{
  "best_metric": 0.07798914611339569,
  "best_model_checkpoint": "saves/psy-course-doc/Llama-3.1-8B-Instruct/train/fold5/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": 0.179071307182312,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.1915,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.17478621006011963,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.1606,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.18289761245250702,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.2237,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.1622197926044464,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.2624,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.1956758350133896,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.2056,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.19062401354312897,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.1867,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.1998380869626999,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.3012,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.16858677566051483,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.2192,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.17125314474105835,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.2052,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.142685204744339,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.1616,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.1590023636817932,
      "eval_runtime": 22.5759,
      "eval_samples_per_second": 1.993,
      "eval_steps_per_second": 1.993,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.13824090361595154,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.0957,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.15559561550617218,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.1443,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.1669289469718933,
      "learning_rate": 0.0001,
      "loss": 0.0972,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.1642448902130127,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.1795,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.1492937207221985,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.1386,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.14514964818954468,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.0868,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.1430801898241043,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1633,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.1358700394630432,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.119,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.1222352385520935,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1038,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.11265887320041656,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1225,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.10629905760288239,
      "eval_runtime": 22.6266,
      "eval_samples_per_second": 1.989,
      "eval_steps_per_second": 1.989,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.13387085497379303,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.158,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.10043662041425705,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.056,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.09858819097280502,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1061,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.10741712152957916,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1249,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.10495370626449585,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.0682,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.1906420737504959,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.1534,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.0946897640824318,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1082,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.09528335928916931,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.0825,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.11285854130983353,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.0821,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.11154665052890778,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.095,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.09256242215633392,
      "eval_runtime": 22.6266,
      "eval_samples_per_second": 1.989,
      "eval_steps_per_second": 1.989,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.09010311216115952,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0632,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.14208534359931946,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1051,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.11092688888311386,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.0821,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.09963589906692505,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.107,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.11486628651618958,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1028,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.1124281957745552,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0845,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.09393428266048431,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0816,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.12599019706249237,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.1233,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.11863153427839279,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.07,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.08344302326440811,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.1007,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.0858151912689209,
      "eval_runtime": 22.6417,
      "eval_samples_per_second": 1.987,
      "eval_steps_per_second": 1.987,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.08714201301336288,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0906,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.08803161233663559,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.079,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.0742732435464859,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0583,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.10445218533277512,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1526,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.07495217770338058,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0377,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.1039033755660057,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0764,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.0826486274600029,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0642,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.08336320519447327,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1087,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.09593306481838226,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.113,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.07292060554027557,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0592,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.08266755938529968,
      "eval_runtime": 22.6286,
      "eval_samples_per_second": 1.989,
      "eval_steps_per_second": 1.989,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.17377887666225433,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.148,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.08676286041736603,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.1411,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.07177270203828812,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0502,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.07616858184337616,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0868,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.08470343798398972,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1259,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.07596971839666367,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0671,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.16759952902793884,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.1081,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.10463081300258636,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.1191,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.07426292449235916,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0328,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.08057385683059692,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0835,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.0807982087135315,
      "eval_runtime": 22.6317,
      "eval_samples_per_second": 1.988,
      "eval_steps_per_second": 1.988,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.08638226985931396,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0826,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.08991046994924545,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0553,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.09229224920272827,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.1102,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.08023947477340698,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0805,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.09353470802307129,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.094,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.07664705812931061,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0225,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.09731356054544449,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0939,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.07285796850919724,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0467,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.08610802888870239,
      "learning_rate": 5e-05,
      "loss": 0.0342,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.09333815425634384,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0771,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.07935161888599396,
      "eval_runtime": 22.6494,
      "eval_samples_per_second": 1.987,
      "eval_steps_per_second": 1.987,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.08782927691936493,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0482,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.09982103109359741,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.1267,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.08077839761972427,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0361,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.10954244434833527,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0801,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.09457288682460785,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0444,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.16691015660762787,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1203,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.07359153777360916,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0459,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.1001354455947876,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.1106,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.0822116881608963,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0745,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.10027966648340225,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.073,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.07833525538444519,
      "eval_runtime": 22.6292,
      "eval_samples_per_second": 1.989,
      "eval_steps_per_second": 1.989,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.0937311202287674,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.1198,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.05918261408805847,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.012,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.09347133338451385,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0882,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.08531496673822403,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0578,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.06988588720560074,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0395,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.06764986366033554,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0487,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.0970442071557045,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0696,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.08221928030252457,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0812,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.09802252054214478,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0869,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.09929746389389038,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.065,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.07846130430698395,
      "eval_runtime": 22.6424,
      "eval_samples_per_second": 1.987,
      "eval_steps_per_second": 1.987,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.10669276118278503,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0394,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.07552552968263626,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0656,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.08562096953392029,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0652,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.10451626032590866,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0656,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.10428772121667862,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0571,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.10598630458116531,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.1089,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.10142865031957626,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0838,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.11463234573602676,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.1232,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.10848049819469452,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0984,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.08141008019447327,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0224,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.07832258939743042,
      "eval_runtime": 22.6344,
      "eval_samples_per_second": 1.988,
      "eval_steps_per_second": 1.988,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.12061808258295059,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0713,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.18013618886470795,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1292,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.10770203918218613,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.1,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.07913533598184586,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0344,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.11021784693002701,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.1024,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.08114725351333618,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0575,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.09120543301105499,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0787,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.06443464010953903,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0124,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.09866588562726974,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0635,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.08159656822681427,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0527,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.07804941385984421,
      "eval_runtime": 22.6511,
      "eval_samples_per_second": 1.987,
      "eval_steps_per_second": 1.987,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.07915913313627243,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0655,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.07952214032411575,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.049,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.08838837593793869,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.037,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.1022355929017067,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0821,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.10233411192893982,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0622,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.06480204313993454,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0191,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.10255326330661774,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0896,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.07931902259588242,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0347,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.10333199799060822,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0809,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.10304973274469376,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0955,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.07798914611339569,
      "eval_runtime": 22.6181,
      "eval_samples_per_second": 1.99,
      "eval_steps_per_second": 1.99,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.09599307179450989,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0788,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.08688204735517502,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0569,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.08426909148693085,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0557,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.1095779538154602,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.121,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.08817500621080399,
      "learning_rate": 0.0,
      "loss": 0.0689,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.4998268210282496e+17,
      "train_loss": 0.09344017395377159,
      "train_runtime": 3645.5193,
      "train_samples_per_second": 0.555,
      "train_steps_per_second": 0.034
    }
  ],
  "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": 1.4998268210282496e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}