| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.5504, | |
| "eval_steps": 500, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.056663136929273605, | |
| "learning_rate": 0.0001, | |
| "loss": 1.074, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.05507315695285797, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9146, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.07707152515649796, | |
| "learning_rate": 0.00018803827751196172, | |
| "loss": 0.8534, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.2752, | |
| "grad_norm": 0.0732378214597702, | |
| "learning_rate": 0.00017607655502392347, | |
| "loss": 0.8235, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.5952, | |
| "grad_norm": 0.07976480573415756, | |
| "learning_rate": 0.00016411483253588518, | |
| "loss": 0.826, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.9152, | |
| "grad_norm": 0.06750624626874924, | |
| "learning_rate": 0.0001521531100478469, | |
| "loss": 0.831, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.2304, | |
| "grad_norm": 0.07449544221162796, | |
| "learning_rate": 0.00014019138755980864, | |
| "loss": 0.811, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.5504, | |
| "grad_norm": 0.079868845641613, | |
| "learning_rate": 0.00012822966507177036, | |
| "loss": 0.8053, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 936, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1519871089836032e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |