{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.05664117813650524, "eval_steps": 354, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.05664117813650524, "grad_norm": 0.7603653073310852, "learning_rate": 0.0001978110599078341, "loss": 0.9425, "step": 50 } ], "logging_steps": 50, "max_steps": 1766, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 50, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1683857178842112.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }