Muennighoff's picture
Upload folder using huggingface_hub
64df15d verified
raw
history blame contribute delete
No virus
60.6 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.07070135746606335,
"eval_steps": 500,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 5.263157894736843e-07,
"loss": 5.3148,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 1.0526315789473685e-06,
"loss": 4.9403,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 1.5789473684210526e-06,
"loss": 5.4427,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 2.105263157894737e-06,
"loss": 4.4435,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 2.631578947368421e-06,
"loss": 4.347,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 3.157894736842105e-06,
"loss": 3.9741,
"step": 6
},
{
"epoch": 0.0,
"learning_rate": 3.6842105263157896e-06,
"loss": 3.0066,
"step": 7
},
{
"epoch": 0.0,
"learning_rate": 4.210526315789474e-06,
"loss": 3.1048,
"step": 8
},
{
"epoch": 0.0,
"learning_rate": 4.736842105263158e-06,
"loss": 2.715,
"step": 9
},
{
"epoch": 0.0,
"learning_rate": 5.263157894736842e-06,
"loss": 2.2166,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 5.789473684210527e-06,
"loss": 2.2135,
"step": 11
},
{
"epoch": 0.0,
"learning_rate": 6.31578947368421e-06,
"loss": 1.9079,
"step": 12
},
{
"epoch": 0.0,
"learning_rate": 6.842105263157896e-06,
"loss": 2.2475,
"step": 13
},
{
"epoch": 0.0,
"learning_rate": 7.368421052631579e-06,
"loss": 1.4853,
"step": 14
},
{
"epoch": 0.0,
"learning_rate": 7.894736842105265e-06,
"loss": 1.3774,
"step": 15
},
{
"epoch": 0.0,
"learning_rate": 8.421052631578948e-06,
"loss": 1.4311,
"step": 16
},
{
"epoch": 0.0,
"learning_rate": 8.947368421052632e-06,
"loss": 1.543,
"step": 17
},
{
"epoch": 0.0,
"learning_rate": 9.473684210526315e-06,
"loss": 1.2706,
"step": 18
},
{
"epoch": 0.0,
"learning_rate": 1e-05,
"loss": 1.1835,
"step": 19
},
{
"epoch": 0.0,
"learning_rate": 1.0526315789473684e-05,
"loss": 1.07,
"step": 20
},
{
"epoch": 0.0,
"learning_rate": 1.105263157894737e-05,
"loss": 1.4392,
"step": 21
},
{
"epoch": 0.0,
"learning_rate": 1.1578947368421053e-05,
"loss": 1.123,
"step": 22
},
{
"epoch": 0.0,
"learning_rate": 1.2105263157894737e-05,
"loss": 1.0913,
"step": 23
},
{
"epoch": 0.0,
"learning_rate": 1.263157894736842e-05,
"loss": 1.2232,
"step": 24
},
{
"epoch": 0.0,
"learning_rate": 1.3157894736842108e-05,
"loss": 1.3482,
"step": 25
},
{
"epoch": 0.0,
"learning_rate": 1.3684210526315791e-05,
"loss": 1.2379,
"step": 26
},
{
"epoch": 0.0,
"learning_rate": 1.4210526315789475e-05,
"loss": 1.2803,
"step": 27
},
{
"epoch": 0.0,
"learning_rate": 1.4736842105263159e-05,
"loss": 1.2853,
"step": 28
},
{
"epoch": 0.0,
"learning_rate": 1.5263157894736846e-05,
"loss": 1.3168,
"step": 29
},
{
"epoch": 0.0,
"learning_rate": 1.578947368421053e-05,
"loss": 1.2187,
"step": 30
},
{
"epoch": 0.0,
"learning_rate": 1.6315789473684213e-05,
"loss": 1.1479,
"step": 31
},
{
"epoch": 0.0,
"learning_rate": 1.6842105263157896e-05,
"loss": 1.1682,
"step": 32
},
{
"epoch": 0.0,
"learning_rate": 1.736842105263158e-05,
"loss": 1.1737,
"step": 33
},
{
"epoch": 0.0,
"learning_rate": 1.7894736842105264e-05,
"loss": 1.0732,
"step": 34
},
{
"epoch": 0.0,
"learning_rate": 1.8421052631578947e-05,
"loss": 1.167,
"step": 35
},
{
"epoch": 0.01,
"learning_rate": 1.894736842105263e-05,
"loss": 1.3212,
"step": 36
},
{
"epoch": 0.01,
"learning_rate": 1.9473684210526318e-05,
"loss": 1.2106,
"step": 37
},
{
"epoch": 0.01,
"learning_rate": 2e-05,
"loss": 1.177,
"step": 38
},
{
"epoch": 0.01,
"learning_rate": 1.998353909465021e-05,
"loss": 1.1748,
"step": 39
},
{
"epoch": 0.01,
"learning_rate": 1.9967078189300412e-05,
"loss": 1.2001,
"step": 40
},
{
"epoch": 0.01,
"learning_rate": 1.995061728395062e-05,
"loss": 1.2563,
"step": 41
},
{
"epoch": 0.01,
"learning_rate": 1.9934156378600823e-05,
"loss": 1.1329,
"step": 42
},
{
"epoch": 0.01,
"learning_rate": 1.991769547325103e-05,
"loss": 1.0743,
"step": 43
},
{
"epoch": 0.01,
"learning_rate": 1.9901234567901237e-05,
"loss": 1.1259,
"step": 44
},
{
"epoch": 0.01,
"learning_rate": 1.988477366255144e-05,
"loss": 1.2712,
"step": 45
},
{
"epoch": 0.01,
"learning_rate": 1.9868312757201648e-05,
"loss": 1.1933,
"step": 46
},
{
"epoch": 0.01,
"learning_rate": 1.9851851851851855e-05,
"loss": 1.1184,
"step": 47
},
{
"epoch": 0.01,
"learning_rate": 1.983539094650206e-05,
"loss": 1.1003,
"step": 48
},
{
"epoch": 0.01,
"learning_rate": 1.9818930041152265e-05,
"loss": 1.1529,
"step": 49
},
{
"epoch": 0.01,
"learning_rate": 1.9802469135802472e-05,
"loss": 1.1991,
"step": 50
},
{
"epoch": 0.01,
"learning_rate": 1.9786008230452676e-05,
"loss": 1.2365,
"step": 51
},
{
"epoch": 0.01,
"learning_rate": 1.9769547325102883e-05,
"loss": 1.1794,
"step": 52
},
{
"epoch": 0.01,
"learning_rate": 1.9753086419753087e-05,
"loss": 1.2881,
"step": 53
},
{
"epoch": 0.01,
"learning_rate": 1.9736625514403294e-05,
"loss": 1.0874,
"step": 54
},
{
"epoch": 0.01,
"learning_rate": 1.97201646090535e-05,
"loss": 1.1835,
"step": 55
},
{
"epoch": 0.01,
"learning_rate": 1.9703703703703704e-05,
"loss": 1.205,
"step": 56
},
{
"epoch": 0.01,
"learning_rate": 1.968724279835391e-05,
"loss": 1.1321,
"step": 57
},
{
"epoch": 0.01,
"learning_rate": 1.9670781893004115e-05,
"loss": 1.1065,
"step": 58
},
{
"epoch": 0.01,
"learning_rate": 1.9654320987654322e-05,
"loss": 1.1393,
"step": 59
},
{
"epoch": 0.01,
"learning_rate": 1.963786008230453e-05,
"loss": 1.2419,
"step": 60
},
{
"epoch": 0.01,
"learning_rate": 1.9621399176954733e-05,
"loss": 1.2029,
"step": 61
},
{
"epoch": 0.01,
"learning_rate": 1.960493827160494e-05,
"loss": 1.1085,
"step": 62
},
{
"epoch": 0.01,
"learning_rate": 1.9588477366255147e-05,
"loss": 1.1212,
"step": 63
},
{
"epoch": 0.01,
"learning_rate": 1.9572016460905354e-05,
"loss": 1.1012,
"step": 64
},
{
"epoch": 0.01,
"learning_rate": 1.9555555555555557e-05,
"loss": 1.1406,
"step": 65
},
{
"epoch": 0.01,
"learning_rate": 1.9539094650205764e-05,
"loss": 1.1625,
"step": 66
},
{
"epoch": 0.01,
"learning_rate": 1.9522633744855968e-05,
"loss": 1.1365,
"step": 67
},
{
"epoch": 0.01,
"learning_rate": 1.9506172839506175e-05,
"loss": 1.2213,
"step": 68
},
{
"epoch": 0.01,
"learning_rate": 1.9489711934156382e-05,
"loss": 1.0968,
"step": 69
},
{
"epoch": 0.01,
"learning_rate": 1.9473251028806586e-05,
"loss": 1.065,
"step": 70
},
{
"epoch": 0.01,
"learning_rate": 1.9456790123456793e-05,
"loss": 1.0782,
"step": 71
},
{
"epoch": 0.01,
"learning_rate": 1.9440329218106996e-05,
"loss": 1.0493,
"step": 72
},
{
"epoch": 0.01,
"learning_rate": 1.9423868312757203e-05,
"loss": 1.1859,
"step": 73
},
{
"epoch": 0.01,
"learning_rate": 1.9407407407407407e-05,
"loss": 1.1291,
"step": 74
},
{
"epoch": 0.01,
"learning_rate": 1.9390946502057614e-05,
"loss": 1.0744,
"step": 75
},
{
"epoch": 0.01,
"learning_rate": 1.937448559670782e-05,
"loss": 1.1164,
"step": 76
},
{
"epoch": 0.01,
"learning_rate": 1.9358024691358025e-05,
"loss": 1.2251,
"step": 77
},
{
"epoch": 0.01,
"learning_rate": 1.934156378600823e-05,
"loss": 1.0088,
"step": 78
},
{
"epoch": 0.01,
"learning_rate": 1.932510288065844e-05,
"loss": 1.1095,
"step": 79
},
{
"epoch": 0.01,
"learning_rate": 1.9308641975308646e-05,
"loss": 1.2309,
"step": 80
},
{
"epoch": 0.01,
"learning_rate": 1.929218106995885e-05,
"loss": 1.111,
"step": 81
},
{
"epoch": 0.01,
"learning_rate": 1.9275720164609056e-05,
"loss": 1.1381,
"step": 82
},
{
"epoch": 0.01,
"learning_rate": 1.925925925925926e-05,
"loss": 1.176,
"step": 83
},
{
"epoch": 0.01,
"learning_rate": 1.9242798353909467e-05,
"loss": 1.0746,
"step": 84
},
{
"epoch": 0.01,
"learning_rate": 1.9226337448559674e-05,
"loss": 1.0809,
"step": 85
},
{
"epoch": 0.01,
"learning_rate": 1.9209876543209878e-05,
"loss": 1.0978,
"step": 86
},
{
"epoch": 0.01,
"learning_rate": 1.9193415637860085e-05,
"loss": 1.111,
"step": 87
},
{
"epoch": 0.01,
"learning_rate": 1.9176954732510288e-05,
"loss": 1.041,
"step": 88
},
{
"epoch": 0.01,
"learning_rate": 1.9160493827160495e-05,
"loss": 1.0565,
"step": 89
},
{
"epoch": 0.01,
"learning_rate": 1.91440329218107e-05,
"loss": 1.1544,
"step": 90
},
{
"epoch": 0.01,
"learning_rate": 1.9127572016460906e-05,
"loss": 1.0169,
"step": 91
},
{
"epoch": 0.01,
"learning_rate": 1.9111111111111113e-05,
"loss": 1.0712,
"step": 92
},
{
"epoch": 0.01,
"learning_rate": 1.9094650205761317e-05,
"loss": 1.2047,
"step": 93
},
{
"epoch": 0.01,
"learning_rate": 1.9078189300411524e-05,
"loss": 1.107,
"step": 94
},
{
"epoch": 0.01,
"learning_rate": 1.906172839506173e-05,
"loss": 1.1155,
"step": 95
},
{
"epoch": 0.01,
"learning_rate": 1.9045267489711938e-05,
"loss": 1.1726,
"step": 96
},
{
"epoch": 0.01,
"learning_rate": 1.902880658436214e-05,
"loss": 1.0075,
"step": 97
},
{
"epoch": 0.01,
"learning_rate": 1.901234567901235e-05,
"loss": 1.0384,
"step": 98
},
{
"epoch": 0.01,
"learning_rate": 1.8995884773662555e-05,
"loss": 1.1236,
"step": 99
},
{
"epoch": 0.01,
"learning_rate": 1.897942386831276e-05,
"loss": 1.1984,
"step": 100
},
{
"epoch": 0.01,
"learning_rate": 1.8962962962962966e-05,
"loss": 1.2089,
"step": 101
},
{
"epoch": 0.01,
"learning_rate": 1.894650205761317e-05,
"loss": 1.138,
"step": 102
},
{
"epoch": 0.01,
"learning_rate": 1.8930041152263377e-05,
"loss": 1.0623,
"step": 103
},
{
"epoch": 0.01,
"learning_rate": 1.891358024691358e-05,
"loss": 1.0937,
"step": 104
},
{
"epoch": 0.01,
"learning_rate": 1.8897119341563787e-05,
"loss": 1.1389,
"step": 105
},
{
"epoch": 0.01,
"learning_rate": 1.8880658436213994e-05,
"loss": 1.1111,
"step": 106
},
{
"epoch": 0.02,
"learning_rate": 1.8864197530864198e-05,
"loss": 1.1742,
"step": 107
},
{
"epoch": 0.02,
"learning_rate": 1.8847736625514405e-05,
"loss": 1.1477,
"step": 108
},
{
"epoch": 0.02,
"learning_rate": 1.883127572016461e-05,
"loss": 1.1087,
"step": 109
},
{
"epoch": 0.02,
"learning_rate": 1.8814814814814816e-05,
"loss": 1.1586,
"step": 110
},
{
"epoch": 0.02,
"learning_rate": 1.8798353909465023e-05,
"loss": 1.1586,
"step": 111
},
{
"epoch": 0.02,
"learning_rate": 1.878189300411523e-05,
"loss": 1.0298,
"step": 112
},
{
"epoch": 0.02,
"learning_rate": 1.8765432098765433e-05,
"loss": 1.0833,
"step": 113
},
{
"epoch": 0.02,
"learning_rate": 1.874897119341564e-05,
"loss": 1.0194,
"step": 114
},
{
"epoch": 0.02,
"learning_rate": 1.8732510288065847e-05,
"loss": 1.0605,
"step": 115
},
{
"epoch": 0.02,
"learning_rate": 1.871604938271605e-05,
"loss": 1.1575,
"step": 116
},
{
"epoch": 0.02,
"learning_rate": 1.8699588477366258e-05,
"loss": 1.1254,
"step": 117
},
{
"epoch": 0.02,
"learning_rate": 1.868312757201646e-05,
"loss": 1.2589,
"step": 118
},
{
"epoch": 0.02,
"learning_rate": 1.866666666666667e-05,
"loss": 1.0231,
"step": 119
},
{
"epoch": 0.02,
"learning_rate": 1.8650205761316872e-05,
"loss": 1.0414,
"step": 120
},
{
"epoch": 0.02,
"learning_rate": 1.863374485596708e-05,
"loss": 1.2159,
"step": 121
},
{
"epoch": 0.02,
"learning_rate": 1.8617283950617286e-05,
"loss": 1.088,
"step": 122
},
{
"epoch": 0.02,
"learning_rate": 1.860082304526749e-05,
"loss": 1.1823,
"step": 123
},
{
"epoch": 0.02,
"learning_rate": 1.8584362139917697e-05,
"loss": 1.0664,
"step": 124
},
{
"epoch": 0.02,
"learning_rate": 1.85679012345679e-05,
"loss": 1.0714,
"step": 125
},
{
"epoch": 0.02,
"learning_rate": 1.8551440329218108e-05,
"loss": 1.047,
"step": 126
},
{
"epoch": 0.02,
"learning_rate": 1.8534979423868315e-05,
"loss": 1.2283,
"step": 127
},
{
"epoch": 0.02,
"learning_rate": 1.851851851851852e-05,
"loss": 1.2039,
"step": 128
},
{
"epoch": 0.02,
"learning_rate": 1.8502057613168725e-05,
"loss": 1.1369,
"step": 129
},
{
"epoch": 0.02,
"learning_rate": 1.8485596707818932e-05,
"loss": 1.1382,
"step": 130
},
{
"epoch": 0.02,
"learning_rate": 1.846913580246914e-05,
"loss": 1.0467,
"step": 131
},
{
"epoch": 0.02,
"learning_rate": 1.8452674897119343e-05,
"loss": 1.1028,
"step": 132
},
{
"epoch": 0.02,
"learning_rate": 1.843621399176955e-05,
"loss": 1.0557,
"step": 133
},
{
"epoch": 0.02,
"learning_rate": 1.8419753086419754e-05,
"loss": 1.0511,
"step": 134
},
{
"epoch": 0.02,
"learning_rate": 1.840329218106996e-05,
"loss": 1.114,
"step": 135
},
{
"epoch": 0.02,
"learning_rate": 1.8386831275720164e-05,
"loss": 1.1142,
"step": 136
},
{
"epoch": 0.02,
"learning_rate": 1.837037037037037e-05,
"loss": 1.2217,
"step": 137
},
{
"epoch": 0.02,
"learning_rate": 1.835390946502058e-05,
"loss": 1.0838,
"step": 138
},
{
"epoch": 0.02,
"learning_rate": 1.8337448559670782e-05,
"loss": 1.0797,
"step": 139
},
{
"epoch": 0.02,
"learning_rate": 1.832098765432099e-05,
"loss": 1.1132,
"step": 140
},
{
"epoch": 0.02,
"learning_rate": 1.8304526748971193e-05,
"loss": 1.1133,
"step": 141
},
{
"epoch": 0.02,
"learning_rate": 1.82880658436214e-05,
"loss": 1.0737,
"step": 142
},
{
"epoch": 0.02,
"learning_rate": 1.8271604938271607e-05,
"loss": 1.1201,
"step": 143
},
{
"epoch": 0.02,
"learning_rate": 1.8255144032921814e-05,
"loss": 1.0197,
"step": 144
},
{
"epoch": 0.02,
"learning_rate": 1.8238683127572017e-05,
"loss": 1.1396,
"step": 145
},
{
"epoch": 0.02,
"learning_rate": 1.8222222222222224e-05,
"loss": 1.067,
"step": 146
},
{
"epoch": 0.02,
"learning_rate": 1.820576131687243e-05,
"loss": 1.0065,
"step": 147
},
{
"epoch": 0.02,
"learning_rate": 1.8189300411522635e-05,
"loss": 1.1946,
"step": 148
},
{
"epoch": 0.02,
"learning_rate": 1.8172839506172842e-05,
"loss": 1.0109,
"step": 149
},
{
"epoch": 0.02,
"learning_rate": 1.8156378600823046e-05,
"loss": 1.0899,
"step": 150
},
{
"epoch": 0.02,
"learning_rate": 1.8139917695473253e-05,
"loss": 1.1406,
"step": 151
},
{
"epoch": 0.02,
"learning_rate": 1.812345679012346e-05,
"loss": 0.9994,
"step": 152
},
{
"epoch": 0.02,
"learning_rate": 1.8106995884773663e-05,
"loss": 1.0095,
"step": 153
},
{
"epoch": 0.02,
"learning_rate": 1.809053497942387e-05,
"loss": 1.1859,
"step": 154
},
{
"epoch": 0.02,
"learning_rate": 1.8074074074074074e-05,
"loss": 1.1195,
"step": 155
},
{
"epoch": 0.02,
"learning_rate": 1.805761316872428e-05,
"loss": 1.034,
"step": 156
},
{
"epoch": 0.02,
"learning_rate": 1.8041152263374485e-05,
"loss": 1.0777,
"step": 157
},
{
"epoch": 0.02,
"learning_rate": 1.802469135802469e-05,
"loss": 1.1262,
"step": 158
},
{
"epoch": 0.02,
"learning_rate": 1.80082304526749e-05,
"loss": 1.0404,
"step": 159
},
{
"epoch": 0.02,
"learning_rate": 1.7991769547325106e-05,
"loss": 1.1523,
"step": 160
},
{
"epoch": 0.02,
"learning_rate": 1.797530864197531e-05,
"loss": 1.0683,
"step": 161
},
{
"epoch": 0.02,
"learning_rate": 1.7958847736625516e-05,
"loss": 1.1239,
"step": 162
},
{
"epoch": 0.02,
"learning_rate": 1.7942386831275723e-05,
"loss": 1.0842,
"step": 163
},
{
"epoch": 0.02,
"learning_rate": 1.7925925925925927e-05,
"loss": 1.1662,
"step": 164
},
{
"epoch": 0.02,
"learning_rate": 1.7909465020576134e-05,
"loss": 0.9218,
"step": 165
},
{
"epoch": 0.02,
"learning_rate": 1.7893004115226338e-05,
"loss": 1.0311,
"step": 166
},
{
"epoch": 0.02,
"learning_rate": 1.7876543209876545e-05,
"loss": 1.0482,
"step": 167
},
{
"epoch": 0.02,
"learning_rate": 1.786008230452675e-05,
"loss": 1.0655,
"step": 168
},
{
"epoch": 0.02,
"learning_rate": 1.7843621399176955e-05,
"loss": 1.0283,
"step": 169
},
{
"epoch": 0.02,
"learning_rate": 1.7827160493827162e-05,
"loss": 1.1081,
"step": 170
},
{
"epoch": 0.02,
"learning_rate": 1.7810699588477366e-05,
"loss": 1.1211,
"step": 171
},
{
"epoch": 0.02,
"learning_rate": 1.7794238683127573e-05,
"loss": 1.0637,
"step": 172
},
{
"epoch": 0.02,
"learning_rate": 1.7777777777777777e-05,
"loss": 1.1307,
"step": 173
},
{
"epoch": 0.02,
"learning_rate": 1.7761316872427984e-05,
"loss": 0.9779,
"step": 174
},
{
"epoch": 0.02,
"learning_rate": 1.774485596707819e-05,
"loss": 1.0568,
"step": 175
},
{
"epoch": 0.02,
"learning_rate": 1.7728395061728398e-05,
"loss": 0.9093,
"step": 176
},
{
"epoch": 0.03,
"learning_rate": 1.77119341563786e-05,
"loss": 1.0758,
"step": 177
},
{
"epoch": 0.03,
"learning_rate": 1.769547325102881e-05,
"loss": 1.0287,
"step": 178
},
{
"epoch": 0.03,
"learning_rate": 1.7679012345679015e-05,
"loss": 1.1866,
"step": 179
},
{
"epoch": 0.03,
"learning_rate": 1.766255144032922e-05,
"loss": 1.1544,
"step": 180
},
{
"epoch": 0.03,
"learning_rate": 1.7646090534979426e-05,
"loss": 1.1839,
"step": 181
},
{
"epoch": 0.03,
"learning_rate": 1.7629629629629633e-05,
"loss": 1.0704,
"step": 182
},
{
"epoch": 0.03,
"learning_rate": 1.7613168724279837e-05,
"loss": 0.9932,
"step": 183
},
{
"epoch": 0.03,
"learning_rate": 1.7596707818930044e-05,
"loss": 1.0875,
"step": 184
},
{
"epoch": 0.03,
"learning_rate": 1.7580246913580247e-05,
"loss": 1.0332,
"step": 185
},
{
"epoch": 0.03,
"learning_rate": 1.7563786008230454e-05,
"loss": 1.038,
"step": 186
},
{
"epoch": 0.03,
"learning_rate": 1.7547325102880658e-05,
"loss": 1.1347,
"step": 187
},
{
"epoch": 0.03,
"learning_rate": 1.7530864197530865e-05,
"loss": 1.0351,
"step": 188
},
{
"epoch": 0.03,
"learning_rate": 1.7514403292181072e-05,
"loss": 1.2042,
"step": 189
},
{
"epoch": 0.03,
"learning_rate": 1.7497942386831276e-05,
"loss": 1.1633,
"step": 190
},
{
"epoch": 0.03,
"learning_rate": 1.7481481481481483e-05,
"loss": 1.0954,
"step": 191
},
{
"epoch": 0.03,
"learning_rate": 1.746502057613169e-05,
"loss": 1.1159,
"step": 192
},
{
"epoch": 0.03,
"learning_rate": 1.7448559670781893e-05,
"loss": 1.081,
"step": 193
},
{
"epoch": 0.03,
"learning_rate": 1.74320987654321e-05,
"loss": 1.1633,
"step": 194
},
{
"epoch": 0.03,
"learning_rate": 1.7415637860082307e-05,
"loss": 1.1813,
"step": 195
},
{
"epoch": 0.03,
"learning_rate": 1.739917695473251e-05,
"loss": 1.0417,
"step": 196
},
{
"epoch": 0.03,
"learning_rate": 1.7382716049382718e-05,
"loss": 1.067,
"step": 197
},
{
"epoch": 0.03,
"learning_rate": 1.7366255144032925e-05,
"loss": 1.055,
"step": 198
},
{
"epoch": 0.03,
"learning_rate": 1.734979423868313e-05,
"loss": 0.9961,
"step": 199
},
{
"epoch": 0.03,
"learning_rate": 1.7333333333333336e-05,
"loss": 1.1443,
"step": 200
},
{
"epoch": 0.03,
"learning_rate": 1.731687242798354e-05,
"loss": 0.9847,
"step": 201
},
{
"epoch": 0.03,
"learning_rate": 1.7300411522633746e-05,
"loss": 1.0637,
"step": 202
},
{
"epoch": 0.03,
"learning_rate": 1.728395061728395e-05,
"loss": 1.1199,
"step": 203
},
{
"epoch": 0.03,
"learning_rate": 1.7267489711934157e-05,
"loss": 0.9536,
"step": 204
},
{
"epoch": 0.03,
"learning_rate": 1.7251028806584364e-05,
"loss": 1.0535,
"step": 205
},
{
"epoch": 0.03,
"learning_rate": 1.7234567901234568e-05,
"loss": 1.0906,
"step": 206
},
{
"epoch": 0.03,
"learning_rate": 1.7218106995884775e-05,
"loss": 1.0135,
"step": 207
},
{
"epoch": 0.03,
"learning_rate": 1.720164609053498e-05,
"loss": 0.9543,
"step": 208
},
{
"epoch": 0.03,
"learning_rate": 1.7185185185185185e-05,
"loss": 1.0429,
"step": 209
},
{
"epoch": 0.03,
"learning_rate": 1.7168724279835392e-05,
"loss": 0.922,
"step": 210
},
{
"epoch": 0.03,
"learning_rate": 1.71522633744856e-05,
"loss": 1.0619,
"step": 211
},
{
"epoch": 0.03,
"learning_rate": 1.7135802469135806e-05,
"loss": 1.0096,
"step": 212
},
{
"epoch": 0.03,
"learning_rate": 1.711934156378601e-05,
"loss": 1.092,
"step": 213
},
{
"epoch": 0.03,
"learning_rate": 1.7102880658436217e-05,
"loss": 0.9757,
"step": 214
},
{
"epoch": 0.03,
"learning_rate": 1.708641975308642e-05,
"loss": 1.1255,
"step": 215
},
{
"epoch": 0.03,
"learning_rate": 1.7069958847736628e-05,
"loss": 1.0475,
"step": 216
},
{
"epoch": 0.03,
"learning_rate": 1.705349794238683e-05,
"loss": 0.9449,
"step": 217
},
{
"epoch": 0.03,
"learning_rate": 1.7037037037037038e-05,
"loss": 1.0008,
"step": 218
},
{
"epoch": 0.03,
"learning_rate": 1.7020576131687242e-05,
"loss": 0.9377,
"step": 219
},
{
"epoch": 0.03,
"learning_rate": 1.700411522633745e-05,
"loss": 0.997,
"step": 220
},
{
"epoch": 0.03,
"learning_rate": 1.6987654320987656e-05,
"loss": 0.8949,
"step": 221
},
{
"epoch": 0.03,
"learning_rate": 1.697119341563786e-05,
"loss": 0.9276,
"step": 222
},
{
"epoch": 0.03,
"learning_rate": 1.6954732510288067e-05,
"loss": 0.8785,
"step": 223
},
{
"epoch": 0.03,
"learning_rate": 1.6938271604938274e-05,
"loss": 0.9711,
"step": 224
},
{
"epoch": 0.03,
"learning_rate": 1.692181069958848e-05,
"loss": 1.1176,
"step": 225
},
{
"epoch": 0.03,
"learning_rate": 1.6905349794238684e-05,
"loss": 1.0029,
"step": 226
},
{
"epoch": 0.03,
"learning_rate": 1.688888888888889e-05,
"loss": 1.0385,
"step": 227
},
{
"epoch": 0.03,
"learning_rate": 1.68724279835391e-05,
"loss": 0.875,
"step": 228
},
{
"epoch": 0.03,
"learning_rate": 1.6855967078189302e-05,
"loss": 0.996,
"step": 229
},
{
"epoch": 0.03,
"learning_rate": 1.683950617283951e-05,
"loss": 0.8966,
"step": 230
},
{
"epoch": 0.03,
"learning_rate": 1.6823045267489713e-05,
"loss": 1.0253,
"step": 231
},
{
"epoch": 0.03,
"learning_rate": 1.680658436213992e-05,
"loss": 0.9323,
"step": 232
},
{
"epoch": 0.03,
"learning_rate": 1.6790123456790123e-05,
"loss": 0.918,
"step": 233
},
{
"epoch": 0.03,
"learning_rate": 1.677366255144033e-05,
"loss": 1.0718,
"step": 234
},
{
"epoch": 0.03,
"learning_rate": 1.6757201646090537e-05,
"loss": 1.1039,
"step": 235
},
{
"epoch": 0.03,
"learning_rate": 1.674074074074074e-05,
"loss": 0.9036,
"step": 236
},
{
"epoch": 0.03,
"learning_rate": 1.6724279835390948e-05,
"loss": 1.0214,
"step": 237
},
{
"epoch": 0.03,
"learning_rate": 1.670781893004115e-05,
"loss": 0.9251,
"step": 238
},
{
"epoch": 0.03,
"learning_rate": 1.669135802469136e-05,
"loss": 1.2242,
"step": 239
},
{
"epoch": 0.03,
"learning_rate": 1.6674897119341566e-05,
"loss": 0.8946,
"step": 240
},
{
"epoch": 0.03,
"learning_rate": 1.6658436213991773e-05,
"loss": 0.9744,
"step": 241
},
{
"epoch": 0.03,
"learning_rate": 1.6641975308641976e-05,
"loss": 1.0234,
"step": 242
},
{
"epoch": 0.03,
"learning_rate": 1.6625514403292183e-05,
"loss": 1.035,
"step": 243
},
{
"epoch": 0.03,
"learning_rate": 1.660905349794239e-05,
"loss": 1.1036,
"step": 244
},
{
"epoch": 0.03,
"learning_rate": 1.6592592592592594e-05,
"loss": 0.9845,
"step": 245
},
{
"epoch": 0.03,
"learning_rate": 1.65761316872428e-05,
"loss": 1.0034,
"step": 246
},
{
"epoch": 0.03,
"learning_rate": 1.6559670781893005e-05,
"loss": 1.0166,
"step": 247
},
{
"epoch": 0.04,
"learning_rate": 1.654320987654321e-05,
"loss": 1.1084,
"step": 248
},
{
"epoch": 0.04,
"learning_rate": 1.6526748971193415e-05,
"loss": 1.0719,
"step": 249
},
{
"epoch": 0.04,
"learning_rate": 1.6510288065843622e-05,
"loss": 0.926,
"step": 250
},
{
"epoch": 0.04,
"learning_rate": 1.649382716049383e-05,
"loss": 1.0327,
"step": 251
},
{
"epoch": 0.04,
"learning_rate": 1.6477366255144033e-05,
"loss": 1.0809,
"step": 252
},
{
"epoch": 0.04,
"learning_rate": 1.646090534979424e-05,
"loss": 1.0163,
"step": 253
},
{
"epoch": 0.04,
"learning_rate": 1.6444444444444444e-05,
"loss": 0.9976,
"step": 254
},
{
"epoch": 0.04,
"learning_rate": 1.642798353909465e-05,
"loss": 0.9137,
"step": 255
},
{
"epoch": 0.04,
"learning_rate": 1.6411522633744858e-05,
"loss": 0.9506,
"step": 256
},
{
"epoch": 0.04,
"learning_rate": 1.6395061728395065e-05,
"loss": 1.0163,
"step": 257
},
{
"epoch": 0.04,
"learning_rate": 1.6378600823045268e-05,
"loss": 0.9648,
"step": 258
},
{
"epoch": 0.04,
"learning_rate": 1.6362139917695475e-05,
"loss": 0.9947,
"step": 259
},
{
"epoch": 0.04,
"learning_rate": 1.6345679012345682e-05,
"loss": 0.948,
"step": 260
},
{
"epoch": 0.04,
"learning_rate": 1.6329218106995886e-05,
"loss": 0.92,
"step": 261
},
{
"epoch": 0.04,
"learning_rate": 1.6312757201646093e-05,
"loss": 0.9264,
"step": 262
},
{
"epoch": 0.04,
"learning_rate": 1.6296296296296297e-05,
"loss": 1.0213,
"step": 263
},
{
"epoch": 0.04,
"learning_rate": 1.6279835390946504e-05,
"loss": 1.0282,
"step": 264
},
{
"epoch": 0.04,
"learning_rate": 1.626337448559671e-05,
"loss": 1.17,
"step": 265
},
{
"epoch": 0.04,
"learning_rate": 1.6246913580246914e-05,
"loss": 1.0919,
"step": 266
},
{
"epoch": 0.04,
"learning_rate": 1.623045267489712e-05,
"loss": 0.9349,
"step": 267
},
{
"epoch": 0.04,
"learning_rate": 1.6213991769547325e-05,
"loss": 0.9435,
"step": 268
},
{
"epoch": 0.04,
"learning_rate": 1.6197530864197532e-05,
"loss": 0.8697,
"step": 269
},
{
"epoch": 0.04,
"learning_rate": 1.6181069958847736e-05,
"loss": 0.9858,
"step": 270
},
{
"epoch": 0.04,
"learning_rate": 1.6164609053497943e-05,
"loss": 1.0095,
"step": 271
},
{
"epoch": 0.04,
"learning_rate": 1.614814814814815e-05,
"loss": 0.9618,
"step": 272
},
{
"epoch": 0.04,
"learning_rate": 1.6131687242798357e-05,
"loss": 1.0359,
"step": 273
},
{
"epoch": 0.04,
"learning_rate": 1.611522633744856e-05,
"loss": 1.0359,
"step": 274
},
{
"epoch": 0.04,
"learning_rate": 1.6098765432098767e-05,
"loss": 1.094,
"step": 275
},
{
"epoch": 0.04,
"learning_rate": 1.6082304526748974e-05,
"loss": 1.0095,
"step": 276
},
{
"epoch": 0.04,
"learning_rate": 1.6065843621399178e-05,
"loss": 1.0735,
"step": 277
},
{
"epoch": 0.04,
"learning_rate": 1.6049382716049385e-05,
"loss": 1.0709,
"step": 278
},
{
"epoch": 0.04,
"learning_rate": 1.603292181069959e-05,
"loss": 0.9953,
"step": 279
},
{
"epoch": 0.04,
"learning_rate": 1.6016460905349796e-05,
"loss": 1.0546,
"step": 280
},
{
"epoch": 0.04,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.9659,
"step": 281
},
{
"epoch": 0.04,
"learning_rate": 1.5983539094650206e-05,
"loss": 0.9779,
"step": 282
},
{
"epoch": 0.04,
"learning_rate": 1.5967078189300413e-05,
"loss": 0.9917,
"step": 283
},
{
"epoch": 0.04,
"learning_rate": 1.5950617283950617e-05,
"loss": 0.9199,
"step": 284
},
{
"epoch": 0.04,
"learning_rate": 1.5934156378600824e-05,
"loss": 0.9744,
"step": 285
},
{
"epoch": 0.04,
"learning_rate": 1.5917695473251028e-05,
"loss": 0.9035,
"step": 286
},
{
"epoch": 0.04,
"learning_rate": 1.5901234567901235e-05,
"loss": 1.0672,
"step": 287
},
{
"epoch": 0.04,
"learning_rate": 1.588477366255144e-05,
"loss": 1.064,
"step": 288
},
{
"epoch": 0.04,
"learning_rate": 1.586831275720165e-05,
"loss": 1.0102,
"step": 289
},
{
"epoch": 0.04,
"learning_rate": 1.5851851851851852e-05,
"loss": 1.0592,
"step": 290
},
{
"epoch": 0.04,
"learning_rate": 1.583539094650206e-05,
"loss": 1.0461,
"step": 291
},
{
"epoch": 0.04,
"learning_rate": 1.5818930041152266e-05,
"loss": 1.0964,
"step": 292
},
{
"epoch": 0.04,
"learning_rate": 1.580246913580247e-05,
"loss": 1.0379,
"step": 293
},
{
"epoch": 0.04,
"learning_rate": 1.5786008230452677e-05,
"loss": 1.2736,
"step": 294
},
{
"epoch": 0.04,
"learning_rate": 1.5769547325102884e-05,
"loss": 1.0701,
"step": 295
},
{
"epoch": 0.04,
"learning_rate": 1.5753086419753088e-05,
"loss": 1.1316,
"step": 296
},
{
"epoch": 0.04,
"learning_rate": 1.5736625514403295e-05,
"loss": 0.9894,
"step": 297
},
{
"epoch": 0.04,
"learning_rate": 1.5720164609053498e-05,
"loss": 1.1578,
"step": 298
},
{
"epoch": 0.04,
"learning_rate": 1.5703703703703705e-05,
"loss": 1.1571,
"step": 299
},
{
"epoch": 0.04,
"learning_rate": 1.568724279835391e-05,
"loss": 1.1343,
"step": 300
},
{
"epoch": 0.04,
"learning_rate": 1.5670781893004116e-05,
"loss": 1.0028,
"step": 301
},
{
"epoch": 0.04,
"learning_rate": 1.565432098765432e-05,
"loss": 0.9467,
"step": 302
},
{
"epoch": 0.04,
"learning_rate": 1.5637860082304527e-05,
"loss": 1.0402,
"step": 303
},
{
"epoch": 0.04,
"learning_rate": 1.5621399176954734e-05,
"loss": 1.0729,
"step": 304
},
{
"epoch": 0.04,
"learning_rate": 1.560493827160494e-05,
"loss": 1.0536,
"step": 305
},
{
"epoch": 0.04,
"learning_rate": 1.5588477366255144e-05,
"loss": 1.1481,
"step": 306
},
{
"epoch": 0.04,
"learning_rate": 1.557201646090535e-05,
"loss": 1.1258,
"step": 307
},
{
"epoch": 0.04,
"learning_rate": 1.555555555555556e-05,
"loss": 1.1179,
"step": 308
},
{
"epoch": 0.04,
"learning_rate": 1.5539094650205762e-05,
"loss": 1.0529,
"step": 309
},
{
"epoch": 0.04,
"learning_rate": 1.552263374485597e-05,
"loss": 1.0538,
"step": 310
},
{
"epoch": 0.04,
"learning_rate": 1.5506172839506176e-05,
"loss": 1.0784,
"step": 311
},
{
"epoch": 0.04,
"learning_rate": 1.548971193415638e-05,
"loss": 1.0694,
"step": 312
},
{
"epoch": 0.04,
"learning_rate": 1.5473251028806587e-05,
"loss": 0.9842,
"step": 313
},
{
"epoch": 0.04,
"learning_rate": 1.545679012345679e-05,
"loss": 0.9911,
"step": 314
},
{
"epoch": 0.04,
"learning_rate": 1.5440329218106997e-05,
"loss": 0.9561,
"step": 315
},
{
"epoch": 0.04,
"learning_rate": 1.54238683127572e-05,
"loss": 1.0082,
"step": 316
},
{
"epoch": 0.04,
"learning_rate": 1.5407407407407408e-05,
"loss": 0.9215,
"step": 317
},
{
"epoch": 0.04,
"learning_rate": 1.5390946502057615e-05,
"loss": 1.0174,
"step": 318
},
{
"epoch": 0.05,
"learning_rate": 1.537448559670782e-05,
"loss": 1.0129,
"step": 319
},
{
"epoch": 0.05,
"learning_rate": 1.5358024691358026e-05,
"loss": 1.1066,
"step": 320
},
{
"epoch": 0.05,
"learning_rate": 1.5341563786008233e-05,
"loss": 1.0391,
"step": 321
},
{
"epoch": 0.05,
"learning_rate": 1.5325102880658436e-05,
"loss": 1.1072,
"step": 322
},
{
"epoch": 0.05,
"learning_rate": 1.5308641975308643e-05,
"loss": 1.1493,
"step": 323
},
{
"epoch": 0.05,
"learning_rate": 1.529218106995885e-05,
"loss": 1.0418,
"step": 324
},
{
"epoch": 0.05,
"learning_rate": 1.5275720164609057e-05,
"loss": 1.0518,
"step": 325
},
{
"epoch": 0.05,
"learning_rate": 1.525925925925926e-05,
"loss": 1.0781,
"step": 326
},
{
"epoch": 0.05,
"learning_rate": 1.5242798353909466e-05,
"loss": 1.1851,
"step": 327
},
{
"epoch": 0.05,
"learning_rate": 1.5226337448559672e-05,
"loss": 1.0541,
"step": 328
},
{
"epoch": 0.05,
"learning_rate": 1.5209876543209879e-05,
"loss": 1.0266,
"step": 329
},
{
"epoch": 0.05,
"learning_rate": 1.5193415637860082e-05,
"loss": 0.9709,
"step": 330
},
{
"epoch": 0.05,
"learning_rate": 1.517695473251029e-05,
"loss": 0.9325,
"step": 331
},
{
"epoch": 0.05,
"learning_rate": 1.5160493827160495e-05,
"loss": 0.9415,
"step": 332
},
{
"epoch": 0.05,
"learning_rate": 1.51440329218107e-05,
"loss": 1.0526,
"step": 333
},
{
"epoch": 0.05,
"learning_rate": 1.5127572016460907e-05,
"loss": 1.0372,
"step": 334
},
{
"epoch": 0.05,
"learning_rate": 1.5111111111111112e-05,
"loss": 1.0553,
"step": 335
},
{
"epoch": 0.05,
"learning_rate": 1.509465020576132e-05,
"loss": 1.0267,
"step": 336
},
{
"epoch": 0.05,
"learning_rate": 1.5078189300411523e-05,
"loss": 1.0489,
"step": 337
},
{
"epoch": 0.05,
"learning_rate": 1.506172839506173e-05,
"loss": 1.1434,
"step": 338
},
{
"epoch": 0.05,
"learning_rate": 1.5045267489711934e-05,
"loss": 0.9498,
"step": 339
},
{
"epoch": 0.05,
"learning_rate": 1.502880658436214e-05,
"loss": 0.8822,
"step": 340
},
{
"epoch": 0.05,
"learning_rate": 1.5012345679012348e-05,
"loss": 0.9624,
"step": 341
},
{
"epoch": 0.05,
"learning_rate": 1.4995884773662553e-05,
"loss": 1.1541,
"step": 342
},
{
"epoch": 0.05,
"learning_rate": 1.4979423868312758e-05,
"loss": 1.1122,
"step": 343
},
{
"epoch": 0.05,
"learning_rate": 1.4962962962962964e-05,
"loss": 0.9543,
"step": 344
},
{
"epoch": 0.05,
"learning_rate": 1.494650205761317e-05,
"loss": 1.1048,
"step": 345
},
{
"epoch": 0.05,
"learning_rate": 1.4930041152263374e-05,
"loss": 0.9729,
"step": 346
},
{
"epoch": 0.05,
"learning_rate": 1.4913580246913581e-05,
"loss": 0.9737,
"step": 347
},
{
"epoch": 0.05,
"learning_rate": 1.4897119341563788e-05,
"loss": 0.9169,
"step": 348
},
{
"epoch": 0.05,
"learning_rate": 1.4880658436213992e-05,
"loss": 1.0849,
"step": 349
},
{
"epoch": 0.05,
"learning_rate": 1.4864197530864199e-05,
"loss": 1.0365,
"step": 350
},
{
"epoch": 0.05,
"learning_rate": 1.4847736625514404e-05,
"loss": 1.0824,
"step": 351
},
{
"epoch": 0.05,
"learning_rate": 1.4831275720164611e-05,
"loss": 1.0517,
"step": 352
},
{
"epoch": 0.05,
"learning_rate": 1.4814814814814815e-05,
"loss": 1.0526,
"step": 353
},
{
"epoch": 0.05,
"learning_rate": 1.4798353909465022e-05,
"loss": 0.9509,
"step": 354
},
{
"epoch": 0.05,
"learning_rate": 1.4781893004115229e-05,
"loss": 0.8995,
"step": 355
},
{
"epoch": 0.05,
"learning_rate": 1.4765432098765433e-05,
"loss": 0.9317,
"step": 356
},
{
"epoch": 0.05,
"learning_rate": 1.474897119341564e-05,
"loss": 1.0613,
"step": 357
},
{
"epoch": 0.05,
"learning_rate": 1.4732510288065845e-05,
"loss": 0.9504,
"step": 358
},
{
"epoch": 0.05,
"learning_rate": 1.471604938271605e-05,
"loss": 0.8927,
"step": 359
},
{
"epoch": 0.05,
"learning_rate": 1.4699588477366256e-05,
"loss": 1.0056,
"step": 360
},
{
"epoch": 0.05,
"learning_rate": 1.4683127572016463e-05,
"loss": 1.024,
"step": 361
},
{
"epoch": 0.05,
"learning_rate": 1.4666666666666666e-05,
"loss": 1.0015,
"step": 362
},
{
"epoch": 0.05,
"learning_rate": 1.4650205761316873e-05,
"loss": 0.9922,
"step": 363
},
{
"epoch": 0.05,
"learning_rate": 1.463374485596708e-05,
"loss": 0.9541,
"step": 364
},
{
"epoch": 0.05,
"learning_rate": 1.4617283950617284e-05,
"loss": 1.0441,
"step": 365
},
{
"epoch": 0.05,
"learning_rate": 1.4600823045267491e-05,
"loss": 0.968,
"step": 366
},
{
"epoch": 0.05,
"learning_rate": 1.4584362139917696e-05,
"loss": 0.9912,
"step": 367
},
{
"epoch": 0.05,
"learning_rate": 1.4567901234567903e-05,
"loss": 0.9521,
"step": 368
},
{
"epoch": 0.05,
"learning_rate": 1.4551440329218107e-05,
"loss": 1.1217,
"step": 369
},
{
"epoch": 0.05,
"learning_rate": 1.4534979423868314e-05,
"loss": 0.9222,
"step": 370
},
{
"epoch": 0.05,
"learning_rate": 1.4518518518518521e-05,
"loss": 1.0547,
"step": 371
},
{
"epoch": 0.05,
"learning_rate": 1.4502057613168725e-05,
"loss": 1.095,
"step": 372
},
{
"epoch": 0.05,
"learning_rate": 1.4485596707818932e-05,
"loss": 0.8783,
"step": 373
},
{
"epoch": 0.05,
"learning_rate": 1.4469135802469137e-05,
"loss": 1.1016,
"step": 374
},
{
"epoch": 0.05,
"learning_rate": 1.4452674897119342e-05,
"loss": 1.0765,
"step": 375
},
{
"epoch": 0.05,
"learning_rate": 1.4436213991769548e-05,
"loss": 1.0556,
"step": 376
},
{
"epoch": 0.05,
"learning_rate": 1.4419753086419755e-05,
"loss": 1.0816,
"step": 377
},
{
"epoch": 0.05,
"learning_rate": 1.4403292181069962e-05,
"loss": 0.907,
"step": 378
},
{
"epoch": 0.05,
"learning_rate": 1.4386831275720165e-05,
"loss": 1.0292,
"step": 379
},
{
"epoch": 0.05,
"learning_rate": 1.4370370370370372e-05,
"loss": 0.9094,
"step": 380
},
{
"epoch": 0.05,
"learning_rate": 1.4353909465020578e-05,
"loss": 0.9327,
"step": 381
},
{
"epoch": 0.05,
"learning_rate": 1.4337448559670783e-05,
"loss": 0.9394,
"step": 382
},
{
"epoch": 0.05,
"learning_rate": 1.4320987654320988e-05,
"loss": 0.9977,
"step": 383
},
{
"epoch": 0.05,
"learning_rate": 1.4304526748971195e-05,
"loss": 1.1002,
"step": 384
},
{
"epoch": 0.05,
"learning_rate": 1.4288065843621399e-05,
"loss": 0.8877,
"step": 385
},
{
"epoch": 0.05,
"learning_rate": 1.4271604938271606e-05,
"loss": 0.9889,
"step": 386
},
{
"epoch": 0.05,
"learning_rate": 1.4255144032921813e-05,
"loss": 0.8992,
"step": 387
},
{
"epoch": 0.05,
"learning_rate": 1.4238683127572017e-05,
"loss": 0.9379,
"step": 388
},
{
"epoch": 0.06,
"learning_rate": 1.4222222222222224e-05,
"loss": 0.9436,
"step": 389
},
{
"epoch": 0.06,
"learning_rate": 1.4205761316872429e-05,
"loss": 1.0277,
"step": 390
},
{
"epoch": 0.06,
"learning_rate": 1.4189300411522636e-05,
"loss": 1.0469,
"step": 391
},
{
"epoch": 0.06,
"learning_rate": 1.417283950617284e-05,
"loss": 0.9465,
"step": 392
},
{
"epoch": 0.06,
"learning_rate": 1.4156378600823047e-05,
"loss": 0.928,
"step": 393
},
{
"epoch": 0.06,
"learning_rate": 1.4139917695473254e-05,
"loss": 1.0752,
"step": 394
},
{
"epoch": 0.06,
"learning_rate": 1.4123456790123457e-05,
"loss": 0.9346,
"step": 395
},
{
"epoch": 0.06,
"learning_rate": 1.4106995884773664e-05,
"loss": 0.9594,
"step": 396
},
{
"epoch": 0.06,
"learning_rate": 1.409053497942387e-05,
"loss": 1.0107,
"step": 397
},
{
"epoch": 0.06,
"learning_rate": 1.4074074074074075e-05,
"loss": 0.9988,
"step": 398
},
{
"epoch": 0.06,
"learning_rate": 1.405761316872428e-05,
"loss": 1.0611,
"step": 399
},
{
"epoch": 0.06,
"learning_rate": 1.4041152263374487e-05,
"loss": 0.9946,
"step": 400
},
{
"epoch": 0.06,
"learning_rate": 1.4024691358024694e-05,
"loss": 0.9682,
"step": 401
},
{
"epoch": 0.06,
"learning_rate": 1.4008230452674898e-05,
"loss": 0.881,
"step": 402
},
{
"epoch": 0.06,
"learning_rate": 1.3991769547325105e-05,
"loss": 1.0052,
"step": 403
},
{
"epoch": 0.06,
"learning_rate": 1.3975308641975309e-05,
"loss": 0.9103,
"step": 404
},
{
"epoch": 0.06,
"learning_rate": 1.3958847736625516e-05,
"loss": 0.8972,
"step": 405
},
{
"epoch": 0.06,
"learning_rate": 1.3942386831275721e-05,
"loss": 1.0199,
"step": 406
},
{
"epoch": 0.06,
"learning_rate": 1.3925925925925928e-05,
"loss": 0.9253,
"step": 407
},
{
"epoch": 0.06,
"learning_rate": 1.3909465020576133e-05,
"loss": 0.9232,
"step": 408
},
{
"epoch": 0.06,
"learning_rate": 1.3893004115226339e-05,
"loss": 0.9453,
"step": 409
},
{
"epoch": 0.06,
"learning_rate": 1.3876543209876546e-05,
"loss": 0.9329,
"step": 410
},
{
"epoch": 0.06,
"learning_rate": 1.386008230452675e-05,
"loss": 0.9699,
"step": 411
},
{
"epoch": 0.06,
"learning_rate": 1.3843621399176956e-05,
"loss": 0.9594,
"step": 412
},
{
"epoch": 0.06,
"learning_rate": 1.3827160493827162e-05,
"loss": 0.9635,
"step": 413
},
{
"epoch": 0.06,
"learning_rate": 1.3810699588477367e-05,
"loss": 1.0724,
"step": 414
},
{
"epoch": 0.06,
"learning_rate": 1.3794238683127572e-05,
"loss": 0.9907,
"step": 415
},
{
"epoch": 0.06,
"learning_rate": 1.377777777777778e-05,
"loss": 0.9986,
"step": 416
},
{
"epoch": 0.06,
"learning_rate": 1.3761316872427986e-05,
"loss": 0.9383,
"step": 417
},
{
"epoch": 0.06,
"learning_rate": 1.374485596707819e-05,
"loss": 1.0464,
"step": 418
},
{
"epoch": 0.06,
"learning_rate": 1.3728395061728397e-05,
"loss": 0.972,
"step": 419
},
{
"epoch": 0.06,
"learning_rate": 1.37119341563786e-05,
"loss": 0.8984,
"step": 420
},
{
"epoch": 0.06,
"learning_rate": 1.3695473251028808e-05,
"loss": 1.0289,
"step": 421
},
{
"epoch": 0.06,
"learning_rate": 1.3679012345679013e-05,
"loss": 1.0084,
"step": 422
},
{
"epoch": 0.06,
"learning_rate": 1.366255144032922e-05,
"loss": 0.9695,
"step": 423
},
{
"epoch": 0.06,
"learning_rate": 1.3646090534979425e-05,
"loss": 1.0034,
"step": 424
},
{
"epoch": 0.06,
"learning_rate": 1.362962962962963e-05,
"loss": 0.9311,
"step": 425
},
{
"epoch": 0.06,
"learning_rate": 1.3613168724279838e-05,
"loss": 1.0491,
"step": 426
},
{
"epoch": 0.06,
"learning_rate": 1.3596707818930041e-05,
"loss": 1.0019,
"step": 427
},
{
"epoch": 0.06,
"learning_rate": 1.3580246913580248e-05,
"loss": 0.9684,
"step": 428
},
{
"epoch": 0.06,
"learning_rate": 1.3563786008230454e-05,
"loss": 1.0375,
"step": 429
},
{
"epoch": 0.06,
"learning_rate": 1.3547325102880659e-05,
"loss": 0.936,
"step": 430
},
{
"epoch": 0.06,
"learning_rate": 1.3530864197530866e-05,
"loss": 0.9626,
"step": 431
},
{
"epoch": 0.06,
"learning_rate": 1.3514403292181071e-05,
"loss": 0.8943,
"step": 432
},
{
"epoch": 0.06,
"learning_rate": 1.3497942386831278e-05,
"loss": 1.0094,
"step": 433
},
{
"epoch": 0.06,
"learning_rate": 1.3481481481481482e-05,
"loss": 0.9154,
"step": 434
},
{
"epoch": 0.06,
"learning_rate": 1.3465020576131689e-05,
"loss": 0.93,
"step": 435
},
{
"epoch": 0.06,
"learning_rate": 1.3448559670781893e-05,
"loss": 0.9672,
"step": 436
},
{
"epoch": 0.06,
"learning_rate": 1.34320987654321e-05,
"loss": 0.9761,
"step": 437
},
{
"epoch": 0.06,
"learning_rate": 1.3415637860082307e-05,
"loss": 0.9848,
"step": 438
},
{
"epoch": 0.06,
"learning_rate": 1.3399176954732512e-05,
"loss": 1.0087,
"step": 439
},
{
"epoch": 0.06,
"learning_rate": 1.3382716049382717e-05,
"loss": 1.008,
"step": 440
},
{
"epoch": 0.06,
"learning_rate": 1.3366255144032923e-05,
"loss": 1.041,
"step": 441
},
{
"epoch": 0.06,
"learning_rate": 1.334979423868313e-05,
"loss": 0.8952,
"step": 442
},
{
"epoch": 0.06,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.9657,
"step": 443
},
{
"epoch": 0.06,
"learning_rate": 1.331687242798354e-05,
"loss": 1.0101,
"step": 444
},
{
"epoch": 0.06,
"learning_rate": 1.3300411522633746e-05,
"loss": 0.9346,
"step": 445
},
{
"epoch": 0.06,
"learning_rate": 1.3283950617283951e-05,
"loss": 0.961,
"step": 446
},
{
"epoch": 0.06,
"learning_rate": 1.3267489711934158e-05,
"loss": 0.9417,
"step": 447
},
{
"epoch": 0.06,
"learning_rate": 1.3251028806584363e-05,
"loss": 0.9372,
"step": 448
},
{
"epoch": 0.06,
"learning_rate": 1.323456790123457e-05,
"loss": 0.9536,
"step": 449
},
{
"epoch": 0.06,
"learning_rate": 1.3218106995884774e-05,
"loss": 0.957,
"step": 450
},
{
"epoch": 0.06,
"learning_rate": 1.3201646090534981e-05,
"loss": 0.9326,
"step": 451
},
{
"epoch": 0.06,
"learning_rate": 1.3185185185185185e-05,
"loss": 0.9298,
"step": 452
},
{
"epoch": 0.06,
"learning_rate": 1.3168724279835392e-05,
"loss": 0.9881,
"step": 453
},
{
"epoch": 0.06,
"learning_rate": 1.3152263374485599e-05,
"loss": 0.9827,
"step": 454
},
{
"epoch": 0.06,
"learning_rate": 1.3135802469135804e-05,
"loss": 0.9693,
"step": 455
},
{
"epoch": 0.06,
"learning_rate": 1.311934156378601e-05,
"loss": 0.8531,
"step": 456
},
{
"epoch": 0.06,
"learning_rate": 1.3102880658436215e-05,
"loss": 0.929,
"step": 457
},
{
"epoch": 0.06,
"learning_rate": 1.3086419753086422e-05,
"loss": 1.1433,
"step": 458
},
{
"epoch": 0.06,
"learning_rate": 1.3069958847736625e-05,
"loss": 1.0321,
"step": 459
},
{
"epoch": 0.07,
"learning_rate": 1.3053497942386832e-05,
"loss": 1.0393,
"step": 460
},
{
"epoch": 0.07,
"learning_rate": 1.303703703703704e-05,
"loss": 0.9525,
"step": 461
},
{
"epoch": 0.07,
"learning_rate": 1.3020576131687243e-05,
"loss": 0.9497,
"step": 462
},
{
"epoch": 0.07,
"learning_rate": 1.300411522633745e-05,
"loss": 0.9661,
"step": 463
},
{
"epoch": 0.07,
"learning_rate": 1.2987654320987655e-05,
"loss": 0.9187,
"step": 464
},
{
"epoch": 0.07,
"learning_rate": 1.2971193415637862e-05,
"loss": 0.932,
"step": 465
},
{
"epoch": 0.07,
"learning_rate": 1.2954732510288066e-05,
"loss": 1.0016,
"step": 466
},
{
"epoch": 0.07,
"learning_rate": 1.2938271604938273e-05,
"loss": 0.9858,
"step": 467
},
{
"epoch": 0.07,
"learning_rate": 1.2921810699588477e-05,
"loss": 1.0164,
"step": 468
},
{
"epoch": 0.07,
"learning_rate": 1.2905349794238684e-05,
"loss": 1.0032,
"step": 469
},
{
"epoch": 0.07,
"learning_rate": 1.288888888888889e-05,
"loss": 1.0028,
"step": 470
},
{
"epoch": 0.07,
"learning_rate": 1.2872427983539096e-05,
"loss": 0.8651,
"step": 471
},
{
"epoch": 0.07,
"learning_rate": 1.2855967078189301e-05,
"loss": 0.9147,
"step": 472
},
{
"epoch": 0.07,
"learning_rate": 1.2839506172839507e-05,
"loss": 0.8979,
"step": 473
},
{
"epoch": 0.07,
"learning_rate": 1.2823045267489714e-05,
"loss": 1.0485,
"step": 474
},
{
"epoch": 0.07,
"learning_rate": 1.2806584362139917e-05,
"loss": 1.0153,
"step": 475
},
{
"epoch": 0.07,
"learning_rate": 1.2790123456790124e-05,
"loss": 0.9301,
"step": 476
},
{
"epoch": 0.07,
"learning_rate": 1.2773662551440331e-05,
"loss": 0.9498,
"step": 477
},
{
"epoch": 0.07,
"learning_rate": 1.2757201646090535e-05,
"loss": 1.0876,
"step": 478
},
{
"epoch": 0.07,
"learning_rate": 1.2740740740740742e-05,
"loss": 0.9355,
"step": 479
},
{
"epoch": 0.07,
"learning_rate": 1.2724279835390947e-05,
"loss": 1.0122,
"step": 480
},
{
"epoch": 0.07,
"learning_rate": 1.2707818930041154e-05,
"loss": 0.9826,
"step": 481
},
{
"epoch": 0.07,
"learning_rate": 1.2691358024691358e-05,
"loss": 1.0108,
"step": 482
},
{
"epoch": 0.07,
"learning_rate": 1.2674897119341565e-05,
"loss": 0.9705,
"step": 483
},
{
"epoch": 0.07,
"learning_rate": 1.2658436213991772e-05,
"loss": 0.9385,
"step": 484
},
{
"epoch": 0.07,
"learning_rate": 1.2641975308641976e-05,
"loss": 1.0155,
"step": 485
},
{
"epoch": 0.07,
"learning_rate": 1.2625514403292183e-05,
"loss": 0.9185,
"step": 486
},
{
"epoch": 0.07,
"learning_rate": 1.2609053497942388e-05,
"loss": 1.0073,
"step": 487
},
{
"epoch": 0.07,
"learning_rate": 1.2592592592592593e-05,
"loss": 0.9324,
"step": 488
},
{
"epoch": 0.07,
"learning_rate": 1.2576131687242799e-05,
"loss": 1.0555,
"step": 489
},
{
"epoch": 0.07,
"learning_rate": 1.2559670781893006e-05,
"loss": 0.9906,
"step": 490
},
{
"epoch": 0.07,
"learning_rate": 1.2543209876543213e-05,
"loss": 0.9306,
"step": 491
},
{
"epoch": 0.07,
"learning_rate": 1.2526748971193416e-05,
"loss": 0.9454,
"step": 492
},
{
"epoch": 0.07,
"learning_rate": 1.2510288065843623e-05,
"loss": 0.866,
"step": 493
},
{
"epoch": 0.07,
"learning_rate": 1.2493827160493827e-05,
"loss": 0.9542,
"step": 494
},
{
"epoch": 0.07,
"learning_rate": 1.2477366255144034e-05,
"loss": 0.8917,
"step": 495
},
{
"epoch": 0.07,
"learning_rate": 1.246090534979424e-05,
"loss": 0.9321,
"step": 496
},
{
"epoch": 0.07,
"learning_rate": 1.2444444444444446e-05,
"loss": 1.0921,
"step": 497
},
{
"epoch": 0.07,
"learning_rate": 1.242798353909465e-05,
"loss": 0.8781,
"step": 498
},
{
"epoch": 0.07,
"learning_rate": 1.2411522633744857e-05,
"loss": 0.8599,
"step": 499
},
{
"epoch": 0.07,
"learning_rate": 1.2395061728395064e-05,
"loss": 0.9962,
"step": 500
}
],
"logging_steps": 1.0,
"max_steps": 1253,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"total_flos": 0.0,
"train_batch_size": null,
"trial_name": null,
"trial_params": null
}