{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 36, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.8333333333333334, "grad_norm": 0.3025244176387787, "learning_rate": 0.000179801722728024, "loss": 1.4845, "step": 10 }, { "epoch": 1.6666666666666665, "grad_norm": 0.12496389448642731, "learning_rate": 0.0001, "loss": 0.9811, "step": 20 }, { "epoch": 2.5, "grad_norm": 0.10617413371801376, "learning_rate": 2.0198277271976052e-05, "loss": 0.8801, "step": 30 } ], "logging_steps": 10, "max_steps": 36, "num_input_tokens_seen": 0, "num_train_epochs": 3, "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": 1.0077636057366528e+17, "train_batch_size": 4, "trial_name": null, "trial_params": null }