| { |
| "best_metric": 0.4859355092048645, |
| "best_model_checkpoint": "./output/checkpoint-200", |
| "epoch": 2.1498152502519314, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.11, |
| "learning_rate": 5e-06, |
| "loss": 1.5355, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 1e-05, |
| "loss": 1.5218, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 1.5e-05, |
| "loss": 1.4822, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 2e-05, |
| "loss": 1.4292, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 2.5e-05, |
| "loss": 1.3539, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 3e-05, |
| "loss": 1.2282, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 3.5e-05, |
| "loss": 1.0398, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 4e-05, |
| "loss": 0.8365, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 4.5e-05, |
| "loss": 0.6591, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 5e-05, |
| "loss": 0.5647, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 4.863013698630137e-05, |
| "loss": 0.5343, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.29, |
| "learning_rate": 4.726027397260274e-05, |
| "loss": 0.5249, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 4.589041095890411e-05, |
| "loss": 0.5126, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 4.452054794520548e-05, |
| "loss": 0.5099, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.61, |
| "learning_rate": 4.3150684931506855e-05, |
| "loss": 0.5067, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.72, |
| "learning_rate": 4.1780821917808224e-05, |
| "loss": 0.5047, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.83, |
| "learning_rate": 4.041095890410959e-05, |
| "loss": 0.4949, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.93, |
| "learning_rate": 3.904109589041096e-05, |
| "loss": 0.4961, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.04, |
| "learning_rate": 3.767123287671233e-05, |
| "loss": 0.4933, |
| "step": 190 |
| }, |
| { |
| "epoch": 2.15, |
| "learning_rate": 3.63013698630137e-05, |
| "loss": 0.488, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.15, |
| "eval_loss": 0.4859355092048645, |
| "eval_runtime": 182.5747, |
| "eval_samples_per_second": 10.954, |
| "eval_steps_per_second": 1.369, |
| "step": 200 |
| } |
| ], |
| "max_steps": 465, |
| "num_train_epochs": 5, |
| "total_flos": 1.0396612701664051e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
