sarahyo941's picture
End of training
9772ef6 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 434,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.1111111111111112e-05,
"loss": 2.3254,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 2.2222222222222223e-05,
"loss": 2.4112,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 3.3333333333333335e-05,
"loss": 2.3104,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 4.4444444444444447e-05,
"loss": 2.1862,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 5.555555555555556e-05,
"loss": 1.8671,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 6.666666666666667e-05,
"loss": 1.632,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 7.777777777777778e-05,
"loss": 1.2926,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 8.888888888888889e-05,
"loss": 1.1784,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 0.9747,
"step": 9
},
{
"epoch": 0.02,
"learning_rate": 9.999863397100895e-05,
"loss": 0.6938,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 9.999453595867717e-05,
"loss": 0.4035,
"step": 11
},
{
"epoch": 0.03,
"learning_rate": 9.998770618692483e-05,
"loss": 0.228,
"step": 12
},
{
"epoch": 0.03,
"learning_rate": 9.997814502893856e-05,
"loss": 0.202,
"step": 13
},
{
"epoch": 0.03,
"learning_rate": 9.996585300715116e-05,
"loss": 0.1499,
"step": 14
},
{
"epoch": 0.03,
"learning_rate": 9.99508307932129e-05,
"loss": 0.0606,
"step": 15
},
{
"epoch": 0.04,
"learning_rate": 9.993307920795501e-05,
"loss": 0.0492,
"step": 16
},
{
"epoch": 0.04,
"learning_rate": 9.991259922134466e-05,
"loss": 0.0409,
"step": 17
},
{
"epoch": 0.04,
"learning_rate": 9.98893919524321e-05,
"loss": 0.0374,
"step": 18
},
{
"epoch": 0.04,
"learning_rate": 9.986345866928941e-05,
"loss": 0.0137,
"step": 19
},
{
"epoch": 0.05,
"learning_rate": 9.983480078894124e-05,
"loss": 0.0101,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 9.98034198772874e-05,
"loss": 0.0066,
"step": 21
},
{
"epoch": 0.05,
"learning_rate": 9.976931764901733e-05,
"loss": 0.0057,
"step": 22
},
{
"epoch": 0.05,
"learning_rate": 9.973249596751631e-05,
"loss": 0.0359,
"step": 23
},
{
"epoch": 0.06,
"learning_rate": 9.96929568447637e-05,
"loss": 0.0038,
"step": 24
},
{
"epoch": 0.06,
"learning_rate": 9.965070244122301e-05,
"loss": 0.0014,
"step": 25
},
{
"epoch": 0.06,
"learning_rate": 9.96057350657239e-05,
"loss": 0.0004,
"step": 26
},
{
"epoch": 0.06,
"learning_rate": 9.955805717533586e-05,
"loss": 0.0017,
"step": 27
},
{
"epoch": 0.06,
"learning_rate": 9.950767137523416e-05,
"loss": 0.0003,
"step": 28
},
{
"epoch": 0.07,
"learning_rate": 9.94545804185573e-05,
"loss": 0.0002,
"step": 29
},
{
"epoch": 0.07,
"learning_rate": 9.939878720625675e-05,
"loss": 0.0002,
"step": 30
},
{
"epoch": 0.07,
"learning_rate": 9.934029478693832e-05,
"loss": 0.0002,
"step": 31
},
{
"epoch": 0.07,
"learning_rate": 9.927910635669562e-05,
"loss": 0.0001,
"step": 32
},
{
"epoch": 0.08,
"learning_rate": 9.921522525893548e-05,
"loss": 0.0337,
"step": 33
},
{
"epoch": 0.08,
"learning_rate": 9.91486549841951e-05,
"loss": 0.0001,
"step": 34
},
{
"epoch": 0.08,
"learning_rate": 9.907939916995152e-05,
"loss": 0.0032,
"step": 35
},
{
"epoch": 0.08,
"learning_rate": 9.900746160042273e-05,
"loss": 0.0001,
"step": 36
},
{
"epoch": 0.09,
"learning_rate": 9.893284620636099e-05,
"loss": 0.0002,
"step": 37
},
{
"epoch": 0.09,
"learning_rate": 9.885555706483792e-05,
"loss": 0.0005,
"step": 38
},
{
"epoch": 0.09,
"learning_rate": 9.877559839902184e-05,
"loss": 0.0006,
"step": 39
},
{
"epoch": 0.09,
"learning_rate": 9.869297457794699e-05,
"loss": 0.0001,
"step": 40
},
{
"epoch": 0.09,
"learning_rate": 9.860769011627475e-05,
"loss": 0.0002,
"step": 41
},
{
"epoch": 0.1,
"learning_rate": 9.851974967404704e-05,
"loss": 0.0001,
"step": 42
},
{
"epoch": 0.1,
"learning_rate": 9.842915805643155e-05,
"loss": 0.0001,
"step": 43
},
{
"epoch": 0.1,
"learning_rate": 9.833592021345937e-05,
"loss": 0.0001,
"step": 44
},
{
"epoch": 0.1,
"learning_rate": 9.824004123975435e-05,
"loss": 0.0001,
"step": 45
},
{
"epoch": 0.11,
"learning_rate": 9.814152637425478e-05,
"loss": 0.0001,
"step": 46
},
{
"epoch": 0.11,
"learning_rate": 9.804038099992717e-05,
"loss": 0.0001,
"step": 47
},
{
"epoch": 0.11,
"learning_rate": 9.793661064347205e-05,
"loss": 0.0001,
"step": 48
},
{
"epoch": 0.11,
"learning_rate": 9.783022097502204e-05,
"loss": 0.0001,
"step": 49
},
{
"epoch": 0.12,
"learning_rate": 9.772121780783201e-05,
"loss": 0.0001,
"step": 50
},
{
"epoch": 0.12,
"learning_rate": 9.760960709796141e-05,
"loss": 0.0001,
"step": 51
},
{
"epoch": 0.12,
"learning_rate": 9.749539494394886e-05,
"loss": 0.0001,
"step": 52
},
{
"epoch": 0.12,
"learning_rate": 9.737858758647889e-05,
"loss": 0.0001,
"step": 53
},
{
"epoch": 0.12,
"learning_rate": 9.725919140804099e-05,
"loss": 0.0,
"step": 54
},
{
"epoch": 0.13,
"learning_rate": 9.713721293258078e-05,
"loss": 0.0,
"step": 55
},
{
"epoch": 0.13,
"learning_rate": 9.701265882514361e-05,
"loss": 0.0,
"step": 56
},
{
"epoch": 0.13,
"learning_rate": 9.688553589151037e-05,
"loss": 0.0,
"step": 57
},
{
"epoch": 0.13,
"learning_rate": 9.675585107782557e-05,
"loss": 0.0001,
"step": 58
},
{
"epoch": 0.14,
"learning_rate": 9.662361147021779e-05,
"loss": 0.0,
"step": 59
},
{
"epoch": 0.14,
"learning_rate": 9.648882429441257e-05,
"loss": 0.0,
"step": 60
},
{
"epoch": 0.14,
"learning_rate": 9.635149691533749e-05,
"loss": 0.0,
"step": 61
},
{
"epoch": 0.14,
"learning_rate": 9.62116368367198e-05,
"loss": 0.0,
"step": 62
},
{
"epoch": 0.15,
"learning_rate": 9.606925170067638e-05,
"loss": 0.0,
"step": 63
},
{
"epoch": 0.15,
"learning_rate": 9.592434928729616e-05,
"loss": 0.0,
"step": 64
},
{
"epoch": 0.15,
"learning_rate": 9.577693751421506e-05,
"loss": 0.0,
"step": 65
},
{
"epoch": 0.15,
"learning_rate": 9.562702443618331e-05,
"loss": 0.0,
"step": 66
},
{
"epoch": 0.15,
"learning_rate": 9.547461824462534e-05,
"loss": 0.0,
"step": 67
},
{
"epoch": 0.16,
"learning_rate": 9.531972726719216e-05,
"loss": 0.0,
"step": 68
},
{
"epoch": 0.16,
"learning_rate": 9.516235996730645e-05,
"loss": 0.0,
"step": 69
},
{
"epoch": 0.16,
"learning_rate": 9.500252494369993e-05,
"loss": 0.0,
"step": 70
},
{
"epoch": 0.16,
"learning_rate": 9.484023092994366e-05,
"loss": 0.0,
"step": 71
},
{
"epoch": 0.17,
"learning_rate": 9.467548679397072e-05,
"loss": 0.0,
"step": 72
},
{
"epoch": 0.17,
"learning_rate": 9.450830153759177e-05,
"loss": 0.0,
"step": 73
},
{
"epoch": 0.17,
"learning_rate": 9.43386842960031e-05,
"loss": 0.0,
"step": 74
},
{
"epoch": 0.17,
"learning_rate": 9.416664433728748e-05,
"loss": 0.0,
"step": 75
},
{
"epoch": 0.18,
"learning_rate": 9.399219106190775e-05,
"loss": 0.0,
"step": 76
},
{
"epoch": 0.18,
"learning_rate": 9.381533400219318e-05,
"loss": 0.0,
"step": 77
},
{
"epoch": 0.18,
"learning_rate": 9.363608282181861e-05,
"loss": 0.0,
"step": 78
},
{
"epoch": 0.18,
"learning_rate": 9.345444731527642e-05,
"loss": 0.0,
"step": 79
},
{
"epoch": 0.18,
"learning_rate": 9.32704374073413e-05,
"loss": 0.0,
"step": 80
},
{
"epoch": 0.19,
"learning_rate": 9.308406315252799e-05,
"loss": 0.0172,
"step": 81
},
{
"epoch": 0.19,
"learning_rate": 9.289533473454192e-05,
"loss": 0.0,
"step": 82
},
{
"epoch": 0.19,
"learning_rate": 9.270426246572272e-05,
"loss": 0.0359,
"step": 83
},
{
"epoch": 0.19,
"learning_rate": 9.251085678648072e-05,
"loss": 0.0,
"step": 84
},
{
"epoch": 0.2,
"learning_rate": 9.23151282647265e-05,
"loss": 0.0,
"step": 85
},
{
"epoch": 0.2,
"learning_rate": 9.211708759529347e-05,
"loss": 0.0,
"step": 86
},
{
"epoch": 0.2,
"learning_rate": 9.191674559935348e-05,
"loss": 0.0001,
"step": 87
},
{
"epoch": 0.2,
"learning_rate": 9.171411322382552e-05,
"loss": 0.0,
"step": 88
},
{
"epoch": 0.21,
"learning_rate": 9.150920154077754e-05,
"loss": 0.0,
"step": 89
},
{
"epoch": 0.21,
"learning_rate": 9.130202174682155e-05,
"loss": 0.0001,
"step": 90
},
{
"epoch": 0.21,
"learning_rate": 9.109258516250172e-05,
"loss": 0.0001,
"step": 91
},
{
"epoch": 0.21,
"learning_rate": 9.08809032316759e-05,
"loss": 0.0001,
"step": 92
},
{
"epoch": 0.21,
"learning_rate": 9.066698752089029e-05,
"loss": 0.0001,
"step": 93
},
{
"epoch": 0.22,
"learning_rate": 9.045084971874738e-05,
"loss": 0.0001,
"step": 94
},
{
"epoch": 0.22,
"learning_rate": 9.023250163526731e-05,
"loss": 0.0001,
"step": 95
},
{
"epoch": 0.22,
"learning_rate": 9.001195520124255e-05,
"loss": 0.0001,
"step": 96
},
{
"epoch": 0.22,
"learning_rate": 8.978922246758606e-05,
"loss": 0.1254,
"step": 97
},
{
"epoch": 0.23,
"learning_rate": 8.956431560467267e-05,
"loss": 0.0001,
"step": 98
},
{
"epoch": 0.23,
"learning_rate": 8.933724690167417e-05,
"loss": 0.1316,
"step": 99
},
{
"epoch": 0.23,
"learning_rate": 8.910802876588781e-05,
"loss": 0.0001,
"step": 100
},
{
"epoch": 0.23,
"learning_rate": 8.887667372205839e-05,
"loss": 0.0001,
"step": 101
},
{
"epoch": 0.24,
"learning_rate": 8.864319441169373e-05,
"loss": 0.0001,
"step": 102
},
{
"epoch": 0.24,
"learning_rate": 8.840760359237412e-05,
"loss": 0.0002,
"step": 103
},
{
"epoch": 0.24,
"learning_rate": 8.816991413705516e-05,
"loss": 0.0002,
"step": 104
},
{
"epoch": 0.24,
"learning_rate": 8.793013903336428e-05,
"loss": 0.0002,
"step": 105
},
{
"epoch": 0.24,
"learning_rate": 8.768829138289124e-05,
"loss": 0.0002,
"step": 106
},
{
"epoch": 0.25,
"learning_rate": 8.744438440047206e-05,
"loss": 0.0002,
"step": 107
},
{
"epoch": 0.25,
"learning_rate": 8.719843141346718e-05,
"loss": 0.0001,
"step": 108
},
{
"epoch": 0.25,
"learning_rate": 8.695044586103296e-05,
"loss": 0.0002,
"step": 109
},
{
"epoch": 0.25,
"learning_rate": 8.670044129338761e-05,
"loss": 0.0001,
"step": 110
},
{
"epoch": 0.26,
"learning_rate": 8.644843137107059e-05,
"loss": 0.0001,
"step": 111
},
{
"epoch": 0.26,
"learning_rate": 8.61944298641963e-05,
"loss": 0.0001,
"step": 112
},
{
"epoch": 0.26,
"learning_rate": 8.593845065170164e-05,
"loss": 0.0001,
"step": 113
},
{
"epoch": 0.26,
"learning_rate": 8.568050772058762e-05,
"loss": 0.0001,
"step": 114
},
{
"epoch": 0.26,
"learning_rate": 8.542061516515512e-05,
"loss": 0.0001,
"step": 115
},
{
"epoch": 0.27,
"learning_rate": 8.515878718623473e-05,
"loss": 0.0,
"step": 116
},
{
"epoch": 0.27,
"learning_rate": 8.489503809041088e-05,
"loss": 0.1113,
"step": 117
},
{
"epoch": 0.27,
"learning_rate": 8.462938228924e-05,
"loss": 0.0,
"step": 118
},
{
"epoch": 0.27,
"learning_rate": 8.436183429846313e-05,
"loss": 0.0,
"step": 119
},
{
"epoch": 0.28,
"learning_rate": 8.409240873721277e-05,
"loss": 0.0,
"step": 120
},
{
"epoch": 0.28,
"learning_rate": 8.382112032721398e-05,
"loss": 0.0,
"step": 121
},
{
"epoch": 0.28,
"learning_rate": 8.354798389198013e-05,
"loss": 0.0,
"step": 122
},
{
"epoch": 0.28,
"learning_rate": 8.327301435600273e-05,
"loss": 0.0,
"step": 123
},
{
"epoch": 0.29,
"learning_rate": 8.299622674393614e-05,
"loss": 0.0893,
"step": 124
},
{
"epoch": 0.29,
"learning_rate": 8.271763617977641e-05,
"loss": 0.0,
"step": 125
},
{
"epoch": 0.29,
"learning_rate": 8.243725788603509e-05,
"loss": 0.0,
"step": 126
},
{
"epoch": 0.29,
"learning_rate": 8.215510718290725e-05,
"loss": 0.0,
"step": 127
},
{
"epoch": 0.29,
"learning_rate": 8.18711994874345e-05,
"loss": 0.0,
"step": 128
},
{
"epoch": 0.3,
"learning_rate": 8.158555031266254e-05,
"loss": 0.0,
"step": 129
},
{
"epoch": 0.3,
"learning_rate": 8.129817526679358e-05,
"loss": 0.0,
"step": 130
},
{
"epoch": 0.3,
"learning_rate": 8.100909005233334e-05,
"loss": 0.0,
"step": 131
},
{
"epoch": 0.3,
"learning_rate": 8.071831046523319e-05,
"loss": 0.0,
"step": 132
},
{
"epoch": 0.31,
"learning_rate": 8.042585239402697e-05,
"loss": 0.0752,
"step": 133
},
{
"epoch": 0.31,
"learning_rate": 8.013173181896283e-05,
"loss": 0.0,
"step": 134
},
{
"epoch": 0.31,
"learning_rate": 7.983596481113005e-05,
"loss": 0.0,
"step": 135
},
{
"epoch": 0.31,
"learning_rate": 7.953856753158096e-05,
"loss": 0.0,
"step": 136
},
{
"epoch": 0.32,
"learning_rate": 7.923955623044775e-05,
"loss": 0.0,
"step": 137
},
{
"epoch": 0.32,
"learning_rate": 7.893894724605469e-05,
"loss": 0.0,
"step": 138
},
{
"epoch": 0.32,
"learning_rate": 7.863675700402526e-05,
"loss": 0.0,
"step": 139
},
{
"epoch": 0.32,
"learning_rate": 7.833300201638475e-05,
"loss": 0.0,
"step": 140
},
{
"epoch": 0.32,
"learning_rate": 7.80276988806579e-05,
"loss": 0.0,
"step": 141
},
{
"epoch": 0.33,
"learning_rate": 7.772086427896211e-05,
"loss": 0.0,
"step": 142
},
{
"epoch": 0.33,
"learning_rate": 7.741251497709583e-05,
"loss": 0.0,
"step": 143
},
{
"epoch": 0.33,
"learning_rate": 7.710266782362247e-05,
"loss": 0.0,
"step": 144
},
{
"epoch": 0.33,
"learning_rate": 7.679133974894983e-05,
"loss": 0.0,
"step": 145
},
{
"epoch": 0.34,
"learning_rate": 7.647854776440496e-05,
"loss": 0.0,
"step": 146
},
{
"epoch": 0.34,
"learning_rate": 7.616430896130455e-05,
"loss": 0.0,
"step": 147
},
{
"epoch": 0.34,
"learning_rate": 7.584864051002128e-05,
"loss": 0.0,
"step": 148
},
{
"epoch": 0.34,
"learning_rate": 7.553155965904535e-05,
"loss": 0.0,
"step": 149
},
{
"epoch": 0.35,
"learning_rate": 7.521308373404217e-05,
"loss": 0.0,
"step": 150
},
{
"epoch": 0.35,
"learning_rate": 7.489323013690562e-05,
"loss": 0.0,
"step": 151
},
{
"epoch": 0.35,
"learning_rate": 7.457201634480713e-05,
"loss": 0.0,
"step": 152
},
{
"epoch": 0.35,
"learning_rate": 7.424945990924079e-05,
"loss": 0.0,
"step": 153
},
{
"epoch": 0.35,
"learning_rate": 7.392557845506432e-05,
"loss": 0.0,
"step": 154
},
{
"epoch": 0.36,
"learning_rate": 7.360038967953598e-05,
"loss": 0.0,
"step": 155
},
{
"epoch": 0.36,
"learning_rate": 7.327391135134748e-05,
"loss": 0.0,
"step": 156
},
{
"epoch": 0.36,
"learning_rate": 7.294616130965337e-05,
"loss": 0.0,
"step": 157
},
{
"epoch": 0.36,
"learning_rate": 7.261715746309595e-05,
"loss": 0.0,
"step": 158
},
{
"epoch": 0.37,
"learning_rate": 7.228691778882693e-05,
"loss": 0.0,
"step": 159
},
{
"epoch": 0.37,
"learning_rate": 7.195546033152505e-05,
"loss": 0.0,
"step": 160
},
{
"epoch": 0.37,
"learning_rate": 7.16228032024102e-05,
"loss": 0.0,
"step": 161
},
{
"epoch": 0.37,
"learning_rate": 7.128896457825364e-05,
"loss": 0.0,
"step": 162
},
{
"epoch": 0.38,
"learning_rate": 7.095396270038493e-05,
"loss": 0.0,
"step": 163
},
{
"epoch": 0.38,
"learning_rate": 7.061781587369519e-05,
"loss": 0.0,
"step": 164
},
{
"epoch": 0.38,
"learning_rate": 7.02805424656368e-05,
"loss": 0.0,
"step": 165
},
{
"epoch": 0.38,
"learning_rate": 6.994216090521991e-05,
"loss": 0.0,
"step": 166
},
{
"epoch": 0.38,
"learning_rate": 6.960268968200538e-05,
"loss": 0.0,
"step": 167
},
{
"epoch": 0.39,
"learning_rate": 6.92621473450945e-05,
"loss": 0.0,
"step": 168
},
{
"epoch": 0.39,
"learning_rate": 6.892055250211552e-05,
"loss": 0.0,
"step": 169
},
{
"epoch": 0.39,
"learning_rate": 6.857792381820672e-05,
"loss": 0.0,
"step": 170
},
{
"epoch": 0.39,
"learning_rate": 6.823428001499677e-05,
"loss": 0.0,
"step": 171
},
{
"epoch": 0.4,
"learning_rate": 6.788963986958153e-05,
"loss": 0.0,
"step": 172
},
{
"epoch": 0.4,
"learning_rate": 6.754402221349824e-05,
"loss": 0.0,
"step": 173
},
{
"epoch": 0.4,
"learning_rate": 6.719744593169641e-05,
"loss": 0.0,
"step": 174
},
{
"epoch": 0.4,
"learning_rate": 6.684992996150599e-05,
"loss": 0.0,
"step": 175
},
{
"epoch": 0.41,
"learning_rate": 6.650149329160259e-05,
"loss": 0.0,
"step": 176
},
{
"epoch": 0.41,
"learning_rate": 6.615215496096986e-05,
"loss": 0.0,
"step": 177
},
{
"epoch": 0.41,
"learning_rate": 6.580193405785938e-05,
"loss": 0.0,
"step": 178
},
{
"epoch": 0.41,
"learning_rate": 6.545084971874738e-05,
"loss": 0.0,
"step": 179
},
{
"epoch": 0.41,
"learning_rate": 6.509892112728928e-05,
"loss": 0.0,
"step": 180
},
{
"epoch": 0.42,
"learning_rate": 6.474616751327142e-05,
"loss": 0.0,
"step": 181
},
{
"epoch": 0.42,
"learning_rate": 6.439260815156039e-05,
"loss": 0.0,
"step": 182
},
{
"epoch": 0.42,
"learning_rate": 6.403826236104965e-05,
"loss": 0.0,
"step": 183
},
{
"epoch": 0.42,
"learning_rate": 6.368314950360415e-05,
"loss": 0.0,
"step": 184
},
{
"epoch": 0.43,
"learning_rate": 6.332728898300221e-05,
"loss": 0.0,
"step": 185
},
{
"epoch": 0.43,
"learning_rate": 6.297070024387535e-05,
"loss": 0.0,
"step": 186
},
{
"epoch": 0.43,
"learning_rate": 6.261340277064578e-05,
"loss": 0.0,
"step": 187
},
{
"epoch": 0.43,
"learning_rate": 6.225541608646179e-05,
"loss": 0.0,
"step": 188
},
{
"epoch": 0.44,
"learning_rate": 6.189675975213094e-05,
"loss": 0.0,
"step": 189
},
{
"epoch": 0.44,
"learning_rate": 6.153745336505125e-05,
"loss": 0.0,
"step": 190
},
{
"epoch": 0.44,
"learning_rate": 6.117751655814037e-05,
"loss": 0.0,
"step": 191
},
{
"epoch": 0.44,
"learning_rate": 6.081696899876282e-05,
"loss": 0.0,
"step": 192
},
{
"epoch": 0.44,
"learning_rate": 6.0455830387655376e-05,
"loss": 0.0,
"step": 193
},
{
"epoch": 0.45,
"learning_rate": 6.009412045785051e-05,
"loss": 0.0,
"step": 194
},
{
"epoch": 0.45,
"learning_rate": 5.973185897359828e-05,
"loss": 0.0,
"step": 195
},
{
"epoch": 0.45,
"learning_rate": 5.9369065729286245e-05,
"loss": 0.0,
"step": 196
},
{
"epoch": 0.45,
"learning_rate": 5.900576054835798e-05,
"loss": 0.0,
"step": 197
},
{
"epoch": 0.46,
"learning_rate": 5.8641963282229905e-05,
"loss": 0.0,
"step": 198
},
{
"epoch": 0.46,
"learning_rate": 5.82776938092065e-05,
"loss": 0.0,
"step": 199
},
{
"epoch": 0.46,
"learning_rate": 5.7912972033394195e-05,
"loss": 0.0,
"step": 200
},
{
"epoch": 0.46,
"learning_rate": 5.7547817883613764e-05,
"loss": 0.0358,
"step": 201
},
{
"epoch": 0.47,
"learning_rate": 5.718225131231142e-05,
"loss": 0.0,
"step": 202
},
{
"epoch": 0.47,
"learning_rate": 5.6816292294468495e-05,
"loss": 0.0,
"step": 203
},
{
"epoch": 0.47,
"learning_rate": 5.644996082651017e-05,
"loss": 0.0676,
"step": 204
},
{
"epoch": 0.47,
"learning_rate": 5.6083276925212624e-05,
"loss": 0.0,
"step": 205
},
{
"epoch": 0.47,
"learning_rate": 5.571626062660946e-05,
"loss": 0.0,
"step": 206
},
{
"epoch": 0.48,
"learning_rate": 5.5348931984896836e-05,
"loss": 0.0,
"step": 207
},
{
"epoch": 0.48,
"learning_rate": 5.49813110713377e-05,
"loss": 0.0743,
"step": 208
},
{
"epoch": 0.48,
"learning_rate": 5.4613417973165106e-05,
"loss": 0.0,
"step": 209
},
{
"epoch": 0.48,
"learning_rate": 5.4245272792484524e-05,
"loss": 0.0,
"step": 210
},
{
"epoch": 0.49,
"learning_rate": 5.387689564517558e-05,
"loss": 0.0,
"step": 211
},
{
"epoch": 0.49,
"learning_rate": 5.3508306659792764e-05,
"loss": 0.0,
"step": 212
},
{
"epoch": 0.49,
"learning_rate": 5.313952597646568e-05,
"loss": 0.0,
"step": 213
},
{
"epoch": 0.49,
"learning_rate": 5.27705737457985e-05,
"loss": 0.0,
"step": 214
},
{
"epoch": 0.5,
"learning_rate": 5.240147012776899e-05,
"loss": 0.0,
"step": 215
},
{
"epoch": 0.5,
"learning_rate": 5.203223529062684e-05,
"loss": 0.0,
"step": 216
},
{
"epoch": 0.5,
"learning_rate": 5.166288940979175e-05,
"loss": 0.0,
"step": 217
},
{
"epoch": 0.5,
"learning_rate": 5.129345266675095e-05,
"loss": 0.0,
"step": 218
},
{
"epoch": 0.5,
"learning_rate": 5.092394524795649e-05,
"loss": 0.0,
"step": 219
},
{
"epoch": 0.51,
"learning_rate": 5.055438734372225e-05,
"loss": 0.0,
"step": 220
},
{
"epoch": 0.51,
"learning_rate": 5.0184799147120656e-05,
"loss": 0.0,
"step": 221
},
{
"epoch": 0.51,
"learning_rate": 4.981520085287935e-05,
"loss": 0.0,
"step": 222
},
{
"epoch": 0.51,
"learning_rate": 4.944561265627776e-05,
"loss": 0.0625,
"step": 223
},
{
"epoch": 0.52,
"learning_rate": 4.907605475204352e-05,
"loss": 0.0,
"step": 224
},
{
"epoch": 0.52,
"learning_rate": 4.870654733324907e-05,
"loss": 0.0,
"step": 225
},
{
"epoch": 0.52,
"learning_rate": 4.833711059020826e-05,
"loss": 0.0,
"step": 226
},
{
"epoch": 0.52,
"learning_rate": 4.796776470937317e-05,
"loss": 0.0,
"step": 227
},
{
"epoch": 0.53,
"learning_rate": 4.759852987223103e-05,
"loss": 0.0,
"step": 228
},
{
"epoch": 0.53,
"learning_rate": 4.72294262542015e-05,
"loss": 0.0,
"step": 229
},
{
"epoch": 0.53,
"learning_rate": 4.6860474023534335e-05,
"loss": 0.0,
"step": 230
},
{
"epoch": 0.53,
"learning_rate": 4.6491693340207254e-05,
"loss": 0.0,
"step": 231
},
{
"epoch": 0.53,
"learning_rate": 4.612310435482443e-05,
"loss": 0.0,
"step": 232
},
{
"epoch": 0.54,
"learning_rate": 4.575472720751547e-05,
"loss": 0.0,
"step": 233
},
{
"epoch": 0.54,
"learning_rate": 4.5386582026834906e-05,
"loss": 0.0,
"step": 234
},
{
"epoch": 0.54,
"learning_rate": 4.50186889286623e-05,
"loss": 0.0,
"step": 235
},
{
"epoch": 0.54,
"learning_rate": 4.465106801510319e-05,
"loss": 0.0,
"step": 236
},
{
"epoch": 0.55,
"learning_rate": 4.428373937339055e-05,
"loss": 0.0,
"step": 237
},
{
"epoch": 0.55,
"learning_rate": 4.391672307478739e-05,
"loss": 0.0,
"step": 238
},
{
"epoch": 0.55,
"learning_rate": 4.3550039173489845e-05,
"loss": 0.0,
"step": 239
},
{
"epoch": 0.55,
"learning_rate": 4.3183707705531496e-05,
"loss": 0.0,
"step": 240
},
{
"epoch": 0.56,
"learning_rate": 4.2817748687688594e-05,
"loss": 0.0,
"step": 241
},
{
"epoch": 0.56,
"learning_rate": 4.245218211638624e-05,
"loss": 0.0,
"step": 242
},
{
"epoch": 0.56,
"learning_rate": 4.2087027966605816e-05,
"loss": 0.0,
"step": 243
},
{
"epoch": 0.56,
"learning_rate": 4.1722306190793495e-05,
"loss": 0.0,
"step": 244
},
{
"epoch": 0.56,
"learning_rate": 4.135803671777011e-05,
"loss": 0.0,
"step": 245
},
{
"epoch": 0.57,
"learning_rate": 4.099423945164203e-05,
"loss": 0.0,
"step": 246
},
{
"epoch": 0.57,
"learning_rate": 4.063093427071376e-05,
"loss": 0.0,
"step": 247
},
{
"epoch": 0.57,
"learning_rate": 4.026814102640173e-05,
"loss": 0.0,
"step": 248
},
{
"epoch": 0.57,
"learning_rate": 3.99058795421495e-05,
"loss": 0.0,
"step": 249
},
{
"epoch": 0.58,
"learning_rate": 3.9544169612344636e-05,
"loss": 0.0,
"step": 250
},
{
"epoch": 0.58,
"learning_rate": 3.918303100123718e-05,
"loss": 0.0,
"step": 251
},
{
"epoch": 0.58,
"learning_rate": 3.8822483441859646e-05,
"loss": 0.0,
"step": 252
},
{
"epoch": 0.58,
"learning_rate": 3.8462546634948764e-05,
"loss": 0.0,
"step": 253
},
{
"epoch": 0.59,
"learning_rate": 3.8103240247869075e-05,
"loss": 0.0,
"step": 254
},
{
"epoch": 0.59,
"learning_rate": 3.774458391353821e-05,
"loss": 0.0,
"step": 255
},
{
"epoch": 0.59,
"learning_rate": 3.7386597229354225e-05,
"loss": 0.0,
"step": 256
},
{
"epoch": 0.59,
"learning_rate": 3.702929975612467e-05,
"loss": 0.0,
"step": 257
},
{
"epoch": 0.59,
"learning_rate": 3.66727110169978e-05,
"loss": 0.0,
"step": 258
},
{
"epoch": 0.6,
"learning_rate": 3.631685049639586e-05,
"loss": 0.0,
"step": 259
},
{
"epoch": 0.6,
"learning_rate": 3.5961737638950365e-05,
"loss": 0.0,
"step": 260
},
{
"epoch": 0.6,
"learning_rate": 3.560739184843963e-05,
"loss": 0.0,
"step": 261
},
{
"epoch": 0.6,
"learning_rate": 3.525383248672857e-05,
"loss": 0.0,
"step": 262
},
{
"epoch": 0.61,
"learning_rate": 3.4901078872710734e-05,
"loss": 0.0,
"step": 263
},
{
"epoch": 0.61,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.0,
"step": 264
},
{
"epoch": 0.61,
"learning_rate": 3.419806594214063e-05,
"loss": 0.0,
"step": 265
},
{
"epoch": 0.61,
"learning_rate": 3.3847845039030134e-05,
"loss": 0.0,
"step": 266
},
{
"epoch": 0.62,
"learning_rate": 3.349850670839744e-05,
"loss": 0.0,
"step": 267
},
{
"epoch": 0.62,
"learning_rate": 3.315007003849403e-05,
"loss": 0.0,
"step": 268
},
{
"epoch": 0.62,
"learning_rate": 3.2802554068303596e-05,
"loss": 0.0971,
"step": 269
},
{
"epoch": 0.62,
"learning_rate": 3.245597778650176e-05,
"loss": 0.0,
"step": 270
},
{
"epoch": 0.62,
"learning_rate": 3.2110360130418483e-05,
"loss": 0.0976,
"step": 271
},
{
"epoch": 0.63,
"learning_rate": 3.176571998500325e-05,
"loss": 0.0,
"step": 272
},
{
"epoch": 0.63,
"learning_rate": 3.142207618179327e-05,
"loss": 0.0,
"step": 273
},
{
"epoch": 0.63,
"learning_rate": 3.107944749788449e-05,
"loss": 0.0,
"step": 274
},
{
"epoch": 0.63,
"learning_rate": 3.0737852654905497e-05,
"loss": 0.0,
"step": 275
},
{
"epoch": 0.64,
"learning_rate": 3.0397310317994622e-05,
"loss": 0.0,
"step": 276
},
{
"epoch": 0.64,
"learning_rate": 3.0057839094780106e-05,
"loss": 0.0,
"step": 277
},
{
"epoch": 0.64,
"learning_rate": 2.9719457534363225e-05,
"loss": 0.0,
"step": 278
},
{
"epoch": 0.64,
"learning_rate": 2.9382184126304834e-05,
"loss": 0.0,
"step": 279
},
{
"epoch": 0.65,
"learning_rate": 2.904603729961508e-05,
"loss": 0.0,
"step": 280
},
{
"epoch": 0.65,
"learning_rate": 2.8711035421746367e-05,
"loss": 0.0,
"step": 281
},
{
"epoch": 0.65,
"learning_rate": 2.837719679758981e-05,
"loss": 0.0,
"step": 282
},
{
"epoch": 0.65,
"learning_rate": 2.804453966847497e-05,
"loss": 0.0,
"step": 283
},
{
"epoch": 0.65,
"learning_rate": 2.771308221117309e-05,
"loss": 0.0,
"step": 284
},
{
"epoch": 0.66,
"learning_rate": 2.7382842536904075e-05,
"loss": 0.0,
"step": 285
},
{
"epoch": 0.66,
"learning_rate": 2.705383869034664e-05,
"loss": 0.0,
"step": 286
},
{
"epoch": 0.66,
"learning_rate": 2.6726088648652503e-05,
"loss": 0.0,
"step": 287
},
{
"epoch": 0.66,
"learning_rate": 2.639961032046404e-05,
"loss": 0.0172,
"step": 288
},
{
"epoch": 0.67,
"learning_rate": 2.607442154493568e-05,
"loss": 0.0,
"step": 289
},
{
"epoch": 0.67,
"learning_rate": 2.5750540090759224e-05,
"loss": 0.0252,
"step": 290
},
{
"epoch": 0.67,
"learning_rate": 2.5427983655192888e-05,
"loss": 0.0015,
"step": 291
},
{
"epoch": 0.67,
"learning_rate": 2.5106769863094386e-05,
"loss": 0.0,
"step": 292
},
{
"epoch": 0.68,
"learning_rate": 2.4786916265957834e-05,
"loss": 0.0,
"step": 293
},
{
"epoch": 0.68,
"learning_rate": 2.446844034095466e-05,
"loss": 0.0,
"step": 294
},
{
"epoch": 0.68,
"learning_rate": 2.4151359489978733e-05,
"loss": 0.0,
"step": 295
},
{
"epoch": 0.68,
"learning_rate": 2.3835691038695462e-05,
"loss": 0.0001,
"step": 296
},
{
"epoch": 0.68,
"learning_rate": 2.3521452235595066e-05,
"loss": 0.0001,
"step": 297
},
{
"epoch": 0.69,
"learning_rate": 2.3208660251050158e-05,
"loss": 0.0001,
"step": 298
},
{
"epoch": 0.69,
"learning_rate": 2.2897332176377528e-05,
"loss": 0.0,
"step": 299
},
{
"epoch": 0.69,
"learning_rate": 2.2587485022904187e-05,
"loss": 0.0,
"step": 300
},
{
"epoch": 0.69,
"learning_rate": 2.2279135721037908e-05,
"loss": 0.0,
"step": 301
},
{
"epoch": 0.7,
"learning_rate": 2.197230111934211e-05,
"loss": 0.0,
"step": 302
},
{
"epoch": 0.7,
"learning_rate": 2.166699798361527e-05,
"loss": 0.0,
"step": 303
},
{
"epoch": 0.7,
"learning_rate": 2.136324299597474e-05,
"loss": 0.0,
"step": 304
},
{
"epoch": 0.7,
"learning_rate": 2.106105275394533e-05,
"loss": 0.0,
"step": 305
},
{
"epoch": 0.71,
"learning_rate": 2.0760443769552258e-05,
"loss": 0.0,
"step": 306
},
{
"epoch": 0.71,
"learning_rate": 2.046143246841906e-05,
"loss": 0.0,
"step": 307
},
{
"epoch": 0.71,
"learning_rate": 2.0164035188869968e-05,
"loss": 0.0,
"step": 308
},
{
"epoch": 0.71,
"learning_rate": 1.9868268181037185e-05,
"loss": 0.0,
"step": 309
},
{
"epoch": 0.71,
"learning_rate": 1.957414760597303e-05,
"loss": 0.0,
"step": 310
},
{
"epoch": 0.72,
"learning_rate": 1.9281689534766813e-05,
"loss": 0.0,
"step": 311
},
{
"epoch": 0.72,
"learning_rate": 1.8990909947666668e-05,
"loss": 0.0,
"step": 312
},
{
"epoch": 0.72,
"learning_rate": 1.870182473320642e-05,
"loss": 0.0,
"step": 313
},
{
"epoch": 0.72,
"learning_rate": 1.8414449687337464e-05,
"loss": 0.0,
"step": 314
},
{
"epoch": 0.73,
"learning_rate": 1.8128800512565513e-05,
"loss": 0.0,
"step": 315
},
{
"epoch": 0.73,
"learning_rate": 1.7844892817092756e-05,
"loss": 0.0,
"step": 316
},
{
"epoch": 0.73,
"learning_rate": 1.7562742113964914e-05,
"loss": 0.0,
"step": 317
},
{
"epoch": 0.73,
"learning_rate": 1.728236382022359e-05,
"loss": 0.0,
"step": 318
},
{
"epoch": 0.74,
"learning_rate": 1.700377325606388e-05,
"loss": 0.0,
"step": 319
},
{
"epoch": 0.74,
"learning_rate": 1.6726985643997273e-05,
"loss": 0.0,
"step": 320
},
{
"epoch": 0.74,
"learning_rate": 1.645201610801988e-05,
"loss": 0.0,
"step": 321
},
{
"epoch": 0.74,
"learning_rate": 1.617887967278602e-05,
"loss": 0.0,
"step": 322
},
{
"epoch": 0.74,
"learning_rate": 1.5907591262787247e-05,
"loss": 0.0,
"step": 323
},
{
"epoch": 0.75,
"learning_rate": 1.5638165701536868e-05,
"loss": 0.0,
"step": 324
},
{
"epoch": 0.75,
"learning_rate": 1.5370617710760004e-05,
"loss": 0.0221,
"step": 325
},
{
"epoch": 0.75,
"learning_rate": 1.5104961909589116e-05,
"loss": 0.0,
"step": 326
},
{
"epoch": 0.75,
"learning_rate": 1.4841212813765255e-05,
"loss": 0.0,
"step": 327
},
{
"epoch": 0.76,
"learning_rate": 1.457938483484489e-05,
"loss": 0.0,
"step": 328
},
{
"epoch": 0.76,
"learning_rate": 1.4319492279412388e-05,
"loss": 0.0,
"step": 329
},
{
"epoch": 0.76,
"learning_rate": 1.4061549348298376e-05,
"loss": 0.0,
"step": 330
},
{
"epoch": 0.76,
"learning_rate": 1.3805570135803708e-05,
"loss": 0.0,
"step": 331
},
{
"epoch": 0.76,
"learning_rate": 1.3551568628929434e-05,
"loss": 0.0,
"step": 332
},
{
"epoch": 0.77,
"learning_rate": 1.3299558706612409e-05,
"loss": 0.0,
"step": 333
},
{
"epoch": 0.77,
"learning_rate": 1.3049554138967051e-05,
"loss": 0.0,
"step": 334
},
{
"epoch": 0.77,
"learning_rate": 1.2801568586532837e-05,
"loss": 0.0,
"step": 335
},
{
"epoch": 0.77,
"learning_rate": 1.2555615599527948e-05,
"loss": 0.0,
"step": 336
},
{
"epoch": 0.78,
"learning_rate": 1.231170861710879e-05,
"loss": 0.0,
"step": 337
},
{
"epoch": 0.78,
"learning_rate": 1.2069860966635732e-05,
"loss": 0.0,
"step": 338
},
{
"epoch": 0.78,
"learning_rate": 1.183008586294485e-05,
"loss": 0.0,
"step": 339
},
{
"epoch": 0.78,
"learning_rate": 1.1592396407625883e-05,
"loss": 0.0,
"step": 340
},
{
"epoch": 0.79,
"learning_rate": 1.1356805588306291e-05,
"loss": 0.0209,
"step": 341
},
{
"epoch": 0.79,
"learning_rate": 1.1123326277941626e-05,
"loss": 0.0,
"step": 342
},
{
"epoch": 0.79,
"learning_rate": 1.0891971234112191e-05,
"loss": 0.0,
"step": 343
},
{
"epoch": 0.79,
"learning_rate": 1.066275309832584e-05,
"loss": 0.0,
"step": 344
},
{
"epoch": 0.79,
"learning_rate": 1.043568439532735e-05,
"loss": 0.0124,
"step": 345
},
{
"epoch": 0.8,
"learning_rate": 1.0210777532413939e-05,
"loss": 0.0,
"step": 346
},
{
"epoch": 0.8,
"learning_rate": 9.988044798757452e-06,
"loss": 0.0,
"step": 347
},
{
"epoch": 0.8,
"learning_rate": 9.767498364732713e-06,
"loss": 0.0,
"step": 348
},
{
"epoch": 0.8,
"learning_rate": 9.549150281252633e-06,
"loss": 0.0,
"step": 349
},
{
"epoch": 0.81,
"learning_rate": 9.333012479109704e-06,
"loss": 0.0,
"step": 350
},
{
"epoch": 0.81,
"learning_rate": 9.119096768324097e-06,
"loss": 0.0,
"step": 351
},
{
"epoch": 0.81,
"learning_rate": 8.907414837498296e-06,
"loss": 0.0,
"step": 352
},
{
"epoch": 0.81,
"learning_rate": 8.697978253178468e-06,
"loss": 0.0,
"step": 353
},
{
"epoch": 0.82,
"learning_rate": 8.490798459222476e-06,
"loss": 0.0,
"step": 354
},
{
"epoch": 0.82,
"learning_rate": 8.2858867761745e-06,
"loss": 0.0,
"step": 355
},
{
"epoch": 0.82,
"learning_rate": 8.083254400646506e-06,
"loss": 0.0,
"step": 356
},
{
"epoch": 0.82,
"learning_rate": 7.882912404706528e-06,
"loss": 0.0,
"step": 357
},
{
"epoch": 0.82,
"learning_rate": 7.684871735273513e-06,
"loss": 0.0,
"step": 358
},
{
"epoch": 0.83,
"learning_rate": 7.489143213519301e-06,
"loss": 0.0,
"step": 359
},
{
"epoch": 0.83,
"learning_rate": 7.295737534277286e-06,
"loss": 0.0,
"step": 360
},
{
"epoch": 0.83,
"learning_rate": 7.104665265458083e-06,
"loss": 0.0,
"step": 361
},
{
"epoch": 0.83,
"learning_rate": 6.9159368474720155e-06,
"loss": 0.0,
"step": 362
},
{
"epoch": 0.84,
"learning_rate": 6.729562592658717e-06,
"loss": 0.0,
"step": 363
},
{
"epoch": 0.84,
"learning_rate": 6.5455526847235825e-06,
"loss": 0.0,
"step": 364
},
{
"epoch": 0.84,
"learning_rate": 6.363917178181389e-06,
"loss": 0.0,
"step": 365
},
{
"epoch": 0.84,
"learning_rate": 6.184665997806832e-06,
"loss": 0.0,
"step": 366
},
{
"epoch": 0.85,
"learning_rate": 6.007808938092263e-06,
"loss": 0.0,
"step": 367
},
{
"epoch": 0.85,
"learning_rate": 5.833355662712525e-06,
"loss": 0.0,
"step": 368
},
{
"epoch": 0.85,
"learning_rate": 5.6613157039969055e-06,
"loss": 0.0,
"step": 369
},
{
"epoch": 0.85,
"learning_rate": 5.49169846240824e-06,
"loss": 0.0,
"step": 370
},
{
"epoch": 0.85,
"learning_rate": 5.3245132060292915e-06,
"loss": 0.0,
"step": 371
},
{
"epoch": 0.86,
"learning_rate": 5.159769070056364e-06,
"loss": 0.0,
"step": 372
},
{
"epoch": 0.86,
"learning_rate": 4.997475056300077e-06,
"loss": 0.0,
"step": 373
},
{
"epoch": 0.86,
"learning_rate": 4.837640032693558e-06,
"loss": 0.0,
"step": 374
},
{
"epoch": 0.86,
"learning_rate": 4.680272732807834e-06,
"loss": 0.0,
"step": 375
},
{
"epoch": 0.87,
"learning_rate": 4.52538175537468e-06,
"loss": 0.0,
"step": 376
},
{
"epoch": 0.87,
"learning_rate": 4.372975563816706e-06,
"loss": 0.0,
"step": 377
},
{
"epoch": 0.87,
"learning_rate": 4.223062485784945e-06,
"loss": 0.0,
"step": 378
},
{
"epoch": 0.87,
"learning_rate": 4.075650712703849e-06,
"loss": 0.0,
"step": 379
},
{
"epoch": 0.88,
"learning_rate": 3.930748299323639e-06,
"loss": 0.0,
"step": 380
},
{
"epoch": 0.88,
"learning_rate": 3.788363163280212e-06,
"loss": 0.0,
"step": 381
},
{
"epoch": 0.88,
"learning_rate": 3.6485030846625077e-06,
"loss": 0.0,
"step": 382
},
{
"epoch": 0.88,
"learning_rate": 3.511175705587433e-06,
"loss": 0.0,
"step": 383
},
{
"epoch": 0.88,
"learning_rate": 3.376388529782215e-06,
"loss": 0.0,
"step": 384
},
{
"epoch": 0.89,
"learning_rate": 3.244148922174445e-06,
"loss": 0.0,
"step": 385
},
{
"epoch": 0.89,
"learning_rate": 3.1144641084896285e-06,
"loss": 0.0,
"step": 386
},
{
"epoch": 0.89,
"learning_rate": 2.987341174856395e-06,
"loss": 0.0,
"step": 387
},
{
"epoch": 0.89,
"learning_rate": 2.862787067419237e-06,
"loss": 0.0,
"step": 388
},
{
"epoch": 0.9,
"learning_rate": 2.7408085919590264e-06,
"loss": 0.0,
"step": 389
},
{
"epoch": 0.9,
"learning_rate": 2.6214124135211184e-06,
"loss": 0.0,
"step": 390
},
{
"epoch": 0.9,
"learning_rate": 2.504605056051146e-06,
"loss": 0.0,
"step": 391
},
{
"epoch": 0.9,
"learning_rate": 2.3903929020385962e-06,
"loss": 0.0,
"step": 392
},
{
"epoch": 0.91,
"learning_rate": 2.2787821921679885e-06,
"loss": 0.0,
"step": 393
},
{
"epoch": 0.91,
"learning_rate": 2.1697790249779636e-06,
"loss": 0.0,
"step": 394
},
{
"epoch": 0.91,
"learning_rate": 2.0633893565279615e-06,
"loss": 0.0,
"step": 395
},
{
"epoch": 0.91,
"learning_rate": 1.9596190000728433e-06,
"loss": 0.0,
"step": 396
},
{
"epoch": 0.91,
"learning_rate": 1.8584736257452272e-06,
"loss": 0.0,
"step": 397
},
{
"epoch": 0.92,
"learning_rate": 1.7599587602456559e-06,
"loss": 0.0,
"step": 398
},
{
"epoch": 0.92,
"learning_rate": 1.6640797865406288e-06,
"loss": 0.0,
"step": 399
},
{
"epoch": 0.92,
"learning_rate": 1.5708419435684462e-06,
"loss": 0.0,
"step": 400
},
{
"epoch": 0.92,
"learning_rate": 1.4802503259529753e-06,
"loss": 0.0,
"step": 401
},
{
"epoch": 0.93,
"learning_rate": 1.3923098837252457e-06,
"loss": 0.0,
"step": 402
},
{
"epoch": 0.93,
"learning_rate": 1.307025422053021e-06,
"loss": 0.0,
"step": 403
},
{
"epoch": 0.93,
"learning_rate": 1.2244016009781701e-06,
"loss": 0.0,
"step": 404
},
{
"epoch": 0.93,
"learning_rate": 1.1444429351620933e-06,
"loss": 0.0,
"step": 405
},
{
"epoch": 0.94,
"learning_rate": 1.0671537936390198e-06,
"loss": 0.0,
"step": 406
},
{
"epoch": 0.94,
"learning_rate": 9.92538399577264e-07,
"loss": 0.0,
"step": 407
},
{
"epoch": 0.94,
"learning_rate": 9.206008300484848e-07,
"loss": 0.0,
"step": 408
},
{
"epoch": 0.94,
"learning_rate": 8.513450158049108e-07,
"loss": 0.0,
"step": 409
},
{
"epoch": 0.94,
"learning_rate": 7.847747410645368e-07,
"loss": 0.0,
"step": 410
},
{
"epoch": 0.95,
"learning_rate": 7.208936433043767e-07,
"loss": 0.0,
"step": 411
},
{
"epoch": 0.95,
"learning_rate": 6.597052130616899e-07,
"loss": 0.0,
"step": 412
},
{
"epoch": 0.95,
"learning_rate": 6.012127937432554e-07,
"loss": 0.0,
"step": 413
},
{
"epoch": 0.95,
"learning_rate": 5.454195814427021e-07,
"loss": 0.0,
"step": 414
},
{
"epoch": 0.96,
"learning_rate": 4.923286247658476e-07,
"loss": 0.0,
"step": 415
},
{
"epoch": 0.96,
"learning_rate": 4.419428246641377e-07,
"loss": 0.0,
"step": 416
},
{
"epoch": 0.96,
"learning_rate": 3.9426493427611177e-07,
"loss": 0.0,
"step": 417
},
{
"epoch": 0.96,
"learning_rate": 3.492975587769898e-07,
"loss": 0.0,
"step": 418
},
{
"epoch": 0.97,
"learning_rate": 3.0704315523631953e-07,
"loss": 0.0,
"step": 419
},
{
"epoch": 0.97,
"learning_rate": 2.6750403248370636e-07,
"loss": 0.0,
"step": 420
},
{
"epoch": 0.97,
"learning_rate": 2.3068235098266944e-07,
"loss": 0.0,
"step": 421
},
{
"epoch": 0.97,
"learning_rate": 1.9658012271259185e-07,
"loss": 0.0,
"step": 422
},
{
"epoch": 0.97,
"learning_rate": 1.6519921105876412e-07,
"loss": 0.0,
"step": 423
},
{
"epoch": 0.98,
"learning_rate": 1.3654133071059893e-07,
"loss": 0.0,
"step": 424
},
{
"epoch": 0.98,
"learning_rate": 1.1060804756790055e-07,
"loss": 0.0,
"step": 425
},
{
"epoch": 0.98,
"learning_rate": 8.740077865534435e-08,
"loss": 0.0,
"step": 426
},
{
"epoch": 0.98,
"learning_rate": 6.692079204500545e-08,
"loss": 0.0,
"step": 427
},
{
"epoch": 0.99,
"learning_rate": 4.916920678710857e-08,
"loss": 0.0499,
"step": 428
},
{
"epoch": 0.99,
"learning_rate": 3.4146992848854695e-08,
"loss": 0.0,
"step": 429
},
{
"epoch": 0.99,
"learning_rate": 2.1854971061435747e-08,
"loss": 0.0,
"step": 430
},
{
"epoch": 0.99,
"learning_rate": 1.2293813075175963e-08,
"loss": 0.0,
"step": 431
},
{
"epoch": 1.0,
"learning_rate": 5.464041322833513e-09,
"loss": 0.0658,
"step": 432
},
{
"epoch": 1.0,
"learning_rate": 1.366028991062196e-09,
"loss": 0.0473,
"step": 433
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 0.0,
"step": 434
},
{
"epoch": 1.0,
"step": 434,
"total_flos": 510790631161856.0,
"train_loss": 0.04482437436082502,
"train_runtime": 12466.6764,
"train_samples_per_second": 2.227,
"train_steps_per_second": 0.035
}
],
"logging_steps": 1.0,
"max_steps": 434,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50000,
"total_flos": 510790631161856.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}