{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 511,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19598236158745713,
      "grad_norm": 0.5924571752548218,
      "learning_rate": 4.8717575860738964e-05,
      "loss": 2.7653,
      "step": 100
    },
    {
      "epoch": 0.39196472317491426,
      "grad_norm": 0.619646430015564,
      "learning_rate": 3.837832853196751e-05,
      "loss": 2.5824,
      "step": 200
    },
    {
      "epoch": 0.5879470847623713,
      "grad_norm": 0.639843761920929,
      "learning_rate": 2.2012717447288033e-05,
      "loss": 2.5573,
      "step": 300
    },
    {
      "epoch": 0.7839294463498285,
      "grad_norm": 0.5742502808570862,
      "learning_rate": 6.992749150592343e-06,
      "loss": 2.5434,
      "step": 400
    },
    {
      "epoch": 0.9799118079372856,
      "grad_norm": 0.5816153883934021,
      "learning_rate": 8.427576920763958e-08,
      "loss": 2.5382,
      "step": 500
    },
    {
      "epoch": 1.0,
      "step": 511,
      "total_flos": 1.57501919592864e+16,
      "train_loss": 2.5953986285484,
      "train_runtime": 1479.6737,
      "train_samples_per_second": 11.034,
      "train_steps_per_second": 0.345
    }
  ],
  "logging_steps": 100,
  "max_steps": 511,
  "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": 1.57501919592864e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}