| { | |
| "best_metric": 0.9845642879906822, | |
| "best_model_checkpoint": "distilbert-type-classifier/checkpoint-875", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 875, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11428571428571428, | |
| "grad_norm": 1.4620862007141113, | |
| "learning_rate": 1.923809523809524e-05, | |
| "loss": 0.8914, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 0.9015448093414307, | |
| "learning_rate": 1.8476190476190478e-05, | |
| "loss": 0.186, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.34285714285714286, | |
| "grad_norm": 0.17388969659805298, | |
| "learning_rate": 1.7714285714285717e-05, | |
| "loss": 0.0844, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 5.441539764404297, | |
| "learning_rate": 1.6952380952380955e-05, | |
| "loss": 0.0738, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.07328463345766068, | |
| "learning_rate": 1.6190476190476193e-05, | |
| "loss": 0.0524, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6857142857142857, | |
| "grad_norm": 0.07699141651391983, | |
| "learning_rate": 1.542857142857143e-05, | |
| "loss": 0.0567, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 13.823246002197266, | |
| "learning_rate": 1.4666666666666666e-05, | |
| "loss": 0.0444, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 0.07251616567373276, | |
| "learning_rate": 1.3904761904761905e-05, | |
| "loss": 0.0375, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9849949983327776, | |
| "eval_f1": 0.9845642879906822, | |
| "eval_loss": 0.07195836305618286, | |
| "eval_precision": 0.9850021393367597, | |
| "eval_recall": 0.9849949983327776, | |
| "eval_runtime": 11.3969, | |
| "eval_samples_per_second": 263.142, | |
| "eval_steps_per_second": 16.496, | |
| "step": 875 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2625, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 463577877328128.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |