| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 2600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9624639076034649, | |
| "grad_norm": 151.24244689941406, | |
| "learning_rate": 8.080769230769231e-06, | |
| "loss": -102.647, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.9239653512993262, | |
| "grad_norm": 79.63270568847656, | |
| "learning_rate": 6.157692307692308e-06, | |
| "loss": -151.0656, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.8854667949951875, | |
| "grad_norm": 81.43527221679688, | |
| "learning_rate": 4.234615384615385e-06, | |
| "loss": -155.8242, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.846968238691049, | |
| "grad_norm": 79.75184631347656, | |
| "learning_rate": 2.3115384615384617e-06, | |
| "loss": -158.1746, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.80846968238691, | |
| "grad_norm": 66.93490600585938, | |
| "learning_rate": 3.8846153846153845e-07, | |
| "loss": -159.1291, | |
| "step": 2500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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 | |
| } | |