| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 19.393939393939394, |
| "eval_steps": 500, |
| "global_step": 160, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.73, |
| "learning_rate": 7.500000000000001e-05, |
| "loss": 2.5979, |
| "step": 6 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 0.00015000000000000001, |
| "loss": 2.5438, |
| "step": 12 |
| }, |
| { |
| "epoch": 2.18, |
| "learning_rate": 0.00019722222222222225, |
| "loss": 2.4147, |
| "step": 18 |
| }, |
| { |
| "epoch": 2.91, |
| "learning_rate": 0.00018888888888888888, |
| "loss": 2.1395, |
| "step": 24 |
| }, |
| { |
| "epoch": 3.64, |
| "learning_rate": 0.00018055555555555557, |
| "loss": 2.0771, |
| "step": 30 |
| }, |
| { |
| "epoch": 4.36, |
| "learning_rate": 0.00017222222222222224, |
| "loss": 1.9096, |
| "step": 36 |
| }, |
| { |
| "epoch": 5.09, |
| "learning_rate": 0.0001638888888888889, |
| "loss": 1.9748, |
| "step": 42 |
| }, |
| { |
| "epoch": 5.82, |
| "learning_rate": 0.00015555555555555556, |
| "loss": 1.8121, |
| "step": 48 |
| }, |
| { |
| "epoch": 6.55, |
| "learning_rate": 0.00014722222222222223, |
| "loss": 1.7856, |
| "step": 54 |
| }, |
| { |
| "epoch": 7.27, |
| "learning_rate": 0.0001388888888888889, |
| "loss": 1.7752, |
| "step": 60 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 0.00013055555555555555, |
| "loss": 1.6423, |
| "step": 66 |
| }, |
| { |
| "epoch": 8.73, |
| "learning_rate": 0.00012222222222222224, |
| "loss": 1.6135, |
| "step": 72 |
| }, |
| { |
| "epoch": 9.45, |
| "learning_rate": 0.00011388888888888889, |
| "loss": 1.574, |
| "step": 78 |
| }, |
| { |
| "epoch": 10.18, |
| "learning_rate": 0.00010555555555555557, |
| "loss": 1.4749, |
| "step": 84 |
| }, |
| { |
| "epoch": 10.91, |
| "learning_rate": 9.722222222222223e-05, |
| "loss": 1.4809, |
| "step": 90 |
| }, |
| { |
| "epoch": 11.64, |
| "learning_rate": 8.888888888888889e-05, |
| "loss": 1.4328, |
| "step": 96 |
| }, |
| { |
| "epoch": 12.36, |
| "learning_rate": 8.055555555555556e-05, |
| "loss": 1.299, |
| "step": 102 |
| }, |
| { |
| "epoch": 13.09, |
| "learning_rate": 7.222222222222222e-05, |
| "loss": 1.2881, |
| "step": 108 |
| }, |
| { |
| "epoch": 13.82, |
| "learning_rate": 6.388888888888888e-05, |
| "loss": 1.2392, |
| "step": 114 |
| }, |
| { |
| "epoch": 14.55, |
| "learning_rate": 5.555555555555556e-05, |
| "loss": 1.1873, |
| "step": 120 |
| }, |
| { |
| "epoch": 15.27, |
| "learning_rate": 4.722222222222222e-05, |
| "loss": 1.1339, |
| "step": 126 |
| }, |
| { |
| "epoch": 16.0, |
| "learning_rate": 3.888888888888889e-05, |
| "loss": 1.0971, |
| "step": 132 |
| }, |
| { |
| "epoch": 16.73, |
| "learning_rate": 3.055555555555556e-05, |
| "loss": 1.0632, |
| "step": 138 |
| }, |
| { |
| "epoch": 17.45, |
| "learning_rate": 2.2222222222222223e-05, |
| "loss": 0.9817, |
| "step": 144 |
| }, |
| { |
| "epoch": 18.18, |
| "learning_rate": 1.388888888888889e-05, |
| "loss": 1.0649, |
| "step": 150 |
| }, |
| { |
| "epoch": 18.91, |
| "learning_rate": 5.555555555555556e-06, |
| "loss": 0.9804, |
| "step": 156 |
| } |
| ], |
| "logging_steps": 6, |
| "max_steps": 160, |
| "num_train_epochs": 20, |
| "save_steps": 500, |
| "total_flos": 2.601411762192384e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
