| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "global_step": 9900, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.15, |
| "learning_rate": 4.7474747474747476e-05, |
| "loss": 3.8805, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 4.494949494949495e-05, |
| "loss": 3.7417, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 4.242424242424243e-05, |
| "loss": 3.7075, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 3.98989898989899e-05, |
| "loss": 3.6816, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 3.7373737373737376e-05, |
| "loss": 3.6595, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 3.484848484848485e-05, |
| "loss": 3.6445, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 3.232323232323233e-05, |
| "loss": 3.6022, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.21, |
| "learning_rate": 2.9797979797979796e-05, |
| "loss": 3.5327, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.36, |
| "learning_rate": 2.7272727272727273e-05, |
| "loss": 3.5349, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.52, |
| "learning_rate": 2.474747474747475e-05, |
| "loss": 3.548, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 2.2222222222222223e-05, |
| "loss": 3.5086, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.82, |
| "learning_rate": 1.9696969696969697e-05, |
| "loss": 3.5125, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.97, |
| "learning_rate": 1.7171717171717173e-05, |
| "loss": 3.5208, |
| "step": 6500 |
| }, |
| { |
| "epoch": 2.12, |
| "learning_rate": 1.4646464646464647e-05, |
| "loss": 3.4884, |
| "step": 7000 |
| }, |
| { |
| "epoch": 2.27, |
| "learning_rate": 1.2121212121212122e-05, |
| "loss": 3.4552, |
| "step": 7500 |
| }, |
| { |
| "epoch": 2.42, |
| "learning_rate": 9.595959595959595e-06, |
| "loss": 3.4452, |
| "step": 8000 |
| }, |
| { |
| "epoch": 2.58, |
| "learning_rate": 7.0707070707070704e-06, |
| "loss": 3.46, |
| "step": 8500 |
| }, |
| { |
| "epoch": 2.73, |
| "learning_rate": 4.5454545454545455e-06, |
| "loss": 3.4782, |
| "step": 9000 |
| }, |
| { |
| "epoch": 2.88, |
| "learning_rate": 2.0202020202020206e-06, |
| "loss": 3.4563, |
| "step": 9500 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 9900, |
| "total_flos": 1.03471644672e+16, |
| "train_loss": 3.5661124057962437, |
| "train_runtime": 7133.7737, |
| "train_samples_per_second": 2.776, |
| "train_steps_per_second": 1.388 |
| } |
| ], |
| "max_steps": 9900, |
| "num_train_epochs": 3, |
| "total_flos": 1.03471644672e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
