{
  "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": 2.2727272727272729e-07,
      "loss": 1.0833,
      "step": 1
    },
    {
      "epoch": 0.003367003367003367,
      "eval_loss": 1.032954454421997,
      "eval_runtime": 8.7985,
      "eval_samples_per_second": 56.828,
      "eval_steps_per_second": 3.637,
      "step": 1
    },
    {
      "epoch": 0.006734006734006734,
      "grad_norm": 2.265625,
      "learning_rate": 4.5454545454545457e-07,
      "loss": 0.996,
      "step": 2
    },
    {
      "epoch": 0.010101010101010102,
      "grad_norm": 1.640625,
      "learning_rate": 6.818181818181818e-07,
      "loss": 1.0489,
      "step": 3
    },
    {
      "epoch": 0.013468013468013467,
      "grad_norm": 2.0625,
      "learning_rate": 9.090909090909091e-07,
      "loss": 1.0546,
      "step": 4
    },
    {
      "epoch": 0.016835016835016835,
      "grad_norm": 2.453125,
      "learning_rate": 1.1363636363636364e-06,
      "loss": 1.0341,
      "step": 5
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 1.9921875,
      "learning_rate": 1.3636363636363636e-06,
      "loss": 1.0136,
      "step": 6
    },
    {
      "epoch": 0.02356902356902357,
      "grad_norm": 2.640625,
      "learning_rate": 1.590909090909091e-06,
      "loss": 1.0305,
      "step": 7
    },
    {
      "epoch": 0.026936026936026935,
      "grad_norm": 2.359375,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 1.0226,
      "step": 8
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 2.3125,
      "learning_rate": 2.0454545454545457e-06,
      "loss": 1.0745,
      "step": 9
    },
    {
      "epoch": 0.03367003367003367,
      "grad_norm": 2.359375,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 1.0232,
      "step": 10
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 2.53125,
      "learning_rate": 2.5e-06,
      "loss": 1.0106,
      "step": 11
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 2.125,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 1.0541,
      "step": 12
    },
    {
      "epoch": 0.04377104377104377,
      "grad_norm": 2.15625,
      "learning_rate": 2.954545454545455e-06,
      "loss": 1.0693,
      "step": 13
    },
    {
      "epoch": 0.04713804713804714,
      "grad_norm": 1.8359375,
      "learning_rate": 3.181818181818182e-06,
      "loss": 1.0338,
      "step": 14
    },
    {
      "epoch": 0.050505050505050504,
      "grad_norm": 2.0,
      "learning_rate": 3.409090909090909e-06,
      "loss": 1.0464,
      "step": 15
    },
    {
      "epoch": 0.05387205387205387,
      "grad_norm": 2.34375,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 1.0684,
      "step": 16
    },
    {
      "epoch": 0.05723905723905724,
      "grad_norm": 1.8125,
      "learning_rate": 3.863636363636364e-06,
      "loss": 1.0117,
      "step": 17
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 1.90625,
      "learning_rate": 4.0909090909090915e-06,
      "loss": 1.0138,
      "step": 18
    },
    {
      "epoch": 0.06397306397306397,
      "grad_norm": 1.59375,
      "learning_rate": 4.3181818181818185e-06,
      "loss": 0.9873,
      "step": 19
    },
    {
      "epoch": 0.06734006734006734,
      "grad_norm": 1.59375,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 1.0524,
      "step": 20
    },
    {
      "epoch": 0.0707070707070707,
      "grad_norm": 1.3984375,
      "learning_rate": 4.772727272727273e-06,
      "loss": 1.0479,
      "step": 21
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 1.609375,
      "learning_rate": 5e-06,
      "loss": 0.9894,
      "step": 22
    },
    {
      "epoch": 0.07744107744107744,
      "grad_norm": 1.3671875,
      "learning_rate": 5.2272727272727274e-06,
      "loss": 0.983,
      "step": 23
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 1.6328125,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 1.0563,
      "step": 24
    },
    {
      "epoch": 0.08417508417508418,
      "grad_norm": 1.34375,
      "learning_rate": 5.681818181818183e-06,
      "loss": 0.9966,
      "step": 25
    },
    {
      "epoch": 0.08754208754208755,
      "grad_norm": 1.25,
      "learning_rate": 5.90909090909091e-06,
      "loss": 0.9922,
      "step": 26
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 1.3984375,
      "learning_rate": 6.136363636363637e-06,
      "loss": 1.0677,
      "step": 27
    },
    {
      "epoch": 0.09427609427609428,
      "grad_norm": 1.3828125,
      "learning_rate": 6.363636363636364e-06,
      "loss": 1.0325,
      "step": 28
    },
    {
      "epoch": 0.09764309764309764,
      "grad_norm": 1.1953125,
      "learning_rate": 6.590909090909091e-06,
      "loss": 1.0159,
      "step": 29
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 1.3125,
      "learning_rate": 6.818181818181818e-06,
      "loss": 1.0384,
      "step": 30
    },
    {
      "epoch": 0.10437710437710437,
      "grad_norm": 1.1171875,
      "learning_rate": 7.045454545454546e-06,
      "loss": 0.9949,
      "step": 31
    },
    {
      "epoch": 0.10774410774410774,
      "grad_norm": 1.2421875,
      "learning_rate": 7.272727272727273e-06,
      "loss": 1.0284,
      "step": 32
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 1.15625,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.0245,
      "step": 33
    },
    {
      "epoch": 0.11447811447811448,
      "grad_norm": 1.1875,
      "learning_rate": 7.727272727272727e-06,
      "loss": 1.0103,
      "step": 34
    },
    {
      "epoch": 0.11784511784511785,
      "grad_norm": 1.125,
      "learning_rate": 7.954545454545455e-06,
      "loss": 1.0129,
      "step": 35
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 1.03125,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.965,
      "step": 36
    },
    {
      "epoch": 0.12457912457912458,
      "grad_norm": 1.109375,
      "learning_rate": 8.40909090909091e-06,
      "loss": 1.0027,
      "step": 37
    },
    {
      "epoch": 0.12794612794612795,
      "grad_norm": 1.0859375,
      "learning_rate": 8.636363636363637e-06,
      "loss": 1.0093,
      "step": 38
    },
    {
      "epoch": 0.12794612794612795,
      "eval_loss": 0.9909602999687195,
      "eval_runtime": 8.9064,
      "eval_samples_per_second": 56.139,
      "eval_steps_per_second": 3.593,
      "step": 38
    },
    {
      "epoch": 0.13131313131313133,
      "grad_norm": 0.96484375,
      "learning_rate": 8.863636363636365e-06,
      "loss": 0.98,
      "step": 39
    },
    {
      "epoch": 0.13468013468013468,
      "grad_norm": 1.0078125,
      "learning_rate": 9.090909090909091e-06,
      "loss": 1.0,
      "step": 40
    },
    {
      "epoch": 0.13804713804713806,
      "grad_norm": 1.109375,
      "learning_rate": 9.318181818181819e-06,
      "loss": 0.9658,
      "step": 41
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": 0.95703125,
      "learning_rate": 9.545454545454547e-06,
      "loss": 0.9656,
      "step": 42
    },
    {
      "epoch": 0.1447811447811448,
      "grad_norm": 1.0,
      "learning_rate": 9.772727272727273e-06,
      "loss": 0.9528,
      "step": 43
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.88671875,
      "learning_rate": 1e-05,
      "loss": 0.9546,
      "step": 44
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 0.984375,
      "learning_rate": 9.999965606811854e-06,
      "loss": 0.9406,
      "step": 45
    },
    {
      "epoch": 0.15488215488215487,
      "grad_norm": 1.0625,
      "learning_rate": 9.99986242772057e-06,
      "loss": 0.9975,
      "step": 46
    },
    {
      "epoch": 0.15824915824915825,
      "grad_norm": 0.94140625,
      "learning_rate": 9.99969046414561e-06,
      "loss": 0.9567,
      "step": 47
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 0.96484375,
      "learning_rate": 9.999449718452724e-06,
      "loss": 0.9707,
      "step": 48
    },
    {
      "epoch": 0.16498316498316498,
      "grad_norm": 1.0,
      "learning_rate": 9.999140193953923e-06,
      "loss": 0.9559,
      "step": 49
    },
    {
      "epoch": 0.16835016835016836,
      "grad_norm": 0.99609375,
      "learning_rate": 9.998761894907414e-06,
      "loss": 0.9398,
      "step": 50
    },
    {
      "epoch": 0.1717171717171717,
      "grad_norm": 0.83203125,
      "learning_rate": 9.998314826517564e-06,
      "loss": 0.9329,
      "step": 51
    },
    {
      "epoch": 0.1750841750841751,
      "grad_norm": 0.91015625,
      "learning_rate": 9.997798994934812e-06,
      "loss": 0.9478,
      "step": 52
    },
    {
      "epoch": 0.17845117845117844,
      "grad_norm": 0.94140625,
      "learning_rate": 9.997214407255602e-06,
      "loss": 0.9062,
      "step": 53
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.83203125,
      "learning_rate": 9.996561071522264e-06,
      "loss": 0.9089,
      "step": 54
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 1.0078125,
      "learning_rate": 9.995838996722916e-06,
      "loss": 0.9561,
      "step": 55
    },
    {
      "epoch": 0.18855218855218855,
      "grad_norm": 0.796875,
      "learning_rate": 9.995048192791341e-06,
      "loss": 0.8948,
      "step": 56
    },
    {
      "epoch": 0.1919191919191919,
      "grad_norm": 0.91796875,
      "learning_rate": 9.994188670606845e-06,
      "loss": 0.9095,
      "step": 57
    },
    {
      "epoch": 0.19528619528619529,
      "grad_norm": 0.8515625,
      "learning_rate": 9.993260441994116e-06,
      "loss": 0.9137,
      "step": 58
    },
    {
      "epoch": 0.19865319865319866,
      "grad_norm": 0.8671875,
      "learning_rate": 9.992263519723046e-06,
      "loss": 0.9012,
      "step": 59
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 0.8046875,
      "learning_rate": 9.99119791750857e-06,
      "loss": 0.9074,
      "step": 60
    },
    {
      "epoch": 0.2053872053872054,
      "grad_norm": 1.0859375,
      "learning_rate": 9.990063650010473e-06,
      "loss": 0.9106,
      "step": 61
    },
    {
      "epoch": 0.20875420875420875,
      "grad_norm": 1.0625,
      "learning_rate": 9.988860732833183e-06,
      "loss": 0.9012,
      "step": 62
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 0.93359375,
      "learning_rate": 9.987589182525562e-06,
      "loss": 0.8928,
      "step": 63
    },
    {
      "epoch": 0.21548821548821548,
      "grad_norm": 0.921875,
      "learning_rate": 9.98624901658068e-06,
      "loss": 0.9487,
      "step": 64
    },
    {
      "epoch": 0.21885521885521886,
      "grad_norm": 0.92578125,
      "learning_rate": 9.984840253435569e-06,
      "loss": 0.8887,
      "step": 65
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.8671875,
      "learning_rate": 9.983362912470967e-06,
      "loss": 0.9152,
      "step": 66
    },
    {
      "epoch": 0.2255892255892256,
      "grad_norm": 0.83984375,
      "learning_rate": 9.981817014011066e-06,
      "loss": 0.8849,
      "step": 67
    },
    {
      "epoch": 0.22895622895622897,
      "grad_norm": 0.94921875,
      "learning_rate": 9.980202579323212e-06,
      "loss": 0.9386,
      "step": 68
    },
    {
      "epoch": 0.23232323232323232,
      "grad_norm": 0.8203125,
      "learning_rate": 9.978519630617632e-06,
      "loss": 0.8651,
      "step": 69
    },
    {
      "epoch": 0.2356902356902357,
      "grad_norm": 0.7109375,
      "learning_rate": 9.976768191047109e-06,
      "loss": 0.9044,
      "step": 70
    },
    {
      "epoch": 0.23905723905723905,
      "grad_norm": 1.03125,
      "learning_rate": 9.974948284706684e-06,
      "loss": 0.8702,
      "step": 71
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.91796875,
      "learning_rate": 9.973059936633308e-06,
      "loss": 0.8748,
      "step": 72
    },
    {
      "epoch": 0.24579124579124578,
      "grad_norm": 0.66796875,
      "learning_rate": 9.971103172805504e-06,
      "loss": 0.8443,
      "step": 73
    },
    {
      "epoch": 0.24915824915824916,
      "grad_norm": 0.671875,
      "learning_rate": 9.969078020143013e-06,
      "loss": 0.8605,
      "step": 74
    },
    {
      "epoch": 0.25252525252525254,
      "grad_norm": 0.6796875,
      "learning_rate": 9.966984506506415e-06,
      "loss": 0.8661,
      "step": 75
    },
    {
      "epoch": 0.2558922558922559,
      "grad_norm": 0.953125,
      "learning_rate": 9.964822660696753e-06,
      "loss": 0.9169,
      "step": 76
    },
    {
      "epoch": 0.2558922558922559,
      "eval_loss": 0.8667835593223572,
      "eval_runtime": 8.6819,
      "eval_samples_per_second": 57.591,
      "eval_steps_per_second": 3.686,
      "step": 76
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 0.86328125,
      "learning_rate": 9.96259251245514e-06,
      "loss": 0.8719,
      "step": 77
    },
    {
      "epoch": 0.26262626262626265,
      "grad_norm": 0.66796875,
      "learning_rate": 9.960294092462332e-06,
      "loss": 0.8438,
      "step": 78
    },
    {
      "epoch": 0.265993265993266,
      "grad_norm": 0.66796875,
      "learning_rate": 9.957927432338332e-06,
      "loss": 0.8723,
      "step": 79
    },
    {
      "epoch": 0.26936026936026936,
      "grad_norm": 1.3828125,
      "learning_rate": 9.95549256464193e-06,
      "loss": 0.8987,
      "step": 80
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.69921875,
      "learning_rate": 9.952989522870275e-06,
      "loss": 0.8188,
      "step": 81
    },
    {
      "epoch": 0.2760942760942761,
      "grad_norm": 0.9375,
      "learning_rate": 9.950418341458398e-06,
      "loss": 0.8521,
      "step": 82
    },
    {
      "epoch": 0.27946127946127947,
      "grad_norm": 0.828125,
      "learning_rate": 9.947779055778752e-06,
      "loss": 0.8305,
      "step": 83
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 0.9453125,
      "learning_rate": 9.945071702140716e-06,
      "loss": 0.856,
      "step": 84
    },
    {
      "epoch": 0.28619528619528617,
      "grad_norm": 0.609375,
      "learning_rate": 9.9422963177901e-06,
      "loss": 0.8512,
      "step": 85
    },
    {
      "epoch": 0.2895622895622896,
      "grad_norm": 1.546875,
      "learning_rate": 9.939452940908627e-06,
      "loss": 0.818,
      "step": 86
    },
    {
      "epoch": 0.29292929292929293,
      "grad_norm": 0.640625,
      "learning_rate": 9.936541610613417e-06,
      "loss": 0.8071,
      "step": 87
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.82421875,
      "learning_rate": 9.933562366956445e-06,
      "loss": 0.8559,
      "step": 88
    },
    {
      "epoch": 0.2996632996632997,
      "grad_norm": 1.046875,
      "learning_rate": 9.930515250923985e-06,
      "loss": 0.8646,
      "step": 89
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 0.76953125,
      "learning_rate": 9.927400304436048e-06,
      "loss": 0.8179,
      "step": 90
    },
    {
      "epoch": 0.3063973063973064,
      "grad_norm": 1.09375,
      "learning_rate": 9.924217570345814e-06,
      "loss": 0.8093,
      "step": 91
    },
    {
      "epoch": 0.30976430976430974,
      "grad_norm": 0.6015625,
      "learning_rate": 9.920967092439028e-06,
      "loss": 0.8073,
      "step": 92
    },
    {
      "epoch": 0.31313131313131315,
      "grad_norm": 0.84375,
      "learning_rate": 9.917648915433413e-06,
      "loss": 0.9031,
      "step": 93
    },
    {
      "epoch": 0.3164983164983165,
      "grad_norm": 0.76171875,
      "learning_rate": 9.914263084978041e-06,
      "loss": 0.8568,
      "step": 94
    },
    {
      "epoch": 0.31986531986531985,
      "grad_norm": 0.8671875,
      "learning_rate": 9.910809647652716e-06,
      "loss": 0.7819,
      "step": 95
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 0.84765625,
      "learning_rate": 9.907288650967324e-06,
      "loss": 0.8236,
      "step": 96
    },
    {
      "epoch": 0.3265993265993266,
      "grad_norm": 0.70703125,
      "learning_rate": 9.903700143361185e-06,
      "loss": 0.8418,
      "step": 97
    },
    {
      "epoch": 0.32996632996632996,
      "grad_norm": 0.94921875,
      "learning_rate": 9.900044174202389e-06,
      "loss": 0.8313,
      "step": 98
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.8125,
      "learning_rate": 9.896320793787106e-06,
      "loss": 0.8158,
      "step": 99
    },
    {
      "epoch": 0.3367003367003367,
      "grad_norm": 0.76171875,
      "learning_rate": 9.892530053338909e-06,
      "loss": 0.7956,
      "step": 100
    },
    {
      "epoch": 0.3400673400673401,
      "grad_norm": 0.94921875,
      "learning_rate": 9.888672005008054e-06,
      "loss": 0.8154,
      "step": 101
    },
    {
      "epoch": 0.3434343434343434,
      "grad_norm": 0.6328125,
      "learning_rate": 9.884746701870778e-06,
      "loss": 0.8322,
      "step": 102
    },
    {
      "epoch": 0.3468013468013468,
      "grad_norm": 0.62890625,
      "learning_rate": 9.880754197928553e-06,
      "loss": 0.8133,
      "step": 103
    },
    {
      "epoch": 0.3501683501683502,
      "grad_norm": 0.76953125,
      "learning_rate": 9.876694548107358e-06,
      "loss": 0.7882,
      "step": 104
    },
    {
      "epoch": 0.35353535353535354,
      "grad_norm": 1.03125,
      "learning_rate": 9.87256780825691e-06,
      "loss": 0.8264,
      "step": 105
    },
    {
      "epoch": 0.3569023569023569,
      "grad_norm": 0.7421875,
      "learning_rate": 9.868374035149906e-06,
      "loss": 0.7894,
      "step": 106
    },
    {
      "epoch": 0.3602693602693603,
      "grad_norm": 0.6171875,
      "learning_rate": 9.864113286481237e-06,
      "loss": 0.7807,
      "step": 107
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 1.015625,
      "learning_rate": 9.859785620867197e-06,
      "loss": 0.7895,
      "step": 108
    },
    {
      "epoch": 0.367003367003367,
      "grad_norm": 1.0625,
      "learning_rate": 9.855391097844671e-06,
      "loss": 0.7936,
      "step": 109
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.8984375,
      "learning_rate": 9.850929777870324e-06,
      "loss": 0.8024,
      "step": 110
    },
    {
      "epoch": 0.37373737373737376,
      "grad_norm": 0.6640625,
      "learning_rate": 9.846401722319759e-06,
      "loss": 0.7542,
      "step": 111
    },
    {
      "epoch": 0.3771043771043771,
      "grad_norm": 1.1640625,
      "learning_rate": 9.841806993486686e-06,
      "loss": 0.7689,
      "step": 112
    },
    {
      "epoch": 0.38047138047138046,
      "grad_norm": 0.765625,
      "learning_rate": 9.837145654582055e-06,
      "loss": 0.7133,
      "step": 113
    },
    {
      "epoch": 0.3838383838383838,
      "grad_norm": 0.87109375,
      "learning_rate": 9.832417769733185e-06,
      "loss": 0.795,
      "step": 114
    },
    {
      "epoch": 0.3838383838383838,
      "eval_loss": 0.7676474452018738,
      "eval_runtime": 8.7789,
      "eval_samples_per_second": 56.955,
      "eval_steps_per_second": 3.645,
      "step": 114
    },
    {
      "epoch": 0.3872053872053872,
      "grad_norm": 0.86328125,
      "learning_rate": 9.827623403982893e-06,
      "loss": 0.7992,
      "step": 115
    },
    {
      "epoch": 0.39057239057239057,
      "grad_norm": 0.7421875,
      "learning_rate": 9.822762623288584e-06,
      "loss": 0.7678,
      "step": 116
    },
    {
      "epoch": 0.3939393939393939,
      "grad_norm": 0.85546875,
      "learning_rate": 9.81783549452136e-06,
      "loss": 0.7861,
      "step": 117
    },
    {
      "epoch": 0.39730639730639733,
      "grad_norm": 0.71484375,
      "learning_rate": 9.812842085465086e-06,
      "loss": 0.7447,
      "step": 118
    },
    {
      "epoch": 0.4006734006734007,
      "grad_norm": 0.5703125,
      "learning_rate": 9.807782464815463e-06,
      "loss": 0.7218,
      "step": 119
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 0.6171875,
      "learning_rate": 9.802656702179088e-06,
      "loss": 0.7637,
      "step": 120
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 0.54296875,
      "learning_rate": 9.797464868072489e-06,
      "loss": 0.7588,
      "step": 121
    },
    {
      "epoch": 0.4107744107744108,
      "grad_norm": 0.6171875,
      "learning_rate": 9.792207033921152e-06,
      "loss": 0.7539,
      "step": 122
    },
    {
      "epoch": 0.41414141414141414,
      "grad_norm": 0.8046875,
      "learning_rate": 9.786883272058554e-06,
      "loss": 0.7524,
      "step": 123
    },
    {
      "epoch": 0.4175084175084175,
      "grad_norm": 0.6953125,
      "learning_rate": 9.781493655725149e-06,
      "loss": 0.731,
      "step": 124
    },
    {
      "epoch": 0.4208754208754209,
      "grad_norm": 0.64453125,
      "learning_rate": 9.776038259067375e-06,
      "loss": 0.8022,
      "step": 125
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 0.48046875,
      "learning_rate": 9.770517157136625e-06,
      "loss": 0.7528,
      "step": 126
    },
    {
      "epoch": 0.4276094276094276,
      "grad_norm": 0.5546875,
      "learning_rate": 9.764930425888216e-06,
      "loss": 0.7037,
      "step": 127
    },
    {
      "epoch": 0.43097643097643096,
      "grad_norm": 0.546875,
      "learning_rate": 9.759278142180348e-06,
      "loss": 0.7519,
      "step": 128
    },
    {
      "epoch": 0.43434343434343436,
      "grad_norm": 0.61328125,
      "learning_rate": 9.753560383773046e-06,
      "loss": 0.8163,
      "step": 129
    },
    {
      "epoch": 0.4377104377104377,
      "grad_norm": 0.53125,
      "learning_rate": 9.747777229327085e-06,
      "loss": 0.7292,
      "step": 130
    },
    {
      "epoch": 0.44107744107744107,
      "grad_norm": 0.58203125,
      "learning_rate": 9.741928758402912e-06,
      "loss": 0.7351,
      "step": 131
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.5234375,
      "learning_rate": 9.736015051459551e-06,
      "loss": 0.7429,
      "step": 132
    },
    {
      "epoch": 0.4478114478114478,
      "grad_norm": 0.65234375,
      "learning_rate": 9.730036189853497e-06,
      "loss": 0.7616,
      "step": 133
    },
    {
      "epoch": 0.4511784511784512,
      "grad_norm": 0.53125,
      "learning_rate": 9.723992255837596e-06,
      "loss": 0.7263,
      "step": 134
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.5546875,
      "learning_rate": 9.717883332559911e-06,
      "loss": 0.7427,
      "step": 135
    },
    {
      "epoch": 0.45791245791245794,
      "grad_norm": 0.66796875,
      "learning_rate": 9.71170950406258e-06,
      "loss": 0.7261,
      "step": 136
    },
    {
      "epoch": 0.4612794612794613,
      "grad_norm": 0.58984375,
      "learning_rate": 9.705470855280661e-06,
      "loss": 0.754,
      "step": 137
    },
    {
      "epoch": 0.46464646464646464,
      "grad_norm": 0.6015625,
      "learning_rate": 9.699167472040965e-06,
      "loss": 0.7554,
      "step": 138
    },
    {
      "epoch": 0.468013468013468,
      "grad_norm": 0.5546875,
      "learning_rate": 9.692799441060868e-06,
      "loss": 0.7488,
      "step": 139
    },
    {
      "epoch": 0.4713804713804714,
      "grad_norm": 0.53125,
      "learning_rate": 9.686366849947126e-06,
      "loss": 0.7066,
      "step": 140
    },
    {
      "epoch": 0.47474747474747475,
      "grad_norm": 0.55078125,
      "learning_rate": 9.679869787194664e-06,
      "loss": 0.7818,
      "step": 141
    },
    {
      "epoch": 0.4781144781144781,
      "grad_norm": 0.4765625,
      "learning_rate": 9.673308342185366e-06,
      "loss": 0.7289,
      "step": 142
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 0.62109375,
      "learning_rate": 9.666682605186834e-06,
      "loss": 0.7301,
      "step": 143
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.54296875,
      "learning_rate": 9.659992667351157e-06,
      "loss": 0.7673,
      "step": 144
    },
    {
      "epoch": 0.4882154882154882,
      "grad_norm": 0.486328125,
      "learning_rate": 9.653238620713652e-06,
      "loss": 0.6884,
      "step": 145
    },
    {
      "epoch": 0.49158249158249157,
      "grad_norm": 0.6484375,
      "learning_rate": 9.646420558191596e-06,
      "loss": 0.7043,
      "step": 146
    },
    {
      "epoch": 0.494949494949495,
      "grad_norm": 0.51171875,
      "learning_rate": 9.639538573582952e-06,
      "loss": 0.7122,
      "step": 147
    },
    {
      "epoch": 0.4983164983164983,
      "grad_norm": 0.498046875,
      "learning_rate": 9.632592761565078e-06,
      "loss": 0.7232,
      "step": 148
    },
    {
      "epoch": 0.5016835016835017,
      "grad_norm": 0.5625,
      "learning_rate": 9.625583217693419e-06,
      "loss": 0.7311,
      "step": 149
    },
    {
      "epoch": 0.5050505050505051,
      "grad_norm": 0.63671875,
      "learning_rate": 9.618510038400203e-06,
      "loss": 0.7322,
      "step": 150
    },
    {
      "epoch": 0.5084175084175084,
      "grad_norm": 0.75390625,
      "learning_rate": 9.611373320993104e-06,
      "loss": 0.6983,
      "step": 151
    },
    {
      "epoch": 0.5117845117845118,
      "grad_norm": 0.53125,
      "learning_rate": 9.604173163653906e-06,
      "loss": 0.6999,
      "step": 152
    },
    {
      "epoch": 0.5117845117845118,
      "eval_loss": 0.7242563366889954,
      "eval_runtime": 8.7081,
      "eval_samples_per_second": 57.418,
      "eval_steps_per_second": 3.675,
      "step": 152
    },
    {
      "epoch": 0.5151515151515151,
      "grad_norm": 0.55859375,
      "learning_rate": 9.596909665437155e-06,
      "loss": 0.7469,
      "step": 153
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 0.5078125,
      "learning_rate": 9.589582926268798e-06,
      "loss": 0.7176,
      "step": 154
    },
    {
      "epoch": 0.5218855218855218,
      "grad_norm": 0.4921875,
      "learning_rate": 9.582193046944799e-06,
      "loss": 0.7455,
      "step": 155
    },
    {
      "epoch": 0.5252525252525253,
      "grad_norm": 0.51171875,
      "learning_rate": 9.574740129129767e-06,
      "loss": 0.7204,
      "step": 156
    },
    {
      "epoch": 0.5286195286195287,
      "grad_norm": 0.474609375,
      "learning_rate": 9.567224275355538e-06,
      "loss": 0.7321,
      "step": 157
    },
    {
      "epoch": 0.531986531986532,
      "grad_norm": 0.53125,
      "learning_rate": 9.559645589019787e-06,
      "loss": 0.7455,
      "step": 158
    },
    {
      "epoch": 0.5353535353535354,
      "grad_norm": 0.494140625,
      "learning_rate": 9.552004174384582e-06,
      "loss": 0.7464,
      "step": 159
    },
    {
      "epoch": 0.5387205387205387,
      "grad_norm": 0.5234375,
      "learning_rate": 9.544300136574973e-06,
      "loss": 0.7138,
      "step": 160
    },
    {
      "epoch": 0.5420875420875421,
      "grad_norm": 0.59375,
      "learning_rate": 9.536533581577526e-06,
      "loss": 0.7321,
      "step": 161
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.57421875,
      "learning_rate": 9.528704616238875e-06,
      "loss": 0.7205,
      "step": 162
    },
    {
      "epoch": 0.5488215488215489,
      "grad_norm": 0.484375,
      "learning_rate": 9.520813348264252e-06,
      "loss": 0.7107,
      "step": 163
    },
    {
      "epoch": 0.5521885521885522,
      "grad_norm": 0.455078125,
      "learning_rate": 9.512859886216003e-06,
      "loss": 0.6975,
      "step": 164
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.46875,
      "learning_rate": 9.504844339512096e-06,
      "loss": 0.7209,
      "step": 165
    },
    {
      "epoch": 0.5589225589225589,
      "grad_norm": 0.50390625,
      "learning_rate": 9.496766818424612e-06,
      "loss": 0.6932,
      "step": 166
    },
    {
      "epoch": 0.5622895622895623,
      "grad_norm": 0.69140625,
      "learning_rate": 9.488627434078232e-06,
      "loss": 0.6676,
      "step": 167
    },
    {
      "epoch": 0.5656565656565656,
      "grad_norm": 0.443359375,
      "learning_rate": 9.480426298448706e-06,
      "loss": 0.6909,
      "step": 168
    },
    {
      "epoch": 0.569023569023569,
      "grad_norm": 0.4609375,
      "learning_rate": 9.472163524361317e-06,
      "loss": 0.7142,
      "step": 169
    },
    {
      "epoch": 0.5723905723905723,
      "grad_norm": 0.474609375,
      "learning_rate": 9.46383922548932e-06,
      "loss": 0.7168,
      "step": 170
    },
    {
      "epoch": 0.5757575757575758,
      "grad_norm": 0.435546875,
      "learning_rate": 9.455453516352385e-06,
      "loss": 0.6618,
      "step": 171
    },
    {
      "epoch": 0.5791245791245792,
      "grad_norm": 0.45703125,
      "learning_rate": 9.447006512315025e-06,
      "loss": 0.694,
      "step": 172
    },
    {
      "epoch": 0.5824915824915825,
      "grad_norm": 0.59765625,
      "learning_rate": 9.438498329584995e-06,
      "loss": 0.6858,
      "step": 173
    },
    {
      "epoch": 0.5858585858585859,
      "grad_norm": 0.48046875,
      "learning_rate": 9.429929085211711e-06,
      "loss": 0.7419,
      "step": 174
    },
    {
      "epoch": 0.5892255892255892,
      "grad_norm": 0.4375,
      "learning_rate": 9.421298897084622e-06,
      "loss": 0.6734,
      "step": 175
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.494140625,
      "learning_rate": 9.412607883931608e-06,
      "loss": 0.7188,
      "step": 176
    },
    {
      "epoch": 0.5959595959595959,
      "grad_norm": 0.41796875,
      "learning_rate": 9.403856165317322e-06,
      "loss": 0.6732,
      "step": 177
    },
    {
      "epoch": 0.5993265993265994,
      "grad_norm": 0.59765625,
      "learning_rate": 9.39504386164157e-06,
      "loss": 0.6594,
      "step": 178
    },
    {
      "epoch": 0.6026936026936027,
      "grad_norm": 0.490234375,
      "learning_rate": 9.38617109413764e-06,
      "loss": 0.7153,
      "step": 179
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.60546875,
      "learning_rate": 9.377237984870636e-06,
      "loss": 0.6762,
      "step": 180
    },
    {
      "epoch": 0.6094276094276094,
      "grad_norm": 0.53125,
      "learning_rate": 9.3682446567358e-06,
      "loss": 0.6839,
      "step": 181
    },
    {
      "epoch": 0.6127946127946128,
      "grad_norm": 0.515625,
      "learning_rate": 9.359191233456821e-06,
      "loss": 0.6949,
      "step": 182
    },
    {
      "epoch": 0.6161616161616161,
      "grad_norm": 0.50390625,
      "learning_rate": 9.350077839584139e-06,
      "loss": 0.7045,
      "step": 183
    },
    {
      "epoch": 0.6195286195286195,
      "grad_norm": 0.42578125,
      "learning_rate": 9.34090460049322e-06,
      "loss": 0.668,
      "step": 184
    },
    {
      "epoch": 0.622895622895623,
      "grad_norm": 0.54296875,
      "learning_rate": 9.33167164238284e-06,
      "loss": 0.7144,
      "step": 185
    },
    {
      "epoch": 0.6262626262626263,
      "grad_norm": 0.44921875,
      "learning_rate": 9.322379092273345e-06,
      "loss": 0.7084,
      "step": 186
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 0.427734375,
      "learning_rate": 9.313027078004903e-06,
      "loss": 0.7555,
      "step": 187
    },
    {
      "epoch": 0.632996632996633,
      "grad_norm": 0.44140625,
      "learning_rate": 9.303615728235753e-06,
      "loss": 0.6963,
      "step": 188
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 0.515625,
      "learning_rate": 9.29414517244042e-06,
      "loss": 0.6785,
      "step": 189
    },
    {
      "epoch": 0.6397306397306397,
      "grad_norm": 0.5078125,
      "learning_rate": 9.284615540907947e-06,
      "loss": 0.7246,
      "step": 190
    },
    {
      "epoch": 0.6397306397306397,
      "eval_loss": 0.6989265084266663,
      "eval_runtime": 8.6934,
      "eval_samples_per_second": 57.515,
      "eval_steps_per_second": 3.681,
      "step": 190
    },
    {
      "epoch": 0.6430976430976431,
      "grad_norm": 0.54296875,
      "learning_rate": 9.275026964740101e-06,
      "loss": 0.6995,
      "step": 191
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 0.427734375,
      "learning_rate": 9.265379575849561e-06,
      "loss": 0.6988,
      "step": 192
    },
    {
      "epoch": 0.6498316498316499,
      "grad_norm": 0.48046875,
      "learning_rate": 9.255673506958114e-06,
      "loss": 0.6569,
      "step": 193
    },
    {
      "epoch": 0.6531986531986532,
      "grad_norm": 0.486328125,
      "learning_rate": 9.245908891594818e-06,
      "loss": 0.6645,
      "step": 194
    },
    {
      "epoch": 0.6565656565656566,
      "grad_norm": 0.58984375,
      "learning_rate": 9.236085864094178e-06,
      "loss": 0.6745,
      "step": 195
    },
    {
      "epoch": 0.6599326599326599,
      "grad_norm": 0.609375,
      "learning_rate": 9.226204559594284e-06,
      "loss": 0.7157,
      "step": 196
    },
    {
      "epoch": 0.6632996632996633,
      "grad_norm": 0.59375,
      "learning_rate": 9.216265114034964e-06,
      "loss": 0.7298,
      "step": 197
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.451171875,
      "learning_rate": 9.206267664155906e-06,
      "loss": 0.6439,
      "step": 198
    },
    {
      "epoch": 0.67003367003367,
      "grad_norm": 0.447265625,
      "learning_rate": 9.19621234749478e-06,
      "loss": 0.6719,
      "step": 199
    },
    {
      "epoch": 0.6734006734006734,
      "grad_norm": 0.41796875,
      "learning_rate": 9.186099302385345e-06,
      "loss": 0.6496,
      "step": 200
    },
    {
      "epoch": 0.6767676767676768,
      "grad_norm": 0.482421875,
      "learning_rate": 9.175928667955547e-06,
      "loss": 0.709,
      "step": 201
    },
    {
      "epoch": 0.6801346801346801,
      "grad_norm": 0.50390625,
      "learning_rate": 9.1657005841256e-06,
      "loss": 0.7054,
      "step": 202
    },
    {
      "epoch": 0.6835016835016835,
      "grad_norm": 0.455078125,
      "learning_rate": 9.155415191606074e-06,
      "loss": 0.6941,
      "step": 203
    },
    {
      "epoch": 0.6868686868686869,
      "grad_norm": 0.53515625,
      "learning_rate": 9.145072631895942e-06,
      "loss": 0.6919,
      "step": 204
    },
    {
      "epoch": 0.6902356902356902,
      "grad_norm": 0.62890625,
      "learning_rate": 9.134673047280644e-06,
      "loss": 0.7098,
      "step": 205
    },
    {
      "epoch": 0.6936026936026936,
      "grad_norm": 0.546875,
      "learning_rate": 9.12421658083013e-06,
      "loss": 0.6902,
      "step": 206
    },
    {
      "epoch": 0.696969696969697,
      "grad_norm": 0.58984375,
      "learning_rate": 9.113703376396885e-06,
      "loss": 0.7228,
      "step": 207
    },
    {
      "epoch": 0.7003367003367004,
      "grad_norm": 0.484375,
      "learning_rate": 9.103133578613959e-06,
      "loss": 0.6961,
      "step": 208
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 0.515625,
      "learning_rate": 9.092507332892968e-06,
      "loss": 0.6689,
      "step": 209
    },
    {
      "epoch": 0.7070707070707071,
      "grad_norm": 0.5390625,
      "learning_rate": 9.081824785422099e-06,
      "loss": 0.6552,
      "step": 210
    },
    {
      "epoch": 0.7104377104377104,
      "grad_norm": 0.462890625,
      "learning_rate": 9.071086083164099e-06,
      "loss": 0.6739,
      "step": 211
    },
    {
      "epoch": 0.7138047138047138,
      "grad_norm": 0.435546875,
      "learning_rate": 9.060291373854252e-06,
      "loss": 0.699,
      "step": 212
    },
    {
      "epoch": 0.7171717171717171,
      "grad_norm": 0.49609375,
      "learning_rate": 9.04944080599834e-06,
      "loss": 0.6964,
      "step": 213
    },
    {
      "epoch": 0.7205387205387206,
      "grad_norm": 0.47265625,
      "learning_rate": 9.038534528870618e-06,
      "loss": 0.678,
      "step": 214
    },
    {
      "epoch": 0.7239057239057239,
      "grad_norm": 0.455078125,
      "learning_rate": 9.027572692511739e-06,
      "loss": 0.6847,
      "step": 215
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.53515625,
      "learning_rate": 9.016555447726704e-06,
      "loss": 0.6811,
      "step": 216
    },
    {
      "epoch": 0.7306397306397306,
      "grad_norm": 0.482421875,
      "learning_rate": 9.005482946082784e-06,
      "loss": 0.6831,
      "step": 217
    },
    {
      "epoch": 0.734006734006734,
      "grad_norm": 0.474609375,
      "learning_rate": 8.994355339907429e-06,
      "loss": 0.6803,
      "step": 218
    },
    {
      "epoch": 0.7373737373737373,
      "grad_norm": 0.443359375,
      "learning_rate": 8.98317278228618e-06,
      "loss": 0.6639,
      "step": 219
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.474609375,
      "learning_rate": 8.971935427060563e-06,
      "loss": 0.6509,
      "step": 220
    },
    {
      "epoch": 0.7441077441077442,
      "grad_norm": 0.47265625,
      "learning_rate": 8.960643428825965e-06,
      "loss": 0.647,
      "step": 221
    },
    {
      "epoch": 0.7474747474747475,
      "grad_norm": 0.498046875,
      "learning_rate": 8.949296942929515e-06,
      "loss": 0.6686,
      "step": 222
    },
    {
      "epoch": 0.7508417508417509,
      "grad_norm": 0.5078125,
      "learning_rate": 8.937896125467941e-06,
      "loss": 0.6512,
      "step": 223
    },
    {
      "epoch": 0.7542087542087542,
      "grad_norm": 0.60546875,
      "learning_rate": 8.92644113328543e-06,
      "loss": 0.6544,
      "step": 224
    },
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 0.474609375,
      "learning_rate": 8.91493212397146e-06,
      "loss": 0.7091,
      "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
}