Wanfq's picture
Upload folder using huggingface_hub
f53a932 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 1155,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 5.714285714285715e-07,
"loss": 0.4868,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 1.142857142857143e-06,
"loss": 0.4975,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 1.7142857142857145e-06,
"loss": 0.5102,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 2.285714285714286e-06,
"loss": 0.4681,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 2.8571428571428573e-06,
"loss": 0.4564,
"step": 5
},
{
"epoch": 0.02,
"learning_rate": 3.428571428571429e-06,
"loss": 0.4654,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 4.000000000000001e-06,
"loss": 0.4472,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 4.571428571428572e-06,
"loss": 0.4593,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 5.142857142857142e-06,
"loss": 0.4098,
"step": 9
},
{
"epoch": 0.03,
"learning_rate": 5.7142857142857145e-06,
"loss": 0.4698,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 6.285714285714286e-06,
"loss": 0.4479,
"step": 11
},
{
"epoch": 0.03,
"learning_rate": 6.857142857142858e-06,
"loss": 0.4194,
"step": 12
},
{
"epoch": 0.03,
"learning_rate": 7.428571428571429e-06,
"loss": 0.4717,
"step": 13
},
{
"epoch": 0.04,
"learning_rate": 8.000000000000001e-06,
"loss": 0.4196,
"step": 14
},
{
"epoch": 0.04,
"learning_rate": 8.571428571428571e-06,
"loss": 0.4257,
"step": 15
},
{
"epoch": 0.04,
"learning_rate": 9.142857142857144e-06,
"loss": 0.4308,
"step": 16
},
{
"epoch": 0.04,
"learning_rate": 9.714285714285715e-06,
"loss": 0.4301,
"step": 17
},
{
"epoch": 0.05,
"learning_rate": 1.0285714285714285e-05,
"loss": 0.472,
"step": 18
},
{
"epoch": 0.05,
"learning_rate": 1.0857142857142858e-05,
"loss": 0.4391,
"step": 19
},
{
"epoch": 0.05,
"learning_rate": 1.1428571428571429e-05,
"loss": 0.4184,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 1.2e-05,
"loss": 0.4483,
"step": 21
},
{
"epoch": 0.06,
"learning_rate": 1.2571428571428572e-05,
"loss": 0.4637,
"step": 22
},
{
"epoch": 0.06,
"learning_rate": 1.3142857142857145e-05,
"loss": 0.4559,
"step": 23
},
{
"epoch": 0.06,
"learning_rate": 1.3714285714285716e-05,
"loss": 0.4265,
"step": 24
},
{
"epoch": 0.06,
"learning_rate": 1.4285714285714287e-05,
"loss": 0.4282,
"step": 25
},
{
"epoch": 0.07,
"learning_rate": 1.4857142857142858e-05,
"loss": 0.4729,
"step": 26
},
{
"epoch": 0.07,
"learning_rate": 1.542857142857143e-05,
"loss": 0.4903,
"step": 27
},
{
"epoch": 0.07,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.4552,
"step": 28
},
{
"epoch": 0.08,
"learning_rate": 1.6571428571428574e-05,
"loss": 0.5345,
"step": 29
},
{
"epoch": 0.08,
"learning_rate": 1.7142857142857142e-05,
"loss": 0.4552,
"step": 30
},
{
"epoch": 0.08,
"learning_rate": 1.7714285714285717e-05,
"loss": 0.4995,
"step": 31
},
{
"epoch": 0.08,
"learning_rate": 1.8285714285714288e-05,
"loss": 0.4681,
"step": 32
},
{
"epoch": 0.09,
"learning_rate": 1.885714285714286e-05,
"loss": 0.4138,
"step": 33
},
{
"epoch": 0.09,
"learning_rate": 1.942857142857143e-05,
"loss": 0.5171,
"step": 34
},
{
"epoch": 0.09,
"learning_rate": 2e-05,
"loss": 0.5247,
"step": 35
},
{
"epoch": 0.09,
"learning_rate": 1.9999960660084782e-05,
"loss": 0.4537,
"step": 36
},
{
"epoch": 0.1,
"learning_rate": 1.9999842640648656e-05,
"loss": 0.4809,
"step": 37
},
{
"epoch": 0.1,
"learning_rate": 1.9999645942620192e-05,
"loss": 0.5046,
"step": 38
},
{
"epoch": 0.1,
"learning_rate": 1.9999370567547008e-05,
"loss": 0.4591,
"step": 39
},
{
"epoch": 0.1,
"learning_rate": 1.9999016517595752e-05,
"loss": 0.5057,
"step": 40
},
{
"epoch": 0.11,
"learning_rate": 1.9998583795552086e-05,
"loss": 0.524,
"step": 41
},
{
"epoch": 0.11,
"learning_rate": 1.9998072404820648e-05,
"loss": 0.5207,
"step": 42
},
{
"epoch": 0.11,
"learning_rate": 1.999748234942507e-05,
"loss": 0.5083,
"step": 43
},
{
"epoch": 0.11,
"learning_rate": 1.999681363400788e-05,
"loss": 0.4954,
"step": 44
},
{
"epoch": 0.12,
"learning_rate": 1.9996066263830533e-05,
"loss": 0.528,
"step": 45
},
{
"epoch": 0.12,
"learning_rate": 1.9995240244773315e-05,
"loss": 0.4914,
"step": 46
},
{
"epoch": 0.12,
"learning_rate": 1.9994335583335336e-05,
"loss": 0.4667,
"step": 47
},
{
"epoch": 0.12,
"learning_rate": 1.9993352286634455e-05,
"loss": 0.522,
"step": 48
},
{
"epoch": 0.13,
"learning_rate": 1.9992290362407232e-05,
"loss": 0.5272,
"step": 49
},
{
"epoch": 0.13,
"learning_rate": 1.999114981900887e-05,
"loss": 0.5033,
"step": 50
},
{
"epoch": 0.13,
"learning_rate": 1.9989930665413148e-05,
"loss": 0.5159,
"step": 51
},
{
"epoch": 0.14,
"learning_rate": 1.9988632911212344e-05,
"loss": 0.5247,
"step": 52
},
{
"epoch": 0.14,
"learning_rate": 1.9987256566617165e-05,
"loss": 0.589,
"step": 53
},
{
"epoch": 0.14,
"learning_rate": 1.9985801642456666e-05,
"loss": 0.5033,
"step": 54
},
{
"epoch": 0.14,
"learning_rate": 1.998426815017817e-05,
"loss": 0.5337,
"step": 55
},
{
"epoch": 0.15,
"learning_rate": 1.998265610184716e-05,
"loss": 0.5059,
"step": 56
},
{
"epoch": 0.15,
"learning_rate": 1.9980965510147214e-05,
"loss": 0.5465,
"step": 57
},
{
"epoch": 0.15,
"learning_rate": 1.9979196388379876e-05,
"loss": 0.5584,
"step": 58
},
{
"epoch": 0.15,
"learning_rate": 1.997734875046456e-05,
"loss": 0.5605,
"step": 59
},
{
"epoch": 0.16,
"learning_rate": 1.9975422610938463e-05,
"loss": 0.5733,
"step": 60
},
{
"epoch": 0.16,
"learning_rate": 1.9973417984956404e-05,
"loss": 0.5454,
"step": 61
},
{
"epoch": 0.16,
"learning_rate": 1.9971334888290756e-05,
"loss": 0.5226,
"step": 62
},
{
"epoch": 0.16,
"learning_rate": 1.9969173337331283e-05,
"loss": 0.5591,
"step": 63
},
{
"epoch": 0.17,
"learning_rate": 1.9966933349085033e-05,
"loss": 0.5396,
"step": 64
},
{
"epoch": 0.17,
"learning_rate": 1.9964614941176194e-05,
"loss": 0.5218,
"step": 65
},
{
"epoch": 0.17,
"learning_rate": 1.996221813184596e-05,
"loss": 0.5651,
"step": 66
},
{
"epoch": 0.17,
"learning_rate": 1.9959742939952393e-05,
"loss": 0.519,
"step": 67
},
{
"epoch": 0.18,
"learning_rate": 1.9957189384970253e-05,
"loss": 0.5197,
"step": 68
},
{
"epoch": 0.18,
"learning_rate": 1.995455748699087e-05,
"loss": 0.5281,
"step": 69
},
{
"epoch": 0.18,
"learning_rate": 1.995184726672197e-05,
"loss": 0.5506,
"step": 70
},
{
"epoch": 0.18,
"learning_rate": 1.9949058745487524e-05,
"loss": 0.5501,
"step": 71
},
{
"epoch": 0.19,
"learning_rate": 1.994619194522757e-05,
"loss": 0.5291,
"step": 72
},
{
"epoch": 0.19,
"learning_rate": 1.994324688849804e-05,
"loss": 0.5371,
"step": 73
},
{
"epoch": 0.19,
"learning_rate": 1.9940223598470596e-05,
"loss": 0.5193,
"step": 74
},
{
"epoch": 0.19,
"learning_rate": 1.9937122098932428e-05,
"loss": 0.5086,
"step": 75
},
{
"epoch": 0.2,
"learning_rate": 1.9933942414286082e-05,
"loss": 0.5464,
"step": 76
},
{
"epoch": 0.2,
"learning_rate": 1.9930684569549265e-05,
"loss": 0.5489,
"step": 77
},
{
"epoch": 0.2,
"learning_rate": 1.9927348590354642e-05,
"loss": 0.5633,
"step": 78
},
{
"epoch": 0.21,
"learning_rate": 1.9923934502949645e-05,
"loss": 0.5568,
"step": 79
},
{
"epoch": 0.21,
"learning_rate": 1.9920442334196248e-05,
"loss": 0.5615,
"step": 80
},
{
"epoch": 0.21,
"learning_rate": 1.9916872111570782e-05,
"loss": 0.5245,
"step": 81
},
{
"epoch": 0.21,
"learning_rate": 1.9913223863163698e-05,
"loss": 0.5616,
"step": 82
},
{
"epoch": 0.22,
"learning_rate": 1.990949761767935e-05,
"loss": 0.511,
"step": 83
},
{
"epoch": 0.22,
"learning_rate": 1.990569340443577e-05,
"loss": 0.555,
"step": 84
},
{
"epoch": 0.22,
"learning_rate": 1.9901811253364458e-05,
"loss": 0.549,
"step": 85
},
{
"epoch": 0.22,
"learning_rate": 1.98978511950101e-05,
"loss": 0.5182,
"step": 86
},
{
"epoch": 0.23,
"learning_rate": 1.9893813260530368e-05,
"loss": 0.5959,
"step": 87
},
{
"epoch": 0.23,
"learning_rate": 1.988969748169567e-05,
"loss": 0.5429,
"step": 88
},
{
"epoch": 0.23,
"learning_rate": 1.9885503890888874e-05,
"loss": 0.5149,
"step": 89
},
{
"epoch": 0.23,
"learning_rate": 1.988123252110509e-05,
"loss": 0.6095,
"step": 90
},
{
"epoch": 0.24,
"learning_rate": 1.9876883405951378e-05,
"loss": 0.5392,
"step": 91
},
{
"epoch": 0.24,
"learning_rate": 1.9872456579646506e-05,
"loss": 0.5788,
"step": 92
},
{
"epoch": 0.24,
"learning_rate": 1.9867952077020667e-05,
"loss": 0.5683,
"step": 93
},
{
"epoch": 0.24,
"learning_rate": 1.986336993351521e-05,
"loss": 0.4926,
"step": 94
},
{
"epoch": 0.25,
"learning_rate": 1.985871018518236e-05,
"loss": 0.5168,
"step": 95
},
{
"epoch": 0.25,
"learning_rate": 1.9853972868684942e-05,
"loss": 0.5942,
"step": 96
},
{
"epoch": 0.25,
"learning_rate": 1.9849158021296083e-05,
"loss": 0.5226,
"step": 97
},
{
"epoch": 0.25,
"learning_rate": 1.9844265680898917e-05,
"loss": 0.5336,
"step": 98
},
{
"epoch": 0.26,
"learning_rate": 1.98392958859863e-05,
"loss": 0.5428,
"step": 99
},
{
"epoch": 0.26,
"learning_rate": 1.9834248675660484e-05,
"loss": 0.5222,
"step": 100
},
{
"epoch": 0.26,
"learning_rate": 1.982912408963285e-05,
"loss": 0.5296,
"step": 101
},
{
"epoch": 0.26,
"learning_rate": 1.9823922168223537e-05,
"loss": 0.5106,
"step": 102
},
{
"epoch": 0.27,
"learning_rate": 1.9818642952361188e-05,
"loss": 0.519,
"step": 103
},
{
"epoch": 0.27,
"learning_rate": 1.9813286483582576e-05,
"loss": 0.5174,
"step": 104
},
{
"epoch": 0.27,
"learning_rate": 1.9807852804032306e-05,
"loss": 0.5442,
"step": 105
},
{
"epoch": 0.28,
"learning_rate": 1.980234195646248e-05,
"loss": 0.5328,
"step": 106
},
{
"epoch": 0.28,
"learning_rate": 1.9796753984232357e-05,
"loss": 0.5327,
"step": 107
},
{
"epoch": 0.28,
"learning_rate": 1.9791088931308004e-05,
"loss": 0.5224,
"step": 108
},
{
"epoch": 0.28,
"learning_rate": 1.9785346842261957e-05,
"loss": 0.5269,
"step": 109
},
{
"epoch": 0.29,
"learning_rate": 1.9779527762272877e-05,
"loss": 0.5778,
"step": 110
},
{
"epoch": 0.29,
"learning_rate": 1.9773631737125192e-05,
"loss": 0.5772,
"step": 111
},
{
"epoch": 0.29,
"learning_rate": 1.9767658813208725e-05,
"loss": 0.5056,
"step": 112
},
{
"epoch": 0.29,
"learning_rate": 1.976160903751834e-05,
"loss": 0.5359,
"step": 113
},
{
"epoch": 0.3,
"learning_rate": 1.975548245765357e-05,
"loss": 0.5479,
"step": 114
},
{
"epoch": 0.3,
"learning_rate": 1.9749279121818235e-05,
"loss": 0.5421,
"step": 115
},
{
"epoch": 0.3,
"learning_rate": 1.974299907882009e-05,
"loss": 0.5495,
"step": 116
},
{
"epoch": 0.3,
"learning_rate": 1.9736642378070393e-05,
"loss": 0.5441,
"step": 117
},
{
"epoch": 0.31,
"learning_rate": 1.9730209069583564e-05,
"loss": 0.5263,
"step": 118
},
{
"epoch": 0.31,
"learning_rate": 1.9723699203976768e-05,
"loss": 0.4971,
"step": 119
},
{
"epoch": 0.31,
"learning_rate": 1.971711283246951e-05,
"loss": 0.5732,
"step": 120
},
{
"epoch": 0.31,
"learning_rate": 1.9710450006883258e-05,
"loss": 0.5422,
"step": 121
},
{
"epoch": 0.32,
"learning_rate": 1.9703710779641e-05,
"loss": 0.5178,
"step": 122
},
{
"epoch": 0.32,
"learning_rate": 1.969689520376687e-05,
"loss": 0.5178,
"step": 123
},
{
"epoch": 0.32,
"learning_rate": 1.96900033328857e-05,
"loss": 0.5468,
"step": 124
},
{
"epoch": 0.32,
"learning_rate": 1.9683035221222617e-05,
"loss": 0.5372,
"step": 125
},
{
"epoch": 0.33,
"learning_rate": 1.96759909236026e-05,
"loss": 0.5347,
"step": 126
},
{
"epoch": 0.33,
"learning_rate": 1.9668870495450064e-05,
"loss": 0.5496,
"step": 127
},
{
"epoch": 0.33,
"learning_rate": 1.9661673992788423e-05,
"loss": 0.5518,
"step": 128
},
{
"epoch": 0.34,
"learning_rate": 1.965440147223963e-05,
"loss": 0.5198,
"step": 129
},
{
"epoch": 0.34,
"learning_rate": 1.964705299102376e-05,
"loss": 0.4986,
"step": 130
},
{
"epoch": 0.34,
"learning_rate": 1.9639628606958535e-05,
"loss": 0.4872,
"step": 131
},
{
"epoch": 0.34,
"learning_rate": 1.9632128378458882e-05,
"loss": 0.6289,
"step": 132
},
{
"epoch": 0.35,
"learning_rate": 1.9624552364536472e-05,
"loss": 0.5451,
"step": 133
},
{
"epoch": 0.35,
"learning_rate": 1.961690062479926e-05,
"loss": 0.5655,
"step": 134
},
{
"epoch": 0.35,
"learning_rate": 1.9609173219450998e-05,
"loss": 0.547,
"step": 135
},
{
"epoch": 0.35,
"learning_rate": 1.960137020929078e-05,
"loss": 0.5638,
"step": 136
},
{
"epoch": 0.36,
"learning_rate": 1.959349165571256e-05,
"loss": 0.5802,
"step": 137
},
{
"epoch": 0.36,
"learning_rate": 1.9585537620704665e-05,
"loss": 0.533,
"step": 138
},
{
"epoch": 0.36,
"learning_rate": 1.9577508166849308e-05,
"loss": 0.5431,
"step": 139
},
{
"epoch": 0.36,
"learning_rate": 1.956940335732209e-05,
"loss": 0.5715,
"step": 140
},
{
"epoch": 0.37,
"learning_rate": 1.956122325589152e-05,
"loss": 0.5393,
"step": 141
},
{
"epoch": 0.37,
"learning_rate": 1.95529679269185e-05,
"loss": 0.5588,
"step": 142
},
{
"epoch": 0.37,
"learning_rate": 1.954463743535581e-05,
"loss": 0.4889,
"step": 143
},
{
"epoch": 0.37,
"learning_rate": 1.9536231846747622e-05,
"loss": 0.5242,
"step": 144
},
{
"epoch": 0.38,
"learning_rate": 1.9527751227228964e-05,
"loss": 0.555,
"step": 145
},
{
"epoch": 0.38,
"learning_rate": 1.9519195643525205e-05,
"loss": 0.512,
"step": 146
},
{
"epoch": 0.38,
"learning_rate": 1.9510565162951538e-05,
"loss": 0.5627,
"step": 147
},
{
"epoch": 0.38,
"learning_rate": 1.9501859853412432e-05,
"loss": 0.5689,
"step": 148
},
{
"epoch": 0.39,
"learning_rate": 1.9493079783401116e-05,
"loss": 0.5427,
"step": 149
},
{
"epoch": 0.39,
"learning_rate": 1.9484225021999032e-05,
"loss": 0.577,
"step": 150
},
{
"epoch": 0.39,
"learning_rate": 1.947529563887529e-05,
"loss": 0.5636,
"step": 151
},
{
"epoch": 0.39,
"learning_rate": 1.946629170428613e-05,
"loss": 0.4971,
"step": 152
},
{
"epoch": 0.4,
"learning_rate": 1.9457213289074353e-05,
"loss": 0.5761,
"step": 153
},
{
"epoch": 0.4,
"learning_rate": 1.944806046466878e-05,
"loss": 0.5259,
"step": 154
},
{
"epoch": 0.4,
"learning_rate": 1.9438833303083677e-05,
"loss": 0.5168,
"step": 155
},
{
"epoch": 0.41,
"learning_rate": 1.9429531876918193e-05,
"loss": 0.5655,
"step": 156
},
{
"epoch": 0.41,
"learning_rate": 1.942015625935579e-05,
"loss": 0.5254,
"step": 157
},
{
"epoch": 0.41,
"learning_rate": 1.9410706524163673e-05,
"loss": 0.534,
"step": 158
},
{
"epoch": 0.41,
"learning_rate": 1.940118274569219e-05,
"loss": 0.5526,
"step": 159
},
{
"epoch": 0.42,
"learning_rate": 1.939158499887428e-05,
"loss": 0.4877,
"step": 160
},
{
"epoch": 0.42,
"learning_rate": 1.9381913359224844e-05,
"loss": 0.5212,
"step": 161
},
{
"epoch": 0.42,
"learning_rate": 1.9372167902840178e-05,
"loss": 0.5529,
"step": 162
},
{
"epoch": 0.42,
"learning_rate": 1.9362348706397374e-05,
"loss": 0.498,
"step": 163
},
{
"epoch": 0.43,
"learning_rate": 1.93524558471537e-05,
"loss": 0.5078,
"step": 164
},
{
"epoch": 0.43,
"learning_rate": 1.9342489402945997e-05,
"loss": 0.5592,
"step": 165
},
{
"epoch": 0.43,
"learning_rate": 1.9332449452190096e-05,
"loss": 0.5348,
"step": 166
},
{
"epoch": 0.43,
"learning_rate": 1.9322336073880143e-05,
"loss": 0.5449,
"step": 167
},
{
"epoch": 0.44,
"learning_rate": 1.9312149347588035e-05,
"loss": 0.5534,
"step": 168
},
{
"epoch": 0.44,
"learning_rate": 1.9301889353462765e-05,
"loss": 0.5158,
"step": 169
},
{
"epoch": 0.44,
"learning_rate": 1.9291556172229784e-05,
"loss": 0.5365,
"step": 170
},
{
"epoch": 0.44,
"learning_rate": 1.928114988519039e-05,
"loss": 0.544,
"step": 171
},
{
"epoch": 0.45,
"learning_rate": 1.9270670574221077e-05,
"loss": 0.5488,
"step": 172
},
{
"epoch": 0.45,
"learning_rate": 1.926011832177288e-05,
"loss": 0.5393,
"step": 173
},
{
"epoch": 0.45,
"learning_rate": 1.9249493210870746e-05,
"loss": 0.5377,
"step": 174
},
{
"epoch": 0.45,
"learning_rate": 1.9238795325112867e-05,
"loss": 0.548,
"step": 175
},
{
"epoch": 0.46,
"learning_rate": 1.922802474867003e-05,
"loss": 0.5322,
"step": 176
},
{
"epoch": 0.46,
"learning_rate": 1.9217181566284942e-05,
"loss": 0.5313,
"step": 177
},
{
"epoch": 0.46,
"learning_rate": 1.920626586327158e-05,
"loss": 0.5497,
"step": 178
},
{
"epoch": 0.46,
"learning_rate": 1.919527772551451e-05,
"loss": 0.5687,
"step": 179
},
{
"epoch": 0.47,
"learning_rate": 1.9184217239468213e-05,
"loss": 0.5408,
"step": 180
},
{
"epoch": 0.47,
"learning_rate": 1.9173084492156406e-05,
"loss": 0.5232,
"step": 181
},
{
"epoch": 0.47,
"learning_rate": 1.916187957117136e-05,
"loss": 0.4866,
"step": 182
},
{
"epoch": 0.48,
"learning_rate": 1.91506025646732e-05,
"loss": 0.5197,
"step": 183
},
{
"epoch": 0.48,
"learning_rate": 1.9139253561389222e-05,
"loss": 0.552,
"step": 184
},
{
"epoch": 0.48,
"learning_rate": 1.912783265061319e-05,
"loss": 0.5456,
"step": 185
},
{
"epoch": 0.48,
"learning_rate": 1.911633992220464e-05,
"loss": 0.5094,
"step": 186
},
{
"epoch": 0.49,
"learning_rate": 1.9104775466588162e-05,
"loss": 0.5524,
"step": 187
},
{
"epoch": 0.49,
"learning_rate": 1.9093139374752697e-05,
"loss": 0.6092,
"step": 188
},
{
"epoch": 0.49,
"learning_rate": 1.9081431738250815e-05,
"loss": 0.5288,
"step": 189
},
{
"epoch": 0.49,
"learning_rate": 1.9069652649198004e-05,
"loss": 0.5468,
"step": 190
},
{
"epoch": 0.5,
"learning_rate": 1.9057802200271943e-05,
"loss": 0.5319,
"step": 191
},
{
"epoch": 0.5,
"learning_rate": 1.9045880484711753e-05,
"loss": 0.563,
"step": 192
},
{
"epoch": 0.5,
"learning_rate": 1.90338875963173e-05,
"loss": 0.5652,
"step": 193
},
{
"epoch": 0.5,
"learning_rate": 1.9021823629448416e-05,
"loss": 0.4983,
"step": 194
},
{
"epoch": 0.51,
"learning_rate": 1.900968867902419e-05,
"loss": 0.5022,
"step": 195
},
{
"epoch": 0.51,
"learning_rate": 1.8997482840522218e-05,
"loss": 0.553,
"step": 196
},
{
"epoch": 0.51,
"learning_rate": 1.8985206209977813e-05,
"loss": 0.5612,
"step": 197
},
{
"epoch": 0.51,
"learning_rate": 1.897285888398331e-05,
"loss": 0.5548,
"step": 198
},
{
"epoch": 0.52,
"learning_rate": 1.8960440959687254e-05,
"loss": 0.5579,
"step": 199
},
{
"epoch": 0.52,
"learning_rate": 1.8947952534793663e-05,
"loss": 0.5325,
"step": 200
},
{
"epoch": 0.52,
"learning_rate": 1.893539370756125e-05,
"loss": 0.5458,
"step": 201
},
{
"epoch": 0.52,
"learning_rate": 1.892276457680266e-05,
"loss": 0.5364,
"step": 202
},
{
"epoch": 0.53,
"learning_rate": 1.891006524188368e-05,
"loss": 0.5008,
"step": 203
},
{
"epoch": 0.53,
"learning_rate": 1.8897295802722457e-05,
"loss": 0.523,
"step": 204
},
{
"epoch": 0.53,
"learning_rate": 1.8884456359788725e-05,
"loss": 0.5595,
"step": 205
},
{
"epoch": 0.54,
"learning_rate": 1.8871547014103e-05,
"loss": 0.5263,
"step": 206
},
{
"epoch": 0.54,
"learning_rate": 1.88585678672358e-05,
"loss": 0.5548,
"step": 207
},
{
"epoch": 0.54,
"learning_rate": 1.884551902130683e-05,
"loss": 0.4893,
"step": 208
},
{
"epoch": 0.54,
"learning_rate": 1.8832400578984183e-05,
"loss": 0.5374,
"step": 209
},
{
"epoch": 0.55,
"learning_rate": 1.881921264348355e-05,
"loss": 0.5213,
"step": 210
},
{
"epoch": 0.55,
"learning_rate": 1.880595531856738e-05,
"loss": 0.5873,
"step": 211
},
{
"epoch": 0.55,
"learning_rate": 1.879262870854408e-05,
"loss": 0.5154,
"step": 212
},
{
"epoch": 0.55,
"learning_rate": 1.8779232918267194e-05,
"loss": 0.5023,
"step": 213
},
{
"epoch": 0.56,
"learning_rate": 1.876576805313457e-05,
"loss": 0.5607,
"step": 214
},
{
"epoch": 0.56,
"learning_rate": 1.8752234219087538e-05,
"loss": 0.5406,
"step": 215
},
{
"epoch": 0.56,
"learning_rate": 1.8738631522610077e-05,
"loss": 0.543,
"step": 216
},
{
"epoch": 0.56,
"learning_rate": 1.8724960070727974e-05,
"loss": 0.5532,
"step": 217
},
{
"epoch": 0.57,
"learning_rate": 1.8711219971007976e-05,
"loss": 0.5271,
"step": 218
},
{
"epoch": 0.57,
"learning_rate": 1.8697411331556958e-05,
"loss": 0.4911,
"step": 219
},
{
"epoch": 0.57,
"learning_rate": 1.8683534261021058e-05,
"loss": 0.4968,
"step": 220
},
{
"epoch": 0.57,
"learning_rate": 1.8669588868584832e-05,
"loss": 0.5193,
"step": 221
},
{
"epoch": 0.58,
"learning_rate": 1.8655575263970394e-05,
"loss": 0.4912,
"step": 222
},
{
"epoch": 0.58,
"learning_rate": 1.864149355743655e-05,
"loss": 0.5648,
"step": 223
},
{
"epoch": 0.58,
"learning_rate": 1.862734385977792e-05,
"loss": 0.5279,
"step": 224
},
{
"epoch": 0.58,
"learning_rate": 1.8613126282324092e-05,
"loss": 0.5535,
"step": 225
},
{
"epoch": 0.59,
"learning_rate": 1.859884093693872e-05,
"loss": 0.566,
"step": 226
},
{
"epoch": 0.59,
"learning_rate": 1.8584487936018663e-05,
"loss": 0.5366,
"step": 227
},
{
"epoch": 0.59,
"learning_rate": 1.857006739249309e-05,
"loss": 0.514,
"step": 228
},
{
"epoch": 0.59,
"learning_rate": 1.855557941982258e-05,
"loss": 0.5122,
"step": 229
},
{
"epoch": 0.6,
"learning_rate": 1.8541024131998277e-05,
"loss": 0.5156,
"step": 230
},
{
"epoch": 0.6,
"learning_rate": 1.8526401643540924e-05,
"loss": 0.551,
"step": 231
},
{
"epoch": 0.6,
"learning_rate": 1.8511712069500016e-05,
"loss": 0.533,
"step": 232
},
{
"epoch": 0.61,
"learning_rate": 1.8496955525452877e-05,
"loss": 0.5988,
"step": 233
},
{
"epoch": 0.61,
"learning_rate": 1.8482132127503735e-05,
"loss": 0.5142,
"step": 234
},
{
"epoch": 0.61,
"learning_rate": 1.8467241992282842e-05,
"loss": 0.5397,
"step": 235
},
{
"epoch": 0.61,
"learning_rate": 1.845228523694553e-05,
"loss": 0.5189,
"step": 236
},
{
"epoch": 0.62,
"learning_rate": 1.8437261979171294e-05,
"loss": 0.5457,
"step": 237
},
{
"epoch": 0.62,
"learning_rate": 1.8422172337162865e-05,
"loss": 0.5244,
"step": 238
},
{
"epoch": 0.62,
"learning_rate": 1.8407016429645305e-05,
"loss": 0.5009,
"step": 239
},
{
"epoch": 0.62,
"learning_rate": 1.8391794375865025e-05,
"loss": 0.5228,
"step": 240
},
{
"epoch": 0.63,
"learning_rate": 1.8376506295588887e-05,
"loss": 0.5927,
"step": 241
},
{
"epoch": 0.63,
"learning_rate": 1.8361152309103256e-05,
"loss": 0.5132,
"step": 242
},
{
"epoch": 0.63,
"learning_rate": 1.834573253721303e-05,
"loss": 0.5235,
"step": 243
},
{
"epoch": 0.63,
"learning_rate": 1.8330247101240713e-05,
"loss": 0.4966,
"step": 244
},
{
"epoch": 0.64,
"learning_rate": 1.8314696123025456e-05,
"loss": 0.5286,
"step": 245
},
{
"epoch": 0.64,
"learning_rate": 1.8299079724922087e-05,
"loss": 0.5829,
"step": 246
},
{
"epoch": 0.64,
"learning_rate": 1.8283398029800167e-05,
"loss": 0.5302,
"step": 247
},
{
"epoch": 0.64,
"learning_rate": 1.8267651161043004e-05,
"loss": 0.4956,
"step": 248
},
{
"epoch": 0.65,
"learning_rate": 1.8251839242546696e-05,
"loss": 0.5648,
"step": 249
},
{
"epoch": 0.65,
"learning_rate": 1.823596239871915e-05,
"loss": 0.5528,
"step": 250
},
{
"epoch": 0.65,
"learning_rate": 1.8220020754479104e-05,
"loss": 0.5284,
"step": 251
},
{
"epoch": 0.65,
"learning_rate": 1.8204014435255136e-05,
"loss": 0.5178,
"step": 252
},
{
"epoch": 0.66,
"learning_rate": 1.818794356698471e-05,
"loss": 0.5634,
"step": 253
},
{
"epoch": 0.66,
"learning_rate": 1.8171808276113133e-05,
"loss": 0.5228,
"step": 254
},
{
"epoch": 0.66,
"learning_rate": 1.8155608689592604e-05,
"loss": 0.5311,
"step": 255
},
{
"epoch": 0.66,
"learning_rate": 1.8139344934881195e-05,
"loss": 0.5004,
"step": 256
},
{
"epoch": 0.67,
"learning_rate": 1.8123017139941853e-05,
"loss": 0.5408,
"step": 257
},
{
"epoch": 0.67,
"learning_rate": 1.810662543324139e-05,
"loss": 0.52,
"step": 258
},
{
"epoch": 0.67,
"learning_rate": 1.8090169943749477e-05,
"loss": 0.5263,
"step": 259
},
{
"epoch": 0.68,
"learning_rate": 1.8073650800937627e-05,
"loss": 0.4928,
"step": 260
},
{
"epoch": 0.68,
"learning_rate": 1.8057068134778174e-05,
"loss": 0.5378,
"step": 261
},
{
"epoch": 0.68,
"learning_rate": 1.8040422075743253e-05,
"loss": 0.5151,
"step": 262
},
{
"epoch": 0.68,
"learning_rate": 1.8023712754803783e-05,
"loss": 0.5355,
"step": 263
},
{
"epoch": 0.69,
"learning_rate": 1.8006940303428406e-05,
"loss": 0.4691,
"step": 264
},
{
"epoch": 0.69,
"learning_rate": 1.7990104853582494e-05,
"loss": 0.5247,
"step": 265
},
{
"epoch": 0.69,
"learning_rate": 1.797320653772707e-05,
"loss": 0.4729,
"step": 266
},
{
"epoch": 0.69,
"learning_rate": 1.795624548881781e-05,
"loss": 0.4805,
"step": 267
},
{
"epoch": 0.7,
"learning_rate": 1.793922184030395e-05,
"loss": 0.5214,
"step": 268
},
{
"epoch": 0.7,
"learning_rate": 1.7922135726127276e-05,
"loss": 0.4843,
"step": 269
},
{
"epoch": 0.7,
"learning_rate": 1.7904987280721037e-05,
"loss": 0.5802,
"step": 270
},
{
"epoch": 0.7,
"learning_rate": 1.7887776639008912e-05,
"loss": 0.4953,
"step": 271
},
{
"epoch": 0.71,
"learning_rate": 1.787050393640394e-05,
"loss": 0.5112,
"step": 272
},
{
"epoch": 0.71,
"learning_rate": 1.785316930880745e-05,
"loss": 0.576,
"step": 273
},
{
"epoch": 0.71,
"learning_rate": 1.7835772892608002e-05,
"loss": 0.5704,
"step": 274
},
{
"epoch": 0.71,
"learning_rate": 1.78183148246803e-05,
"loss": 0.5564,
"step": 275
},
{
"epoch": 0.72,
"learning_rate": 1.7800795242384126e-05,
"loss": 0.5357,
"step": 276
},
{
"epoch": 0.72,
"learning_rate": 1.778321428356326e-05,
"loss": 0.5603,
"step": 277
},
{
"epoch": 0.72,
"learning_rate": 1.7765572086544387e-05,
"loss": 0.4863,
"step": 278
},
{
"epoch": 0.72,
"learning_rate": 1.7747868790136012e-05,
"loss": 0.5042,
"step": 279
},
{
"epoch": 0.73,
"learning_rate": 1.773010453362737e-05,
"loss": 0.5151,
"step": 280
},
{
"epoch": 0.73,
"learning_rate": 1.7712279456787334e-05,
"loss": 0.4892,
"step": 281
},
{
"epoch": 0.73,
"learning_rate": 1.7694393699863302e-05,
"loss": 0.5511,
"step": 282
},
{
"epoch": 0.74,
"learning_rate": 1.7676447403580114e-05,
"loss": 0.5347,
"step": 283
},
{
"epoch": 0.74,
"learning_rate": 1.7658440709138914e-05,
"loss": 0.5121,
"step": 284
},
{
"epoch": 0.74,
"learning_rate": 1.7640373758216075e-05,
"loss": 0.5131,
"step": 285
},
{
"epoch": 0.74,
"learning_rate": 1.762224669296206e-05,
"loss": 0.5432,
"step": 286
},
{
"epoch": 0.75,
"learning_rate": 1.7604059656000313e-05,
"loss": 0.5289,
"step": 287
},
{
"epoch": 0.75,
"learning_rate": 1.7585812790426128e-05,
"loss": 0.4746,
"step": 288
},
{
"epoch": 0.75,
"learning_rate": 1.756750623980553e-05,
"loss": 0.5082,
"step": 289
},
{
"epoch": 0.75,
"learning_rate": 1.754914014817416e-05,
"loss": 0.5313,
"step": 290
},
{
"epoch": 0.76,
"learning_rate": 1.7530714660036112e-05,
"loss": 0.531,
"step": 291
},
{
"epoch": 0.76,
"learning_rate": 1.751222992036281e-05,
"loss": 0.4826,
"step": 292
},
{
"epoch": 0.76,
"learning_rate": 1.7493686074591873e-05,
"loss": 0.5284,
"step": 293
},
{
"epoch": 0.76,
"learning_rate": 1.747508326862597e-05,
"loss": 0.5312,
"step": 294
},
{
"epoch": 0.77,
"learning_rate": 1.7456421648831658e-05,
"loss": 0.5418,
"step": 295
},
{
"epoch": 0.77,
"learning_rate": 1.743770136203825e-05,
"loss": 0.522,
"step": 296
},
{
"epoch": 0.77,
"learning_rate": 1.741892255553664e-05,
"loss": 0.5009,
"step": 297
},
{
"epoch": 0.77,
"learning_rate": 1.740008537707816e-05,
"loss": 0.4959,
"step": 298
},
{
"epoch": 0.78,
"learning_rate": 1.738118997487341e-05,
"loss": 0.4811,
"step": 299
},
{
"epoch": 0.78,
"learning_rate": 1.7362236497591097e-05,
"loss": 0.5638,
"step": 300
},
{
"epoch": 0.78,
"learning_rate": 1.7343225094356857e-05,
"loss": 0.5691,
"step": 301
},
{
"epoch": 0.78,
"learning_rate": 1.732415591475209e-05,
"loss": 0.4918,
"step": 302
},
{
"epoch": 0.79,
"learning_rate": 1.7305029108812777e-05,
"loss": 0.5563,
"step": 303
},
{
"epoch": 0.79,
"learning_rate": 1.7285844827028303e-05,
"loss": 0.49,
"step": 304
},
{
"epoch": 0.79,
"learning_rate": 1.7266603220340273e-05,
"loss": 0.5295,
"step": 305
},
{
"epoch": 0.79,
"learning_rate": 1.724730444014132e-05,
"loss": 0.4937,
"step": 306
},
{
"epoch": 0.8,
"learning_rate": 1.7227948638273918e-05,
"loss": 0.5554,
"step": 307
},
{
"epoch": 0.8,
"learning_rate": 1.720853596702919e-05,
"loss": 0.5592,
"step": 308
},
{
"epoch": 0.8,
"learning_rate": 1.7189066579145704e-05,
"loss": 0.5494,
"step": 309
},
{
"epoch": 0.81,
"learning_rate": 1.7169540627808276e-05,
"loss": 0.5341,
"step": 310
},
{
"epoch": 0.81,
"learning_rate": 1.7149958266646756e-05,
"loss": 0.548,
"step": 311
},
{
"epoch": 0.81,
"learning_rate": 1.713031964973483e-05,
"loss": 0.5295,
"step": 312
},
{
"epoch": 0.81,
"learning_rate": 1.7110624931588805e-05,
"loss": 0.4884,
"step": 313
},
{
"epoch": 0.82,
"learning_rate": 1.709087426716639e-05,
"loss": 0.4945,
"step": 314
},
{
"epoch": 0.82,
"learning_rate": 1.7071067811865477e-05,
"loss": 0.5027,
"step": 315
},
{
"epoch": 0.82,
"learning_rate": 1.705120572152292e-05,
"loss": 0.5626,
"step": 316
},
{
"epoch": 0.82,
"learning_rate": 1.7031288152413304e-05,
"loss": 0.464,
"step": 317
},
{
"epoch": 0.83,
"learning_rate": 1.7011315261247735e-05,
"loss": 0.5139,
"step": 318
},
{
"epoch": 0.83,
"learning_rate": 1.6991287205172575e-05,
"loss": 0.5166,
"step": 319
},
{
"epoch": 0.83,
"learning_rate": 1.6971204141768235e-05,
"loss": 0.5225,
"step": 320
},
{
"epoch": 0.83,
"learning_rate": 1.695106622904791e-05,
"loss": 0.5166,
"step": 321
},
{
"epoch": 0.84,
"learning_rate": 1.6930873625456362e-05,
"loss": 0.5701,
"step": 322
},
{
"epoch": 0.84,
"learning_rate": 1.691062648986865e-05,
"loss": 0.4787,
"step": 323
},
{
"epoch": 0.84,
"learning_rate": 1.6890324981588893e-05,
"loss": 0.5298,
"step": 324
},
{
"epoch": 0.84,
"learning_rate": 1.686996926034902e-05,
"loss": 0.5479,
"step": 325
},
{
"epoch": 0.85,
"learning_rate": 1.6849559486307493e-05,
"loss": 0.5469,
"step": 326
},
{
"epoch": 0.85,
"learning_rate": 1.682909582004807e-05,
"loss": 0.5514,
"step": 327
},
{
"epoch": 0.85,
"learning_rate": 1.6808578422578534e-05,
"loss": 0.527,
"step": 328
},
{
"epoch": 0.85,
"learning_rate": 1.678800745532942e-05,
"loss": 0.5184,
"step": 329
},
{
"epoch": 0.86,
"learning_rate": 1.6767383080152744e-05,
"loss": 0.5286,
"step": 330
},
{
"epoch": 0.86,
"learning_rate": 1.6746705459320746e-05,
"loss": 0.4791,
"step": 331
},
{
"epoch": 0.86,
"learning_rate": 1.672597475552459e-05,
"loss": 0.4887,
"step": 332
},
{
"epoch": 0.86,
"learning_rate": 1.670519113187311e-05,
"loss": 0.5073,
"step": 333
},
{
"epoch": 0.87,
"learning_rate": 1.66843547518915e-05,
"loss": 0.5796,
"step": 334
},
{
"epoch": 0.87,
"learning_rate": 1.6663465779520042e-05,
"loss": 0.5469,
"step": 335
},
{
"epoch": 0.87,
"learning_rate": 1.664252437911282e-05,
"loss": 0.5516,
"step": 336
},
{
"epoch": 0.88,
"learning_rate": 1.6621530715436413e-05,
"loss": 0.5655,
"step": 337
},
{
"epoch": 0.88,
"learning_rate": 1.660048495366862e-05,
"loss": 0.4783,
"step": 338
},
{
"epoch": 0.88,
"learning_rate": 1.657938725939713e-05,
"loss": 0.5357,
"step": 339
},
{
"epoch": 0.88,
"learning_rate": 1.6558237798618243e-05,
"loss": 0.4464,
"step": 340
},
{
"epoch": 0.89,
"learning_rate": 1.6537036737735563e-05,
"loss": 0.5214,
"step": 341
},
{
"epoch": 0.89,
"learning_rate": 1.651578424355867e-05,
"loss": 0.5047,
"step": 342
},
{
"epoch": 0.89,
"learning_rate": 1.6494480483301836e-05,
"loss": 0.5226,
"step": 343
},
{
"epoch": 0.89,
"learning_rate": 1.6473125624582683e-05,
"loss": 0.5009,
"step": 344
},
{
"epoch": 0.9,
"learning_rate": 1.645171983542088e-05,
"loss": 0.4959,
"step": 345
},
{
"epoch": 0.9,
"learning_rate": 1.6430263284236803e-05,
"loss": 0.4996,
"step": 346
},
{
"epoch": 0.9,
"learning_rate": 1.6408756139850243e-05,
"loss": 0.5208,
"step": 347
},
{
"epoch": 0.9,
"learning_rate": 1.6387198571479044e-05,
"loss": 0.5566,
"step": 348
},
{
"epoch": 0.91,
"learning_rate": 1.6365590748737786e-05,
"loss": 0.4824,
"step": 349
},
{
"epoch": 0.91,
"learning_rate": 1.6343932841636455e-05,
"loss": 0.4818,
"step": 350
},
{
"epoch": 0.91,
"learning_rate": 1.63222250205791e-05,
"loss": 0.4929,
"step": 351
},
{
"epoch": 0.91,
"learning_rate": 1.630046745636248e-05,
"loss": 0.4794,
"step": 352
},
{
"epoch": 0.92,
"learning_rate": 1.627866032017475e-05,
"loss": 0.491,
"step": 353
},
{
"epoch": 0.92,
"learning_rate": 1.625680378359408e-05,
"loss": 0.4631,
"step": 354
},
{
"epoch": 0.92,
"learning_rate": 1.6234898018587336e-05,
"loss": 0.4988,
"step": 355
},
{
"epoch": 0.92,
"learning_rate": 1.6212943197508706e-05,
"loss": 0.5452,
"step": 356
},
{
"epoch": 0.93,
"learning_rate": 1.6190939493098344e-05,
"loss": 0.482,
"step": 357
},
{
"epoch": 0.93,
"learning_rate": 1.6168887078481023e-05,
"loss": 0.4669,
"step": 358
},
{
"epoch": 0.93,
"learning_rate": 1.6146786127164773e-05,
"loss": 0.5453,
"step": 359
},
{
"epoch": 0.94,
"learning_rate": 1.6124636813039502e-05,
"loss": 0.5317,
"step": 360
},
{
"epoch": 0.94,
"learning_rate": 1.6102439310375637e-05,
"loss": 0.5385,
"step": 361
},
{
"epoch": 0.94,
"learning_rate": 1.6080193793822757e-05,
"loss": 0.533,
"step": 362
},
{
"epoch": 0.94,
"learning_rate": 1.60579004384082e-05,
"loss": 0.5103,
"step": 363
},
{
"epoch": 0.95,
"learning_rate": 1.6035559419535714e-05,
"loss": 0.4996,
"step": 364
},
{
"epoch": 0.95,
"learning_rate": 1.601317091298406e-05,
"loss": 0.522,
"step": 365
},
{
"epoch": 0.95,
"learning_rate": 1.5990735094905622e-05,
"loss": 0.5029,
"step": 366
},
{
"epoch": 0.95,
"learning_rate": 1.5968252141825038e-05,
"loss": 0.5086,
"step": 367
},
{
"epoch": 0.96,
"learning_rate": 1.5945722230637804e-05,
"loss": 0.4879,
"step": 368
},
{
"epoch": 0.96,
"learning_rate": 1.5923145538608874e-05,
"loss": 0.512,
"step": 369
},
{
"epoch": 0.96,
"learning_rate": 1.5900522243371283e-05,
"loss": 0.4881,
"step": 370
},
{
"epoch": 0.96,
"learning_rate": 1.5877852522924733e-05,
"loss": 0.5143,
"step": 371
},
{
"epoch": 0.97,
"learning_rate": 1.5855136555634198e-05,
"loss": 0.4916,
"step": 372
},
{
"epoch": 0.97,
"learning_rate": 1.5832374520228527e-05,
"loss": 0.5533,
"step": 373
},
{
"epoch": 0.97,
"learning_rate": 1.580956659579903e-05,
"loss": 0.5009,
"step": 374
},
{
"epoch": 0.97,
"learning_rate": 1.578671296179806e-05,
"loss": 0.4879,
"step": 375
},
{
"epoch": 0.98,
"learning_rate": 1.576381379803763e-05,
"loss": 0.5327,
"step": 376
},
{
"epoch": 0.98,
"learning_rate": 1.574086928468797e-05,
"loss": 0.5433,
"step": 377
},
{
"epoch": 0.98,
"learning_rate": 1.5717879602276123e-05,
"loss": 0.5271,
"step": 378
},
{
"epoch": 0.98,
"learning_rate": 1.569484493168452e-05,
"loss": 0.5018,
"step": 379
},
{
"epoch": 0.99,
"learning_rate": 1.5671765454149558e-05,
"loss": 0.4925,
"step": 380
},
{
"epoch": 0.99,
"learning_rate": 1.564864135126018e-05,
"loss": 0.5153,
"step": 381
},
{
"epoch": 0.99,
"learning_rate": 1.5625472804956424e-05,
"loss": 0.4702,
"step": 382
},
{
"epoch": 0.99,
"learning_rate": 1.5602259997528028e-05,
"loss": 0.478,
"step": 383
},
{
"epoch": 1.0,
"learning_rate": 1.557900311161297e-05,
"loss": 0.5211,
"step": 384
},
{
"epoch": 1.0,
"learning_rate": 1.5555702330196024e-05,
"loss": 0.5089,
"step": 385
},
{
"epoch": 1.0,
"learning_rate": 1.553235783660735e-05,
"loss": 0.4347,
"step": 386
},
{
"epoch": 1.01,
"learning_rate": 1.5508969814521026e-05,
"loss": 0.4595,
"step": 387
},
{
"epoch": 1.01,
"learning_rate": 1.5485538447953615e-05,
"loss": 0.4657,
"step": 388
},
{
"epoch": 1.01,
"learning_rate": 1.5462063921262708e-05,
"loss": 0.4186,
"step": 389
},
{
"epoch": 1.01,
"learning_rate": 1.543854641914549e-05,
"loss": 0.4016,
"step": 390
},
{
"epoch": 1.02,
"learning_rate": 1.541498612663726e-05,
"loss": 0.407,
"step": 391
},
{
"epoch": 1.02,
"learning_rate": 1.5391383229110005e-05,
"loss": 0.388,
"step": 392
},
{
"epoch": 1.02,
"learning_rate": 1.536773791227092e-05,
"loss": 0.3883,
"step": 393
},
{
"epoch": 1.02,
"learning_rate": 1.5344050362160962e-05,
"loss": 0.4545,
"step": 394
},
{
"epoch": 1.03,
"learning_rate": 1.5320320765153367e-05,
"loss": 0.3737,
"step": 395
},
{
"epoch": 1.03,
"learning_rate": 1.5296549307952203e-05,
"loss": 0.3448,
"step": 396
},
{
"epoch": 1.03,
"learning_rate": 1.5272736177590902e-05,
"loss": 0.3078,
"step": 397
},
{
"epoch": 1.03,
"learning_rate": 1.5248881561430758e-05,
"loss": 0.3482,
"step": 398
},
{
"epoch": 1.04,
"learning_rate": 1.5224985647159489e-05,
"loss": 0.2986,
"step": 399
},
{
"epoch": 1.04,
"learning_rate": 1.5201048622789747e-05,
"loss": 0.3122,
"step": 400
},
{
"epoch": 1.04,
"learning_rate": 1.5177070676657632e-05,
"loss": 0.2978,
"step": 401
},
{
"epoch": 1.04,
"learning_rate": 1.5153051997421218e-05,
"loss": 0.2865,
"step": 402
},
{
"epoch": 1.05,
"learning_rate": 1.5128992774059063e-05,
"loss": 0.3256,
"step": 403
},
{
"epoch": 1.05,
"learning_rate": 1.5104893195868733e-05,
"loss": 0.2684,
"step": 404
},
{
"epoch": 1.05,
"learning_rate": 1.5080753452465296e-05,
"loss": 0.2595,
"step": 405
},
{
"epoch": 1.05,
"learning_rate": 1.5056573733779848e-05,
"loss": 0.2567,
"step": 406
},
{
"epoch": 1.06,
"learning_rate": 1.5032354230058004e-05,
"loss": 0.2735,
"step": 407
},
{
"epoch": 1.06,
"learning_rate": 1.5008095131858407e-05,
"loss": 0.2814,
"step": 408
},
{
"epoch": 1.06,
"learning_rate": 1.498379663005123e-05,
"loss": 0.2443,
"step": 409
},
{
"epoch": 1.06,
"learning_rate": 1.4959458915816681e-05,
"loss": 0.2346,
"step": 410
},
{
"epoch": 1.07,
"learning_rate": 1.493508218064347e-05,
"loss": 0.2469,
"step": 411
},
{
"epoch": 1.07,
"learning_rate": 1.4910666616327345e-05,
"loss": 0.2713,
"step": 412
},
{
"epoch": 1.07,
"learning_rate": 1.4886212414969551e-05,
"loss": 0.2233,
"step": 413
},
{
"epoch": 1.08,
"learning_rate": 1.4861719768975326e-05,
"loss": 0.2695,
"step": 414
},
{
"epoch": 1.08,
"learning_rate": 1.4837188871052399e-05,
"loss": 0.2308,
"step": 415
},
{
"epoch": 1.08,
"learning_rate": 1.4812619914209455e-05,
"loss": 0.2247,
"step": 416
},
{
"epoch": 1.08,
"learning_rate": 1.4788013091754629e-05,
"loss": 0.2221,
"step": 417
},
{
"epoch": 1.09,
"learning_rate": 1.4763368597293986e-05,
"loss": 0.1883,
"step": 418
},
{
"epoch": 1.09,
"learning_rate": 1.4738686624729987e-05,
"loss": 0.2606,
"step": 419
},
{
"epoch": 1.09,
"learning_rate": 1.4713967368259981e-05,
"loss": 0.2472,
"step": 420
},
{
"epoch": 1.09,
"learning_rate": 1.4689211022374645e-05,
"loss": 0.239,
"step": 421
},
{
"epoch": 1.1,
"learning_rate": 1.4664417781856504e-05,
"loss": 0.2216,
"step": 422
},
{
"epoch": 1.1,
"learning_rate": 1.4639587841778342e-05,
"loss": 0.246,
"step": 423
},
{
"epoch": 1.1,
"learning_rate": 1.4614721397501715e-05,
"loss": 0.2104,
"step": 424
},
{
"epoch": 1.1,
"learning_rate": 1.4589818644675378e-05,
"loss": 0.2078,
"step": 425
},
{
"epoch": 1.11,
"learning_rate": 1.4564879779233773e-05,
"loss": 0.2181,
"step": 426
},
{
"epoch": 1.11,
"learning_rate": 1.4539904997395468e-05,
"loss": 0.2274,
"step": 427
},
{
"epoch": 1.11,
"learning_rate": 1.4514894495661627e-05,
"loss": 0.2392,
"step": 428
},
{
"epoch": 1.11,
"learning_rate": 1.4489848470814447e-05,
"loss": 0.202,
"step": 429
},
{
"epoch": 1.12,
"learning_rate": 1.446476711991563e-05,
"loss": 0.2073,
"step": 430
},
{
"epoch": 1.12,
"learning_rate": 1.4439650640304822e-05,
"loss": 0.2454,
"step": 431
},
{
"epoch": 1.12,
"learning_rate": 1.4414499229598056e-05,
"loss": 0.2013,
"step": 432
},
{
"epoch": 1.12,
"learning_rate": 1.4389313085686205e-05,
"loss": 0.232,
"step": 433
},
{
"epoch": 1.13,
"learning_rate": 1.436409240673342e-05,
"loss": 0.2291,
"step": 434
},
{
"epoch": 1.13,
"learning_rate": 1.4338837391175582e-05,
"loss": 0.2238,
"step": 435
},
{
"epoch": 1.13,
"learning_rate": 1.431354823771872e-05,
"loss": 0.2353,
"step": 436
},
{
"epoch": 1.14,
"learning_rate": 1.4288225145337467e-05,
"loss": 0.2153,
"step": 437
},
{
"epoch": 1.14,
"learning_rate": 1.4262868313273482e-05,
"loss": 0.2536,
"step": 438
},
{
"epoch": 1.14,
"learning_rate": 1.4237477941033888e-05,
"loss": 0.2118,
"step": 439
},
{
"epoch": 1.14,
"learning_rate": 1.4212054228389712e-05,
"loss": 0.2367,
"step": 440
},
{
"epoch": 1.15,
"learning_rate": 1.4186597375374283e-05,
"loss": 0.2045,
"step": 441
},
{
"epoch": 1.15,
"learning_rate": 1.4161107582281696e-05,
"loss": 0.2262,
"step": 442
},
{
"epoch": 1.15,
"learning_rate": 1.4135585049665207e-05,
"loss": 0.2233,
"step": 443
},
{
"epoch": 1.15,
"learning_rate": 1.4110029978335675e-05,
"loss": 0.2234,
"step": 444
},
{
"epoch": 1.16,
"learning_rate": 1.4084442569359964e-05,
"loss": 0.241,
"step": 445
},
{
"epoch": 1.16,
"learning_rate": 1.4058823024059374e-05,
"loss": 0.2302,
"step": 446
},
{
"epoch": 1.16,
"learning_rate": 1.4033171544008053e-05,
"loss": 0.2039,
"step": 447
},
{
"epoch": 1.16,
"learning_rate": 1.4007488331031409e-05,
"loss": 0.2128,
"step": 448
},
{
"epoch": 1.17,
"learning_rate": 1.3981773587204535e-05,
"loss": 0.2296,
"step": 449
},
{
"epoch": 1.17,
"learning_rate": 1.395602751485059e-05,
"loss": 0.2022,
"step": 450
},
{
"epoch": 1.17,
"learning_rate": 1.3930250316539237e-05,
"loss": 0.2321,
"step": 451
},
{
"epoch": 1.17,
"learning_rate": 1.3904442195085037e-05,
"loss": 0.2072,
"step": 452
},
{
"epoch": 1.18,
"learning_rate": 1.3878603353545854e-05,
"loss": 0.2161,
"step": 453
},
{
"epoch": 1.18,
"learning_rate": 1.3852733995221249e-05,
"loss": 0.1979,
"step": 454
},
{
"epoch": 1.18,
"learning_rate": 1.3826834323650899e-05,
"loss": 0.2053,
"step": 455
},
{
"epoch": 1.18,
"learning_rate": 1.380090454261298e-05,
"loss": 0.2045,
"step": 456
},
{
"epoch": 1.19,
"learning_rate": 1.377494485612257e-05,
"loss": 0.205,
"step": 457
},
{
"epoch": 1.19,
"learning_rate": 1.374895546843004e-05,
"loss": 0.2163,
"step": 458
},
{
"epoch": 1.19,
"learning_rate": 1.3722936584019453e-05,
"loss": 0.1894,
"step": 459
},
{
"epoch": 1.19,
"learning_rate": 1.3696888407606952e-05,
"loss": 0.2008,
"step": 460
},
{
"epoch": 1.2,
"learning_rate": 1.3670811144139144e-05,
"loss": 0.2125,
"step": 461
},
{
"epoch": 1.2,
"learning_rate": 1.3644704998791501e-05,
"loss": 0.2204,
"step": 462
},
{
"epoch": 1.2,
"learning_rate": 1.3618570176966723e-05,
"loss": 0.2174,
"step": 463
},
{
"epoch": 1.21,
"learning_rate": 1.3592406884293153e-05,
"loss": 0.217,
"step": 464
},
{
"epoch": 1.21,
"learning_rate": 1.3566215326623131e-05,
"loss": 0.2109,
"step": 465
},
{
"epoch": 1.21,
"learning_rate": 1.3539995710031391e-05,
"loss": 0.1982,
"step": 466
},
{
"epoch": 1.21,
"learning_rate": 1.3513748240813429e-05,
"loss": 0.2108,
"step": 467
},
{
"epoch": 1.22,
"learning_rate": 1.3487473125483888e-05,
"loss": 0.1822,
"step": 468
},
{
"epoch": 1.22,
"learning_rate": 1.346117057077493e-05,
"loss": 0.1995,
"step": 469
},
{
"epoch": 1.22,
"learning_rate": 1.3434840783634611e-05,
"loss": 0.2081,
"step": 470
},
{
"epoch": 1.22,
"learning_rate": 1.340848397122525e-05,
"loss": 0.196,
"step": 471
},
{
"epoch": 1.23,
"learning_rate": 1.3382100340921798e-05,
"loss": 0.2275,
"step": 472
},
{
"epoch": 1.23,
"learning_rate": 1.3355690100310213e-05,
"loss": 0.1986,
"step": 473
},
{
"epoch": 1.23,
"learning_rate": 1.3329253457185817e-05,
"loss": 0.1889,
"step": 474
},
{
"epoch": 1.23,
"learning_rate": 1.3302790619551673e-05,
"loss": 0.2363,
"step": 475
},
{
"epoch": 1.24,
"learning_rate": 1.3276301795616937e-05,
"loss": 0.1827,
"step": 476
},
{
"epoch": 1.24,
"learning_rate": 1.3249787193795227e-05,
"loss": 0.2414,
"step": 477
},
{
"epoch": 1.24,
"learning_rate": 1.3223247022702983e-05,
"loss": 0.2368,
"step": 478
},
{
"epoch": 1.24,
"learning_rate": 1.3196681491157816e-05,
"loss": 0.2083,
"step": 479
},
{
"epoch": 1.25,
"learning_rate": 1.3170090808176883e-05,
"loss": 0.1865,
"step": 480
},
{
"epoch": 1.25,
"learning_rate": 1.3143475182975222e-05,
"loss": 0.2261,
"step": 481
},
{
"epoch": 1.25,
"learning_rate": 1.3116834824964125e-05,
"loss": 0.1887,
"step": 482
},
{
"epoch": 1.25,
"learning_rate": 1.3090169943749475e-05,
"loss": 0.2,
"step": 483
},
{
"epoch": 1.26,
"learning_rate": 1.3063480749130106e-05,
"loss": 0.2132,
"step": 484
},
{
"epoch": 1.26,
"learning_rate": 1.3036767451096148e-05,
"loss": 0.1993,
"step": 485
},
{
"epoch": 1.26,
"learning_rate": 1.3010030259827378e-05,
"loss": 0.1982,
"step": 486
},
{
"epoch": 1.26,
"learning_rate": 1.2983269385691562e-05,
"loss": 0.1862,
"step": 487
},
{
"epoch": 1.27,
"learning_rate": 1.2956485039242805e-05,
"loss": 0.1971,
"step": 488
},
{
"epoch": 1.27,
"learning_rate": 1.292967743121989e-05,
"loss": 0.1897,
"step": 489
},
{
"epoch": 1.27,
"learning_rate": 1.2902846772544625e-05,
"loss": 0.2022,
"step": 490
},
{
"epoch": 1.28,
"learning_rate": 1.2875993274320173e-05,
"loss": 0.1945,
"step": 491
},
{
"epoch": 1.28,
"learning_rate": 1.2849117147829408e-05,
"loss": 0.1862,
"step": 492
},
{
"epoch": 1.28,
"learning_rate": 1.2822218604533232e-05,
"loss": 0.1902,
"step": 493
},
{
"epoch": 1.28,
"learning_rate": 1.2795297856068932e-05,
"loss": 0.1899,
"step": 494
},
{
"epoch": 1.29,
"learning_rate": 1.2768355114248493e-05,
"loss": 0.2219,
"step": 495
},
{
"epoch": 1.29,
"learning_rate": 1.2741390591056964e-05,
"loss": 0.2158,
"step": 496
},
{
"epoch": 1.29,
"learning_rate": 1.2714404498650743e-05,
"loss": 0.1861,
"step": 497
},
{
"epoch": 1.29,
"learning_rate": 1.2687397049355958e-05,
"loss": 0.1883,
"step": 498
},
{
"epoch": 1.3,
"learning_rate": 1.2660368455666752e-05,
"loss": 0.1926,
"step": 499
},
{
"epoch": 1.3,
"learning_rate": 1.2633318930243647e-05,
"loss": 0.1836,
"step": 500
},
{
"epoch": 1.3,
"learning_rate": 1.2606248685911856e-05,
"loss": 0.1954,
"step": 501
},
{
"epoch": 1.3,
"learning_rate": 1.2579157935659592e-05,
"loss": 0.1987,
"step": 502
},
{
"epoch": 1.31,
"learning_rate": 1.2552046892636427e-05,
"loss": 0.1821,
"step": 503
},
{
"epoch": 1.31,
"learning_rate": 1.252491577015158e-05,
"loss": 0.1876,
"step": 504
},
{
"epoch": 1.31,
"learning_rate": 1.249776478167227e-05,
"loss": 0.1997,
"step": 505
},
{
"epoch": 1.31,
"learning_rate": 1.2470594140822008e-05,
"loss": 0.191,
"step": 506
},
{
"epoch": 1.32,
"learning_rate": 1.2443404061378941e-05,
"loss": 0.2029,
"step": 507
},
{
"epoch": 1.32,
"learning_rate": 1.2416194757274152e-05,
"loss": 0.1745,
"step": 508
},
{
"epoch": 1.32,
"learning_rate": 1.2388966442589978e-05,
"loss": 0.1926,
"step": 509
},
{
"epoch": 1.32,
"learning_rate": 1.2361719331558346e-05,
"loss": 0.183,
"step": 510
},
{
"epoch": 1.33,
"learning_rate": 1.2334453638559057e-05,
"loss": 0.1879,
"step": 511
},
{
"epoch": 1.33,
"learning_rate": 1.2307169578118123e-05,
"loss": 0.1871,
"step": 512
},
{
"epoch": 1.33,
"learning_rate": 1.227986736490607e-05,
"loss": 0.1982,
"step": 513
},
{
"epoch": 1.34,
"learning_rate": 1.225254721373625e-05,
"loss": 0.198,
"step": 514
},
{
"epoch": 1.34,
"learning_rate": 1.2225209339563144e-05,
"loss": 0.176,
"step": 515
},
{
"epoch": 1.34,
"learning_rate": 1.2197853957480689e-05,
"loss": 0.1766,
"step": 516
},
{
"epoch": 1.34,
"learning_rate": 1.2170481282720563e-05,
"loss": 0.204,
"step": 517
},
{
"epoch": 1.35,
"learning_rate": 1.2143091530650508e-05,
"loss": 0.1926,
"step": 518
},
{
"epoch": 1.35,
"learning_rate": 1.211568491677263e-05,
"loss": 0.1903,
"step": 519
},
{
"epoch": 1.35,
"learning_rate": 1.20882616567217e-05,
"loss": 0.1826,
"step": 520
},
{
"epoch": 1.35,
"learning_rate": 1.2060821966263465e-05,
"loss": 0.1989,
"step": 521
},
{
"epoch": 1.36,
"learning_rate": 1.2033366061292942e-05,
"loss": 0.1947,
"step": 522
},
{
"epoch": 1.36,
"learning_rate": 1.200589415783273e-05,
"loss": 0.1786,
"step": 523
},
{
"epoch": 1.36,
"learning_rate": 1.1978406472031294e-05,
"loss": 0.1776,
"step": 524
},
{
"epoch": 1.36,
"learning_rate": 1.1950903220161286e-05,
"loss": 0.2122,
"step": 525
},
{
"epoch": 1.37,
"learning_rate": 1.1923384618617819e-05,
"loss": 0.1802,
"step": 526
},
{
"epoch": 1.37,
"learning_rate": 1.1895850883916786e-05,
"loss": 0.1874,
"step": 527
},
{
"epoch": 1.37,
"learning_rate": 1.1868302232693147e-05,
"loss": 0.1844,
"step": 528
},
{
"epoch": 1.37,
"learning_rate": 1.1840738881699218e-05,
"loss": 0.1843,
"step": 529
},
{
"epoch": 1.38,
"learning_rate": 1.1813161047802986e-05,
"loss": 0.2008,
"step": 530
},
{
"epoch": 1.38,
"learning_rate": 1.1785568947986368e-05,
"loss": 0.1965,
"step": 531
},
{
"epoch": 1.38,
"learning_rate": 1.1757962799343548e-05,
"loss": 0.1822,
"step": 532
},
{
"epoch": 1.38,
"learning_rate": 1.1730342819079229e-05,
"loss": 0.1864,
"step": 533
},
{
"epoch": 1.39,
"learning_rate": 1.170270922450695e-05,
"loss": 0.1891,
"step": 534
},
{
"epoch": 1.39,
"learning_rate": 1.1675062233047365e-05,
"loss": 0.2034,
"step": 535
},
{
"epoch": 1.39,
"learning_rate": 1.1647402062226534e-05,
"loss": 0.2028,
"step": 536
},
{
"epoch": 1.39,
"learning_rate": 1.161972892967421e-05,
"loss": 0.1842,
"step": 537
},
{
"epoch": 1.4,
"learning_rate": 1.1592043053122133e-05,
"loss": 0.2136,
"step": 538
},
{
"epoch": 1.4,
"learning_rate": 1.156434465040231e-05,
"loss": 0.1839,
"step": 539
},
{
"epoch": 1.4,
"learning_rate": 1.1536633939445302e-05,
"loss": 0.1844,
"step": 540
},
{
"epoch": 1.41,
"learning_rate": 1.1508911138278516e-05,
"loss": 0.1896,
"step": 541
},
{
"epoch": 1.41,
"learning_rate": 1.1481176465024477e-05,
"loss": 0.1811,
"step": 542
},
{
"epoch": 1.41,
"learning_rate": 1.1453430137899129e-05,
"loss": 0.1736,
"step": 543
},
{
"epoch": 1.41,
"learning_rate": 1.14256723752101e-05,
"loss": 0.1747,
"step": 544
},
{
"epoch": 1.42,
"learning_rate": 1.1397903395354996e-05,
"loss": 0.1761,
"step": 545
},
{
"epoch": 1.42,
"learning_rate": 1.1370123416819683e-05,
"loss": 0.1832,
"step": 546
},
{
"epoch": 1.42,
"learning_rate": 1.1342332658176556e-05,
"loss": 0.207,
"step": 547
},
{
"epoch": 1.42,
"learning_rate": 1.131453133808284e-05,
"loss": 0.1631,
"step": 548
},
{
"epoch": 1.43,
"learning_rate": 1.1286719675278838e-05,
"loss": 0.1936,
"step": 549
},
{
"epoch": 1.43,
"learning_rate": 1.1258897888586256e-05,
"loss": 0.2137,
"step": 550
},
{
"epoch": 1.43,
"learning_rate": 1.123106619690643e-05,
"loss": 0.1991,
"step": 551
},
{
"epoch": 1.43,
"learning_rate": 1.120322481921864e-05,
"loss": 0.2057,
"step": 552
},
{
"epoch": 1.44,
"learning_rate": 1.1175373974578378e-05,
"loss": 0.1853,
"step": 553
},
{
"epoch": 1.44,
"learning_rate": 1.114751388211561e-05,
"loss": 0.1906,
"step": 554
},
{
"epoch": 1.44,
"learning_rate": 1.1119644761033079e-05,
"loss": 0.1908,
"step": 555
},
{
"epoch": 1.44,
"learning_rate": 1.1091766830604552e-05,
"loss": 0.2029,
"step": 556
},
{
"epoch": 1.45,
"learning_rate": 1.1063880310173114e-05,
"loss": 0.1729,
"step": 557
},
{
"epoch": 1.45,
"learning_rate": 1.1035985419149436e-05,
"loss": 0.1718,
"step": 558
},
{
"epoch": 1.45,
"learning_rate": 1.1008082377010045e-05,
"loss": 0.1992,
"step": 559
},
{
"epoch": 1.45,
"learning_rate": 1.098017140329561e-05,
"loss": 0.1784,
"step": 560
},
{
"epoch": 1.46,
"learning_rate": 1.0952252717609188e-05,
"loss": 0.1944,
"step": 561
},
{
"epoch": 1.46,
"learning_rate": 1.0924326539614534e-05,
"loss": 0.1913,
"step": 562
},
{
"epoch": 1.46,
"learning_rate": 1.0896393089034336e-05,
"loss": 0.1899,
"step": 563
},
{
"epoch": 1.46,
"learning_rate": 1.0868452585648517e-05,
"loss": 0.1897,
"step": 564
},
{
"epoch": 1.47,
"learning_rate": 1.0840505249292477e-05,
"loss": 0.1653,
"step": 565
},
{
"epoch": 1.47,
"learning_rate": 1.0812551299855389e-05,
"loss": 0.1723,
"step": 566
},
{
"epoch": 1.47,
"learning_rate": 1.0784590957278452e-05,
"loss": 0.1727,
"step": 567
},
{
"epoch": 1.48,
"learning_rate": 1.0756624441553168e-05,
"loss": 0.1754,
"step": 568
},
{
"epoch": 1.48,
"learning_rate": 1.0728651972719603e-05,
"loss": 0.1771,
"step": 569
},
{
"epoch": 1.48,
"learning_rate": 1.0700673770864673e-05,
"loss": 0.2934,
"step": 570
},
{
"epoch": 1.48,
"learning_rate": 1.0672690056120398e-05,
"loss": 0.1826,
"step": 571
},
{
"epoch": 1.49,
"learning_rate": 1.0644701048662164e-05,
"loss": 0.2936,
"step": 572
},
{
"epoch": 1.49,
"learning_rate": 1.0616706968707015e-05,
"loss": 0.2254,
"step": 573
},
{
"epoch": 1.49,
"learning_rate": 1.058870803651189e-05,
"loss": 0.172,
"step": 574
},
{
"epoch": 1.49,
"learning_rate": 1.0560704472371919e-05,
"loss": 0.2053,
"step": 575
},
{
"epoch": 1.5,
"learning_rate": 1.0532696496618664e-05,
"loss": 0.1972,
"step": 576
},
{
"epoch": 1.5,
"learning_rate": 1.0504684329618408e-05,
"loss": 0.2,
"step": 577
},
{
"epoch": 1.5,
"learning_rate": 1.0476668191770407e-05,
"loss": 0.1794,
"step": 578
},
{
"epoch": 1.5,
"learning_rate": 1.044864830350515e-05,
"loss": 0.1788,
"step": 579
},
{
"epoch": 1.51,
"learning_rate": 1.0420624885282653e-05,
"loss": 0.1645,
"step": 580
},
{
"epoch": 1.51,
"learning_rate": 1.0392598157590687e-05,
"loss": 0.1781,
"step": 581
},
{
"epoch": 1.51,
"learning_rate": 1.0364568340943077e-05,
"loss": 0.1865,
"step": 582
},
{
"epoch": 1.51,
"learning_rate": 1.0336535655877942e-05,
"loss": 0.1913,
"step": 583
},
{
"epoch": 1.52,
"learning_rate": 1.0308500322955971e-05,
"loss": 0.1846,
"step": 584
},
{
"epoch": 1.52,
"learning_rate": 1.028046256275869e-05,
"loss": 0.1726,
"step": 585
},
{
"epoch": 1.52,
"learning_rate": 1.0252422595886723e-05,
"loss": 0.1734,
"step": 586
},
{
"epoch": 1.52,
"learning_rate": 1.0224380642958052e-05,
"loss": 0.1771,
"step": 587
},
{
"epoch": 1.53,
"learning_rate": 1.0196336924606282e-05,
"loss": 0.1596,
"step": 588
},
{
"epoch": 1.53,
"learning_rate": 1.0168291661478924e-05,
"loss": 0.1886,
"step": 589
},
{
"epoch": 1.53,
"learning_rate": 1.0140245074235624e-05,
"loss": 0.1827,
"step": 590
},
{
"epoch": 1.54,
"learning_rate": 1.011219738354646e-05,
"loss": 0.1702,
"step": 591
},
{
"epoch": 1.54,
"learning_rate": 1.0084148810090185e-05,
"loss": 0.1769,
"step": 592
},
{
"epoch": 1.54,
"learning_rate": 1.0056099574552498e-05,
"loss": 0.1675,
"step": 593
},
{
"epoch": 1.54,
"learning_rate": 1.0028049897624308e-05,
"loss": 0.1643,
"step": 594
},
{
"epoch": 1.55,
"learning_rate": 1e-05,
"loss": 0.1717,
"step": 595
},
{
"epoch": 1.55,
"learning_rate": 9.971950102375696e-06,
"loss": 0.2031,
"step": 596
},
{
"epoch": 1.55,
"learning_rate": 9.943900425447505e-06,
"loss": 0.1806,
"step": 597
},
{
"epoch": 1.55,
"learning_rate": 9.91585118990982e-06,
"loss": 0.1817,
"step": 598
},
{
"epoch": 1.56,
"learning_rate": 9.887802616453543e-06,
"loss": 0.1765,
"step": 599
},
{
"epoch": 1.56,
"learning_rate": 9.85975492576438e-06,
"loss": 0.1727,
"step": 600
},
{
"epoch": 1.56,
"learning_rate": 9.83170833852108e-06,
"loss": 0.1708,
"step": 601
},
{
"epoch": 1.56,
"learning_rate": 9.80366307539372e-06,
"loss": 0.1852,
"step": 602
},
{
"epoch": 1.57,
"learning_rate": 9.775619357041952e-06,
"loss": 0.1633,
"step": 603
},
{
"epoch": 1.57,
"learning_rate": 9.747577404113282e-06,
"loss": 0.1759,
"step": 604
},
{
"epoch": 1.57,
"learning_rate": 9.719537437241311e-06,
"loss": 0.1575,
"step": 605
},
{
"epoch": 1.57,
"learning_rate": 9.691499677044032e-06,
"loss": 0.174,
"step": 606
},
{
"epoch": 1.58,
"learning_rate": 9.663464344122064e-06,
"loss": 0.1668,
"step": 607
},
{
"epoch": 1.58,
"learning_rate": 9.635431659056928e-06,
"loss": 0.1902,
"step": 608
},
{
"epoch": 1.58,
"learning_rate": 9.607401842409318e-06,
"loss": 0.1791,
"step": 609
},
{
"epoch": 1.58,
"learning_rate": 9.579375114717352e-06,
"loss": 0.1863,
"step": 610
},
{
"epoch": 1.59,
"learning_rate": 9.551351696494854e-06,
"loss": 0.1702,
"step": 611
},
{
"epoch": 1.59,
"learning_rate": 9.5233318082296e-06,
"loss": 0.1667,
"step": 612
},
{
"epoch": 1.59,
"learning_rate": 9.495315670381592e-06,
"loss": 0.1572,
"step": 613
},
{
"epoch": 1.59,
"learning_rate": 9.467303503381335e-06,
"loss": 0.1547,
"step": 614
},
{
"epoch": 1.6,
"learning_rate": 9.439295527628083e-06,
"loss": 0.1568,
"step": 615
},
{
"epoch": 1.6,
"learning_rate": 9.41129196348811e-06,
"loss": 0.1657,
"step": 616
},
{
"epoch": 1.6,
"learning_rate": 9.383293031292985e-06,
"loss": 0.1595,
"step": 617
},
{
"epoch": 1.61,
"learning_rate": 9.355298951337836e-06,
"loss": 0.1966,
"step": 618
},
{
"epoch": 1.61,
"learning_rate": 9.327309943879604e-06,
"loss": 0.165,
"step": 619
},
{
"epoch": 1.61,
"learning_rate": 9.299326229135326e-06,
"loss": 0.1707,
"step": 620
},
{
"epoch": 1.61,
"learning_rate": 9.2713480272804e-06,
"loss": 0.153,
"step": 621
},
{
"epoch": 1.62,
"learning_rate": 9.243375558446837e-06,
"loss": 0.1674,
"step": 622
},
{
"epoch": 1.62,
"learning_rate": 9.215409042721553e-06,
"loss": 0.1712,
"step": 623
},
{
"epoch": 1.62,
"learning_rate": 9.187448700144613e-06,
"loss": 0.1666,
"step": 624
},
{
"epoch": 1.62,
"learning_rate": 9.159494750707527e-06,
"loss": 0.173,
"step": 625
},
{
"epoch": 1.63,
"learning_rate": 9.131547414351486e-06,
"loss": 0.1982,
"step": 626
},
{
"epoch": 1.63,
"learning_rate": 9.103606910965666e-06,
"loss": 0.1628,
"step": 627
},
{
"epoch": 1.63,
"learning_rate": 9.07567346038547e-06,
"loss": 0.1833,
"step": 628
},
{
"epoch": 1.63,
"learning_rate": 9.047747282390815e-06,
"loss": 0.1467,
"step": 629
},
{
"epoch": 1.64,
"learning_rate": 9.019828596704394e-06,
"loss": 0.1537,
"step": 630
},
{
"epoch": 1.64,
"learning_rate": 8.991917622989957e-06,
"loss": 0.1926,
"step": 631
},
{
"epoch": 1.64,
"learning_rate": 8.964014580850568e-06,
"loss": 0.1723,
"step": 632
},
{
"epoch": 1.64,
"learning_rate": 8.936119689826888e-06,
"loss": 0.1509,
"step": 633
},
{
"epoch": 1.65,
"learning_rate": 8.90823316939545e-06,
"loss": 0.1611,
"step": 634
},
{
"epoch": 1.65,
"learning_rate": 8.880355238966923e-06,
"loss": 0.1756,
"step": 635
},
{
"epoch": 1.65,
"learning_rate": 8.852486117884391e-06,
"loss": 0.1637,
"step": 636
},
{
"epoch": 1.65,
"learning_rate": 8.824626025421625e-06,
"loss": 0.145,
"step": 637
},
{
"epoch": 1.66,
"learning_rate": 8.796775180781363e-06,
"loss": 0.164,
"step": 638
},
{
"epoch": 1.66,
"learning_rate": 8.768933803093573e-06,
"loss": 0.1502,
"step": 639
},
{
"epoch": 1.66,
"learning_rate": 8.741102111413749e-06,
"loss": 0.1721,
"step": 640
},
{
"epoch": 1.66,
"learning_rate": 8.713280324721163e-06,
"loss": 0.146,
"step": 641
},
{
"epoch": 1.67,
"learning_rate": 8.685468661917167e-06,
"loss": 0.1868,
"step": 642
},
{
"epoch": 1.67,
"learning_rate": 8.657667341823449e-06,
"loss": 0.1736,
"step": 643
},
{
"epoch": 1.67,
"learning_rate": 8.629876583180322e-06,
"loss": 0.1524,
"step": 644
},
{
"epoch": 1.68,
"learning_rate": 8.602096604645009e-06,
"loss": 0.1539,
"step": 645
},
{
"epoch": 1.68,
"learning_rate": 8.574327624789904e-06,
"loss": 0.1768,
"step": 646
},
{
"epoch": 1.68,
"learning_rate": 8.546569862100876e-06,
"loss": 0.1576,
"step": 647
},
{
"epoch": 1.68,
"learning_rate": 8.518823534975525e-06,
"loss": 0.1719,
"step": 648
},
{
"epoch": 1.69,
"learning_rate": 8.491088861721486e-06,
"loss": 0.1468,
"step": 649
},
{
"epoch": 1.69,
"learning_rate": 8.463366060554698e-06,
"loss": 0.1673,
"step": 650
},
{
"epoch": 1.69,
"learning_rate": 8.43565534959769e-06,
"loss": 0.1357,
"step": 651
},
{
"epoch": 1.69,
"learning_rate": 8.407956946877868e-06,
"loss": 0.156,
"step": 652
},
{
"epoch": 1.7,
"learning_rate": 8.380271070325789e-06,
"loss": 0.1652,
"step": 653
},
{
"epoch": 1.7,
"learning_rate": 8.352597937773468e-06,
"loss": 0.1529,
"step": 654
},
{
"epoch": 1.7,
"learning_rate": 8.324937766952638e-06,
"loss": 0.1623,
"step": 655
},
{
"epoch": 1.7,
"learning_rate": 8.297290775493051e-06,
"loss": 0.1618,
"step": 656
},
{
"epoch": 1.71,
"learning_rate": 8.269657180920773e-06,
"loss": 0.1458,
"step": 657
},
{
"epoch": 1.71,
"learning_rate": 8.242037200656455e-06,
"loss": 0.1689,
"step": 658
},
{
"epoch": 1.71,
"learning_rate": 8.214431052013636e-06,
"loss": 0.1663,
"step": 659
},
{
"epoch": 1.71,
"learning_rate": 8.186838952197019e-06,
"loss": 0.1579,
"step": 660
},
{
"epoch": 1.72,
"learning_rate": 8.159261118300784e-06,
"loss": 0.1618,
"step": 661
},
{
"epoch": 1.72,
"learning_rate": 8.131697767306856e-06,
"loss": 0.1866,
"step": 662
},
{
"epoch": 1.72,
"learning_rate": 8.104149116083216e-06,
"loss": 0.15,
"step": 663
},
{
"epoch": 1.72,
"learning_rate": 8.076615381382184e-06,
"loss": 0.1511,
"step": 664
},
{
"epoch": 1.73,
"learning_rate": 8.04909677983872e-06,
"loss": 0.1541,
"step": 665
},
{
"epoch": 1.73,
"learning_rate": 8.02159352796871e-06,
"loss": 0.1508,
"step": 666
},
{
"epoch": 1.73,
"learning_rate": 7.994105842167274e-06,
"loss": 0.1649,
"step": 667
},
{
"epoch": 1.74,
"learning_rate": 7.966633938707062e-06,
"loss": 0.152,
"step": 668
},
{
"epoch": 1.74,
"learning_rate": 7.939178033736538e-06,
"loss": 0.1485,
"step": 669
},
{
"epoch": 1.74,
"learning_rate": 7.911738343278303e-06,
"loss": 0.1545,
"step": 670
},
{
"epoch": 1.74,
"learning_rate": 7.884315083227373e-06,
"loss": 0.1667,
"step": 671
},
{
"epoch": 1.75,
"learning_rate": 7.856908469349495e-06,
"loss": 0.163,
"step": 672
},
{
"epoch": 1.75,
"learning_rate": 7.829518717279439e-06,
"loss": 0.1422,
"step": 673
},
{
"epoch": 1.75,
"learning_rate": 7.802146042519314e-06,
"loss": 0.1619,
"step": 674
},
{
"epoch": 1.75,
"learning_rate": 7.774790660436857e-06,
"loss": 0.1454,
"step": 675
},
{
"epoch": 1.76,
"learning_rate": 7.747452786263755e-06,
"loss": 0.1581,
"step": 676
},
{
"epoch": 1.76,
"learning_rate": 7.720132635093935e-06,
"loss": 0.1553,
"step": 677
},
{
"epoch": 1.76,
"learning_rate": 7.69283042188188e-06,
"loss": 0.1451,
"step": 678
},
{
"epoch": 1.76,
"learning_rate": 7.66554636144095e-06,
"loss": 0.1697,
"step": 679
},
{
"epoch": 1.77,
"learning_rate": 7.63828066844166e-06,
"loss": 0.1627,
"step": 680
},
{
"epoch": 1.77,
"learning_rate": 7.611033557410027e-06,
"loss": 0.1624,
"step": 681
},
{
"epoch": 1.77,
"learning_rate": 7.583805242725853e-06,
"loss": 0.151,
"step": 682
},
{
"epoch": 1.77,
"learning_rate": 7.556595938621058e-06,
"loss": 0.1643,
"step": 683
},
{
"epoch": 1.78,
"learning_rate": 7.529405859177992e-06,
"loss": 0.1999,
"step": 684
},
{
"epoch": 1.78,
"learning_rate": 7.50223521832773e-06,
"loss": 0.1816,
"step": 685
},
{
"epoch": 1.78,
"learning_rate": 7.4750842298484205e-06,
"loss": 0.1734,
"step": 686
},
{
"epoch": 1.78,
"learning_rate": 7.447953107363574e-06,
"loss": 0.2372,
"step": 687
},
{
"epoch": 1.79,
"learning_rate": 7.420842064340408e-06,
"loss": 0.1917,
"step": 688
},
{
"epoch": 1.79,
"learning_rate": 7.393751314088147e-06,
"loss": 0.1431,
"step": 689
},
{
"epoch": 1.79,
"learning_rate": 7.366681069756352e-06,
"loss": 0.1777,
"step": 690
},
{
"epoch": 1.79,
"learning_rate": 7.33963154433325e-06,
"loss": 0.1451,
"step": 691
},
{
"epoch": 1.8,
"learning_rate": 7.312602950644046e-06,
"loss": 0.1858,
"step": 692
},
{
"epoch": 1.8,
"learning_rate": 7.285595501349259e-06,
"loss": 0.4727,
"step": 693
},
{
"epoch": 1.8,
"learning_rate": 7.258609408943038e-06,
"loss": 0.175,
"step": 694
},
{
"epoch": 1.81,
"learning_rate": 7.2316448857515076e-06,
"loss": 0.1715,
"step": 695
},
{
"epoch": 1.81,
"learning_rate": 7.204702143931072e-06,
"loss": 0.3151,
"step": 696
},
{
"epoch": 1.81,
"learning_rate": 7.1777813954667716e-06,
"loss": 0.2031,
"step": 697
},
{
"epoch": 1.81,
"learning_rate": 7.1508828521705955e-06,
"loss": 0.1625,
"step": 698
},
{
"epoch": 1.82,
"learning_rate": 7.124006725679828e-06,
"loss": 0.162,
"step": 699
},
{
"epoch": 1.82,
"learning_rate": 7.097153227455379e-06,
"loss": 0.1566,
"step": 700
},
{
"epoch": 1.82,
"learning_rate": 7.070322568780111e-06,
"loss": 0.194,
"step": 701
},
{
"epoch": 1.82,
"learning_rate": 7.043514960757199e-06,
"loss": 0.1443,
"step": 702
},
{
"epoch": 1.83,
"learning_rate": 7.01673061430844e-06,
"loss": 0.1649,
"step": 703
},
{
"epoch": 1.83,
"learning_rate": 6.989969740172626e-06,
"loss": 0.1559,
"step": 704
},
{
"epoch": 1.83,
"learning_rate": 6.963232548903853e-06,
"loss": 0.1579,
"step": 705
},
{
"epoch": 1.83,
"learning_rate": 6.9365192508698975e-06,
"loss": 0.1796,
"step": 706
},
{
"epoch": 1.84,
"learning_rate": 6.909830056250527e-06,
"loss": 0.167,
"step": 707
},
{
"epoch": 1.84,
"learning_rate": 6.883165175035879e-06,
"loss": 0.1678,
"step": 708
},
{
"epoch": 1.84,
"learning_rate": 6.85652481702478e-06,
"loss": 0.1589,
"step": 709
},
{
"epoch": 1.84,
"learning_rate": 6.829909191823121e-06,
"loss": 0.2298,
"step": 710
},
{
"epoch": 1.85,
"learning_rate": 6.8033185088421874e-06,
"loss": 0.1701,
"step": 711
},
{
"epoch": 1.85,
"learning_rate": 6.776752977297022e-06,
"loss": 0.1565,
"step": 712
},
{
"epoch": 1.85,
"learning_rate": 6.750212806204778e-06,
"loss": 0.1679,
"step": 713
},
{
"epoch": 1.85,
"learning_rate": 6.723698204383067e-06,
"loss": 0.146,
"step": 714
},
{
"epoch": 1.86,
"learning_rate": 6.697209380448333e-06,
"loss": 0.154,
"step": 715
},
{
"epoch": 1.86,
"learning_rate": 6.670746542814187e-06,
"loss": 0.1428,
"step": 716
},
{
"epoch": 1.86,
"learning_rate": 6.644309899689794e-06,
"loss": 0.3363,
"step": 717
},
{
"epoch": 1.86,
"learning_rate": 6.617899659078204e-06,
"loss": 0.146,
"step": 718
},
{
"epoch": 1.87,
"learning_rate": 6.59151602877475e-06,
"loss": 0.1719,
"step": 719
},
{
"epoch": 1.87,
"learning_rate": 6.5651592163653885e-06,
"loss": 0.1726,
"step": 720
},
{
"epoch": 1.87,
"learning_rate": 6.538829429225068e-06,
"loss": 0.1629,
"step": 721
},
{
"epoch": 1.88,
"learning_rate": 6.512526874516114e-06,
"loss": 0.1687,
"step": 722
},
{
"epoch": 1.88,
"learning_rate": 6.486251759186573e-06,
"loss": 0.1379,
"step": 723
},
{
"epoch": 1.88,
"learning_rate": 6.460004289968611e-06,
"loss": 0.1566,
"step": 724
},
{
"epoch": 1.88,
"learning_rate": 6.43378467337687e-06,
"loss": 0.1441,
"step": 725
},
{
"epoch": 1.89,
"learning_rate": 6.407593115706849e-06,
"loss": 0.1473,
"step": 726
},
{
"epoch": 1.89,
"learning_rate": 6.381429823033281e-06,
"loss": 0.1708,
"step": 727
},
{
"epoch": 1.89,
"learning_rate": 6.355295001208504e-06,
"loss": 0.1535,
"step": 728
},
{
"epoch": 1.89,
"learning_rate": 6.329188855860859e-06,
"loss": 0.1543,
"step": 729
},
{
"epoch": 1.9,
"learning_rate": 6.303111592393051e-06,
"loss": 0.1523,
"step": 730
},
{
"epoch": 1.9,
"learning_rate": 6.277063415980549e-06,
"loss": 0.1627,
"step": 731
},
{
"epoch": 1.9,
"learning_rate": 6.251044531569962e-06,
"loss": 0.1847,
"step": 732
},
{
"epoch": 1.9,
"learning_rate": 6.225055143877434e-06,
"loss": 0.1795,
"step": 733
},
{
"epoch": 1.91,
"learning_rate": 6.199095457387021e-06,
"loss": 0.1412,
"step": 734
},
{
"epoch": 1.91,
"learning_rate": 6.173165676349103e-06,
"loss": 0.1348,
"step": 735
},
{
"epoch": 1.91,
"learning_rate": 6.147266004778755e-06,
"loss": 0.1318,
"step": 736
},
{
"epoch": 1.91,
"learning_rate": 6.12139664645415e-06,
"loss": 0.1389,
"step": 737
},
{
"epoch": 1.92,
"learning_rate": 6.095557804914965e-06,
"loss": 0.1439,
"step": 738
},
{
"epoch": 1.92,
"learning_rate": 6.069749683460765e-06,
"loss": 0.1431,
"step": 739
},
{
"epoch": 1.92,
"learning_rate": 6.043972485149414e-06,
"loss": 0.1608,
"step": 740
},
{
"epoch": 1.92,
"learning_rate": 6.018226412795469e-06,
"loss": 0.1674,
"step": 741
},
{
"epoch": 1.93,
"learning_rate": 5.9925116689685925e-06,
"loss": 0.1443,
"step": 742
},
{
"epoch": 1.93,
"learning_rate": 5.966828455991951e-06,
"loss": 0.1496,
"step": 743
},
{
"epoch": 1.93,
"learning_rate": 5.941176975940631e-06,
"loss": 0.1806,
"step": 744
},
{
"epoch": 1.94,
"learning_rate": 5.91555743064004e-06,
"loss": 0.1618,
"step": 745
},
{
"epoch": 1.94,
"learning_rate": 5.889970021664329e-06,
"loss": 0.1743,
"step": 746
},
{
"epoch": 1.94,
"learning_rate": 5.864414950334796e-06,
"loss": 0.1761,
"step": 747
},
{
"epoch": 1.94,
"learning_rate": 5.8388924177183085e-06,
"loss": 0.1645,
"step": 748
},
{
"epoch": 1.95,
"learning_rate": 5.813402624625722e-06,
"loss": 0.1496,
"step": 749
},
{
"epoch": 1.95,
"learning_rate": 5.787945771610296e-06,
"loss": 0.1599,
"step": 750
},
{
"epoch": 1.95,
"learning_rate": 5.7625220589661136e-06,
"loss": 0.152,
"step": 751
},
{
"epoch": 1.95,
"learning_rate": 5.7371316867265235e-06,
"loss": 0.1571,
"step": 752
},
{
"epoch": 1.96,
"learning_rate": 5.711774854662535e-06,
"loss": 0.1465,
"step": 753
},
{
"epoch": 1.96,
"learning_rate": 5.686451762281282e-06,
"loss": 0.1623,
"step": 754
},
{
"epoch": 1.96,
"learning_rate": 5.66116260882442e-06,
"loss": 0.156,
"step": 755
},
{
"epoch": 1.96,
"learning_rate": 5.635907593266578e-06,
"loss": 0.1604,
"step": 756
},
{
"epoch": 1.97,
"learning_rate": 5.610686914313796e-06,
"loss": 0.1376,
"step": 757
},
{
"epoch": 1.97,
"learning_rate": 5.585500770401946e-06,
"loss": 0.1724,
"step": 758
},
{
"epoch": 1.97,
"learning_rate": 5.560349359695181e-06,
"loss": 0.1488,
"step": 759
},
{
"epoch": 1.97,
"learning_rate": 5.535232880084373e-06,
"loss": 0.1426,
"step": 760
},
{
"epoch": 1.98,
"learning_rate": 5.510151529185554e-06,
"loss": 0.1577,
"step": 761
},
{
"epoch": 1.98,
"learning_rate": 5.485105504338375e-06,
"loss": 0.161,
"step": 762
},
{
"epoch": 1.98,
"learning_rate": 5.460095002604533e-06,
"loss": 0.1582,
"step": 763
},
{
"epoch": 1.98,
"learning_rate": 5.43512022076623e-06,
"loss": 0.1695,
"step": 764
},
{
"epoch": 1.99,
"learning_rate": 5.410181355324622e-06,
"loss": 0.1503,
"step": 765
},
{
"epoch": 1.99,
"learning_rate": 5.385278602498288e-06,
"loss": 0.1672,
"step": 766
},
{
"epoch": 1.99,
"learning_rate": 5.360412158221661e-06,
"loss": 0.1503,
"step": 767
},
{
"epoch": 1.99,
"learning_rate": 5.335582218143502e-06,
"loss": 0.1512,
"step": 768
},
{
"epoch": 2.0,
"learning_rate": 5.3107889776253544e-06,
"loss": 0.1738,
"step": 769
},
{
"epoch": 2.0,
"learning_rate": 5.286032631740023e-06,
"loss": 0.16,
"step": 770
},
{
"epoch": 2.0,
"learning_rate": 5.2613133752700145e-06,
"loss": 0.1429,
"step": 771
},
{
"epoch": 2.01,
"learning_rate": 5.236631402706018e-06,
"loss": 0.1298,
"step": 772
},
{
"epoch": 2.01,
"learning_rate": 5.211986908245374e-06,
"loss": 0.1395,
"step": 773
},
{
"epoch": 2.01,
"learning_rate": 5.187380085790548e-06,
"loss": 0.1344,
"step": 774
},
{
"epoch": 2.01,
"learning_rate": 5.1628111289476025e-06,
"loss": 0.1135,
"step": 775
},
{
"epoch": 2.02,
"learning_rate": 5.138280231024676e-06,
"loss": 0.1241,
"step": 776
},
{
"epoch": 2.02,
"learning_rate": 5.1137875850304545e-06,
"loss": 0.1191,
"step": 777
},
{
"epoch": 2.02,
"learning_rate": 5.089333383672657e-06,
"loss": 0.1231,
"step": 778
},
{
"epoch": 2.02,
"learning_rate": 5.064917819356532e-06,
"loss": 0.2508,
"step": 779
},
{
"epoch": 2.03,
"learning_rate": 5.040541084183326e-06,
"loss": 0.1158,
"step": 780
},
{
"epoch": 2.03,
"learning_rate": 5.016203369948774e-06,
"loss": 0.0988,
"step": 781
},
{
"epoch": 2.03,
"learning_rate": 4.991904868141599e-06,
"loss": 0.0878,
"step": 782
},
{
"epoch": 2.03,
"learning_rate": 4.967645769942e-06,
"loss": 0.1098,
"step": 783
},
{
"epoch": 2.04,
"learning_rate": 4.943426266220156e-06,
"loss": 0.0808,
"step": 784
},
{
"epoch": 2.04,
"learning_rate": 4.919246547534709e-06,
"loss": 0.1106,
"step": 785
},
{
"epoch": 2.04,
"learning_rate": 4.895106804131274e-06,
"loss": 0.0936,
"step": 786
},
{
"epoch": 2.04,
"learning_rate": 4.871007225940939e-06,
"loss": 0.0813,
"step": 787
},
{
"epoch": 2.05,
"learning_rate": 4.846948002578783e-06,
"loss": 0.1197,
"step": 788
},
{
"epoch": 2.05,
"learning_rate": 4.822929323342369e-06,
"loss": 0.0864,
"step": 789
},
{
"epoch": 2.05,
"learning_rate": 4.798951377210253e-06,
"loss": 0.081,
"step": 790
},
{
"epoch": 2.05,
"learning_rate": 4.775014352840512e-06,
"loss": 0.0733,
"step": 791
},
{
"epoch": 2.06,
"learning_rate": 4.751118438569242e-06,
"loss": 0.086,
"step": 792
},
{
"epoch": 2.06,
"learning_rate": 4.727263822409099e-06,
"loss": 0.0934,
"step": 793
},
{
"epoch": 2.06,
"learning_rate": 4.703450692047795e-06,
"loss": 0.0779,
"step": 794
},
{
"epoch": 2.06,
"learning_rate": 4.679679234846636e-06,
"loss": 0.0707,
"step": 795
},
{
"epoch": 2.07,
"learning_rate": 4.655949637839042e-06,
"loss": 0.0718,
"step": 796
},
{
"epoch": 2.07,
"learning_rate": 4.63226208772908e-06,
"loss": 0.0756,
"step": 797
},
{
"epoch": 2.07,
"learning_rate": 4.608616770889998e-06,
"loss": 0.0654,
"step": 798
},
{
"epoch": 2.08,
"learning_rate": 4.5850138733627435e-06,
"loss": 0.0703,
"step": 799
},
{
"epoch": 2.08,
"learning_rate": 4.561453580854516e-06,
"loss": 0.0664,
"step": 800
},
{
"epoch": 2.08,
"learning_rate": 4.537936078737291e-06,
"loss": 0.0593,
"step": 801
},
{
"epoch": 2.08,
"learning_rate": 4.514461552046386e-06,
"loss": 0.0726,
"step": 802
},
{
"epoch": 2.09,
"learning_rate": 4.491030185478976e-06,
"loss": 0.0494,
"step": 803
},
{
"epoch": 2.09,
"learning_rate": 4.467642163392654e-06,
"loss": 0.0712,
"step": 804
},
{
"epoch": 2.09,
"learning_rate": 4.444297669803981e-06,
"loss": 0.0642,
"step": 805
},
{
"epoch": 2.09,
"learning_rate": 4.420996888387033e-06,
"loss": 0.0665,
"step": 806
},
{
"epoch": 2.1,
"learning_rate": 4.397740002471973e-06,
"loss": 0.0585,
"step": 807
},
{
"epoch": 2.1,
"learning_rate": 4.374527195043579e-06,
"loss": 0.0733,
"step": 808
},
{
"epoch": 2.1,
"learning_rate": 4.351358648739826e-06,
"loss": 0.0585,
"step": 809
},
{
"epoch": 2.1,
"learning_rate": 4.328234545850441e-06,
"loss": 0.0499,
"step": 810
},
{
"epoch": 2.11,
"learning_rate": 4.305155068315481e-06,
"loss": 0.0544,
"step": 811
},
{
"epoch": 2.11,
"learning_rate": 4.282120397723879e-06,
"loss": 0.0579,
"step": 812
},
{
"epoch": 2.11,
"learning_rate": 4.2591307153120335e-06,
"loss": 0.067,
"step": 813
},
{
"epoch": 2.11,
"learning_rate": 4.236186201962372e-06,
"loss": 0.0476,
"step": 814
},
{
"epoch": 2.12,
"learning_rate": 4.213287038201943e-06,
"loss": 0.0504,
"step": 815
},
{
"epoch": 2.12,
"learning_rate": 4.190433404200977e-06,
"loss": 0.2316,
"step": 816
},
{
"epoch": 2.12,
"learning_rate": 4.167625479771476e-06,
"loss": 0.0494,
"step": 817
},
{
"epoch": 2.12,
"learning_rate": 4.144863444365806e-06,
"loss": 0.0544,
"step": 818
},
{
"epoch": 2.13,
"learning_rate": 4.12214747707527e-06,
"loss": 0.0549,
"step": 819
},
{
"epoch": 2.13,
"learning_rate": 4.09947775662872e-06,
"loss": 0.0529,
"step": 820
},
{
"epoch": 2.13,
"learning_rate": 4.07685446139113e-06,
"loss": 0.0877,
"step": 821
},
{
"epoch": 2.14,
"learning_rate": 4.054277769362203e-06,
"loss": 0.0528,
"step": 822
},
{
"epoch": 2.14,
"learning_rate": 4.0317478581749644e-06,
"loss": 0.0686,
"step": 823
},
{
"epoch": 2.14,
"learning_rate": 4.009264905094378e-06,
"loss": 0.0494,
"step": 824
},
{
"epoch": 2.14,
"learning_rate": 3.986829087015941e-06,
"loss": 0.062,
"step": 825
},
{
"epoch": 2.15,
"learning_rate": 3.964440580464286e-06,
"loss": 0.0487,
"step": 826
},
{
"epoch": 2.15,
"learning_rate": 3.942099561591802e-06,
"loss": 0.0635,
"step": 827
},
{
"epoch": 2.15,
"learning_rate": 3.919806206177245e-06,
"loss": 0.0543,
"step": 828
},
{
"epoch": 2.15,
"learning_rate": 3.897560689624362e-06,
"loss": 0.058,
"step": 829
},
{
"epoch": 2.16,
"learning_rate": 3.875363186960499e-06,
"loss": 0.0601,
"step": 830
},
{
"epoch": 2.16,
"learning_rate": 3.853213872835229e-06,
"loss": 0.0568,
"step": 831
},
{
"epoch": 2.16,
"learning_rate": 3.83111292151898e-06,
"loss": 0.0488,
"step": 832
},
{
"epoch": 2.16,
"learning_rate": 3.8090605069016596e-06,
"loss": 0.0532,
"step": 833
},
{
"epoch": 2.17,
"learning_rate": 3.787056802491298e-06,
"loss": 0.0576,
"step": 834
},
{
"epoch": 2.17,
"learning_rate": 3.7651019814126656e-06,
"loss": 0.0473,
"step": 835
},
{
"epoch": 2.17,
"learning_rate": 3.743196216405922e-06,
"loss": 0.0598,
"step": 836
},
{
"epoch": 2.17,
"learning_rate": 3.7213396798252522e-06,
"loss": 0.0462,
"step": 837
},
{
"epoch": 2.18,
"learning_rate": 3.6995325436375218e-06,
"loss": 0.0596,
"step": 838
},
{
"epoch": 2.18,
"learning_rate": 3.677774979420904e-06,
"loss": 0.0437,
"step": 839
},
{
"epoch": 2.18,
"learning_rate": 3.6560671583635467e-06,
"loss": 0.0411,
"step": 840
},
{
"epoch": 2.18,
"learning_rate": 3.6344092512622173e-06,
"loss": 0.0435,
"step": 841
},
{
"epoch": 2.19,
"learning_rate": 3.6128014285209588e-06,
"loss": 0.0435,
"step": 842
},
{
"epoch": 2.19,
"learning_rate": 3.591243860149759e-06,
"loss": 0.0479,
"step": 843
},
{
"epoch": 2.19,
"learning_rate": 3.5697367157632e-06,
"loss": 0.0417,
"step": 844
},
{
"epoch": 2.19,
"learning_rate": 3.5482801645791266e-06,
"loss": 0.0426,
"step": 845
},
{
"epoch": 2.2,
"learning_rate": 3.5268743754173174e-06,
"loss": 0.0472,
"step": 846
},
{
"epoch": 2.2,
"learning_rate": 3.505519516698165e-06,
"loss": 0.0513,
"step": 847
},
{
"epoch": 2.2,
"learning_rate": 3.4842157564413313e-06,
"loss": 0.0482,
"step": 848
},
{
"epoch": 2.21,
"learning_rate": 3.4629632622644437e-06,
"loss": 0.0441,
"step": 849
},
{
"epoch": 2.21,
"learning_rate": 3.4417622013817597e-06,
"loss": 0.0449,
"step": 850
},
{
"epoch": 2.21,
"learning_rate": 3.4206127406028744e-06,
"loss": 0.0432,
"step": 851
},
{
"epoch": 2.21,
"learning_rate": 3.3995150463313842e-06,
"loss": 0.0515,
"step": 852
},
{
"epoch": 2.22,
"learning_rate": 3.378469284563589e-06,
"loss": 0.0382,
"step": 853
},
{
"epoch": 2.22,
"learning_rate": 3.3574756208871862e-06,
"loss": 0.0444,
"step": 854
},
{
"epoch": 2.22,
"learning_rate": 3.3365342204799613e-06,
"loss": 0.0455,
"step": 855
},
{
"epoch": 2.22,
"learning_rate": 3.3156452481085056e-06,
"loss": 0.0465,
"step": 856
},
{
"epoch": 2.23,
"learning_rate": 3.294808868126894e-06,
"loss": 0.05,
"step": 857
},
{
"epoch": 2.23,
"learning_rate": 3.2740252444754095e-06,
"loss": 0.0421,
"step": 858
},
{
"epoch": 2.23,
"learning_rate": 3.2532945406792573e-06,
"loss": 0.0391,
"step": 859
},
{
"epoch": 2.23,
"learning_rate": 3.2326169198472555e-06,
"loss": 0.0544,
"step": 860
},
{
"epoch": 2.24,
"learning_rate": 3.2119925446705824e-06,
"loss": 0.0385,
"step": 861
},
{
"epoch": 2.24,
"learning_rate": 3.191421577421466e-06,
"loss": 0.049,
"step": 862
},
{
"epoch": 2.24,
"learning_rate": 3.1709041799519312e-06,
"loss": 0.0555,
"step": 863
},
{
"epoch": 2.24,
"learning_rate": 3.150440513692511e-06,
"loss": 0.0724,
"step": 864
},
{
"epoch": 2.25,
"learning_rate": 3.1300307396509833e-06,
"loss": 0.0434,
"step": 865
},
{
"epoch": 2.25,
"learning_rate": 3.109675018411108e-06,
"loss": 0.0528,
"step": 866
},
{
"epoch": 2.25,
"learning_rate": 3.089373510131354e-06,
"loss": 0.0438,
"step": 867
},
{
"epoch": 2.25,
"learning_rate": 3.069126374543643e-06,
"loss": 0.0421,
"step": 868
},
{
"epoch": 2.26,
"learning_rate": 3.0489337709520918e-06,
"loss": 0.0479,
"step": 869
},
{
"epoch": 2.26,
"learning_rate": 3.028795858231768e-06,
"loss": 0.0444,
"step": 870
},
{
"epoch": 2.26,
"learning_rate": 3.0087127948274264e-06,
"loss": 0.0417,
"step": 871
},
{
"epoch": 2.26,
"learning_rate": 2.9886847387522675e-06,
"loss": 0.0452,
"step": 872
},
{
"epoch": 2.27,
"learning_rate": 2.9687118475866948e-06,
"loss": 0.0441,
"step": 873
},
{
"epoch": 2.27,
"learning_rate": 2.948794278477083e-06,
"loss": 0.0419,
"step": 874
},
{
"epoch": 2.27,
"learning_rate": 2.9289321881345257e-06,
"loss": 0.0454,
"step": 875
},
{
"epoch": 2.28,
"learning_rate": 2.909125732833612e-06,
"loss": 0.0424,
"step": 876
},
{
"epoch": 2.28,
"learning_rate": 2.8893750684111977e-06,
"loss": 0.0431,
"step": 877
},
{
"epoch": 2.28,
"learning_rate": 2.8696803502651716e-06,
"loss": 0.0415,
"step": 878
},
{
"epoch": 2.28,
"learning_rate": 2.850041733353247e-06,
"loss": 0.043,
"step": 879
},
{
"epoch": 2.29,
"learning_rate": 2.8304593721917283e-06,
"loss": 0.0682,
"step": 880
},
{
"epoch": 2.29,
"learning_rate": 2.8109334208542994e-06,
"loss": 0.0698,
"step": 881
},
{
"epoch": 2.29,
"learning_rate": 2.791464032970812e-06,
"loss": 0.0457,
"step": 882
},
{
"epoch": 2.29,
"learning_rate": 2.7720513617260857e-06,
"loss": 0.042,
"step": 883
},
{
"epoch": 2.3,
"learning_rate": 2.7526955598586856e-06,
"loss": 0.0752,
"step": 884
},
{
"epoch": 2.3,
"learning_rate": 2.7333967796597317e-06,
"loss": 0.0372,
"step": 885
},
{
"epoch": 2.3,
"learning_rate": 2.7141551729716974e-06,
"loss": 0.0466,
"step": 886
},
{
"epoch": 2.3,
"learning_rate": 2.694970891187225e-06,
"loss": 0.0436,
"step": 887
},
{
"epoch": 2.31,
"learning_rate": 2.675844085247913e-06,
"loss": 0.0364,
"step": 888
},
{
"epoch": 2.31,
"learning_rate": 2.656774905643147e-06,
"loss": 0.0385,
"step": 889
},
{
"epoch": 2.31,
"learning_rate": 2.637763502408909e-06,
"loss": 0.0415,
"step": 890
},
{
"epoch": 2.31,
"learning_rate": 2.6188100251265947e-06,
"loss": 0.0411,
"step": 891
},
{
"epoch": 2.32,
"learning_rate": 2.5999146229218473e-06,
"loss": 0.0441,
"step": 892
},
{
"epoch": 2.32,
"learning_rate": 2.581077444463365e-06,
"loss": 0.0396,
"step": 893
},
{
"epoch": 2.32,
"learning_rate": 2.5622986379617556e-06,
"loss": 0.0386,
"step": 894
},
{
"epoch": 2.32,
"learning_rate": 2.5435783511683444e-06,
"loss": 0.0384,
"step": 895
},
{
"epoch": 2.33,
"learning_rate": 2.5249167313740307e-06,
"loss": 0.0365,
"step": 896
},
{
"epoch": 2.33,
"learning_rate": 2.506313925408127e-06,
"loss": 0.0401,
"step": 897
},
{
"epoch": 2.33,
"learning_rate": 2.487770079637193e-06,
"loss": 0.0423,
"step": 898
},
{
"epoch": 2.34,
"learning_rate": 2.469285339963892e-06,
"loss": 0.0464,
"step": 899
},
{
"epoch": 2.34,
"learning_rate": 2.450859851825842e-06,
"loss": 0.0362,
"step": 900
},
{
"epoch": 2.34,
"learning_rate": 2.432493760194469e-06,
"loss": 0.0407,
"step": 901
},
{
"epoch": 2.34,
"learning_rate": 2.4141872095738773e-06,
"loss": 0.0428,
"step": 902
},
{
"epoch": 2.35,
"learning_rate": 2.395940343999691e-06,
"loss": 0.0441,
"step": 903
},
{
"epoch": 2.35,
"learning_rate": 2.377753307037942e-06,
"loss": 0.0462,
"step": 904
},
{
"epoch": 2.35,
"learning_rate": 2.3596262417839256e-06,
"loss": 0.0394,
"step": 905
},
{
"epoch": 2.35,
"learning_rate": 2.3415592908610874e-06,
"loss": 0.0435,
"step": 906
},
{
"epoch": 2.36,
"learning_rate": 2.323552596419889e-06,
"loss": 0.041,
"step": 907
},
{
"epoch": 2.36,
"learning_rate": 2.305606300136698e-06,
"loss": 0.0399,
"step": 908
},
{
"epoch": 2.36,
"learning_rate": 2.287720543212666e-06,
"loss": 0.0386,
"step": 909
},
{
"epoch": 2.36,
"learning_rate": 2.26989546637263e-06,
"loss": 0.0618,
"step": 910
},
{
"epoch": 2.37,
"learning_rate": 2.2521312098639914e-06,
"loss": 0.0386,
"step": 911
},
{
"epoch": 2.37,
"learning_rate": 2.2344279134556157e-06,
"loss": 0.0384,
"step": 912
},
{
"epoch": 2.37,
"learning_rate": 2.2167857164367424e-06,
"loss": 0.0504,
"step": 913
},
{
"epoch": 2.37,
"learning_rate": 2.199204757615875e-06,
"loss": 0.0392,
"step": 914
},
{
"epoch": 2.38,
"learning_rate": 2.1816851753197023e-06,
"loss": 0.0435,
"step": 915
},
{
"epoch": 2.38,
"learning_rate": 2.164227107392002e-06,
"loss": 0.0413,
"step": 916
},
{
"epoch": 2.38,
"learning_rate": 2.146830691192553e-06,
"loss": 0.0327,
"step": 917
},
{
"epoch": 2.38,
"learning_rate": 2.1294960635960617e-06,
"loss": 0.038,
"step": 918
},
{
"epoch": 2.39,
"learning_rate": 2.1122233609910903e-06,
"loss": 0.0447,
"step": 919
},
{
"epoch": 2.39,
"learning_rate": 2.095012719278966e-06,
"loss": 0.0444,
"step": 920
},
{
"epoch": 2.39,
"learning_rate": 2.077864273872727e-06,
"loss": 0.0504,
"step": 921
},
{
"epoch": 2.39,
"learning_rate": 2.060778159696051e-06,
"loss": 0.0424,
"step": 922
},
{
"epoch": 2.4,
"learning_rate": 2.043754511182191e-06,
"loss": 0.0496,
"step": 923
},
{
"epoch": 2.4,
"learning_rate": 2.02679346227293e-06,
"loss": 0.0459,
"step": 924
},
{
"epoch": 2.4,
"learning_rate": 2.009895146417512e-06,
"loss": 0.0442,
"step": 925
},
{
"epoch": 2.41,
"learning_rate": 1.9930596965715985e-06,
"loss": 0.0408,
"step": 926
},
{
"epoch": 2.41,
"learning_rate": 1.9762872451962214e-06,
"loss": 0.0451,
"step": 927
},
{
"epoch": 2.41,
"learning_rate": 1.959577924256745e-06,
"loss": 0.0372,
"step": 928
},
{
"epoch": 2.41,
"learning_rate": 1.9429318652218277e-06,
"loss": 0.0371,
"step": 929
},
{
"epoch": 2.42,
"learning_rate": 1.9263491990623763e-06,
"loss": 0.0487,
"step": 930
},
{
"epoch": 2.42,
"learning_rate": 1.9098300562505266e-06,
"loss": 0.0393,
"step": 931
},
{
"epoch": 2.42,
"learning_rate": 1.8933745667586112e-06,
"loss": 0.05,
"step": 932
},
{
"epoch": 2.42,
"learning_rate": 1.8769828600581497e-06,
"loss": 0.0343,
"step": 933
},
{
"epoch": 2.43,
"learning_rate": 1.8606550651188071e-06,
"loss": 0.0559,
"step": 934
},
{
"epoch": 2.43,
"learning_rate": 1.8443913104073984e-06,
"loss": 0.0516,
"step": 935
},
{
"epoch": 2.43,
"learning_rate": 1.8281917238868707e-06,
"loss": 0.0429,
"step": 936
},
{
"epoch": 2.43,
"learning_rate": 1.8120564330152924e-06,
"loss": 0.0453,
"step": 937
},
{
"epoch": 2.44,
"learning_rate": 1.7959855647448642e-06,
"loss": 0.0381,
"step": 938
},
{
"epoch": 2.44,
"learning_rate": 1.7799792455209019e-06,
"loss": 0.0447,
"step": 939
},
{
"epoch": 2.44,
"learning_rate": 1.7640376012808536e-06,
"loss": 0.0408,
"step": 940
},
{
"epoch": 2.44,
"learning_rate": 1.7481607574533044e-06,
"loss": 0.052,
"step": 941
},
{
"epoch": 2.45,
"learning_rate": 1.7323488389569976e-06,
"loss": 0.0334,
"step": 942
},
{
"epoch": 2.45,
"learning_rate": 1.716601970199836e-06,
"loss": 0.0361,
"step": 943
},
{
"epoch": 2.45,
"learning_rate": 1.7009202750779163e-06,
"loss": 0.048,
"step": 944
},
{
"epoch": 2.45,
"learning_rate": 1.6853038769745466e-06,
"loss": 0.0348,
"step": 945
},
{
"epoch": 2.46,
"learning_rate": 1.6697528987592893e-06,
"loss": 0.0433,
"step": 946
},
{
"epoch": 2.46,
"learning_rate": 1.6542674627869738e-06,
"loss": 0.0484,
"step": 947
},
{
"epoch": 2.46,
"learning_rate": 1.6388476908967477e-06,
"loss": 0.0448,
"step": 948
},
{
"epoch": 2.46,
"learning_rate": 1.6234937044111155e-06,
"loss": 0.0429,
"step": 949
},
{
"epoch": 2.47,
"learning_rate": 1.6082056241349787e-06,
"loss": 0.0312,
"step": 950
},
{
"epoch": 2.47,
"learning_rate": 1.5929835703546992e-06,
"loss": 0.0366,
"step": 951
},
{
"epoch": 2.47,
"learning_rate": 1.577827662837136e-06,
"loss": 0.0373,
"step": 952
},
{
"epoch": 2.48,
"learning_rate": 1.5627380208287114e-06,
"loss": 0.041,
"step": 953
},
{
"epoch": 2.48,
"learning_rate": 1.547714763054472e-06,
"loss": 0.0371,
"step": 954
},
{
"epoch": 2.48,
"learning_rate": 1.5327580077171589e-06,
"loss": 0.0988,
"step": 955
},
{
"epoch": 2.48,
"learning_rate": 1.517867872496267e-06,
"loss": 0.0453,
"step": 956
},
{
"epoch": 2.49,
"learning_rate": 1.5030444745471295e-06,
"loss": 0.1408,
"step": 957
},
{
"epoch": 2.49,
"learning_rate": 1.4882879304999875e-06,
"loss": 0.0583,
"step": 958
},
{
"epoch": 2.49,
"learning_rate": 1.4735983564590784e-06,
"loss": 0.0362,
"step": 959
},
{
"epoch": 2.49,
"learning_rate": 1.4589758680017263e-06,
"loss": 0.0463,
"step": 960
},
{
"epoch": 2.5,
"learning_rate": 1.4444205801774204e-06,
"loss": 0.0529,
"step": 961
},
{
"epoch": 2.5,
"learning_rate": 1.4299326075069175e-06,
"loss": 0.0446,
"step": 962
},
{
"epoch": 2.5,
"learning_rate": 1.4155120639813392e-06,
"loss": 0.0384,
"step": 963
},
{
"epoch": 2.5,
"learning_rate": 1.4011590630612804e-06,
"loss": 0.0421,
"step": 964
},
{
"epoch": 2.51,
"learning_rate": 1.3868737176759105e-06,
"loss": 0.0362,
"step": 965
},
{
"epoch": 2.51,
"learning_rate": 1.3726561402220818e-06,
"loss": 0.036,
"step": 966
},
{
"epoch": 2.51,
"learning_rate": 1.3585064425634542e-06,
"loss": 0.044,
"step": 967
},
{
"epoch": 2.51,
"learning_rate": 1.3444247360296059e-06,
"loss": 0.0465,
"step": 968
},
{
"epoch": 2.52,
"learning_rate": 1.330411131415169e-06,
"loss": 0.044,
"step": 969
},
{
"epoch": 2.52,
"learning_rate": 1.3164657389789459e-06,
"loss": 0.0396,
"step": 970
},
{
"epoch": 2.52,
"learning_rate": 1.3025886684430467e-06,
"loss": 0.0383,
"step": 971
},
{
"epoch": 2.52,
"learning_rate": 1.2887800289920283e-06,
"loss": 0.041,
"step": 972
},
{
"epoch": 2.53,
"learning_rate": 1.2750399292720284e-06,
"loss": 0.0364,
"step": 973
},
{
"epoch": 2.53,
"learning_rate": 1.2613684773899238e-06,
"loss": 0.0476,
"step": 974
},
{
"epoch": 2.53,
"learning_rate": 1.2477657809124632e-06,
"loss": 0.0411,
"step": 975
},
{
"epoch": 2.54,
"learning_rate": 1.2342319468654329e-06,
"loss": 0.0358,
"step": 976
},
{
"epoch": 2.54,
"learning_rate": 1.2207670817328065e-06,
"loss": 0.0374,
"step": 977
},
{
"epoch": 2.54,
"learning_rate": 1.20737129145592e-06,
"loss": 0.0377,
"step": 978
},
{
"epoch": 2.54,
"learning_rate": 1.19404468143262e-06,
"loss": 0.0355,
"step": 979
},
{
"epoch": 2.55,
"learning_rate": 1.1807873565164507e-06,
"loss": 0.0359,
"step": 980
},
{
"epoch": 2.55,
"learning_rate": 1.167599421015818e-06,
"loss": 0.0463,
"step": 981
},
{
"epoch": 2.55,
"learning_rate": 1.1544809786931732e-06,
"loss": 0.0377,
"step": 982
},
{
"epoch": 2.55,
"learning_rate": 1.1414321327642019e-06,
"loss": 0.0456,
"step": 983
},
{
"epoch": 2.56,
"learning_rate": 1.1284529858970016e-06,
"loss": 0.0341,
"step": 984
},
{
"epoch": 2.56,
"learning_rate": 1.1155436402112785e-06,
"loss": 0.0351,
"step": 985
},
{
"epoch": 2.56,
"learning_rate": 1.1027041972775442e-06,
"loss": 0.0371,
"step": 986
},
{
"epoch": 2.56,
"learning_rate": 1.0899347581163222e-06,
"loss": 0.0417,
"step": 987
},
{
"epoch": 2.57,
"learning_rate": 1.0772354231973404e-06,
"loss": 0.0342,
"step": 988
},
{
"epoch": 2.57,
"learning_rate": 1.0646062924387513e-06,
"loss": 0.036,
"step": 989
},
{
"epoch": 2.57,
"learning_rate": 1.0520474652063395e-06,
"loss": 0.0349,
"step": 990
},
{
"epoch": 2.57,
"learning_rate": 1.0395590403127487e-06,
"loss": 0.0415,
"step": 991
},
{
"epoch": 2.58,
"learning_rate": 1.0271411160166922e-06,
"loss": 0.0375,
"step": 992
},
{
"epoch": 2.58,
"learning_rate": 1.0147937900221882e-06,
"loss": 0.0421,
"step": 993
},
{
"epoch": 2.58,
"learning_rate": 1.0025171594777872e-06,
"loss": 0.0428,
"step": 994
},
{
"epoch": 2.58,
"learning_rate": 9.903113209758098e-07,
"loss": 0.0424,
"step": 995
},
{
"epoch": 2.59,
"learning_rate": 9.78176370551588e-07,
"loss": 0.0363,
"step": 996
},
{
"epoch": 2.59,
"learning_rate": 9.661124036827064e-07,
"loss": 0.0447,
"step": 997
},
{
"epoch": 2.59,
"learning_rate": 9.541195152882477e-07,
"loss": 0.0372,
"step": 998
},
{
"epoch": 2.59,
"learning_rate": 9.421977997280596e-07,
"loss": 0.0342,
"step": 999
},
{
"epoch": 2.6,
"learning_rate": 9.303473508019944e-07,
"loss": 0.0327,
"step": 1000
},
{
"epoch": 2.6,
"learning_rate": 9.185682617491865e-07,
"loss": 0.0319,
"step": 1001
},
{
"epoch": 2.6,
"learning_rate": 9.068606252473067e-07,
"loss": 0.0338,
"step": 1002
},
{
"epoch": 2.61,
"learning_rate": 8.952245334118415e-07,
"loss": 0.0483,
"step": 1003
},
{
"epoch": 2.61,
"learning_rate": 8.83660077795363e-07,
"loss": 0.0386,
"step": 1004
},
{
"epoch": 2.61,
"learning_rate": 8.721673493868111e-07,
"loss": 0.0404,
"step": 1005
},
{
"epoch": 2.61,
"learning_rate": 8.6074643861078e-07,
"loss": 0.0336,
"step": 1006
},
{
"epoch": 2.62,
"learning_rate": 8.493974353268019e-07,
"loss": 0.0353,
"step": 1007
},
{
"epoch": 2.62,
"learning_rate": 8.381204288286415e-07,
"loss": 0.038,
"step": 1008
},
{
"epoch": 2.62,
"learning_rate": 8.26915507843593e-07,
"loss": 0.0389,
"step": 1009
},
{
"epoch": 2.62,
"learning_rate": 8.157827605317892e-07,
"loss": 0.0436,
"step": 1010
},
{
"epoch": 2.63,
"learning_rate": 8.047222744854943e-07,
"loss": 0.0442,
"step": 1011
},
{
"epoch": 2.63,
"learning_rate": 7.937341367284246e-07,
"loss": 0.0358,
"step": 1012
},
{
"epoch": 2.63,
"learning_rate": 7.828184337150613e-07,
"loss": 0.0434,
"step": 1013
},
{
"epoch": 2.63,
"learning_rate": 7.719752513299728e-07,
"loss": 0.0309,
"step": 1014
},
{
"epoch": 2.64,
"learning_rate": 7.612046748871327e-07,
"loss": 0.0381,
"step": 1015
},
{
"epoch": 2.64,
"learning_rate": 7.50506789129255e-07,
"loss": 0.049,
"step": 1016
},
{
"epoch": 2.64,
"learning_rate": 7.398816782271223e-07,
"loss": 0.0393,
"step": 1017
},
{
"epoch": 2.64,
"learning_rate": 7.293294257789252e-07,
"loss": 0.0337,
"step": 1018
},
{
"epoch": 2.65,
"learning_rate": 7.188501148096117e-07,
"loss": 0.033,
"step": 1019
},
{
"epoch": 2.65,
"learning_rate": 7.084438277702188e-07,
"loss": 0.0383,
"step": 1020
},
{
"epoch": 2.65,
"learning_rate": 6.981106465372389e-07,
"loss": 0.0363,
"step": 1021
},
{
"epoch": 2.65,
"learning_rate": 6.878506524119644e-07,
"loss": 0.0276,
"step": 1022
},
{
"epoch": 2.66,
"learning_rate": 6.776639261198581e-07,
"loss": 0.0339,
"step": 1023
},
{
"epoch": 2.66,
"learning_rate": 6.675505478099075e-07,
"loss": 0.0322,
"step": 1024
},
{
"epoch": 2.66,
"learning_rate": 6.57510597054003e-07,
"loss": 0.0413,
"step": 1025
},
{
"epoch": 2.66,
"learning_rate": 6.475441528463033e-07,
"loss": 0.0291,
"step": 1026
},
{
"epoch": 2.67,
"learning_rate": 6.37651293602628e-07,
"loss": 0.0495,
"step": 1027
},
{
"epoch": 2.67,
"learning_rate": 6.278320971598228e-07,
"loss": 0.0446,
"step": 1028
},
{
"epoch": 2.67,
"learning_rate": 6.180866407751595e-07,
"loss": 0.0318,
"step": 1029
},
{
"epoch": 2.68,
"learning_rate": 6.084150011257239e-07,
"loss": 0.0337,
"step": 1030
},
{
"epoch": 2.68,
"learning_rate": 5.988172543078097e-07,
"loss": 0.045,
"step": 1031
},
{
"epoch": 2.68,
"learning_rate": 5.892934758363311e-07,
"loss": 0.0348,
"step": 1032
},
{
"epoch": 2.68,
"learning_rate": 5.798437406442104e-07,
"loss": 0.0452,
"step": 1033
},
{
"epoch": 2.69,
"learning_rate": 5.704681230818087e-07,
"loss": 0.034,
"step": 1034
},
{
"epoch": 2.69,
"learning_rate": 5.611666969163243e-07,
"loss": 0.0443,
"step": 1035
},
{
"epoch": 2.69,
"learning_rate": 5.519395353312195e-07,
"loss": 0.0299,
"step": 1036
},
{
"epoch": 2.69,
"learning_rate": 5.427867109256457e-07,
"loss": 0.0361,
"step": 1037
},
{
"epoch": 2.7,
"learning_rate": 5.337082957138717e-07,
"loss": 0.0403,
"step": 1038
},
{
"epoch": 2.7,
"learning_rate": 5.247043611247127e-07,
"loss": 0.0339,
"step": 1039
},
{
"epoch": 2.7,
"learning_rate": 5.157749780009735e-07,
"loss": 0.0381,
"step": 1040
},
{
"epoch": 2.7,
"learning_rate": 5.069202165988874e-07,
"loss": 0.0397,
"step": 1041
},
{
"epoch": 2.71,
"learning_rate": 4.981401465875713e-07,
"loss": 0.0325,
"step": 1042
},
{
"epoch": 2.71,
"learning_rate": 4.894348370484648e-07,
"loss": 0.0404,
"step": 1043
},
{
"epoch": 2.71,
"learning_rate": 4.808043564747955e-07,
"loss": 0.0417,
"step": 1044
},
{
"epoch": 2.71,
"learning_rate": 4.7224877277103673e-07,
"loss": 0.0337,
"step": 1045
},
{
"epoch": 2.72,
"learning_rate": 4.6376815325237966e-07,
"loss": 0.0407,
"step": 1046
},
{
"epoch": 2.72,
"learning_rate": 4.553625646441928e-07,
"loss": 0.0472,
"step": 1047
},
{
"epoch": 2.72,
"learning_rate": 4.4703207308150474e-07,
"loss": 0.0365,
"step": 1048
},
{
"epoch": 2.72,
"learning_rate": 4.3877674410848005e-07,
"loss": 0.0367,
"step": 1049
},
{
"epoch": 2.73,
"learning_rate": 4.305966426779118e-07,
"loss": 0.0359,
"step": 1050
},
{
"epoch": 2.73,
"learning_rate": 4.224918331506955e-07,
"loss": 0.0385,
"step": 1051
},
{
"epoch": 2.73,
"learning_rate": 4.1446237929533616e-07,
"loss": 0.0436,
"step": 1052
},
{
"epoch": 2.74,
"learning_rate": 4.065083442874418e-07,
"loss": 0.0341,
"step": 1053
},
{
"epoch": 2.74,
"learning_rate": 3.986297907092218e-07,
"loss": 0.0371,
"step": 1054
},
{
"epoch": 2.74,
"learning_rate": 3.908267805490051e-07,
"loss": 0.04,
"step": 1055
},
{
"epoch": 2.74,
"learning_rate": 3.8309937520074283e-07,
"loss": 0.0427,
"step": 1056
},
{
"epoch": 2.75,
"learning_rate": 3.7544763546352834e-07,
"loss": 0.0472,
"step": 1057
},
{
"epoch": 2.75,
"learning_rate": 3.6787162154111935e-07,
"loss": 0.0369,
"step": 1058
},
{
"epoch": 2.75,
"learning_rate": 3.603713930414676e-07,
"loss": 0.0391,
"step": 1059
},
{
"epoch": 2.75,
"learning_rate": 3.529470089762421e-07,
"loss": 0.0357,
"step": 1060
},
{
"epoch": 2.76,
"learning_rate": 3.455985277603713e-07,
"loss": 0.0416,
"step": 1061
},
{
"epoch": 2.76,
"learning_rate": 3.3832600721158016e-07,
"loss": 0.0443,
"step": 1062
},
{
"epoch": 2.76,
"learning_rate": 3.3112950454993633e-07,
"loss": 0.0365,
"step": 1063
},
{
"epoch": 2.76,
"learning_rate": 3.2400907639740243e-07,
"loss": 0.0478,
"step": 1064
},
{
"epoch": 2.77,
"learning_rate": 3.1696477877738664e-07,
"loss": 0.1376,
"step": 1065
},
{
"epoch": 2.77,
"learning_rate": 3.099966671143018e-07,
"loss": 0.0508,
"step": 1066
},
{
"epoch": 2.77,
"learning_rate": 3.0310479623313125e-07,
"loss": 0.0418,
"step": 1067
},
{
"epoch": 2.77,
"learning_rate": 2.9628922035900067e-07,
"loss": 0.0499,
"step": 1068
},
{
"epoch": 2.78,
"learning_rate": 2.8954999311674557e-07,
"loss": 0.0682,
"step": 1069
},
{
"epoch": 2.78,
"learning_rate": 2.8288716753049007e-07,
"loss": 0.0489,
"step": 1070
},
{
"epoch": 2.78,
"learning_rate": 2.7630079602323447e-07,
"loss": 0.0474,
"step": 1071
},
{
"epoch": 2.78,
"learning_rate": 2.6979093041643477e-07,
"loss": 0.0933,
"step": 1072
},
{
"epoch": 2.79,
"learning_rate": 2.6335762192960743e-07,
"loss": 0.0648,
"step": 1073
},
{
"epoch": 2.79,
"learning_rate": 2.570009211799129e-07,
"loss": 0.0409,
"step": 1074
},
{
"epoch": 2.79,
"learning_rate": 2.507208781817638e-07,
"loss": 0.055,
"step": 1075
},
{
"epoch": 2.79,
"learning_rate": 2.445175423464341e-07,
"loss": 0.0383,
"step": 1076
},
{
"epoch": 2.8,
"learning_rate": 2.383909624816616e-07,
"loss": 0.0619,
"step": 1077
},
{
"epoch": 2.8,
"learning_rate": 2.3234118679127615e-07,
"loss": 0.4593,
"step": 1078
},
{
"epoch": 2.8,
"learning_rate": 2.2636826287480872e-07,
"loss": 0.1119,
"step": 1079
},
{
"epoch": 2.81,
"learning_rate": 2.20472237727124e-07,
"loss": 0.0578,
"step": 1080
},
{
"epoch": 2.81,
"learning_rate": 2.1465315773804617e-07,
"loss": 0.2489,
"step": 1081
},
{
"epoch": 2.81,
"learning_rate": 2.089110686920004e-07,
"loss": 0.0698,
"step": 1082
},
{
"epoch": 2.81,
"learning_rate": 2.0324601576764525e-07,
"loss": 0.0561,
"step": 1083
},
{
"epoch": 2.82,
"learning_rate": 1.9765804353751973e-07,
"loss": 0.0573,
"step": 1084
},
{
"epoch": 2.82,
"learning_rate": 1.921471959676957e-07,
"loss": 0.052,
"step": 1085
},
{
"epoch": 2.82,
"learning_rate": 1.867135164174283e-07,
"loss": 0.0649,
"step": 1086
},
{
"epoch": 2.82,
"learning_rate": 1.81357047638816e-07,
"loss": 0.0441,
"step": 1087
},
{
"epoch": 2.83,
"learning_rate": 1.7607783177646443e-07,
"loss": 0.0518,
"step": 1088
},
{
"epoch": 2.83,
"learning_rate": 1.7087591036715534e-07,
"loss": 0.0501,
"step": 1089
},
{
"epoch": 2.83,
"learning_rate": 1.657513243395159e-07,
"loss": 0.0509,
"step": 1090
},
{
"epoch": 2.83,
"learning_rate": 1.6070411401370335e-07,
"loss": 0.0626,
"step": 1091
},
{
"epoch": 2.84,
"learning_rate": 1.5573431910108404e-07,
"loss": 0.0485,
"step": 1092
},
{
"epoch": 2.84,
"learning_rate": 1.5084197870391836e-07,
"loss": 0.0781,
"step": 1093
},
{
"epoch": 2.84,
"learning_rate": 1.4602713131505852e-07,
"loss": 0.0524,
"step": 1094
},
{
"epoch": 2.84,
"learning_rate": 1.4128981481764115e-07,
"loss": 0.0949,
"step": 1095
},
{
"epoch": 2.85,
"learning_rate": 1.3663006648479415e-07,
"loss": 0.0602,
"step": 1096
},
{
"epoch": 2.85,
"learning_rate": 1.320479229793359e-07,
"loss": 0.0467,
"step": 1097
},
{
"epoch": 2.85,
"learning_rate": 1.2754342035349642e-07,
"loss": 0.063,
"step": 1098
},
{
"epoch": 2.85,
"learning_rate": 1.231165940486234e-07,
"loss": 0.0439,
"step": 1099
},
{
"epoch": 2.86,
"learning_rate": 1.1876747889491225e-07,
"loss": 0.0528,
"step": 1100
},
{
"epoch": 2.86,
"learning_rate": 1.1449610911112741e-07,
"loss": 0.0482,
"step": 1101
},
{
"epoch": 2.86,
"learning_rate": 1.1030251830433492e-07,
"loss": 0.3036,
"step": 1102
},
{
"epoch": 2.86,
"learning_rate": 1.0618673946963365e-07,
"loss": 0.0479,
"step": 1103
},
{
"epoch": 2.87,
"learning_rate": 1.0214880498990332e-07,
"loss": 0.0537,
"step": 1104
},
{
"epoch": 2.87,
"learning_rate": 9.818874663554356e-08,
"loss": 0.0623,
"step": 1105
},
{
"epoch": 2.87,
"learning_rate": 9.43065955642275e-08,
"loss": 0.0573,
"step": 1106
},
{
"epoch": 2.88,
"learning_rate": 9.0502382320653e-08,
"loss": 0.0578,
"step": 1107
},
{
"epoch": 2.88,
"learning_rate": 8.677613683630404e-08,
"loss": 0.0486,
"step": 1108
},
{
"epoch": 2.88,
"learning_rate": 8.31278884292186e-08,
"loss": 0.0521,
"step": 1109
},
{
"epoch": 2.88,
"learning_rate": 7.955766580375334e-08,
"loss": 0.0477,
"step": 1110
},
{
"epoch": 2.89,
"learning_rate": 7.606549705035937e-08,
"loss": 0.0447,
"step": 1111
},
{
"epoch": 2.89,
"learning_rate": 7.26514096453601e-08,
"loss": 0.0627,
"step": 1112
},
{
"epoch": 2.89,
"learning_rate": 6.931543045073708e-08,
"loss": 0.051,
"step": 1113
},
{
"epoch": 2.89,
"learning_rate": 6.605758571392006e-08,
"loss": 0.0584,
"step": 1114
},
{
"epoch": 2.9,
"learning_rate": 6.287790106757396e-08,
"loss": 0.0513,
"step": 1115
},
{
"epoch": 2.9,
"learning_rate": 5.977640152940556e-08,
"loss": 0.0571,
"step": 1116
},
{
"epoch": 2.9,
"learning_rate": 5.675311150195928e-08,
"loss": 0.0686,
"step": 1117
},
{
"epoch": 2.9,
"learning_rate": 5.380805477243067e-08,
"loss": 0.0672,
"step": 1118
},
{
"epoch": 2.91,
"learning_rate": 5.094125451247656e-08,
"loss": 0.0488,
"step": 1119
},
{
"epoch": 2.91,
"learning_rate": 4.815273327803183e-08,
"loss": 0.0446,
"step": 1120
},
{
"epoch": 2.91,
"learning_rate": 4.544251300913405e-08,
"loss": 0.0419,
"step": 1121
},
{
"epoch": 2.91,
"learning_rate": 4.281061502975026e-08,
"loss": 0.0523,
"step": 1122
},
{
"epoch": 2.92,
"learning_rate": 4.025706004760932e-08,
"loss": 0.0547,
"step": 1123
},
{
"epoch": 2.92,
"learning_rate": 3.7781868154039835e-08,
"loss": 0.0551,
"step": 1124
},
{
"epoch": 2.92,
"learning_rate": 3.538505882380916e-08,
"loss": 0.0556,
"step": 1125
},
{
"epoch": 2.92,
"learning_rate": 3.3066650914970186e-08,
"loss": 0.0671,
"step": 1126
},
{
"epoch": 2.93,
"learning_rate": 3.082666266872036e-08,
"loss": 0.0535,
"step": 1127
},
{
"epoch": 2.93,
"learning_rate": 2.866511170924735e-08,
"loss": 0.0597,
"step": 1128
},
{
"epoch": 2.93,
"learning_rate": 2.658201504359803e-08,
"loss": 0.0759,
"step": 1129
},
{
"epoch": 2.94,
"learning_rate": 2.4577389061539724e-08,
"loss": 0.062,
"step": 1130
},
{
"epoch": 2.94,
"learning_rate": 2.265124953543918e-08,
"loss": 0.0722,
"step": 1131
},
{
"epoch": 2.94,
"learning_rate": 2.0803611620127118e-08,
"loss": 0.0771,
"step": 1132
},
{
"epoch": 2.94,
"learning_rate": 1.903448985278722e-08,
"loss": 0.0735,
"step": 1133
},
{
"epoch": 2.95,
"learning_rate": 1.7343898152841765e-08,
"loss": 0.0555,
"step": 1134
},
{
"epoch": 2.95,
"learning_rate": 1.5731849821833955e-08,
"loss": 0.0656,
"step": 1135
},
{
"epoch": 2.95,
"learning_rate": 1.4198357543336871e-08,
"loss": 0.0584,
"step": 1136
},
{
"epoch": 2.95,
"learning_rate": 1.274343338283801e-08,
"loss": 0.0649,
"step": 1137
},
{
"epoch": 2.96,
"learning_rate": 1.1367088787658242e-08,
"loss": 0.0595,
"step": 1138
},
{
"epoch": 2.96,
"learning_rate": 1.0069334586854106e-08,
"loss": 0.0726,
"step": 1139
},
{
"epoch": 2.96,
"learning_rate": 8.850180991131219e-09,
"loss": 0.0648,
"step": 1140
},
{
"epoch": 2.96,
"learning_rate": 7.70963759277099e-09,
"loss": 0.0712,
"step": 1141
},
{
"epoch": 2.97,
"learning_rate": 6.647713365548481e-09,
"loss": 0.0536,
"step": 1142
},
{
"epoch": 2.97,
"learning_rate": 5.664416664666883e-09,
"loss": 0.0797,
"step": 1143
},
{
"epoch": 2.97,
"learning_rate": 4.75975522668759e-09,
"loss": 0.0591,
"step": 1144
},
{
"epoch": 2.97,
"learning_rate": 3.933736169471347e-09,
"loss": 0.0582,
"step": 1145
},
{
"epoch": 2.98,
"learning_rate": 3.1863659921216316e-09,
"loss": 0.0663,
"step": 1146
},
{
"epoch": 2.98,
"learning_rate": 2.5176505749346937e-09,
"loss": 0.0716,
"step": 1147
},
{
"epoch": 2.98,
"learning_rate": 1.9275951793518154e-09,
"loss": 0.0702,
"step": 1148
},
{
"epoch": 2.98,
"learning_rate": 1.4162044479182347e-09,
"loss": 0.0806,
"step": 1149
},
{
"epoch": 2.99,
"learning_rate": 9.83482404249836e-10,
"loss": 0.0642,
"step": 1150
},
{
"epoch": 2.99,
"learning_rate": 6.294324529942942e-10,
"loss": 0.0796,
"step": 1151
},
{
"epoch": 2.99,
"learning_rate": 3.5405737981109023e-10,
"loss": 0.0752,
"step": 1152
},
{
"epoch": 2.99,
"learning_rate": 1.5735935134708613e-10,
"loss": 0.0704,
"step": 1153
},
{
"epoch": 3.0,
"learning_rate": 3.933991521765101e-11,
"loss": 0.0883,
"step": 1154
},
{
"epoch": 3.0,
"learning_rate": 0.0,
"loss": 0.0724,
"step": 1155
},
{
"epoch": 3.0,
"step": 1155,
"total_flos": 1.644468745839575e+18,
"train_loss": 0.2576451237825475,
"train_runtime": 11338.5773,
"train_samples_per_second": 13.03,
"train_steps_per_second": 0.102
}
],
"logging_steps": 1.0,
"max_steps": 1155,
"num_train_epochs": 3,
"save_steps": 10000,
"total_flos": 1.644468745839575e+18,
"trial_name": null,
"trial_params": null
}