| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 15.0, | |
| "eval_steps": 500, | |
| "global_step": 2040, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.6764705882352944, | |
| "grad_norm": 0.18811045587062836, | |
| "learning_rate": 1.8872549019607844e-05, | |
| "loss": 0.0955, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.352941176470588, | |
| "grad_norm": 0.11713749170303345, | |
| "learning_rate": 1.2745098039215686e-05, | |
| "loss": 0.0115, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 11.029411764705882, | |
| "grad_norm": 0.12211091816425323, | |
| "learning_rate": 6.61764705882353e-06, | |
| "loss": 0.0095, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 14.705882352941176, | |
| "grad_norm": 0.1121136024594307, | |
| "learning_rate": 4.901960784313725e-07, | |
| "loss": 0.0082, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2040, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1364347962353254e+18, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |