{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.031735537190082645,
  "eval_steps": 500,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005289256198347108,
      "grad_norm": 641.732177734375,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 8.8563,
      "step": 10
    },
    {
      "epoch": 0.0010578512396694215,
      "grad_norm": 167.62478637695312,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 8.669,
      "step": 20
    },
    {
      "epoch": 0.0015867768595041322,
      "grad_norm": 132.942138671875,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 8.4099,
      "step": 30
    },
    {
      "epoch": 0.002115702479338843,
      "grad_norm": 87.03181457519531,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 8.3399,
      "step": 40
    },
    {
      "epoch": 0.002644628099173554,
      "grad_norm": 83.94163513183594,
      "learning_rate": 3.6e-06,
      "loss": 8.4131,
      "step": 50
    },
    {
      "epoch": 0.0031735537190082643,
      "grad_norm": 224.91473388671875,
      "learning_rate": 4.4e-06,
      "loss": 8.1753,
      "step": 60
    },
    {
      "epoch": 0.0037024793388429752,
      "grad_norm": 316.9183044433594,
      "learning_rate": 5.2e-06,
      "loss": 8.411,
      "step": 70
    },
    {
      "epoch": 0.004231404958677686,
      "grad_norm": 344.9347839355469,
      "learning_rate": 6e-06,
      "loss": 8.2236,
      "step": 80
    },
    {
      "epoch": 0.004760330578512397,
      "grad_norm": 131.94554138183594,
      "learning_rate": 6.800000000000001e-06,
      "loss": 8.2993,
      "step": 90
    },
    {
      "epoch": 0.005289256198347108,
      "grad_norm": 187.1765594482422,
      "learning_rate": 7.6e-06,
      "loss": 8.0748,
      "step": 100
    },
    {
      "epoch": 0.005818181818181818,
      "grad_norm": 185.48715209960938,
      "learning_rate": 8.400000000000001e-06,
      "loss": 8.0531,
      "step": 110
    },
    {
      "epoch": 0.006347107438016529,
      "grad_norm": 292.0998840332031,
      "learning_rate": 9.2e-06,
      "loss": 8.1898,
      "step": 120
    },
    {
      "epoch": 0.00687603305785124,
      "grad_norm": 236.91464233398438,
      "learning_rate": 1e-05,
      "loss": 8.0968,
      "step": 130
    },
    {
      "epoch": 0.0074049586776859504,
      "grad_norm": 276.836669921875,
      "learning_rate": 1.08e-05,
      "loss": 8.0387,
      "step": 140
    },
    {
      "epoch": 0.007933884297520661,
      "grad_norm": 226.5710906982422,
      "learning_rate": 1.16e-05,
      "loss": 7.9954,
      "step": 150
    },
    {
      "epoch": 0.008462809917355372,
      "grad_norm": 341.735595703125,
      "learning_rate": 1.232e-05,
      "loss": 7.9396,
      "step": 160
    },
    {
      "epoch": 0.008991735537190083,
      "grad_norm": 215.15040588378906,
      "learning_rate": 1.3120000000000001e-05,
      "loss": 8.0838,
      "step": 170
    },
    {
      "epoch": 0.009520661157024794,
      "grad_norm": 314.2020263671875,
      "learning_rate": 1.3919999999999999e-05,
      "loss": 7.9612,
      "step": 180
    },
    {
      "epoch": 0.010049586776859505,
      "grad_norm": 1104.496826171875,
      "learning_rate": 1.472e-05,
      "loss": 7.8864,
      "step": 190
    },
    {
      "epoch": 0.010578512396694216,
      "grad_norm": 114.84138488769531,
      "learning_rate": 1.552e-05,
      "loss": 7.7783,
      "step": 200
    },
    {
      "epoch": 0.0005289256198347108,
      "grad_norm": 298.0364685058594,
      "learning_rate": 1.6320000000000003e-05,
      "loss": 7.7893,
      "step": 210
    },
    {
      "epoch": 0.0010578512396694215,
      "grad_norm": 215.82244873046875,
      "learning_rate": 1.712e-05,
      "loss": 7.779,
      "step": 220
    },
    {
      "epoch": 0.0015867768595041322,
      "grad_norm": 247.94859313964844,
      "learning_rate": 1.792e-05,
      "loss": 7.6925,
      "step": 230
    },
    {
      "epoch": 0.002115702479338843,
      "grad_norm": 97.73837280273438,
      "learning_rate": 1.872e-05,
      "loss": 7.6725,
      "step": 240
    },
    {
      "epoch": 0.002644628099173554,
      "grad_norm": 141.45123291015625,
      "learning_rate": 1.9520000000000003e-05,
      "loss": 7.7421,
      "step": 250
    },
    {
      "epoch": 0.0031735537190082643,
      "grad_norm": 200.86509704589844,
      "learning_rate": 2.032e-05,
      "loss": 7.5497,
      "step": 260
    },
    {
      "epoch": 0.0037024793388429752,
      "grad_norm": 185.7206268310547,
      "learning_rate": 2.112e-05,
      "loss": 7.7364,
      "step": 270
    },
    {
      "epoch": 0.004231404958677686,
      "grad_norm": 101.28189086914062,
      "learning_rate": 2.192e-05,
      "loss": 7.5938,
      "step": 280
    },
    {
      "epoch": 0.004760330578512397,
      "grad_norm": 330.9864807128906,
      "learning_rate": 2.2720000000000003e-05,
      "loss": 7.6908,
      "step": 290
    },
    {
      "epoch": 0.005289256198347108,
      "grad_norm": 148.31687927246094,
      "learning_rate": 2.3520000000000002e-05,
      "loss": 7.5153,
      "step": 300
    },
    {
      "epoch": 0.005818181818181818,
      "grad_norm": 123.8593521118164,
      "learning_rate": 2.432e-05,
      "loss": 7.5011,
      "step": 310
    },
    {
      "epoch": 0.006347107438016529,
      "grad_norm": 114.53250122070312,
      "learning_rate": 2.512e-05,
      "loss": 7.6091,
      "step": 320
    },
    {
      "epoch": 0.00687603305785124,
      "grad_norm": 112.7503662109375,
      "learning_rate": 2.592e-05,
      "loss": 7.5382,
      "step": 330
    },
    {
      "epoch": 0.0074049586776859504,
      "grad_norm": 97.62100219726562,
      "learning_rate": 2.672e-05,
      "loss": 7.5186,
      "step": 340
    },
    {
      "epoch": 0.007933884297520661,
      "grad_norm": 171.15858459472656,
      "learning_rate": 2.752e-05,
      "loss": 7.4748,
      "step": 350
    },
    {
      "epoch": 0.008462809917355372,
      "grad_norm": 149.8796844482422,
      "learning_rate": 2.8320000000000003e-05,
      "loss": 7.4303,
      "step": 360
    },
    {
      "epoch": 0.008991735537190083,
      "grad_norm": 92.16109466552734,
      "learning_rate": 2.9120000000000002e-05,
      "loss": 7.5469,
      "step": 370
    },
    {
      "epoch": 0.009520661157024794,
      "grad_norm": 94.65399932861328,
      "learning_rate": 2.9920000000000005e-05,
      "loss": 7.477,
      "step": 380
    },
    {
      "epoch": 0.010049586776859505,
      "grad_norm": 100.26766967773438,
      "learning_rate": 3.072e-05,
      "loss": 7.4068,
      "step": 390
    },
    {
      "epoch": 0.010578512396694216,
      "grad_norm": 121.88914489746094,
      "learning_rate": 3.1519999999999996e-05,
      "loss": 7.3082,
      "step": 400
    },
    {
      "epoch": 0.011107438016528925,
      "grad_norm": 129.8812255859375,
      "learning_rate": 3.232e-05,
      "loss": 7.2946,
      "step": 410
    },
    {
      "epoch": 0.011636363636363636,
      "grad_norm": 161.5423126220703,
      "learning_rate": 3.312e-05,
      "loss": 7.2299,
      "step": 420
    },
    {
      "epoch": 0.012165289256198347,
      "grad_norm": 143.5394744873047,
      "learning_rate": 3.392e-05,
      "loss": 7.242,
      "step": 430
    },
    {
      "epoch": 0.012694214876033057,
      "grad_norm": 68.21272277832031,
      "learning_rate": 3.472e-05,
      "loss": 7.191,
      "step": 440
    },
    {
      "epoch": 0.013223140495867768,
      "grad_norm": 103.70673370361328,
      "learning_rate": 3.5520000000000006e-05,
      "loss": 7.2327,
      "step": 450
    },
    {
      "epoch": 0.01375206611570248,
      "grad_norm": 185.54530334472656,
      "learning_rate": 3.6320000000000005e-05,
      "loss": 7.2653,
      "step": 460
    },
    {
      "epoch": 0.01428099173553719,
      "grad_norm": 119.81388092041016,
      "learning_rate": 3.712e-05,
      "loss": 7.1239,
      "step": 470
    },
    {
      "epoch": 0.014809917355371901,
      "grad_norm": 151.85702514648438,
      "learning_rate": 3.792e-05,
      "loss": 7.156,
      "step": 480
    },
    {
      "epoch": 0.015338842975206612,
      "grad_norm": 142.77293395996094,
      "learning_rate": 3.872e-05,
      "loss": 7.1226,
      "step": 490
    },
    {
      "epoch": 0.015867768595041323,
      "grad_norm": 91.57913970947266,
      "learning_rate": 3.952e-05,
      "loss": 7.1236,
      "step": 500
    },
    {
      "epoch": 0.016396694214876033,
      "grad_norm": 105.25820922851562,
      "learning_rate": 4.032e-05,
      "loss": 7.0561,
      "step": 510
    },
    {
      "epoch": 0.016925619834710744,
      "grad_norm": 96.5208740234375,
      "learning_rate": 4.1120000000000006e-05,
      "loss": 7.1003,
      "step": 520
    },
    {
      "epoch": 0.017454545454545455,
      "grad_norm": 101.59559631347656,
      "learning_rate": 4.1920000000000005e-05,
      "loss": 7.0201,
      "step": 530
    },
    {
      "epoch": 0.017983471074380166,
      "grad_norm": 82.07259368896484,
      "learning_rate": 4.2720000000000004e-05,
      "loss": 6.9144,
      "step": 540
    },
    {
      "epoch": 0.018512396694214877,
      "grad_norm": 132.1178436279297,
      "learning_rate": 4.352e-05,
      "loss": 7.0484,
      "step": 550
    },
    {
      "epoch": 0.019041322314049588,
      "grad_norm": 179.69866943359375,
      "learning_rate": 4.432e-05,
      "loss": 6.8724,
      "step": 560
    },
    {
      "epoch": 0.0195702479338843,
      "grad_norm": 108.14857482910156,
      "learning_rate": 4.512e-05,
      "loss": 7.0,
      "step": 570
    },
    {
      "epoch": 0.02009917355371901,
      "grad_norm": 93.1995849609375,
      "learning_rate": 4.592e-05,
      "loss": 7.0588,
      "step": 580
    },
    {
      "epoch": 0.02062809917355372,
      "grad_norm": 78.22120666503906,
      "learning_rate": 4.672e-05,
      "loss": 6.9692,
      "step": 590
    },
    {
      "epoch": 0.02115702479338843,
      "grad_norm": 81.8231201171875,
      "learning_rate": 4.7520000000000006e-05,
      "loss": 6.8607,
      "step": 600
    },
    {
      "epoch": 0.021685950413223142,
      "grad_norm": 81.69812774658203,
      "learning_rate": 4.8320000000000005e-05,
      "loss": 6.8804,
      "step": 610
    },
    {
      "epoch": 0.02221487603305785,
      "grad_norm": 67.32670593261719,
      "learning_rate": 4.9120000000000004e-05,
      "loss": 6.8825,
      "step": 620
    },
    {
      "epoch": 0.02274380165289256,
      "grad_norm": 79.66416931152344,
      "learning_rate": 4.992e-05,
      "loss": 6.8302,
      "step": 630
    },
    {
      "epoch": 0.02327272727272727,
      "grad_norm": 91.50218200683594,
      "learning_rate": 5.072e-05,
      "loss": 6.8396,
      "step": 640
    },
    {
      "epoch": 0.023801652892561982,
      "grad_norm": 68.5249252319336,
      "learning_rate": 5.152e-05,
      "loss": 6.8103,
      "step": 650
    },
    {
      "epoch": 0.024330578512396693,
      "grad_norm": 50.630306243896484,
      "learning_rate": 5.232e-05,
      "loss": 6.8521,
      "step": 660
    },
    {
      "epoch": 0.024859504132231404,
      "grad_norm": 59.39335632324219,
      "learning_rate": 5.3120000000000006e-05,
      "loss": 6.8262,
      "step": 670
    },
    {
      "epoch": 0.025388429752066115,
      "grad_norm": 52.00175094604492,
      "learning_rate": 5.3920000000000006e-05,
      "loss": 6.7173,
      "step": 680
    },
    {
      "epoch": 0.025917355371900826,
      "grad_norm": 59.93027877807617,
      "learning_rate": 5.4720000000000005e-05,
      "loss": 6.6567,
      "step": 690
    },
    {
      "epoch": 0.026446280991735537,
      "grad_norm": 71.15003204345703,
      "learning_rate": 5.5520000000000004e-05,
      "loss": 6.7098,
      "step": 700
    },
    {
      "epoch": 0.026975206611570247,
      "grad_norm": 81.00093841552734,
      "learning_rate": 5.632e-05,
      "loss": 6.7311,
      "step": 710
    },
    {
      "epoch": 0.02750413223140496,
      "grad_norm": 88.47158813476562,
      "learning_rate": 5.712000000000001e-05,
      "loss": 6.6873,
      "step": 720
    },
    {
      "epoch": 0.02803305785123967,
      "grad_norm": 74.94734191894531,
      "learning_rate": 5.792000000000001e-05,
      "loss": 6.6633,
      "step": 730
    },
    {
      "epoch": 0.02856198347107438,
      "grad_norm": 70.46430969238281,
      "learning_rate": 5.872000000000001e-05,
      "loss": 6.6849,
      "step": 740
    },
    {
      "epoch": 0.02909090909090909,
      "grad_norm": 56.99905014038086,
      "learning_rate": 5.952e-05,
      "loss": 6.6271,
      "step": 750
    },
    {
      "epoch": 0.029619834710743802,
      "grad_norm": 63.47657012939453,
      "learning_rate": 6.032e-05,
      "loss": 6.6473,
      "step": 760
    },
    {
      "epoch": 0.030148760330578513,
      "grad_norm": 60.045875549316406,
      "learning_rate": 6.112e-05,
      "loss": 6.5595,
      "step": 770
    },
    {
      "epoch": 0.030677685950413223,
      "grad_norm": 50.319881439208984,
      "learning_rate": 6.192e-05,
      "loss": 6.5524,
      "step": 780
    },
    {
      "epoch": 0.031206611570247934,
      "grad_norm": 47.301361083984375,
      "learning_rate": 6.272e-05,
      "loss": 6.5123,
      "step": 790
    },
    {
      "epoch": 0.031735537190082645,
      "grad_norm": 52.02754211425781,
      "learning_rate": 6.352e-05,
      "loss": 6.4223,
      "step": 800
    }
  ],
  "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": 1.35981486022656e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}