| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5741726452210136, | |
| "global_step": 4962, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.9997685720897943e-05, | |
| "loss": 2.316, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9259430687340893e-05, | |
| "loss": 2.541, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.850960425827355e-05, | |
| "loss": 2.3336, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.7759777829206203e-05, | |
| "loss": 2.1896, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.7009951400138856e-05, | |
| "loss": 2.2036, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.667900948854432e-05, | |
| "loss": 2.122, | |
| "step": 1442 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.620226799352002e-05, | |
| "loss": 2.1447, | |
| "step": 1648 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.572552649849572e-05, | |
| "loss": 2.0965, | |
| "step": 1854 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.524878500347142e-05, | |
| "loss": 2.1287, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.477435778754918e-05, | |
| "loss": 2.1001, | |
| "step": 2266 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.429761629252488e-05, | |
| "loss": 2.1086, | |
| "step": 2472 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.382087479750058e-05, | |
| "loss": 2.0791, | |
| "step": 2678 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.3344133302476279e-05, | |
| "loss": 2.0026, | |
| "step": 2884 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.2867391807451979e-05, | |
| "loss": 1.9953, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2390650312427679e-05, | |
| "loss": 2.0375, | |
| "step": 3296 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.19185373756075e-05, | |
| "loss": 2.0465, | |
| "step": 3502 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.144411015968526e-05, | |
| "loss": 2.0147, | |
| "step": 3708 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.096736866466096e-05, | |
| "loss": 2.0066, | |
| "step": 3914 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.0490627169636659e-05, | |
| "loss": 2.0109, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0013885674612359e-05, | |
| "loss": 1.9669, | |
| "step": 4326 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.537144179588059e-06, | |
| "loss": 1.9822, | |
| "step": 4532 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.062716963665819e-06, | |
| "loss": 1.9876, | |
| "step": 4738 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.585975468641519e-06, | |
| "loss": 1.9557, | |
| "step": 4944 | |
| } | |
| ], | |
| "max_steps": 8642, | |
| "num_train_epochs": 1, | |
| "total_flos": 9216488128905216.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |