{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.02506265664160401, "eval_steps": 500, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.02506265664160401, "grad_norm": 1.0692139863967896, "learning_rate": 2.5e-06, "loss": 4.188, "step": 10 } ], "logging_steps": 10, "max_steps": 400, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.078395171373056e+16, "train_batch_size": 64, "trial_name": null, "trial_params": null }