| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 9654, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.742075823492853e-05, | |
| "loss": 3.736, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.483115806919412e-05, | |
| "loss": 3.6583, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.224155790345971e-05, | |
| "loss": 3.6089, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.96519577377253e-05, | |
| "loss": 3.5785, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.706235757199089e-05, | |
| "loss": 3.5712, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.447275740625648e-05, | |
| "loss": 3.5492, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.188315724052207e-05, | |
| "loss": 3.5441, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.9293557074787652e-05, | |
| "loss": 3.528, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.6703956909053245e-05, | |
| "loss": 3.5161, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.4114356743318832e-05, | |
| "loss": 3.4965, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.1524756577584422e-05, | |
| "loss": 3.502, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.8935156411850012e-05, | |
| "loss": 3.4984, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.6345556246115602e-05, | |
| "loss": 3.4832, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.375595608038119e-05, | |
| "loss": 3.4808, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.116635591464678e-05, | |
| "loss": 3.4683, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.576755748912369e-06, | |
| "loss": 3.4613, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 5.992334783509427e-06, | |
| "loss": 3.4763, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.402734617775016e-06, | |
| "loss": 3.4537, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 8.131344520406049e-07, | |
| "loss": 3.4605, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 9654, | |
| "total_flos": 5044921687867392.0, | |
| "train_loss": 3.5289945189493994, | |
| "train_runtime": 1832.9089, | |
| "train_samples_per_second": 42.135, | |
| "train_steps_per_second": 5.267 | |
| } | |
| ], | |
| "max_steps": 9654, | |
| "num_train_epochs": 1, | |
| "total_flos": 5044921687867392.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |