{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010578512396694216,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005289256198347108,
      "grad_norm": 7458.9189453125,
      "learning_rate": 1.6e-07,
      "loss": 16.4424,
      "step": 10
    },
    {
      "epoch": 0.0010578512396694215,
      "grad_norm": 2789.625,
      "learning_rate": 9.6e-07,
      "loss": 15.6542,
      "step": 20
    },
    {
      "epoch": 0.0015867768595041322,
      "grad_norm": 2489.71142578125,
      "learning_rate": 1.76e-06,
      "loss": 15.1573,
      "step": 30
    },
    {
      "epoch": 0.002115702479338843,
      "grad_norm": 2955.32568359375,
      "learning_rate": 2.56e-06,
      "loss": 14.8308,
      "step": 40
    },
    {
      "epoch": 0.002644628099173554,
      "grad_norm": 2157.26318359375,
      "learning_rate": 3.36e-06,
      "loss": 14.6636,
      "step": 50
    },
    {
      "epoch": 0.0031735537190082643,
      "grad_norm": 2898.47314453125,
      "learning_rate": 4.16e-06,
      "loss": 14.5921,
      "step": 60
    },
    {
      "epoch": 0.0037024793388429752,
      "grad_norm": 2458.47607421875,
      "learning_rate": 4.96e-06,
      "loss": 14.501,
      "step": 70
    },
    {
      "epoch": 0.004231404958677686,
      "grad_norm": 2568.217529296875,
      "learning_rate": 5.76e-06,
      "loss": 14.3649,
      "step": 80
    },
    {
      "epoch": 0.004760330578512397,
      "grad_norm": 2298.6142578125,
      "learning_rate": 6.560000000000001e-06,
      "loss": 14.2622,
      "step": 90
    },
    {
      "epoch": 0.005289256198347108,
      "grad_norm": 2145.729248046875,
      "learning_rate": 7.36e-06,
      "loss": 14.1271,
      "step": 100
    },
    {
      "epoch": 0.005818181818181818,
      "grad_norm": 2116.720458984375,
      "learning_rate": 8.160000000000001e-06,
      "loss": 14.0036,
      "step": 110
    },
    {
      "epoch": 0.006347107438016529,
      "grad_norm": 1847.9112548828125,
      "learning_rate": 8.96e-06,
      "loss": 13.8998,
      "step": 120
    },
    {
      "epoch": 0.00687603305785124,
      "grad_norm": 1758.4593505859375,
      "learning_rate": 9.760000000000001e-06,
      "loss": 13.8227,
      "step": 130
    },
    {
      "epoch": 0.0074049586776859504,
      "grad_norm": 3267.474365234375,
      "learning_rate": 1.056e-05,
      "loss": 13.7623,
      "step": 140
    },
    {
      "epoch": 0.007933884297520661,
      "grad_norm": 1531.384521484375,
      "learning_rate": 1.1360000000000001e-05,
      "loss": 13.5285,
      "step": 150
    },
    {
      "epoch": 0.008462809917355372,
      "grad_norm": 1631.8902587890625,
      "learning_rate": 1.216e-05,
      "loss": 13.3848,
      "step": 160
    },
    {
      "epoch": 0.008991735537190083,
      "grad_norm": 1016.30419921875,
      "learning_rate": 1.296e-05,
      "loss": 13.3074,
      "step": 170
    },
    {
      "epoch": 0.009520661157024794,
      "grad_norm": 1558.402099609375,
      "learning_rate": 1.376e-05,
      "loss": 13.121,
      "step": 180
    },
    {
      "epoch": 0.010049586776859505,
      "grad_norm": 1313.5159912109375,
      "learning_rate": 1.4560000000000001e-05,
      "loss": 12.9932,
      "step": 190
    },
    {
      "epoch": 0.010578512396694216,
      "grad_norm": 1270.5982666015625,
      "learning_rate": 1.536e-05,
      "loss": 13.0639,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 10000000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 529,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3369969725030400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}