8000 |
| }, |
| { |
| "eval_hard_loss": 0.34612923860549927, |
| "eval_hard_accuracy": 0.8957983193277311, |
| "eval_hard_runtime": 0.2561, |
| "eval_hard_samples_per_second": 4646.719, |
| "eval_hard_steps_per_second": 74.191, |
| "epoch": 1.2360939431396787, |
| "step": 8000 |
| }, |
| { |
| "loss": 0.13536205291748046, |
| "grad_norm": 1.5142947435379028, |
| "learning_rate": 9.95121945299005e-05, |
| "epoch": 1.2669962917181705, |
| "step": 8200 |
| }, |
| { |
| "loss": 0.12326237678527832, |
| "grad_norm": 5.0126051902771, |
| "learning_rate": 9.227498688962761e-05, |
| "epoch": 1.2978986402966626, |
| "step": 8400 |
| }, |
| { |
| "loss": 0.12851189613342284, |
| "grad_norm": 3.0441036224365234, |
| "learning_rate": 8.519227031772971e-05, |
| "epoch": 1.3288009888751544, |
| "step": 8600 |
| }, |
| { |
| "loss": 0.11189216613769531, |
| "grad_norm": 1.7037580013275146, |
| "learning_rate": 7.828300048682143e-05, |
| "epoch": 1.3597033374536465, |
| "step": 8800 |
| }, |
| { |
| "loss": 0.12371747016906738, |
| "grad_norm": 0.7055680751800537, |
| "learning_rate": 7.156566886914933e-05, |
| "epoch": 1.3906056860321385, |
| "step": 9000 |
| }, |
| { |
| "eval_unseen_lanes_loss": 0.23261435329914093, |
| "eval_unseen_lanes_accuracy": 0.9221222463543283, |
| "eval_unseen_lanes_runtime": 0.5543, |
| "eval_unseen_lanes_samples_per_second": 5814.13, |
| "eval_unseen_lanes_steps_per_second": 92.001, |
| "epoch": 1.3906056860321385, |
| "step": 9000 |
| }, |
| { |
| "eval_unseen_domain_loss": 0.9834672808647156, |
| "eval_unseen_domain_accuracy": 0.6840893161109443, |
| "eval_unseen_domain_runtime": 1.579, |
| "eval_unseen_domain_samples_per_second": 6324.919, |
| "eval_unseen_domain_steps_per_second": 99.43, |
| "epoch": 1.3906056860321385, |
| "step": 9000 |
| }, |
| { |
| "eval_unseen_axis_loss": 1.5792756080627441, |
| "eval_unseen_axis_accuracy": 0.593996459037502, |
| "eval_unseen_axis_runtime": 1.2867, |
| "eval_unseen_axis_samples_per_second": 9657.248, |
| "eval_unseen_axis_steps_per_second": 151.55, |
| "epoch": 1.3906056860321385, |
| "step": 9000 |
| }, |
| { |
| "eval_hard_loss": 0.31886979937553406, |
| "eval_hard_accuracy": 0.9, |
| "eval_hard_runtime": 0.2641, |
| "eval_hard_samples_per_second": 4505.693, |
| "eval_hard_steps_per_second": 71.94, |
| "epoch": 1.3906056860321385, |
| "step": 9000 |
| }, |
| { |
| "loss": 0.11327756881713867, |
| "grad_norm": 2.5306780338287354, |
| "learning_rate": 6.505825324734749e-05, |
| "epoch": 1.4215080346106304, |
| "step": 9200 |
| }, |
| { |
| "loss": 0.11213048934936523, |
| "grad_norm": 3.7060656547546387, |
| "learning_rate": 5.8778169599994366e-05, |
| "epoch": 1.4524103831891224, |
| "step": 9400 |
| }, |
| { |
| "loss": 0.11299308776855468, |
| "grad_norm": 2.2346725463867188, |
| "learning_rate": 5.274222549074192e-05, |
| "epoch": 1.4833127317676142, |
| "step": 9600 |
| }, |
| { |
| "loss": 0.10625232696533203, |
| "grad_norm": 2.6063334941864014, |
| "learning_rate": 4.696657508576255e-05, |
| "epoch": 1.5142150803461063, |
| "step": 9800 |
| }, |
| { |
| "loss": 0.10512189865112305, |
| "grad_norm": 4.146987438201904, |
| "learning_rate": 4.146667591990211e-05, |
| "epoch": 1.5451174289245984, |
| "step": 10000 |
| }, |
| { |
| "eval_unseen_lanes_loss": 0.2341764271259308, |
| "eval_unseen_lanes_accuracy": 0.9286379149860379, |
| "eval_unseen_lanes_runtime": 0.5514, |
| "eval_unseen_lanes_samples_per_second": 5845.486, |
| "eval_unseen_lanes_steps_per_second": 92.498, |
| "epoch": 1.5451174289245984, |
| "step": 10000 |
| }, |
| { |
| "eval_unseen_domain_loss": 1.1408356428146362, |
| "eval_unseen_domain_accuracy": 0.6845899669570441, |
| "eval_unseen_domain_runtime": 1.5844, |
| "eval_unseen_domain_samples_per_second": 6303.222, |
| "eval_unseen_domain_steps_per_second": 99.089, |
| "epoch": 1.5451174289245984, |
| "step": 10000 |
| }, |
| { |
| "eval_unseen_axis_loss": 1.6913553476333618, |
| "eval_unseen_axis_accuracy": 0.6064703042008691, |
| "eval_unseen_axis_runtime": 1.2705, |
| "eval_unseen_axis_samples_per_second": 9780.492, |
| "eval_unseen_axis_steps_per_second": 153.484, |
| "epoch": 1.5451174289245984, |
| "step": 10000 |
| }, |
| { |
| "eval_hard_loss": 0.3436157703399658, |
| "eval_hard_accuracy": 0.9042016806722689, |
| "eval_hard_runtime": 0.2553, |
| "eval_hard_samples_per_second": 4661.691, |
| "eval_hard_steps_per_second": 74.43, |
| "epoch": 1.5451174289245984, |
| "step": 10000 |
| }, |
| { |
| "loss": 0.10526069641113281, |
| "grad_norm": 1.0956754684448242, |
| "learning_rate": 3.625724752724645e-05, |
| "epoch": 1.5760197775030902, |
| "step": 10200 |
| }, |
| { |
| "loss": 0.0974786376953125, |
| "grad_norm": 1.1272306442260742, |
| "learning_rate": 3.135223204682058e-05, |
| "epoch": 1.6069221260815822, |
| "step": 10400 |
| }, |
| { |
| "loss": 0.101556396484375, |
| "grad_norm": 3.4264066219329834, |
| "learning_rate": 2.6764756908851686e-05, |
| "epoch": 1.637824474660074, |
| "step": 10600 |
| }, |
| { |
| "loss": 0.10870396614074707, |
| "grad_norm": 1.7836824655532837, |
| "learning_rate": 2.2507099701460036e-05, |
| "epoch": 1.6687268232385661, |
| "step": 10800 |
| }, |
| { |
| "loss": 0.09275879859924316, |
| "grad_norm": 1.3714878559112549, |
| "learning_rate": 1.8590655311806385e-05, |
| "epoch": 1.6996291718170582, |
| "step": 11000 |
| }, |
| { |
| "eval_unseen_lanes_loss": 0.21319718658924103, |
| "eval_unseen_lanes_accuracy": 0.9304995345950977, |
| "eval_unseen_lanes_runtime": 0.5553, |
| "eval_unseen_lanes_samples_per_second": 5804.033, |
| "eval_unseen_lanes_steps_per_second": 91.842, |
| "epoch": 1.6996291718170582, |
| "step": 11000 |
| }, |
| { |
| "eval_unseen_domain_loss": 1.022688627243042, |
| "eval_unseen_domain_accuracy": 0.6976068889556424, |
| "eval_unseen_domain_runtime": 1.5825, |
| "eval_unseen_domain_samples_per_second": 6310.792, |
| "eval_unseen_domain_steps_per_second": 99.208, |
| "epoch": 1.6996291718170582, |
| "step": 11000 |
| }, |
| { |
| "eval_unseen_axis_loss": 1.5096590518951416, |
| "eval_unseen_axis_accuracy": 0.6129888942539836, |
| "eval_unseen_axis_runtime": 1.2878, |
| "eval_unseen_axis_samples_per_second": 9649.329, |
| "eval_unseen_axis_steps_per_second": 151.426, |
| "epoch": 1.6996291718170582, |
| "step": 11000 |
| }, |
| { |
| "eval_hard_loss": 0.31117716431617737, |
| "eval_hard_accuracy": 0.9008403361344538, |
| "eval_hard_runtime": 0.2589, |
| "eval_hard_samples_per_second": 4596.879, |
| "eval_hard_steps_per_second": 73.396, |
| "epoch": 1.6996291718170582, |
| "step": 11000 |
| }, |
| { |
| "loss": 0.09593048095703124, |
| "grad_norm": 3.177462100982666, |
| "learning_rate": 1.5025905429636426e-05, |
| "epoch": 1.73053152039555, |
| "step": 11200 |
| }, |
| { |
| "loss": 0.09772712707519532, |
| "grad_norm": 2.102013349533081, |
| "learning_rate": 1.1822390494841139e-05, |
| "epoch": 1.7614338689740419, |
| "step": 11400 |
| }, |
| { |
| "loss": 0.08881115913391113, |
| "grad_norm": 0.3349379897117615, |
| "learning_rate": 8.98868416411046e-06, |
| "epoch": 1.792336217552534, |
| "step": 11600 |
| }, |
| { |
| "loss": 0.09125228881835938, |
| "grad_norm": 1.5826376676559448, |
| "learning_rate": 6.532370365015982e-06, |
| "epoch": 1.823238566131026, |
| "step": 11800 |
| }, |
| { |
| "loss": 0.1032994556427002, |
| "grad_norm": 2.430258274078369, |
| "learning_rate": 4.460022998933166e-06, |
| "epoch": 1.854140914709518, |
| "step": 12000 |
| }, |
| { |
| "eval_unseen_lanes_loss": 0.21029867231845856, |
| "eval_unseen_lanes_accuracy": 0.9329816940738442, |
| "eval_unseen_lanes_runtime": 0.5539, |
| "eval_unseen_lanes_samples_per_second": 5818.497, |
| "eval_unseen_lanes_steps_per_second": 92.071, |
| "epoch": 1.854140914709518, |
| "step": 12000 |
| }, |
| { |
| "eval_unseen_domain_loss": 1.0129146575927734, |
| "eval_unseen_domain_accuracy": 0.700010013016922, |
| "eval_unseen_domain_runtime": 1.5764, |
| "eval_unseen_domain_samples_per_second": 6335.382, |
| "eval_unseen_domain_steps_per_second": 99.595, |
| "epoch": 1.854140914709518, |
| "step": 12000 |
| }, |
| { |
| "eval_unseen_axis_loss": 1.5864043235778809, |
| "eval_unseen_axis_accuracy": 0.6117817479478512, |
| "eval_unseen_axis_runtime": 1.2684, |
| "eval_unseen_axis_samples_per_second": 9796.563, |
| "eval_unseen_axis_steps_per_second": 153.737, |
| "epoch": 1.854140914709518, |
| "step": 12000 |
| }, |
| { |
| "eval_hard_loss": 0.30691978335380554, |
| "eval_hard_accuracy": 0.9084033613445378, |
| "eval_hard_runtime": 0.2602, |
| "eval_hard_samples_per_second": 4573.644, |
| "eval_hard_steps_per_second": 73.025, |
| "epoch": 1.854140914709518, |
| "step": 12000 |
| }, |
| { |
| "loss": 0.08737665176391601, |
| "grad_norm": 1.072799801826477, |
| "learning_rate": 2.7771883471252034e-06, |
| "epoch": 1.8850432632880099, |
| "step": 12200 |
| }, |
| { |
| "loss": 0.08102713584899902, |
| "grad_norm": 1.5238364934921265, |
| "learning_rate": 1.4883702270751197e-06, |
| "epoch": 1.9159456118665017, |
| "step": 12400 |
| }, |
| { |
| "loss": 0.09933463096618653, |
| "grad_norm": 0.16273926198482513, |
| "learning_rate": 5.970179387931151e-07, |
| "epoch": 1.9468479604449938, |
| "step": 12600 |
| }, |
| { |
| "loss": 0.10335576057434082, |
| "grad_norm": 0.17151758074760437, |
| "learning_rate": 1.0551703335823225e-07, |
| "epoch": 1.9777503090234858, |
| "step": 12800 |
| }, |
| { |
| "eval_unseen_lanes_loss": 0.21011516451835632, |
| "eval_unseen_lanes_accuracy": 0.9336022339435309, |
| "eval_unseen_lanes_runtime": 0.5534, |
| "eval_unseen_lanes_samples_per_second": 5823.753, |
| "eval_unseen_lanes_steps_per_second": 92.154, |
| "epoch": 2.0, |
| "step": 12944 |
| }, |
| { |
| "eval_unseen_domain_loss": 1.0266432762145996, |
| "eval_unseen_domain_accuracy": 0.7009111845399019, |
| "eval_unseen_domain_runtime": 1.5817, |
| "eval_unseen_domain_samples_per_second": 6314.155, |
| "eval_unseen_domain_steps_per_second": 99.261, |
| "epoch": 2.0, |
| "step": 12944 |
| }, |
| { |
| "eval_unseen_axis_loss": 1.6092302799224854, |
| "eval_unseen_axis_accuracy": 0.6111379365845807, |
| "eval_unseen_axis_runtime": 1.2767, |
| "eval_unseen_axis_samples_per_second": 9732.892, |
| "eval_unseen_axis_steps_per_second": 152.737, |
| "epoch": 2.0, |
| "step": 12944 |
| }, |
| { |
| "eval_hard_loss": 0.3078996539115906, |
| "eval_hard_accuracy": 0.9084033613445378, |
| "eval_hard_runtime": 0.2718, |
| "eval_hard_samples_per_second": 4377.996, |
| "eval_hard_steps_per_second": 69.901, |
| "epoch": 2.0, |
| "step": 12944 |
| }, |
| { |
| "train_runtime": 262.1825, |
| "train_samples_per_second": 1579.793, |
| "train_steps_per_second": 49.37, |
| "total_flos": 0.0, |
| "train_loss": 0.2282541081106707, |
| "epoch": 2.0, |
| "step": 12944 |
| } |
| ] |
| } |
