| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.998942694015648, |
| "eval_steps": 500, |
| "global_step": 11820, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.21, |
| "learning_rate": 4.9800000000000004e-05, |
| "loss": 0.0466, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 4.976161211704926e-05, |
| "loss": 0.0691, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 4.9047204098004095e-05, |
| "loss": 0.0741, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 4.7870506066506904e-05, |
| "loss": 0.0763, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 4.62541391865573e-05, |
| "loss": 0.0716, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.27, |
| "learning_rate": 4.422917693605373e-05, |
| "loss": 0.0591, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.48, |
| "learning_rate": 4.183454774177651e-05, |
| "loss": 0.0632, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.69, |
| "learning_rate": 3.91162866086904e-05, |
| "loss": 0.0608, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.9, |
| "learning_rate": 3.613286279641655e-05, |
| "loss": 0.0622, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2.11, |
| "learning_rate": 3.292969207944561e-05, |
| "loss": 0.0533, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.33, |
| "learning_rate": 2.9574078798457334e-05, |
| "loss": 0.0498, |
| "step": 5500 |
| }, |
| { |
| "epoch": 2.54, |
| "learning_rate": 2.613053217868765e-05, |
| "loss": 0.0479, |
| "step": 6000 |
| }, |
| { |
| "epoch": 2.75, |
| "learning_rate": 2.2672159813612203e-05, |
| "loss": 0.0445, |
| "step": 6500 |
| }, |
| { |
| "epoch": 2.96, |
| "learning_rate": 1.925835994414427e-05, |
| "loss": 0.0429, |
| "step": 7000 |
| }, |
| { |
| "epoch": 3.17, |
| "learning_rate": 1.5948030836583748e-05, |
| "loss": 0.0348, |
| "step": 7500 |
| }, |
| { |
| "epoch": 3.38, |
| "learning_rate": 1.2811719253897084e-05, |
| "loss": 0.032, |
| "step": 8000 |
| }, |
| { |
| "epoch": 3.59, |
| "learning_rate": 9.909718505639284e-06, |
| "loss": 0.0335, |
| "step": 8500 |
| }, |
| { |
| "epoch": 3.81, |
| "learning_rate": 7.302717325477024e-06, |
| "loss": 0.0334, |
| "step": 9000 |
| }, |
| { |
| "epoch": 4.02, |
| "learning_rate": 5.030401317985792e-06, |
| "loss": 0.0309, |
| "step": 9500 |
| }, |
| { |
| "epoch": 4.23, |
| "learning_rate": 3.141986323924076e-06, |
| "loss": 0.0269, |
| "step": 10000 |
| }, |
| { |
| "epoch": 4.44, |
| "learning_rate": 1.6737757483597487e-06, |
| "loss": 0.0311, |
| "step": 10500 |
| }, |
| { |
| "epoch": 4.65, |
| "learning_rate": 6.539948719738204e-07, |
| "loss": 0.0303, |
| "step": 11000 |
| }, |
| { |
| "epoch": 4.86, |
| "learning_rate": 1.0287606124971538e-07, |
| "loss": 0.0325, |
| "step": 11500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 11820, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "total_flos": 1.0019728060420915e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
