{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.9551569506726456,
  "eval_steps": 500,
  "global_step": 296,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013452914798206279,
      "grad_norm": 95.4926986694336,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 12.2856,
      "step": 1
    },
    {
      "epoch": 0.026905829596412557,
      "grad_norm": 93.69285583496094,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 12.2383,
      "step": 2
    },
    {
      "epoch": 0.04035874439461883,
      "grad_norm": 95.09840393066406,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 12.1293,
      "step": 3
    },
    {
      "epoch": 0.053811659192825115,
      "grad_norm": 95.04216766357422,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 12.1453,
      "step": 4
    },
    {
      "epoch": 0.06726457399103139,
      "grad_norm": 93.44210052490234,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 12.165,
      "step": 5
    },
    {
      "epoch": 0.08071748878923767,
      "grad_norm": 93.28514862060547,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 12.063,
      "step": 6
    },
    {
      "epoch": 0.09417040358744394,
      "grad_norm": 95.3654556274414,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 11.9676,
      "step": 7
    },
    {
      "epoch": 0.10762331838565023,
      "grad_norm": 96.05154418945312,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 12.0911,
      "step": 8
    },
    {
      "epoch": 0.1210762331838565,
      "grad_norm": 97.69881439208984,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 12.0717,
      "step": 9
    },
    {
      "epoch": 0.13452914798206278,
      "grad_norm": 95.55254364013672,
      "learning_rate": 5.000000000000001e-07,
      "loss": 11.9752,
      "step": 10
    },
    {
      "epoch": 0.14798206278026907,
      "grad_norm": 95.9182357788086,
      "learning_rate": 5.5e-07,
      "loss": 11.9413,
      "step": 11
    },
    {
      "epoch": 0.16143497757847533,
      "grad_norm": 95.40771484375,
      "learning_rate": 6.000000000000001e-07,
      "loss": 11.7523,
      "step": 12
    },
    {
      "epoch": 0.17488789237668162,
      "grad_norm": 94.40055847167969,
      "learning_rate": 6.5e-07,
      "loss": 11.6384,
      "step": 13
    },
    {
      "epoch": 0.18834080717488788,
      "grad_norm": 93.58352661132812,
      "learning_rate": 7.000000000000001e-07,
      "loss": 11.4293,
      "step": 14
    },
    {
      "epoch": 0.20179372197309417,
      "grad_norm": 94.48737335205078,
      "learning_rate": 7.5e-07,
      "loss": 11.1445,
      "step": 15
    },
    {
      "epoch": 0.21524663677130046,
      "grad_norm": 92.44265747070312,
      "learning_rate": 8.000000000000001e-07,
      "loss": 10.7705,
      "step": 16
    },
    {
      "epoch": 0.22869955156950672,
      "grad_norm": 90.97422790527344,
      "learning_rate": 8.500000000000001e-07,
      "loss": 10.3754,
      "step": 17
    },
    {
      "epoch": 0.242152466367713,
      "grad_norm": 88.54856872558594,
      "learning_rate": 9.000000000000001e-07,
      "loss": 10.0019,
      "step": 18
    },
    {
      "epoch": 0.2556053811659193,
      "grad_norm": 88.39138793945312,
      "learning_rate": 9.500000000000001e-07,
      "loss": 9.5093,
      "step": 19
    },
    {
      "epoch": 0.26905829596412556,
      "grad_norm": 86.55109405517578,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 9.2342,
      "step": 20
    },
    {
      "epoch": 0.2825112107623318,
      "grad_norm": 80.62335205078125,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 8.597,
      "step": 21
    },
    {
      "epoch": 0.29596412556053814,
      "grad_norm": 73.67768859863281,
      "learning_rate": 1.1e-06,
      "loss": 8.1122,
      "step": 22
    },
    {
      "epoch": 0.3094170403587444,
      "grad_norm": 64.57353210449219,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 7.6455,
      "step": 23
    },
    {
      "epoch": 0.32286995515695066,
      "grad_norm": 55.2818603515625,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 7.2493,
      "step": 24
    },
    {
      "epoch": 0.336322869955157,
      "grad_norm": 48.274452209472656,
      "learning_rate": 1.25e-06,
      "loss": 7.0377,
      "step": 25
    },
    {
      "epoch": 0.34977578475336324,
      "grad_norm": 42.7370491027832,
      "learning_rate": 1.3e-06,
      "loss": 6.5782,
      "step": 26
    },
    {
      "epoch": 0.3632286995515695,
      "grad_norm": 39.297462463378906,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 6.2558,
      "step": 27
    },
    {
      "epoch": 0.37668161434977576,
      "grad_norm": 37.91667938232422,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 5.9809,
      "step": 28
    },
    {
      "epoch": 0.3901345291479821,
      "grad_norm": 37.87322998046875,
      "learning_rate": 1.45e-06,
      "loss": 5.7268,
      "step": 29
    },
    {
      "epoch": 0.40358744394618834,
      "grad_norm": 36.48906707763672,
      "learning_rate": 1.5e-06,
      "loss": 5.449,
      "step": 30
    },
    {
      "epoch": 0.4170403587443946,
      "grad_norm": 36.38510513305664,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 5.1884,
      "step": 31
    },
    {
      "epoch": 0.4304932735426009,
      "grad_norm": 35.656829833984375,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 4.899,
      "step": 32
    },
    {
      "epoch": 0.4439461883408072,
      "grad_norm": 34.09960174560547,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 4.5842,
      "step": 33
    },
    {
      "epoch": 0.45739910313901344,
      "grad_norm": 32.74240493774414,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 4.3009,
      "step": 34
    },
    {
      "epoch": 0.47085201793721976,
      "grad_norm": 31.867507934570312,
      "learning_rate": 1.75e-06,
      "loss": 3.9865,
      "step": 35
    },
    {
      "epoch": 0.484304932735426,
      "grad_norm": 30.741374969482422,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 3.6916,
      "step": 36
    },
    {
      "epoch": 0.4977578475336323,
      "grad_norm": 27.8775577545166,
      "learning_rate": 1.85e-06,
      "loss": 3.3719,
      "step": 37
    },
    {
      "epoch": 0.5112107623318386,
      "grad_norm": 25.97083282470703,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 3.0907,
      "step": 38
    },
    {
      "epoch": 0.5246636771300448,
      "grad_norm": 23.62006950378418,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 2.8336,
      "step": 39
    },
    {
      "epoch": 0.5381165919282511,
      "grad_norm": 23.80520248413086,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.5717,
      "step": 40
    },
    {
      "epoch": 0.5515695067264574,
      "grad_norm": 25.32924461364746,
      "learning_rate": 2.05e-06,
      "loss": 2.3658,
      "step": 41
    },
    {
      "epoch": 0.5650224215246636,
      "grad_norm": 26.20570182800293,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 2.2443,
      "step": 42
    },
    {
      "epoch": 0.57847533632287,
      "grad_norm": 24.581693649291992,
      "learning_rate": 2.15e-06,
      "loss": 1.926,
      "step": 43
    },
    {
      "epoch": 0.5919282511210763,
      "grad_norm": 24.414310455322266,
      "learning_rate": 2.2e-06,
      "loss": 1.7034,
      "step": 44
    },
    {
      "epoch": 0.6053811659192825,
      "grad_norm": 22.691083908081055,
      "learning_rate": 2.25e-06,
      "loss": 1.4857,
      "step": 45
    },
    {
      "epoch": 0.6188340807174888,
      "grad_norm": 20.669803619384766,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 1.2415,
      "step": 46
    },
    {
      "epoch": 0.6322869955156951,
      "grad_norm": 20.149641036987305,
      "learning_rate": 2.35e-06,
      "loss": 0.997,
      "step": 47
    },
    {
      "epoch": 0.6457399103139013,
      "grad_norm": 18.632596969604492,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.7552,
      "step": 48
    },
    {
      "epoch": 0.6591928251121076,
      "grad_norm": 16.93793296813965,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.5883,
      "step": 49
    },
    {
      "epoch": 0.672645739910314,
      "grad_norm": 14.432519912719727,
      "learning_rate": 2.5e-06,
      "loss": 0.4382,
      "step": 50
    },
    {
      "epoch": 0.6860986547085202,
      "grad_norm": 11.829660415649414,
      "learning_rate": 2.55e-06,
      "loss": 0.2983,
      "step": 51
    },
    {
      "epoch": 0.6995515695067265,
      "grad_norm": 8.680500030517578,
      "learning_rate": 2.6e-06,
      "loss": 0.1988,
      "step": 52
    },
    {
      "epoch": 0.7130044843049327,
      "grad_norm": 6.53156852722168,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.1589,
      "step": 53
    },
    {
      "epoch": 0.726457399103139,
      "grad_norm": 2.9756624698638916,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.0686,
      "step": 54
    },
    {
      "epoch": 0.7399103139013453,
      "grad_norm": 5.545580863952637,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.0865,
      "step": 55
    },
    {
      "epoch": 0.7533632286995515,
      "grad_norm": 4.045405387878418,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.0949,
      "step": 56
    },
    {
      "epoch": 0.7668161434977578,
      "grad_norm": 1.6688120365142822,
      "learning_rate": 2.85e-06,
      "loss": 0.0396,
      "step": 57
    },
    {
      "epoch": 0.7802690582959642,
      "grad_norm": 2.4520657062530518,
      "learning_rate": 2.9e-06,
      "loss": 0.0439,
      "step": 58
    },
    {
      "epoch": 0.7937219730941704,
      "grad_norm": 2.608729600906372,
      "learning_rate": 2.95e-06,
      "loss": 0.057,
      "step": 59
    },
    {
      "epoch": 0.8071748878923767,
      "grad_norm": 2.365234851837158,
      "learning_rate": 3e-06,
      "loss": 0.0547,
      "step": 60
    },
    {
      "epoch": 0.820627802690583,
      "grad_norm": 0.787550687789917,
      "learning_rate": 3.05e-06,
      "loss": 0.0209,
      "step": 61
    },
    {
      "epoch": 0.8340807174887892,
      "grad_norm": 0.7686442732810974,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.0221,
      "step": 62
    },
    {
      "epoch": 0.8475336322869955,
      "grad_norm": 1.2510555982589722,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.0165,
      "step": 63
    },
    {
      "epoch": 0.8609865470852018,
      "grad_norm": 0.8923770189285278,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.0187,
      "step": 64
    },
    {
      "epoch": 0.874439461883408,
      "grad_norm": 0.8052615523338318,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.0266,
      "step": 65
    },
    {
      "epoch": 0.8878923766816144,
      "grad_norm": 0.6710303425788879,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.0154,
      "step": 66
    },
    {
      "epoch": 0.9013452914798207,
      "grad_norm": 0.5213025212287903,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.0085,
      "step": 67
    },
    {
      "epoch": 0.9147982062780269,
      "grad_norm": 0.5758580565452576,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.0133,
      "step": 68
    },
    {
      "epoch": 0.9282511210762332,
      "grad_norm": 0.6828752160072327,
      "learning_rate": 3.45e-06,
      "loss": 0.0186,
      "step": 69
    },
    {
      "epoch": 0.9417040358744395,
      "grad_norm": 0.6814988255500793,
      "learning_rate": 3.5e-06,
      "loss": 0.0215,
      "step": 70
    },
    {
      "epoch": 0.9551569506726457,
      "grad_norm": 0.718296229839325,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.0204,
      "step": 71
    },
    {
      "epoch": 0.968609865470852,
      "grad_norm": 0.7816944122314453,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.0184,
      "step": 72
    },
    {
      "epoch": 0.9820627802690582,
      "grad_norm": 0.6058817505836487,
      "learning_rate": 3.65e-06,
      "loss": 0.0179,
      "step": 73
    },
    {
      "epoch": 0.9955156950672646,
      "grad_norm": 1.0496101379394531,
      "learning_rate": 3.7e-06,
      "loss": 0.032,
      "step": 74
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.0496101379394531,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0137,
      "step": 75
    },
    {
      "epoch": 1.0134529147982063,
      "grad_norm": 1.598720669746399,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.0211,
      "step": 76
    },
    {
      "epoch": 1.0269058295964126,
      "grad_norm": 0.7792187333106995,
      "learning_rate": 3.85e-06,
      "loss": 0.0213,
      "step": 77
    },
    {
      "epoch": 1.0403587443946187,
      "grad_norm": 0.7717252373695374,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.0151,
      "step": 78
    },
    {
      "epoch": 1.053811659192825,
      "grad_norm": 0.39334648847579956,
      "learning_rate": 3.95e-06,
      "loss": 0.0186,
      "step": 79
    },
    {
      "epoch": 1.0672645739910314,
      "grad_norm": 0.9775457382202148,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0043,
      "step": 80
    },
    {
      "epoch": 1.0807174887892377,
      "grad_norm": 1.2425150871276855,
      "learning_rate": 4.05e-06,
      "loss": 0.0179,
      "step": 81
    },
    {
      "epoch": 1.094170403587444,
      "grad_norm": 0.3884654939174652,
      "learning_rate": 4.1e-06,
      "loss": 0.008,
      "step": 82
    },
    {
      "epoch": 1.1076233183856503,
      "grad_norm": 0.4746466875076294,
      "learning_rate": 4.15e-06,
      "loss": 0.0144,
      "step": 83
    },
    {
      "epoch": 1.1210762331838564,
      "grad_norm": 0.6812214255332947,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.0072,
      "step": 84
    },
    {
      "epoch": 1.1345291479820627,
      "grad_norm": 0.5414469838142395,
      "learning_rate": 4.25e-06,
      "loss": 0.016,
      "step": 85
    },
    {
      "epoch": 1.147982062780269,
      "grad_norm": 0.8709024786949158,
      "learning_rate": 4.3e-06,
      "loss": 0.0154,
      "step": 86
    },
    {
      "epoch": 1.1614349775784754,
      "grad_norm": 0.3181096613407135,
      "learning_rate": 4.350000000000001e-06,
      "loss": 0.0039,
      "step": 87
    },
    {
      "epoch": 1.1748878923766817,
      "grad_norm": 0.2581265866756439,
      "learning_rate": 4.4e-06,
      "loss": 0.0014,
      "step": 88
    },
    {
      "epoch": 1.188340807174888,
      "grad_norm": 0.10870776325464249,
      "learning_rate": 4.450000000000001e-06,
      "loss": 0.0088,
      "step": 89
    },
    {
      "epoch": 1.201793721973094,
      "grad_norm": 0.45314452052116394,
      "learning_rate": 4.5e-06,
      "loss": 0.0019,
      "step": 90
    },
    {
      "epoch": 1.2152466367713004,
      "grad_norm": 0.7328381538391113,
      "learning_rate": 4.5500000000000005e-06,
      "loss": 0.0082,
      "step": 91
    },
    {
      "epoch": 1.2286995515695067,
      "grad_norm": 0.6641069650650024,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.0075,
      "step": 92
    },
    {
      "epoch": 1.242152466367713,
      "grad_norm": 0.27984222769737244,
      "learning_rate": 4.65e-06,
      "loss": 0.0009,
      "step": 93
    },
    {
      "epoch": 1.2556053811659194,
      "grad_norm": 0.8341127634048462,
      "learning_rate": 4.7e-06,
      "loss": 0.0204,
      "step": 94
    },
    {
      "epoch": 1.2690582959641254,
      "grad_norm": 1.0140557289123535,
      "learning_rate": 4.75e-06,
      "loss": 0.0228,
      "step": 95
    },
    {
      "epoch": 1.2825112107623318,
      "grad_norm": 0.9439787268638611,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.027,
      "step": 96
    },
    {
      "epoch": 1.295964125560538,
      "grad_norm": 1.3867762088775635,
      "learning_rate": 4.85e-06,
      "loss": 0.0223,
      "step": 97
    },
    {
      "epoch": 1.3094170403587444,
      "grad_norm": 0.4747941493988037,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.0048,
      "step": 98
    },
    {
      "epoch": 1.3228699551569507,
      "grad_norm": 0.5673424601554871,
      "learning_rate": 4.95e-06,
      "loss": 0.0033,
      "step": 99
    },
    {
      "epoch": 1.336322869955157,
      "grad_norm": 0.24510182440280914,
      "learning_rate": 5e-06,
      "loss": 0.0048,
      "step": 100
    },
    {
      "epoch": 1.3497757847533634,
      "grad_norm": 0.6084151268005371,
      "learning_rate": 4.99989574668946e-06,
      "loss": 0.032,
      "step": 101
    },
    {
      "epoch": 1.3632286995515694,
      "grad_norm": 0.606272280216217,
      "learning_rate": 4.999582995452842e-06,
      "loss": 0.0058,
      "step": 102
    },
    {
      "epoch": 1.3766816143497758,
      "grad_norm": 0.2270481288433075,
      "learning_rate": 4.999061772374426e-06,
      "loss": 0.0043,
      "step": 103
    },
    {
      "epoch": 1.390134529147982,
      "grad_norm": 0.2832431495189667,
      "learning_rate": 4.998332120925598e-06,
      "loss": 0.0079,
      "step": 104
    },
    {
      "epoch": 1.4035874439461884,
      "grad_norm": 0.44565466046333313,
      "learning_rate": 4.9973941019612235e-06,
      "loss": 0.017,
      "step": 105
    },
    {
      "epoch": 1.4170403587443947,
      "grad_norm": 0.3518397808074951,
      "learning_rate": 4.996247793714565e-06,
      "loss": 0.0057,
      "step": 106
    },
    {
      "epoch": 1.4304932735426008,
      "grad_norm": 0.41977858543395996,
      "learning_rate": 4.994893291790768e-06,
      "loss": 0.0056,
      "step": 107
    },
    {
      "epoch": 1.4439461883408071,
      "grad_norm": 0.22567600011825562,
      "learning_rate": 4.993330709158879e-06,
      "loss": 0.0067,
      "step": 108
    },
    {
      "epoch": 1.4573991031390134,
      "grad_norm": 0.2184637039899826,
      "learning_rate": 4.9915601761424304e-06,
      "loss": 0.0043,
      "step": 109
    },
    {
      "epoch": 1.4708520179372198,
      "grad_norm": 0.24834735691547394,
      "learning_rate": 4.989581840408562e-06,
      "loss": 0.0034,
      "step": 110
    },
    {
      "epoch": 1.484304932735426,
      "grad_norm": 0.13165591657161713,
      "learning_rate": 4.987395866955716e-06,
      "loss": 0.0041,
      "step": 111
    },
    {
      "epoch": 1.4977578475336322,
      "grad_norm": 0.27152982354164124,
      "learning_rate": 4.9850024380998655e-06,
      "loss": 0.0034,
      "step": 112
    },
    {
      "epoch": 1.5112107623318387,
      "grad_norm": 0.2793160676956177,
      "learning_rate": 4.982401753459317e-06,
      "loss": 0.0049,
      "step": 113
    },
    {
      "epoch": 1.5246636771300448,
      "grad_norm": 0.06674113124608994,
      "learning_rate": 4.979594029938058e-06,
      "loss": 0.0034,
      "step": 114
    },
    {
      "epoch": 1.5381165919282511,
      "grad_norm": 0.2601087689399719,
      "learning_rate": 4.976579501707665e-06,
      "loss": 0.0025,
      "step": 115
    },
    {
      "epoch": 1.5515695067264574,
      "grad_norm": 0.17075951397418976,
      "learning_rate": 4.973358420187776e-06,
      "loss": 0.0005,
      "step": 116
    },
    {
      "epoch": 1.5650224215246635,
      "grad_norm": 0.11211276799440384,
      "learning_rate": 4.969931054025122e-06,
      "loss": 0.0059,
      "step": 117
    },
    {
      "epoch": 1.57847533632287,
      "grad_norm": 0.5140838027000427,
      "learning_rate": 4.966297689071117e-06,
      "loss": 0.018,
      "step": 118
    },
    {
      "epoch": 1.5919282511210762,
      "grad_norm": 0.5356995463371277,
      "learning_rate": 4.962458628358021e-06,
      "loss": 0.0007,
      "step": 119
    },
    {
      "epoch": 1.6053811659192825,
      "grad_norm": 0.3967442214488983,
      "learning_rate": 4.958414192073665e-06,
      "loss": 0.014,
      "step": 120
    },
    {
      "epoch": 1.6188340807174888,
      "grad_norm": 0.4567921757698059,
      "learning_rate": 4.954164717534748e-06,
      "loss": 0.0027,
      "step": 121
    },
    {
      "epoch": 1.6322869955156951,
      "grad_norm": 0.4405613839626312,
      "learning_rate": 4.949710559158699e-06,
      "loss": 0.0135,
      "step": 122
    },
    {
      "epoch": 1.6457399103139014,
      "grad_norm": 0.7164422869682312,
      "learning_rate": 4.945052088434123e-06,
      "loss": 0.0207,
      "step": 123
    },
    {
      "epoch": 1.6591928251121075,
      "grad_norm": 0.47173142433166504,
      "learning_rate": 4.940189693889819e-06,
      "loss": 0.0019,
      "step": 124
    },
    {
      "epoch": 1.672645739910314,
      "grad_norm": 0.4606887996196747,
      "learning_rate": 4.9351237810623655e-06,
      "loss": 0.0125,
      "step": 125
    },
    {
      "epoch": 1.6860986547085202,
      "grad_norm": 0.7209401726722717,
      "learning_rate": 4.929854772462312e-06,
      "loss": 0.012,
      "step": 126
    },
    {
      "epoch": 1.6995515695067265,
      "grad_norm": 1.7617985010147095,
      "learning_rate": 4.924383107538929e-06,
      "loss": 0.0079,
      "step": 127
    },
    {
      "epoch": 1.7130044843049328,
      "grad_norm": 1.0861084461212158,
      "learning_rate": 4.918709242643563e-06,
      "loss": 0.0091,
      "step": 128
    },
    {
      "epoch": 1.726457399103139,
      "grad_norm": 0.11263061314821243,
      "learning_rate": 4.9128336509915746e-06,
      "loss": 0.0006,
      "step": 129
    },
    {
      "epoch": 1.7399103139013454,
      "grad_norm": 0.3411642909049988,
      "learning_rate": 4.906756822622865e-06,
      "loss": 0.0037,
      "step": 130
    },
    {
      "epoch": 1.7533632286995515,
      "grad_norm": 0.1550491899251938,
      "learning_rate": 4.900479264361017e-06,
      "loss": 0.0056,
      "step": 131
    },
    {
      "epoch": 1.7668161434977578,
      "grad_norm": 0.8448930382728577,
      "learning_rate": 4.894001499771015e-06,
      "loss": 0.0135,
      "step": 132
    },
    {
      "epoch": 1.7802690582959642,
      "grad_norm": 0.5105615258216858,
      "learning_rate": 4.887324069115582e-06,
      "loss": 0.009,
      "step": 133
    },
    {
      "epoch": 1.7937219730941703,
      "grad_norm": 0.5042226910591125,
      "learning_rate": 4.880447529310118e-06,
      "loss": 0.0022,
      "step": 134
    },
    {
      "epoch": 1.8071748878923768,
      "grad_norm": 0.15797697007656097,
      "learning_rate": 4.873372453876255e-06,
      "loss": 0.0073,
      "step": 135
    },
    {
      "epoch": 1.8206278026905829,
      "grad_norm": 0.47805944085121155,
      "learning_rate": 4.866099432894023e-06,
      "loss": 0.0084,
      "step": 136
    },
    {
      "epoch": 1.8340807174887892,
      "grad_norm": 0.3370952904224396,
      "learning_rate": 4.858629072952635e-06,
      "loss": 0.0037,
      "step": 137
    },
    {
      "epoch": 1.8475336322869955,
      "grad_norm": 0.30983835458755493,
      "learning_rate": 4.850961997099892e-06,
      "loss": 0.0024,
      "step": 138
    },
    {
      "epoch": 1.8609865470852018,
      "grad_norm": 0.2800588011741638,
      "learning_rate": 4.843098844790228e-06,
      "loss": 0.0032,
      "step": 139
    },
    {
      "epoch": 1.8744394618834082,
      "grad_norm": 0.2037343531847,
      "learning_rate": 4.835040271831371e-06,
      "loss": 0.0016,
      "step": 140
    },
    {
      "epoch": 1.8878923766816142,
      "grad_norm": 0.45981553196907043,
      "learning_rate": 4.826786950329646e-06,
      "loss": 0.0035,
      "step": 141
    },
    {
      "epoch": 1.9013452914798208,
      "grad_norm": 0.17092454433441162,
      "learning_rate": 4.818339568633926e-06,
      "loss": 0.0068,
      "step": 142
    },
    {
      "epoch": 1.9147982062780269,
      "grad_norm": 0.5339077711105347,
      "learning_rate": 4.809698831278217e-06,
      "loss": 0.0026,
      "step": 143
    },
    {
      "epoch": 1.9282511210762332,
      "grad_norm": 0.5208529829978943,
      "learning_rate": 4.800865458922899e-06,
      "loss": 0.0047,
      "step": 144
    },
    {
      "epoch": 1.9417040358744395,
      "grad_norm": 0.7488933801651001,
      "learning_rate": 4.79184018829462e-06,
      "loss": 0.0096,
      "step": 145
    },
    {
      "epoch": 1.9551569506726456,
      "grad_norm": 0.5727106332778931,
      "learning_rate": 4.782623772124854e-06,
      "loss": 0.001,
      "step": 146
    },
    {
      "epoch": 1.9686098654708521,
      "grad_norm": 0.3813195526599884,
      "learning_rate": 4.77321697908712e-06,
      "loss": 0.0085,
      "step": 147
    },
    {
      "epoch": 1.9820627802690582,
      "grad_norm": 0.5406109094619751,
      "learning_rate": 4.763620593732867e-06,
      "loss": 0.0017,
      "step": 148
    },
    {
      "epoch": 1.9955156950672646,
      "grad_norm": 0.391985148191452,
      "learning_rate": 4.7538354164260515e-06,
      "loss": 0.0019,
      "step": 149
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.391985148191452,
      "learning_rate": 4.743862263276376e-06,
      "loss": 0.0003,
      "step": 150
    },
    {
      "epoch": 2.013452914798206,
      "grad_norm": 0.10133524239063263,
      "learning_rate": 4.733701966071226e-06,
      "loss": 0.0012,
      "step": 151
    },
    {
      "epoch": 2.0269058295964126,
      "grad_norm": 0.2032414674758911,
      "learning_rate": 4.723355372206297e-06,
      "loss": 0.0001,
      "step": 152
    },
    {
      "epoch": 2.0403587443946187,
      "grad_norm": 0.00796876847743988,
      "learning_rate": 4.712823344614921e-06,
      "loss": 0.0025,
      "step": 153
    },
    {
      "epoch": 2.0538116591928253,
      "grad_norm": 0.36200040578842163,
      "learning_rate": 4.702106761696091e-06,
      "loss": 0.0003,
      "step": 154
    },
    {
      "epoch": 2.0672645739910314,
      "grad_norm": 0.19646115601062775,
      "learning_rate": 4.691206517241205e-06,
      "loss": 0.0009,
      "step": 155
    },
    {
      "epoch": 2.0807174887892375,
      "grad_norm": 0.06766581535339355,
      "learning_rate": 4.68012352035952e-06,
      "loss": 0.0001,
      "step": 156
    },
    {
      "epoch": 2.094170403587444,
      "grad_norm": 0.00797713827341795,
      "learning_rate": 4.668858695402326e-06,
      "loss": 0.0001,
      "step": 157
    },
    {
      "epoch": 2.10762331838565,
      "grad_norm": 0.020394539460539818,
      "learning_rate": 4.657412981885862e-06,
      "loss": 0.0002,
      "step": 158
    },
    {
      "epoch": 2.1210762331838566,
      "grad_norm": 0.017584379762411118,
      "learning_rate": 4.645787334412945e-06,
      "loss": 0.0002,
      "step": 159
    },
    {
      "epoch": 2.1345291479820627,
      "grad_norm": 0.07967082411050797,
      "learning_rate": 4.633982722593367e-06,
      "loss": 0.0003,
      "step": 160
    },
    {
      "epoch": 2.1479820627802693,
      "grad_norm": 0.01606675237417221,
      "learning_rate": 4.622000130963015e-06,
      "loss": 0.0003,
      "step": 161
    },
    {
      "epoch": 2.1614349775784754,
      "grad_norm": 0.06052660569548607,
      "learning_rate": 4.6098405589017685e-06,
      "loss": 0.0007,
      "step": 162
    },
    {
      "epoch": 2.1748878923766815,
      "grad_norm": 0.07991409301757812,
      "learning_rate": 4.597505020550138e-06,
      "loss": 0.0002,
      "step": 163
    },
    {
      "epoch": 2.188340807174888,
      "grad_norm": 0.04991272836923599,
      "learning_rate": 4.584994544724695e-06,
      "loss": 0.0001,
      "step": 164
    },
    {
      "epoch": 2.201793721973094,
      "grad_norm": 0.027111921459436417,
      "learning_rate": 4.572310174832255e-06,
      "loss": 0.0001,
      "step": 165
    },
    {
      "epoch": 2.2152466367713006,
      "grad_norm": 0.006566982250660658,
      "learning_rate": 4.5594529687828615e-06,
      "loss": 0.0,
      "step": 166
    },
    {
      "epoch": 2.2286995515695067,
      "grad_norm": 0.002437079790979624,
      "learning_rate": 4.546423998901549e-06,
      "loss": 0.0004,
      "step": 167
    },
    {
      "epoch": 2.242152466367713,
      "grad_norm": 0.08434150367975235,
      "learning_rate": 4.533224351838914e-06,
      "loss": 0.0001,
      "step": 168
    },
    {
      "epoch": 2.2556053811659194,
      "grad_norm": 0.013094129040837288,
      "learning_rate": 4.519855128480478e-06,
      "loss": 0.0001,
      "step": 169
    },
    {
      "epoch": 2.2690582959641254,
      "grad_norm": 0.002770340768620372,
      "learning_rate": 4.5063174438548775e-06,
      "loss": 0.0001,
      "step": 170
    },
    {
      "epoch": 2.282511210762332,
      "grad_norm": 0.021480072289705276,
      "learning_rate": 4.492612427040864e-06,
      "loss": 0.0001,
      "step": 171
    },
    {
      "epoch": 2.295964125560538,
      "grad_norm": 0.0028862387407571077,
      "learning_rate": 4.478741221073136e-06,
      "loss": 0.0001,
      "step": 172
    },
    {
      "epoch": 2.3094170403587446,
      "grad_norm": 0.01969303749501705,
      "learning_rate": 4.464704982847008e-06,
      "loss": 0.0,
      "step": 173
    },
    {
      "epoch": 2.3228699551569507,
      "grad_norm": 0.00244798487983644,
      "learning_rate": 4.450504883021923e-06,
      "loss": 0.0,
      "step": 174
    },
    {
      "epoch": 2.336322869955157,
      "grad_norm": 0.0036638586316257715,
      "learning_rate": 4.436142105923814e-06,
      "loss": 0.0009,
      "step": 175
    },
    {
      "epoch": 2.3497757847533634,
      "grad_norm": 0.4378701448440552,
      "learning_rate": 4.4216178494463305e-06,
      "loss": 0.0003,
      "step": 176
    },
    {
      "epoch": 2.3632286995515694,
      "grad_norm": 0.004919757135212421,
      "learning_rate": 4.406933324950929e-06,
      "loss": 0.0,
      "step": 177
    },
    {
      "epoch": 2.376681614349776,
      "grad_norm": 0.0061010573990643024,
      "learning_rate": 4.392089757165841e-06,
      "loss": 0.0001,
      "step": 178
    },
    {
      "epoch": 2.390134529147982,
      "grad_norm": 0.00750540429726243,
      "learning_rate": 4.377088384083935e-06,
      "loss": 0.0004,
      "step": 179
    },
    {
      "epoch": 2.403587443946188,
      "grad_norm": 0.18055735528469086,
      "learning_rate": 4.361930456859455e-06,
      "loss": 0.0001,
      "step": 180
    },
    {
      "epoch": 2.4170403587443947,
      "grad_norm": 0.00540179992094636,
      "learning_rate": 4.346617239703676e-06,
      "loss": 0.0017,
      "step": 181
    },
    {
      "epoch": 2.430493273542601,
      "grad_norm": 0.6051300764083862,
      "learning_rate": 4.3311500097794655e-06,
      "loss": 0.0002,
      "step": 182
    },
    {
      "epoch": 2.4439461883408073,
      "grad_norm": 0.04465539753437042,
      "learning_rate": 4.315530057094763e-06,
      "loss": 0.0001,
      "step": 183
    },
    {
      "epoch": 2.4573991031390134,
      "grad_norm": 0.009125534445047379,
      "learning_rate": 4.2997586843949905e-06,
      "loss": 0.0001,
      "step": 184
    },
    {
      "epoch": 2.4708520179372195,
      "grad_norm": 0.009754106402397156,
      "learning_rate": 4.2838372070544e-06,
      "loss": 0.0001,
      "step": 185
    },
    {
      "epoch": 2.484304932735426,
      "grad_norm": 0.03795509785413742,
      "learning_rate": 4.267766952966369e-06,
      "loss": 0.0006,
      "step": 186
    },
    {
      "epoch": 2.497757847533632,
      "grad_norm": 0.19477951526641846,
      "learning_rate": 4.25154926243265e-06,
      "loss": 0.0013,
      "step": 187
    },
    {
      "epoch": 2.5112107623318387,
      "grad_norm": 0.27783000469207764,
      "learning_rate": 4.2351854880515856e-06,
      "loss": 0.0001,
      "step": 188
    },
    {
      "epoch": 2.524663677130045,
      "grad_norm": 0.030597640201449394,
      "learning_rate": 4.218676994605295e-06,
      "loss": 0.0,
      "step": 189
    },
    {
      "epoch": 2.538116591928251,
      "grad_norm": 0.019212787970900536,
      "learning_rate": 4.202025158945855e-06,
      "loss": 0.0001,
      "step": 190
    },
    {
      "epoch": 2.5515695067264574,
      "grad_norm": 0.017139675095677376,
      "learning_rate": 4.185231369880461e-06,
      "loss": 0.0001,
      "step": 191
    },
    {
      "epoch": 2.5650224215246635,
      "grad_norm": 0.0013709627091884613,
      "learning_rate": 4.168297028055599e-06,
      "loss": 0.0002,
      "step": 192
    },
    {
      "epoch": 2.57847533632287,
      "grad_norm": 0.07277967780828476,
      "learning_rate": 4.151223545840225e-06,
      "loss": 0.0,
      "step": 193
    },
    {
      "epoch": 2.591928251121076,
      "grad_norm": 0.0014003290561959147,
      "learning_rate": 4.134012347207974e-06,
      "loss": 0.0001,
      "step": 194
    },
    {
      "epoch": 2.6053811659192823,
      "grad_norm": 0.04370618611574173,
      "learning_rate": 4.116664867618395e-06,
      "loss": 0.0004,
      "step": 195
    },
    {
      "epoch": 2.618834080717489,
      "grad_norm": 0.24697266519069672,
      "learning_rate": 4.099182553897228e-06,
      "loss": 0.0,
      "step": 196
    },
    {
      "epoch": 2.6322869955156953,
      "grad_norm": 0.0013013904681429267,
      "learning_rate": 4.081566864115741e-06,
      "loss": 0.0,
      "step": 197
    },
    {
      "epoch": 2.6457399103139014,
      "grad_norm": 0.001239327946677804,
      "learning_rate": 4.063819267469114e-06,
      "loss": 0.0,
      "step": 198
    },
    {
      "epoch": 2.6591928251121075,
      "grad_norm": 0.007082940544933081,
      "learning_rate": 4.04594124415391e-06,
      "loss": 0.0,
      "step": 199
    },
    {
      "epoch": 2.672645739910314,
      "grad_norm": 0.00556205864995718,
      "learning_rate": 4.027934285244624e-06,
      "loss": 0.0001,
      "step": 200
    },
    {
      "epoch": 2.68609865470852,
      "grad_norm": 0.025378312915563583,
      "learning_rate": 4.009799892569317e-06,
      "loss": 0.0001,
      "step": 201
    },
    {
      "epoch": 2.6995515695067267,
      "grad_norm": 0.006344004534184933,
      "learning_rate": 3.991539578584368e-06,
      "loss": 0.0,
      "step": 202
    },
    {
      "epoch": 2.713004484304933,
      "grad_norm": 0.0016575426561757922,
      "learning_rate": 3.973154866248323e-06,
      "loss": 0.0,
      "step": 203
    },
    {
      "epoch": 2.726457399103139,
      "grad_norm": 0.0020909749437123537,
      "learning_rate": 3.9546472888948825e-06,
      "loss": 0.0,
      "step": 204
    },
    {
      "epoch": 2.7399103139013454,
      "grad_norm": 0.004855802282691002,
      "learning_rate": 3.936018390105013e-06,
      "loss": 0.0,
      "step": 205
    },
    {
      "epoch": 2.7533632286995515,
      "grad_norm": 0.0082467095926404,
      "learning_rate": 3.917269723578212e-06,
      "loss": 0.0,
      "step": 206
    },
    {
      "epoch": 2.766816143497758,
      "grad_norm": 0.0013344286708161235,
      "learning_rate": 3.898402853002921e-06,
      "loss": 0.0,
      "step": 207
    },
    {
      "epoch": 2.780269058295964,
      "grad_norm": 0.0034061160404235125,
      "learning_rate": 3.879419351926115e-06,
      "loss": 0.0,
      "step": 208
    },
    {
      "epoch": 2.7937219730941703,
      "grad_norm": 0.011912211775779724,
      "learning_rate": 3.86032080362206e-06,
      "loss": 0.0,
      "step": 209
    },
    {
      "epoch": 2.807174887892377,
      "grad_norm": 0.00134057376999408,
      "learning_rate": 3.841108800960264e-06,
      "loss": 0.0,
      "step": 210
    },
    {
      "epoch": 2.820627802690583,
      "grad_norm": 0.0016560767544433475,
      "learning_rate": 3.8217849462726334e-06,
      "loss": 0.0,
      "step": 211
    },
    {
      "epoch": 2.8340807174887894,
      "grad_norm": 0.006285225041210651,
      "learning_rate": 3.802350851219826e-06,
      "loss": 0.0,
      "step": 212
    },
    {
      "epoch": 2.8475336322869955,
      "grad_norm": 0.0018534021219238639,
      "learning_rate": 3.7828081366568388e-06,
      "loss": 0.0,
      "step": 213
    },
    {
      "epoch": 2.8609865470852016,
      "grad_norm": 0.0041048116981983185,
      "learning_rate": 3.763158432497824e-06,
      "loss": 0.0,
      "step": 214
    },
    {
      "epoch": 2.874439461883408,
      "grad_norm": 0.0023216214030981064,
      "learning_rate": 3.743403377580149e-06,
      "loss": 0.0,
      "step": 215
    },
    {
      "epoch": 2.8878923766816142,
      "grad_norm": 0.000994804548099637,
      "learning_rate": 3.723544619527714e-06,
      "loss": 0.0,
      "step": 216
    },
    {
      "epoch": 2.901345291479821,
      "grad_norm": 0.003168656025081873,
      "learning_rate": 3.703583814613536e-06,
      "loss": 0.0,
      "step": 217
    },
    {
      "epoch": 2.914798206278027,
      "grad_norm": 0.0013909138506278396,
      "learning_rate": 3.6835226276216087e-06,
      "loss": 0.0,
      "step": 218
    },
    {
      "epoch": 2.928251121076233,
      "grad_norm": 0.008506865240633488,
      "learning_rate": 3.663362731708059e-06,
      "loss": 0.0,
      "step": 219
    },
    {
      "epoch": 2.9417040358744395,
      "grad_norm": 0.0017819993663579226,
      "learning_rate": 3.6431058082615966e-06,
      "loss": 0.0,
      "step": 220
    },
    {
      "epoch": 2.9551569506726456,
      "grad_norm": 0.0014212332898750901,
      "learning_rate": 3.6227535467632873e-06,
      "loss": 0.0,
      "step": 221
    },
    {
      "epoch": 2.968609865470852,
      "grad_norm": 0.003146026050671935,
      "learning_rate": 3.6023076446456415e-06,
      "loss": 0.0,
      "step": 222
    },
    {
      "epoch": 2.9820627802690582,
      "grad_norm": 0.0012437553377822042,
      "learning_rate": 3.581769807151044e-06,
      "loss": 0.0,
      "step": 223
    },
    {
      "epoch": 2.9955156950672643,
      "grad_norm": 0.017311880365014076,
      "learning_rate": 3.561141747189538e-06,
      "loss": 0.0001,
      "step": 224
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.012313771061599255,
      "learning_rate": 3.5404251851959537e-06,
      "loss": 0.0,
      "step": 225
    },
    {
      "epoch": 3.013452914798206,
      "grad_norm": 0.0043451120145618916,
      "learning_rate": 3.519621848986428e-06,
      "loss": 0.0,
      "step": 226
    },
    {
      "epoch": 3.0269058295964126,
      "grad_norm": 0.002464739605784416,
      "learning_rate": 3.498733473614298e-06,
      "loss": 0.0,
      "step": 227
    },
    {
      "epoch": 3.0403587443946187,
      "grad_norm": 0.0019529856508597732,
      "learning_rate": 3.47776180122539e-06,
      "loss": 0.0,
      "step": 228
    },
    {
      "epoch": 3.0538116591928253,
      "grad_norm": 0.0013189928140491247,
      "learning_rate": 3.4567085809127247e-06,
      "loss": 0.0,
      "step": 229
    },
    {
      "epoch": 3.0672645739910314,
      "grad_norm": 0.0021529668010771275,
      "learning_rate": 3.435575568570633e-06,
      "loss": 0.0,
      "step": 230
    },
    {
      "epoch": 3.0807174887892375,
      "grad_norm": 0.007290184032171965,
      "learning_rate": 3.4143645267483144e-06,
      "loss": 0.0,
      "step": 231
    },
    {
      "epoch": 3.094170403587444,
      "grad_norm": 0.001345694880001247,
      "learning_rate": 3.393077224502832e-06,
      "loss": 0.0,
      "step": 232
    },
    {
      "epoch": 3.10762331838565,
      "grad_norm": 0.004343180451542139,
      "learning_rate": 3.3717154372515716e-06,
      "loss": 0.0,
      "step": 233
    },
    {
      "epoch": 3.1210762331838566,
      "grad_norm": 0.0010816323338076472,
      "learning_rate": 3.350280946624166e-06,
      "loss": 0.0,
      "step": 234
    },
    {
      "epoch": 3.1345291479820627,
      "grad_norm": 0.003842687699943781,
      "learning_rate": 3.3287755403139007e-06,
      "loss": 0.0,
      "step": 235
    },
    {
      "epoch": 3.1479820627802693,
      "grad_norm": 0.0013102421071380377,
      "learning_rate": 3.3072010119286156e-06,
      "loss": 0.0,
      "step": 236
    },
    {
      "epoch": 3.1614349775784754,
      "grad_norm": 0.0014620574656873941,
      "learning_rate": 3.2855591608411203e-06,
      "loss": 0.0,
      "step": 237
    },
    {
      "epoch": 3.1748878923766815,
      "grad_norm": 0.0007613594643771648,
      "learning_rate": 3.2638517920391095e-06,
      "loss": 0.0,
      "step": 238
    },
    {
      "epoch": 3.188340807174888,
      "grad_norm": 0.001927120960317552,
      "learning_rate": 3.2420807159746333e-06,
      "loss": 0.0,
      "step": 239
    },
    {
      "epoch": 3.201793721973094,
      "grad_norm": 0.0047145108692348,
      "learning_rate": 3.2202477484130947e-06,
      "loss": 0.0,
      "step": 240
    },
    {
      "epoch": 3.2152466367713006,
      "grad_norm": 0.001525243278592825,
      "learning_rate": 3.1983547102818104e-06,
      "loss": 0.0,
      "step": 241
    },
    {
      "epoch": 3.2286995515695067,
      "grad_norm": 0.0008274471038021147,
      "learning_rate": 3.1764034275181436e-06,
      "loss": 0.0,
      "step": 242
    },
    {
      "epoch": 3.242152466367713,
      "grad_norm": 0.0009357924573123455,
      "learning_rate": 3.1543957309172136e-06,
      "loss": 0.0,
      "step": 243
    },
    {
      "epoch": 3.2556053811659194,
      "grad_norm": 0.0016225146828219295,
      "learning_rate": 3.132333455979202e-06,
      "loss": 0.0,
      "step": 244
    },
    {
      "epoch": 3.2690582959641254,
      "grad_norm": 0.013506707735359669,
      "learning_rate": 3.1102184427562696e-06,
      "loss": 0.0001,
      "step": 245
    },
    {
      "epoch": 3.282511210762332,
      "grad_norm": 0.0010258476249873638,
      "learning_rate": 3.0880525356990898e-06,
      "loss": 0.0,
      "step": 246
    },
    {
      "epoch": 3.295964125560538,
      "grad_norm": 0.006462691817432642,
      "learning_rate": 3.0658375835030148e-06,
      "loss": 0.0,
      "step": 247
    },
    {
      "epoch": 3.3094170403587446,
      "grad_norm": 0.0011441456153988838,
      "learning_rate": 3.043575438953893e-06,
      "loss": 0.0,
      "step": 248
    },
    {
      "epoch": 3.3228699551569507,
      "grad_norm": 0.000751970277633518,
      "learning_rate": 3.02126795877354e-06,
      "loss": 0.0,
      "step": 249
    },
    {
      "epoch": 3.336322869955157,
      "grad_norm": 0.006623424123972654,
      "learning_rate": 2.9989170034648823e-06,
      "loss": 0.0,
      "step": 250
    },
    {
      "epoch": 3.3497757847533634,
      "grad_norm": 0.0021056546829640865,
      "learning_rate": 2.9765244371567873e-06,
      "loss": 0.0,
      "step": 251
    },
    {
      "epoch": 3.3632286995515694,
      "grad_norm": 0.003343602642416954,
      "learning_rate": 2.9540921274485913e-06,
      "loss": 0.0,
      "step": 252
    },
    {
      "epoch": 3.376681614349776,
      "grad_norm": 0.0032404386438429356,
      "learning_rate": 2.9316219452543342e-06,
      "loss": 0.0,
      "step": 253
    },
    {
      "epoch": 3.390134529147982,
      "grad_norm": 0.02200383134186268,
      "learning_rate": 2.9091157646467205e-06,
      "loss": 0.0001,
      "step": 254
    },
    {
      "epoch": 3.403587443946188,
      "grad_norm": 0.0015861240681260824,
      "learning_rate": 2.886575462700821e-06,
      "loss": 0.0,
      "step": 255
    },
    {
      "epoch": 3.4170403587443947,
      "grad_norm": 0.0023104625288397074,
      "learning_rate": 2.864002919337513e-06,
      "loss": 0.0,
      "step": 256
    },
    {
      "epoch": 3.430493273542601,
      "grad_norm": 0.0009963945485651493,
      "learning_rate": 2.8414000171666952e-06,
      "loss": 0.0,
      "step": 257
    },
    {
      "epoch": 3.4439461883408073,
      "grad_norm": 0.006071928422898054,
      "learning_rate": 2.81876864133027e-06,
      "loss": 0.0,
      "step": 258
    },
    {
      "epoch": 3.4573991031390134,
      "grad_norm": 0.003969075623899698,
      "learning_rate": 2.7961106793449217e-06,
      "loss": 0.0,
      "step": 259
    },
    {
      "epoch": 3.4708520179372195,
      "grad_norm": 0.0010353871621191502,
      "learning_rate": 2.773428020944687e-06,
      "loss": 0.0,
      "step": 260
    },
    {
      "epoch": 3.484304932735426,
      "grad_norm": 0.003665305208414793,
      "learning_rate": 2.7507225579233487e-06,
      "loss": 0.0,
      "step": 261
    },
    {
      "epoch": 3.497757847533632,
      "grad_norm": 0.003311133710667491,
      "learning_rate": 2.727996183976659e-06,
      "loss": 0.0,
      "step": 262
    },
    {
      "epoch": 3.5112107623318387,
      "grad_norm": 0.004625072702765465,
      "learning_rate": 2.705250794544393e-06,
      "loss": 0.0,
      "step": 263
    },
    {
      "epoch": 3.524663677130045,
      "grad_norm": 0.0023010042496025562,
      "learning_rate": 2.682488286652269e-06,
      "loss": 0.0,
      "step": 264
    },
    {
      "epoch": 3.538116591928251,
      "grad_norm": 0.0008537416579201818,
      "learning_rate": 2.6597105587537307e-06,
      "loss": 0.0,
      "step": 265
    },
    {
      "epoch": 3.5515695067264574,
      "grad_norm": 0.0014414336765184999,
      "learning_rate": 2.6369195105716087e-06,
      "loss": 0.0,
      "step": 266
    },
    {
      "epoch": 3.5650224215246635,
      "grad_norm": 0.003060834715142846,
      "learning_rate": 2.614117042939685e-06,
      "loss": 0.0,
      "step": 267
    },
    {
      "epoch": 3.57847533632287,
      "grad_norm": 0.002594274003058672,
      "learning_rate": 2.591305057644148e-06,
      "loss": 0.0,
      "step": 268
    },
    {
      "epoch": 3.591928251121076,
      "grad_norm": 0.0009433673694729805,
      "learning_rate": 2.5684854572649876e-06,
      "loss": 0.0,
      "step": 269
    },
    {
      "epoch": 3.6053811659192823,
      "grad_norm": 0.000922717503271997,
      "learning_rate": 2.5456601450173123e-06,
      "loss": 0.0,
      "step": 270
    },
    {
      "epoch": 3.618834080717489,
      "grad_norm": 0.0013827934162691236,
      "learning_rate": 2.522831024592615e-06,
      "loss": 0.0,
      "step": 271
    },
    {
      "epoch": 3.6322869955156953,
      "grad_norm": 0.0007690931670367718,
      "learning_rate": 2.5e-06,
      "loss": 0.0,
      "step": 272
    },
    {
      "epoch": 3.6457399103139014,
      "grad_norm": 0.002565343165770173,
      "learning_rate": 2.4771689754073856e-06,
      "loss": 0.0,
      "step": 273
    },
    {
      "epoch": 3.6591928251121075,
      "grad_norm": 0.0013943302910774946,
      "learning_rate": 2.454339854982688e-06,
      "loss": 0.0,
      "step": 274
    },
    {
      "epoch": 3.672645739910314,
      "grad_norm": 0.0006668591522611678,
      "learning_rate": 2.4315145427350132e-06,
      "loss": 0.0,
      "step": 275
    },
    {
      "epoch": 3.68609865470852,
      "grad_norm": 0.0025589216966181993,
      "learning_rate": 2.408694942355853e-06,
      "loss": 0.0,
      "step": 276
    },
    {
      "epoch": 3.6995515695067267,
      "grad_norm": 0.001420054235495627,
      "learning_rate": 2.3858829570603157e-06,
      "loss": 0.0,
      "step": 277
    },
    {
      "epoch": 3.713004484304933,
      "grad_norm": 0.0014220779994502664,
      "learning_rate": 2.363080489428391e-06,
      "loss": 0.0,
      "step": 278
    },
    {
      "epoch": 3.726457399103139,
      "grad_norm": 0.0009400748531334102,
      "learning_rate": 2.3402894412462697e-06,
      "loss": 0.0,
      "step": 279
    },
    {
      "epoch": 3.7399103139013454,
      "grad_norm": 0.0006919830339029431,
      "learning_rate": 2.317511713347731e-06,
      "loss": 0.0,
      "step": 280
    },
    {
      "epoch": 3.7533632286995515,
      "grad_norm": 0.0011200032895430923,
      "learning_rate": 2.2947492054556075e-06,
      "loss": 0.0,
      "step": 281
    },
    {
      "epoch": 3.766816143497758,
      "grad_norm": 0.0008829529979266226,
      "learning_rate": 2.272003816023341e-06,
      "loss": 0.0,
      "step": 282
    },
    {
      "epoch": 3.780269058295964,
      "grad_norm": 0.0009032113594003022,
      "learning_rate": 2.2492774420766517e-06,
      "loss": 0.0,
      "step": 283
    },
    {
      "epoch": 3.7937219730941703,
      "grad_norm": 0.0012500348966568708,
      "learning_rate": 2.2265719790553147e-06,
      "loss": 0.0,
      "step": 284
    },
    {
      "epoch": 3.807174887892377,
      "grad_norm": 0.0008029688615351915,
      "learning_rate": 2.20388932065508e-06,
      "loss": 0.0,
      "step": 285
    },
    {
      "epoch": 3.820627802690583,
      "grad_norm": 0.0015973382396623492,
      "learning_rate": 2.1812313586697307e-06,
      "loss": 0.0,
      "step": 286
    },
    {
      "epoch": 3.8340807174887894,
      "grad_norm": 0.0021750489249825478,
      "learning_rate": 2.1585999828333065e-06,
      "loss": 0.0,
      "step": 287
    },
    {
      "epoch": 3.8475336322869955,
      "grad_norm": 0.004780885297805071,
      "learning_rate": 2.1359970806624886e-06,
      "loss": 0.0,
      "step": 288
    },
    {
      "epoch": 3.8609865470852016,
      "grad_norm": 0.0007556549389846623,
      "learning_rate": 2.11342453729918e-06,
      "loss": 0.0,
      "step": 289
    },
    {
      "epoch": 3.874439461883408,
      "grad_norm": 0.0006669393624179065,
      "learning_rate": 2.0908842353532803e-06,
      "loss": 0.0,
      "step": 290
    },
    {
      "epoch": 3.8878923766816142,
      "grad_norm": 0.001046078628860414,
      "learning_rate": 2.0683780547456666e-06,
      "loss": 0.0,
      "step": 291
    },
    {
      "epoch": 3.901345291479821,
      "grad_norm": 0.004534538835287094,
      "learning_rate": 2.045907872551409e-06,
      "loss": 0.0,
      "step": 292
    },
    {
      "epoch": 3.914798206278027,
      "grad_norm": 0.0008524219738319516,
      "learning_rate": 2.0234755628432135e-06,
      "loss": 0.0,
      "step": 293
    },
    {
      "epoch": 3.928251121076233,
      "grad_norm": 0.0006630662246607244,
      "learning_rate": 2.0010829965351185e-06,
      "loss": 0.0,
      "step": 294
    },
    {
      "epoch": 3.9417040358744395,
      "grad_norm": 0.008820832706987858,
      "learning_rate": 1.978732041226461e-06,
      "loss": 0.0,
      "step": 295
    },
    {
      "epoch": 3.9551569506726456,
      "grad_norm": 0.0007411285769194365,
      "learning_rate": 1.956424561046108e-06,
      "loss": 0.0,
      "step": 296
    }
  ],
  "logging_steps": 1,
  "max_steps": 444,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 74,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.586020432455926e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}