{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 540.0,
  "global_step": 540,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003703703703703704,
      "grad_norm": 9.5,
      "learning_rate": 2.787878787878788e-07,
      "loss": 0.7464,
      "step": 2
    },
    {
      "epoch": 0.007407407407407408,
      "grad_norm": 9.6875,
      "learning_rate": 5.575757575757576e-07,
      "loss": 0.7497,
      "step": 4
    },
    {
      "epoch": 0.011111111111111112,
      "grad_norm": 9.6875,
      "learning_rate": 8.363636363636364e-07,
      "loss": 0.7544,
      "step": 6
    },
    {
      "epoch": 0.014814814814814815,
      "grad_norm": 9.375,
      "learning_rate": 1.1151515151515153e-06,
      "loss": 0.7549,
      "step": 8
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 9.6875,
      "learning_rate": 1.393939393939394e-06,
      "loss": 0.7816,
      "step": 10
    },
    {
      "epoch": 0.022222222222222223,
      "grad_norm": 9.5,
      "learning_rate": 1.6727272727272728e-06,
      "loss": 0.7629,
      "step": 12
    },
    {
      "epoch": 0.025925925925925925,
      "grad_norm": 9.375,
      "learning_rate": 1.9515151515151518e-06,
      "loss": 0.777,
      "step": 14
    },
    {
      "epoch": 0.02962962962962963,
      "grad_norm": 9.625,
      "learning_rate": 2.2303030303030305e-06,
      "loss": 0.7604,
      "step": 16
    },
    {
      "epoch": 0.03333333333333333,
      "grad_norm": 9.3125,
      "learning_rate": 2.509090909090909e-06,
      "loss": 0.7431,
      "step": 18
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 9.125,
      "learning_rate": 2.787878787878788e-06,
      "loss": 0.7333,
      "step": 20
    },
    {
      "epoch": 0.040740740740740744,
      "grad_norm": 9.875,
      "learning_rate": 3.0666666666666664e-06,
      "loss": 0.7854,
      "step": 22
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 9.5625,
      "learning_rate": 3.3454545454545456e-06,
      "loss": 0.7264,
      "step": 24
    },
    {
      "epoch": 0.04814814814814815,
      "grad_norm": 9.5625,
      "learning_rate": 3.624242424242424e-06,
      "loss": 0.7634,
      "step": 26
    },
    {
      "epoch": 0.05185185185185185,
      "grad_norm": 9.4375,
      "learning_rate": 3.9030303030303035e-06,
      "loss": 0.7677,
      "step": 28
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 9.5,
      "learning_rate": 4.1818181818181814e-06,
      "loss": 0.76,
      "step": 30
    },
    {
      "epoch": 0.05925925925925926,
      "grad_norm": 9.625,
      "learning_rate": 4.460606060606061e-06,
      "loss": 0.7615,
      "step": 32
    },
    {
      "epoch": 0.06296296296296296,
      "grad_norm": 9.5,
      "learning_rate": 4.59998964610166e-06,
      "loss": 0.7493,
      "step": 34
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 9.4375,
      "learning_rate": 4.599906815474259e-06,
      "loss": 0.7541,
      "step": 36
    },
    {
      "epoch": 0.07037037037037037,
      "grad_norm": 9.5625,
      "learning_rate": 4.599741157202478e-06,
      "loss": 0.7721,
      "step": 38
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 9.125,
      "learning_rate": 4.599492677252244e-06,
      "loss": 0.7385,
      "step": 40
    },
    {
      "epoch": 0.07777777777777778,
      "grad_norm": 9.375,
      "learning_rate": 4.599161384572187e-06,
      "loss": 0.7255,
      "step": 42
    },
    {
      "epoch": 0.08148148148148149,
      "grad_norm": 9.375,
      "learning_rate": 4.5987472910933085e-06,
      "loss": 0.7548,
      "step": 44
    },
    {
      "epoch": 0.08518518518518518,
      "grad_norm": 9.3125,
      "learning_rate": 4.598250411728554e-06,
      "loss": 0.747,
      "step": 46
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 9.3125,
      "learning_rate": 4.597670764372279e-06,
      "loss": 0.7368,
      "step": 48
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 9.25,
      "learning_rate": 4.5970083698996e-06,
      "loss": 0.7536,
      "step": 50
    },
    {
      "epoch": 0.0962962962962963,
      "grad_norm": 9.3125,
      "learning_rate": 4.596263252165647e-06,
      "loss": 0.7242,
      "step": 52
    },
    {
      "epoch": 0.1,
      "grad_norm": 9.375,
      "learning_rate": 4.595435438004701e-06,
      "loss": 0.7248,
      "step": 54
    },
    {
      "epoch": 0.1037037037037037,
      "grad_norm": 9.1875,
      "learning_rate": 4.594524957229229e-06,
      "loss": 0.7113,
      "step": 56
    },
    {
      "epoch": 0.10740740740740741,
      "grad_norm": 9.375,
      "learning_rate": 4.593531842628811e-06,
      "loss": 0.7352,
      "step": 58
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 8.875,
      "learning_rate": 4.592456129968958e-06,
      "loss": 0.6914,
      "step": 60
    },
    {
      "epoch": 0.11481481481481481,
      "grad_norm": 9.125,
      "learning_rate": 4.591297857989825e-06,
      "loss": 0.6962,
      "step": 62
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 8.9375,
      "learning_rate": 4.590057068404815e-06,
      "loss": 0.7002,
      "step": 64
    },
    {
      "epoch": 0.12222222222222222,
      "grad_norm": 9.1875,
      "learning_rate": 4.588733805899076e-06,
      "loss": 0.7196,
      "step": 66
    },
    {
      "epoch": 0.1259259259259259,
      "grad_norm": 9.5625,
      "learning_rate": 4.587328118127894e-06,
      "loss": 0.7366,
      "step": 68
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 9.0625,
      "learning_rate": 4.585840055714976e-06,
      "loss": 0.7042,
      "step": 70
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 9.1875,
      "learning_rate": 4.584269672250625e-06,
      "loss": 0.6914,
      "step": 72
    },
    {
      "epoch": 0.13703703703703704,
      "grad_norm": 9.1875,
      "learning_rate": 4.582617024289811e-06,
      "loss": 0.7045,
      "step": 74
    },
    {
      "epoch": 0.14074074074074075,
      "grad_norm": 9.1875,
      "learning_rate": 4.5808821713501374e-06,
      "loss": 0.7275,
      "step": 76
    },
    {
      "epoch": 0.14444444444444443,
      "grad_norm": 9.125,
      "learning_rate": 4.579065175909692e-06,
      "loss": 0.6943,
      "step": 78
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 8.9375,
      "learning_rate": 4.577166103404801e-06,
      "loss": 0.6792,
      "step": 80
    },
    {
      "epoch": 0.15185185185185185,
      "grad_norm": 9.1875,
      "learning_rate": 4.5751850222276705e-06,
      "loss": 0.6854,
      "step": 82
    },
    {
      "epoch": 0.15555555555555556,
      "grad_norm": 8.875,
      "learning_rate": 4.573122003723925e-06,
      "loss": 0.6675,
      "step": 84
    },
    {
      "epoch": 0.15925925925925927,
      "grad_norm": 9.625,
      "learning_rate": 4.5709771221900375e-06,
      "loss": 0.6882,
      "step": 86
    },
    {
      "epoch": 0.16296296296296298,
      "grad_norm": 8.875,
      "learning_rate": 4.568750454870651e-06,
      "loss": 0.675,
      "step": 88
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 9.0625,
      "learning_rate": 4.5664420819558035e-06,
      "loss": 0.6996,
      "step": 90
    },
    {
      "epoch": 0.17037037037037037,
      "grad_norm": 9.375,
      "learning_rate": 4.564052086578031e-06,
      "loss": 0.7039,
      "step": 92
    },
    {
      "epoch": 0.17407407407407408,
      "grad_norm": 8.8125,
      "learning_rate": 4.561580554809381e-06,
      "loss": 0.6587,
      "step": 94
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 9.0,
      "learning_rate": 4.559027575658309e-06,
      "loss": 0.6556,
      "step": 96
    },
    {
      "epoch": 0.1814814814814815,
      "grad_norm": 8.6875,
      "learning_rate": 4.556393241066476e-06,
      "loss": 0.6617,
      "step": 98
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 9.375,
      "learning_rate": 4.553677645905431e-06,
      "loss": 0.6828,
      "step": 100
    },
    {
      "epoch": 0.18888888888888888,
      "grad_norm": 8.625,
      "learning_rate": 4.550880887973204e-06,
      "loss": 0.6371,
      "step": 102
    },
    {
      "epoch": 0.1925925925925926,
      "grad_norm": 8.8125,
      "learning_rate": 4.548003067990776e-06,
      "loss": 0.65,
      "step": 104
    },
    {
      "epoch": 0.1962962962962963,
      "grad_norm": 8.875,
      "learning_rate": 4.545044289598454e-06,
      "loss": 0.6718,
      "step": 106
    },
    {
      "epoch": 0.2,
      "grad_norm": 9.0625,
      "learning_rate": 4.54200465935214e-06,
      "loss": 0.6834,
      "step": 108
    },
    {
      "epoch": 0.2037037037037037,
      "grad_norm": 8.9375,
      "learning_rate": 4.5388842867194925e-06,
      "loss": 0.6696,
      "step": 110
    },
    {
      "epoch": 0.2074074074074074,
      "grad_norm": 8.8125,
      "learning_rate": 4.535683284075984e-06,
      "loss": 0.6811,
      "step": 112
    },
    {
      "epoch": 0.2111111111111111,
      "grad_norm": 8.875,
      "learning_rate": 4.5324017667008535e-06,
      "loss": 0.666,
      "step": 114
    },
    {
      "epoch": 0.21481481481481482,
      "grad_norm": 9.125,
      "learning_rate": 4.529039852772956e-06,
      "loss": 0.6534,
      "step": 116
    },
    {
      "epoch": 0.21851851851851853,
      "grad_norm": 9.0,
      "learning_rate": 4.525597663366506e-06,
      "loss": 0.66,
      "step": 118
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 8.6875,
      "learning_rate": 4.522075322446718e-06,
      "loss": 0.6418,
      "step": 120
    },
    {
      "epoch": 0.22592592592592592,
      "grad_norm": 9.125,
      "learning_rate": 4.51847295686534e-06,
      "loss": 0.6477,
      "step": 122
    },
    {
      "epoch": 0.22962962962962963,
      "grad_norm": 8.75,
      "learning_rate": 4.514790696356086e-06,
      "loss": 0.6517,
      "step": 124
    },
    {
      "epoch": 0.23333333333333334,
      "grad_norm": 9.125,
      "learning_rate": 4.511028673529967e-06,
      "loss": 0.6605,
      "step": 126
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 8.75,
      "learning_rate": 4.507187023870511e-06,
      "loss": 0.6302,
      "step": 128
    },
    {
      "epoch": 0.24074074074074073,
      "grad_norm": 8.75,
      "learning_rate": 4.503265885728883e-06,
      "loss": 0.6274,
      "step": 130
    },
    {
      "epoch": 0.24444444444444444,
      "grad_norm": 8.625,
      "learning_rate": 4.499265400318908e-06,
      "loss": 0.6427,
      "step": 132
    },
    {
      "epoch": 0.24814814814814815,
      "grad_norm": 8.5,
      "learning_rate": 4.49518571171198e-06,
      "loss": 0.6336,
      "step": 134
    },
    {
      "epoch": 0.2518518518518518,
      "grad_norm": 9.0,
      "learning_rate": 4.4910269668318775e-06,
      "loss": 0.6704,
      "step": 136
    },
    {
      "epoch": 0.25555555555555554,
      "grad_norm": 8.8125,
      "learning_rate": 4.486789315449469e-06,
      "loss": 0.6276,
      "step": 138
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 8.875,
      "learning_rate": 4.4824729101773205e-06,
      "loss": 0.6456,
      "step": 140
    },
    {
      "epoch": 0.26296296296296295,
      "grad_norm": 8.875,
      "learning_rate": 4.4780779064642e-06,
      "loss": 0.6438,
      "step": 142
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 8.875,
      "learning_rate": 4.473604462589479e-06,
      "loss": 0.6319,
      "step": 144
    },
    {
      "epoch": 0.27037037037037037,
      "grad_norm": 9.5625,
      "learning_rate": 4.469052739657432e-06,
      "loss": 0.6766,
      "step": 146
    },
    {
      "epoch": 0.2740740740740741,
      "grad_norm": 8.875,
      "learning_rate": 4.464422901591434e-06,
      "loss": 0.6316,
      "step": 148
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 8.6875,
      "learning_rate": 4.459715115128058e-06,
      "loss": 0.629,
      "step": 150
    },
    {
      "epoch": 0.2814814814814815,
      "grad_norm": 8.9375,
      "learning_rate": 4.454929549811071e-06,
      "loss": 0.6362,
      "step": 152
    },
    {
      "epoch": 0.2851851851851852,
      "grad_norm": 8.75,
      "learning_rate": 4.450066377985326e-06,
      "loss": 0.6216,
      "step": 154
    },
    {
      "epoch": 0.28888888888888886,
      "grad_norm": 9.0625,
      "learning_rate": 4.445125774790555e-06,
      "loss": 0.6535,
      "step": 156
    },
    {
      "epoch": 0.29259259259259257,
      "grad_norm": 8.8125,
      "learning_rate": 4.440107918155065e-06,
      "loss": 0.6278,
      "step": 158
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 8.8125,
      "learning_rate": 4.435012988789327e-06,
      "loss": 0.6178,
      "step": 160
    },
    {
      "epoch": 0.3,
      "grad_norm": 8.4375,
      "learning_rate": 4.429841170179471e-06,
      "loss": 0.6243,
      "step": 162
    },
    {
      "epoch": 0.3037037037037037,
      "grad_norm": 8.875,
      "learning_rate": 4.4245926485806745e-06,
      "loss": 0.6201,
      "step": 164
    },
    {
      "epoch": 0.3074074074074074,
      "grad_norm": 8.75,
      "learning_rate": 4.419267613010454e-06,
      "loss": 0.6267,
      "step": 166
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 8.75,
      "learning_rate": 4.413866255241867e-06,
      "loss": 0.6474,
      "step": 168
    },
    {
      "epoch": 0.3148148148148148,
      "grad_norm": 8.4375,
      "learning_rate": 4.4083887697965915e-06,
      "loss": 0.6021,
      "step": 170
    },
    {
      "epoch": 0.31851851851851853,
      "grad_norm": 8.5625,
      "learning_rate": 4.402835353937933e-06,
      "loss": 0.6044,
      "step": 172
    },
    {
      "epoch": 0.32222222222222224,
      "grad_norm": 8.9375,
      "learning_rate": 4.397206207663713e-06,
      "loss": 0.6293,
      "step": 174
    },
    {
      "epoch": 0.32592592592592595,
      "grad_norm": 8.6875,
      "learning_rate": 4.391501533699068e-06,
      "loss": 0.6039,
      "step": 176
    },
    {
      "epoch": 0.3296296296296296,
      "grad_norm": 8.875,
      "learning_rate": 4.385721537489152e-06,
      "loss": 0.6116,
      "step": 178
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 8.4375,
      "learning_rate": 4.379866427191734e-06,
      "loss": 0.5855,
      "step": 180
    },
    {
      "epoch": 0.337037037037037,
      "grad_norm": 8.625,
      "learning_rate": 4.373936413669699e-06,
      "loss": 0.5902,
      "step": 182
    },
    {
      "epoch": 0.34074074074074073,
      "grad_norm": 8.25,
      "learning_rate": 4.367931710483465e-06,
      "loss": 0.6014,
      "step": 184
    },
    {
      "epoch": 0.34444444444444444,
      "grad_norm": 8.625,
      "learning_rate": 4.361852533883278e-06,
      "loss": 0.6035,
      "step": 186
    },
    {
      "epoch": 0.34814814814814815,
      "grad_norm": 8.3125,
      "learning_rate": 4.355699102801434e-06,
      "loss": 0.5791,
      "step": 188
    },
    {
      "epoch": 0.35185185185185186,
      "grad_norm": 8.6875,
      "learning_rate": 4.349471638844388e-06,
      "loss": 0.5952,
      "step": 190
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 8.9375,
      "learning_rate": 4.3431703662847814e-06,
      "loss": 0.6405,
      "step": 192
    },
    {
      "epoch": 0.3592592592592593,
      "grad_norm": 8.375,
      "learning_rate": 4.336795512053356e-06,
      "loss": 0.5953,
      "step": 194
    },
    {
      "epoch": 0.362962962962963,
      "grad_norm": 8.6875,
      "learning_rate": 4.330347305730786e-06,
      "loss": 0.6133,
      "step": 196
    },
    {
      "epoch": 0.36666666666666664,
      "grad_norm": 8.6875,
      "learning_rate": 4.323825979539413e-06,
      "loss": 0.6232,
      "step": 198
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 8.625,
      "learning_rate": 4.317231768334875e-06,
      "loss": 0.6017,
      "step": 200
    },
    {
      "epoch": 0.37407407407407406,
      "grad_norm": 8.4375,
      "learning_rate": 4.310564909597654e-06,
      "loss": 0.5907,
      "step": 202
    },
    {
      "epoch": 0.37777777777777777,
      "grad_norm": 8.4375,
      "learning_rate": 4.303825643424525e-06,
      "loss": 0.62,
      "step": 204
    },
    {
      "epoch": 0.3814814814814815,
      "grad_norm": 8.375,
      "learning_rate": 4.297014212519903e-06,
      "loss": 0.5838,
      "step": 206
    },
    {
      "epoch": 0.3851851851851852,
      "grad_norm": 8.25,
      "learning_rate": 4.290130862187108e-06,
      "loss": 0.5953,
      "step": 208
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 9.0,
      "learning_rate": 4.283175840319529e-06,
      "loss": 0.6231,
      "step": 210
    },
    {
      "epoch": 0.3925925925925926,
      "grad_norm": 8.375,
      "learning_rate": 4.276149397391696e-06,
      "loss": 0.6054,
      "step": 212
    },
    {
      "epoch": 0.3962962962962963,
      "grad_norm": 8.4375,
      "learning_rate": 4.269051786450258e-06,
      "loss": 0.5715,
      "step": 214
    },
    {
      "epoch": 0.4,
      "grad_norm": 8.1875,
      "learning_rate": 4.261883263104874e-06,
      "loss": 0.5643,
      "step": 216
    },
    {
      "epoch": 0.40370370370370373,
      "grad_norm": 8.375,
      "learning_rate": 4.2546440855190055e-06,
      "loss": 0.5686,
      "step": 218
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 8.875,
      "learning_rate": 4.2473345144006165e-06,
      "loss": 0.595,
      "step": 220
    },
    {
      "epoch": 0.4111111111111111,
      "grad_norm": 8.8125,
      "learning_rate": 4.239954812992789e-06,
      "loss": 0.6095,
      "step": 222
    },
    {
      "epoch": 0.4148148148148148,
      "grad_norm": 8.3125,
      "learning_rate": 4.23250524706424e-06,
      "loss": 0.554,
      "step": 224
    },
    {
      "epoch": 0.4185185185185185,
      "grad_norm": 8.875,
      "learning_rate": 4.224986084899751e-06,
      "loss": 0.6128,
      "step": 226
    },
    {
      "epoch": 0.4222222222222222,
      "grad_norm": 8.4375,
      "learning_rate": 4.217397597290506e-06,
      "loss": 0.5895,
      "step": 228
    },
    {
      "epoch": 0.42592592592592593,
      "grad_norm": 8.6875,
      "learning_rate": 4.20974005752434e-06,
      "loss": 0.613,
      "step": 230
    },
    {
      "epoch": 0.42962962962962964,
      "grad_norm": 8.625,
      "learning_rate": 4.202013741375896e-06,
      "loss": 0.5693,
      "step": 232
    },
    {
      "epoch": 0.43333333333333335,
      "grad_norm": 8.0625,
      "learning_rate": 4.194218927096692e-06,
      "loss": 0.5706,
      "step": 234
    },
    {
      "epoch": 0.43703703703703706,
      "grad_norm": 8.75,
      "learning_rate": 4.186355895405106e-06,
      "loss": 0.5816,
      "step": 236
    },
    {
      "epoch": 0.44074074074074077,
      "grad_norm": 8.6875,
      "learning_rate": 4.1784249294762585e-06,
      "loss": 0.5983,
      "step": 238
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 8.5625,
      "learning_rate": 4.170426314931819e-06,
      "loss": 0.5774,
      "step": 240
    },
    {
      "epoch": 0.44814814814814813,
      "grad_norm": 8.8125,
      "learning_rate": 4.16236033982972e-06,
      "loss": 0.5933,
      "step": 242
    },
    {
      "epoch": 0.45185185185185184,
      "grad_norm": 8.8125,
      "learning_rate": 4.154227294653782e-06,
      "loss": 0.5751,
      "step": 244
    },
    {
      "epoch": 0.45555555555555555,
      "grad_norm": 8.0625,
      "learning_rate": 4.146027472303251e-06,
      "loss": 0.5488,
      "step": 246
    },
    {
      "epoch": 0.45925925925925926,
      "grad_norm": 8.375,
      "learning_rate": 4.137761168082251e-06,
      "loss": 0.5881,
      "step": 248
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 8.5625,
      "learning_rate": 4.129428679689153e-06,
      "loss": 0.5714,
      "step": 250
    },
    {
      "epoch": 0.4666666666666667,
      "grad_norm": 8.4375,
      "learning_rate": 4.121030307205846e-06,
      "loss": 0.5852,
      "step": 252
    },
    {
      "epoch": 0.4703703703703704,
      "grad_norm": 8.1875,
      "learning_rate": 4.112566353086935e-06,
      "loss": 0.5773,
      "step": 254
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 8.3125,
      "learning_rate": 4.1040371221488506e-06,
      "loss": 0.5557,
      "step": 256
    },
    {
      "epoch": 0.4777777777777778,
      "grad_norm": 8.5,
      "learning_rate": 4.0954429215588655e-06,
      "loss": 0.5793,
      "step": 258
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 8.125,
      "learning_rate": 4.086784060824037e-06,
      "loss": 0.5691,
      "step": 260
    },
    {
      "epoch": 0.48518518518518516,
      "grad_norm": 8.5,
      "learning_rate": 4.078060851780059e-06,
      "loss": 0.569,
      "step": 262
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 8.5,
      "learning_rate": 4.069273608580033e-06,
      "loss": 0.5831,
      "step": 264
    },
    {
      "epoch": 0.4925925925925926,
      "grad_norm": 8.8125,
      "learning_rate": 4.060422647683151e-06,
      "loss": 0.5827,
      "step": 266
    },
    {
      "epoch": 0.4962962962962963,
      "grad_norm": 8.1875,
      "learning_rate": 4.051508287843302e-06,
      "loss": 0.5563,
      "step": 268
    },
    {
      "epoch": 0.5,
      "grad_norm": 8.75,
      "learning_rate": 4.042530850097591e-06,
      "loss": 0.5807,
      "step": 270
    },
    {
      "epoch": 0.5037037037037037,
      "grad_norm": 8.4375,
      "learning_rate": 4.033490657754778e-06,
      "loss": 0.5927,
      "step": 272
    },
    {
      "epoch": 0.5074074074074074,
      "grad_norm": 8.75,
      "learning_rate": 4.024388036383636e-06,
      "loss": 0.5615,
      "step": 274
    },
    {
      "epoch": 0.5111111111111111,
      "grad_norm": 8.625,
      "learning_rate": 4.015223313801222e-06,
      "loss": 0.5552,
      "step": 276
    },
    {
      "epoch": 0.5148148148148148,
      "grad_norm": 8.25,
      "learning_rate": 4.0059968200610755e-06,
      "loss": 0.5492,
      "step": 278
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 8.375,
      "learning_rate": 3.996708887441328e-06,
      "loss": 0.5802,
      "step": 280
    },
    {
      "epoch": 0.5222222222222223,
      "grad_norm": 8.375,
      "learning_rate": 3.98735985043274e-06,
      "loss": 0.5961,
      "step": 282
    },
    {
      "epoch": 0.5259259259259259,
      "grad_norm": 8.6875,
      "learning_rate": 3.977950045726656e-06,
      "loss": 0.587,
      "step": 284
    },
    {
      "epoch": 0.5296296296296297,
      "grad_norm": 8.125,
      "learning_rate": 3.968479812202871e-06,
      "loss": 0.5425,
      "step": 286
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 8.5625,
      "learning_rate": 3.9589494909174376e-06,
      "loss": 0.5566,
      "step": 288
    },
    {
      "epoch": 0.5370370370370371,
      "grad_norm": 8.5625,
      "learning_rate": 3.949359425090375e-06,
      "loss": 0.5746,
      "step": 290
    },
    {
      "epoch": 0.5407407407407407,
      "grad_norm": 8.5625,
      "learning_rate": 3.939709960093312e-06,
      "loss": 0.5679,
      "step": 292
    },
    {
      "epoch": 0.5444444444444444,
      "grad_norm": 8.125,
      "learning_rate": 3.930001443437046e-06,
      "loss": 0.5553,
      "step": 294
    },
    {
      "epoch": 0.5481481481481482,
      "grad_norm": 8.75,
      "learning_rate": 3.920234224759034e-06,
      "loss": 0.578,
      "step": 296
    },
    {
      "epoch": 0.5518518518518518,
      "grad_norm": 8.625,
      "learning_rate": 3.910408655810793e-06,
      "loss": 0.5866,
      "step": 298
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 8.625,
      "learning_rate": 3.900525090445238e-06,
      "loss": 0.5767,
      "step": 300
    },
    {
      "epoch": 0.5592592592592592,
      "grad_norm": 8.5,
      "learning_rate": 3.890583884603937e-06,
      "loss": 0.5557,
      "step": 302
    },
    {
      "epoch": 0.562962962962963,
      "grad_norm": 8.625,
      "learning_rate": 3.880585396304293e-06,
      "loss": 0.5618,
      "step": 304
    },
    {
      "epoch": 0.5666666666666667,
      "grad_norm": 8.0625,
      "learning_rate": 3.870529985626646e-06,
      "loss": 0.5323,
      "step": 306
    },
    {
      "epoch": 0.5703703703703704,
      "grad_norm": 8.8125,
      "learning_rate": 3.860418014701313e-06,
      "loss": 0.5737,
      "step": 308
    },
    {
      "epoch": 0.5740740740740741,
      "grad_norm": 8.125,
      "learning_rate": 3.850249847695538e-06,
      "loss": 0.5486,
      "step": 310
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 8.125,
      "learning_rate": 3.840025850800386e-06,
      "loss": 0.5394,
      "step": 312
    },
    {
      "epoch": 0.5814814814814815,
      "grad_norm": 8.125,
      "learning_rate": 3.8297463922175465e-06,
      "loss": 0.5573,
      "step": 314
    },
    {
      "epoch": 0.5851851851851851,
      "grad_norm": 8.5625,
      "learning_rate": 3.81941184214608e-06,
      "loss": 0.5522,
      "step": 316
    },
    {
      "epoch": 0.5888888888888889,
      "grad_norm": 8.625,
      "learning_rate": 3.8090225727690826e-06,
      "loss": 0.5727,
      "step": 318
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 8.125,
      "learning_rate": 3.798578958240281e-06,
      "loss": 0.5549,
      "step": 320
    },
    {
      "epoch": 0.5962962962962963,
      "grad_norm": 8.1875,
      "learning_rate": 3.7880813746705614e-06,
      "loss": 0.5452,
      "step": 322
    },
    {
      "epoch": 0.6,
      "grad_norm": 8.0625,
      "learning_rate": 3.7775302001144237e-06,
      "loss": 0.5246,
      "step": 324
    },
    {
      "epoch": 0.6037037037037037,
      "grad_norm": 8.6875,
      "learning_rate": 3.7669258145563636e-06,
      "loss": 0.5316,
      "step": 326
    },
    {
      "epoch": 0.6074074074074074,
      "grad_norm": 8.5625,
      "learning_rate": 3.756268599897193e-06,
      "loss": 0.5523,
      "step": 328
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 8.375,
      "learning_rate": 3.74555893994028e-06,
      "loss": 0.5412,
      "step": 330
    },
    {
      "epoch": 0.6148148148148148,
      "grad_norm": 8.4375,
      "learning_rate": 3.7347972203777317e-06,
      "loss": 0.5598,
      "step": 332
    },
    {
      "epoch": 0.6185185185185185,
      "grad_norm": 7.96875,
      "learning_rate": 3.7239838287765044e-06,
      "loss": 0.5334,
      "step": 334
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 8.1875,
      "learning_rate": 3.7131191545644415e-06,
      "loss": 0.5353,
      "step": 336
    },
    {
      "epoch": 0.6259259259259259,
      "grad_norm": 8.375,
      "learning_rate": 3.702203589016253e-06,
      "loss": 0.5547,
      "step": 338
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 8.625,
      "learning_rate": 3.691237525239424e-06,
      "loss": 0.5703,
      "step": 340
    },
    {
      "epoch": 0.6333333333333333,
      "grad_norm": 8.5,
      "learning_rate": 3.6802213581600538e-06,
      "loss": 0.5669,
      "step": 342
    },
    {
      "epoch": 0.6370370370370371,
      "grad_norm": 8.6875,
      "learning_rate": 3.669155484508639e-06,
      "loss": 0.5535,
      "step": 344
    },
    {
      "epoch": 0.6407407407407407,
      "grad_norm": 8.125,
      "learning_rate": 3.6580403028057785e-06,
      "loss": 0.544,
      "step": 346
    },
    {
      "epoch": 0.6444444444444445,
      "grad_norm": 8.375,
      "learning_rate": 3.6468762133478317e-06,
      "loss": 0.5295,
      "step": 348
    },
    {
      "epoch": 0.6481481481481481,
      "grad_norm": 8.625,
      "learning_rate": 3.6356636181924892e-06,
      "loss": 0.5698,
      "step": 350
    },
    {
      "epoch": 0.6518518518518519,
      "grad_norm": 7.9375,
      "learning_rate": 3.6244029211443076e-06,
      "loss": 0.5422,
      "step": 352
    },
    {
      "epoch": 0.6555555555555556,
      "grad_norm": 8.6875,
      "learning_rate": 3.613094527740155e-06,
      "loss": 0.5365,
      "step": 354
    },
    {
      "epoch": 0.6592592592592592,
      "grad_norm": 8.5625,
      "learning_rate": 3.601738845234613e-06,
      "loss": 0.5389,
      "step": 356
    },
    {
      "epoch": 0.662962962962963,
      "grad_norm": 8.625,
      "learning_rate": 3.5903362825853077e-06,
      "loss": 0.5571,
      "step": 358
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 8.0625,
      "learning_rate": 3.5788872504381836e-06,
      "loss": 0.5259,
      "step": 360
    },
    {
      "epoch": 0.6703703703703704,
      "grad_norm": 8.375,
      "learning_rate": 3.5673921611127115e-06,
      "loss": 0.557,
      "step": 362
    },
    {
      "epoch": 0.674074074074074,
      "grad_norm": 8.0625,
      "learning_rate": 3.5558514285870426e-06,
      "loss": 0.5442,
      "step": 364
    },
    {
      "epoch": 0.6777777777777778,
      "grad_norm": 8.0625,
      "learning_rate": 3.5442654684830982e-06,
      "loss": 0.5267,
      "step": 366
    },
    {
      "epoch": 0.6814814814814815,
      "grad_norm": 8.5,
      "learning_rate": 3.5326346980516022e-06,
      "loss": 0.5572,
      "step": 368
    },
    {
      "epoch": 0.6851851851851852,
      "grad_norm": 8.375,
      "learning_rate": 3.520959536157054e-06,
      "loss": 0.5482,
      "step": 370
    },
    {
      "epoch": 0.6888888888888889,
      "grad_norm": 8.4375,
      "learning_rate": 3.5092404032626437e-06,
      "loss": 0.5537,
      "step": 372
    },
    {
      "epoch": 0.6925925925925925,
      "grad_norm": 8.0625,
      "learning_rate": 3.4974777214151117e-06,
      "loss": 0.5388,
      "step": 374
    },
    {
      "epoch": 0.6962962962962963,
      "grad_norm": 8.5,
      "learning_rate": 3.4856719142295446e-06,
      "loss": 0.5352,
      "step": 376
    },
    {
      "epoch": 0.7,
      "grad_norm": 8.375,
      "learning_rate": 3.4738234068741254e-06,
      "loss": 0.5161,
      "step": 378
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 7.96875,
      "learning_rate": 3.4619326260548185e-06,
      "loss": 0.544,
      "step": 380
    },
    {
      "epoch": 0.7074074074074074,
      "grad_norm": 7.9375,
      "learning_rate": 3.45e-06,
      "loss": 0.5386,
      "step": 382
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 8.375,
      "learning_rate": 3.438025958445042e-06,
      "loss": 0.5254,
      "step": 384
    },
    {
      "epoch": 0.7148148148148148,
      "grad_norm": 8.375,
      "learning_rate": 3.4260109326168295e-06,
      "loss": 0.5373,
      "step": 386
    },
    {
      "epoch": 0.7185185185185186,
      "grad_norm": 8.0625,
      "learning_rate": 3.413955355218237e-06,
      "loss": 0.5188,
      "step": 388
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 8.0625,
      "learning_rate": 3.40185966041254e-06,
      "loss": 0.5286,
      "step": 390
    },
    {
      "epoch": 0.725925925925926,
      "grad_norm": 8.3125,
      "learning_rate": 3.3897242838077815e-06,
      "loss": 0.5281,
      "step": 392
    },
    {
      "epoch": 0.7296296296296296,
      "grad_norm": 8.5,
      "learning_rate": 3.3775496624410846e-06,
      "loss": 0.5568,
      "step": 394
    },
    {
      "epoch": 0.7333333333333333,
      "grad_norm": 7.90625,
      "learning_rate": 3.365336234762914e-06,
      "loss": 0.5025,
      "step": 396
    },
    {
      "epoch": 0.737037037037037,
      "grad_norm": 7.9375,
      "learning_rate": 3.3530844406212813e-06,
      "loss": 0.5306,
      "step": 398
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 8.125,
      "learning_rate": 3.340794721245911e-06,
      "loss": 0.5232,
      "step": 400
    },
    {
      "epoch": 0.7444444444444445,
      "grad_norm": 8.4375,
      "learning_rate": 3.3284675192323466e-06,
      "loss": 0.5402,
      "step": 402
    },
    {
      "epoch": 0.7481481481481481,
      "grad_norm": 8.625,
      "learning_rate": 3.3161032785260114e-06,
      "loss": 0.5587,
      "step": 404
    },
    {
      "epoch": 0.7518518518518519,
      "grad_norm": 7.875,
      "learning_rate": 3.30370244440622e-06,
      "loss": 0.5217,
      "step": 406
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 8.125,
      "learning_rate": 3.291265463470143e-06,
      "loss": 0.5097,
      "step": 408
    },
    {
      "epoch": 0.7592592592592593,
      "grad_norm": 7.90625,
      "learning_rate": 3.2787927836167273e-06,
      "loss": 0.5301,
      "step": 410
    },
    {
      "epoch": 0.762962962962963,
      "grad_norm": 7.875,
      "learning_rate": 3.2662848540305566e-06,
      "loss": 0.515,
      "step": 412
    },
    {
      "epoch": 0.7666666666666667,
      "grad_norm": 8.1875,
      "learning_rate": 3.253742125165684e-06,
      "loss": 0.5769,
      "step": 414
    },
    {
      "epoch": 0.7703703703703704,
      "grad_norm": 8.0625,
      "learning_rate": 3.241165048729404e-06,
      "loss": 0.5125,
      "step": 416
    },
    {
      "epoch": 0.774074074074074,
      "grad_norm": 7.96875,
      "learning_rate": 3.2285540776659865e-06,
      "loss": 0.5187,
      "step": 418
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 7.96875,
      "learning_rate": 3.215909666140367e-06,
      "loss": 0.5163,
      "step": 420
    },
    {
      "epoch": 0.7814814814814814,
      "grad_norm": 8.4375,
      "learning_rate": 3.2032322695217835e-06,
      "loss": 0.5378,
      "step": 422
    },
    {
      "epoch": 0.7851851851851852,
      "grad_norm": 8.1875,
      "learning_rate": 3.1905223443673878e-06,
      "loss": 0.5254,
      "step": 424
    },
    {
      "epoch": 0.7888888888888889,
      "grad_norm": 8.1875,
      "learning_rate": 3.1777803484057937e-06,
      "loss": 0.5277,
      "step": 426
    },
    {
      "epoch": 0.7925925925925926,
      "grad_norm": 7.90625,
      "learning_rate": 3.165006740520598e-06,
      "loss": 0.514,
      "step": 428
    },
    {
      "epoch": 0.7962962962962963,
      "grad_norm": 8.0625,
      "learning_rate": 3.1522019807338508e-06,
      "loss": 0.5231,
      "step": 430
    },
    {
      "epoch": 0.8,
      "grad_norm": 8.25,
      "learning_rate": 3.1393665301894926e-06,
      "loss": 0.5135,
      "step": 432
    },
    {
      "epoch": 0.8037037037037037,
      "grad_norm": 8.0,
      "learning_rate": 3.126500851136745e-06,
      "loss": 0.5319,
      "step": 434
    },
    {
      "epoch": 0.8074074074074075,
      "grad_norm": 8.0625,
      "learning_rate": 3.1136054069134607e-06,
      "loss": 0.53,
      "step": 436
    },
    {
      "epoch": 0.8111111111111111,
      "grad_norm": 8.5,
      "learning_rate": 3.1006806619294428e-06,
      "loss": 0.5229,
      "step": 438
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 8.5625,
      "learning_rate": 3.087727081649715e-06,
      "loss": 0.5429,
      "step": 440
    },
    {
      "epoch": 0.8185185185185185,
      "grad_norm": 8.0625,
      "learning_rate": 3.0747451325777605e-06,
      "loss": 0.5103,
      "step": 442
    },
    {
      "epoch": 0.8222222222222222,
      "grad_norm": 8.5625,
      "learning_rate": 3.061735282238722e-06,
      "loss": 0.5541,
      "step": 444
    },
    {
      "epoch": 0.825925925925926,
      "grad_norm": 7.90625,
      "learning_rate": 3.0486979991625627e-06,
      "loss": 0.5284,
      "step": 446
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 8.375,
      "learning_rate": 3.035633752867196e-06,
      "loss": 0.5209,
      "step": 448
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 8.375,
      "learning_rate": 3.022543013841572e-06,
      "loss": 0.53,
      "step": 450
    },
    {
      "epoch": 0.837037037037037,
      "grad_norm": 7.8125,
      "learning_rate": 3.0094262535287385e-06,
      "loss": 0.5104,
      "step": 452
    },
    {
      "epoch": 0.8407407407407408,
      "grad_norm": 7.78125,
      "learning_rate": 2.99628394430886e-06,
      "loss": 0.4987,
      "step": 454
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 7.875,
      "learning_rate": 2.9831165594822035e-06,
      "loss": 0.5181,
      "step": 456
    },
    {
      "epoch": 0.8481481481481481,
      "grad_norm": 7.90625,
      "learning_rate": 2.9699245732521005e-06,
      "loss": 0.5204,
      "step": 458
    },
    {
      "epoch": 0.8518518518518519,
      "grad_norm": 8.3125,
      "learning_rate": 2.95670846070786e-06,
      "loss": 0.5254,
      "step": 460
    },
    {
      "epoch": 0.8555555555555555,
      "grad_norm": 8.5,
      "learning_rate": 2.943468697807666e-06,
      "loss": 0.5233,
      "step": 462
    },
    {
      "epoch": 0.8592592592592593,
      "grad_norm": 8.25,
      "learning_rate": 2.930205761361434e-06,
      "loss": 0.5238,
      "step": 464
    },
    {
      "epoch": 0.8629629629629629,
      "grad_norm": 8.5,
      "learning_rate": 2.9169201290136377e-06,
      "loss": 0.5196,
      "step": 466
    },
    {
      "epoch": 0.8666666666666667,
      "grad_norm": 8.3125,
      "learning_rate": 2.903612279226112e-06,
      "loss": 0.5359,
      "step": 468
    },
    {
      "epoch": 0.8703703703703703,
      "grad_norm": 7.6875,
      "learning_rate": 2.8902826912608155e-06,
      "loss": 0.5168,
      "step": 470
    },
    {
      "epoch": 0.8740740740740741,
      "grad_norm": 8.0625,
      "learning_rate": 2.8769318451625792e-06,
      "loss": 0.5393,
      "step": 472
    },
    {
      "epoch": 0.8777777777777778,
      "grad_norm": 7.75,
      "learning_rate": 2.8635602217418073e-06,
      "loss": 0.5155,
      "step": 474
    },
    {
      "epoch": 0.8814814814814815,
      "grad_norm": 7.75,
      "learning_rate": 2.850168302557173e-06,
      "loss": 0.4892,
      "step": 476
    },
    {
      "epoch": 0.8851851851851852,
      "grad_norm": 7.8125,
      "learning_rate": 2.8367565698982674e-06,
      "loss": 0.5184,
      "step": 478
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 8.4375,
      "learning_rate": 2.8233255067682357e-06,
      "loss": 0.526,
      "step": 480
    },
    {
      "epoch": 0.8925925925925926,
      "grad_norm": 8.4375,
      "learning_rate": 2.8098755968663775e-06,
      "loss": 0.5202,
      "step": 482
    },
    {
      "epoch": 0.8962962962962963,
      "grad_norm": 8.25,
      "learning_rate": 2.7964073245707345e-06,
      "loss": 0.5124,
      "step": 484
    },
    {
      "epoch": 0.9,
      "grad_norm": 8.375,
      "learning_rate": 2.7829211749206393e-06,
      "loss": 0.5341,
      "step": 486
    },
    {
      "epoch": 0.9037037037037037,
      "grad_norm": 8.25,
      "learning_rate": 2.76941763359925e-06,
      "loss": 0.5118,
      "step": 488
    },
    {
      "epoch": 0.9074074074074074,
      "grad_norm": 8.3125,
      "learning_rate": 2.7558971869160605e-06,
      "loss": 0.5252,
      "step": 490
    },
    {
      "epoch": 0.9111111111111111,
      "grad_norm": 7.6875,
      "learning_rate": 2.7423603217893853e-06,
      "loss": 0.5061,
      "step": 492
    },
    {
      "epoch": 0.9148148148148149,
      "grad_norm": 8.375,
      "learning_rate": 2.7288075257288237e-06,
      "loss": 0.5002,
      "step": 494
    },
    {
      "epoch": 0.9185185185185185,
      "grad_norm": 8.5625,
      "learning_rate": 2.7152392868177043e-06,
      "loss": 0.542,
      "step": 496
    },
    {
      "epoch": 0.9222222222222223,
      "grad_norm": 7.78125,
      "learning_rate": 2.7016560936955053e-06,
      "loss": 0.5133,
      "step": 498
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 8.0,
      "learning_rate": 2.6880584355402586e-06,
      "loss": 0.524,
      "step": 500
    },
    {
      "epoch": 0.9296296296296296,
      "grad_norm": 7.8125,
      "learning_rate": 2.6744468020509324e-06,
      "loss": 0.5031,
      "step": 502
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 8.375,
      "learning_rate": 2.6608216834297947e-06,
      "loss": 0.5137,
      "step": 504
    },
    {
      "epoch": 0.937037037037037,
      "grad_norm": 7.8125,
      "learning_rate": 2.647183570364761e-06,
      "loss": 0.5095,
      "step": 506
    },
    {
      "epoch": 0.9407407407407408,
      "grad_norm": 8.25,
      "learning_rate": 2.633532954011721e-06,
      "loss": 0.5195,
      "step": 508
    },
    {
      "epoch": 0.9444444444444444,
      "grad_norm": 8.375,
      "learning_rate": 2.6198703259768517e-06,
      "loss": 0.5133,
      "step": 510
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 7.84375,
      "learning_rate": 2.606196178298913e-06,
      "loss": 0.4951,
      "step": 512
    },
    {
      "epoch": 0.9518518518518518,
      "grad_norm": 8.5,
      "learning_rate": 2.592511003431526e-06,
      "loss": 0.5214,
      "step": 514
    },
    {
      "epoch": 0.9555555555555556,
      "grad_norm": 8.5,
      "learning_rate": 2.5788152942254395e-06,
      "loss": 0.5309,
      "step": 516
    },
    {
      "epoch": 0.9592592592592593,
      "grad_norm": 7.78125,
      "learning_rate": 2.5651095439107826e-06,
      "loss": 0.5009,
      "step": 518
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 8.375,
      "learning_rate": 2.5513942460792966e-06,
      "loss": 0.503,
      "step": 520
    },
    {
      "epoch": 0.9666666666666667,
      "grad_norm": 8.25,
      "learning_rate": 2.5376698946665634e-06,
      "loss": 0.5223,
      "step": 522
    },
    {
      "epoch": 0.9703703703703703,
      "grad_norm": 8.4375,
      "learning_rate": 2.523936983934217e-06,
      "loss": 0.5341,
      "step": 524
    },
    {
      "epoch": 0.9740740740740741,
      "grad_norm": 8.375,
      "learning_rate": 2.5101960084521407e-06,
      "loss": 0.5507,
      "step": 526
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 8.3125,
      "learning_rate": 2.4964474630806573e-06,
      "loss": 0.5107,
      "step": 528
    },
    {
      "epoch": 0.9814814814814815,
      "grad_norm": 8.25,
      "learning_rate": 2.482691842952709e-06,
      "loss": 0.5035,
      "step": 530
    },
    {
      "epoch": 0.9851851851851852,
      "grad_norm": 8.5,
      "learning_rate": 2.468929643456024e-06,
      "loss": 0.5083,
      "step": 532
    },
    {
      "epoch": 0.9888888888888889,
      "grad_norm": 8.25,
      "learning_rate": 2.4551613602152758e-06,
      "loss": 0.5121,
      "step": 534
    },
    {
      "epoch": 0.9925925925925926,
      "grad_norm": 8.3125,
      "learning_rate": 2.4413874890742364e-06,
      "loss": 0.535,
      "step": 536
    },
    {
      "epoch": 0.9962962962962963,
      "grad_norm": 8.1875,
      "learning_rate": 2.427608526077915e-06,
      "loss": 0.5184,
      "step": 538
    },
    {
      "epoch": 1.0,
      "grad_norm": 7.6875,
      "learning_rate": 2.413824967454698e-06,
      "loss": 0.4873,
      "step": 540
    }
  ],
  "logging_steps": 2,
  "max_steps": 1080,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 540,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.66563154509824e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}