{
  "best_metric": 0.14555972814559937,
  "best_model_checkpoint": "saves/psy-course-info/MentaLLaMA-chat-7B/train/fold1/checkpoint-120",
  "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": 0.8831675052642822,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.9492,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.8380454778671265,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 1.002,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.9136907458305359,
      "learning_rate": 2.307692307692308e-05,
      "loss": 1.071,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.9394763708114624,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 1.1055,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.9565200805664062,
      "learning_rate": 3.846153846153846e-05,
      "loss": 1.1171,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.9917623996734619,
      "learning_rate": 4.615384615384616e-05,
      "loss": 1.0424,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 1.0711687803268433,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.9371,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 1.0785679817199707,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.9213,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.2583428621292114,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.9886,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 1.4162931442260742,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.7837,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.7542588114738464,
      "eval_runtime": 22.533,
      "eval_samples_per_second": 1.997,
      "eval_steps_per_second": 1.997,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 1.2629787921905518,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.6732,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.9119262099266052,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.6115,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.6693624258041382,
      "learning_rate": 0.0001,
      "loss": 0.5413,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.6868858337402344,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.4075,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.5335227251052856,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.347,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.586911678314209,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.4062,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.5954338908195496,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.2423,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.4876900613307953,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.2523,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.44848746061325073,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.3278,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.46652474999427795,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.2931,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.2810686230659485,
      "eval_runtime": 22.4651,
      "eval_samples_per_second": 2.003,
      "eval_steps_per_second": 2.003,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.44894707202911377,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.2341,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.5279524922370911,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.253,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.46272173523902893,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1967,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.4724982678890228,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.2832,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.4622252583503723,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.2855,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.6512012481689453,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.3211,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.3514662981033325,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.2032,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.41068628430366516,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.2985,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.35777747631073,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1901,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.3695032298564911,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1974,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.2092229425907135,
      "eval_runtime": 22.4878,
      "eval_samples_per_second": 2.001,
      "eval_steps_per_second": 2.001,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.36013153195381165,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1991,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.3780241906642914,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.2061,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.38102811574935913,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.203,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.35677415132522583,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1553,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.3739641606807709,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.2012,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.383306086063385,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1661,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.26645469665527344,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.1218,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.2891363799571991,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.1414,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.3711816370487213,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1725,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.3484783172607422,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.144,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.1874631941318512,
      "eval_runtime": 22.5244,
      "eval_samples_per_second": 1.998,
      "eval_steps_per_second": 1.998,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.36839693784713745,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1841,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.564883291721344,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.1598,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.29378893971443176,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.1499,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.35966038703918457,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1356,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.43347644805908203,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.2259,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.343942791223526,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.157,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.430485337972641,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.1731,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.2836102247238159,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1294,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.43477100133895874,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.2119,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.3841744363307953,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.1558,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.17156915366649628,
      "eval_runtime": 22.5056,
      "eval_samples_per_second": 2.0,
      "eval_steps_per_second": 2.0,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.7081446051597595,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.2625,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.33255016803741455,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.1106,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.2924251854419708,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.1197,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.30840620398521423,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.1626,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.33414316177368164,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1342,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.4599325358867645,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.1537,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.31713733077049255,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.1264,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.3231431543827057,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.1229,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.34301650524139404,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.1136,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.29565224051475525,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0987,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.1600760817527771,
      "eval_runtime": 22.4268,
      "eval_samples_per_second": 2.007,
      "eval_steps_per_second": 2.007,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.28324073553085327,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.1161,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.507408857345581,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.1828,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.29785823822021484,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.1433,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.3387358486652374,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.1724,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.4336045980453491,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.1229,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.31423696875572205,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.1181,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.3084644675254822,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.1191,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.31573107838630676,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.1013,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.3134782910346985,
      "learning_rate": 5e-05,
      "loss": 0.0987,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.37504109740257263,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.1066,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.15221436321735382,
      "eval_runtime": 22.4172,
      "eval_samples_per_second": 2.007,
      "eval_steps_per_second": 2.007,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.30067524313926697,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0965,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.40663811564445496,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.1518,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.5172812938690186,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.1678,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.3032599687576294,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.1033,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.4573477506637573,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.1493,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.6785665154457092,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.2777,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.2837696969509125,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0958,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.3821134865283966,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.104,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.3729143440723419,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.131,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.2934877574443817,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0932,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.1546574831008911,
      "eval_runtime": 22.4487,
      "eval_samples_per_second": 2.005,
      "eval_steps_per_second": 2.005,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.3151495158672333,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0958,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.37021705508232117,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0959,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.361158162355423,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.1014,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.40403109788894653,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.1139,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.31589552760124207,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.1066,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.3179355561733246,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.108,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.376476526260376,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.1205,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.33170247077941895,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.1064,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.3528650999069214,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.1362,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.35834309458732605,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0981,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.15438534319400787,
      "eval_runtime": 22.4909,
      "eval_samples_per_second": 2.001,
      "eval_steps_per_second": 2.001,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.5136727094650269,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.1463,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.36773088574409485,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.1175,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.5553377866744995,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.127,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.4456188976764679,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.1193,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.3486391007900238,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.1098,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.3378802537918091,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.089,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.3151121139526367,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.1019,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.27301889657974243,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0934,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.27396801114082336,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0942,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.31572967767715454,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.1145,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.14721176028251648,
      "eval_runtime": 22.5185,
      "eval_samples_per_second": 1.998,
      "eval_steps_per_second": 1.998,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.34827569127082825,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.1005,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.7272560596466064,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1571,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.27554798126220703,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0844,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.28635308146476746,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0907,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.32259735465049744,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.085,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.263408899307251,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0968,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.2651858925819397,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0902,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.33785250782966614,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.1146,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.3886694312095642,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.096,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.2637059986591339,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0768,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.1458897739648819,
      "eval_runtime": 22.535,
      "eval_samples_per_second": 1.997,
      "eval_steps_per_second": 1.997,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.3989276587963104,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.1107,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.3226042091846466,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.1183,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.3306662142276764,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0913,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.2665714621543884,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0835,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.3207409977912903,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.1096,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.3568267822265625,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0949,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.2524173855781555,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.086,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.27770474553108215,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.083,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.44202956557273865,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.1213,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.239474818110466,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0802,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.14555972814559937,
      "eval_runtime": 22.5228,
      "eval_samples_per_second": 1.998,
      "eval_steps_per_second": 1.998,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.35366666316986084,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0878,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.32910242676734924,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.1139,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.28884387016296387,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0863,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.41008782386779785,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.1279,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.28698375821113586,
      "learning_rate": 0.0,
      "loss": 0.1065,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.3800777564173107e+17,
      "train_loss": 0.22897324532270433,
      "train_runtime": 3966.9108,
      "train_samples_per_second": 0.51,
      "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": 1.3800777564173107e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}