{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06347107438016529,
  "eval_steps": 500,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005289256198347108,
      "grad_norm": 2042.0159912109375,
      "learning_rate": 3.2e-07,
      "loss": 8.126,
      "step": 10
    },
    {
      "epoch": 0.0010578512396694215,
      "grad_norm": 132.607666015625,
      "learning_rate": 1.12e-06,
      "loss": 8.0108,
      "step": 20
    },
    {
      "epoch": 0.0015867768595041322,
      "grad_norm": 117.4473876953125,
      "learning_rate": 1.92e-06,
      "loss": 7.8388,
      "step": 30
    },
    {
      "epoch": 0.002115702479338843,
      "grad_norm": 58.00923538208008,
      "learning_rate": 2.72e-06,
      "loss": 7.7671,
      "step": 40
    },
    {
      "epoch": 0.002644628099173554,
      "grad_norm": 62.31724166870117,
      "learning_rate": 3.52e-06,
      "loss": 7.821,
      "step": 50
    },
    {
      "epoch": 0.0031735537190082643,
      "grad_norm": 99.75863647460938,
      "learning_rate": 4.32e-06,
      "loss": 7.6772,
      "step": 60
    },
    {
      "epoch": 0.0037024793388429752,
      "grad_norm": 337.9526672363281,
      "learning_rate": 5.12e-06,
      "loss": 7.8172,
      "step": 70
    },
    {
      "epoch": 0.004231404958677686,
      "grad_norm": 95.75334167480469,
      "learning_rate": 5.920000000000001e-06,
      "loss": 7.6801,
      "step": 80
    },
    {
      "epoch": 0.004760330578512397,
      "grad_norm": 589.1984252929688,
      "learning_rate": 6.72e-06,
      "loss": 7.7462,
      "step": 90
    },
    {
      "epoch": 0.005289256198347108,
      "grad_norm": 115.37745666503906,
      "learning_rate": 7.520000000000001e-06,
      "loss": 7.5665,
      "step": 100
    },
    {
      "epoch": 0.005818181818181818,
      "grad_norm": 104.31098937988281,
      "learning_rate": 8.32e-06,
      "loss": 7.6031,
      "step": 110
    },
    {
      "epoch": 0.006347107438016529,
      "grad_norm": 357.35272216796875,
      "learning_rate": 9.12e-06,
      "loss": 7.6829,
      "step": 120
    },
    {
      "epoch": 0.00687603305785124,
      "grad_norm": 299.00555419921875,
      "learning_rate": 9.92e-06,
      "loss": 7.6717,
      "step": 130
    },
    {
      "epoch": 0.0074049586776859504,
      "grad_norm": 593.5489501953125,
      "learning_rate": 1.072e-05,
      "loss": 7.6622,
      "step": 140
    },
    {
      "epoch": 0.007933884297520661,
      "grad_norm": 174.9026336669922,
      "learning_rate": 1.152e-05,
      "loss": 7.595,
      "step": 150
    },
    {
      "epoch": 0.008462809917355372,
      "grad_norm": 199.49935913085938,
      "learning_rate": 1.232e-05,
      "loss": 7.5791,
      "step": 160
    },
    {
      "epoch": 0.008991735537190083,
      "grad_norm": 557.2059936523438,
      "learning_rate": 1.3120000000000001e-05,
      "loss": 7.7285,
      "step": 170
    },
    {
      "epoch": 0.009520661157024794,
      "grad_norm": 333.83441162109375,
      "learning_rate": 1.3919999999999999e-05,
      "loss": 7.6101,
      "step": 180
    },
    {
      "epoch": 0.010049586776859505,
      "grad_norm": 213.27163696289062,
      "learning_rate": 1.472e-05,
      "loss": 7.6139,
      "step": 190
    },
    {
      "epoch": 0.010578512396694216,
      "grad_norm": 192.46920776367188,
      "learning_rate": 1.552e-05,
      "loss": 7.4358,
      "step": 200
    },
    {
      "epoch": 0.011107438016528925,
      "grad_norm": 369.1148986816406,
      "learning_rate": 1.6320000000000003e-05,
      "loss": 7.4565,
      "step": 210
    },
    {
      "epoch": 0.011636363636363636,
      "grad_norm": 244.7185821533203,
      "learning_rate": 1.712e-05,
      "loss": 7.3962,
      "step": 220
    },
    {
      "epoch": 0.012165289256198347,
      "grad_norm": 308.51544189453125,
      "learning_rate": 1.792e-05,
      "loss": 7.4273,
      "step": 230
    },
    {
      "epoch": 0.012694214876033057,
      "grad_norm": 208.3214569091797,
      "learning_rate": 1.872e-05,
      "loss": 7.3567,
      "step": 240
    },
    {
      "epoch": 0.013223140495867768,
      "grad_norm": 121.53463745117188,
      "learning_rate": 1.9520000000000003e-05,
      "loss": 7.4131,
      "step": 250
    },
    {
      "epoch": 0.01375206611570248,
      "grad_norm": 124.09678649902344,
      "learning_rate": 2.032e-05,
      "loss": 7.426,
      "step": 260
    },
    {
      "epoch": 0.01428099173553719,
      "grad_norm": 237.53346252441406,
      "learning_rate": 2.112e-05,
      "loss": 7.377,
      "step": 270
    },
    {
      "epoch": 0.014809917355371901,
      "grad_norm": 174.61985778808594,
      "learning_rate": 2.192e-05,
      "loss": 7.3773,
      "step": 280
    },
    {
      "epoch": 0.015338842975206612,
      "grad_norm": 86.74190521240234,
      "learning_rate": 2.2720000000000003e-05,
      "loss": 7.3686,
      "step": 290
    },
    {
      "epoch": 0.015867768595041323,
      "grad_norm": 123.0051498413086,
      "learning_rate": 2.3520000000000002e-05,
      "loss": 7.363,
      "step": 300
    },
    {
      "epoch": 0.016396694214876033,
      "grad_norm": 149.46461486816406,
      "learning_rate": 2.432e-05,
      "loss": 7.3321,
      "step": 310
    },
    {
      "epoch": 0.016925619834710744,
      "grad_norm": 129.9262237548828,
      "learning_rate": 2.512e-05,
      "loss": 7.3589,
      "step": 320
    },
    {
      "epoch": 0.017454545454545455,
      "grad_norm": 287.2998962402344,
      "learning_rate": 2.592e-05,
      "loss": 7.3022,
      "step": 330
    },
    {
      "epoch": 0.017983471074380166,
      "grad_norm": 149.36317443847656,
      "learning_rate": 2.672e-05,
      "loss": 7.1559,
      "step": 340
    },
    {
      "epoch": 0.018512396694214877,
      "grad_norm": 133.55393981933594,
      "learning_rate": 2.752e-05,
      "loss": 7.2833,
      "step": 350
    },
    {
      "epoch": 0.019041322314049588,
      "grad_norm": 111.75740814208984,
      "learning_rate": 2.8320000000000003e-05,
      "loss": 7.0669,
      "step": 360
    },
    {
      "epoch": 0.0195702479338843,
      "grad_norm": 108.92760467529297,
      "learning_rate": 2.9120000000000002e-05,
      "loss": 7.2586,
      "step": 370
    },
    {
      "epoch": 0.02009917355371901,
      "grad_norm": 160.08486938476562,
      "learning_rate": 2.9920000000000005e-05,
      "loss": 7.2912,
      "step": 380
    },
    {
      "epoch": 0.02062809917355372,
      "grad_norm": 115.86800384521484,
      "learning_rate": 3.072e-05,
      "loss": 7.1553,
      "step": 390
    },
    {
      "epoch": 0.02115702479338843,
      "grad_norm": 131.96246337890625,
      "learning_rate": 3.1519999999999996e-05,
      "loss": 7.0865,
      "step": 400
    },
    {
      "epoch": 0.021685950413223142,
      "grad_norm": 175.23385620117188,
      "learning_rate": 3.232e-05,
      "loss": 7.1718,
      "step": 410
    },
    {
      "epoch": 0.02221487603305785,
      "grad_norm": 130.51516723632812,
      "learning_rate": 3.312e-05,
      "loss": 7.1449,
      "step": 420
    },
    {
      "epoch": 0.02274380165289256,
      "grad_norm": 142.1250762939453,
      "learning_rate": 3.392e-05,
      "loss": 7.0811,
      "step": 430
    },
    {
      "epoch": 0.02327272727272727,
      "grad_norm": 93.60326385498047,
      "learning_rate": 3.472e-05,
      "loss": 7.0511,
      "step": 440
    },
    {
      "epoch": 0.023801652892561982,
      "grad_norm": 85.3148193359375,
      "learning_rate": 3.5520000000000006e-05,
      "loss": 7.057,
      "step": 450
    },
    {
      "epoch": 0.024330578512396693,
      "grad_norm": 77.96083068847656,
      "learning_rate": 3.6320000000000005e-05,
      "loss": 7.0768,
      "step": 460
    },
    {
      "epoch": 0.024859504132231404,
      "grad_norm": 64.50347900390625,
      "learning_rate": 3.712e-05,
      "loss": 7.0468,
      "step": 470
    },
    {
      "epoch": 0.025388429752066115,
      "grad_norm": 89.8930892944336,
      "learning_rate": 3.792e-05,
      "loss": 6.9279,
      "step": 480
    },
    {
      "epoch": 0.025917355371900826,
      "grad_norm": 103.4708251953125,
      "learning_rate": 3.872e-05,
      "loss": 6.8665,
      "step": 490
    },
    {
      "epoch": 0.026446280991735537,
      "grad_norm": 96.82048034667969,
      "learning_rate": 3.952e-05,
      "loss": 6.9254,
      "step": 500
    },
    {
      "epoch": 0.026975206611570247,
      "grad_norm": 127.65508270263672,
      "learning_rate": 4.032e-05,
      "loss": 6.9533,
      "step": 510
    },
    {
      "epoch": 0.02750413223140496,
      "grad_norm": 123.8250503540039,
      "learning_rate": 4.1120000000000006e-05,
      "loss": 6.8762,
      "step": 520
    },
    {
      "epoch": 0.02803305785123967,
      "grad_norm": 80.71707153320312,
      "learning_rate": 4.1920000000000005e-05,
      "loss": 6.9264,
      "step": 530
    },
    {
      "epoch": 0.02856198347107438,
      "grad_norm": 76.69340515136719,
      "learning_rate": 4.2720000000000004e-05,
      "loss": 6.8932,
      "step": 540
    },
    {
      "epoch": 0.02909090909090909,
      "grad_norm": 64.87788391113281,
      "learning_rate": 4.352e-05,
      "loss": 6.8852,
      "step": 550
    },
    {
      "epoch": 0.029619834710743802,
      "grad_norm": 55.4420280456543,
      "learning_rate": 4.432e-05,
      "loss": 6.8624,
      "step": 560
    },
    {
      "epoch": 0.030148760330578513,
      "grad_norm": 83.48722076416016,
      "learning_rate": 4.512e-05,
      "loss": 6.791,
      "step": 570
    },
    {
      "epoch": 0.030677685950413223,
      "grad_norm": 67.83543395996094,
      "learning_rate": 4.592e-05,
      "loss": 6.78,
      "step": 580
    },
    {
      "epoch": 0.031206611570247934,
      "grad_norm": 75.6465072631836,
      "learning_rate": 4.672e-05,
      "loss": 6.7436,
      "step": 590
    },
    {
      "epoch": 0.031735537190082645,
      "grad_norm": 57.24126434326172,
      "learning_rate": 4.7520000000000006e-05,
      "loss": 6.6183,
      "step": 600
    },
    {
      "epoch": 0.032264462809917356,
      "grad_norm": 53.670318603515625,
      "learning_rate": 4.8320000000000005e-05,
      "loss": 6.7423,
      "step": 610
    },
    {
      "epoch": 0.03279338842975207,
      "grad_norm": 90.657958984375,
      "learning_rate": 4.9120000000000004e-05,
      "loss": 6.796,
      "step": 620
    },
    {
      "epoch": 0.03332231404958678,
      "grad_norm": 59.86640167236328,
      "learning_rate": 4.992e-05,
      "loss": 6.6875,
      "step": 630
    },
    {
      "epoch": 0.03385123966942149,
      "grad_norm": 82.00715637207031,
      "learning_rate": 5.072e-05,
      "loss": 6.8297,
      "step": 640
    },
    {
      "epoch": 0.0343801652892562,
      "grad_norm": 77.67565155029297,
      "learning_rate": 5.152e-05,
      "loss": 6.6996,
      "step": 650
    },
    {
      "epoch": 0.03490909090909091,
      "grad_norm": 76.80774688720703,
      "learning_rate": 5.232e-05,
      "loss": 6.6164,
      "step": 660
    },
    {
      "epoch": 0.03543801652892562,
      "grad_norm": 90.92999267578125,
      "learning_rate": 5.3120000000000006e-05,
      "loss": 6.6109,
      "step": 670
    },
    {
      "epoch": 0.03596694214876033,
      "grad_norm": 60.101036071777344,
      "learning_rate": 5.3920000000000006e-05,
      "loss": 6.6207,
      "step": 680
    },
    {
      "epoch": 0.03649586776859504,
      "grad_norm": 71.14286804199219,
      "learning_rate": 5.4720000000000005e-05,
      "loss": 6.6988,
      "step": 690
    },
    {
      "epoch": 0.037024793388429754,
      "grad_norm": 79.58287048339844,
      "learning_rate": 5.5520000000000004e-05,
      "loss": 6.6793,
      "step": 700
    },
    {
      "epoch": 0.037553719008264465,
      "grad_norm": 57.14976119995117,
      "learning_rate": 5.632e-05,
      "loss": 6.5679,
      "step": 710
    },
    {
      "epoch": 0.038082644628099176,
      "grad_norm": 48.05242919921875,
      "learning_rate": 5.712000000000001e-05,
      "loss": 6.6146,
      "step": 720
    },
    {
      "epoch": 0.03861157024793389,
      "grad_norm": 44.47470474243164,
      "learning_rate": 5.792000000000001e-05,
      "loss": 6.5374,
      "step": 730
    },
    {
      "epoch": 0.0391404958677686,
      "grad_norm": 51.66844177246094,
      "learning_rate": 5.872000000000001e-05,
      "loss": 6.4478,
      "step": 740
    },
    {
      "epoch": 0.03966942148760331,
      "grad_norm": 54.69235610961914,
      "learning_rate": 5.952e-05,
      "loss": 6.4556,
      "step": 750
    },
    {
      "epoch": 0.04019834710743802,
      "grad_norm": 62.92082214355469,
      "learning_rate": 6.032e-05,
      "loss": 6.494,
      "step": 760
    },
    {
      "epoch": 0.04072727272727273,
      "grad_norm": 59.18268585205078,
      "learning_rate": 6.112e-05,
      "loss": 6.4632,
      "step": 770
    },
    {
      "epoch": 0.04125619834710744,
      "grad_norm": 43.41447448730469,
      "learning_rate": 6.192e-05,
      "loss": 6.4568,
      "step": 780
    },
    {
      "epoch": 0.04178512396694215,
      "grad_norm": 68.496337890625,
      "learning_rate": 6.272e-05,
      "loss": 6.3378,
      "step": 790
    },
    {
      "epoch": 0.04231404958677686,
      "grad_norm": 55.83193588256836,
      "learning_rate": 6.352e-05,
      "loss": 6.5272,
      "step": 800
    },
    {
      "epoch": 0.042842975206611573,
      "grad_norm": 52.77011489868164,
      "learning_rate": 6.432000000000001e-05,
      "loss": 6.3882,
      "step": 810
    },
    {
      "epoch": 0.043371900826446284,
      "grad_norm": 47.83772659301758,
      "learning_rate": 6.512e-05,
      "loss": 6.3745,
      "step": 820
    },
    {
      "epoch": 0.04390082644628099,
      "grad_norm": 64.70166015625,
      "learning_rate": 6.592e-05,
      "loss": 6.3783,
      "step": 830
    },
    {
      "epoch": 0.0444297520661157,
      "grad_norm": 69.14620208740234,
      "learning_rate": 6.672e-05,
      "loss": 6.403,
      "step": 840
    },
    {
      "epoch": 0.04495867768595041,
      "grad_norm": 41.3566780090332,
      "learning_rate": 6.752e-05,
      "loss": 6.273,
      "step": 850
    },
    {
      "epoch": 0.04548760330578512,
      "grad_norm": 57.124813079833984,
      "learning_rate": 6.832000000000001e-05,
      "loss": 6.3434,
      "step": 860
    },
    {
      "epoch": 0.04601652892561983,
      "grad_norm": 47.598854064941406,
      "learning_rate": 6.912e-05,
      "loss": 6.2613,
      "step": 870
    },
    {
      "epoch": 0.04654545454545454,
      "grad_norm": 63.111759185791016,
      "learning_rate": 6.992000000000001e-05,
      "loss": 6.2488,
      "step": 880
    },
    {
      "epoch": 0.047074380165289254,
      "grad_norm": 53.83757781982422,
      "learning_rate": 7.072000000000001e-05,
      "loss": 6.1787,
      "step": 890
    },
    {
      "epoch": 0.047603305785123964,
      "grad_norm": 42.92972946166992,
      "learning_rate": 7.151999999999999e-05,
      "loss": 6.2455,
      "step": 900
    },
    {
      "epoch": 0.048132231404958675,
      "grad_norm": 40.897098541259766,
      "learning_rate": 7.232e-05,
      "loss": 6.1776,
      "step": 910
    },
    {
      "epoch": 0.048661157024793386,
      "grad_norm": 67.57796478271484,
      "learning_rate": 7.312e-05,
      "loss": 6.0933,
      "step": 920
    },
    {
      "epoch": 0.0491900826446281,
      "grad_norm": 54.34871292114258,
      "learning_rate": 7.392e-05,
      "loss": 6.1669,
      "step": 930
    },
    {
      "epoch": 0.04971900826446281,
      "grad_norm": 46.664188385009766,
      "learning_rate": 7.472e-05,
      "loss": 6.0994,
      "step": 940
    },
    {
      "epoch": 0.05024793388429752,
      "grad_norm": 40.62440490722656,
      "learning_rate": 7.552e-05,
      "loss": 6.1375,
      "step": 950
    },
    {
      "epoch": 0.05077685950413223,
      "grad_norm": 40.99917221069336,
      "learning_rate": 7.632e-05,
      "loss": 6.0468,
      "step": 960
    },
    {
      "epoch": 0.05130578512396694,
      "grad_norm": 41.27398681640625,
      "learning_rate": 7.712000000000001e-05,
      "loss": 6.0949,
      "step": 970
    },
    {
      "epoch": 0.05183471074380165,
      "grad_norm": 40.87042236328125,
      "learning_rate": 7.792e-05,
      "loss": 6.0498,
      "step": 980
    },
    {
      "epoch": 0.05236363636363636,
      "grad_norm": 41.66493606567383,
      "learning_rate": 7.872e-05,
      "loss": 6.0707,
      "step": 990
    },
    {
      "epoch": 0.05289256198347107,
      "grad_norm": 36.58250427246094,
      "learning_rate": 7.952000000000001e-05,
      "loss": 6.0559,
      "step": 1000
    },
    {
      "epoch": 0.053421487603305784,
      "grad_norm": 34.69593048095703,
      "learning_rate": 8.032e-05,
      "loss": 6.0294,
      "step": 1010
    },
    {
      "epoch": 0.053950413223140495,
      "grad_norm": 36.51956558227539,
      "learning_rate": 8.112000000000001e-05,
      "loss": 6.008,
      "step": 1020
    },
    {
      "epoch": 0.054479338842975206,
      "grad_norm": 38.489219665527344,
      "learning_rate": 8.192e-05,
      "loss": 5.9906,
      "step": 1030
    },
    {
      "epoch": 0.05500826446280992,
      "grad_norm": 35.57550048828125,
      "learning_rate": 8.272000000000001e-05,
      "loss": 5.9222,
      "step": 1040
    },
    {
      "epoch": 0.05553719008264463,
      "grad_norm": 36.05617904663086,
      "learning_rate": 8.352000000000001e-05,
      "loss": 6.0426,
      "step": 1050
    },
    {
      "epoch": 0.05606611570247934,
      "grad_norm": 31.7716121673584,
      "learning_rate": 8.431999999999999e-05,
      "loss": 5.9889,
      "step": 1060
    },
    {
      "epoch": 0.05659504132231405,
      "grad_norm": 34.74286651611328,
      "learning_rate": 8.512e-05,
      "loss": 5.8873,
      "step": 1070
    },
    {
      "epoch": 0.05712396694214876,
      "grad_norm": 45.21353530883789,
      "learning_rate": 8.592e-05,
      "loss": 5.9505,
      "step": 1080
    },
    {
      "epoch": 0.05765289256198347,
      "grad_norm": 30.405447006225586,
      "learning_rate": 8.672e-05,
      "loss": 5.8087,
      "step": 1090
    },
    {
      "epoch": 0.05818181818181818,
      "grad_norm": 30.943218231201172,
      "learning_rate": 8.752e-05,
      "loss": 5.7337,
      "step": 1100
    },
    {
      "epoch": 0.05871074380165289,
      "grad_norm": 32.396610260009766,
      "learning_rate": 8.832000000000001e-05,
      "loss": 5.7989,
      "step": 1110
    },
    {
      "epoch": 0.059239669421487604,
      "grad_norm": 31.198833465576172,
      "learning_rate": 8.912e-05,
      "loss": 5.8181,
      "step": 1120
    },
    {
      "epoch": 0.059768595041322314,
      "grad_norm": 40.59803009033203,
      "learning_rate": 8.992e-05,
      "loss": 5.8761,
      "step": 1130
    },
    {
      "epoch": 0.060297520661157025,
      "grad_norm": 43.126766204833984,
      "learning_rate": 9.072e-05,
      "loss": 5.8239,
      "step": 1140
    },
    {
      "epoch": 0.060826446280991736,
      "grad_norm": 39.69029998779297,
      "learning_rate": 9.152e-05,
      "loss": 5.7444,
      "step": 1150
    },
    {
      "epoch": 0.06135537190082645,
      "grad_norm": 28.941499710083008,
      "learning_rate": 9.232000000000001e-05,
      "loss": 5.8256,
      "step": 1160
    },
    {
      "epoch": 0.06188429752066116,
      "grad_norm": 46.216552734375,
      "learning_rate": 9.312e-05,
      "loss": 5.8361,
      "step": 1170
    },
    {
      "epoch": 0.06241322314049587,
      "grad_norm": 42.1989860534668,
      "learning_rate": 9.392000000000001e-05,
      "loss": 5.7034,
      "step": 1180
    },
    {
      "epoch": 0.06294214876033058,
      "grad_norm": 36.610836029052734,
      "learning_rate": 9.472000000000001e-05,
      "loss": 5.7089,
      "step": 1190
    },
    {
      "epoch": 0.06347107438016529,
      "grad_norm": 38.280452728271484,
      "learning_rate": 9.552000000000001e-05,
      "loss": 5.8296,
      "step": 1200
    }
  ],
  "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": 2.09401883541504e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}