| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4807692307692308, | |
| "eval_steps": 500, | |
| "global_step": 350, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9673, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002, | |
| "loss": 1.524, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4671, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9931, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2852, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7958, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1292, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8171, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1259, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8211, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0453, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7793, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0234, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8, | |
| "step": 350 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 728, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "total_flos": 3378406907609088.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |