{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.951768488745981,
  "eval_steps": 500,
  "global_step": 385,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012861736334405145,
      "grad_norm": 258.1509094238281,
      "learning_rate": 8.333333333333335e-09,
      "loss": 8.1083,
      "num_input_tokens_seen": 16544,
      "step": 1
    },
    {
      "epoch": 0.02572347266881029,
      "grad_norm": 266.15087890625,
      "learning_rate": 1.666666666666667e-08,
      "loss": 8.1052,
      "num_input_tokens_seen": 33248,
      "step": 2
    },
    {
      "epoch": 0.03858520900321544,
      "grad_norm": 276.69952392578125,
      "learning_rate": 2.5000000000000002e-08,
      "loss": 8.1366,
      "num_input_tokens_seen": 49760,
      "step": 3
    },
    {
      "epoch": 0.05144694533762058,
      "grad_norm": 268.43804931640625,
      "learning_rate": 3.333333333333334e-08,
      "loss": 8.0413,
      "num_input_tokens_seen": 65824,
      "step": 4
    },
    {
      "epoch": 0.06430868167202572,
      "grad_norm": 269.6364440917969,
      "learning_rate": 4.166666666666667e-08,
      "loss": 8.1055,
      "num_input_tokens_seen": 82560,
      "step": 5
    },
    {
      "epoch": 0.07717041800643087,
      "grad_norm": 274.33538818359375,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 7.9666,
      "num_input_tokens_seen": 99808,
      "step": 6
    },
    {
      "epoch": 0.09003215434083602,
      "grad_norm": 266.3240051269531,
      "learning_rate": 5.833333333333334e-08,
      "loss": 8.0182,
      "num_input_tokens_seen": 115808,
      "step": 7
    },
    {
      "epoch": 0.10289389067524116,
      "grad_norm": 274.253662109375,
      "learning_rate": 6.666666666666668e-08,
      "loss": 8.0363,
      "num_input_tokens_seen": 131392,
      "step": 8
    },
    {
      "epoch": 0.1157556270096463,
      "grad_norm": 263.321533203125,
      "learning_rate": 7.500000000000001e-08,
      "loss": 8.0918,
      "num_input_tokens_seen": 147840,
      "step": 9
    },
    {
      "epoch": 0.12861736334405144,
      "grad_norm": 266.48394775390625,
      "learning_rate": 8.333333333333334e-08,
      "loss": 8.0197,
      "num_input_tokens_seen": 164064,
      "step": 10
    },
    {
      "epoch": 0.1414790996784566,
      "grad_norm": 258.7409362792969,
      "learning_rate": 9.166666666666668e-08,
      "loss": 7.9714,
      "num_input_tokens_seen": 180704,
      "step": 11
    },
    {
      "epoch": 0.15434083601286175,
      "grad_norm": 271.2587585449219,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 8.0131,
      "num_input_tokens_seen": 196064,
      "step": 12
    },
    {
      "epoch": 0.16720257234726688,
      "grad_norm": 255.18431091308594,
      "learning_rate": 1.0833333333333335e-07,
      "loss": 7.9796,
      "num_input_tokens_seen": 211424,
      "step": 13
    },
    {
      "epoch": 0.18006430868167203,
      "grad_norm": 269.7242736816406,
      "learning_rate": 1.1666666666666668e-07,
      "loss": 7.9999,
      "num_input_tokens_seen": 228096,
      "step": 14
    },
    {
      "epoch": 0.19292604501607716,
      "grad_norm": 264.5142517089844,
      "learning_rate": 1.2500000000000002e-07,
      "loss": 8.0168,
      "num_input_tokens_seen": 244416,
      "step": 15
    },
    {
      "epoch": 0.2057877813504823,
      "grad_norm": 267.4490661621094,
      "learning_rate": 1.3333333333333336e-07,
      "loss": 7.8423,
      "num_input_tokens_seen": 261056,
      "step": 16
    },
    {
      "epoch": 0.21864951768488747,
      "grad_norm": 269.4408874511719,
      "learning_rate": 1.4166666666666668e-07,
      "loss": 7.9208,
      "num_input_tokens_seen": 276992,
      "step": 17
    },
    {
      "epoch": 0.2315112540192926,
      "grad_norm": 256.512939453125,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 7.6898,
      "num_input_tokens_seen": 293536,
      "step": 18
    },
    {
      "epoch": 0.24437299035369775,
      "grad_norm": 265.34490966796875,
      "learning_rate": 1.5833333333333336e-07,
      "loss": 7.9285,
      "num_input_tokens_seen": 309024,
      "step": 19
    },
    {
      "epoch": 0.2572347266881029,
      "grad_norm": 268.9532470703125,
      "learning_rate": 1.6666666666666668e-07,
      "loss": 7.8924,
      "num_input_tokens_seen": 325024,
      "step": 20
    },
    {
      "epoch": 0.27009646302250806,
      "grad_norm": 268.1192321777344,
      "learning_rate": 1.7500000000000002e-07,
      "loss": 7.6173,
      "num_input_tokens_seen": 341856,
      "step": 21
    },
    {
      "epoch": 0.2829581993569132,
      "grad_norm": 271.13006591796875,
      "learning_rate": 1.8333333333333336e-07,
      "loss": 7.7661,
      "num_input_tokens_seen": 358848,
      "step": 22
    },
    {
      "epoch": 0.2958199356913183,
      "grad_norm": 260.5618591308594,
      "learning_rate": 1.9166666666666668e-07,
      "loss": 7.2936,
      "num_input_tokens_seen": 375360,
      "step": 23
    },
    {
      "epoch": 0.3086816720257235,
      "grad_norm": 249.86729431152344,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 7.3044,
      "num_input_tokens_seen": 392608,
      "step": 24
    },
    {
      "epoch": 0.3215434083601286,
      "grad_norm": 257.8570861816406,
      "learning_rate": 2.0833333333333333e-07,
      "loss": 7.35,
      "num_input_tokens_seen": 408800,
      "step": 25
    },
    {
      "epoch": 0.33440514469453375,
      "grad_norm": 246.40611267089844,
      "learning_rate": 2.166666666666667e-07,
      "loss": 7.1213,
      "num_input_tokens_seen": 425632,
      "step": 26
    },
    {
      "epoch": 0.34726688102893893,
      "grad_norm": 252.2755889892578,
      "learning_rate": 2.2500000000000002e-07,
      "loss": 7.1363,
      "num_input_tokens_seen": 441952,
      "step": 27
    },
    {
      "epoch": 0.36012861736334406,
      "grad_norm": 235.94859313964844,
      "learning_rate": 2.3333333333333336e-07,
      "loss": 6.9016,
      "num_input_tokens_seen": 458080,
      "step": 28
    },
    {
      "epoch": 0.3729903536977492,
      "grad_norm": 243.25863647460938,
      "learning_rate": 2.416666666666667e-07,
      "loss": 6.9764,
      "num_input_tokens_seen": 473824,
      "step": 29
    },
    {
      "epoch": 0.3858520900321543,
      "grad_norm": 250.39564514160156,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 6.9005,
      "num_input_tokens_seen": 490336,
      "step": 30
    },
    {
      "epoch": 0.3987138263665595,
      "grad_norm": 253.6007843017578,
      "learning_rate": 2.5833333333333333e-07,
      "loss": 6.9852,
      "num_input_tokens_seen": 506976,
      "step": 31
    },
    {
      "epoch": 0.4115755627009646,
      "grad_norm": 155.81201171875,
      "learning_rate": 2.666666666666667e-07,
      "loss": 5.834,
      "num_input_tokens_seen": 523520,
      "step": 32
    },
    {
      "epoch": 0.42443729903536975,
      "grad_norm": 124.55789947509766,
      "learning_rate": 2.75e-07,
      "loss": 5.5452,
      "num_input_tokens_seen": 540672,
      "step": 33
    },
    {
      "epoch": 0.43729903536977494,
      "grad_norm": 130.3427276611328,
      "learning_rate": 2.8333333333333336e-07,
      "loss": 5.5189,
      "num_input_tokens_seen": 557696,
      "step": 34
    },
    {
      "epoch": 0.45016077170418006,
      "grad_norm": 126.62003326416016,
      "learning_rate": 2.916666666666667e-07,
      "loss": 5.4654,
      "num_input_tokens_seen": 574400,
      "step": 35
    },
    {
      "epoch": 0.4630225080385852,
      "grad_norm": 120.25413513183594,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 5.3117,
      "num_input_tokens_seen": 590112,
      "step": 36
    },
    {
      "epoch": 0.4758842443729904,
      "grad_norm": 123.52056884765625,
      "learning_rate": 3.083333333333334e-07,
      "loss": 5.2744,
      "num_input_tokens_seen": 605920,
      "step": 37
    },
    {
      "epoch": 0.4887459807073955,
      "grad_norm": 124.25894927978516,
      "learning_rate": 3.166666666666667e-07,
      "loss": 5.2821,
      "num_input_tokens_seen": 622208,
      "step": 38
    },
    {
      "epoch": 0.5016077170418006,
      "grad_norm": 111.38367462158203,
      "learning_rate": 3.25e-07,
      "loss": 5.0967,
      "num_input_tokens_seen": 638464,
      "step": 39
    },
    {
      "epoch": 0.5144694533762058,
      "grad_norm": 119.48200225830078,
      "learning_rate": 3.3333333333333335e-07,
      "loss": 5.2167,
      "num_input_tokens_seen": 654656,
      "step": 40
    },
    {
      "epoch": 0.5273311897106109,
      "grad_norm": 108.62528991699219,
      "learning_rate": 3.416666666666667e-07,
      "loss": 5.1517,
      "num_input_tokens_seen": 671424,
      "step": 41
    },
    {
      "epoch": 0.5401929260450161,
      "grad_norm": 109.66475677490234,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 4.6959,
      "num_input_tokens_seen": 687968,
      "step": 42
    },
    {
      "epoch": 0.5530546623794212,
      "grad_norm": 107.45171356201172,
      "learning_rate": 3.583333333333334e-07,
      "loss": 4.1458,
      "num_input_tokens_seen": 704224,
      "step": 43
    },
    {
      "epoch": 0.5659163987138264,
      "grad_norm": 102.30545806884766,
      "learning_rate": 3.666666666666667e-07,
      "loss": 3.6692,
      "num_input_tokens_seen": 720704,
      "step": 44
    },
    {
      "epoch": 0.5787781350482315,
      "grad_norm": 96.8830795288086,
      "learning_rate": 3.75e-07,
      "loss": 3.3322,
      "num_input_tokens_seen": 737408,
      "step": 45
    },
    {
      "epoch": 0.5916398713826366,
      "grad_norm": 102.91023254394531,
      "learning_rate": 3.8333333333333335e-07,
      "loss": 3.2857,
      "num_input_tokens_seen": 753728,
      "step": 46
    },
    {
      "epoch": 0.6045016077170418,
      "grad_norm": 105.37537384033203,
      "learning_rate": 3.9166666666666675e-07,
      "loss": 3.0806,
      "num_input_tokens_seen": 770080,
      "step": 47
    },
    {
      "epoch": 0.617363344051447,
      "grad_norm": 98.45983123779297,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.8239,
      "num_input_tokens_seen": 786912,
      "step": 48
    },
    {
      "epoch": 0.6302250803858521,
      "grad_norm": 108.93148040771484,
      "learning_rate": 4.083333333333334e-07,
      "loss": 2.8695,
      "num_input_tokens_seen": 804192,
      "step": 49
    },
    {
      "epoch": 0.6430868167202572,
      "grad_norm": 100.31180572509766,
      "learning_rate": 4.1666666666666667e-07,
      "loss": 2.6218,
      "num_input_tokens_seen": 820928,
      "step": 50
    },
    {
      "epoch": 0.6559485530546624,
      "grad_norm": 101.31784057617188,
      "learning_rate": 4.2500000000000006e-07,
      "loss": 2.3993,
      "num_input_tokens_seen": 837152,
      "step": 51
    },
    {
      "epoch": 0.6688102893890675,
      "grad_norm": 101.09466552734375,
      "learning_rate": 4.333333333333334e-07,
      "loss": 2.2828,
      "num_input_tokens_seen": 853568,
      "step": 52
    },
    {
      "epoch": 0.6816720257234726,
      "grad_norm": 99.55025482177734,
      "learning_rate": 4.416666666666667e-07,
      "loss": 2.2063,
      "num_input_tokens_seen": 870592,
      "step": 53
    },
    {
      "epoch": 0.6945337620578779,
      "grad_norm": 104.6786117553711,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 1.8878,
      "num_input_tokens_seen": 886080,
      "step": 54
    },
    {
      "epoch": 0.707395498392283,
      "grad_norm": 106.05968475341797,
      "learning_rate": 4.583333333333333e-07,
      "loss": 1.5971,
      "num_input_tokens_seen": 903296,
      "step": 55
    },
    {
      "epoch": 0.7202572347266881,
      "grad_norm": 93.43476867675781,
      "learning_rate": 4.666666666666667e-07,
      "loss": 0.9604,
      "num_input_tokens_seen": 919296,
      "step": 56
    },
    {
      "epoch": 0.7331189710610932,
      "grad_norm": 60.13694763183594,
      "learning_rate": 4.7500000000000006e-07,
      "loss": 0.6287,
      "num_input_tokens_seen": 936096,
      "step": 57
    },
    {
      "epoch": 0.7459807073954984,
      "grad_norm": 42.870086669921875,
      "learning_rate": 4.833333333333334e-07,
      "loss": 0.4844,
      "num_input_tokens_seen": 953024,
      "step": 58
    },
    {
      "epoch": 0.7588424437299035,
      "grad_norm": 45.984989166259766,
      "learning_rate": 4.916666666666667e-07,
      "loss": 0.3891,
      "num_input_tokens_seen": 969024,
      "step": 59
    },
    {
      "epoch": 0.7717041800643086,
      "grad_norm": 44.375484466552734,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.357,
      "num_input_tokens_seen": 985600,
      "step": 60
    },
    {
      "epoch": 0.7845659163987139,
      "grad_norm": 28.2038516998291,
      "learning_rate": 5.083333333333334e-07,
      "loss": 0.2854,
      "num_input_tokens_seen": 1002336,
      "step": 61
    },
    {
      "epoch": 0.797427652733119,
      "grad_norm": 13.842344284057617,
      "learning_rate": 5.166666666666667e-07,
      "loss": 0.2403,
      "num_input_tokens_seen": 1018496,
      "step": 62
    },
    {
      "epoch": 0.8102893890675241,
      "grad_norm": 21.351642608642578,
      "learning_rate": 5.250000000000001e-07,
      "loss": 0.2522,
      "num_input_tokens_seen": 1035552,
      "step": 63
    },
    {
      "epoch": 0.8231511254019293,
      "grad_norm": 21.38069725036621,
      "learning_rate": 5.333333333333335e-07,
      "loss": 0.2339,
      "num_input_tokens_seen": 1051584,
      "step": 64
    },
    {
      "epoch": 0.8360128617363344,
      "grad_norm": 9.553906440734863,
      "learning_rate": 5.416666666666667e-07,
      "loss": 0.2214,
      "num_input_tokens_seen": 1068640,
      "step": 65
    },
    {
      "epoch": 0.8488745980707395,
      "grad_norm": 6.100700855255127,
      "learning_rate": 5.5e-07,
      "loss": 0.1912,
      "num_input_tokens_seen": 1085568,
      "step": 66
    },
    {
      "epoch": 0.8617363344051447,
      "grad_norm": 18.959564208984375,
      "learning_rate": 5.583333333333333e-07,
      "loss": 0.2157,
      "num_input_tokens_seen": 1102784,
      "step": 67
    },
    {
      "epoch": 0.8745980707395499,
      "grad_norm": 16.303438186645508,
      "learning_rate": 5.666666666666667e-07,
      "loss": 0.2045,
      "num_input_tokens_seen": 1118432,
      "step": 68
    },
    {
      "epoch": 0.887459807073955,
      "grad_norm": 12.491047859191895,
      "learning_rate": 5.750000000000001e-07,
      "loss": 0.1964,
      "num_input_tokens_seen": 1135232,
      "step": 69
    },
    {
      "epoch": 0.9003215434083601,
      "grad_norm": 16.655309677124023,
      "learning_rate": 5.833333333333334e-07,
      "loss": 0.1901,
      "num_input_tokens_seen": 1150496,
      "step": 70
    },
    {
      "epoch": 0.9131832797427653,
      "grad_norm": 12.015859603881836,
      "learning_rate": 5.916666666666667e-07,
      "loss": 0.1891,
      "num_input_tokens_seen": 1166848,
      "step": 71
    },
    {
      "epoch": 0.9260450160771704,
      "grad_norm": 12.255152702331543,
      "learning_rate": 6.000000000000001e-07,
      "loss": 0.1841,
      "num_input_tokens_seen": 1183552,
      "step": 72
    },
    {
      "epoch": 0.9389067524115756,
      "grad_norm": 5.163099765777588,
      "learning_rate": 6.083333333333334e-07,
      "loss": 0.1803,
      "num_input_tokens_seen": 1199968,
      "step": 73
    },
    {
      "epoch": 0.9517684887459807,
      "grad_norm": 10.502095222473145,
      "learning_rate": 6.166666666666668e-07,
      "loss": 0.1657,
      "num_input_tokens_seen": 1216256,
      "step": 74
    },
    {
      "epoch": 0.9646302250803859,
      "grad_norm": 23.80043601989746,
      "learning_rate": 6.25e-07,
      "loss": 0.2157,
      "num_input_tokens_seen": 1232736,
      "step": 75
    },
    {
      "epoch": 0.977491961414791,
      "grad_norm": 19.7410831451416,
      "learning_rate": 6.333333333333334e-07,
      "loss": 0.2,
      "num_input_tokens_seen": 1249248,
      "step": 76
    },
    {
      "epoch": 0.9903536977491961,
      "grad_norm": 4.730998516082764,
      "learning_rate": 6.416666666666667e-07,
      "loss": 0.1519,
      "num_input_tokens_seen": 1265152,
      "step": 77
    },
    {
      "epoch": 1.0032154340836013,
      "grad_norm": 14.700318336486816,
      "learning_rate": 6.5e-07,
      "loss": 0.1765,
      "num_input_tokens_seen": 1282336,
      "step": 78
    },
    {
      "epoch": 1.0160771704180065,
      "grad_norm": 18.6468448638916,
      "learning_rate": 6.583333333333333e-07,
      "loss": 0.1907,
      "num_input_tokens_seen": 1299168,
      "step": 79
    },
    {
      "epoch": 1.0289389067524115,
      "grad_norm": 11.44071102142334,
      "learning_rate": 6.666666666666667e-07,
      "loss": 0.1593,
      "num_input_tokens_seen": 1314816,
      "step": 80
    },
    {
      "epoch": 1.0418006430868167,
      "grad_norm": 3.6438238620758057,
      "learning_rate": 6.750000000000001e-07,
      "loss": 0.1659,
      "num_input_tokens_seen": 1331168,
      "step": 81
    },
    {
      "epoch": 1.0546623794212218,
      "grad_norm": 3.6471991539001465,
      "learning_rate": 6.833333333333334e-07,
      "loss": 0.1619,
      "num_input_tokens_seen": 1347968,
      "step": 82
    },
    {
      "epoch": 1.067524115755627,
      "grad_norm": 4.136232376098633,
      "learning_rate": 6.916666666666668e-07,
      "loss": 0.168,
      "num_input_tokens_seen": 1363872,
      "step": 83
    },
    {
      "epoch": 1.0803858520900322,
      "grad_norm": 4.436996936798096,
      "learning_rate": 7.000000000000001e-07,
      "loss": 0.1627,
      "num_input_tokens_seen": 1380896,
      "step": 84
    },
    {
      "epoch": 1.0932475884244373,
      "grad_norm": 10.516170501708984,
      "learning_rate": 7.083333333333334e-07,
      "loss": 0.1421,
      "num_input_tokens_seen": 1397792,
      "step": 85
    },
    {
      "epoch": 1.1061093247588425,
      "grad_norm": 15.584237098693848,
      "learning_rate": 7.166666666666668e-07,
      "loss": 0.1517,
      "num_input_tokens_seen": 1414272,
      "step": 86
    },
    {
      "epoch": 1.1189710610932475,
      "grad_norm": 8.475227355957031,
      "learning_rate": 7.25e-07,
      "loss": 0.1519,
      "num_input_tokens_seen": 1429696,
      "step": 87
    },
    {
      "epoch": 1.1318327974276527,
      "grad_norm": 5.768808841705322,
      "learning_rate": 7.333333333333334e-07,
      "loss": 0.128,
      "num_input_tokens_seen": 1446720,
      "step": 88
    },
    {
      "epoch": 1.144694533762058,
      "grad_norm": 15.064901351928711,
      "learning_rate": 7.416666666666668e-07,
      "loss": 0.1481,
      "num_input_tokens_seen": 1463008,
      "step": 89
    },
    {
      "epoch": 1.157556270096463,
      "grad_norm": 17.70471954345703,
      "learning_rate": 7.5e-07,
      "loss": 0.1636,
      "num_input_tokens_seen": 1480096,
      "step": 90
    },
    {
      "epoch": 1.1704180064308682,
      "grad_norm": 5.037917613983154,
      "learning_rate": 7.583333333333334e-07,
      "loss": 0.1443,
      "num_input_tokens_seen": 1497024,
      "step": 91
    },
    {
      "epoch": 1.1832797427652733,
      "grad_norm": 17.397666931152344,
      "learning_rate": 7.666666666666667e-07,
      "loss": 0.1592,
      "num_input_tokens_seen": 1513792,
      "step": 92
    },
    {
      "epoch": 1.1961414790996785,
      "grad_norm": 18.808683395385742,
      "learning_rate": 7.750000000000001e-07,
      "loss": 0.1744,
      "num_input_tokens_seen": 1529696,
      "step": 93
    },
    {
      "epoch": 1.2090032154340835,
      "grad_norm": 15.173974990844727,
      "learning_rate": 7.833333333333335e-07,
      "loss": 0.1615,
      "num_input_tokens_seen": 1546400,
      "step": 94
    },
    {
      "epoch": 1.2218649517684887,
      "grad_norm": 3.6459403038024902,
      "learning_rate": 7.916666666666667e-07,
      "loss": 0.1466,
      "num_input_tokens_seen": 1564448,
      "step": 95
    },
    {
      "epoch": 1.234726688102894,
      "grad_norm": 4.910373210906982,
      "learning_rate": 8.000000000000001e-07,
      "loss": 0.1333,
      "num_input_tokens_seen": 1580736,
      "step": 96
    },
    {
      "epoch": 1.247588424437299,
      "grad_norm": 11.399758338928223,
      "learning_rate": 8.083333333333334e-07,
      "loss": 0.1475,
      "num_input_tokens_seen": 1596928,
      "step": 97
    },
    {
      "epoch": 1.2604501607717042,
      "grad_norm": 4.701439380645752,
      "learning_rate": 8.166666666666668e-07,
      "loss": 0.142,
      "num_input_tokens_seen": 1613728,
      "step": 98
    },
    {
      "epoch": 1.2733118971061093,
      "grad_norm": 7.250323295593262,
      "learning_rate": 8.250000000000001e-07,
      "loss": 0.148,
      "num_input_tokens_seen": 1630112,
      "step": 99
    },
    {
      "epoch": 1.2861736334405145,
      "grad_norm": 17.24268341064453,
      "learning_rate": 8.333333333333333e-07,
      "loss": 0.1539,
      "num_input_tokens_seen": 1645248,
      "step": 100
    },
    {
      "epoch": 1.2990353697749195,
      "grad_norm": 4.017528057098389,
      "learning_rate": 8.416666666666667e-07,
      "loss": 0.1496,
      "num_input_tokens_seen": 1662400,
      "step": 101
    },
    {
      "epoch": 1.3118971061093248,
      "grad_norm": 10.226727485656738,
      "learning_rate": 8.500000000000001e-07,
      "loss": 0.1563,
      "num_input_tokens_seen": 1678528,
      "step": 102
    },
    {
      "epoch": 1.32475884244373,
      "grad_norm": 4.085242748260498,
      "learning_rate": 8.583333333333334e-07,
      "loss": 0.1295,
      "num_input_tokens_seen": 1694432,
      "step": 103
    },
    {
      "epoch": 1.337620578778135,
      "grad_norm": 9.983370780944824,
      "learning_rate": 8.666666666666668e-07,
      "loss": 0.1353,
      "num_input_tokens_seen": 1710624,
      "step": 104
    },
    {
      "epoch": 1.3504823151125402,
      "grad_norm": 6.53292179107666,
      "learning_rate": 8.75e-07,
      "loss": 0.1376,
      "num_input_tokens_seen": 1726560,
      "step": 105
    },
    {
      "epoch": 1.3633440514469453,
      "grad_norm": 4.412125587463379,
      "learning_rate": 8.833333333333334e-07,
      "loss": 0.1313,
      "num_input_tokens_seen": 1742912,
      "step": 106
    },
    {
      "epoch": 1.3762057877813505,
      "grad_norm": 13.620604515075684,
      "learning_rate": 8.916666666666668e-07,
      "loss": 0.1367,
      "num_input_tokens_seen": 1758688,
      "step": 107
    },
    {
      "epoch": 1.3890675241157555,
      "grad_norm": 6.362453937530518,
      "learning_rate": 9.000000000000001e-07,
      "loss": 0.135,
      "num_input_tokens_seen": 1775264,
      "step": 108
    },
    {
      "epoch": 1.4019292604501608,
      "grad_norm": 3.8915514945983887,
      "learning_rate": 9.083333333333335e-07,
      "loss": 0.1212,
      "num_input_tokens_seen": 1791904,
      "step": 109
    },
    {
      "epoch": 1.414790996784566,
      "grad_norm": 9.137332916259766,
      "learning_rate": 9.166666666666666e-07,
      "loss": 0.1355,
      "num_input_tokens_seen": 1808736,
      "step": 110
    },
    {
      "epoch": 1.427652733118971,
      "grad_norm": 4.745510578155518,
      "learning_rate": 9.25e-07,
      "loss": 0.1439,
      "num_input_tokens_seen": 1825504,
      "step": 111
    },
    {
      "epoch": 1.4405144694533762,
      "grad_norm": 10.531625747680664,
      "learning_rate": 9.333333333333334e-07,
      "loss": 0.1323,
      "num_input_tokens_seen": 1842080,
      "step": 112
    },
    {
      "epoch": 1.4533762057877815,
      "grad_norm": 11.189078330993652,
      "learning_rate": 9.416666666666667e-07,
      "loss": 0.1376,
      "num_input_tokens_seen": 1858432,
      "step": 113
    },
    {
      "epoch": 1.4662379421221865,
      "grad_norm": 5.619433879852295,
      "learning_rate": 9.500000000000001e-07,
      "loss": 0.1191,
      "num_input_tokens_seen": 1874304,
      "step": 114
    },
    {
      "epoch": 1.4790996784565915,
      "grad_norm": 4.590907096862793,
      "learning_rate": 9.583333333333334e-07,
      "loss": 0.1045,
      "num_input_tokens_seen": 1890144,
      "step": 115
    },
    {
      "epoch": 1.4919614147909968,
      "grad_norm": 4.900210380554199,
      "learning_rate": 9.666666666666668e-07,
      "loss": 0.1467,
      "num_input_tokens_seen": 1905664,
      "step": 116
    },
    {
      "epoch": 1.504823151125402,
      "grad_norm": 3.0244414806365967,
      "learning_rate": 9.750000000000002e-07,
      "loss": 0.1142,
      "num_input_tokens_seen": 1922240,
      "step": 117
    },
    {
      "epoch": 1.517684887459807,
      "grad_norm": 2.886939287185669,
      "learning_rate": 9.833333333333334e-07,
      "loss": 0.1107,
      "num_input_tokens_seen": 1938240,
      "step": 118
    },
    {
      "epoch": 1.5305466237942122,
      "grad_norm": 6.869494438171387,
      "learning_rate": 9.916666666666668e-07,
      "loss": 0.146,
      "num_input_tokens_seen": 1955008,
      "step": 119
    },
    {
      "epoch": 1.5434083601286175,
      "grad_norm": 16.34566879272461,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.1533,
      "num_input_tokens_seen": 1971456,
      "step": 120
    },
    {
      "epoch": 1.5562700964630225,
      "grad_norm": 15.347967147827148,
      "learning_rate": 1.0083333333333333e-06,
      "loss": 0.1315,
      "num_input_tokens_seen": 1987552,
      "step": 121
    },
    {
      "epoch": 1.5691318327974275,
      "grad_norm": 4.213266372680664,
      "learning_rate": 1.0166666666666667e-06,
      "loss": 0.1197,
      "num_input_tokens_seen": 2004192,
      "step": 122
    },
    {
      "epoch": 1.5819935691318328,
      "grad_norm": 14.208905220031738,
      "learning_rate": 1.025e-06,
      "loss": 0.1228,
      "num_input_tokens_seen": 2020832,
      "step": 123
    },
    {
      "epoch": 1.594855305466238,
      "grad_norm": 17.388845443725586,
      "learning_rate": 1.0333333333333333e-06,
      "loss": 0.1273,
      "num_input_tokens_seen": 2037312,
      "step": 124
    },
    {
      "epoch": 1.607717041800643,
      "grad_norm": 14.383207321166992,
      "learning_rate": 1.0416666666666667e-06,
      "loss": 0.141,
      "num_input_tokens_seen": 2054304,
      "step": 125
    },
    {
      "epoch": 1.6205787781350482,
      "grad_norm": 6.2650370597839355,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 0.1315,
      "num_input_tokens_seen": 2071136,
      "step": 126
    },
    {
      "epoch": 1.6334405144694535,
      "grad_norm": 8.396490097045898,
      "learning_rate": 1.0583333333333335e-06,
      "loss": 0.1136,
      "num_input_tokens_seen": 2088064,
      "step": 127
    },
    {
      "epoch": 1.6463022508038585,
      "grad_norm": 4.598783016204834,
      "learning_rate": 1.066666666666667e-06,
      "loss": 0.1013,
      "num_input_tokens_seen": 2105120,
      "step": 128
    },
    {
      "epoch": 1.6591639871382635,
      "grad_norm": 9.912994384765625,
      "learning_rate": 1.075e-06,
      "loss": 0.1056,
      "num_input_tokens_seen": 2120992,
      "step": 129
    },
    {
      "epoch": 1.6720257234726688,
      "grad_norm": 7.70595645904541,
      "learning_rate": 1.0833333333333335e-06,
      "loss": 0.1071,
      "num_input_tokens_seen": 2137984,
      "step": 130
    },
    {
      "epoch": 1.684887459807074,
      "grad_norm": 6.183793544769287,
      "learning_rate": 1.0916666666666667e-06,
      "loss": 0.1357,
      "num_input_tokens_seen": 2154240,
      "step": 131
    },
    {
      "epoch": 1.697749196141479,
      "grad_norm": 6.863802909851074,
      "learning_rate": 1.1e-06,
      "loss": 0.1181,
      "num_input_tokens_seen": 2170464,
      "step": 132
    },
    {
      "epoch": 1.7106109324758842,
      "grad_norm": 2.7540361881256104,
      "learning_rate": 1.1083333333333335e-06,
      "loss": 0.0826,
      "num_input_tokens_seen": 2187008,
      "step": 133
    },
    {
      "epoch": 1.7234726688102895,
      "grad_norm": 12.97872257232666,
      "learning_rate": 1.1166666666666666e-06,
      "loss": 0.1221,
      "num_input_tokens_seen": 2202880,
      "step": 134
    },
    {
      "epoch": 1.7363344051446945,
      "grad_norm": 4.774652004241943,
      "learning_rate": 1.125e-06,
      "loss": 0.1021,
      "num_input_tokens_seen": 2219744,
      "step": 135
    },
    {
      "epoch": 1.7491961414790995,
      "grad_norm": 3.889441967010498,
      "learning_rate": 1.1333333333333334e-06,
      "loss": 0.098,
      "num_input_tokens_seen": 2236064,
      "step": 136
    },
    {
      "epoch": 1.762057877813505,
      "grad_norm": 5.095253944396973,
      "learning_rate": 1.1416666666666668e-06,
      "loss": 0.1085,
      "num_input_tokens_seen": 2252832,
      "step": 137
    },
    {
      "epoch": 1.77491961414791,
      "grad_norm": 5.206950664520264,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 0.1038,
      "num_input_tokens_seen": 2268704,
      "step": 138
    },
    {
      "epoch": 1.787781350482315,
      "grad_norm": 10.339069366455078,
      "learning_rate": 1.1583333333333334e-06,
      "loss": 0.1081,
      "num_input_tokens_seen": 2285280,
      "step": 139
    },
    {
      "epoch": 1.8006430868167203,
      "grad_norm": 8.227212905883789,
      "learning_rate": 1.1666666666666668e-06,
      "loss": 0.1287,
      "num_input_tokens_seen": 2301600,
      "step": 140
    },
    {
      "epoch": 1.8135048231511255,
      "grad_norm": 6.72472620010376,
      "learning_rate": 1.175e-06,
      "loss": 0.1068,
      "num_input_tokens_seen": 2318048,
      "step": 141
    },
    {
      "epoch": 1.8263665594855305,
      "grad_norm": 10.02261734008789,
      "learning_rate": 1.1833333333333334e-06,
      "loss": 0.1202,
      "num_input_tokens_seen": 2333728,
      "step": 142
    },
    {
      "epoch": 1.8392282958199357,
      "grad_norm": 10.770837783813477,
      "learning_rate": 1.1916666666666668e-06,
      "loss": 0.119,
      "num_input_tokens_seen": 2349760,
      "step": 143
    },
    {
      "epoch": 1.852090032154341,
      "grad_norm": 6.685535907745361,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.1273,
      "num_input_tokens_seen": 2366336,
      "step": 144
    },
    {
      "epoch": 1.864951768488746,
      "grad_norm": 4.437434673309326,
      "learning_rate": 1.2083333333333333e-06,
      "loss": 0.1024,
      "num_input_tokens_seen": 2382016,
      "step": 145
    },
    {
      "epoch": 1.877813504823151,
      "grad_norm": 11.942359924316406,
      "learning_rate": 1.2166666666666667e-06,
      "loss": 0.1143,
      "num_input_tokens_seen": 2398176,
      "step": 146
    },
    {
      "epoch": 1.8906752411575563,
      "grad_norm": 6.428237438201904,
      "learning_rate": 1.2250000000000001e-06,
      "loss": 0.1229,
      "num_input_tokens_seen": 2414656,
      "step": 147
    },
    {
      "epoch": 1.9035369774919615,
      "grad_norm": 7.896732807159424,
      "learning_rate": 1.2333333333333335e-06,
      "loss": 0.0964,
      "num_input_tokens_seen": 2430400,
      "step": 148
    },
    {
      "epoch": 1.9163987138263665,
      "grad_norm": 12.14167594909668,
      "learning_rate": 1.2416666666666667e-06,
      "loss": 0.1132,
      "num_input_tokens_seen": 2447520,
      "step": 149
    },
    {
      "epoch": 1.9292604501607717,
      "grad_norm": 3.0627174377441406,
      "learning_rate": 1.25e-06,
      "loss": 0.0734,
      "num_input_tokens_seen": 2463872,
      "step": 150
    },
    {
      "epoch": 1.942122186495177,
      "grad_norm": 3.2333552837371826,
      "learning_rate": 1.2583333333333333e-06,
      "loss": 0.0939,
      "num_input_tokens_seen": 2481344,
      "step": 151
    },
    {
      "epoch": 1.954983922829582,
      "grad_norm": 14.160690307617188,
      "learning_rate": 1.2666666666666669e-06,
      "loss": 0.1143,
      "num_input_tokens_seen": 2497632,
      "step": 152
    },
    {
      "epoch": 1.967845659163987,
      "grad_norm": 5.38826322555542,
      "learning_rate": 1.275e-06,
      "loss": 0.1114,
      "num_input_tokens_seen": 2513024,
      "step": 153
    },
    {
      "epoch": 1.9807073954983923,
      "grad_norm": 3.4523892402648926,
      "learning_rate": 1.2833333333333335e-06,
      "loss": 0.0948,
      "num_input_tokens_seen": 2528800,
      "step": 154
    },
    {
      "epoch": 1.9935691318327975,
      "grad_norm": 6.9574127197265625,
      "learning_rate": 1.2916666666666669e-06,
      "loss": 0.0805,
      "num_input_tokens_seen": 2545696,
      "step": 155
    },
    {
      "epoch": 2.0064308681672025,
      "grad_norm": 7.220541954040527,
      "learning_rate": 1.3e-06,
      "loss": 0.1001,
      "num_input_tokens_seen": 2561728,
      "step": 156
    },
    {
      "epoch": 2.0192926045016075,
      "grad_norm": 6.95176887512207,
      "learning_rate": 1.3083333333333334e-06,
      "loss": 0.1002,
      "num_input_tokens_seen": 2577856,
      "step": 157
    },
    {
      "epoch": 2.032154340836013,
      "grad_norm": 10.752556800842285,
      "learning_rate": 1.3166666666666666e-06,
      "loss": 0.0847,
      "num_input_tokens_seen": 2593984,
      "step": 158
    },
    {
      "epoch": 2.045016077170418,
      "grad_norm": 6.510659217834473,
      "learning_rate": 1.3250000000000002e-06,
      "loss": 0.071,
      "num_input_tokens_seen": 2610720,
      "step": 159
    },
    {
      "epoch": 2.057877813504823,
      "grad_norm": 3.897312641143799,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 0.0791,
      "num_input_tokens_seen": 2626400,
      "step": 160
    },
    {
      "epoch": 2.0707395498392285,
      "grad_norm": 2.8594729900360107,
      "learning_rate": 1.3416666666666666e-06,
      "loss": 0.0769,
      "num_input_tokens_seen": 2642496,
      "step": 161
    },
    {
      "epoch": 2.0836012861736335,
      "grad_norm": 8.970246315002441,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 0.0916,
      "num_input_tokens_seen": 2658144,
      "step": 162
    },
    {
      "epoch": 2.0964630225080385,
      "grad_norm": 2.965878963470459,
      "learning_rate": 1.3583333333333334e-06,
      "loss": 0.0584,
      "num_input_tokens_seen": 2674560,
      "step": 163
    },
    {
      "epoch": 2.1093247588424435,
      "grad_norm": 6.79748010635376,
      "learning_rate": 1.3666666666666668e-06,
      "loss": 0.0811,
      "num_input_tokens_seen": 2690688,
      "step": 164
    },
    {
      "epoch": 2.122186495176849,
      "grad_norm": 10.366084098815918,
      "learning_rate": 1.3750000000000002e-06,
      "loss": 0.0663,
      "num_input_tokens_seen": 2706720,
      "step": 165
    },
    {
      "epoch": 2.135048231511254,
      "grad_norm": 8.038703918457031,
      "learning_rate": 1.3833333333333336e-06,
      "loss": 0.0802,
      "num_input_tokens_seen": 2723008,
      "step": 166
    },
    {
      "epoch": 2.147909967845659,
      "grad_norm": 6.01867151260376,
      "learning_rate": 1.3916666666666668e-06,
      "loss": 0.0587,
      "num_input_tokens_seen": 2738784,
      "step": 167
    },
    {
      "epoch": 2.1607717041800645,
      "grad_norm": 5.053437232971191,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.0953,
      "num_input_tokens_seen": 2755072,
      "step": 168
    },
    {
      "epoch": 2.1736334405144695,
      "grad_norm": 7.119932174682617,
      "learning_rate": 1.4083333333333335e-06,
      "loss": 0.0795,
      "num_input_tokens_seen": 2771296,
      "step": 169
    },
    {
      "epoch": 2.1864951768488745,
      "grad_norm": 4.602327346801758,
      "learning_rate": 1.4166666666666667e-06,
      "loss": 0.1015,
      "num_input_tokens_seen": 2787712,
      "step": 170
    },
    {
      "epoch": 2.19935691318328,
      "grad_norm": 2.7282161712646484,
      "learning_rate": 1.425e-06,
      "loss": 0.0614,
      "num_input_tokens_seen": 2803552,
      "step": 171
    },
    {
      "epoch": 2.212218649517685,
      "grad_norm": 4.694391250610352,
      "learning_rate": 1.4333333333333335e-06,
      "loss": 0.0753,
      "num_input_tokens_seen": 2820352,
      "step": 172
    },
    {
      "epoch": 2.22508038585209,
      "grad_norm": 3.231022357940674,
      "learning_rate": 1.4416666666666667e-06,
      "loss": 0.08,
      "num_input_tokens_seen": 2837696,
      "step": 173
    },
    {
      "epoch": 2.237942122186495,
      "grad_norm": 4.522435188293457,
      "learning_rate": 1.45e-06,
      "loss": 0.0603,
      "num_input_tokens_seen": 2854272,
      "step": 174
    },
    {
      "epoch": 2.2508038585209005,
      "grad_norm": 8.292889595031738,
      "learning_rate": 1.4583333333333335e-06,
      "loss": 0.0874,
      "num_input_tokens_seen": 2870464,
      "step": 175
    },
    {
      "epoch": 2.2636655948553055,
      "grad_norm": 3.635068655014038,
      "learning_rate": 1.4666666666666669e-06,
      "loss": 0.0833,
      "num_input_tokens_seen": 2886880,
      "step": 176
    },
    {
      "epoch": 2.2765273311897105,
      "grad_norm": 3.8000781536102295,
      "learning_rate": 1.475e-06,
      "loss": 0.0676,
      "num_input_tokens_seen": 2902880,
      "step": 177
    },
    {
      "epoch": 2.289389067524116,
      "grad_norm": 9.920318603515625,
      "learning_rate": 1.4833333333333337e-06,
      "loss": 0.086,
      "num_input_tokens_seen": 2919584,
      "step": 178
    },
    {
      "epoch": 2.302250803858521,
      "grad_norm": 3.8999791145324707,
      "learning_rate": 1.4916666666666669e-06,
      "loss": 0.0662,
      "num_input_tokens_seen": 2935136,
      "step": 179
    },
    {
      "epoch": 2.315112540192926,
      "grad_norm": 6.011571407318115,
      "learning_rate": 1.5e-06,
      "loss": 0.1028,
      "num_input_tokens_seen": 2951680,
      "step": 180
    },
    {
      "epoch": 2.327974276527331,
      "grad_norm": 5.94368839263916,
      "learning_rate": 1.5083333333333336e-06,
      "loss": 0.0882,
      "num_input_tokens_seen": 2967712,
      "step": 181
    },
    {
      "epoch": 2.3408360128617365,
      "grad_norm": 3.9432876110076904,
      "learning_rate": 1.5166666666666668e-06,
      "loss": 0.0806,
      "num_input_tokens_seen": 2984224,
      "step": 182
    },
    {
      "epoch": 2.3536977491961415,
      "grad_norm": 18.06218147277832,
      "learning_rate": 1.525e-06,
      "loss": 0.1108,
      "num_input_tokens_seen": 2999904,
      "step": 183
    },
    {
      "epoch": 2.3665594855305465,
      "grad_norm": 5.799235820770264,
      "learning_rate": 1.5333333333333334e-06,
      "loss": 0.0687,
      "num_input_tokens_seen": 3017376,
      "step": 184
    },
    {
      "epoch": 2.379421221864952,
      "grad_norm": 4.252455711364746,
      "learning_rate": 1.5416666666666668e-06,
      "loss": 0.0736,
      "num_input_tokens_seen": 3033728,
      "step": 185
    },
    {
      "epoch": 2.392282958199357,
      "grad_norm": 6.050833702087402,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 0.0779,
      "num_input_tokens_seen": 3050176,
      "step": 186
    },
    {
      "epoch": 2.405144694533762,
      "grad_norm": 8.076692581176758,
      "learning_rate": 1.5583333333333334e-06,
      "loss": 0.0709,
      "num_input_tokens_seen": 3066400,
      "step": 187
    },
    {
      "epoch": 2.418006430868167,
      "grad_norm": 7.372990608215332,
      "learning_rate": 1.566666666666667e-06,
      "loss": 0.0652,
      "num_input_tokens_seen": 3083104,
      "step": 188
    },
    {
      "epoch": 2.4308681672025725,
      "grad_norm": 14.172348022460938,
      "learning_rate": 1.5750000000000002e-06,
      "loss": 0.1095,
      "num_input_tokens_seen": 3100000,
      "step": 189
    },
    {
      "epoch": 2.4437299035369775,
      "grad_norm": 4.726587772369385,
      "learning_rate": 1.5833333333333333e-06,
      "loss": 0.0618,
      "num_input_tokens_seen": 3116800,
      "step": 190
    },
    {
      "epoch": 2.4565916398713825,
      "grad_norm": 10.408024787902832,
      "learning_rate": 1.591666666666667e-06,
      "loss": 0.0666,
      "num_input_tokens_seen": 3133568,
      "step": 191
    },
    {
      "epoch": 2.469453376205788,
      "grad_norm": 7.295907497406006,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.0573,
      "num_input_tokens_seen": 3150048,
      "step": 192
    },
    {
      "epoch": 2.482315112540193,
      "grad_norm": 6.490230083465576,
      "learning_rate": 1.6083333333333333e-06,
      "loss": 0.0577,
      "num_input_tokens_seen": 3166688,
      "step": 193
    },
    {
      "epoch": 2.495176848874598,
      "grad_norm": 6.940796375274658,
      "learning_rate": 1.6166666666666667e-06,
      "loss": 0.0813,
      "num_input_tokens_seen": 3182752,
      "step": 194
    },
    {
      "epoch": 2.508038585209003,
      "grad_norm": 8.307454109191895,
      "learning_rate": 1.6250000000000001e-06,
      "loss": 0.066,
      "num_input_tokens_seen": 3198944,
      "step": 195
    },
    {
      "epoch": 2.5209003215434085,
      "grad_norm": 4.472862243652344,
      "learning_rate": 1.6333333333333335e-06,
      "loss": 0.0622,
      "num_input_tokens_seen": 3215552,
      "step": 196
    },
    {
      "epoch": 2.5337620578778135,
      "grad_norm": 3.5001590251922607,
      "learning_rate": 1.6416666666666667e-06,
      "loss": 0.0616,
      "num_input_tokens_seen": 3231488,
      "step": 197
    },
    {
      "epoch": 2.5466237942122185,
      "grad_norm": 13.425641059875488,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 0.0993,
      "num_input_tokens_seen": 3247840,
      "step": 198
    },
    {
      "epoch": 2.559485530546624,
      "grad_norm": 12.016642570495605,
      "learning_rate": 1.6583333333333335e-06,
      "loss": 0.0702,
      "num_input_tokens_seen": 3264128,
      "step": 199
    },
    {
      "epoch": 2.572347266881029,
      "grad_norm": 10.653433799743652,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.0743,
      "num_input_tokens_seen": 3280192,
      "step": 200
    },
    {
      "epoch": 2.585209003215434,
      "grad_norm": 3.59945011138916,
      "learning_rate": 1.6750000000000003e-06,
      "loss": 0.0647,
      "num_input_tokens_seen": 3296480,
      "step": 201
    },
    {
      "epoch": 2.598070739549839,
      "grad_norm": 11.130800247192383,
      "learning_rate": 1.6833333333333335e-06,
      "loss": 0.0814,
      "num_input_tokens_seen": 3313120,
      "step": 202
    },
    {
      "epoch": 2.6109324758842445,
      "grad_norm": 11.733818054199219,
      "learning_rate": 1.6916666666666666e-06,
      "loss": 0.0861,
      "num_input_tokens_seen": 3329184,
      "step": 203
    },
    {
      "epoch": 2.6237942122186495,
      "grad_norm": 6.696333885192871,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.0769,
      "num_input_tokens_seen": 3346208,
      "step": 204
    },
    {
      "epoch": 2.6366559485530545,
      "grad_norm": 8.523835182189941,
      "learning_rate": 1.7083333333333334e-06,
      "loss": 0.0888,
      "num_input_tokens_seen": 3363008,
      "step": 205
    },
    {
      "epoch": 2.64951768488746,
      "grad_norm": 12.503429412841797,
      "learning_rate": 1.7166666666666668e-06,
      "loss": 0.1017,
      "num_input_tokens_seen": 3379488,
      "step": 206
    },
    {
      "epoch": 2.662379421221865,
      "grad_norm": 7.644631385803223,
      "learning_rate": 1.725e-06,
      "loss": 0.0677,
      "num_input_tokens_seen": 3395648,
      "step": 207
    },
    {
      "epoch": 2.67524115755627,
      "grad_norm": 7.251969814300537,
      "learning_rate": 1.7333333333333336e-06,
      "loss": 0.0861,
      "num_input_tokens_seen": 3412736,
      "step": 208
    },
    {
      "epoch": 2.688102893890675,
      "grad_norm": 3.763118267059326,
      "learning_rate": 1.7416666666666668e-06,
      "loss": 0.0562,
      "num_input_tokens_seen": 3429472,
      "step": 209
    },
    {
      "epoch": 2.7009646302250805,
      "grad_norm": 8.583102226257324,
      "learning_rate": 1.75e-06,
      "loss": 0.0641,
      "num_input_tokens_seen": 3445632,
      "step": 210
    },
    {
      "epoch": 2.7138263665594855,
      "grad_norm": 9.621906280517578,
      "learning_rate": 1.7583333333333336e-06,
      "loss": 0.0829,
      "num_input_tokens_seen": 3462720,
      "step": 211
    },
    {
      "epoch": 2.7266881028938905,
      "grad_norm": 6.067561626434326,
      "learning_rate": 1.7666666666666668e-06,
      "loss": 0.0632,
      "num_input_tokens_seen": 3478720,
      "step": 212
    },
    {
      "epoch": 2.739549839228296,
      "grad_norm": 4.912470817565918,
      "learning_rate": 1.7750000000000002e-06,
      "loss": 0.062,
      "num_input_tokens_seen": 3494304,
      "step": 213
    },
    {
      "epoch": 2.752411575562701,
      "grad_norm": 8.044519424438477,
      "learning_rate": 1.7833333333333336e-06,
      "loss": 0.0816,
      "num_input_tokens_seen": 3510176,
      "step": 214
    },
    {
      "epoch": 2.765273311897106,
      "grad_norm": 8.589887619018555,
      "learning_rate": 1.7916666666666667e-06,
      "loss": 0.096,
      "num_input_tokens_seen": 3526848,
      "step": 215
    },
    {
      "epoch": 2.778135048231511,
      "grad_norm": 3.3357672691345215,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.0639,
      "num_input_tokens_seen": 3543136,
      "step": 216
    },
    {
      "epoch": 2.7909967845659165,
      "grad_norm": 5.992812156677246,
      "learning_rate": 1.8083333333333335e-06,
      "loss": 0.0915,
      "num_input_tokens_seen": 3558240,
      "step": 217
    },
    {
      "epoch": 2.8038585209003215,
      "grad_norm": 4.8690924644470215,
      "learning_rate": 1.816666666666667e-06,
      "loss": 0.061,
      "num_input_tokens_seen": 3574240,
      "step": 218
    },
    {
      "epoch": 2.816720257234727,
      "grad_norm": 2.928898811340332,
      "learning_rate": 1.825e-06,
      "loss": 0.0572,
      "num_input_tokens_seen": 3590240,
      "step": 219
    },
    {
      "epoch": 2.829581993569132,
      "grad_norm": 2.8405849933624268,
      "learning_rate": 1.8333333333333333e-06,
      "loss": 0.0497,
      "num_input_tokens_seen": 3606912,
      "step": 220
    },
    {
      "epoch": 2.842443729903537,
      "grad_norm": 5.940427303314209,
      "learning_rate": 1.8416666666666669e-06,
      "loss": 0.0672,
      "num_input_tokens_seen": 3623008,
      "step": 221
    },
    {
      "epoch": 2.855305466237942,
      "grad_norm": 4.370597839355469,
      "learning_rate": 1.85e-06,
      "loss": 0.0563,
      "num_input_tokens_seen": 3639456,
      "step": 222
    },
    {
      "epoch": 2.868167202572347,
      "grad_norm": 3.9959638118743896,
      "learning_rate": 1.8583333333333335e-06,
      "loss": 0.069,
      "num_input_tokens_seen": 3656288,
      "step": 223
    },
    {
      "epoch": 2.8810289389067525,
      "grad_norm": 4.756357192993164,
      "learning_rate": 1.8666666666666669e-06,
      "loss": 0.0824,
      "num_input_tokens_seen": 3672896,
      "step": 224
    },
    {
      "epoch": 2.8938906752411575,
      "grad_norm": 3.312553644180298,
      "learning_rate": 1.8750000000000003e-06,
      "loss": 0.057,
      "num_input_tokens_seen": 3689632,
      "step": 225
    },
    {
      "epoch": 2.906752411575563,
      "grad_norm": 3.71880841255188,
      "learning_rate": 1.8833333333333334e-06,
      "loss": 0.0549,
      "num_input_tokens_seen": 3706944,
      "step": 226
    },
    {
      "epoch": 2.919614147909968,
      "grad_norm": 4.111685276031494,
      "learning_rate": 1.8916666666666668e-06,
      "loss": 0.0652,
      "num_input_tokens_seen": 3723072,
      "step": 227
    },
    {
      "epoch": 2.932475884244373,
      "grad_norm": 4.362407684326172,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.0743,
      "num_input_tokens_seen": 3740064,
      "step": 228
    },
    {
      "epoch": 2.945337620578778,
      "grad_norm": 2.441969156265259,
      "learning_rate": 1.9083333333333334e-06,
      "loss": 0.0416,
      "num_input_tokens_seen": 3756864,
      "step": 229
    },
    {
      "epoch": 2.958199356913183,
      "grad_norm": 3.4988579750061035,
      "learning_rate": 1.916666666666667e-06,
      "loss": 0.0668,
      "num_input_tokens_seen": 3774336,
      "step": 230
    },
    {
      "epoch": 2.9710610932475885,
      "grad_norm": 3.7807693481445312,
      "learning_rate": 1.925e-06,
      "loss": 0.0603,
      "num_input_tokens_seen": 3790336,
      "step": 231
    },
    {
      "epoch": 2.9839228295819935,
      "grad_norm": 3.471942901611328,
      "learning_rate": 1.9333333333333336e-06,
      "loss": 0.066,
      "num_input_tokens_seen": 3807520,
      "step": 232
    },
    {
      "epoch": 2.996784565916399,
      "grad_norm": 3.4720284938812256,
      "learning_rate": 1.9416666666666666e-06,
      "loss": 0.0692,
      "num_input_tokens_seen": 3823872,
      "step": 233
    },
    {
      "epoch": 3.009646302250804,
      "grad_norm": 1.9317958354949951,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.0323,
      "num_input_tokens_seen": 3840320,
      "step": 234
    },
    {
      "epoch": 3.022508038585209,
      "grad_norm": 4.849405288696289,
      "learning_rate": 1.9583333333333334e-06,
      "loss": 0.0403,
      "num_input_tokens_seen": 3856256,
      "step": 235
    },
    {
      "epoch": 3.035369774919614,
      "grad_norm": 2.371988296508789,
      "learning_rate": 1.9666666666666668e-06,
      "loss": 0.0477,
      "num_input_tokens_seen": 3872512,
      "step": 236
    },
    {
      "epoch": 3.0482315112540195,
      "grad_norm": 3.362964153289795,
      "learning_rate": 1.975e-06,
      "loss": 0.0356,
      "num_input_tokens_seen": 3888256,
      "step": 237
    },
    {
      "epoch": 3.0610932475884245,
      "grad_norm": 2.618176221847534,
      "learning_rate": 1.9833333333333335e-06,
      "loss": 0.0324,
      "num_input_tokens_seen": 3905024,
      "step": 238
    },
    {
      "epoch": 3.0739549839228295,
      "grad_norm": 2.5595703125,
      "learning_rate": 1.991666666666667e-06,
      "loss": 0.0428,
      "num_input_tokens_seen": 3922016,
      "step": 239
    },
    {
      "epoch": 3.0868167202572345,
      "grad_norm": 2.788818597793579,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0315,
      "num_input_tokens_seen": 3938400,
      "step": 240
    },
    {
      "epoch": 3.09967845659164,
      "grad_norm": 3.9531607627868652,
      "learning_rate": 2.0083333333333337e-06,
      "loss": 0.0366,
      "num_input_tokens_seen": 3954912,
      "step": 241
    },
    {
      "epoch": 3.112540192926045,
      "grad_norm": 3.2901012897491455,
      "learning_rate": 2.0166666666666667e-06,
      "loss": 0.0307,
      "num_input_tokens_seen": 3970400,
      "step": 242
    },
    {
      "epoch": 3.12540192926045,
      "grad_norm": 4.283529281616211,
      "learning_rate": 2.025e-06,
      "loss": 0.0338,
      "num_input_tokens_seen": 3986944,
      "step": 243
    },
    {
      "epoch": 3.1382636655948555,
      "grad_norm": 4.467242240905762,
      "learning_rate": 2.0333333333333335e-06,
      "loss": 0.0348,
      "num_input_tokens_seen": 4003648,
      "step": 244
    },
    {
      "epoch": 3.1511254019292605,
      "grad_norm": 3.3191885948181152,
      "learning_rate": 2.041666666666667e-06,
      "loss": 0.0355,
      "num_input_tokens_seen": 4020384,
      "step": 245
    },
    {
      "epoch": 3.1639871382636655,
      "grad_norm": 4.061459064483643,
      "learning_rate": 2.05e-06,
      "loss": 0.0272,
      "num_input_tokens_seen": 4037088,
      "step": 246
    },
    {
      "epoch": 3.176848874598071,
      "grad_norm": 3.0776522159576416,
      "learning_rate": 2.0583333333333337e-06,
      "loss": 0.0464,
      "num_input_tokens_seen": 4053472,
      "step": 247
    },
    {
      "epoch": 3.189710610932476,
      "grad_norm": 2.13104510307312,
      "learning_rate": 2.0666666666666666e-06,
      "loss": 0.0268,
      "num_input_tokens_seen": 4069248,
      "step": 248
    },
    {
      "epoch": 3.202572347266881,
      "grad_norm": 2.1540310382843018,
      "learning_rate": 2.075e-06,
      "loss": 0.0229,
      "num_input_tokens_seen": 4085024,
      "step": 249
    },
    {
      "epoch": 3.215434083601286,
      "grad_norm": 3.068967342376709,
      "learning_rate": 2.0833333333333334e-06,
      "loss": 0.0373,
      "num_input_tokens_seen": 4102432,
      "step": 250
    },
    {
      "epoch": 3.2282958199356915,
      "grad_norm": 2.7403666973114014,
      "learning_rate": 2.091666666666667e-06,
      "loss": 0.0361,
      "num_input_tokens_seen": 4118368,
      "step": 251
    },
    {
      "epoch": 3.2411575562700965,
      "grad_norm": 4.994419574737549,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.0401,
      "num_input_tokens_seen": 4134784,
      "step": 252
    },
    {
      "epoch": 3.2540192926045015,
      "grad_norm": 2.287346839904785,
      "learning_rate": 2.1083333333333336e-06,
      "loss": 0.0262,
      "num_input_tokens_seen": 4150528,
      "step": 253
    },
    {
      "epoch": 3.266881028938907,
      "grad_norm": 3.649418354034424,
      "learning_rate": 2.116666666666667e-06,
      "loss": 0.0481,
      "num_input_tokens_seen": 4166816,
      "step": 254
    },
    {
      "epoch": 3.279742765273312,
      "grad_norm": 2.9041836261749268,
      "learning_rate": 2.125e-06,
      "loss": 0.0417,
      "num_input_tokens_seen": 4182880,
      "step": 255
    },
    {
      "epoch": 3.292604501607717,
      "grad_norm": 3.602240800857544,
      "learning_rate": 2.133333333333334e-06,
      "loss": 0.0457,
      "num_input_tokens_seen": 4200128,
      "step": 256
    },
    {
      "epoch": 3.305466237942122,
      "grad_norm": 1.6382755041122437,
      "learning_rate": 2.1416666666666668e-06,
      "loss": 0.0175,
      "num_input_tokens_seen": 4215680,
      "step": 257
    },
    {
      "epoch": 3.3183279742765275,
      "grad_norm": 2.4267561435699463,
      "learning_rate": 2.15e-06,
      "loss": 0.0371,
      "num_input_tokens_seen": 4232736,
      "step": 258
    },
    {
      "epoch": 3.3311897106109325,
      "grad_norm": 2.553440570831299,
      "learning_rate": 2.1583333333333336e-06,
      "loss": 0.0268,
      "num_input_tokens_seen": 4249664,
      "step": 259
    },
    {
      "epoch": 3.3440514469453375,
      "grad_norm": 2.951179027557373,
      "learning_rate": 2.166666666666667e-06,
      "loss": 0.0417,
      "num_input_tokens_seen": 4266016,
      "step": 260
    },
    {
      "epoch": 3.356913183279743,
      "grad_norm": 2.710747003555298,
      "learning_rate": 2.1750000000000004e-06,
      "loss": 0.0264,
      "num_input_tokens_seen": 4281664,
      "step": 261
    },
    {
      "epoch": 3.369774919614148,
      "grad_norm": 3.465902090072632,
      "learning_rate": 2.1833333333333333e-06,
      "loss": 0.0336,
      "num_input_tokens_seen": 4298368,
      "step": 262
    },
    {
      "epoch": 3.382636655948553,
      "grad_norm": 4.009627819061279,
      "learning_rate": 2.191666666666667e-06,
      "loss": 0.0434,
      "num_input_tokens_seen": 4314336,
      "step": 263
    },
    {
      "epoch": 3.395498392282958,
      "grad_norm": 4.071226596832275,
      "learning_rate": 2.2e-06,
      "loss": 0.0389,
      "num_input_tokens_seen": 4330144,
      "step": 264
    },
    {
      "epoch": 3.4083601286173635,
      "grad_norm": 4.341132164001465,
      "learning_rate": 2.2083333333333335e-06,
      "loss": 0.045,
      "num_input_tokens_seen": 4345856,
      "step": 265
    },
    {
      "epoch": 3.4212218649517685,
      "grad_norm": 4.663236141204834,
      "learning_rate": 2.216666666666667e-06,
      "loss": 0.0331,
      "num_input_tokens_seen": 4361696,
      "step": 266
    },
    {
      "epoch": 3.4340836012861735,
      "grad_norm": 2.17475962638855,
      "learning_rate": 2.2250000000000003e-06,
      "loss": 0.0228,
      "num_input_tokens_seen": 4378304,
      "step": 267
    },
    {
      "epoch": 3.446945337620579,
      "grad_norm": 5.099360942840576,
      "learning_rate": 2.2333333333333333e-06,
      "loss": 0.0307,
      "num_input_tokens_seen": 4395232,
      "step": 268
    },
    {
      "epoch": 3.459807073954984,
      "grad_norm": 4.4752020835876465,
      "learning_rate": 2.2416666666666667e-06,
      "loss": 0.0332,
      "num_input_tokens_seen": 4411232,
      "step": 269
    },
    {
      "epoch": 3.472668810289389,
      "grad_norm": 4.047648906707764,
      "learning_rate": 2.25e-06,
      "loss": 0.0662,
      "num_input_tokens_seen": 4427520,
      "step": 270
    },
    {
      "epoch": 3.485530546623794,
      "grad_norm": 5.564074516296387,
      "learning_rate": 2.2583333333333335e-06,
      "loss": 0.0431,
      "num_input_tokens_seen": 4443904,
      "step": 271
    },
    {
      "epoch": 3.4983922829581995,
      "grad_norm": 3.9845523834228516,
      "learning_rate": 2.266666666666667e-06,
      "loss": 0.0423,
      "num_input_tokens_seen": 4460608,
      "step": 272
    },
    {
      "epoch": 3.5112540192926045,
      "grad_norm": 3.6314871311187744,
      "learning_rate": 2.2750000000000002e-06,
      "loss": 0.0447,
      "num_input_tokens_seen": 4477120,
      "step": 273
    },
    {
      "epoch": 3.5241157556270095,
      "grad_norm": 3.1981313228607178,
      "learning_rate": 2.2833333333333336e-06,
      "loss": 0.0337,
      "num_input_tokens_seen": 4493152,
      "step": 274
    },
    {
      "epoch": 3.536977491961415,
      "grad_norm": 2.1383423805236816,
      "learning_rate": 2.2916666666666666e-06,
      "loss": 0.0319,
      "num_input_tokens_seen": 4509120,
      "step": 275
    },
    {
      "epoch": 3.54983922829582,
      "grad_norm": 2.778956890106201,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.027,
      "num_input_tokens_seen": 4525984,
      "step": 276
    },
    {
      "epoch": 3.562700964630225,
      "grad_norm": 2.518002510070801,
      "learning_rate": 2.3083333333333334e-06,
      "loss": 0.0244,
      "num_input_tokens_seen": 4542816,
      "step": 277
    },
    {
      "epoch": 3.57556270096463,
      "grad_norm": 3.8519890308380127,
      "learning_rate": 2.316666666666667e-06,
      "loss": 0.0377,
      "num_input_tokens_seen": 4559872,
      "step": 278
    },
    {
      "epoch": 3.5884244372990355,
      "grad_norm": 5.541743278503418,
      "learning_rate": 2.325e-06,
      "loss": 0.0477,
      "num_input_tokens_seen": 4576288,
      "step": 279
    },
    {
      "epoch": 3.6012861736334405,
      "grad_norm": 4.099382400512695,
      "learning_rate": 2.3333333333333336e-06,
      "loss": 0.0332,
      "num_input_tokens_seen": 4591456,
      "step": 280
    },
    {
      "epoch": 3.6141479099678455,
      "grad_norm": 2.509037733078003,
      "learning_rate": 2.341666666666667e-06,
      "loss": 0.0285,
      "num_input_tokens_seen": 4608608,
      "step": 281
    },
    {
      "epoch": 3.627009646302251,
      "grad_norm": 6.764764308929443,
      "learning_rate": 2.35e-06,
      "loss": 0.0468,
      "num_input_tokens_seen": 4625120,
      "step": 282
    },
    {
      "epoch": 3.639871382636656,
      "grad_norm": 6.219926834106445,
      "learning_rate": 2.3583333333333338e-06,
      "loss": 0.037,
      "num_input_tokens_seen": 4641952,
      "step": 283
    },
    {
      "epoch": 3.652733118971061,
      "grad_norm": 3.869555950164795,
      "learning_rate": 2.3666666666666667e-06,
      "loss": 0.041,
      "num_input_tokens_seen": 4657920,
      "step": 284
    },
    {
      "epoch": 3.665594855305466,
      "grad_norm": 4.1329264640808105,
      "learning_rate": 2.375e-06,
      "loss": 0.0461,
      "num_input_tokens_seen": 4674688,
      "step": 285
    },
    {
      "epoch": 3.6784565916398715,
      "grad_norm": 6.7732648849487305,
      "learning_rate": 2.3833333333333335e-06,
      "loss": 0.0594,
      "num_input_tokens_seen": 4690592,
      "step": 286
    },
    {
      "epoch": 3.6913183279742765,
      "grad_norm": 8.550586700439453,
      "learning_rate": 2.391666666666667e-06,
      "loss": 0.0728,
      "num_input_tokens_seen": 4707360,
      "step": 287
    },
    {
      "epoch": 3.7041800643086815,
      "grad_norm": 4.587222099304199,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.029,
      "num_input_tokens_seen": 4724192,
      "step": 288
    },
    {
      "epoch": 3.717041800643087,
      "grad_norm": 3.3474302291870117,
      "learning_rate": 2.4083333333333337e-06,
      "loss": 0.0412,
      "num_input_tokens_seen": 4741344,
      "step": 289
    },
    {
      "epoch": 3.729903536977492,
      "grad_norm": 4.359026908874512,
      "learning_rate": 2.4166666666666667e-06,
      "loss": 0.0262,
      "num_input_tokens_seen": 4756768,
      "step": 290
    },
    {
      "epoch": 3.742765273311897,
      "grad_norm": 8.029643058776855,
      "learning_rate": 2.425e-06,
      "loss": 0.0796,
      "num_input_tokens_seen": 4772608,
      "step": 291
    },
    {
      "epoch": 3.755627009646302,
      "grad_norm": 3.9188246726989746,
      "learning_rate": 2.4333333333333335e-06,
      "loss": 0.0447,
      "num_input_tokens_seen": 4788928,
      "step": 292
    },
    {
      "epoch": 3.7684887459807075,
      "grad_norm": 2.2623226642608643,
      "learning_rate": 2.441666666666667e-06,
      "loss": 0.0252,
      "num_input_tokens_seen": 4805408,
      "step": 293
    },
    {
      "epoch": 3.7813504823151125,
      "grad_norm": 5.41758394241333,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.0458,
      "num_input_tokens_seen": 4821248,
      "step": 294
    },
    {
      "epoch": 3.7942122186495175,
      "grad_norm": 3.402024984359741,
      "learning_rate": 2.4583333333333332e-06,
      "loss": 0.0431,
      "num_input_tokens_seen": 4837024,
      "step": 295
    },
    {
      "epoch": 3.807073954983923,
      "grad_norm": 2.2912893295288086,
      "learning_rate": 2.466666666666667e-06,
      "loss": 0.0422,
      "num_input_tokens_seen": 4853760,
      "step": 296
    },
    {
      "epoch": 3.819935691318328,
      "grad_norm": 2.5446107387542725,
      "learning_rate": 2.475e-06,
      "loss": 0.0428,
      "num_input_tokens_seen": 4870560,
      "step": 297
    },
    {
      "epoch": 3.832797427652733,
      "grad_norm": 4.001276969909668,
      "learning_rate": 2.4833333333333334e-06,
      "loss": 0.0473,
      "num_input_tokens_seen": 4887040,
      "step": 298
    },
    {
      "epoch": 3.845659163987138,
      "grad_norm": 2.1214165687561035,
      "learning_rate": 2.491666666666667e-06,
      "loss": 0.0223,
      "num_input_tokens_seen": 4903232,
      "step": 299
    },
    {
      "epoch": 3.8585209003215435,
      "grad_norm": 2.0410876274108887,
      "learning_rate": 2.5e-06,
      "loss": 0.0274,
      "num_input_tokens_seen": 4919392,
      "step": 300
    },
    {
      "epoch": 3.8713826366559485,
      "grad_norm": 4.287325382232666,
      "learning_rate": 2.5083333333333336e-06,
      "loss": 0.0454,
      "num_input_tokens_seen": 4935648,
      "step": 301
    },
    {
      "epoch": 3.884244372990354,
      "grad_norm": 4.437230110168457,
      "learning_rate": 2.5166666666666666e-06,
      "loss": 0.022,
      "num_input_tokens_seen": 4952768,
      "step": 302
    },
    {
      "epoch": 3.897106109324759,
      "grad_norm": 3.8610730171203613,
      "learning_rate": 2.5250000000000004e-06,
      "loss": 0.0357,
      "num_input_tokens_seen": 4969408,
      "step": 303
    },
    {
      "epoch": 3.909967845659164,
      "grad_norm": 2.636066436767578,
      "learning_rate": 2.5333333333333338e-06,
      "loss": 0.0458,
      "num_input_tokens_seen": 4986592,
      "step": 304
    },
    {
      "epoch": 3.922829581993569,
      "grad_norm": 4.873857021331787,
      "learning_rate": 2.5416666666666668e-06,
      "loss": 0.0454,
      "num_input_tokens_seen": 5002720,
      "step": 305
    },
    {
      "epoch": 3.935691318327974,
      "grad_norm": 2.460498571395874,
      "learning_rate": 2.55e-06,
      "loss": 0.0262,
      "num_input_tokens_seen": 5018848,
      "step": 306
    },
    {
      "epoch": 3.9485530546623795,
      "grad_norm": 1.9787613153457642,
      "learning_rate": 2.558333333333334e-06,
      "loss": 0.0234,
      "num_input_tokens_seen": 5034528,
      "step": 307
    },
    {
      "epoch": 3.9614147909967845,
      "grad_norm": 2.9524741172790527,
      "learning_rate": 2.566666666666667e-06,
      "loss": 0.0366,
      "num_input_tokens_seen": 5051328,
      "step": 308
    },
    {
      "epoch": 3.97427652733119,
      "grad_norm": 2.858250379562378,
      "learning_rate": 2.5750000000000003e-06,
      "loss": 0.0236,
      "num_input_tokens_seen": 5067712,
      "step": 309
    },
    {
      "epoch": 3.987138263665595,
      "grad_norm": 2.985665798187256,
      "learning_rate": 2.5833333333333337e-06,
      "loss": 0.0403,
      "num_input_tokens_seen": 5085088,
      "step": 310
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.72078013420105,
      "learning_rate": 2.5916666666666667e-06,
      "loss": 0.0395,
      "num_input_tokens_seen": 5101536,
      "step": 311
    },
    {
      "epoch": 4.012861736334405,
      "grad_norm": 1.2907602787017822,
      "learning_rate": 2.6e-06,
      "loss": 0.0163,
      "num_input_tokens_seen": 5117696,
      "step": 312
    },
    {
      "epoch": 4.02572347266881,
      "grad_norm": 1.910504937171936,
      "learning_rate": 2.608333333333333e-06,
      "loss": 0.0181,
      "num_input_tokens_seen": 5133408,
      "step": 313
    },
    {
      "epoch": 4.038585209003215,
      "grad_norm": 1.1473162174224854,
      "learning_rate": 2.616666666666667e-06,
      "loss": 0.013,
      "num_input_tokens_seen": 5149664,
      "step": 314
    },
    {
      "epoch": 4.051446945337621,
      "grad_norm": 2.9885878562927246,
      "learning_rate": 2.6250000000000003e-06,
      "loss": 0.0178,
      "num_input_tokens_seen": 5165344,
      "step": 315
    },
    {
      "epoch": 4.064308681672026,
      "grad_norm": 2.308147430419922,
      "learning_rate": 2.6333333333333332e-06,
      "loss": 0.0153,
      "num_input_tokens_seen": 5183264,
      "step": 316
    },
    {
      "epoch": 4.077170418006431,
      "grad_norm": 3.1830930709838867,
      "learning_rate": 2.6416666666666666e-06,
      "loss": 0.0205,
      "num_input_tokens_seen": 5199296,
      "step": 317
    },
    {
      "epoch": 4.090032154340836,
      "grad_norm": 0.674608051776886,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.0021,
      "num_input_tokens_seen": 5216032,
      "step": 318
    },
    {
      "epoch": 4.102893890675241,
      "grad_norm": 3.075059175491333,
      "learning_rate": 2.6583333333333334e-06,
      "loss": 0.022,
      "num_input_tokens_seen": 5232544,
      "step": 319
    },
    {
      "epoch": 4.115755627009646,
      "grad_norm": 1.1589558124542236,
      "learning_rate": 2.666666666666667e-06,
      "loss": 0.0134,
      "num_input_tokens_seen": 5248704,
      "step": 320
    },
    {
      "epoch": 4.128617363344051,
      "grad_norm": 4.190515518188477,
      "learning_rate": 2.6750000000000002e-06,
      "loss": 0.0175,
      "num_input_tokens_seen": 5264384,
      "step": 321
    },
    {
      "epoch": 4.141479099678457,
      "grad_norm": 3.435070276260376,
      "learning_rate": 2.683333333333333e-06,
      "loss": 0.023,
      "num_input_tokens_seen": 5280928,
      "step": 322
    },
    {
      "epoch": 4.154340836012862,
      "grad_norm": 3.3521199226379395,
      "learning_rate": 2.691666666666667e-06,
      "loss": 0.0303,
      "num_input_tokens_seen": 5296512,
      "step": 323
    },
    {
      "epoch": 4.167202572347267,
      "grad_norm": 2.0815391540527344,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.0187,
      "num_input_tokens_seen": 5313440,
      "step": 324
    },
    {
      "epoch": 4.180064308681672,
      "grad_norm": 1.968308687210083,
      "learning_rate": 2.7083333333333334e-06,
      "loss": 0.0126,
      "num_input_tokens_seen": 5329088,
      "step": 325
    },
    {
      "epoch": 4.192926045016077,
      "grad_norm": 2.134216070175171,
      "learning_rate": 2.7166666666666668e-06,
      "loss": 0.0203,
      "num_input_tokens_seen": 5345376,
      "step": 326
    },
    {
      "epoch": 4.205787781350482,
      "grad_norm": 1.2245476245880127,
      "learning_rate": 2.7250000000000006e-06,
      "loss": 0.0078,
      "num_input_tokens_seen": 5361568,
      "step": 327
    },
    {
      "epoch": 4.218649517684887,
      "grad_norm": 1.908057451248169,
      "learning_rate": 2.7333333333333336e-06,
      "loss": 0.0165,
      "num_input_tokens_seen": 5377536,
      "step": 328
    },
    {
      "epoch": 4.231511254019293,
      "grad_norm": 1.6413862705230713,
      "learning_rate": 2.741666666666667e-06,
      "loss": 0.0113,
      "num_input_tokens_seen": 5395040,
      "step": 329
    },
    {
      "epoch": 4.244372990353698,
      "grad_norm": 1.442226529121399,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.0058,
      "num_input_tokens_seen": 5411488,
      "step": 330
    },
    {
      "epoch": 4.257234726688103,
      "grad_norm": 0.9877079129219055,
      "learning_rate": 2.7583333333333333e-06,
      "loss": 0.007,
      "num_input_tokens_seen": 5427328,
      "step": 331
    },
    {
      "epoch": 4.270096463022508,
      "grad_norm": 2.9424357414245605,
      "learning_rate": 2.766666666666667e-06,
      "loss": 0.027,
      "num_input_tokens_seen": 5444352,
      "step": 332
    },
    {
      "epoch": 4.282958199356913,
      "grad_norm": 3.5407063961029053,
      "learning_rate": 2.7750000000000005e-06,
      "loss": 0.0276,
      "num_input_tokens_seen": 5459840,
      "step": 333
    },
    {
      "epoch": 4.295819935691318,
      "grad_norm": 4.147865295410156,
      "learning_rate": 2.7833333333333335e-06,
      "loss": 0.0367,
      "num_input_tokens_seen": 5476000,
      "step": 334
    },
    {
      "epoch": 4.308681672025724,
      "grad_norm": 2.4164767265319824,
      "learning_rate": 2.791666666666667e-06,
      "loss": 0.0161,
      "num_input_tokens_seen": 5491968,
      "step": 335
    },
    {
      "epoch": 4.321543408360129,
      "grad_norm": 2.553860902786255,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.018,
      "num_input_tokens_seen": 5508864,
      "step": 336
    },
    {
      "epoch": 4.334405144694534,
      "grad_norm": 1.050309419631958,
      "learning_rate": 2.8083333333333333e-06,
      "loss": 0.0044,
      "num_input_tokens_seen": 5525536,
      "step": 337
    },
    {
      "epoch": 4.347266881028939,
      "grad_norm": 2.375540018081665,
      "learning_rate": 2.816666666666667e-06,
      "loss": 0.0109,
      "num_input_tokens_seen": 5542368,
      "step": 338
    },
    {
      "epoch": 4.360128617363344,
      "grad_norm": 3.041912794113159,
      "learning_rate": 2.825e-06,
      "loss": 0.0173,
      "num_input_tokens_seen": 5558400,
      "step": 339
    },
    {
      "epoch": 4.372990353697749,
      "grad_norm": 2.464390754699707,
      "learning_rate": 2.8333333333333335e-06,
      "loss": 0.0107,
      "num_input_tokens_seen": 5575008,
      "step": 340
    },
    {
      "epoch": 4.385852090032154,
      "grad_norm": 1.3086371421813965,
      "learning_rate": 2.841666666666667e-06,
      "loss": 0.0116,
      "num_input_tokens_seen": 5590784,
      "step": 341
    },
    {
      "epoch": 4.39871382636656,
      "grad_norm": 3.057859420776367,
      "learning_rate": 2.85e-06,
      "loss": 0.0281,
      "num_input_tokens_seen": 5608032,
      "step": 342
    },
    {
      "epoch": 4.411575562700965,
      "grad_norm": 2.7371633052825928,
      "learning_rate": 2.8583333333333336e-06,
      "loss": 0.0246,
      "num_input_tokens_seen": 5624704,
      "step": 343
    },
    {
      "epoch": 4.42443729903537,
      "grad_norm": 1.7932931184768677,
      "learning_rate": 2.866666666666667e-06,
      "loss": 0.0146,
      "num_input_tokens_seen": 5641056,
      "step": 344
    },
    {
      "epoch": 4.437299035369775,
      "grad_norm": 3.9446775913238525,
      "learning_rate": 2.875e-06,
      "loss": 0.0439,
      "num_input_tokens_seen": 5656608,
      "step": 345
    },
    {
      "epoch": 4.45016077170418,
      "grad_norm": 3.7706024646759033,
      "learning_rate": 2.8833333333333334e-06,
      "loss": 0.0279,
      "num_input_tokens_seen": 5672928,
      "step": 346
    },
    {
      "epoch": 4.463022508038585,
      "grad_norm": 2.38531756401062,
      "learning_rate": 2.8916666666666672e-06,
      "loss": 0.0276,
      "num_input_tokens_seen": 5689728,
      "step": 347
    },
    {
      "epoch": 4.47588424437299,
      "grad_norm": 2.534675121307373,
      "learning_rate": 2.9e-06,
      "loss": 0.0167,
      "num_input_tokens_seen": 5705824,
      "step": 348
    },
    {
      "epoch": 4.488745980707396,
      "grad_norm": 3.28116774559021,
      "learning_rate": 2.9083333333333336e-06,
      "loss": 0.0258,
      "num_input_tokens_seen": 5723008,
      "step": 349
    },
    {
      "epoch": 4.501607717041801,
      "grad_norm": 3.5873191356658936,
      "learning_rate": 2.916666666666667e-06,
      "loss": 0.0306,
      "num_input_tokens_seen": 5739680,
      "step": 350
    },
    {
      "epoch": 4.514469453376206,
      "grad_norm": 4.889535427093506,
      "learning_rate": 2.925e-06,
      "loss": 0.0395,
      "num_input_tokens_seen": 5756480,
      "step": 351
    },
    {
      "epoch": 4.527331189710611,
      "grad_norm": 1.8129762411117554,
      "learning_rate": 2.9333333333333338e-06,
      "loss": 0.0203,
      "num_input_tokens_seen": 5773088,
      "step": 352
    },
    {
      "epoch": 4.540192926045016,
      "grad_norm": 1.5045830011367798,
      "learning_rate": 2.941666666666667e-06,
      "loss": 0.0241,
      "num_input_tokens_seen": 5789312,
      "step": 353
    },
    {
      "epoch": 4.553054662379421,
      "grad_norm": 1.4582304954528809,
      "learning_rate": 2.95e-06,
      "loss": 0.0151,
      "num_input_tokens_seen": 5804352,
      "step": 354
    },
    {
      "epoch": 4.565916398713826,
      "grad_norm": 1.6875511407852173,
      "learning_rate": 2.9583333333333335e-06,
      "loss": 0.0355,
      "num_input_tokens_seen": 5820384,
      "step": 355
    },
    {
      "epoch": 4.578778135048232,
      "grad_norm": 1.0483993291854858,
      "learning_rate": 2.9666666666666673e-06,
      "loss": 0.0093,
      "num_input_tokens_seen": 5837280,
      "step": 356
    },
    {
      "epoch": 4.591639871382637,
      "grad_norm": 2.731086254119873,
      "learning_rate": 2.9750000000000003e-06,
      "loss": 0.0314,
      "num_input_tokens_seen": 5853760,
      "step": 357
    },
    {
      "epoch": 4.604501607717042,
      "grad_norm": 1.5985758304595947,
      "learning_rate": 2.9833333333333337e-06,
      "loss": 0.0155,
      "num_input_tokens_seen": 5870240,
      "step": 358
    },
    {
      "epoch": 4.617363344051447,
      "grad_norm": 1.3119585514068604,
      "learning_rate": 2.991666666666667e-06,
      "loss": 0.0138,
      "num_input_tokens_seen": 5887296,
      "step": 359
    },
    {
      "epoch": 4.630225080385852,
      "grad_norm": 2.3107335567474365,
      "learning_rate": 3e-06,
      "loss": 0.0212,
      "num_input_tokens_seen": 5904384,
      "step": 360
    },
    {
      "epoch": 4.643086816720257,
      "grad_norm": 1.8473104238510132,
      "learning_rate": 3.0083333333333335e-06,
      "loss": 0.0255,
      "num_input_tokens_seen": 5920832,
      "step": 361
    },
    {
      "epoch": 4.655948553054662,
      "grad_norm": 1.6255360841751099,
      "learning_rate": 3.0166666666666673e-06,
      "loss": 0.0231,
      "num_input_tokens_seen": 5936736,
      "step": 362
    },
    {
      "epoch": 4.668810289389068,
      "grad_norm": 1.843116044998169,
      "learning_rate": 3.0250000000000003e-06,
      "loss": 0.0083,
      "num_input_tokens_seen": 5953120,
      "step": 363
    },
    {
      "epoch": 4.681672025723473,
      "grad_norm": 1.7974934577941895,
      "learning_rate": 3.0333333333333337e-06,
      "loss": 0.0122,
      "num_input_tokens_seen": 5970336,
      "step": 364
    },
    {
      "epoch": 4.694533762057878,
      "grad_norm": 1.799026370048523,
      "learning_rate": 3.0416666666666666e-06,
      "loss": 0.0142,
      "num_input_tokens_seen": 5987488,
      "step": 365
    },
    {
      "epoch": 4.707395498392283,
      "grad_norm": 2.38661789894104,
      "learning_rate": 3.05e-06,
      "loss": 0.0293,
      "num_input_tokens_seen": 6003296,
      "step": 366
    },
    {
      "epoch": 4.720257234726688,
      "grad_norm": 2.2720234394073486,
      "learning_rate": 3.058333333333334e-06,
      "loss": 0.0292,
      "num_input_tokens_seen": 6020768,
      "step": 367
    },
    {
      "epoch": 4.733118971061093,
      "grad_norm": 3.6864068508148193,
      "learning_rate": 3.066666666666667e-06,
      "loss": 0.032,
      "num_input_tokens_seen": 6036992,
      "step": 368
    },
    {
      "epoch": 4.745980707395498,
      "grad_norm": 2.1829123497009277,
      "learning_rate": 3.075e-06,
      "loss": 0.0189,
      "num_input_tokens_seen": 6053568,
      "step": 369
    },
    {
      "epoch": 4.758842443729904,
      "grad_norm": 2.033625602722168,
      "learning_rate": 3.0833333333333336e-06,
      "loss": 0.022,
      "num_input_tokens_seen": 6070336,
      "step": 370
    },
    {
      "epoch": 4.771704180064309,
      "grad_norm": 2.665611982345581,
      "learning_rate": 3.0916666666666666e-06,
      "loss": 0.0242,
      "num_input_tokens_seen": 6087200,
      "step": 371
    },
    {
      "epoch": 4.784565916398714,
      "grad_norm": 1.981733798980713,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.015,
      "num_input_tokens_seen": 6104224,
      "step": 372
    },
    {
      "epoch": 4.797427652733119,
      "grad_norm": 1.30072820186615,
      "learning_rate": 3.1083333333333338e-06,
      "loss": 0.0154,
      "num_input_tokens_seen": 6120576,
      "step": 373
    },
    {
      "epoch": 4.810289389067524,
      "grad_norm": 2.196270704269409,
      "learning_rate": 3.1166666666666668e-06,
      "loss": 0.0195,
      "num_input_tokens_seen": 6137440,
      "step": 374
    },
    {
      "epoch": 4.823151125401929,
      "grad_norm": 2.597658157348633,
      "learning_rate": 3.125e-06,
      "loss": 0.031,
      "num_input_tokens_seen": 6154976,
      "step": 375
    },
    {
      "epoch": 4.836012861736334,
      "grad_norm": 3.6647465229034424,
      "learning_rate": 3.133333333333334e-06,
      "loss": 0.0376,
      "num_input_tokens_seen": 6170912,
      "step": 376
    },
    {
      "epoch": 4.84887459807074,
      "grad_norm": 1.159162998199463,
      "learning_rate": 3.141666666666667e-06,
      "loss": 0.0093,
      "num_input_tokens_seen": 6187968,
      "step": 377
    },
    {
      "epoch": 4.861736334405145,
      "grad_norm": 1.5810602903366089,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.027,
      "num_input_tokens_seen": 6204320,
      "step": 378
    },
    {
      "epoch": 4.87459807073955,
      "grad_norm": 2.0108237266540527,
      "learning_rate": 3.1583333333333337e-06,
      "loss": 0.0191,
      "num_input_tokens_seen": 6220512,
      "step": 379
    },
    {
      "epoch": 4.887459807073955,
      "grad_norm": 1.5167394876480103,
      "learning_rate": 3.1666666666666667e-06,
      "loss": 0.0132,
      "num_input_tokens_seen": 6236512,
      "step": 380
    },
    {
      "epoch": 4.90032154340836,
      "grad_norm": 2.1819732189178467,
      "learning_rate": 3.175e-06,
      "loss": 0.0111,
      "num_input_tokens_seen": 6252416,
      "step": 381
    },
    {
      "epoch": 4.913183279742765,
      "grad_norm": 1.414007306098938,
      "learning_rate": 3.183333333333334e-06,
      "loss": 0.0145,
      "num_input_tokens_seen": 6268992,
      "step": 382
    },
    {
      "epoch": 4.92604501607717,
      "grad_norm": 1.6091843843460083,
      "learning_rate": 3.191666666666667e-06,
      "loss": 0.0082,
      "num_input_tokens_seen": 6285312,
      "step": 383
    },
    {
      "epoch": 4.938906752411576,
      "grad_norm": 1.0037862062454224,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.0165,
      "num_input_tokens_seen": 6300992,
      "step": 384
    },
    {
      "epoch": 4.951768488745981,
      "grad_norm": 2.4763152599334717,
      "learning_rate": 3.2083333333333337e-06,
      "loss": 0.0243,
      "num_input_tokens_seen": 6318560,
      "step": 385
    },
    {
      "epoch": 4.951768488745981,
      "num_input_tokens_seen": 6318560,
      "step": 385,
      "total_flos": 2.5049338265940787e+17,
      "train_loss": 0.9364173337708336,
      "train_runtime": 4331.1035,
      "train_samples_per_second": 22.95,
      "train_steps_per_second": 0.089
    }
  ],
  "logging_steps": 1,
  "max_steps": 385,
  "num_input_tokens_seen": 6318560,
  "num_train_epochs": 5,
  "save_steps": 980,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.5049338265940787e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}