{
  "best_metric": 0.16757896542549133,
  "best_model_checkpoint": "saves/psy-course-info-chain/MentaLLaMA-chat-7B/train/fold5/checkpoint-110",
  "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": 0.9399666786193848,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.7494,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.7798468470573425,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.5954,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.8584246039390564,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.7075,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 1.2191941738128662,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 1.2616,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.8689261078834534,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.6307,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.9409822225570679,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.6235,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.9526281952857971,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.6346,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 1.0750806331634521,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.65,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.0670281648635864,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.5729,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 1.0963526964187622,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.4285,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.5010885000228882,
      "eval_runtime": 26.6425,
      "eval_samples_per_second": 1.689,
      "eval_steps_per_second": 1.689,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.999976396560669,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.2892,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.6545792818069458,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.2089,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.4064624607563019,
      "learning_rate": 0.0001,
      "loss": 0.1797,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.3851904571056366,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.2057,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.5409020781517029,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.1985,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.43398234248161316,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1604,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.44849419593811035,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1512,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.73968905210495,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.2919,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.30472424626350403,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1235,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.35886484384536743,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1559,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.312578409910202,
      "eval_runtime": 26.6191,
      "eval_samples_per_second": 1.691,
      "eval_steps_per_second": 1.691,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 1.0865068435668945,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.6305,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.26597321033477783,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.0702,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.25156739354133606,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1191,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.273281067609787,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1288,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.24366356432437897,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.1117,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.47392556071281433,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.2204,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.2793697714805603,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1217,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.2459385097026825,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1055,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.256089448928833,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.0938,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.22372572124004364,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.0865,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.2532704174518585,
      "eval_runtime": 26.6184,
      "eval_samples_per_second": 1.691,
      "eval_steps_per_second": 1.691,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.17964555323123932,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0595,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.21336323022842407,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.0754,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.23924316465854645,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.0902,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.3265473246574402,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1372,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.3360477089881897,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1014,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.24750031530857086,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1082,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.2568953335285187,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.078,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.31045210361480713,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.091,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.3094371259212494,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0928,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.2792067527770996,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.1025,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.2434244155883789,
      "eval_runtime": 26.6195,
      "eval_samples_per_second": 1.69,
      "eval_steps_per_second": 1.69,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.22295866906642914,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0625,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.2748081684112549,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.1055,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.19323140382766724,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.089,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.8864141702651978,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.431,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.37144479155540466,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.1101,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 1.357034683227539,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.6141,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.25677791237831116,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0782,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.5520341396331787,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1993,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.24107950925827026,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.1154,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.291416734457016,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.1035,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.21257731318473816,
      "eval_runtime": 26.6104,
      "eval_samples_per_second": 1.691,
      "eval_steps_per_second": 1.691,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.5557723641395569,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1621,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.24108169972896576,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.073,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.14241664111614227,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0486,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.20462079346179962,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0797,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.9917683601379395,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.4136,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.30442169308662415,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0962,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.3856891691684723,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.1417,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.21324853599071503,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0774,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.32424890995025635,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.1069,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.29053208231925964,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.1296,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.19640770554542542,
      "eval_runtime": 26.5959,
      "eval_samples_per_second": 1.692,
      "eval_steps_per_second": 1.692,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.16483941674232483,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0579,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.2482336163520813,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0721,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.2072003185749054,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0662,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.20124496519565582,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0615,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.18263165652751923,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0548,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.17469483613967896,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0696,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.24580545723438263,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0735,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.2160508781671524,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0651,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.23282276093959808,
      "learning_rate": 5e-05,
      "loss": 0.0714,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.19877292215824127,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0576,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.1925821304321289,
      "eval_runtime": 26.5222,
      "eval_samples_per_second": 1.697,
      "eval_steps_per_second": 1.697,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.25136253237724304,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0524,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.76519376039505,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.278,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.23623672127723694,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0503,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.24934470653533936,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0697,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.3680875301361084,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0934,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.5044507384300232,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0982,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.29395592212677,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.067,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.29567936062812805,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0774,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.3866867423057556,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0842,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.2598724365234375,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0551,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.1794537454843521,
      "eval_runtime": 26.4985,
      "eval_samples_per_second": 1.698,
      "eval_steps_per_second": 1.698,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.4744437634944916,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.1961,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.286018431186676,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0802,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.789360761642456,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.2945,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.23763126134872437,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0629,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.19278249144554138,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0607,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.23397354781627655,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0767,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.26039326190948486,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0622,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.1982918530702591,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0414,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.2635875344276428,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.077,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.25485193729400635,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0603,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.16927620768547058,
      "eval_runtime": 26.4368,
      "eval_samples_per_second": 1.702,
      "eval_steps_per_second": 1.702,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.2588127553462982,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0593,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.21750041842460632,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0473,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.20880186557769775,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0479,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.2746797204017639,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0626,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.2471173107624054,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0649,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.24595136940479279,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0532,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.3868515193462372,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0984,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.2379412055015564,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.074,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.20769593119621277,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0493,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.2040483057498932,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0443,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.16781629621982574,
      "eval_runtime": 26.3566,
      "eval_samples_per_second": 1.707,
      "eval_steps_per_second": 1.707,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.3683007061481476,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0806,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.468542218208313,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1043,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.23284344375133514,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0567,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.2368522733449936,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0444,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.45298531651496887,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.1827,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.22404728829860687,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0631,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.24604305624961853,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0536,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.239935964345932,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.048,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.21218270063400269,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0485,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.20015065371990204,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0542,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.16757896542549133,
      "eval_runtime": 26.3605,
      "eval_samples_per_second": 1.707,
      "eval_steps_per_second": 1.707,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.2250269055366516,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.045,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.28506630659103394,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0714,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.24619945883750916,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0605,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.24418121576309204,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0571,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.3040781617164612,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0514,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.2686023712158203,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0642,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.24542157351970673,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0417,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.2977822422981262,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0761,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.2816627025604248,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0584,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.23390667140483856,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0602,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.16764962673187256,
      "eval_runtime": 26.3432,
      "eval_samples_per_second": 1.708,
      "eval_steps_per_second": 1.708,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.24440333247184753,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0602,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.24100303649902344,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0507,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.5422549247741699,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.2414,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.3109036684036255,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.085,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.24656899273395538,
      "learning_rate": 0.0,
      "loss": 0.0508,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.4132218395092582e+17,
      "train_loss": 0.15743611985445022,
      "train_runtime": 4255.9574,
      "train_samples_per_second": 0.476,
      "train_steps_per_second": 0.029
    }
  ],
  "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": 1.4132218395092582e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}