| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 1722, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0004375, | |
| "loss": 2.2956, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.000375, | |
| "loss": 2.2508, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0003125, | |
| "loss": 2.223, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.00025, | |
| "loss": 2.1849, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0001875, | |
| "loss": 2.129, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.000125, | |
| "loss": 2.0923, | |
| "step": 1722 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2296, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "save_steps": 500, | |
| "total_flos": 0.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |