{
  "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": 9168.4580078125,
      "learning_rate": 2.4e-07,
      "loss": 16.6978,
      "step": 10
    },
    {
      "epoch": 0.0010578512396694215,
      "grad_norm": 2087.102783203125,
      "learning_rate": 1.04e-06,
      "loss": 15.7625,
      "step": 20
    },
    {
      "epoch": 0.0015867768595041322,
      "grad_norm": 2472.9306640625,
      "learning_rate": 1.84e-06,
      "loss": 15.1353,
      "step": 30
    },
    {
      "epoch": 0.002115702479338843,
      "grad_norm": 2254.28271484375,
      "learning_rate": 2.64e-06,
      "loss": 14.9132,
      "step": 40
    },
    {
      "epoch": 0.002644628099173554,
      "grad_norm": 2219.509521484375,
      "learning_rate": 3.44e-06,
      "loss": 14.6851,
      "step": 50
    },
    {
      "epoch": 0.0031735537190082643,
      "grad_norm": 2151.2685546875,
      "learning_rate": 4.24e-06,
      "loss": 14.5536,
      "step": 60
    },
    {
      "epoch": 0.0037024793388429752,
      "grad_norm": 2181.529052734375,
      "learning_rate": 5.04e-06,
      "loss": 14.489,
      "step": 70
    },
    {
      "epoch": 0.004231404958677686,
      "grad_norm": 2351.65869140625,
      "learning_rate": 5.84e-06,
      "loss": 14.3607,
      "step": 80
    },
    {
      "epoch": 0.004760330578512397,
      "grad_norm": 1830.1292724609375,
      "learning_rate": 6.640000000000001e-06,
      "loss": 14.3096,
      "step": 90
    },
    {
      "epoch": 0.005289256198347108,
      "grad_norm": 2534.877197265625,
      "learning_rate": 7.44e-06,
      "loss": 14.1419,
      "step": 100
    },
    {
      "epoch": 0.005818181818181818,
      "grad_norm": 3552.001708984375,
      "learning_rate": 8.24e-06,
      "loss": 13.9957,
      "step": 110
    },
    {
      "epoch": 0.006347107438016529,
      "grad_norm": 1729.5421142578125,
      "learning_rate": 8.96e-06,
      "loss": 13.9384,
      "step": 120
    },
    {
      "epoch": 0.00687603305785124,
      "grad_norm": 1677.7344970703125,
      "learning_rate": 9.760000000000001e-06,
      "loss": 13.8056,
      "step": 130
    },
    {
      "epoch": 0.0074049586776859504,
      "grad_norm": 1419.7279052734375,
      "learning_rate": 1.056e-05,
      "loss": 13.5914,
      "step": 140
    },
    {
      "epoch": 0.007933884297520661,
      "grad_norm": 1191.801025390625,
      "learning_rate": 1.1360000000000001e-05,
      "loss": 13.4104,
      "step": 150
    },
    {
      "epoch": 0.008462809917355372,
      "grad_norm": 1145.3717041015625,
      "learning_rate": 1.216e-05,
      "loss": 13.4135,
      "step": 160
    },
    {
      "epoch": 0.008991735537190083,
      "grad_norm": 1149.420654296875,
      "learning_rate": 1.296e-05,
      "loss": 13.3217,
      "step": 170
    },
    {
      "epoch": 0.009520661157024794,
      "grad_norm": 690.7573852539062,
      "learning_rate": 1.376e-05,
      "loss": 13.2032,
      "step": 180
    },
    {
      "epoch": 0.010049586776859505,
      "grad_norm": 783.4169311523438,
      "learning_rate": 1.4560000000000001e-05,
      "loss": 13.2695,
      "step": 190
    },
    {
      "epoch": 0.010578512396694216,
      "grad_norm": 2450.64501953125,
      "learning_rate": 1.536e-05,
      "loss": 13.204,
      "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": 3228762868531200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}