{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 158, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.31645569620253167, "grad_norm": 7.34375, "learning_rate": 3.8380281690140847e-05, "loss": 0.3713, "step": 50 }, { "epoch": 0.6329113924050633, "grad_norm": 6.59375, "learning_rate": 2.0774647887323944e-05, "loss": 0.25, "step": 100 }, { "epoch": 0.9493670886075949, "grad_norm": 5.4375, "learning_rate": 3.1690140845070423e-06, "loss": 0.2071, "step": 150 } ], "logging_steps": 50, "max_steps": 158, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 200, "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": 512, "trial_name": null, "trial_params": null }