{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7039764359351989,
  "eval_steps": 500,
  "global_step": 239,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0029455081001472753,
      "grad_norm": 148176371712.0,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 3.5829,
      "step": 1
    },
    {
      "epoch": 0.005891016200294551,
      "grad_norm": 521838526464.0,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 3.7866,
      "step": 2
    },
    {
      "epoch": 0.008836524300441826,
      "grad_norm": 29312.015625,
      "learning_rate": 3e-06,
      "loss": 5.4788,
      "step": 3
    },
    {
      "epoch": 0.011782032400589101,
      "grad_norm": 4224.009765625,
      "learning_rate": 4.000000000000001e-06,
      "loss": 4.9963,
      "step": 4
    },
    {
      "epoch": 0.014727540500736377,
      "grad_norm": 6816.009765625,
      "learning_rate": 5e-06,
      "loss": 6.1696,
      "step": 5
    },
    {
      "epoch": 0.017673048600883652,
      "grad_norm": 37120.00390625,
      "learning_rate": 6e-06,
      "loss": 6.0103,
      "step": 6
    },
    {
      "epoch": 0.020618556701030927,
      "grad_norm": 16512.0078125,
      "learning_rate": 7.000000000000001e-06,
      "loss": 5.2747,
      "step": 7
    },
    {
      "epoch": 0.023564064801178203,
      "grad_norm": 4544.0126953125,
      "learning_rate": 8.000000000000001e-06,
      "loss": 5.0828,
      "step": 8
    },
    {
      "epoch": 0.026509572901325478,
      "grad_norm": 1360.0126953125,
      "learning_rate": 9e-06,
      "loss": 4.4745,
      "step": 9
    },
    {
      "epoch": 0.029455081001472753,
      "grad_norm": 2528.019287109375,
      "learning_rate": 1e-05,
      "loss": 6.0115,
      "step": 10
    },
    {
      "epoch": 0.03240058910162003,
      "grad_norm": 608.0706787109375,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 5.1475,
      "step": 11
    },
    {
      "epoch": 0.035346097201767304,
      "grad_norm": 1560.0152587890625,
      "learning_rate": 1.2e-05,
      "loss": 5.2077,
      "step": 12
    },
    {
      "epoch": 0.03829160530191458,
      "grad_norm": 1152.024169921875,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 4.9248,
      "step": 13
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 1096.0169677734375,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 4.3356,
      "step": 14
    },
    {
      "epoch": 0.044182621502209134,
      "grad_norm": 2560.037841796875,
      "learning_rate": 1.5e-05,
      "loss": 5.9271,
      "step": 15
    },
    {
      "epoch": 0.047128129602356406,
      "grad_norm": 1312.0172119140625,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 4.9467,
      "step": 16
    },
    {
      "epoch": 0.050073637702503684,
      "grad_norm": 748.0582275390625,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 5.5781,
      "step": 17
    },
    {
      "epoch": 0.053019145802650956,
      "grad_norm": 608.0347290039062,
      "learning_rate": 1.8e-05,
      "loss": 4.9313,
      "step": 18
    },
    {
      "epoch": 0.055964653902798235,
      "grad_norm": 444.0478820800781,
      "learning_rate": 1.9e-05,
      "loss": 4.7802,
      "step": 19
    },
    {
      "epoch": 0.05891016200294551,
      "grad_norm": 400.05474853515625,
      "learning_rate": 2e-05,
      "loss": 4.9916,
      "step": 20
    },
    {
      "epoch": 0.061855670103092786,
      "grad_norm": 324.0529479980469,
      "learning_rate": 2.1e-05,
      "loss": 4.5852,
      "step": 21
    },
    {
      "epoch": 0.06480117820324006,
      "grad_norm": 552.0383911132812,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 4.5658,
      "step": 22
    },
    {
      "epoch": 0.06774668630338733,
      "grad_norm": 780.0543823242188,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 4.9509,
      "step": 23
    },
    {
      "epoch": 0.07069219440353461,
      "grad_norm": 1352.05712890625,
      "learning_rate": 2.4e-05,
      "loss": 4.9526,
      "step": 24
    },
    {
      "epoch": 0.07363770250368189,
      "grad_norm": 692.063720703125,
      "learning_rate": 2.5e-05,
      "loss": 5.1079,
      "step": 25
    },
    {
      "epoch": 0.07658321060382917,
      "grad_norm": 940.0375366210938,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 4.3864,
      "step": 26
    },
    {
      "epoch": 0.07952871870397643,
      "grad_norm": 406.0652770996094,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 4.7486,
      "step": 27
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 736.0764770507812,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 5.4081,
      "step": 28
    },
    {
      "epoch": 0.08541973490427099,
      "grad_norm": 1240.040283203125,
      "learning_rate": 2.9e-05,
      "loss": 4.6019,
      "step": 29
    },
    {
      "epoch": 0.08836524300441827,
      "grad_norm": 1312.10302734375,
      "learning_rate": 3e-05,
      "loss": 5.481,
      "step": 30
    },
    {
      "epoch": 0.09131075110456553,
      "grad_norm": 466.0743103027344,
      "learning_rate": 3.1e-05,
      "loss": 4.4326,
      "step": 31
    },
    {
      "epoch": 0.09425625920471281,
      "grad_norm": 828.0822143554688,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 5.0284,
      "step": 32
    },
    {
      "epoch": 0.09720176730486009,
      "grad_norm": 764.077880859375,
      "learning_rate": 3.3e-05,
      "loss": 4.9104,
      "step": 33
    },
    {
      "epoch": 0.10014727540500737,
      "grad_norm": 231.1255340576172,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 3.9872,
      "step": 34
    },
    {
      "epoch": 0.10309278350515463,
      "grad_norm": 434.1127624511719,
      "learning_rate": 3.5e-05,
      "loss": 5.2373,
      "step": 35
    },
    {
      "epoch": 0.10603829160530191,
      "grad_norm": 253.16815185546875,
      "learning_rate": 3.6e-05,
      "loss": 4.8148,
      "step": 36
    },
    {
      "epoch": 0.10898379970544919,
      "grad_norm": 290.1834716796875,
      "learning_rate": 3.7e-05,
      "loss": 3.6852,
      "step": 37
    },
    {
      "epoch": 0.11192930780559647,
      "grad_norm": 584.0982666015625,
      "learning_rate": 3.8e-05,
      "loss": 3.8818,
      "step": 38
    },
    {
      "epoch": 0.11487481590574374,
      "grad_norm": 904.0762329101562,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 4.2878,
      "step": 39
    },
    {
      "epoch": 0.11782032400589101,
      "grad_norm": 336.28033447265625,
      "learning_rate": 4e-05,
      "loss": 4.2046,
      "step": 40
    },
    {
      "epoch": 0.12076583210603829,
      "grad_norm": 704.1439208984375,
      "learning_rate": 4.1e-05,
      "loss": 4.4065,
      "step": 41
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 804.0842895507812,
      "learning_rate": 4.2e-05,
      "loss": 3.9044,
      "step": 42
    },
    {
      "epoch": 0.12665684830633284,
      "grad_norm": 752.0977172851562,
      "learning_rate": 4.3e-05,
      "loss": 3.5964,
      "step": 43
    },
    {
      "epoch": 0.12960235640648013,
      "grad_norm": 752.181884765625,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 4.3488,
      "step": 44
    },
    {
      "epoch": 0.1325478645066274,
      "grad_norm": 664.2083129882812,
      "learning_rate": 4.5e-05,
      "loss": 4.6978,
      "step": 45
    },
    {
      "epoch": 0.13549337260677466,
      "grad_norm": 1984.197998046875,
      "learning_rate": 4.600000000000001e-05,
      "loss": 3.8173,
      "step": 46
    },
    {
      "epoch": 0.13843888070692195,
      "grad_norm": 1536.0904541015625,
      "learning_rate": 4.7e-05,
      "loss": 3.3992,
      "step": 47
    },
    {
      "epoch": 0.14138438880706922,
      "grad_norm": 616.1571044921875,
      "learning_rate": 4.8e-05,
      "loss": 3.5619,
      "step": 48
    },
    {
      "epoch": 0.14432989690721648,
      "grad_norm": 5408.072265625,
      "learning_rate": 4.9e-05,
      "loss": 4.3322,
      "step": 49
    },
    {
      "epoch": 0.14727540500736377,
      "grad_norm": 3408.068603515625,
      "learning_rate": 5e-05,
      "loss": 4.0344,
      "step": 50
    },
    {
      "epoch": 0.15022091310751104,
      "grad_norm": 724.0775146484375,
      "learning_rate": 5.1000000000000006e-05,
      "loss": 3.8171,
      "step": 51
    },
    {
      "epoch": 0.15316642120765833,
      "grad_norm": 1448.1661376953125,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 2.6826,
      "step": 52
    },
    {
      "epoch": 0.1561119293078056,
      "grad_norm": 304.0506591796875,
      "learning_rate": 5.300000000000001e-05,
      "loss": 2.4422,
      "step": 53
    },
    {
      "epoch": 0.15905743740795286,
      "grad_norm": 396.0224914550781,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 2.4475,
      "step": 54
    },
    {
      "epoch": 0.16200294550810015,
      "grad_norm": 684.0194702148438,
      "learning_rate": 5.500000000000001e-05,
      "loss": 2.2932,
      "step": 55
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 231.03273010253906,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 2.5193,
      "step": 56
    },
    {
      "epoch": 0.16789396170839468,
      "grad_norm": 164.0357208251953,
      "learning_rate": 5.6999999999999996e-05,
      "loss": 1.9575,
      "step": 57
    },
    {
      "epoch": 0.17083946980854198,
      "grad_norm": 1600.0091552734375,
      "learning_rate": 5.8e-05,
      "loss": 2.5806,
      "step": 58
    },
    {
      "epoch": 0.17378497790868924,
      "grad_norm": 50.36320114135742,
      "learning_rate": 5.9e-05,
      "loss": 3.651,
      "step": 59
    },
    {
      "epoch": 0.17673048600883653,
      "grad_norm": 66.08223724365234,
      "learning_rate": 6e-05,
      "loss": 3.5998,
      "step": 60
    },
    {
      "epoch": 0.1796759941089838,
      "grad_norm": 20.88555335998535,
      "learning_rate": 6.1e-05,
      "loss": 3.2898,
      "step": 61
    },
    {
      "epoch": 0.18262150220913106,
      "grad_norm": 33.95121765136719,
      "learning_rate": 6.2e-05,
      "loss": 3.5322,
      "step": 62
    },
    {
      "epoch": 0.18556701030927836,
      "grad_norm": 18.569725036621094,
      "learning_rate": 6.3e-05,
      "loss": 2.7009,
      "step": 63
    },
    {
      "epoch": 0.18851251840942562,
      "grad_norm": 11.800430297851562,
      "learning_rate": 6.400000000000001e-05,
      "loss": 3.0148,
      "step": 64
    },
    {
      "epoch": 0.19145802650957292,
      "grad_norm": 11.598824501037598,
      "learning_rate": 6.500000000000001e-05,
      "loss": 2.5356,
      "step": 65
    },
    {
      "epoch": 0.19440353460972018,
      "grad_norm": 29.798603057861328,
      "learning_rate": 6.6e-05,
      "loss": 3.419,
      "step": 66
    },
    {
      "epoch": 0.19734904270986744,
      "grad_norm": 23.390228271484375,
      "learning_rate": 6.7e-05,
      "loss": 3.0823,
      "step": 67
    },
    {
      "epoch": 0.20029455081001474,
      "grad_norm": 30.04606056213379,
      "learning_rate": 6.800000000000001e-05,
      "loss": 2.6675,
      "step": 68
    },
    {
      "epoch": 0.203240058910162,
      "grad_norm": 59.424739837646484,
      "learning_rate": 6.9e-05,
      "loss": 2.6406,
      "step": 69
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 18.69099235534668,
      "learning_rate": 7e-05,
      "loss": 2.8912,
      "step": 70
    },
    {
      "epoch": 0.20913107511045656,
      "grad_norm": 11.040902137756348,
      "learning_rate": 7.1e-05,
      "loss": 2.2423,
      "step": 71
    },
    {
      "epoch": 0.21207658321060383,
      "grad_norm": 15.589529991149902,
      "learning_rate": 7.2e-05,
      "loss": 2.6387,
      "step": 72
    },
    {
      "epoch": 0.21502209131075112,
      "grad_norm": 8.346650123596191,
      "learning_rate": 7.3e-05,
      "loss": 2.7416,
      "step": 73
    },
    {
      "epoch": 0.21796759941089838,
      "grad_norm": 16.002195358276367,
      "learning_rate": 7.4e-05,
      "loss": 2.5981,
      "step": 74
    },
    {
      "epoch": 0.22091310751104565,
      "grad_norm": 12.781440734863281,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.8455,
      "step": 75
    },
    {
      "epoch": 0.22385861561119294,
      "grad_norm": 14.14976978302002,
      "learning_rate": 7.6e-05,
      "loss": 2.3376,
      "step": 76
    },
    {
      "epoch": 0.2268041237113402,
      "grad_norm": 14.174376487731934,
      "learning_rate": 7.7e-05,
      "loss": 2.2975,
      "step": 77
    },
    {
      "epoch": 0.22974963181148747,
      "grad_norm": 12.794411659240723,
      "learning_rate": 7.800000000000001e-05,
      "loss": 2.2424,
      "step": 78
    },
    {
      "epoch": 0.23269513991163476,
      "grad_norm": 8.186522483825684,
      "learning_rate": 7.900000000000001e-05,
      "loss": 1.9646,
      "step": 79
    },
    {
      "epoch": 0.23564064801178203,
      "grad_norm": 7.599482536315918,
      "learning_rate": 8e-05,
      "loss": 2.2699,
      "step": 80
    },
    {
      "epoch": 0.23858615611192932,
      "grad_norm": 13.385209083557129,
      "learning_rate": 8.1e-05,
      "loss": 2.9279,
      "step": 81
    },
    {
      "epoch": 0.24153166421207659,
      "grad_norm": 10.520708084106445,
      "learning_rate": 8.2e-05,
      "loss": 2.6627,
      "step": 82
    },
    {
      "epoch": 0.24447717231222385,
      "grad_norm": 10.881275177001953,
      "learning_rate": 8.3e-05,
      "loss": 2.6776,
      "step": 83
    },
    {
      "epoch": 0.24742268041237114,
      "grad_norm": 11.189691543579102,
      "learning_rate": 8.4e-05,
      "loss": 2.5101,
      "step": 84
    },
    {
      "epoch": 0.2503681885125184,
      "grad_norm": 14.185538291931152,
      "learning_rate": 8.5e-05,
      "loss": 2.4517,
      "step": 85
    },
    {
      "epoch": 0.2533136966126657,
      "grad_norm": 11.319371223449707,
      "learning_rate": 8.6e-05,
      "loss": 2.3935,
      "step": 86
    },
    {
      "epoch": 0.25625920471281294,
      "grad_norm": 11.8043212890625,
      "learning_rate": 8.7e-05,
      "loss": 2.3776,
      "step": 87
    },
    {
      "epoch": 0.25920471281296026,
      "grad_norm": 17.876741409301758,
      "learning_rate": 8.800000000000001e-05,
      "loss": 2.1173,
      "step": 88
    },
    {
      "epoch": 0.2621502209131075,
      "grad_norm": 9.818507194519043,
      "learning_rate": 8.900000000000001e-05,
      "loss": 2.4566,
      "step": 89
    },
    {
      "epoch": 0.2650957290132548,
      "grad_norm": 17.97085189819336,
      "learning_rate": 9e-05,
      "loss": 2.4889,
      "step": 90
    },
    {
      "epoch": 0.26804123711340205,
      "grad_norm": 13.525333404541016,
      "learning_rate": 9.1e-05,
      "loss": 2.6413,
      "step": 91
    },
    {
      "epoch": 0.2709867452135493,
      "grad_norm": 11.17566204071045,
      "learning_rate": 9.200000000000001e-05,
      "loss": 2.5934,
      "step": 92
    },
    {
      "epoch": 0.27393225331369664,
      "grad_norm": 10.861861228942871,
      "learning_rate": 9.300000000000001e-05,
      "loss": 2.0431,
      "step": 93
    },
    {
      "epoch": 0.2768777614138439,
      "grad_norm": 10.782200813293457,
      "learning_rate": 9.4e-05,
      "loss": 2.2952,
      "step": 94
    },
    {
      "epoch": 0.27982326951399117,
      "grad_norm": 10.202653884887695,
      "learning_rate": 9.5e-05,
      "loss": 1.9,
      "step": 95
    },
    {
      "epoch": 0.28276877761413843,
      "grad_norm": 11.118406295776367,
      "learning_rate": 9.6e-05,
      "loss": 1.8267,
      "step": 96
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 11.998210906982422,
      "learning_rate": 9.7e-05,
      "loss": 2.7094,
      "step": 97
    },
    {
      "epoch": 0.28865979381443296,
      "grad_norm": 11.203243255615234,
      "learning_rate": 9.8e-05,
      "loss": 2.6765,
      "step": 98
    },
    {
      "epoch": 0.2916053019145803,
      "grad_norm": 11.754383087158203,
      "learning_rate": 9.900000000000001e-05,
      "loss": 2.323,
      "step": 99
    },
    {
      "epoch": 0.29455081001472755,
      "grad_norm": 20.766103744506836,
      "learning_rate": 0.0001,
      "loss": 3.2395,
      "step": 100
    },
    {
      "epoch": 0.2974963181148748,
      "grad_norm": 19.38508415222168,
      "learning_rate": 9.999568045802217e-05,
      "loss": 3.1611,
      "step": 101
    },
    {
      "epoch": 0.3004418262150221,
      "grad_norm": 12.322184562683105,
      "learning_rate": 9.998272257842641e-05,
      "loss": 1.8749,
      "step": 102
    },
    {
      "epoch": 0.30338733431516934,
      "grad_norm": 8.819778442382812,
      "learning_rate": 9.996112860009688e-05,
      "loss": 2.1352,
      "step": 103
    },
    {
      "epoch": 0.30633284241531666,
      "grad_norm": 4.589802265167236,
      "learning_rate": 9.993090225407743e-05,
      "loss": 1.9195,
      "step": 104
    },
    {
      "epoch": 0.30927835051546393,
      "grad_norm": 3.1305477619171143,
      "learning_rate": 9.989204876292688e-05,
      "loss": 1.6522,
      "step": 105
    },
    {
      "epoch": 0.3122238586156112,
      "grad_norm": 2.7143571376800537,
      "learning_rate": 9.984457483981669e-05,
      "loss": 1.1763,
      "step": 106
    },
    {
      "epoch": 0.31516936671575846,
      "grad_norm": 2.8804931640625,
      "learning_rate": 9.978848868737098e-05,
      "loss": 1.7974,
      "step": 107
    },
    {
      "epoch": 0.3181148748159057,
      "grad_norm": 3.790278673171997,
      "learning_rate": 9.972379999624936e-05,
      "loss": 2.1482,
      "step": 108
    },
    {
      "epoch": 0.32106038291605304,
      "grad_norm": 4.674582004547119,
      "learning_rate": 9.96505199434725e-05,
      "loss": 2.5313,
      "step": 109
    },
    {
      "epoch": 0.3240058910162003,
      "grad_norm": 3.20375657081604,
      "learning_rate": 9.956866119049095e-05,
      "loss": 2.2333,
      "step": 110
    },
    {
      "epoch": 0.3269513991163476,
      "grad_norm": 3.65432071685791,
      "learning_rate": 9.947823788099753e-05,
      "loss": 2.3037,
      "step": 111
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": 4.25070858001709,
      "learning_rate": 9.937926563848346e-05,
      "loss": 2.1421,
      "step": 112
    },
    {
      "epoch": 0.3328424153166421,
      "grad_norm": 3.4754691123962402,
      "learning_rate": 9.927176156353899e-05,
      "loss": 1.6731,
      "step": 113
    },
    {
      "epoch": 0.33578792341678937,
      "grad_norm": 4.312386989593506,
      "learning_rate": 9.91557442308987e-05,
      "loss": 2.2766,
      "step": 114
    },
    {
      "epoch": 0.3387334315169367,
      "grad_norm": 8.520076751708984,
      "learning_rate": 9.903123368623216e-05,
      "loss": 2.3844,
      "step": 115
    },
    {
      "epoch": 0.34167893961708395,
      "grad_norm": 9.280426979064941,
      "learning_rate": 9.889825144268029e-05,
      "loss": 2.5895,
      "step": 116
    },
    {
      "epoch": 0.3446244477172312,
      "grad_norm": 5.867470741271973,
      "learning_rate": 9.875682047713846e-05,
      "loss": 2.1818,
      "step": 117
    },
    {
      "epoch": 0.3475699558173785,
      "grad_norm": 4.29853630065918,
      "learning_rate": 9.860696522628639e-05,
      "loss": 2.1243,
      "step": 118
    },
    {
      "epoch": 0.35051546391752575,
      "grad_norm": 4.369655132293701,
      "learning_rate": 9.844871158236591e-05,
      "loss": 1.9835,
      "step": 119
    },
    {
      "epoch": 0.35346097201767307,
      "grad_norm": 15.677599906921387,
      "learning_rate": 9.828208688870735e-05,
      "loss": 2.3591,
      "step": 120
    },
    {
      "epoch": 0.35640648011782033,
      "grad_norm": 7.070474624633789,
      "learning_rate": 9.810711993500507e-05,
      "loss": 2.1378,
      "step": 121
    },
    {
      "epoch": 0.3593519882179676,
      "grad_norm": 4.5425004959106445,
      "learning_rate": 9.792384095234313e-05,
      "loss": 1.838,
      "step": 122
    },
    {
      "epoch": 0.36229749631811486,
      "grad_norm": 5.75803804397583,
      "learning_rate": 9.773228160797188e-05,
      "loss": 2.045,
      "step": 123
    },
    {
      "epoch": 0.36524300441826213,
      "grad_norm": 4.905186653137207,
      "learning_rate": 9.753247499983649e-05,
      "loss": 2.263,
      "step": 124
    },
    {
      "epoch": 0.36818851251840945,
      "grad_norm": 5.079438209533691,
      "learning_rate": 9.732445565085824e-05,
      "loss": 1.9375,
      "step": 125
    },
    {
      "epoch": 0.3711340206185567,
      "grad_norm": 5.083024978637695,
      "learning_rate": 9.71082595029695e-05,
      "loss": 1.9512,
      "step": 126
    },
    {
      "epoch": 0.374079528718704,
      "grad_norm": 5.701948642730713,
      "learning_rate": 9.688392391090373e-05,
      "loss": 2.0932,
      "step": 127
    },
    {
      "epoch": 0.37702503681885124,
      "grad_norm": 5.612240314483643,
      "learning_rate": 9.665148763574123e-05,
      "loss": 2.1218,
      "step": 128
    },
    {
      "epoch": 0.3799705449189985,
      "grad_norm": 5.693153381347656,
      "learning_rate": 9.64109908382119e-05,
      "loss": 2.4763,
      "step": 129
    },
    {
      "epoch": 0.38291605301914583,
      "grad_norm": 5.299254417419434,
      "learning_rate": 9.616247507175623e-05,
      "loss": 2.3062,
      "step": 130
    },
    {
      "epoch": 0.3858615611192931,
      "grad_norm": 5.711902618408203,
      "learning_rate": 9.590598327534564e-05,
      "loss": 2.4087,
      "step": 131
    },
    {
      "epoch": 0.38880706921944036,
      "grad_norm": 4.181498050689697,
      "learning_rate": 9.564155976606339e-05,
      "loss": 1.7175,
      "step": 132
    },
    {
      "epoch": 0.3917525773195876,
      "grad_norm": 5.31155252456665,
      "learning_rate": 9.536925023144742e-05,
      "loss": 1.6347,
      "step": 133
    },
    {
      "epoch": 0.3946980854197349,
      "grad_norm": 6.574872970581055,
      "learning_rate": 9.508910172159635e-05,
      "loss": 1.8686,
      "step": 134
    },
    {
      "epoch": 0.39764359351988215,
      "grad_norm": 6.77908992767334,
      "learning_rate": 9.480116264104011e-05,
      "loss": 2.1223,
      "step": 135
    },
    {
      "epoch": 0.4005891016200295,
      "grad_norm": 7.450313091278076,
      "learning_rate": 9.450548274037653e-05,
      "loss": 2.3148,
      "step": 136
    },
    {
      "epoch": 0.40353460972017674,
      "grad_norm": 5.135898113250732,
      "learning_rate": 9.420211310767533e-05,
      "loss": 1.386,
      "step": 137
    },
    {
      "epoch": 0.406480117820324,
      "grad_norm": 8.198874473571777,
      "learning_rate": 9.389110615965102e-05,
      "loss": 1.9208,
      "step": 138
    },
    {
      "epoch": 0.40942562592047127,
      "grad_norm": 10.153027534484863,
      "learning_rate": 9.35725156326063e-05,
      "loss": 2.2577,
      "step": 139
    },
    {
      "epoch": 0.41237113402061853,
      "grad_norm": 8.334872245788574,
      "learning_rate": 9.324639657314742e-05,
      "loss": 2.0401,
      "step": 140
    },
    {
      "epoch": 0.41531664212076586,
      "grad_norm": 6.7754950523376465,
      "learning_rate": 9.291280532867302e-05,
      "loss": 1.5202,
      "step": 141
    },
    {
      "epoch": 0.4182621502209131,
      "grad_norm": 9.433147430419922,
      "learning_rate": 9.257179953763845e-05,
      "loss": 2.1687,
      "step": 142
    },
    {
      "epoch": 0.4212076583210604,
      "grad_norm": 7.446643352508545,
      "learning_rate": 9.222343811959693e-05,
      "loss": 1.6996,
      "step": 143
    },
    {
      "epoch": 0.42415316642120765,
      "grad_norm": 7.048992156982422,
      "learning_rate": 9.186778126501916e-05,
      "loss": 1.5279,
      "step": 144
    },
    {
      "epoch": 0.4270986745213549,
      "grad_norm": 7.340887069702148,
      "learning_rate": 9.150489042489367e-05,
      "loss": 1.4406,
      "step": 145
    },
    {
      "epoch": 0.43004418262150224,
      "grad_norm": 11.633044242858887,
      "learning_rate": 9.113482830010918e-05,
      "loss": 1.5187,
      "step": 146
    },
    {
      "epoch": 0.4329896907216495,
      "grad_norm": 9.241588592529297,
      "learning_rate": 9.075765883062093e-05,
      "loss": 1.8564,
      "step": 147
    },
    {
      "epoch": 0.43593519882179677,
      "grad_norm": 8.745128631591797,
      "learning_rate": 9.037344718440322e-05,
      "loss": 1.5419,
      "step": 148
    },
    {
      "epoch": 0.43888070692194403,
      "grad_norm": 16.220924377441406,
      "learning_rate": 8.99822597461894e-05,
      "loss": 2.5006,
      "step": 149
    },
    {
      "epoch": 0.4418262150220913,
      "grad_norm": 15.44288444519043,
      "learning_rate": 8.958416410600187e-05,
      "loss": 2.0001,
      "step": 150
    },
    {
      "epoch": 0.44477172312223856,
      "grad_norm": 10.727198600769043,
      "learning_rate": 8.917922904747384e-05,
      "loss": 2.8376,
      "step": 151
    },
    {
      "epoch": 0.4477172312223859,
      "grad_norm": 5.658038139343262,
      "learning_rate": 8.876752453596462e-05,
      "loss": 1.7435,
      "step": 152
    },
    {
      "epoch": 0.45066273932253315,
      "grad_norm": 4.7606892585754395,
      "learning_rate": 8.834912170647101e-05,
      "loss": 1.3439,
      "step": 153
    },
    {
      "epoch": 0.4536082474226804,
      "grad_norm": 4.7208757400512695,
      "learning_rate": 8.792409285133642e-05,
      "loss": 1.8022,
      "step": 154
    },
    {
      "epoch": 0.4565537555228277,
      "grad_norm": 3.1722121238708496,
      "learning_rate": 8.749251140776016e-05,
      "loss": 0.7509,
      "step": 155
    },
    {
      "epoch": 0.45949926362297494,
      "grad_norm": 2.528482675552368,
      "learning_rate": 8.705445194510868e-05,
      "loss": 1.6068,
      "step": 156
    },
    {
      "epoch": 0.46244477172312226,
      "grad_norm": 2.8189425468444824,
      "learning_rate": 8.66099901520315e-05,
      "loss": 0.4364,
      "step": 157
    },
    {
      "epoch": 0.4653902798232695,
      "grad_norm": 2.734297752380371,
      "learning_rate": 8.615920282338355e-05,
      "loss": 1.6278,
      "step": 158
    },
    {
      "epoch": 0.4683357879234168,
      "grad_norm": 2.981930732727051,
      "learning_rate": 8.570216784695637e-05,
      "loss": 1.9541,
      "step": 159
    },
    {
      "epoch": 0.47128129602356406,
      "grad_norm": 3.195127248764038,
      "learning_rate": 8.52389641900206e-05,
      "loss": 2.0949,
      "step": 160
    },
    {
      "epoch": 0.4742268041237113,
      "grad_norm": 3.8657867908477783,
      "learning_rate": 8.476967188568188e-05,
      "loss": 1.8021,
      "step": 161
    },
    {
      "epoch": 0.47717231222385864,
      "grad_norm": 3.0095670223236084,
      "learning_rate": 8.429437201905254e-05,
      "loss": 1.8119,
      "step": 162
    },
    {
      "epoch": 0.4801178203240059,
      "grad_norm": 3.025339365005493,
      "learning_rate": 8.381314671324159e-05,
      "loss": 1.8117,
      "step": 163
    },
    {
      "epoch": 0.48306332842415317,
      "grad_norm": 4.113118648529053,
      "learning_rate": 8.332607911516545e-05,
      "loss": 1.7912,
      "step": 164
    },
    {
      "epoch": 0.48600883652430044,
      "grad_norm": 3.183894395828247,
      "learning_rate": 8.283325338118153e-05,
      "loss": 1.7364,
      "step": 165
    },
    {
      "epoch": 0.4889543446244477,
      "grad_norm": 5.081910610198975,
      "learning_rate": 8.233475466254765e-05,
      "loss": 2.0706,
      "step": 166
    },
    {
      "epoch": 0.49189985272459497,
      "grad_norm": 4.033633708953857,
      "learning_rate": 8.183066909070947e-05,
      "loss": 2.0481,
      "step": 167
    },
    {
      "epoch": 0.4948453608247423,
      "grad_norm": 4.505871772766113,
      "learning_rate": 8.132108376241849e-05,
      "loss": 2.044,
      "step": 168
    },
    {
      "epoch": 0.49779086892488955,
      "grad_norm": 6.440969944000244,
      "learning_rate": 8.08060867246834e-05,
      "loss": 2.209,
      "step": 169
    },
    {
      "epoch": 0.5007363770250368,
      "grad_norm": 6.235000133514404,
      "learning_rate": 8.028576695955711e-05,
      "loss": 2.0359,
      "step": 170
    },
    {
      "epoch": 0.5036818851251841,
      "grad_norm": 4.07951021194458,
      "learning_rate": 7.97602143687623e-05,
      "loss": 1.6721,
      "step": 171
    },
    {
      "epoch": 0.5066273932253313,
      "grad_norm": 4.1656413078308105,
      "learning_rate": 7.922951975815811e-05,
      "loss": 1.7503,
      "step": 172
    },
    {
      "epoch": 0.5095729013254786,
      "grad_norm": 3.7077293395996094,
      "learning_rate": 7.869377482205042e-05,
      "loss": 1.6881,
      "step": 173
    },
    {
      "epoch": 0.5125184094256259,
      "grad_norm": 4.08639669418335,
      "learning_rate": 7.815307212734888e-05,
      "loss": 1.4451,
      "step": 174
    },
    {
      "epoch": 0.5154639175257731,
      "grad_norm": 4.255699157714844,
      "learning_rate": 7.760750509757298e-05,
      "loss": 1.7914,
      "step": 175
    },
    {
      "epoch": 0.5184094256259205,
      "grad_norm": 4.119191646575928,
      "learning_rate": 7.705716799671019e-05,
      "loss": 1.8201,
      "step": 176
    },
    {
      "epoch": 0.5213549337260678,
      "grad_norm": 4.7409467697143555,
      "learning_rate": 7.650215591292888e-05,
      "loss": 1.8449,
      "step": 177
    },
    {
      "epoch": 0.524300441826215,
      "grad_norm": 5.348622798919678,
      "learning_rate": 7.594256474214882e-05,
      "loss": 1.6767,
      "step": 178
    },
    {
      "epoch": 0.5272459499263623,
      "grad_norm": 4.13510799407959,
      "learning_rate": 7.537849117147212e-05,
      "loss": 1.2513,
      "step": 179
    },
    {
      "epoch": 0.5301914580265096,
      "grad_norm": 4.210190296173096,
      "learning_rate": 7.481003266247744e-05,
      "loss": 1.5867,
      "step": 180
    },
    {
      "epoch": 0.5331369661266568,
      "grad_norm": 5.271762371063232,
      "learning_rate": 7.423728743438048e-05,
      "loss": 2.1488,
      "step": 181
    },
    {
      "epoch": 0.5360824742268041,
      "grad_norm": 5.800075054168701,
      "learning_rate": 7.366035444706347e-05,
      "loss": 1.8385,
      "step": 182
    },
    {
      "epoch": 0.5390279823269514,
      "grad_norm": 6.030768871307373,
      "learning_rate": 7.307933338397667e-05,
      "loss": 1.6634,
      "step": 183
    },
    {
      "epoch": 0.5419734904270986,
      "grad_norm": 5.144318580627441,
      "learning_rate": 7.249432463491498e-05,
      "loss": 1.4081,
      "step": 184
    },
    {
      "epoch": 0.5449189985272459,
      "grad_norm": 5.144754409790039,
      "learning_rate": 7.190542927867234e-05,
      "loss": 1.4496,
      "step": 185
    },
    {
      "epoch": 0.5478645066273933,
      "grad_norm": 7.374088764190674,
      "learning_rate": 7.131274906557725e-05,
      "loss": 1.94,
      "step": 186
    },
    {
      "epoch": 0.5508100147275405,
      "grad_norm": 6.2576003074646,
      "learning_rate": 7.071638639991207e-05,
      "loss": 1.701,
      "step": 187
    },
    {
      "epoch": 0.5537555228276878,
      "grad_norm": 5.392474174499512,
      "learning_rate": 7.011644432221958e-05,
      "loss": 1.474,
      "step": 188
    },
    {
      "epoch": 0.5567010309278351,
      "grad_norm": 7.743690013885498,
      "learning_rate": 6.95130264914993e-05,
      "loss": 2.1458,
      "step": 189
    },
    {
      "epoch": 0.5596465390279823,
      "grad_norm": 7.468958377838135,
      "learning_rate": 6.890623716729724e-05,
      "loss": 2.2593,
      "step": 190
    },
    {
      "epoch": 0.5625920471281296,
      "grad_norm": 6.144321918487549,
      "learning_rate": 6.82961811916917e-05,
      "loss": 1.3348,
      "step": 191
    },
    {
      "epoch": 0.5655375552282769,
      "grad_norm": 7.852849006652832,
      "learning_rate": 6.768296397117848e-05,
      "loss": 1.4751,
      "step": 192
    },
    {
      "epoch": 0.5684830633284241,
      "grad_norm": 7.6272172927856445,
      "learning_rate": 6.706669145845863e-05,
      "loss": 1.7606,
      "step": 193
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 13.624709129333496,
      "learning_rate": 6.644747013413168e-05,
      "loss": 1.9716,
      "step": 194
    },
    {
      "epoch": 0.5743740795287187,
      "grad_norm": 8.707653999328613,
      "learning_rate": 6.582540698829781e-05,
      "loss": 1.8245,
      "step": 195
    },
    {
      "epoch": 0.5773195876288659,
      "grad_norm": 6.5573039054870605,
      "learning_rate": 6.520060950207185e-05,
      "loss": 1.1733,
      "step": 196
    },
    {
      "epoch": 0.5802650957290133,
      "grad_norm": 8.433490753173828,
      "learning_rate": 6.457318562901256e-05,
      "loss": 1.2757,
      "step": 197
    },
    {
      "epoch": 0.5832106038291606,
      "grad_norm": 9.936591148376465,
      "learning_rate": 6.394324377647028e-05,
      "loss": 1.4713,
      "step": 198
    },
    {
      "epoch": 0.5861561119293078,
      "grad_norm": 12.52322769165039,
      "learning_rate": 6.331089278685599e-05,
      "loss": 1.6688,
      "step": 199
    },
    {
      "epoch": 0.5891016200294551,
      "grad_norm": 16.770870208740234,
      "learning_rate": 6.26762419188355e-05,
      "loss": 2.3924,
      "step": 200
    },
    {
      "epoch": 0.5920471281296024,
      "grad_norm": 3.7220280170440674,
      "learning_rate": 6.203940082845144e-05,
      "loss": 1.8733,
      "step": 201
    },
    {
      "epoch": 0.5949926362297496,
      "grad_norm": 3.919069290161133,
      "learning_rate": 6.140047955017671e-05,
      "loss": 0.7927,
      "step": 202
    },
    {
      "epoch": 0.5979381443298969,
      "grad_norm": 3.081045150756836,
      "learning_rate": 6.075958847790262e-05,
      "loss": 1.2878,
      "step": 203
    },
    {
      "epoch": 0.6008836524300442,
      "grad_norm": 2.82151198387146,
      "learning_rate": 6.011683834586473e-05,
      "loss": 1.2722,
      "step": 204
    },
    {
      "epoch": 0.6038291605301914,
      "grad_norm": 2.1925573348999023,
      "learning_rate": 5.947234020951015e-05,
      "loss": 0.7102,
      "step": 205
    },
    {
      "epoch": 0.6067746686303387,
      "grad_norm": 2.2746307849884033,
      "learning_rate": 5.882620542630901e-05,
      "loss": 0.8639,
      "step": 206
    },
    {
      "epoch": 0.6097201767304861,
      "grad_norm": 2.5907399654388428,
      "learning_rate": 5.8178545636514145e-05,
      "loss": 1.3898,
      "step": 207
    },
    {
      "epoch": 0.6126656848306333,
      "grad_norm": 3.3455467224121094,
      "learning_rate": 5.752947274387147e-05,
      "loss": 1.6453,
      "step": 208
    },
    {
      "epoch": 0.6156111929307806,
      "grad_norm": 3.1584908962249756,
      "learning_rate": 5.687909889628529e-05,
      "loss": 1.8621,
      "step": 209
    },
    {
      "epoch": 0.6185567010309279,
      "grad_norm": 3.1960365772247314,
      "learning_rate": 5.622753646644102e-05,
      "loss": 1.6358,
      "step": 210
    },
    {
      "epoch": 0.6215022091310751,
      "grad_norm": 3.073702573776245,
      "learning_rate": 5.557489803238933e-05,
      "loss": 1.5381,
      "step": 211
    },
    {
      "epoch": 0.6244477172312224,
      "grad_norm": 2.917039632797241,
      "learning_rate": 5.492129635809473e-05,
      "loss": 1.6452,
      "step": 212
    },
    {
      "epoch": 0.6273932253313697,
      "grad_norm": 3.823730707168579,
      "learning_rate": 5.426684437395196e-05,
      "loss": 1.7625,
      "step": 213
    },
    {
      "epoch": 0.6303387334315169,
      "grad_norm": 4.05581521987915,
      "learning_rate": 5.361165515727374e-05,
      "loss": 1.9468,
      "step": 214
    },
    {
      "epoch": 0.6332842415316642,
      "grad_norm": 3.9730498790740967,
      "learning_rate": 5.295584191275308e-05,
      "loss": 2.2487,
      "step": 215
    },
    {
      "epoch": 0.6362297496318114,
      "grad_norm": 3.2518630027770996,
      "learning_rate": 5.229951795290353e-05,
      "loss": 1.5587,
      "step": 216
    },
    {
      "epoch": 0.6391752577319587,
      "grad_norm": 4.549688816070557,
      "learning_rate": 5.164279667848094e-05,
      "loss": 1.9062,
      "step": 217
    },
    {
      "epoch": 0.6421207658321061,
      "grad_norm": 3.6768784523010254,
      "learning_rate": 5.0985791558889785e-05,
      "loss": 1.6801,
      "step": 218
    },
    {
      "epoch": 0.6450662739322534,
      "grad_norm": 3.8859946727752686,
      "learning_rate": 5.032861611257783e-05,
      "loss": 1.9869,
      "step": 219
    },
    {
      "epoch": 0.6480117820324006,
      "grad_norm": 4.19022798538208,
      "learning_rate": 4.967138388742218e-05,
      "loss": 2.0944,
      "step": 220
    },
    {
      "epoch": 0.6509572901325479,
      "grad_norm": 3.7361319065093994,
      "learning_rate": 4.901420844111021e-05,
      "loss": 1.3391,
      "step": 221
    },
    {
      "epoch": 0.6539027982326951,
      "grad_norm": 3.7620272636413574,
      "learning_rate": 4.835720332151907e-05,
      "loss": 1.2597,
      "step": 222
    },
    {
      "epoch": 0.6568483063328424,
      "grad_norm": 3.610649824142456,
      "learning_rate": 4.770048204709648e-05,
      "loss": 1.2885,
      "step": 223
    },
    {
      "epoch": 0.6597938144329897,
      "grad_norm": 4.286924839019775,
      "learning_rate": 4.7044158087246926e-05,
      "loss": 1.7704,
      "step": 224
    },
    {
      "epoch": 0.6627393225331369,
      "grad_norm": 4.295466423034668,
      "learning_rate": 4.6388344842726264e-05,
      "loss": 1.3672,
      "step": 225
    },
    {
      "epoch": 0.6656848306332842,
      "grad_norm": 5.368373870849609,
      "learning_rate": 4.5733155626048036e-05,
      "loss": 1.5249,
      "step": 226
    },
    {
      "epoch": 0.6686303387334315,
      "grad_norm": 5.0956950187683105,
      "learning_rate": 4.507870364190527e-05,
      "loss": 1.3973,
      "step": 227
    },
    {
      "epoch": 0.6715758468335787,
      "grad_norm": 4.604374408721924,
      "learning_rate": 4.4425101967610674e-05,
      "loss": 1.3965,
      "step": 228
    },
    {
      "epoch": 0.6745213549337261,
      "grad_norm": 6.400148391723633,
      "learning_rate": 4.377246353355899e-05,
      "loss": 2.1319,
      "step": 229
    },
    {
      "epoch": 0.6774668630338734,
      "grad_norm": 6.704805850982666,
      "learning_rate": 4.312090110371473e-05,
      "loss": 1.9594,
      "step": 230
    },
    {
      "epoch": 0.6804123711340206,
      "grad_norm": 4.956854343414307,
      "learning_rate": 4.247052725612852e-05,
      "loss": 1.3392,
      "step": 231
    },
    {
      "epoch": 0.6833578792341679,
      "grad_norm": 8.188490867614746,
      "learning_rate": 4.1821454363485866e-05,
      "loss": 1.7636,
      "step": 232
    },
    {
      "epoch": 0.6863033873343152,
      "grad_norm": 5.5076751708984375,
      "learning_rate": 4.1173794573690996e-05,
      "loss": 1.3066,
      "step": 233
    },
    {
      "epoch": 0.6892488954344624,
      "grad_norm": 6.480940341949463,
      "learning_rate": 4.052765979048986e-05,
      "loss": 1.8326,
      "step": 234
    },
    {
      "epoch": 0.6921944035346097,
      "grad_norm": 7.0487284660339355,
      "learning_rate": 3.988316165413528e-05,
      "loss": 1.7487,
      "step": 235
    },
    {
      "epoch": 0.695139911634757,
      "grad_norm": 6.207117557525635,
      "learning_rate": 3.924041152209739e-05,
      "loss": 1.4652,
      "step": 236
    },
    {
      "epoch": 0.6980854197349042,
      "grad_norm": 5.3427205085754395,
      "learning_rate": 3.859952044982329e-05,
      "loss": 1.3738,
      "step": 237
    },
    {
      "epoch": 0.7010309278350515,
      "grad_norm": 7.366813659667969,
      "learning_rate": 3.7960599171548574e-05,
      "loss": 1.4897,
      "step": 238
    },
    {
      "epoch": 0.7039764359351989,
      "grad_norm": 6.943472862243652,
      "learning_rate": 3.732375808116451e-05,
      "loss": 1.2526,
      "step": 239
    }
  ],
  "logging_steps": 1,
  "max_steps": 339,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 239,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.287612097809613e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}