{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.851063829787234,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0001994318181818182,
      "loss": 2.7526,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019886363636363637,
      "loss": 2.6231,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019829545454545455,
      "loss": 2.5691,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019772727272727273,
      "loss": 2.5755,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019715909090909094,
      "loss": 2.5077,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001965909090909091,
      "loss": 2.4698,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019602272727272727,
      "loss": 2.4541,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019545454545454548,
      "loss": 2.4764,
      "step": 8
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019488636363636366,
      "loss": 2.4176,
      "step": 9
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001943181818181818,
      "loss": 2.396,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019375000000000002,
      "loss": 2.3929,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001931818181818182,
      "loss": 2.405,
      "step": 12
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019261363636363635,
      "loss": 2.3947,
      "step": 13
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019204545454545456,
      "loss": 2.4164,
      "step": 14
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019147727272727274,
      "loss": 2.373,
      "step": 15
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019090909090909092,
      "loss": 2.3552,
      "step": 16
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001903409090909091,
      "loss": 2.3988,
      "step": 17
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00018977272727272728,
      "loss": 2.3826,
      "step": 18
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00018920454545454546,
      "loss": 2.3672,
      "step": 19
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00018863636363636364,
      "loss": 2.3885,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00018806818181818182,
      "loss": 2.3043,
      "step": 21
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001875,
      "loss": 2.2597,
      "step": 22
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00018693181818181818,
      "loss": 2.3457,
      "step": 23
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00018636363636363636,
      "loss": 2.3409,
      "step": 24
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00018579545454545454,
      "loss": 2.303,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00018522727272727273,
      "loss": 2.3253,
      "step": 26
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00018465909090909093,
      "loss": 2.3453,
      "step": 27
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00018409090909090909,
      "loss": 2.3151,
      "step": 28
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00018352272727272727,
      "loss": 2.3457,
      "step": 29
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018295454545454547,
      "loss": 2.2792,
      "step": 30
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018238636363636365,
      "loss": 2.3257,
      "step": 31
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018181818181818183,
      "loss": 2.353,
      "step": 32
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018125000000000001,
      "loss": 2.2633,
      "step": 33
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001806818181818182,
      "loss": 2.3089,
      "step": 34
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00018011363636363638,
      "loss": 2.3085,
      "step": 35
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00017954545454545456,
      "loss": 2.2746,
      "step": 36
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00017897727272727274,
      "loss": 2.3212,
      "step": 37
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00017840909090909092,
      "loss": 2.2991,
      "step": 38
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001778409090909091,
      "loss": 2.2807,
      "step": 39
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00017727272727272728,
      "loss": 2.3342,
      "step": 40
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00017670454545454546,
      "loss": 2.3144,
      "step": 41
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00017613636363636366,
      "loss": 2.3084,
      "step": 42
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00017556818181818182,
      "loss": 2.3032,
      "step": 43
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000175,
      "loss": 2.3105,
      "step": 44
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001744318181818182,
      "loss": 2.3101,
      "step": 45
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00017386363636363636,
      "loss": 2.313,
      "step": 46
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00017329545454545454,
      "loss": 2.293,
      "step": 47
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00017272727272727275,
      "loss": 2.2807,
      "step": 48
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00017215909090909093,
      "loss": 2.2665,
      "step": 49
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00017159090909090908,
      "loss": 2.2626,
      "step": 50
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001710227272727273,
      "loss": 2.2839,
      "step": 51
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00017045454545454547,
      "loss": 2.2865,
      "step": 52
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00016988636363636365,
      "loss": 2.2788,
      "step": 53
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00016931818181818183,
      "loss": 2.2622,
      "step": 54
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00016875,
      "loss": 2.3121,
      "step": 55
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001681818181818182,
      "loss": 2.2958,
      "step": 56
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00016761363636363637,
      "loss": 2.2898,
      "step": 57
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00016704545454545455,
      "loss": 2.2903,
      "step": 58
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00016647727272727273,
      "loss": 2.3393,
      "step": 59
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00016590909090909094,
      "loss": 2.3086,
      "step": 60
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001653409090909091,
      "loss": 2.2739,
      "step": 61
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00016477272727272727,
      "loss": 2.252,
      "step": 62
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00016420454545454548,
      "loss": 2.2868,
      "step": 63
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00016363636363636366,
      "loss": 2.2301,
      "step": 64
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001630681818181818,
      "loss": 2.2563,
      "step": 65
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00016250000000000002,
      "loss": 2.2552,
      "step": 66
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001619318181818182,
      "loss": 2.2615,
      "step": 67
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00016136363636363635,
      "loss": 2.3237,
      "step": 68
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00016079545454545456,
      "loss": 2.2741,
      "step": 69
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00016022727272727274,
      "loss": 2.2152,
      "step": 70
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00015965909090909092,
      "loss": 2.2558,
      "step": 71
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001590909090909091,
      "loss": 2.2293,
      "step": 72
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00015852272727272728,
      "loss": 2.2278,
      "step": 73
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00015795454545454546,
      "loss": 2.2583,
      "step": 74
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00015738636363636364,
      "loss": 2.2609,
      "step": 75
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00015681818181818182,
      "loss": 2.2955,
      "step": 76
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00015625,
      "loss": 2.2359,
      "step": 77
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00015568181818181818,
      "loss": 2.2427,
      "step": 78
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00015511363636363636,
      "loss": 2.2632,
      "step": 79
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00015454545454545454,
      "loss": 2.2649,
      "step": 80
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00015397727272727272,
      "loss": 2.2347,
      "step": 81
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00015340909090909093,
      "loss": 2.2439,
      "step": 82
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00015284090909090909,
      "loss": 2.267,
      "step": 83
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00015227272727272727,
      "loss": 2.2682,
      "step": 84
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00015170454545454547,
      "loss": 2.2477,
      "step": 85
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00015113636363636365,
      "loss": 2.2534,
      "step": 86
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001505681818181818,
      "loss": 2.2609,
      "step": 87
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00015000000000000001,
      "loss": 2.2381,
      "step": 88
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001494318181818182,
      "loss": 2.2505,
      "step": 89
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00014886363636363635,
      "loss": 2.2628,
      "step": 90
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00014829545454545455,
      "loss": 2.1874,
      "step": 91
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00014772727272727274,
      "loss": 2.2024,
      "step": 92
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00014715909090909092,
      "loss": 2.2453,
      "step": 93
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001465909090909091,
      "loss": 2.259,
      "step": 94
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00014602272727272728,
      "loss": 2.2304,
      "step": 95
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00014545454545454546,
      "loss": 2.2179,
      "step": 96
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00014488636363636366,
      "loss": 2.2497,
      "step": 97
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00014431818181818182,
      "loss": 2.2458,
      "step": 98
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00014375,
      "loss": 2.2438,
      "step": 99
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001431818181818182,
      "loss": 2.2461,
      "step": 100
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00014261363636363636,
      "loss": 2.1966,
      "step": 101
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00014204545454545454,
      "loss": 2.2191,
      "step": 102
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00014147727272727275,
      "loss": 2.1765,
      "step": 103
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00014090909090909093,
      "loss": 2.1917,
      "step": 104
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00014034090909090908,
      "loss": 2.2025,
      "step": 105
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001397727272727273,
      "loss": 2.2496,
      "step": 106
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00013920454545454547,
      "loss": 2.2012,
      "step": 107
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00013863636363636365,
      "loss": 2.2051,
      "step": 108
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00013806818181818183,
      "loss": 2.2027,
      "step": 109
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001375,
      "loss": 2.21,
      "step": 110
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001369318181818182,
      "loss": 2.2501,
      "step": 111
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00013636363636363637,
      "loss": 2.1916,
      "step": 112
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00013579545454545455,
      "loss": 2.1972,
      "step": 113
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00013522727272727273,
      "loss": 2.1821,
      "step": 114
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00013465909090909094,
      "loss": 2.2448,
      "step": 115
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001340909090909091,
      "loss": 2.2253,
      "step": 116
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00013352272727272727,
      "loss": 2.2088,
      "step": 117
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00013295454545454548,
      "loss": 2.2203,
      "step": 118
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00013238636363636366,
      "loss": 2.2236,
      "step": 119
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001318181818181818,
      "loss": 2.2074,
      "step": 120
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00013125000000000002,
      "loss": 2.2355,
      "step": 121
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001306818181818182,
      "loss": 2.2215,
      "step": 122
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00013011363636363635,
      "loss": 2.1854,
      "step": 123
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00012954545454545456,
      "loss": 2.2046,
      "step": 124
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00012897727272727274,
      "loss": 2.2079,
      "step": 125
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00012840909090909092,
      "loss": 2.2204,
      "step": 126
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001278409090909091,
      "loss": 2.2223,
      "step": 127
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00012727272727272728,
      "loss": 2.2149,
      "step": 128
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00012670454545454546,
      "loss": 2.1887,
      "step": 129
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00012613636363636364,
      "loss": 2.1908,
      "step": 130
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00012556818181818182,
      "loss": 2.2434,
      "step": 131
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000125,
      "loss": 2.2169,
      "step": 132
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00012443181818181818,
      "loss": 2.2113,
      "step": 133
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00012386363636363636,
      "loss": 2.2334,
      "step": 134
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00012329545454545454,
      "loss": 2.2034,
      "step": 135
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00012272727272727272,
      "loss": 2.2297,
      "step": 136
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00012215909090909093,
      "loss": 2.2049,
      "step": 137
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00012159090909090908,
      "loss": 2.1773,
      "step": 138
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00012102272727272728,
      "loss": 2.2057,
      "step": 139
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00012045454545454546,
      "loss": 2.1652,
      "step": 140
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00011988636363636365,
      "loss": 2.2157,
      "step": 141
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00011931818181818182,
      "loss": 2.1987,
      "step": 142
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00011875,
      "loss": 2.1666,
      "step": 143
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001181818181818182,
      "loss": 2.1734,
      "step": 144
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00011761363636363636,
      "loss": 2.2221,
      "step": 145
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00011704545454545454,
      "loss": 2.1488,
      "step": 146
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00011647727272727273,
      "loss": 2.1487,
      "step": 147
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00011590909090909093,
      "loss": 2.1678,
      "step": 148
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00011534090909090908,
      "loss": 2.1988,
      "step": 149
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00011477272727272728,
      "loss": 2.1803,
      "step": 150
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00011420454545454547,
      "loss": 2.1671,
      "step": 151
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00011363636363636365,
      "loss": 2.1472,
      "step": 152
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00011306818181818182,
      "loss": 2.1456,
      "step": 153
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00011250000000000001,
      "loss": 2.1769,
      "step": 154
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00011193181818181819,
      "loss": 2.1484,
      "step": 155
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00011136363636363636,
      "loss": 2.1862,
      "step": 156
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011079545454545455,
      "loss": 2.1088,
      "step": 157
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011022727272727273,
      "loss": 2.1746,
      "step": 158
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00010965909090909093,
      "loss": 2.1609,
      "step": 159
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00010909090909090909,
      "loss": 2.2089,
      "step": 160
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00010852272727272727,
      "loss": 2.1862,
      "step": 161
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00010795454545454547,
      "loss": 2.1844,
      "step": 162
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00010738636363636365,
      "loss": 2.1717,
      "step": 163
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00010681818181818181,
      "loss": 2.1764,
      "step": 164
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00010625000000000001,
      "loss": 2.1642,
      "step": 165
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00010568181818181819,
      "loss": 2.164,
      "step": 166
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00010511363636363635,
      "loss": 2.1743,
      "step": 167
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00010454545454545455,
      "loss": 2.1688,
      "step": 168
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00010397727272727273,
      "loss": 2.1756,
      "step": 169
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00010340909090909092,
      "loss": 2.1488,
      "step": 170
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010284090909090909,
      "loss": 2.1558,
      "step": 171
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010227272727272727,
      "loss": 2.1551,
      "step": 172
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010170454545454546,
      "loss": 2.1462,
      "step": 173
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010113636363636366,
      "loss": 2.134,
      "step": 174
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010056818181818181,
      "loss": 2.1278,
      "step": 175
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001,
      "loss": 2.1436,
      "step": 176
    },
    {
      "epoch": 0.5,
      "learning_rate": 9.943181818181819e-05,
      "loss": 2.142,
      "step": 177
    },
    {
      "epoch": 0.5,
      "learning_rate": 9.886363636363637e-05,
      "loss": 2.1481,
      "step": 178
    },
    {
      "epoch": 0.51,
      "learning_rate": 9.829545454545455e-05,
      "loss": 2.1406,
      "step": 179
    },
    {
      "epoch": 0.51,
      "learning_rate": 9.772727272727274e-05,
      "loss": 2.1555,
      "step": 180
    },
    {
      "epoch": 0.51,
      "learning_rate": 9.71590909090909e-05,
      "loss": 2.1667,
      "step": 181
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.65909090909091e-05,
      "loss": 2.1455,
      "step": 182
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.602272727272728e-05,
      "loss": 2.1447,
      "step": 183
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.545454545454546e-05,
      "loss": 2.1642,
      "step": 184
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.488636363636364e-05,
      "loss": 2.1278,
      "step": 185
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.431818181818182e-05,
      "loss": 2.1548,
      "step": 186
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.375e-05,
      "loss": 2.1506,
      "step": 187
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.318181818181818e-05,
      "loss": 2.1649,
      "step": 188
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.261363636363636e-05,
      "loss": 2.1824,
      "step": 189
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.204545454545454e-05,
      "loss": 2.1451,
      "step": 190
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.147727272727274e-05,
      "loss": 2.089,
      "step": 191
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.090909090909092e-05,
      "loss": 2.1457,
      "step": 192
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.03409090909091e-05,
      "loss": 2.1647,
      "step": 193
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.977272727272728e-05,
      "loss": 2.1464,
      "step": 194
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.920454545454546e-05,
      "loss": 2.116,
      "step": 195
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.863636363636364e-05,
      "loss": 2.1326,
      "step": 196
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.806818181818183e-05,
      "loss": 2.1248,
      "step": 197
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.75e-05,
      "loss": 2.172,
      "step": 198
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.693181818181818e-05,
      "loss": 2.1478,
      "step": 199
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.636363636363637e-05,
      "loss": 2.1691,
      "step": 200
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.579545454545454e-05,
      "loss": 2.1429,
      "step": 201
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.522727272727273e-05,
      "loss": 2.1427,
      "step": 202
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.465909090909091e-05,
      "loss": 2.1568,
      "step": 203
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.40909090909091e-05,
      "loss": 2.0458,
      "step": 204
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.352272727272727e-05,
      "loss": 2.148,
      "step": 205
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.295454545454547e-05,
      "loss": 2.1835,
      "step": 206
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.238636363636364e-05,
      "loss": 2.1176,
      "step": 207
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.181818181818183e-05,
      "loss": 2.1307,
      "step": 208
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.125000000000001e-05,
      "loss": 2.167,
      "step": 209
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.068181818181818e-05,
      "loss": 2.141,
      "step": 210
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.011363636363637e-05,
      "loss": 2.1373,
      "step": 211
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.954545454545455e-05,
      "loss": 2.1276,
      "step": 212
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.897727272727273e-05,
      "loss": 2.1287,
      "step": 213
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.840909090909091e-05,
      "loss": 2.1247,
      "step": 214
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.784090909090909e-05,
      "loss": 2.1223,
      "step": 215
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.727272727272727e-05,
      "loss": 2.1513,
      "step": 216
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.670454545454547e-05,
      "loss": 2.1089,
      "step": 217
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.613636363636363e-05,
      "loss": 2.1237,
      "step": 218
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.556818181818183e-05,
      "loss": 2.095,
      "step": 219
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.09,
      "step": 220
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.443181818181817e-05,
      "loss": 2.095,
      "step": 221
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.386363636363637e-05,
      "loss": 2.1064,
      "step": 222
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.329545454545455e-05,
      "loss": 2.123,
      "step": 223
    },
    {
      "epoch": 0.64,
      "learning_rate": 7.272727272727273e-05,
      "loss": 2.1385,
      "step": 224
    },
    {
      "epoch": 0.64,
      "learning_rate": 7.215909090909091e-05,
      "loss": 2.1287,
      "step": 225
    },
    {
      "epoch": 0.64,
      "learning_rate": 7.15909090909091e-05,
      "loss": 2.1189,
      "step": 226
    },
    {
      "epoch": 0.64,
      "learning_rate": 7.102272727272727e-05,
      "loss": 2.1318,
      "step": 227
    },
    {
      "epoch": 0.65,
      "learning_rate": 7.045454545454546e-05,
      "loss": 2.1235,
      "step": 228
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.988636363636364e-05,
      "loss": 2.1088,
      "step": 229
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.931818181818182e-05,
      "loss": 2.1246,
      "step": 230
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.875e-05,
      "loss": 2.1006,
      "step": 231
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.818181818181818e-05,
      "loss": 2.1215,
      "step": 232
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.761363636363636e-05,
      "loss": 2.1018,
      "step": 233
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.704545454545455e-05,
      "loss": 2.1014,
      "step": 234
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.647727272727274e-05,
      "loss": 2.0915,
      "step": 235
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.59090909090909e-05,
      "loss": 2.1134,
      "step": 236
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.53409090909091e-05,
      "loss": 2.0789,
      "step": 237
    },
    {
      "epoch": 0.68,
      "learning_rate": 6.477272727272728e-05,
      "loss": 2.1148,
      "step": 238
    },
    {
      "epoch": 0.68,
      "learning_rate": 6.420454545454546e-05,
      "loss": 2.1209,
      "step": 239
    },
    {
      "epoch": 0.68,
      "learning_rate": 6.363636363636364e-05,
      "loss": 2.1602,
      "step": 240
    },
    {
      "epoch": 0.68,
      "learning_rate": 6.306818181818182e-05,
      "loss": 2.121,
      "step": 241
    },
    {
      "epoch": 0.69,
      "learning_rate": 6.25e-05,
      "loss": 2.1224,
      "step": 242
    },
    {
      "epoch": 0.69,
      "learning_rate": 6.193181818181818e-05,
      "loss": 2.084,
      "step": 243
    },
    {
      "epoch": 0.69,
      "learning_rate": 6.136363636363636e-05,
      "loss": 2.1332,
      "step": 244
    },
    {
      "epoch": 0.7,
      "learning_rate": 6.079545454545454e-05,
      "loss": 2.1131,
      "step": 245
    },
    {
      "epoch": 0.7,
      "learning_rate": 6.022727272727273e-05,
      "loss": 2.1303,
      "step": 246
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.965909090909091e-05,
      "loss": 2.1348,
      "step": 247
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.90909090909091e-05,
      "loss": 2.1159,
      "step": 248
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.852272727272727e-05,
      "loss": 2.1326,
      "step": 249
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.7954545454545464e-05,
      "loss": 2.0715,
      "step": 250
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.738636363636364e-05,
      "loss": 2.0846,
      "step": 251
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.6818181818181825e-05,
      "loss": 2.1289,
      "step": 252
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.6250000000000005e-05,
      "loss": 2.1195,
      "step": 253
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.568181818181818e-05,
      "loss": 2.1124,
      "step": 254
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.5113636363636366e-05,
      "loss": 2.088,
      "step": 255
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 2.0993,
      "step": 256
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.397727272727273e-05,
      "loss": 2.1008,
      "step": 257
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.340909090909091e-05,
      "loss": 2.1095,
      "step": 258
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.2840909090909094e-05,
      "loss": 2.1112,
      "step": 259
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.2272727272727274e-05,
      "loss": 2.1127,
      "step": 260
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.170454545454546e-05,
      "loss": 2.1226,
      "step": 261
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.1136363636363635e-05,
      "loss": 2.0889,
      "step": 262
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.056818181818183e-05,
      "loss": 2.1581,
      "step": 263
    },
    {
      "epoch": 0.75,
      "learning_rate": 5e-05,
      "loss": 2.0899,
      "step": 264
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.943181818181818e-05,
      "loss": 2.1067,
      "step": 265
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.886363636363637e-05,
      "loss": 2.1016,
      "step": 266
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.829545454545455e-05,
      "loss": 2.1103,
      "step": 267
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.772727272727273e-05,
      "loss": 2.1024,
      "step": 268
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.715909090909091e-05,
      "loss": 2.1142,
      "step": 269
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.659090909090909e-05,
      "loss": 2.1082,
      "step": 270
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.602272727272727e-05,
      "loss": 2.0955,
      "step": 271
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.545454545454546e-05,
      "loss": 2.098,
      "step": 272
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.488636363636364e-05,
      "loss": 2.0908,
      "step": 273
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.431818181818182e-05,
      "loss": 2.1048,
      "step": 274
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.375e-05,
      "loss": 2.1128,
      "step": 275
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.318181818181819e-05,
      "loss": 2.1101,
      "step": 276
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.261363636363637e-05,
      "loss": 2.0914,
      "step": 277
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.204545454545455e-05,
      "loss": 2.083,
      "step": 278
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.1477272727272734e-05,
      "loss": 2.0961,
      "step": 279
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.0909090909090915e-05,
      "loss": 2.1202,
      "step": 280
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.034090909090909e-05,
      "loss": 2.0776,
      "step": 281
    },
    {
      "epoch": 0.8,
      "learning_rate": 3.9772727272727275e-05,
      "loss": 2.0483,
      "step": 282
    },
    {
      "epoch": 0.8,
      "learning_rate": 3.9204545454545456e-05,
      "loss": 2.0784,
      "step": 283
    },
    {
      "epoch": 0.81,
      "learning_rate": 3.8636363636363636e-05,
      "loss": 2.0645,
      "step": 284
    },
    {
      "epoch": 0.81,
      "learning_rate": 3.8068181818181816e-05,
      "loss": 2.0973,
      "step": 285
    },
    {
      "epoch": 0.81,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 2.058,
      "step": 286
    },
    {
      "epoch": 0.81,
      "learning_rate": 3.6931818181818184e-05,
      "loss": 2.1144,
      "step": 287
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 2.08,
      "step": 288
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.579545454545455e-05,
      "loss": 2.0978,
      "step": 289
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.522727272727273e-05,
      "loss": 2.0766,
      "step": 290
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.465909090909091e-05,
      "loss": 2.0871,
      "step": 291
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.409090909090909e-05,
      "loss": 2.1145,
      "step": 292
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.352272727272727e-05,
      "loss": 2.0603,
      "step": 293
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.295454545454545e-05,
      "loss": 2.091,
      "step": 294
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.238636363636364e-05,
      "loss": 2.0621,
      "step": 295
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.181818181818182e-05,
      "loss": 2.0905,
      "step": 296
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.125e-05,
      "loss": 2.0749,
      "step": 297
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.068181818181818e-05,
      "loss": 2.0848,
      "step": 298
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.0113636363636365e-05,
      "loss": 2.0962,
      "step": 299
    },
    {
      "epoch": 0.85,
      "learning_rate": 2.954545454545455e-05,
      "loss": 2.0919,
      "step": 300
    }
  ],
  "logging_steps": 1,
  "max_steps": 352,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 7.603665299822592e+17,
  "trial_name": null,
  "trial_params": null
}