| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "global_step": 3860, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 4.352331606217617e-05, | |
| "loss": 2.4632, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 3.704663212435233e-05, | |
| "loss": 1.02, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 3.05699481865285e-05, | |
| "loss": 0.8995, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 2.4093264248704665e-05, | |
| "loss": 0.8539, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 1.761658031088083e-05, | |
| "loss": 0.812, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 1.1139896373056995e-05, | |
| "loss": 0.801, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 4.663212435233161e-06, | |
| "loss": 0.7741, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 3860, | |
| "total_flos": 2149699402137600.0, | |
| "train_loss": 1.0592799369535297, | |
| "train_runtime": 503.7989, | |
| "train_samples_per_second": 122.39, | |
| "train_steps_per_second": 7.662 | |
| } | |
| ], | |
| "max_steps": 3860, | |
| "num_train_epochs": 10, | |
| "total_flos": 2149699402137600.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |