| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6566850538481744, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.8358287365379566e-05, | |
| "loss": 7.8649, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.671657473075913e-05, | |
| "loss": 7.2652, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.5074862096138694e-05, | |
| "loss": 7.0778, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.343314946151826e-05, | |
| "loss": 6.9737, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.179143682689782e-05, | |
| "loss": 6.8729, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.0149724192277385e-05, | |
| "loss": 6.79, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.850801155765695e-05, | |
| "loss": 6.752, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.686629892303651e-05, | |
| "loss": 6.7012, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.522458628841608e-05, | |
| "loss": 6.6312, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.358287365379564e-05, | |
| "loss": 6.5047, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.1941161019175205e-05, | |
| "loss": 6.3916, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.029944838455477e-05, | |
| "loss": 6.24, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.8657735749934332e-05, | |
| "loss": 6.1126, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.70160231153139e-05, | |
| "loss": 5.9892, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.5374310480693457e-05, | |
| "loss": 5.8802, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.3732597846073024e-05, | |
| "loss": 5.7723, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.2090885211452588e-05, | |
| "loss": 5.6834, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.0449172576832152e-05, | |
| "loss": 5.5951, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.8807459942211716e-05, | |
| "loss": 5.5049, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.716574730759128e-05, | |
| "loss": 5.4411, | |
| "step": 10000 | |
| } | |
| ], | |
| "max_steps": 15228, | |
| "num_train_epochs": 1, | |
| "total_flos": 2.1220159479607296e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |