| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 15.742397137745975, | |
| "eval_steps": 500, | |
| "global_step": 2200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6928, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8598, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 0.0002, | |
| "loss": 0.348, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1732, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.111, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 0.0002, | |
| "loss": 0.09, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0797, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 12.59, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0712, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 14.17, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0704, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 15.74, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0673, | |
| "step": 2200 | |
| } | |
| ], | |
| "logging_steps": 220, | |
| "max_steps": 2200, | |
| "num_train_epochs": 16, | |
| "save_steps": 220, | |
| "total_flos": 1.0258908883550208e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |