{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3189792663476874,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001594896331738437,
      "grad_norm": 9.529223442077637,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 3.8964,
      "step": 1
    },
    {
      "epoch": 0.003189792663476874,
      "grad_norm": 3.4800214767456055,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.2247,
      "step": 2
    },
    {
      "epoch": 0.004784688995215311,
      "grad_norm": 3.026850461959839,
      "learning_rate": 6e-06,
      "loss": 2.2337,
      "step": 3
    },
    {
      "epoch": 0.006379585326953748,
      "grad_norm": 7.065993785858154,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.9733,
      "step": 4
    },
    {
      "epoch": 0.007974481658692184,
      "grad_norm": 5.338789463043213,
      "learning_rate": 1e-05,
      "loss": 2.2808,
      "step": 5
    },
    {
      "epoch": 0.009569377990430622,
      "grad_norm": 12.933262825012207,
      "learning_rate": 1.2e-05,
      "loss": 2.2984,
      "step": 6
    },
    {
      "epoch": 0.011164274322169059,
      "grad_norm": 3.535792350769043,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 2.6236,
      "step": 7
    },
    {
      "epoch": 0.012759170653907496,
      "grad_norm": 7.564616680145264,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.4849,
      "step": 8
    },
    {
      "epoch": 0.014354066985645933,
      "grad_norm": 7.379055976867676,
      "learning_rate": 1.8e-05,
      "loss": 2.9017,
      "step": 9
    },
    {
      "epoch": 0.01594896331738437,
      "grad_norm": 6.781640529632568,
      "learning_rate": 2e-05,
      "loss": 2.5836,
      "step": 10
    },
    {
      "epoch": 0.017543859649122806,
      "grad_norm": Infinity,
      "learning_rate": 2e-05,
      "loss": 2.6482,
      "step": 11
    },
    {
      "epoch": 0.019138755980861243,
      "grad_norm": 9.666836738586426,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.5775,
      "step": 12
    },
    {
      "epoch": 0.02073365231259968,
      "grad_norm": 7.910143852233887,
      "learning_rate": 2.4e-05,
      "loss": 2.259,
      "step": 13
    },
    {
      "epoch": 0.022328548644338118,
      "grad_norm": 5.05098295211792,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 2.1146,
      "step": 14
    },
    {
      "epoch": 0.023923444976076555,
      "grad_norm": 4.457101345062256,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 2.1058,
      "step": 15
    },
    {
      "epoch": 0.025518341307814992,
      "grad_norm": NaN,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 2.4278,
      "step": 16
    },
    {
      "epoch": 0.02711323763955343,
      "grad_norm": 4.420550346374512,
      "learning_rate": 3e-05,
      "loss": 1.9174,
      "step": 17
    },
    {
      "epoch": 0.028708133971291867,
      "grad_norm": 9.368809700012207,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 2.0925,
      "step": 18
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 4.382827281951904,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.3716,
      "step": 19
    },
    {
      "epoch": 0.03189792663476874,
      "grad_norm": 24.012392044067383,
      "learning_rate": 3.6e-05,
      "loss": 2.348,
      "step": 20
    },
    {
      "epoch": 0.03349282296650718,
      "grad_norm": 2.227252721786499,
      "learning_rate": 3.8e-05,
      "loss": 2.0678,
      "step": 21
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 6.851357460021973,
      "learning_rate": 4e-05,
      "loss": 3.2008,
      "step": 22
    },
    {
      "epoch": 0.03668261562998405,
      "grad_norm": 5.75844144821167,
      "learning_rate": 4.2e-05,
      "loss": 1.8704,
      "step": 23
    },
    {
      "epoch": 0.03827751196172249,
      "grad_norm": 14.692899703979492,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 2.9055,
      "step": 24
    },
    {
      "epoch": 0.03987240829346093,
      "grad_norm": NaN,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 2.4497,
      "step": 25
    },
    {
      "epoch": 0.04146730462519936,
      "grad_norm": NaN,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 2.4382,
      "step": 26
    },
    {
      "epoch": 0.0430622009569378,
      "grad_norm": 6.065037727355957,
      "learning_rate": 4.600000000000001e-05,
      "loss": 2.105,
      "step": 27
    },
    {
      "epoch": 0.044657097288676235,
      "grad_norm": 4.765100479125977,
      "learning_rate": 4.8e-05,
      "loss": 2.5292,
      "step": 28
    },
    {
      "epoch": 0.046251993620414676,
      "grad_norm": 10.693521499633789,
      "learning_rate": 5e-05,
      "loss": 1.4471,
      "step": 29
    },
    {
      "epoch": 0.04784688995215311,
      "grad_norm": 5.703505992889404,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 1.8759,
      "step": 30
    },
    {
      "epoch": 0.049441786283891544,
      "grad_norm": 6.594554424285889,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 2.3555,
      "step": 31
    },
    {
      "epoch": 0.051036682615629984,
      "grad_norm": 10.944120407104492,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 2.6607,
      "step": 32
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 4.437515735626221,
      "learning_rate": 5.8e-05,
      "loss": 2.1366,
      "step": 33
    },
    {
      "epoch": 0.05422647527910686,
      "grad_norm": 18.751192092895508,
      "learning_rate": 6e-05,
      "loss": 2.8504,
      "step": 34
    },
    {
      "epoch": 0.05582137161084529,
      "grad_norm": 4.625219821929932,
      "learning_rate": 6.2e-05,
      "loss": 1.7409,
      "step": 35
    },
    {
      "epoch": 0.05741626794258373,
      "grad_norm": 5.256422996520996,
      "learning_rate": 6.400000000000001e-05,
      "loss": 2.965,
      "step": 36
    },
    {
      "epoch": 0.05901116427432217,
      "grad_norm": 5.383383274078369,
      "learning_rate": 6.6e-05,
      "loss": 2.5555,
      "step": 37
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 20.616491317749023,
      "learning_rate": 6.800000000000001e-05,
      "loss": 2.1693,
      "step": 38
    },
    {
      "epoch": 0.06220095693779904,
      "grad_norm": 14.188122749328613,
      "learning_rate": 7e-05,
      "loss": 3.2098,
      "step": 39
    },
    {
      "epoch": 0.06379585326953748,
      "grad_norm": 7.294703483581543,
      "learning_rate": 7.2e-05,
      "loss": 2.8137,
      "step": 40
    },
    {
      "epoch": 0.06539074960127592,
      "grad_norm": 16.109020233154297,
      "learning_rate": 7.4e-05,
      "loss": 3.4821,
      "step": 41
    },
    {
      "epoch": 0.06698564593301436,
      "grad_norm": 12.77609920501709,
      "learning_rate": 7.6e-05,
      "loss": 3.2586,
      "step": 42
    },
    {
      "epoch": 0.0685805422647528,
      "grad_norm": 7.247976303100586,
      "learning_rate": 7.800000000000001e-05,
      "loss": 2.1131,
      "step": 43
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 3.0302693843841553,
      "learning_rate": 8e-05,
      "loss": 2.3047,
      "step": 44
    },
    {
      "epoch": 0.07177033492822966,
      "grad_norm": 6.998560905456543,
      "learning_rate": 8.2e-05,
      "loss": 1.9685,
      "step": 45
    },
    {
      "epoch": 0.0733652312599681,
      "grad_norm": 11.82168197631836,
      "learning_rate": 8.4e-05,
      "loss": 2.412,
      "step": 46
    },
    {
      "epoch": 0.07496012759170653,
      "grad_norm": 2.4560766220092773,
      "learning_rate": 8.6e-05,
      "loss": 1.5546,
      "step": 47
    },
    {
      "epoch": 0.07655502392344497,
      "grad_norm": 7.5531110763549805,
      "learning_rate": 8.800000000000001e-05,
      "loss": 2.0706,
      "step": 48
    },
    {
      "epoch": 0.07814992025518341,
      "grad_norm": 9.41441535949707,
      "learning_rate": 9e-05,
      "loss": 2.0769,
      "step": 49
    },
    {
      "epoch": 0.07974481658692185,
      "grad_norm": 5.027219295501709,
      "learning_rate": 9.200000000000001e-05,
      "loss": 1.0112,
      "step": 50
    },
    {
      "epoch": 0.08133971291866028,
      "grad_norm": 4.590622901916504,
      "learning_rate": 9.4e-05,
      "loss": 2.4014,
      "step": 51
    },
    {
      "epoch": 0.08293460925039872,
      "grad_norm": 110.29186248779297,
      "learning_rate": 9.6e-05,
      "loss": 2.2312,
      "step": 52
    },
    {
      "epoch": 0.08452950558213716,
      "grad_norm": 13.907599449157715,
      "learning_rate": 9.8e-05,
      "loss": 3.74,
      "step": 53
    },
    {
      "epoch": 0.0861244019138756,
      "grad_norm": 21.45476722717285,
      "learning_rate": 0.0001,
      "loss": 2.2449,
      "step": 54
    },
    {
      "epoch": 0.08771929824561403,
      "grad_norm": 26.367050170898438,
      "learning_rate": 0.00010200000000000001,
      "loss": 2.4117,
      "step": 55
    },
    {
      "epoch": 0.08931419457735247,
      "grad_norm": 11.473040580749512,
      "learning_rate": 0.00010400000000000001,
      "loss": 1.9575,
      "step": 56
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 7.996298789978027,
      "learning_rate": 0.00010600000000000002,
      "loss": 2.2506,
      "step": 57
    },
    {
      "epoch": 0.09250398724082935,
      "grad_norm": 5.780291557312012,
      "learning_rate": 0.00010800000000000001,
      "loss": 1.685,
      "step": 58
    },
    {
      "epoch": 0.09409888357256778,
      "grad_norm": 14.359979629516602,
      "learning_rate": 0.00011000000000000002,
      "loss": 2.1997,
      "step": 59
    },
    {
      "epoch": 0.09569377990430622,
      "grad_norm": 2.4853787422180176,
      "learning_rate": 0.00011200000000000001,
      "loss": 1.2731,
      "step": 60
    },
    {
      "epoch": 0.09728867623604466,
      "grad_norm": 7.136777877807617,
      "learning_rate": 0.00011399999999999999,
      "loss": 2.1987,
      "step": 61
    },
    {
      "epoch": 0.09888357256778309,
      "grad_norm": 7.219399929046631,
      "learning_rate": 0.000116,
      "loss": 2.3118,
      "step": 62
    },
    {
      "epoch": 0.10047846889952153,
      "grad_norm": 15.516590118408203,
      "learning_rate": 0.000118,
      "loss": 2.2534,
      "step": 63
    },
    {
      "epoch": 0.10207336523125997,
      "grad_norm": 4.05905818939209,
      "learning_rate": 0.00012,
      "loss": 2.0509,
      "step": 64
    },
    {
      "epoch": 0.10366826156299841,
      "grad_norm": 51.53736877441406,
      "learning_rate": 0.000122,
      "loss": 3.7686,
      "step": 65
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 4.316274642944336,
      "learning_rate": 0.000124,
      "loss": 1.332,
      "step": 66
    },
    {
      "epoch": 0.10685805422647528,
      "grad_norm": 47.97142028808594,
      "learning_rate": 0.000126,
      "loss": 1.4256,
      "step": 67
    },
    {
      "epoch": 0.10845295055821372,
      "grad_norm": 10.22885513305664,
      "learning_rate": 0.00012800000000000002,
      "loss": 1.4572,
      "step": 68
    },
    {
      "epoch": 0.11004784688995216,
      "grad_norm": 5.966179370880127,
      "learning_rate": 0.00013000000000000002,
      "loss": 1.3998,
      "step": 69
    },
    {
      "epoch": 0.11164274322169059,
      "grad_norm": 3.413966178894043,
      "learning_rate": 0.000132,
      "loss": 1.6306,
      "step": 70
    },
    {
      "epoch": 0.11323763955342903,
      "grad_norm": 197.0709991455078,
      "learning_rate": 0.000134,
      "loss": 1.6587,
      "step": 71
    },
    {
      "epoch": 0.11483253588516747,
      "grad_norm": 12.735696792602539,
      "learning_rate": 0.00013600000000000003,
      "loss": 2.0253,
      "step": 72
    },
    {
      "epoch": 0.11642743221690591,
      "grad_norm": 14.38369083404541,
      "learning_rate": 0.000138,
      "loss": 2.0833,
      "step": 73
    },
    {
      "epoch": 0.11802232854864433,
      "grad_norm": 5.746401786804199,
      "learning_rate": 0.00014,
      "loss": 1.959,
      "step": 74
    },
    {
      "epoch": 0.11961722488038277,
      "grad_norm": 4.266767501831055,
      "learning_rate": 0.000142,
      "loss": 1.5752,
      "step": 75
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 16.618648529052734,
      "learning_rate": 0.000144,
      "loss": 3.0947,
      "step": 76
    },
    {
      "epoch": 0.12280701754385964,
      "grad_norm": 2.3666510581970215,
      "learning_rate": 0.000146,
      "loss": 2.0715,
      "step": 77
    },
    {
      "epoch": 0.12440191387559808,
      "grad_norm": 6.622753143310547,
      "learning_rate": 0.000148,
      "loss": 1.8844,
      "step": 78
    },
    {
      "epoch": 0.12599681020733652,
      "grad_norm": 43.816375732421875,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.9108,
      "step": 79
    },
    {
      "epoch": 0.12759170653907495,
      "grad_norm": 6.682168006896973,
      "learning_rate": 0.000152,
      "loss": 1.5588,
      "step": 80
    },
    {
      "epoch": 0.1291866028708134,
      "grad_norm": 3.0997276306152344,
      "learning_rate": 0.000154,
      "loss": 2.1988,
      "step": 81
    },
    {
      "epoch": 0.13078149920255183,
      "grad_norm": 4.309176445007324,
      "learning_rate": 0.00015600000000000002,
      "loss": 1.406,
      "step": 82
    },
    {
      "epoch": 0.13237639553429026,
      "grad_norm": 5.416724681854248,
      "learning_rate": 0.00015800000000000002,
      "loss": 1.576,
      "step": 83
    },
    {
      "epoch": 0.1339712918660287,
      "grad_norm": 4.361196517944336,
      "learning_rate": 0.00016,
      "loss": 2.2985,
      "step": 84
    },
    {
      "epoch": 0.13556618819776714,
      "grad_norm": 7.655956745147705,
      "learning_rate": 0.000162,
      "loss": 1.3693,
      "step": 85
    },
    {
      "epoch": 0.1371610845295056,
      "grad_norm": 5.973109245300293,
      "learning_rate": 0.000164,
      "loss": 2.4914,
      "step": 86
    },
    {
      "epoch": 0.13875598086124402,
      "grad_norm": 5.1589436531066895,
      "learning_rate": 0.000166,
      "loss": 1.6638,
      "step": 87
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 6.356327056884766,
      "learning_rate": 0.000168,
      "loss": 1.381,
      "step": 88
    },
    {
      "epoch": 0.1419457735247209,
      "grad_norm": 1.5582388639450073,
      "learning_rate": 0.00017,
      "loss": 1.4864,
      "step": 89
    },
    {
      "epoch": 0.14354066985645933,
      "grad_norm": 2.830798387527466,
      "learning_rate": 0.000172,
      "loss": 1.897,
      "step": 90
    },
    {
      "epoch": 0.14513556618819776,
      "grad_norm": 20.24082374572754,
      "learning_rate": 0.000174,
      "loss": 1.7698,
      "step": 91
    },
    {
      "epoch": 0.1467304625199362,
      "grad_norm": 35.429466247558594,
      "learning_rate": 0.00017600000000000002,
      "loss": 3.6051,
      "step": 92
    },
    {
      "epoch": 0.14832535885167464,
      "grad_norm": 9.8428373336792,
      "learning_rate": 0.00017800000000000002,
      "loss": 1.9402,
      "step": 93
    },
    {
      "epoch": 0.14992025518341306,
      "grad_norm": 3.7131340503692627,
      "learning_rate": 0.00018,
      "loss": 2.2192,
      "step": 94
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 8.838521003723145,
      "learning_rate": 0.000182,
      "loss": 2.0167,
      "step": 95
    },
    {
      "epoch": 0.15311004784688995,
      "grad_norm": 9.63149356842041,
      "learning_rate": 0.00018400000000000003,
      "loss": 1.6169,
      "step": 96
    },
    {
      "epoch": 0.1547049441786284,
      "grad_norm": 6.012756824493408,
      "learning_rate": 0.00018600000000000002,
      "loss": 1.4477,
      "step": 97
    },
    {
      "epoch": 0.15629984051036683,
      "grad_norm": 9.02092456817627,
      "learning_rate": 0.000188,
      "loss": 1.5999,
      "step": 98
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 5.8646416664123535,
      "learning_rate": 0.00019,
      "loss": 1.2515,
      "step": 99
    },
    {
      "epoch": 0.1594896331738437,
      "grad_norm": 3.3447864055633545,
      "learning_rate": 0.000192,
      "loss": 1.257,
      "step": 100
    },
    {
      "epoch": 0.16108452950558214,
      "grad_norm": 8.706202507019043,
      "learning_rate": 0.000194,
      "loss": 2.0047,
      "step": 101
    },
    {
      "epoch": 0.16267942583732056,
      "grad_norm": 17.863378524780273,
      "learning_rate": 0.000196,
      "loss": 2.421,
      "step": 102
    },
    {
      "epoch": 0.16427432216905902,
      "grad_norm": 5.376917362213135,
      "learning_rate": 0.00019800000000000002,
      "loss": 2.1448,
      "step": 103
    },
    {
      "epoch": 0.16586921850079744,
      "grad_norm": 3.9824860095977783,
      "learning_rate": 0.0002,
      "loss": 1.7987,
      "step": 104
    },
    {
      "epoch": 0.1674641148325359,
      "grad_norm": 6.7771382331848145,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.8173,
      "step": 105
    },
    {
      "epoch": 0.16905901116427433,
      "grad_norm": 6.204737186431885,
      "learning_rate": 0.000196,
      "loss": 1.2615,
      "step": 106
    },
    {
      "epoch": 0.17065390749601275,
      "grad_norm": 5.108335018157959,
      "learning_rate": 0.000194,
      "loss": 1.6966,
      "step": 107
    },
    {
      "epoch": 0.1722488038277512,
      "grad_norm": 51.948585510253906,
      "learning_rate": 0.000192,
      "loss": 2.8226,
      "step": 108
    },
    {
      "epoch": 0.17384370015948963,
      "grad_norm": 3.510647773742676,
      "learning_rate": 0.00019,
      "loss": 1.4454,
      "step": 109
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 5.786037921905518,
      "learning_rate": 0.000188,
      "loss": 1.3979,
      "step": 110
    },
    {
      "epoch": 0.17703349282296652,
      "grad_norm": 5.4267964363098145,
      "learning_rate": 0.00018600000000000002,
      "loss": 1.8775,
      "step": 111
    },
    {
      "epoch": 0.17862838915470494,
      "grad_norm": 7.448083400726318,
      "learning_rate": 0.00018400000000000003,
      "loss": 1.8377,
      "step": 112
    },
    {
      "epoch": 0.18022328548644337,
      "grad_norm": 6.855521202087402,
      "learning_rate": 0.000182,
      "loss": 1.7079,
      "step": 113
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 6.257575988769531,
      "learning_rate": 0.00018,
      "loss": 2.2364,
      "step": 114
    },
    {
      "epoch": 0.18341307814992025,
      "grad_norm": 15.47193431854248,
      "learning_rate": 0.00017800000000000002,
      "loss": 1.7272,
      "step": 115
    },
    {
      "epoch": 0.1850079744816587,
      "grad_norm": 12.51389217376709,
      "learning_rate": 0.00017600000000000002,
      "loss": 1.8385,
      "step": 116
    },
    {
      "epoch": 0.18660287081339713,
      "grad_norm": 8.150806427001953,
      "learning_rate": 0.000174,
      "loss": 2.429,
      "step": 117
    },
    {
      "epoch": 0.18819776714513556,
      "grad_norm": 29.065210342407227,
      "learning_rate": 0.000172,
      "loss": 1.3318,
      "step": 118
    },
    {
      "epoch": 0.189792663476874,
      "grad_norm": 5.457766532897949,
      "learning_rate": 0.00017,
      "loss": 1.2329,
      "step": 119
    },
    {
      "epoch": 0.19138755980861244,
      "grad_norm": 3.7080814838409424,
      "learning_rate": 0.000168,
      "loss": 1.1145,
      "step": 120
    },
    {
      "epoch": 0.19298245614035087,
      "grad_norm": 5.2060065269470215,
      "learning_rate": 0.000166,
      "loss": 1.6808,
      "step": 121
    },
    {
      "epoch": 0.19457735247208932,
      "grad_norm": 15.03097152709961,
      "learning_rate": 0.000164,
      "loss": 2.207,
      "step": 122
    },
    {
      "epoch": 0.19617224880382775,
      "grad_norm": 3.1523945331573486,
      "learning_rate": 0.000162,
      "loss": 0.8121,
      "step": 123
    },
    {
      "epoch": 0.19776714513556617,
      "grad_norm": 12.531198501586914,
      "learning_rate": 0.00016,
      "loss": 1.6493,
      "step": 124
    },
    {
      "epoch": 0.19936204146730463,
      "grad_norm": 18.13838768005371,
      "learning_rate": 0.00015800000000000002,
      "loss": 1.9895,
      "step": 125
    },
    {
      "epoch": 0.20095693779904306,
      "grad_norm": 3.7068324089050293,
      "learning_rate": 0.00015600000000000002,
      "loss": 1.2397,
      "step": 126
    },
    {
      "epoch": 0.2025518341307815,
      "grad_norm": 3.565275192260742,
      "learning_rate": 0.000154,
      "loss": 1.1711,
      "step": 127
    },
    {
      "epoch": 0.20414673046251994,
      "grad_norm": 2.20239520072937,
      "learning_rate": 0.000152,
      "loss": 1.8436,
      "step": 128
    },
    {
      "epoch": 0.20574162679425836,
      "grad_norm": 3.103001117706299,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.0085,
      "step": 129
    },
    {
      "epoch": 0.20733652312599682,
      "grad_norm": 3.8708302974700928,
      "learning_rate": 0.000148,
      "loss": 1.0336,
      "step": 130
    },
    {
      "epoch": 0.20893141945773525,
      "grad_norm": 4.008622646331787,
      "learning_rate": 0.000146,
      "loss": 1.7669,
      "step": 131
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 3.847217559814453,
      "learning_rate": 0.000144,
      "loss": 1.5163,
      "step": 132
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 9.75152587890625,
      "learning_rate": 0.000142,
      "loss": 2.3286,
      "step": 133
    },
    {
      "epoch": 0.21371610845295055,
      "grad_norm": 9.416215896606445,
      "learning_rate": 0.00014,
      "loss": 2.0397,
      "step": 134
    },
    {
      "epoch": 0.215311004784689,
      "grad_norm": 8.208052635192871,
      "learning_rate": 0.000138,
      "loss": 1.7927,
      "step": 135
    },
    {
      "epoch": 0.21690590111642744,
      "grad_norm": 11.827594757080078,
      "learning_rate": 0.00013600000000000003,
      "loss": 2.1958,
      "step": 136
    },
    {
      "epoch": 0.21850079744816586,
      "grad_norm": 5.788820266723633,
      "learning_rate": 0.000134,
      "loss": 1.8336,
      "step": 137
    },
    {
      "epoch": 0.22009569377990432,
      "grad_norm": 3.6653785705566406,
      "learning_rate": 0.000132,
      "loss": 1.0477,
      "step": 138
    },
    {
      "epoch": 0.22169059011164274,
      "grad_norm": 63.57593536376953,
      "learning_rate": 0.00013000000000000002,
      "loss": 1.5667,
      "step": 139
    },
    {
      "epoch": 0.22328548644338117,
      "grad_norm": 12.209519386291504,
      "learning_rate": 0.00012800000000000002,
      "loss": 1.6414,
      "step": 140
    },
    {
      "epoch": 0.22488038277511962,
      "grad_norm": 8.834230422973633,
      "learning_rate": 0.000126,
      "loss": 1.1292,
      "step": 141
    },
    {
      "epoch": 0.22647527910685805,
      "grad_norm": 3.4640305042266846,
      "learning_rate": 0.000124,
      "loss": 1.3858,
      "step": 142
    },
    {
      "epoch": 0.22807017543859648,
      "grad_norm": 5.367834091186523,
      "learning_rate": 0.000122,
      "loss": 1.4735,
      "step": 143
    },
    {
      "epoch": 0.22966507177033493,
      "grad_norm": 3.5475995540618896,
      "learning_rate": 0.00012,
      "loss": 1.8889,
      "step": 144
    },
    {
      "epoch": 0.23125996810207336,
      "grad_norm": 4.0117621421813965,
      "learning_rate": 0.000118,
      "loss": 0.6609,
      "step": 145
    },
    {
      "epoch": 0.23285486443381181,
      "grad_norm": 2.641918420791626,
      "learning_rate": 0.000116,
      "loss": 1.439,
      "step": 146
    },
    {
      "epoch": 0.23444976076555024,
      "grad_norm": 24.166297912597656,
      "learning_rate": 0.00011399999999999999,
      "loss": 1.5829,
      "step": 147
    },
    {
      "epoch": 0.23604465709728867,
      "grad_norm": 12.261051177978516,
      "learning_rate": 0.00011200000000000001,
      "loss": 2.6259,
      "step": 148
    },
    {
      "epoch": 0.23763955342902712,
      "grad_norm": 4.844594955444336,
      "learning_rate": 0.00011000000000000002,
      "loss": 2.2162,
      "step": 149
    },
    {
      "epoch": 0.23923444976076555,
      "grad_norm": 6.697972297668457,
      "learning_rate": 0.00010800000000000001,
      "loss": 2.7383,
      "step": 150
    },
    {
      "epoch": 0.24082934609250398,
      "grad_norm": 4.018860340118408,
      "learning_rate": 0.00010600000000000002,
      "loss": 2.4861,
      "step": 151
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 7.205791473388672,
      "learning_rate": 0.00010400000000000001,
      "loss": 1.4837,
      "step": 152
    },
    {
      "epoch": 0.24401913875598086,
      "grad_norm": 8.773712158203125,
      "learning_rate": 0.00010200000000000001,
      "loss": 1.6268,
      "step": 153
    },
    {
      "epoch": 0.24561403508771928,
      "grad_norm": 4.254454135894775,
      "learning_rate": 0.0001,
      "loss": 1.6405,
      "step": 154
    },
    {
      "epoch": 0.24720893141945774,
      "grad_norm": 4.130655288696289,
      "learning_rate": 9.8e-05,
      "loss": 0.9554,
      "step": 155
    },
    {
      "epoch": 0.24880382775119617,
      "grad_norm": 7.5216169357299805,
      "learning_rate": 9.6e-05,
      "loss": 1.3912,
      "step": 156
    },
    {
      "epoch": 0.2503987240829346,
      "grad_norm": 70.0249252319336,
      "learning_rate": 9.4e-05,
      "loss": 1.8041,
      "step": 157
    },
    {
      "epoch": 0.25199362041467305,
      "grad_norm": 3.9001526832580566,
      "learning_rate": 9.200000000000001e-05,
      "loss": 1.7109,
      "step": 158
    },
    {
      "epoch": 0.2535885167464115,
      "grad_norm": 5.0965094566345215,
      "learning_rate": 9e-05,
      "loss": 1.0314,
      "step": 159
    },
    {
      "epoch": 0.2551834130781499,
      "grad_norm": 3.0462706089019775,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.3541,
      "step": 160
    },
    {
      "epoch": 0.2567783094098884,
      "grad_norm": 2.8334619998931885,
      "learning_rate": 8.6e-05,
      "loss": 1.9827,
      "step": 161
    },
    {
      "epoch": 0.2583732057416268,
      "grad_norm": 5.991235256195068,
      "learning_rate": 8.4e-05,
      "loss": 1.4319,
      "step": 162
    },
    {
      "epoch": 0.25996810207336524,
      "grad_norm": 6.401395320892334,
      "learning_rate": 8.2e-05,
      "loss": 1.912,
      "step": 163
    },
    {
      "epoch": 0.26156299840510366,
      "grad_norm": 3.0269479751586914,
      "learning_rate": 8e-05,
      "loss": 1.5637,
      "step": 164
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 10.380670547485352,
      "learning_rate": 7.800000000000001e-05,
      "loss": 1.8585,
      "step": 165
    },
    {
      "epoch": 0.2647527910685805,
      "grad_norm": 7.375792503356934,
      "learning_rate": 7.6e-05,
      "loss": 1.8773,
      "step": 166
    },
    {
      "epoch": 0.266347687400319,
      "grad_norm": 3.75229811668396,
      "learning_rate": 7.4e-05,
      "loss": 1.9936,
      "step": 167
    },
    {
      "epoch": 0.2679425837320574,
      "grad_norm": 4.587918281555176,
      "learning_rate": 7.2e-05,
      "loss": 1.0402,
      "step": 168
    },
    {
      "epoch": 0.26953748006379585,
      "grad_norm": 4.558103561401367,
      "learning_rate": 7e-05,
      "loss": 2.0408,
      "step": 169
    },
    {
      "epoch": 0.2711323763955343,
      "grad_norm": 6.410488605499268,
      "learning_rate": 6.800000000000001e-05,
      "loss": 1.448,
      "step": 170
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 9.21990966796875,
      "learning_rate": 6.6e-05,
      "loss": 0.963,
      "step": 171
    },
    {
      "epoch": 0.2743221690590112,
      "grad_norm": 10.446578025817871,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.4381,
      "step": 172
    },
    {
      "epoch": 0.2759170653907496,
      "grad_norm": 13.717737197875977,
      "learning_rate": 6.2e-05,
      "loss": 1.2965,
      "step": 173
    },
    {
      "epoch": 0.27751196172248804,
      "grad_norm": 36.117401123046875,
      "learning_rate": 6e-05,
      "loss": 1.2144,
      "step": 174
    },
    {
      "epoch": 0.27910685805422647,
      "grad_norm": 8.741774559020996,
      "learning_rate": 5.8e-05,
      "loss": 1.5059,
      "step": 175
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 3.040428400039673,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.4881,
      "step": 176
    },
    {
      "epoch": 0.2822966507177033,
      "grad_norm": 7.401648044586182,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.7462,
      "step": 177
    },
    {
      "epoch": 0.2838915470494418,
      "grad_norm": 3.3486616611480713,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.8773,
      "step": 178
    },
    {
      "epoch": 0.28548644338118023,
      "grad_norm": 9.647512435913086,
      "learning_rate": 5e-05,
      "loss": 1.3147,
      "step": 179
    },
    {
      "epoch": 0.28708133971291866,
      "grad_norm": 4.068251132965088,
      "learning_rate": 4.8e-05,
      "loss": 1.4796,
      "step": 180
    },
    {
      "epoch": 0.2886762360446571,
      "grad_norm": 5.119231700897217,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.2465,
      "step": 181
    },
    {
      "epoch": 0.2902711323763955,
      "grad_norm": 11.434249877929688,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.0839,
      "step": 182
    },
    {
      "epoch": 0.291866028708134,
      "grad_norm": 2.6633126735687256,
      "learning_rate": 4.2e-05,
      "loss": 1.1653,
      "step": 183
    },
    {
      "epoch": 0.2934609250398724,
      "grad_norm": 8.366178512573242,
      "learning_rate": 4e-05,
      "loss": 1.8623,
      "step": 184
    },
    {
      "epoch": 0.29505582137161085,
      "grad_norm": 13.434002876281738,
      "learning_rate": 3.8e-05,
      "loss": 1.4409,
      "step": 185
    },
    {
      "epoch": 0.2966507177033493,
      "grad_norm": 3.535421371459961,
      "learning_rate": 3.6e-05,
      "loss": 1.2367,
      "step": 186
    },
    {
      "epoch": 0.2982456140350877,
      "grad_norm": 5.332886219024658,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.4744,
      "step": 187
    },
    {
      "epoch": 0.29984051036682613,
      "grad_norm": 3.7560222148895264,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.3489,
      "step": 188
    },
    {
      "epoch": 0.3014354066985646,
      "grad_norm": 4.513449668884277,
      "learning_rate": 3e-05,
      "loss": 1.3738,
      "step": 189
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 7.969113826751709,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.7352,
      "step": 190
    },
    {
      "epoch": 0.30462519936204147,
      "grad_norm": 4.11577033996582,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.6171,
      "step": 191
    },
    {
      "epoch": 0.3062200956937799,
      "grad_norm": 4.727830410003662,
      "learning_rate": 2.4e-05,
      "loss": 1.3359,
      "step": 192
    },
    {
      "epoch": 0.3078149920255183,
      "grad_norm": 1.7988307476043701,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.834,
      "step": 193
    },
    {
      "epoch": 0.3094098883572568,
      "grad_norm": 4.455323696136475,
      "learning_rate": 2e-05,
      "loss": 1.2367,
      "step": 194
    },
    {
      "epoch": 0.31100478468899523,
      "grad_norm": 5.334070682525635,
      "learning_rate": 1.8e-05,
      "loss": 1.0581,
      "step": 195
    },
    {
      "epoch": 0.31259968102073366,
      "grad_norm": 4.967501640319824,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.2129,
      "step": 196
    },
    {
      "epoch": 0.3141945773524721,
      "grad_norm": 4.0120673179626465,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 1.2043,
      "step": 197
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 4.491064548492432,
      "learning_rate": 1.2e-05,
      "loss": 1.3383,
      "step": 198
    },
    {
      "epoch": 0.31738437001594894,
      "grad_norm": 3.6377949714660645,
      "learning_rate": 1e-05,
      "loss": 1.2878,
      "step": 199
    },
    {
      "epoch": 0.3189792663476874,
      "grad_norm": 3.7990877628326416,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.7178,
      "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": 1717079281606656.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}