| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "global_step": 25000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07, |
| "learning_rate": 2.9550022498875057e-05, |
| "loss": 1.4723, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 2.9100044997750113e-05, |
| "loss": 1.1147, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 2.865006749662517e-05, |
| "loss": 1.0838, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 2.8200089995500226e-05, |
| "loss": 1.0829, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 2.775011249437528e-05, |
| "loss": 1.0867, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 2.730013499325034e-05, |
| "loss": 1.0653, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 2.6850157492125395e-05, |
| "loss": 1.0727, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 2.640017999100045e-05, |
| "loss": 1.0808, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 2.5950202489875508e-05, |
| "loss": 1.0751, |
| "step": 4500 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 2.5500224988750564e-05, |
| "loss": 1.0788, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 2.505024748762562e-05, |
| "loss": 1.0742, |
| "step": 5500 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 2.4600269986500677e-05, |
| "loss": 1.0765, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 2.415029248537573e-05, |
| "loss": 1.0781, |
| "step": 6500 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 2.16e-05, |
| "loss": 1.0563, |
| "step": 7000 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 2.1e-05, |
| "loss": 1.0432, |
| "step": 7500 |
| }, |
| { |
| "epoch": 1.6, |
| "learning_rate": 2.04e-05, |
| "loss": 1.0363, |
| "step": 8000 |
| }, |
| { |
| "epoch": 1.7, |
| "learning_rate": 1.98e-05, |
| "loss": 1.044, |
| "step": 8500 |
| }, |
| { |
| "epoch": 1.8, |
| "learning_rate": 1.9200000000000003e-05, |
| "loss": 1.0317, |
| "step": 9000 |
| }, |
| { |
| "epoch": 1.9, |
| "learning_rate": 1.86e-05, |
| "loss": 1.0381, |
| "step": 9500 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 1.8e-05, |
| "loss": 1.0314, |
| "step": 10000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.9475362300872803, |
| "eval_runtime": 248.7207, |
| "eval_samples_per_second": 40.206, |
| "eval_steps_per_second": 5.026, |
| "step": 10000 |
| }, |
| { |
| "epoch": 2.1, |
| "learning_rate": 1.74e-05, |
| "loss": 1.0283, |
| "step": 10500 |
| }, |
| { |
| "epoch": 2.2, |
| "learning_rate": 1.6800000000000002e-05, |
| "loss": 1.0251, |
| "step": 11000 |
| }, |
| { |
| "epoch": 2.3, |
| "learning_rate": 1.62e-05, |
| "loss": 1.0191, |
| "step": 11500 |
| }, |
| { |
| "epoch": 2.4, |
| "learning_rate": 1.56e-05, |
| "loss": 1.0175, |
| "step": 12000 |
| }, |
| { |
| "epoch": 2.5, |
| "learning_rate": 1.5e-05, |
| "loss": 1.0132, |
| "step": 12500 |
| }, |
| { |
| "epoch": 2.6, |
| "learning_rate": 1.44e-05, |
| "loss": 1.0127, |
| "step": 13000 |
| }, |
| { |
| "epoch": 2.7, |
| "learning_rate": 1.3800000000000002e-05, |
| "loss": 0.9994, |
| "step": 13500 |
| }, |
| { |
| "epoch": 2.8, |
| "learning_rate": 1.32e-05, |
| "loss": 1.0096, |
| "step": 14000 |
| }, |
| { |
| "epoch": 2.9, |
| "learning_rate": 1.26e-05, |
| "loss": 1.0119, |
| "step": 14500 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 1.2e-05, |
| "loss": 1.0087, |
| "step": 15000 |
| }, |
| { |
| "epoch": 3.1, |
| "learning_rate": 1.1400000000000001e-05, |
| "loss": 1.0075, |
| "step": 15500 |
| }, |
| { |
| "epoch": 3.2, |
| "learning_rate": 1.08e-05, |
| "loss": 1.0002, |
| "step": 16000 |
| }, |
| { |
| "epoch": 3.3, |
| "learning_rate": 1.02e-05, |
| "loss": 1.001, |
| "step": 16500 |
| }, |
| { |
| "epoch": 3.4, |
| "learning_rate": 9.600000000000001e-06, |
| "loss": 0.9938, |
| "step": 17000 |
| }, |
| { |
| "epoch": 3.5, |
| "learning_rate": 9e-06, |
| "loss": 0.9887, |
| "step": 17500 |
| }, |
| { |
| "epoch": 3.6, |
| "learning_rate": 8.400000000000001e-06, |
| "loss": 0.9931, |
| "step": 18000 |
| }, |
| { |
| "epoch": 3.7, |
| "learning_rate": 7.8e-06, |
| "loss": 0.9879, |
| "step": 18500 |
| }, |
| { |
| "epoch": 3.8, |
| "learning_rate": 7.2e-06, |
| "loss": 0.9825, |
| "step": 19000 |
| }, |
| { |
| "epoch": 3.9, |
| "learning_rate": 6.6e-06, |
| "loss": 0.9939, |
| "step": 19500 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 6e-06, |
| "loss": 0.9785, |
| "step": 20000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.9039560556411743, |
| "eval_runtime": 248.8855, |
| "eval_samples_per_second": 40.179, |
| "eval_steps_per_second": 5.022, |
| "step": 20000 |
| }, |
| { |
| "epoch": 4.1, |
| "learning_rate": 5.4e-06, |
| "loss": 0.9823, |
| "step": 20500 |
| }, |
| { |
| "epoch": 4.2, |
| "learning_rate": 4.800000000000001e-06, |
| "loss": 0.9772, |
| "step": 21000 |
| }, |
| { |
| "epoch": 4.3, |
| "learning_rate": 4.2000000000000004e-06, |
| "loss": 0.9766, |
| "step": 21500 |
| }, |
| { |
| "epoch": 4.4, |
| "learning_rate": 3.6e-06, |
| "loss": 0.9655, |
| "step": 22000 |
| }, |
| { |
| "epoch": 4.5, |
| "learning_rate": 3e-06, |
| "loss": 0.9723, |
| "step": 22500 |
| }, |
| { |
| "epoch": 4.6, |
| "learning_rate": 2.4000000000000003e-06, |
| "loss": 0.9602, |
| "step": 23000 |
| }, |
| { |
| "epoch": 4.7, |
| "learning_rate": 1.8e-06, |
| "loss": 0.9763, |
| "step": 23500 |
| }, |
| { |
| "epoch": 4.8, |
| "learning_rate": 1.2000000000000002e-06, |
| "loss": 0.9717, |
| "step": 24000 |
| }, |
| { |
| "epoch": 4.9, |
| "learning_rate": 6.000000000000001e-07, |
| "loss": 0.964, |
| "step": 24500 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 0.0, |
| "loss": 0.9579, |
| "step": 25000 |
| } |
| ], |
| "max_steps": 25000, |
| "num_train_epochs": 5, |
| "total_flos": 4.9230641636352e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
