{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.978181818181818,
  "eval_steps": 69,
  "global_step": 550,
  "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": 2.5429,
      "step": 1
    },
    {
      "epoch": 0.0,
      "eval_loss": 2.5242362022399902,
      "eval_runtime": 44.0094,
      "eval_samples_per_second": 25.676,
      "eval_steps_per_second": 1.613,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.5186,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2e-05,
      "loss": 2.5088,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.5423,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 2e-05,
      "loss": 2.5137,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.4e-05,
      "loss": 2.4817,
      "step": 6
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 2.4889,
      "step": 7
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 2.4334,
      "step": 8
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.6e-05,
      "loss": 2.4707,
      "step": 9
    },
    {
      "epoch": 0.04,
      "learning_rate": 4e-05,
      "loss": 2.4251,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 2.4167,
      "step": 11
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.8e-05,
      "loss": 2.4235,
      "step": 12
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 2.411,
      "step": 13
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 2.4181,
      "step": 14
    },
    {
      "epoch": 0.05,
      "learning_rate": 6e-05,
      "loss": 2.3847,
      "step": 15
    },
    {
      "epoch": 0.06,
      "learning_rate": 6.400000000000001e-05,
      "loss": 2.407,
      "step": 16
    },
    {
      "epoch": 0.06,
      "learning_rate": 6.800000000000001e-05,
      "loss": 2.3764,
      "step": 17
    },
    {
      "epoch": 0.07,
      "learning_rate": 7.2e-05,
      "loss": 2.3801,
      "step": 18
    },
    {
      "epoch": 0.07,
      "learning_rate": 7.6e-05,
      "loss": 2.387,
      "step": 19
    },
    {
      "epoch": 0.07,
      "learning_rate": 8e-05,
      "loss": 2.3782,
      "step": 20
    },
    {
      "epoch": 0.08,
      "learning_rate": 8.4e-05,
      "loss": 2.3684,
      "step": 21
    },
    {
      "epoch": 0.08,
      "learning_rate": 8.800000000000001e-05,
      "loss": 2.381,
      "step": 22
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.200000000000001e-05,
      "loss": 2.381,
      "step": 23
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.6e-05,
      "loss": 2.34,
      "step": 24
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001,
      "loss": 2.3467,
      "step": 25
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00010400000000000001,
      "loss": 2.335,
      "step": 26
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00010800000000000001,
      "loss": 2.3741,
      "step": 27
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00011200000000000001,
      "loss": 2.3716,
      "step": 28
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000116,
      "loss": 2.3168,
      "step": 29
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00012,
      "loss": 2.3438,
      "step": 30
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000124,
      "loss": 2.3625,
      "step": 31
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00012800000000000002,
      "loss": 2.3581,
      "step": 32
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000132,
      "loss": 2.3283,
      "step": 33
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00013600000000000003,
      "loss": 2.3691,
      "step": 34
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00014,
      "loss": 2.3538,
      "step": 35
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000144,
      "loss": 2.337,
      "step": 36
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000148,
      "loss": 2.2913,
      "step": 37
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000152,
      "loss": 2.2872,
      "step": 38
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00015600000000000002,
      "loss": 2.319,
      "step": 39
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00016,
      "loss": 2.3445,
      "step": 40
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000164,
      "loss": 2.3293,
      "step": 41
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000168,
      "loss": 2.3142,
      "step": 42
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000172,
      "loss": 2.3172,
      "step": 43
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00017600000000000002,
      "loss": 2.3179,
      "step": 44
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00018,
      "loss": 2.3018,
      "step": 45
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018400000000000003,
      "loss": 2.3266,
      "step": 46
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000188,
      "loss": 2.3131,
      "step": 47
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000192,
      "loss": 2.3235,
      "step": 48
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000196,
      "loss": 2.3281,
      "step": 49
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 2.3332,
      "step": 50
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001999980260856137,
      "loss": 2.3148,
      "step": 51
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019999210442038162,
      "loss": 2.2979,
      "step": 52
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001999822352380809,
      "loss": 2.3257,
      "step": 53
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019996841892833,
      "loss": 2.2947,
      "step": 54
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019995065603657316,
      "loss": 2.3266,
      "step": 55
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019992894726405893,
      "loss": 2.3385,
      "step": 56
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001999032934678125,
      "loss": 2.3289,
      "step": 57
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019987369566060176,
      "loss": 2.2741,
      "step": 58
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019984015501089752,
      "loss": 2.2867,
      "step": 59
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019980267284282717,
      "loss": 2.2836,
      "step": 60
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019976125063612252,
      "loss": 2.3015,
      "step": 61
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001997158900260614,
      "loss": 2.3233,
      "step": 62
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019966659280340297,
      "loss": 2.2758,
      "step": 63
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019961336091431727,
      "loss": 2.2709,
      "step": 64
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019955619646030802,
      "loss": 2.2797,
      "step": 65
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019949510169813003,
      "loss": 2.304,
      "step": 66
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001994300790396999,
      "loss": 2.276,
      "step": 67
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019936113105200085,
      "loss": 2.2041,
      "step": 68
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019928826045698136,
      "loss": 2.2283,
      "step": 69
    },
    {
      "epoch": 0.25,
      "eval_loss": 2.2513792514801025,
      "eval_runtime": 44.1028,
      "eval_samples_per_second": 25.622,
      "eval_steps_per_second": 1.61,
      "step": 69
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.2609,
      "step": 70
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019913076310695068,
      "loss": 2.2827,
      "step": 71
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019904614256966512,
      "loss": 2.209,
      "step": 72
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001989576118602651,
      "loss": 2.2145,
      "step": 73
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001988651744737914,
      "loss": 2.2473,
      "step": 74
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019876883405951377,
      "loss": 2.2453,
      "step": 75
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001986685944207868,
      "loss": 2.211,
      "step": 76
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019856445951489982,
      "loss": 2.2569,
      "step": 77
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019845643345292054,
      "loss": 2.2212,
      "step": 78
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019834452049953297,
      "loss": 2.1689,
      "step": 79
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001982287250728689,
      "loss": 2.2705,
      "step": 80
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001981090517443334,
      "loss": 2.1772,
      "step": 81
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001979855052384247,
      "loss": 2.1771,
      "step": 82
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019785809043254722,
      "loss": 2.2058,
      "step": 83
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019772681235681936,
      "loss": 2.1685,
      "step": 84
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019759167619387476,
      "loss": 2.1862,
      "step": 85
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019745268727865774,
      "loss": 2.1707,
      "step": 86
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019730985109821266,
      "loss": 2.1632,
      "step": 87
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001971631732914674,
      "loss": 2.1792,
      "step": 88
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001970126596490106,
      "loss": 2.1885,
      "step": 89
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001968583161128631,
      "loss": 2.2058,
      "step": 90
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019670014877624353,
      "loss": 2.1616,
      "step": 91
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001965381638833274,
      "loss": 2.1764,
      "step": 92
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000196372367829001,
      "loss": 2.1524,
      "step": 93
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001962027671586086,
      "loss": 2.1466,
      "step": 94
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001960293685676943,
      "loss": 2.1066,
      "step": 95
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001958521789017376,
      "loss": 2.1546,
      "step": 96
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019567120515588308,
      "loss": 2.1259,
      "step": 97
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019548645447466431,
      "loss": 2.1833,
      "step": 98
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019529793415172192,
      "loss": 2.1349,
      "step": 99
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.1688,
      "step": 100
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019490961449902946,
      "loss": 2.1241,
      "step": 101
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019470983049947444,
      "loss": 2.0855,
      "step": 102
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019450630751798048,
      "loss": 2.1153,
      "step": 103
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019429905358928646,
      "loss": 2.134,
      "step": 104
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019408807689542257,
      "loss": 2.097,
      "step": 105
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019387338576538744,
      "loss": 2.0723,
      "step": 106
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019365498867481923,
      "loss": 2.1019,
      "step": 107
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019343289424566122,
      "loss": 2.1268,
      "step": 108
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001932071112458211,
      "loss": 2.0742,
      "step": 109
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019297764858882514,
      "loss": 2.0667,
      "step": 110
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019274451533346615,
      "loss": 2.066,
      "step": 111
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001925077206834458,
      "loss": 2.0845,
      "step": 112
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001922672739870115,
      "loss": 2.112,
      "step": 113
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019202318473658705,
      "loss": 2.1757,
      "step": 114
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019177546256839812,
      "loss": 2.12,
      "step": 115
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019152411726209176,
      "loss": 2.0802,
      "step": 116
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001912691587403503,
      "loss": 2.0203,
      "step": 117
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019101059706849957,
      "loss": 2.078,
      "step": 118
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001907484424541117,
      "loss": 2.0773,
      "step": 119
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019048270524660196,
      "loss": 2.0601,
      "step": 120
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019021339593682028,
      "loss": 2.0711,
      "step": 121
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001899405251566371,
      "loss": 2.0607,
      "step": 122
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00018966410367852362,
      "loss": 2.0505,
      "step": 123
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001893841424151264,
      "loss": 2.0371,
      "step": 124
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001891006524188368,
      "loss": 2.0507,
      "step": 125
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00018881364488135448,
      "loss": 2.0541,
      "step": 126
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00018852313113324552,
      "loss": 2.0362,
      "step": 127
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00018822912264349534,
      "loss": 2.0668,
      "step": 128
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00018793163101905563,
      "loss": 3.3779,
      "step": 129
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.0519,
      "step": 130
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00018732624548099204,
      "loss": 2.0925,
      "step": 131
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001870183754669526,
      "loss": 2.0931,
      "step": 132
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000186707070116449,
      "loss": 2.0339,
      "step": 133
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00018639234171928353,
      "loss": 1.9732,
      "step": 134
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001860742027003944,
      "loss": 2.0093,
      "step": 135
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00018575266561936523,
      "loss": 1.9884,
      "step": 136
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001854277431699295,
      "loss": 1.9744,
      "step": 137
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00018509944817946922,
      "loss": 1.9539,
      "step": 138
    },
    {
      "epoch": 0.5,
      "eval_loss": 2.0380747318267822,
      "eval_runtime": 44.126,
      "eval_samples_per_second": 25.608,
      "eval_steps_per_second": 1.609,
      "step": 138
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00018476779360850832,
      "loss": 2.0191,
      "step": 139
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00018443279255020152,
      "loss": 2.0294,
      "step": 140
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00018409445822981693,
      "loss": 2.021,
      "step": 141
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001837528040042142,
      "loss": 2.0358,
      "step": 142
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018340784336131713,
      "loss": 1.9937,
      "step": 143
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018305958991958127,
      "loss": 2.0256,
      "step": 144
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018270805742745617,
      "loss": 2.0468,
      "step": 145
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018235325976284275,
      "loss": 1.9277,
      "step": 146
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018199521093254523,
      "loss": 2.047,
      "step": 147
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00018163392507171842,
      "loss": 2.0202,
      "step": 148
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001812694164433094,
      "loss": 1.9753,
      "step": 149
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.9769,
      "step": 150
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001805307885711122,
      "loss": 1.9002,
      "step": 151
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00018015669848708767,
      "loss": 1.8904,
      "step": 152
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001797794439538571,
      "loss": 1.8454,
      "step": 153
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00017939903986478355,
      "loss": 1.9393,
      "step": 154
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00017901550123756906,
      "loss": 1.9692,
      "step": 155
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00017862884321366188,
      "loss": 1.8821,
      "step": 156
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001782390810576588,
      "loss": 1.9025,
      "step": 157
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00017784623015670238,
      "loss": 1.8977,
      "step": 158
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00017745030601987337,
      "loss": 1.9179,
      "step": 159
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00017705132427757895,
      "loss": 1.8895,
      "step": 160
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00017664930068093498,
      "loss": 1.8531,
      "step": 161
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001762442511011448,
      "loss": 1.9298,
      "step": 162
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001758361915288722,
      "loss": 1.862,
      "step": 163
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00017542513807361037,
      "loss": 1.9015,
      "step": 164
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00017501110696304596,
      "loss": 1.8509,
      "step": 165
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00017459411454241822,
      "loss": 1.8403,
      "step": 166
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00017417417727387394,
      "loss": 1.9279,
      "step": 167
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001737513117358174,
      "loss": 1.7867,
      "step": 168
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00017332553462225602,
      "loss": 1.8755,
      "step": 169
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00017289686274214118,
      "loss": 1.8639,
      "step": 170
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001724653130187047,
      "loss": 1.8795,
      "step": 171
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001720309024887907,
      "loss": 1.8081,
      "step": 172
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00017159364830218312,
      "loss": 1.8725,
      "step": 173
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00017115356772092857,
      "loss": 1.8081,
      "step": 174
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.8939,
      "step": 175
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00017026499697988493,
      "loss": 1.819,
      "step": 176
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00016981654189934727,
      "loss": 1.8051,
      "step": 177
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001693653305812805,
      "loss": 1.8504,
      "step": 178
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00016891138083873487,
      "loss": 1.7902,
      "step": 179
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00016845471059286887,
      "loss": 1.787,
      "step": 180
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00016799533787224192,
      "loss": 1.8533,
      "step": 181
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00016753328081210245,
      "loss": 1.831,
      "step": 182
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000167068557653672,
      "loss": 1.8204,
      "step": 183
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00016660118674342517,
      "loss": 1.8043,
      "step": 184
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00016613118653236518,
      "loss": 1.778,
      "step": 185
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00016565857557529566,
      "loss": 1.7868,
      "step": 186
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001651833725300879,
      "loss": 1.8423,
      "step": 187
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00016470559615694446,
      "loss": 1.8157,
      "step": 188
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00016422526531765846,
      "loss": 1.7796,
      "step": 189
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000163742398974869,
      "loss": 1.705,
      "step": 190
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00016325701619131246,
      "loss": 1.7537,
      "step": 191
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00016276913612907007,
      "loss": 1.7629,
      "step": 192
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00016227877804881127,
      "loss": 1.7667,
      "step": 193
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00016178596130903344,
      "loss": 1.7376,
      "step": 194
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00016129070536529766,
      "loss": 1.7776,
      "step": 195
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00016079302976946055,
      "loss": 1.6759,
      "step": 196
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00016029295416890248,
      "loss": 1.7559,
      "step": 197
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001597904983057519,
      "loss": 1.76,
      "step": 198
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00015928568201610595,
      "loss": 1.7412,
      "step": 199
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00015877852522924732,
      "loss": 1.6685,
      "step": 200
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00015826904796685762,
      "loss": 1.7587,
      "step": 201
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00015775727034222675,
      "loss": 1.7417,
      "step": 202
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001572432125594591,
      "loss": 1.6513,
      "step": 203
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00015672689491267567,
      "loss": 1.6968,
      "step": 204
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00015620833778521307,
      "loss": 1.6509,
      "step": 205
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00015568756164881882,
      "loss": 1.6245,
      "step": 206
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00015516458706284303,
      "loss": 1.6608,
      "step": 207
    },
    {
      "epoch": 0.75,
      "eval_loss": 1.6871771812438965,
      "eval_runtime": 44.071,
      "eval_samples_per_second": 25.64,
      "eval_steps_per_second": 1.611,
      "step": 207
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00015463943467342693,
      "loss": 1.6572,
      "step": 208
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00015411212521268758,
      "loss": 1.5938,
      "step": 209
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00015358267949789966,
      "loss": 1.6421,
      "step": 210
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001530511184306734,
      "loss": 1.7423,
      "step": 211
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001525174629961296,
      "loss": 1.6636,
      "step": 212
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00015198173426207094,
      "loss": 1.7339,
      "step": 213
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00015144395337815064,
      "loss": 1.6729,
      "step": 214
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00015090414157503714,
      "loss": 1.6939,
      "step": 215
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001503623201635761,
      "loss": 1.6394,
      "step": 216
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001498185105339491,
      "loss": 1.6196,
      "step": 217
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00014927273415482915,
      "loss": 1.6304,
      "step": 218
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00014872501257253323,
      "loss": 1.6124,
      "step": 219
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00014817536741017152,
      "loss": 1.6011,
      "step": 220
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001476238203667939,
      "loss": 1.5667,
      "step": 221
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001470703932165333,
      "loss": 1.6536,
      "step": 222
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00014651510780774583,
      "loss": 1.5861,
      "step": 223
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00014595798606214882,
      "loss": 1.5339,
      "step": 224
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00014539904997395468,
      "loss": 1.6058,
      "step": 225
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00014483832160900326,
      "loss": 1.605,
      "step": 226
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001442758231038902,
      "loss": 1.5731,
      "step": 227
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001437115766650933,
      "loss": 1.5876,
      "step": 228
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001431456045680959,
      "loss": 1.6278,
      "step": 229
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00014257792915650728,
      "loss": 1.5877,
      "step": 230
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00014200857284118066,
      "loss": 1.5985,
      "step": 231
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00014143755809932845,
      "loss": 1.5359,
      "step": 232
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00014086490747363493,
      "loss": 1.4969,
      "step": 233
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00014029064357136628,
      "loss": 1.5615,
      "step": 234
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00013971478906347806,
      "loss": 1.5356,
      "step": 235
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00013913736668372026,
      "loss": 1.5306,
      "step": 236
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00013855839922773968,
      "loss": 1.4575,
      "step": 237
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00013797790955218014,
      "loss": 1.5216,
      "step": 238
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00013739592057378003,
      "loss": 1.5153,
      "step": 239
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00013681245526846783,
      "loss": 1.4623,
      "step": 240
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00013622753667045457,
      "loss": 1.4995,
      "step": 241
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00013564118787132506,
      "loss": 1.5363,
      "step": 242
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001350534320191259,
      "loss": 1.425,
      "step": 243
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001344642923174517,
      "loss": 1.4145,
      "step": 244
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00013387379202452917,
      "loss": 1.4994,
      "step": 245
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00013328195445229868,
      "loss": 1.4758,
      "step": 246
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00013268880296549425,
      "loss": 1.5288,
      "step": 247
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00013209436098072095,
      "loss": 1.4809,
      "step": 248
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001314986519655305,
      "loss": 1.4916,
      "step": 249
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.5181,
      "step": 250
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00013030352696327742,
      "loss": 1.4987,
      "step": 251
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001297041581577035,
      "loss": 1.4526,
      "step": 252
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00012910361668282719,
      "loss": 1.4375,
      "step": 253
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001285019262469976,
      "loss": 1.4934,
      "step": 254
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00012789911060392294,
      "loss": 1.443,
      "step": 255
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00012729519355173254,
      "loss": 1.359,
      "step": 256
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00012669019893203759,
      "loss": 1.4471,
      "step": 257
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00012608415062898972,
      "loss": 1.4615,
      "step": 258
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00012547707256833823,
      "loss": 1.4249,
      "step": 259
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001248689887164855,
      "loss": 1.4157,
      "step": 260
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00012425992307954075,
      "loss": 1.4213,
      "step": 261
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00012364989970237248,
      "loss": 1.3552,
      "step": 262
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00012303894266765908,
      "loss": 1.3715,
      "step": 263
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00012242707609493814,
      "loss": 1.3484,
      "step": 264
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00012181432413965428,
      "loss": 1.4268,
      "step": 265
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00012120071099220549,
      "loss": 1.3612,
      "step": 266
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00012058626087698814,
      "loss": 1.341,
      "step": 267
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00011997099805144069,
      "loss": 1.3221,
      "step": 268
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00011935494680508606,
      "loss": 1.3872,
      "step": 269
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00011873813145857249,
      "loss": 1.4136,
      "step": 270
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00011812057636271374,
      "loss": 1.3503,
      "step": 271
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00011750230589752762,
      "loss": 1.4157,
      "step": 272
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00011688334447127338,
      "loss": 1.3828,
      "step": 273
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00011626371651948838,
      "loss": 1.3542,
      "step": 274
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001156434465040231,
      "loss": 1.3105,
      "step": 275
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00011502255891207572,
      "loss": 1.3767,
      "step": 276
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.3322992324829102,
      "eval_runtime": 43.9906,
      "eval_samples_per_second": 25.687,
      "eval_steps_per_second": 1.614,
      "step": 276
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00011440107825522521,
      "loss": 1.329,
      "step": 277
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001137790290684638,
      "loss": 1.3425,
      "step": 278
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00011315643590922827,
      "loss": 1.3341,
      "step": 279
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00011253332335643043,
      "loss": 1.2998,
      "step": 280
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00011190971600948699,
      "loss": 1.2836,
      "step": 281
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00011128563848734816,
      "loss": 0.9234,
      "step": 282
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.000110661115427526,
      "loss": 1.0205,
      "step": 283
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00011003617148512149,
      "loss": 0.8919,
      "step": 284
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00010941083133185146,
      "loss": 0.9155,
      "step": 285
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00010878511965507434,
      "loss": 0.9399,
      "step": 286
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00010815906115681578,
      "loss": 0.9605,
      "step": 287
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00010753268055279329,
      "loss": 0.9216,
      "step": 288
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00010690600257144061,
      "loss": 0.8771,
      "step": 289
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00010627905195293135,
      "loss": 0.8391,
      "step": 290
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00010565185344820247,
      "loss": 0.8604,
      "step": 291
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00010502443181797697,
      "loss": 0.911,
      "step": 292
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001043968118317865,
      "loss": 0.9754,
      "step": 293
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00010376901826699348,
      "loss": 0.9006,
      "step": 294
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00010314107590781284,
      "loss": 0.8617,
      "step": 295
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00010251300954433376,
      "loss": 0.9077,
      "step": 296
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00010188484397154084,
      "loss": 0.8979,
      "step": 297
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00010125660398833528,
      "loss": 0.8798,
      "step": 298
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00010062831439655591,
      "loss": 0.8271,
      "step": 299
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0001,
      "loss": 0.8504,
      "step": 300
    },
    {
      "epoch": 1.07,
      "learning_rate": 9.937168560344412e-05,
      "loss": 0.8761,
      "step": 301
    },
    {
      "epoch": 1.08,
      "learning_rate": 9.874339601166473e-05,
      "loss": 0.9453,
      "step": 302
    },
    {
      "epoch": 1.08,
      "learning_rate": 9.81151560284592e-05,
      "loss": 0.828,
      "step": 303
    },
    {
      "epoch": 1.08,
      "learning_rate": 9.748699045566626e-05,
      "loss": 0.7736,
      "step": 304
    },
    {
      "epoch": 1.09,
      "learning_rate": 9.685892409218717e-05,
      "loss": 0.8621,
      "step": 305
    },
    {
      "epoch": 1.09,
      "learning_rate": 9.623098173300654e-05,
      "loss": 0.8606,
      "step": 306
    },
    {
      "epoch": 1.09,
      "learning_rate": 9.560318816821353e-05,
      "loss": 0.8186,
      "step": 307
    },
    {
      "epoch": 1.1,
      "learning_rate": 9.497556818202306e-05,
      "loss": 0.8447,
      "step": 308
    },
    {
      "epoch": 1.1,
      "learning_rate": 9.434814655179755e-05,
      "loss": 0.8451,
      "step": 309
    },
    {
      "epoch": 1.11,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.8788,
      "step": 310
    },
    {
      "epoch": 1.11,
      "learning_rate": 9.309399742855942e-05,
      "loss": 0.8211,
      "step": 311
    },
    {
      "epoch": 1.11,
      "learning_rate": 9.246731944720675e-05,
      "loss": 0.8384,
      "step": 312
    },
    {
      "epoch": 1.12,
      "learning_rate": 9.184093884318425e-05,
      "loss": 0.8284,
      "step": 313
    },
    {
      "epoch": 1.12,
      "learning_rate": 9.121488034492569e-05,
      "loss": 0.8377,
      "step": 314
    },
    {
      "epoch": 1.12,
      "learning_rate": 9.058916866814858e-05,
      "loss": 0.8355,
      "step": 315
    },
    {
      "epoch": 1.13,
      "learning_rate": 8.99638285148785e-05,
      "loss": 0.8995,
      "step": 316
    },
    {
      "epoch": 1.13,
      "learning_rate": 8.933888457247402e-05,
      "loss": 0.8128,
      "step": 317
    },
    {
      "epoch": 1.13,
      "learning_rate": 8.871436151265184e-05,
      "loss": 0.8239,
      "step": 318
    },
    {
      "epoch": 1.14,
      "learning_rate": 8.809028399051302e-05,
      "loss": 0.8796,
      "step": 319
    },
    {
      "epoch": 1.14,
      "learning_rate": 8.746667664356956e-05,
      "loss": 0.8583,
      "step": 320
    },
    {
      "epoch": 1.15,
      "learning_rate": 8.684356409077176e-05,
      "loss": 0.8328,
      "step": 321
    },
    {
      "epoch": 1.15,
      "learning_rate": 8.62209709315362e-05,
      "loss": 0.8706,
      "step": 322
    },
    {
      "epoch": 1.15,
      "learning_rate": 8.559892174477479e-05,
      "loss": 0.8346,
      "step": 323
    },
    {
      "epoch": 1.16,
      "learning_rate": 8.497744108792429e-05,
      "loss": 0.8461,
      "step": 324
    },
    {
      "epoch": 1.16,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.8005,
      "step": 325
    },
    {
      "epoch": 1.16,
      "learning_rate": 8.373628348051165e-05,
      "loss": 0.8283,
      "step": 326
    },
    {
      "epoch": 1.17,
      "learning_rate": 8.311665552872662e-05,
      "loss": 0.8153,
      "step": 327
    },
    {
      "epoch": 1.17,
      "learning_rate": 8.249769410247239e-05,
      "loss": 0.819,
      "step": 328
    },
    {
      "epoch": 1.17,
      "learning_rate": 8.187942363728625e-05,
      "loss": 0.7948,
      "step": 329
    },
    {
      "epoch": 1.18,
      "learning_rate": 8.126186854142752e-05,
      "loss": 0.8707,
      "step": 330
    },
    {
      "epoch": 1.18,
      "learning_rate": 8.064505319491398e-05,
      "loss": 0.7892,
      "step": 331
    },
    {
      "epoch": 1.19,
      "learning_rate": 8.002900194855932e-05,
      "loss": 0.7967,
      "step": 332
    },
    {
      "epoch": 1.19,
      "learning_rate": 7.941373912301189e-05,
      "loss": 0.8121,
      "step": 333
    },
    {
      "epoch": 1.19,
      "learning_rate": 7.879928900779456e-05,
      "loss": 0.8048,
      "step": 334
    },
    {
      "epoch": 1.2,
      "learning_rate": 7.818567586034577e-05,
      "loss": 0.8349,
      "step": 335
    },
    {
      "epoch": 1.2,
      "learning_rate": 7.75729239050619e-05,
      "loss": 0.8283,
      "step": 336
    },
    {
      "epoch": 1.2,
      "learning_rate": 7.696105733234098e-05,
      "loss": 0.7967,
      "step": 337
    },
    {
      "epoch": 1.21,
      "learning_rate": 7.635010029762756e-05,
      "loss": 0.7849,
      "step": 338
    },
    {
      "epoch": 1.21,
      "learning_rate": 7.574007692045928e-05,
      "loss": 0.7551,
      "step": 339
    },
    {
      "epoch": 1.21,
      "learning_rate": 7.513101128351454e-05,
      "loss": 0.7867,
      "step": 340
    },
    {
      "epoch": 1.22,
      "learning_rate": 7.45229274316618e-05,
      "loss": 0.803,
      "step": 341
    },
    {
      "epoch": 1.22,
      "learning_rate": 7.391584937101033e-05,
      "loss": 0.7521,
      "step": 342
    },
    {
      "epoch": 1.23,
      "learning_rate": 7.330980106796246e-05,
      "loss": 0.763,
      "step": 343
    },
    {
      "epoch": 1.23,
      "learning_rate": 7.270480644826749e-05,
      "loss": 0.7401,
      "step": 344
    },
    {
      "epoch": 1.23,
      "learning_rate": 7.210088939607708e-05,
      "loss": 0.7872,
      "step": 345
    },
    {
      "epoch": 1.23,
      "eval_loss": 1.0583446025848389,
      "eval_runtime": 44.1159,
      "eval_samples_per_second": 25.614,
      "eval_steps_per_second": 1.609,
      "step": 345
    },
    {
      "epoch": 1.24,
      "learning_rate": 7.149807375300239e-05,
      "loss": 0.815,
      "step": 346
    },
    {
      "epoch": 1.24,
      "learning_rate": 7.089638331717284e-05,
      "loss": 0.7244,
      "step": 347
    },
    {
      "epoch": 1.24,
      "learning_rate": 7.029584184229653e-05,
      "loss": 0.7499,
      "step": 348
    },
    {
      "epoch": 1.25,
      "learning_rate": 6.969647303672262e-05,
      "loss": 0.6976,
      "step": 349
    },
    {
      "epoch": 1.25,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.787,
      "step": 350
    },
    {
      "epoch": 1.25,
      "learning_rate": 6.850134803446954e-05,
      "loss": 0.8019,
      "step": 351
    },
    {
      "epoch": 1.26,
      "learning_rate": 6.790563901927907e-05,
      "loss": 0.7323,
      "step": 352
    },
    {
      "epoch": 1.26,
      "learning_rate": 6.731119703450577e-05,
      "loss": 0.7873,
      "step": 353
    },
    {
      "epoch": 1.27,
      "learning_rate": 6.671804554770135e-05,
      "loss": 0.8039,
      "step": 354
    },
    {
      "epoch": 1.27,
      "learning_rate": 6.612620797547087e-05,
      "loss": 0.7192,
      "step": 355
    },
    {
      "epoch": 1.27,
      "learning_rate": 6.55357076825483e-05,
      "loss": 0.7871,
      "step": 356
    },
    {
      "epoch": 1.28,
      "learning_rate": 6.494656798087412e-05,
      "loss": 0.6948,
      "step": 357
    },
    {
      "epoch": 1.28,
      "learning_rate": 6.435881212867493e-05,
      "loss": 0.7302,
      "step": 358
    },
    {
      "epoch": 1.28,
      "learning_rate": 6.377246332954544e-05,
      "loss": 0.7555,
      "step": 359
    },
    {
      "epoch": 1.29,
      "learning_rate": 6.318754473153221e-05,
      "loss": 0.7155,
      "step": 360
    },
    {
      "epoch": 1.29,
      "learning_rate": 6.260407942621998e-05,
      "loss": 0.7348,
      "step": 361
    },
    {
      "epoch": 1.29,
      "learning_rate": 6.20220904478199e-05,
      "loss": 0.7378,
      "step": 362
    },
    {
      "epoch": 1.3,
      "learning_rate": 6.144160077226036e-05,
      "loss": 0.6851,
      "step": 363
    },
    {
      "epoch": 1.3,
      "learning_rate": 6.086263331627976e-05,
      "loss": 0.7479,
      "step": 364
    },
    {
      "epoch": 1.31,
      "learning_rate": 6.0285210936521955e-05,
      "loss": 0.6409,
      "step": 365
    },
    {
      "epoch": 1.31,
      "learning_rate": 5.9709356428633746e-05,
      "loss": 0.697,
      "step": 366
    },
    {
      "epoch": 1.31,
      "learning_rate": 5.913509252636511e-05,
      "loss": 0.7208,
      "step": 367
    },
    {
      "epoch": 1.32,
      "learning_rate": 5.856244190067159e-05,
      "loss": 0.7362,
      "step": 368
    },
    {
      "epoch": 1.32,
      "learning_rate": 5.799142715881938e-05,
      "loss": 0.7458,
      "step": 369
    },
    {
      "epoch": 1.32,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 0.715,
      "step": 370
    },
    {
      "epoch": 1.33,
      "learning_rate": 5.6854395431904094e-05,
      "loss": 0.7802,
      "step": 371
    },
    {
      "epoch": 1.33,
      "learning_rate": 5.6288423334906735e-05,
      "loss": 0.7155,
      "step": 372
    },
    {
      "epoch": 1.33,
      "learning_rate": 5.572417689610987e-05,
      "loss": 0.7218,
      "step": 373
    },
    {
      "epoch": 1.34,
      "learning_rate": 5.5161678390996796e-05,
      "loss": 0.6944,
      "step": 374
    },
    {
      "epoch": 1.34,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 0.6461,
      "step": 375
    },
    {
      "epoch": 1.35,
      "learning_rate": 5.404201393785122e-05,
      "loss": 0.6931,
      "step": 376
    },
    {
      "epoch": 1.35,
      "learning_rate": 5.348489219225416e-05,
      "loss": 0.6618,
      "step": 377
    },
    {
      "epoch": 1.35,
      "learning_rate": 5.292960678346675e-05,
      "loss": 0.6212,
      "step": 378
    },
    {
      "epoch": 1.36,
      "learning_rate": 5.237617963320608e-05,
      "loss": 0.7231,
      "step": 379
    },
    {
      "epoch": 1.36,
      "learning_rate": 5.182463258982846e-05,
      "loss": 0.6582,
      "step": 380
    },
    {
      "epoch": 1.36,
      "learning_rate": 5.127498742746675e-05,
      "loss": 0.6574,
      "step": 381
    },
    {
      "epoch": 1.37,
      "learning_rate": 5.072726584517086e-05,
      "loss": 0.6529,
      "step": 382
    },
    {
      "epoch": 1.37,
      "learning_rate": 5.018148946605092e-05,
      "loss": 0.6178,
      "step": 383
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.9637679836423924e-05,
      "loss": 0.7012,
      "step": 384
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.909585842496287e-05,
      "loss": 0.7101,
      "step": 385
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.8556046621849346e-05,
      "loss": 0.6351,
      "step": 386
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.8018265737929044e-05,
      "loss": 0.6254,
      "step": 387
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.748253700387042e-05,
      "loss": 0.6286,
      "step": 388
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.694888156932658e-05,
      "loss": 0.6273,
      "step": 389
    },
    {
      "epoch": 1.4,
      "learning_rate": 4.6417320502100316e-05,
      "loss": 0.5979,
      "step": 390
    },
    {
      "epoch": 1.4,
      "learning_rate": 4.588787478731242e-05,
      "loss": 0.6387,
      "step": 391
    },
    {
      "epoch": 1.4,
      "learning_rate": 4.5360565326573104e-05,
      "loss": 0.5849,
      "step": 392
    },
    {
      "epoch": 1.41,
      "learning_rate": 4.483541293715698e-05,
      "loss": 0.6265,
      "step": 393
    },
    {
      "epoch": 1.41,
      "learning_rate": 4.431243835118124e-05,
      "loss": 0.7038,
      "step": 394
    },
    {
      "epoch": 1.41,
      "learning_rate": 4.379166221478697e-05,
      "loss": 0.5836,
      "step": 395
    },
    {
      "epoch": 1.42,
      "learning_rate": 4.327310508732437e-05,
      "loss": 0.6163,
      "step": 396
    },
    {
      "epoch": 1.42,
      "learning_rate": 4.2756787440540936e-05,
      "loss": 0.6606,
      "step": 397
    },
    {
      "epoch": 1.43,
      "learning_rate": 4.224272965777326e-05,
      "loss": 0.6412,
      "step": 398
    },
    {
      "epoch": 1.43,
      "learning_rate": 4.173095203314241e-05,
      "loss": 0.6556,
      "step": 399
    },
    {
      "epoch": 1.43,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.6199,
      "step": 400
    },
    {
      "epoch": 1.44,
      "learning_rate": 4.071431798389408e-05,
      "loss": 0.6253,
      "step": 401
    },
    {
      "epoch": 1.44,
      "learning_rate": 4.020950169424815e-05,
      "loss": 0.6303,
      "step": 402
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.9707045831097555e-05,
      "loss": 0.6379,
      "step": 403
    },
    {
      "epoch": 1.45,
      "learning_rate": 3.920697023053949e-05,
      "loss": 0.589,
      "step": 404
    },
    {
      "epoch": 1.45,
      "learning_rate": 3.8709294634702376e-05,
      "loss": 0.5801,
      "step": 405
    },
    {
      "epoch": 1.45,
      "learning_rate": 3.821403869096658e-05,
      "loss": 0.5913,
      "step": 406
    },
    {
      "epoch": 1.46,
      "learning_rate": 3.7721221951188765e-05,
      "loss": 0.6082,
      "step": 407
    },
    {
      "epoch": 1.46,
      "learning_rate": 3.7230863870929964e-05,
      "loss": 0.6199,
      "step": 408
    },
    {
      "epoch": 1.47,
      "learning_rate": 3.674298380868756e-05,
      "loss": 0.5785,
      "step": 409
    },
    {
      "epoch": 1.47,
      "learning_rate": 3.6257601025131026e-05,
      "loss": 0.588,
      "step": 410
    },
    {
      "epoch": 1.47,
      "learning_rate": 3.577473468234156e-05,
      "loss": 0.5988,
      "step": 411
    },
    {
      "epoch": 1.48,
      "learning_rate": 3.52944038430556e-05,
      "loss": 0.5986,
      "step": 412
    },
    {
      "epoch": 1.48,
      "learning_rate": 3.481662746991214e-05,
      "loss": 0.6181,
      "step": 413
    },
    {
      "epoch": 1.48,
      "learning_rate": 3.4341424424704375e-05,
      "loss": 0.5873,
      "step": 414
    },
    {
      "epoch": 1.48,
      "eval_loss": 0.8250847458839417,
      "eval_runtime": 44.0494,
      "eval_samples_per_second": 25.653,
      "eval_steps_per_second": 1.612,
      "step": 414
    },
    {
      "epoch": 1.49,
      "learning_rate": 3.386881346763483e-05,
      "loss": 0.599,
      "step": 415
    },
    {
      "epoch": 1.49,
      "learning_rate": 3.339881325657484e-05,
      "loss": 0.5636,
      "step": 416
    },
    {
      "epoch": 1.49,
      "learning_rate": 3.2931442346328004e-05,
      "loss": 0.5657,
      "step": 417
    },
    {
      "epoch": 1.5,
      "learning_rate": 3.246671918789755e-05,
      "loss": 0.6404,
      "step": 418
    },
    {
      "epoch": 1.5,
      "learning_rate": 3.200466212775808e-05,
      "loss": 0.6046,
      "step": 419
    },
    {
      "epoch": 1.51,
      "learning_rate": 3.154528940713113e-05,
      "loss": 0.5863,
      "step": 420
    },
    {
      "epoch": 1.51,
      "learning_rate": 3.108861916126518e-05,
      "loss": 0.5241,
      "step": 421
    },
    {
      "epoch": 1.51,
      "learning_rate": 3.063466941871952e-05,
      "loss": 0.5882,
      "step": 422
    },
    {
      "epoch": 1.52,
      "learning_rate": 3.018345810065275e-05,
      "loss": 0.5735,
      "step": 423
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.9735003020115092e-05,
      "loss": 0.6128,
      "step": 424
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.5456,
      "step": 425
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.8846432279071467e-05,
      "loss": 0.5692,
      "step": 426
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.840635169781688e-05,
      "loss": 0.5997,
      "step": 427
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.7969097511209308e-05,
      "loss": 0.5698,
      "step": 428
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.753468698129533e-05,
      "loss": 0.5583,
      "step": 429
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 0.5595,
      "step": 430
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.6674465377744017e-05,
      "loss": 0.5426,
      "step": 431
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.624868826418262e-05,
      "loss": 0.5478,
      "step": 432
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.582582272612609e-05,
      "loss": 0.5857,
      "step": 433
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.540588545758179e-05,
      "loss": 0.5367,
      "step": 434
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.4988893036954043e-05,
      "loss": 0.5333,
      "step": 435
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.4574861926389615e-05,
      "loss": 0.5319,
      "step": 436
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.4163808471127812e-05,
      "loss": 0.59,
      "step": 437
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.37557488988552e-05,
      "loss": 0.5218,
      "step": 438
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.3350699319065026e-05,
      "loss": 0.5501,
      "step": 439
    },
    {
      "epoch": 1.58,
      "learning_rate": 2.2948675722421086e-05,
      "loss": 0.5955,
      "step": 440
    },
    {
      "epoch": 1.58,
      "learning_rate": 2.254969398012663e-05,
      "loss": 0.5356,
      "step": 441
    },
    {
      "epoch": 1.59,
      "learning_rate": 2.2153769843297667e-05,
      "loss": 0.5743,
      "step": 442
    },
    {
      "epoch": 1.59,
      "learning_rate": 2.1760918942341192e-05,
      "loss": 0.5952,
      "step": 443
    },
    {
      "epoch": 1.59,
      "learning_rate": 2.137115678633811e-05,
      "loss": 0.5604,
      "step": 444
    },
    {
      "epoch": 1.6,
      "learning_rate": 2.098449876243096e-05,
      "loss": 0.5339,
      "step": 445
    },
    {
      "epoch": 1.6,
      "learning_rate": 2.0600960135216462e-05,
      "loss": 0.5411,
      "step": 446
    },
    {
      "epoch": 1.6,
      "learning_rate": 2.0220556046142893e-05,
      "loss": 0.554,
      "step": 447
    },
    {
      "epoch": 1.61,
      "learning_rate": 1.9843301512912327e-05,
      "loss": 0.5875,
      "step": 448
    },
    {
      "epoch": 1.61,
      "learning_rate": 1.946921142888781e-05,
      "loss": 0.5284,
      "step": 449
    },
    {
      "epoch": 1.61,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.5418,
      "step": 450
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.8730583556690605e-05,
      "loss": 0.5146,
      "step": 451
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.8366074928281607e-05,
      "loss": 0.5023,
      "step": 452
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.8004789067454764e-05,
      "loss": 0.5407,
      "step": 453
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.7646740237157256e-05,
      "loss": 0.5389,
      "step": 454
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.7291942572543807e-05,
      "loss": 0.5224,
      "step": 455
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.6940410080418723e-05,
      "loss": 0.503,
      "step": 456
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.6592156638682886e-05,
      "loss": 0.5115,
      "step": 457
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.6247195995785837e-05,
      "loss": 0.5031,
      "step": 458
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.5905541770183096e-05,
      "loss": 0.5371,
      "step": 459
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.5567207449798515e-05,
      "loss": 0.5685,
      "step": 460
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.5232206391491699e-05,
      "loss": 0.5498,
      "step": 461
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.4900551820530828e-05,
      "loss": 0.5875,
      "step": 462
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.4572256830070497e-05,
      "loss": 0.499,
      "step": 463
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.4247334380634792e-05,
      "loss": 0.5447,
      "step": 464
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.3925797299605647e-05,
      "loss": 0.4996,
      "step": 465
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.3607658280716473e-05,
      "loss": 0.5528,
      "step": 466
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.3292929883550998e-05,
      "loss": 0.5656,
      "step": 467
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.2981624533047432e-05,
      "loss": 0.5276,
      "step": 468
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.2673754519008008e-05,
      "loss": 0.5376,
      "step": 469
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.2369331995613665e-05,
      "loss": 0.525,
      "step": 470
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.206836898094439e-05,
      "loss": 0.5625,
      "step": 471
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.1770877356504683e-05,
      "loss": 0.512,
      "step": 472
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.1476868866754486e-05,
      "loss": 0.5057,
      "step": 473
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.1186355118645554e-05,
      "loss": 0.5255,
      "step": 474
    },
    {
      "epoch": 1.71,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.5742,
      "step": 475
    },
    {
      "epoch": 1.71,
      "learning_rate": 1.0615857584873623e-05,
      "loss": 0.5368,
      "step": 476
    },
    {
      "epoch": 1.71,
      "learning_rate": 1.0335896321476413e-05,
      "loss": 0.5122,
      "step": 477
    },
    {
      "epoch": 1.72,
      "learning_rate": 1.0059474843362892e-05,
      "loss": 0.5292,
      "step": 478
    },
    {
      "epoch": 1.72,
      "learning_rate": 9.786604063179728e-06,
      "loss": 0.4903,
      "step": 479
    },
    {
      "epoch": 1.72,
      "learning_rate": 9.517294753398064e-06,
      "loss": 0.5403,
      "step": 480
    },
    {
      "epoch": 1.73,
      "learning_rate": 9.251557545888312e-06,
      "loss": 0.5243,
      "step": 481
    },
    {
      "epoch": 1.73,
      "learning_rate": 8.989402931500434e-06,
      "loss": 0.5179,
      "step": 482
    },
    {
      "epoch": 1.73,
      "learning_rate": 8.730841259649725e-06,
      "loss": 0.5154,
      "step": 483
    },
    {
      "epoch": 1.73,
      "eval_loss": 0.7377763986587524,
      "eval_runtime": 44.2257,
      "eval_samples_per_second": 25.551,
      "eval_steps_per_second": 1.605,
      "step": 483
    },
    {
      "epoch": 1.74,
      "learning_rate": 8.475882737908248e-06,
      "loss": 0.5378,
      "step": 484
    },
    {
      "epoch": 1.74,
      "learning_rate": 8.224537431601886e-06,
      "loss": 0.5589,
      "step": 485
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.976815263412963e-06,
      "loss": 0.5938,
      "step": 486
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.73272601298851e-06,
      "loss": 0.5143,
      "step": 487
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.492279316554207e-06,
      "loss": 0.5098,
      "step": 488
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.255484666533874e-06,
      "loss": 0.5097,
      "step": 489
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.022351411174866e-06,
      "loss": 0.5456,
      "step": 490
    },
    {
      "epoch": 1.76,
      "learning_rate": 6.7928887541789055e-06,
      "loss": 0.539,
      "step": 491
    },
    {
      "epoch": 1.77,
      "learning_rate": 6.5671057543387985e-06,
      "loss": 0.471,
      "step": 492
    },
    {
      "epoch": 1.77,
      "learning_rate": 6.345011325180772e-06,
      "loss": 0.506,
      "step": 493
    },
    {
      "epoch": 1.77,
      "learning_rate": 6.126614234612593e-06,
      "loss": 0.5465,
      "step": 494
    },
    {
      "epoch": 1.78,
      "learning_rate": 5.911923104577455e-06,
      "loss": 0.4872,
      "step": 495
    },
    {
      "epoch": 1.78,
      "learning_rate": 5.700946410713548e-06,
      "loss": 0.5338,
      "step": 496
    },
    {
      "epoch": 1.79,
      "learning_rate": 5.49369248201953e-06,
      "loss": 0.5305,
      "step": 497
    },
    {
      "epoch": 1.79,
      "learning_rate": 5.290169500525577e-06,
      "loss": 0.4829,
      "step": 498
    },
    {
      "epoch": 1.79,
      "learning_rate": 5.0903855009705514e-06,
      "loss": 0.5006,
      "step": 499
    },
    {
      "epoch": 1.8,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.5341,
      "step": 500
    },
    {
      "epoch": 1.8,
      "learning_rate": 4.702065848278126e-06,
      "loss": 0.5244,
      "step": 501
    },
    {
      "epoch": 1.8,
      "learning_rate": 4.513545525335705e-06,
      "loss": 0.5144,
      "step": 502
    },
    {
      "epoch": 1.81,
      "learning_rate": 4.328794844116946e-06,
      "loss": 0.5192,
      "step": 503
    },
    {
      "epoch": 1.81,
      "learning_rate": 4.147821098262405e-06,
      "loss": 0.4968,
      "step": 504
    },
    {
      "epoch": 1.81,
      "learning_rate": 3.970631432305694e-06,
      "loss": 0.5383,
      "step": 505
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.797232841391407e-06,
      "loss": 0.5149,
      "step": 506
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.627632170999029e-06,
      "loss": 0.5104,
      "step": 507
    },
    {
      "epoch": 1.83,
      "learning_rate": 3.461836116672612e-06,
      "loss": 0.5108,
      "step": 508
    },
    {
      "epoch": 1.83,
      "learning_rate": 3.2998512237565005e-06,
      "loss": 0.526,
      "step": 509
    },
    {
      "epoch": 1.83,
      "learning_rate": 3.1416838871368924e-06,
      "loss": 0.5518,
      "step": 510
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.9873403509894203e-06,
      "loss": 0.5257,
      "step": 511
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.836826708532603e-06,
      "loss": 0.5527,
      "step": 512
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.690148901787337e-06,
      "loss": 0.5411,
      "step": 513
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.5473127213422763e-06,
      "loss": 0.4848,
      "step": 514
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.4083238061252567e-06,
      "loss": 0.5216,
      "step": 515
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.273187643180652e-06,
      "loss": 0.526,
      "step": 516
    },
    {
      "epoch": 1.86,
      "learning_rate": 2.141909567452793e-06,
      "loss": 0.5351,
      "step": 517
    },
    {
      "epoch": 1.86,
      "learning_rate": 2.014494761575314e-06,
      "loss": 0.5087,
      "step": 518
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.8909482556666024e-06,
      "loss": 0.4533,
      "step": 519
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.771274927131139e-06,
      "loss": 0.5023,
      "step": 520
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.6554795004670388e-06,
      "loss": 0.5154,
      "step": 521
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.543566547079467e-06,
      "loss": 0.5292,
      "step": 522
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.4355404851001952e-06,
      "loss": 0.5136,
      "step": 523
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.3314055792131964e-06,
      "loss": 0.5698,
      "step": 524
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.231165940486234e-06,
      "loss": 0.5363,
      "step": 525
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.134825526208605e-06,
      "loss": 0.4928,
      "step": 526
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.0423881397349068e-06,
      "loss": 0.5235,
      "step": 527
    },
    {
      "epoch": 1.9,
      "learning_rate": 9.538574303348813e-07,
      "loss": 0.5244,
      "step": 528
    },
    {
      "epoch": 1.9,
      "learning_rate": 8.692368930493521e-07,
      "loss": 0.5381,
      "step": 529
    },
    {
      "epoch": 1.91,
      "learning_rate": 7.885298685522235e-07,
      "loss": 0.5538,
      "step": 530
    },
    {
      "epoch": 1.91,
      "learning_rate": 7.117395430186414e-07,
      "loss": 0.5859,
      "step": 531
    },
    {
      "epoch": 1.91,
      "learning_rate": 6.388689479991605e-07,
      "loss": 0.541,
      "step": 532
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.699209603001076e-07,
      "loss": 0.5342,
      "step": 533
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.048983018699827e-07,
      "loss": 0.5255,
      "step": 534
    },
    {
      "epoch": 1.92,
      "learning_rate": 4.438035396920004e-07,
      "loss": 0.4907,
      "step": 535
    },
    {
      "epoch": 1.93,
      "learning_rate": 3.866390856827495e-07,
      "loss": 0.5084,
      "step": 536
    },
    {
      "epoch": 1.93,
      "learning_rate": 3.3340719659701313e-07,
      "loss": 0.5013,
      "step": 537
    },
    {
      "epoch": 1.93,
      "learning_rate": 2.841099739386066e-07,
      "loss": 0.5997,
      "step": 538
    },
    {
      "epoch": 1.94,
      "learning_rate": 2.387493638774774e-07,
      "loss": 0.5665,
      "step": 539
    },
    {
      "epoch": 1.94,
      "learning_rate": 1.973271571728441e-07,
      "loss": 0.5652,
      "step": 540
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.598449891024978e-07,
      "loss": 0.5198,
      "step": 541
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.2630433939825327e-07,
      "loss": 0.5551,
      "step": 542
    },
    {
      "epoch": 1.95,
      "learning_rate": 9.670653218752934e-08,
      "loss": 0.4814,
      "step": 543
    },
    {
      "epoch": 1.96,
      "learning_rate": 7.105273594107953e-08,
      "loss": 0.5496,
      "step": 544
    },
    {
      "epoch": 1.96,
      "learning_rate": 4.934396342684e-08,
      "loss": 0.5146,
      "step": 545
    },
    {
      "epoch": 1.96,
      "learning_rate": 3.1581071670006015e-08,
      "loss": 0.5035,
      "step": 546
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.7764761919103477e-08,
      "loss": 0.4571,
      "step": 547
    },
    {
      "epoch": 1.97,
      "learning_rate": 7.895579618388827e-09,
      "loss": 0.4909,
      "step": 548
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.973914386288467e-09,
      "loss": 0.5427,
      "step": 549
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0,
      "loss": 0.5284,
      "step": 550
    }
  ],
  "logging_steps": 1,
  "max_steps": 550,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 275,
  "total_flos": 5.533792253824205e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}