| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 8080, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 9.381188118811881e-05, | |
| "loss": 1.7918, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 8.762376237623763e-05, | |
| "loss": 1.4547, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 8.143564356435644e-05, | |
| "loss": 1.3849, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.524752475247526e-05, | |
| "loss": 1.3378, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 6.905940594059406e-05, | |
| "loss": 1.3125, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 6.287128712871287e-05, | |
| "loss": 1.2841, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 5.668316831683168e-05, | |
| "loss": 1.2655, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 5.0495049504950497e-05, | |
| "loss": 1.2478, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 4.430693069306931e-05, | |
| "loss": 1.2333, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 3.811881188118812e-05, | |
| "loss": 1.2248, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 3.1930693069306936e-05, | |
| "loss": 1.2144, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 2.5742574257425746e-05, | |
| "loss": 1.1982, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 1.9554455445544556e-05, | |
| "loss": 1.2003, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 1.3366336633663367e-05, | |
| "loss": 1.19, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 7.178217821782178e-06, | |
| "loss": 1.1888, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 9.900990099009902e-07, | |
| "loss": 1.1881, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 8080, | |
| "total_flos": 5.248284377481216e+16, | |
| "train_loss": 1.2936539687732658, | |
| "train_runtime": 11629.1597, | |
| "train_samples_per_second": 44.461, | |
| "train_steps_per_second": 0.695 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 8080, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 5.248284377481216e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |