{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 30,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025078369905956112,
      "grad_norm": 0.43725547194480896,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.9437,
      "step": 2
    },
    {
      "epoch": 0.050156739811912224,
      "grad_norm": 0.6708689332008362,
      "learning_rate": 2.4e-05,
      "loss": 1.849,
      "step": 4
    },
    {
      "epoch": 0.07523510971786834,
      "grad_norm": 0.3925197422504425,
      "learning_rate": 4e-05,
      "loss": 1.8725,
      "step": 6
    },
    {
      "epoch": 0.10031347962382445,
      "grad_norm": 0.4107086956501007,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.7837,
      "step": 8
    },
    {
      "epoch": 0.12539184952978055,
      "grad_norm": 0.5341728329658508,
      "learning_rate": 7.2e-05,
      "loss": 1.8033,
      "step": 10
    },
    {
      "epoch": 0.15047021943573669,
      "grad_norm": 0.43938425183296204,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.5958,
      "step": 12
    },
    {
      "epoch": 0.1755485893416928,
      "grad_norm": 0.3650668263435364,
      "learning_rate": 0.00010400000000000001,
      "loss": 1.5566,
      "step": 14
    },
    {
      "epoch": 0.2006269592476489,
      "grad_norm": 0.3861461877822876,
      "learning_rate": 0.00012,
      "loss": 1.3631,
      "step": 16
    },
    {
      "epoch": 0.22570532915360503,
      "grad_norm": 0.3685659170150757,
      "learning_rate": 0.00013600000000000003,
      "loss": 1.3227,
      "step": 18
    },
    {
      "epoch": 0.2507836990595611,
      "grad_norm": 0.4720342457294464,
      "learning_rate": 0.000152,
      "loss": 1.1027,
      "step": 20
    },
    {
      "epoch": 0.27586206896551724,
      "grad_norm": 0.40199315547943115,
      "learning_rate": 0.000168,
      "loss": 1.018,
      "step": 22
    },
    {
      "epoch": 0.30094043887147337,
      "grad_norm": 0.22768579423427582,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.9077,
      "step": 24
    },
    {
      "epoch": 0.32601880877742945,
      "grad_norm": 0.2388496696949005,
      "learning_rate": 0.0002,
      "loss": 0.7587,
      "step": 26
    },
    {
      "epoch": 0.3510971786833856,
      "grad_norm": 0.19000130891799927,
      "learning_rate": 0.0001998993710691824,
      "loss": 0.7766,
      "step": 28
    },
    {
      "epoch": 0.3761755485893417,
      "grad_norm": 0.1965627372264862,
      "learning_rate": 0.0001997987421383648,
      "loss": 0.7575,
      "step": 30
    },
    {
      "epoch": 0.4012539184952978,
      "grad_norm": 0.18852603435516357,
      "learning_rate": 0.00019969811320754718,
      "loss": 0.8292,
      "step": 32
    },
    {
      "epoch": 0.4263322884012539,
      "grad_norm": 0.16236507892608643,
      "learning_rate": 0.00019959748427672956,
      "loss": 0.7272,
      "step": 34
    },
    {
      "epoch": 0.45141065830721006,
      "grad_norm": 0.14128465950489044,
      "learning_rate": 0.00019949685534591195,
      "loss": 0.751,
      "step": 36
    },
    {
      "epoch": 0.47648902821316613,
      "grad_norm": 0.14623811841011047,
      "learning_rate": 0.00019939622641509434,
      "loss": 0.6661,
      "step": 38
    },
    {
      "epoch": 0.5015673981191222,
      "grad_norm": 0.14945009350776672,
      "learning_rate": 0.00019929559748427673,
      "loss": 0.7435,
      "step": 40
    },
    {
      "epoch": 0.5266457680250783,
      "grad_norm": 0.1485632061958313,
      "learning_rate": 0.00019919496855345915,
      "loss": 0.6466,
      "step": 42
    },
    {
      "epoch": 0.5517241379310345,
      "grad_norm": 0.14336936175823212,
      "learning_rate": 0.00019909433962264153,
      "loss": 0.7,
      "step": 44
    },
    {
      "epoch": 0.5768025078369906,
      "grad_norm": 0.1316949725151062,
      "learning_rate": 0.0001989937106918239,
      "loss": 0.6194,
      "step": 46
    },
    {
      "epoch": 0.6018808777429467,
      "grad_norm": 0.14485935866832733,
      "learning_rate": 0.00019889308176100629,
      "loss": 0.8044,
      "step": 48
    },
    {
      "epoch": 0.6269592476489029,
      "grad_norm": 0.12860289216041565,
      "learning_rate": 0.00019879245283018867,
      "loss": 0.5773,
      "step": 50
    },
    {
      "epoch": 0.6520376175548589,
      "grad_norm": 0.16889798641204834,
      "learning_rate": 0.0001986918238993711,
      "loss": 0.7281,
      "step": 52
    },
    {
      "epoch": 0.677115987460815,
      "grad_norm": 0.14104238152503967,
      "learning_rate": 0.00019859119496855348,
      "loss": 0.6654,
      "step": 54
    },
    {
      "epoch": 0.7021943573667712,
      "grad_norm": 0.1515515297651291,
      "learning_rate": 0.00019849056603773587,
      "loss": 0.6833,
      "step": 56
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.16043280065059662,
      "learning_rate": 0.00019838993710691826,
      "loss": 0.6599,
      "step": 58
    },
    {
      "epoch": 0.7523510971786834,
      "grad_norm": 0.15895870327949524,
      "learning_rate": 0.00019828930817610062,
      "loss": 0.686,
      "step": 60
    },
    {
      "epoch": 0.7774294670846394,
      "grad_norm": 0.3486965298652649,
      "learning_rate": 0.00019818867924528303,
      "loss": 0.6835,
      "step": 62
    },
    {
      "epoch": 0.8025078369905956,
      "grad_norm": 0.1274975836277008,
      "learning_rate": 0.00019808805031446542,
      "loss": 0.5425,
      "step": 64
    },
    {
      "epoch": 0.8275862068965517,
      "grad_norm": 0.1669531911611557,
      "learning_rate": 0.0001979874213836478,
      "loss": 0.766,
      "step": 66
    },
    {
      "epoch": 0.8526645768025078,
      "grad_norm": 0.14856377243995667,
      "learning_rate": 0.0001978867924528302,
      "loss": 0.5993,
      "step": 68
    },
    {
      "epoch": 0.877742946708464,
      "grad_norm": 0.13947483897209167,
      "learning_rate": 0.0001977861635220126,
      "loss": 0.7071,
      "step": 70
    },
    {
      "epoch": 0.9028213166144201,
      "grad_norm": 0.15276968479156494,
      "learning_rate": 0.00019768553459119498,
      "loss": 0.687,
      "step": 72
    },
    {
      "epoch": 0.9278996865203761,
      "grad_norm": 0.14595958590507507,
      "learning_rate": 0.00019758490566037737,
      "loss": 0.6495,
      "step": 74
    },
    {
      "epoch": 0.9529780564263323,
      "grad_norm": 0.17588546872138977,
      "learning_rate": 0.00019748427672955975,
      "loss": 0.6584,
      "step": 76
    },
    {
      "epoch": 0.9780564263322884,
      "grad_norm": 0.15688568353652954,
      "learning_rate": 0.00019738364779874214,
      "loss": 0.6769,
      "step": 78
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.1879902333021164,
      "learning_rate": 0.00019728301886792453,
      "loss": 0.5924,
      "step": 80
    },
    {
      "epoch": 1.025078369905956,
      "grad_norm": 0.15292422473430634,
      "learning_rate": 0.00019718238993710695,
      "loss": 0.5727,
      "step": 82
    },
    {
      "epoch": 1.0501567398119123,
      "grad_norm": 0.14542542397975922,
      "learning_rate": 0.00019708176100628934,
      "loss": 0.5528,
      "step": 84
    },
    {
      "epoch": 1.0752351097178683,
      "grad_norm": 0.15912258625030518,
      "learning_rate": 0.0001969811320754717,
      "loss": 0.5404,
      "step": 86
    },
    {
      "epoch": 1.1003134796238245,
      "grad_norm": 0.16443438827991486,
      "learning_rate": 0.00019688050314465409,
      "loss": 0.544,
      "step": 88
    },
    {
      "epoch": 1.1253918495297806,
      "grad_norm": 0.18315915763378143,
      "learning_rate": 0.00019677987421383647,
      "loss": 0.5768,
      "step": 90
    },
    {
      "epoch": 1.1504702194357366,
      "grad_norm": 0.16878078877925873,
      "learning_rate": 0.0001966792452830189,
      "loss": 0.6918,
      "step": 92
    },
    {
      "epoch": 1.1755485893416928,
      "grad_norm": 0.1652018129825592,
      "learning_rate": 0.00019657861635220128,
      "loss": 0.5903,
      "step": 94
    },
    {
      "epoch": 1.2006269592476488,
      "grad_norm": 0.181439608335495,
      "learning_rate": 0.00019647798742138367,
      "loss": 0.5917,
      "step": 96
    },
    {
      "epoch": 1.225705329153605,
      "grad_norm": 0.15887363255023956,
      "learning_rate": 0.00019637735849056606,
      "loss": 0.5631,
      "step": 98
    },
    {
      "epoch": 1.250783699059561,
      "grad_norm": 0.16309796273708344,
      "learning_rate": 0.00019627672955974842,
      "loss": 0.6206,
      "step": 100
    },
    {
      "epoch": 1.2758620689655173,
      "grad_norm": 0.19174307584762573,
      "learning_rate": 0.00019617610062893083,
      "loss": 0.5375,
      "step": 102
    },
    {
      "epoch": 1.3009404388714734,
      "grad_norm": 0.2240614891052246,
      "learning_rate": 0.00019607547169811322,
      "loss": 0.6407,
      "step": 104
    },
    {
      "epoch": 1.3260188087774294,
      "grad_norm": 0.1673874855041504,
      "learning_rate": 0.0001959748427672956,
      "loss": 0.631,
      "step": 106
    },
    {
      "epoch": 1.3510971786833856,
      "grad_norm": 0.16143380105495453,
      "learning_rate": 0.000195874213836478,
      "loss": 0.4985,
      "step": 108
    },
    {
      "epoch": 1.3761755485893417,
      "grad_norm": 0.18511593341827393,
      "learning_rate": 0.0001957735849056604,
      "loss": 0.5844,
      "step": 110
    },
    {
      "epoch": 1.4012539184952977,
      "grad_norm": 0.15226313471794128,
      "learning_rate": 0.00019567295597484278,
      "loss": 0.5237,
      "step": 112
    },
    {
      "epoch": 1.426332288401254,
      "grad_norm": 0.16536672413349152,
      "learning_rate": 0.00019557232704402517,
      "loss": 0.4945,
      "step": 114
    },
    {
      "epoch": 1.4514106583072102,
      "grad_norm": 0.17802752554416656,
      "learning_rate": 0.00019547169811320755,
      "loss": 0.632,
      "step": 116
    },
    {
      "epoch": 1.4764890282131662,
      "grad_norm": 0.18615730106830597,
      "learning_rate": 0.00019537106918238994,
      "loss": 0.6778,
      "step": 118
    },
    {
      "epoch": 1.5015673981191222,
      "grad_norm": 0.16418549418449402,
      "learning_rate": 0.00019527044025157233,
      "loss": 0.6141,
      "step": 120
    },
    {
      "epoch": 1.5266457680250785,
      "grad_norm": 0.16458265483379364,
      "learning_rate": 0.00019516981132075475,
      "loss": 0.5316,
      "step": 122
    },
    {
      "epoch": 1.5517241379310345,
      "grad_norm": 0.15842436254024506,
      "learning_rate": 0.0001950691823899371,
      "loss": 0.4761,
      "step": 124
    },
    {
      "epoch": 1.5768025078369905,
      "grad_norm": 0.15368856489658356,
      "learning_rate": 0.0001949685534591195,
      "loss": 0.471,
      "step": 126
    },
    {
      "epoch": 1.6018808777429467,
      "grad_norm": 0.16104081273078918,
      "learning_rate": 0.0001948679245283019,
      "loss": 0.572,
      "step": 128
    },
    {
      "epoch": 1.626959247648903,
      "grad_norm": 0.1696012020111084,
      "learning_rate": 0.00019476729559748428,
      "loss": 0.5293,
      "step": 130
    },
    {
      "epoch": 1.6520376175548588,
      "grad_norm": 0.16601622104644775,
      "learning_rate": 0.0001946666666666667,
      "loss": 0.6569,
      "step": 132
    },
    {
      "epoch": 1.677115987460815,
      "grad_norm": 0.15106241405010223,
      "learning_rate": 0.00019456603773584908,
      "loss": 0.5687,
      "step": 134
    },
    {
      "epoch": 1.7021943573667713,
      "grad_norm": 0.18189087510108948,
      "learning_rate": 0.00019446540880503147,
      "loss": 0.4965,
      "step": 136
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 0.15463034808635712,
      "learning_rate": 0.00019436477987421383,
      "loss": 0.6398,
      "step": 138
    },
    {
      "epoch": 1.7523510971786833,
      "grad_norm": 0.17576032876968384,
      "learning_rate": 0.00019426415094339622,
      "loss": 0.6122,
      "step": 140
    },
    {
      "epoch": 1.7774294670846396,
      "grad_norm": 0.14750592410564423,
      "learning_rate": 0.00019416352201257863,
      "loss": 0.5475,
      "step": 142
    },
    {
      "epoch": 1.8025078369905956,
      "grad_norm": 0.15765072405338287,
      "learning_rate": 0.00019406289308176102,
      "loss": 0.443,
      "step": 144
    },
    {
      "epoch": 1.8275862068965516,
      "grad_norm": 0.16872242093086243,
      "learning_rate": 0.0001939622641509434,
      "loss": 0.5061,
      "step": 146
    },
    {
      "epoch": 1.8526645768025078,
      "grad_norm": 0.16207149624824524,
      "learning_rate": 0.0001938616352201258,
      "loss": 0.572,
      "step": 148
    },
    {
      "epoch": 1.877742946708464,
      "grad_norm": 0.16720207035541534,
      "learning_rate": 0.0001937610062893082,
      "loss": 0.5329,
      "step": 150
    },
    {
      "epoch": 1.90282131661442,
      "grad_norm": 0.1653318852186203,
      "learning_rate": 0.00019366037735849058,
      "loss": 0.5361,
      "step": 152
    },
    {
      "epoch": 1.9278996865203761,
      "grad_norm": 0.1918332576751709,
      "learning_rate": 0.00019355974842767297,
      "loss": 0.6219,
      "step": 154
    },
    {
      "epoch": 1.9529780564263324,
      "grad_norm": 0.1535947322845459,
      "learning_rate": 0.00019345911949685536,
      "loss": 0.586,
      "step": 156
    },
    {
      "epoch": 1.9780564263322884,
      "grad_norm": 0.16222791373729706,
      "learning_rate": 0.00019335849056603774,
      "loss": 0.5228,
      "step": 158
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.24010032415390015,
      "learning_rate": 0.00019325786163522013,
      "loss": 0.5218,
      "step": 160
    },
    {
      "epoch": 2.0250783699059562,
      "grad_norm": 0.15844006836414337,
      "learning_rate": 0.00019315723270440255,
      "loss": 0.5111,
      "step": 162
    },
    {
      "epoch": 2.050156739811912,
      "grad_norm": 0.1755230873823166,
      "learning_rate": 0.0001930566037735849,
      "loss": 0.6063,
      "step": 164
    },
    {
      "epoch": 2.0752351097178683,
      "grad_norm": 0.2025759369134903,
      "learning_rate": 0.0001929559748427673,
      "loss": 0.5672,
      "step": 166
    },
    {
      "epoch": 2.1003134796238245,
      "grad_norm": 0.2058378905057907,
      "learning_rate": 0.0001928553459119497,
      "loss": 0.4629,
      "step": 168
    },
    {
      "epoch": 2.1253918495297803,
      "grad_norm": 0.1765381544828415,
      "learning_rate": 0.00019275471698113208,
      "loss": 0.5236,
      "step": 170
    },
    {
      "epoch": 2.1504702194357366,
      "grad_norm": 0.20618358254432678,
      "learning_rate": 0.0001926540880503145,
      "loss": 0.5029,
      "step": 172
    },
    {
      "epoch": 2.175548589341693,
      "grad_norm": 0.1737968772649765,
      "learning_rate": 0.00019255345911949688,
      "loss": 0.3964,
      "step": 174
    },
    {
      "epoch": 2.200626959247649,
      "grad_norm": 0.20385882258415222,
      "learning_rate": 0.00019245283018867927,
      "loss": 0.5188,
      "step": 176
    },
    {
      "epoch": 2.225705329153605,
      "grad_norm": 0.2051456868648529,
      "learning_rate": 0.00019235220125786163,
      "loss": 0.4548,
      "step": 178
    },
    {
      "epoch": 2.250783699059561,
      "grad_norm": 0.18826241791248322,
      "learning_rate": 0.00019225157232704402,
      "loss": 0.4515,
      "step": 180
    },
    {
      "epoch": 2.2758620689655173,
      "grad_norm": 0.18653476238250732,
      "learning_rate": 0.00019215094339622644,
      "loss": 0.5373,
      "step": 182
    },
    {
      "epoch": 2.300940438871473,
      "grad_norm": 0.179554283618927,
      "learning_rate": 0.00019205031446540882,
      "loss": 0.49,
      "step": 184
    },
    {
      "epoch": 2.3260188087774294,
      "grad_norm": 0.18949083983898163,
      "learning_rate": 0.0001919496855345912,
      "loss": 0.4795,
      "step": 186
    },
    {
      "epoch": 2.3510971786833856,
      "grad_norm": 0.21681569516658783,
      "learning_rate": 0.0001918490566037736,
      "loss": 0.4826,
      "step": 188
    },
    {
      "epoch": 2.376175548589342,
      "grad_norm": 0.20997639000415802,
      "learning_rate": 0.000191748427672956,
      "loss": 0.3699,
      "step": 190
    },
    {
      "epoch": 2.4012539184952977,
      "grad_norm": 0.3043127954006195,
      "learning_rate": 0.00019164779874213838,
      "loss": 0.5264,
      "step": 192
    },
    {
      "epoch": 2.426332288401254,
      "grad_norm": 0.19533301889896393,
      "learning_rate": 0.00019154716981132077,
      "loss": 0.4243,
      "step": 194
    },
    {
      "epoch": 2.45141065830721,
      "grad_norm": 0.20891591906547546,
      "learning_rate": 0.00019144654088050316,
      "loss": 0.4748,
      "step": 196
    },
    {
      "epoch": 2.476489028213166,
      "grad_norm": 0.1940625011920929,
      "learning_rate": 0.00019134591194968554,
      "loss": 0.456,
      "step": 198
    },
    {
      "epoch": 2.501567398119122,
      "grad_norm": 0.2169208973646164,
      "learning_rate": 0.00019124528301886793,
      "loss": 0.577,
      "step": 200
    },
    {
      "epoch": 2.5266457680250785,
      "grad_norm": 0.21462920308113098,
      "learning_rate": 0.00019114465408805032,
      "loss": 0.3583,
      "step": 202
    },
    {
      "epoch": 2.5517241379310347,
      "grad_norm": 0.22243842482566833,
      "learning_rate": 0.0001910440251572327,
      "loss": 0.5473,
      "step": 204
    },
    {
      "epoch": 2.5768025078369905,
      "grad_norm": 0.20357415080070496,
      "learning_rate": 0.0001909433962264151,
      "loss": 0.5596,
      "step": 206
    },
    {
      "epoch": 2.6018808777429467,
      "grad_norm": 0.21374137699604034,
      "learning_rate": 0.0001908427672955975,
      "loss": 0.6041,
      "step": 208
    },
    {
      "epoch": 2.626959247648903,
      "grad_norm": 0.22612103819847107,
      "learning_rate": 0.00019074213836477988,
      "loss": 0.4825,
      "step": 210
    },
    {
      "epoch": 2.652037617554859,
      "grad_norm": 0.182185098528862,
      "learning_rate": 0.0001906415094339623,
      "loss": 0.5961,
      "step": 212
    },
    {
      "epoch": 2.677115987460815,
      "grad_norm": 0.21316243708133698,
      "learning_rate": 0.00019054088050314468,
      "loss": 0.4892,
      "step": 214
    },
    {
      "epoch": 2.7021943573667713,
      "grad_norm": 0.20594292879104614,
      "learning_rate": 0.00019044025157232704,
      "loss": 0.5294,
      "step": 216
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.18579436838626862,
      "learning_rate": 0.00019033962264150943,
      "loss": 0.4867,
      "step": 218
    },
    {
      "epoch": 2.7523510971786833,
      "grad_norm": 0.20978513360023499,
      "learning_rate": 0.00019023899371069182,
      "loss": 0.5459,
      "step": 220
    },
    {
      "epoch": 2.7774294670846396,
      "grad_norm": 0.20766879618167877,
      "learning_rate": 0.00019013836477987424,
      "loss": 0.4467,
      "step": 222
    },
    {
      "epoch": 2.8025078369905954,
      "grad_norm": 0.2247876673936844,
      "learning_rate": 0.00019003773584905662,
      "loss": 0.4955,
      "step": 224
    },
    {
      "epoch": 2.8275862068965516,
      "grad_norm": 0.20031589269638062,
      "learning_rate": 0.00018993710691823901,
      "loss": 0.4274,
      "step": 226
    },
    {
      "epoch": 2.852664576802508,
      "grad_norm": 0.22423385083675385,
      "learning_rate": 0.0001898364779874214,
      "loss": 0.4741,
      "step": 228
    },
    {
      "epoch": 2.877742946708464,
      "grad_norm": 0.1920011192560196,
      "learning_rate": 0.00018973584905660376,
      "loss": 0.4802,
      "step": 230
    },
    {
      "epoch": 2.9028213166144203,
      "grad_norm": 0.1996566653251648,
      "learning_rate": 0.00018963522012578615,
      "loss": 0.5204,
      "step": 232
    },
    {
      "epoch": 2.927899686520376,
      "grad_norm": 0.18659324944019318,
      "learning_rate": 0.00018953459119496857,
      "loss": 0.563,
      "step": 234
    },
    {
      "epoch": 2.9529780564263324,
      "grad_norm": 0.20645543932914734,
      "learning_rate": 0.00018943396226415096,
      "loss": 0.5968,
      "step": 236
    },
    {
      "epoch": 2.978056426332288,
      "grad_norm": 0.20103755593299866,
      "learning_rate": 0.00018933333333333335,
      "loss": 0.4683,
      "step": 238
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.26790672540664673,
      "learning_rate": 0.00018923270440251573,
      "loss": 0.4214,
      "step": 240
    },
    {
      "epoch": 3.0250783699059562,
      "grad_norm": 0.24234965443611145,
      "learning_rate": 0.00018913207547169812,
      "loss": 0.4778,
      "step": 242
    },
    {
      "epoch": 3.050156739811912,
      "grad_norm": 0.2758055031299591,
      "learning_rate": 0.0001890314465408805,
      "loss": 0.4029,
      "step": 244
    },
    {
      "epoch": 3.0752351097178683,
      "grad_norm": 0.2382444590330124,
      "learning_rate": 0.0001889308176100629,
      "loss": 0.3801,
      "step": 246
    },
    {
      "epoch": 3.1003134796238245,
      "grad_norm": 0.24490897357463837,
      "learning_rate": 0.0001888301886792453,
      "loss": 0.3975,
      "step": 248
    },
    {
      "epoch": 3.1253918495297803,
      "grad_norm": 0.26239147782325745,
      "learning_rate": 0.00018872955974842768,
      "loss": 0.4038,
      "step": 250
    },
    {
      "epoch": 3.1504702194357366,
      "grad_norm": 0.24605032801628113,
      "learning_rate": 0.00018862893081761007,
      "loss": 0.4364,
      "step": 252
    },
    {
      "epoch": 3.175548589341693,
      "grad_norm": 0.28764280676841736,
      "learning_rate": 0.00018852830188679248,
      "loss": 0.3577,
      "step": 254
    },
    {
      "epoch": 3.200626959247649,
      "grad_norm": 0.23804618418216705,
      "learning_rate": 0.00018842767295597484,
      "loss": 0.4155,
      "step": 256
    },
    {
      "epoch": 3.225705329153605,
      "grad_norm": 0.25497862696647644,
      "learning_rate": 0.00018832704402515723,
      "loss": 0.4654,
      "step": 258
    },
    {
      "epoch": 3.250783699059561,
      "grad_norm": 0.23537839949131012,
      "learning_rate": 0.00018822641509433962,
      "loss": 0.4144,
      "step": 260
    },
    {
      "epoch": 3.2758620689655173,
      "grad_norm": 0.268036812543869,
      "learning_rate": 0.000188125786163522,
      "loss": 0.4546,
      "step": 262
    },
    {
      "epoch": 3.300940438871473,
      "grad_norm": 0.25395911931991577,
      "learning_rate": 0.00018802515723270443,
      "loss": 0.4604,
      "step": 264
    },
    {
      "epoch": 3.3260188087774294,
      "grad_norm": 0.3395281732082367,
      "learning_rate": 0.00018792452830188681,
      "loss": 0.5816,
      "step": 266
    },
    {
      "epoch": 3.3510971786833856,
      "grad_norm": 0.258900910615921,
      "learning_rate": 0.0001878238993710692,
      "loss": 0.4415,
      "step": 268
    },
    {
      "epoch": 3.376175548589342,
      "grad_norm": 0.24031828343868256,
      "learning_rate": 0.00018772327044025156,
      "loss": 0.469,
      "step": 270
    },
    {
      "epoch": 3.4012539184952977,
      "grad_norm": 0.26624906063079834,
      "learning_rate": 0.00018762264150943395,
      "loss": 0.4304,
      "step": 272
    },
    {
      "epoch": 3.426332288401254,
      "grad_norm": 0.2869020998477936,
      "learning_rate": 0.00018752201257861637,
      "loss": 0.4623,
      "step": 274
    },
    {
      "epoch": 3.45141065830721,
      "grad_norm": 0.2383798062801361,
      "learning_rate": 0.00018742138364779876,
      "loss": 0.3973,
      "step": 276
    },
    {
      "epoch": 3.476489028213166,
      "grad_norm": 0.25947991013526917,
      "learning_rate": 0.00018732075471698115,
      "loss": 0.4468,
      "step": 278
    },
    {
      "epoch": 3.501567398119122,
      "grad_norm": 0.21950559318065643,
      "learning_rate": 0.00018722012578616354,
      "loss": 0.3432,
      "step": 280
    },
    {
      "epoch": 3.5266457680250785,
      "grad_norm": 0.26003995537757874,
      "learning_rate": 0.00018711949685534592,
      "loss": 0.4664,
      "step": 282
    },
    {
      "epoch": 3.5517241379310347,
      "grad_norm": 0.2847505807876587,
      "learning_rate": 0.0001870188679245283,
      "loss": 0.4583,
      "step": 284
    },
    {
      "epoch": 3.5768025078369905,
      "grad_norm": 0.2824760973453522,
      "learning_rate": 0.0001869182389937107,
      "loss": 0.4735,
      "step": 286
    },
    {
      "epoch": 3.6018808777429467,
      "grad_norm": 0.268838107585907,
      "learning_rate": 0.0001868176100628931,
      "loss": 0.4071,
      "step": 288
    },
    {
      "epoch": 3.626959247648903,
      "grad_norm": 0.24519529938697815,
      "learning_rate": 0.00018671698113207548,
      "loss": 0.4178,
      "step": 290
    },
    {
      "epoch": 3.652037617554859,
      "grad_norm": 0.24740180373191833,
      "learning_rate": 0.00018661635220125787,
      "loss": 0.4716,
      "step": 292
    },
    {
      "epoch": 3.677115987460815,
      "grad_norm": 0.22623687982559204,
      "learning_rate": 0.00018651572327044026,
      "loss": 0.3645,
      "step": 294
    },
    {
      "epoch": 3.7021943573667713,
      "grad_norm": 0.2554280459880829,
      "learning_rate": 0.00018641509433962264,
      "loss": 0.4044,
      "step": 296
    },
    {
      "epoch": 3.7272727272727275,
      "grad_norm": 0.2251761108636856,
      "learning_rate": 0.00018631446540880503,
      "loss": 0.3663,
      "step": 298
    },
    {
      "epoch": 3.7523510971786833,
      "grad_norm": 0.20053140819072723,
      "learning_rate": 0.00018621383647798742,
      "loss": 0.4342,
      "step": 300
    },
    {
      "epoch": 3.7774294670846396,
      "grad_norm": 0.2692326605319977,
      "learning_rate": 0.0001861132075471698,
      "loss": 0.4268,
      "step": 302
    },
    {
      "epoch": 3.8025078369905954,
      "grad_norm": 0.23218081891536713,
      "learning_rate": 0.00018601257861635223,
      "loss": 0.4848,
      "step": 304
    },
    {
      "epoch": 3.8275862068965516,
      "grad_norm": 0.2571001648902893,
      "learning_rate": 0.00018591194968553462,
      "loss": 0.5391,
      "step": 306
    },
    {
      "epoch": 3.852664576802508,
      "grad_norm": 0.20899826288223267,
      "learning_rate": 0.00018581132075471698,
      "loss": 0.4183,
      "step": 308
    },
    {
      "epoch": 3.877742946708464,
      "grad_norm": 0.24893143773078918,
      "learning_rate": 0.00018571069182389937,
      "loss": 0.4314,
      "step": 310
    },
    {
      "epoch": 3.9028213166144203,
      "grad_norm": 0.26598888635635376,
      "learning_rate": 0.00018561006289308175,
      "loss": 0.4182,
      "step": 312
    },
    {
      "epoch": 3.927899686520376,
      "grad_norm": 0.24121470749378204,
      "learning_rate": 0.00018550943396226417,
      "loss": 0.4327,
      "step": 314
    },
    {
      "epoch": 3.9529780564263324,
      "grad_norm": 0.2874317467212677,
      "learning_rate": 0.00018540880503144656,
      "loss": 0.4616,
      "step": 316
    },
    {
      "epoch": 3.978056426332288,
      "grad_norm": 0.22735589742660522,
      "learning_rate": 0.00018530817610062895,
      "loss": 0.376,
      "step": 318
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.3424147069454193,
      "learning_rate": 0.00018520754716981134,
      "loss": 0.537,
      "step": 320
    },
    {
      "epoch": 4.025078369905956,
      "grad_norm": 0.27403339743614197,
      "learning_rate": 0.0001851069182389937,
      "loss": 0.3539,
      "step": 322
    },
    {
      "epoch": 4.0501567398119125,
      "grad_norm": 0.33905503153800964,
      "learning_rate": 0.0001850062893081761,
      "loss": 0.3367,
      "step": 324
    },
    {
      "epoch": 4.075235109717869,
      "grad_norm": 0.47853460907936096,
      "learning_rate": 0.0001849056603773585,
      "loss": 0.393,
      "step": 326
    },
    {
      "epoch": 4.100313479623824,
      "grad_norm": 0.3133102059364319,
      "learning_rate": 0.0001848050314465409,
      "loss": 0.3762,
      "step": 328
    },
    {
      "epoch": 4.12539184952978,
      "grad_norm": 0.22834369540214539,
      "learning_rate": 0.00018470440251572328,
      "loss": 0.3404,
      "step": 330
    },
    {
      "epoch": 4.150470219435737,
      "grad_norm": 0.2537166476249695,
      "learning_rate": 0.00018460377358490567,
      "loss": 0.3582,
      "step": 332
    },
    {
      "epoch": 4.175548589341693,
      "grad_norm": 0.35708144307136536,
      "learning_rate": 0.00018450314465408806,
      "loss": 0.369,
      "step": 334
    },
    {
      "epoch": 4.200626959247649,
      "grad_norm": 0.3224405348300934,
      "learning_rate": 0.00018440251572327045,
      "loss": 0.3458,
      "step": 336
    },
    {
      "epoch": 4.225705329153605,
      "grad_norm": 0.34621739387512207,
      "learning_rate": 0.00018430188679245283,
      "loss": 0.4176,
      "step": 338
    },
    {
      "epoch": 4.250783699059561,
      "grad_norm": 0.24818404018878937,
      "learning_rate": 0.00018420125786163522,
      "loss": 0.3205,
      "step": 340
    },
    {
      "epoch": 4.275862068965517,
      "grad_norm": 0.29599064588546753,
      "learning_rate": 0.0001841006289308176,
      "loss": 0.3696,
      "step": 342
    },
    {
      "epoch": 4.300940438871473,
      "grad_norm": 0.2980504333972931,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.3256,
      "step": 344
    },
    {
      "epoch": 4.326018808777429,
      "grad_norm": 0.35454604029655457,
      "learning_rate": 0.0001838993710691824,
      "loss": 0.4957,
      "step": 346
    },
    {
      "epoch": 4.351097178683386,
      "grad_norm": 0.3497369885444641,
      "learning_rate": 0.00018379874213836478,
      "loss": 0.3941,
      "step": 348
    },
    {
      "epoch": 4.376175548589342,
      "grad_norm": 0.32460692524909973,
      "learning_rate": 0.00018369811320754717,
      "loss": 0.3615,
      "step": 350
    },
    {
      "epoch": 4.401253918495298,
      "grad_norm": 0.29358094930648804,
      "learning_rate": 0.00018359748427672955,
      "loss": 0.3749,
      "step": 352
    },
    {
      "epoch": 4.4263322884012535,
      "grad_norm": 0.2807920575141907,
      "learning_rate": 0.00018349685534591197,
      "loss": 0.3575,
      "step": 354
    },
    {
      "epoch": 4.45141065830721,
      "grad_norm": 0.2809455096721649,
      "learning_rate": 0.00018339622641509436,
      "loss": 0.3097,
      "step": 356
    },
    {
      "epoch": 4.476489028213166,
      "grad_norm": 0.3250884413719177,
      "learning_rate": 0.00018329559748427675,
      "loss": 0.4113,
      "step": 358
    },
    {
      "epoch": 4.501567398119122,
      "grad_norm": 0.29040804505348206,
      "learning_rate": 0.0001831949685534591,
      "loss": 0.4481,
      "step": 360
    },
    {
      "epoch": 4.5266457680250785,
      "grad_norm": 0.3208359479904175,
      "learning_rate": 0.0001830943396226415,
      "loss": 0.4438,
      "step": 362
    },
    {
      "epoch": 4.551724137931035,
      "grad_norm": 0.23080404102802277,
      "learning_rate": 0.00018299371069182391,
      "loss": 0.2099,
      "step": 364
    },
    {
      "epoch": 4.576802507836991,
      "grad_norm": 0.2984071373939514,
      "learning_rate": 0.0001828930817610063,
      "loss": 0.3339,
      "step": 366
    },
    {
      "epoch": 4.601880877742946,
      "grad_norm": 0.3299279808998108,
      "learning_rate": 0.0001827924528301887,
      "loss": 0.4208,
      "step": 368
    },
    {
      "epoch": 4.6269592476489025,
      "grad_norm": 0.3243483006954193,
      "learning_rate": 0.00018269182389937108,
      "loss": 0.4165,
      "step": 370
    },
    {
      "epoch": 4.652037617554859,
      "grad_norm": 0.29541853070259094,
      "learning_rate": 0.00018259119496855347,
      "loss": 0.3703,
      "step": 372
    },
    {
      "epoch": 4.677115987460815,
      "grad_norm": 0.3010431230068207,
      "learning_rate": 0.00018249056603773586,
      "loss": 0.4034,
      "step": 374
    },
    {
      "epoch": 4.702194357366771,
      "grad_norm": 0.2970607578754425,
      "learning_rate": 0.00018238993710691825,
      "loss": 0.3151,
      "step": 376
    },
    {
      "epoch": 4.7272727272727275,
      "grad_norm": 0.2794083058834076,
      "learning_rate": 0.00018228930817610063,
      "loss": 0.3605,
      "step": 378
    },
    {
      "epoch": 4.752351097178684,
      "grad_norm": 0.2949012219905853,
      "learning_rate": 0.00018218867924528302,
      "loss": 0.343,
      "step": 380
    },
    {
      "epoch": 4.777429467084639,
      "grad_norm": 0.28160709142684937,
      "learning_rate": 0.0001820880503144654,
      "loss": 0.4515,
      "step": 382
    },
    {
      "epoch": 4.802507836990595,
      "grad_norm": 0.296051561832428,
      "learning_rate": 0.00018198742138364783,
      "loss": 0.3908,
      "step": 384
    },
    {
      "epoch": 4.827586206896552,
      "grad_norm": 0.26115506887435913,
      "learning_rate": 0.0001818867924528302,
      "loss": 0.3312,
      "step": 386
    },
    {
      "epoch": 4.852664576802508,
      "grad_norm": 0.27632880210876465,
      "learning_rate": 0.00018178616352201258,
      "loss": 0.3179,
      "step": 388
    },
    {
      "epoch": 4.877742946708464,
      "grad_norm": 0.2973230481147766,
      "learning_rate": 0.00018168553459119497,
      "loss": 0.382,
      "step": 390
    },
    {
      "epoch": 4.90282131661442,
      "grad_norm": 0.2833520472049713,
      "learning_rate": 0.00018158490566037736,
      "loss": 0.3363,
      "step": 392
    },
    {
      "epoch": 4.927899686520377,
      "grad_norm": 0.30823326110839844,
      "learning_rate": 0.00018148427672955977,
      "loss": 0.3234,
      "step": 394
    },
    {
      "epoch": 4.952978056426332,
      "grad_norm": 0.2736763060092926,
      "learning_rate": 0.00018138364779874216,
      "loss": 0.415,
      "step": 396
    },
    {
      "epoch": 4.978056426332288,
      "grad_norm": 0.2832898199558258,
      "learning_rate": 0.00018128301886792455,
      "loss": 0.3755,
      "step": 398
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.3281781077384949,
      "learning_rate": 0.0001811823899371069,
      "loss": 0.2756,
      "step": 400
    }
  ],
  "logging_steps": 2,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.25570189464994e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}