| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9955555555555555, | |
| "eval_steps": 2500, | |
| "global_step": 56, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 83.4717788696289, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 9.6928, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 17.011417388916016, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 5.4563, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 12.439817428588867, | |
| "learning_rate": 6e-06, | |
| "loss": 4.6011, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 9.316488265991211, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 4.5413, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 6.6849894523620605, | |
| "learning_rate": 1e-05, | |
| "loss": 3.8187, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 56, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2203965689167872.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |