| { | |
| "best_metric": 0.20468038320541382, | |
| "best_model_checkpoint": "autotrain-o5mxr-bsop6/checkpoint-753", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 753, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.099601593625498, | |
| "grad_norm": 5.523846626281738, | |
| "learning_rate": 1.6447368421052635e-05, | |
| "loss": 1.3608, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.199203187250996, | |
| "grad_norm": 4.111423969268799, | |
| "learning_rate": 3.289473684210527e-05, | |
| "loss": 1.0428, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.29880478087649404, | |
| "grad_norm": 5.932701110839844, | |
| "learning_rate": 4.9342105263157894e-05, | |
| "loss": 0.824, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.398406374501992, | |
| "grad_norm": 14.16284465789795, | |
| "learning_rate": 4.82274741506647e-05, | |
| "loss": 0.8565, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.49800796812749004, | |
| "grad_norm": 7.437353610992432, | |
| "learning_rate": 4.638109305760709e-05, | |
| "loss": 0.7849, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5976095617529881, | |
| "grad_norm": 14.002378463745117, | |
| "learning_rate": 4.453471196454949e-05, | |
| "loss": 0.6819, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6972111553784861, | |
| "grad_norm": 7.128929138183594, | |
| "learning_rate": 4.2688330871491875e-05, | |
| "loss": 0.9145, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.796812749003984, | |
| "grad_norm": 7.11976432800293, | |
| "learning_rate": 4.084194977843427e-05, | |
| "loss": 0.7596, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.896414342629482, | |
| "grad_norm": 10.390266418457031, | |
| "learning_rate": 3.8995568685376664e-05, | |
| "loss": 0.704, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.9960159362549801, | |
| "grad_norm": 8.346457481384277, | |
| "learning_rate": 3.714918759231906e-05, | |
| "loss": 0.6437, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8041958041958042, | |
| "eval_f1_macro": 0.36845586105500655, | |
| "eval_f1_micro": 0.8041958041958042, | |
| "eval_f1_weighted": 0.7771738216042354, | |
| "eval_loss": 0.5281614065170288, | |
| "eval_precision_macro": 0.4761472822311331, | |
| "eval_precision_micro": 0.8041958041958042, | |
| "eval_precision_weighted": 0.80077693322795, | |
| "eval_recall_macro": 0.36810085833863637, | |
| "eval_recall_micro": 0.8041958041958042, | |
| "eval_recall_weighted": 0.8041958041958042, | |
| "eval_runtime": 359.8505, | |
| "eval_samples_per_second": 5.563, | |
| "eval_steps_per_second": 0.35, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 1.095617529880478, | |
| "grad_norm": 4.572272300720215, | |
| "learning_rate": 3.5302806499261446e-05, | |
| "loss": 0.6044, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.1952191235059761, | |
| "grad_norm": 3.9493234157562256, | |
| "learning_rate": 3.345642540620384e-05, | |
| "loss": 0.6022, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.294820717131474, | |
| "grad_norm": 6.116109848022461, | |
| "learning_rate": 3.1610044313146235e-05, | |
| "loss": 0.494, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.3944223107569722, | |
| "grad_norm": 11.72847843170166, | |
| "learning_rate": 2.976366322008863e-05, | |
| "loss": 0.5509, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.4940239043824701, | |
| "grad_norm": 6.265529632568359, | |
| "learning_rate": 2.791728212703102e-05, | |
| "loss": 0.5268, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.593625498007968, | |
| "grad_norm": 5.475246906280518, | |
| "learning_rate": 2.6070901033973415e-05, | |
| "loss": 0.6499, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.6932270916334662, | |
| "grad_norm": 5.1211256980896, | |
| "learning_rate": 2.4224519940915806e-05, | |
| "loss": 0.5373, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.792828685258964, | |
| "grad_norm": 2.6638262271881104, | |
| "learning_rate": 2.23781388478582e-05, | |
| "loss": 0.4476, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.8924302788844622, | |
| "grad_norm": 45.47649383544922, | |
| "learning_rate": 2.053175775480059e-05, | |
| "loss": 0.5096, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.9920318725099602, | |
| "grad_norm": 6.048641204833984, | |
| "learning_rate": 1.8685376661742986e-05, | |
| "loss": 0.424, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9100899100899101, | |
| "eval_f1_macro": 0.4902522309112827, | |
| "eval_f1_micro": 0.9100899100899101, | |
| "eval_f1_weighted": 0.9024494723879539, | |
| "eval_loss": 0.2924034893512726, | |
| "eval_precision_macro": 0.5296504253394911, | |
| "eval_precision_micro": 0.9100899100899101, | |
| "eval_precision_weighted": 0.9052689915360643, | |
| "eval_recall_macro": 0.4726016384805666, | |
| "eval_recall_micro": 0.9100899100899101, | |
| "eval_recall_weighted": 0.9100899100899101, | |
| "eval_runtime": 365.8456, | |
| "eval_samples_per_second": 5.472, | |
| "eval_steps_per_second": 0.344, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 2.091633466135458, | |
| "grad_norm": 2.1055290699005127, | |
| "learning_rate": 1.6838995568685377e-05, | |
| "loss": 0.4131, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.191235059760956, | |
| "grad_norm": 22.558122634887695, | |
| "learning_rate": 1.499261447562777e-05, | |
| "loss": 0.3949, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.2908366533864544, | |
| "grad_norm": 9.2990083694458, | |
| "learning_rate": 1.3146233382570164e-05, | |
| "loss": 0.2408, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 2.3904382470119523, | |
| "grad_norm": 23.017541885375977, | |
| "learning_rate": 1.1299852289512555e-05, | |
| "loss": 0.2457, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.49003984063745, | |
| "grad_norm": 0.9120715260505676, | |
| "learning_rate": 9.45347119645495e-06, | |
| "loss": 0.3485, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 2.589641434262948, | |
| "grad_norm": 2.4525136947631836, | |
| "learning_rate": 7.607090103397342e-06, | |
| "loss": 0.2528, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.6892430278884465, | |
| "grad_norm": 10.707359313964844, | |
| "learning_rate": 5.760709010339734e-06, | |
| "loss": 0.298, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 2.7888446215139444, | |
| "grad_norm": 24.448265075683594, | |
| "learning_rate": 3.914327917282127e-06, | |
| "loss": 0.2448, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.8884462151394423, | |
| "grad_norm": 1.235875129699707, | |
| "learning_rate": 2.06794682422452e-06, | |
| "loss": 0.4039, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 2.9880478087649402, | |
| "grad_norm": 9.670615196228027, | |
| "learning_rate": 2.215657311669129e-07, | |
| "loss": 0.3307, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9440559440559441, | |
| "eval_f1_macro": 0.5346970986126391, | |
| "eval_f1_micro": 0.9440559440559441, | |
| "eval_f1_weighted": 0.9410445215583293, | |
| "eval_loss": 0.20468038320541382, | |
| "eval_precision_macro": 0.5573908674461452, | |
| "eval_precision_micro": 0.9440559440559441, | |
| "eval_precision_weighted": 0.9419302500177272, | |
| "eval_recall_macro": 0.5198802592658838, | |
| "eval_recall_micro": 0.9440559440559441, | |
| "eval_recall_weighted": 0.9440559440559441, | |
| "eval_runtime": 338.5361, | |
| "eval_samples_per_second": 5.914, | |
| "eval_steps_per_second": 0.372, | |
| "step": 753 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 753, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 395071890909696.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |