{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.8, "eval_steps": 400, "global_step": 500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.64, "grad_norm": 1.596258521080017, "learning_rate": 1.5430508550092123e-05, "loss": 2.1626, "step": 400 }, { "epoch": 0.64, "eval_loss": 1.3615399599075317, "eval_runtime": 578.5432, "eval_samples_per_second": 4.321, "eval_steps_per_second": 0.541, "step": 400 } ], "logging_steps": 400, "max_steps": 1250, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 2.11050943217664e+17, "train_batch_size": 4, "trial_name": null, "trial_params": null }