| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 2222, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.000154995499549955, | |
| "loss": 4.8347, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00010999099909990999, | |
| "loss": 2.2463, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 6.498649864986499e-05, | |
| "loss": 1.6708, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.9981998199819982e-05, | |
| "loss": 1.3752, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 2222, | |
| "train_runtime": 3913.5949, | |
| "train_samples_per_second": 0.568 | |
| } | |
| ], | |
| "max_steps": 2222, | |
| "num_train_epochs": 2, | |
| "total_flos": 401870376571760640, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |