| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 42.234676361083984, | |
| "learning_rate": 1.973044870579824e-05, | |
| "loss": 3.4586, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "grad_norm": 17.283308029174805, | |
| "learning_rate": 1.686241637868734e-05, | |
| "loss": 0.6618, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 6.132094860076904, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.2557, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "grad_norm": 4.710355281829834, | |
| "learning_rate": 6.039202339608432e-06, | |
| "loss": 0.2293, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "grad_norm": 4.715655326843262, | |
| "learning_rate": 1.6451218858706374e-06, | |
| "loss": 0.1895, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 4.625955104827881, | |
| "learning_rate": 0.0, | |
| "loss": 0.1849, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 30, | |
| "total_flos": 1216660853751808.0, | |
| "train_loss": 0.8299674133459727, | |
| "train_runtime": 23.6875, | |
| "train_samples_per_second": 25.33, | |
| "train_steps_per_second": 1.266 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1216660853751808.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |