| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 20, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1084, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2032, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 6e-05, | |
| "loss": 2.1944, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 8e-05, | |
| "loss": 2.166, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1799, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00012, | |
| "loss": 2.1193, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.00014, | |
| "loss": 2.1065, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.00016, | |
| "loss": 1.9974, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.00018, | |
| "loss": 1.8511, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 9, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 2.296278864101376e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |