coreset-selection/mix_diff_5

1{2  "best_global_step": null,3  "best_metric": null,4  "best_model_checkpoint": null,5  "epoch": 5.0,6  "eval_steps": 500,7  "global_step": 650,8  "is_hyper_param_search": false,9  "is_local_process_zero": true,10  "is_world_process_zero": true,11  "log_history": [12    {13      "epoch": 3.8461538461538463,14      "grad_norm": 168.01385498046875,15      "learning_rate": 2.3230769230769234e-06,16      "loss": -75.8711,17      "step": 50018    }19  ],20  "logging_steps": 500,21  "max_steps": 650,22  "num_input_tokens_seen": 0,23  "num_train_epochs": 5,24  "save_steps": 500,25  "stateful_callbacks": {26    "TrainerControl": {27      "args": {28        "should_epoch_stop": false,29        "should_evaluate": false,30        "should_log": false,31        "should_save": true,32        "should_training_stop": true33      },34      "attributes": {}35    }36  },37  "total_flos": 0.0,38  "train_batch_size": 2,39  "trial_name": null,40  "trial_params": null41}42