{
  "best_metric": 0.09572803974151611,
  "best_model_checkpoint": "saves/psy-course-doc-info/MentaLLaMA-chat-7B/train/fold8/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": 0.28007856011390686,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.433,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.24837623536586761,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.4159,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.3082425892353058,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.4514,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 1.5509341955184937,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 1.9055,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.24132554233074188,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.3823,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.30457136034965515,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.443,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.6854003071784973,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.8178,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.3168322443962097,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.3904,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.30583322048187256,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.3782,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.3310084342956543,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.3878,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.5401856899261475,
      "eval_runtime": 33.3859,
      "eval_samples_per_second": 1.348,
      "eval_steps_per_second": 1.348,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.3072730302810669,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.4077,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.28253456950187683,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.3585,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.22483812272548676,
      "learning_rate": 0.0001,
      "loss": 0.3077,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.4366050064563751,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.4211,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.21070708334445953,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.2615,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.2253689169883728,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.275,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.16458497941493988,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.2522,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 1.371113657951355,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.9138,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.2135397493839264,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.2484,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.2562556266784668,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.261,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.3376403748989105,
      "eval_runtime": 33.3703,
      "eval_samples_per_second": 1.349,
      "eval_steps_per_second": 1.349,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 1.6434333324432373,
      "learning_rate": 9.874639560909117e-05,
      "loss": 1.2291,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.2279050648212433,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.2169,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.21798649430274963,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.2337,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.18217793107032776,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.2138,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.19455815851688385,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.2065,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.4130234122276306,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.3604,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.1802195906639099,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1853,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.174123153090477,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.204,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.20781689882278442,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1901,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.19443999230861664,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1716,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.25965526700019836,
      "eval_runtime": 33.3807,
      "eval_samples_per_second": 1.348,
      "eval_steps_per_second": 1.348,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.21562638878822327,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1224,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.17822474241256714,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.2067,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.14956490695476532,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1434,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.22571897506713867,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1605,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.1723530888557434,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.142,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.19512102007865906,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1525,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.17981749773025513,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.1424,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.21143867075443268,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.1417,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.3208419680595398,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.195,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.14526233077049255,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.1226,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.23008215427398682,
      "eval_runtime": 33.3327,
      "eval_samples_per_second": 1.35,
      "eval_steps_per_second": 1.35,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.16875430941581726,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1541,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.9690858125686646,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.3109,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.7152979373931885,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.2552,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 2.116842031478882,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.7543,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.15060631930828094,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.1085,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 1.5826088190078735,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.6337,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.2171413153409958,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.1893,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.5370022058486938,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.2345,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.1858329474925995,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.1086,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.19618359208106995,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.1363,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.16122816503047943,
      "eval_runtime": 33.1801,
      "eval_samples_per_second": 1.356,
      "eval_steps_per_second": 1.356,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.3099558651447296,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.169,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.183892622590065,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.1114,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.1499486118555069,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0997,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.1976601928472519,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.134,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 1.470460057258606,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.52,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.19609004259109497,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.1105,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.3585953414440155,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.1824,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.2738560736179352,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.1258,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.2583808898925781,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.1156,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.1760481745004654,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.116,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.13656340539455414,
      "eval_runtime": 32.9424,
      "eval_samples_per_second": 1.366,
      "eval_steps_per_second": 1.366,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.3053383529186249,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.1617,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.2491649091243744,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.1061,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.2362040877342224,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.1014,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.20005322992801666,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0992,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.25204432010650635,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.1215,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.22927068173885345,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.1018,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.2401135265827179,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.1134,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.19086837768554688,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0953,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.21295559406280518,
      "learning_rate": 5e-05,
      "loss": 0.0991,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.20448651909828186,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0883,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.12156534940004349,
      "eval_runtime": 32.6105,
      "eval_samples_per_second": 1.38,
      "eval_steps_per_second": 1.38,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.19235223531723022,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0826,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.8395757675170898,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.3135,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.2000177502632141,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.1221,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.25711140036582947,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0964,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.20767894387245178,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0743,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.34206250309944153,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1741,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.16954265534877777,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0897,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.22587436437606812,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0733,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.19472086429595947,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.128,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.18975740671157837,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0747,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.10817178338766098,
      "eval_runtime": 32.3985,
      "eval_samples_per_second": 1.389,
      "eval_steps_per_second": 1.389,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.5480496883392334,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.2363,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.2200697511434555,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0854,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.5781704783439636,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.2889,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.24655422568321228,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0743,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.19895653426647186,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0793,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.2225782424211502,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0885,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.18249814212322235,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0758,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.18983371555805206,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0918,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.19800600409507751,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0821,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.23010219633579254,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.089,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.10052080452442169,
      "eval_runtime": 32.3467,
      "eval_samples_per_second": 1.391,
      "eval_steps_per_second": 1.391,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.24633342027664185,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0732,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.19849640130996704,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0759,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.2324657440185547,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0691,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.20950950682163239,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0885,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.22205498814582825,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0867,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.19257056713104248,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0599,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.2717740535736084,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.1432,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.2212703675031662,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0815,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.31523391604423523,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0754,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.24747225642204285,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0792,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.09750425815582275,
      "eval_runtime": 32.2879,
      "eval_samples_per_second": 1.394,
      "eval_steps_per_second": 1.394,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.27939897775650024,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.1239,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.319589227437973,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1608,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.19000943005084991,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0812,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.16687999665737152,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0615,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.4187617897987366,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.2082,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.22634799778461456,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0818,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.253135621547699,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0731,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.2201540470123291,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0642,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.21101011335849762,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0991,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.20909126102924347,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0645,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.0961577519774437,
      "eval_runtime": 32.2861,
      "eval_samples_per_second": 1.394,
      "eval_steps_per_second": 1.394,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.2009512484073639,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.081,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.18526527285575867,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0716,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.2022845298051834,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.084,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.26533183455467224,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0943,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.20336537063121796,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0599,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.22721871733665466,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0849,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.18592388927936554,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.066,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.2008654624223709,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.081,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.17485450208187103,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0726,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.22233444452285767,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.075,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.09572803974151611,
      "eval_runtime": 32.2719,
      "eval_samples_per_second": 1.394,
      "eval_steps_per_second": 1.394,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.21517060697078705,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0571,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.1863366812467575,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0678,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.41858094930648804,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.2238,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.21728137135505676,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0658,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.17819035053253174,
      "learning_rate": 0.0,
      "loss": 0.0779,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.8408438156715622e+17,
      "train_loss": 0.20515184563398361,
      "train_runtime": 5864.2949,
      "train_samples_per_second": 0.345,
      "train_steps_per_second": 0.021
    }
  ],
  "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": 1.8408438156715622e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}