{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3004115226337449,
  "eval_steps": 110,
  "global_step": 219,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013717421124828531,
      "grad_norm": 13.75906753540039,
      "learning_rate": 1.8281535648994516e-06,
      "loss": 1.2468,
      "step": 1
    },
    {
      "epoch": 0.0027434842249657062,
      "grad_norm": 14.05058765411377,
      "learning_rate": 3.6563071297989032e-06,
      "loss": 1.4692,
      "step": 2
    },
    {
      "epoch": 0.00411522633744856,
      "grad_norm": 13.991771697998047,
      "learning_rate": 5.484460694698355e-06,
      "loss": 1.2457,
      "step": 3
    },
    {
      "epoch": 0.0054869684499314125,
      "grad_norm": 13.429465293884277,
      "learning_rate": 7.3126142595978065e-06,
      "loss": 1.1859,
      "step": 4
    },
    {
      "epoch": 0.006858710562414266,
      "grad_norm": 12.403002738952637,
      "learning_rate": 9.140767824497258e-06,
      "loss": 1.2404,
      "step": 5
    },
    {
      "epoch": 0.00823045267489712,
      "grad_norm": 1.5524662733078003,
      "learning_rate": 1.096892138939671e-05,
      "loss": 0.042,
      "step": 6
    },
    {
      "epoch": 0.009602194787379973,
      "grad_norm": 10.1494140625,
      "learning_rate": 1.2797074954296162e-05,
      "loss": 0.8856,
      "step": 7
    },
    {
      "epoch": 0.010973936899862825,
      "grad_norm": Infinity,
      "learning_rate": 1.2797074954296162e-05,
      "loss": 1.5417,
      "step": 8
    },
    {
      "epoch": 0.012345679012345678,
      "grad_norm": 0.4553964138031006,
      "learning_rate": 1.4625228519195613e-05,
      "loss": 0.023,
      "step": 9
    },
    {
      "epoch": 0.013717421124828532,
      "grad_norm": 10.332369804382324,
      "learning_rate": 1.6453382084095062e-05,
      "loss": 0.8655,
      "step": 10
    },
    {
      "epoch": 0.015089163237311385,
      "grad_norm": 7.544310092926025,
      "learning_rate": 1.8281535648994517e-05,
      "loss": 0.5894,
      "step": 11
    },
    {
      "epoch": 0.01646090534979424,
      "grad_norm": 8.16427230834961,
      "learning_rate": 2.0109689213893968e-05,
      "loss": 0.7053,
      "step": 12
    },
    {
      "epoch": 0.01783264746227709,
      "grad_norm": 7.403252601623535,
      "learning_rate": 2.193784277879342e-05,
      "loss": 0.5857,
      "step": 13
    },
    {
      "epoch": 0.019204389574759947,
      "grad_norm": 8.974674224853516,
      "learning_rate": 2.376599634369287e-05,
      "loss": 0.8375,
      "step": 14
    },
    {
      "epoch": 0.0205761316872428,
      "grad_norm": 13.417745590209961,
      "learning_rate": 2.5594149908592324e-05,
      "loss": 0.9043,
      "step": 15
    },
    {
      "epoch": 0.02194787379972565,
      "grad_norm": 12.881294250488281,
      "learning_rate": 2.742230347349177e-05,
      "loss": 0.8756,
      "step": 16
    },
    {
      "epoch": 0.023319615912208505,
      "grad_norm": 7.439205169677734,
      "learning_rate": 2.9250457038391226e-05,
      "loss": 0.5076,
      "step": 17
    },
    {
      "epoch": 0.024691358024691357,
      "grad_norm": 8.46964168548584,
      "learning_rate": 3.107861060329068e-05,
      "loss": 0.4757,
      "step": 18
    },
    {
      "epoch": 0.02606310013717421,
      "grad_norm": 17.02773666381836,
      "learning_rate": 3.2906764168190124e-05,
      "loss": 0.9993,
      "step": 19
    },
    {
      "epoch": 0.027434842249657063,
      "grad_norm": 6.2668776512146,
      "learning_rate": 3.473491773308958e-05,
      "loss": 0.2622,
      "step": 20
    },
    {
      "epoch": 0.02880658436213992,
      "grad_norm": 8.273824691772461,
      "learning_rate": 3.656307129798903e-05,
      "loss": 0.3497,
      "step": 21
    },
    {
      "epoch": 0.03017832647462277,
      "grad_norm": 5.5460944175720215,
      "learning_rate": 3.839122486288849e-05,
      "loss": 0.2514,
      "step": 22
    },
    {
      "epoch": 0.03155006858710562,
      "grad_norm": 4.283128261566162,
      "learning_rate": 4.0219378427787935e-05,
      "loss": 0.1673,
      "step": 23
    },
    {
      "epoch": 0.03292181069958848,
      "grad_norm": 4.708792209625244,
      "learning_rate": 4.204753199268738e-05,
      "loss": 0.203,
      "step": 24
    },
    {
      "epoch": 0.03429355281207133,
      "grad_norm": 14.491021156311035,
      "learning_rate": 4.387568555758684e-05,
      "loss": 0.698,
      "step": 25
    },
    {
      "epoch": 0.03566529492455418,
      "grad_norm": 7.903520584106445,
      "learning_rate": 4.570383912248629e-05,
      "loss": 0.3401,
      "step": 26
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 7.333080291748047,
      "learning_rate": 4.753199268738574e-05,
      "loss": 0.2185,
      "step": 27
    },
    {
      "epoch": 0.038408779149519894,
      "grad_norm": 8.625358581542969,
      "learning_rate": 4.936014625228519e-05,
      "loss": 0.4424,
      "step": 28
    },
    {
      "epoch": 0.039780521262002745,
      "grad_norm": 1.5588488578796387,
      "learning_rate": 5.118829981718465e-05,
      "loss": 0.0381,
      "step": 29
    },
    {
      "epoch": 0.0411522633744856,
      "grad_norm": 12.401138305664062,
      "learning_rate": 5.3016453382084095e-05,
      "loss": 0.8215,
      "step": 30
    },
    {
      "epoch": 0.04252400548696845,
      "grad_norm": 5.405845642089844,
      "learning_rate": 5.484460694698354e-05,
      "loss": 0.1542,
      "step": 31
    },
    {
      "epoch": 0.0438957475994513,
      "grad_norm": 8.558808326721191,
      "learning_rate": 5.6672760511883e-05,
      "loss": 0.6893,
      "step": 32
    },
    {
      "epoch": 0.04526748971193416,
      "grad_norm": 7.206741809844971,
      "learning_rate": 5.850091407678245e-05,
      "loss": 0.3773,
      "step": 33
    },
    {
      "epoch": 0.04663923182441701,
      "grad_norm": 8.300729751586914,
      "learning_rate": 6.0329067641681906e-05,
      "loss": 0.538,
      "step": 34
    },
    {
      "epoch": 0.04801097393689986,
      "grad_norm": 0.2500181496143341,
      "learning_rate": 6.215722120658135e-05,
      "loss": 0.0073,
      "step": 35
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 17.457223892211914,
      "learning_rate": 6.398537477148081e-05,
      "loss": 2.378,
      "step": 36
    },
    {
      "epoch": 0.05075445816186557,
      "grad_norm": 10.884990692138672,
      "learning_rate": 6.581352833638025e-05,
      "loss": 0.5949,
      "step": 37
    },
    {
      "epoch": 0.05212620027434842,
      "grad_norm": 10.013723373413086,
      "learning_rate": 6.764168190127972e-05,
      "loss": 0.7071,
      "step": 38
    },
    {
      "epoch": 0.053497942386831275,
      "grad_norm": 4.653324604034424,
      "learning_rate": 6.946983546617916e-05,
      "loss": 0.1607,
      "step": 39
    },
    {
      "epoch": 0.05486968449931413,
      "grad_norm": 9.527400970458984,
      "learning_rate": 7.129798903107861e-05,
      "loss": 0.7735,
      "step": 40
    },
    {
      "epoch": 0.056241426611796985,
      "grad_norm": 12.477531433105469,
      "learning_rate": 7.312614259597807e-05,
      "loss": 0.7594,
      "step": 41
    },
    {
      "epoch": 0.05761316872427984,
      "grad_norm": 5.369799613952637,
      "learning_rate": 7.495429616087751e-05,
      "loss": 0.3569,
      "step": 42
    },
    {
      "epoch": 0.05898491083676269,
      "grad_norm": 5.1385908126831055,
      "learning_rate": 7.678244972577697e-05,
      "loss": 0.2454,
      "step": 43
    },
    {
      "epoch": 0.06035665294924554,
      "grad_norm": 6.1807708740234375,
      "learning_rate": 7.861060329067642e-05,
      "loss": 0.2723,
      "step": 44
    },
    {
      "epoch": 0.06172839506172839,
      "grad_norm": 7.941879749298096,
      "learning_rate": 8.043875685557587e-05,
      "loss": 0.5338,
      "step": 45
    },
    {
      "epoch": 0.06310013717421124,
      "grad_norm": 5.015410423278809,
      "learning_rate": 8.226691042047532e-05,
      "loss": 0.1891,
      "step": 46
    },
    {
      "epoch": 0.0644718792866941,
      "grad_norm": 7.299699306488037,
      "learning_rate": 8.409506398537477e-05,
      "loss": 0.3647,
      "step": 47
    },
    {
      "epoch": 0.06584362139917696,
      "grad_norm": 8.421393394470215,
      "learning_rate": 8.592321755027423e-05,
      "loss": 0.383,
      "step": 48
    },
    {
      "epoch": 0.06721536351165981,
      "grad_norm": 5.5915937423706055,
      "learning_rate": 8.775137111517367e-05,
      "loss": 0.2353,
      "step": 49
    },
    {
      "epoch": 0.06858710562414266,
      "grad_norm": 8.187829971313477,
      "learning_rate": 8.957952468007313e-05,
      "loss": 0.5541,
      "step": 50
    },
    {
      "epoch": 0.06995884773662552,
      "grad_norm": 6.386786460876465,
      "learning_rate": 9.140767824497258e-05,
      "loss": 0.4908,
      "step": 51
    },
    {
      "epoch": 0.07133058984910837,
      "grad_norm": 8.64050006866455,
      "learning_rate": 9.323583180987204e-05,
      "loss": 0.586,
      "step": 52
    },
    {
      "epoch": 0.07270233196159122,
      "grad_norm": 5.879551410675049,
      "learning_rate": 9.506398537477148e-05,
      "loss": 0.2241,
      "step": 53
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 7.824138164520264,
      "learning_rate": 9.689213893967093e-05,
      "loss": 0.6046,
      "step": 54
    },
    {
      "epoch": 0.07544581618655692,
      "grad_norm": 6.351109504699707,
      "learning_rate": 9.872029250457039e-05,
      "loss": 0.231,
      "step": 55
    },
    {
      "epoch": 0.07681755829903979,
      "grad_norm": 9.437410354614258,
      "learning_rate": 0.00010054844606946984,
      "loss": 0.7105,
      "step": 56
    },
    {
      "epoch": 0.07818930041152264,
      "grad_norm": 8.40911865234375,
      "learning_rate": 0.0001023765996343693,
      "loss": 0.5591,
      "step": 57
    },
    {
      "epoch": 0.07956104252400549,
      "grad_norm": 7.631382942199707,
      "learning_rate": 0.00010420475319926874,
      "loss": 0.5194,
      "step": 58
    },
    {
      "epoch": 0.08093278463648834,
      "grad_norm": 5.773220062255859,
      "learning_rate": 0.00010603290676416819,
      "loss": 0.3297,
      "step": 59
    },
    {
      "epoch": 0.0823045267489712,
      "grad_norm": 1.3606321811676025,
      "learning_rate": 0.00010786106032906765,
      "loss": 0.0299,
      "step": 60
    },
    {
      "epoch": 0.08367626886145405,
      "grad_norm": 7.216275215148926,
      "learning_rate": 0.00010968921389396709,
      "loss": 0.3514,
      "step": 61
    },
    {
      "epoch": 0.0850480109739369,
      "grad_norm": 4.70477294921875,
      "learning_rate": 0.00011151736745886655,
      "loss": 0.1932,
      "step": 62
    },
    {
      "epoch": 0.08641975308641975,
      "grad_norm": 6.754104137420654,
      "learning_rate": 0.000113345521023766,
      "loss": 0.4035,
      "step": 63
    },
    {
      "epoch": 0.0877914951989026,
      "grad_norm": 0.19067375361919403,
      "learning_rate": 0.00011517367458866546,
      "loss": 0.0094,
      "step": 64
    },
    {
      "epoch": 0.08916323731138547,
      "grad_norm": 1.1715893745422363,
      "learning_rate": 0.0001170018281535649,
      "loss": 0.0148,
      "step": 65
    },
    {
      "epoch": 0.09053497942386832,
      "grad_norm": 1.6287739276885986,
      "learning_rate": 0.00011882998171846434,
      "loss": 0.0231,
      "step": 66
    },
    {
      "epoch": 0.09190672153635117,
      "grad_norm": 7.027708053588867,
      "learning_rate": 0.00012065813528336381,
      "loss": 0.3204,
      "step": 67
    },
    {
      "epoch": 0.09327846364883402,
      "grad_norm": 7.248253345489502,
      "learning_rate": 0.00012248628884826325,
      "loss": 0.3011,
      "step": 68
    },
    {
      "epoch": 0.09465020576131687,
      "grad_norm": 9.592718124389648,
      "learning_rate": 0.0001243144424131627,
      "loss": 0.3871,
      "step": 69
    },
    {
      "epoch": 0.09602194787379972,
      "grad_norm": 5.128874778747559,
      "learning_rate": 0.00012614259597806216,
      "loss": 0.1823,
      "step": 70
    },
    {
      "epoch": 0.09739368998628258,
      "grad_norm": 6.496853351593018,
      "learning_rate": 0.00012797074954296162,
      "loss": 0.3572,
      "step": 71
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 6.564659118652344,
      "learning_rate": 0.00012979890310786104,
      "loss": 0.5289,
      "step": 72
    },
    {
      "epoch": 0.10013717421124829,
      "grad_norm": 6.480371952056885,
      "learning_rate": 0.0001316270566727605,
      "loss": 0.3223,
      "step": 73
    },
    {
      "epoch": 0.10150891632373114,
      "grad_norm": 7.222306728363037,
      "learning_rate": 0.00013345521023765998,
      "loss": 0.3247,
      "step": 74
    },
    {
      "epoch": 0.102880658436214,
      "grad_norm": 5.406076431274414,
      "learning_rate": 0.00013528336380255943,
      "loss": 0.2133,
      "step": 75
    },
    {
      "epoch": 0.10425240054869685,
      "grad_norm": 11.029163360595703,
      "learning_rate": 0.00013711151736745886,
      "loss": 0.8249,
      "step": 76
    },
    {
      "epoch": 0.1056241426611797,
      "grad_norm": 7.284115314483643,
      "learning_rate": 0.00013893967093235832,
      "loss": 0.4341,
      "step": 77
    },
    {
      "epoch": 0.10699588477366255,
      "grad_norm": 6.240738868713379,
      "learning_rate": 0.00014076782449725777,
      "loss": 0.2932,
      "step": 78
    },
    {
      "epoch": 0.1083676268861454,
      "grad_norm": 0.1745665967464447,
      "learning_rate": 0.00014259597806215722,
      "loss": 0.0099,
      "step": 79
    },
    {
      "epoch": 0.10973936899862825,
      "grad_norm": 5.460353851318359,
      "learning_rate": 0.00014442413162705668,
      "loss": 0.3348,
      "step": 80
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 8.869246482849121,
      "learning_rate": 0.00014625228519195613,
      "loss": 0.6405,
      "step": 81
    },
    {
      "epoch": 0.11248285322359397,
      "grad_norm": 4.475996971130371,
      "learning_rate": 0.0001480804387568556,
      "loss": 0.1536,
      "step": 82
    },
    {
      "epoch": 0.11385459533607682,
      "grad_norm": 2.700299024581909,
      "learning_rate": 0.00014990859232175501,
      "loss": 0.1299,
      "step": 83
    },
    {
      "epoch": 0.11522633744855967,
      "grad_norm": 7.5515618324279785,
      "learning_rate": 0.00015173674588665447,
      "loss": 0.5863,
      "step": 84
    },
    {
      "epoch": 0.11659807956104253,
      "grad_norm": 9.869407653808594,
      "learning_rate": 0.00015356489945155395,
      "loss": 0.7205,
      "step": 85
    },
    {
      "epoch": 0.11796982167352538,
      "grad_norm": 8.208423614501953,
      "learning_rate": 0.00015539305301645338,
      "loss": 0.4052,
      "step": 86
    },
    {
      "epoch": 0.11934156378600823,
      "grad_norm": 6.408420562744141,
      "learning_rate": 0.00015722120658135283,
      "loss": 0.3953,
      "step": 87
    },
    {
      "epoch": 0.12071330589849108,
      "grad_norm": 7.050099849700928,
      "learning_rate": 0.00015904936014625229,
      "loss": 0.5598,
      "step": 88
    },
    {
      "epoch": 0.12208504801097393,
      "grad_norm": 5.326991558074951,
      "learning_rate": 0.00016087751371115174,
      "loss": 0.2856,
      "step": 89
    },
    {
      "epoch": 0.12345679012345678,
      "grad_norm": 4.510193347930908,
      "learning_rate": 0.0001627056672760512,
      "loss": 0.2277,
      "step": 90
    },
    {
      "epoch": 0.12482853223593965,
      "grad_norm": 5.769596576690674,
      "learning_rate": 0.00016453382084095065,
      "loss": 0.3296,
      "step": 91
    },
    {
      "epoch": 0.1262002743484225,
      "grad_norm": 6.066390037536621,
      "learning_rate": 0.0001663619744058501,
      "loss": 0.3079,
      "step": 92
    },
    {
      "epoch": 0.12757201646090535,
      "grad_norm": 6.80173921585083,
      "learning_rate": 0.00016819012797074953,
      "loss": 0.4867,
      "step": 93
    },
    {
      "epoch": 0.1289437585733882,
      "grad_norm": 6.219693183898926,
      "learning_rate": 0.00017001828153564899,
      "loss": 0.4319,
      "step": 94
    },
    {
      "epoch": 0.13031550068587106,
      "grad_norm": 5.316290855407715,
      "learning_rate": 0.00017184643510054847,
      "loss": 0.2952,
      "step": 95
    },
    {
      "epoch": 0.13168724279835392,
      "grad_norm": 6.86447811126709,
      "learning_rate": 0.00017367458866544792,
      "loss": 0.5531,
      "step": 96
    },
    {
      "epoch": 0.13305898491083676,
      "grad_norm": 1.2648167610168457,
      "learning_rate": 0.00017550274223034735,
      "loss": 0.0296,
      "step": 97
    },
    {
      "epoch": 0.13443072702331962,
      "grad_norm": 8.14661979675293,
      "learning_rate": 0.0001773308957952468,
      "loss": 0.8536,
      "step": 98
    },
    {
      "epoch": 0.13580246913580246,
      "grad_norm": 8.927884101867676,
      "learning_rate": 0.00017915904936014626,
      "loss": 0.4879,
      "step": 99
    },
    {
      "epoch": 0.13717421124828533,
      "grad_norm": 9.555243492126465,
      "learning_rate": 0.00018098720292504568,
      "loss": 0.67,
      "step": 100
    },
    {
      "epoch": 0.13854595336076816,
      "grad_norm": 7.783656120300293,
      "learning_rate": 0.00018281535648994517,
      "loss": 0.4813,
      "step": 101
    },
    {
      "epoch": 0.13991769547325103,
      "grad_norm": 0.5169872641563416,
      "learning_rate": 0.00018464351005484462,
      "loss": 0.0488,
      "step": 102
    },
    {
      "epoch": 0.1412894375857339,
      "grad_norm": 6.967692852020264,
      "learning_rate": 0.00018647166361974407,
      "loss": 0.5388,
      "step": 103
    },
    {
      "epoch": 0.14266117969821673,
      "grad_norm": 6.324373245239258,
      "learning_rate": 0.0001882998171846435,
      "loss": 0.376,
      "step": 104
    },
    {
      "epoch": 0.1440329218106996,
      "grad_norm": 0.7642683982849121,
      "learning_rate": 0.00019012797074954296,
      "loss": 0.017,
      "step": 105
    },
    {
      "epoch": 0.14540466392318244,
      "grad_norm": 8.600672721862793,
      "learning_rate": 0.00019195612431444244,
      "loss": 0.7542,
      "step": 106
    },
    {
      "epoch": 0.1467764060356653,
      "grad_norm": 7.111880302429199,
      "learning_rate": 0.00019378427787934186,
      "loss": 0.4063,
      "step": 107
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 6.075577735900879,
      "learning_rate": 0.00019561243144424132,
      "loss": 0.3658,
      "step": 108
    },
    {
      "epoch": 0.149519890260631,
      "grad_norm": 6.12313175201416,
      "learning_rate": 0.00019744058500914077,
      "loss": 0.4389,
      "step": 109
    },
    {
      "epoch": 0.15089163237311384,
      "grad_norm": 5.813235759735107,
      "learning_rate": 0.00019926873857404023,
      "loss": 0.3803,
      "step": 110
    },
    {
      "epoch": 0.15089163237311384,
      "eval_Qnli-dev_cosine_accuracy": 0.705078125,
      "eval_Qnli-dev_cosine_accuracy_threshold": 0.6866907477378845,
      "eval_Qnli-dev_cosine_ap": 0.7567018413685389,
      "eval_Qnli-dev_cosine_f1": 0.6931818181818182,
      "eval_Qnli-dev_cosine_f1_threshold": 0.6343963146209717,
      "eval_Qnli-dev_cosine_precision": 0.6267123287671232,
      "eval_Qnli-dev_cosine_recall": 0.7754237288135594,
      "eval_allNLI-dev_cosine_accuracy": 0.76953125,
      "eval_allNLI-dev_cosine_accuracy_threshold": 0.7752166986465454,
      "eval_allNLI-dev_cosine_ap": 0.6627175481841632,
      "eval_allNLI-dev_cosine_f1": 0.6624737945492662,
      "eval_allNLI-dev_cosine_f1_threshold": 0.6564935445785522,
      "eval_allNLI-dev_cosine_precision": 0.5197368421052632,
      "eval_allNLI-dev_cosine_recall": 0.9132947976878613,
      "eval_sequential_score": 0.7567018413685389,
      "eval_sts-test_pearson_cosine": 0.9026620207137961,
      "eval_sts-test_spearman_cosine": 0.913678627606199,
      "eval_vitaminc-pairs_loss": 2.009296178817749,
      "eval_vitaminc-pairs_runtime": 14.3224,
      "eval_vitaminc-pairs_samples_per_second": 8.937,
      "eval_vitaminc-pairs_steps_per_second": 0.07,
      "step": 110
    },
    {
      "epoch": 0.15089163237311384,
      "eval_negation-triplets_loss": 1.59572434425354,
      "eval_negation-triplets_runtime": 1.1528,
      "eval_negation-triplets_samples_per_second": 111.029,
      "eval_negation-triplets_steps_per_second": 0.867,
      "step": 110
    },
    {
      "epoch": 0.15089163237311384,
      "eval_scitail-pairs-pos_loss": 0.061776161193847656,
      "eval_scitail-pairs-pos_runtime": 1.5728,
      "eval_scitail-pairs-pos_samples_per_second": 81.383,
      "eval_scitail-pairs-pos_steps_per_second": 0.636,
      "step": 110
    },
    {
      "epoch": 0.15089163237311384,
      "eval_scitail-pairs-qa_loss": 0.009187542833387852,
      "eval_scitail-pairs-qa_runtime": 1.2102,
      "eval_scitail-pairs-qa_samples_per_second": 105.771,
      "eval_scitail-pairs-qa_steps_per_second": 0.826,
      "step": 110
    },
    {
      "epoch": 0.15089163237311384,
      "eval_xsum-pairs_loss": 0.37210211157798767,
      "eval_xsum-pairs_runtime": 6.2854,
      "eval_xsum-pairs_samples_per_second": 20.365,
      "eval_xsum-pairs_steps_per_second": 0.159,
      "step": 110
    },
    {
      "epoch": 0.15089163237311384,
      "eval_sciq_pairs_loss": 0.04122849553823471,
      "eval_sciq_pairs_runtime": 8.8116,
      "eval_sciq_pairs_samples_per_second": 14.526,
      "eval_sciq_pairs_steps_per_second": 0.113,
      "step": 110
    },
    {
      "epoch": 0.15089163237311384,
      "eval_qasc_pairs_loss": 0.4748501479625702,
      "eval_qasc_pairs_runtime": 1.3827,
      "eval_qasc_pairs_samples_per_second": 92.573,
      "eval_qasc_pairs_steps_per_second": 0.723,
      "step": 110
    },
    {
      "epoch": 0.15089163237311384,
      "eval_openbookqa_pairs_loss": 1.1540580987930298,
      "eval_openbookqa_pairs_runtime": 1.1788,
      "eval_openbookqa_pairs_samples_per_second": 108.581,
      "eval_openbookqa_pairs_steps_per_second": 0.848,
      "step": 110
    },
    {
      "epoch": 0.15089163237311384,
      "eval_nq_pairs_loss": 0.2363465428352356,
      "eval_nq_pairs_runtime": 7.8515,
      "eval_nq_pairs_samples_per_second": 16.303,
      "eval_nq_pairs_steps_per_second": 0.127,
      "step": 110
    },
    {
      "epoch": 0.15089163237311384,
      "eval_trivia_pairs_loss": 0.6520176529884338,
      "eval_trivia_pairs_runtime": 8.9067,
      "eval_trivia_pairs_samples_per_second": 14.371,
      "eval_trivia_pairs_steps_per_second": 0.112,
      "step": 110
    },
    {
      "epoch": 0.15089163237311384,
      "eval_gooaq_pairs_loss": 0.22620199620723724,
      "eval_gooaq_pairs_runtime": 2.067,
      "eval_gooaq_pairs_samples_per_second": 61.924,
      "eval_gooaq_pairs_steps_per_second": 0.484,
      "step": 110
    },
    {
      "epoch": 0.15089163237311384,
      "eval_paws-pos_loss": 0.02822125516831875,
      "eval_paws-pos_runtime": 1.5117,
      "eval_paws-pos_samples_per_second": 84.672,
      "eval_paws-pos_steps_per_second": 0.662,
      "step": 110
    },
    {
      "epoch": 0.15089163237311384,
      "eval_global_dataset_loss": 0.30668479204177856,
      "eval_global_dataset_runtime": 33.2591,
      "eval_global_dataset_samples_per_second": 11.546,
      "eval_global_dataset_steps_per_second": 0.06,
      "step": 110
    },
    {
      "epoch": 0.1522633744855967,
      "grad_norm": 4.30504846572876,
      "learning_rate": 0.00020109689213893968,
      "loss": 0.2478,
      "step": 111
    },
    {
      "epoch": 0.15363511659807957,
      "grad_norm": 6.559568881988525,
      "learning_rate": 0.00020292504570383914,
      "loss": 0.8402,
      "step": 112
    },
    {
      "epoch": 0.1550068587105624,
      "grad_norm": 5.812280654907227,
      "learning_rate": 0.0002047531992687386,
      "loss": 0.6608,
      "step": 113
    },
    {
      "epoch": 0.15637860082304528,
      "grad_norm": 2.0805885791778564,
      "learning_rate": 0.00020658135283363802,
      "loss": 0.0934,
      "step": 114
    },
    {
      "epoch": 0.15775034293552812,
      "grad_norm": 5.199294090270996,
      "learning_rate": 0.00020840950639853747,
      "loss": 0.3907,
      "step": 115
    },
    {
      "epoch": 0.15912208504801098,
      "grad_norm": 6.3685078620910645,
      "learning_rate": 0.00021023765996343693,
      "loss": 0.449,
      "step": 116
    },
    {
      "epoch": 0.16049382716049382,
      "grad_norm": 6.4199652671813965,
      "learning_rate": 0.00021206581352833638,
      "loss": 0.4041,
      "step": 117
    },
    {
      "epoch": 0.16186556927297668,
      "grad_norm": 6.015898704528809,
      "learning_rate": 0.00021389396709323584,
      "loss": 0.6749,
      "step": 118
    },
    {
      "epoch": 0.16323731138545952,
      "grad_norm": 7.721911430358887,
      "learning_rate": 0.0002157221206581353,
      "loss": 0.4847,
      "step": 119
    },
    {
      "epoch": 0.1646090534979424,
      "grad_norm": 1.8774610757827759,
      "learning_rate": 0.00021755027422303474,
      "loss": 0.0526,
      "step": 120
    },
    {
      "epoch": 0.16598079561042525,
      "grad_norm": 8.094359397888184,
      "learning_rate": 0.00021937842778793417,
      "loss": 0.6795,
      "step": 121
    },
    {
      "epoch": 0.1673525377229081,
      "grad_norm": 0.33090323209762573,
      "learning_rate": 0.00022120658135283365,
      "loss": 0.0064,
      "step": 122
    },
    {
      "epoch": 0.16872427983539096,
      "grad_norm": 7.3609418869018555,
      "learning_rate": 0.0002230347349177331,
      "loss": 0.5918,
      "step": 123
    },
    {
      "epoch": 0.1700960219478738,
      "grad_norm": 6.189216613769531,
      "learning_rate": 0.00022486288848263253,
      "loss": 0.3544,
      "step": 124
    },
    {
      "epoch": 0.17146776406035666,
      "grad_norm": 5.588890075683594,
      "learning_rate": 0.000226691042047532,
      "loss": 0.3849,
      "step": 125
    },
    {
      "epoch": 0.1728395061728395,
      "grad_norm": 3.4582345485687256,
      "learning_rate": 0.00022851919561243144,
      "loss": 0.2051,
      "step": 126
    },
    {
      "epoch": 0.17421124828532236,
      "grad_norm": 4.075862407684326,
      "learning_rate": 0.00023034734917733092,
      "loss": 0.2129,
      "step": 127
    },
    {
      "epoch": 0.1755829903978052,
      "grad_norm": 15.110091209411621,
      "learning_rate": 0.00023217550274223035,
      "loss": 2.7937,
      "step": 128
    },
    {
      "epoch": 0.17695473251028807,
      "grad_norm": 0.35791516304016113,
      "learning_rate": 0.0002340036563071298,
      "loss": 0.0166,
      "step": 129
    },
    {
      "epoch": 0.17832647462277093,
      "grad_norm": 7.5200090408325195,
      "learning_rate": 0.00023583180987202926,
      "loss": 0.7856,
      "step": 130
    },
    {
      "epoch": 0.17969821673525377,
      "grad_norm": 6.566864490509033,
      "learning_rate": 0.0002376599634369287,
      "loss": 0.8368,
      "step": 131
    },
    {
      "epoch": 0.18106995884773663,
      "grad_norm": 4.958701133728027,
      "learning_rate": 0.00023948811700182814,
      "loss": 0.3813,
      "step": 132
    },
    {
      "epoch": 0.18244170096021947,
      "grad_norm": 5.745133876800537,
      "learning_rate": 0.00024131627056672762,
      "loss": 0.5695,
      "step": 133
    },
    {
      "epoch": 0.18381344307270234,
      "grad_norm": 4.952736854553223,
      "learning_rate": 0.00024314442413162708,
      "loss": 0.351,
      "step": 134
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 5.733601093292236,
      "learning_rate": 0.0002449725776965265,
      "loss": 0.3821,
      "step": 135
    },
    {
      "epoch": 0.18655692729766804,
      "grad_norm": 5.019097328186035,
      "learning_rate": 0.00024680073126142596,
      "loss": 0.3249,
      "step": 136
    },
    {
      "epoch": 0.18792866941015088,
      "grad_norm": 5.300777912139893,
      "learning_rate": 0.0002486288848263254,
      "loss": 0.3404,
      "step": 137
    },
    {
      "epoch": 0.18930041152263374,
      "grad_norm": 4.518141269683838,
      "learning_rate": 0.00025045703839122487,
      "loss": 0.4535,
      "step": 138
    },
    {
      "epoch": 0.1906721536351166,
      "grad_norm": 1.0158088207244873,
      "learning_rate": 0.0002522851919561243,
      "loss": 0.0577,
      "step": 139
    },
    {
      "epoch": 0.19204389574759945,
      "grad_norm": 5.966796398162842,
      "learning_rate": 0.0002541133455210238,
      "loss": 0.7431,
      "step": 140
    },
    {
      "epoch": 0.1934156378600823,
      "grad_norm": 6.123642921447754,
      "learning_rate": 0.00025594149908592323,
      "loss": 0.6778,
      "step": 141
    },
    {
      "epoch": 0.19478737997256515,
      "grad_norm": 5.842874050140381,
      "learning_rate": 0.0002577696526508227,
      "loss": 0.5436,
      "step": 142
    },
    {
      "epoch": 0.19615912208504802,
      "grad_norm": 4.759068012237549,
      "learning_rate": 0.0002595978062157221,
      "loss": 0.3582,
      "step": 143
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 4.080338478088379,
      "learning_rate": 0.00026142595978062154,
      "loss": 0.316,
      "step": 144
    },
    {
      "epoch": 0.19890260631001372,
      "grad_norm": 4.1391448974609375,
      "learning_rate": 0.000263254113345521,
      "loss": 0.4446,
      "step": 145
    },
    {
      "epoch": 0.20027434842249658,
      "grad_norm": 5.856256008148193,
      "learning_rate": 0.0002650822669104205,
      "loss": 0.7792,
      "step": 146
    },
    {
      "epoch": 0.20164609053497942,
      "grad_norm": 7.747331142425537,
      "learning_rate": 0.00026691042047531996,
      "loss": 1.1147,
      "step": 147
    },
    {
      "epoch": 0.2030178326474623,
      "grad_norm": 6.825289249420166,
      "learning_rate": 0.0002687385740402194,
      "loss": 0.8267,
      "step": 148
    },
    {
      "epoch": 0.20438957475994513,
      "grad_norm": 7.336719512939453,
      "learning_rate": 0.00027056672760511887,
      "loss": 0.8149,
      "step": 149
    },
    {
      "epoch": 0.205761316872428,
      "grad_norm": 6.731626510620117,
      "learning_rate": 0.00027239488117001827,
      "loss": 0.942,
      "step": 150
    },
    {
      "epoch": 0.20713305898491083,
      "grad_norm": 10.727692604064941,
      "learning_rate": 0.0002742230347349177,
      "loss": 2.4865,
      "step": 151
    },
    {
      "epoch": 0.2085048010973937,
      "grad_norm": 8.583380699157715,
      "learning_rate": 0.0002760511882998172,
      "loss": 1.0715,
      "step": 152
    },
    {
      "epoch": 0.20987654320987653,
      "grad_norm": 6.236877918243408,
      "learning_rate": 0.00027787934186471663,
      "loss": 0.6219,
      "step": 153
    },
    {
      "epoch": 0.2112482853223594,
      "grad_norm": 6.254538536071777,
      "learning_rate": 0.0002797074954296161,
      "loss": 0.8705,
      "step": 154
    },
    {
      "epoch": 0.21262002743484226,
      "grad_norm": 3.0917959213256836,
      "learning_rate": 0.00028153564899451554,
      "loss": 0.2407,
      "step": 155
    },
    {
      "epoch": 0.2139917695473251,
      "grad_norm": 4.438024997711182,
      "learning_rate": 0.000283363802559415,
      "loss": 0.4925,
      "step": 156
    },
    {
      "epoch": 0.21536351165980797,
      "grad_norm": 0.43344631791114807,
      "learning_rate": 0.00028519195612431445,
      "loss": 0.0316,
      "step": 157
    },
    {
      "epoch": 0.2167352537722908,
      "grad_norm": 5.73934268951416,
      "learning_rate": 0.0002870201096892139,
      "loss": 0.3935,
      "step": 158
    },
    {
      "epoch": 0.21810699588477367,
      "grad_norm": 4.532804012298584,
      "learning_rate": 0.00028884826325411336,
      "loss": 0.2083,
      "step": 159
    },
    {
      "epoch": 0.2194787379972565,
      "grad_norm": 4.846848487854004,
      "learning_rate": 0.0002906764168190128,
      "loss": 0.2798,
      "step": 160
    },
    {
      "epoch": 0.22085048010973937,
      "grad_norm": 7.060863018035889,
      "learning_rate": 0.00029250457038391227,
      "loss": 0.8777,
      "step": 161
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.012754157185554504,
      "learning_rate": 0.0002943327239488117,
      "loss": 0.0002,
      "step": 162
    },
    {
      "epoch": 0.22359396433470508,
      "grad_norm": 4.094379901885986,
      "learning_rate": 0.0002961608775137112,
      "loss": 0.2736,
      "step": 163
    },
    {
      "epoch": 0.22496570644718794,
      "grad_norm": 10.741785049438477,
      "learning_rate": 0.0002979890310786106,
      "loss": 2.4185,
      "step": 164
    },
    {
      "epoch": 0.22633744855967078,
      "grad_norm": 4.820891380310059,
      "learning_rate": 0.00029981718464351003,
      "loss": 0.7767,
      "step": 165
    },
    {
      "epoch": 0.22770919067215364,
      "grad_norm": 6.423076152801514,
      "learning_rate": 0.0003016453382084095,
      "loss": 0.7971,
      "step": 166
    },
    {
      "epoch": 0.22908093278463648,
      "grad_norm": 4.492727756500244,
      "learning_rate": 0.00030347349177330894,
      "loss": 0.4535,
      "step": 167
    },
    {
      "epoch": 0.23045267489711935,
      "grad_norm": 5.301379680633545,
      "learning_rate": 0.00030530164533820845,
      "loss": 0.6654,
      "step": 168
    },
    {
      "epoch": 0.23182441700960219,
      "grad_norm": 5.155853748321533,
      "learning_rate": 0.0003071297989031079,
      "loss": 0.3985,
      "step": 169
    },
    {
      "epoch": 0.23319615912208505,
      "grad_norm": 0.4378865361213684,
      "learning_rate": 0.00030895795246800735,
      "loss": 0.0338,
      "step": 170
    },
    {
      "epoch": 0.2345679012345679,
      "grad_norm": 4.022473335266113,
      "learning_rate": 0.00031078610603290675,
      "loss": 0.1834,
      "step": 171
    },
    {
      "epoch": 0.23593964334705075,
      "grad_norm": 7.863429069519043,
      "learning_rate": 0.0003126142595978062,
      "loss": 0.603,
      "step": 172
    },
    {
      "epoch": 0.23731138545953362,
      "grad_norm": 8.951998710632324,
      "learning_rate": 0.00031444241316270566,
      "loss": 0.7871,
      "step": 173
    },
    {
      "epoch": 0.23868312757201646,
      "grad_norm": 6.265102386474609,
      "learning_rate": 0.0003162705667276051,
      "loss": 0.4304,
      "step": 174
    },
    {
      "epoch": 0.24005486968449932,
      "grad_norm": 6.6486005783081055,
      "learning_rate": 0.00031809872029250457,
      "loss": 0.649,
      "step": 175
    },
    {
      "epoch": 0.24142661179698216,
      "grad_norm": 0.47100114822387695,
      "learning_rate": 0.000319926873857404,
      "loss": 0.048,
      "step": 176
    },
    {
      "epoch": 0.24279835390946503,
      "grad_norm": 4.884115695953369,
      "learning_rate": 0.0003217550274223035,
      "loss": 0.4079,
      "step": 177
    },
    {
      "epoch": 0.24417009602194786,
      "grad_norm": 4.508667469024658,
      "learning_rate": 0.0003235831809872029,
      "loss": 0.4627,
      "step": 178
    },
    {
      "epoch": 0.24554183813443073,
      "grad_norm": 3.22367262840271,
      "learning_rate": 0.0003254113345521024,
      "loss": 0.3703,
      "step": 179
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 7.695303916931152,
      "learning_rate": 0.00032723948811700184,
      "loss": 0.8343,
      "step": 180
    },
    {
      "epoch": 0.24828532235939643,
      "grad_norm": 7.249318599700928,
      "learning_rate": 0.0003290676416819013,
      "loss": 0.692,
      "step": 181
    },
    {
      "epoch": 0.2496570644718793,
      "grad_norm": 11.686202049255371,
      "learning_rate": 0.00033089579524680075,
      "loss": 2.7071,
      "step": 182
    },
    {
      "epoch": 0.25102880658436216,
      "grad_norm": 6.061092376708984,
      "learning_rate": 0.0003327239488117002,
      "loss": 0.8451,
      "step": 183
    },
    {
      "epoch": 0.252400548696845,
      "grad_norm": 5.932607650756836,
      "learning_rate": 0.00033455210237659966,
      "loss": 0.635,
      "step": 184
    },
    {
      "epoch": 0.25377229080932784,
      "grad_norm": 3.491114616394043,
      "learning_rate": 0.00033638025594149906,
      "loss": 0.312,
      "step": 185
    },
    {
      "epoch": 0.2551440329218107,
      "grad_norm": 6.4914164543151855,
      "learning_rate": 0.0003382084095063985,
      "loss": 0.6996,
      "step": 186
    },
    {
      "epoch": 0.25651577503429357,
      "grad_norm": 6.15857458114624,
      "learning_rate": 0.00034003656307129797,
      "loss": 0.4432,
      "step": 187
    },
    {
      "epoch": 0.2578875171467764,
      "grad_norm": 4.767185211181641,
      "learning_rate": 0.0003418647166361974,
      "loss": 0.375,
      "step": 188
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 7.944342613220215,
      "learning_rate": 0.00034369287020109693,
      "loss": 0.9366,
      "step": 189
    },
    {
      "epoch": 0.2606310013717421,
      "grad_norm": 6.573953628540039,
      "learning_rate": 0.0003455210237659964,
      "loss": 0.755,
      "step": 190
    },
    {
      "epoch": 0.262002743484225,
      "grad_norm": 4.173367023468018,
      "learning_rate": 0.00034734917733089584,
      "loss": 0.6068,
      "step": 191
    },
    {
      "epoch": 0.26337448559670784,
      "grad_norm": 5.26171875,
      "learning_rate": 0.00034917733089579524,
      "loss": 0.5336,
      "step": 192
    },
    {
      "epoch": 0.26474622770919065,
      "grad_norm": 6.669304370880127,
      "learning_rate": 0.0003510054844606947,
      "loss": 0.8783,
      "step": 193
    },
    {
      "epoch": 0.2661179698216735,
      "grad_norm": 4.4192938804626465,
      "learning_rate": 0.00035283363802559415,
      "loss": 0.3576,
      "step": 194
    },
    {
      "epoch": 0.2674897119341564,
      "grad_norm": 10.117819786071777,
      "learning_rate": 0.0003546617915904936,
      "loss": 2.1854,
      "step": 195
    },
    {
      "epoch": 0.26886145404663925,
      "grad_norm": 5.256247520446777,
      "learning_rate": 0.00035648994515539306,
      "loss": 0.7835,
      "step": 196
    },
    {
      "epoch": 0.27023319615912206,
      "grad_norm": 5.784887313842773,
      "learning_rate": 0.0003583180987202925,
      "loss": 0.5668,
      "step": 197
    },
    {
      "epoch": 0.2716049382716049,
      "grad_norm": 4.977567672729492,
      "learning_rate": 0.00036014625228519197,
      "loss": 0.7033,
      "step": 198
    },
    {
      "epoch": 0.2729766803840878,
      "grad_norm": 0.011424711905419827,
      "learning_rate": 0.00036197440585009137,
      "loss": 0.0002,
      "step": 199
    },
    {
      "epoch": 0.27434842249657065,
      "grad_norm": 5.805008411407471,
      "learning_rate": 0.0003638025594149909,
      "loss": 0.5791,
      "step": 200
    },
    {
      "epoch": 0.2757201646090535,
      "grad_norm": 3.8826043605804443,
      "learning_rate": 0.00036563071297989033,
      "loss": 0.2697,
      "step": 201
    },
    {
      "epoch": 0.27709190672153633,
      "grad_norm": 6.563521385192871,
      "learning_rate": 0.0003674588665447898,
      "loss": 0.6261,
      "step": 202
    },
    {
      "epoch": 0.2784636488340192,
      "grad_norm": 4.584529399871826,
      "learning_rate": 0.00036928702010968924,
      "loss": 0.3253,
      "step": 203
    },
    {
      "epoch": 0.27983539094650206,
      "grad_norm": 6.636009216308594,
      "learning_rate": 0.0003711151736745887,
      "loss": 0.8323,
      "step": 204
    },
    {
      "epoch": 0.2812071330589849,
      "grad_norm": 5.0911359786987305,
      "learning_rate": 0.00037294332723948815,
      "loss": 0.4472,
      "step": 205
    },
    {
      "epoch": 0.2825788751714678,
      "grad_norm": 3.9219255447387695,
      "learning_rate": 0.00037477148080438755,
      "loss": 0.3342,
      "step": 206
    },
    {
      "epoch": 0.2839506172839506,
      "grad_norm": 5.114777565002441,
      "learning_rate": 0.000376599634369287,
      "loss": 0.6313,
      "step": 207
    },
    {
      "epoch": 0.28532235939643347,
      "grad_norm": 0.3298715353012085,
      "learning_rate": 0.00037842778793418646,
      "loss": 0.059,
      "step": 208
    },
    {
      "epoch": 0.28669410150891633,
      "grad_norm": 1.5965046882629395,
      "learning_rate": 0.0003802559414990859,
      "loss": 0.1195,
      "step": 209
    },
    {
      "epoch": 0.2880658436213992,
      "grad_norm": 0.39121323823928833,
      "learning_rate": 0.00038208409506398537,
      "loss": 0.0296,
      "step": 210
    },
    {
      "epoch": 0.289437585733882,
      "grad_norm": 4.317224025726318,
      "learning_rate": 0.0003839122486288849,
      "loss": 0.5316,
      "step": 211
    },
    {
      "epoch": 0.2908093278463649,
      "grad_norm": 4.000308036804199,
      "learning_rate": 0.00038574040219378433,
      "loss": 0.5201,
      "step": 212
    },
    {
      "epoch": 0.29218106995884774,
      "grad_norm": 6.2192301750183105,
      "learning_rate": 0.00038756855575868373,
      "loss": 0.6602,
      "step": 213
    },
    {
      "epoch": 0.2935528120713306,
      "grad_norm": 6.702320098876953,
      "learning_rate": 0.0003893967093235832,
      "loss": 0.9578,
      "step": 214
    },
    {
      "epoch": 0.29492455418381347,
      "grad_norm": 3.9136242866516113,
      "learning_rate": 0.00039122486288848264,
      "loss": 0.2089,
      "step": 215
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 6.901303768157959,
      "learning_rate": 0.0003930530164533821,
      "loss": 1.2112,
      "step": 216
    },
    {
      "epoch": 0.29766803840877915,
      "grad_norm": 4.04884672164917,
      "learning_rate": 0.00039488117001828155,
      "loss": 0.3294,
      "step": 217
    },
    {
      "epoch": 0.299039780521262,
      "grad_norm": 5.46201753616333,
      "learning_rate": 0.000396709323583181,
      "loss": 0.867,
      "step": 218
    },
    {
      "epoch": 0.3004115226337449,
      "grad_norm": 5.559458255767822,
      "learning_rate": 0.00039853747714808046,
      "loss": 1.1745,
      "step": 219
    }
  ],
  "logging_steps": 1,
  "max_steps": 2187,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 219,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}