| { | |
| "best_metric": 1.2596017122268677, | |
| "best_model_checkpoint": "model/checkpoint-6615", | |
| "epoch": 3.0, | |
| "eval_steps": 100, | |
| "global_step": 6615, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 37.24568557739258, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 1.482, | |
| "step": 2205 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5065759637188209, | |
| "eval_f1": 0.5016373346532207, | |
| "eval_loss": 1.3115675449371338, | |
| "eval_precision": 0.5224665615391555, | |
| "eval_recall": 0.5065759637188209, | |
| "eval_runtime": 59.0262, | |
| "eval_samples_per_second": 74.713, | |
| "eval_steps_per_second": 4.676, | |
| "step": 2205 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 29.510208129882812, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.225, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5340136054421769, | |
| "eval_f1": 0.5207496781913654, | |
| "eval_loss": 1.262213945388794, | |
| "eval_precision": 0.5372608560773618, | |
| "eval_recall": 0.5340136054421769, | |
| "eval_runtime": 58.9744, | |
| "eval_samples_per_second": 74.778, | |
| "eval_steps_per_second": 4.68, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 9.824317932128906, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1182, | |
| "step": 6615 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5394557823129251, | |
| "eval_f1": 0.5357869320793935, | |
| "eval_loss": 1.2596017122268677, | |
| "eval_precision": 0.5369446417328734, | |
| "eval_recall": 0.5394557823129251, | |
| "eval_runtime": 58.9757, | |
| "eval_samples_per_second": 74.777, | |
| "eval_steps_per_second": 4.68, | |
| "step": 6615 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 13230, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 100, | |
| "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": 4.931897418878976e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |