| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9998440667394355, | |
| "global_step": 3206, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.440424204616345e-05, | |
| "loss": 2.503, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.880848409232689e-05, | |
| "loss": 2.5143, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.321272613849033e-05, | |
| "loss": 2.4359, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.761696818465378e-05, | |
| "loss": 2.379, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.202121023081722e-05, | |
| "loss": 2.3396, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 6.456643792888335e-06, | |
| "loss": 2.3217, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.1647815704345703, | |
| "eval_runtime": 58.8555, | |
| "eval_samples_per_second": 484.27, | |
| "eval_steps_per_second": 7.578, | |
| "step": 3206 | |
| } | |
| ], | |
| "max_steps": 3206, | |
| "num_train_epochs": 1, | |
| "total_flos": 6.750556804153344e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |