{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 0,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": 26.334327697753906,
      "learning_rate": 1e-05,
      "loss": 2.1409,
      "step": 1
    },
    {
      "epoch": 0.1,
      "grad_norm": 15.562271118164062,
      "learning_rate": 9.938441702975689e-06,
      "loss": 1.6196,
      "step": 2
    },
    {
      "epoch": 0.15,
      "grad_norm": 14.094306945800781,
      "learning_rate": 9.755282581475769e-06,
      "loss": 1.129,
      "step": 3
    },
    {
      "epoch": 0.2,
      "grad_norm": 4.661797046661377,
      "learning_rate": 9.45503262094184e-06,
      "loss": 1.0874,
      "step": 4
    },
    {
      "epoch": 0.25,
      "grad_norm": 4.918830394744873,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.753,
      "step": 5
    },
    {
      "epoch": 0.3,
      "grad_norm": 2.3401432037353516,
      "learning_rate": 8.535533905932739e-06,
      "loss": 1.1073,
      "step": 6
    },
    {
      "epoch": 0.35,
      "grad_norm": 3.3569436073303223,
      "learning_rate": 7.938926261462366e-06,
      "loss": 0.7875,
      "step": 7
    },
    {
      "epoch": 0.4,
      "grad_norm": 2.3275091648101807,
      "learning_rate": 7.269952498697734e-06,
      "loss": 0.9165,
      "step": 8
    },
    {
      "epoch": 0.45,
      "grad_norm": 1.800915241241455,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.6282,
      "step": 9
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.53364098072052,
      "learning_rate": 5.782172325201155e-06,
      "loss": 0.76,
      "step": 10
    },
    {
      "epoch": 0.55,
      "grad_norm": 1.6132928133010864,
      "learning_rate": 5e-06,
      "loss": 0.7304,
      "step": 11
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.694688081741333,
      "learning_rate": 4.217827674798845e-06,
      "loss": 0.8017,
      "step": 12
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.9866068363189697,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.689,
      "step": 13
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.8587181568145752,
      "learning_rate": 2.7300475013022666e-06,
      "loss": 0.5015,
      "step": 14
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.231115698814392,
      "learning_rate": 2.061073738537635e-06,
      "loss": 0.6943,
      "step": 15
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.9891624450683594,
      "learning_rate": 1.4644660940672628e-06,
      "loss": 0.6611,
      "step": 16
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.6427974700927734,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.6361,
      "step": 17
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.6921979784965515,
      "learning_rate": 5.449673790581611e-07,
      "loss": 0.693,
      "step": 18
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.5541855096817017,
      "learning_rate": 2.447174185242324e-07,
      "loss": 0.584,
      "step": 19
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6362800598144531,
      "learning_rate": 6.15582970243117e-08,
      "loss": 0.6599,
      "step": 20
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1749898475850957e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}