| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 20.0, | |
| "global_step": 8140, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_runtime": 5.9123, | |
| "eval_samples_per_second": 84.4, | |
| "eval_steps_per_second": 10.656, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.877886977886978e-05, | |
| "loss": 0.3917, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_runtime": 5.883, | |
| "eval_samples_per_second": 84.821, | |
| "eval_steps_per_second": 10.709, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 1.7552825552825554e-05, | |
| "loss": 0.191, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_runtime": 5.8655, | |
| "eval_samples_per_second": 85.073, | |
| "eval_steps_per_second": 10.741, | |
| "step": 1221 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 1.6324324324324326e-05, | |
| "loss": 0.1213, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_runtime": 5.8538, | |
| "eval_samples_per_second": 85.244, | |
| "eval_steps_per_second": 10.762, | |
| "step": 1628 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 1.5095823095823097e-05, | |
| "loss": 0.0805, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_runtime": 5.8461, | |
| "eval_samples_per_second": 85.356, | |
| "eval_steps_per_second": 10.776, | |
| "step": 2035 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_runtime": 5.8536, | |
| "eval_samples_per_second": 85.246, | |
| "eval_steps_per_second": 10.763, | |
| "step": 2442 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 1.3867321867321867e-05, | |
| "loss": 0.0494, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_runtime": 5.8462, | |
| "eval_samples_per_second": 85.354, | |
| "eval_steps_per_second": 10.776, | |
| "step": 2849 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 1.2641277641277642e-05, | |
| "loss": 0.0343, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_runtime": 5.8523, | |
| "eval_samples_per_second": 85.265, | |
| "eval_steps_per_second": 10.765, | |
| "step": 3256 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 1.1412776412776414e-05, | |
| "loss": 0.0308, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_runtime": 5.8555, | |
| "eval_samples_per_second": 85.22, | |
| "eval_steps_per_second": 10.759, | |
| "step": 3663 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "learning_rate": 1.0184275184275186e-05, | |
| "loss": 0.0262, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_runtime": 5.8564, | |
| "eval_samples_per_second": 85.207, | |
| "eval_steps_per_second": 10.758, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_runtime": 5.8649, | |
| "eval_samples_per_second": 85.082, | |
| "eval_steps_per_second": 10.742, | |
| "step": 4477 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "learning_rate": 8.955773955773957e-06, | |
| "loss": 0.0249, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_runtime": 5.8497, | |
| "eval_samples_per_second": 85.303, | |
| "eval_steps_per_second": 10.77, | |
| "step": 4884 | |
| }, | |
| { | |
| "epoch": 12.29, | |
| "learning_rate": 7.727272727272727e-06, | |
| "loss": 0.0122, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_runtime": 5.8618, | |
| "eval_samples_per_second": 85.127, | |
| "eval_steps_per_second": 10.748, | |
| "step": 5291 | |
| }, | |
| { | |
| "epoch": 13.51, | |
| "learning_rate": 6.501228501228501e-06, | |
| "loss": 0.0137, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_runtime": 5.8612, | |
| "eval_samples_per_second": 85.136, | |
| "eval_steps_per_second": 10.749, | |
| "step": 5698 | |
| }, | |
| { | |
| "epoch": 14.74, | |
| "learning_rate": 5.272727272727273e-06, | |
| "loss": 0.0071, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_runtime": 5.8722, | |
| "eval_samples_per_second": 84.977, | |
| "eval_steps_per_second": 10.729, | |
| "step": 6105 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 4.0442260442260445e-06, | |
| "loss": 0.0094, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_runtime": 5.8761, | |
| "eval_samples_per_second": 84.92, | |
| "eval_steps_per_second": 10.721, | |
| "step": 6512 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_runtime": 5.8601, | |
| "eval_samples_per_second": 85.153, | |
| "eval_steps_per_second": 10.751, | |
| "step": 6919 | |
| }, | |
| { | |
| "epoch": 17.2, | |
| "learning_rate": 2.8157248157248157e-06, | |
| "loss": 0.0094, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_runtime": 5.8528, | |
| "eval_samples_per_second": 85.258, | |
| "eval_steps_per_second": 10.764, | |
| "step": 7326 | |
| }, | |
| { | |
| "epoch": 18.43, | |
| "learning_rate": 1.5872235872235874e-06, | |
| "loss": 0.0072, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_runtime": 5.8548, | |
| "eval_samples_per_second": 85.23, | |
| "eval_steps_per_second": 10.76, | |
| "step": 7733 | |
| }, | |
| { | |
| "epoch": 19.66, | |
| "learning_rate": 3.587223587223587e-07, | |
| "loss": 0.0065, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_runtime": 5.8599, | |
| "eval_samples_per_second": 85.155, | |
| "eval_steps_per_second": 10.751, | |
| "step": 8140 | |
| } | |
| ], | |
| "max_steps": 8140, | |
| "num_train_epochs": 20, | |
| "total_flos": 3.403128959729664e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |