| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8635578583765112, | |
| "eval_steps": 500, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2158894645941278, | |
| "grad_norm": 1.0430593490600586, | |
| "learning_rate": 1.856649395509499e-05, | |
| "loss": 0.8043, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4317789291882556, | |
| "grad_norm": 0.8806478977203369, | |
| "learning_rate": 1.7127230857800806e-05, | |
| "loss": 0.4945, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6476683937823834, | |
| "grad_norm": 0.49951252341270447, | |
| "learning_rate": 1.568796776050662e-05, | |
| "loss": 0.4456, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.8635578583765112, | |
| "grad_norm": 0.8921486139297485, | |
| "learning_rate": 1.4248704663212436e-05, | |
| "loss": 0.4194, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6948, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4871663124480000.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |