{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 1163, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.021505376344086023, "grad_norm": 0.20223873853683472, "learning_rate": 0.00019587274290627687, "loss": 0.684, "step": 25 }, { "epoch": 0.043010752688172046, "grad_norm": 0.15471471846103668, "learning_rate": 0.00019157351676698194, "loss": 0.5158, "step": 50 }, { "epoch": 0.06451612903225806, "grad_norm": 0.18991973996162415, "learning_rate": 0.00018727429062768703, "loss": 0.4924, "step": 75 }, { "epoch": 0.08602150537634409, "grad_norm": 0.14841178059577942, "learning_rate": 0.0001829750644883921, "loss": 0.4843, "step": 100 }, { "epoch": 0.10752688172043011, "grad_norm": 0.14833126962184906, "learning_rate": 0.00017867583834909717, "loss": 0.482, "step": 125 }, { "epoch": 0.12903225806451613, "grad_norm": 0.12203475832939148, "learning_rate": 0.00017437661220980223, "loss": 0.4834, "step": 150 }, { "epoch": 0.15053763440860216, "grad_norm": 0.15162743628025055, "learning_rate": 0.00017007738607050733, "loss": 0.4785, "step": 175 }, { "epoch": 0.17204301075268819, "grad_norm": 0.13962391018867493, "learning_rate": 0.0001657781599312124, "loss": 0.494, "step": 200 }, { "epoch": 0.1935483870967742, "grad_norm": 0.1615317463874817, "learning_rate": 0.00016147893379191746, "loss": 0.4665, "step": 225 }, { "epoch": 0.21505376344086022, "grad_norm": 0.18397337198257446, "learning_rate": 0.00015717970765262253, "loss": 0.4894, "step": 250 }, { "epoch": 0.23655913978494625, "grad_norm": 0.13035638630390167, "learning_rate": 0.00015288048151332762, "loss": 0.4757, "step": 275 }, { "epoch": 0.25806451612903225, "grad_norm": 0.14732472598552704, "learning_rate": 0.0001485812553740327, "loss": 0.4752, "step": 300 }, { "epoch": 0.27956989247311825, "grad_norm": 0.14634062349796295, "learning_rate": 0.00014428202923473776, "loss": 0.4828, "step": 325 }, { "epoch": 0.3010752688172043, "grad_norm": 0.13563473522663116, "learning_rate": 0.00013998280309544282, "loss": 0.4875, "step": 350 }, { "epoch": 0.3225806451612903, "grad_norm": 0.18935735523700714, "learning_rate": 0.00013568357695614792, "loss": 0.477, "step": 375 }, { "epoch": 0.34408602150537637, "grad_norm": 0.12452180683612823, "learning_rate": 0.00013138435081685296, "loss": 0.4759, "step": 400 }, { "epoch": 0.3655913978494624, "grad_norm": 0.11475691199302673, "learning_rate": 0.00012708512467755805, "loss": 0.4701, "step": 425 }, { "epoch": 0.3870967741935484, "grad_norm": 0.15240037441253662, "learning_rate": 0.00012278589853826312, "loss": 0.4633, "step": 450 }, { "epoch": 0.40860215053763443, "grad_norm": 0.13332103192806244, "learning_rate": 0.0001184866723989682, "loss": 0.4764, "step": 475 }, { "epoch": 0.43010752688172044, "grad_norm": 0.12083959579467773, "learning_rate": 0.00011418744625967325, "loss": 0.4641, "step": 500 }, { "epoch": 0.45161290322580644, "grad_norm": 0.13380204141139984, "learning_rate": 0.00010988822012037833, "loss": 0.4694, "step": 525 }, { "epoch": 0.4731182795698925, "grad_norm": 0.12465644627809525, "learning_rate": 0.00010558899398108341, "loss": 0.4688, "step": 550 }, { "epoch": 0.4946236559139785, "grad_norm": 0.11857310682535172, "learning_rate": 0.00010128976784178847, "loss": 0.4652, "step": 575 }, { "epoch": 0.5161290322580645, "grad_norm": 0.12590761482715607, "learning_rate": 9.699054170249355e-05, "loss": 0.478, "step": 600 }, { "epoch": 0.5376344086021505, "grad_norm": 0.1139000728726387, "learning_rate": 9.269131556319863e-05, "loss": 0.4507, "step": 625 }, { "epoch": 0.5591397849462365, "grad_norm": 0.12646405398845673, "learning_rate": 8.83920894239037e-05, "loss": 0.4802, "step": 650 }, { "epoch": 0.5806451612903226, "grad_norm": 0.12067534774541855, "learning_rate": 8.409286328460876e-05, "loss": 0.4775, "step": 675 }, { "epoch": 0.6021505376344086, "grad_norm": 0.13150258362293243, "learning_rate": 7.979363714531384e-05, "loss": 0.4916, "step": 700 }, { "epoch": 0.6236559139784946, "grad_norm": 0.11777201294898987, "learning_rate": 7.549441100601891e-05, "loss": 0.5076, "step": 725 }, { "epoch": 0.6451612903225806, "grad_norm": 0.1362081915140152, "learning_rate": 7.119518486672399e-05, "loss": 0.4737, "step": 750 }, { "epoch": 0.6666666666666666, "grad_norm": 0.13432231545448303, "learning_rate": 6.689595872742906e-05, "loss": 0.4659, "step": 775 }, { "epoch": 0.6881720430107527, "grad_norm": 0.11704669147729874, "learning_rate": 6.259673258813414e-05, "loss": 0.4635, "step": 800 }, { "epoch": 0.7096774193548387, "grad_norm": 0.13714410364627838, "learning_rate": 5.829750644883921e-05, "loss": 0.4668, "step": 825 }, { "epoch": 0.7311827956989247, "grad_norm": 0.1475558876991272, "learning_rate": 5.399828030954428e-05, "loss": 0.4802, "step": 850 }, { "epoch": 0.7526881720430108, "grad_norm": 0.13451053202152252, "learning_rate": 4.969905417024936e-05, "loss": 0.4758, "step": 875 }, { "epoch": 0.7741935483870968, "grad_norm": 0.1707237958908081, "learning_rate": 4.539982803095443e-05, "loss": 0.4721, "step": 900 }, { "epoch": 0.7956989247311828, "grad_norm": 0.11293122917413712, "learning_rate": 4.11006018916595e-05, "loss": 0.4455, "step": 925 }, { "epoch": 0.8172043010752689, "grad_norm": 0.15928679704666138, "learning_rate": 3.6801375752364576e-05, "loss": 0.4672, "step": 950 }, { "epoch": 0.8387096774193549, "grad_norm": 0.11904233694076538, "learning_rate": 3.250214961306965e-05, "loss": 0.4583, "step": 975 }, { "epoch": 0.8602150537634409, "grad_norm": 0.1470075398683548, "learning_rate": 2.8202923473774723e-05, "loss": 0.466, "step": 1000 }, { "epoch": 0.8817204301075269, "grad_norm": 0.14105826616287231, "learning_rate": 2.3903697334479794e-05, "loss": 0.4623, "step": 1025 }, { "epoch": 0.9032258064516129, "grad_norm": 0.1548405885696411, "learning_rate": 1.9604471195184867e-05, "loss": 0.4675, "step": 1050 }, { "epoch": 0.9247311827956989, "grad_norm": 0.1382945477962494, "learning_rate": 1.530524505588994e-05, "loss": 0.462, "step": 1075 }, { "epoch": 0.946236559139785, "grad_norm": 0.13733048737049103, "learning_rate": 1.1006018916595013e-05, "loss": 0.4852, "step": 1100 }, { "epoch": 0.967741935483871, "grad_norm": 0.13711115717887878, "learning_rate": 6.706792777300086e-06, "loss": 0.4524, "step": 1125 }, { "epoch": 0.989247311827957, "grad_norm": 0.13078077137470245, "learning_rate": 2.407566638005159e-06, "loss": 0.4582, "step": 1150 } ], "logging_steps": 25, "max_steps": 1163, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.064873996845056e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }