| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 1224, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00019674796747967482, | |
| "loss": 0.6343, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00017820163487738418, | |
| "loss": 0.1353, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00015603996366939145, | |
| "loss": 0.1221, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00013387829246139875, | |
| "loss": 0.1169, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.000111716621253406, | |
| "loss": 0.1133, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 8.955495004541326e-05, | |
| "loss": 0.1058, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 6.739327883742053e-05, | |
| "loss": 0.1027, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 4.52316076294278e-05, | |
| "loss": 0.1029, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.306993642143506e-05, | |
| "loss": 0.1012, | |
| "step": 1098 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 9.082652134423252e-07, | |
| "loss": 0.1025, | |
| "step": 1220 | |
| } | |
| ], | |
| "logging_steps": 122, | |
| "max_steps": 1224, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 9.950406150979584e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |