| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 2600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.8461538461538463, | |
| "grad_norm": 80.5483169555664, | |
| "learning_rate": 8.080769230769231e-06, | |
| "loss": -100.2026, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.6923076923076925, | |
| "grad_norm": 132.2296142578125, | |
| "learning_rate": 6.157692307692308e-06, | |
| "loss": -152.0627, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 11.538461538461538, | |
| "grad_norm": 149.9707489013672, | |
| "learning_rate": 4.234615384615385e-06, | |
| "loss": -156.2695, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 15.384615384615385, | |
| "grad_norm": 82.32199096679688, | |
| "learning_rate": 2.3115384615384617e-06, | |
| "loss": -158.9122, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 19.23076923076923, | |
| "grad_norm": 61.2541618347168, | |
| "learning_rate": 3.8846153846153845e-07, | |
| "loss": -160.1657, | |
| "step": 2500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "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": 0.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |