| { | |
| "best_metric": 0.526961176646401, | |
| "best_model_checkpoint": "training_dir-augmented\\checkpoint-18604", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 18604, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.9803293943405151, | |
| "learning_rate": 8.086937622256031e-06, | |
| "loss": 0.5312, | |
| "step": 9302 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.40428321678321677, | |
| "eval_f1": 0.3406020494510067, | |
| "eval_loss": 3.0353851318359375, | |
| "eval_precision": 0.6901256632128517, | |
| "eval_recall": 0.40428321678321677, | |
| "eval_runtime": 16.0409, | |
| "eval_samples_per_second": 142.636, | |
| "eval_steps_per_second": 17.829, | |
| "step": 9302 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 196.54563903808594, | |
| "learning_rate": 6.065203216692024e-06, | |
| "loss": 0.3949, | |
| "step": 18604 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.527972027972028, | |
| "eval_f1": 0.526961176646401, | |
| "eval_loss": 2.4327211380004883, | |
| "eval_precision": 0.6358079986576912, | |
| "eval_recall": 0.527972027972028, | |
| "eval_runtime": 16.8165, | |
| "eval_samples_per_second": 136.057, | |
| "eval_steps_per_second": 17.007, | |
| "step": 18604 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 46510, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.808840369845105e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |