{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 198,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005050505050505051,
      "grad_norm": 35.239383697509766,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 2.6493,
      "step": 1
    },
    {
      "epoch": 0.010101010101010102,
      "grad_norm": 35.41305923461914,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 2.6401,
      "step": 2
    },
    {
      "epoch": 0.015151515151515152,
      "grad_norm": 35.47914505004883,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 2.6401,
      "step": 3
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 34.923484802246094,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 2.6202,
      "step": 4
    },
    {
      "epoch": 0.025252525252525252,
      "grad_norm": 34.7836799621582,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 2.6071,
      "step": 5
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 36.033050537109375,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 2.6612,
      "step": 6
    },
    {
      "epoch": 0.03535353535353535,
      "grad_norm": 34.26911926269531,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 2.5487,
      "step": 7
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 33.940216064453125,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.5171,
      "step": 8
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 33.55999755859375,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 2.5295,
      "step": 9
    },
    {
      "epoch": 0.050505050505050504,
      "grad_norm": 35.171165466308594,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.6192,
      "step": 10
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 32.917484283447266,
      "learning_rate": 5.5e-07,
      "loss": 2.4022,
      "step": 11
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 34.53117752075195,
      "learning_rate": 6.000000000000001e-07,
      "loss": 2.5785,
      "step": 12
    },
    {
      "epoch": 0.06565656565656566,
      "grad_norm": 34.89581298828125,
      "learning_rate": 6.5e-07,
      "loss": 2.52,
      "step": 13
    },
    {
      "epoch": 0.0707070707070707,
      "grad_norm": 32.23255920410156,
      "learning_rate": 7.000000000000001e-07,
      "loss": 2.2731,
      "step": 14
    },
    {
      "epoch": 0.07575757575757576,
      "grad_norm": 33.4830207824707,
      "learning_rate": 7.5e-07,
      "loss": 2.3016,
      "step": 15
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 33.69716262817383,
      "learning_rate": 8.000000000000001e-07,
      "loss": 2.2107,
      "step": 16
    },
    {
      "epoch": 0.08585858585858586,
      "grad_norm": 33.970333099365234,
      "learning_rate": 8.500000000000001e-07,
      "loss": 2.1916,
      "step": 17
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 32.690433502197266,
      "learning_rate": 9.000000000000001e-07,
      "loss": 1.9767,
      "step": 18
    },
    {
      "epoch": 0.09595959595959595,
      "grad_norm": 34.36090850830078,
      "learning_rate": 9.500000000000001e-07,
      "loss": 1.9856,
      "step": 19
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 34.156280517578125,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.7905,
      "step": 20
    },
    {
      "epoch": 0.10606060606060606,
      "grad_norm": 34.23146438598633,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 1.6931,
      "step": 21
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 33.700294494628906,
      "learning_rate": 1.1e-06,
      "loss": 1.5142,
      "step": 22
    },
    {
      "epoch": 0.11616161616161616,
      "grad_norm": 32.60850143432617,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 1.4211,
      "step": 23
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 30.005735397338867,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.2172,
      "step": 24
    },
    {
      "epoch": 0.12626262626262627,
      "grad_norm": 29.669198989868164,
      "learning_rate": 1.25e-06,
      "loss": 1.1584,
      "step": 25
    },
    {
      "epoch": 0.13131313131313133,
      "grad_norm": 30.327133178710938,
      "learning_rate": 1.3e-06,
      "loss": 0.8788,
      "step": 26
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 29.821216583251953,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 0.7566,
      "step": 27
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": 27.04122543334961,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.5775,
      "step": 28
    },
    {
      "epoch": 0.14646464646464646,
      "grad_norm": 24.890750885009766,
      "learning_rate": 1.45e-06,
      "loss": 0.5193,
      "step": 29
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 21.845609664916992,
      "learning_rate": 1.5e-06,
      "loss": 0.3785,
      "step": 30
    },
    {
      "epoch": 0.15656565656565657,
      "grad_norm": 17.295909881591797,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 0.3091,
      "step": 31
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 11.265312194824219,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.1745,
      "step": 32
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 5.728430271148682,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 0.1413,
      "step": 33
    },
    {
      "epoch": 0.1717171717171717,
      "grad_norm": 7.306532859802246,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.1613,
      "step": 34
    },
    {
      "epoch": 0.17676767676767677,
      "grad_norm": 5.182886600494385,
      "learning_rate": 1.75e-06,
      "loss": 0.1155,
      "step": 35
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 3.8576388359069824,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.0764,
      "step": 36
    },
    {
      "epoch": 0.18686868686868688,
      "grad_norm": 2.638275623321533,
      "learning_rate": 1.85e-06,
      "loss": 0.0745,
      "step": 37
    },
    {
      "epoch": 0.1919191919191919,
      "grad_norm": 2.225215435028076,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.0719,
      "step": 38
    },
    {
      "epoch": 0.19696969696969696,
      "grad_norm": 1.7595651149749756,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.0633,
      "step": 39
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 1.4759680032730103,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0529,
      "step": 40
    },
    {
      "epoch": 0.20707070707070707,
      "grad_norm": 1.3384065628051758,
      "learning_rate": 2.05e-06,
      "loss": 0.0433,
      "step": 41
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 1.564224362373352,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.061,
      "step": 42
    },
    {
      "epoch": 0.21717171717171718,
      "grad_norm": 1.419657826423645,
      "learning_rate": 2.15e-06,
      "loss": 0.0615,
      "step": 43
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 1.1758321523666382,
      "learning_rate": 2.2e-06,
      "loss": 0.059,
      "step": 44
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 1.3546487092971802,
      "learning_rate": 2.25e-06,
      "loss": 0.0574,
      "step": 45
    },
    {
      "epoch": 0.23232323232323232,
      "grad_norm": 1.0917863845825195,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.0601,
      "step": 46
    },
    {
      "epoch": 0.23737373737373738,
      "grad_norm": 0.990371823310852,
      "learning_rate": 2.35e-06,
      "loss": 0.0515,
      "step": 47
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 1.3220105171203613,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.0584,
      "step": 48
    },
    {
      "epoch": 0.2474747474747475,
      "grad_norm": 1.1640170812606812,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.0487,
      "step": 49
    },
    {
      "epoch": 0.25252525252525254,
      "grad_norm": 1.0264198780059814,
      "learning_rate": 2.5e-06,
      "loss": 0.0456,
      "step": 50
    },
    {
      "epoch": 0.25757575757575757,
      "grad_norm": 1.1187573671340942,
      "learning_rate": 2.55e-06,
      "loss": 0.0588,
      "step": 51
    },
    {
      "epoch": 0.26262626262626265,
      "grad_norm": 0.8740547299385071,
      "learning_rate": 2.6e-06,
      "loss": 0.0415,
      "step": 52
    },
    {
      "epoch": 0.2676767676767677,
      "grad_norm": 1.128773808479309,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.0535,
      "step": 53
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 1.1845512390136719,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.0543,
      "step": 54
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 1.0151381492614746,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.0467,
      "step": 55
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 1.0951204299926758,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.0432,
      "step": 56
    },
    {
      "epoch": 0.2878787878787879,
      "grad_norm": 0.8145187497138977,
      "learning_rate": 2.85e-06,
      "loss": 0.0433,
      "step": 57
    },
    {
      "epoch": 0.29292929292929293,
      "grad_norm": 0.8338307738304138,
      "learning_rate": 2.9e-06,
      "loss": 0.0442,
      "step": 58
    },
    {
      "epoch": 0.29797979797979796,
      "grad_norm": 1.2009202241897583,
      "learning_rate": 2.95e-06,
      "loss": 0.0471,
      "step": 59
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 1.0247856378555298,
      "learning_rate": 3e-06,
      "loss": 0.0418,
      "step": 60
    },
    {
      "epoch": 0.30808080808080807,
      "grad_norm": 0.8393287062644958,
      "learning_rate": 3.05e-06,
      "loss": 0.0411,
      "step": 61
    },
    {
      "epoch": 0.31313131313131315,
      "grad_norm": 0.807152271270752,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.0428,
      "step": 62
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 1.0362982749938965,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.0412,
      "step": 63
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 0.8612103462219238,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.0374,
      "step": 64
    },
    {
      "epoch": 0.3282828282828283,
      "grad_norm": 0.763271152973175,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.038,
      "step": 65
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.993196427822113,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.0476,
      "step": 66
    },
    {
      "epoch": 0.3383838383838384,
      "grad_norm": 1.1754580736160278,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.0496,
      "step": 67
    },
    {
      "epoch": 0.3434343434343434,
      "grad_norm": 0.7608982920646667,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.0371,
      "step": 68
    },
    {
      "epoch": 0.3484848484848485,
      "grad_norm": 0.8498206734657288,
      "learning_rate": 3.45e-06,
      "loss": 0.0422,
      "step": 69
    },
    {
      "epoch": 0.35353535353535354,
      "grad_norm": 0.8418146371841431,
      "learning_rate": 3.5e-06,
      "loss": 0.0361,
      "step": 70
    },
    {
      "epoch": 0.35858585858585856,
      "grad_norm": 0.8102655410766602,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.0356,
      "step": 71
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.7071998119354248,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.0352,
      "step": 72
    },
    {
      "epoch": 0.3686868686868687,
      "grad_norm": 0.8242170810699463,
      "learning_rate": 3.65e-06,
      "loss": 0.0393,
      "step": 73
    },
    {
      "epoch": 0.37373737373737376,
      "grad_norm": 0.93561190366745,
      "learning_rate": 3.7e-06,
      "loss": 0.047,
      "step": 74
    },
    {
      "epoch": 0.3787878787878788,
      "grad_norm": 0.8524022698402405,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0325,
      "step": 75
    },
    {
      "epoch": 0.3838383838383838,
      "grad_norm": 0.8019789457321167,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.0358,
      "step": 76
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 0.9955350160598755,
      "learning_rate": 3.85e-06,
      "loss": 0.0373,
      "step": 77
    },
    {
      "epoch": 0.3939393939393939,
      "grad_norm": 1.2481234073638916,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.0353,
      "step": 78
    },
    {
      "epoch": 0.398989898989899,
      "grad_norm": 0.7706320285797119,
      "learning_rate": 3.95e-06,
      "loss": 0.0352,
      "step": 79
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 0.8946953415870667,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0389,
      "step": 80
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 0.7142760753631592,
      "learning_rate": 4.05e-06,
      "loss": 0.0347,
      "step": 81
    },
    {
      "epoch": 0.41414141414141414,
      "grad_norm": 0.6389093399047852,
      "learning_rate": 4.1e-06,
      "loss": 0.0352,
      "step": 82
    },
    {
      "epoch": 0.41919191919191917,
      "grad_norm": 0.9447190165519714,
      "learning_rate": 4.15e-06,
      "loss": 0.0392,
      "step": 83
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 0.832013726234436,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.0361,
      "step": 84
    },
    {
      "epoch": 0.4292929292929293,
      "grad_norm": 0.8298827409744263,
      "learning_rate": 4.25e-06,
      "loss": 0.0342,
      "step": 85
    },
    {
      "epoch": 0.43434343434343436,
      "grad_norm": 0.8309102654457092,
      "learning_rate": 4.3e-06,
      "loss": 0.0253,
      "step": 86
    },
    {
      "epoch": 0.4393939393939394,
      "grad_norm": 0.8921272158622742,
      "learning_rate": 4.350000000000001e-06,
      "loss": 0.0356,
      "step": 87
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.9582182765007019,
      "learning_rate": 4.4e-06,
      "loss": 0.0307,
      "step": 88
    },
    {
      "epoch": 0.4494949494949495,
      "grad_norm": 0.9414967894554138,
      "learning_rate": 4.450000000000001e-06,
      "loss": 0.0347,
      "step": 89
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.8414708375930786,
      "learning_rate": 4.5e-06,
      "loss": 0.0324,
      "step": 90
    },
    {
      "epoch": 0.4595959595959596,
      "grad_norm": 0.97618168592453,
      "learning_rate": 4.5500000000000005e-06,
      "loss": 0.035,
      "step": 91
    },
    {
      "epoch": 0.46464646464646464,
      "grad_norm": 0.7519140839576721,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.0291,
      "step": 92
    },
    {
      "epoch": 0.4696969696969697,
      "grad_norm": 0.7026158571243286,
      "learning_rate": 4.65e-06,
      "loss": 0.0343,
      "step": 93
    },
    {
      "epoch": 0.47474747474747475,
      "grad_norm": 0.8826281428337097,
      "learning_rate": 4.7e-06,
      "loss": 0.0283,
      "step": 94
    },
    {
      "epoch": 0.4797979797979798,
      "grad_norm": 0.8762742877006531,
      "learning_rate": 4.75e-06,
      "loss": 0.027,
      "step": 95
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.7252739667892456,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.0286,
      "step": 96
    },
    {
      "epoch": 0.4898989898989899,
      "grad_norm": 0.7852551341056824,
      "learning_rate": 4.85e-06,
      "loss": 0.0287,
      "step": 97
    },
    {
      "epoch": 0.494949494949495,
      "grad_norm": 0.6870710849761963,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.0324,
      "step": 98
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.0492205619812012,
      "learning_rate": 4.95e-06,
      "loss": 0.0384,
      "step": 99
    },
    {
      "epoch": 0.5050505050505051,
      "grad_norm": 0.9691818952560425,
      "learning_rate": 5e-06,
      "loss": 0.0324,
      "step": 100
    },
    {
      "epoch": 0.51010101010101,
      "grad_norm": 0.7680443525314331,
      "learning_rate": 4.999989577985671e-06,
      "loss": 0.0239,
      "step": 101
    },
    {
      "epoch": 0.5151515151515151,
      "grad_norm": 0.7711728811264038,
      "learning_rate": 4.99995831202958e-06,
      "loss": 0.0339,
      "step": 102
    },
    {
      "epoch": 0.5202020202020202,
      "grad_norm": 0.664016842842102,
      "learning_rate": 4.999906202392409e-06,
      "loss": 0.0242,
      "step": 103
    },
    {
      "epoch": 0.5252525252525253,
      "grad_norm": 0.6629706621170044,
      "learning_rate": 4.999833249508629e-06,
      "loss": 0.0272,
      "step": 104
    },
    {
      "epoch": 0.5303030303030303,
      "grad_norm": 0.8449888229370117,
      "learning_rate": 4.999739453986491e-06,
      "loss": 0.0313,
      "step": 105
    },
    {
      "epoch": 0.5353535353535354,
      "grad_norm": 0.9404881000518799,
      "learning_rate": 4.999624816608027e-06,
      "loss": 0.0333,
      "step": 106
    },
    {
      "epoch": 0.5404040404040404,
      "grad_norm": 0.8782823085784912,
      "learning_rate": 4.99948933832904e-06,
      "loss": 0.0298,
      "step": 107
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.8479216694831848,
      "learning_rate": 4.999333020279094e-06,
      "loss": 0.0305,
      "step": 108
    },
    {
      "epoch": 0.5505050505050505,
      "grad_norm": 0.7747307419776917,
      "learning_rate": 4.999155863761507e-06,
      "loss": 0.0275,
      "step": 109
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.8345880508422852,
      "learning_rate": 4.998957870253344e-06,
      "loss": 0.0326,
      "step": 110
    },
    {
      "epoch": 0.5606060606060606,
      "grad_norm": 0.84605473279953,
      "learning_rate": 4.998739041405395e-06,
      "loss": 0.0302,
      "step": 111
    },
    {
      "epoch": 0.5656565656565656,
      "grad_norm": 0.7808102369308472,
      "learning_rate": 4.998499379042172e-06,
      "loss": 0.0262,
      "step": 112
    },
    {
      "epoch": 0.5707070707070707,
      "grad_norm": 0.8007850050926208,
      "learning_rate": 4.998238885161886e-06,
      "loss": 0.0272,
      "step": 113
    },
    {
      "epoch": 0.5757575757575758,
      "grad_norm": 0.8897403478622437,
      "learning_rate": 4.997957561936433e-06,
      "loss": 0.0261,
      "step": 114
    },
    {
      "epoch": 0.5808080808080808,
      "grad_norm": 0.8403050899505615,
      "learning_rate": 4.997655411711378e-06,
      "loss": 0.0292,
      "step": 115
    },
    {
      "epoch": 0.5858585858585859,
      "grad_norm": 0.7349573969841003,
      "learning_rate": 4.997332437005932e-06,
      "loss": 0.0243,
      "step": 116
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 0.8440062999725342,
      "learning_rate": 4.996988640512931e-06,
      "loss": 0.0253,
      "step": 117
    },
    {
      "epoch": 0.5959595959595959,
      "grad_norm": 0.8826310038566589,
      "learning_rate": 4.996624025098819e-06,
      "loss": 0.0209,
      "step": 118
    },
    {
      "epoch": 0.601010101010101,
      "grad_norm": 1.1104847192764282,
      "learning_rate": 4.996238593803616e-06,
      "loss": 0.0242,
      "step": 119
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 1.3400338888168335,
      "learning_rate": 4.9958323498409e-06,
      "loss": 0.0347,
      "step": 120
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 0.9243490099906921,
      "learning_rate": 4.9954052965977725e-06,
      "loss": 0.0202,
      "step": 121
    },
    {
      "epoch": 0.6161616161616161,
      "grad_norm": 1.075374960899353,
      "learning_rate": 4.99495743763484e-06,
      "loss": 0.0309,
      "step": 122
    },
    {
      "epoch": 0.6212121212121212,
      "grad_norm": 1.0591344833374023,
      "learning_rate": 4.9944887766861765e-06,
      "loss": 0.0241,
      "step": 123
    },
    {
      "epoch": 0.6262626262626263,
      "grad_norm": 0.7506961226463318,
      "learning_rate": 4.993999317659293e-06,
      "loss": 0.025,
      "step": 124
    },
    {
      "epoch": 0.6313131313131313,
      "grad_norm": 1.016758680343628,
      "learning_rate": 4.993489064635109e-06,
      "loss": 0.0219,
      "step": 125
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 0.7476636171340942,
      "learning_rate": 4.9929580218679195e-06,
      "loss": 0.021,
      "step": 126
    },
    {
      "epoch": 0.6414141414141414,
      "grad_norm": 0.7349154949188232,
      "learning_rate": 4.992406193785348e-06,
      "loss": 0.0228,
      "step": 127
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 0.672728419303894,
      "learning_rate": 4.991833584988326e-06,
      "loss": 0.0209,
      "step": 128
    },
    {
      "epoch": 0.6515151515151515,
      "grad_norm": 0.5250627398490906,
      "learning_rate": 4.991240200251041e-06,
      "loss": 0.0124,
      "step": 129
    },
    {
      "epoch": 0.6565656565656566,
      "grad_norm": 1.0610628128051758,
      "learning_rate": 4.990626044520905e-06,
      "loss": 0.0176,
      "step": 130
    },
    {
      "epoch": 0.6616161616161617,
      "grad_norm": 1.0880004167556763,
      "learning_rate": 4.98999112291851e-06,
      "loss": 0.024,
      "step": 131
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.9670020937919617,
      "learning_rate": 4.989335440737587e-06,
      "loss": 0.0224,
      "step": 132
    },
    {
      "epoch": 0.6717171717171717,
      "grad_norm": 0.869041383266449,
      "learning_rate": 4.988659003444956e-06,
      "loss": 0.0184,
      "step": 133
    },
    {
      "epoch": 0.6767676767676768,
      "grad_norm": 0.9090948700904846,
      "learning_rate": 4.987961816680493e-06,
      "loss": 0.0192,
      "step": 134
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 1.0600134134292603,
      "learning_rate": 4.987243886257066e-06,
      "loss": 0.029,
      "step": 135
    },
    {
      "epoch": 0.6868686868686869,
      "grad_norm": 0.5932410359382629,
      "learning_rate": 4.986505218160502e-06,
      "loss": 0.0172,
      "step": 136
    },
    {
      "epoch": 0.6919191919191919,
      "grad_norm": 0.8293594121932983,
      "learning_rate": 4.985745818549527e-06,
      "loss": 0.0207,
      "step": 137
    },
    {
      "epoch": 0.696969696969697,
      "grad_norm": 0.863837718963623,
      "learning_rate": 4.984965693755723e-06,
      "loss": 0.0262,
      "step": 138
    },
    {
      "epoch": 0.702020202020202,
      "grad_norm": 0.8079712390899658,
      "learning_rate": 4.984164850283465e-06,
      "loss": 0.0226,
      "step": 139
    },
    {
      "epoch": 0.7070707070707071,
      "grad_norm": 0.7353380918502808,
      "learning_rate": 4.983343294809875e-06,
      "loss": 0.031,
      "step": 140
    },
    {
      "epoch": 0.7121212121212122,
      "grad_norm": 0.6296212673187256,
      "learning_rate": 4.9825010341847644e-06,
      "loss": 0.016,
      "step": 141
    },
    {
      "epoch": 0.7171717171717171,
      "grad_norm": 0.9319673180580139,
      "learning_rate": 4.981638075430572e-06,
      "loss": 0.0213,
      "step": 142
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 0.6460096836090088,
      "learning_rate": 4.980754425742318e-06,
      "loss": 0.0203,
      "step": 143
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.6757596731185913,
      "learning_rate": 4.979850092487525e-06,
      "loss": 0.0175,
      "step": 144
    },
    {
      "epoch": 0.7323232323232324,
      "grad_norm": 0.7001456022262573,
      "learning_rate": 4.978925083206174e-06,
      "loss": 0.021,
      "step": 145
    },
    {
      "epoch": 0.7373737373737373,
      "grad_norm": 0.602177619934082,
      "learning_rate": 4.977979405610635e-06,
      "loss": 0.0168,
      "step": 146
    },
    {
      "epoch": 0.7424242424242424,
      "grad_norm": 0.7525290250778198,
      "learning_rate": 4.977013067585597e-06,
      "loss": 0.022,
      "step": 147
    },
    {
      "epoch": 0.7474747474747475,
      "grad_norm": 0.6703810095787048,
      "learning_rate": 4.976026077188013e-06,
      "loss": 0.016,
      "step": 148
    },
    {
      "epoch": 0.7525252525252525,
      "grad_norm": 0.7743527293205261,
      "learning_rate": 4.975018442647026e-06,
      "loss": 0.0226,
      "step": 149
    },
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 0.6670228838920593,
      "learning_rate": 4.973990172363899e-06,
      "loss": 0.0181,
      "step": 150
    },
    {
      "epoch": 0.7626262626262627,
      "grad_norm": 0.7247374653816223,
      "learning_rate": 4.972941274911953e-06,
      "loss": 0.0146,
      "step": 151
    },
    {
      "epoch": 0.7676767676767676,
      "grad_norm": 0.6329397559165955,
      "learning_rate": 4.9718717590364855e-06,
      "loss": 0.0165,
      "step": 152
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 0.859639048576355,
      "learning_rate": 4.9707816336547045e-06,
      "loss": 0.0216,
      "step": 153
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.7974834442138672,
      "learning_rate": 4.969670907855651e-06,
      "loss": 0.0212,
      "step": 154
    },
    {
      "epoch": 0.7828282828282829,
      "grad_norm": 1.1814897060394287,
      "learning_rate": 4.968539590900128e-06,
      "loss": 0.0231,
      "step": 155
    },
    {
      "epoch": 0.7878787878787878,
      "grad_norm": 0.7747610211372375,
      "learning_rate": 4.967387692220615e-06,
      "loss": 0.0137,
      "step": 156
    },
    {
      "epoch": 0.7929292929292929,
      "grad_norm": 0.5962601900100708,
      "learning_rate": 4.966215221421195e-06,
      "loss": 0.0139,
      "step": 157
    },
    {
      "epoch": 0.797979797979798,
      "grad_norm": 1.1249876022338867,
      "learning_rate": 4.965022188277474e-06,
      "loss": 0.0192,
      "step": 158
    },
    {
      "epoch": 0.803030303030303,
      "grad_norm": 0.559429407119751,
      "learning_rate": 4.9638086027365005e-06,
      "loss": 0.0128,
      "step": 159
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 1.0353529453277588,
      "learning_rate": 4.962574474916678e-06,
      "loss": 0.0179,
      "step": 160
    },
    {
      "epoch": 0.8131313131313131,
      "grad_norm": 0.5366432666778564,
      "learning_rate": 4.961319815107685e-06,
      "loss": 0.0098,
      "step": 161
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.673726499080658,
      "learning_rate": 4.960044633770387e-06,
      "loss": 0.0144,
      "step": 162
    },
    {
      "epoch": 0.8232323232323232,
      "grad_norm": 0.517419695854187,
      "learning_rate": 4.95874894153675e-06,
      "loss": 0.016,
      "step": 163
    },
    {
      "epoch": 0.8282828282828283,
      "grad_norm": 0.5697750449180603,
      "learning_rate": 4.957432749209755e-06,
      "loss": 0.0117,
      "step": 164
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 1.0551936626434326,
      "learning_rate": 4.9560960677633e-06,
      "loss": 0.0179,
      "step": 165
    },
    {
      "epoch": 0.8383838383838383,
      "grad_norm": 0.564612865447998,
      "learning_rate": 4.954738908342116e-06,
      "loss": 0.0112,
      "step": 166
    },
    {
      "epoch": 0.8434343434343434,
      "grad_norm": 0.7717934846878052,
      "learning_rate": 4.953361282261671e-06,
      "loss": 0.0121,
      "step": 167
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 0.6095231175422668,
      "learning_rate": 4.9519632010080765e-06,
      "loss": 0.0071,
      "step": 168
    },
    {
      "epoch": 0.8535353535353535,
      "grad_norm": 0.7816880941390991,
      "learning_rate": 4.95054467623799e-06,
      "loss": 0.0107,
      "step": 169
    },
    {
      "epoch": 0.8585858585858586,
      "grad_norm": 0.5223932266235352,
      "learning_rate": 4.9491057197785205e-06,
      "loss": 0.0106,
      "step": 170
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 0.9016621708869934,
      "learning_rate": 4.947646343627128e-06,
      "loss": 0.0118,
      "step": 171
    },
    {
      "epoch": 0.8686868686868687,
      "grad_norm": 0.4834199547767639,
      "learning_rate": 4.946166559951523e-06,
      "loss": 0.0063,
      "step": 172
    },
    {
      "epoch": 0.8737373737373737,
      "grad_norm": 0.8252310752868652,
      "learning_rate": 4.944666381089567e-06,
      "loss": 0.0175,
      "step": 173
    },
    {
      "epoch": 0.8787878787878788,
      "grad_norm": 0.6991069912910461,
      "learning_rate": 4.943145819549169e-06,
      "loss": 0.0104,
      "step": 174
    },
    {
      "epoch": 0.8838383838383839,
      "grad_norm": 0.6017345786094666,
      "learning_rate": 4.941604888008181e-06,
      "loss": 0.0117,
      "step": 175
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.69279944896698,
      "learning_rate": 4.9400435993142895e-06,
      "loss": 0.0137,
      "step": 176
    },
    {
      "epoch": 0.8939393939393939,
      "grad_norm": 1.0663758516311646,
      "learning_rate": 4.938461966484914e-06,
      "loss": 0.01,
      "step": 177
    },
    {
      "epoch": 0.898989898989899,
      "grad_norm": 0.9510229229927063,
      "learning_rate": 4.936860002707096e-06,
      "loss": 0.0085,
      "step": 178
    },
    {
      "epoch": 0.9040404040404041,
      "grad_norm": 0.8557943105697632,
      "learning_rate": 4.935237721337384e-06,
      "loss": 0.0141,
      "step": 179
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.7711794972419739,
      "learning_rate": 4.933595135901733e-06,
      "loss": 0.0117,
      "step": 180
    },
    {
      "epoch": 0.9141414141414141,
      "grad_norm": 0.8024590015411377,
      "learning_rate": 4.931932260095379e-06,
      "loss": 0.01,
      "step": 181
    },
    {
      "epoch": 0.9191919191919192,
      "grad_norm": 0.8047268390655518,
      "learning_rate": 4.9302491077827366e-06,
      "loss": 0.0192,
      "step": 182
    },
    {
      "epoch": 0.9242424242424242,
      "grad_norm": 0.5250588655471802,
      "learning_rate": 4.928545692997275e-06,
      "loss": 0.0096,
      "step": 183
    },
    {
      "epoch": 0.9292929292929293,
      "grad_norm": 0.45513755083084106,
      "learning_rate": 4.926822029941406e-06,
      "loss": 0.0087,
      "step": 184
    },
    {
      "epoch": 0.9343434343434344,
      "grad_norm": 0.4509701728820801,
      "learning_rate": 4.925078132986361e-06,
      "loss": 0.0118,
      "step": 185
    },
    {
      "epoch": 0.9393939393939394,
      "grad_norm": 0.5309934616088867,
      "learning_rate": 4.923314016672075e-06,
      "loss": 0.0084,
      "step": 186
    },
    {
      "epoch": 0.9444444444444444,
      "grad_norm": 0.4668470621109009,
      "learning_rate": 4.921529695707065e-06,
      "loss": 0.0076,
      "step": 187
    },
    {
      "epoch": 0.9494949494949495,
      "grad_norm": 0.5394138097763062,
      "learning_rate": 4.919725184968307e-06,
      "loss": 0.0129,
      "step": 188
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 0.5527902841567993,
      "learning_rate": 4.917900499501109e-06,
      "loss": 0.0099,
      "step": 189
    },
    {
      "epoch": 0.9595959595959596,
      "grad_norm": 0.4318401515483856,
      "learning_rate": 4.9160556545189895e-06,
      "loss": 0.0116,
      "step": 190
    },
    {
      "epoch": 0.9646464646464646,
      "grad_norm": 0.5038670301437378,
      "learning_rate": 4.91419066540355e-06,
      "loss": 0.0089,
      "step": 191
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.5830440521240234,
      "learning_rate": 4.9123055477043454e-06,
      "loss": 0.0072,
      "step": 192
    },
    {
      "epoch": 0.9747474747474747,
      "grad_norm": 0.3858352303504944,
      "learning_rate": 4.910400317138752e-06,
      "loss": 0.0078,
      "step": 193
    },
    {
      "epoch": 0.9797979797979798,
      "grad_norm": 0.7046027183532715,
      "learning_rate": 4.908474989591846e-06,
      "loss": 0.0111,
      "step": 194
    },
    {
      "epoch": 0.9848484848484849,
      "grad_norm": 0.8276668787002563,
      "learning_rate": 4.906529581116259e-06,
      "loss": 0.011,
      "step": 195
    },
    {
      "epoch": 0.98989898989899,
      "grad_norm": 0.8134333491325378,
      "learning_rate": 4.904564107932048e-06,
      "loss": 0.0073,
      "step": 196
    },
    {
      "epoch": 0.9949494949494949,
      "grad_norm": 0.41067278385162354,
      "learning_rate": 4.902578586426569e-06,
      "loss": 0.0073,
      "step": 197
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6972447633743286,
      "learning_rate": 4.900573033154325e-06,
      "loss": 0.0113,
      "step": 198
    }
  ],
  "logging_steps": 1,
  "max_steps": 1188,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 198,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.0015526595854336e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}