{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5050505050505051,
  "eval_steps": 38,
  "global_step": 150,
  "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": 3.5714285714285716e-07,
      "loss": 1.0833,
      "step": 1
    },
    {
      "epoch": 0.003367003367003367,
      "eval_loss": 1.032954454421997,
      "eval_runtime": 8.7744,
      "eval_samples_per_second": 56.984,
      "eval_steps_per_second": 3.647,
      "step": 1
    },
    {
      "epoch": 0.006734006734006734,
      "grad_norm": 2.265625,
      "learning_rate": 7.142857142857143e-07,
      "loss": 0.996,
      "step": 2
    },
    {
      "epoch": 0.010101010101010102,
      "grad_norm": 1.640625,
      "learning_rate": 1.0714285714285714e-06,
      "loss": 1.0487,
      "step": 3
    },
    {
      "epoch": 0.013468013468013467,
      "grad_norm": 2.046875,
      "learning_rate": 1.4285714285714286e-06,
      "loss": 1.0553,
      "step": 4
    },
    {
      "epoch": 0.016835016835016835,
      "grad_norm": 2.453125,
      "learning_rate": 1.7857142857142859e-06,
      "loss": 1.0339,
      "step": 5
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 1.984375,
      "learning_rate": 2.1428571428571427e-06,
      "loss": 1.014,
      "step": 6
    },
    {
      "epoch": 0.02356902356902357,
      "grad_norm": 2.609375,
      "learning_rate": 2.5e-06,
      "loss": 1.0298,
      "step": 7
    },
    {
      "epoch": 0.026936026936026935,
      "grad_norm": 2.328125,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 1.0226,
      "step": 8
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 2.25,
      "learning_rate": 3.2142857142857147e-06,
      "loss": 1.0739,
      "step": 9
    },
    {
      "epoch": 0.03367003367003367,
      "grad_norm": 2.28125,
      "learning_rate": 3.5714285714285718e-06,
      "loss": 1.0224,
      "step": 10
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 2.4375,
      "learning_rate": 3.928571428571429e-06,
      "loss": 1.0089,
      "step": 11
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 2.03125,
      "learning_rate": 4.2857142857142855e-06,
      "loss": 1.0529,
      "step": 12
    },
    {
      "epoch": 0.04377104377104377,
      "grad_norm": 2.03125,
      "learning_rate": 4.642857142857144e-06,
      "loss": 1.068,
      "step": 13
    },
    {
      "epoch": 0.04713804713804714,
      "grad_norm": 1.7265625,
      "learning_rate": 5e-06,
      "loss": 1.0318,
      "step": 14
    },
    {
      "epoch": 0.050505050505050504,
      "grad_norm": 1.8359375,
      "learning_rate": 4.9998459603839726e-06,
      "loss": 1.0439,
      "step": 15
    },
    {
      "epoch": 0.05387205387205387,
      "grad_norm": 2.15625,
      "learning_rate": 4.9993838605184505e-06,
      "loss": 1.0647,
      "step": 16
    },
    {
      "epoch": 0.05723905723905724,
      "grad_norm": 1.6015625,
      "learning_rate": 4.998613757348784e-06,
      "loss": 1.0081,
      "step": 17
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 1.65625,
      "learning_rate": 4.99753574577609e-06,
      "loss": 1.0098,
      "step": 18
    },
    {
      "epoch": 0.06397306397306397,
      "grad_norm": 1.4140625,
      "learning_rate": 4.996149958645559e-06,
      "loss": 0.9822,
      "step": 19
    },
    {
      "epoch": 0.06734006734006734,
      "grad_norm": 1.375,
      "learning_rate": 4.994456566730085e-06,
      "loss": 1.0474,
      "step": 20
    },
    {
      "epoch": 0.0707070707070707,
      "grad_norm": 1.2265625,
      "learning_rate": 4.992455778709222e-06,
      "loss": 1.0421,
      "step": 21
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 1.4609375,
      "learning_rate": 4.990147841143462e-06,
      "loss": 0.9845,
      "step": 22
    },
    {
      "epoch": 0.07744107744107744,
      "grad_norm": 1.2421875,
      "learning_rate": 4.98753303844386e-06,
      "loss": 0.9773,
      "step": 23
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 1.4296875,
      "learning_rate": 4.984611692836979e-06,
      "loss": 1.0511,
      "step": 24
    },
    {
      "epoch": 0.08417508417508418,
      "grad_norm": 1.1875,
      "learning_rate": 4.981384164325184e-06,
      "loss": 0.9915,
      "step": 25
    },
    {
      "epoch": 0.08754208754208755,
      "grad_norm": 1.15625,
      "learning_rate": 4.977850850642275e-06,
      "loss": 0.9881,
      "step": 26
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 1.296875,
      "learning_rate": 4.97401218720448e-06,
      "loss": 1.0623,
      "step": 27
    },
    {
      "epoch": 0.09427609427609428,
      "grad_norm": 1.2734375,
      "learning_rate": 4.969868647056793e-06,
      "loss": 1.0282,
      "step": 28
    },
    {
      "epoch": 0.09764309764309764,
      "grad_norm": 1.125,
      "learning_rate": 4.965420740814679e-06,
      "loss": 1.0122,
      "step": 29
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 1.25,
      "learning_rate": 4.960669016601155e-06,
      "loss": 1.0342,
      "step": 30
    },
    {
      "epoch": 0.10437710437710437,
      "grad_norm": 1.0625,
      "learning_rate": 4.95561405997924e-06,
      "loss": 0.9911,
      "step": 31
    },
    {
      "epoch": 0.10774410774410774,
      "grad_norm": 1.21875,
      "learning_rate": 4.950256493879795e-06,
      "loss": 1.025,
      "step": 32
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 1.1328125,
      "learning_rate": 4.94459697852476e-06,
      "loss": 1.022,
      "step": 33
    },
    {
      "epoch": 0.11447811447811448,
      "grad_norm": 1.1953125,
      "learning_rate": 4.938636211345792e-06,
      "loss": 1.0085,
      "step": 34
    },
    {
      "epoch": 0.11784511784511785,
      "grad_norm": 1.1484375,
      "learning_rate": 4.932374926898321e-06,
      "loss": 1.0109,
      "step": 35
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 1.0390625,
      "learning_rate": 4.92581389677103e-06,
      "loss": 0.9654,
      "step": 36
    },
    {
      "epoch": 0.12457912457912458,
      "grad_norm": 1.109375,
      "learning_rate": 4.918953929490768e-06,
      "loss": 1.0041,
      "step": 37
    },
    {
      "epoch": 0.12794612794612795,
      "grad_norm": 1.09375,
      "learning_rate": 4.911795870422916e-06,
      "loss": 1.0118,
      "step": 38
    },
    {
      "epoch": 0.12794612794612795,
      "eval_loss": 0.9947459697723389,
      "eval_runtime": 8.7184,
      "eval_samples_per_second": 57.35,
      "eval_steps_per_second": 3.67,
      "step": 38
    },
    {
      "epoch": 0.13131313131313133,
      "grad_norm": 0.9765625,
      "learning_rate": 4.904340601667208e-06,
      "loss": 0.9841,
      "step": 39
    },
    {
      "epoch": 0.13468013468013468,
      "grad_norm": 1.046875,
      "learning_rate": 4.896589041949036e-06,
      "loss": 1.0055,
      "step": 40
    },
    {
      "epoch": 0.13804713804713806,
      "grad_norm": 1.171875,
      "learning_rate": 4.888542146506224e-06,
      "loss": 0.9728,
      "step": 41
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": 0.9765625,
      "learning_rate": 4.880200906971321e-06,
      "loss": 0.975,
      "step": 42
    },
    {
      "epoch": 0.1447811447811448,
      "grad_norm": 1.0234375,
      "learning_rate": 4.8715663512493924e-06,
      "loss": 0.9628,
      "step": 43
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.92578125,
      "learning_rate": 4.8626395433913595e-06,
      "loss": 0.9668,
      "step": 44
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 1.078125,
      "learning_rate": 4.853421583462866e-06,
      "loss": 0.9539,
      "step": 45
    },
    {
      "epoch": 0.15488215488215487,
      "grad_norm": 1.1484375,
      "learning_rate": 4.8439136074087165e-06,
      "loss": 1.0145,
      "step": 46
    },
    {
      "epoch": 0.15824915824915825,
      "grad_norm": 1.015625,
      "learning_rate": 4.834116786912897e-06,
      "loss": 0.9738,
      "step": 47
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 1.0390625,
      "learning_rate": 4.82403232925418e-06,
      "loss": 0.9907,
      "step": 48
    },
    {
      "epoch": 0.16498316498316498,
      "grad_norm": 1.0546875,
      "learning_rate": 4.813661477157355e-06,
      "loss": 0.9773,
      "step": 49
    },
    {
      "epoch": 0.16835016835016836,
      "grad_norm": 1.015625,
      "learning_rate": 4.803005508640083e-06,
      "loss": 0.9636,
      "step": 50
    },
    {
      "epoch": 0.1717171717171717,
      "grad_norm": 0.9375,
      "learning_rate": 4.7920657368554e-06,
      "loss": 0.9589,
      "step": 51
    },
    {
      "epoch": 0.1750841750841751,
      "grad_norm": 0.9765625,
      "learning_rate": 4.780843509929905e-06,
      "loss": 0.9753,
      "step": 52
    },
    {
      "epoch": 0.17845117845117844,
      "grad_norm": 1.015625,
      "learning_rate": 4.769340210797618e-06,
      "loss": 0.9324,
      "step": 53
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.96875,
      "learning_rate": 4.757557257029563e-06,
      "loss": 0.9439,
      "step": 54
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 1.0078125,
      "learning_rate": 4.745496100659083e-06,
      "loss": 0.9925,
      "step": 55
    },
    {
      "epoch": 0.18855218855218855,
      "grad_norm": 0.8828125,
      "learning_rate": 4.733158228002891e-06,
      "loss": 0.9294,
      "step": 56
    },
    {
      "epoch": 0.1919191919191919,
      "grad_norm": 0.95703125,
      "learning_rate": 4.720545159477921e-06,
      "loss": 0.9502,
      "step": 57
    },
    {
      "epoch": 0.19528619528619529,
      "grad_norm": 0.90234375,
      "learning_rate": 4.707658449413961e-06,
      "loss": 0.9538,
      "step": 58
    },
    {
      "epoch": 0.19865319865319866,
      "grad_norm": 1.03125,
      "learning_rate": 4.694499685862106e-06,
      "loss": 0.9484,
      "step": 59
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 1.0390625,
      "learning_rate": 4.681070490399064e-06,
      "loss": 0.9515,
      "step": 60
    },
    {
      "epoch": 0.2053872053872054,
      "grad_norm": 0.921875,
      "learning_rate": 4.667372517927323e-06,
      "loss": 0.956,
      "step": 61
    },
    {
      "epoch": 0.20875420875420875,
      "grad_norm": 0.88671875,
      "learning_rate": 4.653407456471222e-06,
      "loss": 0.9478,
      "step": 62
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 1.0390625,
      "learning_rate": 4.639177026968924e-06,
      "loss": 0.9427,
      "step": 63
    },
    {
      "epoch": 0.21548821548821548,
      "grad_norm": 0.9296875,
      "learning_rate": 4.624682983060346e-06,
      "loss": 1.0028,
      "step": 64
    },
    {
      "epoch": 0.21885521885521886,
      "grad_norm": 0.8828125,
      "learning_rate": 4.609927110871053e-06,
      "loss": 0.9442,
      "step": 65
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.890625,
      "learning_rate": 4.594911228792156e-06,
      "loss": 0.9695,
      "step": 66
    },
    {
      "epoch": 0.2255892255892256,
      "grad_norm": 0.94140625,
      "learning_rate": 4.579637187256222e-06,
      "loss": 0.9407,
      "step": 67
    },
    {
      "epoch": 0.22895622895622897,
      "grad_norm": 0.9609375,
      "learning_rate": 4.564106868509246e-06,
      "loss": 1.0014,
      "step": 68
    },
    {
      "epoch": 0.23232323232323232,
      "grad_norm": 0.9140625,
      "learning_rate": 4.5483221863786965e-06,
      "loss": 0.9249,
      "step": 69
    },
    {
      "epoch": 0.2356902356902357,
      "grad_norm": 0.83984375,
      "learning_rate": 4.5322850860376744e-06,
      "loss": 0.9623,
      "step": 70
    },
    {
      "epoch": 0.23905723905723905,
      "grad_norm": 0.9765625,
      "learning_rate": 4.515997543765202e-06,
      "loss": 0.9321,
      "step": 71
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.94921875,
      "learning_rate": 4.499461566702685e-06,
      "loss": 0.9407,
      "step": 72
    },
    {
      "epoch": 0.24579124579124578,
      "grad_norm": 0.86328125,
      "learning_rate": 4.48267919260657e-06,
      "loss": 0.9081,
      "step": 73
    },
    {
      "epoch": 0.24915824915824916,
      "grad_norm": 0.87890625,
      "learning_rate": 4.465652489597226e-06,
      "loss": 0.9259,
      "step": 74
    },
    {
      "epoch": 0.25252525252525254,
      "grad_norm": 0.984375,
      "learning_rate": 4.4483835559040885e-06,
      "loss": 0.9386,
      "step": 75
    },
    {
      "epoch": 0.2558922558922559,
      "grad_norm": 1.0546875,
      "learning_rate": 4.430874519607089e-06,
      "loss": 0.9884,
      "step": 76
    },
    {
      "epoch": 0.2558922558922559,
      "eval_loss": 0.9393355846405029,
      "eval_runtime": 8.6902,
      "eval_samples_per_second": 57.536,
      "eval_steps_per_second": 3.682,
      "step": 76
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 0.9765625,
      "learning_rate": 4.413127538374411e-06,
      "loss": 0.9479,
      "step": 77
    },
    {
      "epoch": 0.26262626262626265,
      "grad_norm": 0.8671875,
      "learning_rate": 4.395144799196593e-06,
      "loss": 0.9165,
      "step": 78
    },
    {
      "epoch": 0.265993265993266,
      "grad_norm": 1.0390625,
      "learning_rate": 4.376928518117028e-06,
      "loss": 0.9428,
      "step": 79
    },
    {
      "epoch": 0.26936026936026936,
      "grad_norm": 1.0703125,
      "learning_rate": 4.358480939958867e-06,
      "loss": 0.9752,
      "step": 80
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 1.0078125,
      "learning_rate": 4.339804338048397e-06,
      "loss": 0.8951,
      "step": 81
    },
    {
      "epoch": 0.2760942760942761,
      "grad_norm": 0.87890625,
      "learning_rate": 4.320901013934887e-06,
      "loss": 0.9329,
      "step": 82
    },
    {
      "epoch": 0.27946127946127947,
      "grad_norm": 0.84765625,
      "learning_rate": 4.301773297106968e-06,
      "loss": 0.9086,
      "step": 83
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 0.84765625,
      "learning_rate": 4.282423544705564e-06,
      "loss": 0.9417,
      "step": 84
    },
    {
      "epoch": 0.28619528619528617,
      "grad_norm": 0.91015625,
      "learning_rate": 4.262854141233419e-06,
      "loss": 0.9344,
      "step": 85
    },
    {
      "epoch": 0.2895622895622896,
      "grad_norm": 0.921875,
      "learning_rate": 4.243067498261251e-06,
      "loss": 0.905,
      "step": 86
    },
    {
      "epoch": 0.29292929292929293,
      "grad_norm": 0.8671875,
      "learning_rate": 4.223066054130568e-06,
      "loss": 0.8943,
      "step": 87
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.91015625,
      "learning_rate": 4.2028522736531895e-06,
      "loss": 0.9407,
      "step": 88
    },
    {
      "epoch": 0.2996632996632997,
      "grad_norm": 0.95703125,
      "learning_rate": 4.182428647807503e-06,
      "loss": 0.957,
      "step": 89
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 1.03125,
      "learning_rate": 4.161797693431493e-06,
      "loss": 0.9128,
      "step": 90
    },
    {
      "epoch": 0.3063973063973064,
      "grad_norm": 0.8515625,
      "learning_rate": 4.140961952912594e-06,
      "loss": 0.9008,
      "step": 91
    },
    {
      "epoch": 0.30976430976430974,
      "grad_norm": 1.09375,
      "learning_rate": 4.11992399387438e-06,
      "loss": 0.9073,
      "step": 92
    },
    {
      "epoch": 0.31313131313131315,
      "grad_norm": 0.90625,
      "learning_rate": 4.098686408860157e-06,
      "loss": 1.0136,
      "step": 93
    },
    {
      "epoch": 0.3164983164983165,
      "grad_norm": 0.9140625,
      "learning_rate": 4.077251815013477e-06,
      "loss": 0.965,
      "step": 94
    },
    {
      "epoch": 0.31986531986531985,
      "grad_norm": 0.9375,
      "learning_rate": 4.055622853755627e-06,
      "loss": 0.8822,
      "step": 95
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 0.859375,
      "learning_rate": 4.033802190460114e-06,
      "loss": 0.9241,
      "step": 96
    },
    {
      "epoch": 0.3265993265993266,
      "grad_norm": 1.015625,
      "learning_rate": 4.011792514124217e-06,
      "loss": 0.9491,
      "step": 97
    },
    {
      "epoch": 0.32996632996632996,
      "grad_norm": 0.890625,
      "learning_rate": 3.989596537037608e-06,
      "loss": 0.9461,
      "step": 98
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.0,
      "learning_rate": 3.967216994448116e-06,
      "loss": 0.9298,
      "step": 99
    },
    {
      "epoch": 0.3367003367003367,
      "grad_norm": 1.0078125,
      "learning_rate": 3.9446566442246615e-06,
      "loss": 0.9133,
      "step": 100
    },
    {
      "epoch": 0.3400673400673401,
      "grad_norm": 0.9765625,
      "learning_rate": 3.921918266517392e-06,
      "loss": 0.9334,
      "step": 101
    },
    {
      "epoch": 0.3434343434343434,
      "grad_norm": 0.79296875,
      "learning_rate": 3.899004663415083e-06,
      "loss": 0.9477,
      "step": 102
    },
    {
      "epoch": 0.3468013468013468,
      "grad_norm": 0.87109375,
      "learning_rate": 3.875918658599837e-06,
      "loss": 0.9307,
      "step": 103
    },
    {
      "epoch": 0.3501683501683502,
      "grad_norm": 1.0078125,
      "learning_rate": 3.852663096999104e-06,
      "loss": 0.8982,
      "step": 104
    },
    {
      "epoch": 0.35353535353535354,
      "grad_norm": 0.99609375,
      "learning_rate": 3.829240844435109e-06,
      "loss": 0.9564,
      "step": 105
    },
    {
      "epoch": 0.3569023569023569,
      "grad_norm": 0.890625,
      "learning_rate": 3.8056547872716865e-06,
      "loss": 0.916,
      "step": 106
    },
    {
      "epoch": 0.3602693602693603,
      "grad_norm": 0.90234375,
      "learning_rate": 3.7819078320585865e-06,
      "loss": 0.9077,
      "step": 107
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.9296875,
      "learning_rate": 3.7580029051732992e-06,
      "loss": 0.9215,
      "step": 108
    },
    {
      "epoch": 0.367003367003367,
      "grad_norm": 1.25,
      "learning_rate": 3.733942952460432e-06,
      "loss": 0.9287,
      "step": 109
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.828125,
      "learning_rate": 3.7097309388686865e-06,
      "loss": 0.9261,
      "step": 110
    },
    {
      "epoch": 0.37373737373737376,
      "grad_norm": 0.91796875,
      "learning_rate": 3.6853698480854853e-06,
      "loss": 0.8885,
      "step": 111
    },
    {
      "epoch": 0.3771043771043771,
      "grad_norm": 0.90234375,
      "learning_rate": 3.660862682169283e-06,
      "loss": 0.905,
      "step": 112
    },
    {
      "epoch": 0.38047138047138046,
      "grad_norm": 0.703125,
      "learning_rate": 3.636212461179623e-06,
      "loss": 0.8435,
      "step": 113
    },
    {
      "epoch": 0.3838383838383838,
      "grad_norm": 0.7734375,
      "learning_rate": 3.6114222228049657e-06,
      "loss": 0.9277,
      "step": 114
    },
    {
      "epoch": 0.3838383838383838,
      "eval_loss": 0.8986863493919373,
      "eval_runtime": 8.7365,
      "eval_samples_per_second": 57.231,
      "eval_steps_per_second": 3.663,
      "step": 114
    },
    {
      "epoch": 0.3872053872053872,
      "grad_norm": 0.8828125,
      "learning_rate": 3.5864950219883514e-06,
      "loss": 0.9274,
      "step": 115
    },
    {
      "epoch": 0.39057239057239057,
      "grad_norm": 0.8125,
      "learning_rate": 3.561433930550934e-06,
      "loss": 0.8989,
      "step": 116
    },
    {
      "epoch": 0.3939393939393939,
      "grad_norm": 0.81640625,
      "learning_rate": 3.536242036813436e-06,
      "loss": 0.9125,
      "step": 117
    },
    {
      "epoch": 0.39730639730639733,
      "grad_norm": 0.80859375,
      "learning_rate": 3.510922445215568e-06,
      "loss": 0.883,
      "step": 118
    },
    {
      "epoch": 0.4006734006734007,
      "grad_norm": 0.7578125,
      "learning_rate": 3.4854782759334625e-06,
      "loss": 0.8644,
      "step": 119
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 0.84765625,
      "learning_rate": 3.4599126644951758e-06,
      "loss": 0.907,
      "step": 120
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 0.796875,
      "learning_rate": 3.4342287613942804e-06,
      "loss": 0.889,
      "step": 121
    },
    {
      "epoch": 0.4107744107744108,
      "grad_norm": 0.80859375,
      "learning_rate": 3.4084297317016353e-06,
      "loss": 0.896,
      "step": 122
    },
    {
      "epoch": 0.41414141414141414,
      "grad_norm": 0.8359375,
      "learning_rate": 3.3825187546753426e-06,
      "loss": 0.8874,
      "step": 123
    },
    {
      "epoch": 0.4175084175084175,
      "grad_norm": 0.7890625,
      "learning_rate": 3.3564990233689632e-06,
      "loss": 0.8811,
      "step": 124
    },
    {
      "epoch": 0.4208754208754209,
      "grad_norm": 0.8203125,
      "learning_rate": 3.330373744238033e-06,
      "loss": 0.9437,
      "step": 125
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 0.890625,
      "learning_rate": 3.3041461367449256e-06,
      "loss": 0.8829,
      "step": 126
    },
    {
      "epoch": 0.4276094276094276,
      "grad_norm": 0.77734375,
      "learning_rate": 3.2778194329621104e-06,
      "loss": 0.8412,
      "step": 127
    },
    {
      "epoch": 0.43097643097643096,
      "grad_norm": 0.83984375,
      "learning_rate": 3.2513968771738606e-06,
      "loss": 0.8916,
      "step": 128
    },
    {
      "epoch": 0.43434343434343436,
      "grad_norm": 1.0078125,
      "learning_rate": 3.224881725476456e-06,
      "loss": 0.9644,
      "step": 129
    },
    {
      "epoch": 0.4377104377104377,
      "grad_norm": 0.78125,
      "learning_rate": 3.198277245376924e-06,
      "loss": 0.8623,
      "step": 130
    },
    {
      "epoch": 0.44107744107744107,
      "grad_norm": 0.71484375,
      "learning_rate": 3.1715867153903844e-06,
      "loss": 0.8786,
      "step": 131
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.69140625,
      "learning_rate": 3.144813424636031e-06,
      "loss": 0.8786,
      "step": 132
    },
    {
      "epoch": 0.4478114478114478,
      "grad_norm": 0.91015625,
      "learning_rate": 3.1179606724318052e-06,
      "loss": 0.9163,
      "step": 133
    },
    {
      "epoch": 0.4511784511784512,
      "grad_norm": 0.78515625,
      "learning_rate": 3.091031767887817e-06,
      "loss": 0.8656,
      "step": 134
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.72265625,
      "learning_rate": 3.0640300294985613e-06,
      "loss": 0.8901,
      "step": 135
    },
    {
      "epoch": 0.45791245791245794,
      "grad_norm": 0.83203125,
      "learning_rate": 3.036958784733967e-06,
      "loss": 0.8706,
      "step": 136
    },
    {
      "epoch": 0.4612794612794613,
      "grad_norm": 0.75390625,
      "learning_rate": 3.0098213696293542e-06,
      "loss": 0.8987,
      "step": 137
    },
    {
      "epoch": 0.46464646464646464,
      "grad_norm": 0.77734375,
      "learning_rate": 2.982621128374325e-06,
      "loss": 0.8984,
      "step": 138
    },
    {
      "epoch": 0.468013468013468,
      "grad_norm": 0.8828125,
      "learning_rate": 2.9553614129006543e-06,
      "loss": 0.8986,
      "step": 139
    },
    {
      "epoch": 0.4713804713804714,
      "grad_norm": 0.78515625,
      "learning_rate": 2.9280455824692255e-06,
      "loss": 0.8514,
      "step": 140
    },
    {
      "epoch": 0.47474747474747475,
      "grad_norm": 0.6875,
      "learning_rate": 2.9006770032560637e-06,
      "loss": 0.9182,
      "step": 141
    },
    {
      "epoch": 0.4781144781144781,
      "grad_norm": 1.1171875,
      "learning_rate": 2.8732590479375167e-06,
      "loss": 0.8728,
      "step": 142
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 0.68359375,
      "learning_rate": 2.8457950952746293e-06,
      "loss": 0.8692,
      "step": 143
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 1.2734375,
      "learning_rate": 2.8182885296967833e-06,
      "loss": 0.907,
      "step": 144
    },
    {
      "epoch": 0.4882154882154882,
      "grad_norm": 0.88671875,
      "learning_rate": 2.7907427408846156e-06,
      "loss": 0.8318,
      "step": 145
    },
    {
      "epoch": 0.49158249158249157,
      "grad_norm": 1.0703125,
      "learning_rate": 2.763161123352314e-06,
      "loss": 0.8542,
      "step": 146
    },
    {
      "epoch": 0.494949494949495,
      "grad_norm": 0.67578125,
      "learning_rate": 2.735547076029296e-06,
      "loss": 0.8602,
      "step": 147
    },
    {
      "epoch": 0.4983164983164983,
      "grad_norm": 1.0625,
      "learning_rate": 2.7079040018413586e-06,
      "loss": 0.8775,
      "step": 148
    },
    {
      "epoch": 0.5016835016835017,
      "grad_norm": 0.96484375,
      "learning_rate": 2.6802353072913307e-06,
      "loss": 0.8884,
      "step": 149
    },
    {
      "epoch": 0.5050505050505051,
      "grad_norm": 0.87890625,
      "learning_rate": 2.6525444020392794e-06,
      "loss": 0.8886,
      "step": 150
    }
  ],
  "logging_steps": 1,
  "max_steps": 297,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 2.72875344887808e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}