| { | |
| "best_metric": 0.8289012162572651, | |
| "best_model_checkpoint": "model/checkpoint-471", | |
| "epoch": 3.0, | |
| "eval_steps": 50, | |
| "global_step": 471, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 4.966571807861328, | |
| "learning_rate": 1.6927223719676552e-05, | |
| "loss": 0.6737, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8338658146964856, | |
| "eval_f1": 0.7583239638877448, | |
| "eval_loss": 0.4658426344394684, | |
| "eval_precision": 0.6953321969194337, | |
| "eval_recall": 0.8338658146964856, | |
| "eval_runtime": 4.2259, | |
| "eval_samples_per_second": 74.067, | |
| "eval_steps_per_second": 4.733, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 2.303415060043335, | |
| "learning_rate": 8.463611859838276e-06, | |
| "loss": 0.4314, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8434504792332268, | |
| "eval_f1": 0.7790813157791667, | |
| "eval_loss": 0.4860698878765106, | |
| "eval_precision": 0.7691538699371329, | |
| "eval_recall": 0.8434504792332268, | |
| "eval_runtime": 4.2642, | |
| "eval_samples_per_second": 73.402, | |
| "eval_steps_per_second": 4.69, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 11.434114456176758, | |
| "learning_rate": 0.0, | |
| "loss": 0.286, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8466453674121406, | |
| "eval_f1": 0.8289012162572651, | |
| "eval_loss": 0.4335961937904358, | |
| "eval_precision": 0.8219730992689277, | |
| "eval_recall": 0.8466453674121406, | |
| "eval_runtime": 4.1847, | |
| "eval_samples_per_second": 74.796, | |
| "eval_steps_per_second": 4.779, | |
| "step": 471 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 471, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 986675316480000.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |