{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.5911330049261084, "eval_steps": 500, "global_step": 30, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.09852216748768473, "grad_norm": 0.9535083770751953, "learning_rate": 1e-05, "loss": 0.8235, "step": 5 }, { "epoch": 0.19704433497536947, "grad_norm": 0.8967114686965942, "learning_rate": 2e-05, "loss": 0.8996, "step": 10 }, { "epoch": 0.2955665024630542, "grad_norm": 0.7553922533988953, "learning_rate": 3e-05, "loss": 0.8739, "step": 15 }, { "epoch": 0.39408866995073893, "grad_norm": 12.434737205505371, "learning_rate": 4e-05, "loss": 0.6414, "step": 20 }, { "epoch": 0.49261083743842365, "grad_norm": 0.6539486646652222, "learning_rate": 5e-05, "loss": 0.8106, "step": 25 }, { "epoch": 0.5911330049261084, "grad_norm": 0.5894852876663208, "learning_rate": 6e-05, "loss": 0.7937, "step": 30 } ], "logging_steps": 5, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3091040890361856.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }