| { | |
| "best_metric": 0.8406563997268677, | |
| "best_model_checkpoint": "model/checkpoint-11646", | |
| "epoch": 3.0, | |
| "eval_steps": 100, | |
| "global_step": 11646, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 33.41036605834961, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.9899, | |
| "step": 3882 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6830242143225141, | |
| "eval_f1": 0.6892624503418725, | |
| "eval_loss": 0.872677206993103, | |
| "eval_precision": 0.7118974398297161, | |
| "eval_recall": 0.6830242143225141, | |
| "eval_runtime": 100.3944, | |
| "eval_samples_per_second": 77.335, | |
| "eval_steps_per_second": 4.841, | |
| "step": 3882 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 115.28584289550781, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.7952, | |
| "step": 7764 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7046625450798557, | |
| "eval_f1": 0.7069110464849921, | |
| "eval_loss": 0.8472453355789185, | |
| "eval_precision": 0.7109987245656574, | |
| "eval_recall": 0.7046625450798557, | |
| "eval_runtime": 101.3813, | |
| "eval_samples_per_second": 76.582, | |
| "eval_steps_per_second": 4.794, | |
| "step": 7764 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 37.54659652709961, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7057, | |
| "step": 11646 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7071097372488409, | |
| "eval_f1": 0.7077519652794403, | |
| "eval_loss": 0.8406563997268677, | |
| "eval_precision": 0.7107620038824047, | |
| "eval_recall": 0.7071097372488409, | |
| "eval_runtime": 101.1862, | |
| "eval_samples_per_second": 76.73, | |
| "eval_steps_per_second": 4.803, | |
| "step": 11646 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 23292, | |
| "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": 8.681565345936538e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |