{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 0.8, | |
"eval_steps": 500, | |
"global_step": 500, | |
"is_hyper_param_search": true, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.8, | |
"grad_norm": 3.093435764312744, | |
"learning_rate": 3.636597898147889e-05, | |
"loss": 0.3015, | |
"step": 500 | |
} | |
], | |
"logging_steps": 500, | |
"max_steps": 1250, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 2, | |
"save_steps": 500, | |
"total_flos": 304478945280000.0, | |
"train_batch_size": 8, | |
"trial_name": null, | |
"trial_params": { | |
"_wandb": {}, | |
"assignments": {}, | |
"learning_rate": 5.5686918546871806e-05, | |
"metric": "eval/loss", | |
"per_device_train_batch_size": 8, | |
"weight_decay": 0.02272383002428056 | |
} | |
} | |