{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7575757575757576,
  "eval_steps": 38,
  "global_step": 225,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003367003367003367,
      "grad_norm": 2.0,
      "learning_rate": 4.5454545454545457e-07,
      "loss": 1.0833,
      "step": 1
    },
    {
      "epoch": 0.003367003367003367,
      "eval_loss": 1.032954454421997,
      "eval_runtime": 8.7786,
      "eval_samples_per_second": 56.957,
      "eval_steps_per_second": 3.645,
      "step": 1
    },
    {
      "epoch": 0.006734006734006734,
      "grad_norm": 2.265625,
      "learning_rate": 9.090909090909091e-07,
      "loss": 0.996,
      "step": 2
    },
    {
      "epoch": 0.010101010101010102,
      "grad_norm": 1.6484375,
      "learning_rate": 1.3636363636363636e-06,
      "loss": 1.0487,
      "step": 3
    },
    {
      "epoch": 0.013468013468013467,
      "grad_norm": 2.046875,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 1.0554,
      "step": 4
    },
    {
      "epoch": 0.016835016835016835,
      "grad_norm": 2.4375,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 1.0341,
      "step": 5
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 1.9609375,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 1.0132,
      "step": 6
    },
    {
      "epoch": 0.02356902356902357,
      "grad_norm": 2.625,
      "learning_rate": 3.181818181818182e-06,
      "loss": 1.0298,
      "step": 7
    },
    {
      "epoch": 0.026936026936026935,
      "grad_norm": 2.296875,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 1.0216,
      "step": 8
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 2.234375,
      "learning_rate": 4.0909090909090915e-06,
      "loss": 1.0736,
      "step": 9
    },
    {
      "epoch": 0.03367003367003367,
      "grad_norm": 2.1875,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 1.0216,
      "step": 10
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 2.359375,
      "learning_rate": 5e-06,
      "loss": 1.0075,
      "step": 11
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 1.890625,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 1.051,
      "step": 12
    },
    {
      "epoch": 0.04377104377104377,
      "grad_norm": 1.90625,
      "learning_rate": 5.90909090909091e-06,
      "loss": 1.0655,
      "step": 13
    },
    {
      "epoch": 0.04713804713804714,
      "grad_norm": 1.6484375,
      "learning_rate": 6.363636363636364e-06,
      "loss": 1.0297,
      "step": 14
    },
    {
      "epoch": 0.050505050505050504,
      "grad_norm": 1.6953125,
      "learning_rate": 6.818181818181818e-06,
      "loss": 1.0411,
      "step": 15
    },
    {
      "epoch": 0.05387205387205387,
      "grad_norm": 1.9921875,
      "learning_rate": 7.272727272727273e-06,
      "loss": 1.0618,
      "step": 16
    },
    {
      "epoch": 0.05723905723905724,
      "grad_norm": 1.4453125,
      "learning_rate": 7.727272727272727e-06,
      "loss": 1.0052,
      "step": 17
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 1.390625,
      "learning_rate": 8.181818181818183e-06,
      "loss": 1.0053,
      "step": 18
    },
    {
      "epoch": 0.06397306397306397,
      "grad_norm": 1.2734375,
      "learning_rate": 8.636363636363637e-06,
      "loss": 0.9786,
      "step": 19
    },
    {
      "epoch": 0.06734006734006734,
      "grad_norm": 1.234375,
      "learning_rate": 9.090909090909091e-06,
      "loss": 1.0419,
      "step": 20
    },
    {
      "epoch": 0.0707070707070707,
      "grad_norm": 1.1484375,
      "learning_rate": 9.545454545454547e-06,
      "loss": 1.0356,
      "step": 21
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 1.28125,
      "learning_rate": 1e-05,
      "loss": 0.9778,
      "step": 22
    },
    {
      "epoch": 0.07744107744107744,
      "grad_norm": 1.1875,
      "learning_rate": 1.0454545454545455e-05,
      "loss": 0.9691,
      "step": 23
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 1.1953125,
      "learning_rate": 1.0909090909090909e-05,
      "loss": 1.0408,
      "step": 24
    },
    {
      "epoch": 0.08417508417508418,
      "grad_norm": 1.078125,
      "learning_rate": 1.1363636363636366e-05,
      "loss": 0.9799,
      "step": 25
    },
    {
      "epoch": 0.08754208754208755,
      "grad_norm": 1.0390625,
      "learning_rate": 1.181818181818182e-05,
      "loss": 0.9756,
      "step": 26
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 1.1875,
      "learning_rate": 1.2272727272727274e-05,
      "loss": 1.0451,
      "step": 27
    },
    {
      "epoch": 0.09427609427609428,
      "grad_norm": 1.0546875,
      "learning_rate": 1.2727272727272728e-05,
      "loss": 1.0093,
      "step": 28
    },
    {
      "epoch": 0.09764309764309764,
      "grad_norm": 0.96484375,
      "learning_rate": 1.3181818181818183e-05,
      "loss": 0.99,
      "step": 29
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 1.0703125,
      "learning_rate": 1.3636363636363637e-05,
      "loss": 1.0079,
      "step": 30
    },
    {
      "epoch": 0.10437710437710437,
      "grad_norm": 0.89453125,
      "learning_rate": 1.4090909090909092e-05,
      "loss": 0.9653,
      "step": 31
    },
    {
      "epoch": 0.10774410774410774,
      "grad_norm": 1.0546875,
      "learning_rate": 1.4545454545454546e-05,
      "loss": 0.9926,
      "step": 32
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.96875,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.9857,
      "step": 33
    },
    {
      "epoch": 0.11447811447811448,
      "grad_norm": 1.1484375,
      "learning_rate": 1.5454545454545454e-05,
      "loss": 0.9676,
      "step": 34
    },
    {
      "epoch": 0.11784511784511785,
      "grad_norm": 1.078125,
      "learning_rate": 1.590909090909091e-05,
      "loss": 0.9686,
      "step": 35
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.8203125,
      "learning_rate": 1.6363636363636366e-05,
      "loss": 0.9182,
      "step": 36
    },
    {
      "epoch": 0.12457912457912458,
      "grad_norm": 0.8515625,
      "learning_rate": 1.681818181818182e-05,
      "loss": 0.9506,
      "step": 37
    },
    {
      "epoch": 0.12794612794612795,
      "grad_norm": 0.86328125,
      "learning_rate": 1.7272727272727274e-05,
      "loss": 0.9533,
      "step": 38
    },
    {
      "epoch": 0.12794612794612795,
      "eval_loss": 0.9329763054847717,
      "eval_runtime": 8.7095,
      "eval_samples_per_second": 57.409,
      "eval_steps_per_second": 3.674,
      "step": 38
    },
    {
      "epoch": 0.13131313131313133,
      "grad_norm": 0.7890625,
      "learning_rate": 1.772727272727273e-05,
      "loss": 0.9225,
      "step": 39
    },
    {
      "epoch": 0.13468013468013468,
      "grad_norm": 0.890625,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.9378,
      "step": 40
    },
    {
      "epoch": 0.13804713804713806,
      "grad_norm": 1.046875,
      "learning_rate": 1.8636363636363638e-05,
      "loss": 0.8982,
      "step": 41
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": 0.94921875,
      "learning_rate": 1.9090909090909094e-05,
      "loss": 0.8958,
      "step": 42
    },
    {
      "epoch": 0.1447811447811448,
      "grad_norm": 0.9765625,
      "learning_rate": 1.9545454545454546e-05,
      "loss": 0.8796,
      "step": 43
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.92578125,
      "learning_rate": 2e-05,
      "loss": 0.8808,
      "step": 44
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 0.94921875,
      "learning_rate": 1.9999931213623708e-05,
      "loss": 0.8638,
      "step": 45
    },
    {
      "epoch": 0.15488215488215487,
      "grad_norm": 1.0390625,
      "learning_rate": 1.999972485544114e-05,
      "loss": 0.9124,
      "step": 46
    },
    {
      "epoch": 0.15824915824915825,
      "grad_norm": 1.046875,
      "learning_rate": 1.999938092829122e-05,
      "loss": 0.8757,
      "step": 47
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 0.73046875,
      "learning_rate": 1.999889943690545e-05,
      "loss": 0.885,
      "step": 48
    },
    {
      "epoch": 0.16498316498316498,
      "grad_norm": 0.86328125,
      "learning_rate": 1.9998280387907845e-05,
      "loss": 0.8664,
      "step": 49
    },
    {
      "epoch": 0.16835016835016836,
      "grad_norm": 0.87109375,
      "learning_rate": 1.9997523789814827e-05,
      "loss": 0.8512,
      "step": 50
    },
    {
      "epoch": 0.1717171717171717,
      "grad_norm": 0.80859375,
      "learning_rate": 1.9996629653035128e-05,
      "loss": 0.8428,
      "step": 51
    },
    {
      "epoch": 0.1750841750841751,
      "grad_norm": 0.71875,
      "learning_rate": 1.9995597989869625e-05,
      "loss": 0.8536,
      "step": 52
    },
    {
      "epoch": 0.17845117845117844,
      "grad_norm": 0.6171875,
      "learning_rate": 1.9994428814511205e-05,
      "loss": 0.82,
      "step": 53
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.71875,
      "learning_rate": 1.999312214304453e-05,
      "loss": 0.8043,
      "step": 54
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 0.8046875,
      "learning_rate": 1.9991677993445832e-05,
      "loss": 0.8525,
      "step": 55
    },
    {
      "epoch": 0.18855218855218855,
      "grad_norm": 0.6015625,
      "learning_rate": 1.9990096385582682e-05,
      "loss": 0.7958,
      "step": 56
    },
    {
      "epoch": 0.1919191919191919,
      "grad_norm": 0.79296875,
      "learning_rate": 1.998837734121369e-05,
      "loss": 0.8001,
      "step": 57
    },
    {
      "epoch": 0.19528619528619529,
      "grad_norm": 0.7109375,
      "learning_rate": 1.9986520883988233e-05,
      "loss": 0.805,
      "step": 58
    },
    {
      "epoch": 0.19865319865319866,
      "grad_norm": 0.84375,
      "learning_rate": 1.9984527039446093e-05,
      "loss": 0.7821,
      "step": 59
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 1.1015625,
      "learning_rate": 1.998239583501714e-05,
      "loss": 0.7932,
      "step": 60
    },
    {
      "epoch": 0.2053872053872054,
      "grad_norm": 0.6953125,
      "learning_rate": 1.9980127300020946e-05,
      "loss": 0.7925,
      "step": 61
    },
    {
      "epoch": 0.20875420875420875,
      "grad_norm": 0.60546875,
      "learning_rate": 1.9977721465666365e-05,
      "loss": 0.7846,
      "step": 62
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 0.7265625,
      "learning_rate": 1.9975178365051123e-05,
      "loss": 0.7671,
      "step": 63
    },
    {
      "epoch": 0.21548821548821548,
      "grad_norm": 0.70703125,
      "learning_rate": 1.997249803316136e-05,
      "loss": 0.8194,
      "step": 64
    },
    {
      "epoch": 0.21885521885521886,
      "grad_norm": 0.81640625,
      "learning_rate": 1.9969680506871138e-05,
      "loss": 0.7607,
      "step": 65
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.61328125,
      "learning_rate": 1.9966725824941933e-05,
      "loss": 0.7858,
      "step": 66
    },
    {
      "epoch": 0.2255892255892256,
      "grad_norm": 0.66015625,
      "learning_rate": 1.9963634028022133e-05,
      "loss": 0.7546,
      "step": 67
    },
    {
      "epoch": 0.22895622895622897,
      "grad_norm": 0.6875,
      "learning_rate": 1.9960405158646425e-05,
      "loss": 0.7915,
      "step": 68
    },
    {
      "epoch": 0.23232323232323232,
      "grad_norm": 0.59765625,
      "learning_rate": 1.9957039261235263e-05,
      "loss": 0.7324,
      "step": 69
    },
    {
      "epoch": 0.2356902356902357,
      "grad_norm": 0.65625,
      "learning_rate": 1.9953536382094218e-05,
      "loss": 0.7735,
      "step": 70
    },
    {
      "epoch": 0.23905723905723905,
      "grad_norm": 0.984375,
      "learning_rate": 1.9949896569413368e-05,
      "loss": 0.7356,
      "step": 71
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.8125,
      "learning_rate": 1.9946119873266615e-05,
      "loss": 0.7407,
      "step": 72
    },
    {
      "epoch": 0.24579124579124578,
      "grad_norm": 0.76953125,
      "learning_rate": 1.9942206345611008e-05,
      "loss": 0.7124,
      "step": 73
    },
    {
      "epoch": 0.24915824915824916,
      "grad_norm": 0.6640625,
      "learning_rate": 1.9938156040286027e-05,
      "loss": 0.7295,
      "step": 74
    },
    {
      "epoch": 0.25252525252525254,
      "grad_norm": 0.5546875,
      "learning_rate": 1.993396901301283e-05,
      "loss": 0.733,
      "step": 75
    },
    {
      "epoch": 0.2558922558922559,
      "grad_norm": 0.5703125,
      "learning_rate": 1.9929645321393505e-05,
      "loss": 0.779,
      "step": 76
    },
    {
      "epoch": 0.2558922558922559,
      "eval_loss": 0.7325140237808228,
      "eval_runtime": 8.7635,
      "eval_samples_per_second": 57.055,
      "eval_steps_per_second": 3.652,
      "step": 76
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 0.67578125,
      "learning_rate": 1.992518502491028e-05,
      "loss": 0.7345,
      "step": 77
    },
    {
      "epoch": 0.26262626262626265,
      "grad_norm": 0.5,
      "learning_rate": 1.9920588184924664e-05,
      "loss": 0.7102,
      "step": 78
    },
    {
      "epoch": 0.265993265993266,
      "grad_norm": 0.51953125,
      "learning_rate": 1.9915854864676665e-05,
      "loss": 0.7433,
      "step": 79
    },
    {
      "epoch": 0.26936026936026936,
      "grad_norm": 0.48828125,
      "learning_rate": 1.991098512928386e-05,
      "loss": 0.7628,
      "step": 80
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.55859375,
      "learning_rate": 1.990597904574055e-05,
      "loss": 0.6858,
      "step": 81
    },
    {
      "epoch": 0.2760942760942761,
      "grad_norm": 0.5390625,
      "learning_rate": 1.9900836682916796e-05,
      "loss": 0.7169,
      "step": 82
    },
    {
      "epoch": 0.27946127946127947,
      "grad_norm": 0.494140625,
      "learning_rate": 1.9895558111557503e-05,
      "loss": 0.6995,
      "step": 83
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 0.4765625,
      "learning_rate": 1.989014340428143e-05,
      "loss": 0.7234,
      "step": 84
    },
    {
      "epoch": 0.28619528619528617,
      "grad_norm": 0.5546875,
      "learning_rate": 1.98845926355802e-05,
      "loss": 0.7182,
      "step": 85
    },
    {
      "epoch": 0.2895622895622896,
      "grad_norm": 0.51171875,
      "learning_rate": 1.9878905881817254e-05,
      "loss": 0.6837,
      "step": 86
    },
    {
      "epoch": 0.29292929292929293,
      "grad_norm": 0.54296875,
      "learning_rate": 1.9873083221226833e-05,
      "loss": 0.6759,
      "step": 87
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.52734375,
      "learning_rate": 1.986712473391289e-05,
      "loss": 0.7275,
      "step": 88
    },
    {
      "epoch": 0.2996632996632997,
      "grad_norm": 0.51171875,
      "learning_rate": 1.986103050184797e-05,
      "loss": 0.728,
      "step": 89
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 0.4609375,
      "learning_rate": 1.9854800608872096e-05,
      "loss": 0.6865,
      "step": 90
    },
    {
      "epoch": 0.3063973063973064,
      "grad_norm": 0.44921875,
      "learning_rate": 1.9848435140691627e-05,
      "loss": 0.6816,
      "step": 91
    },
    {
      "epoch": 0.30976430976430974,
      "grad_norm": 0.4453125,
      "learning_rate": 1.9841934184878056e-05,
      "loss": 0.6767,
      "step": 92
    },
    {
      "epoch": 0.31313131313131315,
      "grad_norm": 0.546875,
      "learning_rate": 1.9835297830866827e-05,
      "loss": 0.7623,
      "step": 93
    },
    {
      "epoch": 0.3164983164983165,
      "grad_norm": 0.45703125,
      "learning_rate": 1.9828526169956083e-05,
      "loss": 0.7193,
      "step": 94
    },
    {
      "epoch": 0.31986531986531985,
      "grad_norm": 0.482421875,
      "learning_rate": 1.9821619295305432e-05,
      "loss": 0.6573,
      "step": 95
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 0.43359375,
      "learning_rate": 1.9814577301934647e-05,
      "loss": 0.7,
      "step": 96
    },
    {
      "epoch": 0.3265993265993266,
      "grad_norm": 0.56640625,
      "learning_rate": 1.980740028672237e-05,
      "loss": 0.7111,
      "step": 97
    },
    {
      "epoch": 0.32996632996632996,
      "grad_norm": 0.47265625,
      "learning_rate": 1.9800088348404778e-05,
      "loss": 0.7025,
      "step": 98
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.51953125,
      "learning_rate": 1.9792641587574212e-05,
      "loss": 0.6925,
      "step": 99
    },
    {
      "epoch": 0.3367003367003367,
      "grad_norm": 0.484375,
      "learning_rate": 1.9785060106677818e-05,
      "loss": 0.6715,
      "step": 100
    },
    {
      "epoch": 0.3400673400673401,
      "grad_norm": 0.443359375,
      "learning_rate": 1.977734401001611e-05,
      "loss": 0.6929,
      "step": 101
    },
    {
      "epoch": 0.3434343434343434,
      "grad_norm": 0.5703125,
      "learning_rate": 1.9769493403741556e-05,
      "loss": 0.7126,
      "step": 102
    },
    {
      "epoch": 0.3468013468013468,
      "grad_norm": 0.490234375,
      "learning_rate": 1.9761508395857106e-05,
      "loss": 0.7012,
      "step": 103
    },
    {
      "epoch": 0.3501683501683502,
      "grad_norm": 0.54296875,
      "learning_rate": 1.9753389096214716e-05,
      "loss": 0.6819,
      "step": 104
    },
    {
      "epoch": 0.35353535353535354,
      "grad_norm": 0.412109375,
      "learning_rate": 1.974513561651382e-05,
      "loss": 0.7073,
      "step": 105
    },
    {
      "epoch": 0.3569023569023569,
      "grad_norm": 0.4296875,
      "learning_rate": 1.9736748070299813e-05,
      "loss": 0.6743,
      "step": 106
    },
    {
      "epoch": 0.3602693602693603,
      "grad_norm": 0.4140625,
      "learning_rate": 1.9728226572962474e-05,
      "loss": 0.6746,
      "step": 107
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.5078125,
      "learning_rate": 1.9719571241734395e-05,
      "loss": 0.6729,
      "step": 108
    },
    {
      "epoch": 0.367003367003367,
      "grad_norm": 0.74609375,
      "learning_rate": 1.9710782195689343e-05,
      "loss": 0.6781,
      "step": 109
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.462890625,
      "learning_rate": 1.9701859555740647e-05,
      "loss": 0.6976,
      "step": 110
    },
    {
      "epoch": 0.37373737373737376,
      "grad_norm": 0.396484375,
      "learning_rate": 1.9692803444639517e-05,
      "loss": 0.6464,
      "step": 111
    },
    {
      "epoch": 0.3771043771043771,
      "grad_norm": 0.58203125,
      "learning_rate": 1.9683613986973373e-05,
      "loss": 0.6614,
      "step": 112
    },
    {
      "epoch": 0.38047138047138046,
      "grad_norm": 0.416015625,
      "learning_rate": 1.967429130916411e-05,
      "loss": 0.6087,
      "step": 113
    },
    {
      "epoch": 0.3838383838383838,
      "grad_norm": 0.431640625,
      "learning_rate": 1.966483553946637e-05,
      "loss": 0.6894,
      "step": 114
    },
    {
      "epoch": 0.3838383838383838,
      "eval_loss": 0.6650684475898743,
      "eval_runtime": 8.7352,
      "eval_samples_per_second": 57.24,
      "eval_steps_per_second": 3.663,
      "step": 114
    },
    {
      "epoch": 0.3872053872053872,
      "grad_norm": 0.396484375,
      "learning_rate": 1.9655246807965786e-05,
      "loss": 0.6962,
      "step": 115
    },
    {
      "epoch": 0.39057239057239057,
      "grad_norm": 0.39453125,
      "learning_rate": 1.9645525246577168e-05,
      "loss": 0.6614,
      "step": 116
    },
    {
      "epoch": 0.3939393939393939,
      "grad_norm": 0.427734375,
      "learning_rate": 1.963567098904272e-05,
      "loss": 0.6889,
      "step": 117
    },
    {
      "epoch": 0.39730639730639733,
      "grad_norm": 0.357421875,
      "learning_rate": 1.9625684170930172e-05,
      "loss": 0.642,
      "step": 118
    },
    {
      "epoch": 0.4006734006734007,
      "grad_norm": 0.3828125,
      "learning_rate": 1.9615564929630925e-05,
      "loss": 0.6185,
      "step": 119
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 0.396484375,
      "learning_rate": 1.9605313404358176e-05,
      "loss": 0.6624,
      "step": 120
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 0.390625,
      "learning_rate": 1.9594929736144978e-05,
      "loss": 0.6632,
      "step": 121
    },
    {
      "epoch": 0.4107744107744108,
      "grad_norm": 0.51953125,
      "learning_rate": 1.9584414067842304e-05,
      "loss": 0.6504,
      "step": 122
    },
    {
      "epoch": 0.41414141414141414,
      "grad_norm": 0.44140625,
      "learning_rate": 1.957376654411711e-05,
      "loss": 0.6543,
      "step": 123
    },
    {
      "epoch": 0.4175084175084175,
      "grad_norm": 0.48828125,
      "learning_rate": 1.9562987311450298e-05,
      "loss": 0.626,
      "step": 124
    },
    {
      "epoch": 0.4208754208754209,
      "grad_norm": 0.38671875,
      "learning_rate": 1.955207651813475e-05,
      "loss": 0.7022,
      "step": 125
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 0.34765625,
      "learning_rate": 1.954103431427325e-05,
      "loss": 0.6574,
      "step": 126
    },
    {
      "epoch": 0.4276094276094276,
      "grad_norm": 0.3984375,
      "learning_rate": 1.952986085177643e-05,
      "loss": 0.6068,
      "step": 127
    },
    {
      "epoch": 0.43097643097643096,
      "grad_norm": 0.380859375,
      "learning_rate": 1.9518556284360696e-05,
      "loss": 0.6538,
      "step": 128
    },
    {
      "epoch": 0.43434343434343436,
      "grad_norm": 0.42578125,
      "learning_rate": 1.950712076754609e-05,
      "loss": 0.7139,
      "step": 129
    },
    {
      "epoch": 0.4377104377104377,
      "grad_norm": 0.42578125,
      "learning_rate": 1.949555445865417e-05,
      "loss": 0.6362,
      "step": 130
    },
    {
      "epoch": 0.44107744107744107,
      "grad_norm": 0.357421875,
      "learning_rate": 1.9483857516805823e-05,
      "loss": 0.6382,
      "step": 131
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.337890625,
      "learning_rate": 1.9472030102919102e-05,
      "loss": 0.6522,
      "step": 132
    },
    {
      "epoch": 0.4478114478114478,
      "grad_norm": 0.390625,
      "learning_rate": 1.9460072379706995e-05,
      "loss": 0.6583,
      "step": 133
    },
    {
      "epoch": 0.4511784511784512,
      "grad_norm": 0.373046875,
      "learning_rate": 1.9447984511675192e-05,
      "loss": 0.6343,
      "step": 134
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.392578125,
      "learning_rate": 1.9435766665119823e-05,
      "loss": 0.6442,
      "step": 135
    },
    {
      "epoch": 0.45791245791245794,
      "grad_norm": 0.375,
      "learning_rate": 1.942341900812516e-05,
      "loss": 0.6286,
      "step": 136
    },
    {
      "epoch": 0.4612794612794613,
      "grad_norm": 0.427734375,
      "learning_rate": 1.9410941710561323e-05,
      "loss": 0.6596,
      "step": 137
    },
    {
      "epoch": 0.46464646464646464,
      "grad_norm": 0.423828125,
      "learning_rate": 1.939833494408193e-05,
      "loss": 0.6632,
      "step": 138
    },
    {
      "epoch": 0.468013468013468,
      "grad_norm": 0.349609375,
      "learning_rate": 1.9385598882121735e-05,
      "loss": 0.6525,
      "step": 139
    },
    {
      "epoch": 0.4713804713804714,
      "grad_norm": 0.431640625,
      "learning_rate": 1.9372733699894253e-05,
      "loss": 0.6136,
      "step": 140
    },
    {
      "epoch": 0.47474747474747475,
      "grad_norm": 0.37109375,
      "learning_rate": 1.935973957438933e-05,
      "loss": 0.6908,
      "step": 141
    },
    {
      "epoch": 0.4781144781144781,
      "grad_norm": 0.341796875,
      "learning_rate": 1.934661668437073e-05,
      "loss": 0.6374,
      "step": 142
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 0.37890625,
      "learning_rate": 1.9333365210373668e-05,
      "loss": 0.6386,
      "step": 143
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.3828125,
      "learning_rate": 1.9319985334702315e-05,
      "loss": 0.6775,
      "step": 144
    },
    {
      "epoch": 0.4882154882154882,
      "grad_norm": 0.400390625,
      "learning_rate": 1.9306477241427303e-05,
      "loss": 0.6006,
      "step": 145
    },
    {
      "epoch": 0.49158249158249157,
      "grad_norm": 0.37890625,
      "learning_rate": 1.9292841116383192e-05,
      "loss": 0.6123,
      "step": 146
    },
    {
      "epoch": 0.494949494949495,
      "grad_norm": 0.416015625,
      "learning_rate": 1.9279077147165903e-05,
      "loss": 0.6198,
      "step": 147
    },
    {
      "epoch": 0.4983164983164983,
      "grad_norm": 0.365234375,
      "learning_rate": 1.9265185523130156e-05,
      "loss": 0.624,
      "step": 148
    },
    {
      "epoch": 0.5016835016835017,
      "grad_norm": 0.337890625,
      "learning_rate": 1.9251166435386837e-05,
      "loss": 0.6348,
      "step": 149
    },
    {
      "epoch": 0.5050505050505051,
      "grad_norm": 0.361328125,
      "learning_rate": 1.9237020076800407e-05,
      "loss": 0.6379,
      "step": 150
    },
    {
      "epoch": 0.5084175084175084,
      "grad_norm": 0.3828125,
      "learning_rate": 1.9222746641986207e-05,
      "loss": 0.6065,
      "step": 151
    },
    {
      "epoch": 0.5117845117845118,
      "grad_norm": 0.419921875,
      "learning_rate": 1.920834632730781e-05,
      "loss": 0.6137,
      "step": 152
    },
    {
      "epoch": 0.5117845117845118,
      "eval_loss": 0.6364830732345581,
      "eval_runtime": 8.689,
      "eval_samples_per_second": 57.544,
      "eval_steps_per_second": 3.683,
      "step": 152
    },
    {
      "epoch": 0.5151515151515151,
      "grad_norm": 0.365234375,
      "learning_rate": 1.919381933087431e-05,
      "loss": 0.6596,
      "step": 153
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 0.38671875,
      "learning_rate": 1.9179165852537596e-05,
      "loss": 0.6292,
      "step": 154
    },
    {
      "epoch": 0.5218855218855218,
      "grad_norm": 0.345703125,
      "learning_rate": 1.9164386093889598e-05,
      "loss": 0.6555,
      "step": 155
    },
    {
      "epoch": 0.5252525252525253,
      "grad_norm": 0.376953125,
      "learning_rate": 1.9149480258259535e-05,
      "loss": 0.632,
      "step": 156
    },
    {
      "epoch": 0.5286195286195287,
      "grad_norm": 0.3515625,
      "learning_rate": 1.9134448550711077e-05,
      "loss": 0.644,
      "step": 157
    },
    {
      "epoch": 0.531986531986532,
      "grad_norm": 0.353515625,
      "learning_rate": 1.9119291178039573e-05,
      "loss": 0.6549,
      "step": 158
    },
    {
      "epoch": 0.5353535353535354,
      "grad_norm": 0.330078125,
      "learning_rate": 1.9104008348769164e-05,
      "loss": 0.6572,
      "step": 159
    },
    {
      "epoch": 0.5387205387205387,
      "grad_norm": 0.3515625,
      "learning_rate": 1.9088600273149947e-05,
      "loss": 0.6284,
      "step": 160
    },
    {
      "epoch": 0.5420875420875421,
      "grad_norm": 0.5,
      "learning_rate": 1.907306716315505e-05,
      "loss": 0.6495,
      "step": 161
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.357421875,
      "learning_rate": 1.905740923247775e-05,
      "loss": 0.6357,
      "step": 162
    },
    {
      "epoch": 0.5488215488215489,
      "grad_norm": 0.349609375,
      "learning_rate": 1.9041626696528503e-05,
      "loss": 0.6188,
      "step": 163
    },
    {
      "epoch": 0.5521885521885522,
      "grad_norm": 0.34375,
      "learning_rate": 1.9025719772432006e-05,
      "loss": 0.6142,
      "step": 164
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.337890625,
      "learning_rate": 1.900968867902419e-05,
      "loss": 0.6339,
      "step": 165
    },
    {
      "epoch": 0.5589225589225589,
      "grad_norm": 0.412109375,
      "learning_rate": 1.8993533636849223e-05,
      "loss": 0.6067,
      "step": 166
    },
    {
      "epoch": 0.5622895622895623,
      "grad_norm": 0.494140625,
      "learning_rate": 1.8977254868156465e-05,
      "loss": 0.5849,
      "step": 167
    },
    {
      "epoch": 0.5656565656565656,
      "grad_norm": 0.31640625,
      "learning_rate": 1.896085259689741e-05,
      "loss": 0.6083,
      "step": 168
    },
    {
      "epoch": 0.569023569023569,
      "grad_norm": 0.3984375,
      "learning_rate": 1.8944327048722634e-05,
      "loss": 0.6319,
      "step": 169
    },
    {
      "epoch": 0.5723905723905723,
      "grad_norm": 0.4375,
      "learning_rate": 1.892767845097864e-05,
      "loss": 0.6299,
      "step": 170
    },
    {
      "epoch": 0.5757575757575758,
      "grad_norm": 0.302734375,
      "learning_rate": 1.891090703270477e-05,
      "loss": 0.5819,
      "step": 171
    },
    {
      "epoch": 0.5791245791245792,
      "grad_norm": 0.34375,
      "learning_rate": 1.889401302463005e-05,
      "loss": 0.6166,
      "step": 172
    },
    {
      "epoch": 0.5824915824915825,
      "grad_norm": 0.392578125,
      "learning_rate": 1.887699665916999e-05,
      "loss": 0.605,
      "step": 173
    },
    {
      "epoch": 0.5858585858585859,
      "grad_norm": 0.33984375,
      "learning_rate": 1.8859858170423423e-05,
      "loss": 0.6573,
      "step": 174
    },
    {
      "epoch": 0.5892255892255892,
      "grad_norm": 0.34375,
      "learning_rate": 1.8842597794169245e-05,
      "loss": 0.5891,
      "step": 175
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.359375,
      "learning_rate": 1.8825215767863215e-05,
      "loss": 0.6383,
      "step": 176
    },
    {
      "epoch": 0.5959595959595959,
      "grad_norm": 0.30859375,
      "learning_rate": 1.8807712330634645e-05,
      "loss": 0.5958,
      "step": 177
    },
    {
      "epoch": 0.5993265993265994,
      "grad_norm": 0.3671875,
      "learning_rate": 1.879008772328314e-05,
      "loss": 0.5791,
      "step": 178
    },
    {
      "epoch": 0.6026936026936027,
      "grad_norm": 0.37890625,
      "learning_rate": 1.877234218827528e-05,
      "loss": 0.6294,
      "step": 179
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.40625,
      "learning_rate": 1.8754475969741272e-05,
      "loss": 0.5971,
      "step": 180
    },
    {
      "epoch": 0.6094276094276094,
      "grad_norm": 0.34375,
      "learning_rate": 1.87364893134716e-05,
      "loss": 0.6078,
      "step": 181
    },
    {
      "epoch": 0.6127946127946128,
      "grad_norm": 0.326171875,
      "learning_rate": 1.8718382466913642e-05,
      "loss": 0.6115,
      "step": 182
    },
    {
      "epoch": 0.6161616161616161,
      "grad_norm": 0.3515625,
      "learning_rate": 1.8700155679168277e-05,
      "loss": 0.6263,
      "step": 183
    },
    {
      "epoch": 0.6195286195286195,
      "grad_norm": 0.365234375,
      "learning_rate": 1.868180920098644e-05,
      "loss": 0.5933,
      "step": 184
    },
    {
      "epoch": 0.622895622895623,
      "grad_norm": 0.419921875,
      "learning_rate": 1.866334328476568e-05,
      "loss": 0.6371,
      "step": 185
    },
    {
      "epoch": 0.6262626262626263,
      "grad_norm": 0.333984375,
      "learning_rate": 1.864475818454669e-05,
      "loss": 0.6314,
      "step": 186
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 0.302734375,
      "learning_rate": 1.8626054156009807e-05,
      "loss": 0.6802,
      "step": 187
    },
    {
      "epoch": 0.632996632996633,
      "grad_norm": 0.359375,
      "learning_rate": 1.8607231456471505e-05,
      "loss": 0.6189,
      "step": 188
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 0.337890625,
      "learning_rate": 1.858829034488084e-05,
      "loss": 0.5987,
      "step": 189
    },
    {
      "epoch": 0.6397306397306397,
      "grad_norm": 0.328125,
      "learning_rate": 1.8569231081815895e-05,
      "loss": 0.6492,
      "step": 190
    },
    {
      "epoch": 0.6397306397306397,
      "eval_loss": 0.6246641874313354,
      "eval_runtime": 8.7145,
      "eval_samples_per_second": 57.375,
      "eval_steps_per_second": 3.672,
      "step": 190
    },
    {
      "epoch": 0.6430976430976431,
      "grad_norm": 0.326171875,
      "learning_rate": 1.8550053929480202e-05,
      "loss": 0.6198,
      "step": 191
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 0.330078125,
      "learning_rate": 1.8530759151699122e-05,
      "loss": 0.6253,
      "step": 192
    },
    {
      "epoch": 0.6498316498316499,
      "grad_norm": 0.330078125,
      "learning_rate": 1.8511347013916228e-05,
      "loss": 0.5804,
      "step": 193
    },
    {
      "epoch": 0.6531986531986532,
      "grad_norm": 0.3671875,
      "learning_rate": 1.8491817783189636e-05,
      "loss": 0.5909,
      "step": 194
    },
    {
      "epoch": 0.6565656565656566,
      "grad_norm": 0.3359375,
      "learning_rate": 1.8472171728188356e-05,
      "loss": 0.5996,
      "step": 195
    },
    {
      "epoch": 0.6599326599326599,
      "grad_norm": 0.357421875,
      "learning_rate": 1.845240911918857e-05,
      "loss": 0.6401,
      "step": 196
    },
    {
      "epoch": 0.6632996632996633,
      "grad_norm": 0.34375,
      "learning_rate": 1.843253022806993e-05,
      "loss": 0.6576,
      "step": 197
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.30859375,
      "learning_rate": 1.8412535328311813e-05,
      "loss": 0.5715,
      "step": 198
    },
    {
      "epoch": 0.67003367003367,
      "grad_norm": 0.3203125,
      "learning_rate": 1.839242469498956e-05,
      "loss": 0.5988,
      "step": 199
    },
    {
      "epoch": 0.6734006734006734,
      "grad_norm": 0.31640625,
      "learning_rate": 1.837219860477069e-05,
      "loss": 0.5796,
      "step": 200
    },
    {
      "epoch": 0.6767676767676768,
      "grad_norm": 0.33984375,
      "learning_rate": 1.8351857335911094e-05,
      "loss": 0.6329,
      "step": 201
    },
    {
      "epoch": 0.6801346801346801,
      "grad_norm": 0.330078125,
      "learning_rate": 1.83314011682512e-05,
      "loss": 0.6374,
      "step": 202
    },
    {
      "epoch": 0.6835016835016835,
      "grad_norm": 0.3125,
      "learning_rate": 1.831083038321215e-05,
      "loss": 0.6235,
      "step": 203
    },
    {
      "epoch": 0.6868686868686869,
      "grad_norm": 0.349609375,
      "learning_rate": 1.8290145263791883e-05,
      "loss": 0.621,
      "step": 204
    },
    {
      "epoch": 0.6902356902356902,
      "grad_norm": 0.359375,
      "learning_rate": 1.826934609456129e-05,
      "loss": 0.6396,
      "step": 205
    },
    {
      "epoch": 0.6936026936026936,
      "grad_norm": 0.337890625,
      "learning_rate": 1.824843316166026e-05,
      "loss": 0.6197,
      "step": 206
    },
    {
      "epoch": 0.696969696969697,
      "grad_norm": 0.361328125,
      "learning_rate": 1.822740675279377e-05,
      "loss": 0.6473,
      "step": 207
    },
    {
      "epoch": 0.7003367003367004,
      "grad_norm": 0.34375,
      "learning_rate": 1.8206267157227918e-05,
      "loss": 0.6227,
      "step": 208
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 0.330078125,
      "learning_rate": 1.8185014665785936e-05,
      "loss": 0.6009,
      "step": 209
    },
    {
      "epoch": 0.7070707070707071,
      "grad_norm": 0.353515625,
      "learning_rate": 1.8163649570844198e-05,
      "loss": 0.592,
      "step": 210
    },
    {
      "epoch": 0.7104377104377104,
      "grad_norm": 0.376953125,
      "learning_rate": 1.8142172166328198e-05,
      "loss": 0.6063,
      "step": 211
    },
    {
      "epoch": 0.7138047138047138,
      "grad_norm": 0.34765625,
      "learning_rate": 1.8120582747708503e-05,
      "loss": 0.6315,
      "step": 212
    },
    {
      "epoch": 0.7171717171717171,
      "grad_norm": 0.36328125,
      "learning_rate": 1.809888161199668e-05,
      "loss": 0.6297,
      "step": 213
    },
    {
      "epoch": 0.7205387205387206,
      "grad_norm": 0.349609375,
      "learning_rate": 1.8077069057741235e-05,
      "loss": 0.6079,
      "step": 214
    },
    {
      "epoch": 0.7239057239057239,
      "grad_norm": 0.318359375,
      "learning_rate": 1.8055145385023477e-05,
      "loss": 0.6192,
      "step": 215
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.326171875,
      "learning_rate": 1.803311089545341e-05,
      "loss": 0.6104,
      "step": 216
    },
    {
      "epoch": 0.7306397306397306,
      "grad_norm": 0.3359375,
      "learning_rate": 1.8010965892165568e-05,
      "loss": 0.6166,
      "step": 217
    },
    {
      "epoch": 0.734006734006734,
      "grad_norm": 0.361328125,
      "learning_rate": 1.7988710679814857e-05,
      "loss": 0.6145,
      "step": 218
    },
    {
      "epoch": 0.7373737373737373,
      "grad_norm": 0.32421875,
      "learning_rate": 1.796634556457236e-05,
      "loss": 0.5994,
      "step": 219
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.34765625,
      "learning_rate": 1.7943870854121126e-05,
      "loss": 0.586,
      "step": 220
    },
    {
      "epoch": 0.7441077441077442,
      "grad_norm": 0.32421875,
      "learning_rate": 1.792128685765193e-05,
      "loss": 0.582,
      "step": 221
    },
    {
      "epoch": 0.7474747474747475,
      "grad_norm": 0.337890625,
      "learning_rate": 1.789859388585903e-05,
      "loss": 0.6017,
      "step": 222
    },
    {
      "epoch": 0.7508417508417509,
      "grad_norm": 0.36328125,
      "learning_rate": 1.7875792250935883e-05,
      "loss": 0.5864,
      "step": 223
    },
    {
      "epoch": 0.7542087542087542,
      "grad_norm": 0.373046875,
      "learning_rate": 1.785288226657086e-05,
      "loss": 0.5869,
      "step": 224
    },
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 0.3203125,
      "learning_rate": 1.782986424794292e-05,
      "loss": 0.6448,
      "step": 225
    }
  ],
  "logging_steps": 1,
  "max_steps": 891,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 75,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.09313017331712e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}