8bit-coder's picture
lets put an actual model on here (#4)
4634358
raw
history blame
51 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.995319812792512,
"global_step": 420,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.0,
"loss": 1.4861,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 0.0,
"loss": 1.4901,
"step": 2
},
{
"epoch": 0.02,
"learning_rate": 1.5384615384615387e-06,
"loss": 1.4646,
"step": 3
},
{
"epoch": 0.03,
"learning_rate": 3.0769230769230774e-06,
"loss": 1.44,
"step": 4
},
{
"epoch": 0.04,
"learning_rate": 4.615384615384616e-06,
"loss": 1.4355,
"step": 5
},
{
"epoch": 0.04,
"learning_rate": 6.153846153846155e-06,
"loss": 1.1764,
"step": 6
},
{
"epoch": 0.05,
"learning_rate": 7.692307692307694e-06,
"loss": 1.0584,
"step": 7
},
{
"epoch": 0.06,
"learning_rate": 9.230769230769232e-06,
"loss": 1.0187,
"step": 8
},
{
"epoch": 0.06,
"learning_rate": 1.076923076923077e-05,
"loss": 1.0039,
"step": 9
},
{
"epoch": 0.07,
"learning_rate": 1.230769230769231e-05,
"loss": 0.9911,
"step": 10
},
{
"epoch": 0.08,
"learning_rate": 1.3846153846153847e-05,
"loss": 0.972,
"step": 11
},
{
"epoch": 0.09,
"learning_rate": 1.5384615384615387e-05,
"loss": 0.9573,
"step": 12
},
{
"epoch": 0.09,
"learning_rate": 1.6923076923076924e-05,
"loss": 0.9277,
"step": 13
},
{
"epoch": 0.1,
"learning_rate": 1.8461538461538465e-05,
"loss": 0.8686,
"step": 14
},
{
"epoch": 0.11,
"learning_rate": 2e-05,
"loss": 0.9066,
"step": 15
},
{
"epoch": 0.11,
"learning_rate": 1.9999702094326033e-05,
"loss": 0.9442,
"step": 16
},
{
"epoch": 0.12,
"learning_rate": 1.9998808395053687e-05,
"loss": 0.8849,
"step": 17
},
{
"epoch": 0.13,
"learning_rate": 1.999731895543058e-05,
"loss": 0.8767,
"step": 18
},
{
"epoch": 0.14,
"learning_rate": 1.9995233864199213e-05,
"loss": 0.9332,
"step": 19
},
{
"epoch": 0.14,
"learning_rate": 1.9992553245591694e-05,
"loss": 0.9058,
"step": 20
},
{
"epoch": 0.15,
"learning_rate": 1.9989277259322314e-05,
"loss": 0.9563,
"step": 21
},
{
"epoch": 0.16,
"learning_rate": 1.998540610057806e-05,
"loss": 0.9188,
"step": 22
},
{
"epoch": 0.16,
"learning_rate": 1.9980940000006956e-05,
"loss": 0.9445,
"step": 23
},
{
"epoch": 0.17,
"learning_rate": 1.997587922370434e-05,
"loss": 0.8958,
"step": 24
},
{
"epoch": 0.18,
"learning_rate": 1.997022407319702e-05,
"loss": 0.8969,
"step": 25
},
{
"epoch": 0.19,
"learning_rate": 1.9963974885425267e-05,
"loss": 0.9201,
"step": 26
},
{
"epoch": 0.19,
"learning_rate": 1.9957132032722787e-05,
"loss": 0.8686,
"step": 27
},
{
"epoch": 0.2,
"learning_rate": 1.9949695922794508e-05,
"loss": 0.8845,
"step": 28
},
{
"epoch": 0.21,
"learning_rate": 1.99416669986923e-05,
"loss": 0.9125,
"step": 29
},
{
"epoch": 0.21,
"learning_rate": 1.9933045738788564e-05,
"loss": 0.9097,
"step": 30
},
{
"epoch": 0.22,
"learning_rate": 1.992383265674776e-05,
"loss": 0.886,
"step": 31
},
{
"epoch": 0.23,
"learning_rate": 1.991402830149576e-05,
"loss": 0.9274,
"step": 32
},
{
"epoch": 0.24,
"learning_rate": 1.9903633257187186e-05,
"loss": 0.9153,
"step": 33
},
{
"epoch": 0.24,
"learning_rate": 1.9892648143170565e-05,
"loss": 0.9458,
"step": 34
},
{
"epoch": 0.25,
"learning_rate": 1.9881073613951464e-05,
"loss": 0.9064,
"step": 35
},
{
"epoch": 0.26,
"learning_rate": 1.986891035915346e-05,
"loss": 0.8758,
"step": 36
},
{
"epoch": 0.26,
"learning_rate": 1.9856159103477085e-05,
"loss": 0.8764,
"step": 37
},
{
"epoch": 0.27,
"learning_rate": 1.984282060665662e-05,
"loss": 0.9475,
"step": 38
},
{
"epoch": 0.28,
"learning_rate": 1.9828895663414838e-05,
"loss": 0.883,
"step": 39
},
{
"epoch": 0.29,
"learning_rate": 1.9814385103415662e-05,
"loss": 0.8835,
"step": 40
},
{
"epoch": 0.29,
"learning_rate": 1.9799289791214725e-05,
"loss": 0.8706,
"step": 41
},
{
"epoch": 0.3,
"learning_rate": 1.9783610626207855e-05,
"loss": 0.923,
"step": 42
},
{
"epoch": 0.31,
"learning_rate": 1.9767348542577496e-05,
"loss": 0.8666,
"step": 43
},
{
"epoch": 0.31,
"learning_rate": 1.9750504509237046e-05,
"loss": 0.882,
"step": 44
},
{
"epoch": 0.32,
"learning_rate": 1.9733079529773123e-05,
"loss": 0.8919,
"step": 45
},
{
"epoch": 0.33,
"learning_rate": 1.9715074642385785e-05,
"loss": 0.911,
"step": 46
},
{
"epoch": 0.34,
"learning_rate": 1.9696490919826647e-05,
"loss": 0.9278,
"step": 47
},
{
"epoch": 0.34,
"learning_rate": 1.967732946933499e-05,
"loss": 0.8796,
"step": 48
},
{
"epoch": 0.35,
"learning_rate": 1.965759143257178e-05,
"loss": 0.9192,
"step": 49
},
{
"epoch": 0.36,
"learning_rate": 1.9637277985551643e-05,
"loss": 0.8925,
"step": 50
},
{
"epoch": 0.36,
"learning_rate": 1.9616390338572805e-05,
"loss": 0.9026,
"step": 51
},
{
"epoch": 0.37,
"learning_rate": 1.9594929736144978e-05,
"loss": 0.8203,
"step": 52
},
{
"epoch": 0.38,
"learning_rate": 1.95728974569152e-05,
"loss": 0.8867,
"step": 53
},
{
"epoch": 0.39,
"learning_rate": 1.9550294813591685e-05,
"loss": 0.8783,
"step": 54
},
{
"epoch": 0.39,
"learning_rate": 1.9527123152865562e-05,
"loss": 0.897,
"step": 55
},
{
"epoch": 0.4,
"learning_rate": 1.950338385533067e-05,
"loss": 0.8365,
"step": 56
},
{
"epoch": 0.41,
"learning_rate": 1.9479078335401297e-05,
"loss": 0.8951,
"step": 57
},
{
"epoch": 0.41,
"learning_rate": 1.9454208041227905e-05,
"loss": 0.8633,
"step": 58
},
{
"epoch": 0.42,
"learning_rate": 1.9428774454610845e-05,
"loss": 0.9022,
"step": 59
},
{
"epoch": 0.43,
"learning_rate": 1.940277909091206e-05,
"loss": 0.885,
"step": 60
},
{
"epoch": 0.44,
"learning_rate": 1.937622349896483e-05,
"loss": 0.8765,
"step": 61
},
{
"epoch": 0.44,
"learning_rate": 1.9349109260981455e-05,
"loss": 0.8465,
"step": 62
},
{
"epoch": 0.45,
"learning_rate": 1.9321437992458996e-05,
"loss": 0.8642,
"step": 63
},
{
"epoch": 0.46,
"learning_rate": 1.929321134208304e-05,
"loss": 0.8872,
"step": 64
},
{
"epoch": 0.46,
"learning_rate": 1.9264430991629447e-05,
"loss": 0.9043,
"step": 65
},
{
"epoch": 0.47,
"learning_rate": 1.9235098655864156e-05,
"loss": 0.9398,
"step": 66
},
{
"epoch": 0.48,
"learning_rate": 1.920521608244102e-05,
"loss": 0.9099,
"step": 67
},
{
"epoch": 0.48,
"learning_rate": 1.9174785051797668e-05,
"loss": 0.8736,
"step": 68
},
{
"epoch": 0.49,
"learning_rate": 1.9143807377049443e-05,
"loss": 0.7984,
"step": 69
},
{
"epoch": 0.5,
"learning_rate": 1.911228490388136e-05,
"loss": 0.8401,
"step": 70
},
{
"epoch": 0.51,
"learning_rate": 1.9080219510438137e-05,
"loss": 0.8782,
"step": 71
},
{
"epoch": 0.51,
"learning_rate": 1.9047613107212314e-05,
"loss": 0.8569,
"step": 72
},
{
"epoch": 0.52,
"learning_rate": 1.9014467636930387e-05,
"loss": 0.8467,
"step": 73
},
{
"epoch": 0.53,
"learning_rate": 1.8980785074437095e-05,
"loss": 0.8492,
"step": 74
},
{
"epoch": 0.53,
"learning_rate": 1.8946567426577724e-05,
"loss": 0.8786,
"step": 75
},
{
"epoch": 0.54,
"learning_rate": 1.8911816732078577e-05,
"loss": 0.8782,
"step": 76
},
{
"epoch": 0.55,
"learning_rate": 1.8876535061425454e-05,
"loss": 0.8979,
"step": 77
},
{
"epoch": 0.56,
"learning_rate": 1.884072451674034e-05,
"loss": 0.906,
"step": 78
},
{
"epoch": 0.56,
"learning_rate": 1.880438723165612e-05,
"loss": 0.9005,
"step": 79
},
{
"epoch": 0.57,
"learning_rate": 1.8767525371189473e-05,
"loss": 0.828,
"step": 80
},
{
"epoch": 0.58,
"learning_rate": 1.8730141131611882e-05,
"loss": 0.8725,
"step": 81
},
{
"epoch": 0.58,
"learning_rate": 1.869223674031876e-05,
"loss": 0.8478,
"step": 82
},
{
"epoch": 0.59,
"learning_rate": 1.865381445569676e-05,
"loss": 0.8932,
"step": 83
},
{
"epoch": 0.6,
"learning_rate": 1.861487656698919e-05,
"loss": 0.8847,
"step": 84
},
{
"epoch": 0.61,
"learning_rate": 1.8575425394159653e-05,
"loss": 0.9109,
"step": 85
},
{
"epoch": 0.61,
"learning_rate": 1.8535463287753797e-05,
"loss": 0.8571,
"step": 86
},
{
"epoch": 0.62,
"learning_rate": 1.849499262875927e-05,
"loss": 0.8681,
"step": 87
},
{
"epoch": 0.63,
"learning_rate": 1.845401582846385e-05,
"loss": 0.8969,
"step": 88
},
{
"epoch": 0.63,
"learning_rate": 1.8412535328311813e-05,
"loss": 0.8889,
"step": 89
},
{
"epoch": 0.64,
"learning_rate": 1.8370553599758424e-05,
"loss": 0.8971,
"step": 90
},
{
"epoch": 0.65,
"learning_rate": 1.8328073144122708e-05,
"loss": 0.8818,
"step": 91
},
{
"epoch": 0.66,
"learning_rate": 1.8285096492438424e-05,
"loss": 0.8723,
"step": 92
},
{
"epoch": 0.66,
"learning_rate": 1.8241626205303245e-05,
"loss": 0.8822,
"step": 93
},
{
"epoch": 0.67,
"learning_rate": 1.8197664872726206e-05,
"loss": 0.852,
"step": 94
},
{
"epoch": 0.68,
"learning_rate": 1.8153215113973398e-05,
"loss": 0.8946,
"step": 95
},
{
"epoch": 0.68,
"learning_rate": 1.810827957741188e-05,
"loss": 0.8812,
"step": 96
},
{
"epoch": 0.69,
"learning_rate": 1.8062860940351916e-05,
"loss": 0.8572,
"step": 97
},
{
"epoch": 0.7,
"learning_rate": 1.8016961908887444e-05,
"loss": 0.8703,
"step": 98
},
{
"epoch": 0.71,
"learning_rate": 1.7970585217734843e-05,
"loss": 0.8565,
"step": 99
},
{
"epoch": 0.71,
"learning_rate": 1.792373363007e-05,
"loss": 0.8724,
"step": 100
},
{
"epoch": 0.72,
"learning_rate": 1.7876409937363677e-05,
"loss": 0.8421,
"step": 101
},
{
"epoch": 0.73,
"learning_rate": 1.7828616959215185e-05,
"loss": 0.8504,
"step": 102
},
{
"epoch": 0.73,
"learning_rate": 1.7780357543184396e-05,
"loss": 0.8842,
"step": 103
},
{
"epoch": 0.74,
"learning_rate": 1.7731634564622087e-05,
"loss": 0.8467,
"step": 104
},
{
"epoch": 0.75,
"learning_rate": 1.768245092649861e-05,
"loss": 0.893,
"step": 105
},
{
"epoch": 0.76,
"learning_rate": 1.763280955923093e-05,
"loss": 0.8401,
"step": 106
},
{
"epoch": 0.76,
"learning_rate": 1.7582713420508052e-05,
"loss": 0.8824,
"step": 107
},
{
"epoch": 0.77,
"learning_rate": 1.7532165495114765e-05,
"loss": 0.8969,
"step": 108
},
{
"epoch": 0.78,
"learning_rate": 1.748116879475383e-05,
"loss": 0.8517,
"step": 109
},
{
"epoch": 0.78,
"learning_rate": 1.7429726357866516e-05,
"loss": 0.9263,
"step": 110
},
{
"epoch": 0.79,
"learning_rate": 1.7377841249451596e-05,
"loss": 0.8942,
"step": 111
},
{
"epoch": 0.8,
"learning_rate": 1.7325516560882706e-05,
"loss": 0.8849,
"step": 112
},
{
"epoch": 0.81,
"learning_rate": 1.727275540972417e-05,
"loss": 0.8786,
"step": 113
},
{
"epoch": 0.81,
"learning_rate": 1.7219560939545246e-05,
"loss": 0.8361,
"step": 114
},
{
"epoch": 0.82,
"learning_rate": 1.7165936319732833e-05,
"loss": 0.8518,
"step": 115
},
{
"epoch": 0.83,
"learning_rate": 1.711188474530263e-05,
"loss": 0.8686,
"step": 116
},
{
"epoch": 0.83,
"learning_rate": 1.7057409436708783e-05,
"loss": 0.8457,
"step": 117
},
{
"epoch": 0.84,
"learning_rate": 1.700251363965199e-05,
"loss": 0.8331,
"step": 118
},
{
"epoch": 0.85,
"learning_rate": 1.6947200624886145e-05,
"loss": 0.8336,
"step": 119
},
{
"epoch": 0.86,
"learning_rate": 1.6891473688023425e-05,
"loss": 0.8896,
"step": 120
},
{
"epoch": 0.86,
"learning_rate": 1.6835336149337976e-05,
"loss": 0.8698,
"step": 121
},
{
"epoch": 0.87,
"learning_rate": 1.677879135356805e-05,
"loss": 0.8493,
"step": 122
},
{
"epoch": 0.88,
"learning_rate": 1.6721842669716752e-05,
"loss": 0.8637,
"step": 123
},
{
"epoch": 0.88,
"learning_rate": 1.666449349085129e-05,
"loss": 0.8614,
"step": 124
},
{
"epoch": 0.89,
"learning_rate": 1.6606747233900816e-05,
"loss": 0.8878,
"step": 125
},
{
"epoch": 0.9,
"learning_rate": 1.6548607339452853e-05,
"loss": 0.8685,
"step": 126
},
{
"epoch": 0.91,
"learning_rate": 1.6490077271548287e-05,
"loss": 0.8429,
"step": 127
},
{
"epoch": 0.91,
"learning_rate": 1.6431160517474986e-05,
"loss": 0.8828,
"step": 128
},
{
"epoch": 0.92,
"learning_rate": 1.637186058756001e-05,
"loss": 0.8589,
"step": 129
},
{
"epoch": 0.93,
"learning_rate": 1.6312181014960483e-05,
"loss": 0.864,
"step": 130
},
{
"epoch": 0.93,
"learning_rate": 1.6252125355453058e-05,
"loss": 0.8906,
"step": 131
},
{
"epoch": 0.94,
"learning_rate": 1.619169718722209e-05,
"loss": 0.854,
"step": 132
},
{
"epoch": 0.95,
"learning_rate": 1.6130900110646404e-05,
"loss": 0.9064,
"step": 133
},
{
"epoch": 0.96,
"learning_rate": 1.6069737748084823e-05,
"loss": 0.9017,
"step": 134
},
{
"epoch": 0.96,
"learning_rate": 1.600821374366031e-05,
"loss": 0.8955,
"step": 135
},
{
"epoch": 0.97,
"learning_rate": 1.594633176304287e-05,
"loss": 0.8569,
"step": 136
},
{
"epoch": 0.98,
"learning_rate": 1.5884095493231123e-05,
"loss": 0.8699,
"step": 137
},
{
"epoch": 0.98,
"learning_rate": 1.582150864233266e-05,
"loss": 0.8945,
"step": 138
},
{
"epoch": 0.99,
"learning_rate": 1.5758574939343073e-05,
"loss": 0.8861,
"step": 139
},
{
"epoch": 1.0,
"learning_rate": 1.569529813392381e-05,
"loss": 0.8806,
"step": 140
},
{
"epoch": 1.01,
"learning_rate": 1.5631681996178735e-05,
"loss": 0.7215,
"step": 141
},
{
"epoch": 1.01,
"learning_rate": 1.5567730316429536e-05,
"loss": 0.6521,
"step": 142
},
{
"epoch": 1.02,
"learning_rate": 1.5503446904989856e-05,
"loss": 0.6706,
"step": 143
},
{
"epoch": 1.03,
"learning_rate": 1.54388355919383e-05,
"loss": 0.6824,
"step": 144
},
{
"epoch": 1.03,
"learning_rate": 1.537390022689022e-05,
"loss": 0.6543,
"step": 145
},
{
"epoch": 1.04,
"learning_rate": 1.530864467876836e-05,
"loss": 0.6559,
"step": 146
},
{
"epoch": 1.05,
"learning_rate": 1.5243072835572319e-05,
"loss": 0.6764,
"step": 147
},
{
"epoch": 1.06,
"learning_rate": 1.5177188604146929e-05,
"loss": 0.6662,
"step": 148
},
{
"epoch": 1.06,
"learning_rate": 1.5110995909949465e-05,
"loss": 0.6668,
"step": 149
},
{
"epoch": 1.07,
"learning_rate": 1.504449869681576e-05,
"loss": 0.6746,
"step": 150
},
{
"epoch": 1.08,
"learning_rate": 1.4977700926725231e-05,
"loss": 0.6726,
"step": 151
},
{
"epoch": 1.08,
"learning_rate": 1.4910606579564827e-05,
"loss": 0.6261,
"step": 152
},
{
"epoch": 1.09,
"learning_rate": 1.4843219652891889e-05,
"loss": 0.6561,
"step": 153
},
{
"epoch": 1.1,
"learning_rate": 1.4775544161695975e-05,
"loss": 0.6725,
"step": 154
},
{
"epoch": 1.11,
"learning_rate": 1.4707584138159652e-05,
"loss": 0.6421,
"step": 155
},
{
"epoch": 1.11,
"learning_rate": 1.4639343631418239e-05,
"loss": 0.6568,
"step": 156
},
{
"epoch": 1.12,
"learning_rate": 1.457082670731857e-05,
"loss": 0.6381,
"step": 157
},
{
"epoch": 1.13,
"learning_rate": 1.4502037448176734e-05,
"loss": 0.6663,
"step": 158
},
{
"epoch": 1.13,
"learning_rate": 1.4432979952534853e-05,
"loss": 0.6344,
"step": 159
},
{
"epoch": 1.14,
"learning_rate": 1.4363658334916883e-05,
"loss": 0.6778,
"step": 160
},
{
"epoch": 1.15,
"learning_rate": 1.4294076725583463e-05,
"loss": 0.6412,
"step": 161
},
{
"epoch": 1.16,
"learning_rate": 1.4224239270285847e-05,
"loss": 0.6905,
"step": 162
},
{
"epoch": 1.16,
"learning_rate": 1.4154150130018867e-05,
"loss": 0.6732,
"step": 163
},
{
"epoch": 1.17,
"learning_rate": 1.4083813480773036e-05,
"loss": 0.6823,
"step": 164
},
{
"epoch": 1.18,
"learning_rate": 1.4013233513285734e-05,
"loss": 0.6621,
"step": 165
},
{
"epoch": 1.18,
"learning_rate": 1.394241443279152e-05,
"loss": 0.6802,
"step": 166
},
{
"epoch": 1.19,
"learning_rate": 1.3871360458771575e-05,
"loss": 0.6327,
"step": 167
},
{
"epoch": 1.2,
"learning_rate": 1.38000758247023e-05,
"loss": 0.6688,
"step": 168
},
{
"epoch": 1.21,
"learning_rate": 1.3728564777803089e-05,
"loss": 0.6781,
"step": 169
},
{
"epoch": 1.21,
"learning_rate": 1.3656831578783263e-05,
"loss": 0.6387,
"step": 170
},
{
"epoch": 1.22,
"learning_rate": 1.3584880501588225e-05,
"loss": 0.6211,
"step": 171
},
{
"epoch": 1.23,
"learning_rate": 1.35127158331448e-05,
"loss": 0.6674,
"step": 172
},
{
"epoch": 1.23,
"learning_rate": 1.3440341873105834e-05,
"loss": 0.664,
"step": 173
},
{
"epoch": 1.24,
"learning_rate": 1.3367762933593989e-05,
"loss": 0.6374,
"step": 174
},
{
"epoch": 1.25,
"learning_rate": 1.3294983338944842e-05,
"loss": 0.7106,
"step": 175
},
{
"epoch": 1.26,
"learning_rate": 1.3222007425449234e-05,
"loss": 0.6743,
"step": 176
},
{
"epoch": 1.26,
"learning_rate": 1.314883954109491e-05,
"loss": 0.6266,
"step": 177
},
{
"epoch": 1.27,
"learning_rate": 1.3075484045307443e-05,
"loss": 0.6409,
"step": 178
},
{
"epoch": 1.28,
"learning_rate": 1.3001945308690514e-05,
"loss": 0.696,
"step": 179
},
{
"epoch": 1.28,
"learning_rate": 1.2928227712765504e-05,
"loss": 0.6427,
"step": 180
},
{
"epoch": 1.29,
"learning_rate": 1.2854335649710436e-05,
"loss": 0.687,
"step": 181
},
{
"epoch": 1.3,
"learning_rate": 1.2780273522098276e-05,
"loss": 0.624,
"step": 182
},
{
"epoch": 1.31,
"learning_rate": 1.2706045742634637e-05,
"loss": 0.6444,
"step": 183
},
{
"epoch": 1.31,
"learning_rate": 1.2631656733894842e-05,
"loss": 0.64,
"step": 184
},
{
"epoch": 1.32,
"learning_rate": 1.2557110928060456e-05,
"loss": 0.6345,
"step": 185
},
{
"epoch": 1.33,
"learning_rate": 1.2482412766655183e-05,
"loss": 0.6863,
"step": 186
},
{
"epoch": 1.33,
"learning_rate": 1.2407566700280247e-05,
"loss": 0.6546,
"step": 187
},
{
"epoch": 1.34,
"learning_rate": 1.2332577188349217e-05,
"loss": 0.6767,
"step": 188
},
{
"epoch": 1.35,
"learning_rate": 1.2257448698822314e-05,
"loss": 0.6265,
"step": 189
},
{
"epoch": 1.36,
"learning_rate": 1.2182185707940196e-05,
"loss": 0.6039,
"step": 190
},
{
"epoch": 1.36,
"learning_rate": 1.2106792699957264e-05,
"loss": 0.6537,
"step": 191
},
{
"epoch": 1.37,
"learning_rate": 1.2031274166874498e-05,
"loss": 0.671,
"step": 192
},
{
"epoch": 1.38,
"learning_rate": 1.1955634608171792e-05,
"loss": 0.6542,
"step": 193
},
{
"epoch": 1.38,
"learning_rate": 1.187987853053989e-05,
"loss": 0.6243,
"step": 194
},
{
"epoch": 1.39,
"learning_rate": 1.1804010447611862e-05,
"loss": 0.6399,
"step": 195
},
{
"epoch": 1.4,
"learning_rate": 1.1728034879694185e-05,
"loss": 0.6114,
"step": 196
},
{
"epoch": 1.4,
"learning_rate": 1.1651956353497418e-05,
"loss": 0.6876,
"step": 197
},
{
"epoch": 1.41,
"learning_rate": 1.1575779401866475e-05,
"loss": 0.6567,
"step": 198
},
{
"epoch": 1.42,
"learning_rate": 1.1499508563510587e-05,
"loss": 0.6602,
"step": 199
},
{
"epoch": 1.43,
"learning_rate": 1.1423148382732854e-05,
"loss": 0.6618,
"step": 200
},
{
"epoch": 1.43,
"learning_rate": 1.1346703409159495e-05,
"loss": 0.6235,
"step": 201
},
{
"epoch": 1.44,
"learning_rate": 1.1270178197468788e-05,
"loss": 0.6743,
"step": 202
},
{
"epoch": 1.45,
"learning_rate": 1.1193577307119687e-05,
"loss": 0.676,
"step": 203
},
{
"epoch": 1.45,
"learning_rate": 1.1116905302080163e-05,
"loss": 0.6091,
"step": 204
},
{
"epoch": 1.46,
"learning_rate": 1.1040166750555288e-05,
"loss": 0.6412,
"step": 205
},
{
"epoch": 1.47,
"learning_rate": 1.0963366224715035e-05,
"loss": 0.6593,
"step": 206
},
{
"epoch": 1.48,
"learning_rate": 1.0886508300421892e-05,
"loss": 0.6369,
"step": 207
},
{
"epoch": 1.48,
"learning_rate": 1.080959755695821e-05,
"loss": 0.7025,
"step": 208
},
{
"epoch": 1.49,
"learning_rate": 1.0732638576753355e-05,
"loss": 0.6387,
"step": 209
},
{
"epoch": 1.5,
"learning_rate": 1.0655635945110705e-05,
"loss": 0.6821,
"step": 210
},
{
"epoch": 1.5,
"learning_rate": 1.0578594249934433e-05,
"loss": 0.673,
"step": 211
},
{
"epoch": 1.51,
"learning_rate": 1.0501518081456164e-05,
"loss": 0.6481,
"step": 212
},
{
"epoch": 1.52,
"learning_rate": 1.0424412031961485e-05,
"loss": 0.6704,
"step": 213
},
{
"epoch": 1.53,
"learning_rate": 1.0347280695516319e-05,
"loss": 0.6656,
"step": 214
},
{
"epoch": 1.53,
"learning_rate": 1.0270128667693225e-05,
"loss": 0.644,
"step": 215
},
{
"epoch": 1.54,
"learning_rate": 1.0192960545297568e-05,
"loss": 0.6596,
"step": 216
},
{
"epoch": 1.55,
"learning_rate": 1.011578092609365e-05,
"loss": 0.6377,
"step": 217
},
{
"epoch": 1.55,
"learning_rate": 1.0038594408530768e-05,
"loss": 0.6317,
"step": 218
},
{
"epoch": 1.56,
"learning_rate": 9.96140559146923e-06,
"loss": 0.6491,
"step": 219
},
{
"epoch": 1.57,
"learning_rate": 9.884219073906353e-06,
"loss": 0.6474,
"step": 220
},
{
"epoch": 1.58,
"learning_rate": 9.807039454702436e-06,
"loss": 0.6897,
"step": 221
},
{
"epoch": 1.58,
"learning_rate": 9.729871332306775e-06,
"loss": 0.6109,
"step": 222
},
{
"epoch": 1.59,
"learning_rate": 9.652719304483683e-06,
"loss": 0.6783,
"step": 223
},
{
"epoch": 1.6,
"learning_rate": 9.57558796803852e-06,
"loss": 0.6471,
"step": 224
},
{
"epoch": 1.6,
"learning_rate": 9.498481918543836e-06,
"loss": 0.6259,
"step": 225
},
{
"epoch": 1.61,
"learning_rate": 9.42140575006557e-06,
"loss": 0.6444,
"step": 226
},
{
"epoch": 1.62,
"learning_rate": 9.344364054889298e-06,
"loss": 0.6624,
"step": 227
},
{
"epoch": 1.63,
"learning_rate": 9.267361423246645e-06,
"loss": 0.6863,
"step": 228
},
{
"epoch": 1.63,
"learning_rate": 9.190402443041792e-06,
"loss": 0.643,
"step": 229
},
{
"epoch": 1.64,
"learning_rate": 9.11349169957811e-06,
"loss": 0.6617,
"step": 230
},
{
"epoch": 1.65,
"learning_rate": 9.036633775284968e-06,
"loss": 0.6689,
"step": 231
},
{
"epoch": 1.65,
"learning_rate": 8.959833249444715e-06,
"loss": 0.6269,
"step": 232
},
{
"epoch": 1.66,
"learning_rate": 8.883094697919839e-06,
"loss": 0.6601,
"step": 233
},
{
"epoch": 1.67,
"learning_rate": 8.806422692880318e-06,
"loss": 0.6672,
"step": 234
},
{
"epoch": 1.68,
"learning_rate": 8.729821802531213e-06,
"loss": 0.6126,
"step": 235
},
{
"epoch": 1.68,
"learning_rate": 8.653296590840509e-06,
"loss": 0.6506,
"step": 236
},
{
"epoch": 1.69,
"learning_rate": 8.576851617267151e-06,
"loss": 0.6503,
"step": 237
},
{
"epoch": 1.7,
"learning_rate": 8.500491436489413e-06,
"loss": 0.6969,
"step": 238
},
{
"epoch": 1.7,
"learning_rate": 8.424220598133526e-06,
"loss": 0.6609,
"step": 239
},
{
"epoch": 1.71,
"learning_rate": 8.348043646502588e-06,
"loss": 0.648,
"step": 240
},
{
"epoch": 1.72,
"learning_rate": 8.271965120305815e-06,
"loss": 0.7073,
"step": 241
},
{
"epoch": 1.73,
"learning_rate": 8.19598955238814e-06,
"loss": 0.6661,
"step": 242
},
{
"epoch": 1.73,
"learning_rate": 8.120121469460114e-06,
"loss": 0.727,
"step": 243
},
{
"epoch": 1.74,
"learning_rate": 8.04436539182821e-06,
"loss": 0.6866,
"step": 244
},
{
"epoch": 1.75,
"learning_rate": 7.968725833125505e-06,
"loss": 0.6556,
"step": 245
},
{
"epoch": 1.75,
"learning_rate": 7.89320730004274e-06,
"loss": 0.6132,
"step": 246
},
{
"epoch": 1.76,
"learning_rate": 7.81781429205981e-06,
"loss": 0.6601,
"step": 247
},
{
"epoch": 1.77,
"learning_rate": 7.74255130117769e-06,
"loss": 0.6627,
"step": 248
},
{
"epoch": 1.78,
"learning_rate": 7.667422811650786e-06,
"loss": 0.6766,
"step": 249
},
{
"epoch": 1.78,
"learning_rate": 7.592433299719757e-06,
"loss": 0.6407,
"step": 250
},
{
"epoch": 1.79,
"learning_rate": 7.51758723334482e-06,
"loss": 0.6199,
"step": 251
},
{
"epoch": 1.8,
"learning_rate": 7.442889071939548e-06,
"loss": 0.665,
"step": 252
},
{
"epoch": 1.8,
"learning_rate": 7.368343266105162e-06,
"loss": 0.671,
"step": 253
},
{
"epoch": 1.81,
"learning_rate": 7.293954257365368e-06,
"loss": 0.6747,
"step": 254
},
{
"epoch": 1.82,
"learning_rate": 7.2197264779017275e-06,
"loss": 0.6633,
"step": 255
},
{
"epoch": 1.83,
"learning_rate": 7.145664350289566e-06,
"loss": 0.6527,
"step": 256
},
{
"epoch": 1.83,
"learning_rate": 7.071772287234497e-06,
"loss": 0.6978,
"step": 257
},
{
"epoch": 1.84,
"learning_rate": 6.998054691309489e-06,
"loss": 0.6754,
"step": 258
},
{
"epoch": 1.85,
"learning_rate": 6.924515954692563e-06,
"loss": 0.66,
"step": 259
},
{
"epoch": 1.85,
"learning_rate": 6.851160458905093e-06,
"loss": 0.6229,
"step": 260
},
{
"epoch": 1.86,
"learning_rate": 6.777992574550767e-06,
"loss": 0.6619,
"step": 261
},
{
"epoch": 1.87,
"learning_rate": 6.705016661055162e-06,
"loss": 0.6291,
"step": 262
},
{
"epoch": 1.88,
"learning_rate": 6.632237066406014e-06,
"loss": 0.6353,
"step": 263
},
{
"epoch": 1.88,
"learning_rate": 6.559658126894169e-06,
"loss": 0.6533,
"step": 264
},
{
"epoch": 1.89,
"learning_rate": 6.487284166855203e-06,
"loss": 0.6381,
"step": 265
},
{
"epoch": 1.9,
"learning_rate": 6.4151194984117774e-06,
"loss": 0.6156,
"step": 266
},
{
"epoch": 1.9,
"learning_rate": 6.343168421216741e-06,
"loss": 0.6582,
"step": 267
},
{
"epoch": 1.91,
"learning_rate": 6.2714352221969155e-06,
"loss": 0.6862,
"step": 268
},
{
"epoch": 1.92,
"learning_rate": 6.199924175297701e-06,
"loss": 0.6487,
"step": 269
},
{
"epoch": 1.93,
"learning_rate": 6.128639541228427e-06,
"loss": 0.6534,
"step": 270
},
{
"epoch": 1.93,
"learning_rate": 6.057585567208484e-06,
"loss": 0.6827,
"step": 271
},
{
"epoch": 1.94,
"learning_rate": 5.986766486714268e-06,
"loss": 0.6595,
"step": 272
},
{
"epoch": 1.95,
"learning_rate": 5.916186519226966e-06,
"loss": 0.6754,
"step": 273
},
{
"epoch": 1.95,
"learning_rate": 5.845849869981137e-06,
"loss": 0.6635,
"step": 274
},
{
"epoch": 1.96,
"learning_rate": 5.775760729714155e-06,
"loss": 0.6604,
"step": 275
},
{
"epoch": 1.97,
"learning_rate": 5.705923274416536e-06,
"loss": 0.6956,
"step": 276
},
{
"epoch": 1.98,
"learning_rate": 5.636341665083121e-06,
"loss": 0.6262,
"step": 277
},
{
"epoch": 1.98,
"learning_rate": 5.5670200474651505e-06,
"loss": 0.6186,
"step": 278
},
{
"epoch": 1.99,
"learning_rate": 5.497962551823266e-06,
"loss": 0.6558,
"step": 279
},
{
"epoch": 2.0,
"learning_rate": 5.429173292681433e-06,
"loss": 0.7025,
"step": 280
},
{
"epoch": 2.0,
"learning_rate": 5.3606563685817646e-06,
"loss": 0.5535,
"step": 281
},
{
"epoch": 2.01,
"learning_rate": 5.29241586184035e-06,
"loss": 0.5372,
"step": 282
},
{
"epoch": 2.02,
"learning_rate": 5.224455838304028e-06,
"loss": 0.5183,
"step": 283
},
{
"epoch": 2.03,
"learning_rate": 5.1567803471081164e-06,
"loss": 0.5192,
"step": 284
},
{
"epoch": 2.03,
"learning_rate": 5.089393420435176e-06,
"loss": 0.5072,
"step": 285
},
{
"epoch": 2.04,
"learning_rate": 5.022299073274769e-06,
"loss": 0.5038,
"step": 286
},
{
"epoch": 2.05,
"learning_rate": 4.9555013031842445e-06,
"loss": 0.5133,
"step": 287
},
{
"epoch": 2.05,
"learning_rate": 4.889004090050536e-06,
"loss": 0.483,
"step": 288
},
{
"epoch": 2.06,
"learning_rate": 4.822811395853073e-06,
"loss": 0.478,
"step": 289
},
{
"epoch": 2.07,
"learning_rate": 4.756927164427685e-06,
"loss": 0.491,
"step": 290
},
{
"epoch": 2.08,
"learning_rate": 4.691355321231645e-06,
"loss": 0.5153,
"step": 291
},
{
"epoch": 2.08,
"learning_rate": 4.62609977310978e-06,
"loss": 0.5066,
"step": 292
},
{
"epoch": 2.09,
"learning_rate": 4.561164408061703e-06,
"loss": 0.495,
"step": 293
},
{
"epoch": 2.1,
"learning_rate": 4.496553095010147e-06,
"loss": 0.5069,
"step": 294
},
{
"epoch": 2.1,
"learning_rate": 4.432269683570469e-06,
"loss": 0.4724,
"step": 295
},
{
"epoch": 2.11,
"learning_rate": 4.368318003821266e-06,
"loss": 0.4922,
"step": 296
},
{
"epoch": 2.12,
"learning_rate": 4.304701866076194e-06,
"loss": 0.495,
"step": 297
},
{
"epoch": 2.13,
"learning_rate": 4.241425060656927e-06,
"loss": 0.5082,
"step": 298
},
{
"epoch": 2.13,
"learning_rate": 4.178491357667342e-06,
"loss": 0.4689,
"step": 299
},
{
"epoch": 2.14,
"learning_rate": 4.11590450676888e-06,
"loss": 0.4802,
"step": 300
},
{
"epoch": 2.15,
"learning_rate": 4.053668236957135e-06,
"loss": 0.4662,
"step": 301
},
{
"epoch": 2.15,
"learning_rate": 3.991786256339692e-06,
"loss": 0.529,
"step": 302
},
{
"epoch": 2.16,
"learning_rate": 3.930262251915181e-06,
"loss": 0.5224,
"step": 303
},
{
"epoch": 2.17,
"learning_rate": 3.869099889353597e-06,
"loss": 0.5176,
"step": 304
},
{
"epoch": 2.18,
"learning_rate": 3.8083028127779143e-06,
"loss": 0.5094,
"step": 305
},
{
"epoch": 2.18,
"learning_rate": 3.7478746445469415e-06,
"loss": 0.4926,
"step": 306
},
{
"epoch": 2.19,
"learning_rate": 3.6878189850395186e-06,
"loss": 0.4941,
"step": 307
},
{
"epoch": 2.2,
"learning_rate": 3.628139412439993e-06,
"loss": 0.5487,
"step": 308
},
{
"epoch": 2.2,
"learning_rate": 3.5688394825250193e-06,
"loss": 0.5081,
"step": 309
},
{
"epoch": 2.21,
"learning_rate": 3.5099227284517145e-06,
"loss": 0.4889,
"step": 310
},
{
"epoch": 2.22,
"learning_rate": 3.4513926605471504e-06,
"loss": 0.4938,
"step": 311
},
{
"epoch": 2.23,
"learning_rate": 3.3932527660991877e-06,
"loss": 0.4837,
"step": 312
},
{
"epoch": 2.23,
"learning_rate": 3.335506509148716e-06,
"loss": 0.4979,
"step": 313
},
{
"epoch": 2.24,
"learning_rate": 3.2781573302832493e-06,
"loss": 0.4936,
"step": 314
},
{
"epoch": 2.25,
"learning_rate": 3.221208646431949e-06,
"loss": 0.4766,
"step": 315
},
{
"epoch": 2.25,
"learning_rate": 3.1646638506620265e-06,
"loss": 0.5223,
"step": 316
},
{
"epoch": 2.26,
"learning_rate": 3.108526311976574e-06,
"loss": 0.498,
"step": 317
},
{
"epoch": 2.27,
"learning_rate": 3.0527993751138575e-06,
"loss": 0.4948,
"step": 318
},
{
"epoch": 2.28,
"learning_rate": 2.997486360348011e-06,
"loss": 0.4607,
"step": 319
},
{
"epoch": 2.28,
"learning_rate": 2.942590563291219e-06,
"loss": 0.5286,
"step": 320
},
{
"epoch": 2.29,
"learning_rate": 2.888115254697371e-06,
"loss": 0.5225,
"step": 321
},
{
"epoch": 2.3,
"learning_rate": 2.8340636802671716e-06,
"loss": 0.4547,
"step": 322
},
{
"epoch": 2.3,
"learning_rate": 2.780439060454756e-06,
"loss": 0.4879,
"step": 323
},
{
"epoch": 2.31,
"learning_rate": 2.727244590275834e-06,
"loss": 0.5063,
"step": 324
},
{
"epoch": 2.32,
"learning_rate": 2.674483439117296e-06,
"loss": 0.5119,
"step": 325
},
{
"epoch": 2.32,
"learning_rate": 2.622158750548407e-06,
"loss": 0.5264,
"step": 326
},
{
"epoch": 2.33,
"learning_rate": 2.5702736421334853e-06,
"loss": 0.5035,
"step": 327
},
{
"epoch": 2.34,
"learning_rate": 2.518831205246174e-06,
"loss": 0.5364,
"step": 328
},
{
"epoch": 2.35,
"learning_rate": 2.4678345048852326e-06,
"loss": 0.4828,
"step": 329
},
{
"epoch": 2.35,
"learning_rate": 2.4172865794919477e-06,
"loss": 0.4919,
"step": 330
},
{
"epoch": 2.36,
"learning_rate": 2.3671904407690704e-06,
"loss": 0.5037,
"step": 331
},
{
"epoch": 2.37,
"learning_rate": 2.317549073501396e-06,
"loss": 0.5387,
"step": 332
},
{
"epoch": 2.37,
"learning_rate": 2.268365435377915e-06,
"loss": 0.4866,
"step": 333
},
{
"epoch": 2.38,
"learning_rate": 2.2196424568156073e-06,
"loss": 0.5168,
"step": 334
},
{
"epoch": 2.39,
"learning_rate": 2.171383040784819e-06,
"loss": 0.5497,
"step": 335
},
{
"epoch": 2.4,
"learning_rate": 2.123590062636328e-06,
"loss": 0.4872,
"step": 336
},
{
"epoch": 2.4,
"learning_rate": 2.076266369930002e-06,
"loss": 0.4733,
"step": 337
},
{
"epoch": 2.41,
"learning_rate": 2.02941478226516e-06,
"loss": 0.4585,
"step": 338
},
{
"epoch": 2.42,
"learning_rate": 1.983038091112558e-06,
"loss": 0.5143,
"step": 339
},
{
"epoch": 2.42,
"learning_rate": 1.9371390596480865e-06,
"loss": 0.5329,
"step": 340
},
{
"epoch": 2.43,
"learning_rate": 1.8917204225881236e-06,
"loss": 0.4934,
"step": 341
},
{
"epoch": 2.44,
"learning_rate": 1.8467848860266047e-06,
"loss": 0.5128,
"step": 342
},
{
"epoch": 2.45,
"learning_rate": 1.8023351272737955e-06,
"loss": 0.5159,
"step": 343
},
{
"epoch": 2.45,
"learning_rate": 1.7583737946967606e-06,
"loss": 0.5194,
"step": 344
},
{
"epoch": 2.46,
"learning_rate": 1.7149035075615795e-06,
"loss": 0.5457,
"step": 345
},
{
"epoch": 2.47,
"learning_rate": 1.6719268558772927e-06,
"loss": 0.4861,
"step": 346
},
{
"epoch": 2.47,
"learning_rate": 1.6294464002415789e-06,
"loss": 0.4779,
"step": 347
},
{
"epoch": 2.48,
"learning_rate": 1.587464671688187e-06,
"loss": 0.4923,
"step": 348
},
{
"epoch": 2.49,
"learning_rate": 1.54598417153615e-06,
"loss": 0.4961,
"step": 349
},
{
"epoch": 2.5,
"learning_rate": 1.5050073712407354e-06,
"loss": 0.5059,
"step": 350
},
{
"epoch": 2.5,
"learning_rate": 1.464536712246205e-06,
"loss": 0.504,
"step": 351
},
{
"epoch": 2.51,
"learning_rate": 1.4245746058403464e-06,
"loss": 0.489,
"step": 352
},
{
"epoch": 2.52,
"learning_rate": 1.385123433010812e-06,
"loss": 0.4703,
"step": 353
},
{
"epoch": 2.52,
"learning_rate": 1.3461855443032456e-06,
"loss": 0.5223,
"step": 354
},
{
"epoch": 2.53,
"learning_rate": 1.3077632596812407e-06,
"loss": 0.4904,
"step": 355
},
{
"epoch": 2.54,
"learning_rate": 1.2698588683881185e-06,
"loss": 0.4623,
"step": 356
},
{
"epoch": 2.55,
"learning_rate": 1.2324746288105272e-06,
"loss": 0.5149,
"step": 357
},
{
"epoch": 2.55,
"learning_rate": 1.1956127683438822e-06,
"loss": 0.4923,
"step": 358
},
{
"epoch": 2.56,
"learning_rate": 1.1592754832596632e-06,
"loss": 0.5164,
"step": 359
},
{
"epoch": 2.57,
"learning_rate": 1.1234649385745488e-06,
"loss": 0.5093,
"step": 360
},
{
"epoch": 2.57,
"learning_rate": 1.0881832679214276e-06,
"loss": 0.4929,
"step": 361
},
{
"epoch": 2.58,
"learning_rate": 1.0534325734222773e-06,
"loss": 0.5419,
"step": 362
},
{
"epoch": 2.59,
"learning_rate": 1.0192149255629114e-06,
"loss": 0.5164,
"step": 363
},
{
"epoch": 2.6,
"learning_rate": 9.855323630696146e-07,
"loss": 0.4707,
"step": 364
},
{
"epoch": 2.6,
"learning_rate": 9.523868927876889e-07,
"loss": 0.4744,
"step": 365
},
{
"epoch": 2.61,
"learning_rate": 9.197804895618623e-07,
"loss": 0.4753,
"step": 366
},
{
"epoch": 2.62,
"learning_rate": 8.87715096118642e-07,
"loss": 0.4882,
"step": 367
},
{
"epoch": 2.62,
"learning_rate": 8.561926229505601e-07,
"loss": 0.4818,
"step": 368
},
{
"epoch": 2.63,
"learning_rate": 8.252149482023363e-07,
"loss": 0.4743,
"step": 369
},
{
"epoch": 2.64,
"learning_rate": 7.947839175589845e-07,
"loss": 0.4877,
"step": 370
},
{
"epoch": 2.65,
"learning_rate": 7.649013441358466e-07,
"loss": 0.5093,
"step": 371
},
{
"epoch": 2.65,
"learning_rate": 7.355690083705547e-07,
"loss": 0.4711,
"step": 372
},
{
"epoch": 2.66,
"learning_rate": 7.067886579169625e-07,
"loss": 0.477,
"step": 373
},
{
"epoch": 2.67,
"learning_rate": 6.78562007541006e-07,
"loss": 0.4992,
"step": 374
},
{
"epoch": 2.67,
"learning_rate": 6.508907390185504e-07,
"loss": 0.4993,
"step": 375
},
{
"epoch": 2.68,
"learning_rate": 6.237765010351715e-07,
"loss": 0.466,
"step": 376
},
{
"epoch": 2.69,
"learning_rate": 5.972209090879389e-07,
"loss": 0.4727,
"step": 377
},
{
"epoch": 2.7,
"learning_rate": 5.71225545389158e-07,
"loss": 0.4927,
"step": 378
},
{
"epoch": 2.7,
"learning_rate": 5.457919587720961e-07,
"loss": 0.5099,
"step": 379
},
{
"epoch": 2.71,
"learning_rate": 5.209216645987036e-07,
"loss": 0.5217,
"step": 380
},
{
"epoch": 2.72,
"learning_rate": 4.966161446693329e-07,
"loss": 0.5118,
"step": 381
},
{
"epoch": 2.72,
"learning_rate": 4.728768471344425e-07,
"loss": 0.5118,
"step": 382
},
{
"epoch": 2.73,
"learning_rate": 4.4970518640831687e-07,
"loss": 0.5028,
"step": 383
},
{
"epoch": 2.74,
"learning_rate": 4.271025430847986e-07,
"loss": 0.4986,
"step": 384
},
{
"epoch": 2.75,
"learning_rate": 4.0507026385502747e-07,
"loss": 0.4744,
"step": 385
},
{
"epoch": 2.75,
"learning_rate": 3.836096614271989e-07,
"loss": 0.4928,
"step": 386
},
{
"epoch": 2.76,
"learning_rate": 3.6272201444836006e-07,
"loss": 0.467,
"step": 387
},
{
"epoch": 2.77,
"learning_rate": 3.424085674282229e-07,
"loss": 0.4756,
"step": 388
},
{
"epoch": 2.77,
"learning_rate": 3.226705306650113e-07,
"loss": 0.5302,
"step": 389
},
{
"epoch": 2.78,
"learning_rate": 3.0350908017335423e-07,
"loss": 0.4687,
"step": 390
},
{
"epoch": 2.79,
"learning_rate": 2.8492535761421635e-07,
"loss": 0.4699,
"step": 391
},
{
"epoch": 2.8,
"learning_rate": 2.6692047022687684e-07,
"loss": 0.472,
"step": 392
},
{
"epoch": 2.8,
"learning_rate": 2.494954907629565e-07,
"loss": 0.5102,
"step": 393
},
{
"epoch": 2.81,
"learning_rate": 2.3265145742250694e-07,
"loss": 0.4985,
"step": 394
},
{
"epoch": 2.82,
"learning_rate": 2.1638937379214852e-07,
"loss": 0.4999,
"step": 395
},
{
"epoch": 2.82,
"learning_rate": 2.0071020878527857e-07,
"loss": 0.4821,
"step": 396
},
{
"epoch": 2.83,
"learning_rate": 1.8561489658433963e-07,
"loss": 0.5049,
"step": 397
},
{
"epoch": 2.84,
"learning_rate": 1.711043365851639e-07,
"loss": 0.4672,
"step": 398
},
{
"epoch": 2.85,
"learning_rate": 1.5717939334338184e-07,
"loss": 0.5159,
"step": 399
},
{
"epoch": 2.85,
"learning_rate": 1.4384089652291544e-07,
"loss": 0.4481,
"step": 400
},
{
"epoch": 2.86,
"learning_rate": 1.310896408465401e-07,
"loss": 0.4825,
"step": 401
},
{
"epoch": 2.87,
"learning_rate": 1.1892638604853901e-07,
"loss": 0.4974,
"step": 402
},
{
"epoch": 2.87,
"learning_rate": 1.0735185682943628e-07,
"loss": 0.5136,
"step": 403
},
{
"epoch": 2.88,
"learning_rate": 9.636674281281788e-08,
"loss": 0.4991,
"step": 404
},
{
"epoch": 2.89,
"learning_rate": 8.597169850424136e-08,
"loss": 0.4636,
"step": 405
},
{
"epoch": 2.9,
"learning_rate": 7.616734325224473e-08,
"loss": 0.5009,
"step": 406
},
{
"epoch": 2.9,
"learning_rate": 6.69542612114371e-08,
"loss": 0.4814,
"step": 407
},
{
"epoch": 2.91,
"learning_rate": 5.833300130770436e-08,
"loss": 0.4765,
"step": 408
},
{
"epoch": 2.92,
"learning_rate": 5.030407720549413e-08,
"loss": 0.4909,
"step": 409
},
{
"epoch": 2.92,
"learning_rate": 4.286796727721476e-08,
"loss": 0.4783,
"step": 410
},
{
"epoch": 2.93,
"learning_rate": 3.602511457473479e-08,
"loss": 0.493,
"step": 411
},
{
"epoch": 2.94,
"learning_rate": 2.9775926802984022e-08,
"loss": 0.4648,
"step": 412
},
{
"epoch": 2.95,
"learning_rate": 2.4120776295659675e-08,
"loss": 0.4917,
"step": 413
},
{
"epoch": 2.95,
"learning_rate": 1.905999999304853e-08,
"loss": 0.4844,
"step": 414
},
{
"epoch": 2.96,
"learning_rate": 1.4593899421943003e-08,
"loss": 0.4925,
"step": 415
},
{
"epoch": 2.97,
"learning_rate": 1.0722740677685529e-08,
"loss": 0.4803,
"step": 416
},
{
"epoch": 2.97,
"learning_rate": 7.4467544083067776e-09,
"loss": 0.4579,
"step": 417
},
{
"epoch": 2.98,
"learning_rate": 4.766135800785554e-09,
"loss": 0.4739,
"step": 418
},
{
"epoch": 2.99,
"learning_rate": 2.68104456942031e-09,
"loss": 0.5126,
"step": 419
},
{
"epoch": 3.0,
"learning_rate": 1.1916049463134293e-09,
"loss": 0.4761,
"step": 420
},
{
"epoch": 3.0,
"step": 420,
"total_flos": 1.7711353317818368e+17,
"train_loss": 0.6881538674944923,
"train_runtime": 11850.5144,
"train_samples_per_second": 18.172,
"train_steps_per_second": 0.035
}
],
"max_steps": 420,
"num_train_epochs": 3,
"total_flos": 1.7711353317818368e+17,
"trial_name": null,
"trial_params": null
}