{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 4.0, "eval_steps": 500, "global_step": 48, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.4166666666666667, "grad_norm": 0.19618070125579834, "learning_rate": 2e-05, "loss": 1.244796371459961, "step": 5 }, { "epoch": 0.8333333333333334, "grad_norm": 0.1641506403684616, "learning_rate": 4.5e-05, "loss": 1.1898921966552733, "step": 10 }, { "epoch": 1.25, "grad_norm": 0.18218567967414856, "learning_rate": 4.473684210526316e-05, "loss": 1.1768942832946778, "step": 15 }, { "epoch": 1.6666666666666665, "grad_norm": 0.1867283135652542, "learning_rate": 3.815789473684211e-05, "loss": 1.128943920135498, "step": 20 }, { "epoch": 2.0833333333333335, "grad_norm": 0.3101339638233185, "learning_rate": 3.157894736842105e-05, "loss": 1.1439960479736329, "step": 25 }, { "epoch": 2.5, "grad_norm": 0.21995241940021515, "learning_rate": 2.5e-05, "loss": 1.0380375862121582, "step": 30 }, { "epoch": 2.9166666666666665, "grad_norm": 0.28465187549591064, "learning_rate": 1.8421052631578947e-05, "loss": 0.9982780456542969, "step": 35 }, { "epoch": 3.3333333333333335, "grad_norm": 0.2934967875480652, "learning_rate": 1.1842105263157895e-05, "loss": 1.0306413650512696, "step": 40 }, { "epoch": 3.75, "grad_norm": 0.38119298219680786, "learning_rate": 5.263157894736842e-06, "loss": 0.9537362098693848, "step": 45 } ], "logging_steps": 5, "max_steps": 48, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 50, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3142797807845376.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }