VTGenerator-Pretrained-13B / trainer_state.json
HenryHZY's picture
Upload folder using huggingface_hub
41fc03b verified
Raw
History Blame Contribute Delete
187 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"global_step": 1550,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.2553191489361704e-07,
"loss": 0.2252,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 8.510638297872341e-07,
"loss": 1.2823,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 1.276595744680851e-06,
"loss": 1.3026,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 1.7021276595744682e-06,
"loss": 1.3168,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 2.1276595744680853e-06,
"loss": 0.2487,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 2.553191489361702e-06,
"loss": 1.2707,
"step": 6
},
{
"epoch": 0.0,
"learning_rate": 2.978723404255319e-06,
"loss": 1.2973,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 3.4042553191489363e-06,
"loss": 1.2575,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 3.8297872340425535e-06,
"loss": 1.2083,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 4.255319148936171e-06,
"loss": 1.1949,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 4.680851063829788e-06,
"loss": 1.1814,
"step": 11
},
{
"epoch": 0.01,
"learning_rate": 5.106382978723404e-06,
"loss": 1.142,
"step": 12
},
{
"epoch": 0.01,
"learning_rate": 5.531914893617022e-06,
"loss": 0.2309,
"step": 13
},
{
"epoch": 0.01,
"learning_rate": 5.957446808510638e-06,
"loss": 1.1687,
"step": 14
},
{
"epoch": 0.01,
"learning_rate": 6.382978723404256e-06,
"loss": 1.1634,
"step": 15
},
{
"epoch": 0.01,
"learning_rate": 6.808510638297873e-06,
"loss": 1.1207,
"step": 16
},
{
"epoch": 0.01,
"learning_rate": 7.234042553191491e-06,
"loss": 0.223,
"step": 17
},
{
"epoch": 0.01,
"learning_rate": 7.659574468085107e-06,
"loss": 1.1133,
"step": 18
},
{
"epoch": 0.01,
"learning_rate": 8.085106382978723e-06,
"loss": 0.2492,
"step": 19
},
{
"epoch": 0.01,
"learning_rate": 8.510638297872341e-06,
"loss": 1.1058,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 8.936170212765958e-06,
"loss": 1.0892,
"step": 21
},
{
"epoch": 0.01,
"learning_rate": 9.361702127659576e-06,
"loss": 1.1425,
"step": 22
},
{
"epoch": 0.01,
"learning_rate": 9.787234042553192e-06,
"loss": 0.2262,
"step": 23
},
{
"epoch": 0.02,
"learning_rate": 1.0212765957446808e-05,
"loss": 0.2521,
"step": 24
},
{
"epoch": 0.02,
"learning_rate": 1.0638297872340426e-05,
"loss": 1.0762,
"step": 25
},
{
"epoch": 0.02,
"learning_rate": 1.1063829787234044e-05,
"loss": 1.1283,
"step": 26
},
{
"epoch": 0.02,
"learning_rate": 1.1489361702127662e-05,
"loss": 1.108,
"step": 27
},
{
"epoch": 0.02,
"learning_rate": 1.1914893617021277e-05,
"loss": 0.2265,
"step": 28
},
{
"epoch": 0.02,
"learning_rate": 1.2340425531914895e-05,
"loss": 0.2239,
"step": 29
},
{
"epoch": 0.02,
"learning_rate": 1.2765957446808513e-05,
"loss": 1.0251,
"step": 30
},
{
"epoch": 0.02,
"learning_rate": 1.3191489361702127e-05,
"loss": 1.1263,
"step": 31
},
{
"epoch": 0.02,
"learning_rate": 1.3617021276595745e-05,
"loss": 1.0823,
"step": 32
},
{
"epoch": 0.02,
"learning_rate": 1.4042553191489363e-05,
"loss": 1.0823,
"step": 33
},
{
"epoch": 0.02,
"learning_rate": 1.4468085106382981e-05,
"loss": 1.0479,
"step": 34
},
{
"epoch": 0.02,
"learning_rate": 1.4893617021276596e-05,
"loss": 0.227,
"step": 35
},
{
"epoch": 0.02,
"learning_rate": 1.5319148936170214e-05,
"loss": 1.0303,
"step": 36
},
{
"epoch": 0.02,
"learning_rate": 1.5744680851063832e-05,
"loss": 1.0576,
"step": 37
},
{
"epoch": 0.02,
"learning_rate": 1.6170212765957446e-05,
"loss": 1.0536,
"step": 38
},
{
"epoch": 0.03,
"learning_rate": 1.6595744680851064e-05,
"loss": 1.0688,
"step": 39
},
{
"epoch": 0.03,
"learning_rate": 1.7021276595744682e-05,
"loss": 1.0671,
"step": 40
},
{
"epoch": 0.03,
"learning_rate": 1.74468085106383e-05,
"loss": 0.2009,
"step": 41
},
{
"epoch": 0.03,
"learning_rate": 1.7872340425531915e-05,
"loss": 1.0471,
"step": 42
},
{
"epoch": 0.03,
"learning_rate": 1.8297872340425533e-05,
"loss": 1.0178,
"step": 43
},
{
"epoch": 0.03,
"learning_rate": 1.872340425531915e-05,
"loss": 0.2019,
"step": 44
},
{
"epoch": 0.03,
"learning_rate": 1.914893617021277e-05,
"loss": 1.0846,
"step": 45
},
{
"epoch": 0.03,
"learning_rate": 1.9574468085106384e-05,
"loss": 1.0466,
"step": 46
},
{
"epoch": 0.03,
"learning_rate": 2e-05,
"loss": 0.1999,
"step": 47
},
{
"epoch": 0.03,
"learning_rate": 1.9999978155021058e-05,
"loss": 1.0693,
"step": 48
},
{
"epoch": 0.03,
"learning_rate": 1.9999912620179666e-05,
"loss": 1.0236,
"step": 49
},
{
"epoch": 0.03,
"learning_rate": 1.999980339576215e-05,
"loss": 1.0807,
"step": 50
},
{
"epoch": 0.03,
"learning_rate": 1.999965048224571e-05,
"loss": 0.1916,
"step": 51
},
{
"epoch": 0.03,
"learning_rate": 1.9999453880298423e-05,
"loss": 0.2281,
"step": 52
},
{
"epoch": 0.03,
"learning_rate": 1.9999213590779245e-05,
"loss": 1.0058,
"step": 53
},
{
"epoch": 0.03,
"learning_rate": 1.9998929614738e-05,
"loss": 1.0485,
"step": 54
},
{
"epoch": 0.04,
"learning_rate": 1.9998601953415374e-05,
"loss": 1.0596,
"step": 55
},
{
"epoch": 0.04,
"learning_rate": 1.9998230608242917e-05,
"loss": 0.2309,
"step": 56
},
{
"epoch": 0.04,
"learning_rate": 1.9997815580843043e-05,
"loss": 1.0572,
"step": 57
},
{
"epoch": 0.04,
"learning_rate": 1.9997356873028994e-05,
"loss": 1.0487,
"step": 58
},
{
"epoch": 0.04,
"learning_rate": 1.9996854486804874e-05,
"loss": 1.0403,
"step": 59
},
{
"epoch": 0.04,
"learning_rate": 1.9996308424365596e-05,
"loss": 1.0248,
"step": 60
},
{
"epoch": 0.04,
"learning_rate": 1.999571868809691e-05,
"loss": 0.2435,
"step": 61
},
{
"epoch": 0.04,
"learning_rate": 1.999508528057537e-05,
"loss": 1.0471,
"step": 62
},
{
"epoch": 0.04,
"learning_rate": 1.9994408204568335e-05,
"loss": 1.0297,
"step": 63
},
{
"epoch": 0.04,
"learning_rate": 1.999368746303394e-05,
"loss": 1.0528,
"step": 64
},
{
"epoch": 0.04,
"learning_rate": 1.9992923059121107e-05,
"loss": 1.0331,
"step": 65
},
{
"epoch": 0.04,
"learning_rate": 1.9992114996169506e-05,
"loss": 0.235,
"step": 66
},
{
"epoch": 0.04,
"learning_rate": 1.9991263277709572e-05,
"loss": 1.0164,
"step": 67
},
{
"epoch": 0.04,
"learning_rate": 1.999036790746245e-05,
"loss": 1.0219,
"step": 68
},
{
"epoch": 0.04,
"learning_rate": 1.9989428889340016e-05,
"loss": 1.0205,
"step": 69
},
{
"epoch": 0.05,
"learning_rate": 1.998844622744483e-05,
"loss": 0.2452,
"step": 70
},
{
"epoch": 0.05,
"learning_rate": 1.998741992607014e-05,
"loss": 1.0325,
"step": 71
},
{
"epoch": 0.05,
"learning_rate": 1.998634998969985e-05,
"loss": 1.0247,
"step": 72
},
{
"epoch": 0.05,
"learning_rate": 1.9985236423008513e-05,
"loss": 1.0464,
"step": 73
},
{
"epoch": 0.05,
"learning_rate": 1.9984079230861296e-05,
"loss": 1.0235,
"step": 74
},
{
"epoch": 0.05,
"learning_rate": 1.998287841831396e-05,
"loss": 1.0538,
"step": 75
},
{
"epoch": 0.05,
"learning_rate": 1.998163399061286e-05,
"loss": 1.0596,
"step": 76
},
{
"epoch": 0.05,
"learning_rate": 1.9980345953194892e-05,
"loss": 0.2228,
"step": 77
},
{
"epoch": 0.05,
"learning_rate": 1.9979014311687475e-05,
"loss": 1.0403,
"step": 78
},
{
"epoch": 0.05,
"learning_rate": 1.9977639071908564e-05,
"loss": 1.0242,
"step": 79
},
{
"epoch": 0.05,
"learning_rate": 1.9976220239866563e-05,
"loss": 1.0223,
"step": 80
},
{
"epoch": 0.05,
"learning_rate": 1.9974757821760343e-05,
"loss": 1.0066,
"step": 81
},
{
"epoch": 0.05,
"learning_rate": 1.997325182397921e-05,
"loss": 1.0113,
"step": 82
},
{
"epoch": 0.05,
"learning_rate": 1.9971702253102856e-05,
"loss": 1.0148,
"step": 83
},
{
"epoch": 0.05,
"learning_rate": 1.997010911590135e-05,
"loss": 0.2035,
"step": 84
},
{
"epoch": 0.05,
"learning_rate": 1.9968472419335106e-05,
"loss": 1.0214,
"step": 85
},
{
"epoch": 0.06,
"learning_rate": 1.9966792170554842e-05,
"loss": 1.0216,
"step": 86
},
{
"epoch": 0.06,
"learning_rate": 1.9965068376901556e-05,
"loss": 0.2274,
"step": 87
},
{
"epoch": 0.06,
"learning_rate": 1.9963301045906497e-05,
"loss": 1.0191,
"step": 88
},
{
"epoch": 0.06,
"learning_rate": 1.9961490185291128e-05,
"loss": 1.0329,
"step": 89
},
{
"epoch": 0.06,
"learning_rate": 1.995963580296709e-05,
"loss": 0.1987,
"step": 90
},
{
"epoch": 0.06,
"learning_rate": 1.995773790703617e-05,
"loss": 0.9957,
"step": 91
},
{
"epoch": 0.06,
"learning_rate": 1.9955796505790266e-05,
"loss": 1.0067,
"step": 92
},
{
"epoch": 0.06,
"learning_rate": 1.995381160771136e-05,
"loss": 1.0013,
"step": 93
},
{
"epoch": 0.06,
"learning_rate": 1.9951783221471456e-05,
"loss": 1.009,
"step": 94
},
{
"epoch": 0.06,
"learning_rate": 1.9949711355932565e-05,
"loss": 1.0174,
"step": 95
},
{
"epoch": 0.06,
"learning_rate": 1.9947596020146666e-05,
"loss": 1.0124,
"step": 96
},
{
"epoch": 0.06,
"learning_rate": 1.994543722335564e-05,
"loss": 1.0203,
"step": 97
},
{
"epoch": 0.06,
"learning_rate": 1.994323497499127e-05,
"loss": 1.025,
"step": 98
},
{
"epoch": 0.06,
"learning_rate": 1.994098928467517e-05,
"loss": 0.2078,
"step": 99
},
{
"epoch": 0.06,
"learning_rate": 1.993870016221875e-05,
"loss": 1.0206,
"step": 100
},
{
"epoch": 0.07,
"learning_rate": 1.993636761762317e-05,
"loss": 1.046,
"step": 101
},
{
"epoch": 0.07,
"learning_rate": 1.9933991661079316e-05,
"loss": 1.0425,
"step": 102
},
{
"epoch": 0.07,
"learning_rate": 1.9931572302967735e-05,
"loss": 1.0214,
"step": 103
},
{
"epoch": 0.07,
"learning_rate": 1.9929109553858578e-05,
"loss": 1.0161,
"step": 104
},
{
"epoch": 0.07,
"learning_rate": 1.99266034245116e-05,
"loss": 1.018,
"step": 105
},
{
"epoch": 0.07,
"learning_rate": 1.9924053925876064e-05,
"loss": 0.9872,
"step": 106
},
{
"epoch": 0.07,
"learning_rate": 1.9921461069090715e-05,
"loss": 1.0113,
"step": 107
},
{
"epoch": 0.07,
"learning_rate": 1.991882486548374e-05,
"loss": 0.2196,
"step": 108
},
{
"epoch": 0.07,
"learning_rate": 1.9916145326572696e-05,
"loss": 1.0097,
"step": 109
},
{
"epoch": 0.07,
"learning_rate": 1.991342246406448e-05,
"loss": 1.0246,
"step": 110
},
{
"epoch": 0.07,
"learning_rate": 1.991065628985527e-05,
"loss": 1.0328,
"step": 111
},
{
"epoch": 0.07,
"learning_rate": 1.990784681603046e-05,
"loss": 1.0208,
"step": 112
},
{
"epoch": 0.07,
"learning_rate": 1.990499405486464e-05,
"loss": 1.0111,
"step": 113
},
{
"epoch": 0.07,
"learning_rate": 1.9902098018821504e-05,
"loss": 1.0408,
"step": 114
},
{
"epoch": 0.07,
"learning_rate": 1.9899158720553828e-05,
"loss": 0.9881,
"step": 115
},
{
"epoch": 0.07,
"learning_rate": 1.9896176172903384e-05,
"loss": 1.0275,
"step": 116
},
{
"epoch": 0.08,
"learning_rate": 1.9893150388900918e-05,
"loss": 0.2126,
"step": 117
},
{
"epoch": 0.08,
"learning_rate": 1.9890081381766066e-05,
"loss": 0.2534,
"step": 118
},
{
"epoch": 0.08,
"learning_rate": 1.9886969164907306e-05,
"loss": 0.9866,
"step": 119
},
{
"epoch": 0.08,
"learning_rate": 1.9883813751921904e-05,
"loss": 1.0216,
"step": 120
},
{
"epoch": 0.08,
"learning_rate": 1.988061515659584e-05,
"loss": 1.0392,
"step": 121
},
{
"epoch": 0.08,
"learning_rate": 1.9877373392903768e-05,
"loss": 0.2002,
"step": 122
},
{
"epoch": 0.08,
"learning_rate": 1.987408847500894e-05,
"loss": 1.0269,
"step": 123
},
{
"epoch": 0.08,
"learning_rate": 1.9870760417263145e-05,
"loss": 1.0159,
"step": 124
},
{
"epoch": 0.08,
"learning_rate": 1.9867389234206655e-05,
"loss": 0.2196,
"step": 125
},
{
"epoch": 0.08,
"learning_rate": 1.9863974940568157e-05,
"loss": 1.0475,
"step": 126
},
{
"epoch": 0.08,
"learning_rate": 1.986051755126468e-05,
"loss": 0.9978,
"step": 127
},
{
"epoch": 0.08,
"learning_rate": 1.985701708140155e-05,
"loss": 0.9849,
"step": 128
},
{
"epoch": 0.08,
"learning_rate": 1.98534735462723e-05,
"loss": 0.9828,
"step": 129
},
{
"epoch": 0.08,
"learning_rate": 1.9849886961358624e-05,
"loss": 1.0186,
"step": 130
},
{
"epoch": 0.08,
"learning_rate": 1.984625734233029e-05,
"loss": 1.0218,
"step": 131
},
{
"epoch": 0.09,
"learning_rate": 1.9842584705045097e-05,
"loss": 1.0019,
"step": 132
},
{
"epoch": 0.09,
"learning_rate": 1.9838869065548772e-05,
"loss": 0.2227,
"step": 133
},
{
"epoch": 0.09,
"learning_rate": 1.9835110440074938e-05,
"loss": 1.0439,
"step": 134
},
{
"epoch": 0.09,
"learning_rate": 1.983130884504501e-05,
"loss": 0.2412,
"step": 135
},
{
"epoch": 0.09,
"learning_rate": 1.9827464297068137e-05,
"loss": 1.0453,
"step": 136
},
{
"epoch": 0.09,
"learning_rate": 1.982357681294114e-05,
"loss": 0.9978,
"step": 137
},
{
"epoch": 0.09,
"learning_rate": 1.9819646409648415e-05,
"loss": 1.023,
"step": 138
},
{
"epoch": 0.09,
"learning_rate": 1.9815673104361876e-05,
"loss": 1.023,
"step": 139
},
{
"epoch": 0.09,
"learning_rate": 1.9811656914440885e-05,
"loss": 1.0388,
"step": 140
},
{
"epoch": 0.09,
"learning_rate": 1.9807597857432152e-05,
"loss": 1.002,
"step": 141
},
{
"epoch": 0.09,
"learning_rate": 1.980349595106968e-05,
"loss": 1.0171,
"step": 142
},
{
"epoch": 0.09,
"learning_rate": 1.9799351213274688e-05,
"loss": 1.0097,
"step": 143
},
{
"epoch": 0.09,
"learning_rate": 1.979516366215551e-05,
"loss": 0.23,
"step": 144
},
{
"epoch": 0.09,
"learning_rate": 1.9790933316007543e-05,
"loss": 1.0232,
"step": 145
},
{
"epoch": 0.09,
"learning_rate": 1.978666019331315e-05,
"loss": 1.0192,
"step": 146
},
{
"epoch": 0.09,
"learning_rate": 1.9782344312741585e-05,
"loss": 1.0133,
"step": 147
},
{
"epoch": 0.1,
"learning_rate": 1.9777985693148912e-05,
"loss": 1.0262,
"step": 148
},
{
"epoch": 0.1,
"learning_rate": 1.9773584353577928e-05,
"loss": 1.0047,
"step": 149
},
{
"epoch": 0.1,
"learning_rate": 1.976914031325806e-05,
"loss": 1.0226,
"step": 150
},
{
"epoch": 0.1,
"learning_rate": 1.9764653591605306e-05,
"loss": 1.0122,
"step": 151
},
{
"epoch": 0.1,
"learning_rate": 1.9760124208222128e-05,
"loss": 1.0316,
"step": 152
},
{
"epoch": 0.1,
"learning_rate": 1.9755552182897388e-05,
"loss": 1.0097,
"step": 153
},
{
"epoch": 0.1,
"learning_rate": 1.9750937535606246e-05,
"loss": 1.0235,
"step": 154
},
{
"epoch": 0.1,
"learning_rate": 1.974628028651007e-05,
"loss": 1.0066,
"step": 155
},
{
"epoch": 0.1,
"learning_rate": 1.974158045595637e-05,
"loss": 1.0197,
"step": 156
},
{
"epoch": 0.1,
"learning_rate": 1.9736838064478683e-05,
"loss": 0.2556,
"step": 157
},
{
"epoch": 0.1,
"learning_rate": 1.9732053132796496e-05,
"loss": 0.9894,
"step": 158
},
{
"epoch": 0.1,
"learning_rate": 1.9727225681815154e-05,
"loss": 1.0273,
"step": 159
},
{
"epoch": 0.1,
"learning_rate": 1.9722355732625775e-05,
"loss": 1.0185,
"step": 160
},
{
"epoch": 0.1,
"learning_rate": 1.9717443306505143e-05,
"loss": 0.2332,
"step": 161
},
{
"epoch": 0.1,
"learning_rate": 1.9712488424915625e-05,
"loss": 1.0038,
"step": 162
},
{
"epoch": 0.11,
"learning_rate": 1.9707491109505083e-05,
"loss": 1.0146,
"step": 163
},
{
"epoch": 0.11,
"learning_rate": 1.9702451382106763e-05,
"loss": 1.0111,
"step": 164
},
{
"epoch": 0.11,
"learning_rate": 1.9697369264739213e-05,
"loss": 1.0434,
"step": 165
},
{
"epoch": 0.11,
"learning_rate": 1.9692244779606185e-05,
"loss": 1.022,
"step": 166
},
{
"epoch": 0.11,
"learning_rate": 1.9687077949096528e-05,
"loss": 1.013,
"step": 167
},
{
"epoch": 0.11,
"learning_rate": 1.9681868795784108e-05,
"loss": 0.9847,
"step": 168
},
{
"epoch": 0.11,
"learning_rate": 1.9676617342427696e-05,
"loss": 0.9989,
"step": 169
},
{
"epoch": 0.11,
"learning_rate": 1.9671323611970864e-05,
"loss": 1.0329,
"step": 170
},
{
"epoch": 0.11,
"learning_rate": 1.9665987627541895e-05,
"loss": 0.2547,
"step": 171
},
{
"epoch": 0.11,
"learning_rate": 1.9660609412453692e-05,
"loss": 1.0103,
"step": 172
},
{
"epoch": 0.11,
"learning_rate": 1.9655188990203648e-05,
"loss": 1.0085,
"step": 173
},
{
"epoch": 0.11,
"learning_rate": 1.9649726384473568e-05,
"loss": 1.0005,
"step": 174
},
{
"epoch": 0.11,
"learning_rate": 1.964422161912955e-05,
"loss": 1.007,
"step": 175
},
{
"epoch": 0.11,
"learning_rate": 1.963867471822189e-05,
"loss": 1.0165,
"step": 176
},
{
"epoch": 0.11,
"learning_rate": 1.963308570598498e-05,
"loss": 1.005,
"step": 177
},
{
"epoch": 0.11,
"learning_rate": 1.9627454606837187e-05,
"loss": 0.2324,
"step": 178
},
{
"epoch": 0.12,
"learning_rate": 1.962178144538076e-05,
"loss": 1.0112,
"step": 179
},
{
"epoch": 0.12,
"learning_rate": 1.961606624640172e-05,
"loss": 0.2282,
"step": 180
},
{
"epoch": 0.12,
"learning_rate": 1.9610309034869743e-05,
"loss": 1.0123,
"step": 181
},
{
"epoch": 0.12,
"learning_rate": 1.9604509835938066e-05,
"loss": 0.9915,
"step": 182
},
{
"epoch": 0.12,
"learning_rate": 1.9598668674943362e-05,
"loss": 1.0167,
"step": 183
},
{
"epoch": 0.12,
"learning_rate": 1.959278557740564e-05,
"loss": 1.0292,
"step": 184
},
{
"epoch": 0.12,
"learning_rate": 1.9586860569028126e-05,
"loss": 1.0238,
"step": 185
},
{
"epoch": 0.12,
"learning_rate": 1.958089367569716e-05,
"loss": 0.2066,
"step": 186
},
{
"epoch": 0.12,
"learning_rate": 1.9574884923482073e-05,
"loss": 0.9481,
"step": 187
},
{
"epoch": 0.12,
"learning_rate": 1.956883433863508e-05,
"loss": 0.2759,
"step": 188
},
{
"epoch": 0.12,
"learning_rate": 1.9562741947591154e-05,
"loss": 0.9874,
"step": 189
},
{
"epoch": 0.12,
"learning_rate": 1.955660777696793e-05,
"loss": 1.0366,
"step": 190
},
{
"epoch": 0.12,
"learning_rate": 1.9550431853565577e-05,
"loss": 0.995,
"step": 191
},
{
"epoch": 0.12,
"learning_rate": 1.9544214204366675e-05,
"loss": 1.0166,
"step": 192
},
{
"epoch": 0.12,
"learning_rate": 1.9537954856536104e-05,
"loss": 1.0049,
"step": 193
},
{
"epoch": 0.13,
"learning_rate": 1.9531653837420932e-05,
"loss": 1.0065,
"step": 194
},
{
"epoch": 0.13,
"learning_rate": 1.9525311174550286e-05,
"loss": 0.9526,
"step": 195
},
{
"epoch": 0.13,
"learning_rate": 1.9518926895635232e-05,
"loss": 0.9924,
"step": 196
},
{
"epoch": 0.13,
"learning_rate": 1.951250102856866e-05,
"loss": 0.9736,
"step": 197
},
{
"epoch": 0.13,
"learning_rate": 1.9506033601425146e-05,
"loss": 0.2209,
"step": 198
},
{
"epoch": 0.13,
"learning_rate": 1.9499524642460868e-05,
"loss": 0.9995,
"step": 199
},
{
"epoch": 0.13,
"learning_rate": 1.9492974180113425e-05,
"loss": 0.2194,
"step": 200
},
{
"epoch": 0.13,
"learning_rate": 1.9486382243001773e-05,
"loss": 0.9749,
"step": 201
},
{
"epoch": 0.13,
"learning_rate": 1.947974885992605e-05,
"loss": 0.9989,
"step": 202
},
{
"epoch": 0.13,
"learning_rate": 1.9473074059867476e-05,
"loss": 1.0121,
"step": 203
},
{
"epoch": 0.13,
"learning_rate": 1.946635787198823e-05,
"loss": 0.2201,
"step": 204
},
{
"epoch": 0.13,
"learning_rate": 1.9459600325631306e-05,
"loss": 1.0038,
"step": 205
},
{
"epoch": 0.13,
"learning_rate": 1.9452801450320398e-05,
"loss": 1.0152,
"step": 206
},
{
"epoch": 0.13,
"learning_rate": 1.9445961275759758e-05,
"loss": 0.9947,
"step": 207
},
{
"epoch": 0.13,
"learning_rate": 1.9439079831834087e-05,
"loss": 1.0292,
"step": 208
},
{
"epoch": 0.13,
"learning_rate": 1.943215714860838e-05,
"loss": 0.9807,
"step": 209
},
{
"epoch": 0.14,
"learning_rate": 1.9425193256327812e-05,
"loss": 0.9856,
"step": 210
},
{
"epoch": 0.14,
"learning_rate": 1.94181881854176e-05,
"loss": 1.0152,
"step": 211
},
{
"epoch": 0.14,
"learning_rate": 1.9411141966482865e-05,
"loss": 0.2541,
"step": 212
},
{
"epoch": 0.14,
"learning_rate": 1.9404054630308513e-05,
"loss": 1.0069,
"step": 213
},
{
"epoch": 0.14,
"learning_rate": 1.9396926207859085e-05,
"loss": 0.9857,
"step": 214
},
{
"epoch": 0.14,
"learning_rate": 1.9389756730278625e-05,
"loss": 0.9933,
"step": 215
},
{
"epoch": 0.14,
"learning_rate": 1.9382546228890558e-05,
"loss": 0.2294,
"step": 216
},
{
"epoch": 0.14,
"learning_rate": 1.9375294735197525e-05,
"loss": 1.0356,
"step": 217
},
{
"epoch": 0.14,
"learning_rate": 1.936800228088128e-05,
"loss": 0.9892,
"step": 218
},
{
"epoch": 0.14,
"learning_rate": 1.9360668897802518e-05,
"loss": 0.2265,
"step": 219
},
{
"epoch": 0.14,
"learning_rate": 1.935329461800076e-05,
"loss": 1.0101,
"step": 220
},
{
"epoch": 0.14,
"learning_rate": 1.9345879473694207e-05,
"loss": 0.9994,
"step": 221
},
{
"epoch": 0.14,
"learning_rate": 1.933842349727959e-05,
"loss": 0.9924,
"step": 222
},
{
"epoch": 0.14,
"learning_rate": 1.933092672133204e-05,
"loss": 0.2208,
"step": 223
},
{
"epoch": 0.14,
"learning_rate": 1.9323389178604942e-05,
"loss": 1.0252,
"step": 224
},
{
"epoch": 0.15,
"learning_rate": 1.9315810902029786e-05,
"loss": 1.0074,
"step": 225
},
{
"epoch": 0.15,
"learning_rate": 1.9308191924716027e-05,
"loss": 0.2246,
"step": 226
},
{
"epoch": 0.15,
"learning_rate": 1.930053227995095e-05,
"loss": 0.2418,
"step": 227
},
{
"epoch": 0.15,
"learning_rate": 1.9292832001199507e-05,
"loss": 1.0095,
"step": 228
},
{
"epoch": 0.15,
"learning_rate": 1.928509112210419e-05,
"loss": 0.977,
"step": 229
},
{
"epoch": 0.15,
"learning_rate": 1.927730967648486e-05,
"loss": 1.0416,
"step": 230
},
{
"epoch": 0.15,
"learning_rate": 1.926948769833862e-05,
"loss": 0.9849,
"step": 231
},
{
"epoch": 0.15,
"learning_rate": 1.9261625221839664e-05,
"loss": 0.2056,
"step": 232
},
{
"epoch": 0.15,
"learning_rate": 1.925372228133912e-05,
"loss": 0.9734,
"step": 233
},
{
"epoch": 0.15,
"learning_rate": 1.9245778911364894e-05,
"loss": 0.9837,
"step": 234
},
{
"epoch": 0.15,
"learning_rate": 1.923779514662154e-05,
"loss": 0.9937,
"step": 235
},
{
"epoch": 0.15,
"learning_rate": 1.9229771021990094e-05,
"loss": 1.002,
"step": 236
},
{
"epoch": 0.15,
"learning_rate": 1.9221706572527925e-05,
"loss": 1.0114,
"step": 237
},
{
"epoch": 0.15,
"learning_rate": 1.9213601833468573e-05,
"loss": 0.9961,
"step": 238
},
{
"epoch": 0.15,
"learning_rate": 1.9205456840221614e-05,
"loss": 1.0347,
"step": 239
},
{
"epoch": 0.15,
"learning_rate": 1.9197271628372484e-05,
"loss": 1.0058,
"step": 240
},
{
"epoch": 0.16,
"learning_rate": 1.918904623368234e-05,
"loss": 1.0161,
"step": 241
},
{
"epoch": 0.16,
"learning_rate": 1.9180780692087903e-05,
"loss": 0.9728,
"step": 242
},
{
"epoch": 0.16,
"learning_rate": 1.9172475039701283e-05,
"loss": 1.0137,
"step": 243
},
{
"epoch": 0.16,
"learning_rate": 1.916412931280984e-05,
"loss": 0.9668,
"step": 244
},
{
"epoch": 0.16,
"learning_rate": 1.9155743547876026e-05,
"loss": 0.9968,
"step": 245
},
{
"epoch": 0.16,
"learning_rate": 1.9147317781537204e-05,
"loss": 1.0032,
"step": 246
},
{
"epoch": 0.16,
"learning_rate": 1.913885205060552e-05,
"loss": 0.9953,
"step": 247
},
{
"epoch": 0.16,
"learning_rate": 1.913034639206771e-05,
"loss": 1.0269,
"step": 248
},
{
"epoch": 0.16,
"learning_rate": 1.9121800843084964e-05,
"loss": 1.0162,
"step": 249
},
{
"epoch": 0.16,
"learning_rate": 1.9113215440992752e-05,
"loss": 1.0334,
"step": 250
},
{
"epoch": 0.16,
"learning_rate": 1.9104590223300656e-05,
"loss": 0.9956,
"step": 251
},
{
"epoch": 0.16,
"learning_rate": 1.909592522769221e-05,
"loss": 0.9957,
"step": 252
},
{
"epoch": 0.16,
"learning_rate": 1.9087220492024756e-05,
"loss": 0.9945,
"step": 253
},
{
"epoch": 0.16,
"learning_rate": 1.9078476054329237e-05,
"loss": 1.0007,
"step": 254
},
{
"epoch": 0.16,
"learning_rate": 1.9069691952810073e-05,
"loss": 0.9689,
"step": 255
},
{
"epoch": 0.17,
"learning_rate": 1.9060868225844955e-05,
"loss": 1.018,
"step": 256
},
{
"epoch": 0.17,
"learning_rate": 1.9052004911984722e-05,
"loss": 0.9796,
"step": 257
},
{
"epoch": 0.17,
"learning_rate": 1.9043102049953148e-05,
"loss": 1.0072,
"step": 258
},
{
"epoch": 0.17,
"learning_rate": 1.9034159678646798e-05,
"loss": 0.2296,
"step": 259
},
{
"epoch": 0.17,
"learning_rate": 1.9025177837134858e-05,
"loss": 1.0022,
"step": 260
},
{
"epoch": 0.17,
"learning_rate": 1.9016156564658955e-05,
"loss": 1.0108,
"step": 261
},
{
"epoch": 0.17,
"learning_rate": 1.900709590063299e-05,
"loss": 0.2364,
"step": 262
},
{
"epoch": 0.17,
"learning_rate": 1.8997995884642968e-05,
"loss": 0.2667,
"step": 263
},
{
"epoch": 0.17,
"learning_rate": 1.898885655644682e-05,
"loss": 0.9805,
"step": 264
},
{
"epoch": 0.17,
"learning_rate": 1.8979677955974226e-05,
"loss": 1.0248,
"step": 265
},
{
"epoch": 0.17,
"learning_rate": 1.897046012332646e-05,
"loss": 0.9947,
"step": 266
},
{
"epoch": 0.17,
"learning_rate": 1.8961203098776194e-05,
"loss": 1.0041,
"step": 267
},
{
"epoch": 0.17,
"learning_rate": 1.895190692276733e-05,
"loss": 0.989,
"step": 268
},
{
"epoch": 0.17,
"learning_rate": 1.8942571635914814e-05,
"loss": 1.0122,
"step": 269
},
{
"epoch": 0.17,
"learning_rate": 1.893319727900448e-05,
"loss": 1.0099,
"step": 270
},
{
"epoch": 0.17,
"learning_rate": 1.8923783892992857e-05,
"loss": 0.9908,
"step": 271
},
{
"epoch": 0.18,
"learning_rate": 1.8914331519006985e-05,
"loss": 0.9923,
"step": 272
},
{
"epoch": 0.18,
"learning_rate": 1.890484019834425e-05,
"loss": 0.2316,
"step": 273
},
{
"epoch": 0.18,
"learning_rate": 1.8895309972472184e-05,
"loss": 1.0045,
"step": 274
},
{
"epoch": 0.18,
"learning_rate": 1.888574088302831e-05,
"loss": 0.9874,
"step": 275
},
{
"epoch": 0.18,
"learning_rate": 1.887613297181994e-05,
"loss": 0.2398,
"step": 276
},
{
"epoch": 0.18,
"learning_rate": 1.8866486280823994e-05,
"loss": 0.9949,
"step": 277
},
{
"epoch": 0.18,
"learning_rate": 1.8856800852186826e-05,
"loss": 0.9742,
"step": 278
},
{
"epoch": 0.18,
"learning_rate": 1.8847076728224036e-05,
"loss": 1.0035,
"step": 279
},
{
"epoch": 0.18,
"learning_rate": 1.8837313951420274e-05,
"loss": 0.976,
"step": 280
},
{
"epoch": 0.18,
"learning_rate": 1.8827512564429076e-05,
"loss": 0.9829,
"step": 281
},
{
"epoch": 0.18,
"learning_rate": 1.8817672610072656e-05,
"loss": 0.9701,
"step": 282
},
{
"epoch": 0.18,
"learning_rate": 1.8807794131341742e-05,
"loss": 0.2445,
"step": 283
},
{
"epoch": 0.18,
"learning_rate": 1.8797877171395357e-05,
"loss": 0.9801,
"step": 284
},
{
"epoch": 0.18,
"learning_rate": 1.8787921773560656e-05,
"loss": 0.9753,
"step": 285
},
{
"epoch": 0.18,
"learning_rate": 1.877792798133274e-05,
"loss": 0.9941,
"step": 286
},
{
"epoch": 0.19,
"learning_rate": 1.8767895838374438e-05,
"loss": 0.2344,
"step": 287
},
{
"epoch": 0.19,
"learning_rate": 1.8757825388516148e-05,
"loss": 0.2217,
"step": 288
},
{
"epoch": 0.19,
"learning_rate": 1.8747716675755608e-05,
"loss": 0.2488,
"step": 289
},
{
"epoch": 0.19,
"learning_rate": 1.8737569744257754e-05,
"loss": 1.0014,
"step": 290
},
{
"epoch": 0.19,
"learning_rate": 1.8727384638354484e-05,
"loss": 1.0,
"step": 291
},
{
"epoch": 0.19,
"learning_rate": 1.871716140254448e-05,
"loss": 0.9708,
"step": 292
},
{
"epoch": 0.19,
"learning_rate": 1.870690008149302e-05,
"loss": 0.2315,
"step": 293
},
{
"epoch": 0.19,
"learning_rate": 1.869660072003177e-05,
"loss": 0.9555,
"step": 294
},
{
"epoch": 0.19,
"learning_rate": 1.86862633631586e-05,
"loss": 0.9969,
"step": 295
},
{
"epoch": 0.19,
"learning_rate": 1.8675888056037378e-05,
"loss": 0.2164,
"step": 296
},
{
"epoch": 0.19,
"learning_rate": 1.866547484399777e-05,
"loss": 0.9868,
"step": 297
},
{
"epoch": 0.19,
"learning_rate": 1.8655023772535064e-05,
"loss": 1.01,
"step": 298
},
{
"epoch": 0.19,
"learning_rate": 1.8644534887309947e-05,
"loss": 1.0175,
"step": 299
},
{
"epoch": 0.19,
"learning_rate": 1.863400823414831e-05,
"loss": 0.9935,
"step": 300
},
{
"epoch": 0.19,
"learning_rate": 1.8623443859041055e-05,
"loss": 1.0058,
"step": 301
},
{
"epoch": 0.19,
"learning_rate": 1.8612841808143897e-05,
"loss": 0.9795,
"step": 302
},
{
"epoch": 0.2,
"learning_rate": 1.860220212777715e-05,
"loss": 0.9835,
"step": 303
},
{
"epoch": 0.2,
"learning_rate": 1.8591524864425534e-05,
"loss": 1.0295,
"step": 304
},
{
"epoch": 0.2,
"learning_rate": 1.8580810064737967e-05,
"loss": 0.9863,
"step": 305
},
{
"epoch": 0.2,
"learning_rate": 1.857005777552736e-05,
"loss": 0.27,
"step": 306
},
{
"epoch": 0.2,
"learning_rate": 1.8559268043770427e-05,
"loss": 0.9614,
"step": 307
},
{
"epoch": 0.2,
"learning_rate": 1.8548440916607454e-05,
"loss": 1.0036,
"step": 308
},
{
"epoch": 0.2,
"learning_rate": 1.8537576441342114e-05,
"loss": 1.0172,
"step": 309
},
{
"epoch": 0.2,
"learning_rate": 1.852667466544126e-05,
"loss": 1.0358,
"step": 310
},
{
"epoch": 0.2,
"learning_rate": 1.8515735636534694e-05,
"loss": 0.9924,
"step": 311
},
{
"epoch": 0.2,
"learning_rate": 1.8504759402414996e-05,
"loss": 0.2256,
"step": 312
},
{
"epoch": 0.2,
"learning_rate": 1.8493746011037288e-05,
"loss": 0.964,
"step": 313
},
{
"epoch": 0.2,
"learning_rate": 1.8482695510519027e-05,
"loss": 0.2455,
"step": 314
},
{
"epoch": 0.2,
"learning_rate": 1.84716079491398e-05,
"loss": 0.9941,
"step": 315
},
{
"epoch": 0.2,
"learning_rate": 1.8460483375341123e-05,
"loss": 0.9492,
"step": 316
},
{
"epoch": 0.2,
"learning_rate": 1.8449321837726207e-05,
"loss": 0.9917,
"step": 317
},
{
"epoch": 0.21,
"learning_rate": 1.8438123385059767e-05,
"loss": 1.012,
"step": 318
},
{
"epoch": 0.21,
"learning_rate": 1.8426888066267787e-05,
"loss": 1.0017,
"step": 319
},
{
"epoch": 0.21,
"learning_rate": 1.8415615930437335e-05,
"loss": 0.9892,
"step": 320
},
{
"epoch": 0.21,
"learning_rate": 1.8404307026816326e-05,
"loss": 0.9715,
"step": 321
},
{
"epoch": 0.21,
"learning_rate": 1.8392961404813307e-05,
"loss": 1.0107,
"step": 322
},
{
"epoch": 0.21,
"learning_rate": 1.8381579113997255e-05,
"loss": 0.2487,
"step": 323
},
{
"epoch": 0.21,
"learning_rate": 1.8370160204097352e-05,
"loss": 0.9973,
"step": 324
},
{
"epoch": 0.21,
"learning_rate": 1.8358704725002766e-05,
"loss": 1.0161,
"step": 325
},
{
"epoch": 0.21,
"learning_rate": 1.8347212726762436e-05,
"loss": 0.9926,
"step": 326
},
{
"epoch": 0.21,
"learning_rate": 1.8335684259584855e-05,
"loss": 1.0311,
"step": 327
},
{
"epoch": 0.21,
"learning_rate": 1.832411937383785e-05,
"loss": 0.2318,
"step": 328
},
{
"epoch": 0.21,
"learning_rate": 1.8312518120048354e-05,
"loss": 0.9861,
"step": 329
},
{
"epoch": 0.21,
"learning_rate": 1.83008805489022e-05,
"loss": 0.9702,
"step": 330
},
{
"epoch": 0.21,
"learning_rate": 1.8289206711243883e-05,
"loss": 1.0137,
"step": 331
},
{
"epoch": 0.21,
"learning_rate": 1.827749665807635e-05,
"loss": 1.0218,
"step": 332
},
{
"epoch": 0.21,
"learning_rate": 1.8265750440560783e-05,
"loss": 0.2305,
"step": 333
},
{
"epoch": 0.22,
"learning_rate": 1.8253968110016343e-05,
"loss": 0.9902,
"step": 334
},
{
"epoch": 0.22,
"learning_rate": 1.8242149717919993e-05,
"loss": 0.9824,
"step": 335
},
{
"epoch": 0.22,
"learning_rate": 1.8230295315906237e-05,
"loss": 1.015,
"step": 336
},
{
"epoch": 0.22,
"learning_rate": 1.8218404955766905e-05,
"loss": 0.2074,
"step": 337
},
{
"epoch": 0.22,
"learning_rate": 1.820647868945093e-05,
"loss": 1.005,
"step": 338
},
{
"epoch": 0.22,
"learning_rate": 1.819451656906412e-05,
"loss": 0.9698,
"step": 339
},
{
"epoch": 0.22,
"learning_rate": 1.818251864686893e-05,
"loss": 0.2303,
"step": 340
},
{
"epoch": 0.22,
"learning_rate": 1.8170484975284233e-05,
"loss": 0.9799,
"step": 341
},
{
"epoch": 0.22,
"learning_rate": 1.8158415606885083e-05,
"loss": 0.9846,
"step": 342
},
{
"epoch": 0.22,
"learning_rate": 1.8146310594402504e-05,
"loss": 1.0016,
"step": 343
},
{
"epoch": 0.22,
"learning_rate": 1.8134169990723246e-05,
"loss": 0.9747,
"step": 344
},
{
"epoch": 0.22,
"learning_rate": 1.8121993848889553e-05,
"loss": 0.9855,
"step": 345
},
{
"epoch": 0.22,
"learning_rate": 1.810978222209894e-05,
"loss": 0.2337,
"step": 346
},
{
"epoch": 0.22,
"learning_rate": 1.8097535163703947e-05,
"loss": 0.9648,
"step": 347
},
{
"epoch": 0.22,
"learning_rate": 1.8085252727211927e-05,
"loss": 0.9622,
"step": 348
},
{
"epoch": 0.23,
"learning_rate": 1.807293496628479e-05,
"loss": 0.2499,
"step": 349
},
{
"epoch": 0.23,
"learning_rate": 1.8060581934738783e-05,
"loss": 0.9639,
"step": 350
},
{
"epoch": 0.23,
"learning_rate": 1.8048193686544248e-05,
"loss": 0.2441,
"step": 351
},
{
"epoch": 0.23,
"learning_rate": 1.803577027582539e-05,
"loss": 0.9906,
"step": 352
},
{
"epoch": 0.23,
"learning_rate": 1.8023311756860036e-05,
"loss": 1.016,
"step": 353
},
{
"epoch": 0.23,
"learning_rate": 1.8010818184079405e-05,
"loss": 0.9673,
"step": 354
},
{
"epoch": 0.23,
"learning_rate": 1.7998289612067864e-05,
"loss": 0.9913,
"step": 355
},
{
"epoch": 0.23,
"learning_rate": 1.798572609556269e-05,
"loss": 0.9853,
"step": 356
},
{
"epoch": 0.23,
"learning_rate": 1.7973127689453838e-05,
"loss": 0.9995,
"step": 357
},
{
"epoch": 0.23,
"learning_rate": 1.7960494448783685e-05,
"loss": 0.9827,
"step": 358
},
{
"epoch": 0.23,
"learning_rate": 1.794782642874681e-05,
"loss": 0.9762,
"step": 359
},
{
"epoch": 0.23,
"learning_rate": 1.7935123684689735e-05,
"loss": 0.9915,
"step": 360
},
{
"epoch": 0.23,
"learning_rate": 1.79223862721107e-05,
"loss": 0.9816,
"step": 361
},
{
"epoch": 0.23,
"learning_rate": 1.7909614246659406e-05,
"loss": 0.9885,
"step": 362
},
{
"epoch": 0.23,
"learning_rate": 1.789680766413678e-05,
"loss": 0.9543,
"step": 363
},
{
"epoch": 0.23,
"learning_rate": 1.7883966580494722e-05,
"loss": 0.9884,
"step": 364
},
{
"epoch": 0.24,
"learning_rate": 1.7871091051835873e-05,
"loss": 0.9771,
"step": 365
},
{
"epoch": 0.24,
"learning_rate": 1.785818113441337e-05,
"loss": 0.9671,
"step": 366
},
{
"epoch": 0.24,
"learning_rate": 1.7845236884630583e-05,
"loss": 1.0123,
"step": 367
},
{
"epoch": 0.24,
"learning_rate": 1.7832258359040885e-05,
"loss": 0.9839,
"step": 368
},
{
"epoch": 0.24,
"learning_rate": 1.78192456143474e-05,
"loss": 0.2257,
"step": 369
},
{
"epoch": 0.24,
"learning_rate": 1.7806198707402754e-05,
"loss": 0.9907,
"step": 370
},
{
"epoch": 0.24,
"learning_rate": 1.7793117695208828e-05,
"loss": 1.02,
"step": 371
},
{
"epoch": 0.24,
"learning_rate": 1.7780002634916512e-05,
"loss": 1.0146,
"step": 372
},
{
"epoch": 0.24,
"learning_rate": 1.7766853583825447e-05,
"loss": 0.2329,
"step": 373
},
{
"epoch": 0.24,
"learning_rate": 1.7753670599383784e-05,
"loss": 0.9827,
"step": 374
},
{
"epoch": 0.24,
"learning_rate": 1.7740453739187922e-05,
"loss": 1.0138,
"step": 375
},
{
"epoch": 0.24,
"learning_rate": 1.7727203060982273e-05,
"loss": 0.9674,
"step": 376
},
{
"epoch": 0.24,
"learning_rate": 1.771391862265899e-05,
"loss": 0.9854,
"step": 377
},
{
"epoch": 0.24,
"learning_rate": 1.7700600482257732e-05,
"loss": 1.0202,
"step": 378
},
{
"epoch": 0.24,
"learning_rate": 1.7687248697965395e-05,
"loss": 1.0042,
"step": 379
},
{
"epoch": 0.25,
"learning_rate": 1.767386332811587e-05,
"loss": 0.9878,
"step": 380
},
{
"epoch": 0.25,
"learning_rate": 1.766044443118978e-05,
"loss": 0.2769,
"step": 381
},
{
"epoch": 0.25,
"learning_rate": 1.7646992065814233e-05,
"loss": 0.2492,
"step": 382
},
{
"epoch": 0.25,
"learning_rate": 1.763350629076255e-05,
"loss": 0.978,
"step": 383
},
{
"epoch": 0.25,
"learning_rate": 1.7619987164954034e-05,
"loss": 0.9967,
"step": 384
},
{
"epoch": 0.25,
"learning_rate": 1.760643474745368e-05,
"loss": 0.9884,
"step": 385
},
{
"epoch": 0.25,
"learning_rate": 1.759284909747195e-05,
"loss": 0.2338,
"step": 386
},
{
"epoch": 0.25,
"learning_rate": 1.7579230274364486e-05,
"loss": 1.023,
"step": 387
},
{
"epoch": 0.25,
"learning_rate": 1.7565578337631876e-05,
"loss": 0.9967,
"step": 388
},
{
"epoch": 0.25,
"learning_rate": 1.7551893346919363e-05,
"loss": 0.2178,
"step": 389
},
{
"epoch": 0.25,
"learning_rate": 1.7538175362016622e-05,
"loss": 1.0084,
"step": 390
},
{
"epoch": 0.25,
"learning_rate": 1.752442444285747e-05,
"loss": 1.0017,
"step": 391
},
{
"epoch": 0.25,
"learning_rate": 1.7510640649519617e-05,
"loss": 0.9809,
"step": 392
},
{
"epoch": 0.25,
"learning_rate": 1.7496824042224393e-05,
"loss": 0.9623,
"step": 393
},
{
"epoch": 0.25,
"learning_rate": 1.7482974681336502e-05,
"loss": 0.9667,
"step": 394
},
{
"epoch": 0.25,
"learning_rate": 1.7469092627363738e-05,
"loss": 0.9644,
"step": 395
},
{
"epoch": 0.26,
"learning_rate": 1.7455177940956743e-05,
"loss": 0.2389,
"step": 396
},
{
"epoch": 0.26,
"learning_rate": 1.7441230682908713e-05,
"loss": 0.978,
"step": 397
},
{
"epoch": 0.26,
"learning_rate": 1.742725091415517e-05,
"loss": 0.9528,
"step": 398
},
{
"epoch": 0.26,
"learning_rate": 1.741323869577366e-05,
"loss": 0.2337,
"step": 399
},
{
"epoch": 0.26,
"learning_rate": 1.7399194088983513e-05,
"loss": 0.9634,
"step": 400
},
{
"epoch": 0.26,
"learning_rate": 1.7385117155145547e-05,
"loss": 0.9875,
"step": 401
},
{
"epoch": 0.26,
"learning_rate": 1.7371007955761833e-05,
"loss": 1.0033,
"step": 402
},
{
"epoch": 0.26,
"learning_rate": 1.7356866552475397e-05,
"loss": 0.9838,
"step": 403
},
{
"epoch": 0.26,
"learning_rate": 1.7342693007069974e-05,
"loss": 0.9995,
"step": 404
},
{
"epoch": 0.26,
"learning_rate": 1.732848738146973e-05,
"loss": 0.2411,
"step": 405
},
{
"epoch": 0.26,
"learning_rate": 1.7314249737738977e-05,
"loss": 0.9941,
"step": 406
},
{
"epoch": 0.26,
"learning_rate": 1.729998013808192e-05,
"loss": 0.9605,
"step": 407
},
{
"epoch": 0.26,
"learning_rate": 1.7285678644842384e-05,
"loss": 0.2131,
"step": 408
},
{
"epoch": 0.26,
"learning_rate": 1.7271345320503533e-05,
"loss": 0.9997,
"step": 409
},
{
"epoch": 0.26,
"learning_rate": 1.7256980227687596e-05,
"loss": 0.9939,
"step": 410
},
{
"epoch": 0.27,
"learning_rate": 1.7242583429155602e-05,
"loss": 0.997,
"step": 411
},
{
"epoch": 0.27,
"learning_rate": 1.722815498780711e-05,
"loss": 0.9812,
"step": 412
},
{
"epoch": 0.27,
"learning_rate": 1.7213694966679913e-05,
"loss": 0.9792,
"step": 413
},
{
"epoch": 0.27,
"learning_rate": 1.7199203428949788e-05,
"loss": 0.9823,
"step": 414
},
{
"epoch": 0.27,
"learning_rate": 1.71846804379302e-05,
"loss": 0.9652,
"step": 415
},
{
"epoch": 0.27,
"learning_rate": 1.717012605707203e-05,
"loss": 0.97,
"step": 416
},
{
"epoch": 0.27,
"learning_rate": 1.715554034996332e-05,
"loss": 0.9722,
"step": 417
},
{
"epoch": 0.27,
"learning_rate": 1.7140923380328947e-05,
"loss": 0.9823,
"step": 418
},
{
"epoch": 0.27,
"learning_rate": 1.7126275212030403e-05,
"loss": 0.997,
"step": 419
},
{
"epoch": 0.27,
"learning_rate": 1.7111595909065466e-05,
"loss": 1.0091,
"step": 420
},
{
"epoch": 0.27,
"learning_rate": 1.709688553556795e-05,
"loss": 0.9768,
"step": 421
},
{
"epoch": 0.27,
"learning_rate": 1.708214415580742e-05,
"loss": 0.2424,
"step": 422
},
{
"epoch": 0.27,
"learning_rate": 1.7067371834188895e-05,
"loss": 0.2465,
"step": 423
},
{
"epoch": 0.27,
"learning_rate": 1.705256863525259e-05,
"loss": 0.9533,
"step": 424
},
{
"epoch": 0.27,
"learning_rate": 1.7037734623673616e-05,
"loss": 0.9856,
"step": 425
},
{
"epoch": 0.27,
"learning_rate": 1.702286986426171e-05,
"loss": 0.9816,
"step": 426
},
{
"epoch": 0.28,
"learning_rate": 1.700797442196094e-05,
"loss": 0.2328,
"step": 427
},
{
"epoch": 0.28,
"learning_rate": 1.699304836184944e-05,
"loss": 1.0042,
"step": 428
},
{
"epoch": 0.28,
"learning_rate": 1.6978091749139088e-05,
"loss": 0.9756,
"step": 429
},
{
"epoch": 0.28,
"learning_rate": 1.696310464917527e-05,
"loss": 1.005,
"step": 430
},
{
"epoch": 0.28,
"learning_rate": 1.6948087127436573e-05,
"loss": 0.2513,
"step": 431
},
{
"epoch": 0.28,
"learning_rate": 1.693303924953447e-05,
"loss": 1.0042,
"step": 432
},
{
"epoch": 0.28,
"learning_rate": 1.691796108121308e-05,
"loss": 0.9842,
"step": 433
},
{
"epoch": 0.28,
"learning_rate": 1.6902852688348866e-05,
"loss": 0.9834,
"step": 434
},
{
"epoch": 0.28,
"learning_rate": 1.6887714136950322e-05,
"loss": 0.9865,
"step": 435
},
{
"epoch": 0.28,
"learning_rate": 1.6872545493157718e-05,
"loss": 0.9497,
"step": 436
},
{
"epoch": 0.28,
"learning_rate": 1.68573468232428e-05,
"loss": 0.272,
"step": 437
},
{
"epoch": 0.28,
"learning_rate": 1.684211819360849e-05,
"loss": 0.968,
"step": 438
},
{
"epoch": 0.28,
"learning_rate": 1.6826859670788604e-05,
"loss": 0.9676,
"step": 439
},
{
"epoch": 0.28,
"learning_rate": 1.6811571321447568e-05,
"loss": 0.2513,
"step": 440
},
{
"epoch": 0.28,
"learning_rate": 1.679625321238011e-05,
"loss": 0.9818,
"step": 441
},
{
"epoch": 0.29,
"learning_rate": 1.6780905410510992e-05,
"loss": 0.9716,
"step": 442
},
{
"epoch": 0.29,
"learning_rate": 1.676552798289469e-05,
"loss": 0.972,
"step": 443
},
{
"epoch": 0.29,
"learning_rate": 1.6750120996715123e-05,
"loss": 0.9554,
"step": 444
},
{
"epoch": 0.29,
"learning_rate": 1.6734684519285346e-05,
"loss": 0.9878,
"step": 445
},
{
"epoch": 0.29,
"learning_rate": 1.6719218618047263e-05,
"loss": 0.2487,
"step": 446
},
{
"epoch": 0.29,
"learning_rate": 1.6703723360571338e-05,
"loss": 0.9892,
"step": 447
},
{
"epoch": 0.29,
"learning_rate": 1.6688198814556283e-05,
"loss": 0.2418,
"step": 448
},
{
"epoch": 0.29,
"learning_rate": 1.667264504782877e-05,
"loss": 0.9784,
"step": 449
},
{
"epoch": 0.29,
"learning_rate": 1.6657062128343143e-05,
"loss": 0.9839,
"step": 450
},
{
"epoch": 0.29,
"learning_rate": 1.6641450124181115e-05,
"loss": 0.24,
"step": 451
},
{
"epoch": 0.29,
"learning_rate": 1.6625809103551462e-05,
"loss": 0.9606,
"step": 452
},
{
"epoch": 0.29,
"learning_rate": 1.661013913478974e-05,
"loss": 0.2316,
"step": 453
},
{
"epoch": 0.29,
"learning_rate": 1.659444028635797e-05,
"loss": 0.9971,
"step": 454
},
{
"epoch": 0.29,
"learning_rate": 1.6578712626844365e-05,
"loss": 0.9871,
"step": 455
},
{
"epoch": 0.29,
"learning_rate": 1.6562956224962996e-05,
"loss": 0.9962,
"step": 456
},
{
"epoch": 0.29,
"learning_rate": 1.6547171149553517e-05,
"loss": 0.9626,
"step": 457
},
{
"epoch": 0.3,
"learning_rate": 1.653135746958086e-05,
"loss": 0.981,
"step": 458
},
{
"epoch": 0.3,
"learning_rate": 1.6515515254134918e-05,
"loss": 0.938,
"step": 459
},
{
"epoch": 0.3,
"learning_rate": 1.6499644572430277e-05,
"loss": 0.9822,
"step": 460
},
{
"epoch": 0.3,
"learning_rate": 1.648374549380587e-05,
"loss": 0.9834,
"step": 461
},
{
"epoch": 0.3,
"learning_rate": 1.64678180877247e-05,
"loss": 0.2563,
"step": 462
},
{
"epoch": 0.3,
"learning_rate": 1.6451862423773545e-05,
"loss": 0.2468,
"step": 463
},
{
"epoch": 0.3,
"learning_rate": 1.643587857166263e-05,
"loss": 0.249,
"step": 464
},
{
"epoch": 0.3,
"learning_rate": 1.641986660122534e-05,
"loss": 0.9722,
"step": 465
},
{
"epoch": 0.3,
"learning_rate": 1.6403826582417908e-05,
"loss": 1.0052,
"step": 466
},
{
"epoch": 0.3,
"learning_rate": 1.63877585853191e-05,
"loss": 0.9957,
"step": 467
},
{
"epoch": 0.3,
"learning_rate": 1.6371662680129934e-05,
"loss": 0.9814,
"step": 468
},
{
"epoch": 0.3,
"learning_rate": 1.6355538937173353e-05,
"loss": 0.9613,
"step": 469
},
{
"epoch": 0.3,
"learning_rate": 1.633938742689392e-05,
"loss": 0.9588,
"step": 470
},
{
"epoch": 0.3,
"learning_rate": 1.6323208219857517e-05,
"loss": 0.9723,
"step": 471
},
{
"epoch": 0.3,
"learning_rate": 1.630700138675103e-05,
"loss": 0.2311,
"step": 472
},
{
"epoch": 0.31,
"learning_rate": 1.629076699838204e-05,
"loss": 0.9558,
"step": 473
},
{
"epoch": 0.31,
"learning_rate": 1.627450512567853e-05,
"loss": 0.9685,
"step": 474
},
{
"epoch": 0.31,
"learning_rate": 1.625821583968855e-05,
"loss": 1.002,
"step": 475
},
{
"epoch": 0.31,
"learning_rate": 1.624189921157992e-05,
"loss": 0.9723,
"step": 476
},
{
"epoch": 0.31,
"learning_rate": 1.622555531263992e-05,
"loss": 0.2283,
"step": 477
},
{
"epoch": 0.31,
"learning_rate": 1.620918421427498e-05,
"loss": 0.9785,
"step": 478
},
{
"epoch": 0.31,
"learning_rate": 1.6192785988010354e-05,
"loss": 0.9687,
"step": 479
},
{
"epoch": 0.31,
"learning_rate": 1.6176360705489826e-05,
"loss": 0.2452,
"step": 480
},
{
"epoch": 0.31,
"learning_rate": 1.6159908438475383e-05,
"loss": 1.0033,
"step": 481
},
{
"epoch": 0.31,
"learning_rate": 1.6143429258846917e-05,
"loss": 0.2389,
"step": 482
},
{
"epoch": 0.31,
"learning_rate": 1.612692323860189e-05,
"loss": 0.9875,
"step": 483
},
{
"epoch": 0.31,
"learning_rate": 1.6110390449855034e-05,
"loss": 0.9876,
"step": 484
},
{
"epoch": 0.31,
"learning_rate": 1.6093830964838036e-05,
"loss": 0.9944,
"step": 485
},
{
"epoch": 0.31,
"learning_rate": 1.6077244855899213e-05,
"loss": 0.9474,
"step": 486
},
{
"epoch": 0.31,
"learning_rate": 1.606063219550321e-05,
"loss": 0.9775,
"step": 487
},
{
"epoch": 0.31,
"learning_rate": 1.604399305623067e-05,
"loss": 0.9555,
"step": 488
},
{
"epoch": 0.32,
"learning_rate": 1.602732751077792e-05,
"loss": 0.9374,
"step": 489
},
{
"epoch": 0.32,
"learning_rate": 1.6010635631956653e-05,
"loss": 0.9405,
"step": 490
},
{
"epoch": 0.32,
"learning_rate": 1.5993917492693623e-05,
"loss": 0.2169,
"step": 491
},
{
"epoch": 0.32,
"learning_rate": 1.5977173166030312e-05,
"loss": 0.9878,
"step": 492
},
{
"epoch": 0.32,
"learning_rate": 1.596040272512261e-05,
"loss": 0.9734,
"step": 493
},
{
"epoch": 0.32,
"learning_rate": 1.5943606243240504e-05,
"loss": 0.9984,
"step": 494
},
{
"epoch": 0.32,
"learning_rate": 1.592678379376775e-05,
"loss": 0.231,
"step": 495
},
{
"epoch": 0.32,
"learning_rate": 1.590993545020156e-05,
"loss": 0.24,
"step": 496
},
{
"epoch": 0.32,
"learning_rate": 1.5893061286152275e-05,
"loss": 0.9805,
"step": 497
},
{
"epoch": 0.32,
"learning_rate": 1.587616137534305e-05,
"loss": 0.2385,
"step": 498
},
{
"epoch": 0.32,
"learning_rate": 1.585923579160952e-05,
"loss": 0.272,
"step": 499
},
{
"epoch": 0.32,
"learning_rate": 1.584228460889949e-05,
"loss": 0.9517,
"step": 500
},
{
"epoch": 0.32,
"learning_rate": 1.5825307901272612e-05,
"loss": 0.9404,
"step": 501
},
{
"epoch": 0.32,
"learning_rate": 1.5808305742900044e-05,
"loss": 1.0319,
"step": 502
},
{
"epoch": 0.32,
"learning_rate": 1.5791278208064142e-05,
"loss": 0.993,
"step": 503
},
{
"epoch": 0.33,
"learning_rate": 1.5774225371158142e-05,
"loss": 0.9708,
"step": 504
},
{
"epoch": 0.33,
"learning_rate": 1.5757147306685806e-05,
"loss": 1.0033,
"step": 505
},
{
"epoch": 0.33,
"learning_rate": 1.5740044089261137e-05,
"loss": 0.9726,
"step": 506
},
{
"epoch": 0.33,
"learning_rate": 1.5722915793608017e-05,
"loss": 1.0066,
"step": 507
},
{
"epoch": 0.33,
"learning_rate": 1.570576249455989e-05,
"loss": 0.9803,
"step": 508
},
{
"epoch": 0.33,
"learning_rate": 1.5688584267059453e-05,
"loss": 0.9454,
"step": 509
},
{
"epoch": 0.33,
"learning_rate": 1.567138118615831e-05,
"loss": 0.9823,
"step": 510
},
{
"epoch": 0.33,
"learning_rate": 1.565415332701665e-05,
"loss": 0.239,
"step": 511
},
{
"epoch": 0.33,
"learning_rate": 1.5636900764902914e-05,
"loss": 1.0114,
"step": 512
},
{
"epoch": 0.33,
"learning_rate": 1.561962357519348e-05,
"loss": 0.2282,
"step": 513
},
{
"epoch": 0.33,
"learning_rate": 1.5602321833372304e-05,
"loss": 0.9745,
"step": 514
},
{
"epoch": 0.33,
"learning_rate": 1.5584995615030634e-05,
"loss": 0.2495,
"step": 515
},
{
"epoch": 0.33,
"learning_rate": 1.556764499586664e-05,
"loss": 0.9671,
"step": 516
},
{
"epoch": 0.33,
"learning_rate": 1.555027005168511e-05,
"loss": 0.2598,
"step": 517
},
{
"epoch": 0.33,
"learning_rate": 1.5532870858397093e-05,
"loss": 0.9535,
"step": 518
},
{
"epoch": 0.33,
"learning_rate": 1.5515447492019598e-05,
"loss": 0.961,
"step": 519
},
{
"epoch": 0.34,
"learning_rate": 1.549800002867524e-05,
"loss": 0.9421,
"step": 520
},
{
"epoch": 0.34,
"learning_rate": 1.5480528544591907e-05,
"loss": 0.2503,
"step": 521
},
{
"epoch": 0.34,
"learning_rate": 1.546303311610244e-05,
"loss": 0.9983,
"step": 522
},
{
"epoch": 0.34,
"learning_rate": 1.54455138196443e-05,
"loss": 0.9554,
"step": 523
},
{
"epoch": 0.34,
"learning_rate": 1.5427970731759214e-05,
"loss": 0.9628,
"step": 524
},
{
"epoch": 0.34,
"learning_rate": 1.5410403929092858e-05,
"loss": 0.9603,
"step": 525
},
{
"epoch": 0.34,
"learning_rate": 1.539281348839452e-05,
"loss": 0.9764,
"step": 526
},
{
"epoch": 0.34,
"learning_rate": 1.537519948651676e-05,
"loss": 0.9733,
"step": 527
},
{
"epoch": 0.34,
"learning_rate": 1.5357562000415086e-05,
"loss": 0.9756,
"step": 528
},
{
"epoch": 0.34,
"learning_rate": 1.533990110714759e-05,
"loss": 0.9437,
"step": 529
},
{
"epoch": 0.34,
"learning_rate": 1.5322216883874643e-05,
"loss": 0.9679,
"step": 530
},
{
"epoch": 0.34,
"learning_rate": 1.5304509407858545e-05,
"loss": 0.9656,
"step": 531
},
{
"epoch": 0.34,
"learning_rate": 1.5286778756463184e-05,
"loss": 0.9477,
"step": 532
},
{
"epoch": 0.34,
"learning_rate": 1.52690250071537e-05,
"loss": 0.9638,
"step": 533
},
{
"epoch": 0.34,
"learning_rate": 1.5251248237496148e-05,
"loss": 0.9748,
"step": 534
},
{
"epoch": 0.35,
"learning_rate": 1.5233448525157161e-05,
"loss": 0.973,
"step": 535
},
{
"epoch": 0.35,
"learning_rate": 1.5215625947903604e-05,
"loss": 0.9545,
"step": 536
},
{
"epoch": 0.35,
"learning_rate": 1.5197780583602249e-05,
"loss": 0.2126,
"step": 537
},
{
"epoch": 0.35,
"learning_rate": 1.5179912510219413e-05,
"loss": 0.9249,
"step": 538
},
{
"epoch": 0.35,
"learning_rate": 1.5162021805820633e-05,
"loss": 0.9747,
"step": 539
},
{
"epoch": 0.35,
"learning_rate": 1.5144108548570322e-05,
"loss": 0.2464,
"step": 540
},
{
"epoch": 0.35,
"learning_rate": 1.5126172816731424e-05,
"loss": 0.9811,
"step": 541
},
{
"epoch": 0.35,
"learning_rate": 1.510821468866508e-05,
"loss": 0.2382,
"step": 542
},
{
"epoch": 0.35,
"learning_rate": 1.5090234242830271e-05,
"loss": 0.9396,
"step": 543
},
{
"epoch": 0.35,
"learning_rate": 1.5072231557783492e-05,
"loss": 0.9729,
"step": 544
},
{
"epoch": 0.35,
"learning_rate": 1.50542067121784e-05,
"loss": 0.9949,
"step": 545
},
{
"epoch": 0.35,
"learning_rate": 1.5036159784765464e-05,
"loss": 0.9656,
"step": 546
},
{
"epoch": 0.35,
"learning_rate": 1.5018090854391638e-05,
"loss": 0.9552,
"step": 547
},
{
"epoch": 0.35,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.9374,
"step": 548
},
{
"epoch": 0.35,
"learning_rate": 1.498188730062942e-05,
"loss": 0.2146,
"step": 549
},
{
"epoch": 0.35,
"learning_rate": 1.4963752835414204e-05,
"loss": 0.9622,
"step": 550
},
{
"epoch": 0.36,
"learning_rate": 1.4945596683583754e-05,
"loss": 0.9743,
"step": 551
},
{
"epoch": 0.36,
"learning_rate": 1.492741892446222e-05,
"loss": 0.9704,
"step": 552
},
{
"epoch": 0.36,
"learning_rate": 1.4909219637468153e-05,
"loss": 0.9825,
"step": 553
},
{
"epoch": 0.36,
"learning_rate": 1.4890998902114166e-05,
"loss": 0.9893,
"step": 554
},
{
"epoch": 0.36,
"learning_rate": 1.4872756798006576e-05,
"loss": 0.9797,
"step": 555
},
{
"epoch": 0.36,
"learning_rate": 1.4854493404845051e-05,
"loss": 0.2289,
"step": 556
},
{
"epoch": 0.36,
"learning_rate": 1.4836208802422287e-05,
"loss": 0.9671,
"step": 557
},
{
"epoch": 0.36,
"learning_rate": 1.481790307062363e-05,
"loss": 0.9819,
"step": 558
},
{
"epoch": 0.36,
"learning_rate": 1.4799576289426747e-05,
"loss": 0.975,
"step": 559
},
{
"epoch": 0.36,
"learning_rate": 1.4781228538901267e-05,
"loss": 0.9582,
"step": 560
},
{
"epoch": 0.36,
"learning_rate": 1.4762859899208437e-05,
"loss": 0.9921,
"step": 561
},
{
"epoch": 0.36,
"learning_rate": 1.4744470450600766e-05,
"loss": 0.9755,
"step": 562
},
{
"epoch": 0.36,
"learning_rate": 1.4726060273421675e-05,
"loss": 0.9622,
"step": 563
},
{
"epoch": 0.36,
"learning_rate": 1.4707629448105155e-05,
"loss": 0.9734,
"step": 564
},
{
"epoch": 0.36,
"learning_rate": 1.4689178055175396e-05,
"loss": 0.9562,
"step": 565
},
{
"epoch": 0.37,
"learning_rate": 1.4670706175246463e-05,
"loss": 0.2511,
"step": 566
},
{
"epoch": 0.37,
"learning_rate": 1.465221388902192e-05,
"loss": 0.9808,
"step": 567
},
{
"epoch": 0.37,
"learning_rate": 1.4633701277294487e-05,
"loss": 0.9701,
"step": 568
},
{
"epoch": 0.37,
"learning_rate": 1.4615168420945689e-05,
"loss": 0.9704,
"step": 569
},
{
"epoch": 0.37,
"learning_rate": 1.4596615400945498e-05,
"loss": 0.95,
"step": 570
},
{
"epoch": 0.37,
"learning_rate": 1.4578042298351973e-05,
"loss": 0.9748,
"step": 571
},
{
"epoch": 0.37,
"learning_rate": 1.4559449194310926e-05,
"loss": 0.9353,
"step": 572
},
{
"epoch": 0.37,
"learning_rate": 1.4540836170055552e-05,
"loss": 0.966,
"step": 573
},
{
"epoch": 0.37,
"learning_rate": 1.4522203306906076e-05,
"loss": 0.9819,
"step": 574
},
{
"epoch": 0.37,
"learning_rate": 1.450355068626939e-05,
"loss": 0.9584,
"step": 575
},
{
"epoch": 0.37,
"learning_rate": 1.4484878389638728e-05,
"loss": 0.9467,
"step": 576
},
{
"epoch": 0.37,
"learning_rate": 1.4466186498593265e-05,
"loss": 0.9375,
"step": 577
},
{
"epoch": 0.37,
"learning_rate": 1.4447475094797796e-05,
"loss": 0.2513,
"step": 578
},
{
"epoch": 0.37,
"learning_rate": 1.442874426000237e-05,
"loss": 0.2542,
"step": 579
},
{
"epoch": 0.37,
"learning_rate": 1.4409994076041922e-05,
"loss": 0.9696,
"step": 580
},
{
"epoch": 0.37,
"learning_rate": 1.4391224624835928e-05,
"loss": 0.9811,
"step": 581
},
{
"epoch": 0.38,
"learning_rate": 1.437243598838804e-05,
"loss": 0.9691,
"step": 582
},
{
"epoch": 0.38,
"learning_rate": 1.435362824878573e-05,
"loss": 0.2666,
"step": 583
},
{
"epoch": 0.38,
"learning_rate": 1.4334801488199941e-05,
"loss": 0.9712,
"step": 584
},
{
"epoch": 0.38,
"learning_rate": 1.43159557888847e-05,
"loss": 0.9333,
"step": 585
},
{
"epoch": 0.38,
"learning_rate": 1.4297091233176796e-05,
"loss": 0.2375,
"step": 586
},
{
"epoch": 0.38,
"learning_rate": 1.4278207903495388e-05,
"loss": 0.981,
"step": 587
},
{
"epoch": 0.38,
"learning_rate": 1.425930588234167e-05,
"loss": 0.9757,
"step": 588
},
{
"epoch": 0.38,
"learning_rate": 1.4240385252298485e-05,
"loss": 0.9682,
"step": 589
},
{
"epoch": 0.38,
"learning_rate": 1.4221446096029992e-05,
"loss": 0.9878,
"step": 590
},
{
"epoch": 0.38,
"learning_rate": 1.4202488496281283e-05,
"loss": 0.9423,
"step": 591
},
{
"epoch": 0.38,
"learning_rate": 1.4183512535878032e-05,
"loss": 0.2367,
"step": 592
},
{
"epoch": 0.38,
"learning_rate": 1.4164518297726129e-05,
"loss": 0.9686,
"step": 593
},
{
"epoch": 0.38,
"learning_rate": 1.4145505864811319e-05,
"loss": 0.2229,
"step": 594
},
{
"epoch": 0.38,
"learning_rate": 1.4126475320198845e-05,
"loss": 0.2516,
"step": 595
},
{
"epoch": 0.38,
"learning_rate": 1.4107426747033075e-05,
"loss": 0.9633,
"step": 596
},
{
"epoch": 0.39,
"learning_rate": 1.4088360228537144e-05,
"loss": 1.0011,
"step": 597
},
{
"epoch": 0.39,
"learning_rate": 1.4069275848012596e-05,
"loss": 0.2379,
"step": 598
},
{
"epoch": 0.39,
"learning_rate": 1.4050173688839e-05,
"loss": 0.2344,
"step": 599
},
{
"epoch": 0.39,
"learning_rate": 1.4031053834473614e-05,
"loss": 0.9842,
"step": 600
},
{
"epoch": 0.39,
"learning_rate": 1.4011916368451e-05,
"loss": 0.9993,
"step": 601
},
{
"epoch": 0.39,
"learning_rate": 1.399276137438267e-05,
"loss": 0.9808,
"step": 602
},
{
"epoch": 0.39,
"learning_rate": 1.397358893595671e-05,
"loss": 0.2238,
"step": 603
},
{
"epoch": 0.39,
"learning_rate": 1.395439913693742e-05,
"loss": 0.964,
"step": 604
},
{
"epoch": 0.39,
"learning_rate": 1.3935192061164957e-05,
"loss": 0.2291,
"step": 605
},
{
"epoch": 0.39,
"learning_rate": 1.3915967792554947e-05,
"loss": 0.2311,
"step": 606
},
{
"epoch": 0.39,
"learning_rate": 1.3896726415098147e-05,
"loss": 0.9657,
"step": 607
},
{
"epoch": 0.39,
"learning_rate": 1.3877468012860047e-05,
"loss": 0.9727,
"step": 608
},
{
"epoch": 0.39,
"learning_rate": 1.3858192669980529e-05,
"loss": 0.2659,
"step": 609
},
{
"epoch": 0.39,
"learning_rate": 1.3838900470673482e-05,
"loss": 0.9875,
"step": 610
},
{
"epoch": 0.39,
"learning_rate": 1.3819591499226446e-05,
"loss": 0.9102,
"step": 611
},
{
"epoch": 0.39,
"learning_rate": 1.3800265840000236e-05,
"loss": 0.9814,
"step": 612
},
{
"epoch": 0.4,
"learning_rate": 1.3780923577428574e-05,
"loss": 0.2789,
"step": 613
},
{
"epoch": 0.4,
"learning_rate": 1.3761564796017724e-05,
"loss": 0.9798,
"step": 614
},
{
"epoch": 0.4,
"learning_rate": 1.3742189580346122e-05,
"loss": 0.9454,
"step": 615
},
{
"epoch": 0.4,
"learning_rate": 1.3722798015064003e-05,
"loss": 0.9576,
"step": 616
},
{
"epoch": 0.4,
"learning_rate": 1.3703390184893034e-05,
"loss": 0.9648,
"step": 617
},
{
"epoch": 0.4,
"learning_rate": 1.3683966174625942e-05,
"loss": 0.2354,
"step": 618
},
{
"epoch": 0.4,
"learning_rate": 1.3664526069126148e-05,
"loss": 0.9835,
"step": 619
},
{
"epoch": 0.4,
"learning_rate": 1.364506995332739e-05,
"loss": 0.9725,
"step": 620
},
{
"epoch": 0.4,
"learning_rate": 1.3625597912233355e-05,
"loss": 0.9469,
"step": 621
},
{
"epoch": 0.4,
"learning_rate": 1.3606110030917311e-05,
"loss": 0.9851,
"step": 622
},
{
"epoch": 0.4,
"learning_rate": 1.3586606394521729e-05,
"loss": 1.0069,
"step": 623
},
{
"epoch": 0.4,
"learning_rate": 1.3567087088257913e-05,
"loss": 0.9756,
"step": 624
},
{
"epoch": 0.4,
"learning_rate": 1.3547552197405632e-05,
"loss": 0.9482,
"step": 625
},
{
"epoch": 0.4,
"learning_rate": 1.3528001807312734e-05,
"loss": 0.9614,
"step": 626
},
{
"epoch": 0.4,
"learning_rate": 1.3508436003394804e-05,
"loss": 0.2343,
"step": 627
},
{
"epoch": 0.41,
"learning_rate": 1.3488854871134746e-05,
"loss": 0.952,
"step": 628
},
{
"epoch": 0.41,
"learning_rate": 1.3469258496082452e-05,
"loss": 0.9808,
"step": 629
},
{
"epoch": 0.41,
"learning_rate": 1.3449646963854396e-05,
"loss": 0.2502,
"step": 630
},
{
"epoch": 0.41,
"learning_rate": 1.3430020360133283e-05,
"loss": 0.9748,
"step": 631
},
{
"epoch": 0.41,
"learning_rate": 1.341037877066766e-05,
"loss": 0.9663,
"step": 632
},
{
"epoch": 0.41,
"learning_rate": 1.3390722281271553e-05,
"loss": 0.956,
"step": 633
},
{
"epoch": 0.41,
"learning_rate": 1.3371050977824077e-05,
"loss": 0.9421,
"step": 634
},
{
"epoch": 0.41,
"learning_rate": 1.3351364946269071e-05,
"loss": 0.9834,
"step": 635
},
{
"epoch": 0.41,
"learning_rate": 1.3331664272614733e-05,
"loss": 0.9847,
"step": 636
},
{
"epoch": 0.41,
"learning_rate": 1.3311949042933216e-05,
"loss": 0.9562,
"step": 637
},
{
"epoch": 0.41,
"learning_rate": 1.329221934336028e-05,
"loss": 0.9352,
"step": 638
},
{
"epoch": 0.41,
"learning_rate": 1.3272475260094897e-05,
"loss": 0.2563,
"step": 639
},
{
"epoch": 0.41,
"learning_rate": 1.3252716879398884e-05,
"loss": 0.9522,
"step": 640
},
{
"epoch": 0.41,
"learning_rate": 1.323294428759652e-05,
"loss": 0.2442,
"step": 641
},
{
"epoch": 0.41,
"learning_rate": 1.321315757107418e-05,
"loss": 0.9365,
"step": 642
},
{
"epoch": 0.41,
"learning_rate": 1.3193356816279945e-05,
"loss": 0.9722,
"step": 643
},
{
"epoch": 0.42,
"learning_rate": 1.3173542109723227e-05,
"loss": 0.9511,
"step": 644
},
{
"epoch": 0.42,
"learning_rate": 1.3153713537974396e-05,
"loss": 0.9679,
"step": 645
},
{
"epoch": 0.42,
"learning_rate": 1.31338711876644e-05,
"loss": 0.9679,
"step": 646
},
{
"epoch": 0.42,
"learning_rate": 1.311401514548438e-05,
"loss": 0.9476,
"step": 647
},
{
"epoch": 0.42,
"learning_rate": 1.3094145498185305e-05,
"loss": 0.949,
"step": 648
},
{
"epoch": 0.42,
"learning_rate": 1.3074262332577579e-05,
"loss": 0.9489,
"step": 649
},
{
"epoch": 0.42,
"learning_rate": 1.3054365735530666e-05,
"loss": 0.2183,
"step": 650
},
{
"epoch": 0.42,
"learning_rate": 1.3034455793972719e-05,
"loss": 0.9653,
"step": 651
},
{
"epoch": 0.42,
"learning_rate": 1.3014532594890185e-05,
"loss": 0.9884,
"step": 652
},
{
"epoch": 0.42,
"learning_rate": 1.2994596225327442e-05,
"loss": 0.9617,
"step": 653
},
{
"epoch": 0.42,
"learning_rate": 1.2974646772386399e-05,
"loss": 0.2393,
"step": 654
},
{
"epoch": 0.42,
"learning_rate": 1.2954684323226137e-05,
"loss": 0.9435,
"step": 655
},
{
"epoch": 0.42,
"learning_rate": 1.2934708965062508e-05,
"loss": 0.964,
"step": 656
},
{
"epoch": 0.42,
"learning_rate": 1.291472078516777e-05,
"loss": 0.9473,
"step": 657
},
{
"epoch": 0.42,
"learning_rate": 1.2894719870870197e-05,
"loss": 0.9546,
"step": 658
},
{
"epoch": 0.43,
"learning_rate": 1.2874706309553697e-05,
"loss": 0.9631,
"step": 659
},
{
"epoch": 0.43,
"learning_rate": 1.2854680188657439e-05,
"loss": 1.013,
"step": 660
},
{
"epoch": 0.43,
"learning_rate": 1.2834641595675454e-05,
"loss": 0.9574,
"step": 661
},
{
"epoch": 0.43,
"learning_rate": 1.2814590618156278e-05,
"loss": 0.9675,
"step": 662
},
{
"epoch": 0.43,
"learning_rate": 1.2794527343702546e-05,
"loss": 0.9499,
"step": 663
},
{
"epoch": 0.43,
"learning_rate": 1.2774451859970614e-05,
"loss": 0.2537,
"step": 664
},
{
"epoch": 0.43,
"learning_rate": 1.2754364254670192e-05,
"loss": 0.9451,
"step": 665
},
{
"epoch": 0.43,
"learning_rate": 1.2734264615563941e-05,
"loss": 0.9735,
"step": 666
},
{
"epoch": 0.43,
"learning_rate": 1.2714153030467095e-05,
"loss": 0.9694,
"step": 667
},
{
"epoch": 0.43,
"learning_rate": 1.2694029587247097e-05,
"loss": 0.2515,
"step": 668
},
{
"epoch": 0.43,
"learning_rate": 1.2673894373823171e-05,
"loss": 0.9565,
"step": 669
},
{
"epoch": 0.43,
"learning_rate": 1.2653747478165988e-05,
"loss": 0.9714,
"step": 670
},
{
"epoch": 0.43,
"learning_rate": 1.263358898829725e-05,
"loss": 0.9709,
"step": 671
},
{
"epoch": 0.43,
"learning_rate": 1.2613418992289307e-05,
"loss": 0.9612,
"step": 672
},
{
"epoch": 0.43,
"learning_rate": 1.2593237578264802e-05,
"loss": 0.9565,
"step": 673
},
{
"epoch": 0.43,
"learning_rate": 1.257304483439623e-05,
"loss": 0.9719,
"step": 674
},
{
"epoch": 0.44,
"learning_rate": 1.2552840848905619e-05,
"loss": 0.9949,
"step": 675
},
{
"epoch": 0.44,
"learning_rate": 1.2532625710064084e-05,
"loss": 0.9637,
"step": 676
},
{
"epoch": 0.44,
"learning_rate": 1.251239950619149e-05,
"loss": 0.9458,
"step": 677
},
{
"epoch": 0.44,
"learning_rate": 1.2492162325656035e-05,
"loss": 0.2155,
"step": 678
},
{
"epoch": 0.44,
"learning_rate": 1.2471914256873871e-05,
"loss": 0.9686,
"step": 679
},
{
"epoch": 0.44,
"learning_rate": 1.245165538830873e-05,
"loss": 0.9646,
"step": 680
},
{
"epoch": 0.44,
"learning_rate": 1.2431385808471523e-05,
"loss": 0.9494,
"step": 681
},
{
"epoch": 0.44,
"learning_rate": 1.241110560591996e-05,
"loss": 0.987,
"step": 682
},
{
"epoch": 0.44,
"learning_rate": 1.2390814869258155e-05,
"loss": 0.987,
"step": 683
},
{
"epoch": 0.44,
"learning_rate": 1.2370513687136254e-05,
"loss": 0.9752,
"step": 684
},
{
"epoch": 0.44,
"learning_rate": 1.2350202148250039e-05,
"loss": 0.9573,
"step": 685
},
{
"epoch": 0.44,
"learning_rate": 1.2329880341340533e-05,
"loss": 0.9471,
"step": 686
},
{
"epoch": 0.44,
"learning_rate": 1.2309548355193632e-05,
"loss": 0.2481,
"step": 687
},
{
"epoch": 0.44,
"learning_rate": 1.228920627863969e-05,
"loss": 0.2218,
"step": 688
},
{
"epoch": 0.44,
"learning_rate": 1.2268854200553158e-05,
"loss": 0.9687,
"step": 689
},
{
"epoch": 0.45,
"learning_rate": 1.2248492209852178e-05,
"loss": 0.9778,
"step": 690
},
{
"epoch": 0.45,
"learning_rate": 1.2228120395498201e-05,
"loss": 0.9344,
"step": 691
},
{
"epoch": 0.45,
"learning_rate": 1.22077388464956e-05,
"loss": 0.2554,
"step": 692
},
{
"epoch": 0.45,
"learning_rate": 1.2187347651891277e-05,
"loss": 0.9571,
"step": 693
},
{
"epoch": 0.45,
"learning_rate": 1.2166946900774275e-05,
"loss": 0.1847,
"step": 694
},
{
"epoch": 0.45,
"learning_rate": 1.2146536682275388e-05,
"loss": 0.9607,
"step": 695
},
{
"epoch": 0.45,
"learning_rate": 1.2126117085566776e-05,
"loss": 0.2674,
"step": 696
},
{
"epoch": 0.45,
"learning_rate": 1.210568819986157e-05,
"loss": 0.9813,
"step": 697
},
{
"epoch": 0.45,
"learning_rate": 1.2085250114413484e-05,
"loss": 0.9322,
"step": 698
},
{
"epoch": 0.45,
"learning_rate": 1.2064802918516433e-05,
"loss": 0.9854,
"step": 699
},
{
"epoch": 0.45,
"learning_rate": 1.2044346701504129e-05,
"loss": 0.9709,
"step": 700
},
{
"epoch": 0.45,
"learning_rate": 1.2023881552749693e-05,
"loss": 0.9423,
"step": 701
},
{
"epoch": 0.45,
"learning_rate": 1.2003407561665272e-05,
"loss": 0.9662,
"step": 702
},
{
"epoch": 0.45,
"learning_rate": 1.1982924817701656e-05,
"loss": 0.9859,
"step": 703
},
{
"epoch": 0.45,
"learning_rate": 1.196243341034786e-05,
"loss": 0.9364,
"step": 704
},
{
"epoch": 0.45,
"learning_rate": 1.1941933429130759e-05,
"loss": 0.9702,
"step": 705
},
{
"epoch": 0.46,
"learning_rate": 1.1921424963614686e-05,
"loss": 0.95,
"step": 706
},
{
"epoch": 0.46,
"learning_rate": 1.1900908103401037e-05,
"loss": 0.9629,
"step": 707
},
{
"epoch": 0.46,
"learning_rate": 1.1880382938127886e-05,
"loss": 0.908,
"step": 708
},
{
"epoch": 0.46,
"learning_rate": 1.1859849557469603e-05,
"loss": 0.9699,
"step": 709
},
{
"epoch": 0.46,
"learning_rate": 1.1839308051136432e-05,
"loss": 0.9723,
"step": 710
},
{
"epoch": 0.46,
"learning_rate": 1.1818758508874133e-05,
"loss": 0.9505,
"step": 711
},
{
"epoch": 0.46,
"learning_rate": 1.1798201020463567e-05,
"loss": 0.9539,
"step": 712
},
{
"epoch": 0.46,
"learning_rate": 1.1777635675720313e-05,
"loss": 0.9455,
"step": 713
},
{
"epoch": 0.46,
"learning_rate": 1.1757062564494282e-05,
"loss": 0.9425,
"step": 714
},
{
"epoch": 0.46,
"learning_rate": 1.1736481776669307e-05,
"loss": 0.2497,
"step": 715
},
{
"epoch": 0.46,
"learning_rate": 1.171589340216276e-05,
"loss": 0.9396,
"step": 716
},
{
"epoch": 0.46,
"learning_rate": 1.1695297530925162e-05,
"loss": 0.9517,
"step": 717
},
{
"epoch": 0.46,
"learning_rate": 1.1674694252939795e-05,
"loss": 0.2489,
"step": 718
},
{
"epoch": 0.46,
"learning_rate": 1.1654083658222287e-05,
"loss": 0.2416,
"step": 719
},
{
"epoch": 0.46,
"learning_rate": 1.1633465836820243e-05,
"loss": 0.2388,
"step": 720
},
{
"epoch": 0.47,
"learning_rate": 1.1612840878812839e-05,
"loss": 0.9303,
"step": 721
},
{
"epoch": 0.47,
"learning_rate": 1.1592208874310426e-05,
"loss": 0.9792,
"step": 722
},
{
"epoch": 0.47,
"learning_rate": 1.1571569913454145e-05,
"loss": 0.9629,
"step": 723
},
{
"epoch": 0.47,
"learning_rate": 1.1550924086415532e-05,
"loss": 0.9646,
"step": 724
},
{
"epoch": 0.47,
"learning_rate": 1.1530271483396115e-05,
"loss": 0.2257,
"step": 725
},
{
"epoch": 0.47,
"learning_rate": 1.1509612194627033e-05,
"loss": 0.9505,
"step": 726
},
{
"epoch": 0.47,
"learning_rate": 1.1488946310368629e-05,
"loss": 0.9702,
"step": 727
},
{
"epoch": 0.47,
"learning_rate": 1.146827392091007e-05,
"loss": 0.9662,
"step": 728
},
{
"epoch": 0.47,
"learning_rate": 1.1447595116568928e-05,
"loss": 0.9396,
"step": 729
},
{
"epoch": 0.47,
"learning_rate": 1.142690998769082e-05,
"loss": 0.9548,
"step": 730
},
{
"epoch": 0.47,
"learning_rate": 1.1406218624648986e-05,
"loss": 0.9453,
"step": 731
},
{
"epoch": 0.47,
"learning_rate": 1.1385521117843898e-05,
"loss": 1.0062,
"step": 732
},
{
"epoch": 0.47,
"learning_rate": 1.1364817557702886e-05,
"loss": 0.9898,
"step": 733
},
{
"epoch": 0.47,
"learning_rate": 1.134410803467971e-05,
"loss": 0.9717,
"step": 734
},
{
"epoch": 0.47,
"learning_rate": 1.1323392639254194e-05,
"loss": 0.9413,
"step": 735
},
{
"epoch": 0.47,
"learning_rate": 1.1302671461931805e-05,
"loss": 0.963,
"step": 736
},
{
"epoch": 0.48,
"learning_rate": 1.1281944593243289e-05,
"loss": 0.271,
"step": 737
},
{
"epoch": 0.48,
"learning_rate": 1.126121212374424e-05,
"loss": 0.9428,
"step": 738
},
{
"epoch": 0.48,
"learning_rate": 1.1240474144014735e-05,
"loss": 0.243,
"step": 739
},
{
"epoch": 0.48,
"learning_rate": 1.1219730744658921e-05,
"loss": 0.9717,
"step": 740
},
{
"epoch": 0.48,
"learning_rate": 1.1198982016304618e-05,
"loss": 0.9397,
"step": 741
},
{
"epoch": 0.48,
"learning_rate": 1.1178228049602938e-05,
"loss": 0.9684,
"step": 742
},
{
"epoch": 0.48,
"learning_rate": 1.1157468935227866e-05,
"loss": 0.2376,
"step": 743
},
{
"epoch": 0.48,
"learning_rate": 1.1136704763875895e-05,
"loss": 0.9416,
"step": 744
},
{
"epoch": 0.48,
"learning_rate": 1.1115935626265596e-05,
"loss": 0.9679,
"step": 745
},
{
"epoch": 0.48,
"learning_rate": 1.1095161613137242e-05,
"loss": 0.2137,
"step": 746
},
{
"epoch": 0.48,
"learning_rate": 1.1074382815252418e-05,
"loss": 0.2711,
"step": 747
},
{
"epoch": 0.48,
"learning_rate": 1.1053599323393594e-05,
"loss": 0.9598,
"step": 748
},
{
"epoch": 0.48,
"learning_rate": 1.1032811228363766e-05,
"loss": 0.947,
"step": 749
},
{
"epoch": 0.48,
"learning_rate": 1.1012018620986028e-05,
"loss": 0.961,
"step": 750
},
{
"epoch": 0.48,
"learning_rate": 1.0991221592103198e-05,
"loss": 0.964,
"step": 751
},
{
"epoch": 0.49,
"learning_rate": 1.0970420232577408e-05,
"loss": 0.95,
"step": 752
},
{
"epoch": 0.49,
"learning_rate": 1.0949614633289708e-05,
"loss": 0.9869,
"step": 753
},
{
"epoch": 0.49,
"learning_rate": 1.0928804885139674e-05,
"loss": 0.9749,
"step": 754
},
{
"epoch": 0.49,
"learning_rate": 1.0907991079045006e-05,
"loss": 0.9641,
"step": 755
},
{
"epoch": 0.49,
"learning_rate": 1.088717330594114e-05,
"loss": 0.9731,
"step": 756
},
{
"epoch": 0.49,
"learning_rate": 1.0866351656780835e-05,
"loss": 0.2149,
"step": 757
},
{
"epoch": 0.49,
"learning_rate": 1.0845526222533791e-05,
"loss": 0.9575,
"step": 758
},
{
"epoch": 0.49,
"learning_rate": 1.082469709418624e-05,
"loss": 0.9569,
"step": 759
},
{
"epoch": 0.49,
"learning_rate": 1.0803864362740562e-05,
"loss": 0.9461,
"step": 760
},
{
"epoch": 0.49,
"learning_rate": 1.0783028119214863e-05,
"loss": 0.9554,
"step": 761
},
{
"epoch": 0.49,
"learning_rate": 1.076218845464261e-05,
"loss": 0.9448,
"step": 762
},
{
"epoch": 0.49,
"learning_rate": 1.074134546007221e-05,
"loss": 0.9145,
"step": 763
},
{
"epoch": 0.49,
"learning_rate": 1.0720499226566616e-05,
"loss": 0.9636,
"step": 764
},
{
"epoch": 0.49,
"learning_rate": 1.0699649845202935e-05,
"loss": 0.2498,
"step": 765
},
{
"epoch": 0.49,
"learning_rate": 1.0678797407072027e-05,
"loss": 0.9522,
"step": 766
},
{
"epoch": 0.49,
"learning_rate": 1.0657942003278107e-05,
"loss": 0.9635,
"step": 767
},
{
"epoch": 0.5,
"learning_rate": 1.0637083724938344e-05,
"loss": 0.9575,
"step": 768
},
{
"epoch": 0.5,
"learning_rate": 1.0616222663182474e-05,
"loss": 0.235,
"step": 769
},
{
"epoch": 0.5,
"learning_rate": 1.0595358909152377e-05,
"loss": 0.2393,
"step": 770
},
{
"epoch": 0.5,
"learning_rate": 1.0574492554001718e-05,
"loss": 0.9586,
"step": 771
},
{
"epoch": 0.5,
"learning_rate": 1.0553623688895509e-05,
"loss": 0.9621,
"step": 772
},
{
"epoch": 0.5,
"learning_rate": 1.0532752405009733e-05,
"loss": 0.9745,
"step": 773
},
{
"epoch": 0.5,
"learning_rate": 1.0511878793530943e-05,
"loss": 0.9424,
"step": 774
},
{
"epoch": 0.5,
"learning_rate": 1.0491002945655862e-05,
"loss": 0.9617,
"step": 775
},
{
"epoch": 0.5,
"learning_rate": 1.0470124952590976e-05,
"loss": 0.9386,
"step": 776
},
{
"epoch": 0.5,
"learning_rate": 1.0449244905552153e-05,
"loss": 0.2431,
"step": 777
},
{
"epoch": 0.5,
"learning_rate": 1.0428362895764231e-05,
"loss": 0.9417,
"step": 778
},
{
"epoch": 0.5,
"learning_rate": 1.0407479014460622e-05,
"loss": 0.9467,
"step": 779
},
{
"epoch": 0.5,
"learning_rate": 1.038659335288291e-05,
"loss": 0.9407,
"step": 780
},
{
"epoch": 0.5,
"learning_rate": 1.0365706002280471e-05,
"loss": 0.9979,
"step": 781
},
{
"epoch": 0.5,
"learning_rate": 1.034481705391005e-05,
"loss": 0.2167,
"step": 782
},
{
"epoch": 0.51,
"learning_rate": 1.032392659903537e-05,
"loss": 0.934,
"step": 783
},
{
"epoch": 0.51,
"learning_rate": 1.0303034728926741e-05,
"loss": 0.9673,
"step": 784
},
{
"epoch": 0.51,
"learning_rate": 1.0282141534860662e-05,
"loss": 0.974,
"step": 785
},
{
"epoch": 0.51,
"learning_rate": 1.0261247108119403e-05,
"loss": 0.9848,
"step": 786
},
{
"epoch": 0.51,
"learning_rate": 1.0240351539990628e-05,
"loss": 0.9606,
"step": 787
},
{
"epoch": 0.51,
"learning_rate": 1.0219454921766991e-05,
"loss": 0.9371,
"step": 788
},
{
"epoch": 0.51,
"learning_rate": 1.0198557344745718e-05,
"loss": 0.2384,
"step": 789
},
{
"epoch": 0.51,
"learning_rate": 1.0177658900228249e-05,
"loss": 0.9402,
"step": 790
},
{
"epoch": 0.51,
"learning_rate": 1.015675967951979e-05,
"loss": 0.2208,
"step": 791
},
{
"epoch": 0.51,
"learning_rate": 1.0135859773928949e-05,
"loss": 0.9423,
"step": 792
},
{
"epoch": 0.51,
"learning_rate": 1.011495927476733e-05,
"loss": 0.9846,
"step": 793
},
{
"epoch": 0.51,
"learning_rate": 1.0094058273349125e-05,
"loss": 0.2286,
"step": 794
},
{
"epoch": 0.51,
"learning_rate": 1.007315686099072e-05,
"loss": 0.9518,
"step": 795
},
{
"epoch": 0.51,
"learning_rate": 1.0052255129010293e-05,
"loss": 0.958,
"step": 796
},
{
"epoch": 0.51,
"learning_rate": 1.0031353168727432e-05,
"loss": 0.2308,
"step": 797
},
{
"epoch": 0.51,
"learning_rate": 1.0010451071462707e-05,
"loss": 0.2324,
"step": 798
},
{
"epoch": 0.52,
"learning_rate": 9.989548928537294e-06,
"loss": 0.9341,
"step": 799
},
{
"epoch": 0.52,
"learning_rate": 9.96864683127257e-06,
"loss": 0.947,
"step": 800
},
{
"epoch": 0.52,
"learning_rate": 9.947744870989705e-06,
"loss": 0.2412,
"step": 801
},
{
"epoch": 0.52,
"learning_rate": 9.926843139009286e-06,
"loss": 0.9728,
"step": 802
},
{
"epoch": 0.52,
"learning_rate": 9.90594172665088e-06,
"loss": 0.2251,
"step": 803
},
{
"epoch": 0.52,
"learning_rate": 9.885040725232671e-06,
"loss": 0.9591,
"step": 804
},
{
"epoch": 0.52,
"learning_rate": 9.864140226071054e-06,
"loss": 0.9557,
"step": 805
},
{
"epoch": 0.52,
"learning_rate": 9.843240320480213e-06,
"loss": 0.961,
"step": 806
},
{
"epoch": 0.52,
"learning_rate": 9.822341099771755e-06,
"loss": 0.9448,
"step": 807
},
{
"epoch": 0.52,
"learning_rate": 9.801442655254285e-06,
"loss": 0.9286,
"step": 808
},
{
"epoch": 0.52,
"learning_rate": 9.780545078233015e-06,
"loss": 0.9362,
"step": 809
},
{
"epoch": 0.52,
"learning_rate": 9.759648460009376e-06,
"loss": 0.2591,
"step": 810
},
{
"epoch": 0.52,
"learning_rate": 9.7387528918806e-06,
"loss": 0.2382,
"step": 811
},
{
"epoch": 0.52,
"learning_rate": 9.717858465139341e-06,
"loss": 0.9543,
"step": 812
},
{
"epoch": 0.52,
"learning_rate": 9.696965271073259e-06,
"loss": 0.2299,
"step": 813
},
{
"epoch": 0.53,
"learning_rate": 9.676073400964631e-06,
"loss": 0.2285,
"step": 814
},
{
"epoch": 0.53,
"learning_rate": 9.655182946089957e-06,
"loss": 0.9688,
"step": 815
},
{
"epoch": 0.53,
"learning_rate": 9.63429399771953e-06,
"loss": 0.9791,
"step": 816
},
{
"epoch": 0.53,
"learning_rate": 9.613406647117092e-06,
"loss": 0.2377,
"step": 817
},
{
"epoch": 0.53,
"learning_rate": 9.592520985539382e-06,
"loss": 0.9424,
"step": 818
},
{
"epoch": 0.53,
"learning_rate": 9.57163710423577e-06,
"loss": 0.2593,
"step": 819
},
{
"epoch": 0.53,
"learning_rate": 9.550755094447848e-06,
"loss": 0.9555,
"step": 820
},
{
"epoch": 0.53,
"learning_rate": 9.529875047409027e-06,
"loss": 0.9392,
"step": 821
},
{
"epoch": 0.53,
"learning_rate": 9.508997054344145e-06,
"loss": 0.9377,
"step": 822
},
{
"epoch": 0.53,
"learning_rate": 9.48812120646906e-06,
"loss": 0.9369,
"step": 823
},
{
"epoch": 0.53,
"learning_rate": 9.467247594990272e-06,
"loss": 0.9593,
"step": 824
},
{
"epoch": 0.53,
"learning_rate": 9.446376311104494e-06,
"loss": 0.9567,
"step": 825
},
{
"epoch": 0.53,
"learning_rate": 9.425507445998286e-06,
"loss": 0.9523,
"step": 826
},
{
"epoch": 0.53,
"learning_rate": 9.404641090847628e-06,
"loss": 0.9162,
"step": 827
},
{
"epoch": 0.53,
"learning_rate": 9.383777336817532e-06,
"loss": 0.2588,
"step": 828
},
{
"epoch": 0.53,
"learning_rate": 9.36291627506166e-06,
"loss": 0.9591,
"step": 829
},
{
"epoch": 0.54,
"learning_rate": 9.342057996721894e-06,
"loss": 0.2684,
"step": 830
},
{
"epoch": 0.54,
"learning_rate": 9.321202592927974e-06,
"loss": 0.9823,
"step": 831
},
{
"epoch": 0.54,
"learning_rate": 9.300350154797065e-06,
"loss": 0.9266,
"step": 832
},
{
"epoch": 0.54,
"learning_rate": 9.279500773433385e-06,
"loss": 0.933,
"step": 833
},
{
"epoch": 0.54,
"learning_rate": 9.258654539927795e-06,
"loss": 0.9538,
"step": 834
},
{
"epoch": 0.54,
"learning_rate": 9.237811545357393e-06,
"loss": 0.9254,
"step": 835
},
{
"epoch": 0.54,
"learning_rate": 9.21697188078514e-06,
"loss": 0.9213,
"step": 836
},
{
"epoch": 0.54,
"learning_rate": 9.196135637259443e-06,
"loss": 0.974,
"step": 837
},
{
"epoch": 0.54,
"learning_rate": 9.175302905813761e-06,
"loss": 0.2017,
"step": 838
},
{
"epoch": 0.54,
"learning_rate": 9.154473777466209e-06,
"loss": 0.9298,
"step": 839
},
{
"epoch": 0.54,
"learning_rate": 9.133648343219168e-06,
"loss": 0.9744,
"step": 840
},
{
"epoch": 0.54,
"learning_rate": 9.112826694058864e-06,
"loss": 0.9446,
"step": 841
},
{
"epoch": 0.54,
"learning_rate": 9.092008920954997e-06,
"loss": 0.962,
"step": 842
},
{
"epoch": 0.54,
"learning_rate": 9.07119511486033e-06,
"loss": 0.9444,
"step": 843
},
{
"epoch": 0.54,
"learning_rate": 9.050385366710295e-06,
"loss": 0.9499,
"step": 844
},
{
"epoch": 0.55,
"learning_rate": 9.029579767422592e-06,
"loss": 0.2302,
"step": 845
},
{
"epoch": 0.55,
"learning_rate": 9.008778407896807e-06,
"loss": 0.9446,
"step": 846
},
{
"epoch": 0.55,
"learning_rate": 8.987981379013975e-06,
"loss": 0.9491,
"step": 847
},
{
"epoch": 0.55,
"learning_rate": 8.967188771636237e-06,
"loss": 0.9349,
"step": 848
},
{
"epoch": 0.55,
"learning_rate": 8.946400676606408e-06,
"loss": 0.9492,
"step": 849
},
{
"epoch": 0.55,
"learning_rate": 8.925617184747586e-06,
"loss": 0.9355,
"step": 850
},
{
"epoch": 0.55,
"learning_rate": 8.904838386862758e-06,
"loss": 0.9742,
"step": 851
},
{
"epoch": 0.55,
"learning_rate": 8.884064373734406e-06,
"loss": 0.9362,
"step": 852
},
{
"epoch": 0.55,
"learning_rate": 8.86329523612411e-06,
"loss": 0.9164,
"step": 853
},
{
"epoch": 0.55,
"learning_rate": 8.842531064772137e-06,
"loss": 0.996,
"step": 854
},
{
"epoch": 0.55,
"learning_rate": 8.821771950397065e-06,
"loss": 0.9513,
"step": 855
},
{
"epoch": 0.55,
"learning_rate": 8.801017983695383e-06,
"loss": 0.9379,
"step": 856
},
{
"epoch": 0.55,
"learning_rate": 8.78026925534108e-06,
"loss": 0.9528,
"step": 857
},
{
"epoch": 0.55,
"learning_rate": 8.759525855985265e-06,
"loss": 0.2519,
"step": 858
},
{
"epoch": 0.55,
"learning_rate": 8.738787876255763e-06,
"loss": 0.9523,
"step": 859
},
{
"epoch": 0.55,
"learning_rate": 8.718055406756714e-06,
"loss": 0.9323,
"step": 860
},
{
"epoch": 0.56,
"learning_rate": 8.697328538068197e-06,
"loss": 0.1832,
"step": 861
},
{
"epoch": 0.56,
"learning_rate": 8.67660736074581e-06,
"loss": 0.963,
"step": 862
},
{
"epoch": 0.56,
"learning_rate": 8.655891965320292e-06,
"loss": 0.9636,
"step": 863
},
{
"epoch": 0.56,
"learning_rate": 8.635182442297114e-06,
"loss": 0.2548,
"step": 864
},
{
"epoch": 0.56,
"learning_rate": 8.614478882156104e-06,
"loss": 0.9511,
"step": 865
},
{
"epoch": 0.56,
"learning_rate": 8.59378137535102e-06,
"loss": 0.9293,
"step": 866
},
{
"epoch": 0.56,
"learning_rate": 8.573090012309181e-06,
"loss": 0.9389,
"step": 867
},
{
"epoch": 0.56,
"learning_rate": 8.552404883431075e-06,
"loss": 0.9509,
"step": 868
},
{
"epoch": 0.56,
"learning_rate": 8.531726079089934e-06,
"loss": 0.9582,
"step": 869
},
{
"epoch": 0.56,
"learning_rate": 8.511053689631371e-06,
"loss": 0.9403,
"step": 870
},
{
"epoch": 0.56,
"learning_rate": 8.490387805372965e-06,
"loss": 0.972,
"step": 871
},
{
"epoch": 0.56,
"learning_rate": 8.469728516603886e-06,
"loss": 0.2239,
"step": 872
},
{
"epoch": 0.56,
"learning_rate": 8.449075913584472e-06,
"loss": 0.9298,
"step": 873
},
{
"epoch": 0.56,
"learning_rate": 8.428430086545857e-06,
"loss": 0.2248,
"step": 874
},
{
"epoch": 0.56,
"learning_rate": 8.407791125689577e-06,
"loss": 0.9754,
"step": 875
},
{
"epoch": 0.57,
"learning_rate": 8.387159121187163e-06,
"loss": 0.9355,
"step": 876
},
{
"epoch": 0.57,
"learning_rate": 8.366534163179757e-06,
"loss": 0.9387,
"step": 877
},
{
"epoch": 0.57,
"learning_rate": 8.345916341777716e-06,
"loss": 0.219,
"step": 878
},
{
"epoch": 0.57,
"learning_rate": 8.325305747060208e-06,
"loss": 0.9187,
"step": 879
},
{
"epoch": 0.57,
"learning_rate": 8.30470246907484e-06,
"loss": 0.9448,
"step": 880
},
{
"epoch": 0.57,
"learning_rate": 8.284106597837244e-06,
"loss": 0.9467,
"step": 881
},
{
"epoch": 0.57,
"learning_rate": 8.263518223330698e-06,
"loss": 0.9442,
"step": 882
},
{
"epoch": 0.57,
"learning_rate": 8.242937435505718e-06,
"loss": 0.9723,
"step": 883
},
{
"epoch": 0.57,
"learning_rate": 8.222364324279689e-06,
"loss": 0.9352,
"step": 884
},
{
"epoch": 0.57,
"learning_rate": 8.201798979536438e-06,
"loss": 0.9954,
"step": 885
},
{
"epoch": 0.57,
"learning_rate": 8.18124149112587e-06,
"loss": 0.2378,
"step": 886
},
{
"epoch": 0.57,
"learning_rate": 8.160691948863572e-06,
"loss": 0.9487,
"step": 887
},
{
"epoch": 0.57,
"learning_rate": 8.1401504425304e-06,
"loss": 0.9295,
"step": 888
},
{
"epoch": 0.57,
"learning_rate": 8.119617061872115e-06,
"loss": 0.948,
"step": 889
},
{
"epoch": 0.57,
"learning_rate": 8.099091896598964e-06,
"loss": 0.9699,
"step": 890
},
{
"epoch": 0.57,
"learning_rate": 8.07857503638532e-06,
"loss": 0.9405,
"step": 891
},
{
"epoch": 0.58,
"learning_rate": 8.058066570869244e-06,
"loss": 0.2205,
"step": 892
},
{
"epoch": 0.58,
"learning_rate": 8.037566589652141e-06,
"loss": 0.9287,
"step": 893
},
{
"epoch": 0.58,
"learning_rate": 8.017075182298348e-06,
"loss": 0.246,
"step": 894
},
{
"epoch": 0.58,
"learning_rate": 7.996592438334728e-06,
"loss": 0.9487,
"step": 895
},
{
"epoch": 0.58,
"learning_rate": 7.97611844725031e-06,
"loss": 0.9282,
"step": 896
},
{
"epoch": 0.58,
"learning_rate": 7.955653298495876e-06,
"loss": 0.9427,
"step": 897
},
{
"epoch": 0.58,
"learning_rate": 7.935197081483568e-06,
"loss": 0.9366,
"step": 898
},
{
"epoch": 0.58,
"learning_rate": 7.914749885586517e-06,
"loss": 0.935,
"step": 899
},
{
"epoch": 0.58,
"learning_rate": 7.894311800138432e-06,
"loss": 0.9825,
"step": 900
},
{
"epoch": 0.58,
"learning_rate": 7.87388291443323e-06,
"loss": 0.9702,
"step": 901
},
{
"epoch": 0.58,
"learning_rate": 7.853463317724614e-06,
"loss": 0.9625,
"step": 902
},
{
"epoch": 0.58,
"learning_rate": 7.83305309922573e-06,
"loss": 0.2228,
"step": 903
},
{
"epoch": 0.58,
"learning_rate": 7.812652348108726e-06,
"loss": 0.9417,
"step": 904
},
{
"epoch": 0.58,
"learning_rate": 7.792261153504403e-06,
"loss": 0.9341,
"step": 905
},
{
"epoch": 0.58,
"learning_rate": 7.771879604501802e-06,
"loss": 0.2154,
"step": 906
},
{
"epoch": 0.59,
"learning_rate": 7.751507790147825e-06,
"loss": 0.9291,
"step": 907
},
{
"epoch": 0.59,
"learning_rate": 7.731145799446846e-06,
"loss": 0.9474,
"step": 908
},
{
"epoch": 0.59,
"learning_rate": 7.710793721360312e-06,
"loss": 0.9466,
"step": 909
},
{
"epoch": 0.59,
"learning_rate": 7.690451644806372e-06,
"loss": 0.92,
"step": 910
},
{
"epoch": 0.59,
"learning_rate": 7.670119658659469e-06,
"loss": 0.9375,
"step": 911
},
{
"epoch": 0.59,
"learning_rate": 7.649797851749965e-06,
"loss": 0.9571,
"step": 912
},
{
"epoch": 0.59,
"learning_rate": 7.629486312863749e-06,
"loss": 0.9402,
"step": 913
},
{
"epoch": 0.59,
"learning_rate": 7.6091851307418475e-06,
"loss": 0.9303,
"step": 914
},
{
"epoch": 0.59,
"learning_rate": 7.588894394080044e-06,
"loss": 0.2318,
"step": 915
},
{
"epoch": 0.59,
"learning_rate": 7.568614191528482e-06,
"loss": 0.9428,
"step": 916
},
{
"epoch": 0.59,
"learning_rate": 7.548344611691272e-06,
"loss": 0.9066,
"step": 917
},
{
"epoch": 0.59,
"learning_rate": 7.528085743126132e-06,
"loss": 0.9474,
"step": 918
},
{
"epoch": 0.59,
"learning_rate": 7.507837674343969e-06,
"loss": 0.9685,
"step": 919
},
{
"epoch": 0.59,
"learning_rate": 7.487600493808513e-06,
"loss": 0.9608,
"step": 920
},
{
"epoch": 0.59,
"learning_rate": 7.467374289935917e-06,
"loss": 0.9282,
"step": 921
},
{
"epoch": 0.59,
"learning_rate": 7.447159151094388e-06,
"loss": 0.9488,
"step": 922
},
{
"epoch": 0.6,
"learning_rate": 7.426955165603773e-06,
"loss": 0.9191,
"step": 923
},
{
"epoch": 0.6,
"learning_rate": 7.406762421735203e-06,
"loss": 0.9619,
"step": 924
},
{
"epoch": 0.6,
"learning_rate": 7.386581007710694e-06,
"loss": 0.9234,
"step": 925
},
{
"epoch": 0.6,
"learning_rate": 7.366411011702754e-06,
"loss": 0.9705,
"step": 926
},
{
"epoch": 0.6,
"learning_rate": 7.346252521834012e-06,
"loss": 0.2476,
"step": 927
},
{
"epoch": 0.6,
"learning_rate": 7.326105626176835e-06,
"loss": 0.941,
"step": 928
},
{
"epoch": 0.6,
"learning_rate": 7.30597041275291e-06,
"loss": 0.979,
"step": 929
},
{
"epoch": 0.6,
"learning_rate": 7.285846969532907e-06,
"loss": 0.9297,
"step": 930
},
{
"epoch": 0.6,
"learning_rate": 7.265735384436064e-06,
"loss": 0.9391,
"step": 931
},
{
"epoch": 0.6,
"learning_rate": 7.24563574532981e-06,
"loss": 0.9542,
"step": 932
},
{
"epoch": 0.6,
"learning_rate": 7.225548140029388e-06,
"loss": 0.8969,
"step": 933
},
{
"epoch": 0.6,
"learning_rate": 7.205472656297457e-06,
"loss": 0.9513,
"step": 934
},
{
"epoch": 0.6,
"learning_rate": 7.185409381843727e-06,
"loss": 0.9264,
"step": 935
},
{
"epoch": 0.6,
"learning_rate": 7.1653584043245495e-06,
"loss": 0.9109,
"step": 936
},
{
"epoch": 0.6,
"learning_rate": 7.1453198113425655e-06,
"loss": 0.2353,
"step": 937
},
{
"epoch": 0.61,
"learning_rate": 7.125293690446307e-06,
"loss": 0.9466,
"step": 938
},
{
"epoch": 0.61,
"learning_rate": 7.105280129129806e-06,
"loss": 0.9418,
"step": 939
},
{
"epoch": 0.61,
"learning_rate": 7.085279214832233e-06,
"loss": 0.962,
"step": 940
},
{
"epoch": 0.61,
"learning_rate": 7.065291034937496e-06,
"loss": 0.9573,
"step": 941
},
{
"epoch": 0.61,
"learning_rate": 7.045315676773866e-06,
"loss": 0.9587,
"step": 942
},
{
"epoch": 0.61,
"learning_rate": 7.025353227613604e-06,
"loss": 0.9399,
"step": 943
},
{
"epoch": 0.61,
"learning_rate": 7.00540377467256e-06,
"loss": 0.9434,
"step": 944
},
{
"epoch": 0.61,
"learning_rate": 6.985467405109816e-06,
"loss": 0.961,
"step": 945
},
{
"epoch": 0.61,
"learning_rate": 6.965544206027283e-06,
"loss": 0.2487,
"step": 946
},
{
"epoch": 0.61,
"learning_rate": 6.945634264469338e-06,
"loss": 0.9292,
"step": 947
},
{
"epoch": 0.61,
"learning_rate": 6.925737667422427e-06,
"loss": 0.9186,
"step": 948
},
{
"epoch": 0.61,
"learning_rate": 6.9058545018146986e-06,
"loss": 0.2433,
"step": 949
},
{
"epoch": 0.61,
"learning_rate": 6.885984854515624e-06,
"loss": 0.9474,
"step": 950
},
{
"epoch": 0.61,
"learning_rate": 6.866128812335603e-06,
"loss": 0.9471,
"step": 951
},
{
"epoch": 0.61,
"learning_rate": 6.846286462025606e-06,
"loss": 0.9334,
"step": 952
},
{
"epoch": 0.61,
"learning_rate": 6.826457890276773e-06,
"loss": 0.941,
"step": 953
},
{
"epoch": 0.62,
"learning_rate": 6.8066431837200574e-06,
"loss": 0.9428,
"step": 954
},
{
"epoch": 0.62,
"learning_rate": 6.7868424289258216e-06,
"loss": 0.9487,
"step": 955
},
{
"epoch": 0.62,
"learning_rate": 6.767055712403481e-06,
"loss": 0.9379,
"step": 956
},
{
"epoch": 0.62,
"learning_rate": 6.74728312060112e-06,
"loss": 0.9477,
"step": 957
},
{
"epoch": 0.62,
"learning_rate": 6.727524739905104e-06,
"loss": 0.9216,
"step": 958
},
{
"epoch": 0.62,
"learning_rate": 6.707780656639722e-06,
"loss": 0.9558,
"step": 959
},
{
"epoch": 0.62,
"learning_rate": 6.688050957066787e-06,
"loss": 0.2509,
"step": 960
},
{
"epoch": 0.62,
"learning_rate": 6.6683357273852686e-06,
"loss": 0.9456,
"step": 961
},
{
"epoch": 0.62,
"learning_rate": 6.648635053730931e-06,
"loss": 0.9559,
"step": 962
},
{
"epoch": 0.62,
"learning_rate": 6.628949022175928e-06,
"loss": 0.9681,
"step": 963
},
{
"epoch": 0.62,
"learning_rate": 6.60927771872845e-06,
"loss": 0.9122,
"step": 964
},
{
"epoch": 0.62,
"learning_rate": 6.58962122933234e-06,
"loss": 0.9473,
"step": 965
},
{
"epoch": 0.62,
"learning_rate": 6.5699796398667215e-06,
"loss": 0.917,
"step": 966
},
{
"epoch": 0.62,
"learning_rate": 6.5503530361456095e-06,
"loss": 0.9394,
"step": 967
},
{
"epoch": 0.62,
"learning_rate": 6.530741503917551e-06,
"loss": 0.9661,
"step": 968
},
{
"epoch": 0.63,
"learning_rate": 6.5111451288652565e-06,
"loss": 0.2252,
"step": 969
},
{
"epoch": 0.63,
"learning_rate": 6.491563996605198e-06,
"loss": 0.8962,
"step": 970
},
{
"epoch": 0.63,
"learning_rate": 6.471998192687266e-06,
"loss": 0.9493,
"step": 971
},
{
"epoch": 0.63,
"learning_rate": 6.4524478025943704e-06,
"loss": 0.9577,
"step": 972
},
{
"epoch": 0.63,
"learning_rate": 6.4329129117420904e-06,
"loss": 0.9386,
"step": 973
},
{
"epoch": 0.63,
"learning_rate": 6.413393605478275e-06,
"loss": 0.2571,
"step": 974
},
{
"epoch": 0.63,
"learning_rate": 6.39388996908269e-06,
"loss": 0.9591,
"step": 975
},
{
"epoch": 0.63,
"learning_rate": 6.374402087766647e-06,
"loss": 0.9179,
"step": 976
},
{
"epoch": 0.63,
"learning_rate": 6.354930046672612e-06,
"loss": 0.9471,
"step": 977
},
{
"epoch": 0.63,
"learning_rate": 6.335473930873854e-06,
"loss": 0.9472,
"step": 978
},
{
"epoch": 0.63,
"learning_rate": 6.316033825374064e-06,
"loss": 0.92,
"step": 979
},
{
"epoch": 0.63,
"learning_rate": 6.296609815106971e-06,
"loss": 0.9361,
"step": 980
},
{
"epoch": 0.63,
"learning_rate": 6.277201984936001e-06,
"loss": 0.9675,
"step": 981
},
{
"epoch": 0.63,
"learning_rate": 6.25781041965388e-06,
"loss": 0.9666,
"step": 982
},
{
"epoch": 0.63,
"learning_rate": 6.238435203982278e-06,
"loss": 0.9673,
"step": 983
},
{
"epoch": 0.63,
"learning_rate": 6.2190764225714284e-06,
"loss": 0.9441,
"step": 984
},
{
"epoch": 0.64,
"learning_rate": 6.199734159999768e-06,
"loss": 0.9185,
"step": 985
},
{
"epoch": 0.64,
"learning_rate": 6.180408500773558e-06,
"loss": 0.9426,
"step": 986
},
{
"epoch": 0.64,
"learning_rate": 6.1610995293265215e-06,
"loss": 0.9501,
"step": 987
},
{
"epoch": 0.64,
"learning_rate": 6.141807330019476e-06,
"loss": 0.2279,
"step": 988
},
{
"epoch": 0.64,
"learning_rate": 6.122531987139955e-06,
"loss": 0.9686,
"step": 989
},
{
"epoch": 0.64,
"learning_rate": 6.103273584901857e-06,
"loss": 0.9588,
"step": 990
},
{
"epoch": 0.64,
"learning_rate": 6.084032207445052e-06,
"loss": 0.945,
"step": 991
},
{
"epoch": 0.64,
"learning_rate": 6.064807938835046e-06,
"loss": 0.9279,
"step": 992
},
{
"epoch": 0.64,
"learning_rate": 6.045600863062584e-06,
"loss": 0.9219,
"step": 993
},
{
"epoch": 0.64,
"learning_rate": 6.0264110640432935e-06,
"loss": 0.9492,
"step": 994
},
{
"epoch": 0.64,
"learning_rate": 6.007238625617333e-06,
"loss": 0.9201,
"step": 995
},
{
"epoch": 0.64,
"learning_rate": 5.988083631549001e-06,
"loss": 0.935,
"step": 996
},
{
"epoch": 0.64,
"learning_rate": 5.968946165526389e-06,
"loss": 0.9637,
"step": 997
},
{
"epoch": 0.64,
"learning_rate": 5.949826311161007e-06,
"loss": 0.9352,
"step": 998
},
{
"epoch": 0.64,
"learning_rate": 5.930724151987411e-06,
"loss": 0.9617,
"step": 999
},
{
"epoch": 0.65,
"learning_rate": 5.9116397714628584e-06,
"loss": 0.9705,
"step": 1000
},
{
"epoch": 0.65,
"learning_rate": 5.892573252966926e-06,
"loss": 0.9679,
"step": 1001
},
{
"epoch": 0.65,
"learning_rate": 5.873524679801157e-06,
"loss": 0.943,
"step": 1002
},
{
"epoch": 0.65,
"learning_rate": 5.854494135188682e-06,
"loss": 0.9468,
"step": 1003
},
{
"epoch": 0.65,
"learning_rate": 5.835481702273879e-06,
"loss": 0.9295,
"step": 1004
},
{
"epoch": 0.65,
"learning_rate": 5.816487464121974e-06,
"loss": 0.9538,
"step": 1005
},
{
"epoch": 0.65,
"learning_rate": 5.79751150371872e-06,
"loss": 0.9417,
"step": 1006
},
{
"epoch": 0.65,
"learning_rate": 5.77855390397001e-06,
"loss": 0.9059,
"step": 1007
},
{
"epoch": 0.65,
"learning_rate": 5.759614747701519e-06,
"loss": 0.9582,
"step": 1008
},
{
"epoch": 0.65,
"learning_rate": 5.740694117658334e-06,
"loss": 0.9569,
"step": 1009
},
{
"epoch": 0.65,
"learning_rate": 5.7217920965046115e-06,
"loss": 0.9215,
"step": 1010
},
{
"epoch": 0.65,
"learning_rate": 5.7029087668232075e-06,
"loss": 0.2467,
"step": 1011
},
{
"epoch": 0.65,
"learning_rate": 5.6840442111153e-06,
"loss": 0.9498,
"step": 1012
},
{
"epoch": 0.65,
"learning_rate": 5.665198511800063e-06,
"loss": 0.2404,
"step": 1013
},
{
"epoch": 0.65,
"learning_rate": 5.64637175121427e-06,
"loss": 0.9252,
"step": 1014
},
{
"epoch": 0.65,
"learning_rate": 5.627564011611961e-06,
"loss": 0.955,
"step": 1015
},
{
"epoch": 0.66,
"learning_rate": 5.6087753751640725e-06,
"loss": 0.9393,
"step": 1016
},
{
"epoch": 0.66,
"learning_rate": 5.590005923958079e-06,
"loss": 0.9173,
"step": 1017
},
{
"epoch": 0.66,
"learning_rate": 5.5712557399976345e-06,
"loss": 0.9578,
"step": 1018
},
{
"epoch": 0.66,
"learning_rate": 5.552524905202208e-06,
"loss": 0.2387,
"step": 1019
},
{
"epoch": 0.66,
"learning_rate": 5.533813501406739e-06,
"loss": 0.9509,
"step": 1020
},
{
"epoch": 0.66,
"learning_rate": 5.515121610361275e-06,
"loss": 0.9228,
"step": 1021
},
{
"epoch": 0.66,
"learning_rate": 5.496449313730608e-06,
"loss": 0.9138,
"step": 1022
},
{
"epoch": 0.66,
"learning_rate": 5.477796693093933e-06,
"loss": 0.9359,
"step": 1023
},
{
"epoch": 0.66,
"learning_rate": 5.459163829944451e-06,
"loss": 0.9397,
"step": 1024
},
{
"epoch": 0.66,
"learning_rate": 5.440550805689075e-06,
"loss": 0.9529,
"step": 1025
},
{
"epoch": 0.66,
"learning_rate": 5.421957701648028e-06,
"loss": 0.9535,
"step": 1026
},
{
"epoch": 0.66,
"learning_rate": 5.403384599054504e-06,
"loss": 0.2464,
"step": 1027
},
{
"epoch": 0.66,
"learning_rate": 5.384831579054313e-06,
"loss": 0.9157,
"step": 1028
},
{
"epoch": 0.66,
"learning_rate": 5.3662987227055115e-06,
"loss": 0.954,
"step": 1029
},
{
"epoch": 0.66,
"learning_rate": 5.347786110978084e-06,
"loss": 0.9107,
"step": 1030
},
{
"epoch": 0.67,
"learning_rate": 5.329293824753539e-06,
"loss": 0.9589,
"step": 1031
},
{
"epoch": 0.67,
"learning_rate": 5.310821944824606e-06,
"loss": 0.9411,
"step": 1032
},
{
"epoch": 0.67,
"learning_rate": 5.292370551894852e-06,
"loss": 0.9443,
"step": 1033
},
{
"epoch": 0.67,
"learning_rate": 5.273939726578328e-06,
"loss": 0.9201,
"step": 1034
},
{
"epoch": 0.67,
"learning_rate": 5.255529549399234e-06,
"loss": 0.9381,
"step": 1035
},
{
"epoch": 0.67,
"learning_rate": 5.2371401007915646e-06,
"loss": 0.9234,
"step": 1036
},
{
"epoch": 0.67,
"learning_rate": 5.218771461098733e-06,
"loss": 0.9725,
"step": 1037
},
{
"epoch": 0.67,
"learning_rate": 5.200423710573257e-06,
"loss": 0.9261,
"step": 1038
},
{
"epoch": 0.67,
"learning_rate": 5.182096929376372e-06,
"loss": 0.2575,
"step": 1039
},
{
"epoch": 0.67,
"learning_rate": 5.163791197577714e-06,
"loss": 0.9201,
"step": 1040
},
{
"epoch": 0.67,
"learning_rate": 5.145506595154947e-06,
"loss": 0.2205,
"step": 1041
},
{
"epoch": 0.67,
"learning_rate": 5.127243201993428e-06,
"loss": 0.9645,
"step": 1042
},
{
"epoch": 0.67,
"learning_rate": 5.109001097885837e-06,
"loss": 0.9492,
"step": 1043
},
{
"epoch": 0.67,
"learning_rate": 5.090780362531849e-06,
"loss": 0.9163,
"step": 1044
},
{
"epoch": 0.67,
"learning_rate": 5.0725810755377825e-06,
"loss": 0.9224,
"step": 1045
},
{
"epoch": 0.67,
"learning_rate": 5.054403316416247e-06,
"loss": 0.2707,
"step": 1046
},
{
"epoch": 0.68,
"learning_rate": 5.036247164585799e-06,
"loss": 0.9372,
"step": 1047
},
{
"epoch": 0.68,
"learning_rate": 5.018112699370584e-06,
"loss": 0.2804,
"step": 1048
},
{
"epoch": 0.68,
"learning_rate": 5.000000000000003e-06,
"loss": 0.2554,
"step": 1049
},
{
"epoch": 0.68,
"learning_rate": 4.981909145608365e-06,
"loss": 0.2476,
"step": 1050
},
{
"epoch": 0.68,
"learning_rate": 4.963840215234536e-06,
"loss": 0.9449,
"step": 1051
},
{
"epoch": 0.68,
"learning_rate": 4.945793287821604e-06,
"loss": 0.9658,
"step": 1052
},
{
"epoch": 0.68,
"learning_rate": 4.9277684422165085e-06,
"loss": 0.2335,
"step": 1053
},
{
"epoch": 0.68,
"learning_rate": 4.909765757169729e-06,
"loss": 0.9545,
"step": 1054
},
{
"epoch": 0.68,
"learning_rate": 4.891785311334924e-06,
"loss": 0.9245,
"step": 1055
},
{
"epoch": 0.68,
"learning_rate": 4.873827183268577e-06,
"loss": 0.9724,
"step": 1056
},
{
"epoch": 0.68,
"learning_rate": 4.855891451429682e-06,
"loss": 0.9161,
"step": 1057
},
{
"epoch": 0.68,
"learning_rate": 4.83797819417937e-06,
"loss": 0.9259,
"step": 1058
},
{
"epoch": 0.68,
"learning_rate": 4.820087489780588e-06,
"loss": 0.9384,
"step": 1059
},
{
"epoch": 0.68,
"learning_rate": 4.802219416397749e-06,
"loss": 0.2446,
"step": 1060
},
{
"epoch": 0.68,
"learning_rate": 4.784374052096396e-06,
"loss": 0.9562,
"step": 1061
},
{
"epoch": 0.69,
"learning_rate": 4.7665514748428446e-06,
"loss": 0.2432,
"step": 1062
},
{
"epoch": 0.69,
"learning_rate": 4.748751762503856e-06,
"loss": 0.9385,
"step": 1063
},
{
"epoch": 0.69,
"learning_rate": 4.730974992846304e-06,
"loss": 0.9475,
"step": 1064
},
{
"epoch": 0.69,
"learning_rate": 4.7132212435368166e-06,
"loss": 0.9495,
"step": 1065
},
{
"epoch": 0.69,
"learning_rate": 4.695490592141457e-06,
"loss": 0.9276,
"step": 1066
},
{
"epoch": 0.69,
"learning_rate": 4.677783116125361e-06,
"loss": 0.2296,
"step": 1067
},
{
"epoch": 0.69,
"learning_rate": 4.660098892852416e-06,
"loss": 0.9707,
"step": 1068
},
{
"epoch": 0.69,
"learning_rate": 4.642437999584919e-06,
"loss": 0.223,
"step": 1069
},
{
"epoch": 0.69,
"learning_rate": 4.62480051348324e-06,
"loss": 0.2656,
"step": 1070
},
{
"epoch": 0.69,
"learning_rate": 4.607186511605483e-06,
"loss": 0.9377,
"step": 1071
},
{
"epoch": 0.69,
"learning_rate": 4.589596070907146e-06,
"loss": 0.1998,
"step": 1072
},
{
"epoch": 0.69,
"learning_rate": 4.572029268240787e-06,
"loss": 0.9371,
"step": 1073
},
{
"epoch": 0.69,
"learning_rate": 4.554486180355703e-06,
"loss": 0.9295,
"step": 1074
},
{
"epoch": 0.69,
"learning_rate": 4.53696688389756e-06,
"loss": 0.9452,
"step": 1075
},
{
"epoch": 0.69,
"learning_rate": 4.519471455408099e-06,
"loss": 0.2122,
"step": 1076
},
{
"epoch": 0.69,
"learning_rate": 4.5019999713247646e-06,
"loss": 0.2478,
"step": 1077
},
{
"epoch": 0.7,
"learning_rate": 4.484552507980403e-06,
"loss": 0.9129,
"step": 1078
},
{
"epoch": 0.7,
"learning_rate": 4.467129141602906e-06,
"loss": 0.958,
"step": 1079
},
{
"epoch": 0.7,
"learning_rate": 4.4497299483148935e-06,
"loss": 0.9048,
"step": 1080
},
{
"epoch": 0.7,
"learning_rate": 4.4323550041333644e-06,
"loss": 0.9391,
"step": 1081
},
{
"epoch": 0.7,
"learning_rate": 4.41500438496937e-06,
"loss": 0.2538,
"step": 1082
},
{
"epoch": 0.7,
"learning_rate": 4.397678166627698e-06,
"loss": 0.8927,
"step": 1083
},
{
"epoch": 0.7,
"learning_rate": 4.380376424806524e-06,
"loss": 0.9066,
"step": 1084
},
{
"epoch": 0.7,
"learning_rate": 4.3630992350970866e-06,
"loss": 0.9058,
"step": 1085
},
{
"epoch": 0.7,
"learning_rate": 4.345846672983355e-06,
"loss": 0.9158,
"step": 1086
},
{
"epoch": 0.7,
"learning_rate": 4.3286188138416915e-06,
"loss": 0.9272,
"step": 1087
},
{
"epoch": 0.7,
"learning_rate": 4.3114157329405494e-06,
"loss": 0.94,
"step": 1088
},
{
"epoch": 0.7,
"learning_rate": 4.294237505440112e-06,
"loss": 0.2337,
"step": 1089
},
{
"epoch": 0.7,
"learning_rate": 4.27708420639199e-06,
"loss": 0.2203,
"step": 1090
},
{
"epoch": 0.7,
"learning_rate": 4.2599559107388645e-06,
"loss": 0.9639,
"step": 1091
},
{
"epoch": 0.7,
"learning_rate": 4.242852693314193e-06,
"loss": 0.9586,
"step": 1092
},
{
"epoch": 0.71,
"learning_rate": 4.225774628841864e-06,
"loss": 0.9363,
"step": 1093
},
{
"epoch": 0.71,
"learning_rate": 4.2087217919358604e-06,
"loss": 0.9307,
"step": 1094
},
{
"epoch": 0.71,
"learning_rate": 4.191694257099962e-06,
"loss": 0.8811,
"step": 1095
},
{
"epoch": 0.71,
"learning_rate": 4.174692098727392e-06,
"loss": 0.9281,
"step": 1096
},
{
"epoch": 0.71,
"learning_rate": 4.157715391100509e-06,
"loss": 0.9366,
"step": 1097
},
{
"epoch": 0.71,
"learning_rate": 4.1407642083904805e-06,
"loss": 0.9292,
"step": 1098
},
{
"epoch": 0.71,
"learning_rate": 4.123838624656954e-06,
"loss": 0.2544,
"step": 1099
},
{
"epoch": 0.71,
"learning_rate": 4.10693871384773e-06,
"loss": 0.9433,
"step": 1100
},
{
"epoch": 0.71,
"learning_rate": 4.090064549798445e-06,
"loss": 0.9299,
"step": 1101
},
{
"epoch": 0.71,
"learning_rate": 4.073216206232253e-06,
"loss": 0.9338,
"step": 1102
},
{
"epoch": 0.71,
"learning_rate": 4.056393756759498e-06,
"loss": 0.9476,
"step": 1103
},
{
"epoch": 0.71,
"learning_rate": 4.039597274877388e-06,
"loss": 0.923,
"step": 1104
},
{
"epoch": 0.71,
"learning_rate": 4.022826833969692e-06,
"loss": 0.2155,
"step": 1105
},
{
"epoch": 0.71,
"learning_rate": 4.006082507306379e-06,
"loss": 0.9618,
"step": 1106
},
{
"epoch": 0.71,
"learning_rate": 3.98936436804335e-06,
"loss": 0.9322,
"step": 1107
},
{
"epoch": 0.71,
"learning_rate": 3.972672489222083e-06,
"loss": 0.2146,
"step": 1108
},
{
"epoch": 0.72,
"learning_rate": 3.956006943769331e-06,
"loss": 0.9366,
"step": 1109
},
{
"epoch": 0.72,
"learning_rate": 3.9393678044967895e-06,
"loss": 0.252,
"step": 1110
},
{
"epoch": 0.72,
"learning_rate": 3.922755144100786e-06,
"loss": 0.934,
"step": 1111
},
{
"epoch": 0.72,
"learning_rate": 3.9061690351619675e-06,
"loss": 0.9276,
"step": 1112
},
{
"epoch": 0.72,
"learning_rate": 3.889609550144968e-06,
"loss": 0.9165,
"step": 1113
},
{
"epoch": 0.72,
"learning_rate": 3.873076761398112e-06,
"loss": 0.9243,
"step": 1114
},
{
"epoch": 0.72,
"learning_rate": 3.856570741153087e-06,
"loss": 0.9569,
"step": 1115
},
{
"epoch": 0.72,
"learning_rate": 3.840091561524618e-06,
"loss": 0.2202,
"step": 1116
},
{
"epoch": 0.72,
"learning_rate": 3.823639294510176e-06,
"loss": 0.9487,
"step": 1117
},
{
"epoch": 0.72,
"learning_rate": 3.8072140119896507e-06,
"loss": 0.9211,
"step": 1118
},
{
"epoch": 0.72,
"learning_rate": 3.790815785725024e-06,
"loss": 0.9688,
"step": 1119
},
{
"epoch": 0.72,
"learning_rate": 3.774444687360083e-06,
"loss": 0.9445,
"step": 1120
},
{
"epoch": 0.72,
"learning_rate": 3.7581007884200826e-06,
"loss": 0.952,
"step": 1121
},
{
"epoch": 0.72,
"learning_rate": 3.7417841603114515e-06,
"loss": 0.9133,
"step": 1122
},
{
"epoch": 0.72,
"learning_rate": 3.7254948743214693e-06,
"loss": 0.909,
"step": 1123
},
{
"epoch": 0.73,
"learning_rate": 3.709233001617961e-06,
"loss": 0.2588,
"step": 1124
},
{
"epoch": 0.73,
"learning_rate": 3.692998613248977e-06,
"loss": 0.2416,
"step": 1125
},
{
"epoch": 0.73,
"learning_rate": 3.676791780142487e-06,
"loss": 0.9484,
"step": 1126
},
{
"epoch": 0.73,
"learning_rate": 3.6606125731060815e-06,
"loss": 0.9279,
"step": 1127
},
{
"epoch": 0.73,
"learning_rate": 3.6444610628266466e-06,
"loss": 0.9635,
"step": 1128
},
{
"epoch": 0.73,
"learning_rate": 3.6283373198700676e-06,
"loss": 0.9221,
"step": 1129
},
{
"epoch": 0.73,
"learning_rate": 3.6122414146809014e-06,
"loss": 0.9407,
"step": 1130
},
{
"epoch": 0.73,
"learning_rate": 3.596173417582097e-06,
"loss": 0.2307,
"step": 1131
},
{
"epoch": 0.73,
"learning_rate": 3.5801333987746612e-06,
"loss": 0.9048,
"step": 1132
},
{
"epoch": 0.73,
"learning_rate": 3.564121428337369e-06,
"loss": 0.2153,
"step": 1133
},
{
"epoch": 0.73,
"learning_rate": 3.548137576226458e-06,
"loss": 0.9309,
"step": 1134
},
{
"epoch": 0.73,
"learning_rate": 3.532181912275301e-06,
"loss": 0.922,
"step": 1135
},
{
"epoch": 0.73,
"learning_rate": 3.5162545061941332e-06,
"loss": 0.9347,
"step": 1136
},
{
"epoch": 0.73,
"learning_rate": 3.5003554275697247e-06,
"loss": 0.2315,
"step": 1137
},
{
"epoch": 0.73,
"learning_rate": 3.4844847458650797e-06,
"loss": 0.918,
"step": 1138
},
{
"epoch": 0.73,
"learning_rate": 3.468642530419144e-06,
"loss": 0.2138,
"step": 1139
},
{
"epoch": 0.74,
"learning_rate": 3.4528288504464847e-06,
"loss": 0.9272,
"step": 1140
},
{
"epoch": 0.74,
"learning_rate": 3.437043775037007e-06,
"loss": 0.9028,
"step": 1141
},
{
"epoch": 0.74,
"learning_rate": 3.4212873731556364e-06,
"loss": 0.9409,
"step": 1142
},
{
"epoch": 0.74,
"learning_rate": 3.4055597136420314e-06,
"loss": 0.2623,
"step": 1143
},
{
"epoch": 0.74,
"learning_rate": 3.389860865210267e-06,
"loss": 0.9358,
"step": 1144
},
{
"epoch": 0.74,
"learning_rate": 3.3741908964485415e-06,
"loss": 0.2219,
"step": 1145
},
{
"epoch": 0.74,
"learning_rate": 3.358549875818887e-06,
"loss": 0.9057,
"step": 1146
},
{
"epoch": 0.74,
"learning_rate": 3.3429378716568563e-06,
"loss": 0.9143,
"step": 1147
},
{
"epoch": 0.74,
"learning_rate": 3.327354952171232e-06,
"loss": 0.25,
"step": 1148
},
{
"epoch": 0.74,
"learning_rate": 3.3118011854437226e-06,
"loss": 0.2428,
"step": 1149
},
{
"epoch": 0.74,
"learning_rate": 3.296276639428665e-06,
"loss": 0.9288,
"step": 1150
},
{
"epoch": 0.74,
"learning_rate": 3.2807813819527377e-06,
"loss": 0.2215,
"step": 1151
},
{
"epoch": 0.74,
"learning_rate": 3.265315480714657e-06,
"loss": 0.9404,
"step": 1152
},
{
"epoch": 0.74,
"learning_rate": 3.2498790032848836e-06,
"loss": 0.9061,
"step": 1153
},
{
"epoch": 0.74,
"learning_rate": 3.2344720171053134e-06,
"loss": 0.9462,
"step": 1154
},
{
"epoch": 0.75,
"learning_rate": 3.2190945894890103e-06,
"loss": 0.2145,
"step": 1155
},
{
"epoch": 0.75,
"learning_rate": 3.2037467876198925e-06,
"loss": 0.9354,
"step": 1156
},
{
"epoch": 0.75,
"learning_rate": 3.1884286785524356e-06,
"loss": 0.9123,
"step": 1157
},
{
"epoch": 0.75,
"learning_rate": 3.1731403292114006e-06,
"loss": 0.2315,
"step": 1158
},
{
"epoch": 0.75,
"learning_rate": 3.1578818063915128e-06,
"loss": 0.9455,
"step": 1159
},
{
"epoch": 0.75,
"learning_rate": 3.1426531767572e-06,
"loss": 0.2225,
"step": 1160
},
{
"epoch": 0.75,
"learning_rate": 3.1274545068422803e-06,
"loss": 0.2363,
"step": 1161
},
{
"epoch": 0.75,
"learning_rate": 3.112285863049681e-06,
"loss": 0.9005,
"step": 1162
},
{
"epoch": 0.75,
"learning_rate": 3.09714731165114e-06,
"loss": 0.9378,
"step": 1163
},
{
"epoch": 0.75,
"learning_rate": 3.0820389187869214e-06,
"loss": 0.9209,
"step": 1164
},
{
"epoch": 0.75,
"learning_rate": 3.066960750465533e-06,
"loss": 0.894,
"step": 1165
},
{
"epoch": 0.75,
"learning_rate": 3.0519128725634294e-06,
"loss": 0.9107,
"step": 1166
},
{
"epoch": 0.75,
"learning_rate": 3.036895350824729e-06,
"loss": 0.2399,
"step": 1167
},
{
"epoch": 0.75,
"learning_rate": 3.021908250860918e-06,
"loss": 0.2803,
"step": 1168
},
{
"epoch": 0.75,
"learning_rate": 3.006951638150567e-06,
"loss": 0.9122,
"step": 1169
},
{
"epoch": 0.75,
"learning_rate": 2.9920255780390615e-06,
"loss": 0.9158,
"step": 1170
},
{
"epoch": 0.76,
"learning_rate": 2.977130135738292e-06,
"loss": 0.2359,
"step": 1171
},
{
"epoch": 0.76,
"learning_rate": 2.9622653763263874e-06,
"loss": 0.9323,
"step": 1172
},
{
"epoch": 0.76,
"learning_rate": 2.947431364747414e-06,
"loss": 0.9168,
"step": 1173
},
{
"epoch": 0.76,
"learning_rate": 2.9326281658111066e-06,
"loss": 0.8865,
"step": 1174
},
{
"epoch": 0.76,
"learning_rate": 2.9178558441925843e-06,
"loss": 0.9349,
"step": 1175
},
{
"epoch": 0.76,
"learning_rate": 2.903114464432051e-06,
"loss": 0.9178,
"step": 1176
},
{
"epoch": 0.76,
"learning_rate": 2.8884040909345378e-06,
"loss": 0.9493,
"step": 1177
},
{
"epoch": 0.76,
"learning_rate": 2.8737247879696007e-06,
"loss": 0.921,
"step": 1178
},
{
"epoch": 0.76,
"learning_rate": 2.859076619671053e-06,
"loss": 0.9179,
"step": 1179
},
{
"epoch": 0.76,
"learning_rate": 2.844459650036683e-06,
"loss": 0.9355,
"step": 1180
},
{
"epoch": 0.76,
"learning_rate": 2.829873942927971e-06,
"loss": 0.9098,
"step": 1181
},
{
"epoch": 0.76,
"learning_rate": 2.815319562069806e-06,
"loss": 0.9388,
"step": 1182
},
{
"epoch": 0.76,
"learning_rate": 2.8007965710502162e-06,
"loss": 0.9466,
"step": 1183
},
{
"epoch": 0.76,
"learning_rate": 2.7863050333200894e-06,
"loss": 0.919,
"step": 1184
},
{
"epoch": 0.76,
"learning_rate": 2.771845012192892e-06,
"loss": 0.956,
"step": 1185
},
{
"epoch": 0.77,
"learning_rate": 2.757416570844401e-06,
"loss": 0.2203,
"step": 1186
},
{
"epoch": 0.77,
"learning_rate": 2.743019772312412e-06,
"loss": 0.9122,
"step": 1187
},
{
"epoch": 0.77,
"learning_rate": 2.728654679496473e-06,
"loss": 0.9414,
"step": 1188
},
{
"epoch": 0.77,
"learning_rate": 2.7143213551576177e-06,
"loss": 0.9267,
"step": 1189
},
{
"epoch": 0.77,
"learning_rate": 2.7000198619180795e-06,
"loss": 0.9162,
"step": 1190
},
{
"epoch": 0.77,
"learning_rate": 2.6857502622610267e-06,
"loss": 0.9329,
"step": 1191
},
{
"epoch": 0.77,
"learning_rate": 2.671512618530272e-06,
"loss": 0.9414,
"step": 1192
},
{
"epoch": 0.77,
"learning_rate": 2.6573069929300243e-06,
"loss": 0.9517,
"step": 1193
},
{
"epoch": 0.77,
"learning_rate": 2.6431334475246074e-06,
"loss": 0.9366,
"step": 1194
},
{
"epoch": 0.77,
"learning_rate": 2.628992044238172e-06,
"loss": 0.9395,
"step": 1195
},
{
"epoch": 0.77,
"learning_rate": 2.6148828448544574e-06,
"loss": 0.9318,
"step": 1196
},
{
"epoch": 0.77,
"learning_rate": 2.6008059110164906e-06,
"loss": 0.9176,
"step": 1197
},
{
"epoch": 0.77,
"learning_rate": 2.5867613042263384e-06,
"loss": 0.2414,
"step": 1198
},
{
"epoch": 0.77,
"learning_rate": 2.572749085844829e-06,
"loss": 0.9023,
"step": 1199
},
{
"epoch": 0.77,
"learning_rate": 2.5587693170912876e-06,
"loss": 0.2494,
"step": 1200
},
{
"epoch": 0.77,
"learning_rate": 2.5448220590432604e-06,
"loss": 0.2424,
"step": 1201
},
{
"epoch": 0.78,
"learning_rate": 2.5309073726362656e-06,
"loss": 0.9188,
"step": 1202
},
{
"epoch": 0.78,
"learning_rate": 2.517025318663502e-06,
"loss": 0.9255,
"step": 1203
},
{
"epoch": 0.78,
"learning_rate": 2.5031759577756077e-06,
"loss": 0.9325,
"step": 1204
},
{
"epoch": 0.78,
"learning_rate": 2.4893593504803824e-06,
"loss": 0.9332,
"step": 1205
},
{
"epoch": 0.78,
"learning_rate": 2.47557555714253e-06,
"loss": 0.9181,
"step": 1206
},
{
"epoch": 0.78,
"learning_rate": 2.461824637983381e-06,
"loss": 0.25,
"step": 1207
},
{
"epoch": 0.78,
"learning_rate": 2.44810665308064e-06,
"loss": 0.2341,
"step": 1208
},
{
"epoch": 0.78,
"learning_rate": 2.434421662368128e-06,
"loss": 0.9207,
"step": 1209
},
{
"epoch": 0.78,
"learning_rate": 2.4207697256355144e-06,
"loss": 0.2238,
"step": 1210
},
{
"epoch": 0.78,
"learning_rate": 2.4071509025280526e-06,
"loss": 0.2056,
"step": 1211
},
{
"epoch": 0.78,
"learning_rate": 2.3935652525463206e-06,
"loss": 0.9248,
"step": 1212
},
{
"epoch": 0.78,
"learning_rate": 2.3800128350459695e-06,
"loss": 0.9149,
"step": 1213
},
{
"epoch": 0.78,
"learning_rate": 2.3664937092374497e-06,
"loss": 0.9319,
"step": 1214
},
{
"epoch": 0.78,
"learning_rate": 2.3530079341857682e-06,
"loss": 0.9077,
"step": 1215
},
{
"epoch": 0.78,
"learning_rate": 2.339555568810221e-06,
"loss": 0.21,
"step": 1216
},
{
"epoch": 0.79,
"learning_rate": 2.3261366718841307e-06,
"loss": 0.9209,
"step": 1217
},
{
"epoch": 0.79,
"learning_rate": 2.312751302034605e-06,
"loss": 0.9283,
"step": 1218
},
{
"epoch": 0.79,
"learning_rate": 2.29939951774227e-06,
"loss": 0.9217,
"step": 1219
},
{
"epoch": 0.79,
"learning_rate": 2.2860813773410105e-06,
"loss": 0.9209,
"step": 1220
},
{
"epoch": 0.79,
"learning_rate": 2.2727969390177306e-06,
"loss": 0.9118,
"step": 1221
},
{
"epoch": 0.79,
"learning_rate": 2.25954626081208e-06,
"loss": 0.9264,
"step": 1222
},
{
"epoch": 0.79,
"learning_rate": 2.2463294006162185e-06,
"loss": 0.9351,
"step": 1223
},
{
"epoch": 0.79,
"learning_rate": 2.2331464161745532e-06,
"loss": 0.9394,
"step": 1224
},
{
"epoch": 0.79,
"learning_rate": 2.2199973650834903e-06,
"loss": 0.1996,
"step": 1225
},
{
"epoch": 0.79,
"learning_rate": 2.206882304791176e-06,
"loss": 0.9208,
"step": 1226
},
{
"epoch": 0.79,
"learning_rate": 2.1938012925972507e-06,
"loss": 0.9115,
"step": 1227
},
{
"epoch": 0.79,
"learning_rate": 2.1807543856526037e-06,
"loss": 0.933,
"step": 1228
},
{
"epoch": 0.79,
"learning_rate": 2.167741640959117e-06,
"loss": 0.9061,
"step": 1229
},
{
"epoch": 0.79,
"learning_rate": 2.1547631153694193e-06,
"loss": 0.9503,
"step": 1230
},
{
"epoch": 0.79,
"learning_rate": 2.1418188655866314e-06,
"loss": 0.8992,
"step": 1231
},
{
"epoch": 0.79,
"learning_rate": 2.128908948164128e-06,
"loss": 0.2165,
"step": 1232
},
{
"epoch": 0.8,
"learning_rate": 2.11603341950528e-06,
"loss": 0.2323,
"step": 1233
},
{
"epoch": 0.8,
"learning_rate": 2.103192335863222e-06,
"loss": 0.9357,
"step": 1234
},
{
"epoch": 0.8,
"learning_rate": 2.090385753340596e-06,
"loss": 0.9238,
"step": 1235
},
{
"epoch": 0.8,
"learning_rate": 2.0776137278893005e-06,
"loss": 0.9059,
"step": 1236
},
{
"epoch": 0.8,
"learning_rate": 2.064876315310265e-06,
"loss": 0.223,
"step": 1237
},
{
"epoch": 0.8,
"learning_rate": 2.0521735712531934e-06,
"loss": 0.2296,
"step": 1238
},
{
"epoch": 0.8,
"learning_rate": 2.0395055512163166e-06,
"loss": 0.9228,
"step": 1239
},
{
"epoch": 0.8,
"learning_rate": 2.0268723105461653e-06,
"loss": 0.9213,
"step": 1240
},
{
"epoch": 0.8,
"learning_rate": 2.0142739044373093e-06,
"loss": 0.9057,
"step": 1241
},
{
"epoch": 0.8,
"learning_rate": 2.0017103879321355e-06,
"loss": 0.9368,
"step": 1242
},
{
"epoch": 0.8,
"learning_rate": 1.9891818159205933e-06,
"loss": 0.9447,
"step": 1243
},
{
"epoch": 0.8,
"learning_rate": 1.976688243139965e-06,
"loss": 0.2045,
"step": 1244
},
{
"epoch": 0.8,
"learning_rate": 1.9642297241746146e-06,
"loss": 0.9042,
"step": 1245
},
{
"epoch": 0.8,
"learning_rate": 1.951806313455754e-06,
"loss": 0.2403,
"step": 1246
},
{
"epoch": 0.8,
"learning_rate": 1.9394180652612193e-06,
"loss": 0.9113,
"step": 1247
},
{
"epoch": 0.81,
"learning_rate": 1.9270650337152107e-06,
"loss": 0.2107,
"step": 1248
},
{
"epoch": 0.81,
"learning_rate": 1.9147472727880757e-06,
"loss": 0.9311,
"step": 1249
},
{
"epoch": 0.81,
"learning_rate": 1.902464836296054e-06,
"loss": 0.9361,
"step": 1250
},
{
"epoch": 0.81,
"learning_rate": 1.8902177779010645e-06,
"loss": 0.9144,
"step": 1251
},
{
"epoch": 0.81,
"learning_rate": 1.8780061511104487e-06,
"loss": 0.9243,
"step": 1252
},
{
"epoch": 0.81,
"learning_rate": 1.8658300092767546e-06,
"loss": 0.2124,
"step": 1253
},
{
"epoch": 0.81,
"learning_rate": 1.8536894055974974e-06,
"loss": 0.9514,
"step": 1254
},
{
"epoch": 0.81,
"learning_rate": 1.8415843931149192e-06,
"loss": 0.9546,
"step": 1255
},
{
"epoch": 0.81,
"learning_rate": 1.829515024715769e-06,
"loss": 0.8975,
"step": 1256
},
{
"epoch": 0.81,
"learning_rate": 1.817481353131071e-06,
"loss": 0.9118,
"step": 1257
},
{
"epoch": 0.81,
"learning_rate": 1.8054834309358792e-06,
"loss": 0.9543,
"step": 1258
},
{
"epoch": 0.81,
"learning_rate": 1.7935213105490722e-06,
"loss": 0.9262,
"step": 1259
},
{
"epoch": 0.81,
"learning_rate": 1.7815950442330965e-06,
"loss": 0.904,
"step": 1260
},
{
"epoch": 0.81,
"learning_rate": 1.7697046840937638e-06,
"loss": 0.9065,
"step": 1261
},
{
"epoch": 0.81,
"learning_rate": 1.7578502820800048e-06,
"loss": 0.8976,
"step": 1262
},
{
"epoch": 0.81,
"learning_rate": 1.746031889983657e-06,
"loss": 0.2165,
"step": 1263
},
{
"epoch": 0.82,
"learning_rate": 1.7342495594392227e-06,
"loss": 0.9174,
"step": 1264
},
{
"epoch": 0.82,
"learning_rate": 1.7225033419236502e-06,
"loss": 0.9531,
"step": 1265
},
{
"epoch": 0.82,
"learning_rate": 1.7107932887561196e-06,
"loss": 0.8717,
"step": 1266
},
{
"epoch": 0.82,
"learning_rate": 1.6991194510978015e-06,
"loss": 0.9493,
"step": 1267
},
{
"epoch": 0.82,
"learning_rate": 1.6874818799516468e-06,
"loss": 0.2038,
"step": 1268
},
{
"epoch": 0.82,
"learning_rate": 1.675880626162153e-06,
"loss": 0.229,
"step": 1269
},
{
"epoch": 0.82,
"learning_rate": 1.6643157404151468e-06,
"loss": 0.9073,
"step": 1270
},
{
"epoch": 0.82,
"learning_rate": 1.652787273237565e-06,
"loss": 0.9417,
"step": 1271
},
{
"epoch": 0.82,
"learning_rate": 1.6412952749972355e-06,
"loss": 0.9385,
"step": 1272
},
{
"epoch": 0.82,
"learning_rate": 1.6298397959026513e-06,
"loss": 0.9048,
"step": 1273
},
{
"epoch": 0.82,
"learning_rate": 1.6184208860027473e-06,
"loss": 0.9141,
"step": 1274
},
{
"epoch": 0.82,
"learning_rate": 1.6070385951866951e-06,
"loss": 0.9193,
"step": 1275
},
{
"epoch": 0.82,
"learning_rate": 1.595692973183679e-06,
"loss": 0.8914,
"step": 1276
},
{
"epoch": 0.82,
"learning_rate": 1.5843840695626666e-06,
"loss": 0.9484,
"step": 1277
},
{
"epoch": 0.82,
"learning_rate": 1.5731119337322176e-06,
"loss": 0.2294,
"step": 1278
},
{
"epoch": 0.83,
"learning_rate": 1.5618766149402387e-06,
"loss": 0.9339,
"step": 1279
},
{
"epoch": 0.83,
"learning_rate": 1.5506781622737943e-06,
"loss": 0.2145,
"step": 1280
},
{
"epoch": 0.83,
"learning_rate": 1.5395166246588777e-06,
"loss": 0.8965,
"step": 1281
},
{
"epoch": 0.83,
"learning_rate": 1.5283920508602e-06,
"loss": 0.2083,
"step": 1282
},
{
"epoch": 0.83,
"learning_rate": 1.5173044894809764e-06,
"loss": 0.9242,
"step": 1283
},
{
"epoch": 0.83,
"learning_rate": 1.5062539889627138e-06,
"loss": 0.2257,
"step": 1284
},
{
"epoch": 0.83,
"learning_rate": 1.4952405975850025e-06,
"loss": 0.9179,
"step": 1285
},
{
"epoch": 0.83,
"learning_rate": 1.4842643634653054e-06,
"loss": 0.2442,
"step": 1286
},
{
"epoch": 0.83,
"learning_rate": 1.4733253345587429e-06,
"loss": 0.918,
"step": 1287
},
{
"epoch": 0.83,
"learning_rate": 1.4624235586578895e-06,
"loss": 0.927,
"step": 1288
},
{
"epoch": 0.83,
"learning_rate": 1.4515590833925508e-06,
"loss": 0.9198,
"step": 1289
},
{
"epoch": 0.83,
"learning_rate": 1.4407319562295763e-06,
"loss": 0.9127,
"step": 1290
},
{
"epoch": 0.83,
"learning_rate": 1.4299422244726403e-06,
"loss": 0.9389,
"step": 1291
},
{
"epoch": 0.83,
"learning_rate": 1.4191899352620342e-06,
"loss": 0.2299,
"step": 1292
},
{
"epoch": 0.83,
"learning_rate": 1.4084751355744675e-06,
"loss": 0.9251,
"step": 1293
},
{
"epoch": 0.83,
"learning_rate": 1.3977978722228502e-06,
"loss": 0.9311,
"step": 1294
},
{
"epoch": 0.84,
"learning_rate": 1.387158191856105e-06,
"loss": 0.9079,
"step": 1295
},
{
"epoch": 0.84,
"learning_rate": 1.3765561409589468e-06,
"loss": 0.9321,
"step": 1296
},
{
"epoch": 0.84,
"learning_rate": 1.365991765851693e-06,
"loss": 0.9152,
"step": 1297
},
{
"epoch": 0.84,
"learning_rate": 1.3554651126900564e-06,
"loss": 0.9311,
"step": 1298
},
{
"epoch": 0.84,
"learning_rate": 1.3449762274649358e-06,
"loss": 0.9028,
"step": 1299
},
{
"epoch": 0.84,
"learning_rate": 1.3345251560022288e-06,
"loss": 0.9389,
"step": 1300
},
{
"epoch": 0.84,
"learning_rate": 1.324111943962626e-06,
"loss": 0.8854,
"step": 1301
},
{
"epoch": 0.84,
"learning_rate": 1.3137366368413995e-06,
"loss": 0.8763,
"step": 1302
},
{
"epoch": 0.84,
"learning_rate": 1.3033992799682304e-06,
"loss": 0.9064,
"step": 1303
},
{
"epoch": 0.84,
"learning_rate": 1.2930999185069804e-06,
"loss": 0.9101,
"step": 1304
},
{
"epoch": 0.84,
"learning_rate": 1.2828385974555203e-06,
"loss": 0.8929,
"step": 1305
},
{
"epoch": 0.84,
"learning_rate": 1.2726153616455173e-06,
"loss": 0.9094,
"step": 1306
},
{
"epoch": 0.84,
"learning_rate": 1.2624302557422475e-06,
"loss": 0.2453,
"step": 1307
},
{
"epoch": 0.84,
"learning_rate": 1.2522833242443954e-06,
"loss": 0.2077,
"step": 1308
},
{
"epoch": 0.84,
"learning_rate": 1.2421746114838573e-06,
"loss": 0.9214,
"step": 1309
},
{
"epoch": 0.85,
"learning_rate": 1.2321041616255613e-06,
"loss": 0.9027,
"step": 1310
},
{
"epoch": 0.85,
"learning_rate": 1.2220720186672585e-06,
"loss": 0.2587,
"step": 1311
},
{
"epoch": 0.85,
"learning_rate": 1.2120782264393427e-06,
"loss": 0.2334,
"step": 1312
},
{
"epoch": 0.85,
"learning_rate": 1.2021228286046461e-06,
"loss": 0.9567,
"step": 1313
},
{
"epoch": 0.85,
"learning_rate": 1.1922058686582616e-06,
"loss": 0.9068,
"step": 1314
},
{
"epoch": 0.85,
"learning_rate": 1.1823273899273436e-06,
"loss": 0.9102,
"step": 1315
},
{
"epoch": 0.85,
"learning_rate": 1.1724874355709259e-06,
"loss": 0.9599,
"step": 1316
},
{
"epoch": 0.85,
"learning_rate": 1.1626860485797298e-06,
"loss": 0.9177,
"step": 1317
},
{
"epoch": 0.85,
"learning_rate": 1.1529232717759676e-06,
"loss": 0.9021,
"step": 1318
},
{
"epoch": 0.85,
"learning_rate": 1.1431991478131754e-06,
"loss": 0.9112,
"step": 1319
},
{
"epoch": 0.85,
"learning_rate": 1.1335137191760094e-06,
"loss": 0.2248,
"step": 1320
},
{
"epoch": 0.85,
"learning_rate": 1.1238670281800635e-06,
"loss": 0.9433,
"step": 1321
},
{
"epoch": 0.85,
"learning_rate": 1.1142591169716931e-06,
"loss": 0.9264,
"step": 1322
},
{
"epoch": 0.85,
"learning_rate": 1.1046900275278183e-06,
"loss": 0.228,
"step": 1323
},
{
"epoch": 0.85,
"learning_rate": 1.0951598016557542e-06,
"loss": 0.8924,
"step": 1324
},
{
"epoch": 0.85,
"learning_rate": 1.085668480993015e-06,
"loss": 0.9314,
"step": 1325
},
{
"epoch": 0.86,
"learning_rate": 1.0762161070071441e-06,
"loss": 0.9422,
"step": 1326
},
{
"epoch": 0.86,
"learning_rate": 1.0668027209955212e-06,
"loss": 0.9202,
"step": 1327
},
{
"epoch": 0.86,
"learning_rate": 1.057428364085189e-06,
"loss": 0.2245,
"step": 1328
},
{
"epoch": 0.86,
"learning_rate": 1.0480930772326735e-06,
"loss": 0.9097,
"step": 1329
},
{
"epoch": 0.86,
"learning_rate": 1.0387969012238064e-06,
"loss": 0.9464,
"step": 1330
},
{
"epoch": 0.86,
"learning_rate": 1.029539876673541e-06,
"loss": 0.9156,
"step": 1331
},
{
"epoch": 0.86,
"learning_rate": 1.0203220440257756e-06,
"loss": 0.9045,
"step": 1332
},
{
"epoch": 0.86,
"learning_rate": 1.0111434435531852e-06,
"loss": 0.9263,
"step": 1333
},
{
"epoch": 0.86,
"learning_rate": 1.0020041153570349e-06,
"loss": 0.9464,
"step": 1334
},
{
"epoch": 0.86,
"learning_rate": 9.929040993670113e-07,
"loss": 0.8956,
"step": 1335
},
{
"epoch": 0.86,
"learning_rate": 9.838434353410476e-07,
"loss": 0.9158,
"step": 1336
},
{
"epoch": 0.86,
"learning_rate": 9.748221628651445e-07,
"loss": 0.8941,
"step": 1337
},
{
"epoch": 0.86,
"learning_rate": 9.658403213532042e-07,
"loss": 0.9211,
"step": 1338
},
{
"epoch": 0.86,
"learning_rate": 9.568979500468567e-07,
"loss": 0.9088,
"step": 1339
},
{
"epoch": 0.86,
"learning_rate": 9.47995088015281e-07,
"loss": 0.9169,
"step": 1340
},
{
"epoch": 0.87,
"learning_rate": 9.391317741550465e-07,
"loss": 0.9361,
"step": 1341
},
{
"epoch": 0.87,
"learning_rate": 9.303080471899318e-07,
"loss": 0.2244,
"step": 1342
},
{
"epoch": 0.87,
"learning_rate": 9.215239456707636e-07,
"loss": 0.9238,
"step": 1343
},
{
"epoch": 0.87,
"learning_rate": 9.127795079752455e-07,
"loss": 0.9011,
"step": 1344
},
{
"epoch": 0.87,
"learning_rate": 9.040747723077903e-07,
"loss": 0.9111,
"step": 1345
},
{
"epoch": 0.87,
"learning_rate": 8.954097766993497e-07,
"loss": 0.9293,
"step": 1346
},
{
"epoch": 0.87,
"learning_rate": 8.86784559007251e-07,
"loss": 0.9496,
"step": 1347
},
{
"epoch": 0.87,
"learning_rate": 8.781991569150361e-07,
"loss": 0.9349,
"step": 1348
},
{
"epoch": 0.87,
"learning_rate": 8.696536079322904e-07,
"loss": 0.2209,
"step": 1349
},
{
"epoch": 0.87,
"learning_rate": 8.61147949394483e-07,
"loss": 0.9285,
"step": 1350
},
{
"epoch": 0.87,
"learning_rate": 8.526822184627959e-07,
"loss": 0.9093,
"step": 1351
},
{
"epoch": 0.87,
"learning_rate": 8.442564521239782e-07,
"loss": 0.2666,
"step": 1352
},
{
"epoch": 0.87,
"learning_rate": 8.358706871901612e-07,
"loss": 0.9429,
"step": 1353
},
{
"epoch": 0.87,
"learning_rate": 8.27524960298719e-07,
"loss": 0.9404,
"step": 1354
},
{
"epoch": 0.87,
"learning_rate": 8.192193079121003e-07,
"loss": 0.9293,
"step": 1355
},
{
"epoch": 0.87,
"learning_rate": 8.109537663176603e-07,
"loss": 0.9209,
"step": 1356
},
{
"epoch": 0.88,
"learning_rate": 8.027283716275181e-07,
"loss": 0.9335,
"step": 1357
},
{
"epoch": 0.88,
"learning_rate": 7.945431597783904e-07,
"loss": 0.2318,
"step": 1358
},
{
"epoch": 0.88,
"learning_rate": 7.86398166531428e-07,
"loss": 0.2407,
"step": 1359
},
{
"epoch": 0.88,
"learning_rate": 7.782934274720777e-07,
"loss": 0.9151,
"step": 1360
},
{
"epoch": 0.88,
"learning_rate": 7.70228978009907e-07,
"loss": 0.941,
"step": 1361
},
{
"epoch": 0.88,
"learning_rate": 7.62204853378461e-07,
"loss": 0.9278,
"step": 1362
},
{
"epoch": 0.88,
"learning_rate": 7.542210886351087e-07,
"loss": 0.246,
"step": 1363
},
{
"epoch": 0.88,
"learning_rate": 7.46277718660885e-07,
"loss": 0.9123,
"step": 1364
},
{
"epoch": 0.88,
"learning_rate": 7.38374778160339e-07,
"loss": 0.9362,
"step": 1365
},
{
"epoch": 0.88,
"learning_rate": 7.305123016613825e-07,
"loss": 0.8869,
"step": 1366
},
{
"epoch": 0.88,
"learning_rate": 7.226903235151439e-07,
"loss": 0.9155,
"step": 1367
},
{
"epoch": 0.88,
"learning_rate": 7.149088778958125e-07,
"loss": 0.9291,
"step": 1368
},
{
"epoch": 0.88,
"learning_rate": 7.07167998800491e-07,
"loss": 0.9275,
"step": 1369
},
{
"epoch": 0.88,
"learning_rate": 6.994677200490508e-07,
"loss": 0.9329,
"step": 1370
},
{
"epoch": 0.88,
"learning_rate": 6.91808075283975e-07,
"loss": 0.8953,
"step": 1371
},
{
"epoch": 0.89,
"learning_rate": 6.84189097970217e-07,
"loss": 0.9443,
"step": 1372
},
{
"epoch": 0.89,
"learning_rate": 6.766108213950584e-07,
"loss": 0.8848,
"step": 1373
},
{
"epoch": 0.89,
"learning_rate": 6.690732786679588e-07,
"loss": 0.9271,
"step": 1374
},
{
"epoch": 0.89,
"learning_rate": 6.615765027204101e-07,
"loss": 0.2439,
"step": 1375
},
{
"epoch": 0.89,
"learning_rate": 6.541205263057936e-07,
"loss": 0.9366,
"step": 1376
},
{
"epoch": 0.89,
"learning_rate": 6.467053819992419e-07,
"loss": 0.8941,
"step": 1377
},
{
"epoch": 0.89,
"learning_rate": 6.393311021974858e-07,
"loss": 0.2456,
"step": 1378
},
{
"epoch": 0.89,
"learning_rate": 6.319977191187232e-07,
"loss": 0.9202,
"step": 1379
},
{
"epoch": 0.89,
"learning_rate": 6.247052648024765e-07,
"loss": 0.9175,
"step": 1380
},
{
"epoch": 0.89,
"learning_rate": 6.174537711094442e-07,
"loss": 0.9184,
"step": 1381
},
{
"epoch": 0.89,
"learning_rate": 6.102432697213734e-07,
"loss": 0.8998,
"step": 1382
},
{
"epoch": 0.89,
"learning_rate": 6.030737921409169e-07,
"loss": 0.925,
"step": 1383
},
{
"epoch": 0.89,
"learning_rate": 5.959453696914874e-07,
"loss": 0.9484,
"step": 1384
},
{
"epoch": 0.89,
"learning_rate": 5.888580335171368e-07,
"loss": 0.9415,
"step": 1385
},
{
"epoch": 0.89,
"learning_rate": 5.818118145824036e-07,
"loss": 0.2488,
"step": 1386
},
{
"epoch": 0.89,
"learning_rate": 5.748067436721893e-07,
"loss": 0.911,
"step": 1387
},
{
"epoch": 0.9,
"learning_rate": 5.678428513916212e-07,
"loss": 0.9386,
"step": 1388
},
{
"epoch": 0.9,
"learning_rate": 5.609201681659149e-07,
"loss": 0.8955,
"step": 1389
},
{
"epoch": 0.9,
"learning_rate": 5.540387242402434e-07,
"loss": 0.9014,
"step": 1390
},
{
"epoch": 0.9,
"learning_rate": 5.471985496796051e-07,
"loss": 0.9135,
"step": 1391
},
{
"epoch": 0.9,
"learning_rate": 5.403996743686957e-07,
"loss": 0.9316,
"step": 1392
},
{
"epoch": 0.9,
"learning_rate": 5.33642128011771e-07,
"loss": 0.2361,
"step": 1393
},
{
"epoch": 0.9,
"learning_rate": 5.269259401325256e-07,
"loss": 0.9054,
"step": 1394
},
{
"epoch": 0.9,
"learning_rate": 5.20251140073953e-07,
"loss": 0.2488,
"step": 1395
},
{
"epoch": 0.9,
"learning_rate": 5.136177569982293e-07,
"loss": 0.2334,
"step": 1396
},
{
"epoch": 0.9,
"learning_rate": 5.070258198865741e-07,
"loss": 0.9256,
"step": 1397
},
{
"epoch": 0.9,
"learning_rate": 5.004753575391341e-07,
"loss": 0.2423,
"step": 1398
},
{
"epoch": 0.9,
"learning_rate": 4.939663985748544e-07,
"loss": 0.9463,
"step": 1399
},
{
"epoch": 0.9,
"learning_rate": 4.874989714313449e-07,
"loss": 0.9077,
"step": 1400
},
{
"epoch": 0.9,
"learning_rate": 4.810731043647699e-07,
"loss": 0.9305,
"step": 1401
},
{
"epoch": 0.9,
"learning_rate": 4.7468882544971615e-07,
"loss": 0.9319,
"step": 1402
},
{
"epoch": 0.91,
"learning_rate": 4.683461625790697e-07,
"loss": 0.9677,
"step": 1403
},
{
"epoch": 0.91,
"learning_rate": 4.620451434638995e-07,
"loss": 0.9225,
"step": 1404
},
{
"epoch": 0.91,
"learning_rate": 4.5578579563333006e-07,
"loss": 0.9378,
"step": 1405
},
{
"epoch": 0.91,
"learning_rate": 4.495681464344259e-07,
"loss": 0.9288,
"step": 1406
},
{
"epoch": 0.91,
"learning_rate": 4.4339222303207086e-07,
"loss": 0.9186,
"step": 1407
},
{
"epoch": 0.91,
"learning_rate": 4.372580524088488e-07,
"loss": 0.895,
"step": 1408
},
{
"epoch": 0.91,
"learning_rate": 4.311656613649251e-07,
"loss": 0.9363,
"step": 1409
},
{
"epoch": 0.91,
"learning_rate": 4.2511507651792906e-07,
"loss": 0.9526,
"step": 1410
},
{
"epoch": 0.91,
"learning_rate": 4.191063243028415e-07,
"loss": 0.8911,
"step": 1411
},
{
"epoch": 0.91,
"learning_rate": 4.13139430971875e-07,
"loss": 0.9248,
"step": 1412
},
{
"epoch": 0.91,
"learning_rate": 4.072144225943631e-07,
"loss": 0.9177,
"step": 1413
},
{
"epoch": 0.91,
"learning_rate": 4.0133132505663977e-07,
"loss": 0.1991,
"step": 1414
},
{
"epoch": 0.91,
"learning_rate": 3.9549016406193686e-07,
"loss": 0.9559,
"step": 1415
},
{
"epoch": 0.91,
"learning_rate": 3.8969096513025826e-07,
"loss": 0.2283,
"step": 1416
},
{
"epoch": 0.91,
"learning_rate": 3.839337535982812e-07,
"loss": 0.2219,
"step": 1417
},
{
"epoch": 0.91,
"learning_rate": 3.7821855461924075e-07,
"loss": 0.9536,
"step": 1418
},
{
"epoch": 0.92,
"learning_rate": 3.7254539316281424e-07,
"loss": 0.8931,
"step": 1419
},
{
"epoch": 0.92,
"learning_rate": 3.6691429401502055e-07,
"loss": 0.919,
"step": 1420
},
{
"epoch": 0.92,
"learning_rate": 3.61325281778111e-07,
"loss": 0.9416,
"step": 1421
},
{
"epoch": 0.92,
"learning_rate": 3.557783808704529e-07,
"loss": 0.9167,
"step": 1422
},
{
"epoch": 0.92,
"learning_rate": 3.502736155264352e-07,
"loss": 0.9026,
"step": 1423
},
{
"epoch": 0.92,
"learning_rate": 3.4481100979635304e-07,
"loss": 0.9639,
"step": 1424
},
{
"epoch": 0.92,
"learning_rate": 3.393905875463088e-07,
"loss": 0.9099,
"step": 1425
},
{
"epoch": 0.92,
"learning_rate": 3.340123724581046e-07,
"loss": 0.22,
"step": 1426
},
{
"epoch": 0.92,
"learning_rate": 3.286763880291399e-07,
"loss": 0.2233,
"step": 1427
},
{
"epoch": 0.92,
"learning_rate": 3.2338265757230647e-07,
"loss": 0.9417,
"step": 1428
},
{
"epoch": 0.92,
"learning_rate": 3.1813120421589126e-07,
"loss": 0.2192,
"step": 1429
},
{
"epoch": 0.92,
"learning_rate": 3.129220509034725e-07,
"loss": 0.9046,
"step": 1430
},
{
"epoch": 0.92,
"learning_rate": 3.0775522039381724e-07,
"loss": 0.9189,
"step": 1431
},
{
"epoch": 0.92,
"learning_rate": 3.0263073526079046e-07,
"loss": 0.9472,
"step": 1432
},
{
"epoch": 0.92,
"learning_rate": 2.9754861789324074e-07,
"loss": 0.9089,
"step": 1433
},
{
"epoch": 0.93,
"learning_rate": 2.9250889049492136e-07,
"loss": 0.8963,
"step": 1434
},
{
"epoch": 0.93,
"learning_rate": 2.875115750843771e-07,
"loss": 0.9435,
"step": 1435
},
{
"epoch": 0.93,
"learning_rate": 2.825566934948598e-07,
"loss": 0.9454,
"step": 1436
},
{
"epoch": 0.93,
"learning_rate": 2.776442673742274e-07,
"loss": 0.9257,
"step": 1437
},
{
"epoch": 0.93,
"learning_rate": 2.727743181848463e-07,
"loss": 0.9347,
"step": 1438
},
{
"epoch": 0.93,
"learning_rate": 2.6794686720350573e-07,
"loss": 0.9265,
"step": 1439
},
{
"epoch": 0.93,
"learning_rate": 2.631619355213189e-07,
"loss": 0.9336,
"step": 1440
},
{
"epoch": 0.93,
"learning_rate": 2.584195440436299e-07,
"loss": 0.9556,
"step": 1441
},
{
"epoch": 0.93,
"learning_rate": 2.537197134899294e-07,
"loss": 0.9091,
"step": 1442
},
{
"epoch": 0.93,
"learning_rate": 2.490624643937567e-07,
"loss": 0.8998,
"step": 1443
},
{
"epoch": 0.93,
"learning_rate": 2.4444781710261324e-07,
"loss": 0.2376,
"step": 1444
},
{
"epoch": 0.93,
"learning_rate": 2.398757917778727e-07,
"loss": 0.2301,
"step": 1445
},
{
"epoch": 0.93,
"learning_rate": 2.3534640839469768e-07,
"loss": 0.9216,
"step": 1446
},
{
"epoch": 0.93,
"learning_rate": 2.3085968674194214e-07,
"loss": 0.9513,
"step": 1447
},
{
"epoch": 0.93,
"learning_rate": 2.2641564642207347e-07,
"loss": 0.9179,
"step": 1448
},
{
"epoch": 0.93,
"learning_rate": 2.2201430685108715e-07,
"loss": 0.2737,
"step": 1449
},
{
"epoch": 0.94,
"learning_rate": 2.1765568725841679e-07,
"loss": 0.9041,
"step": 1450
},
{
"epoch": 0.94,
"learning_rate": 2.1333980668685416e-07,
"loss": 0.2308,
"step": 1451
},
{
"epoch": 0.94,
"learning_rate": 2.0906668399246045e-07,
"loss": 0.2263,
"step": 1452
},
{
"epoch": 0.94,
"learning_rate": 2.0483633784449285e-07,
"loss": 0.9514,
"step": 1453
},
{
"epoch": 0.94,
"learning_rate": 2.0064878672531485e-07,
"loss": 0.9405,
"step": 1454
},
{
"epoch": 0.94,
"learning_rate": 1.9650404893031938e-07,
"loss": 0.927,
"step": 1455
},
{
"epoch": 0.94,
"learning_rate": 1.9240214256785128e-07,
"loss": 0.2335,
"step": 1456
},
{
"epoch": 0.94,
"learning_rate": 1.883430855591173e-07,
"loss": 0.2353,
"step": 1457
},
{
"epoch": 0.94,
"learning_rate": 1.84326895638125e-07,
"loss": 0.2154,
"step": 1458
},
{
"epoch": 0.94,
"learning_rate": 1.803535903515885e-07,
"loss": 0.9231,
"step": 1459
},
{
"epoch": 0.94,
"learning_rate": 1.7642318705886284e-07,
"loss": 0.9309,
"step": 1460
},
{
"epoch": 0.94,
"learning_rate": 1.7253570293186418e-07,
"loss": 0.8779,
"step": 1461
},
{
"epoch": 0.94,
"learning_rate": 1.68691154954993e-07,
"loss": 0.8914,
"step": 1462
},
{
"epoch": 0.94,
"learning_rate": 1.6488955992506218e-07,
"loss": 0.9078,
"step": 1463
},
{
"epoch": 0.94,
"learning_rate": 1.6113093445122685e-07,
"loss": 0.9243,
"step": 1464
},
{
"epoch": 0.95,
"learning_rate": 1.574152949549057e-07,
"loss": 0.9003,
"step": 1465
},
{
"epoch": 0.95,
"learning_rate": 1.5374265766971097e-07,
"loss": 0.2149,
"step": 1466
},
{
"epoch": 0.95,
"learning_rate": 1.5011303864137962e-07,
"loss": 0.9239,
"step": 1467
},
{
"epoch": 0.95,
"learning_rate": 1.4652645372770226e-07,
"loss": 0.93,
"step": 1468
},
{
"epoch": 0.95,
"learning_rate": 1.4298291859845215e-07,
"loss": 0.9275,
"step": 1469
},
{
"epoch": 0.95,
"learning_rate": 1.394824487353208e-07,
"loss": 0.9196,
"step": 1470
},
{
"epoch": 0.95,
"learning_rate": 1.3602505943184575e-07,
"loss": 0.9259,
"step": 1471
},
{
"epoch": 0.95,
"learning_rate": 1.326107657933473e-07,
"loss": 0.9032,
"step": 1472
},
{
"epoch": 0.95,
"learning_rate": 1.2923958273685755e-07,
"loss": 0.9375,
"step": 1473
},
{
"epoch": 0.95,
"learning_rate": 1.2591152499106253e-07,
"loss": 0.9411,
"step": 1474
},
{
"epoch": 0.95,
"learning_rate": 1.2262660709623232e-07,
"loss": 0.9017,
"step": 1475
},
{
"epoch": 0.95,
"learning_rate": 1.1938484340416113e-07,
"loss": 0.9018,
"step": 1476
},
{
"epoch": 0.95,
"learning_rate": 1.1618624807809841e-07,
"loss": 0.9239,
"step": 1477
},
{
"epoch": 0.95,
"learning_rate": 1.1303083509269452e-07,
"loss": 0.9218,
"step": 1478
},
{
"epoch": 0.95,
"learning_rate": 1.0991861823393513e-07,
"loss": 0.9064,
"step": 1479
},
{
"epoch": 0.95,
"learning_rate": 1.0684961109908354e-07,
"loss": 0.9434,
"step": 1480
},
{
"epoch": 0.96,
"learning_rate": 1.0382382709661853e-07,
"loss": 0.8902,
"step": 1481
},
{
"epoch": 0.96,
"learning_rate": 1.008412794461766e-07,
"loss": 0.9258,
"step": 1482
},
{
"epoch": 0.96,
"learning_rate": 9.790198117849758e-08,
"loss": 0.9244,
"step": 1483
},
{
"epoch": 0.96,
"learning_rate": 9.500594513536354e-08,
"loss": 0.8889,
"step": 1484
},
{
"epoch": 0.96,
"learning_rate": 9.215318396954109e-08,
"loss": 0.9461,
"step": 1485
},
{
"epoch": 0.96,
"learning_rate": 8.934371014473475e-08,
"loss": 0.9457,
"step": 1486
},
{
"epoch": 0.96,
"learning_rate": 8.657753593552142e-08,
"loss": 0.9239,
"step": 1487
},
{
"epoch": 0.96,
"learning_rate": 8.385467342730602e-08,
"loss": 0.9042,
"step": 1488
},
{
"epoch": 0.96,
"learning_rate": 8.117513451626258e-08,
"loss": 0.9572,
"step": 1489
},
{
"epoch": 0.96,
"learning_rate": 7.853893090928654e-08,
"loss": 0.9081,
"step": 1490
},
{
"epoch": 0.96,
"learning_rate": 7.594607412393928e-08,
"loss": 0.9321,
"step": 1491
},
{
"epoch": 0.96,
"learning_rate": 7.33965754884014e-08,
"loss": 0.9246,
"step": 1492
},
{
"epoch": 0.96,
"learning_rate": 7.08904461414217e-08,
"loss": 0.2532,
"step": 1493
},
{
"epoch": 0.96,
"learning_rate": 6.842769703226836e-08,
"loss": 0.8864,
"step": 1494
},
{
"epoch": 0.96,
"learning_rate": 6.600833892068336e-08,
"loss": 0.9332,
"step": 1495
},
{
"epoch": 0.97,
"learning_rate": 6.363238237683034e-08,
"loss": 0.9563,
"step": 1496
},
{
"epoch": 0.97,
"learning_rate": 6.129983778125348e-08,
"loss": 0.2323,
"step": 1497
},
{
"epoch": 0.97,
"learning_rate": 5.901071532483204e-08,
"loss": 0.9256,
"step": 1498
},
{
"epoch": 0.97,
"learning_rate": 5.676502500873038e-08,
"loss": 0.2037,
"step": 1499
},
{
"epoch": 0.97,
"learning_rate": 5.456277664436127e-08,
"loss": 0.8968,
"step": 1500
},
{
"epoch": 0.97,
"learning_rate": 5.240397985333823e-08,
"loss": 0.9198,
"step": 1501
},
{
"epoch": 0.97,
"learning_rate": 5.0288644067435496e-08,
"loss": 0.9206,
"step": 1502
},
{
"epoch": 0.97,
"learning_rate": 4.8216778528545895e-08,
"loss": 0.9228,
"step": 1503
},
{
"epoch": 0.97,
"learning_rate": 4.618839228864192e-08,
"loss": 0.9209,
"step": 1504
},
{
"epoch": 0.97,
"learning_rate": 4.420349420973358e-08,
"loss": 0.9187,
"step": 1505
},
{
"epoch": 0.97,
"learning_rate": 4.226209296383288e-08,
"loss": 0.9528,
"step": 1506
},
{
"epoch": 0.97,
"learning_rate": 4.036419703291272e-08,
"loss": 0.1757,
"step": 1507
},
{
"epoch": 0.97,
"learning_rate": 3.850981470887361e-08,
"loss": 0.2316,
"step": 1508
},
{
"epoch": 0.97,
"learning_rate": 3.669895409350366e-08,
"loss": 0.8985,
"step": 1509
},
{
"epoch": 0.97,
"learning_rate": 3.493162309844533e-08,
"loss": 0.9608,
"step": 1510
},
{
"epoch": 0.97,
"learning_rate": 3.3207829445159876e-08,
"loss": 0.9294,
"step": 1511
},
{
"epoch": 0.98,
"learning_rate": 3.152758066489514e-08,
"loss": 0.9194,
"step": 1512
},
{
"epoch": 0.98,
"learning_rate": 2.989088409865004e-08,
"loss": 0.9305,
"step": 1513
},
{
"epoch": 0.98,
"learning_rate": 2.8297746897146816e-08,
"loss": 0.2267,
"step": 1514
},
{
"epoch": 0.98,
"learning_rate": 2.674817602079327e-08,
"loss": 0.2145,
"step": 1515
},
{
"epoch": 0.98,
"learning_rate": 2.5242178239658356e-08,
"loss": 0.9438,
"step": 1516
},
{
"epoch": 0.98,
"learning_rate": 2.3779760133441076e-08,
"loss": 0.9159,
"step": 1517
},
{
"epoch": 0.98,
"learning_rate": 2.2360928091439415e-08,
"loss": 0.928,
"step": 1518
},
{
"epoch": 0.98,
"learning_rate": 2.0985688312524787e-08,
"loss": 0.919,
"step": 1519
},
{
"epoch": 0.98,
"learning_rate": 1.965404680511207e-08,
"loss": 0.8935,
"step": 1520
},
{
"epoch": 0.98,
"learning_rate": 1.8366009387140726e-08,
"loss": 0.9102,
"step": 1521
},
{
"epoch": 0.98,
"learning_rate": 1.712158168603928e-08,
"loss": 0.9117,
"step": 1522
},
{
"epoch": 0.98,
"learning_rate": 1.592076913870644e-08,
"loss": 0.9458,
"step": 1523
},
{
"epoch": 0.98,
"learning_rate": 1.4763576991487782e-08,
"loss": 0.2253,
"step": 1524
},
{
"epoch": 0.98,
"learning_rate": 1.3650010300150229e-08,
"loss": 0.2202,
"step": 1525
},
{
"epoch": 0.98,
"learning_rate": 1.2580073929863157e-08,
"loss": 0.9218,
"step": 1526
},
{
"epoch": 0.99,
"learning_rate": 1.1553772555172871e-08,
"loss": 0.9218,
"step": 1527
},
{
"epoch": 0.99,
"learning_rate": 1.057111065998706e-08,
"loss": 0.9451,
"step": 1528
},
{
"epoch": 0.99,
"learning_rate": 9.632092537551485e-09,
"loss": 0.2188,
"step": 1529
},
{
"epoch": 0.99,
"learning_rate": 8.736722290429988e-09,
"loss": 0.9062,
"step": 1530
},
{
"epoch": 0.99,
"learning_rate": 7.885003830494508e-09,
"loss": 0.9076,
"step": 1531
},
{
"epoch": 0.99,
"learning_rate": 7.07694087889621e-09,
"loss": 0.9359,
"step": 1532
},
{
"epoch": 0.99,
"learning_rate": 6.312536966062155e-09,
"loss": 0.9259,
"step": 1533
},
{
"epoch": 0.99,
"learning_rate": 5.591795431667546e-09,
"loss": 0.9223,
"step": 1534
},
{
"epoch": 0.99,
"learning_rate": 4.9147194246290666e-09,
"loss": 0.9284,
"step": 1535
},
{
"epoch": 0.99,
"learning_rate": 4.281311903090446e-09,
"loss": 0.9161,
"step": 1536
},
{
"epoch": 0.99,
"learning_rate": 3.6915756344046983e-09,
"loss": 0.9255,
"step": 1537
},
{
"epoch": 0.99,
"learning_rate": 3.1455131951285688e-09,
"loss": 0.2325,
"step": 1538
},
{
"epoch": 0.99,
"learning_rate": 2.6431269710058827e-09,
"loss": 0.2466,
"step": 1539
},
{
"epoch": 0.99,
"learning_rate": 2.184419156959772e-09,
"loss": 0.9264,
"step": 1540
},
{
"epoch": 0.99,
"learning_rate": 1.7693917570837938e-09,
"loss": 0.9056,
"step": 1541
},
{
"epoch": 0.99,
"learning_rate": 1.3980465846297198e-09,
"loss": 0.2116,
"step": 1542
},
{
"epoch": 1.0,
"learning_rate": 1.070385262003093e-09,
"loss": 0.2364,
"step": 1543
},
{
"epoch": 1.0,
"learning_rate": 7.864092207554575e-10,
"loss": 0.8961,
"step": 1544
},
{
"epoch": 1.0,
"learning_rate": 5.461197015765863e-10,
"loss": 0.9226,
"step": 1545
},
{
"epoch": 1.0,
"learning_rate": 3.4951775429004073e-10,
"loss": 0.949,
"step": 1546
},
{
"epoch": 1.0,
"learning_rate": 1.9660423784984007e-10,
"loss": 0.904,
"step": 1547
},
{
"epoch": 1.0,
"learning_rate": 8.737982033379944e-11,
"loss": 0.8994,
"step": 1548
},
{
"epoch": 1.0,
"learning_rate": 2.184497894353044e-11,
"loss": 0.8921,
"step": 1549
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 0.3274,
"step": 1550
},
{
"epoch": 1.0,
"step": 1550,
"total_flos": 821912105779200.0,
"train_loss": 0.8137407000603214,
"train_runtime": 20704.6732,
"train_samples_per_second": 9.582,
"train_steps_per_second": 0.075
}
],
"max_steps": 1550,
"num_train_epochs": 1,
"total_flos": 821912105779200.0,
"trial_name": null,
"trial_params": null
}