{
  "best_metric": 0.05524740368127823,
  "best_model_checkpoint": "saves/psy-course-doc/Ministral-8B-Instruct-2410/train/fold6/checkpoint-80",
  "epoch": 4.938271604938271,
  "eval_steps": 10,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03950617283950617,
      "grad_norm": 0.3453253209590912,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.1997,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.2724876403808594,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.219,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.3278728723526001,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.1803,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.2860534191131592,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.2016,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.2268516719341278,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.2192,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.249753937125206,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.1953,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.23212018609046936,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.2214,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.19239450991153717,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.1892,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.23025935888290405,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.1861,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.19380125403404236,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.1261,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.12191563844680786,
      "eval_runtime": 22.6925,
      "eval_samples_per_second": 1.983,
      "eval_steps_per_second": 1.983,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.24038347601890564,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.1368,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.19465912878513336,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.1069,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.1955067366361618,
      "learning_rate": 0.0001,
      "loss": 0.1127,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.20961400866508484,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.0931,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.22035710513591766,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.1579,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.17115965485572815,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1528,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.14280855655670166,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1052,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.13526570796966553,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1046,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.11154366284608841,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.0488,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.11634842306375504,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.0689,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.07357785105705261,
      "eval_runtime": 22.7012,
      "eval_samples_per_second": 1.982,
      "eval_steps_per_second": 1.982,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.1411876082420349,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.0612,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.15594454109668732,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1205,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.12550732493400574,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1259,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.12196537107229233,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.0388,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.1719665676355362,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.1895,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.138519749045372,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.1182,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.1516338586807251,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0467,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.11315115541219711,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.0977,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.09231827408075333,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.0564,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.1212570071220398,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.0589,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.06241626292467117,
      "eval_runtime": 22.7126,
      "eval_samples_per_second": 1.981,
      "eval_steps_per_second": 1.981,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.12261682748794556,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0872,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.12572073936462402,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.0871,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.10321181267499924,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1052,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.1558021754026413,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1003,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.10917932540178299,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0768,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.17098411917686462,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0445,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.1191348135471344,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0775,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.17128992080688477,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.11,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.11113065481185913,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0532,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.10157547146081924,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0821,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.059175387024879456,
      "eval_runtime": 22.7663,
      "eval_samples_per_second": 1.977,
      "eval_steps_per_second": 1.977,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.10836565494537354,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0776,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.14213216304779053,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0794,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.11571558564901352,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0769,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.09645584225654602,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.0783,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.11946801096200943,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0657,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.16518084704875946,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0706,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.1529022455215454,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0682,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.10586317628622055,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.077,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.11301428824663162,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0566,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.11077115684747696,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0517,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.05717097222805023,
      "eval_runtime": 22.7569,
      "eval_samples_per_second": 1.977,
      "eval_steps_per_second": 1.977,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.10150635987520218,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.0914,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.09953919798135757,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0605,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.1130269393324852,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0876,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.09398074448108673,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0842,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.09477541595697403,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0722,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.09016451239585876,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0716,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.13022908568382263,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0777,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.10697229951620102,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.1039,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.1107974499464035,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0651,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.0782020092010498,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0246,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.056248340755701065,
      "eval_runtime": 22.7682,
      "eval_samples_per_second": 1.976,
      "eval_steps_per_second": 1.976,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.09783139079809189,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0453,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.08803529292345047,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0501,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.11330702155828476,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0842,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.08565479516983032,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0472,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.10009751468896866,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0709,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.12859654426574707,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0963,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.09846732765436172,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0602,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.11181583255529404,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0511,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.11642862111330032,
      "learning_rate": 5e-05,
      "loss": 0.0448,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.1019311398267746,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0429,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.05577303096652031,
      "eval_runtime": 22.7637,
      "eval_samples_per_second": 1.977,
      "eval_steps_per_second": 1.977,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.13543939590454102,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0599,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.10640951246023178,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0369,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.11836311966180801,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0748,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.10120408236980438,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0511,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.09693686664104462,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0536,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.1149887815117836,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0794,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.11211463809013367,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0624,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.08666456490755081,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.036,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.12312066555023193,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0725,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.10543828457593918,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0479,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.05524740368127823,
      "eval_runtime": 22.7615,
      "eval_samples_per_second": 1.977,
      "eval_steps_per_second": 1.977,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.09587044268846512,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0445,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.10471823066473007,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0515,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.10559819638729095,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0597,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.13821004331111908,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0838,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.11083836853504181,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0466,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.10894396156072617,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0356,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.08983268588781357,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0175,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.11217804998159409,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0483,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.12818579375743866,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0623,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.1306171715259552,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0674,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.056424036622047424,
      "eval_runtime": 22.7658,
      "eval_samples_per_second": 1.977,
      "eval_steps_per_second": 1.977,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.14004842936992645,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0674,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.12425006926059723,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0509,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.11279848217964172,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0596,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.11195692420005798,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0432,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.11617887765169144,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0556,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.11352365463972092,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0384,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.1256469190120697,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0639,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.15063296258449554,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.097,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.16642580926418304,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0992,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.10868074744939804,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0445,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.05599704757332802,
      "eval_runtime": 22.7666,
      "eval_samples_per_second": 1.977,
      "eval_steps_per_second": 1.977,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.12793488800525665,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0577,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.13628368079662323,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0715,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.14548087120056152,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0864,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.08192165940999985,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0176,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.1296483725309372,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0633,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.09645400941371918,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0364,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.13828125596046448,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0765,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.13799108564853668,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0583,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.10257546603679657,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0474,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.11223700642585754,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0331,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.056210994720458984,
      "eval_runtime": 22.7594,
      "eval_samples_per_second": 1.977,
      "eval_steps_per_second": 1.977,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.13155394792556763,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0674,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.12092218548059464,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.037,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.12958674132823944,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0489,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.12511742115020752,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0659,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.14695113897323608,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0849,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.13473036885261536,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.045,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.11503653228282928,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0391,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.12525373697280884,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.047,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.10104631632566452,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0265,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.1077285036444664,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0374,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.056368060410022736,
      "eval_runtime": 22.785,
      "eval_samples_per_second": 1.975,
      "eval_steps_per_second": 1.975,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.12666630744934082,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0607,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.13667650520801544,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0651,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.1325499415397644,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0703,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.085207998752594,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0175,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.12487030774354935,
      "learning_rate": 0.0,
      "loss": 0.0539,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.55140337137877e+17,
      "train_loss": 0.07858721241354942,
      "train_runtime": 3863.1398,
      "train_samples_per_second": 0.524,
      "train_steps_per_second": 0.032
    }
  ],
  "logging_steps": 1,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.55140337137877e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}