| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 114, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.043859649122807015, |
| "grad_norm": 68.8519515991211, |
| "learning_rate": 3.6363636363636366e-06, |
| "loss": 3.8867, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.08771929824561403, |
| "grad_norm": 21.211647033691406, |
| "learning_rate": 8.181818181818183e-06, |
| "loss": 1.8678, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.13157894736842105, |
| "grad_norm": 19.21977424621582, |
| "learning_rate": 9.997973265157192e-06, |
| "loss": 0.5404, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.17543859649122806, |
| "grad_norm": 8.171814918518066, |
| "learning_rate": 9.985593613021873e-06, |
| "loss": 0.3354, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.21929824561403508, |
| "grad_norm": 6.866504669189453, |
| "learning_rate": 9.961988113473708e-06, |
| "loss": 0.2407, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.2631578947368421, |
| "grad_norm": 4.359035968780518, |
| "learning_rate": 9.927209918004095e-06, |
| "loss": 0.1945, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.30701754385964913, |
| "grad_norm": 3.8699371814727783, |
| "learning_rate": 9.881337335184879e-06, |
| "loss": 0.1668, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.3508771929824561, |
| "grad_norm": 5.917017459869385, |
| "learning_rate": 9.824473654344297e-06, |
| "loss": 0.1493, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.39473684210526316, |
| "grad_norm": 7.350202560424805, |
| "learning_rate": 9.756746912994832e-06, |
| "loss": 0.1837, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.43859649122807015, |
| "grad_norm": 2.7234973907470703, |
| "learning_rate": 9.678309608536626e-06, |
| "loss": 0.1241, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.4824561403508772, |
| "grad_norm": 4.651773452758789, |
| "learning_rate": 9.58933835488563e-06, |
| "loss": 0.1548, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.5263157894736842, |
| "grad_norm": 6.711911201477051, |
| "learning_rate": 9.490033484799608e-06, |
| "loss": 0.1292, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.5701754385964912, |
| "grad_norm": 6.491599082946777, |
| "learning_rate": 9.380618598797473e-06, |
| "loss": 0.138, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.6140350877192983, |
| "grad_norm": 3.8013641834259033, |
| "learning_rate": 9.26134006168757e-06, |
| "loss": 0.1113, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.6578947368421053, |
| "grad_norm": 3.2369492053985596, |
| "learning_rate": 9.132466447838598e-06, |
| "loss": 0.1128, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.7017543859649122, |
| "grad_norm": 4.51101016998291, |
| "learning_rate": 8.994287936442226e-06, |
| "loss": 0.1093, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.7456140350877193, |
| "grad_norm": 6.025557518005371, |
| "learning_rate": 8.84711565812904e-06, |
| "loss": 0.131, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.7894736842105263, |
| "grad_norm": 3.6758241653442383, |
| "learning_rate": 8.691280994409044e-06, |
| "loss": 0.119, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.8333333333333334, |
| "grad_norm": 7.3002214431762695, |
| "learning_rate": 8.527134831514116e-06, |
| "loss": 0.118, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.8771929824561403, |
| "grad_norm": 3.0913829803466797, |
| "learning_rate": 8.355046770322528e-06, |
| "loss": 0.0927, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.9210526315789473, |
| "grad_norm": 5.307352066040039, |
| "learning_rate": 8.175404294144482e-06, |
| "loss": 0.1152, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.9649122807017544, |
| "grad_norm": 4.598392963409424, |
| "learning_rate": 7.98861189624256e-06, |
| "loss": 0.1091, |
| "step": 110 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 342, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.8031366314655744e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
