| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 5345, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 8.158091674462115e-06, | |
| "loss": 0.4466, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 7.316183348924229e-06, | |
| "loss": 0.3772, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 6.4742750233863424e-06, | |
| "loss": 0.287, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 5.632366697848456e-06, | |
| "loss": 0.2872, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 4.79045837231057e-06, | |
| "loss": 0.2215, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 3.948550046772685e-06, | |
| "loss": 0.2127, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 3.106641721234799e-06, | |
| "loss": 0.1651, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 2.264733395696913e-06, | |
| "loss": 0.1548, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 1.422825070159027e-06, | |
| "loss": 0.1361, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 5.809167446211413e-07, | |
| "loss": 0.0992, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 5345, | |
| "total_flos": 2812378728829440.0, | |
| "train_loss": 0.2295077174929841, | |
| "train_runtime": 717.9746, | |
| "train_samples_per_second": 59.549, | |
| "train_steps_per_second": 7.445 | |
| } | |
| ], | |
| "max_steps": 5345, | |
| "num_train_epochs": 5, | |
| "total_flos": 2812378728829440.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |