| { | |
| "best_metric": 1.2541574239730835, | |
| "best_model_checkpoint": "model/checkpoint-4410", | |
| "epoch": 2.0, | |
| "eval_steps": 100, | |
| "global_step": 4410, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 44.31188201904297, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 1.584, | |
| "step": 2205 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5222222222222223, | |
| "eval_f1": 0.515083636023541, | |
| "eval_loss": 1.2932672500610352, | |
| "eval_precision": 0.5406457440910268, | |
| "eval_recall": 0.5222222222222223, | |
| "eval_runtime": 58.9593, | |
| "eval_samples_per_second": 74.797, | |
| "eval_steps_per_second": 4.681, | |
| "step": 2205 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 21.185283660888672, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.2405, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5344671201814059, | |
| "eval_f1": 0.5194090089676107, | |
| "eval_loss": 1.2541574239730835, | |
| "eval_precision": 0.537798009379494, | |
| "eval_recall": 0.5344671201814059, | |
| "eval_runtime": 58.8691, | |
| "eval_samples_per_second": 74.912, | |
| "eval_steps_per_second": 4.688, | |
| "step": 4410 | |
| } | |
| ], | |
| "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": 3.287931612585984e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |