| { | |
| "best_metric": 2.716337203979492, | |
| "best_model_checkpoint": "output/tool/checkpoint-33", | |
| "epoch": 3.0, | |
| "global_step": 33, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 7.836279790554737e-05, | |
| "loss": 3.2081, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.778782010045488e-06, | |
| "loss": 3.1621, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.746370792388916, | |
| "eval_runtime": 0.6285, | |
| "eval_samples_per_second": 22.274, | |
| "eval_steps_per_second": 3.182, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 4.0102530108070535e-05, | |
| "loss": 2.9659, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.000126309992352219, | |
| "loss": 2.8367, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.761970043182373, | |
| "eval_runtime": 0.6295, | |
| "eval_samples_per_second": 22.239, | |
| "eval_steps_per_second": 3.177, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.00011352344634864655, | |
| "loss": 2.6931, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.3676553651353525e-05, | |
| "loss": 2.6297, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.716337203979492, | |
| "eval_runtime": 0.6316, | |
| "eval_samples_per_second": 22.166, | |
| "eval_steps_per_second": 3.167, | |
| "step": 33 | |
| } | |
| ], | |
| "max_steps": 44, | |
| "num_train_epochs": 4, | |
| "total_flos": 34490548224000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |