| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.928, | |
| "eval_steps": 500, | |
| "global_step": 310, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 81.96082305908203, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 58.2628, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 36.536678314208984, | |
| "learning_rate": 9.4e-05, | |
| "loss": 2.1587, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.192, | |
| "grad_norm": 30.483903884887695, | |
| "learning_rate": 9.153846153846155e-05, | |
| "loss": 1.7083, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.592, | |
| "grad_norm": 24.5040225982666, | |
| "learning_rate": 8.192307692307693e-05, | |
| "loss": 1.5561, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.992, | |
| "grad_norm": 23.667861938476562, | |
| "learning_rate": 7.23076923076923e-05, | |
| "loss": 1.3954, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.384, | |
| "grad_norm": 19.942045211791992, | |
| "learning_rate": 6.307692307692308e-05, | |
| "loss": 0.7723, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.784, | |
| "grad_norm": 22.397857666015625, | |
| "learning_rate": 5.346153846153846e-05, | |
| "loss": 0.7796, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 3.176, | |
| "grad_norm": 17.26620101928711, | |
| "learning_rate": 4.384615384615385e-05, | |
| "loss": 0.6446, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.576, | |
| "grad_norm": 15.945826530456543, | |
| "learning_rate": 3.4230769230769234e-05, | |
| "loss": 0.4756, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.976, | |
| "grad_norm": 20.171337127685547, | |
| "learning_rate": 2.461538461538462e-05, | |
| "loss": 0.4989, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.368, | |
| "grad_norm": 14.564436912536621, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.2846, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 4.768, | |
| "grad_norm": 15.490738868713379, | |
| "learning_rate": 5.3846153846153855e-06, | |
| "loss": 0.3187, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 310, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.4681387557982144e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |