{
  "best_metric": 1.5421338081359863,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.09195402298850575,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006130268199233716,
      "grad_norm": 0.17289596796035767,
      "learning_rate": 5e-06,
      "loss": 1.8171,
      "step": 1
    },
    {
      "epoch": 0.0006130268199233716,
      "eval_loss": 2.339916467666626,
      "eval_runtime": 74.4463,
      "eval_samples_per_second": 36.899,
      "eval_steps_per_second": 18.456,
      "step": 1
    },
    {
      "epoch": 0.0012260536398467432,
      "grad_norm": 0.058519624173641205,
      "learning_rate": 1e-05,
      "loss": 0.9023,
      "step": 2
    },
    {
      "epoch": 0.0018390804597701149,
      "grad_norm": 0.08261319249868393,
      "learning_rate": 1.5e-05,
      "loss": 1.2611,
      "step": 3
    },
    {
      "epoch": 0.0024521072796934865,
      "grad_norm": 0.1186806932091713,
      "learning_rate": 2e-05,
      "loss": 1.645,
      "step": 4
    },
    {
      "epoch": 0.0030651340996168583,
      "grad_norm": 0.11762425303459167,
      "learning_rate": 2.5e-05,
      "loss": 1.7999,
      "step": 5
    },
    {
      "epoch": 0.0036781609195402297,
      "grad_norm": 0.11499951779842377,
      "learning_rate": 3e-05,
      "loss": 1.746,
      "step": 6
    },
    {
      "epoch": 0.004291187739463602,
      "grad_norm": 0.10910952836275101,
      "learning_rate": 3.5e-05,
      "loss": 1.7095,
      "step": 7
    },
    {
      "epoch": 0.004904214559386973,
      "grad_norm": 0.123331218957901,
      "learning_rate": 4e-05,
      "loss": 1.6834,
      "step": 8
    },
    {
      "epoch": 0.005517241379310344,
      "grad_norm": 0.10685678571462631,
      "learning_rate": 4.5e-05,
      "loss": 1.4608,
      "step": 9
    },
    {
      "epoch": 0.006130268199233717,
      "grad_norm": 0.10967013984918594,
      "learning_rate": 5e-05,
      "loss": 1.7669,
      "step": 10
    },
    {
      "epoch": 0.006743295019157088,
      "grad_norm": 0.1072850227355957,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.5836,
      "step": 11
    },
    {
      "epoch": 0.0073563218390804595,
      "grad_norm": 0.10261864215135574,
      "learning_rate": 6e-05,
      "loss": 1.4728,
      "step": 12
    },
    {
      "epoch": 0.007969348659003832,
      "grad_norm": 0.08355890959501266,
      "learning_rate": 6.500000000000001e-05,
      "loss": 1.4394,
      "step": 13
    },
    {
      "epoch": 0.008582375478927203,
      "grad_norm": 0.08112658560276031,
      "learning_rate": 7e-05,
      "loss": 1.4492,
      "step": 14
    },
    {
      "epoch": 0.009195402298850575,
      "grad_norm": 0.08554258942604065,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.388,
      "step": 15
    },
    {
      "epoch": 0.009808429118773946,
      "grad_norm": 0.09159933030605316,
      "learning_rate": 8e-05,
      "loss": 1.3965,
      "step": 16
    },
    {
      "epoch": 0.010421455938697317,
      "grad_norm": 0.09648030996322632,
      "learning_rate": 8.5e-05,
      "loss": 1.5107,
      "step": 17
    },
    {
      "epoch": 0.011034482758620689,
      "grad_norm": 0.09597115963697433,
      "learning_rate": 9e-05,
      "loss": 1.5881,
      "step": 18
    },
    {
      "epoch": 0.011647509578544062,
      "grad_norm": 0.09753213822841644,
      "learning_rate": 9.5e-05,
      "loss": 1.3361,
      "step": 19
    },
    {
      "epoch": 0.012260536398467433,
      "grad_norm": 0.11020773649215698,
      "learning_rate": 0.0001,
      "loss": 1.6518,
      "step": 20
    },
    {
      "epoch": 0.012873563218390805,
      "grad_norm": 0.10357560962438583,
      "learning_rate": 9.999238475781957e-05,
      "loss": 1.5862,
      "step": 21
    },
    {
      "epoch": 0.013486590038314176,
      "grad_norm": 0.1024681031703949,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.4718,
      "step": 22
    },
    {
      "epoch": 0.014099616858237548,
      "grad_norm": 0.10770165175199509,
      "learning_rate": 9.99314767377287e-05,
      "loss": 1.6456,
      "step": 23
    },
    {
      "epoch": 0.014712643678160919,
      "grad_norm": 0.1296290159225464,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.717,
      "step": 24
    },
    {
      "epoch": 0.01532567049808429,
      "grad_norm": 0.1460258811712265,
      "learning_rate": 9.980973490458728e-05,
      "loss": 1.9824,
      "step": 25
    },
    {
      "epoch": 0.015938697318007664,
      "grad_norm": 0.15795955061912537,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.5489,
      "step": 26
    },
    {
      "epoch": 0.016551724137931035,
      "grad_norm": 0.21399016678333282,
      "learning_rate": 9.962730758206611e-05,
      "loss": 1.2289,
      "step": 27
    },
    {
      "epoch": 0.017164750957854406,
      "grad_norm": 0.22215089201927185,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.3147,
      "step": 28
    },
    {
      "epoch": 0.017777777777777778,
      "grad_norm": 0.1800062209367752,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.1963,
      "step": 29
    },
    {
      "epoch": 0.01839080459770115,
      "grad_norm": 0.19618059694766998,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.2904,
      "step": 30
    },
    {
      "epoch": 0.01900383141762452,
      "grad_norm": 0.1645231992006302,
      "learning_rate": 9.908135917238321e-05,
      "loss": 1.3781,
      "step": 31
    },
    {
      "epoch": 0.019616858237547892,
      "grad_norm": 0.17551617324352264,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.3299,
      "step": 32
    },
    {
      "epoch": 0.020229885057471263,
      "grad_norm": 0.2577083110809326,
      "learning_rate": 9.871850323926177e-05,
      "loss": 1.991,
      "step": 33
    },
    {
      "epoch": 0.020842911877394635,
      "grad_norm": 0.29903480410575867,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.9645,
      "step": 34
    },
    {
      "epoch": 0.021455938697318006,
      "grad_norm": 0.4471134543418884,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.487,
      "step": 35
    },
    {
      "epoch": 0.022068965517241378,
      "grad_norm": 0.6420058012008667,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.4972,
      "step": 36
    },
    {
      "epoch": 0.022681992337164752,
      "grad_norm": 1.0783333778381348,
      "learning_rate": 9.781523779815179e-05,
      "loss": 3.4046,
      "step": 37
    },
    {
      "epoch": 0.023295019157088124,
      "grad_norm": 1.2736737728118896,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.3084,
      "step": 38
    },
    {
      "epoch": 0.023908045977011495,
      "grad_norm": 1.7105984687805176,
      "learning_rate": 9.727592877996585e-05,
      "loss": 3.6723,
      "step": 39
    },
    {
      "epoch": 0.024521072796934867,
      "grad_norm": 1.3899215459823608,
      "learning_rate": 9.698463103929542e-05,
      "loss": 3.2683,
      "step": 40
    },
    {
      "epoch": 0.025134099616858238,
      "grad_norm": 1.1415343284606934,
      "learning_rate": 9.667902132486009e-05,
      "loss": 2.9337,
      "step": 41
    },
    {
      "epoch": 0.02574712643678161,
      "grad_norm": 0.9152843952178955,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.7092,
      "step": 42
    },
    {
      "epoch": 0.02636015325670498,
      "grad_norm": 0.9794624447822571,
      "learning_rate": 9.602524267262203e-05,
      "loss": 2.6276,
      "step": 43
    },
    {
      "epoch": 0.026973180076628352,
      "grad_norm": 0.8603305816650391,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.791,
      "step": 44
    },
    {
      "epoch": 0.027586206896551724,
      "grad_norm": 0.8797575235366821,
      "learning_rate": 9.53153893518325e-05,
      "loss": 2.4874,
      "step": 45
    },
    {
      "epoch": 0.028199233716475095,
      "grad_norm": 0.9300112128257751,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.5845,
      "step": 46
    },
    {
      "epoch": 0.028812260536398467,
      "grad_norm": 0.7892826199531555,
      "learning_rate": 9.45503262094184e-05,
      "loss": 2.4241,
      "step": 47
    },
    {
      "epoch": 0.029425287356321838,
      "grad_norm": 0.7370955348014832,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.2909,
      "step": 48
    },
    {
      "epoch": 0.03003831417624521,
      "grad_norm": 0.8173626661300659,
      "learning_rate": 9.373098535696979e-05,
      "loss": 2.1401,
      "step": 49
    },
    {
      "epoch": 0.03065134099616858,
      "grad_norm": 0.8697667121887207,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.6397,
      "step": 50
    },
    {
      "epoch": 0.03065134099616858,
      "eval_loss": 1.7929205894470215,
      "eval_runtime": 74.4254,
      "eval_samples_per_second": 36.909,
      "eval_steps_per_second": 18.461,
      "step": 50
    },
    {
      "epoch": 0.03126436781609195,
      "grad_norm": 0.6367409229278564,
      "learning_rate": 9.285836503510562e-05,
      "loss": 1.7935,
      "step": 51
    },
    {
      "epoch": 0.03187739463601533,
      "grad_norm": 0.48403412103652954,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.05,
      "step": 52
    },
    {
      "epoch": 0.032490421455938695,
      "grad_norm": 0.46549126505851746,
      "learning_rate": 9.193352839727121e-05,
      "loss": 1.2293,
      "step": 53
    },
    {
      "epoch": 0.03310344827586207,
      "grad_norm": 0.4837709963321686,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.7603,
      "step": 54
    },
    {
      "epoch": 0.03371647509578544,
      "grad_norm": 0.4642130732536316,
      "learning_rate": 9.09576022144496e-05,
      "loss": 1.7952,
      "step": 55
    },
    {
      "epoch": 0.03432950191570881,
      "grad_norm": 0.41608160734176636,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.6661,
      "step": 56
    },
    {
      "epoch": 0.03494252873563218,
      "grad_norm": 0.36912795901298523,
      "learning_rate": 8.993177550236464e-05,
      "loss": 1.6477,
      "step": 57
    },
    {
      "epoch": 0.035555555555555556,
      "grad_norm": 0.3234642744064331,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.6537,
      "step": 58
    },
    {
      "epoch": 0.03616858237547893,
      "grad_norm": 0.340728759765625,
      "learning_rate": 8.885729807284856e-05,
      "loss": 1.7341,
      "step": 59
    },
    {
      "epoch": 0.0367816091954023,
      "grad_norm": 0.2520364224910736,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.6634,
      "step": 60
    },
    {
      "epoch": 0.03739463601532567,
      "grad_norm": 0.2261764407157898,
      "learning_rate": 8.773547901113862e-05,
      "loss": 1.6671,
      "step": 61
    },
    {
      "epoch": 0.03800766283524904,
      "grad_norm": 0.21776960790157318,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.4119,
      "step": 62
    },
    {
      "epoch": 0.038620689655172416,
      "grad_norm": 0.23141559958457947,
      "learning_rate": 8.656768508095853e-05,
      "loss": 1.48,
      "step": 63
    },
    {
      "epoch": 0.039233716475095784,
      "grad_norm": 0.17701898515224457,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.6919,
      "step": 64
    },
    {
      "epoch": 0.03984674329501916,
      "grad_norm": 0.1852775365114212,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.4419,
      "step": 65
    },
    {
      "epoch": 0.04045977011494253,
      "grad_norm": 0.1668386608362198,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.4815,
      "step": 66
    },
    {
      "epoch": 0.0410727969348659,
      "grad_norm": 0.15108704566955566,
      "learning_rate": 8.409991800312493e-05,
      "loss": 1.4889,
      "step": 67
    },
    {
      "epoch": 0.04168582375478927,
      "grad_norm": 0.1600823700428009,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.5095,
      "step": 68
    },
    {
      "epoch": 0.042298850574712644,
      "grad_norm": 0.1606740802526474,
      "learning_rate": 8.280295144952536e-05,
      "loss": 1.4785,
      "step": 69
    },
    {
      "epoch": 0.04291187739463601,
      "grad_norm": 0.1646360158920288,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.4643,
      "step": 70
    },
    {
      "epoch": 0.04352490421455939,
      "grad_norm": 0.15829920768737793,
      "learning_rate": 8.146601955249188e-05,
      "loss": 1.5892,
      "step": 71
    },
    {
      "epoch": 0.044137931034482755,
      "grad_norm": 0.14968441426753998,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.471,
      "step": 72
    },
    {
      "epoch": 0.04475095785440613,
      "grad_norm": 0.13142406940460205,
      "learning_rate": 8.009075115760243e-05,
      "loss": 1.7743,
      "step": 73
    },
    {
      "epoch": 0.045363984674329505,
      "grad_norm": 0.1225341409444809,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.6447,
      "step": 74
    },
    {
      "epoch": 0.04597701149425287,
      "grad_norm": 0.165053129196167,
      "learning_rate": 7.86788218175523e-05,
      "loss": 1.3039,
      "step": 75
    },
    {
      "epoch": 0.04659003831417625,
      "grad_norm": 0.15040135383605957,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.2503,
      "step": 76
    },
    {
      "epoch": 0.047203065134099616,
      "grad_norm": 0.18488284945487976,
      "learning_rate": 7.723195175075136e-05,
      "loss": 1.1981,
      "step": 77
    },
    {
      "epoch": 0.04781609195402299,
      "grad_norm": 0.24201402068138123,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.098,
      "step": 78
    },
    {
      "epoch": 0.04842911877394636,
      "grad_norm": 0.21280105412006378,
      "learning_rate": 7.575190374550272e-05,
      "loss": 0.9585,
      "step": 79
    },
    {
      "epoch": 0.04904214559386973,
      "grad_norm": 0.1866258680820465,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8873,
      "step": 80
    },
    {
      "epoch": 0.0496551724137931,
      "grad_norm": 0.17641842365264893,
      "learning_rate": 7.424048101231686e-05,
      "loss": 1.062,
      "step": 81
    },
    {
      "epoch": 0.050268199233716476,
      "grad_norm": 0.17714175581932068,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.3293,
      "step": 82
    },
    {
      "epoch": 0.050881226053639844,
      "grad_norm": 0.2036144733428955,
      "learning_rate": 7.269952498697734e-05,
      "loss": 1.2956,
      "step": 83
    },
    {
      "epoch": 0.05149425287356322,
      "grad_norm": 0.259493887424469,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.9294,
      "step": 84
    },
    {
      "epoch": 0.05210727969348659,
      "grad_norm": 0.4458560049533844,
      "learning_rate": 7.113091308703498e-05,
      "loss": 2.2645,
      "step": 85
    },
    {
      "epoch": 0.05272030651340996,
      "grad_norm": 0.5572463870048523,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.3613,
      "step": 86
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 0.8086560368537903,
      "learning_rate": 6.953655642446368e-05,
      "loss": 2.4958,
      "step": 87
    },
    {
      "epoch": 0.053946360153256705,
      "grad_norm": 1.1325173377990723,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.465,
      "step": 88
    },
    {
      "epoch": 0.05455938697318008,
      "grad_norm": 1.07203209400177,
      "learning_rate": 6.7918397477265e-05,
      "loss": 2.0465,
      "step": 89
    },
    {
      "epoch": 0.05517241379310345,
      "grad_norm": 1.051229476928711,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.3145,
      "step": 90
    },
    {
      "epoch": 0.05578544061302682,
      "grad_norm": 0.9420087337493896,
      "learning_rate": 6.627840772285784e-05,
      "loss": 1.9357,
      "step": 91
    },
    {
      "epoch": 0.05639846743295019,
      "grad_norm": 0.754643976688385,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.0068,
      "step": 92
    },
    {
      "epoch": 0.057011494252873565,
      "grad_norm": 0.5955482125282288,
      "learning_rate": 6.461858523613684e-05,
      "loss": 1.8173,
      "step": 93
    },
    {
      "epoch": 0.05762452107279693,
      "grad_norm": 0.5796248316764832,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.7837,
      "step": 94
    },
    {
      "epoch": 0.05823754789272031,
      "grad_norm": 0.5394419431686401,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.8448,
      "step": 95
    },
    {
      "epoch": 0.058850574712643676,
      "grad_norm": 0.5442178845405579,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.8558,
      "step": 96
    },
    {
      "epoch": 0.05946360153256705,
      "grad_norm": 0.5913978815078735,
      "learning_rate": 6.124755271719325e-05,
      "loss": 2.1927,
      "step": 97
    },
    {
      "epoch": 0.06007662835249042,
      "grad_norm": 0.5335270166397095,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.8903,
      "step": 98
    },
    {
      "epoch": 0.060689655172413794,
      "grad_norm": 0.5326647162437439,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 1.9073,
      "step": 99
    },
    {
      "epoch": 0.06130268199233716,
      "grad_norm": 0.7210387587547302,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.0738,
      "step": 100
    },
    {
      "epoch": 0.06130268199233716,
      "eval_loss": 1.572197675704956,
      "eval_runtime": 74.7637,
      "eval_samples_per_second": 36.742,
      "eval_steps_per_second": 18.378,
      "step": 100
    },
    {
      "epoch": 0.061915708812260536,
      "grad_norm": 0.1132245659828186,
      "learning_rate": 5.782172325201155e-05,
      "loss": 1.3557,
      "step": 101
    },
    {
      "epoch": 0.0625287356321839,
      "grad_norm": 0.07461534440517426,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.0772,
      "step": 102
    },
    {
      "epoch": 0.06314176245210729,
      "grad_norm": 0.07867616415023804,
      "learning_rate": 5.6093467170257374e-05,
      "loss": 1.3892,
      "step": 103
    },
    {
      "epoch": 0.06375478927203065,
      "grad_norm": 0.09777732938528061,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.8411,
      "step": 104
    },
    {
      "epoch": 0.06436781609195402,
      "grad_norm": 0.08006682246923447,
      "learning_rate": 5.435778713738292e-05,
      "loss": 1.6501,
      "step": 105
    },
    {
      "epoch": 0.06498084291187739,
      "grad_norm": 0.07599913328886032,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.467,
      "step": 106
    },
    {
      "epoch": 0.06559386973180077,
      "grad_norm": 0.08920009434223175,
      "learning_rate": 5.26167978121472e-05,
      "loss": 1.6078,
      "step": 107
    },
    {
      "epoch": 0.06620689655172414,
      "grad_norm": 0.09269789606332779,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.7445,
      "step": 108
    },
    {
      "epoch": 0.06681992337164751,
      "grad_norm": 0.09162865579128265,
      "learning_rate": 5.0872620321864185e-05,
      "loss": 1.6445,
      "step": 109
    },
    {
      "epoch": 0.06743295019157088,
      "grad_norm": 0.08545801043510437,
      "learning_rate": 5e-05,
      "loss": 1.5821,
      "step": 110
    },
    {
      "epoch": 0.06804597701149426,
      "grad_norm": 0.0838240310549736,
      "learning_rate": 4.912737967813583e-05,
      "loss": 1.4377,
      "step": 111
    },
    {
      "epoch": 0.06865900383141763,
      "grad_norm": 0.08086847513914108,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.3009,
      "step": 112
    },
    {
      "epoch": 0.069272030651341,
      "grad_norm": 0.08265014737844467,
      "learning_rate": 4.738320218785281e-05,
      "loss": 1.5102,
      "step": 113
    },
    {
      "epoch": 0.06988505747126436,
      "grad_norm": 0.0930614322423935,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.3524,
      "step": 114
    },
    {
      "epoch": 0.07049808429118774,
      "grad_norm": 0.08706307411193848,
      "learning_rate": 4.564221286261709e-05,
      "loss": 1.3235,
      "step": 115
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 0.09725669771432877,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.4341,
      "step": 116
    },
    {
      "epoch": 0.07172413793103448,
      "grad_norm": 0.09511318802833557,
      "learning_rate": 4.390653282974264e-05,
      "loss": 1.4604,
      "step": 117
    },
    {
      "epoch": 0.07233716475095786,
      "grad_norm": 0.09910958260297775,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.4396,
      "step": 118
    },
    {
      "epoch": 0.07295019157088123,
      "grad_norm": 0.09691473841667175,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 1.517,
      "step": 119
    },
    {
      "epoch": 0.0735632183908046,
      "grad_norm": 0.09580690413713455,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.2088,
      "step": 120
    },
    {
      "epoch": 0.07417624521072796,
      "grad_norm": 0.10472910851240158,
      "learning_rate": 4.045955023117276e-05,
      "loss": 1.3511,
      "step": 121
    },
    {
      "epoch": 0.07478927203065135,
      "grad_norm": 0.12191334366798401,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.5134,
      "step": 122
    },
    {
      "epoch": 0.07540229885057471,
      "grad_norm": 0.10315406322479248,
      "learning_rate": 3.875244728280676e-05,
      "loss": 1.6778,
      "step": 123
    },
    {
      "epoch": 0.07601532567049808,
      "grad_norm": 0.1264035552740097,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.5658,
      "step": 124
    },
    {
      "epoch": 0.07662835249042145,
      "grad_norm": 0.12428142875432968,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.5274,
      "step": 125
    },
    {
      "epoch": 0.07724137931034483,
      "grad_norm": 0.1304025799036026,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.3947,
      "step": 126
    },
    {
      "epoch": 0.0778544061302682,
      "grad_norm": 0.19629023969173431,
      "learning_rate": 3.5381414763863166e-05,
      "loss": 1.1697,
      "step": 127
    },
    {
      "epoch": 0.07846743295019157,
      "grad_norm": 0.2593744993209839,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.1842,
      "step": 128
    },
    {
      "epoch": 0.07908045977011494,
      "grad_norm": 0.23157721757888794,
      "learning_rate": 3.372159227714218e-05,
      "loss": 1.0612,
      "step": 129
    },
    {
      "epoch": 0.07969348659003832,
      "grad_norm": 0.19564573466777802,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.0819,
      "step": 130
    },
    {
      "epoch": 0.08030651340996169,
      "grad_norm": 0.19280073046684265,
      "learning_rate": 3.2081602522734986e-05,
      "loss": 0.9014,
      "step": 131
    },
    {
      "epoch": 0.08091954022988505,
      "grad_norm": 0.18969839811325073,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.1679,
      "step": 132
    },
    {
      "epoch": 0.08153256704980844,
      "grad_norm": 0.22113968431949615,
      "learning_rate": 3.046344357553632e-05,
      "loss": 1.2515,
      "step": 133
    },
    {
      "epoch": 0.0821455938697318,
      "grad_norm": 0.23892644047737122,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.5256,
      "step": 134
    },
    {
      "epoch": 0.08275862068965517,
      "grad_norm": 0.3479028344154358,
      "learning_rate": 2.886908691296504e-05,
      "loss": 1.6069,
      "step": 135
    },
    {
      "epoch": 0.08337164750957854,
      "grad_norm": 0.39232832193374634,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.1823,
      "step": 136
    },
    {
      "epoch": 0.08398467432950192,
      "grad_norm": 0.5148152112960815,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 2.0083,
      "step": 137
    },
    {
      "epoch": 0.08459770114942529,
      "grad_norm": 0.8431908488273621,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.4983,
      "step": 138
    },
    {
      "epoch": 0.08521072796934866,
      "grad_norm": 0.9909766912460327,
      "learning_rate": 2.575951898768315e-05,
      "loss": 2.102,
      "step": 139
    },
    {
      "epoch": 0.08582375478927202,
      "grad_norm": 0.7708740234375,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.2014,
      "step": 140
    },
    {
      "epoch": 0.0864367816091954,
      "grad_norm": 0.8488182425498962,
      "learning_rate": 2.4248096254497288e-05,
      "loss": 1.6694,
      "step": 141
    },
    {
      "epoch": 0.08704980842911877,
      "grad_norm": 0.5637829899787903,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.9671,
      "step": 142
    },
    {
      "epoch": 0.08766283524904214,
      "grad_norm": 0.6969783902168274,
      "learning_rate": 2.2768048249248648e-05,
      "loss": 1.8949,
      "step": 143
    },
    {
      "epoch": 0.08827586206896551,
      "grad_norm": 0.6564290523529053,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.8338,
      "step": 144
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.5121574997901917,
      "learning_rate": 2.132117818244771e-05,
      "loss": 1.7087,
      "step": 145
    },
    {
      "epoch": 0.08950191570881226,
      "grad_norm": 0.4818703830242157,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.8275,
      "step": 146
    },
    {
      "epoch": 0.09011494252873563,
      "grad_norm": 0.5253958702087402,
      "learning_rate": 1.9909248842397584e-05,
      "loss": 1.9628,
      "step": 147
    },
    {
      "epoch": 0.09072796934865901,
      "grad_norm": 0.47828158736228943,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.725,
      "step": 148
    },
    {
      "epoch": 0.09134099616858238,
      "grad_norm": 0.5862099528312683,
      "learning_rate": 1.8533980447508137e-05,
      "loss": 2.04,
      "step": 149
    },
    {
      "epoch": 0.09195402298850575,
      "grad_norm": 0.8157917261123657,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.0551,
      "step": 150
    },
    {
      "epoch": 0.09195402298850575,
      "eval_loss": 1.5421338081359863,
      "eval_runtime": 74.5479,
      "eval_samples_per_second": 36.849,
      "eval_steps_per_second": 18.431,
      "step": 150
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.129930684366848e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}