{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 8, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.12903225806451613, "grad_norm": 2.0922131538391113, "learning_rate": 3.3333333333333333e-06, "loss": 0.6097, "step": 1 }, { "epoch": 0.25806451612903225, "grad_norm": 2.037680149078369, "learning_rate": 6.666666666666667e-06, "loss": 0.5815, "step": 2 }, { "epoch": 0.3870967741935484, "grad_norm": 1.9914177656173706, "learning_rate": 1e-05, "loss": 0.5731, "step": 3 }, { "epoch": 0.5161290322580645, "grad_norm": 1.7522591352462769, "learning_rate": 9.960573506572391e-06, "loss": 0.5499, "step": 4 }, { "epoch": 0.6451612903225806, "grad_norm": 1.2676565647125244, "learning_rate": 9.842915805643156e-06, "loss": 0.5117, "step": 5 }, { "epoch": 0.7741935483870968, "grad_norm": 0.952801525592804, "learning_rate": 9.648882429441258e-06, "loss": 0.4997, "step": 6 }, { "epoch": 0.9032258064516129, "grad_norm": 1.187522053718567, "learning_rate": 9.381533400219319e-06, "loss": 0.5062, "step": 7 }, { "epoch": 1.0, "grad_norm": 1.187522053718567, "learning_rate": 9.045084971874738e-06, "loss": 0.4698, "step": 8 } ], "logging_steps": 1, "max_steps": 28, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 8, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 20890886602752.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }