{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006666666666666667,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003333333333333333,
      "grad_norm": 252.23410034179688,
      "learning_rate": 5.95e-06,
      "loss": 166.30635986328124,
      "original_ce_loss": 10.3935,
      "step": 10
    },
    {
      "epoch": 0.0006666666666666666,
      "grad_norm": 251.30441284179688,
      "learning_rate": 1.445e-05,
      "loss": 166.0551513671875,
      "original_ce_loss": 10.3778,
      "step": 20
    },
    {
      "epoch": 0.001,
      "grad_norm": 252.8511199951172,
      "learning_rate": 2.295e-05,
      "loss": 165.40390625,
      "original_ce_loss": 10.3371,
      "step": 30
    },
    {
      "epoch": 0.0013333333333333333,
      "grad_norm": 279.1929016113281,
      "learning_rate": 3.145e-05,
      "loss": 164.07041015625,
      "original_ce_loss": 10.2537,
      "step": 40
    },
    {
      "epoch": 0.0016666666666666668,
      "grad_norm": 348.9263000488281,
      "learning_rate": 3.9949999999999995e-05,
      "loss": 160.942431640625,
      "original_ce_loss": 10.0582,
      "step": 50
    },
    {
      "epoch": 0.002,
      "grad_norm": 266.1781311035156,
      "learning_rate": 4.76e-05,
      "loss": 153.2720947265625,
      "original_ce_loss": 9.5788,
      "step": 60
    },
    {
      "epoch": 0.0023333333333333335,
      "grad_norm": 68.32039642333984,
      "learning_rate": 5.61e-05,
      "loss": 143.15457763671876,
      "original_ce_loss": 8.9465,
      "step": 70
    },
    {
      "epoch": 0.0026666666666666666,
      "grad_norm": NaN,
      "learning_rate": 5.95e-05,
      "loss": 138.36038818359376,
      "original_ce_loss": 8.6468,
      "step": 80
    },
    {
      "epoch": 0.003,
      "grad_norm": 45.997161865234375,
      "learning_rate": 6.46e-05,
      "loss": 136.0820068359375,
      "original_ce_loss": 8.5044,
      "step": 90
    },
    {
      "epoch": 0.0033333333333333335,
      "grad_norm": 41.57798385620117,
      "learning_rate": 7.309999999999999e-05,
      "loss": 130.63963623046874,
      "original_ce_loss": 8.1643,
      "step": 100
    },
    {
      "epoch": 0.0036666666666666666,
      "grad_norm": 36.38893508911133,
      "learning_rate": 8.159999999999999e-05,
      "loss": 125.012890625,
      "original_ce_loss": 7.8126,
      "step": 110
    },
    {
      "epoch": 0.004,
      "grad_norm": 34.60835647583008,
      "learning_rate": 9.01e-05,
      "loss": 118.98409423828124,
      "original_ce_loss": 7.4358,
      "step": 120
    },
    {
      "epoch": 0.004333333333333333,
      "grad_norm": 27.233781814575195,
      "learning_rate": 9.86e-05,
      "loss": 113.41510009765625,
      "original_ce_loss": 7.0878,
      "step": 130
    },
    {
      "epoch": 0.004666666666666667,
      "grad_norm": 14.006446838378906,
      "learning_rate": 0.0001071,
      "loss": 109.00380859375,
      "original_ce_loss": 6.8121,
      "step": 140
    },
    {
      "epoch": 0.005,
      "grad_norm": 15.040637969970703,
      "learning_rate": 0.0001156,
      "loss": 106.41650390625,
      "original_ce_loss": 6.6504,
      "step": 150
    },
    {
      "epoch": 0.005333333333333333,
      "grad_norm": 16.328678131103516,
      "learning_rate": 0.00012409999999999998,
      "loss": 104.68450927734375,
      "original_ce_loss": 6.5421,
      "step": 160
    },
    {
      "epoch": 0.005666666666666667,
      "grad_norm": 47.60938262939453,
      "learning_rate": 0.0001326,
      "loss": 104.513427734375,
      "original_ce_loss": 6.5314,
      "step": 170
    },
    {
      "epoch": 0.006,
      "grad_norm": 23.81610679626465,
      "learning_rate": 0.0001411,
      "loss": 104.72510986328125,
      "original_ce_loss": 6.5447,
      "step": 180
    },
    {
      "epoch": 0.006333333333333333,
      "grad_norm": 19.716007232666016,
      "learning_rate": 0.00014959999999999998,
      "loss": 104.5696044921875,
      "original_ce_loss": 6.5349,
      "step": 190
    },
    {
      "epoch": 0.006666666666666667,
      "grad_norm": 43.200706481933594,
      "learning_rate": 0.0001581,
      "loss": 104.36375732421875,
      "original_ce_loss": 6.5221,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 30000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.47372918177792e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}