| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01920636791635176, | |
| "eval_steps": 500, | |
| "global_step": 2770, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003466853414503928, | |
| "grad_norm": 1.0329110622406006, | |
| "learning_rate": 1.997688764390331e-05, | |
| "loss": 0.5561, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.006933706829007856, | |
| "grad_norm": 1.2828088998794556, | |
| "learning_rate": 1.9953775287806617e-05, | |
| "loss": 0.5185, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.010400560243511783, | |
| "grad_norm": 1.9677228927612305, | |
| "learning_rate": 1.9930662931709924e-05, | |
| "loss": 0.5365, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.013867413658015712, | |
| "grad_norm": 0.9762986302375793, | |
| "learning_rate": 1.990755057561323e-05, | |
| "loss": 0.5431, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.01733426707251964, | |
| "grad_norm": 1.915410041809082, | |
| "learning_rate": 1.9884438219516536e-05, | |
| "loss": 0.5247, | |
| "step": 2500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 432669, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1502375533608960.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |