{
  "best_metric": 1.8051786422729492,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 3.0123456790123457,
  "eval_steps": 50,
  "global_step": 122,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024691358024691357,
      "grad_norm": 0.25252068042755127,
      "learning_rate": 1e-05,
      "loss": 2.0604,
      "step": 1
    },
    {
      "epoch": 0.024691358024691357,
      "eval_loss": 2.237061023712158,
      "eval_runtime": 1.21,
      "eval_samples_per_second": 57.023,
      "eval_steps_per_second": 14.876,
      "step": 1
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 0.31075847148895264,
      "learning_rate": 2e-05,
      "loss": 2.2158,
      "step": 2
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.38259977102279663,
      "learning_rate": 3e-05,
      "loss": 2.1454,
      "step": 3
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 0.35990017652511597,
      "learning_rate": 4e-05,
      "loss": 2.0522,
      "step": 4
    },
    {
      "epoch": 0.12345679012345678,
      "grad_norm": 0.4168837070465088,
      "learning_rate": 5e-05,
      "loss": 2.3263,
      "step": 5
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.469605028629303,
      "learning_rate": 6e-05,
      "loss": 2.2257,
      "step": 6
    },
    {
      "epoch": 0.1728395061728395,
      "grad_norm": 0.5073450207710266,
      "learning_rate": 7e-05,
      "loss": 2.3573,
      "step": 7
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.7278738021850586,
      "learning_rate": 8e-05,
      "loss": 2.4981,
      "step": 8
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.8480843305587769,
      "learning_rate": 9e-05,
      "loss": 2.4136,
      "step": 9
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 1.1377860307693481,
      "learning_rate": 0.0001,
      "loss": 2.6231,
      "step": 10
    },
    {
      "epoch": 0.2716049382716049,
      "grad_norm": 0.1992480605840683,
      "learning_rate": 9.998033131915266e-05,
      "loss": 2.125,
      "step": 11
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.21675321459770203,
      "learning_rate": 9.992134075089084e-05,
      "loss": 2.1632,
      "step": 12
    },
    {
      "epoch": 0.32098765432098764,
      "grad_norm": 0.2902778387069702,
      "learning_rate": 9.982307470588098e-05,
      "loss": 2.079,
      "step": 13
    },
    {
      "epoch": 0.345679012345679,
      "grad_norm": 0.2948603630065918,
      "learning_rate": 9.968561049466214e-05,
      "loss": 2.031,
      "step": 14
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.347444623708725,
      "learning_rate": 9.950905626682228e-05,
      "loss": 2.0397,
      "step": 15
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.4035986363887787,
      "learning_rate": 9.92935509259118e-05,
      "loss": 2.1259,
      "step": 16
    },
    {
      "epoch": 0.41975308641975306,
      "grad_norm": 0.4339040517807007,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.1056,
      "step": 17
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.5206056833267212,
      "learning_rate": 9.874639560909117e-05,
      "loss": 2.0121,
      "step": 18
    },
    {
      "epoch": 0.4691358024691358,
      "grad_norm": 0.719115674495697,
      "learning_rate": 9.841517610611309e-05,
      "loss": 2.1641,
      "step": 19
    },
    {
      "epoch": 0.49382716049382713,
      "grad_norm": 0.9554781317710876,
      "learning_rate": 9.804586609725499e-05,
      "loss": 2.112,
      "step": 20
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 0.2317459136247635,
      "learning_rate": 9.763875613614482e-05,
      "loss": 2.0239,
      "step": 21
    },
    {
      "epoch": 0.5432098765432098,
      "grad_norm": 0.3069552481174469,
      "learning_rate": 9.719416651541839e-05,
      "loss": 2.0365,
      "step": 22
    },
    {
      "epoch": 0.5679012345679012,
      "grad_norm": 0.34765249490737915,
      "learning_rate": 9.671244701472999e-05,
      "loss": 2.1446,
      "step": 23
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.37877699732780457,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.0267,
      "step": 24
    },
    {
      "epoch": 0.6172839506172839,
      "grad_norm": 0.4079001843929291,
      "learning_rate": 9.563916325306594e-05,
      "loss": 2.0075,
      "step": 25
    },
    {
      "epoch": 0.6419753086419753,
      "grad_norm": 0.3358095586299896,
      "learning_rate": 9.504844339512095e-05,
      "loss": 1.8691,
      "step": 26
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.4075435400009155,
      "learning_rate": 9.442228179894362e-05,
      "loss": 2.0415,
      "step": 27
    },
    {
      "epoch": 0.691358024691358,
      "grad_norm": 0.4543934762477875,
      "learning_rate": 9.376117109543769e-05,
      "loss": 1.9039,
      "step": 28
    },
    {
      "epoch": 0.7160493827160493,
      "grad_norm": 0.5283561944961548,
      "learning_rate": 9.306563141162046e-05,
      "loss": 1.8946,
      "step": 29
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.7076103687286377,
      "learning_rate": 9.233620996141421e-05,
      "loss": 1.5743,
      "step": 30
    },
    {
      "epoch": 0.7654320987654321,
      "grad_norm": 0.19869261980056763,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.9074,
      "step": 31
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.2551741302013397,
      "learning_rate": 9.077804344796302e-05,
      "loss": 1.9752,
      "step": 32
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 0.29231002926826477,
      "learning_rate": 8.995052426791247e-05,
      "loss": 2.0127,
      "step": 33
    },
    {
      "epoch": 0.8395061728395061,
      "grad_norm": 0.2705162465572357,
      "learning_rate": 8.90915741234015e-05,
      "loss": 1.8734,
      "step": 34
    },
    {
      "epoch": 0.8641975308641975,
      "grad_norm": 0.30582037568092346,
      "learning_rate": 8.820186879108038e-05,
      "loss": 1.7893,
      "step": 35
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.2692418694496155,
      "learning_rate": 8.728210824415827e-05,
      "loss": 1.897,
      "step": 36
    },
    {
      "epoch": 0.9135802469135802,
      "grad_norm": 0.3430037498474121,
      "learning_rate": 8.633301610170135e-05,
      "loss": 1.8172,
      "step": 37
    },
    {
      "epoch": 0.9382716049382716,
      "grad_norm": 0.3440125286579132,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.9525,
      "step": 38
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 0.46276724338531494,
      "learning_rate": 8.434984630174509e-05,
      "loss": 1.8196,
      "step": 39
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.7176722288131714,
      "learning_rate": 8.33173288976002e-05,
      "loss": 1.837,
      "step": 40
    },
    {
      "epoch": 1.0123456790123457,
      "grad_norm": 0.38161012530326843,
      "learning_rate": 8.225859917710439e-05,
      "loss": 3.0373,
      "step": 41
    },
    {
      "epoch": 1.037037037037037,
      "grad_norm": 0.16387499868869781,
      "learning_rate": 8.117449009293668e-05,
      "loss": 1.6453,
      "step": 42
    },
    {
      "epoch": 1.0617283950617284,
      "grad_norm": 0.24855704605579376,
      "learning_rate": 8.006585456492029e-05,
      "loss": 2.0729,
      "step": 43
    },
    {
      "epoch": 1.0864197530864197,
      "grad_norm": 0.2932082712650299,
      "learning_rate": 7.89335648089903e-05,
      "loss": 1.991,
      "step": 44
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.2368183583021164,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.6878,
      "step": 45
    },
    {
      "epoch": 1.1358024691358024,
      "grad_norm": 0.3216198682785034,
      "learning_rate": 7.660160382576683e-05,
      "loss": 2.1539,
      "step": 46
    },
    {
      "epoch": 1.1604938271604939,
      "grad_norm": 0.31032422184944153,
      "learning_rate": 7.540376726232648e-05,
      "loss": 1.784,
      "step": 47
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.3157343566417694,
      "learning_rate": 7.4185944355262e-05,
      "loss": 1.6648,
      "step": 48
    },
    {
      "epoch": 1.2098765432098766,
      "grad_norm": 0.4062681794166565,
      "learning_rate": 7.294909322337689e-05,
      "loss": 1.8114,
      "step": 49
    },
    {
      "epoch": 1.2345679012345678,
      "grad_norm": 0.5582627654075623,
      "learning_rate": 7.169418695587791e-05,
      "loss": 1.6857,
      "step": 50
    },
    {
      "epoch": 1.2345679012345678,
      "eval_loss": 1.8255712985992432,
      "eval_runtime": 1.2107,
      "eval_samples_per_second": 56.991,
      "eval_steps_per_second": 14.867,
      "step": 50
    },
    {
      "epoch": 1.2592592592592593,
      "grad_norm": 0.35165345668792725,
      "learning_rate": 7.042221284679982e-05,
      "loss": 1.7912,
      "step": 51
    },
    {
      "epoch": 1.2839506172839505,
      "grad_norm": 0.1966906636953354,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.8102,
      "step": 52
    },
    {
      "epoch": 1.308641975308642,
      "grad_norm": 0.24283820390701294,
      "learning_rate": 6.783107663311565e-05,
      "loss": 2.0686,
      "step": 53
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.21965524554252625,
      "learning_rate": 6.651395309775837e-05,
      "loss": 1.6701,
      "step": 54
    },
    {
      "epoch": 1.3580246913580247,
      "grad_norm": 0.25558704137802124,
      "learning_rate": 6.518383725548074e-05,
      "loss": 1.9965,
      "step": 55
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.24983792006969452,
      "learning_rate": 6.384177557124247e-05,
      "loss": 1.6517,
      "step": 56
    },
    {
      "epoch": 1.4074074074074074,
      "grad_norm": 0.27970802783966064,
      "learning_rate": 6.248882390836135e-05,
      "loss": 1.7792,
      "step": 57
    },
    {
      "epoch": 1.4320987654320987,
      "grad_norm": 0.3209986686706543,
      "learning_rate": 6.112604669781572e-05,
      "loss": 1.9831,
      "step": 58
    },
    {
      "epoch": 1.4567901234567902,
      "grad_norm": 0.3848767876625061,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.8107,
      "step": 59
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 0.5168919563293457,
      "learning_rate": 5.837531116523682e-05,
      "loss": 1.6918,
      "step": 60
    },
    {
      "epoch": 1.5061728395061729,
      "grad_norm": 0.45516857504844666,
      "learning_rate": 5.698951697677498e-05,
      "loss": 1.3992,
      "step": 61
    },
    {
      "epoch": 1.5308641975308643,
      "grad_norm": 0.2247449904680252,
      "learning_rate": 5.559822380516539e-05,
      "loss": 2.0824,
      "step": 62
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 0.23172587156295776,
      "learning_rate": 5.420252624646238e-05,
      "loss": 1.8623,
      "step": 63
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.23838010430335999,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 1.9431,
      "step": 64
    },
    {
      "epoch": 1.6049382716049383,
      "grad_norm": 0.25559642910957336,
      "learning_rate": 5.140231281379345e-05,
      "loss": 1.8672,
      "step": 65
    },
    {
      "epoch": 1.6296296296296298,
      "grad_norm": 0.2604578733444214,
      "learning_rate": 5e-05,
      "loss": 1.9074,
      "step": 66
    },
    {
      "epoch": 1.654320987654321,
      "grad_norm": 0.30712196230888367,
      "learning_rate": 4.859768718620656e-05,
      "loss": 1.8103,
      "step": 67
    },
    {
      "epoch": 1.6790123456790123,
      "grad_norm": 0.3221416175365448,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 1.7468,
      "step": 68
    },
    {
      "epoch": 1.7037037037037037,
      "grad_norm": 0.3665846586227417,
      "learning_rate": 4.579747375353763e-05,
      "loss": 1.6083,
      "step": 69
    },
    {
      "epoch": 1.7283950617283952,
      "grad_norm": 0.47580888867378235,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 1.7429,
      "step": 70
    },
    {
      "epoch": 1.7530864197530864,
      "grad_norm": 0.39478451013565063,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 1.6895,
      "step": 71
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.19653937220573425,
      "learning_rate": 4.162468883476319e-05,
      "loss": 1.8156,
      "step": 72
    },
    {
      "epoch": 1.8024691358024691,
      "grad_norm": 0.26667800545692444,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 2.1007,
      "step": 73
    },
    {
      "epoch": 1.8271604938271606,
      "grad_norm": 0.22694823145866394,
      "learning_rate": 3.887395330218429e-05,
      "loss": 1.6717,
      "step": 74
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 0.27870312333106995,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 1.9098,
      "step": 75
    },
    {
      "epoch": 1.876543209876543,
      "grad_norm": 0.24723252654075623,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 1.75,
      "step": 76
    },
    {
      "epoch": 1.9012345679012346,
      "grad_norm": 0.27670368552207947,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 1.8367,
      "step": 77
    },
    {
      "epoch": 1.925925925925926,
      "grad_norm": 0.33188384771347046,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 1.7393,
      "step": 78
    },
    {
      "epoch": 1.9506172839506173,
      "grad_norm": 0.3645884692668915,
      "learning_rate": 3.216892336688435e-05,
      "loss": 1.7558,
      "step": 79
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.5310534834861755,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.7483,
      "step": 80
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5409613847732544,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 2.4523,
      "step": 81
    },
    {
      "epoch": 2.0246913580246915,
      "grad_norm": 0.1562846601009369,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 1.9007,
      "step": 82
    },
    {
      "epoch": 2.049382716049383,
      "grad_norm": 0.2033800333738327,
      "learning_rate": 2.705090677662311e-05,
      "loss": 1.9369,
      "step": 83
    },
    {
      "epoch": 2.074074074074074,
      "grad_norm": 0.22452938556671143,
      "learning_rate": 2.581405564473801e-05,
      "loss": 1.962,
      "step": 84
    },
    {
      "epoch": 2.0987654320987654,
      "grad_norm": 0.2419237196445465,
      "learning_rate": 2.459623273767354e-05,
      "loss": 1.7808,
      "step": 85
    },
    {
      "epoch": 2.123456790123457,
      "grad_norm": 0.27632632851600647,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 1.9695,
      "step": 86
    },
    {
      "epoch": 2.148148148148148,
      "grad_norm": 0.26683545112609863,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.8651,
      "step": 87
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.2869678735733032,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 1.7975,
      "step": 88
    },
    {
      "epoch": 2.197530864197531,
      "grad_norm": 0.31071460247039795,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 1.7865,
      "step": 89
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.3720311224460602,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 1.5558,
      "step": 90
    },
    {
      "epoch": 2.246913580246914,
      "grad_norm": 0.4831774830818176,
      "learning_rate": 1.774140082289563e-05,
      "loss": 1.4962,
      "step": 91
    },
    {
      "epoch": 2.271604938271605,
      "grad_norm": 0.1712505966424942,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 1.724,
      "step": 92
    },
    {
      "epoch": 2.2962962962962963,
      "grad_norm": 0.24379503726959229,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 1.8886,
      "step": 93
    },
    {
      "epoch": 2.3209876543209877,
      "grad_norm": 0.22222569584846497,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.8285,
      "step": 94
    },
    {
      "epoch": 2.3456790123456788,
      "grad_norm": 0.2787880301475525,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 1.6753,
      "step": 95
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.23695729672908783,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 1.846,
      "step": 96
    },
    {
      "epoch": 2.3950617283950617,
      "grad_norm": 0.255487859249115,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 1.7061,
      "step": 97
    },
    {
      "epoch": 2.419753086419753,
      "grad_norm": 0.32571518421173096,
      "learning_rate": 1.090842587659851e-05,
      "loss": 1.8259,
      "step": 98
    },
    {
      "epoch": 2.4444444444444446,
      "grad_norm": 0.3715745210647583,
      "learning_rate": 1.004947573208756e-05,
      "loss": 1.7244,
      "step": 99
    },
    {
      "epoch": 2.4691358024691357,
      "grad_norm": 0.43399521708488464,
      "learning_rate": 9.221956552036992e-06,
      "loss": 1.6352,
      "step": 100
    },
    {
      "epoch": 2.4691358024691357,
      "eval_loss": 1.8051786422729492,
      "eval_runtime": 1.2101,
      "eval_samples_per_second": 57.02,
      "eval_steps_per_second": 14.875,
      "step": 100
    },
    {
      "epoch": 2.493827160493827,
      "grad_norm": 0.6663125157356262,
      "learning_rate": 8.426519384872733e-06,
      "loss": 1.6124,
      "step": 101
    },
    {
      "epoch": 2.5185185185185186,
      "grad_norm": 0.18589438498020172,
      "learning_rate": 7.663790038585793e-06,
      "loss": 1.8629,
      "step": 102
    },
    {
      "epoch": 2.5432098765432096,
      "grad_norm": 0.2220928966999054,
      "learning_rate": 6.934368588379553e-06,
      "loss": 1.9673,
      "step": 103
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.2574703097343445,
      "learning_rate": 6.238828904562316e-06,
      "loss": 1.9648,
      "step": 104
    },
    {
      "epoch": 2.5925925925925926,
      "grad_norm": 0.21821027994155884,
      "learning_rate": 5.577718201056392e-06,
      "loss": 1.719,
      "step": 105
    },
    {
      "epoch": 2.617283950617284,
      "grad_norm": 0.24519659578800201,
      "learning_rate": 4.951556604879048e-06,
      "loss": 1.7669,
      "step": 106
    },
    {
      "epoch": 2.6419753086419755,
      "grad_norm": 0.2632535398006439,
      "learning_rate": 4.360836746934055e-06,
      "loss": 1.7951,
      "step": 107
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.32132890820503235,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.8676,
      "step": 108
    },
    {
      "epoch": 2.691358024691358,
      "grad_norm": 0.33073845505714417,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 1.7202,
      "step": 109
    },
    {
      "epoch": 2.7160493827160495,
      "grad_norm": 0.3966529369354248,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 1.5839,
      "step": 110
    },
    {
      "epoch": 2.7407407407407405,
      "grad_norm": 0.5801085829734802,
      "learning_rate": 2.361243863855184e-06,
      "loss": 1.4997,
      "step": 111
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.19857348501682281,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 2.031,
      "step": 112
    },
    {
      "epoch": 2.7901234567901234,
      "grad_norm": 0.21141159534454346,
      "learning_rate": 1.584823893886933e-06,
      "loss": 1.8876,
      "step": 113
    },
    {
      "epoch": 2.814814814814815,
      "grad_norm": 0.21823370456695557,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 1.9942,
      "step": 114
    },
    {
      "epoch": 2.8395061728395063,
      "grad_norm": 0.2245025634765625,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.7845,
      "step": 115
    },
    {
      "epoch": 2.8641975308641974,
      "grad_norm": 0.26134663820266724,
      "learning_rate": 7.064490740882057e-07,
      "loss": 1.8277,
      "step": 116
    },
    {
      "epoch": 2.888888888888889,
      "grad_norm": 0.2692930996417999,
      "learning_rate": 4.909437331777179e-07,
      "loss": 1.7512,
      "step": 117
    },
    {
      "epoch": 2.9135802469135803,
      "grad_norm": 0.2990117073059082,
      "learning_rate": 3.143895053378698e-07,
      "loss": 1.8127,
      "step": 118
    },
    {
      "epoch": 2.9382716049382713,
      "grad_norm": 0.3050815165042877,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 1.6489,
      "step": 119
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.4244462549686432,
      "learning_rate": 7.865924910916977e-08,
      "loss": 1.8393,
      "step": 120
    },
    {
      "epoch": 2.9876543209876543,
      "grad_norm": 0.5024273991584778,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 1.2649,
      "step": 121
    },
    {
      "epoch": 3.0123456790123457,
      "grad_norm": 0.3924722373485565,
      "learning_rate": 0.0,
      "loss": 3.0433,
      "step": 122
    }
  ],
  "logging_steps": 1,
  "max_steps": 122,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8373593464504320.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}