| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.792332268370607, | |
| "global_step": 9000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.734291799787008e-05, | |
| "loss": 2.0534, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.468051118210863e-05, | |
| "loss": 1.9997, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.20234291799787e-05, | |
| "loss": 1.9542, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.93716719914803e-05, | |
| "loss": 1.8679, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3.670926517571886e-05, | |
| "loss": 1.5918, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 3.4046858359957404e-05, | |
| "loss": 1.6202, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 3.138445154419595e-05, | |
| "loss": 1.594, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.8722044728434505e-05, | |
| "loss": 1.4514, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 2.6059637912673056e-05, | |
| "loss": 1.3178, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 2.339723109691161e-05, | |
| "loss": 1.3151, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 2.073482428115016e-05, | |
| "loss": 1.318, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 1.8072417465388714e-05, | |
| "loss": 1.1319, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 1.5410010649627264e-05, | |
| "loss": 1.0901, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 1.2747603833865815e-05, | |
| "loss": 1.084, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 1.0085197018104367e-05, | |
| "loss": 1.0844, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 7.422790202342918e-06, | |
| "loss": 0.9108, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 4.76038338658147e-06, | |
| "loss": 0.9162, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 2.0979765708200215e-06, | |
| "loss": 0.9125, | |
| "step": 9000 | |
| } | |
| ], | |
| "max_steps": 9390, | |
| "num_train_epochs": 5, | |
| "total_flos": 2.61046324887552e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |