{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00485074853113271,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.4253742655663552e-05,
      "grad_norm": 3.3759636878967285,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.4074,
      "step": 1
    },
    {
      "epoch": 4.8507485311327104e-05,
      "grad_norm": 0.8539016246795654,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.4688,
      "step": 2
    },
    {
      "epoch": 7.276122796699065e-05,
      "grad_norm": NaN,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.2166,
      "step": 3
    },
    {
      "epoch": 9.701497062265421e-05,
      "grad_norm": 0.8566086888313293,
      "learning_rate": 6e-06,
      "loss": 1.3767,
      "step": 4
    },
    {
      "epoch": 0.00012126871327831776,
      "grad_norm": 1.564802885055542,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.3408,
      "step": 5
    },
    {
      "epoch": 0.0001455224559339813,
      "grad_norm": 6.496278762817383,
      "learning_rate": 1e-05,
      "loss": 2.1242,
      "step": 6
    },
    {
      "epoch": 0.00016977619858964487,
      "grad_norm": 3.3886003494262695,
      "learning_rate": 1.2e-05,
      "loss": 1.639,
      "step": 7
    },
    {
      "epoch": 0.00019402994124530841,
      "grad_norm": 0.5676108598709106,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 1.547,
      "step": 8
    },
    {
      "epoch": 0.00021828368390097196,
      "grad_norm": 7.636886119842529,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.6577,
      "step": 9
    },
    {
      "epoch": 0.00024253742655663553,
      "grad_norm": 13.671367645263672,
      "learning_rate": 1.8e-05,
      "loss": 1.9861,
      "step": 10
    },
    {
      "epoch": 0.00026679116921229907,
      "grad_norm": 1.700162649154663,
      "learning_rate": 2e-05,
      "loss": 2.1347,
      "step": 11
    },
    {
      "epoch": 0.0002910449118679626,
      "grad_norm": 4.465837478637695,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.2903,
      "step": 12
    },
    {
      "epoch": 0.00031529865452362615,
      "grad_norm": 5.200563430786133,
      "learning_rate": 2.4e-05,
      "loss": 1.727,
      "step": 13
    },
    {
      "epoch": 0.00033955239717928975,
      "grad_norm": 2.4282960891723633,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.8629,
      "step": 14
    },
    {
      "epoch": 0.0003638061398349533,
      "grad_norm": 0.8094596266746521,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.3653,
      "step": 15
    },
    {
      "epoch": 0.00038805988249061683,
      "grad_norm": 0.8468468189239502,
      "learning_rate": 3e-05,
      "loss": 1.9853,
      "step": 16
    },
    {
      "epoch": 0.00041231362514628037,
      "grad_norm": 0.9713991284370422,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.0837,
      "step": 17
    },
    {
      "epoch": 0.0004365673678019439,
      "grad_norm": 0.8852229118347168,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.8255,
      "step": 18
    },
    {
      "epoch": 0.0004608211104576075,
      "grad_norm": NaN,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.8453,
      "step": 19
    },
    {
      "epoch": 0.00048507485311327105,
      "grad_norm": 0.7369140982627869,
      "learning_rate": 3.6e-05,
      "loss": 1.4695,
      "step": 20
    },
    {
      "epoch": 0.0005093285957689346,
      "grad_norm": 0.7990018129348755,
      "learning_rate": 3.8e-05,
      "loss": 0.9667,
      "step": 21
    },
    {
      "epoch": 0.0005335823384245981,
      "grad_norm": 51.18899917602539,
      "learning_rate": 4e-05,
      "loss": 2.049,
      "step": 22
    },
    {
      "epoch": 0.0005578360810802617,
      "grad_norm": 2.142543315887451,
      "learning_rate": 4.2e-05,
      "loss": 1.7967,
      "step": 23
    },
    {
      "epoch": 0.0005820898237359252,
      "grad_norm": 14.483644485473633,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.6066,
      "step": 24
    },
    {
      "epoch": 0.0006063435663915888,
      "grad_norm": 0.4434223771095276,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.9649,
      "step": 25
    },
    {
      "epoch": 0.0006305973090472523,
      "grad_norm": 2.3446133136749268,
      "learning_rate": 4.8e-05,
      "loss": 2.2895,
      "step": 26
    },
    {
      "epoch": 0.000654851051702916,
      "grad_norm": 7.05695104598999,
      "learning_rate": 5e-05,
      "loss": 1.5174,
      "step": 27
    },
    {
      "epoch": 0.0006791047943585795,
      "grad_norm": 1.1299482583999634,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 1.6502,
      "step": 28
    },
    {
      "epoch": 0.000703358537014243,
      "grad_norm": 1.1360725164413452,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 1.9164,
      "step": 29
    },
    {
      "epoch": 0.0007276122796699066,
      "grad_norm": 0.6310778260231018,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.3889,
      "step": 30
    },
    {
      "epoch": 0.0007518660223255701,
      "grad_norm": 23.649295806884766,
      "learning_rate": 5.8e-05,
      "loss": 1.8868,
      "step": 31
    },
    {
      "epoch": 0.0007761197649812337,
      "grad_norm": 1.4656137228012085,
      "learning_rate": 6e-05,
      "loss": 2.1166,
      "step": 32
    },
    {
      "epoch": 0.0008003735076368972,
      "grad_norm": 1.1650835275650024,
      "learning_rate": 6.2e-05,
      "loss": 1.6361,
      "step": 33
    },
    {
      "epoch": 0.0008246272502925607,
      "grad_norm": 3.5989675521850586,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.9528,
      "step": 34
    },
    {
      "epoch": 0.0008488809929482243,
      "grad_norm": NaN,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.1095,
      "step": 35
    },
    {
      "epoch": 0.0008731347356038878,
      "grad_norm": 0.7551969885826111,
      "learning_rate": 6.6e-05,
      "loss": 1.4748,
      "step": 36
    },
    {
      "epoch": 0.0008973884782595515,
      "grad_norm": 0.7345149517059326,
      "learning_rate": 6.800000000000001e-05,
      "loss": 1.3746,
      "step": 37
    },
    {
      "epoch": 0.000921642220915215,
      "grad_norm": 0.96466463804245,
      "learning_rate": 7e-05,
      "loss": 1.3491,
      "step": 38
    },
    {
      "epoch": 0.0009458959635708786,
      "grad_norm": 0.895024836063385,
      "learning_rate": 7.2e-05,
      "loss": 1.3976,
      "step": 39
    },
    {
      "epoch": 0.0009701497062265421,
      "grad_norm": 2.5485947132110596,
      "learning_rate": 7.4e-05,
      "loss": 1.6924,
      "step": 40
    },
    {
      "epoch": 0.0009944034488822055,
      "grad_norm": 14.429283142089844,
      "learning_rate": 7.6e-05,
      "loss": 1.2937,
      "step": 41
    },
    {
      "epoch": 0.0010186571915378692,
      "grad_norm": 0.8819990158081055,
      "learning_rate": 7.800000000000001e-05,
      "loss": 1.3237,
      "step": 42
    },
    {
      "epoch": 0.0010429109341935328,
      "grad_norm": 1.2532185316085815,
      "learning_rate": 8e-05,
      "loss": 1.2843,
      "step": 43
    },
    {
      "epoch": 0.0010671646768491963,
      "grad_norm": 3.7754809856414795,
      "learning_rate": 8.2e-05,
      "loss": 2.0701,
      "step": 44
    },
    {
      "epoch": 0.00109141841950486,
      "grad_norm": 6.247189044952393,
      "learning_rate": 8.4e-05,
      "loss": 1.3514,
      "step": 45
    },
    {
      "epoch": 0.0011156721621605234,
      "grad_norm": 2.4143786430358887,
      "learning_rate": 8.6e-05,
      "loss": 1.3366,
      "step": 46
    },
    {
      "epoch": 0.001139925904816187,
      "grad_norm": 0.9999021887779236,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.6014,
      "step": 47
    },
    {
      "epoch": 0.0011641796474718504,
      "grad_norm": 10.256402015686035,
      "learning_rate": 9e-05,
      "loss": 1.5158,
      "step": 48
    },
    {
      "epoch": 0.001188433390127514,
      "grad_norm": 3.1409249305725098,
      "learning_rate": 9.200000000000001e-05,
      "loss": 1.2433,
      "step": 49
    },
    {
      "epoch": 0.0012126871327831775,
      "grad_norm": 5.032261371612549,
      "learning_rate": 9.4e-05,
      "loss": 1.9222,
      "step": 50
    },
    {
      "epoch": 0.0012369408754388412,
      "grad_norm": 32.46524429321289,
      "learning_rate": 9.6e-05,
      "loss": 1.944,
      "step": 51
    },
    {
      "epoch": 0.0012611946180945046,
      "grad_norm": 3.3015825748443604,
      "learning_rate": 9.8e-05,
      "loss": 1.6905,
      "step": 52
    },
    {
      "epoch": 0.0012854483607501683,
      "grad_norm": 33.24071502685547,
      "learning_rate": 0.0001,
      "loss": 1.8358,
      "step": 53
    },
    {
      "epoch": 0.001309702103405832,
      "grad_norm": 1.4521846771240234,
      "learning_rate": 0.00010200000000000001,
      "loss": 1.6665,
      "step": 54
    },
    {
      "epoch": 0.0013339558460614953,
      "grad_norm": 1.9511698484420776,
      "learning_rate": 0.00010400000000000001,
      "loss": 1.2289,
      "step": 55
    },
    {
      "epoch": 0.001358209588717159,
      "grad_norm": 7.6353535652160645,
      "learning_rate": 0.00010600000000000002,
      "loss": 1.762,
      "step": 56
    },
    {
      "epoch": 0.0013824633313728224,
      "grad_norm": 1.035163164138794,
      "learning_rate": 0.00010800000000000001,
      "loss": 1.4294,
      "step": 57
    },
    {
      "epoch": 0.001406717074028486,
      "grad_norm": 4.369189262390137,
      "learning_rate": 0.00011000000000000002,
      "loss": 1.4502,
      "step": 58
    },
    {
      "epoch": 0.0014309708166841495,
      "grad_norm": 1.308000087738037,
      "learning_rate": 0.00011200000000000001,
      "loss": 1.4871,
      "step": 59
    },
    {
      "epoch": 0.0014552245593398132,
      "grad_norm": 0.9026333093643188,
      "learning_rate": 0.00011399999999999999,
      "loss": 1.431,
      "step": 60
    },
    {
      "epoch": 0.0014794783019954766,
      "grad_norm": 1.266846776008606,
      "learning_rate": 0.000116,
      "loss": 1.5601,
      "step": 61
    },
    {
      "epoch": 0.0015037320446511402,
      "grad_norm": 2.569223642349243,
      "learning_rate": 0.000118,
      "loss": 1.3147,
      "step": 62
    },
    {
      "epoch": 0.0015279857873068039,
      "grad_norm": 0.6180663108825684,
      "learning_rate": 0.00012,
      "loss": 0.735,
      "step": 63
    },
    {
      "epoch": 0.0015522395299624673,
      "grad_norm": 7.6248650550842285,
      "learning_rate": 0.000122,
      "loss": 1.1034,
      "step": 64
    },
    {
      "epoch": 0.001576493272618131,
      "grad_norm": NaN,
      "learning_rate": 0.000122,
      "loss": 2.0957,
      "step": 65
    },
    {
      "epoch": 0.0016007470152737944,
      "grad_norm": 17.51434326171875,
      "learning_rate": 0.000124,
      "loss": 1.7337,
      "step": 66
    },
    {
      "epoch": 0.001625000757929458,
      "grad_norm": 4.455969333648682,
      "learning_rate": 0.000126,
      "loss": 1.8453,
      "step": 67
    },
    {
      "epoch": 0.0016492545005851215,
      "grad_norm": 3.6060261726379395,
      "learning_rate": 0.00012800000000000002,
      "loss": 1.304,
      "step": 68
    },
    {
      "epoch": 0.0016735082432407851,
      "grad_norm": 1.1424020528793335,
      "learning_rate": 0.00013000000000000002,
      "loss": 1.2339,
      "step": 69
    },
    {
      "epoch": 0.0016977619858964486,
      "grad_norm": 1.294066309928894,
      "learning_rate": 0.000132,
      "loss": 1.3406,
      "step": 70
    },
    {
      "epoch": 0.0017220157285521122,
      "grad_norm": 8.3845796585083,
      "learning_rate": 0.000134,
      "loss": 2.0366,
      "step": 71
    },
    {
      "epoch": 0.0017462694712077757,
      "grad_norm": 7.098409175872803,
      "learning_rate": 0.00013600000000000003,
      "loss": 1.566,
      "step": 72
    },
    {
      "epoch": 0.0017705232138634393,
      "grad_norm": NaN,
      "learning_rate": 0.00013600000000000003,
      "loss": 1.1374,
      "step": 73
    },
    {
      "epoch": 0.001794776956519103,
      "grad_norm": 3.7947475910186768,
      "learning_rate": 0.000138,
      "loss": 1.4067,
      "step": 74
    },
    {
      "epoch": 0.0018190306991747664,
      "grad_norm": 3.4975695610046387,
      "learning_rate": 0.00014,
      "loss": 1.4905,
      "step": 75
    },
    {
      "epoch": 0.00184328444183043,
      "grad_norm": 1.821387529373169,
      "learning_rate": 0.000142,
      "loss": 1.289,
      "step": 76
    },
    {
      "epoch": 0.0018675381844860935,
      "grad_norm": 58.30936050415039,
      "learning_rate": 0.000144,
      "loss": 1.4909,
      "step": 77
    },
    {
      "epoch": 0.0018917919271417571,
      "grad_norm": 1.3323521614074707,
      "learning_rate": 0.000146,
      "loss": 1.1766,
      "step": 78
    },
    {
      "epoch": 0.0019160456697974206,
      "grad_norm": 5.184061050415039,
      "learning_rate": 0.000148,
      "loss": 0.9555,
      "step": 79
    },
    {
      "epoch": 0.0019402994124530842,
      "grad_norm": 3.7887625694274902,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.8287,
      "step": 80
    },
    {
      "epoch": 0.001964553155108748,
      "grad_norm": 0.8411690592765808,
      "learning_rate": 0.000152,
      "loss": 1.1176,
      "step": 81
    },
    {
      "epoch": 0.001988806897764411,
      "grad_norm": 1.881020426750183,
      "learning_rate": 0.000154,
      "loss": 1.4231,
      "step": 82
    },
    {
      "epoch": 0.0020130606404200747,
      "grad_norm": 2.2068991661071777,
      "learning_rate": 0.00015600000000000002,
      "loss": 1.4049,
      "step": 83
    },
    {
      "epoch": 0.0020373143830757384,
      "grad_norm": 4.380375862121582,
      "learning_rate": 0.00015800000000000002,
      "loss": 1.0798,
      "step": 84
    },
    {
      "epoch": 0.002061568125731402,
      "grad_norm": 1.7205640077590942,
      "learning_rate": 0.00016,
      "loss": 1.4954,
      "step": 85
    },
    {
      "epoch": 0.0020858218683870657,
      "grad_norm": 1.5813369750976562,
      "learning_rate": 0.000162,
      "loss": 1.4113,
      "step": 86
    },
    {
      "epoch": 0.002110075611042729,
      "grad_norm": 1.3017473220825195,
      "learning_rate": 0.000164,
      "loss": 1.2315,
      "step": 87
    },
    {
      "epoch": 0.0021343293536983925,
      "grad_norm": 2.0372846126556396,
      "learning_rate": 0.000166,
      "loss": 1.5282,
      "step": 88
    },
    {
      "epoch": 0.002158583096354056,
      "grad_norm": 1.0349255800247192,
      "learning_rate": 0.000168,
      "loss": 1.3279,
      "step": 89
    },
    {
      "epoch": 0.00218283683900972,
      "grad_norm": 2.119569778442383,
      "learning_rate": 0.00017,
      "loss": 1.0482,
      "step": 90
    },
    {
      "epoch": 0.002207090581665383,
      "grad_norm": 2.0538179874420166,
      "learning_rate": 0.000172,
      "loss": 1.0129,
      "step": 91
    },
    {
      "epoch": 0.0022313443243210467,
      "grad_norm": 1.4903944730758667,
      "learning_rate": 0.000174,
      "loss": 1.7894,
      "step": 92
    },
    {
      "epoch": 0.0022555980669767104,
      "grad_norm": 5.269598007202148,
      "learning_rate": 0.00017600000000000002,
      "loss": 1.1085,
      "step": 93
    },
    {
      "epoch": 0.002279851809632374,
      "grad_norm": 2.082563877105713,
      "learning_rate": 0.00017800000000000002,
      "loss": 1.4559,
      "step": 94
    },
    {
      "epoch": 0.0023041055522880377,
      "grad_norm": 1.0695875883102417,
      "learning_rate": 0.00018,
      "loss": 1.5581,
      "step": 95
    },
    {
      "epoch": 0.002328359294943701,
      "grad_norm": 1.9814307689666748,
      "learning_rate": 0.000182,
      "loss": 1.5945,
      "step": 96
    },
    {
      "epoch": 0.0023526130375993645,
      "grad_norm": 8.308389663696289,
      "learning_rate": 0.00018400000000000003,
      "loss": 2.0305,
      "step": 97
    },
    {
      "epoch": 0.002376866780255028,
      "grad_norm": 1.8079288005828857,
      "learning_rate": 0.00018600000000000002,
      "loss": 1.4862,
      "step": 98
    },
    {
      "epoch": 0.002401120522910692,
      "grad_norm": 12.573166847229004,
      "learning_rate": 0.000188,
      "loss": 1.7458,
      "step": 99
    },
    {
      "epoch": 0.002425374265566355,
      "grad_norm": 33.789764404296875,
      "learning_rate": 0.00019,
      "loss": 1.3982,
      "step": 100
    },
    {
      "epoch": 0.0024496280082220187,
      "grad_norm": 27.591976165771484,
      "learning_rate": 0.000192,
      "loss": 1.5771,
      "step": 101
    },
    {
      "epoch": 0.0024738817508776823,
      "grad_norm": 1.4807827472686768,
      "learning_rate": 0.000194,
      "loss": 1.462,
      "step": 102
    },
    {
      "epoch": 0.002498135493533346,
      "grad_norm": 1.479779601097107,
      "learning_rate": 0.000196,
      "loss": 1.5715,
      "step": 103
    },
    {
      "epoch": 0.002522389236189009,
      "grad_norm": 1.569394826889038,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.7968,
      "step": 104
    },
    {
      "epoch": 0.002546642978844673,
      "grad_norm": 1.3037728071212769,
      "learning_rate": 0.0002,
      "loss": 1.2281,
      "step": 105
    },
    {
      "epoch": 0.0025708967215003365,
      "grad_norm": 3.430941104888916,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.5046,
      "step": 106
    },
    {
      "epoch": 0.002595150464156,
      "grad_norm": 1.2662192583084106,
      "learning_rate": 0.000196,
      "loss": 1.1589,
      "step": 107
    },
    {
      "epoch": 0.002619404206811664,
      "grad_norm": 1.0078253746032715,
      "learning_rate": 0.000194,
      "loss": 1.2159,
      "step": 108
    },
    {
      "epoch": 0.002643657949467327,
      "grad_norm": 1.0011709928512573,
      "learning_rate": 0.000192,
      "loss": 1.3889,
      "step": 109
    },
    {
      "epoch": 0.0026679116921229907,
      "grad_norm": 1.0177195072174072,
      "learning_rate": 0.00019,
      "loss": 1.5495,
      "step": 110
    },
    {
      "epoch": 0.0026921654347786543,
      "grad_norm": 14.817512512207031,
      "learning_rate": 0.000188,
      "loss": 1.3749,
      "step": 111
    },
    {
      "epoch": 0.002716419177434318,
      "grad_norm": 2.8248116970062256,
      "learning_rate": 0.00018600000000000002,
      "loss": 1.4093,
      "step": 112
    },
    {
      "epoch": 0.002740672920089981,
      "grad_norm": 1.23388671875,
      "learning_rate": 0.00018400000000000003,
      "loss": 1.662,
      "step": 113
    },
    {
      "epoch": 0.002764926662745645,
      "grad_norm": 1.2018444538116455,
      "learning_rate": 0.000182,
      "loss": 1.561,
      "step": 114
    },
    {
      "epoch": 0.0027891804054013085,
      "grad_norm": 1.6609792709350586,
      "learning_rate": 0.00018,
      "loss": 1.449,
      "step": 115
    },
    {
      "epoch": 0.002813434148056972,
      "grad_norm": 4.717409610748291,
      "learning_rate": 0.00017800000000000002,
      "loss": 1.3023,
      "step": 116
    },
    {
      "epoch": 0.002837687890712636,
      "grad_norm": 0.6800332069396973,
      "learning_rate": 0.00017600000000000002,
      "loss": 1.1162,
      "step": 117
    },
    {
      "epoch": 0.002861941633368299,
      "grad_norm": 1.1162289381027222,
      "learning_rate": 0.000174,
      "loss": 1.2826,
      "step": 118
    },
    {
      "epoch": 0.0028861953760239627,
      "grad_norm": 0.9007352590560913,
      "learning_rate": 0.000172,
      "loss": 1.7017,
      "step": 119
    },
    {
      "epoch": 0.0029104491186796263,
      "grad_norm": 2.0487279891967773,
      "learning_rate": 0.00017,
      "loss": 2.0916,
      "step": 120
    },
    {
      "epoch": 0.00293470286133529,
      "grad_norm": 4.298633098602295,
      "learning_rate": 0.000168,
      "loss": 2.2025,
      "step": 121
    },
    {
      "epoch": 0.002958956603990953,
      "grad_norm": 1.0514113903045654,
      "learning_rate": 0.000166,
      "loss": 1.3972,
      "step": 122
    },
    {
      "epoch": 0.002983210346646617,
      "grad_norm": 0.7477086186408997,
      "learning_rate": 0.000164,
      "loss": 1.0473,
      "step": 123
    },
    {
      "epoch": 0.0030074640893022805,
      "grad_norm": 1.2515380382537842,
      "learning_rate": 0.000162,
      "loss": 1.4222,
      "step": 124
    },
    {
      "epoch": 0.003031717831957944,
      "grad_norm": 1.1901217699050903,
      "learning_rate": 0.00016,
      "loss": 1.0811,
      "step": 125
    },
    {
      "epoch": 0.0030559715746136078,
      "grad_norm": 1.3582122325897217,
      "learning_rate": 0.00015800000000000002,
      "loss": 1.2179,
      "step": 126
    },
    {
      "epoch": 0.003080225317269271,
      "grad_norm": 0.7772126197814941,
      "learning_rate": 0.00015600000000000002,
      "loss": 1.1056,
      "step": 127
    },
    {
      "epoch": 0.0031044790599249346,
      "grad_norm": 3.8524062633514404,
      "learning_rate": 0.000154,
      "loss": 1.1881,
      "step": 128
    },
    {
      "epoch": 0.0031287328025805983,
      "grad_norm": 1.8099156618118286,
      "learning_rate": 0.000152,
      "loss": 1.6343,
      "step": 129
    },
    {
      "epoch": 0.003152986545236262,
      "grad_norm": 1.2134389877319336,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.3875,
      "step": 130
    },
    {
      "epoch": 0.003177240287891925,
      "grad_norm": 0.938895583152771,
      "learning_rate": 0.000148,
      "loss": 1.2225,
      "step": 131
    },
    {
      "epoch": 0.003201494030547589,
      "grad_norm": 1.9306858777999878,
      "learning_rate": 0.000146,
      "loss": 1.2144,
      "step": 132
    },
    {
      "epoch": 0.0032257477732032525,
      "grad_norm": 1.3297972679138184,
      "learning_rate": 0.000144,
      "loss": 1.4381,
      "step": 133
    },
    {
      "epoch": 0.003250001515858916,
      "grad_norm": 1.270509958267212,
      "learning_rate": 0.000142,
      "loss": 1.1591,
      "step": 134
    },
    {
      "epoch": 0.0032742552585145793,
      "grad_norm": 3.317193031311035,
      "learning_rate": 0.00014,
      "loss": 1.2585,
      "step": 135
    },
    {
      "epoch": 0.003298509001170243,
      "grad_norm": 1.2975448369979858,
      "learning_rate": 0.000138,
      "loss": 1.571,
      "step": 136
    },
    {
      "epoch": 0.0033227627438259066,
      "grad_norm": 1.0426270961761475,
      "learning_rate": 0.00013600000000000003,
      "loss": 1.8555,
      "step": 137
    },
    {
      "epoch": 0.0033470164864815703,
      "grad_norm": 1.228779673576355,
      "learning_rate": 0.000134,
      "loss": 1.3992,
      "step": 138
    },
    {
      "epoch": 0.003371270229137234,
      "grad_norm": 0.977001428604126,
      "learning_rate": 0.000132,
      "loss": 1.1395,
      "step": 139
    },
    {
      "epoch": 0.003395523971792897,
      "grad_norm": 1.0894217491149902,
      "learning_rate": 0.00013000000000000002,
      "loss": 1.4242,
      "step": 140
    },
    {
      "epoch": 0.003419777714448561,
      "grad_norm": 1.0413155555725098,
      "learning_rate": 0.00012800000000000002,
      "loss": 1.4771,
      "step": 141
    },
    {
      "epoch": 0.0034440314571042244,
      "grad_norm": 1.2907966375350952,
      "learning_rate": 0.000126,
      "loss": 1.5202,
      "step": 142
    },
    {
      "epoch": 0.003468285199759888,
      "grad_norm": 0.8118016123771667,
      "learning_rate": 0.000124,
      "loss": 1.5335,
      "step": 143
    },
    {
      "epoch": 0.0034925389424155513,
      "grad_norm": 1.329568862915039,
      "learning_rate": 0.000122,
      "loss": 1.7877,
      "step": 144
    },
    {
      "epoch": 0.003516792685071215,
      "grad_norm": 0.6988470554351807,
      "learning_rate": 0.00012,
      "loss": 0.6288,
      "step": 145
    },
    {
      "epoch": 0.0035410464277268786,
      "grad_norm": 2.3587098121643066,
      "learning_rate": 0.000118,
      "loss": 1.2359,
      "step": 146
    },
    {
      "epoch": 0.0035653001703825423,
      "grad_norm": 1.1087194681167603,
      "learning_rate": 0.000116,
      "loss": 1.3769,
      "step": 147
    },
    {
      "epoch": 0.003589553913038206,
      "grad_norm": 1.6822993755340576,
      "learning_rate": 0.00011399999999999999,
      "loss": 1.3112,
      "step": 148
    },
    {
      "epoch": 0.003613807655693869,
      "grad_norm": 1.3227869272232056,
      "learning_rate": 0.00011200000000000001,
      "loss": 1.4754,
      "step": 149
    },
    {
      "epoch": 0.0036380613983495328,
      "grad_norm": 1.1278481483459473,
      "learning_rate": 0.00011000000000000002,
      "loss": 1.1768,
      "step": 150
    },
    {
      "epoch": 0.0036623151410051964,
      "grad_norm": 1.2085745334625244,
      "learning_rate": 0.00010800000000000001,
      "loss": 1.4345,
      "step": 151
    },
    {
      "epoch": 0.00368656888366086,
      "grad_norm": 1.0850399732589722,
      "learning_rate": 0.00010600000000000002,
      "loss": 1.2432,
      "step": 152
    },
    {
      "epoch": 0.0037108226263165233,
      "grad_norm": 1.2463059425354004,
      "learning_rate": 0.00010400000000000001,
      "loss": 1.5501,
      "step": 153
    },
    {
      "epoch": 0.003735076368972187,
      "grad_norm": 1.059967041015625,
      "learning_rate": 0.00010200000000000001,
      "loss": 1.0448,
      "step": 154
    },
    {
      "epoch": 0.0037593301116278506,
      "grad_norm": 2.2503929138183594,
      "learning_rate": 0.0001,
      "loss": 1.4892,
      "step": 155
    },
    {
      "epoch": 0.0037835838542835142,
      "grad_norm": 0.8803784251213074,
      "learning_rate": 9.8e-05,
      "loss": 1.2764,
      "step": 156
    },
    {
      "epoch": 0.003807837596939178,
      "grad_norm": 1.5173571109771729,
      "learning_rate": 9.6e-05,
      "loss": 1.0656,
      "step": 157
    },
    {
      "epoch": 0.003832091339594841,
      "grad_norm": 2.0226430892944336,
      "learning_rate": 9.4e-05,
      "loss": 1.1382,
      "step": 158
    },
    {
      "epoch": 0.0038563450822505048,
      "grad_norm": 1.9149307012557983,
      "learning_rate": 9.200000000000001e-05,
      "loss": 1.4105,
      "step": 159
    },
    {
      "epoch": 0.0038805988249061684,
      "grad_norm": 0.9839889407157898,
      "learning_rate": 9e-05,
      "loss": 1.7808,
      "step": 160
    },
    {
      "epoch": 0.003904852567561832,
      "grad_norm": 1.306378722190857,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.4799,
      "step": 161
    },
    {
      "epoch": 0.003929106310217496,
      "grad_norm": 1.9649689197540283,
      "learning_rate": 8.6e-05,
      "loss": 1.2497,
      "step": 162
    },
    {
      "epoch": 0.003953360052873159,
      "grad_norm": 0.8306687474250793,
      "learning_rate": 8.4e-05,
      "loss": 1.1058,
      "step": 163
    },
    {
      "epoch": 0.003977613795528822,
      "grad_norm": 1.034351110458374,
      "learning_rate": 8.2e-05,
      "loss": 0.9346,
      "step": 164
    },
    {
      "epoch": 0.004001867538184486,
      "grad_norm": 1.165528416633606,
      "learning_rate": 8e-05,
      "loss": 1.2315,
      "step": 165
    },
    {
      "epoch": 0.0040261212808401494,
      "grad_norm": 1.3174549341201782,
      "learning_rate": 7.800000000000001e-05,
      "loss": 1.7447,
      "step": 166
    },
    {
      "epoch": 0.004050375023495813,
      "grad_norm": 1.8279471397399902,
      "learning_rate": 7.6e-05,
      "loss": 1.6226,
      "step": 167
    },
    {
      "epoch": 0.004074628766151477,
      "grad_norm": 1.1315997838974,
      "learning_rate": 7.4e-05,
      "loss": 1.2114,
      "step": 168
    },
    {
      "epoch": 0.00409888250880714,
      "grad_norm": 1.0842983722686768,
      "learning_rate": 7.2e-05,
      "loss": 1.1462,
      "step": 169
    },
    {
      "epoch": 0.004123136251462804,
      "grad_norm": 0.8647174835205078,
      "learning_rate": 7e-05,
      "loss": 0.9729,
      "step": 170
    },
    {
      "epoch": 0.004147389994118468,
      "grad_norm": 0.9712747931480408,
      "learning_rate": 6.800000000000001e-05,
      "loss": 1.2886,
      "step": 171
    },
    {
      "epoch": 0.004171643736774131,
      "grad_norm": 1.3875259160995483,
      "learning_rate": 6.6e-05,
      "loss": 1.5696,
      "step": 172
    },
    {
      "epoch": 0.004195897479429794,
      "grad_norm": 1.1321961879730225,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.4366,
      "step": 173
    },
    {
      "epoch": 0.004220151222085458,
      "grad_norm": 5.357350826263428,
      "learning_rate": 6.2e-05,
      "loss": 1.5292,
      "step": 174
    },
    {
      "epoch": 0.004244404964741121,
      "grad_norm": 0.7717924118041992,
      "learning_rate": 6e-05,
      "loss": 1.3228,
      "step": 175
    },
    {
      "epoch": 0.004268658707396785,
      "grad_norm": 1.9575989246368408,
      "learning_rate": 5.8e-05,
      "loss": 1.1391,
      "step": 176
    },
    {
      "epoch": 0.004292912450052449,
      "grad_norm": 1.1362651586532593,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.5378,
      "step": 177
    },
    {
      "epoch": 0.004317166192708112,
      "grad_norm": 1.5834994316101074,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 1.7488,
      "step": 178
    },
    {
      "epoch": 0.004341419935363776,
      "grad_norm": Infinity,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 1.945,
      "step": 179
    },
    {
      "epoch": 0.00436567367801944,
      "grad_norm": 1.2279846668243408,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 1.2098,
      "step": 180
    },
    {
      "epoch": 0.004389927420675103,
      "grad_norm": 0.9098599553108215,
      "learning_rate": 5e-05,
      "loss": 1.2899,
      "step": 181
    },
    {
      "epoch": 0.004414181163330766,
      "grad_norm": 1.4090386629104614,
      "learning_rate": 4.8e-05,
      "loss": 1.9194,
      "step": 182
    },
    {
      "epoch": 0.00443843490598643,
      "grad_norm": 0.9789434671401978,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.9409,
      "step": 183
    },
    {
      "epoch": 0.004462688648642093,
      "grad_norm": 0.8534678220748901,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.3122,
      "step": 184
    },
    {
      "epoch": 0.004486942391297757,
      "grad_norm": 0.9604746103286743,
      "learning_rate": 4.2e-05,
      "loss": 1.2598,
      "step": 185
    },
    {
      "epoch": 0.004511196133953421,
      "grad_norm": 1.2235528230667114,
      "learning_rate": 4e-05,
      "loss": 1.1669,
      "step": 186
    },
    {
      "epoch": 0.004535449876609084,
      "grad_norm": 1.1576164960861206,
      "learning_rate": 3.8e-05,
      "loss": 1.2882,
      "step": 187
    },
    {
      "epoch": 0.004559703619264748,
      "grad_norm": 2.6080610752105713,
      "learning_rate": 3.6e-05,
      "loss": 1.7071,
      "step": 188
    },
    {
      "epoch": 0.004583957361920412,
      "grad_norm": 1.0198453664779663,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.5359,
      "step": 189
    },
    {
      "epoch": 0.004608211104576075,
      "grad_norm": 0.536956250667572,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.99,
      "step": 190
    },
    {
      "epoch": 0.004632464847231738,
      "grad_norm": 1.0942273139953613,
      "learning_rate": 3e-05,
      "loss": 1.2758,
      "step": 191
    },
    {
      "epoch": 0.004656718589887402,
      "grad_norm": 0.7441216707229614,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.1892,
      "step": 192
    },
    {
      "epoch": 0.004680972332543065,
      "grad_norm": 1.032776951789856,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.1905,
      "step": 193
    },
    {
      "epoch": 0.004705226075198729,
      "grad_norm": 1.4048435688018799,
      "learning_rate": 2.4e-05,
      "loss": 1.5178,
      "step": 194
    },
    {
      "epoch": 0.004729479817854393,
      "grad_norm": 1.3756521940231323,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.4318,
      "step": 195
    },
    {
      "epoch": 0.004753733560510056,
      "grad_norm": 1.066291332244873,
      "learning_rate": 2e-05,
      "loss": 1.3325,
      "step": 196
    },
    {
      "epoch": 0.00477798730316572,
      "grad_norm": 1.1176751852035522,
      "learning_rate": 1.8e-05,
      "loss": 1.403,
      "step": 197
    },
    {
      "epoch": 0.004802241045821384,
      "grad_norm": 1.995957851409912,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.3541,
      "step": 198
    },
    {
      "epoch": 0.004826494788477047,
      "grad_norm": 2.2354772090911865,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 1.6087,
      "step": 199
    },
    {
      "epoch": 0.00485074853113271,
      "grad_norm": 19.62826919555664,
      "learning_rate": 1.2e-05,
      "loss": 1.8031,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6033065352437760.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}