{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9994691205096443,
  "eval_steps": 20,
  "global_step": 353,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 3.9795,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.000000000000001e-06,
      "loss": 3.2944,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2e-05,
      "loss": 4.0746,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 4.1905,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 2e-05,
      "loss": 4.4667,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.4e-05,
      "loss": 4.8488,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 4.1473,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 3.7834,
      "step": 8
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.6e-05,
      "loss": 3.2778,
      "step": 9
    },
    {
      "epoch": 0.03,
      "learning_rate": 4e-05,
      "loss": 3.1975,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 2.7504,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.8e-05,
      "loss": 2.5047,
      "step": 12
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 2.3366,
      "step": 13
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 2.1348,
      "step": 14
    },
    {
      "epoch": 0.04,
      "learning_rate": 6e-05,
      "loss": 1.6171,
      "step": 15
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.2901,
      "step": 16
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.800000000000001e-05,
      "loss": 1.1358,
      "step": 17
    },
    {
      "epoch": 0.05,
      "learning_rate": 7.2e-05,
      "loss": 0.9456,
      "step": 18
    },
    {
      "epoch": 0.05,
      "learning_rate": 7.6e-05,
      "loss": 0.8864,
      "step": 19
    },
    {
      "epoch": 0.06,
      "learning_rate": 8e-05,
      "loss": 0.8756,
      "step": 20
    },
    {
      "epoch": 0.06,
      "eval_loss": 0.7110548615455627,
      "eval_runtime": 29.5129,
      "eval_samples_per_second": 55.196,
      "eval_steps_per_second": 55.196,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.4e-05,
      "loss": 0.8825,
      "step": 21
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.822,
      "step": 22
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.8001,
      "step": 23
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.6e-05,
      "loss": 0.8978,
      "step": 24
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001,
      "loss": 0.8214,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00010400000000000001,
      "loss": 0.8012,
      "step": 26
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00010800000000000001,
      "loss": 0.9169,
      "step": 27
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00011200000000000001,
      "loss": 0.8436,
      "step": 28
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000116,
      "loss": 0.738,
      "step": 29
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00012,
      "loss": 0.8238,
      "step": 30
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000124,
      "loss": 0.85,
      "step": 31
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00012800000000000002,
      "loss": 0.8292,
      "step": 32
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000132,
      "loss": 0.8739,
      "step": 33
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00013600000000000003,
      "loss": 0.8456,
      "step": 34
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00014,
      "loss": 0.7558,
      "step": 35
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000144,
      "loss": 0.6982,
      "step": 36
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000148,
      "loss": 0.7985,
      "step": 37
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000152,
      "loss": 0.7995,
      "step": 38
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.5988,
      "step": 39
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00016,
      "loss": 0.9058,
      "step": 40
    },
    {
      "epoch": 0.11,
      "eval_loss": 0.6764179468154907,
      "eval_runtime": 29.6679,
      "eval_samples_per_second": 54.908,
      "eval_steps_per_second": 54.908,
      "step": 40
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000164,
      "loss": 0.8351,
      "step": 41
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000168,
      "loss": 0.8182,
      "step": 42
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000172,
      "loss": 0.8694,
      "step": 43
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.7743,
      "step": 44
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00018,
      "loss": 0.7448,
      "step": 45
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.8416,
      "step": 46
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000188,
      "loss": 0.7496,
      "step": 47
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000192,
      "loss": 0.7353,
      "step": 48
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000196,
      "loss": 0.9026,
      "step": 49
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.8415,
      "step": 50
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00020400000000000003,
      "loss": 0.7606,
      "step": 51
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00020800000000000001,
      "loss": 0.743,
      "step": 52
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00021200000000000003,
      "loss": 0.7478,
      "step": 53
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00021600000000000002,
      "loss": 0.6924,
      "step": 54
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00022000000000000003,
      "loss": 0.9163,
      "step": 55
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00022400000000000002,
      "loss": 0.7332,
      "step": 56
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00022799999999999999,
      "loss": 0.7678,
      "step": 57
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000232,
      "loss": 0.7561,
      "step": 58
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000236,
      "loss": 0.8494,
      "step": 59
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00024,
      "loss": 0.7526,
      "step": 60
    },
    {
      "epoch": 0.17,
      "eval_loss": 0.6668684482574463,
      "eval_runtime": 29.5308,
      "eval_samples_per_second": 55.163,
      "eval_steps_per_second": 55.163,
      "step": 60
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000244,
      "loss": 0.7944,
      "step": 61
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000248,
      "loss": 0.7107,
      "step": 62
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000252,
      "loss": 0.7443,
      "step": 63
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00025600000000000004,
      "loss": 0.7802,
      "step": 64
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00026000000000000003,
      "loss": 0.6785,
      "step": 65
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000264,
      "loss": 0.7853,
      "step": 66
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000268,
      "loss": 0.8059,
      "step": 67
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00027200000000000005,
      "loss": 0.6702,
      "step": 68
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000276,
      "loss": 0.7784,
      "step": 69
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00028,
      "loss": 0.7447,
      "step": 70
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000284,
      "loss": 0.6466,
      "step": 71
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000288,
      "loss": 0.6549,
      "step": 72
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000292,
      "loss": 0.6841,
      "step": 73
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000296,
      "loss": 0.6441,
      "step": 74
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00030000000000000003,
      "loss": 0.6777,
      "step": 75
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000304,
      "loss": 0.7301,
      "step": 76
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000308,
      "loss": 0.692,
      "step": 77
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00031200000000000005,
      "loss": 0.7697,
      "step": 78
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00031600000000000004,
      "loss": 0.6374,
      "step": 79
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00032,
      "loss": 0.6926,
      "step": 80
    },
    {
      "epoch": 0.23,
      "eval_loss": 0.6363404989242554,
      "eval_runtime": 29.5123,
      "eval_samples_per_second": 55.197,
      "eval_steps_per_second": 55.197,
      "step": 80
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000324,
      "loss": 0.7258,
      "step": 81
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000328,
      "loss": 0.6556,
      "step": 82
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000332,
      "loss": 0.6122,
      "step": 83
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000336,
      "loss": 0.6915,
      "step": 84
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00034,
      "loss": 0.7711,
      "step": 85
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000344,
      "loss": 0.6637,
      "step": 86
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000348,
      "loss": 0.635,
      "step": 87
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00035200000000000005,
      "loss": 0.648,
      "step": 88
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00035600000000000003,
      "loss": 0.6904,
      "step": 89
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00036,
      "loss": 0.7026,
      "step": 90
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000364,
      "loss": 0.6285,
      "step": 91
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00036800000000000005,
      "loss": 0.6239,
      "step": 92
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00037200000000000004,
      "loss": 0.6897,
      "step": 93
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000376,
      "loss": 0.6162,
      "step": 94
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00038,
      "loss": 0.6414,
      "step": 95
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000384,
      "loss": 0.637,
      "step": 96
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000388,
      "loss": 0.7453,
      "step": 97
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000392,
      "loss": 0.6462,
      "step": 98
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00039600000000000003,
      "loss": 0.6717,
      "step": 99
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0004,
      "loss": 0.6731,
      "step": 100
    },
    {
      "epoch": 0.28,
      "eval_loss": 0.6186901926994324,
      "eval_runtime": 29.5468,
      "eval_samples_per_second": 55.133,
      "eval_steps_per_second": 55.133,
      "step": 100
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00039999731246874025,
      "loss": 0.6801,
      "step": 101
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003999892499471893,
      "loss": 0.6285,
      "step": 102
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00039997581265202993,
      "loss": 0.6436,
      "step": 103
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003999570009443936,
      "loss": 0.7124,
      "step": 104
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00039993281532985087,
      "loss": 0.6157,
      "step": 105
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00039990325645839766,
      "loss": 0.6532,
      "step": 106
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003998683251244379,
      "loss": 0.6072,
      "step": 107
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003998280222667621,
      "loss": 0.6871,
      "step": 108
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00039978234896852216,
      "loss": 0.6139,
      "step": 109
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003997313064572023,
      "loss": 0.7056,
      "step": 110
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003996748961045859,
      "loss": 0.5983,
      "step": 111
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003996131194267189,
      "loss": 0.5374,
      "step": 112
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00039954597808386874,
      "loss": 0.6804,
      "step": 113
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00039947347388048,
      "loss": 0.6254,
      "step": 114
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00039939560876512585,
      "loss": 0.7221,
      "step": 115
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003993123848304556,
      "loss": 0.6417,
      "step": 116
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003992238043131386,
      "loss": 0.4836,
      "step": 117
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003991298695938038,
      "loss": 0.6186,
      "step": 118
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003990305831969761,
      "loss": 0.6362,
      "step": 119
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00039892594779100866,
      "loss": 0.647,
      "step": 120
    },
    {
      "epoch": 0.34,
      "eval_loss": 0.6162068843841553,
      "eval_runtime": 29.5244,
      "eval_samples_per_second": 55.175,
      "eval_steps_per_second": 55.175,
      "step": 120
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003988159661880105,
      "loss": 0.5818,
      "step": 121
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003987006413437718,
      "loss": 0.6267,
      "step": 122
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00039857997635768365,
      "loss": 0.5502,
      "step": 123
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00039845397447265535,
      "loss": 0.6438,
      "step": 124
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00039832263907502684,
      "loss": 0.6472,
      "step": 125
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003981859736944781,
      "loss": 0.6834,
      "step": 126
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00039804398200393395,
      "loss": 0.6091,
      "step": 127
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003978966678194653,
      "loss": 0.58,
      "step": 128
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00039774403510018714,
      "loss": 0.5988,
      "step": 129
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003975860879481514,
      "loss": 0.6177,
      "step": 130
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00039742283060823706,
      "loss": 0.5535,
      "step": 131
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003972542674680364,
      "loss": 0.7208,
      "step": 132
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003970804030577363,
      "loss": 0.626,
      "step": 133
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003969012420499972,
      "loss": 0.5747,
      "step": 134
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00039671678925982723,
      "loss": 0.5567,
      "step": 135
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00039652704964445275,
      "loss": 0.6814,
      "step": 136
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00039633202830318526,
      "loss": 0.5917,
      "step": 137
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003961317304772842,
      "loss": 0.5793,
      "step": 138
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00039592616154981633,
      "loss": 0.6533,
      "step": 139
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00039571532704551083,
      "loss": 0.6219,
      "step": 140
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.6040534377098083,
      "eval_runtime": 29.5629,
      "eval_samples_per_second": 55.103,
      "eval_steps_per_second": 55.103,
      "step": 140
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003954992326306109,
      "loss": 0.5167,
      "step": 141
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00039527788411272143,
      "loss": 0.6516,
      "step": 142
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00039505128744065314,
      "loss": 0.607,
      "step": 143
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003948194487042623,
      "loss": 0.6482,
      "step": 144
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003945823741342875,
      "loss": 0.6133,
      "step": 145
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003943400701021819,
      "loss": 0.5582,
      "step": 146
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00039409254311994216,
      "loss": 0.5985,
      "step": 147
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00039383979983993327,
      "loss": 0.5648,
      "step": 148
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003935818470547098,
      "loss": 0.5884,
      "step": 149
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00039331869169683363,
      "loss": 0.5948,
      "step": 150
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003930503408386871,
      "loss": 0.5532,
      "step": 151
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00039277680169228364,
      "loss": 0.6034,
      "step": 152
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003924980816090731,
      "loss": 0.6522,
      "step": 153
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003922141880797449,
      "loss": 0.6142,
      "step": 154
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003919251287340265,
      "loss": 0.5816,
      "step": 155
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000391630911340478,
      "loss": 0.5686,
      "step": 156
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00039133154380628394,
      "loss": 0.6053,
      "step": 157
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003910270341770404,
      "loss": 0.7025,
      "step": 158
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00039071739063653875,
      "loss": 0.5625,
      "step": 159
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00039040262150654597,
      "loss": 0.5781,
      "step": 160
    },
    {
      "epoch": 0.45,
      "eval_loss": 0.593679666519165,
      "eval_runtime": 29.5229,
      "eval_samples_per_second": 55.178,
      "eval_steps_per_second": 55.178,
      "step": 160
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00039008273524658094,
      "loss": 0.603,
      "step": 161
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003897577404536867,
      "loss": 0.5789,
      "step": 162
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00038942764586220006,
      "loss": 0.6881,
      "step": 163
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00038909246034351624,
      "loss": 0.6034,
      "step": 164
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00038875219290585093,
      "loss": 0.5881,
      "step": 165
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003884068526939978,
      "loss": 0.6318,
      "step": 166
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00038805644898908307,
      "loss": 0.5383,
      "step": 167
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003877009912083159,
      "loss": 0.5284,
      "step": 168
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00038734048890473507,
      "loss": 0.5723,
      "step": 169
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00038697495176695274,
      "loss": 0.6311,
      "step": 170
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00038660438961889387,
      "loss": 0.6043,
      "step": 171
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00038622881241953195,
      "loss": 0.5023,
      "step": 172
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003858482302626216,
      "loss": 0.566,
      "step": 173
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003854626533764273,
      "loss": 0.5677,
      "step": 174
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00038507209212344833,
      "loss": 0.6342,
      "step": 175
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00038467655700014054,
      "loss": 0.6095,
      "step": 176
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003842760586366339,
      "loss": 0.6715,
      "step": 177
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00038387060779644725,
      "loss": 0.5173,
      "step": 178
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00038346021537619866,
      "loss": 0.6155,
      "step": 179
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003830448924053126,
      "loss": 0.6346,
      "step": 180
    },
    {
      "epoch": 0.51,
      "eval_loss": 0.6006138324737549,
      "eval_runtime": 29.5105,
      "eval_samples_per_second": 55.201,
      "eval_steps_per_second": 55.201,
      "step": 180
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00038262465004572377,
      "loss": 0.7549,
      "step": 181
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000382199499591577,
      "loss": 0.5214,
      "step": 182
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00038176945246892367,
      "loss": 0.5625,
      "step": 183
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003813345202354145,
      "loss": 0.5267,
      "step": 184
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003808947145799894,
      "loss": 0.6413,
      "step": 185
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003804500473225627,
      "loss": 0.4987,
      "step": 186
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00038000053041370603,
      "loss": 0.6235,
      "step": 187
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003795461759343268,
      "loss": 0.5331,
      "step": 188
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003790869960953437,
      "loss": 0.6096,
      "step": 189
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003786230032373583,
      "loss": 0.5872,
      "step": 190
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00037815420983032397,
      "loss": 0.6665,
      "step": 191
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003776806284732098,
      "loss": 0.7373,
      "step": 192
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00037720227189366295,
      "loss": 0.5193,
      "step": 193
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00037671915294766606,
      "loss": 0.5335,
      "step": 194
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00037623128461919175,
      "loss": 0.5148,
      "step": 195
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00037573868001985377,
      "loss": 0.5961,
      "step": 196
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003752413523885549,
      "loss": 0.5421,
      "step": 197
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00037473931509113056,
      "loss": 0.6177,
      "step": 198
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003742325816199901,
      "loss": 0.6656,
      "step": 199
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00037372116559375397,
      "loss": 0.7663,
      "step": 200
    },
    {
      "epoch": 0.57,
      "eval_loss": 0.5926464200019836,
      "eval_runtime": 29.5066,
      "eval_samples_per_second": 55.208,
      "eval_steps_per_second": 55.208,
      "step": 200
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00037320508075688776,
      "loss": 0.6667,
      "step": 201
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00037268434097933274,
      "loss": 0.587,
      "step": 202
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003721589602561332,
      "loss": 0.5747,
      "step": 203
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003716289527070604,
      "loss": 0.557,
      "step": 204
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003710943325762328,
      "loss": 0.5724,
      "step": 205
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00037055511423173356,
      "loss": 0.6036,
      "step": 206
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003700113121652243,
      "loss": 0.6007,
      "step": 207
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003694629409915555,
      "loss": 0.6895,
      "step": 208
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00036891001544837393,
      "loss": 0.6642,
      "step": 209
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003683525503957263,
      "loss": 0.7124,
      "step": 210
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00036779056081566024,
      "loss": 0.52,
      "step": 211
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00036722406181182143,
      "loss": 0.6133,
      "step": 212
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003666530686090475,
      "loss": 0.5487,
      "step": 213
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003660775965529595,
      "loss": 0.5686,
      "step": 214
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003654976611095487,
      "loss": 0.4951,
      "step": 215
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003649132778647615,
      "loss": 0.5794,
      "step": 216
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00036432446252408014,
      "loss": 0.4965,
      "step": 217
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003637312309121011,
      "loss": 0.6146,
      "step": 218
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00036313359897210935,
      "loss": 0.5697,
      "step": 219
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00036253158276565006,
      "loss": 0.5864,
      "step": 220
    },
    {
      "epoch": 0.62,
      "eval_loss": 0.5865967273712158,
      "eval_runtime": 29.5042,
      "eval_samples_per_second": 55.212,
      "eval_steps_per_second": 55.212,
      "step": 220
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.000361925198472097,
      "loss": 0.4863,
      "step": 221
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00036131446238821767,
      "loss": 0.5185,
      "step": 222
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00036069939092773514,
      "loss": 0.5846,
      "step": 223
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003600800006208872,
      "loss": 0.5416,
      "step": 224
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00035945630811398205,
      "loss": 0.5783,
      "step": 225
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003588283301689507,
      "loss": 0.7388,
      "step": 226
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003581960836628968,
      "loss": 0.7164,
      "step": 227
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003575595855876427,
      "loss": 0.5729,
      "step": 228
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003569188530492732,
      "loss": 0.5475,
      "step": 229
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003562739032676756,
      "loss": 0.6107,
      "step": 230
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00035562475357607694,
      "loss": 0.5441,
      "step": 231
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.000354971421420578,
      "loss": 0.6148,
      "step": 232
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003543139243596847,
      "loss": 0.5864,
      "step": 233
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00035365228006383614,
      "loss": 0.5044,
      "step": 234
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00035298650631492956,
      "loss": 0.4947,
      "step": 235
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003523166210058426,
      "loss": 0.5524,
      "step": 236
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003516426421399523,
      "loss": 0.5434,
      "step": 237
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00035096458783065145,
      "loss": 0.6695,
      "step": 238
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003502824763008615,
      "loss": 0.6813,
      "step": 239
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00034959632588254304,
      "loss": 0.5943,
      "step": 240
    },
    {
      "epoch": 0.68,
      "eval_loss": 0.5755711793899536,
      "eval_runtime": 29.5,
      "eval_samples_per_second": 55.22,
      "eval_steps_per_second": 55.22,
      "step": 240
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.000348906155016203,
      "loss": 0.5239,
      "step": 241
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003482119822503994,
      "loss": 0.5347,
      "step": 242
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000347513826241242,
      "loss": 0.5513,
      "step": 243
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003468117057518921,
      "loss": 0.6988,
      "step": 244
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000346105639652057,
      "loss": 0.5591,
      "step": 245
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00034539564691748407,
      "loss": 0.5305,
      "step": 246
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00034468174662944995,
      "loss": 0.5492,
      "step": 247
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003439639579742481,
      "loss": 0.5907,
      "step": 248
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00034324230024267285,
      "loss": 0.5596,
      "step": 249
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00034251679282950144,
      "loss": 0.6163,
      "step": 250
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00034178745523297233,
      "loss": 0.7016,
      "step": 251
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003410543070542615,
      "loss": 0.734,
      "step": 252
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00034031736799695537,
      "loss": 0.6601,
      "step": 253
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003395766578665215,
      "loss": 0.5738,
      "step": 254
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00033883219656977615,
      "loss": 0.5691,
      "step": 255
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003380840041143494,
      "loss": 0.4958,
      "step": 256
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003373321006081474,
      "loss": 0.4613,
      "step": 257
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00033657650625881183,
      "loss": 0.5939,
      "step": 258
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003358172413731772,
      "loss": 0.6093,
      "step": 259
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00033505432635672457,
      "loss": 0.5029,
      "step": 260
    },
    {
      "epoch": 0.74,
      "eval_loss": 0.5733422040939331,
      "eval_runtime": 29.5698,
      "eval_samples_per_second": 55.09,
      "eval_steps_per_second": 55.09,
      "step": 260
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003342877817130334,
      "loss": 0.6983,
      "step": 261
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00033351762804323073,
      "loss": 0.5567,
      "step": 262
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003327438860454372,
      "loss": 0.5081,
      "step": 263
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00033196657651421066,
      "loss": 0.5475,
      "step": 264
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.000331185720339988,
      "loss": 0.5527,
      "step": 265
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003304013385085229,
      "loss": 0.5244,
      "step": 266
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003296134521003222,
      "loss": 0.6156,
      "step": 267
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003288220822900796,
      "loss": 0.5203,
      "step": 268
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00032802725034610593,
      "loss": 0.5844,
      "step": 269
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003272289776297583,
      "loss": 0.6262,
      "step": 270
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003264272855948653,
      "loss": 0.552,
      "step": 271
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003256221957871512,
      "loss": 0.5817,
      "step": 272
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003248137298436561,
      "loss": 0.4906,
      "step": 273
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00032400190949215507,
      "loss": 0.4638,
      "step": 274
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003231867565505737,
      "loss": 0.532,
      "step": 275
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003223682929264022,
      "loss": 0.572,
      "step": 276
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003215465406161064,
      "loss": 0.6238,
      "step": 277
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003207215217045363,
      "loss": 0.5751,
      "step": 278
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003198932583643332,
      "loss": 0.5688,
      "step": 279
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003190617728553332,
      "loss": 0.5482,
      "step": 280
    },
    {
      "epoch": 0.79,
      "eval_loss": 0.5711647272109985,
      "eval_runtime": 29.618,
      "eval_samples_per_second": 55.0,
      "eval_steps_per_second": 55.0,
      "step": 280
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003182270875239694,
      "loss": 0.6118,
      "step": 281
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003173892248026708,
      "loss": 0.5704,
      "step": 282
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003165482072092602,
      "loss": 0.6117,
      "step": 283
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00031570405734634814,
      "loss": 0.5798,
      "step": 284
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003148567979007261,
      "loss": 0.5585,
      "step": 285
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00031400645164275653,
      "loss": 0.6552,
      "step": 286
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.000313153041425761,
      "loss": 0.5421,
      "step": 287
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003122965901854058,
      "loss": 0.497,
      "step": 288
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003114371209390857,
      "loss": 0.5207,
      "step": 289
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00031057465678530543,
      "loss": 0.5028,
      "step": 290
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003097092209030588,
      "loss": 0.4905,
      "step": 291
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003088408365512055,
      "loss": 0.6156,
      "step": 292
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00030796952706784646,
      "loss": 0.5414,
      "step": 293
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003070953158696967,
      "loss": 0.4219,
      "step": 294
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00030621822645145506,
      "loss": 0.6778,
      "step": 295
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.000305338282385174,
      "loss": 0.5173,
      "step": 296
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00030445550731962546,
      "loss": 0.5959,
      "step": 297
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003035699249796651,
      "loss": 0.6535,
      "step": 298
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003026815591655953,
      "loss": 0.6306,
      "step": 299
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00030179043375252486,
      "loss": 0.5413,
      "step": 300
    },
    {
      "epoch": 0.85,
      "eval_loss": 0.5820406675338745,
      "eval_runtime": 29.5338,
      "eval_samples_per_second": 55.157,
      "eval_steps_per_second": 55.157,
      "step": 300
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000300896572689728,
      "loss": 0.5046,
      "step": 301
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00030000000000000003,
      "loss": 0.6131,
      "step": 302
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00029910073977901236,
      "loss": 0.4598,
      "step": 303
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00029819881619466443,
      "loss": 0.5017,
      "step": 304
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00029729425348643467,
      "loss": 0.6571,
      "step": 305
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00029638707596472855,
      "loss": 0.577,
      "step": 306
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00029547730801022544,
      "loss": 0.5014,
      "step": 307
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00029456497407322365,
      "loss": 0.4571,
      "step": 308
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002936500986729829,
      "loss": 0.5818,
      "step": 309
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002927327063970655,
      "loss": 0.5138,
      "step": 310
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00029181282190067574,
      "loss": 0.5927,
      "step": 311
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00029089046990599685,
      "loss": 0.5297,
      "step": 312
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002899656752015272,
      "loss": 0.5693,
      "step": 313
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002890384626414134,
      "loss": 0.5579,
      "step": 314
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.000288108857144783,
      "loss": 0.6165,
      "step": 315
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00028717688369507425,
      "loss": 0.4311,
      "step": 316
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00028624256733936486,
      "loss": 0.5919,
      "step": 317
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002853059331876991,
      "loss": 0.6499,
      "step": 318
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002843670064124125,
      "loss": 0.5486,
      "step": 319
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002834258122474556,
      "loss": 0.657,
      "step": 320
    },
    {
      "epoch": 0.91,
      "eval_loss": 0.5696084499359131,
      "eval_runtime": 29.5183,
      "eval_samples_per_second": 55.186,
      "eval_steps_per_second": 55.186,
      "step": 320
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002824823759877159,
      "loss": 0.6218,
      "step": 321
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00028153672298833775,
      "loss": 0.4651,
      "step": 322
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002805888786640412,
      "loss": 0.5388,
      "step": 323
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00027963886848843863,
      "loss": 0.4579,
      "step": 324
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00027868671799335053,
      "loss": 0.6092,
      "step": 325
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00027773245276811905,
      "loss": 0.711,
      "step": 326
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00027677609845892055,
      "loss": 0.6601,
      "step": 327
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002758176807680759,
      "loss": 0.4271,
      "step": 328
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00027485722545336023,
      "loss": 0.5561,
      "step": 329
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00027389475832731035,
      "loss": 0.4772,
      "step": 330
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00027293030525653105,
      "loss": 0.56,
      "step": 331
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002719638921610002,
      "loss": 0.5905,
      "step": 332
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002709955450133718,
      "loss": 0.4981,
      "step": 333
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002700252898382781,
      "loss": 0.5701,
      "step": 334
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002690531527116304,
      "loss": 0.4725,
      "step": 335
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00026807915975991765,
      "loss": 0.5022,
      "step": 336
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.000267103337159505,
      "loss": 0.4953,
      "step": 337
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002661257111359299,
      "loss": 0.5762,
      "step": 338
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002651463079631973,
      "loss": 0.6713,
      "step": 339
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00026416515396307353,
      "loss": 0.506,
      "step": 340
    },
    {
      "epoch": 0.96,
      "eval_loss": 0.5838707685470581,
      "eval_runtime": 29.495,
      "eval_samples_per_second": 55.23,
      "eval_steps_per_second": 55.23,
      "step": 340
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002631822755043793,
      "loss": 0.5368,
      "step": 341
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00026219769900228014,
      "loss": 0.5509,
      "step": 342
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002612114509175775,
      "loss": 0.5365,
      "step": 343
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002602235577559969,
      "loss": 0.6527,
      "step": 344
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002592340460674759,
      "loss": 0.4975,
      "step": 345
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00025824294244545045,
      "loss": 0.6552,
      "step": 346
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00025725027352614015,
      "loss": 0.5523,
      "step": 347
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00025625606598783256,
      "loss": 0.6078,
      "step": 348
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002552603465501661,
      "loss": 0.4592,
      "step": 349
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002542631419734118,
      "loss": 0.587,
      "step": 350
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00025326447905775446,
      "loss": 0.5689,
      "step": 351
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00025226438464257217,
      "loss": 0.4961,
      "step": 352
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00025126288560571483,
      "loss": 0.4735,
      "step": 353
    }
  ],
  "logging_steps": 1,
  "max_steps": 706,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 9.231730747386102e+17,
  "trial_name": null,
  "trial_params": null
}