| { | |
| "best_global_step": 3495, | |
| "best_metric": 0.9739681176533734, | |
| "best_model_checkpoint": "/content/drive/MyDrive/ModernBERT-domain-classifier_v6/checkpoint-3495", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 3495, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 3.0307705402374268, | |
| "learning_rate": 4.218091714923157e-05, | |
| "loss": 0.2001, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9665523156089194, | |
| "eval_f1": 0.9661788617886179, | |
| "eval_loss": 0.09094209969043732, | |
| "eval_precision": 0.9771954829514308, | |
| "eval_recall": 0.9554078679386858, | |
| "eval_runtime": 45.4419, | |
| "eval_samples_per_second": 410.546, | |
| "eval_steps_per_second": 6.426, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.1918050050735474, | |
| "learning_rate": 1.5125189709385162e-05, | |
| "loss": 0.05, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9726093481989708, | |
| "eval_f1": 0.972610816315592, | |
| "eval_loss": 0.08524948358535767, | |
| "eval_precision": 0.9726629502572899, | |
| "eval_recall": 0.9725586879622682, | |
| "eval_runtime": 42.7827, | |
| "eval_samples_per_second": 436.064, | |
| "eval_steps_per_second": 6.825, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 6.105299472808838, | |
| "learning_rate": 1.2472928209716906e-11, | |
| "loss": 0.0072, | |
| "step": 3495 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9740030017152659, | |
| "eval_f1": 0.9739681176533734, | |
| "eval_loss": 0.11646562814712524, | |
| "eval_precision": 0.9753816383573425, | |
| "eval_recall": 0.9725586879622682, | |
| "eval_runtime": 42.8653, | |
| "eval_samples_per_second": 435.224, | |
| "eval_steps_per_second": 6.812, | |
| "step": 3495 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3495, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 7.617369041410867e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |