| { | |
| "best_metric": 0.9693565368652344, | |
| "best_model_checkpoint": "model/checkpoint-12022", | |
| "epoch": 2.0, | |
| "eval_steps": 100, | |
| "global_step": 12022, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 14.125932693481445, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.0593, | |
| "step": 6011 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6449010148061887, | |
| "eval_f1": 0.6090798045608603, | |
| "eval_loss": 0.9724791646003723, | |
| "eval_precision": 0.6399609014205598, | |
| "eval_recall": 0.6449010148061887, | |
| "eval_runtime": 128.4211, | |
| "eval_samples_per_second": 93.614, | |
| "eval_steps_per_second": 5.856, | |
| "step": 6011 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 10.282686233520508, | |
| "learning_rate": 6e-06, | |
| "loss": 0.9302, | |
| "step": 12022 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6383297288304774, | |
| "eval_f1": 0.605702835886063, | |
| "eval_loss": 0.9693565368652344, | |
| "eval_precision": 0.6297167704652535, | |
| "eval_recall": 0.6383297288304774, | |
| "eval_runtime": 128.6794, | |
| "eval_samples_per_second": 93.426, | |
| "eval_steps_per_second": 5.844, | |
| "step": 12022 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 30055, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 8.962875481214054e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |