{
  "best_metric": 0.8706070780754089,
  "best_model_checkpoint": "ckpt/origin/pedes_rewrite/checkpoint-104",
  "epoch": 5.804651162790698,
  "eval_steps": 13,
  "global_step": 156,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.8602,
      "step": 1
    },
    {
      "epoch": 0.07,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.8321,
      "step": 2
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001,
      "loss": 1.8243,
      "step": 3
    },
    {
      "epoch": 0.15,
      "learning_rate": 9.999626433348663e-05,
      "loss": 1.8373,
      "step": 4
    },
    {
      "epoch": 0.19,
      "learning_rate": 9.998505789215469e-05,
      "loss": 1.7732,
      "step": 5
    },
    {
      "epoch": 0.22,
      "learning_rate": 9.996638235054528e-05,
      "loss": 1.7818,
      "step": 6
    },
    {
      "epoch": 0.26,
      "learning_rate": 9.994024049928221e-05,
      "loss": 1.6944,
      "step": 7
    },
    {
      "epoch": 0.3,
      "learning_rate": 9.990663624465504e-05,
      "loss": 1.6106,
      "step": 8
    },
    {
      "epoch": 0.33,
      "learning_rate": 9.986557460803527e-05,
      "loss": 1.6462,
      "step": 9
    },
    {
      "epoch": 0.37,
      "learning_rate": 9.981706172512619e-05,
      "loss": 1.6212,
      "step": 10
    },
    {
      "epoch": 0.41,
      "learning_rate": 9.976110484504588e-05,
      "loss": 1.6387,
      "step": 11
    },
    {
      "epoch": 0.45,
      "learning_rate": 9.969771232924403e-05,
      "loss": 1.6043,
      "step": 12
    },
    {
      "epoch": 0.48,
      "learning_rate": 9.962689365025259e-05,
      "loss": 1.5568,
      "step": 13
    },
    {
      "epoch": 0.48,
      "eval_loss": 1.5163209438323975,
      "eval_runtime": 34.871,
      "eval_samples_per_second": 1.434,
      "eval_steps_per_second": 1.434,
      "step": 13
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.954865939027028e-05,
      "loss": 1.4951,
      "step": 14
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.946302123958131e-05,
      "loss": 1.4334,
      "step": 15
    },
    {
      "epoch": 0.6,
      "learning_rate": 9.936999199480853e-05,
      "loss": 1.4054,
      "step": 16
    },
    {
      "epoch": 0.63,
      "learning_rate": 9.926958555700134e-05,
      "loss": 1.4458,
      "step": 17
    },
    {
      "epoch": 0.67,
      "learning_rate": 9.916181692955842e-05,
      "loss": 1.3881,
      "step": 18
    },
    {
      "epoch": 0.71,
      "learning_rate": 9.90467022159859e-05,
      "loss": 1.3585,
      "step": 19
    },
    {
      "epoch": 0.74,
      "learning_rate": 9.892425861749099e-05,
      "loss": 1.3459,
      "step": 20
    },
    {
      "epoch": 0.78,
      "learning_rate": 9.879450443041171e-05,
      "loss": 1.3004,
      "step": 21
    },
    {
      "epoch": 0.82,
      "learning_rate": 9.865745904348295e-05,
      "loss": 1.2611,
      "step": 22
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.851314293493923e-05,
      "loss": 1.3038,
      "step": 23
    },
    {
      "epoch": 0.89,
      "learning_rate": 9.836157766945466e-05,
      "loss": 1.2547,
      "step": 24
    },
    {
      "epoch": 0.93,
      "learning_rate": 9.820278589492076e-05,
      "loss": 1.2802,
      "step": 25
    },
    {
      "epoch": 0.97,
      "learning_rate": 9.803679133906209e-05,
      "loss": 1.1729,
      "step": 26
    },
    {
      "epoch": 0.97,
      "eval_loss": 1.2355083227157593,
      "eval_runtime": 34.8406,
      "eval_samples_per_second": 1.435,
      "eval_steps_per_second": 1.435,
      "step": 26
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.786361880589083e-05,
      "loss": 1.2083,
      "step": 27
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.768329417200028e-05,
      "loss": 1.1907,
      "step": 28
    },
    {
      "epoch": 1.08,
      "learning_rate": 9.749584438269832e-05,
      "loss": 1.1546,
      "step": 29
    },
    {
      "epoch": 1.12,
      "learning_rate": 9.730129744798095e-05,
      "loss": 1.1084,
      "step": 30
    },
    {
      "epoch": 1.15,
      "learning_rate": 9.709968243834698e-05,
      "loss": 1.112,
      "step": 31
    },
    {
      "epoch": 1.19,
      "learning_rate": 9.689102948045397e-05,
      "loss": 1.0599,
      "step": 32
    },
    {
      "epoch": 1.23,
      "learning_rate": 9.667536975261667e-05,
      "loss": 1.0952,
      "step": 33
    },
    {
      "epoch": 1.27,
      "learning_rate": 9.6452735480148e-05,
      "loss": 1.1067,
      "step": 34
    },
    {
      "epoch": 1.3,
      "learning_rate": 9.622315993054383e-05,
      "loss": 1.0152,
      "step": 35
    },
    {
      "epoch": 1.34,
      "learning_rate": 9.598667740851187e-05,
      "loss": 1.0704,
      "step": 36
    },
    {
      "epoch": 1.38,
      "learning_rate": 9.574332325084563e-05,
      "loss": 1.031,
      "step": 37
    },
    {
      "epoch": 1.41,
      "learning_rate": 9.549313382114426e-05,
      "loss": 1.0216,
      "step": 38
    },
    {
      "epoch": 1.45,
      "learning_rate": 9.523614650437876e-05,
      "loss": 1.0242,
      "step": 39
    },
    {
      "epoch": 1.45,
      "eval_loss": 1.0572456121444702,
      "eval_runtime": 34.7485,
      "eval_samples_per_second": 1.439,
      "eval_steps_per_second": 1.439,
      "step": 39
    },
    {
      "epoch": 1.49,
      "learning_rate": 9.497239970130562e-05,
      "loss": 0.9805,
      "step": 40
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.470193282272886e-05,
      "loss": 0.9745,
      "step": 41
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.442478628361098e-05,
      "loss": 0.9749,
      "step": 42
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.414100149703373e-05,
      "loss": 0.9916,
      "step": 43
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.385062086801013e-05,
      "loss": 0.9389,
      "step": 44
    },
    {
      "epoch": 1.67,
      "learning_rate": 9.355368778714784e-05,
      "loss": 0.9721,
      "step": 45
    },
    {
      "epoch": 1.71,
      "learning_rate": 9.325024662416552e-05,
      "loss": 0.9278,
      "step": 46
    },
    {
      "epoch": 1.75,
      "learning_rate": 9.294034272126287e-05,
      "loss": 0.922,
      "step": 47
    },
    {
      "epoch": 1.79,
      "learning_rate": 9.262402238634515e-05,
      "loss": 0.9192,
      "step": 48
    },
    {
      "epoch": 1.82,
      "learning_rate": 9.230133288610366e-05,
      "loss": 0.9203,
      "step": 49
    },
    {
      "epoch": 1.86,
      "learning_rate": 9.197232243895284e-05,
      "loss": 0.9317,
      "step": 50
    },
    {
      "epoch": 1.9,
      "learning_rate": 9.163704020782507e-05,
      "loss": 0.9355,
      "step": 51
    },
    {
      "epoch": 1.93,
      "learning_rate": 9.129553629282448e-05,
      "loss": 0.9027,
      "step": 52
    },
    {
      "epoch": 1.93,
      "eval_loss": 0.9721283912658691,
      "eval_runtime": 34.6767,
      "eval_samples_per_second": 1.442,
      "eval_steps_per_second": 1.442,
      "step": 52
    },
    {
      "epoch": 1.97,
      "learning_rate": 9.094786172374066e-05,
      "loss": 0.9358,
      "step": 53
    },
    {
      "epoch": 2.01,
      "learning_rate": 9.059406845242342e-05,
      "loss": 0.8565,
      "step": 54
    },
    {
      "epoch": 2.05,
      "learning_rate": 9.02342093450198e-05,
      "loss": 0.8217,
      "step": 55
    },
    {
      "epoch": 2.08,
      "learning_rate": 8.986833817407449e-05,
      "loss": 0.8717,
      "step": 56
    },
    {
      "epoch": 2.12,
      "learning_rate": 8.949650961049478e-05,
      "loss": 0.8637,
      "step": 57
    },
    {
      "epoch": 2.16,
      "learning_rate": 8.911877921538117e-05,
      "loss": 0.8261,
      "step": 58
    },
    {
      "epoch": 2.2,
      "learning_rate": 8.87352034317252e-05,
      "loss": 0.7963,
      "step": 59
    },
    {
      "epoch": 2.23,
      "learning_rate": 8.834583957597529e-05,
      "loss": 0.8731,
      "step": 60
    },
    {
      "epoch": 2.27,
      "learning_rate": 8.795074582947214e-05,
      "loss": 0.8759,
      "step": 61
    },
    {
      "epoch": 2.31,
      "learning_rate": 8.754998122975489e-05,
      "loss": 0.8333,
      "step": 62
    },
    {
      "epoch": 2.34,
      "learning_rate": 8.714360566173931e-05,
      "loss": 0.7972,
      "step": 63
    },
    {
      "epoch": 2.38,
      "learning_rate": 8.673167984876949e-05,
      "loss": 0.8378,
      "step": 64
    },
    {
      "epoch": 2.42,
      "learning_rate": 8.631426534354403e-05,
      "loss": 0.8188,
      "step": 65
    },
    {
      "epoch": 2.42,
      "eval_loss": 0.9200485944747925,
      "eval_runtime": 34.696,
      "eval_samples_per_second": 1.441,
      "eval_steps_per_second": 1.441,
      "step": 65
    },
    {
      "epoch": 2.46,
      "learning_rate": 8.58914245189185e-05,
      "loss": 0.774,
      "step": 66
    },
    {
      "epoch": 2.49,
      "learning_rate": 8.546322055858526e-05,
      "loss": 0.8312,
      "step": 67
    },
    {
      "epoch": 2.53,
      "learning_rate": 8.502971744763215e-05,
      "loss": 0.8011,
      "step": 68
    },
    {
      "epoch": 2.57,
      "learning_rate": 8.459097996298137e-05,
      "loss": 0.7958,
      "step": 69
    },
    {
      "epoch": 2.6,
      "learning_rate": 8.414707366371007e-05,
      "loss": 0.7647,
      "step": 70
    },
    {
      "epoch": 2.64,
      "learning_rate": 8.369806488125418e-05,
      "loss": 0.8322,
      "step": 71
    },
    {
      "epoch": 2.68,
      "learning_rate": 8.324402070949658e-05,
      "loss": 0.7983,
      "step": 72
    },
    {
      "epoch": 2.72,
      "learning_rate": 8.278500899474163e-05,
      "loss": 0.7903,
      "step": 73
    },
    {
      "epoch": 2.75,
      "learning_rate": 8.232109832557696e-05,
      "loss": 0.765,
      "step": 74
    },
    {
      "epoch": 2.79,
      "learning_rate": 8.185235802262469e-05,
      "loss": 0.7847,
      "step": 75
    },
    {
      "epoch": 2.83,
      "learning_rate": 8.137885812818295e-05,
      "loss": 0.7789,
      "step": 76
    },
    {
      "epoch": 2.87,
      "learning_rate": 8.09006693957597e-05,
      "loss": 0.7802,
      "step": 77
    },
    {
      "epoch": 2.9,
      "learning_rate": 8.041786327950036e-05,
      "loss": 0.7535,
      "step": 78
    },
    {
      "epoch": 2.9,
      "eval_loss": 0.8959811925888062,
      "eval_runtime": 34.7154,
      "eval_samples_per_second": 1.44,
      "eval_steps_per_second": 1.44,
      "step": 78
    },
    {
      "epoch": 2.94,
      "learning_rate": 7.993051192351057e-05,
      "loss": 0.7877,
      "step": 79
    },
    {
      "epoch": 2.98,
      "learning_rate": 7.943868815107594e-05,
      "loss": 0.7804,
      "step": 80
    },
    {
      "epoch": 3.01,
      "learning_rate": 7.894246545378037e-05,
      "loss": 0.7512,
      "step": 81
    },
    {
      "epoch": 3.05,
      "learning_rate": 7.844191798052438e-05,
      "loss": 0.713,
      "step": 82
    },
    {
      "epoch": 3.09,
      "learning_rate": 7.793712052644535e-05,
      "loss": 0.7655,
      "step": 83
    },
    {
      "epoch": 3.13,
      "learning_rate": 7.742814852174112e-05,
      "loss": 0.6954,
      "step": 84
    },
    {
      "epoch": 3.16,
      "learning_rate": 7.691507802039862e-05,
      "loss": 0.7137,
      "step": 85
    },
    {
      "epoch": 3.2,
      "learning_rate": 7.639798568882947e-05,
      "loss": 0.7439,
      "step": 86
    },
    {
      "epoch": 3.24,
      "learning_rate": 7.587694879441401e-05,
      "loss": 0.7458,
      "step": 87
    },
    {
      "epoch": 3.27,
      "learning_rate": 7.535204519395538e-05,
      "loss": 0.7443,
      "step": 88
    },
    {
      "epoch": 3.31,
      "learning_rate": 7.482335332204568e-05,
      "loss": 0.7162,
      "step": 89
    },
    {
      "epoch": 3.35,
      "learning_rate": 7.429095217934577e-05,
      "loss": 0.7134,
      "step": 90
    },
    {
      "epoch": 3.39,
      "learning_rate": 7.375492132078052e-05,
      "loss": 0.7311,
      "step": 91
    },
    {
      "epoch": 3.39,
      "eval_loss": 0.8750792741775513,
      "eval_runtime": 34.7072,
      "eval_samples_per_second": 1.441,
      "eval_steps_per_second": 1.441,
      "step": 91
    },
    {
      "epoch": 3.42,
      "learning_rate": 7.321534084365102e-05,
      "loss": 0.6978,
      "step": 92
    },
    {
      "epoch": 3.46,
      "learning_rate": 7.267229137566607e-05,
      "loss": 0.7277,
      "step": 93
    },
    {
      "epoch": 3.5,
      "learning_rate": 7.212585406289418e-05,
      "loss": 0.7412,
      "step": 94
    },
    {
      "epoch": 3.53,
      "learning_rate": 7.157611055763819e-05,
      "loss": 0.6875,
      "step": 95
    },
    {
      "epoch": 3.57,
      "learning_rate": 7.102314300623426e-05,
      "loss": 0.68,
      "step": 96
    },
    {
      "epoch": 3.61,
      "learning_rate": 7.046703403677695e-05,
      "loss": 0.6764,
      "step": 97
    },
    {
      "epoch": 3.65,
      "learning_rate": 6.990786674677245e-05,
      "loss": 0.675,
      "step": 98
    },
    {
      "epoch": 3.68,
      "learning_rate": 6.934572469072162e-05,
      "loss": 0.7028,
      "step": 99
    },
    {
      "epoch": 3.72,
      "learning_rate": 6.878069186763465e-05,
      "loss": 0.6985,
      "step": 100
    },
    {
      "epoch": 3.76,
      "learning_rate": 6.821285270847934e-05,
      "loss": 0.7309,
      "step": 101
    },
    {
      "epoch": 3.8,
      "learning_rate": 6.764229206356498e-05,
      "loss": 0.6851,
      "step": 102
    },
    {
      "epoch": 3.83,
      "learning_rate": 6.70690951898634e-05,
      "loss": 0.6568,
      "step": 103
    },
    {
      "epoch": 3.87,
      "learning_rate": 6.649334773826924e-05,
      "loss": 0.6845,
      "step": 104
    },
    {
      "epoch": 3.87,
      "eval_loss": 0.8706070780754089,
      "eval_runtime": 34.6892,
      "eval_samples_per_second": 1.441,
      "eval_steps_per_second": 1.441,
      "step": 104
    },
    {
      "epoch": 3.91,
      "learning_rate": 6.591513574080151e-05,
      "loss": 0.6993,
      "step": 105
    },
    {
      "epoch": 3.94,
      "learning_rate": 6.533454559774807e-05,
      "loss": 0.6635,
      "step": 106
    },
    {
      "epoch": 3.98,
      "learning_rate": 6.475166406475515e-05,
      "loss": 0.7059,
      "step": 107
    },
    {
      "epoch": 4.02,
      "learning_rate": 6.41665782398637e-05,
      "loss": 0.6543,
      "step": 108
    },
    {
      "epoch": 4.06,
      "learning_rate": 6.357937555049464e-05,
      "loss": 0.6807,
      "step": 109
    },
    {
      "epoch": 4.09,
      "learning_rate": 6.299014374038493e-05,
      "loss": 0.6573,
      "step": 110
    },
    {
      "epoch": 4.13,
      "learning_rate": 6.239897085647623e-05,
      "loss": 0.6481,
      "step": 111
    },
    {
      "epoch": 4.17,
      "learning_rate": 6.180594523575838e-05,
      "loss": 0.6209,
      "step": 112
    },
    {
      "epoch": 4.2,
      "learning_rate": 6.121115549206949e-05,
      "loss": 0.6125,
      "step": 113
    },
    {
      "epoch": 4.24,
      "learning_rate": 6.061469050285469e-05,
      "loss": 0.6703,
      "step": 114
    },
    {
      "epoch": 4.28,
      "learning_rate": 6.001663939588542e-05,
      "loss": 0.6821,
      "step": 115
    },
    {
      "epoch": 4.32,
      "learning_rate": 5.941709153594146e-05,
      "loss": 0.6885,
      "step": 116
    },
    {
      "epoch": 4.35,
      "learning_rate": 5.881613651145732e-05,
      "loss": 0.6598,
      "step": 117
    },
    {
      "epoch": 4.35,
      "eval_loss": 0.8761024475097656,
      "eval_runtime": 34.7313,
      "eval_samples_per_second": 1.44,
      "eval_steps_per_second": 1.44,
      "step": 117
    },
    {
      "epoch": 4.39,
      "learning_rate": 5.821386412113545e-05,
      "loss": 0.6081,
      "step": 118
    },
    {
      "epoch": 4.43,
      "learning_rate": 5.761036436052788e-05,
      "loss": 0.6263,
      "step": 119
    },
    {
      "epoch": 4.47,
      "learning_rate": 5.700572740858847e-05,
      "loss": 0.6068,
      "step": 120
    },
    {
      "epoch": 4.5,
      "learning_rate": 5.640004361419776e-05,
      "loss": 0.626,
      "step": 121
    },
    {
      "epoch": 4.54,
      "learning_rate": 5.579340348266251e-05,
      "loss": 0.6514,
      "step": 122
    },
    {
      "epoch": 4.58,
      "learning_rate": 5.518589766219172e-05,
      "loss": 0.6156,
      "step": 123
    },
    {
      "epoch": 4.61,
      "learning_rate": 5.4577616930351385e-05,
      "loss": 0.6637,
      "step": 124
    },
    {
      "epoch": 4.65,
      "learning_rate": 5.396865218049995e-05,
      "loss": 0.6058,
      "step": 125
    },
    {
      "epoch": 4.69,
      "learning_rate": 5.3359094408206345e-05,
      "loss": 0.6208,
      "step": 126
    },
    {
      "epoch": 4.73,
      "learning_rate": 5.27490346976529e-05,
      "loss": 0.6259,
      "step": 127
    },
    {
      "epoch": 4.76,
      "learning_rate": 5.21385642080249e-05,
      "loss": 0.6001,
      "step": 128
    },
    {
      "epoch": 4.8,
      "learning_rate": 5.152777415988894e-05,
      "loss": 0.6447,
      "step": 129
    },
    {
      "epoch": 4.84,
      "learning_rate": 5.0916755821562237e-05,
      "loss": 0.5753,
      "step": 130
    },
    {
      "epoch": 4.84,
      "eval_loss": 0.8741121888160706,
      "eval_runtime": 34.7416,
      "eval_samples_per_second": 1.439,
      "eval_steps_per_second": 1.439,
      "step": 130
    },
    {
      "epoch": 4.87,
      "learning_rate": 5.030560049547458e-05,
      "loss": 0.6011,
      "step": 131
    },
    {
      "epoch": 4.91,
      "learning_rate": 4.969439950452543e-05,
      "loss": 0.6303,
      "step": 132
    },
    {
      "epoch": 4.95,
      "learning_rate": 4.908324417843778e-05,
      "loss": 0.6238,
      "step": 133
    },
    {
      "epoch": 4.99,
      "learning_rate": 4.847222584011106e-05,
      "loss": 0.623,
      "step": 134
    },
    {
      "epoch": 5.02,
      "learning_rate": 4.7861435791975126e-05,
      "loss": 0.5594,
      "step": 135
    },
    {
      "epoch": 5.06,
      "learning_rate": 4.72509653023471e-05,
      "loss": 0.5714,
      "step": 136
    },
    {
      "epoch": 5.1,
      "learning_rate": 4.664090559179367e-05,
      "loss": 0.6115,
      "step": 137
    },
    {
      "epoch": 5.13,
      "learning_rate": 4.603134781950006e-05,
      "loss": 0.5987,
      "step": 138
    },
    {
      "epoch": 5.17,
      "learning_rate": 4.542238306964863e-05,
      "loss": 0.5588,
      "step": 139
    },
    {
      "epoch": 5.21,
      "learning_rate": 4.4814102337808293e-05,
      "loss": 0.5612,
      "step": 140
    },
    {
      "epoch": 5.25,
      "learning_rate": 4.420659651733751e-05,
      "loss": 0.5595,
      "step": 141
    },
    {
      "epoch": 5.28,
      "learning_rate": 4.359995638580226e-05,
      "loss": 0.5534,
      "step": 142
    },
    {
      "epoch": 5.32,
      "learning_rate": 4.2994272591411556e-05,
      "loss": 0.5499,
      "step": 143
    },
    {
      "epoch": 5.32,
      "eval_loss": 0.897064745426178,
      "eval_runtime": 34.7112,
      "eval_samples_per_second": 1.44,
      "eval_steps_per_second": 1.44,
      "step": 143
    },
    {
      "epoch": 5.36,
      "learning_rate": 4.238963563947212e-05,
      "loss": 0.5902,
      "step": 144
    },
    {
      "epoch": 5.4,
      "learning_rate": 4.178613587886455e-05,
      "loss": 0.5371,
      "step": 145
    },
    {
      "epoch": 5.43,
      "learning_rate": 4.118386348854269e-05,
      "loss": 0.5798,
      "step": 146
    },
    {
      "epoch": 5.47,
      "learning_rate": 4.0582908464058556e-05,
      "loss": 0.5681,
      "step": 147
    },
    {
      "epoch": 5.51,
      "learning_rate": 3.998336060411459e-05,
      "loss": 0.5851,
      "step": 148
    },
    {
      "epoch": 5.54,
      "learning_rate": 3.938530949714533e-05,
      "loss": 0.5849,
      "step": 149
    },
    {
      "epoch": 5.58,
      "learning_rate": 3.878884450793053e-05,
      "loss": 0.5968,
      "step": 150
    },
    {
      "epoch": 5.62,
      "learning_rate": 3.819405476424163e-05,
      "loss": 0.5533,
      "step": 151
    },
    {
      "epoch": 5.66,
      "learning_rate": 3.7601029143523764e-05,
      "loss": 0.5724,
      "step": 152
    },
    {
      "epoch": 5.69,
      "learning_rate": 3.700985625961507e-05,
      "loss": 0.5314,
      "step": 153
    },
    {
      "epoch": 5.73,
      "learning_rate": 3.642062444950537e-05,
      "loss": 0.5572,
      "step": 154
    },
    {
      "epoch": 5.77,
      "learning_rate": 3.5833421760136324e-05,
      "loss": 0.5895,
      "step": 155
    },
    {
      "epoch": 5.8,
      "learning_rate": 3.524833593524487e-05,
      "loss": 0.5349,
      "step": 156
    },
    {
      "epoch": 5.8,
      "eval_loss": 0.8920581936836243,
      "eval_runtime": 34.8827,
      "eval_samples_per_second": 1.433,
      "eval_steps_per_second": 1.433,
      "step": 156
    },
    {
      "epoch": 5.8,
      "step": 156,
      "total_flos": 6.16421344002048e+17,
      "train_loss": 0.8834368617106707,
      "train_runtime": 13302.0563,
      "train_samples_per_second": 0.97,
      "train_steps_per_second": 0.02
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 260,
  "num_train_epochs": 10,
  "save_steps": 26,
  "total_flos": 6.16421344002048e+17,
  "trial_name": null,
  "trial_params": null
}