opt-350m-hy-wiki-alpaca / trainer_state.json
aburnazy's picture
Model save
873499e
raw
history blame
144 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9962358845671266,
"global_step": 1194,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 5.555555555555555e-07,
"loss": 0.6851,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 1.111111111111111e-06,
"loss": 0.6931,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 1.6666666666666667e-06,
"loss": 0.71,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 2.222222222222222e-06,
"loss": 0.6848,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 2.7777777777777783e-06,
"loss": 0.7194,
"step": 5
},
{
"epoch": 0.02,
"learning_rate": 3.3333333333333333e-06,
"loss": 0.6563,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 3.88888888888889e-06,
"loss": 0.6324,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 4.444444444444444e-06,
"loss": 0.648,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 5e-06,
"loss": 0.6078,
"step": 9
},
{
"epoch": 0.03,
"learning_rate": 5.555555555555557e-06,
"loss": 0.6846,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 6.111111111111112e-06,
"loss": 0.5922,
"step": 11
},
{
"epoch": 0.03,
"learning_rate": 6.666666666666667e-06,
"loss": 0.6785,
"step": 12
},
{
"epoch": 0.03,
"learning_rate": 7.222222222222223e-06,
"loss": 0.6388,
"step": 13
},
{
"epoch": 0.04,
"learning_rate": 7.77777777777778e-06,
"loss": 0.6009,
"step": 14
},
{
"epoch": 0.04,
"learning_rate": 8.333333333333334e-06,
"loss": 0.6271,
"step": 15
},
{
"epoch": 0.04,
"learning_rate": 8.888888888888888e-06,
"loss": 0.6202,
"step": 16
},
{
"epoch": 0.04,
"learning_rate": 9.444444444444445e-06,
"loss": 0.6227,
"step": 17
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 0.6181,
"step": 18
},
{
"epoch": 0.05,
"learning_rate": 1.0555555555555557e-05,
"loss": 0.631,
"step": 19
},
{
"epoch": 0.05,
"learning_rate": 1.1111111111111113e-05,
"loss": 0.628,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 1.1666666666666668e-05,
"loss": 0.6002,
"step": 21
},
{
"epoch": 0.06,
"learning_rate": 1.2222222222222224e-05,
"loss": 0.6085,
"step": 22
},
{
"epoch": 0.06,
"learning_rate": 1.2777777777777777e-05,
"loss": 0.6073,
"step": 23
},
{
"epoch": 0.06,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.6028,
"step": 24
},
{
"epoch": 0.06,
"learning_rate": 1.388888888888889e-05,
"loss": 0.6012,
"step": 25
},
{
"epoch": 0.07,
"learning_rate": 1.4444444444444446e-05,
"loss": 0.5809,
"step": 26
},
{
"epoch": 0.07,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.6,
"step": 27
},
{
"epoch": 0.07,
"learning_rate": 1.555555555555556e-05,
"loss": 0.5765,
"step": 28
},
{
"epoch": 0.07,
"learning_rate": 1.6111111111111115e-05,
"loss": 0.5833,
"step": 29
},
{
"epoch": 0.08,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.5944,
"step": 30
},
{
"epoch": 0.08,
"learning_rate": 1.7222222222222224e-05,
"loss": 0.6178,
"step": 31
},
{
"epoch": 0.08,
"learning_rate": 1.7777777777777777e-05,
"loss": 0.5678,
"step": 32
},
{
"epoch": 0.08,
"learning_rate": 1.8333333333333333e-05,
"loss": 0.6079,
"step": 33
},
{
"epoch": 0.09,
"learning_rate": 1.888888888888889e-05,
"loss": 0.602,
"step": 34
},
{
"epoch": 0.09,
"learning_rate": 1.9444444444444445e-05,
"loss": 0.5699,
"step": 35
},
{
"epoch": 0.09,
"learning_rate": 2e-05,
"loss": 0.5733,
"step": 36
},
{
"epoch": 0.09,
"learning_rate": 1.9999963199614804e-05,
"loss": 0.5703,
"step": 37
},
{
"epoch": 0.1,
"learning_rate": 1.999985279873006e-05,
"loss": 0.5729,
"step": 38
},
{
"epoch": 0.1,
"learning_rate": 1.999966879815833e-05,
"loss": 0.5485,
"step": 39
},
{
"epoch": 0.1,
"learning_rate": 1.999941119925387e-05,
"loss": 0.5884,
"step": 40
},
{
"epoch": 0.1,
"learning_rate": 1.9999080003912633e-05,
"loss": 0.5577,
"step": 41
},
{
"epoch": 0.11,
"learning_rate": 1.999867521457224e-05,
"loss": 0.5536,
"step": 42
},
{
"epoch": 0.11,
"learning_rate": 1.9998196834211972e-05,
"loss": 0.5435,
"step": 43
},
{
"epoch": 0.11,
"learning_rate": 1.9997644866352742e-05,
"loss": 0.5483,
"step": 44
},
{
"epoch": 0.11,
"learning_rate": 1.9997019315057083e-05,
"loss": 0.5623,
"step": 45
},
{
"epoch": 0.12,
"learning_rate": 1.9996320184929093e-05,
"loss": 0.5848,
"step": 46
},
{
"epoch": 0.12,
"learning_rate": 1.9995547481114427e-05,
"loss": 0.5944,
"step": 47
},
{
"epoch": 0.12,
"learning_rate": 1.9994701209300245e-05,
"loss": 0.5462,
"step": 48
},
{
"epoch": 0.12,
"learning_rate": 1.9993781375715172e-05,
"loss": 0.5598,
"step": 49
},
{
"epoch": 0.13,
"learning_rate": 1.9992787987129253e-05,
"loss": 0.5629,
"step": 50
},
{
"epoch": 0.13,
"learning_rate": 1.9991721050853908e-05,
"loss": 0.5421,
"step": 51
},
{
"epoch": 0.13,
"learning_rate": 1.9990580574741867e-05,
"loss": 0.5575,
"step": 52
},
{
"epoch": 0.13,
"learning_rate": 1.998936656718712e-05,
"loss": 0.587,
"step": 53
},
{
"epoch": 0.14,
"learning_rate": 1.9988079037124866e-05,
"loss": 0.5908,
"step": 54
},
{
"epoch": 0.14,
"learning_rate": 1.9986717994031415e-05,
"loss": 0.5417,
"step": 55
},
{
"epoch": 0.14,
"learning_rate": 1.998528344792415e-05,
"loss": 0.5734,
"step": 56
},
{
"epoch": 0.14,
"learning_rate": 1.9983775409361447e-05,
"loss": 0.5511,
"step": 57
},
{
"epoch": 0.15,
"learning_rate": 1.9982193889442583e-05,
"loss": 0.5792,
"step": 58
},
{
"epoch": 0.15,
"learning_rate": 1.9980538899807664e-05,
"loss": 0.5506,
"step": 59
},
{
"epoch": 0.15,
"learning_rate": 1.9978810452637544e-05,
"loss": 0.5348,
"step": 60
},
{
"epoch": 0.15,
"learning_rate": 1.9977008560653724e-05,
"loss": 0.5156,
"step": 61
},
{
"epoch": 0.16,
"learning_rate": 1.9975133237118276e-05,
"loss": 0.5565,
"step": 62
},
{
"epoch": 0.16,
"learning_rate": 1.9973184495833717e-05,
"loss": 0.5809,
"step": 63
},
{
"epoch": 0.16,
"learning_rate": 1.9971162351142935e-05,
"loss": 0.5538,
"step": 64
},
{
"epoch": 0.16,
"learning_rate": 1.9969066817929073e-05,
"loss": 0.5506,
"step": 65
},
{
"epoch": 0.17,
"learning_rate": 1.9966897911615417e-05,
"loss": 0.5323,
"step": 66
},
{
"epoch": 0.17,
"learning_rate": 1.996465564816528e-05,
"loss": 0.544,
"step": 67
},
{
"epoch": 0.17,
"learning_rate": 1.9962340044081898e-05,
"loss": 0.5396,
"step": 68
},
{
"epoch": 0.17,
"learning_rate": 1.9959951116408295e-05,
"loss": 0.5334,
"step": 69
},
{
"epoch": 0.18,
"learning_rate": 1.9957488882727163e-05,
"loss": 0.5123,
"step": 70
},
{
"epoch": 0.18,
"learning_rate": 1.995495336116073e-05,
"loss": 0.5396,
"step": 71
},
{
"epoch": 0.18,
"learning_rate": 1.995234457037063e-05,
"loss": 0.5163,
"step": 72
},
{
"epoch": 0.18,
"learning_rate": 1.9949662529557764e-05,
"loss": 0.6043,
"step": 73
},
{
"epoch": 0.19,
"learning_rate": 1.994690725846216e-05,
"loss": 0.5903,
"step": 74
},
{
"epoch": 0.19,
"learning_rate": 1.9944078777362828e-05,
"loss": 0.57,
"step": 75
},
{
"epoch": 0.19,
"learning_rate": 1.9941177107077604e-05,
"loss": 0.5679,
"step": 76
},
{
"epoch": 0.19,
"learning_rate": 1.9938202268963004e-05,
"loss": 0.5383,
"step": 77
},
{
"epoch": 0.2,
"learning_rate": 1.9935154284914063e-05,
"loss": 0.5429,
"step": 78
},
{
"epoch": 0.2,
"learning_rate": 1.9932033177364188e-05,
"loss": 0.5361,
"step": 79
},
{
"epoch": 0.2,
"learning_rate": 1.9928838969284964e-05,
"loss": 0.5557,
"step": 80
},
{
"epoch": 0.2,
"learning_rate": 1.9925571684186006e-05,
"loss": 0.5508,
"step": 81
},
{
"epoch": 0.21,
"learning_rate": 1.9922231346114795e-05,
"loss": 0.5473,
"step": 82
},
{
"epoch": 0.21,
"learning_rate": 1.9918817979656463e-05,
"loss": 0.5123,
"step": 83
},
{
"epoch": 0.21,
"learning_rate": 1.991533160993366e-05,
"loss": 0.5629,
"step": 84
},
{
"epoch": 0.21,
"learning_rate": 1.991177226260633e-05,
"loss": 0.5351,
"step": 85
},
{
"epoch": 0.22,
"learning_rate": 1.9908139963871547e-05,
"loss": 0.549,
"step": 86
},
{
"epoch": 0.22,
"learning_rate": 1.990443474046331e-05,
"loss": 0.5437,
"step": 87
},
{
"epoch": 0.22,
"learning_rate": 1.9900656619652343e-05,
"loss": 0.5403,
"step": 88
},
{
"epoch": 0.22,
"learning_rate": 1.9896805629245912e-05,
"loss": 0.5476,
"step": 89
},
{
"epoch": 0.23,
"learning_rate": 1.98928817975876e-05,
"loss": 0.5399,
"step": 90
},
{
"epoch": 0.23,
"learning_rate": 1.9888885153557113e-05,
"loss": 0.5494,
"step": 91
},
{
"epoch": 0.23,
"learning_rate": 1.988481572657006e-05,
"loss": 0.5453,
"step": 92
},
{
"epoch": 0.23,
"learning_rate": 1.988067354657773e-05,
"loss": 0.574,
"step": 93
},
{
"epoch": 0.24,
"learning_rate": 1.9876458644066896e-05,
"loss": 0.5634,
"step": 94
},
{
"epoch": 0.24,
"learning_rate": 1.987217105005956e-05,
"loss": 0.5004,
"step": 95
},
{
"epoch": 0.24,
"learning_rate": 1.9867810796112742e-05,
"loss": 0.5189,
"step": 96
},
{
"epoch": 0.24,
"learning_rate": 1.986337791431825e-05,
"loss": 0.5305,
"step": 97
},
{
"epoch": 0.25,
"learning_rate": 1.985887243730244e-05,
"loss": 0.545,
"step": 98
},
{
"epoch": 0.25,
"learning_rate": 1.985429439822596e-05,
"loss": 0.5433,
"step": 99
},
{
"epoch": 0.25,
"learning_rate": 1.984964383078354e-05,
"loss": 0.5326,
"step": 100
},
{
"epoch": 0.25,
"learning_rate": 1.984492076920371e-05,
"loss": 0.5309,
"step": 101
},
{
"epoch": 0.26,
"learning_rate": 1.9840125248248564e-05,
"loss": 0.551,
"step": 102
},
{
"epoch": 0.26,
"learning_rate": 1.9835257303213514e-05,
"loss": 0.5504,
"step": 103
},
{
"epoch": 0.26,
"learning_rate": 1.9830316969927002e-05,
"loss": 0.5102,
"step": 104
},
{
"epoch": 0.26,
"learning_rate": 1.9825304284750263e-05,
"loss": 0.5569,
"step": 105
},
{
"epoch": 0.27,
"learning_rate": 1.9820219284577052e-05,
"loss": 0.5249,
"step": 106
},
{
"epoch": 0.27,
"learning_rate": 1.981506200683336e-05,
"loss": 0.5383,
"step": 107
},
{
"epoch": 0.27,
"learning_rate": 1.9809832489477144e-05,
"loss": 0.5321,
"step": 108
},
{
"epoch": 0.27,
"learning_rate": 1.9804530770998058e-05,
"loss": 0.5073,
"step": 109
},
{
"epoch": 0.28,
"learning_rate": 1.9799156890417156e-05,
"loss": 0.536,
"step": 110
},
{
"epoch": 0.28,
"learning_rate": 1.9793710887286613e-05,
"loss": 0.5424,
"step": 111
},
{
"epoch": 0.28,
"learning_rate": 1.978819280168944e-05,
"loss": 0.5491,
"step": 112
},
{
"epoch": 0.28,
"learning_rate": 1.9782602674239163e-05,
"loss": 0.5261,
"step": 113
},
{
"epoch": 0.29,
"learning_rate": 1.9776940546079552e-05,
"loss": 0.5392,
"step": 114
},
{
"epoch": 0.29,
"learning_rate": 1.9771206458884312e-05,
"loss": 0.5344,
"step": 115
},
{
"epoch": 0.29,
"learning_rate": 1.976540045485676e-05,
"loss": 0.5261,
"step": 116
},
{
"epoch": 0.29,
"learning_rate": 1.9759522576729534e-05,
"loss": 0.6193,
"step": 117
},
{
"epoch": 0.3,
"learning_rate": 1.975357286776427e-05,
"loss": 0.5644,
"step": 118
},
{
"epoch": 0.3,
"learning_rate": 1.9747551371751285e-05,
"loss": 0.5439,
"step": 119
},
{
"epoch": 0.3,
"learning_rate": 1.9741458133009258e-05,
"loss": 0.4993,
"step": 120
},
{
"epoch": 0.3,
"learning_rate": 1.973529319638489e-05,
"loss": 0.5127,
"step": 121
},
{
"epoch": 0.31,
"learning_rate": 1.972905660725259e-05,
"loss": 0.5049,
"step": 122
},
{
"epoch": 0.31,
"learning_rate": 1.9722748411514137e-05,
"loss": 0.5208,
"step": 123
},
{
"epoch": 0.31,
"learning_rate": 1.9716368655598333e-05,
"loss": 0.5017,
"step": 124
},
{
"epoch": 0.31,
"learning_rate": 1.970991738646068e-05,
"loss": 0.5192,
"step": 125
},
{
"epoch": 0.32,
"learning_rate": 1.970339465158301e-05,
"loss": 0.5732,
"step": 126
},
{
"epoch": 0.32,
"learning_rate": 1.9696800498973158e-05,
"loss": 0.5403,
"step": 127
},
{
"epoch": 0.32,
"learning_rate": 1.9690134977164594e-05,
"loss": 0.5511,
"step": 128
},
{
"epoch": 0.32,
"learning_rate": 1.9683398135216067e-05,
"loss": 0.5183,
"step": 129
},
{
"epoch": 0.33,
"learning_rate": 1.967659002271126e-05,
"loss": 0.5411,
"step": 130
},
{
"epoch": 0.33,
"learning_rate": 1.9669710689758404e-05,
"loss": 0.5541,
"step": 131
},
{
"epoch": 0.33,
"learning_rate": 1.9662760186989914e-05,
"loss": 0.5108,
"step": 132
},
{
"epoch": 0.33,
"learning_rate": 1.9655738565562035e-05,
"loss": 0.5515,
"step": 133
},
{
"epoch": 0.34,
"learning_rate": 1.9648645877154435e-05,
"loss": 0.4876,
"step": 134
},
{
"epoch": 0.34,
"learning_rate": 1.964148217396985e-05,
"loss": 0.5134,
"step": 135
},
{
"epoch": 0.34,
"learning_rate": 1.9634247508733685e-05,
"loss": 0.5436,
"step": 136
},
{
"epoch": 0.34,
"learning_rate": 1.9626941934693636e-05,
"loss": 0.5043,
"step": 137
},
{
"epoch": 0.35,
"learning_rate": 1.9619565505619288e-05,
"loss": 0.517,
"step": 138
},
{
"epoch": 0.35,
"learning_rate": 1.961211827580173e-05,
"loss": 0.534,
"step": 139
},
{
"epoch": 0.35,
"learning_rate": 1.9604600300053146e-05,
"loss": 0.5416,
"step": 140
},
{
"epoch": 0.35,
"learning_rate": 1.9597011633706414e-05,
"loss": 0.5118,
"step": 141
},
{
"epoch": 0.36,
"learning_rate": 1.9589352332614708e-05,
"loss": 0.5224,
"step": 142
},
{
"epoch": 0.36,
"learning_rate": 1.9581622453151072e-05,
"loss": 0.5335,
"step": 143
},
{
"epoch": 0.36,
"learning_rate": 1.9573822052208013e-05,
"loss": 0.5342,
"step": 144
},
{
"epoch": 0.36,
"learning_rate": 1.9565951187197085e-05,
"loss": 0.5519,
"step": 145
},
{
"epoch": 0.37,
"learning_rate": 1.955800991604846e-05,
"loss": 0.4991,
"step": 146
},
{
"epoch": 0.37,
"learning_rate": 1.95499982972105e-05,
"loss": 0.5461,
"step": 147
},
{
"epoch": 0.37,
"learning_rate": 1.9541916389649346e-05,
"loss": 0.5579,
"step": 148
},
{
"epoch": 0.37,
"learning_rate": 1.953376425284846e-05,
"loss": 0.5263,
"step": 149
},
{
"epoch": 0.38,
"learning_rate": 1.9525541946808187e-05,
"loss": 0.5153,
"step": 150
},
{
"epoch": 0.38,
"learning_rate": 1.9517249532045346e-05,
"loss": 0.5015,
"step": 151
},
{
"epoch": 0.38,
"learning_rate": 1.9508887069592735e-05,
"loss": 0.5042,
"step": 152
},
{
"epoch": 0.38,
"learning_rate": 1.950045462099873e-05,
"loss": 0.5067,
"step": 153
},
{
"epoch": 0.39,
"learning_rate": 1.9491952248326805e-05,
"loss": 0.5113,
"step": 154
},
{
"epoch": 0.39,
"learning_rate": 1.948338001415507e-05,
"loss": 0.5072,
"step": 155
},
{
"epoch": 0.39,
"learning_rate": 1.9474737981575833e-05,
"loss": 0.5248,
"step": 156
},
{
"epoch": 0.39,
"learning_rate": 1.946602621419512e-05,
"loss": 0.5027,
"step": 157
},
{
"epoch": 0.4,
"learning_rate": 1.9457244776132208e-05,
"loss": 0.5065,
"step": 158
},
{
"epoch": 0.4,
"learning_rate": 1.944839373201916e-05,
"loss": 0.4864,
"step": 159
},
{
"epoch": 0.4,
"learning_rate": 1.9439473147000344e-05,
"loss": 0.4984,
"step": 160
},
{
"epoch": 0.4,
"learning_rate": 1.9430483086731945e-05,
"loss": 0.4953,
"step": 161
},
{
"epoch": 0.41,
"learning_rate": 1.942142361738151e-05,
"loss": 0.5094,
"step": 162
},
{
"epoch": 0.41,
"learning_rate": 1.9412294805627423e-05,
"loss": 0.5322,
"step": 163
},
{
"epoch": 0.41,
"learning_rate": 1.9403096718658446e-05,
"loss": 0.5051,
"step": 164
},
{
"epoch": 0.41,
"learning_rate": 1.9393829424173205e-05,
"loss": 0.5123,
"step": 165
},
{
"epoch": 0.42,
"learning_rate": 1.9384492990379703e-05,
"loss": 0.5421,
"step": 166
},
{
"epoch": 0.42,
"learning_rate": 1.937508748599481e-05,
"loss": 0.5095,
"step": 167
},
{
"epoch": 0.42,
"learning_rate": 1.936561298024377e-05,
"loss": 0.4903,
"step": 168
},
{
"epoch": 0.42,
"learning_rate": 1.9356069542859666e-05,
"loss": 0.5391,
"step": 169
},
{
"epoch": 0.43,
"learning_rate": 1.934645724408294e-05,
"loss": 0.5145,
"step": 170
},
{
"epoch": 0.43,
"learning_rate": 1.9336776154660842e-05,
"loss": 0.5282,
"step": 171
},
{
"epoch": 0.43,
"learning_rate": 1.9327026345846945e-05,
"loss": 0.4914,
"step": 172
},
{
"epoch": 0.43,
"learning_rate": 1.9317207889400595e-05,
"loss": 0.5086,
"step": 173
},
{
"epoch": 0.44,
"learning_rate": 1.9307320857586377e-05,
"loss": 0.5177,
"step": 174
},
{
"epoch": 0.44,
"learning_rate": 1.929736532317361e-05,
"loss": 0.5519,
"step": 175
},
{
"epoch": 0.44,
"learning_rate": 1.92873413594358e-05,
"loss": 0.4934,
"step": 176
},
{
"epoch": 0.44,
"learning_rate": 1.9277249040150093e-05,
"loss": 0.5244,
"step": 177
},
{
"epoch": 0.45,
"learning_rate": 1.9267088439596728e-05,
"loss": 0.5062,
"step": 178
},
{
"epoch": 0.45,
"learning_rate": 1.9256859632558513e-05,
"loss": 0.5085,
"step": 179
},
{
"epoch": 0.45,
"learning_rate": 1.9246562694320258e-05,
"loss": 0.5035,
"step": 180
},
{
"epoch": 0.45,
"learning_rate": 1.9236197700668214e-05,
"loss": 0.5051,
"step": 181
},
{
"epoch": 0.46,
"learning_rate": 1.9225764727889543e-05,
"loss": 0.5089,
"step": 182
},
{
"epoch": 0.46,
"learning_rate": 1.921526385277172e-05,
"loss": 0.5282,
"step": 183
},
{
"epoch": 0.46,
"learning_rate": 1.9204695152601997e-05,
"loss": 0.5372,
"step": 184
},
{
"epoch": 0.46,
"learning_rate": 1.9194058705166826e-05,
"loss": 0.4925,
"step": 185
},
{
"epoch": 0.47,
"learning_rate": 1.9183354588751274e-05,
"loss": 0.5308,
"step": 186
},
{
"epoch": 0.47,
"learning_rate": 1.9172582882138466e-05,
"loss": 0.5385,
"step": 187
},
{
"epoch": 0.47,
"learning_rate": 1.916174366460899e-05,
"loss": 0.5091,
"step": 188
},
{
"epoch": 0.47,
"learning_rate": 1.915083701594032e-05,
"loss": 0.5374,
"step": 189
},
{
"epoch": 0.48,
"learning_rate": 1.9139863016406237e-05,
"loss": 0.5217,
"step": 190
},
{
"epoch": 0.48,
"learning_rate": 1.912882174677622e-05,
"loss": 0.5258,
"step": 191
},
{
"epoch": 0.48,
"learning_rate": 1.9117713288314864e-05,
"loss": 0.4952,
"step": 192
},
{
"epoch": 0.48,
"learning_rate": 1.9106537722781276e-05,
"loss": 0.4756,
"step": 193
},
{
"epoch": 0.49,
"learning_rate": 1.9095295132428485e-05,
"loss": 0.5026,
"step": 194
},
{
"epoch": 0.49,
"learning_rate": 1.908398560000282e-05,
"loss": 0.5357,
"step": 195
},
{
"epoch": 0.49,
"learning_rate": 1.9072609208743307e-05,
"loss": 0.4941,
"step": 196
},
{
"epoch": 0.49,
"learning_rate": 1.9061166042381063e-05,
"loss": 0.5243,
"step": 197
},
{
"epoch": 0.5,
"learning_rate": 1.904965618513868e-05,
"loss": 0.4782,
"step": 198
},
{
"epoch": 0.5,
"learning_rate": 1.903807972172959e-05,
"loss": 0.5024,
"step": 199
},
{
"epoch": 0.5,
"learning_rate": 1.9026436737357454e-05,
"loss": 0.5009,
"step": 200
},
{
"epoch": 0.5,
"learning_rate": 1.9014727317715536e-05,
"loss": 0.5067,
"step": 201
},
{
"epoch": 0.51,
"learning_rate": 1.900295154898607e-05,
"loss": 0.5424,
"step": 202
},
{
"epoch": 0.51,
"learning_rate": 1.8991109517839613e-05,
"loss": 0.5136,
"step": 203
},
{
"epoch": 0.51,
"learning_rate": 1.8979201311434434e-05,
"loss": 0.5064,
"step": 204
},
{
"epoch": 0.51,
"learning_rate": 1.8967227017415845e-05,
"loss": 0.4988,
"step": 205
},
{
"epoch": 0.52,
"learning_rate": 1.8955186723915573e-05,
"loss": 0.4983,
"step": 206
},
{
"epoch": 0.52,
"learning_rate": 1.8943080519551108e-05,
"loss": 0.5269,
"step": 207
},
{
"epoch": 0.52,
"learning_rate": 1.8930908493425048e-05,
"loss": 0.4918,
"step": 208
},
{
"epoch": 0.52,
"learning_rate": 1.891867073512444e-05,
"loss": 0.5097,
"step": 209
},
{
"epoch": 0.53,
"learning_rate": 1.8906367334720125e-05,
"loss": 0.5157,
"step": 210
},
{
"epoch": 0.53,
"learning_rate": 1.889399838276608e-05,
"loss": 0.5019,
"step": 211
},
{
"epoch": 0.53,
"learning_rate": 1.888156397029875e-05,
"loss": 0.5122,
"step": 212
},
{
"epoch": 0.53,
"learning_rate": 1.886906418883636e-05,
"loss": 0.513,
"step": 213
},
{
"epoch": 0.54,
"learning_rate": 1.885649913037827e-05,
"loss": 0.5186,
"step": 214
},
{
"epoch": 0.54,
"learning_rate": 1.8843868887404282e-05,
"loss": 0.52,
"step": 215
},
{
"epoch": 0.54,
"learning_rate": 1.8831173552873946e-05,
"loss": 0.5203,
"step": 216
},
{
"epoch": 0.54,
"learning_rate": 1.881841322022591e-05,
"loss": 0.5034,
"step": 217
},
{
"epoch": 0.55,
"learning_rate": 1.8805587983377208e-05,
"loss": 0.4892,
"step": 218
},
{
"epoch": 0.55,
"learning_rate": 1.8792697936722565e-05,
"loss": 0.5142,
"step": 219
},
{
"epoch": 0.55,
"learning_rate": 1.8779743175133718e-05,
"loss": 0.5321,
"step": 220
},
{
"epoch": 0.55,
"learning_rate": 1.876672379395871e-05,
"loss": 0.4902,
"step": 221
},
{
"epoch": 0.56,
"learning_rate": 1.8753639889021197e-05,
"loss": 0.5124,
"step": 222
},
{
"epoch": 0.56,
"learning_rate": 1.874049155661972e-05,
"loss": 0.4841,
"step": 223
},
{
"epoch": 0.56,
"learning_rate": 1.8727278893527015e-05,
"loss": 0.4953,
"step": 224
},
{
"epoch": 0.56,
"learning_rate": 1.8714001996989312e-05,
"loss": 0.5018,
"step": 225
},
{
"epoch": 0.57,
"learning_rate": 1.8700660964725583e-05,
"loss": 0.5065,
"step": 226
},
{
"epoch": 0.57,
"learning_rate": 1.8687255894926853e-05,
"loss": 0.5039,
"step": 227
},
{
"epoch": 0.57,
"learning_rate": 1.8673786886255478e-05,
"loss": 0.5078,
"step": 228
},
{
"epoch": 0.57,
"learning_rate": 1.866025403784439e-05,
"loss": 0.4901,
"step": 229
},
{
"epoch": 0.58,
"learning_rate": 1.8646657449296394e-05,
"loss": 0.5165,
"step": 230
},
{
"epoch": 0.58,
"learning_rate": 1.863299722068344e-05,
"loss": 0.4865,
"step": 231
},
{
"epoch": 0.58,
"learning_rate": 1.8619273452545857e-05,
"loss": 0.5205,
"step": 232
},
{
"epoch": 0.58,
"learning_rate": 1.8605486245891633e-05,
"loss": 0.5214,
"step": 233
},
{
"epoch": 0.59,
"learning_rate": 1.8591635702195672e-05,
"loss": 0.5351,
"step": 234
},
{
"epoch": 0.59,
"learning_rate": 1.8577721923399047e-05,
"loss": 0.5053,
"step": 235
},
{
"epoch": 0.59,
"learning_rate": 1.8563745011908243e-05,
"loss": 0.4985,
"step": 236
},
{
"epoch": 0.59,
"learning_rate": 1.8549705070594396e-05,
"loss": 0.4789,
"step": 237
},
{
"epoch": 0.6,
"learning_rate": 1.8535602202792567e-05,
"loss": 0.4901,
"step": 238
},
{
"epoch": 0.6,
"learning_rate": 1.852143651230094e-05,
"loss": 0.4903,
"step": 239
},
{
"epoch": 0.6,
"learning_rate": 1.8507208103380093e-05,
"loss": 0.513,
"step": 240
},
{
"epoch": 0.6,
"learning_rate": 1.8492917080752208e-05,
"loss": 0.5149,
"step": 241
},
{
"epoch": 0.61,
"learning_rate": 1.8478563549600318e-05,
"loss": 0.54,
"step": 242
},
{
"epoch": 0.61,
"learning_rate": 1.8464147615567517e-05,
"loss": 0.4814,
"step": 243
},
{
"epoch": 0.61,
"learning_rate": 1.844966938475619e-05,
"loss": 0.4874,
"step": 244
},
{
"epoch": 0.61,
"learning_rate": 1.8435128963727225e-05,
"loss": 0.4713,
"step": 245
},
{
"epoch": 0.62,
"learning_rate": 1.8420526459499252e-05,
"loss": 0.467,
"step": 246
},
{
"epoch": 0.62,
"learning_rate": 1.8405861979547816e-05,
"loss": 0.5074,
"step": 247
},
{
"epoch": 0.62,
"learning_rate": 1.8391135631804626e-05,
"loss": 0.4905,
"step": 248
},
{
"epoch": 0.62,
"learning_rate": 1.8376347524656735e-05,
"loss": 0.5028,
"step": 249
},
{
"epoch": 0.63,
"learning_rate": 1.8361497766945747e-05,
"loss": 0.544,
"step": 250
},
{
"epoch": 0.63,
"learning_rate": 1.8346586467967028e-05,
"loss": 0.4808,
"step": 251
},
{
"epoch": 0.63,
"learning_rate": 1.8331613737468888e-05,
"loss": 0.5117,
"step": 252
},
{
"epoch": 0.63,
"learning_rate": 1.831657968565177e-05,
"loss": 0.4918,
"step": 253
},
{
"epoch": 0.64,
"learning_rate": 1.8301484423167456e-05,
"loss": 0.4937,
"step": 254
},
{
"epoch": 0.64,
"learning_rate": 1.8286328061118243e-05,
"loss": 0.5166,
"step": 255
},
{
"epoch": 0.64,
"learning_rate": 1.8271110711056125e-05,
"loss": 0.4977,
"step": 256
},
{
"epoch": 0.64,
"learning_rate": 1.8255832484981968e-05,
"loss": 0.5021,
"step": 257
},
{
"epoch": 0.65,
"learning_rate": 1.8240493495344695e-05,
"loss": 0.4588,
"step": 258
},
{
"epoch": 0.65,
"learning_rate": 1.8225093855040448e-05,
"loss": 0.503,
"step": 259
},
{
"epoch": 0.65,
"learning_rate": 1.8209633677411767e-05,
"loss": 0.5018,
"step": 260
},
{
"epoch": 0.65,
"learning_rate": 1.8194113076246753e-05,
"loss": 0.4895,
"step": 261
},
{
"epoch": 0.66,
"learning_rate": 1.8178532165778225e-05,
"loss": 0.5161,
"step": 262
},
{
"epoch": 0.66,
"learning_rate": 1.816289106068288e-05,
"loss": 0.5112,
"step": 263
},
{
"epoch": 0.66,
"learning_rate": 1.8147189876080463e-05,
"loss": 0.4783,
"step": 264
},
{
"epoch": 0.66,
"learning_rate": 1.8131428727532903e-05,
"loss": 0.4679,
"step": 265
},
{
"epoch": 0.67,
"learning_rate": 1.811560773104346e-05,
"loss": 0.5311,
"step": 266
},
{
"epoch": 0.67,
"learning_rate": 1.8099727003055894e-05,
"loss": 0.5193,
"step": 267
},
{
"epoch": 0.67,
"learning_rate": 1.808378666045358e-05,
"loss": 0.49,
"step": 268
},
{
"epoch": 0.68,
"learning_rate": 1.8067786820558673e-05,
"loss": 0.4768,
"step": 269
},
{
"epoch": 0.68,
"learning_rate": 1.8051727601131228e-05,
"loss": 0.4647,
"step": 270
},
{
"epoch": 0.68,
"learning_rate": 1.8035609120368334e-05,
"loss": 0.5046,
"step": 271
},
{
"epoch": 0.68,
"learning_rate": 1.801943149690325e-05,
"loss": 0.4713,
"step": 272
},
{
"epoch": 0.69,
"learning_rate": 1.800319484980453e-05,
"loss": 0.5632,
"step": 273
},
{
"epoch": 0.69,
"learning_rate": 1.798689929857516e-05,
"loss": 0.4908,
"step": 274
},
{
"epoch": 0.69,
"learning_rate": 1.7970544963151637e-05,
"loss": 0.532,
"step": 275
},
{
"epoch": 0.69,
"learning_rate": 1.7954131963903134e-05,
"loss": 0.5031,
"step": 276
},
{
"epoch": 0.7,
"learning_rate": 1.7937660421630595e-05,
"loss": 0.4989,
"step": 277
},
{
"epoch": 0.7,
"learning_rate": 1.7921130457565835e-05,
"loss": 0.4917,
"step": 278
},
{
"epoch": 0.7,
"learning_rate": 1.7904542193370665e-05,
"loss": 0.5138,
"step": 279
},
{
"epoch": 0.7,
"learning_rate": 1.7887895751135985e-05,
"loss": 0.479,
"step": 280
},
{
"epoch": 0.71,
"learning_rate": 1.78711912533809e-05,
"loss": 0.4857,
"step": 281
},
{
"epoch": 0.71,
"learning_rate": 1.785442882305179e-05,
"loss": 0.5169,
"step": 282
},
{
"epoch": 0.71,
"learning_rate": 1.783760858352144e-05,
"loss": 0.4372,
"step": 283
},
{
"epoch": 0.71,
"learning_rate": 1.7820730658588106e-05,
"loss": 0.4995,
"step": 284
},
{
"epoch": 0.72,
"learning_rate": 1.7803795172474618e-05,
"loss": 0.4789,
"step": 285
},
{
"epoch": 0.72,
"learning_rate": 1.7786802249827454e-05,
"loss": 0.5217,
"step": 286
},
{
"epoch": 0.72,
"learning_rate": 1.7769752015715842e-05,
"loss": 0.4812,
"step": 287
},
{
"epoch": 0.72,
"learning_rate": 1.775264459563081e-05,
"loss": 0.5201,
"step": 288
},
{
"epoch": 0.73,
"learning_rate": 1.7735480115484294e-05,
"loss": 0.4766,
"step": 289
},
{
"epoch": 0.73,
"learning_rate": 1.771825870160819e-05,
"loss": 0.5435,
"step": 290
},
{
"epoch": 0.73,
"learning_rate": 1.770098048075342e-05,
"loss": 0.4821,
"step": 291
},
{
"epoch": 0.73,
"learning_rate": 1.7683645580089038e-05,
"loss": 0.4936,
"step": 292
},
{
"epoch": 0.74,
"learning_rate": 1.7666254127201236e-05,
"loss": 0.4772,
"step": 293
},
{
"epoch": 0.74,
"learning_rate": 1.764880625009245e-05,
"loss": 0.4839,
"step": 294
},
{
"epoch": 0.74,
"learning_rate": 1.7631302077180403e-05,
"loss": 0.4808,
"step": 295
},
{
"epoch": 0.74,
"learning_rate": 1.761374173729715e-05,
"loss": 0.5062,
"step": 296
},
{
"epoch": 0.75,
"learning_rate": 1.7596125359688154e-05,
"loss": 0.4907,
"step": 297
},
{
"epoch": 0.75,
"learning_rate": 1.7578453074011302e-05,
"loss": 0.4915,
"step": 298
},
{
"epoch": 0.75,
"learning_rate": 1.7560725010335985e-05,
"loss": 0.5069,
"step": 299
},
{
"epoch": 0.75,
"learning_rate": 1.7542941299142113e-05,
"loss": 0.5337,
"step": 300
},
{
"epoch": 0.76,
"learning_rate": 1.7525102071319176e-05,
"loss": 0.502,
"step": 301
},
{
"epoch": 0.76,
"learning_rate": 1.7507207458165257e-05,
"loss": 0.4671,
"step": 302
},
{
"epoch": 0.76,
"learning_rate": 1.7489257591386092e-05,
"loss": 0.5064,
"step": 303
},
{
"epoch": 0.76,
"learning_rate": 1.7471252603094084e-05,
"loss": 0.4741,
"step": 304
},
{
"epoch": 0.77,
"learning_rate": 1.7453192625807334e-05,
"loss": 0.4673,
"step": 305
},
{
"epoch": 0.77,
"learning_rate": 1.7435077792448666e-05,
"loss": 0.4705,
"step": 306
},
{
"epoch": 0.77,
"learning_rate": 1.7416908236344647e-05,
"loss": 0.5046,
"step": 307
},
{
"epoch": 0.77,
"learning_rate": 1.7398684091224608e-05,
"loss": 0.4856,
"step": 308
},
{
"epoch": 0.78,
"learning_rate": 1.738040549121967e-05,
"loss": 0.4594,
"step": 309
},
{
"epoch": 0.78,
"learning_rate": 1.736207257086173e-05,
"loss": 0.4717,
"step": 310
},
{
"epoch": 0.78,
"learning_rate": 1.7343685465082488e-05,
"loss": 0.4986,
"step": 311
},
{
"epoch": 0.78,
"learning_rate": 1.7325244309212476e-05,
"loss": 0.4943,
"step": 312
},
{
"epoch": 0.79,
"learning_rate": 1.7306749238980008e-05,
"loss": 0.5307,
"step": 313
},
{
"epoch": 0.79,
"learning_rate": 1.7288200390510227e-05,
"loss": 0.5315,
"step": 314
},
{
"epoch": 0.79,
"learning_rate": 1.7269597900324096e-05,
"loss": 0.4784,
"step": 315
},
{
"epoch": 0.79,
"learning_rate": 1.725094190533737e-05,
"loss": 0.4687,
"step": 316
},
{
"epoch": 0.8,
"learning_rate": 1.7232232542859606e-05,
"loss": 0.4871,
"step": 317
},
{
"epoch": 0.8,
"learning_rate": 1.7213469950593156e-05,
"loss": 0.4784,
"step": 318
},
{
"epoch": 0.8,
"learning_rate": 1.7194654266632146e-05,
"loss": 0.4916,
"step": 319
},
{
"epoch": 0.8,
"learning_rate": 1.717578562946146e-05,
"loss": 0.4908,
"step": 320
},
{
"epoch": 0.81,
"learning_rate": 1.715686417795572e-05,
"loss": 0.4998,
"step": 321
},
{
"epoch": 0.81,
"learning_rate": 1.7137890051378264e-05,
"loss": 0.4824,
"step": 322
},
{
"epoch": 0.81,
"learning_rate": 1.7118863389380126e-05,
"loss": 0.5075,
"step": 323
},
{
"epoch": 0.81,
"learning_rate": 1.709978433199901e-05,
"loss": 0.4804,
"step": 324
},
{
"epoch": 0.82,
"learning_rate": 1.7080653019658244e-05,
"loss": 0.5054,
"step": 325
},
{
"epoch": 0.82,
"learning_rate": 1.706146959316576e-05,
"loss": 0.5214,
"step": 326
},
{
"epoch": 0.82,
"learning_rate": 1.7042234193713058e-05,
"loss": 0.4602,
"step": 327
},
{
"epoch": 0.82,
"learning_rate": 1.7022946962874157e-05,
"loss": 0.4785,
"step": 328
},
{
"epoch": 0.83,
"learning_rate": 1.700360804260456e-05,
"loss": 0.5133,
"step": 329
},
{
"epoch": 0.83,
"learning_rate": 1.6984217575240212e-05,
"loss": 0.4977,
"step": 330
},
{
"epoch": 0.83,
"learning_rate": 1.6964775703496447e-05,
"loss": 0.5202,
"step": 331
},
{
"epoch": 0.83,
"learning_rate": 1.694528257046694e-05,
"loss": 0.4836,
"step": 332
},
{
"epoch": 0.84,
"learning_rate": 1.692573831962265e-05,
"loss": 0.4767,
"step": 333
},
{
"epoch": 0.84,
"learning_rate": 1.6906143094810774e-05,
"loss": 0.4663,
"step": 334
},
{
"epoch": 0.84,
"learning_rate": 1.688649704025367e-05,
"loss": 0.4732,
"step": 335
},
{
"epoch": 0.84,
"learning_rate": 1.6866800300547814e-05,
"loss": 0.4688,
"step": 336
},
{
"epoch": 0.85,
"learning_rate": 1.6847053020662726e-05,
"loss": 0.5012,
"step": 337
},
{
"epoch": 0.85,
"learning_rate": 1.6827255345939915e-05,
"loss": 0.4858,
"step": 338
},
{
"epoch": 0.85,
"learning_rate": 1.6807407422091785e-05,
"loss": 0.4747,
"step": 339
},
{
"epoch": 0.85,
"learning_rate": 1.6787509395200582e-05,
"loss": 0.4729,
"step": 340
},
{
"epoch": 0.86,
"learning_rate": 1.6767561411717327e-05,
"loss": 0.4997,
"step": 341
},
{
"epoch": 0.86,
"learning_rate": 1.674756361846071e-05,
"loss": 0.5108,
"step": 342
},
{
"epoch": 0.86,
"learning_rate": 1.672751616261603e-05,
"loss": 0.466,
"step": 343
},
{
"epoch": 0.86,
"learning_rate": 1.6707419191734104e-05,
"loss": 0.5056,
"step": 344
},
{
"epoch": 0.87,
"learning_rate": 1.668727285373019e-05,
"loss": 0.4598,
"step": 345
},
{
"epoch": 0.87,
"learning_rate": 1.666707729688289e-05,
"loss": 0.488,
"step": 346
},
{
"epoch": 0.87,
"learning_rate": 1.6646832669833047e-05,
"loss": 0.4814,
"step": 347
},
{
"epoch": 0.87,
"learning_rate": 1.6626539121582687e-05,
"loss": 0.4708,
"step": 348
},
{
"epoch": 0.88,
"learning_rate": 1.660619680149388e-05,
"loss": 0.4808,
"step": 349
},
{
"epoch": 0.88,
"learning_rate": 1.658580585928768e-05,
"loss": 0.4708,
"step": 350
},
{
"epoch": 0.88,
"learning_rate": 1.6565366445042982e-05,
"loss": 0.4402,
"step": 351
},
{
"epoch": 0.88,
"learning_rate": 1.6544878709195457e-05,
"loss": 0.4943,
"step": 352
},
{
"epoch": 0.89,
"learning_rate": 1.652434280253641e-05,
"loss": 0.4901,
"step": 353
},
{
"epoch": 0.89,
"learning_rate": 1.650375887621171e-05,
"loss": 0.4798,
"step": 354
},
{
"epoch": 0.89,
"learning_rate": 1.6483127081720626e-05,
"loss": 0.4777,
"step": 355
},
{
"epoch": 0.89,
"learning_rate": 1.646244757091476e-05,
"loss": 0.4988,
"step": 356
},
{
"epoch": 0.9,
"learning_rate": 1.644172049599691e-05,
"loss": 0.4889,
"step": 357
},
{
"epoch": 0.9,
"learning_rate": 1.642094600951994e-05,
"loss": 0.4666,
"step": 358
},
{
"epoch": 0.9,
"learning_rate": 1.6400124264385673e-05,
"loss": 0.49,
"step": 359
},
{
"epoch": 0.9,
"learning_rate": 1.637925541384375e-05,
"loss": 0.4899,
"step": 360
},
{
"epoch": 0.91,
"learning_rate": 1.635833961149053e-05,
"loss": 0.4668,
"step": 361
},
{
"epoch": 0.91,
"learning_rate": 1.6337377011267924e-05,
"loss": 0.4801,
"step": 362
},
{
"epoch": 0.91,
"learning_rate": 1.631636776746228e-05,
"loss": 0.5233,
"step": 363
},
{
"epoch": 0.91,
"learning_rate": 1.6295312034703257e-05,
"loss": 0.4718,
"step": 364
},
{
"epoch": 0.92,
"learning_rate": 1.6274209967962668e-05,
"loss": 0.4685,
"step": 365
},
{
"epoch": 0.92,
"learning_rate": 1.6253061722553353e-05,
"loss": 0.4944,
"step": 366
},
{
"epoch": 0.92,
"learning_rate": 1.6231867454128023e-05,
"loss": 0.4683,
"step": 367
},
{
"epoch": 0.92,
"learning_rate": 1.621062731867813e-05,
"loss": 0.4785,
"step": 368
},
{
"epoch": 0.93,
"learning_rate": 1.6189341472532705e-05,
"loss": 0.4691,
"step": 369
},
{
"epoch": 0.93,
"learning_rate": 1.6168010072357216e-05,
"loss": 0.5389,
"step": 370
},
{
"epoch": 0.93,
"learning_rate": 1.614663327515241e-05,
"loss": 0.4873,
"step": 371
},
{
"epoch": 0.93,
"learning_rate": 1.612521123825317e-05,
"loss": 0.4726,
"step": 372
},
{
"epoch": 0.94,
"learning_rate": 1.6103744119327325e-05,
"loss": 0.5096,
"step": 373
},
{
"epoch": 0.94,
"learning_rate": 1.6082232076374532e-05,
"loss": 0.4604,
"step": 374
},
{
"epoch": 0.94,
"learning_rate": 1.6060675267725083e-05,
"loss": 0.5243,
"step": 375
},
{
"epoch": 0.94,
"learning_rate": 1.6039073852038746e-05,
"loss": 0.4934,
"step": 376
},
{
"epoch": 0.95,
"learning_rate": 1.6017427988303613e-05,
"loss": 0.49,
"step": 377
},
{
"epoch": 0.95,
"learning_rate": 1.5995737835834905e-05,
"loss": 0.4784,
"step": 378
},
{
"epoch": 0.95,
"learning_rate": 1.5974003554273815e-05,
"loss": 0.4511,
"step": 379
},
{
"epoch": 0.95,
"learning_rate": 1.5952225303586323e-05,
"loss": 0.4825,
"step": 380
},
{
"epoch": 0.96,
"learning_rate": 1.593040324406204e-05,
"loss": 0.4963,
"step": 381
},
{
"epoch": 0.96,
"learning_rate": 1.590853753631301e-05,
"loss": 0.542,
"step": 382
},
{
"epoch": 0.96,
"learning_rate": 1.5886628341272513e-05,
"loss": 0.4836,
"step": 383
},
{
"epoch": 0.96,
"learning_rate": 1.586467582019392e-05,
"loss": 0.4713,
"step": 384
},
{
"epoch": 0.97,
"learning_rate": 1.584268013464948e-05,
"loss": 0.513,
"step": 385
},
{
"epoch": 0.97,
"learning_rate": 1.5820641446529127e-05,
"loss": 0.4905,
"step": 386
},
{
"epoch": 0.97,
"learning_rate": 1.579855991803931e-05,
"loss": 0.4839,
"step": 387
},
{
"epoch": 0.97,
"learning_rate": 1.577643571170177e-05,
"loss": 0.4409,
"step": 388
},
{
"epoch": 0.98,
"learning_rate": 1.575426899035238e-05,
"loss": 0.5062,
"step": 389
},
{
"epoch": 0.98,
"learning_rate": 1.5732059917139912e-05,
"loss": 0.494,
"step": 390
},
{
"epoch": 0.98,
"learning_rate": 1.5709808655524858e-05,
"loss": 0.5002,
"step": 391
},
{
"epoch": 0.98,
"learning_rate": 1.5687515369278216e-05,
"loss": 0.5043,
"step": 392
},
{
"epoch": 0.99,
"learning_rate": 1.566518022248029e-05,
"loss": 0.4936,
"step": 393
},
{
"epoch": 0.99,
"learning_rate": 1.564280337951948e-05,
"loss": 0.4778,
"step": 394
},
{
"epoch": 0.99,
"learning_rate": 1.5620385005091077e-05,
"loss": 0.5234,
"step": 395
},
{
"epoch": 0.99,
"learning_rate": 1.5597925264196048e-05,
"loss": 0.4937,
"step": 396
},
{
"epoch": 1.0,
"learning_rate": 1.557542432213981e-05,
"loss": 0.4742,
"step": 397
},
{
"epoch": 1.0,
"learning_rate": 1.5552882344531023e-05,
"loss": 0.4712,
"step": 398
},
{
"epoch": 1.0,
"learning_rate": 1.5530299497280395e-05,
"loss": 0.4569,
"step": 399
},
{
"epoch": 1.0,
"learning_rate": 1.5507675946599413e-05,
"loss": 0.4717,
"step": 400
},
{
"epoch": 1.01,
"learning_rate": 1.548501185899915e-05,
"loss": 0.4758,
"step": 401
},
{
"epoch": 1.01,
"learning_rate": 1.546230740128904e-05,
"loss": 0.4799,
"step": 402
},
{
"epoch": 1.01,
"learning_rate": 1.5439562740575644e-05,
"loss": 0.4617,
"step": 403
},
{
"epoch": 1.01,
"learning_rate": 1.5416778044261413e-05,
"loss": 0.4626,
"step": 404
},
{
"epoch": 1.02,
"learning_rate": 1.5393953480043468e-05,
"loss": 0.4585,
"step": 405
},
{
"epoch": 1.02,
"learning_rate": 1.5371089215912363e-05,
"loss": 0.4473,
"step": 406
},
{
"epoch": 1.02,
"learning_rate": 1.534818542015084e-05,
"loss": 0.4612,
"step": 407
},
{
"epoch": 1.02,
"learning_rate": 1.53252422613326e-05,
"loss": 0.4622,
"step": 408
},
{
"epoch": 1.03,
"learning_rate": 1.530225990832106e-05,
"loss": 0.4389,
"step": 409
},
{
"epoch": 1.03,
"learning_rate": 1.5279238530268112e-05,
"loss": 0.5009,
"step": 410
},
{
"epoch": 1.03,
"learning_rate": 1.5256178296612869e-05,
"loss": 0.4696,
"step": 411
},
{
"epoch": 1.03,
"learning_rate": 1.5233079377080424e-05,
"loss": 0.4681,
"step": 412
},
{
"epoch": 1.04,
"learning_rate": 1.5209941941680614e-05,
"loss": 0.4749,
"step": 413
},
{
"epoch": 1.04,
"learning_rate": 1.5186766160706738e-05,
"loss": 0.4558,
"step": 414
},
{
"epoch": 1.04,
"learning_rate": 1.5163552204734328e-05,
"loss": 0.4633,
"step": 415
},
{
"epoch": 1.04,
"learning_rate": 1.5140300244619894e-05,
"loss": 0.477,
"step": 416
},
{
"epoch": 1.05,
"learning_rate": 1.5117010451499654e-05,
"loss": 0.4619,
"step": 417
},
{
"epoch": 1.05,
"learning_rate": 1.5093682996788274e-05,
"loss": 0.4529,
"step": 418
},
{
"epoch": 1.05,
"learning_rate": 1.5070318052177624e-05,
"loss": 0.4623,
"step": 419
},
{
"epoch": 1.05,
"learning_rate": 1.504691578963549e-05,
"loss": 0.4779,
"step": 420
},
{
"epoch": 1.06,
"learning_rate": 1.5023476381404334e-05,
"loss": 0.4785,
"step": 421
},
{
"epoch": 1.06,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.4701,
"step": 422
},
{
"epoch": 1.06,
"learning_rate": 1.4976486818210467e-05,
"loss": 0.4533,
"step": 423
},
{
"epoch": 1.06,
"learning_rate": 1.4952937009094567e-05,
"loss": 0.4617,
"step": 424
},
{
"epoch": 1.07,
"learning_rate": 1.4929350745980707e-05,
"loss": 0.4686,
"step": 425
},
{
"epoch": 1.07,
"learning_rate": 1.4905728202465596e-05,
"loss": 0.453,
"step": 426
},
{
"epoch": 1.07,
"learning_rate": 1.4882069552412982e-05,
"loss": 0.4801,
"step": 427
},
{
"epoch": 1.07,
"learning_rate": 1.4858374969952345e-05,
"loss": 0.4412,
"step": 428
},
{
"epoch": 1.08,
"learning_rate": 1.4834644629477643e-05,
"loss": 0.4853,
"step": 429
},
{
"epoch": 1.08,
"learning_rate": 1.4810878705646005e-05,
"loss": 0.4889,
"step": 430
},
{
"epoch": 1.08,
"learning_rate": 1.478707737337647e-05,
"loss": 0.4463,
"step": 431
},
{
"epoch": 1.08,
"learning_rate": 1.4763240807848667e-05,
"loss": 0.4835,
"step": 432
},
{
"epoch": 1.09,
"learning_rate": 1.4739369184501557e-05,
"loss": 0.4908,
"step": 433
},
{
"epoch": 1.09,
"learning_rate": 1.4715462679032134e-05,
"loss": 0.4676,
"step": 434
},
{
"epoch": 1.09,
"learning_rate": 1.4691521467394109e-05,
"loss": 0.4526,
"step": 435
},
{
"epoch": 1.09,
"learning_rate": 1.4667545725796655e-05,
"loss": 0.4614,
"step": 436
},
{
"epoch": 1.1,
"learning_rate": 1.4643535630703067e-05,
"loss": 0.4524,
"step": 437
},
{
"epoch": 1.1,
"learning_rate": 1.4619491358829502e-05,
"loss": 0.4795,
"step": 438
},
{
"epoch": 1.1,
"learning_rate": 1.4595413087143656e-05,
"loss": 0.4769,
"step": 439
},
{
"epoch": 1.1,
"learning_rate": 1.4571300992863453e-05,
"loss": 0.4299,
"step": 440
},
{
"epoch": 1.11,
"learning_rate": 1.4547155253455769e-05,
"loss": 0.4601,
"step": 441
},
{
"epoch": 1.11,
"learning_rate": 1.452297604663511e-05,
"loss": 0.4828,
"step": 442
},
{
"epoch": 1.11,
"learning_rate": 1.44987635503623e-05,
"loss": 0.4521,
"step": 443
},
{
"epoch": 1.11,
"learning_rate": 1.4474517942843173e-05,
"loss": 0.518,
"step": 444
},
{
"epoch": 1.12,
"learning_rate": 1.4450239402527271e-05,
"loss": 0.466,
"step": 445
},
{
"epoch": 1.12,
"learning_rate": 1.4425928108106519e-05,
"loss": 0.4829,
"step": 446
},
{
"epoch": 1.12,
"learning_rate": 1.4401584238513921e-05,
"loss": 0.4496,
"step": 447
},
{
"epoch": 1.12,
"learning_rate": 1.4377207972922229e-05,
"loss": 0.4725,
"step": 448
},
{
"epoch": 1.13,
"learning_rate": 1.435279949074264e-05,
"loss": 0.4788,
"step": 449
},
{
"epoch": 1.13,
"learning_rate": 1.4328358971623455e-05,
"loss": 0.4362,
"step": 450
},
{
"epoch": 1.13,
"learning_rate": 1.4303886595448785e-05,
"loss": 0.4574,
"step": 451
},
{
"epoch": 1.13,
"learning_rate": 1.4279382542337202e-05,
"loss": 0.4549,
"step": 452
},
{
"epoch": 1.14,
"learning_rate": 1.4254846992640423e-05,
"loss": 0.4733,
"step": 453
},
{
"epoch": 1.14,
"learning_rate": 1.4230280126941987e-05,
"loss": 0.4345,
"step": 454
},
{
"epoch": 1.14,
"learning_rate": 1.4205682126055915e-05,
"loss": 0.4807,
"step": 455
},
{
"epoch": 1.14,
"learning_rate": 1.4181053171025392e-05,
"loss": 0.4772,
"step": 456
},
{
"epoch": 1.15,
"learning_rate": 1.4156393443121424e-05,
"loss": 0.4823,
"step": 457
},
{
"epoch": 1.15,
"learning_rate": 1.4131703123841503e-05,
"loss": 0.4639,
"step": 458
},
{
"epoch": 1.15,
"learning_rate": 1.4106982394908285e-05,
"loss": 0.4672,
"step": 459
},
{
"epoch": 1.15,
"learning_rate": 1.408223143826824e-05,
"loss": 0.4938,
"step": 460
},
{
"epoch": 1.16,
"learning_rate": 1.4057450436090316e-05,
"loss": 0.4601,
"step": 461
},
{
"epoch": 1.16,
"learning_rate": 1.4032639570764595e-05,
"loss": 0.4365,
"step": 462
},
{
"epoch": 1.16,
"learning_rate": 1.4007799024900962e-05,
"loss": 0.4945,
"step": 463
},
{
"epoch": 1.16,
"learning_rate": 1.3982928981327742e-05,
"loss": 0.4585,
"step": 464
},
{
"epoch": 1.17,
"learning_rate": 1.3958029623090379e-05,
"loss": 0.4769,
"step": 465
},
{
"epoch": 1.17,
"learning_rate": 1.393310113345006e-05,
"loss": 0.4392,
"step": 466
},
{
"epoch": 1.17,
"learning_rate": 1.3908143695882397e-05,
"loss": 0.4613,
"step": 467
},
{
"epoch": 1.17,
"learning_rate": 1.3883157494076048e-05,
"loss": 0.4436,
"step": 468
},
{
"epoch": 1.18,
"learning_rate": 1.3858142711931384e-05,
"loss": 0.468,
"step": 469
},
{
"epoch": 1.18,
"learning_rate": 1.3833099533559129e-05,
"loss": 0.496,
"step": 470
},
{
"epoch": 1.18,
"learning_rate": 1.3808028143279007e-05,
"loss": 0.4471,
"step": 471
},
{
"epoch": 1.18,
"learning_rate": 1.378292872561838e-05,
"loss": 0.4685,
"step": 472
},
{
"epoch": 1.19,
"learning_rate": 1.3757801465310895e-05,
"loss": 0.4309,
"step": 473
},
{
"epoch": 1.19,
"learning_rate": 1.3732646547295128e-05,
"loss": 0.4714,
"step": 474
},
{
"epoch": 1.19,
"learning_rate": 1.3707464156713208e-05,
"loss": 0.4448,
"step": 475
},
{
"epoch": 1.19,
"learning_rate": 1.3682254478909474e-05,
"loss": 0.4598,
"step": 476
},
{
"epoch": 1.2,
"learning_rate": 1.3657017699429092e-05,
"loss": 0.4479,
"step": 477
},
{
"epoch": 1.2,
"learning_rate": 1.3631754004016708e-05,
"loss": 0.462,
"step": 478
},
{
"epoch": 1.2,
"learning_rate": 1.3606463578615064e-05,
"loss": 0.4702,
"step": 479
},
{
"epoch": 1.2,
"learning_rate": 1.358114660936364e-05,
"loss": 0.4477,
"step": 480
},
{
"epoch": 1.21,
"learning_rate": 1.3555803282597279e-05,
"loss": 0.464,
"step": 481
},
{
"epoch": 1.21,
"learning_rate": 1.353043378484482e-05,
"loss": 0.4755,
"step": 482
},
{
"epoch": 1.21,
"learning_rate": 1.3505038302827724e-05,
"loss": 0.4627,
"step": 483
},
{
"epoch": 1.21,
"learning_rate": 1.3479617023458686e-05,
"loss": 0.4238,
"step": 484
},
{
"epoch": 1.22,
"learning_rate": 1.3454170133840291e-05,
"loss": 0.4531,
"step": 485
},
{
"epoch": 1.22,
"learning_rate": 1.34286978212636e-05,
"loss": 0.476,
"step": 486
},
{
"epoch": 1.22,
"learning_rate": 1.3403200273206798e-05,
"loss": 0.4479,
"step": 487
},
{
"epoch": 1.22,
"learning_rate": 1.3377677677333804e-05,
"loss": 0.447,
"step": 488
},
{
"epoch": 1.23,
"learning_rate": 1.335213022149289e-05,
"loss": 0.4497,
"step": 489
},
{
"epoch": 1.23,
"learning_rate": 1.3326558093715294e-05,
"loss": 0.4964,
"step": 490
},
{
"epoch": 1.23,
"learning_rate": 1.3300961482213855e-05,
"loss": 0.4607,
"step": 491
},
{
"epoch": 1.23,
"learning_rate": 1.32753405753816e-05,
"loss": 0.4314,
"step": 492
},
{
"epoch": 1.24,
"learning_rate": 1.3249695561790378e-05,
"loss": 0.466,
"step": 493
},
{
"epoch": 1.24,
"learning_rate": 1.3224026630189465e-05,
"loss": 0.4608,
"step": 494
},
{
"epoch": 1.24,
"learning_rate": 1.3198333969504176e-05,
"loss": 0.4594,
"step": 495
},
{
"epoch": 1.24,
"learning_rate": 1.3172617768834472e-05,
"loss": 0.4533,
"step": 496
},
{
"epoch": 1.25,
"learning_rate": 1.3146878217453572e-05,
"loss": 0.4653,
"step": 497
},
{
"epoch": 1.25,
"learning_rate": 1.3121115504806554e-05,
"loss": 0.4372,
"step": 498
},
{
"epoch": 1.25,
"learning_rate": 1.3095329820508974e-05,
"loss": 0.4395,
"step": 499
},
{
"epoch": 1.25,
"learning_rate": 1.3069521354345449e-05,
"loss": 0.481,
"step": 500
},
{
"epoch": 1.26,
"learning_rate": 1.304369029626828e-05,
"loss": 0.4464,
"step": 501
},
{
"epoch": 1.26,
"learning_rate": 1.3017836836396046e-05,
"loss": 0.4902,
"step": 502
},
{
"epoch": 1.26,
"learning_rate": 1.2991961165012203e-05,
"loss": 0.4622,
"step": 503
},
{
"epoch": 1.26,
"learning_rate": 1.2966063472563686e-05,
"loss": 0.4383,
"step": 504
},
{
"epoch": 1.27,
"learning_rate": 1.2940143949659504e-05,
"loss": 0.4831,
"step": 505
},
{
"epoch": 1.27,
"learning_rate": 1.2914202787069345e-05,
"loss": 0.4715,
"step": 506
},
{
"epoch": 1.27,
"learning_rate": 1.2888240175722163e-05,
"loss": 0.4969,
"step": 507
},
{
"epoch": 1.27,
"learning_rate": 1.2862256306704777e-05,
"loss": 0.4576,
"step": 508
},
{
"epoch": 1.28,
"learning_rate": 1.2836251371260469e-05,
"loss": 0.4614,
"step": 509
},
{
"epoch": 1.28,
"learning_rate": 1.2810225560787561e-05,
"loss": 0.4558,
"step": 510
},
{
"epoch": 1.28,
"learning_rate": 1.278417906683803e-05,
"loss": 0.4565,
"step": 511
},
{
"epoch": 1.28,
"learning_rate": 1.2758112081116071e-05,
"loss": 0.475,
"step": 512
},
{
"epoch": 1.29,
"learning_rate": 1.273202479547671e-05,
"loss": 0.4624,
"step": 513
},
{
"epoch": 1.29,
"learning_rate": 1.2705917401924382e-05,
"loss": 0.4812,
"step": 514
},
{
"epoch": 1.29,
"learning_rate": 1.267979009261151e-05,
"loss": 0.4186,
"step": 515
},
{
"epoch": 1.29,
"learning_rate": 1.2653643059837109e-05,
"loss": 0.4751,
"step": 516
},
{
"epoch": 1.3,
"learning_rate": 1.2627476496045349e-05,
"loss": 0.4844,
"step": 517
},
{
"epoch": 1.3,
"learning_rate": 1.2601290593824155e-05,
"loss": 0.4716,
"step": 518
},
{
"epoch": 1.3,
"learning_rate": 1.2575085545903793e-05,
"loss": 0.4645,
"step": 519
},
{
"epoch": 1.3,
"learning_rate": 1.2548861545155424e-05,
"loss": 0.4198,
"step": 520
},
{
"epoch": 1.31,
"learning_rate": 1.2522618784589724e-05,
"loss": 0.4412,
"step": 521
},
{
"epoch": 1.31,
"learning_rate": 1.2496357457355423e-05,
"loss": 0.4416,
"step": 522
},
{
"epoch": 1.31,
"learning_rate": 1.2470077756737919e-05,
"loss": 0.4207,
"step": 523
},
{
"epoch": 1.31,
"learning_rate": 1.2443779876157831e-05,
"loss": 0.477,
"step": 524
},
{
"epoch": 1.32,
"learning_rate": 1.2417464009169585e-05,
"loss": 0.456,
"step": 525
},
{
"epoch": 1.32,
"learning_rate": 1.239113034945999e-05,
"loss": 0.4617,
"step": 526
},
{
"epoch": 1.32,
"learning_rate": 1.2364779090846811e-05,
"loss": 0.4869,
"step": 527
},
{
"epoch": 1.32,
"learning_rate": 1.2338410427277342e-05,
"loss": 0.4572,
"step": 528
},
{
"epoch": 1.33,
"learning_rate": 1.2312024552826977e-05,
"loss": 0.4865,
"step": 529
},
{
"epoch": 1.33,
"learning_rate": 1.2285621661697787e-05,
"loss": 0.4466,
"step": 530
},
{
"epoch": 1.33,
"learning_rate": 1.2259201948217076e-05,
"loss": 0.4746,
"step": 531
},
{
"epoch": 1.34,
"learning_rate": 1.2232765606835986e-05,
"loss": 0.4433,
"step": 532
},
{
"epoch": 1.34,
"learning_rate": 1.2206312832128013e-05,
"loss": 0.4835,
"step": 533
},
{
"epoch": 1.34,
"learning_rate": 1.2179843818787625e-05,
"loss": 0.444,
"step": 534
},
{
"epoch": 1.34,
"learning_rate": 1.2153358761628793e-05,
"loss": 0.4453,
"step": 535
},
{
"epoch": 1.35,
"learning_rate": 1.212685785558358e-05,
"loss": 0.4412,
"step": 536
},
{
"epoch": 1.35,
"learning_rate": 1.2100341295700702e-05,
"loss": 0.4852,
"step": 537
},
{
"epoch": 1.35,
"learning_rate": 1.207380927714407e-05,
"loss": 0.4491,
"step": 538
},
{
"epoch": 1.35,
"learning_rate": 1.2047261995191397e-05,
"loss": 0.4685,
"step": 539
},
{
"epoch": 1.36,
"learning_rate": 1.202069964523272e-05,
"loss": 0.4871,
"step": 540
},
{
"epoch": 1.36,
"learning_rate": 1.1994122422768978e-05,
"loss": 0.4569,
"step": 541
},
{
"epoch": 1.36,
"learning_rate": 1.1967530523410578e-05,
"loss": 0.4542,
"step": 542
},
{
"epoch": 1.36,
"learning_rate": 1.1940924142875947e-05,
"loss": 0.4528,
"step": 543
},
{
"epoch": 1.37,
"learning_rate": 1.1914303476990096e-05,
"loss": 0.4563,
"step": 544
},
{
"epoch": 1.37,
"learning_rate": 1.1887668721683176e-05,
"loss": 0.4752,
"step": 545
},
{
"epoch": 1.37,
"learning_rate": 1.186102007298904e-05,
"loss": 0.4796,
"step": 546
},
{
"epoch": 1.37,
"learning_rate": 1.1834357727043795e-05,
"loss": 0.4572,
"step": 547
},
{
"epoch": 1.38,
"learning_rate": 1.1807681880084358e-05,
"loss": 0.4523,
"step": 548
},
{
"epoch": 1.38,
"learning_rate": 1.1780992728447018e-05,
"loss": 0.4385,
"step": 549
},
{
"epoch": 1.38,
"learning_rate": 1.1754290468565995e-05,
"loss": 0.4325,
"step": 550
},
{
"epoch": 1.38,
"learning_rate": 1.172757529697197e-05,
"loss": 0.4589,
"step": 551
},
{
"epoch": 1.39,
"learning_rate": 1.1700847410290667e-05,
"loss": 0.4409,
"step": 552
},
{
"epoch": 1.39,
"learning_rate": 1.167410700524139e-05,
"loss": 0.4477,
"step": 553
},
{
"epoch": 1.39,
"learning_rate": 1.1647354278635583e-05,
"loss": 0.4544,
"step": 554
},
{
"epoch": 1.39,
"learning_rate": 1.1620589427375375e-05,
"loss": 0.4684,
"step": 555
},
{
"epoch": 1.4,
"learning_rate": 1.1593812648452128e-05,
"loss": 0.4644,
"step": 556
},
{
"epoch": 1.4,
"learning_rate": 1.1567024138945003e-05,
"loss": 0.4379,
"step": 557
},
{
"epoch": 1.4,
"learning_rate": 1.1540224096019495e-05,
"loss": 0.4969,
"step": 558
},
{
"epoch": 1.4,
"learning_rate": 1.1513412716925978e-05,
"loss": 0.4614,
"step": 559
},
{
"epoch": 1.41,
"learning_rate": 1.148659019899827e-05,
"loss": 0.4275,
"step": 560
},
{
"epoch": 1.41,
"learning_rate": 1.1459756739652175e-05,
"loss": 0.4845,
"step": 561
},
{
"epoch": 1.41,
"learning_rate": 1.1432912536384013e-05,
"loss": 0.4781,
"step": 562
},
{
"epoch": 1.41,
"learning_rate": 1.1406057786769194e-05,
"loss": 0.468,
"step": 563
},
{
"epoch": 1.42,
"learning_rate": 1.137919268846074e-05,
"loss": 0.4744,
"step": 564
},
{
"epoch": 1.42,
"learning_rate": 1.135231743918785e-05,
"loss": 0.448,
"step": 565
},
{
"epoch": 1.42,
"learning_rate": 1.1325432236754424e-05,
"loss": 0.4486,
"step": 566
},
{
"epoch": 1.42,
"learning_rate": 1.129853727903762e-05,
"loss": 0.4523,
"step": 567
},
{
"epoch": 1.43,
"learning_rate": 1.1271632763986408e-05,
"loss": 0.4965,
"step": 568
},
{
"epoch": 1.43,
"learning_rate": 1.1244718889620085e-05,
"loss": 0.4382,
"step": 569
},
{
"epoch": 1.43,
"learning_rate": 1.121779585402684e-05,
"loss": 0.4397,
"step": 570
},
{
"epoch": 1.43,
"learning_rate": 1.1190863855362294e-05,
"loss": 0.4583,
"step": 571
},
{
"epoch": 1.44,
"learning_rate": 1.1163923091848026e-05,
"loss": 0.4555,
"step": 572
},
{
"epoch": 1.44,
"learning_rate": 1.1136973761770136e-05,
"loss": 0.4534,
"step": 573
},
{
"epoch": 1.44,
"learning_rate": 1.1110016063477763e-05,
"loss": 0.4805,
"step": 574
},
{
"epoch": 1.44,
"learning_rate": 1.1083050195381648e-05,
"loss": 0.5015,
"step": 575
},
{
"epoch": 1.45,
"learning_rate": 1.105607635595266e-05,
"loss": 0.4404,
"step": 576
},
{
"epoch": 1.45,
"learning_rate": 1.102909474372033e-05,
"loss": 0.44,
"step": 577
},
{
"epoch": 1.45,
"learning_rate": 1.1002105557271405e-05,
"loss": 0.4603,
"step": 578
},
{
"epoch": 1.45,
"learning_rate": 1.0975108995248378e-05,
"loss": 0.452,
"step": 579
},
{
"epoch": 1.46,
"learning_rate": 1.0948105256348021e-05,
"loss": 0.4285,
"step": 580
},
{
"epoch": 1.46,
"learning_rate": 1.0921094539319936e-05,
"loss": 0.4722,
"step": 581
},
{
"epoch": 1.46,
"learning_rate": 1.0894077042965084e-05,
"loss": 0.4613,
"step": 582
},
{
"epoch": 1.46,
"learning_rate": 1.0867052966134314e-05,
"loss": 0.4425,
"step": 583
},
{
"epoch": 1.47,
"learning_rate": 1.0840022507726915e-05,
"loss": 0.4435,
"step": 584
},
{
"epoch": 1.47,
"learning_rate": 1.0812985866689143e-05,
"loss": 0.4526,
"step": 585
},
{
"epoch": 1.47,
"learning_rate": 1.0785943242012763e-05,
"loss": 0.4608,
"step": 586
},
{
"epoch": 1.47,
"learning_rate": 1.075889483273357e-05,
"loss": 0.4327,
"step": 587
},
{
"epoch": 1.48,
"learning_rate": 1.0731840837929946e-05,
"loss": 0.4589,
"step": 588
},
{
"epoch": 1.48,
"learning_rate": 1.0704781456721372e-05,
"loss": 0.4706,
"step": 589
},
{
"epoch": 1.48,
"learning_rate": 1.0677716888266979e-05,
"loss": 0.4519,
"step": 590
},
{
"epoch": 1.48,
"learning_rate": 1.0650647331764079e-05,
"loss": 0.4662,
"step": 591
},
{
"epoch": 1.49,
"learning_rate": 1.0623572986446689e-05,
"loss": 0.4652,
"step": 592
},
{
"epoch": 1.49,
"learning_rate": 1.059649405158408e-05,
"loss": 0.4539,
"step": 593
},
{
"epoch": 1.49,
"learning_rate": 1.0569410726479301e-05,
"loss": 0.4528,
"step": 594
},
{
"epoch": 1.49,
"learning_rate": 1.0542323210467704e-05,
"loss": 0.4723,
"step": 595
},
{
"epoch": 1.5,
"learning_rate": 1.0515231702915498e-05,
"loss": 0.4278,
"step": 596
},
{
"epoch": 1.5,
"learning_rate": 1.0488136403218265e-05,
"loss": 0.4492,
"step": 597
},
{
"epoch": 1.5,
"learning_rate": 1.0461037510799499e-05,
"loss": 0.4557,
"step": 598
},
{
"epoch": 1.5,
"learning_rate": 1.0433935225109135e-05,
"loss": 0.4612,
"step": 599
},
{
"epoch": 1.51,
"learning_rate": 1.0406829745622085e-05,
"loss": 0.4334,
"step": 600
},
{
"epoch": 1.51,
"learning_rate": 1.0379721271836765e-05,
"loss": 0.4501,
"step": 601
},
{
"epoch": 1.51,
"learning_rate": 1.035261000327363e-05,
"loss": 0.4841,
"step": 602
},
{
"epoch": 1.51,
"learning_rate": 1.0325496139473702e-05,
"loss": 0.5002,
"step": 603
},
{
"epoch": 1.52,
"learning_rate": 1.0298379879997119e-05,
"loss": 0.4445,
"step": 604
},
{
"epoch": 1.52,
"learning_rate": 1.0271261424421628e-05,
"loss": 0.4673,
"step": 605
},
{
"epoch": 1.52,
"learning_rate": 1.0244140972341155e-05,
"loss": 0.4616,
"step": 606
},
{
"epoch": 1.52,
"learning_rate": 1.0217018723364316e-05,
"loss": 0.4305,
"step": 607
},
{
"epoch": 1.53,
"learning_rate": 1.0189894877112956e-05,
"loss": 0.4506,
"step": 608
},
{
"epoch": 1.53,
"learning_rate": 1.0162769633220673e-05,
"loss": 0.4466,
"step": 609
},
{
"epoch": 1.53,
"learning_rate": 1.0135643191331344e-05,
"loss": 0.4479,
"step": 610
},
{
"epoch": 1.53,
"learning_rate": 1.0108515751097678e-05,
"loss": 0.4435,
"step": 611
},
{
"epoch": 1.54,
"learning_rate": 1.008138751217973e-05,
"loss": 0.4541,
"step": 612
},
{
"epoch": 1.54,
"learning_rate": 1.0054258674243418e-05,
"loss": 0.4632,
"step": 613
},
{
"epoch": 1.54,
"learning_rate": 1.0027129436959082e-05,
"loss": 0.4523,
"step": 614
},
{
"epoch": 1.54,
"learning_rate": 1e-05,
"loss": 0.4524,
"step": 615
},
{
"epoch": 1.55,
"learning_rate": 9.97287056304092e-06,
"loss": 0.4476,
"step": 616
},
{
"epoch": 1.55,
"learning_rate": 9.945741325756589e-06,
"loss": 0.4502,
"step": 617
},
{
"epoch": 1.55,
"learning_rate": 9.918612487820274e-06,
"loss": 0.4633,
"step": 618
},
{
"epoch": 1.55,
"learning_rate": 9.891484248902322e-06,
"loss": 0.4557,
"step": 619
},
{
"epoch": 1.56,
"learning_rate": 9.86435680866866e-06,
"loss": 0.4454,
"step": 620
},
{
"epoch": 1.56,
"learning_rate": 9.837230366779332e-06,
"loss": 0.4411,
"step": 621
},
{
"epoch": 1.56,
"learning_rate": 9.810105122887049e-06,
"loss": 0.4624,
"step": 622
},
{
"epoch": 1.56,
"learning_rate": 9.782981276635686e-06,
"loss": 0.4409,
"step": 623
},
{
"epoch": 1.57,
"learning_rate": 9.755859027658848e-06,
"loss": 0.4608,
"step": 624
},
{
"epoch": 1.57,
"learning_rate": 9.728738575578377e-06,
"loss": 0.4563,
"step": 625
},
{
"epoch": 1.57,
"learning_rate": 9.701620120002885e-06,
"loss": 0.4516,
"step": 626
},
{
"epoch": 1.57,
"learning_rate": 9.674503860526297e-06,
"loss": 0.4352,
"step": 627
},
{
"epoch": 1.58,
"learning_rate": 9.647389996726375e-06,
"loss": 0.4534,
"step": 628
},
{
"epoch": 1.58,
"learning_rate": 9.620278728163237e-06,
"loss": 0.43,
"step": 629
},
{
"epoch": 1.58,
"learning_rate": 9.593170254377915e-06,
"loss": 0.473,
"step": 630
},
{
"epoch": 1.58,
"learning_rate": 9.566064774890868e-06,
"loss": 0.4629,
"step": 631
},
{
"epoch": 1.59,
"learning_rate": 9.538962489200503e-06,
"loss": 0.4635,
"step": 632
},
{
"epoch": 1.59,
"learning_rate": 9.511863596781733e-06,
"loss": 0.4511,
"step": 633
},
{
"epoch": 1.59,
"learning_rate": 9.484768297084504e-06,
"loss": 0.4333,
"step": 634
},
{
"epoch": 1.59,
"learning_rate": 9.457676789532299e-06,
"loss": 0.4456,
"step": 635
},
{
"epoch": 1.6,
"learning_rate": 9.430589273520704e-06,
"loss": 0.4592,
"step": 636
},
{
"epoch": 1.6,
"learning_rate": 9.403505948415923e-06,
"loss": 0.4895,
"step": 637
},
{
"epoch": 1.6,
"learning_rate": 9.376427013553311e-06,
"loss": 0.4105,
"step": 638
},
{
"epoch": 1.6,
"learning_rate": 9.349352668235925e-06,
"loss": 0.4597,
"step": 639
},
{
"epoch": 1.61,
"learning_rate": 9.322283111733023e-06,
"loss": 0.4429,
"step": 640
},
{
"epoch": 1.61,
"learning_rate": 9.29521854327863e-06,
"loss": 0.4539,
"step": 641
},
{
"epoch": 1.61,
"learning_rate": 9.268159162070058e-06,
"loss": 0.4596,
"step": 642
},
{
"epoch": 1.61,
"learning_rate": 9.241105167266433e-06,
"loss": 0.4556,
"step": 643
},
{
"epoch": 1.62,
"learning_rate": 9.214056757987238e-06,
"loss": 0.4619,
"step": 644
},
{
"epoch": 1.62,
"learning_rate": 9.18701413331086e-06,
"loss": 0.4443,
"step": 645
},
{
"epoch": 1.62,
"learning_rate": 9.159977492273086e-06,
"loss": 0.4438,
"step": 646
},
{
"epoch": 1.62,
"learning_rate": 9.13294703386569e-06,
"loss": 0.4571,
"step": 647
},
{
"epoch": 1.63,
"learning_rate": 9.105922957034921e-06,
"loss": 0.4573,
"step": 648
},
{
"epoch": 1.63,
"learning_rate": 9.078905460680064e-06,
"loss": 0.452,
"step": 649
},
{
"epoch": 1.63,
"learning_rate": 9.05189474365198e-06,
"loss": 0.4074,
"step": 650
},
{
"epoch": 1.63,
"learning_rate": 9.024891004751625e-06,
"loss": 0.4465,
"step": 651
},
{
"epoch": 1.64,
"learning_rate": 8.997894442728598e-06,
"loss": 0.412,
"step": 652
},
{
"epoch": 1.64,
"learning_rate": 8.970905256279675e-06,
"loss": 0.423,
"step": 653
},
{
"epoch": 1.64,
"learning_rate": 8.943923644047343e-06,
"loss": 0.4553,
"step": 654
},
{
"epoch": 1.64,
"learning_rate": 8.916949804618353e-06,
"loss": 0.4543,
"step": 655
},
{
"epoch": 1.65,
"learning_rate": 8.889983936522242e-06,
"loss": 0.4569,
"step": 656
},
{
"epoch": 1.65,
"learning_rate": 8.863026238229869e-06,
"loss": 0.4605,
"step": 657
},
{
"epoch": 1.65,
"learning_rate": 8.836076908151981e-06,
"loss": 0.4514,
"step": 658
},
{
"epoch": 1.65,
"learning_rate": 8.80913614463771e-06,
"loss": 0.4794,
"step": 659
},
{
"epoch": 1.66,
"learning_rate": 8.782204145973162e-06,
"loss": 0.4574,
"step": 660
},
{
"epoch": 1.66,
"learning_rate": 8.755281110379922e-06,
"loss": 0.4528,
"step": 661
},
{
"epoch": 1.66,
"learning_rate": 8.728367236013595e-06,
"loss": 0.4409,
"step": 662
},
{
"epoch": 1.66,
"learning_rate": 8.701462720962382e-06,
"loss": 0.4384,
"step": 663
},
{
"epoch": 1.67,
"learning_rate": 8.674567763245581e-06,
"loss": 0.4666,
"step": 664
},
{
"epoch": 1.67,
"learning_rate": 8.647682560812152e-06,
"loss": 0.4494,
"step": 665
},
{
"epoch": 1.67,
"learning_rate": 8.620807311539258e-06,
"loss": 0.483,
"step": 666
},
{
"epoch": 1.67,
"learning_rate": 8.593942213230808e-06,
"loss": 0.4377,
"step": 667
},
{
"epoch": 1.68,
"learning_rate": 8.567087463615988e-06,
"loss": 0.4686,
"step": 668
},
{
"epoch": 1.68,
"learning_rate": 8.540243260347825e-06,
"loss": 0.4519,
"step": 669
},
{
"epoch": 1.68,
"learning_rate": 8.513409801001731e-06,
"loss": 0.4305,
"step": 670
},
{
"epoch": 1.68,
"learning_rate": 8.486587283074026e-06,
"loss": 0.4582,
"step": 671
},
{
"epoch": 1.69,
"learning_rate": 8.45977590398051e-06,
"loss": 0.4652,
"step": 672
},
{
"epoch": 1.69,
"learning_rate": 8.432975861054999e-06,
"loss": 0.4723,
"step": 673
},
{
"epoch": 1.69,
"learning_rate": 8.406187351547872e-06,
"loss": 0.452,
"step": 674
},
{
"epoch": 1.69,
"learning_rate": 8.379410572624629e-06,
"loss": 0.4676,
"step": 675
},
{
"epoch": 1.7,
"learning_rate": 8.352645721364419e-06,
"loss": 0.4543,
"step": 676
},
{
"epoch": 1.7,
"learning_rate": 8.32589299475861e-06,
"loss": 0.4388,
"step": 677
},
{
"epoch": 1.7,
"learning_rate": 8.299152589709336e-06,
"loss": 0.4728,
"step": 678
},
{
"epoch": 1.7,
"learning_rate": 8.272424703028032e-06,
"loss": 0.445,
"step": 679
},
{
"epoch": 1.71,
"learning_rate": 8.245709531434005e-06,
"loss": 0.4498,
"step": 680
},
{
"epoch": 1.71,
"learning_rate": 8.219007271552984e-06,
"loss": 0.4825,
"step": 681
},
{
"epoch": 1.71,
"learning_rate": 8.192318119915644e-06,
"loss": 0.471,
"step": 682
},
{
"epoch": 1.71,
"learning_rate": 8.16564227295621e-06,
"loss": 0.4363,
"step": 683
},
{
"epoch": 1.72,
"learning_rate": 8.138979927010964e-06,
"loss": 0.4634,
"step": 684
},
{
"epoch": 1.72,
"learning_rate": 8.112331278316824e-06,
"loss": 0.434,
"step": 685
},
{
"epoch": 1.72,
"learning_rate": 8.085696523009907e-06,
"loss": 0.4708,
"step": 686
},
{
"epoch": 1.72,
"learning_rate": 8.059075857124056e-06,
"loss": 0.427,
"step": 687
},
{
"epoch": 1.73,
"learning_rate": 8.032469476589424e-06,
"loss": 0.4308,
"step": 688
},
{
"epoch": 1.73,
"learning_rate": 8.005877577231027e-06,
"loss": 0.4595,
"step": 689
},
{
"epoch": 1.73,
"learning_rate": 7.979300354767282e-06,
"loss": 0.4503,
"step": 690
},
{
"epoch": 1.73,
"learning_rate": 7.952738004808603e-06,
"loss": 0.4721,
"step": 691
},
{
"epoch": 1.74,
"learning_rate": 7.926190722855931e-06,
"loss": 0.4395,
"step": 692
},
{
"epoch": 1.74,
"learning_rate": 7.899658704299302e-06,
"loss": 0.4606,
"step": 693
},
{
"epoch": 1.74,
"learning_rate": 7.873142144416423e-06,
"loss": 0.4542,
"step": 694
},
{
"epoch": 1.74,
"learning_rate": 7.846641238371212e-06,
"loss": 0.4499,
"step": 695
},
{
"epoch": 1.75,
"learning_rate": 7.82015618121238e-06,
"loss": 0.4525,
"step": 696
},
{
"epoch": 1.75,
"learning_rate": 7.79368716787199e-06,
"loss": 0.4447,
"step": 697
},
{
"epoch": 1.75,
"learning_rate": 7.767234393164017e-06,
"loss": 0.4499,
"step": 698
},
{
"epoch": 1.75,
"learning_rate": 7.740798051782922e-06,
"loss": 0.431,
"step": 699
},
{
"epoch": 1.76,
"learning_rate": 7.71437833830222e-06,
"loss": 0.4185,
"step": 700
},
{
"epoch": 1.76,
"learning_rate": 7.687975447173025e-06,
"loss": 0.4403,
"step": 701
},
{
"epoch": 1.76,
"learning_rate": 7.66158957272266e-06,
"loss": 0.488,
"step": 702
},
{
"epoch": 1.76,
"learning_rate": 7.635220909153192e-06,
"loss": 0.4453,
"step": 703
},
{
"epoch": 1.77,
"learning_rate": 7.608869650540014e-06,
"loss": 0.4522,
"step": 704
},
{
"epoch": 1.77,
"learning_rate": 7.582535990830416e-06,
"loss": 0.455,
"step": 705
},
{
"epoch": 1.77,
"learning_rate": 7.556220123842173e-06,
"loss": 0.4731,
"step": 706
},
{
"epoch": 1.77,
"learning_rate": 7.529922243262085e-06,
"loss": 0.4664,
"step": 707
},
{
"epoch": 1.78,
"learning_rate": 7.503642542644581e-06,
"loss": 0.447,
"step": 708
},
{
"epoch": 1.78,
"learning_rate": 7.47738121541028e-06,
"loss": 0.4661,
"step": 709
},
{
"epoch": 1.78,
"learning_rate": 7.451138454844575e-06,
"loss": 0.4714,
"step": 710
},
{
"epoch": 1.78,
"learning_rate": 7.424914454096211e-06,
"loss": 0.4797,
"step": 711
},
{
"epoch": 1.79,
"learning_rate": 7.398709406175846e-06,
"loss": 0.4498,
"step": 712
},
{
"epoch": 1.79,
"learning_rate": 7.372523503954654e-06,
"loss": 0.4499,
"step": 713
},
{
"epoch": 1.79,
"learning_rate": 7.346356940162895e-06,
"loss": 0.4708,
"step": 714
},
{
"epoch": 1.79,
"learning_rate": 7.320209907388491e-06,
"loss": 0.4472,
"step": 715
},
{
"epoch": 1.8,
"learning_rate": 7.294082598075619e-06,
"loss": 0.4569,
"step": 716
},
{
"epoch": 1.8,
"learning_rate": 7.267975204523294e-06,
"loss": 0.4943,
"step": 717
},
{
"epoch": 1.8,
"learning_rate": 7.241887918883932e-06,
"loss": 0.4533,
"step": 718
},
{
"epoch": 1.8,
"learning_rate": 7.215820933161976e-06,
"loss": 0.4635,
"step": 719
},
{
"epoch": 1.81,
"learning_rate": 7.189774439212442e-06,
"loss": 0.449,
"step": 720
},
{
"epoch": 1.81,
"learning_rate": 7.163748628739533e-06,
"loss": 0.4784,
"step": 721
},
{
"epoch": 1.81,
"learning_rate": 7.137743693295225e-06,
"loss": 0.4468,
"step": 722
},
{
"epoch": 1.81,
"learning_rate": 7.11175982427784e-06,
"loss": 0.4313,
"step": 723
},
{
"epoch": 1.82,
"learning_rate": 7.0857972129306584e-06,
"loss": 0.463,
"step": 724
},
{
"epoch": 1.82,
"learning_rate": 7.059856050340501e-06,
"loss": 0.4672,
"step": 725
},
{
"epoch": 1.82,
"learning_rate": 7.033936527436318e-06,
"loss": 0.4391,
"step": 726
},
{
"epoch": 1.82,
"learning_rate": 7.0080388349877985e-06,
"loss": 0.4746,
"step": 727
},
{
"epoch": 1.83,
"learning_rate": 6.982163163603957e-06,
"loss": 0.4508,
"step": 728
},
{
"epoch": 1.83,
"learning_rate": 6.95630970373172e-06,
"loss": 0.4631,
"step": 729
},
{
"epoch": 1.83,
"learning_rate": 6.930478645654554e-06,
"loss": 0.4577,
"step": 730
},
{
"epoch": 1.83,
"learning_rate": 6.90467017949103e-06,
"loss": 0.4524,
"step": 731
},
{
"epoch": 1.84,
"learning_rate": 6.878884495193448e-06,
"loss": 0.4169,
"step": 732
},
{
"epoch": 1.84,
"learning_rate": 6.853121782546434e-06,
"loss": 0.4515,
"step": 733
},
{
"epoch": 1.84,
"learning_rate": 6.827382231165531e-06,
"loss": 0.4754,
"step": 734
},
{
"epoch": 1.84,
"learning_rate": 6.801666030495826e-06,
"loss": 0.4598,
"step": 735
},
{
"epoch": 1.85,
"learning_rate": 6.775973369810539e-06,
"loss": 0.4417,
"step": 736
},
{
"epoch": 1.85,
"learning_rate": 6.7503044382096235e-06,
"loss": 0.4506,
"step": 737
},
{
"epoch": 1.85,
"learning_rate": 6.724659424618401e-06,
"loss": 0.4624,
"step": 738
},
{
"epoch": 1.85,
"learning_rate": 6.699038517786149e-06,
"loss": 0.4722,
"step": 739
},
{
"epoch": 1.86,
"learning_rate": 6.673441906284708e-06,
"loss": 0.4403,
"step": 740
},
{
"epoch": 1.86,
"learning_rate": 6.6478697785071125e-06,
"loss": 0.4438,
"step": 741
},
{
"epoch": 1.86,
"learning_rate": 6.6223223226661994e-06,
"loss": 0.4689,
"step": 742
},
{
"epoch": 1.86,
"learning_rate": 6.596799726793204e-06,
"loss": 0.4471,
"step": 743
},
{
"epoch": 1.87,
"learning_rate": 6.571302178736404e-06,
"loss": 0.4659,
"step": 744
},
{
"epoch": 1.87,
"learning_rate": 6.545829866159711e-06,
"loss": 0.4463,
"step": 745
},
{
"epoch": 1.87,
"learning_rate": 6.520382976541313e-06,
"loss": 0.4597,
"step": 746
},
{
"epoch": 1.87,
"learning_rate": 6.49496169717228e-06,
"loss": 0.4371,
"step": 747
},
{
"epoch": 1.88,
"learning_rate": 6.4695662151551805e-06,
"loss": 0.4493,
"step": 748
},
{
"epoch": 1.88,
"learning_rate": 6.444196717402721e-06,
"loss": 0.4719,
"step": 749
},
{
"epoch": 1.88,
"learning_rate": 6.418853390636363e-06,
"loss": 0.44,
"step": 750
},
{
"epoch": 1.88,
"learning_rate": 6.393536421384938e-06,
"loss": 0.4621,
"step": 751
},
{
"epoch": 1.89,
"learning_rate": 6.368245995983293e-06,
"loss": 0.44,
"step": 752
},
{
"epoch": 1.89,
"learning_rate": 6.342982300570913e-06,
"loss": 0.4435,
"step": 753
},
{
"epoch": 1.89,
"learning_rate": 6.31774552109053e-06,
"loss": 0.4284,
"step": 754
},
{
"epoch": 1.89,
"learning_rate": 6.292535843286795e-06,
"loss": 0.4513,
"step": 755
},
{
"epoch": 1.9,
"learning_rate": 6.267353452704876e-06,
"loss": 0.4557,
"step": 756
},
{
"epoch": 1.9,
"learning_rate": 6.2421985346891055e-06,
"loss": 0.4662,
"step": 757
},
{
"epoch": 1.9,
"learning_rate": 6.217071274381623e-06,
"loss": 0.4904,
"step": 758
},
{
"epoch": 1.9,
"learning_rate": 6.191971856720997e-06,
"loss": 0.4403,
"step": 759
},
{
"epoch": 1.91,
"learning_rate": 6.166900466440871e-06,
"loss": 0.4368,
"step": 760
},
{
"epoch": 1.91,
"learning_rate": 6.141857288068621e-06,
"loss": 0.4473,
"step": 761
},
{
"epoch": 1.91,
"learning_rate": 6.116842505923955e-06,
"loss": 0.4411,
"step": 762
},
{
"epoch": 1.91,
"learning_rate": 6.091856304117606e-06,
"loss": 0.4645,
"step": 763
},
{
"epoch": 1.92,
"learning_rate": 6.066898866549943e-06,
"loss": 0.444,
"step": 764
},
{
"epoch": 1.92,
"learning_rate": 6.041970376909624e-06,
"loss": 0.4648,
"step": 765
},
{
"epoch": 1.92,
"learning_rate": 6.0170710186722605e-06,
"loss": 0.4577,
"step": 766
},
{
"epoch": 1.92,
"learning_rate": 5.9922009750990425e-06,
"loss": 0.4638,
"step": 767
},
{
"epoch": 1.93,
"learning_rate": 5.967360429235407e-06,
"loss": 0.4412,
"step": 768
},
{
"epoch": 1.93,
"learning_rate": 5.9425495639096894e-06,
"loss": 0.4563,
"step": 769
},
{
"epoch": 1.93,
"learning_rate": 5.917768561731763e-06,
"loss": 0.4591,
"step": 770
},
{
"epoch": 1.93,
"learning_rate": 5.893017605091718e-06,
"loss": 0.4651,
"step": 771
},
{
"epoch": 1.94,
"learning_rate": 5.868296876158501e-06,
"loss": 0.4725,
"step": 772
},
{
"epoch": 1.94,
"learning_rate": 5.843606556878581e-06,
"loss": 0.4274,
"step": 773
},
{
"epoch": 1.94,
"learning_rate": 5.8189468289746075e-06,
"loss": 0.4664,
"step": 774
},
{
"epoch": 1.94,
"learning_rate": 5.7943178739440865e-06,
"loss": 0.4521,
"step": 775
},
{
"epoch": 1.95,
"learning_rate": 5.769719873058015e-06,
"loss": 0.4475,
"step": 776
},
{
"epoch": 1.95,
"learning_rate": 5.745153007359578e-06,
"loss": 0.4588,
"step": 777
},
{
"epoch": 1.95,
"learning_rate": 5.720617457662801e-06,
"loss": 0.4552,
"step": 778
},
{
"epoch": 1.95,
"learning_rate": 5.696113404551218e-06,
"loss": 0.4625,
"step": 779
},
{
"epoch": 1.96,
"learning_rate": 5.671641028376547e-06,
"loss": 0.4396,
"step": 780
},
{
"epoch": 1.96,
"learning_rate": 5.647200509257364e-06,
"loss": 0.4702,
"step": 781
},
{
"epoch": 1.96,
"learning_rate": 5.622792027077773e-06,
"loss": 0.4374,
"step": 782
},
{
"epoch": 1.96,
"learning_rate": 5.598415761486085e-06,
"loss": 0.4276,
"step": 783
},
{
"epoch": 1.97,
"learning_rate": 5.57407189189348e-06,
"loss": 0.4349,
"step": 784
},
{
"epoch": 1.97,
"learning_rate": 5.549760597472731e-06,
"loss": 0.4384,
"step": 785
},
{
"epoch": 1.97,
"learning_rate": 5.525482057156833e-06,
"loss": 0.4318,
"step": 786
},
{
"epoch": 1.97,
"learning_rate": 5.501236449637701e-06,
"loss": 0.4805,
"step": 787
},
{
"epoch": 1.98,
"learning_rate": 5.4770239533648885e-06,
"loss": 0.4556,
"step": 788
},
{
"epoch": 1.98,
"learning_rate": 5.452844746544234e-06,
"loss": 0.4552,
"step": 789
},
{
"epoch": 1.98,
"learning_rate": 5.4286990071365516e-06,
"loss": 0.4607,
"step": 790
},
{
"epoch": 1.98,
"learning_rate": 5.40458691285635e-06,
"loss": 0.4714,
"step": 791
},
{
"epoch": 1.99,
"learning_rate": 5.380508641170499e-06,
"loss": 0.4227,
"step": 792
},
{
"epoch": 1.99,
"learning_rate": 5.356464369296934e-06,
"loss": 0.4426,
"step": 793
},
{
"epoch": 1.99,
"learning_rate": 5.332454274203349e-06,
"loss": 0.4671,
"step": 794
},
{
"epoch": 1.99,
"learning_rate": 5.3084785326058925e-06,
"loss": 0.4661,
"step": 795
},
{
"epoch": 2.0,
"learning_rate": 5.2845373209678705e-06,
"loss": 0.4591,
"step": 796
},
{
"epoch": 2.0,
"learning_rate": 5.260630815498444e-06,
"loss": 0.4552,
"step": 797
},
{
"epoch": 2.0,
"learning_rate": 5.236759192151336e-06,
"loss": 0.4715,
"step": 798
},
{
"epoch": 2.01,
"learning_rate": 5.212922626623533e-06,
"loss": 0.4214,
"step": 799
},
{
"epoch": 2.01,
"learning_rate": 5.189121294353994e-06,
"loss": 0.4559,
"step": 800
},
{
"epoch": 2.01,
"learning_rate": 5.165355370522358e-06,
"loss": 0.447,
"step": 801
},
{
"epoch": 2.01,
"learning_rate": 5.141625030047659e-06,
"loss": 0.416,
"step": 802
},
{
"epoch": 2.02,
"learning_rate": 5.11793044758702e-06,
"loss": 0.4196,
"step": 803
},
{
"epoch": 2.02,
"learning_rate": 5.094271797534404e-06,
"loss": 0.4223,
"step": 804
},
{
"epoch": 2.02,
"learning_rate": 5.070649254019298e-06,
"loss": 0.4361,
"step": 805
},
{
"epoch": 2.02,
"learning_rate": 5.047062990905436e-06,
"loss": 0.457,
"step": 806
},
{
"epoch": 2.03,
"learning_rate": 5.02351318178953e-06,
"loss": 0.4447,
"step": 807
},
{
"epoch": 2.03,
"learning_rate": 5.000000000000003e-06,
"loss": 0.4237,
"step": 808
},
{
"epoch": 2.03,
"learning_rate": 4.97652361859567e-06,
"loss": 0.4086,
"step": 809
},
{
"epoch": 2.03,
"learning_rate": 4.953084210364508e-06,
"loss": 0.4356,
"step": 810
},
{
"epoch": 2.04,
"learning_rate": 4.92968194782238e-06,
"loss": 0.4553,
"step": 811
},
{
"epoch": 2.04,
"learning_rate": 4.906317003211728e-06,
"loss": 0.4326,
"step": 812
},
{
"epoch": 2.04,
"learning_rate": 4.882989548500349e-06,
"loss": 0.4335,
"step": 813
},
{
"epoch": 2.04,
"learning_rate": 4.859699755380106e-06,
"loss": 0.4608,
"step": 814
},
{
"epoch": 2.05,
"learning_rate": 4.836447795265673e-06,
"loss": 0.4318,
"step": 815
},
{
"epoch": 2.05,
"learning_rate": 4.813233839293265e-06,
"loss": 0.4166,
"step": 816
},
{
"epoch": 2.05,
"learning_rate": 4.7900580583193875e-06,
"loss": 0.4486,
"step": 817
},
{
"epoch": 2.05,
"learning_rate": 4.766920622919575e-06,
"loss": 0.4546,
"step": 818
},
{
"epoch": 2.06,
"learning_rate": 4.743821703387137e-06,
"loss": 0.4338,
"step": 819
},
{
"epoch": 2.06,
"learning_rate": 4.7207614697318895e-06,
"loss": 0.4265,
"step": 820
},
{
"epoch": 2.06,
"learning_rate": 4.69774009167894e-06,
"loss": 0.4552,
"step": 821
},
{
"epoch": 2.06,
"learning_rate": 4.674757738667405e-06,
"loss": 0.4456,
"step": 822
},
{
"epoch": 2.07,
"learning_rate": 4.651814579849161e-06,
"loss": 0.4628,
"step": 823
},
{
"epoch": 2.07,
"learning_rate": 4.6289107840876366e-06,
"loss": 0.4361,
"step": 824
},
{
"epoch": 2.07,
"learning_rate": 4.606046519956534e-06,
"loss": 0.4449,
"step": 825
},
{
"epoch": 2.07,
"learning_rate": 4.5832219557385896e-06,
"loss": 0.4208,
"step": 826
},
{
"epoch": 2.08,
"learning_rate": 4.560437259424359e-06,
"loss": 0.41,
"step": 827
},
{
"epoch": 2.08,
"learning_rate": 4.537692598710962e-06,
"loss": 0.4377,
"step": 828
},
{
"epoch": 2.08,
"learning_rate": 4.514988141000853e-06,
"loss": 0.4337,
"step": 829
},
{
"epoch": 2.08,
"learning_rate": 4.492324053400592e-06,
"loss": 0.4464,
"step": 830
},
{
"epoch": 2.09,
"learning_rate": 4.469700502719607e-06,
"loss": 0.4314,
"step": 831
},
{
"epoch": 2.09,
"learning_rate": 4.447117655468978e-06,
"loss": 0.4217,
"step": 832
},
{
"epoch": 2.09,
"learning_rate": 4.4245756778601955e-06,
"loss": 0.453,
"step": 833
},
{
"epoch": 2.09,
"learning_rate": 4.402074735803955e-06,
"loss": 0.4402,
"step": 834
},
{
"epoch": 2.1,
"learning_rate": 4.379614994908922e-06,
"loss": 0.4312,
"step": 835
},
{
"epoch": 2.1,
"learning_rate": 4.35719662048052e-06,
"loss": 0.4549,
"step": 836
},
{
"epoch": 2.1,
"learning_rate": 4.334819777519712e-06,
"loss": 0.4613,
"step": 837
},
{
"epoch": 2.1,
"learning_rate": 4.312484630721786e-06,
"loss": 0.4421,
"step": 838
},
{
"epoch": 2.11,
"learning_rate": 4.290191344475143e-06,
"loss": 0.4246,
"step": 839
},
{
"epoch": 2.11,
"learning_rate": 4.267940082860088e-06,
"loss": 0.4494,
"step": 840
},
{
"epoch": 2.11,
"learning_rate": 4.245731009647624e-06,
"loss": 0.4474,
"step": 841
},
{
"epoch": 2.11,
"learning_rate": 4.223564288298233e-06,
"loss": 0.4515,
"step": 842
},
{
"epoch": 2.12,
"learning_rate": 4.201440081960693e-06,
"loss": 0.437,
"step": 843
},
{
"epoch": 2.12,
"learning_rate": 4.179358553470876e-06,
"loss": 0.4233,
"step": 844
},
{
"epoch": 2.12,
"learning_rate": 4.157319865350523e-06,
"loss": 0.4595,
"step": 845
},
{
"epoch": 2.12,
"learning_rate": 4.135324179806079e-06,
"loss": 0.4331,
"step": 846
},
{
"epoch": 2.13,
"learning_rate": 4.113371658727489e-06,
"loss": 0.436,
"step": 847
},
{
"epoch": 2.13,
"learning_rate": 4.091462463686995e-06,
"loss": 0.4358,
"step": 848
},
{
"epoch": 2.13,
"learning_rate": 4.06959675593796e-06,
"loss": 0.4342,
"step": 849
},
{
"epoch": 2.13,
"learning_rate": 4.047774696413679e-06,
"loss": 0.4286,
"step": 850
},
{
"epoch": 2.14,
"learning_rate": 4.02599644572619e-06,
"loss": 0.4411,
"step": 851
},
{
"epoch": 2.14,
"learning_rate": 4.004262164165098e-06,
"loss": 0.4251,
"step": 852
},
{
"epoch": 2.14,
"learning_rate": 3.982572011696388e-06,
"loss": 0.4525,
"step": 853
},
{
"epoch": 2.14,
"learning_rate": 3.960926147961253e-06,
"loss": 0.4136,
"step": 854
},
{
"epoch": 2.15,
"learning_rate": 3.939324732274924e-06,
"loss": 0.4538,
"step": 855
},
{
"epoch": 2.15,
"learning_rate": 3.917767923625471e-06,
"loss": 0.4563,
"step": 856
},
{
"epoch": 2.15,
"learning_rate": 3.896255880672677e-06,
"loss": 0.4351,
"step": 857
},
{
"epoch": 2.15,
"learning_rate": 3.874788761746836e-06,
"loss": 0.4475,
"step": 858
},
{
"epoch": 2.16,
"learning_rate": 3.853366724847588e-06,
"loss": 0.4195,
"step": 859
},
{
"epoch": 2.16,
"learning_rate": 3.831989927642784e-06,
"loss": 0.4466,
"step": 860
},
{
"epoch": 2.16,
"learning_rate": 3.810658527467298e-06,
"loss": 0.4471,
"step": 861
},
{
"epoch": 2.16,
"learning_rate": 3.7893726813218734e-06,
"loss": 0.462,
"step": 862
},
{
"epoch": 2.17,
"learning_rate": 3.76813254587198e-06,
"loss": 0.4397,
"step": 863
},
{
"epoch": 2.17,
"learning_rate": 3.74693827744665e-06,
"loss": 0.4181,
"step": 864
},
{
"epoch": 2.17,
"learning_rate": 3.725790032037334e-06,
"loss": 0.4489,
"step": 865
},
{
"epoch": 2.17,
"learning_rate": 3.704687965296746e-06,
"loss": 0.4326,
"step": 866
},
{
"epoch": 2.18,
"learning_rate": 3.6836322325377226e-06,
"loss": 0.4307,
"step": 867
},
{
"epoch": 2.18,
"learning_rate": 3.6626229887320807e-06,
"loss": 0.433,
"step": 868
},
{
"epoch": 2.18,
"learning_rate": 3.6416603885094726e-06,
"loss": 0.4431,
"step": 869
},
{
"epoch": 2.18,
"learning_rate": 3.6207445861562497e-06,
"loss": 0.4604,
"step": 870
},
{
"epoch": 2.19,
"learning_rate": 3.59987573561433e-06,
"loss": 0.439,
"step": 871
},
{
"epoch": 2.19,
"learning_rate": 3.5790539904800605e-06,
"loss": 0.4435,
"step": 872
},
{
"epoch": 2.19,
"learning_rate": 3.5582795040030905e-06,
"loss": 0.4261,
"step": 873
},
{
"epoch": 2.19,
"learning_rate": 3.5375524290852394e-06,
"loss": 0.4249,
"step": 874
},
{
"epoch": 2.2,
"learning_rate": 3.516872918279377e-06,
"loss": 0.4495,
"step": 875
},
{
"epoch": 2.2,
"learning_rate": 3.4962411237882945e-06,
"loss": 0.424,
"step": 876
},
{
"epoch": 2.2,
"learning_rate": 3.4756571974635935e-06,
"loss": 0.4412,
"step": 877
},
{
"epoch": 2.2,
"learning_rate": 3.4551212908045497e-06,
"loss": 0.4168,
"step": 878
},
{
"epoch": 2.21,
"learning_rate": 3.4346335549570186e-06,
"loss": 0.4486,
"step": 879
},
{
"epoch": 2.21,
"learning_rate": 3.414194140712325e-06,
"loss": 0.4647,
"step": 880
},
{
"epoch": 2.21,
"learning_rate": 3.3938031985061216e-06,
"loss": 0.4578,
"step": 881
},
{
"epoch": 2.21,
"learning_rate": 3.373460878417315e-06,
"loss": 0.4143,
"step": 882
},
{
"epoch": 2.22,
"learning_rate": 3.3531673301669563e-06,
"loss": 0.4639,
"step": 883
},
{
"epoch": 2.22,
"learning_rate": 3.3329227031171165e-06,
"loss": 0.4357,
"step": 884
},
{
"epoch": 2.22,
"learning_rate": 3.312727146269812e-06,
"loss": 0.452,
"step": 885
},
{
"epoch": 2.22,
"learning_rate": 3.292580808265897e-06,
"loss": 0.4261,
"step": 886
},
{
"epoch": 2.23,
"learning_rate": 3.2724838373839716e-06,
"loss": 0.4187,
"step": 887
},
{
"epoch": 2.23,
"learning_rate": 3.252436381539291e-06,
"loss": 0.4172,
"step": 888
},
{
"epoch": 2.23,
"learning_rate": 3.2324385882826726e-06,
"loss": 0.4384,
"step": 889
},
{
"epoch": 2.23,
"learning_rate": 3.2124906047994165e-06,
"loss": 0.4445,
"step": 890
},
{
"epoch": 2.24,
"learning_rate": 3.192592577908221e-06,
"loss": 0.4514,
"step": 891
},
{
"epoch": 2.24,
"learning_rate": 3.1727446540600882e-06,
"loss": 0.4456,
"step": 892
},
{
"epoch": 2.24,
"learning_rate": 3.1529469793372735e-06,
"loss": 0.4059,
"step": 893
},
{
"epoch": 2.24,
"learning_rate": 3.1331996994521917e-06,
"loss": 0.4492,
"step": 894
},
{
"epoch": 2.25,
"learning_rate": 3.1135029597463328e-06,
"loss": 0.4528,
"step": 895
},
{
"epoch": 2.25,
"learning_rate": 3.0938569051892276e-06,
"loss": 0.4237,
"step": 896
},
{
"epoch": 2.25,
"learning_rate": 3.0742616803773518e-06,
"loss": 0.4453,
"step": 897
},
{
"epoch": 2.25,
"learning_rate": 3.054717429533063e-06,
"loss": 0.4262,
"step": 898
},
{
"epoch": 2.26,
"learning_rate": 3.0352242965035562e-06,
"loss": 0.4651,
"step": 899
},
{
"epoch": 2.26,
"learning_rate": 3.015782424759792e-06,
"loss": 0.4118,
"step": 900
},
{
"epoch": 2.26,
"learning_rate": 2.9963919573954447e-06,
"loss": 0.4507,
"step": 901
},
{
"epoch": 2.26,
"learning_rate": 2.977053037125849e-06,
"loss": 0.4577,
"step": 902
},
{
"epoch": 2.27,
"learning_rate": 2.9577658062869465e-06,
"loss": 0.4234,
"step": 903
},
{
"epoch": 2.27,
"learning_rate": 2.9385304068342414e-06,
"loss": 0.4484,
"step": 904
},
{
"epoch": 2.27,
"learning_rate": 2.9193469803417574e-06,
"loss": 0.4325,
"step": 905
},
{
"epoch": 2.27,
"learning_rate": 2.900215668000991e-06,
"loss": 0.4432,
"step": 906
},
{
"epoch": 2.28,
"learning_rate": 2.8811366106198734e-06,
"loss": 0.4255,
"step": 907
},
{
"epoch": 2.28,
"learning_rate": 2.8621099486217376e-06,
"loss": 0.4324,
"step": 908
},
{
"epoch": 2.28,
"learning_rate": 2.843135822044283e-06,
"loss": 0.45,
"step": 909
},
{
"epoch": 2.28,
"learning_rate": 2.8242143705385417e-06,
"loss": 0.439,
"step": 910
},
{
"epoch": 2.29,
"learning_rate": 2.8053457333678535e-06,
"loss": 0.447,
"step": 911
},
{
"epoch": 2.29,
"learning_rate": 2.786530049406844e-06,
"loss": 0.4341,
"step": 912
},
{
"epoch": 2.29,
"learning_rate": 2.767767457140399e-06,
"loss": 0.4495,
"step": 913
},
{
"epoch": 2.29,
"learning_rate": 2.7490580946626355e-06,
"loss": 0.4458,
"step": 914
},
{
"epoch": 2.3,
"learning_rate": 2.730402099675904e-06,
"loss": 0.4166,
"step": 915
},
{
"epoch": 2.3,
"learning_rate": 2.7117996094897737e-06,
"loss": 0.4534,
"step": 916
},
{
"epoch": 2.3,
"learning_rate": 2.6932507610199964e-06,
"loss": 0.4461,
"step": 917
},
{
"epoch": 2.3,
"learning_rate": 2.674755690787526e-06,
"loss": 0.4343,
"step": 918
},
{
"epoch": 2.31,
"learning_rate": 2.6563145349175136e-06,
"loss": 0.4561,
"step": 919
},
{
"epoch": 2.31,
"learning_rate": 2.637927429138276e-06,
"loss": 0.4239,
"step": 920
},
{
"epoch": 2.31,
"learning_rate": 2.6195945087803345e-06,
"loss": 0.4165,
"step": 921
},
{
"epoch": 2.31,
"learning_rate": 2.6013159087753927e-06,
"loss": 0.4608,
"step": 922
},
{
"epoch": 2.32,
"learning_rate": 2.5830917636553563e-06,
"loss": 0.4165,
"step": 923
},
{
"epoch": 2.32,
"learning_rate": 2.564922207551337e-06,
"loss": 0.4266,
"step": 924
},
{
"epoch": 2.32,
"learning_rate": 2.546807374192668e-06,
"loss": 0.4337,
"step": 925
},
{
"epoch": 2.32,
"learning_rate": 2.5287473969059174e-06,
"loss": 0.4578,
"step": 926
},
{
"epoch": 2.33,
"learning_rate": 2.510742408613912e-06,
"loss": 0.4525,
"step": 927
},
{
"epoch": 2.33,
"learning_rate": 2.4927925418347455e-06,
"loss": 0.456,
"step": 928
},
{
"epoch": 2.33,
"learning_rate": 2.474897928680827e-06,
"loss": 0.4608,
"step": 929
},
{
"epoch": 2.33,
"learning_rate": 2.4570587008578896e-06,
"loss": 0.4186,
"step": 930
},
{
"epoch": 2.34,
"learning_rate": 2.4392749896640157e-06,
"loss": 0.4274,
"step": 931
},
{
"epoch": 2.34,
"learning_rate": 2.421546925988697e-06,
"loss": 0.4537,
"step": 932
},
{
"epoch": 2.34,
"learning_rate": 2.4038746403118495e-06,
"loss": 0.4316,
"step": 933
},
{
"epoch": 2.34,
"learning_rate": 2.386258262702851e-06,
"loss": 0.4073,
"step": 934
},
{
"epoch": 2.35,
"learning_rate": 2.3686979228195994e-06,
"loss": 0.4453,
"step": 935
},
{
"epoch": 2.35,
"learning_rate": 2.351193749907551e-06,
"loss": 0.4475,
"step": 936
},
{
"epoch": 2.35,
"learning_rate": 2.333745872798767e-06,
"loss": 0.4456,
"step": 937
},
{
"epoch": 2.35,
"learning_rate": 2.3163544199109656e-06,
"loss": 0.4242,
"step": 938
},
{
"epoch": 2.36,
"learning_rate": 2.2990195192465803e-06,
"loss": 0.4436,
"step": 939
},
{
"epoch": 2.36,
"learning_rate": 2.281741298391815e-06,
"loss": 0.4313,
"step": 940
},
{
"epoch": 2.36,
"learning_rate": 2.2645198845157078e-06,
"loss": 0.4424,
"step": 941
},
{
"epoch": 2.36,
"learning_rate": 2.2473554043691915e-06,
"loss": 0.4371,
"step": 942
},
{
"epoch": 2.37,
"learning_rate": 2.2302479842841608e-06,
"loss": 0.4358,
"step": 943
},
{
"epoch": 2.37,
"learning_rate": 2.2131977501725465e-06,
"loss": 0.4212,
"step": 944
},
{
"epoch": 2.37,
"learning_rate": 2.1962048275253845e-06,
"loss": 0.4257,
"step": 945
},
{
"epoch": 2.37,
"learning_rate": 2.179269341411896e-06,
"loss": 0.4239,
"step": 946
},
{
"epoch": 2.38,
"learning_rate": 2.1623914164785618e-06,
"loss": 0.4313,
"step": 947
},
{
"epoch": 2.38,
"learning_rate": 2.1455711769482113e-06,
"loss": 0.4238,
"step": 948
},
{
"epoch": 2.38,
"learning_rate": 2.1288087466191053e-06,
"loss": 0.4444,
"step": 949
},
{
"epoch": 2.38,
"learning_rate": 2.1121042488640166e-06,
"loss": 0.43,
"step": 950
},
{
"epoch": 2.39,
"learning_rate": 2.095457806629335e-06,
"loss": 0.4468,
"step": 951
},
{
"epoch": 2.39,
"learning_rate": 2.0788695424341674e-06,
"loss": 0.4574,
"step": 952
},
{
"epoch": 2.39,
"learning_rate": 2.062339578369408e-06,
"loss": 0.4425,
"step": 953
},
{
"epoch": 2.39,
"learning_rate": 2.045868036096864e-06,
"loss": 0.4439,
"step": 954
},
{
"epoch": 2.4,
"learning_rate": 2.0294550368483668e-06,
"loss": 0.4526,
"step": 955
},
{
"epoch": 2.4,
"learning_rate": 2.013100701424844e-06,
"loss": 0.4477,
"step": 956
},
{
"epoch": 2.4,
"learning_rate": 1.9968051501954676e-06,
"loss": 0.4527,
"step": 957
},
{
"epoch": 2.4,
"learning_rate": 1.9805685030967527e-06,
"loss": 0.4277,
"step": 958
},
{
"epoch": 2.41,
"learning_rate": 1.964390879631669e-06,
"loss": 0.4282,
"step": 959
},
{
"epoch": 2.41,
"learning_rate": 1.9482723988687734e-06,
"loss": 0.4335,
"step": 960
},
{
"epoch": 2.41,
"learning_rate": 1.932213179441327e-06,
"loss": 0.4262,
"step": 961
},
{
"epoch": 2.41,
"learning_rate": 1.916213339546421e-06,
"loss": 0.4376,
"step": 962
},
{
"epoch": 2.42,
"learning_rate": 1.9002729969441113e-06,
"loss": 0.4499,
"step": 963
},
{
"epoch": 2.42,
"learning_rate": 1.8843922689565418e-06,
"loss": 0.4427,
"step": 964
},
{
"epoch": 2.42,
"learning_rate": 1.8685712724671e-06,
"loss": 0.4345,
"step": 965
},
{
"epoch": 2.42,
"learning_rate": 1.8528101239195394e-06,
"loss": 0.4446,
"step": 966
},
{
"epoch": 2.43,
"learning_rate": 1.8371089393171193e-06,
"loss": 0.4304,
"step": 967
},
{
"epoch": 2.43,
"learning_rate": 1.8214678342217774e-06,
"loss": 0.4759,
"step": 968
},
{
"epoch": 2.43,
"learning_rate": 1.8058869237532506e-06,
"loss": 0.4293,
"step": 969
},
{
"epoch": 2.43,
"learning_rate": 1.790366322588236e-06,
"loss": 0.4569,
"step": 970
},
{
"epoch": 2.44,
"learning_rate": 1.7749061449595562e-06,
"loss": 0.4297,
"step": 971
},
{
"epoch": 2.44,
"learning_rate": 1.7595065046553085e-06,
"loss": 0.4496,
"step": 972
},
{
"epoch": 2.44,
"learning_rate": 1.7441675150180337e-06,
"loss": 0.4264,
"step": 973
},
{
"epoch": 2.44,
"learning_rate": 1.728889288943877e-06,
"loss": 0.4235,
"step": 974
},
{
"epoch": 2.45,
"learning_rate": 1.713671938881758e-06,
"loss": 0.4289,
"step": 975
},
{
"epoch": 2.45,
"learning_rate": 1.6985155768325456e-06,
"loss": 0.4397,
"step": 976
},
{
"epoch": 2.45,
"learning_rate": 1.6834203143482341e-06,
"loss": 0.4667,
"step": 977
},
{
"epoch": 2.45,
"learning_rate": 1.6683862625311165e-06,
"loss": 0.4299,
"step": 978
},
{
"epoch": 2.46,
"learning_rate": 1.6534135320329736e-06,
"loss": 0.4399,
"step": 979
},
{
"epoch": 2.46,
"learning_rate": 1.6385022330542533e-06,
"loss": 0.4444,
"step": 980
},
{
"epoch": 2.46,
"learning_rate": 1.623652475343268e-06,
"loss": 0.452,
"step": 981
},
{
"epoch": 2.46,
"learning_rate": 1.6088643681953752e-06,
"loss": 0.488,
"step": 982
},
{
"epoch": 2.47,
"learning_rate": 1.5941380204521851e-06,
"loss": 0.4447,
"step": 983
},
{
"epoch": 2.47,
"learning_rate": 1.579473540500751e-06,
"loss": 0.4357,
"step": 984
},
{
"epoch": 2.47,
"learning_rate": 1.564871036272777e-06,
"loss": 0.4096,
"step": 985
},
{
"epoch": 2.47,
"learning_rate": 1.5503306152438146e-06,
"loss": 0.4476,
"step": 986
},
{
"epoch": 2.48,
"learning_rate": 1.5358523844324834e-06,
"loss": 0.4273,
"step": 987
},
{
"epoch": 2.48,
"learning_rate": 1.5214364503996838e-06,
"loss": 0.422,
"step": 988
},
{
"epoch": 2.48,
"learning_rate": 1.5070829192477943e-06,
"loss": 0.4631,
"step": 989
},
{
"epoch": 2.48,
"learning_rate": 1.4927918966199095e-06,
"loss": 0.4371,
"step": 990
},
{
"epoch": 2.49,
"learning_rate": 1.478563487699065e-06,
"loss": 0.4291,
"step": 991
},
{
"epoch": 2.49,
"learning_rate": 1.4643977972074386e-06,
"loss": 0.4618,
"step": 992
},
{
"epoch": 2.49,
"learning_rate": 1.4502949294056056e-06,
"loss": 0.4444,
"step": 993
},
{
"epoch": 2.49,
"learning_rate": 1.4362549880917609e-06,
"loss": 0.4543,
"step": 994
},
{
"epoch": 2.5,
"learning_rate": 1.4222780766009536e-06,
"loss": 0.4336,
"step": 995
},
{
"epoch": 2.5,
"learning_rate": 1.4083642978043278e-06,
"loss": 0.4326,
"step": 996
},
{
"epoch": 2.5,
"learning_rate": 1.3945137541083697e-06,
"loss": 0.4391,
"step": 997
},
{
"epoch": 2.5,
"learning_rate": 1.3807265474541465e-06,
"loss": 0.4204,
"step": 998
},
{
"epoch": 2.51,
"learning_rate": 1.3670027793165642e-06,
"loss": 0.4072,
"step": 999
},
{
"epoch": 2.51,
"learning_rate": 1.3533425507036057e-06,
"loss": 0.457,
"step": 1000
},
{
"epoch": 2.51,
"learning_rate": 1.339745962155613e-06,
"loss": 0.3991,
"step": 1001
},
{
"epoch": 2.51,
"learning_rate": 1.3262131137445266e-06,
"loss": 0.4193,
"step": 1002
},
{
"epoch": 2.52,
"learning_rate": 1.312744105073146e-06,
"loss": 0.4425,
"step": 1003
},
{
"epoch": 2.52,
"learning_rate": 1.2993390352744184e-06,
"loss": 0.4504,
"step": 1004
},
{
"epoch": 2.52,
"learning_rate": 1.2859980030106922e-06,
"loss": 0.4385,
"step": 1005
},
{
"epoch": 2.52,
"learning_rate": 1.2727211064729862e-06,
"loss": 0.4226,
"step": 1006
},
{
"epoch": 2.53,
"learning_rate": 1.2595084433802829e-06,
"loss": 0.4344,
"step": 1007
},
{
"epoch": 2.53,
"learning_rate": 1.2463601109788058e-06,
"loss": 0.4217,
"step": 1008
},
{
"epoch": 2.53,
"learning_rate": 1.2332762060412905e-06,
"loss": 0.473,
"step": 1009
},
{
"epoch": 2.53,
"learning_rate": 1.220256824866285e-06,
"loss": 0.4443,
"step": 1010
},
{
"epoch": 2.54,
"learning_rate": 1.2073020632774391e-06,
"loss": 0.4488,
"step": 1011
},
{
"epoch": 2.54,
"learning_rate": 1.1944120166227947e-06,
"loss": 0.4171,
"step": 1012
},
{
"epoch": 2.54,
"learning_rate": 1.18158677977409e-06,
"loss": 0.4268,
"step": 1013
},
{
"epoch": 2.54,
"learning_rate": 1.1688264471260546e-06,
"loss": 0.4426,
"step": 1014
},
{
"epoch": 2.55,
"learning_rate": 1.1561311125957208e-06,
"loss": 0.4307,
"step": 1015
},
{
"epoch": 2.55,
"learning_rate": 1.1435008696217298e-06,
"loss": 0.4062,
"step": 1016
},
{
"epoch": 2.55,
"learning_rate": 1.1309358111636405e-06,
"loss": 0.445,
"step": 1017
},
{
"epoch": 2.55,
"learning_rate": 1.1184360297012532e-06,
"loss": 0.4252,
"step": 1018
},
{
"epoch": 2.56,
"learning_rate": 1.1060016172339206e-06,
"loss": 0.4156,
"step": 1019
},
{
"epoch": 2.56,
"learning_rate": 1.093632665279878e-06,
"loss": 0.435,
"step": 1020
},
{
"epoch": 2.56,
"learning_rate": 1.081329264875567e-06,
"loss": 0.4275,
"step": 1021
},
{
"epoch": 2.56,
"learning_rate": 1.0690915065749564e-06,
"loss": 0.4316,
"step": 1022
},
{
"epoch": 2.57,
"learning_rate": 1.0569194804488914e-06,
"loss": 0.4336,
"step": 1023
},
{
"epoch": 2.57,
"learning_rate": 1.0448132760844287e-06,
"loss": 0.4369,
"step": 1024
},
{
"epoch": 2.57,
"learning_rate": 1.032772982584157e-06,
"loss": 0.4246,
"step": 1025
},
{
"epoch": 2.57,
"learning_rate": 1.0207986885655664e-06,
"loss": 0.4546,
"step": 1026
},
{
"epoch": 2.58,
"learning_rate": 1.0088904821603884e-06,
"loss": 0.4544,
"step": 1027
},
{
"epoch": 2.58,
"learning_rate": 9.970484510139323e-07,
"loss": 0.4309,
"step": 1028
},
{
"epoch": 2.58,
"learning_rate": 9.852726822844639e-07,
"loss": 0.4452,
"step": 1029
},
{
"epoch": 2.58,
"learning_rate": 9.735632626425463e-07,
"loss": 0.4342,
"step": 1030
},
{
"epoch": 2.59,
"learning_rate": 9.619202782704118e-07,
"loss": 0.4629,
"step": 1031
},
{
"epoch": 2.59,
"learning_rate": 9.503438148613208e-07,
"loss": 0.4312,
"step": 1032
},
{
"epoch": 2.59,
"learning_rate": 9.388339576189376e-07,
"loss": 0.4198,
"step": 1033
},
{
"epoch": 2.59,
"learning_rate": 9.273907912566959e-07,
"loss": 0.4274,
"step": 1034
},
{
"epoch": 2.6,
"learning_rate": 9.16014399997186e-07,
"loss": 0.4319,
"step": 1035
},
{
"epoch": 2.6,
"learning_rate": 9.047048675715164e-07,
"loss": 0.4127,
"step": 1036
},
{
"epoch": 2.6,
"learning_rate": 8.93462277218724e-07,
"loss": 0.4491,
"step": 1037
},
{
"epoch": 2.6,
"learning_rate": 8.822867116851397e-07,
"loss": 0.4413,
"step": 1038
},
{
"epoch": 2.61,
"learning_rate": 8.7117825322378e-07,
"loss": 0.4345,
"step": 1039
},
{
"epoch": 2.61,
"learning_rate": 8.601369835937623e-07,
"loss": 0.4171,
"step": 1040
},
{
"epoch": 2.61,
"learning_rate": 8.491629840596805e-07,
"loss": 0.444,
"step": 1041
},
{
"epoch": 2.61,
"learning_rate": 8.382563353910122e-07,
"loss": 0.4271,
"step": 1042
},
{
"epoch": 2.62,
"learning_rate": 8.274171178615354e-07,
"loss": 0.4331,
"step": 1043
},
{
"epoch": 2.62,
"learning_rate": 8.166454112487287e-07,
"loss": 0.4379,
"step": 1044
},
{
"epoch": 2.62,
"learning_rate": 8.059412948331768e-07,
"loss": 0.422,
"step": 1045
},
{
"epoch": 2.62,
"learning_rate": 7.953048473980041e-07,
"loss": 0.4274,
"step": 1046
},
{
"epoch": 2.63,
"learning_rate": 7.847361472282822e-07,
"loss": 0.4465,
"step": 1047
},
{
"epoch": 2.63,
"learning_rate": 7.742352721104607e-07,
"loss": 0.4341,
"step": 1048
},
{
"epoch": 2.63,
"learning_rate": 7.638022993317873e-07,
"loss": 0.4431,
"step": 1049
},
{
"epoch": 2.63,
"learning_rate": 7.534373056797451e-07,
"loss": 0.448,
"step": 1050
},
{
"epoch": 2.64,
"learning_rate": 7.431403674414883e-07,
"loss": 0.432,
"step": 1051
},
{
"epoch": 2.64,
"learning_rate": 7.329115604032732e-07,
"loss": 0.4388,
"step": 1052
},
{
"epoch": 2.64,
"learning_rate": 7.227509598499094e-07,
"loss": 0.4571,
"step": 1053
},
{
"epoch": 2.64,
"learning_rate": 7.126586405641989e-07,
"loss": 0.4459,
"step": 1054
},
{
"epoch": 2.65,
"learning_rate": 7.026346768263892e-07,
"loss": 0.4189,
"step": 1055
},
{
"epoch": 2.65,
"learning_rate": 6.926791424136259e-07,
"loss": 0.4564,
"step": 1056
},
{
"epoch": 2.65,
"learning_rate": 6.827921105994096e-07,
"loss": 0.4406,
"step": 1057
},
{
"epoch": 2.65,
"learning_rate": 6.729736541530551e-07,
"loss": 0.4236,
"step": 1058
},
{
"epoch": 2.66,
"learning_rate": 6.63223845339157e-07,
"loss": 0.4381,
"step": 1059
},
{
"epoch": 2.66,
"learning_rate": 6.535427559170638e-07,
"loss": 0.4147,
"step": 1060
},
{
"epoch": 2.66,
"learning_rate": 6.439304571403349e-07,
"loss": 0.4486,
"step": 1061
},
{
"epoch": 2.66,
"learning_rate": 6.343870197562307e-07,
"loss": 0.4637,
"step": 1062
},
{
"epoch": 2.67,
"learning_rate": 6.249125140051893e-07,
"loss": 0.4342,
"step": 1063
},
{
"epoch": 2.67,
"learning_rate": 6.155070096202986e-07,
"loss": 0.4394,
"step": 1064
},
{
"epoch": 2.67,
"learning_rate": 6.061705758267978e-07,
"loss": 0.4545,
"step": 1065
},
{
"epoch": 2.68,
"learning_rate": 5.969032813415577e-07,
"loss": 0.439,
"step": 1066
},
{
"epoch": 2.68,
"learning_rate": 5.877051943725798e-07,
"loss": 0.4341,
"step": 1067
},
{
"epoch": 2.68,
"learning_rate": 5.785763826184931e-07,
"loss": 0.4183,
"step": 1068
},
{
"epoch": 2.68,
"learning_rate": 5.695169132680556e-07,
"loss": 0.4387,
"step": 1069
},
{
"epoch": 2.69,
"learning_rate": 5.605268529996588e-07,
"loss": 0.4392,
"step": 1070
},
{
"epoch": 2.69,
"learning_rate": 5.51606267980842e-07,
"loss": 0.4203,
"step": 1071
},
{
"epoch": 2.69,
"learning_rate": 5.427552238677925e-07,
"loss": 0.4024,
"step": 1072
},
{
"epoch": 2.69,
"learning_rate": 5.339737858048811e-07,
"loss": 0.4244,
"step": 1073
},
{
"epoch": 2.7,
"learning_rate": 5.252620184241697e-07,
"loss": 0.4009,
"step": 1074
},
{
"epoch": 2.7,
"learning_rate": 5.166199858449317e-07,
"loss": 0.4497,
"step": 1075
},
{
"epoch": 2.7,
"learning_rate": 5.080477516731974e-07,
"loss": 0.4243,
"step": 1076
},
{
"epoch": 2.7,
"learning_rate": 4.995453790012706e-07,
"loss": 0.4374,
"step": 1077
},
{
"epoch": 2.71,
"learning_rate": 4.911129304072648e-07,
"loss": 0.4422,
"step": 1078
},
{
"epoch": 2.71,
"learning_rate": 4.827504679546569e-07,
"loss": 0.4367,
"step": 1079
},
{
"epoch": 2.71,
"learning_rate": 4.7445805319181305e-07,
"loss": 0.4403,
"step": 1080
},
{
"epoch": 2.71,
"learning_rate": 4.662357471515433e-07,
"loss": 0.431,
"step": 1081
},
{
"epoch": 2.72,
"learning_rate": 4.5808361035065364e-07,
"loss": 0.4514,
"step": 1082
},
{
"epoch": 2.72,
"learning_rate": 4.5000170278949984e-07,
"loss": 0.4349,
"step": 1083
},
{
"epoch": 2.72,
"learning_rate": 4.419900839515434e-07,
"loss": 0.4322,
"step": 1084
},
{
"epoch": 2.72,
"learning_rate": 4.3404881280291744e-07,
"loss": 0.4265,
"step": 1085
},
{
"epoch": 2.73,
"learning_rate": 4.261779477919892e-07,
"loss": 0.4252,
"step": 1086
},
{
"epoch": 2.73,
"learning_rate": 4.183775468489304e-07,
"loss": 0.447,
"step": 1087
},
{
"epoch": 2.73,
"learning_rate": 4.1064766738529326e-07,
"loss": 0.4361,
"step": 1088
},
{
"epoch": 2.73,
"learning_rate": 4.0298836629358626e-07,
"loss": 0.4385,
"step": 1089
},
{
"epoch": 2.74,
"learning_rate": 3.9539969994685676e-07,
"loss": 0.4454,
"step": 1090
},
{
"epoch": 2.74,
"learning_rate": 3.878817241982713e-07,
"loss": 0.4522,
"step": 1091
},
{
"epoch": 2.74,
"learning_rate": 3.804344943807126e-07,
"loss": 0.4371,
"step": 1092
},
{
"epoch": 2.74,
"learning_rate": 3.7305806530636647e-07,
"loss": 0.4371,
"step": 1093
},
{
"epoch": 2.75,
"learning_rate": 3.6575249126631683e-07,
"loss": 0.4249,
"step": 1094
},
{
"epoch": 2.75,
"learning_rate": 3.585178260301514e-07,
"loss": 0.4182,
"step": 1095
},
{
"epoch": 2.75,
"learning_rate": 3.5135412284556637e-07,
"loss": 0.444,
"step": 1096
},
{
"epoch": 2.75,
"learning_rate": 3.442614344379669e-07,
"loss": 0.4464,
"step": 1097
},
{
"epoch": 2.76,
"learning_rate": 3.372398130100851e-07,
"loss": 0.4473,
"step": 1098
},
{
"epoch": 2.76,
"learning_rate": 3.302893102415994e-07,
"loss": 0.4671,
"step": 1099
},
{
"epoch": 2.76,
"learning_rate": 3.2340997728874223e-07,
"loss": 0.4189,
"step": 1100
},
{
"epoch": 2.76,
"learning_rate": 3.166018647839353e-07,
"loss": 0.4355,
"step": 1101
},
{
"epoch": 2.77,
"learning_rate": 3.0986502283541055e-07,
"loss": 0.4313,
"step": 1102
},
{
"epoch": 2.77,
"learning_rate": 3.031995010268451e-07,
"loss": 0.4454,
"step": 1103
},
{
"epoch": 2.77,
"learning_rate": 2.9660534841699175e-07,
"loss": 0.4265,
"step": 1104
},
{
"epoch": 2.77,
"learning_rate": 2.900826135393231e-07,
"loss": 0.4361,
"step": 1105
},
{
"epoch": 2.78,
"learning_rate": 2.8363134440166806e-07,
"loss": 0.4319,
"step": 1106
},
{
"epoch": 2.78,
"learning_rate": 2.772515884858673e-07,
"loss": 0.4161,
"step": 1107
},
{
"epoch": 2.78,
"learning_rate": 2.7094339274741254e-07,
"loss": 0.4202,
"step": 1108
},
{
"epoch": 2.78,
"learning_rate": 2.6470680361511346e-07,
"loss": 0.4312,
"step": 1109
},
{
"epoch": 2.79,
"learning_rate": 2.585418669907458e-07,
"loss": 0.4519,
"step": 1110
},
{
"epoch": 2.79,
"learning_rate": 2.52448628248716e-07,
"loss": 0.4481,
"step": 1111
},
{
"epoch": 2.79,
"learning_rate": 2.4642713223573254e-07,
"loss": 0.4176,
"step": 1112
},
{
"epoch": 2.79,
"learning_rate": 2.40477423270471e-07,
"loss": 0.4472,
"step": 1113
},
{
"epoch": 2.8,
"learning_rate": 2.345995451432448e-07,
"loss": 0.4308,
"step": 1114
},
{
"epoch": 2.8,
"learning_rate": 2.2879354111569163e-07,
"loss": 0.4485,
"step": 1115
},
{
"epoch": 2.8,
"learning_rate": 2.2305945392044893e-07,
"loss": 0.4277,
"step": 1116
},
{
"epoch": 2.8,
"learning_rate": 2.173973257608397e-07,
"loss": 0.456,
"step": 1117
},
{
"epoch": 2.81,
"learning_rate": 2.1180719831056184e-07,
"loss": 0.4203,
"step": 1118
},
{
"epoch": 2.81,
"learning_rate": 2.0628911271338593e-07,
"loss": 0.4094,
"step": 1119
},
{
"epoch": 2.81,
"learning_rate": 2.008431095828467e-07,
"loss": 0.4272,
"step": 1120
},
{
"epoch": 2.81,
"learning_rate": 1.9546922900194553e-07,
"loss": 0.4248,
"step": 1121
},
{
"epoch": 2.82,
"learning_rate": 1.9016751052285952e-07,
"loss": 0.4381,
"step": 1122
},
{
"epoch": 2.82,
"learning_rate": 1.8493799316664395e-07,
"loss": 0.4155,
"step": 1123
},
{
"epoch": 2.82,
"learning_rate": 1.7978071542294916e-07,
"loss": 0.4425,
"step": 1124
},
{
"epoch": 2.82,
"learning_rate": 1.746957152497375e-07,
"loss": 0.4424,
"step": 1125
},
{
"epoch": 2.83,
"learning_rate": 1.6968303007300124e-07,
"loss": 0.4397,
"step": 1126
},
{
"epoch": 2.83,
"learning_rate": 1.6474269678648956e-07,
"loss": 0.4713,
"step": 1127
},
{
"epoch": 2.83,
"learning_rate": 1.598747517514365e-07,
"loss": 0.4485,
"step": 1128
},
{
"epoch": 2.83,
"learning_rate": 1.550792307962934e-07,
"loss": 0.4268,
"step": 1129
},
{
"epoch": 2.84,
"learning_rate": 1.5035616921646234e-07,
"loss": 0.4134,
"step": 1130
},
{
"epoch": 2.84,
"learning_rate": 1.457056017740399e-07,
"loss": 0.4595,
"step": 1131
},
{
"epoch": 2.84,
"learning_rate": 1.4112756269756278e-07,
"loss": 0.4282,
"step": 1132
},
{
"epoch": 2.84,
"learning_rate": 1.3662208568175017e-07,
"loss": 0.4575,
"step": 1133
},
{
"epoch": 2.85,
"learning_rate": 1.3218920388725853e-07,
"loss": 0.424,
"step": 1134
},
{
"epoch": 2.85,
"learning_rate": 1.2782894994044393e-07,
"loss": 0.4532,
"step": 1135
},
{
"epoch": 2.85,
"learning_rate": 1.2354135593310669e-07,
"loss": 0.4334,
"step": 1136
},
{
"epoch": 2.85,
"learning_rate": 1.1932645342227046e-07,
"loss": 0.4335,
"step": 1137
},
{
"epoch": 2.86,
"learning_rate": 1.1518427342994243e-07,
"loss": 0.4393,
"step": 1138
},
{
"epoch": 2.86,
"learning_rate": 1.1111484644288684e-07,
"loss": 0.4442,
"step": 1139
},
{
"epoch": 2.86,
"learning_rate": 1.0711820241240067e-07,
"loss": 0.4406,
"step": 1140
},
{
"epoch": 2.86,
"learning_rate": 1.0319437075409056e-07,
"loss": 0.4381,
"step": 1141
},
{
"epoch": 2.87,
"learning_rate": 9.934338034765956e-08,
"loss": 0.4375,
"step": 1142
},
{
"epoch": 2.87,
"learning_rate": 9.556525953669516e-08,
"loss": 0.4246,
"step": 1143
},
{
"epoch": 2.87,
"learning_rate": 9.186003612845496e-08,
"loss": 0.4255,
"step": 1144
},
{
"epoch": 2.87,
"learning_rate": 8.82277373936713e-08,
"loss": 0.4375,
"step": 1145
},
{
"epoch": 2.88,
"learning_rate": 8.466839006634364e-08,
"loss": 0.4414,
"step": 1146
},
{
"epoch": 2.88,
"learning_rate": 8.118202034353872e-08,
"loss": 0.4515,
"step": 1147
},
{
"epoch": 2.88,
"learning_rate": 7.77686538852085e-08,
"loss": 0.4411,
"step": 1148
},
{
"epoch": 2.88,
"learning_rate": 7.442831581399357e-08,
"loss": 0.4376,
"step": 1149
},
{
"epoch": 2.89,
"learning_rate": 7.116103071503788e-08,
"loss": 0.4584,
"step": 1150
},
{
"epoch": 2.89,
"learning_rate": 6.796682263581322e-08,
"loss": 0.4518,
"step": 1151
},
{
"epoch": 2.89,
"learning_rate": 6.484571508593718e-08,
"loss": 0.4378,
"step": 1152
},
{
"epoch": 2.89,
"learning_rate": 6.179773103699993e-08,
"loss": 0.4199,
"step": 1153
},
{
"epoch": 2.9,
"learning_rate": 5.8822892922399956e-08,
"loss": 0.4244,
"step": 1154
},
{
"epoch": 2.9,
"learning_rate": 5.592122263717414e-08,
"loss": 0.4379,
"step": 1155
},
{
"epoch": 2.9,
"learning_rate": 5.3092741537841276e-08,
"loss": 0.4268,
"step": 1156
},
{
"epoch": 2.9,
"learning_rate": 5.033747044223769e-08,
"loss": 0.4317,
"step": 1157
},
{
"epoch": 2.91,
"learning_rate": 4.7655429629372975e-08,
"loss": 0.4479,
"step": 1158
},
{
"epoch": 2.91,
"learning_rate": 4.504663883927341e-08,
"loss": 0.4195,
"step": 1159
},
{
"epoch": 2.91,
"learning_rate": 4.251111727283985e-08,
"loss": 0.4493,
"step": 1160
},
{
"epoch": 2.91,
"learning_rate": 4.004888359170678e-08,
"loss": 0.4415,
"step": 1161
},
{
"epoch": 2.92,
"learning_rate": 3.7659955918103455e-08,
"loss": 0.4145,
"step": 1162
},
{
"epoch": 2.92,
"learning_rate": 3.5344351834721844e-08,
"loss": 0.4102,
"step": 1163
},
{
"epoch": 2.92,
"learning_rate": 3.310208838458562e-08,
"loss": 0.4549,
"step": 1164
},
{
"epoch": 2.92,
"learning_rate": 3.093318207092799e-08,
"loss": 0.4227,
"step": 1165
},
{
"epoch": 2.93,
"learning_rate": 2.8837648857066304e-08,
"loss": 0.427,
"step": 1166
},
{
"epoch": 2.93,
"learning_rate": 2.681550416628431e-08,
"loss": 0.455,
"step": 1167
},
{
"epoch": 2.93,
"learning_rate": 2.4866762881725627e-08,
"loss": 0.4124,
"step": 1168
},
{
"epoch": 2.93,
"learning_rate": 2.2991439346274902e-08,
"loss": 0.4392,
"step": 1169
},
{
"epoch": 2.94,
"learning_rate": 2.118954736245682e-08,
"loss": 0.472,
"step": 1170
},
{
"epoch": 2.94,
"learning_rate": 1.9461100192337267e-08,
"loss": 0.4335,
"step": 1171
},
{
"epoch": 2.94,
"learning_rate": 1.7806110557418988e-08,
"loss": 0.4354,
"step": 1172
},
{
"epoch": 2.94,
"learning_rate": 1.6224590638553863e-08,
"loss": 0.447,
"step": 1173
},
{
"epoch": 2.95,
"learning_rate": 1.4716552075849655e-08,
"loss": 0.4422,
"step": 1174
},
{
"epoch": 2.95,
"learning_rate": 1.3282005968587864e-08,
"loss": 0.4249,
"step": 1175
},
{
"epoch": 2.95,
"learning_rate": 1.1920962875137109e-08,
"loss": 0.4343,
"step": 1176
},
{
"epoch": 2.95,
"learning_rate": 1.0633432812878763e-08,
"loss": 0.4564,
"step": 1177
},
{
"epoch": 2.96,
"learning_rate": 9.419425258135884e-09,
"loss": 0.403,
"step": 1178
},
{
"epoch": 2.96,
"learning_rate": 8.278949146094394e-09,
"loss": 0.4348,
"step": 1179
},
{
"epoch": 2.96,
"learning_rate": 7.212012870748686e-09,
"loss": 0.4491,
"step": 1180
},
{
"epoch": 2.96,
"learning_rate": 6.218624284831664e-09,
"loss": 0.4162,
"step": 1181
},
{
"epoch": 2.97,
"learning_rate": 5.2987906997581385e-09,
"loss": 0.4377,
"step": 1182
},
{
"epoch": 2.97,
"learning_rate": 4.452518885575963e-09,
"loss": 0.4406,
"step": 1183
},
{
"epoch": 2.97,
"learning_rate": 3.6798150709105306e-09,
"loss": 0.4088,
"step": 1184
},
{
"epoch": 2.97,
"learning_rate": 2.9806849429203642e-09,
"loss": 0.4499,
"step": 1185
},
{
"epoch": 2.98,
"learning_rate": 2.3551336472582563e-09,
"loss": 0.4435,
"step": 1186
},
{
"epoch": 2.98,
"learning_rate": 1.8031657880301924e-09,
"loss": 0.4465,
"step": 1187
},
{
"epoch": 2.98,
"learning_rate": 1.324785427760933e-09,
"loss": 0.4174,
"step": 1188
},
{
"epoch": 2.98,
"learning_rate": 9.199960873673697e-10,
"loss": 0.4662,
"step": 1189
},
{
"epoch": 2.99,
"learning_rate": 5.888007461307688e-10,
"loss": 0.4339,
"step": 1190
},
{
"epoch": 2.99,
"learning_rate": 3.3120184167345636e-10,
"loss": 0.4384,
"step": 1191
},
{
"epoch": 2.99,
"learning_rate": 1.4720126994327567e-10,
"loss": 0.4322,
"step": 1192
},
{
"epoch": 2.99,
"learning_rate": 3.6800385199153853e-11,
"loss": 0.4474,
"step": 1193
},
{
"epoch": 3.0,
"learning_rate": 0.0,
"loss": 0.4107,
"step": 1194
},
{
"epoch": 3.0,
"step": 1194,
"total_flos": 1.4240637666721792e+17,
"train_loss": 0.47233876441191985,
"train_runtime": 3256.6622,
"train_samples_per_second": 46.98,
"train_steps_per_second": 0.367
}
],
"max_steps": 1194,
"num_train_epochs": 3,
"total_flos": 1.4240637666721792e+17,
"trial_name": null,
"trial_params": null
}