{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.19047619047619,
  "eval_steps": 500,
  "global_step": 160,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.3809523809523808e-06,
      "loss": 1.4962,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.7619047619047615e-06,
      "loss": 1.5498,
      "step": 2
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.142857142857143e-06,
      "loss": 1.4765,
      "step": 3
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.523809523809523e-06,
      "loss": 1.4702,
      "step": 4
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.1904761904761905e-05,
      "loss": 1.4907,
      "step": 5
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 1.4473,
      "step": 6
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.4735,
      "step": 7
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9047619047619046e-05,
      "loss": 1.4303,
      "step": 8
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 1.3977,
      "step": 9
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.380952380952381e-05,
      "loss": 1.4021,
      "step": 10
    },
    {
      "epoch": 0.13,
      "learning_rate": 2.6190476190476192e-05,
      "loss": 1.3709,
      "step": 11
    },
    {
      "epoch": 0.14,
      "learning_rate": 2.857142857142857e-05,
      "loss": 1.3842,
      "step": 12
    },
    {
      "epoch": 0.15,
      "learning_rate": 3.095238095238095e-05,
      "loss": 1.3646,
      "step": 13
    },
    {
      "epoch": 0.17,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.3196,
      "step": 14
    },
    {
      "epoch": 0.18,
      "learning_rate": 3.571428571428572e-05,
      "loss": 1.2991,
      "step": 15
    },
    {
      "epoch": 0.19,
      "learning_rate": 3.809523809523809e-05,
      "loss": 1.2953,
      "step": 16
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.047619047619048e-05,
      "loss": 1.2344,
      "step": 17
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 1.2148,
      "step": 18
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.523809523809524e-05,
      "loss": 1.2092,
      "step": 19
    },
    {
      "epoch": 1.05,
      "learning_rate": 4.761904761904762e-05,
      "loss": 1.154,
      "step": 20
    },
    {
      "epoch": 1.06,
      "learning_rate": 5e-05,
      "loss": 1.1733,
      "step": 21
    },
    {
      "epoch": 1.07,
      "learning_rate": 5.2380952380952384e-05,
      "loss": 1.1218,
      "step": 22
    },
    {
      "epoch": 1.08,
      "learning_rate": 5.4761904761904766e-05,
      "loss": 1.1347,
      "step": 23
    },
    {
      "epoch": 1.1,
      "learning_rate": 5.714285714285714e-05,
      "loss": 1.1216,
      "step": 24
    },
    {
      "epoch": 1.11,
      "learning_rate": 5.9523809523809524e-05,
      "loss": 1.0923,
      "step": 25
    },
    {
      "epoch": 1.12,
      "learning_rate": 6.19047619047619e-05,
      "loss": 1.0948,
      "step": 26
    },
    {
      "epoch": 1.13,
      "learning_rate": 6.428571428571429e-05,
      "loss": 1.0617,
      "step": 27
    },
    {
      "epoch": 1.14,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.033,
      "step": 28
    },
    {
      "epoch": 1.15,
      "learning_rate": 6.904761904761905e-05,
      "loss": 1.0342,
      "step": 29
    },
    {
      "epoch": 1.17,
      "learning_rate": 7.142857142857143e-05,
      "loss": 1.0059,
      "step": 30
    },
    {
      "epoch": 1.18,
      "learning_rate": 7.380952380952382e-05,
      "loss": 0.9941,
      "step": 31
    },
    {
      "epoch": 1.19,
      "learning_rate": 7.619047619047618e-05,
      "loss": 0.9912,
      "step": 32
    },
    {
      "epoch": 2.01,
      "learning_rate": 7.857142857142858e-05,
      "loss": 0.9595,
      "step": 33
    },
    {
      "epoch": 2.02,
      "learning_rate": 8.095238095238096e-05,
      "loss": 0.9719,
      "step": 34
    },
    {
      "epoch": 2.04,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.9437,
      "step": 35
    },
    {
      "epoch": 2.05,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.9174,
      "step": 36
    },
    {
      "epoch": 2.06,
      "learning_rate": 8.80952380952381e-05,
      "loss": 0.9494,
      "step": 37
    },
    {
      "epoch": 2.07,
      "learning_rate": 9.047619047619048e-05,
      "loss": 0.8654,
      "step": 38
    },
    {
      "epoch": 2.08,
      "learning_rate": 9.285714285714286e-05,
      "loss": 0.8685,
      "step": 39
    },
    {
      "epoch": 2.1,
      "learning_rate": 9.523809523809524e-05,
      "loss": 0.8946,
      "step": 40
    },
    {
      "epoch": 2.11,
      "learning_rate": 9.761904761904762e-05,
      "loss": 0.875,
      "step": 41
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0001,
      "loss": 0.827,
      "step": 42
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00010238095238095237,
      "loss": 0.8373,
      "step": 43
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00010476190476190477,
      "loss": 0.8291,
      "step": 44
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00010714285714285715,
      "loss": 0.8238,
      "step": 45
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00010952380952380953,
      "loss": 0.7971,
      "step": 46
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00011190476190476191,
      "loss": 0.7925,
      "step": 47
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00011428571428571428,
      "loss": 0.7865,
      "step": 48
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.00011666666666666668,
      "loss": 0.7714,
      "step": 49
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.00011904761904761905,
      "loss": 0.7508,
      "step": 50
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.00012142857142857143,
      "loss": 0.7757,
      "step": 51
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.0001238095238095238,
      "loss": 0.7479,
      "step": 52
    },
    {
      "epoch": 3.06,
      "learning_rate": 0.0001261904761904762,
      "loss": 0.7393,
      "step": 53
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.00012857142857142858,
      "loss": 0.7341,
      "step": 54
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.00013095238095238096,
      "loss": 0.7271,
      "step": 55
    },
    {
      "epoch": 3.1,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.7134,
      "step": 56
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.00013571428571428572,
      "loss": 0.7295,
      "step": 57
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.0001380952380952381,
      "loss": 0.7143,
      "step": 58
    },
    {
      "epoch": 3.13,
      "learning_rate": 0.00014047619047619049,
      "loss": 0.6903,
      "step": 59
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.00014285714285714287,
      "loss": 0.7002,
      "step": 60
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.00014523809523809525,
      "loss": 0.6684,
      "step": 61
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.00014761904761904763,
      "loss": 0.6841,
      "step": 62
    },
    {
      "epoch": 3.18,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.6641,
      "step": 63
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.00015238095238095237,
      "loss": 0.6571,
      "step": 64
    },
    {
      "epoch": 4.01,
      "learning_rate": 0.00015476190476190478,
      "loss": 0.6287,
      "step": 65
    },
    {
      "epoch": 4.02,
      "learning_rate": 0.00015714285714285716,
      "loss": 0.6545,
      "step": 66
    },
    {
      "epoch": 4.04,
      "learning_rate": 0.00015952380952380954,
      "loss": 0.63,
      "step": 67
    },
    {
      "epoch": 4.05,
      "learning_rate": 0.00016190476190476192,
      "loss": 0.639,
      "step": 68
    },
    {
      "epoch": 4.06,
      "learning_rate": 0.00016428571428571428,
      "loss": 0.6242,
      "step": 69
    },
    {
      "epoch": 4.07,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.6127,
      "step": 70
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.00016904761904761904,
      "loss": 0.5939,
      "step": 71
    },
    {
      "epoch": 4.1,
      "learning_rate": 0.00017142857142857143,
      "loss": 0.6449,
      "step": 72
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.00017380952380952383,
      "loss": 0.6348,
      "step": 73
    },
    {
      "epoch": 4.12,
      "learning_rate": 0.0001761904761904762,
      "loss": 0.6129,
      "step": 74
    },
    {
      "epoch": 4.13,
      "learning_rate": 0.0001785714285714286,
      "loss": 0.587,
      "step": 75
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.00018095238095238095,
      "loss": 0.5818,
      "step": 76
    },
    {
      "epoch": 4.15,
      "learning_rate": 0.00018333333333333334,
      "loss": 0.5803,
      "step": 77
    },
    {
      "epoch": 4.17,
      "learning_rate": 0.00018571428571428572,
      "loss": 0.6319,
      "step": 78
    },
    {
      "epoch": 4.18,
      "learning_rate": 0.0001880952380952381,
      "loss": 0.6171,
      "step": 79
    },
    {
      "epoch": 4.19,
      "learning_rate": 0.00019047619047619048,
      "loss": 0.5772,
      "step": 80
    },
    {
      "epoch": 5.01,
      "learning_rate": 0.00019285714285714286,
      "loss": 0.5688,
      "step": 81
    },
    {
      "epoch": 5.02,
      "learning_rate": 0.00019523809523809525,
      "loss": 0.5648,
      "step": 82
    },
    {
      "epoch": 5.04,
      "learning_rate": 0.00019761904761904763,
      "loss": 0.5557,
      "step": 83
    },
    {
      "epoch": 5.05,
      "learning_rate": 0.0002,
      "loss": 0.5314,
      "step": 84
    },
    {
      "epoch": 5.06,
      "learning_rate": 0.0001999991365731819,
      "loss": 0.5659,
      "step": 85
    },
    {
      "epoch": 5.07,
      "learning_rate": 0.0001999965463076377,
      "loss": 0.5497,
      "step": 86
    },
    {
      "epoch": 5.08,
      "learning_rate": 0.0001999922292480975,
      "loss": 0.5202,
      "step": 87
    },
    {
      "epoch": 5.1,
      "learning_rate": 0.00019998618546911056,
      "loss": 0.5209,
      "step": 88
    },
    {
      "epoch": 5.11,
      "learning_rate": 0.0001999784150750442,
      "loss": 0.5657,
      "step": 89
    },
    {
      "epoch": 5.12,
      "learning_rate": 0.00019996891820008164,
      "loss": 0.5286,
      "step": 90
    },
    {
      "epoch": 5.13,
      "learning_rate": 0.0001999576950082201,
      "loss": 0.5218,
      "step": 91
    },
    {
      "epoch": 5.14,
      "learning_rate": 0.00019994474569326757,
      "loss": 0.5362,
      "step": 92
    },
    {
      "epoch": 5.15,
      "learning_rate": 0.00019993007047883988,
      "loss": 0.5371,
      "step": 93
    },
    {
      "epoch": 5.17,
      "learning_rate": 0.00019991366961835642,
      "loss": 0.5427,
      "step": 94
    },
    {
      "epoch": 5.18,
      "learning_rate": 0.00019989554339503612,
      "loss": 0.5583,
      "step": 95
    },
    {
      "epoch": 5.19,
      "learning_rate": 0.00019987569212189224,
      "loss": 0.5376,
      "step": 96
    },
    {
      "epoch": 6.01,
      "learning_rate": 0.0001998541161417273,
      "loss": 0.5138,
      "step": 97
    },
    {
      "epoch": 6.02,
      "learning_rate": 0.00019983081582712685,
      "loss": 0.5236,
      "step": 98
    },
    {
      "epoch": 6.04,
      "learning_rate": 0.0001998057915804532,
      "loss": 0.4955,
      "step": 99
    },
    {
      "epoch": 6.05,
      "learning_rate": 0.0001997790438338385,
      "loss": 0.4824,
      "step": 100
    },
    {
      "epoch": 6.06,
      "learning_rate": 0.00019975057304917718,
      "loss": 0.464,
      "step": 101
    },
    {
      "epoch": 6.07,
      "learning_rate": 0.00019972037971811802,
      "loss": 0.4967,
      "step": 102
    },
    {
      "epoch": 6.08,
      "learning_rate": 0.00019968846436205567,
      "loss": 0.4571,
      "step": 103
    },
    {
      "epoch": 6.1,
      "learning_rate": 0.00019965482753212156,
      "loss": 0.4994,
      "step": 104
    },
    {
      "epoch": 6.11,
      "learning_rate": 0.00019961946980917456,
      "loss": 0.4789,
      "step": 105
    },
    {
      "epoch": 6.12,
      "learning_rate": 0.0001995823918037908,
      "loss": 0.4653,
      "step": 106
    },
    {
      "epoch": 6.13,
      "learning_rate": 0.0001995435941562531,
      "loss": 0.489,
      "step": 107
    },
    {
      "epoch": 6.14,
      "learning_rate": 0.00019950307753654017,
      "loss": 0.501,
      "step": 108
    },
    {
      "epoch": 6.15,
      "learning_rate": 0.00019946084264431459,
      "loss": 0.462,
      "step": 109
    },
    {
      "epoch": 6.17,
      "learning_rate": 0.0001994168902089112,
      "loss": 0.4511,
      "step": 110
    },
    {
      "epoch": 6.18,
      "learning_rate": 0.00019937122098932428,
      "loss": 0.4744,
      "step": 111
    },
    {
      "epoch": 6.19,
      "learning_rate": 0.00019932383577419432,
      "loss": 0.4991,
      "step": 112
    },
    {
      "epoch": 7.01,
      "learning_rate": 0.00019927473538179467,
      "loss": 0.4277,
      "step": 113
    },
    {
      "epoch": 7.02,
      "learning_rate": 0.00019922392066001722,
      "loss": 0.4083,
      "step": 114
    },
    {
      "epoch": 7.04,
      "learning_rate": 0.00019917139248635786,
      "loss": 0.424,
      "step": 115
    },
    {
      "epoch": 7.05,
      "learning_rate": 0.0001991171517679013,
      "loss": 0.4305,
      "step": 116
    },
    {
      "epoch": 7.06,
      "learning_rate": 0.0001990611994413053,
      "loss": 0.4379,
      "step": 117
    },
    {
      "epoch": 7.07,
      "learning_rate": 0.00019900353647278466,
      "loss": 0.4251,
      "step": 118
    },
    {
      "epoch": 7.08,
      "learning_rate": 0.00019894416385809444,
      "loss": 0.4367,
      "step": 119
    },
    {
      "epoch": 7.1,
      "learning_rate": 0.00019888308262251285,
      "loss": 0.4524,
      "step": 120
    },
    {
      "epoch": 7.11,
      "learning_rate": 0.0001988202938208234,
      "loss": 0.4351,
      "step": 121
    },
    {
      "epoch": 7.12,
      "learning_rate": 0.00019875579853729676,
      "loss": 0.4269,
      "step": 122
    },
    {
      "epoch": 7.13,
      "learning_rate": 0.00019868959788567212,
      "loss": 0.4128,
      "step": 123
    },
    {
      "epoch": 7.14,
      "learning_rate": 0.00019862169300913785,
      "loss": 0.4383,
      "step": 124
    },
    {
      "epoch": 7.15,
      "learning_rate": 0.0001985520850803117,
      "loss": 0.43,
      "step": 125
    },
    {
      "epoch": 7.17,
      "learning_rate": 0.00019848077530122083,
      "loss": 0.4613,
      "step": 126
    },
    {
      "epoch": 7.18,
      "learning_rate": 0.00019840776490328066,
      "loss": 0.4438,
      "step": 127
    },
    {
      "epoch": 7.19,
      "learning_rate": 0.00019833305514727395,
      "loss": 0.4393,
      "step": 128
    },
    {
      "epoch": 8.01,
      "learning_rate": 0.00019825664732332884,
      "loss": 0.4018,
      "step": 129
    },
    {
      "epoch": 8.02,
      "learning_rate": 0.0001981785427508966,
      "loss": 0.3602,
      "step": 130
    },
    {
      "epoch": 8.04,
      "learning_rate": 0.00019809874277872886,
      "loss": 0.3728,
      "step": 131
    },
    {
      "epoch": 8.05,
      "learning_rate": 0.00019801724878485438,
      "loss": 0.3727,
      "step": 132
    },
    {
      "epoch": 8.06,
      "learning_rate": 0.00019793406217655517,
      "loss": 0.3898,
      "step": 133
    },
    {
      "epoch": 8.07,
      "learning_rate": 0.00019784918439034216,
      "loss": 0.3964,
      "step": 134
    },
    {
      "epoch": 8.08,
      "learning_rate": 0.00019776261689193048,
      "loss": 0.3741,
      "step": 135
    },
    {
      "epoch": 8.1,
      "learning_rate": 0.00019767436117621413,
      "loss": 0.3853,
      "step": 136
    },
    {
      "epoch": 8.11,
      "learning_rate": 0.00019758441876724017,
      "loss": 0.3783,
      "step": 137
    },
    {
      "epoch": 8.12,
      "learning_rate": 0.00019749279121818235,
      "loss": 0.3946,
      "step": 138
    },
    {
      "epoch": 8.13,
      "learning_rate": 0.00019739948011131438,
      "loss": 0.382,
      "step": 139
    },
    {
      "epoch": 8.14,
      "learning_rate": 0.00019730448705798239,
      "loss": 0.3858,
      "step": 140
    },
    {
      "epoch": 8.15,
      "learning_rate": 0.00019720781369857746,
      "loss": 0.3769,
      "step": 141
    },
    {
      "epoch": 8.17,
      "learning_rate": 0.000197109461702507,
      "loss": 0.3988,
      "step": 142
    },
    {
      "epoch": 8.18,
      "learning_rate": 0.00019700943276816603,
      "loss": 0.388,
      "step": 143
    },
    {
      "epoch": 8.19,
      "learning_rate": 0.0001969077286229078,
      "loss": 0.3886,
      "step": 144
    },
    {
      "epoch": 9.01,
      "learning_rate": 0.00019680435102301412,
      "loss": 0.3481,
      "step": 145
    },
    {
      "epoch": 9.02,
      "learning_rate": 0.00019669930175366472,
      "loss": 0.3392,
      "step": 146
    },
    {
      "epoch": 9.04,
      "learning_rate": 0.00019659258262890683,
      "loss": 0.3199,
      "step": 147
    },
    {
      "epoch": 9.05,
      "learning_rate": 0.00019648419549162348,
      "loss": 0.3502,
      "step": 148
    },
    {
      "epoch": 9.06,
      "learning_rate": 0.00019637414221350196,
      "loss": 0.3302,
      "step": 149
    },
    {
      "epoch": 9.07,
      "learning_rate": 0.0001962624246950012,
      "loss": 0.3369,
      "step": 150
    },
    {
      "epoch": 9.08,
      "learning_rate": 0.00019614904486531934,
      "loss": 0.3271,
      "step": 151
    },
    {
      "epoch": 9.1,
      "learning_rate": 0.00019603400468235998,
      "loss": 0.331,
      "step": 152
    },
    {
      "epoch": 9.11,
      "learning_rate": 0.0001959173061326988,
      "loss": 0.3368,
      "step": 153
    },
    {
      "epoch": 9.12,
      "learning_rate": 0.0001957989512315489,
      "loss": 0.3282,
      "step": 154
    },
    {
      "epoch": 9.13,
      "learning_rate": 0.0001956789420227262,
      "loss": 0.3251,
      "step": 155
    },
    {
      "epoch": 9.14,
      "learning_rate": 0.0001955572805786141,
      "loss": 0.3312,
      "step": 156
    },
    {
      "epoch": 9.15,
      "learning_rate": 0.00019543396900012763,
      "loss": 0.3673,
      "step": 157
    },
    {
      "epoch": 9.17,
      "learning_rate": 0.0001953090094166773,
      "loss": 0.3287,
      "step": 158
    },
    {
      "epoch": 9.18,
      "learning_rate": 0.00019518240398613227,
      "loss": 0.3374,
      "step": 159
    },
    {
      "epoch": 9.19,
      "learning_rate": 0.0001950541548947829,
      "loss": 0.3209,
      "step": 160
    }
  ],
  "logging_steps": 1,
  "max_steps": 840,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 8.39611613970432e+16,
  "trial_name": null,
  "trial_params": null
}