| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 5148, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.5143745143745146e-05, | |
| "loss": 3.3531, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.028749028749029e-05, | |
| "loss": 3.3091, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.5431235431235434e-05, | |
| "loss": 3.2838, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.057498057498058e-05, | |
| "loss": 3.2211, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.571872571872572e-05, | |
| "loss": 3.1811, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.0862470862470865e-05, | |
| "loss": 3.1818, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.600621600621601e-05, | |
| "loss": 3.1671, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.114996114996115e-05, | |
| "loss": 3.1207, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 6.2937062937062944e-06, | |
| "loss": 3.1162, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.4374514374514376e-06, | |
| "loss": 3.118, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 5148, | |
| "total_flos": 7.645621337771213e+16, | |
| "train_loss": 3.2029559499270803, | |
| "train_runtime": 3531.7217, | |
| "train_samples_per_second": 11.655, | |
| "train_steps_per_second": 1.458 | |
| } | |
| ], | |
| "max_steps": 5148, | |
| "num_train_epochs": 3, | |
| "total_flos": 7.645621337771213e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |