{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9966555183946488, "eval_steps": 500, "global_step": 149, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.33444816053511706, "grad_norm": 0.13640224933624268, "learning_rate": 0.0001342281879194631, "loss": 0.483, "step": 50 }, { "epoch": 0.6688963210702341, "grad_norm": 0.1237262412905693, "learning_rate": 6.711409395973155e-05, "loss": 0.4136, "step": 100 } ], "logging_steps": 50, "max_steps": 149, "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": 4.842105642732749e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }