{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02099875319902881,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005249688299757202,
      "grad_norm": 4051.18359375,
      "learning_rate": 9e-07,
      "loss": 7.93,
      "step": 10
    },
    {
      "epoch": 0.0010499376599514404,
      "grad_norm": 111.26915740966797,
      "learning_rate": 3.899999999999999e-06,
      "loss": 7.7273,
      "step": 20
    },
    {
      "epoch": 0.0015749064899271605,
      "grad_norm": 176.40713500976562,
      "learning_rate": 6.899999999999999e-06,
      "loss": 7.5271,
      "step": 30
    },
    {
      "epoch": 0.002099875319902881,
      "grad_norm": 668.3442993164062,
      "learning_rate": 9.9e-06,
      "loss": 7.6155,
      "step": 40
    },
    {
      "epoch": 0.002624844149878601,
      "grad_norm": 171.85369873046875,
      "learning_rate": 1.2899999999999998e-05,
      "loss": 7.4873,
      "step": 50
    },
    {
      "epoch": 0.003149812979854321,
      "grad_norm": 477.1031494140625,
      "learning_rate": 1.5899999999999997e-05,
      "loss": 7.4295,
      "step": 60
    },
    {
      "epoch": 0.0036747818098300414,
      "grad_norm": 256.7841491699219,
      "learning_rate": 1.89e-05,
      "loss": 7.3037,
      "step": 70
    },
    {
      "epoch": 0.004199750639805762,
      "grad_norm": 240.86167907714844,
      "learning_rate": 2.1899999999999997e-05,
      "loss": 7.3488,
      "step": 80
    },
    {
      "epoch": 0.0047247194697814816,
      "grad_norm": 151.8752899169922,
      "learning_rate": 2.49e-05,
      "loss": 7.1664,
      "step": 90
    },
    {
      "epoch": 0.005249688299757202,
      "grad_norm": 92.41702270507812,
      "learning_rate": 2.7899999999999997e-05,
      "loss": 7.2001,
      "step": 100
    },
    {
      "epoch": 0.005774657129732922,
      "grad_norm": 125.6628189086914,
      "learning_rate": 3.09e-05,
      "loss": 7.1956,
      "step": 110
    },
    {
      "epoch": 0.006299625959708642,
      "grad_norm": 105.1700210571289,
      "learning_rate": 3.39e-05,
      "loss": 7.2136,
      "step": 120
    },
    {
      "epoch": 0.006824594789684363,
      "grad_norm": 95.49678039550781,
      "learning_rate": 3.6899999999999996e-05,
      "loss": 7.2046,
      "step": 130
    },
    {
      "epoch": 0.007349563619660083,
      "grad_norm": 70.33267974853516,
      "learning_rate": 3.99e-05,
      "loss": 7.0895,
      "step": 140
    },
    {
      "epoch": 0.007874532449635803,
      "grad_norm": 42.994972229003906,
      "learning_rate": 4.289999999999999e-05,
      "loss": 7.1157,
      "step": 150
    },
    {
      "epoch": 0.008399501279611523,
      "grad_norm": 87.23907470703125,
      "learning_rate": 4.59e-05,
      "loss": 7.1537,
      "step": 160
    },
    {
      "epoch": 0.008924470109587244,
      "grad_norm": 53.14045333862305,
      "learning_rate": 4.8899999999999996e-05,
      "loss": 7.0126,
      "step": 170
    },
    {
      "epoch": 0.009449438939562963,
      "grad_norm": 44.222225189208984,
      "learning_rate": 5.1899999999999994e-05,
      "loss": 7.1067,
      "step": 180
    },
    {
      "epoch": 0.009974407769538684,
      "grad_norm": 65.67877197265625,
      "learning_rate": 5.489999999999999e-05,
      "loss": 7.0359,
      "step": 190
    },
    {
      "epoch": 0.010499376599514405,
      "grad_norm": 34.80784225463867,
      "learning_rate": 5.79e-05,
      "loss": 7.0124,
      "step": 200
    },
    {
      "epoch": 0.011024345429490124,
      "grad_norm": 80.05706024169922,
      "learning_rate": 6.0899999999999996e-05,
      "loss": 6.9882,
      "step": 210
    },
    {
      "epoch": 0.011549314259465844,
      "grad_norm": 18.072044372558594,
      "learning_rate": 6.39e-05,
      "loss": 7.082,
      "step": 220
    },
    {
      "epoch": 0.012074283089441565,
      "grad_norm": 27.460533142089844,
      "learning_rate": 6.69e-05,
      "loss": 7.0056,
      "step": 230
    },
    {
      "epoch": 0.012599251919417284,
      "grad_norm": 20.942256927490234,
      "learning_rate": 6.989999999999999e-05,
      "loss": 7.0385,
      "step": 240
    },
    {
      "epoch": 0.013124220749393005,
      "grad_norm": 21.205760955810547,
      "learning_rate": 7.29e-05,
      "loss": 6.9065,
      "step": 250
    },
    {
      "epoch": 0.013649189579368726,
      "grad_norm": 30.357505798339844,
      "learning_rate": 7.589999999999999e-05,
      "loss": 6.9887,
      "step": 260
    },
    {
      "epoch": 0.014174158409344445,
      "grad_norm": 21.6142520904541,
      "learning_rate": 7.89e-05,
      "loss": 7.0671,
      "step": 270
    },
    {
      "epoch": 0.014699127239320165,
      "grad_norm": 34.31865310668945,
      "learning_rate": 8.19e-05,
      "loss": 6.9352,
      "step": 280
    },
    {
      "epoch": 0.015224096069295886,
      "grad_norm": 31.643892288208008,
      "learning_rate": 8.489999999999999e-05,
      "loss": 7.0615,
      "step": 290
    },
    {
      "epoch": 0.015749064899271605,
      "grad_norm": 21.246601104736328,
      "learning_rate": 8.789999999999998e-05,
      "loss": 6.8747,
      "step": 300
    },
    {
      "epoch": 0.016274033729247326,
      "grad_norm": 17.99869155883789,
      "learning_rate": 9.089999999999999e-05,
      "loss": 6.9325,
      "step": 310
    },
    {
      "epoch": 0.016799002559223047,
      "grad_norm": 10.438518524169922,
      "learning_rate": 9.389999999999999e-05,
      "loss": 6.975,
      "step": 320
    },
    {
      "epoch": 0.017323971389198767,
      "grad_norm": 38.324283599853516,
      "learning_rate": 9.69e-05,
      "loss": 6.8833,
      "step": 330
    },
    {
      "epoch": 0.017848940219174488,
      "grad_norm": 25.789045333862305,
      "learning_rate": 9.99e-05,
      "loss": 6.869,
      "step": 340
    },
    {
      "epoch": 0.018373909049150206,
      "grad_norm": 26.649545669555664,
      "learning_rate": 0.0001029,
      "loss": 6.8773,
      "step": 350
    },
    {
      "epoch": 0.018898877879125926,
      "grad_norm": 24.452266693115234,
      "learning_rate": 0.00010589999999999999,
      "loss": 6.7558,
      "step": 360
    },
    {
      "epoch": 0.019423846709101647,
      "grad_norm": 14.234713554382324,
      "learning_rate": 0.00010889999999999999,
      "loss": 6.9624,
      "step": 370
    },
    {
      "epoch": 0.019948815539077368,
      "grad_norm": 16.222957611083984,
      "learning_rate": 0.0001119,
      "loss": 6.9116,
      "step": 380
    },
    {
      "epoch": 0.02047378436905309,
      "grad_norm": 14.955327033996582,
      "learning_rate": 0.00011489999999999999,
      "loss": 6.8227,
      "step": 390
    },
    {
      "epoch": 0.02099875319902881,
      "grad_norm": 13.272610664367676,
      "learning_rate": 0.00011789999999999999,
      "loss": 6.8292,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 10000000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 525,
  "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": 6034263560601600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}