{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.027932960893854747, "eval_steps": 5, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00558659217877095, "eval_loss": NaN, "eval_runtime": 8.7411, "eval_samples_per_second": 34.549, "eval_steps_per_second": 4.347, "step": 1 }, { "epoch": 0.01675977653631285, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.027932960893854747, "eval_loss": NaN, "eval_runtime": 8.1897, "eval_samples_per_second": 36.876, "eval_steps_per_second": 4.64, "step": 5 } ], "logging_steps": 3, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 5, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1360723653427200.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }