| { | |
| "best_metric": 0.04332950338721275, | |
| "best_model_checkpoint": "doc-topic-model_eval-04_train-03/checkpoint-6000", | |
| "epoch": 2.9585798816568047, | |
| "eval_steps": 1000, | |
| "global_step": 6000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2465483234714004, | |
| "grad_norm": 0.3881610631942749, | |
| "learning_rate": 1.9950690335305722e-05, | |
| "loss": 0.1669, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4930966469428008, | |
| "grad_norm": 0.3564796447753906, | |
| "learning_rate": 1.9901380670611442e-05, | |
| "loss": 0.0935, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4930966469428008, | |
| "eval_accuracy": 0.981496987239155, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.08937656879425049, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 12.1325, | |
| "eval_samples_per_second": 668.698, | |
| "eval_steps_per_second": 2.638, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7396449704142012, | |
| "grad_norm": 0.4097365140914917, | |
| "learning_rate": 1.9852071005917162e-05, | |
| "loss": 0.0869, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.9861932938856016, | |
| "grad_norm": 0.3858756422996521, | |
| "learning_rate": 1.980276134122288e-05, | |
| "loss": 0.0764, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9861932938856016, | |
| "eval_accuracy": 0.981496987239155, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.06986432522535324, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 12.1072, | |
| "eval_samples_per_second": 670.097, | |
| "eval_steps_per_second": 2.643, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.232741617357002, | |
| "grad_norm": 0.3765203356742859, | |
| "learning_rate": 1.9753451676528602e-05, | |
| "loss": 0.068, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.4792899408284024, | |
| "grad_norm": 0.3380969762802124, | |
| "learning_rate": 1.9704142011834322e-05, | |
| "loss": 0.0621, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.4792899408284024, | |
| "eval_accuracy": 0.982110448535131, | |
| "eval_f1": 0.07324770642201835, | |
| "eval_loss": 0.05668229982256889, | |
| "eval_precision": 0.8831858407079646, | |
| "eval_recall": 0.03820826952526799, | |
| "eval_runtime": 14.4297, | |
| "eval_samples_per_second": 562.245, | |
| "eval_steps_per_second": 2.218, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.725838264299803, | |
| "grad_norm": 0.3490855395793915, | |
| "learning_rate": 1.965483234714004e-05, | |
| "loss": 0.056, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.972386587771203, | |
| "grad_norm": 0.4068734347820282, | |
| "learning_rate": 1.9605522682445763e-05, | |
| "loss": 0.0542, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.972386587771203, | |
| "eval_accuracy": 0.9840103367519987, | |
| "eval_f1": 0.28812917875614985, | |
| "eval_loss": 0.04953226447105408, | |
| "eval_precision": 0.8174659985683608, | |
| "eval_recall": 0.17488514548238898, | |
| "eval_runtime": 14.3697, | |
| "eval_samples_per_second": 564.59, | |
| "eval_steps_per_second": 2.227, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.2189349112426036, | |
| "grad_norm": 0.39391544461250305, | |
| "learning_rate": 1.9556213017751483e-05, | |
| "loss": 0.0488, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.465483234714004, | |
| "grad_norm": 0.2698710858821869, | |
| "learning_rate": 1.95069033530572e-05, | |
| "loss": 0.0468, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.465483234714004, | |
| "eval_accuracy": 0.985417189100507, | |
| "eval_f1": 0.4302241904234708, | |
| "eval_loss": 0.046475622802972794, | |
| "eval_precision": 0.7764235764235764, | |
| "eval_recall": 0.2975497702909648, | |
| "eval_runtime": 14.4141, | |
| "eval_samples_per_second": 562.851, | |
| "eval_steps_per_second": 2.22, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.712031558185404, | |
| "grad_norm": 0.39123860001564026, | |
| "learning_rate": 1.9457593688362923e-05, | |
| "loss": 0.0456, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.9585798816568047, | |
| "grad_norm": 0.4525609016418457, | |
| "learning_rate": 1.940828402366864e-05, | |
| "loss": 0.0441, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.9585798816568047, | |
| "eval_accuracy": 0.9861241571991028, | |
| "eval_f1": 0.4928016571724495, | |
| "eval_loss": 0.04332950338721275, | |
| "eval_precision": 0.76128, | |
| "eval_recall": 0.36431852986217456, | |
| "eval_runtime": 14.4207, | |
| "eval_samples_per_second": 562.594, | |
| "eval_steps_per_second": 2.219, | |
| "step": 6000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 202800, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 135256930917768.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |