| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.887640449438202, | |
| "eval_steps": 500, | |
| "global_step": 110, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.898876404494382, | |
| "grad_norm": 4.305147647857666, | |
| "learning_rate": 9.090909090909092e-05, | |
| "loss": 1.8819, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.797752808988764, | |
| "grad_norm": 1.784299373626709, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 0.9762, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.696629213483146, | |
| "grad_norm": 2.494720458984375, | |
| "learning_rate": 9.118382907149165e-05, | |
| "loss": 0.6304, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.595505617977528, | |
| "grad_norm": 1.597534418106079, | |
| "learning_rate": 8.028048435688333e-05, | |
| "loss": 0.495, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.49438202247191, | |
| "grad_norm": 1.0912885665893555, | |
| "learning_rate": 6.635339816587109e-05, | |
| "loss": 0.3405, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 5.393258426966292, | |
| "grad_norm": 1.4524614810943604, | |
| "learning_rate": 5.0793298191740404e-05, | |
| "loss": 0.2878, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 6.292134831460674, | |
| "grad_norm": 1.4030110836029053, | |
| "learning_rate": 3.515398123358627e-05, | |
| "loss": 0.2239, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 7.191011235955056, | |
| "grad_norm": 1.2836480140686035, | |
| "learning_rate": 2.09971545214401e-05, | |
| "loss": 0.1738, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 8.089887640449438, | |
| "grad_norm": 0.8559394478797913, | |
| "learning_rate": 9.73648712344707e-06, | |
| "loss": 0.1554, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 8.98876404494382, | |
| "grad_norm": 1.1216458082199097, | |
| "learning_rate": 2.496444112952734e-06, | |
| "loss": 0.1294, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 9.887640449438202, | |
| "grad_norm": 0.8491550087928772, | |
| "learning_rate": 0.0, | |
| "loss": 0.123, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 9.887640449438202, | |
| "step": 110, | |
| "total_flos": 582886539362304.0, | |
| "train_loss": 0.49246828881177035, | |
| "train_runtime": 12.5387, | |
| "train_samples_per_second": 70.98, | |
| "train_steps_per_second": 8.773 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 110, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 582886539362304.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |