exgra-med-dci / trainer_state.json
taindp98's picture
Add files using upload-large-folder tool
88f3e38 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"global_step": 1329,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 5.000000000000001e-07,
"loss": 2.7921,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 1.0000000000000002e-06,
"loss": 2.7341,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 1.5e-06,
"loss": 2.8151,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 2.0000000000000003e-06,
"loss": 2.7216,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 2.5e-06,
"loss": 2.5898,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 3e-06,
"loss": 2.7029,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 3.5e-06,
"loss": 2.6816,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 4.000000000000001e-06,
"loss": 2.6626,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 4.5e-06,
"loss": 2.5352,
"step": 9
},
{
"epoch": 0.02,
"learning_rate": 5e-06,
"loss": 2.5139,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 5.500000000000001e-06,
"loss": 2.6674,
"step": 11
},
{
"epoch": 0.03,
"learning_rate": 6e-06,
"loss": 2.5652,
"step": 12
},
{
"epoch": 0.03,
"learning_rate": 6.5000000000000004e-06,
"loss": 2.5165,
"step": 13
},
{
"epoch": 0.03,
"learning_rate": 7e-06,
"loss": 2.4227,
"step": 14
},
{
"epoch": 0.03,
"learning_rate": 7.500000000000001e-06,
"loss": 2.4806,
"step": 15
},
{
"epoch": 0.04,
"learning_rate": 8.000000000000001e-06,
"loss": 2.5979,
"step": 16
},
{
"epoch": 0.04,
"learning_rate": 8.5e-06,
"loss": 2.4325,
"step": 17
},
{
"epoch": 0.04,
"learning_rate": 9e-06,
"loss": 2.2942,
"step": 18
},
{
"epoch": 0.04,
"learning_rate": 9.5e-06,
"loss": 2.4361,
"step": 19
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 2.4365,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 1.0500000000000001e-05,
"loss": 2.2536,
"step": 21
},
{
"epoch": 0.05,
"learning_rate": 1.1000000000000001e-05,
"loss": 2.2818,
"step": 22
},
{
"epoch": 0.05,
"learning_rate": 1.15e-05,
"loss": 2.304,
"step": 23
},
{
"epoch": 0.05,
"learning_rate": 1.2e-05,
"loss": 2.1969,
"step": 24
},
{
"epoch": 0.06,
"learning_rate": 1.25e-05,
"loss": 2.1164,
"step": 25
},
{
"epoch": 0.06,
"learning_rate": 1.3000000000000001e-05,
"loss": 2.2132,
"step": 26
},
{
"epoch": 0.06,
"learning_rate": 1.3500000000000001e-05,
"loss": 2.065,
"step": 27
},
{
"epoch": 0.06,
"learning_rate": 1.4e-05,
"loss": 2.0703,
"step": 28
},
{
"epoch": 0.07,
"learning_rate": 1.45e-05,
"loss": 1.9844,
"step": 29
},
{
"epoch": 0.07,
"learning_rate": 1.5000000000000002e-05,
"loss": 2.0265,
"step": 30
},
{
"epoch": 0.07,
"learning_rate": 1.55e-05,
"loss": 1.8093,
"step": 31
},
{
"epoch": 0.07,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.9518,
"step": 32
},
{
"epoch": 0.07,
"learning_rate": 1.65e-05,
"loss": 1.8611,
"step": 33
},
{
"epoch": 0.08,
"learning_rate": 1.7e-05,
"loss": 1.6355,
"step": 34
},
{
"epoch": 0.08,
"learning_rate": 1.7500000000000002e-05,
"loss": 1.7262,
"step": 35
},
{
"epoch": 0.08,
"learning_rate": 1.8e-05,
"loss": 1.6861,
"step": 36
},
{
"epoch": 0.08,
"learning_rate": 1.8500000000000002e-05,
"loss": 1.5701,
"step": 37
},
{
"epoch": 0.09,
"learning_rate": 1.9e-05,
"loss": 1.5863,
"step": 38
},
{
"epoch": 0.09,
"learning_rate": 1.95e-05,
"loss": 1.349,
"step": 39
},
{
"epoch": 0.09,
"learning_rate": 2e-05,
"loss": 1.3674,
"step": 40
},
{
"epoch": 0.09,
"learning_rate": 1.9999970299504145e-05,
"loss": 1.3706,
"step": 41
},
{
"epoch": 0.09,
"learning_rate": 1.9999881198192997e-05,
"loss": 1.3871,
"step": 42
},
{
"epoch": 0.1,
"learning_rate": 1.9999732696595825e-05,
"loss": 1.2545,
"step": 43
},
{
"epoch": 0.1,
"learning_rate": 1.999952479559475e-05,
"loss": 1.3386,
"step": 44
},
{
"epoch": 0.1,
"learning_rate": 1.999925749642472e-05,
"loss": 1.3576,
"step": 45
},
{
"epoch": 0.1,
"learning_rate": 1.999893080067352e-05,
"loss": 1.2272,
"step": 46
},
{
"epoch": 0.11,
"learning_rate": 1.9998544710281757e-05,
"loss": 1.2747,
"step": 47
},
{
"epoch": 0.11,
"learning_rate": 1.9998099227542843e-05,
"loss": 1.2944,
"step": 48
},
{
"epoch": 0.11,
"learning_rate": 1.9997594355102988e-05,
"loss": 1.243,
"step": 49
},
{
"epoch": 0.11,
"learning_rate": 1.999703009596119e-05,
"loss": 1.1542,
"step": 50
},
{
"epoch": 0.12,
"learning_rate": 1.99964064534692e-05,
"loss": 1.1436,
"step": 51
},
{
"epoch": 0.12,
"learning_rate": 1.9995723431331517e-05,
"loss": 1.2183,
"step": 52
},
{
"epoch": 0.12,
"learning_rate": 1.9994981033605364e-05,
"loss": 1.1039,
"step": 53
},
{
"epoch": 0.12,
"learning_rate": 1.999417926470065e-05,
"loss": 1.1347,
"step": 54
},
{
"epoch": 0.12,
"learning_rate": 1.999331812937997e-05,
"loss": 1.1239,
"step": 55
},
{
"epoch": 0.13,
"learning_rate": 1.9992397632758545e-05,
"loss": 1.0616,
"step": 56
},
{
"epoch": 0.13,
"learning_rate": 1.999141778030422e-05,
"loss": 1.1196,
"step": 57
},
{
"epoch": 0.13,
"learning_rate": 1.999037857783742e-05,
"loss": 1.0849,
"step": 58
},
{
"epoch": 0.13,
"learning_rate": 1.9989280031531103e-05,
"loss": 1.0734,
"step": 59
},
{
"epoch": 0.14,
"learning_rate": 1.998812214791075e-05,
"loss": 1.0206,
"step": 60
},
{
"epoch": 0.14,
"learning_rate": 1.99869049338543e-05,
"loss": 0.9276,
"step": 61
},
{
"epoch": 0.14,
"learning_rate": 1.9985628396592122e-05,
"loss": 1.0207,
"step": 62
},
{
"epoch": 0.14,
"learning_rate": 1.9984292543706982e-05,
"loss": 1.0138,
"step": 63
},
{
"epoch": 0.14,
"learning_rate": 1.9982897383133978e-05,
"loss": 0.9639,
"step": 64
},
{
"epoch": 0.15,
"learning_rate": 1.9981442923160494e-05,
"loss": 0.9498,
"step": 65
},
{
"epoch": 0.15,
"learning_rate": 1.9979929172426175e-05,
"loss": 1.0486,
"step": 66
},
{
"epoch": 0.15,
"learning_rate": 1.9978356139922844e-05,
"loss": 0.9061,
"step": 67
},
{
"epoch": 0.15,
"learning_rate": 1.9976723834994475e-05,
"loss": 1.0376,
"step": 68
},
{
"epoch": 0.16,
"learning_rate": 1.9975032267337122e-05,
"loss": 0.9994,
"step": 69
},
{
"epoch": 0.16,
"learning_rate": 1.997328144699886e-05,
"loss": 0.9606,
"step": 70
},
{
"epoch": 0.16,
"learning_rate": 1.9971471384379737e-05,
"loss": 0.942,
"step": 71
},
{
"epoch": 0.16,
"learning_rate": 1.9969602090231704e-05,
"loss": 0.9768,
"step": 72
},
{
"epoch": 0.16,
"learning_rate": 1.9967673575658554e-05,
"loss": 0.8961,
"step": 73
},
{
"epoch": 0.17,
"learning_rate": 1.996568585211586e-05,
"loss": 0.8958,
"step": 74
},
{
"epoch": 0.17,
"learning_rate": 1.9963638931410887e-05,
"loss": 0.9206,
"step": 75
},
{
"epoch": 0.17,
"learning_rate": 1.9961532825702553e-05,
"loss": 1.0313,
"step": 76
},
{
"epoch": 0.17,
"learning_rate": 1.9959367547501335e-05,
"loss": 0.9968,
"step": 77
},
{
"epoch": 0.18,
"learning_rate": 1.99571431096692e-05,
"loss": 0.8786,
"step": 78
},
{
"epoch": 0.18,
"learning_rate": 1.995485952541953e-05,
"loss": 0.9039,
"step": 79
},
{
"epoch": 0.18,
"learning_rate": 1.9952516808317036e-05,
"loss": 0.9654,
"step": 80
},
{
"epoch": 0.18,
"learning_rate": 1.9950114972277698e-05,
"loss": 0.8409,
"step": 81
},
{
"epoch": 0.19,
"learning_rate": 1.9947654031568657e-05,
"loss": 0.9234,
"step": 82
},
{
"epoch": 0.19,
"learning_rate": 1.9945134000808143e-05,
"loss": 0.8606,
"step": 83
},
{
"epoch": 0.19,
"learning_rate": 1.9942554894965392e-05,
"loss": 0.8819,
"step": 84
},
{
"epoch": 0.19,
"learning_rate": 1.9939916729360544e-05,
"loss": 0.9028,
"step": 85
},
{
"epoch": 0.19,
"learning_rate": 1.9937219519664567e-05,
"loss": 0.9007,
"step": 86
},
{
"epoch": 0.2,
"learning_rate": 1.9934463281899157e-05,
"loss": 0.8164,
"step": 87
},
{
"epoch": 0.2,
"learning_rate": 1.9931648032436634e-05,
"loss": 0.9644,
"step": 88
},
{
"epoch": 0.2,
"learning_rate": 1.992877378799986e-05,
"loss": 0.9359,
"step": 89
},
{
"epoch": 0.2,
"learning_rate": 1.992584056566214e-05,
"loss": 0.8641,
"step": 90
},
{
"epoch": 0.21,
"learning_rate": 1.9922848382847094e-05,
"loss": 0.9085,
"step": 91
},
{
"epoch": 0.21,
"learning_rate": 1.9919797257328596e-05,
"loss": 0.869,
"step": 92
},
{
"epoch": 0.21,
"learning_rate": 1.9916687207230622e-05,
"loss": 0.8349,
"step": 93
},
{
"epoch": 0.21,
"learning_rate": 1.9913518251027187e-05,
"loss": 0.8558,
"step": 94
},
{
"epoch": 0.21,
"learning_rate": 1.9910290407542202e-05,
"loss": 0.8784,
"step": 95
},
{
"epoch": 0.22,
"learning_rate": 1.9907003695949377e-05,
"loss": 0.8321,
"step": 96
},
{
"epoch": 0.22,
"learning_rate": 1.9903658135772106e-05,
"loss": 0.8658,
"step": 97
},
{
"epoch": 0.22,
"learning_rate": 1.9900253746883347e-05,
"loss": 0.8395,
"step": 98
},
{
"epoch": 0.22,
"learning_rate": 1.9896790549505508e-05,
"loss": 0.8121,
"step": 99
},
{
"epoch": 0.23,
"learning_rate": 1.9893268564210327e-05,
"loss": 0.8644,
"step": 100
},
{
"epoch": 0.23,
"learning_rate": 1.9889687811918744e-05,
"loss": 0.823,
"step": 101
},
{
"epoch": 0.23,
"learning_rate": 1.988604831390078e-05,
"loss": 0.9383,
"step": 102
},
{
"epoch": 0.23,
"learning_rate": 1.988235009177542e-05,
"loss": 0.7767,
"step": 103
},
{
"epoch": 0.23,
"learning_rate": 1.9878593167510466e-05,
"loss": 0.8295,
"step": 104
},
{
"epoch": 0.24,
"learning_rate": 1.9874777563422425e-05,
"loss": 0.8656,
"step": 105
},
{
"epoch": 0.24,
"learning_rate": 1.987090330217636e-05,
"loss": 0.8626,
"step": 106
},
{
"epoch": 0.24,
"learning_rate": 1.9866970406785763e-05,
"loss": 0.7942,
"step": 107
},
{
"epoch": 0.24,
"learning_rate": 1.9862978900612432e-05,
"loss": 0.8658,
"step": 108
},
{
"epoch": 0.25,
"learning_rate": 1.9858928807366303e-05,
"loss": 0.8264,
"step": 109
},
{
"epoch": 0.25,
"learning_rate": 1.985482015110533e-05,
"loss": 0.8445,
"step": 110
},
{
"epoch": 0.25,
"learning_rate": 1.9850652956235347e-05,
"loss": 0.8318,
"step": 111
},
{
"epoch": 0.25,
"learning_rate": 1.98464272475099e-05,
"loss": 0.7747,
"step": 112
},
{
"epoch": 0.26,
"learning_rate": 1.9842143050030115e-05,
"loss": 0.8545,
"step": 113
},
{
"epoch": 0.26,
"learning_rate": 1.9837800389244553e-05,
"loss": 0.8254,
"step": 114
},
{
"epoch": 0.26,
"learning_rate": 1.983339929094905e-05,
"loss": 0.7988,
"step": 115
},
{
"epoch": 0.26,
"learning_rate": 1.9828939781286564e-05,
"loss": 0.873,
"step": 116
},
{
"epoch": 0.26,
"learning_rate": 1.982442188674703e-05,
"loss": 0.7796,
"step": 117
},
{
"epoch": 0.27,
"learning_rate": 1.981984563416718e-05,
"loss": 0.8491,
"step": 118
},
{
"epoch": 0.27,
"learning_rate": 1.981521105073042e-05,
"loss": 0.7819,
"step": 119
},
{
"epoch": 0.27,
"learning_rate": 1.9810518163966627e-05,
"loss": 0.8041,
"step": 120
},
{
"epoch": 0.27,
"learning_rate": 1.9805767001752016e-05,
"loss": 0.8117,
"step": 121
},
{
"epoch": 0.28,
"learning_rate": 1.980095759230896e-05,
"loss": 0.8403,
"step": 122
},
{
"epoch": 0.28,
"learning_rate": 1.9796089964205832e-05,
"loss": 0.8192,
"step": 123
},
{
"epoch": 0.28,
"learning_rate": 1.9791164146356823e-05,
"loss": 0.806,
"step": 124
},
{
"epoch": 0.28,
"learning_rate": 1.978618016802178e-05,
"loss": 0.7675,
"step": 125
},
{
"epoch": 0.28,
"learning_rate": 1.978113805880603e-05,
"loss": 0.7825,
"step": 126
},
{
"epoch": 0.29,
"learning_rate": 1.9776037848660202e-05,
"loss": 0.7986,
"step": 127
},
{
"epoch": 0.29,
"learning_rate": 1.9770879567880046e-05,
"loss": 0.8481,
"step": 128
},
{
"epoch": 0.29,
"learning_rate": 1.9765663247106265e-05,
"loss": 0.7997,
"step": 129
},
{
"epoch": 0.29,
"learning_rate": 1.9760388917324317e-05,
"loss": 0.8009,
"step": 130
},
{
"epoch": 0.3,
"learning_rate": 1.975505660986425e-05,
"loss": 0.8215,
"step": 131
},
{
"epoch": 0.3,
"learning_rate": 1.97496663564005e-05,
"loss": 0.8177,
"step": 132
},
{
"epoch": 0.3,
"learning_rate": 1.9744218188951698e-05,
"loss": 0.8077,
"step": 133
},
{
"epoch": 0.3,
"learning_rate": 1.973871213988051e-05,
"loss": 0.6987,
"step": 134
},
{
"epoch": 0.3,
"learning_rate": 1.9733148241893403e-05,
"loss": 0.8333,
"step": 135
},
{
"epoch": 0.31,
"learning_rate": 1.972752652804049e-05,
"loss": 0.7606,
"step": 136
},
{
"epoch": 0.31,
"learning_rate": 1.972184703171531e-05,
"loss": 0.7712,
"step": 137
},
{
"epoch": 0.31,
"learning_rate": 1.9716109786654627e-05,
"loss": 0.789,
"step": 138
},
{
"epoch": 0.31,
"learning_rate": 1.9710314826938254e-05,
"loss": 0.7854,
"step": 139
},
{
"epoch": 0.32,
"learning_rate": 1.970446218698882e-05,
"loss": 0.7522,
"step": 140
},
{
"epoch": 0.32,
"learning_rate": 1.969855190157159e-05,
"loss": 0.8335,
"step": 141
},
{
"epoch": 0.32,
"learning_rate": 1.9692584005794245e-05,
"loss": 0.8291,
"step": 142
},
{
"epoch": 0.32,
"learning_rate": 1.9686558535106675e-05,
"loss": 0.7212,
"step": 143
},
{
"epoch": 0.33,
"learning_rate": 1.9680475525300778e-05,
"loss": 0.7672,
"step": 144
},
{
"epoch": 0.33,
"learning_rate": 1.967433501251023e-05,
"loss": 0.7229,
"step": 145
},
{
"epoch": 0.33,
"learning_rate": 1.9668137033210292e-05,
"loss": 0.7872,
"step": 146
},
{
"epoch": 0.33,
"learning_rate": 1.9661881624217573e-05,
"loss": 0.8126,
"step": 147
},
{
"epoch": 0.33,
"learning_rate": 1.9655568822689825e-05,
"loss": 0.8099,
"step": 148
},
{
"epoch": 0.34,
"learning_rate": 1.964919866612571e-05,
"loss": 0.7901,
"step": 149
},
{
"epoch": 0.34,
"learning_rate": 1.9642771192364593e-05,
"loss": 0.764,
"step": 150
},
{
"epoch": 0.34,
"learning_rate": 1.9636286439586303e-05,
"loss": 0.7654,
"step": 151
},
{
"epoch": 0.34,
"learning_rate": 1.962974444631092e-05,
"loss": 0.7325,
"step": 152
},
{
"epoch": 0.35,
"learning_rate": 1.9623145251398527e-05,
"loss": 0.7639,
"step": 153
},
{
"epoch": 0.35,
"learning_rate": 1.9616488894049e-05,
"loss": 0.7469,
"step": 154
},
{
"epoch": 0.35,
"learning_rate": 1.9609775413801763e-05,
"loss": 0.7931,
"step": 155
},
{
"epoch": 0.35,
"learning_rate": 1.9603004850535547e-05,
"loss": 0.7947,
"step": 156
},
{
"epoch": 0.35,
"learning_rate": 1.9596177244468177e-05,
"loss": 0.7884,
"step": 157
},
{
"epoch": 0.36,
"learning_rate": 1.9589292636156306e-05,
"loss": 0.7227,
"step": 158
},
{
"epoch": 0.36,
"learning_rate": 1.9582351066495193e-05,
"loss": 0.7837,
"step": 159
},
{
"epoch": 0.36,
"learning_rate": 1.957535257671845e-05,
"loss": 0.7729,
"step": 160
},
{
"epoch": 0.36,
"learning_rate": 1.95682972083978e-05,
"loss": 0.7594,
"step": 161
},
{
"epoch": 0.37,
"learning_rate": 1.9561185003442827e-05,
"loss": 0.7461,
"step": 162
},
{
"epoch": 0.37,
"learning_rate": 1.9554016004100734e-05,
"loss": 0.7548,
"step": 163
},
{
"epoch": 0.37,
"learning_rate": 1.9546790252956093e-05,
"loss": 0.795,
"step": 164
},
{
"epoch": 0.37,
"learning_rate": 1.9539507792930582e-05,
"loss": 0.7066,
"step": 165
},
{
"epoch": 0.37,
"learning_rate": 1.9532168667282732e-05,
"loss": 0.7259,
"step": 166
},
{
"epoch": 0.38,
"learning_rate": 1.952477291960768e-05,
"loss": 0.8147,
"step": 167
},
{
"epoch": 0.38,
"learning_rate": 1.9517320593836895e-05,
"loss": 0.7231,
"step": 168
},
{
"epoch": 0.38,
"learning_rate": 1.9509811734237938e-05,
"loss": 0.7954,
"step": 169
},
{
"epoch": 0.38,
"learning_rate": 1.9502246385414177e-05,
"loss": 0.7019,
"step": 170
},
{
"epoch": 0.39,
"learning_rate": 1.9494624592304536e-05,
"loss": 0.7428,
"step": 171
},
{
"epoch": 0.39,
"learning_rate": 1.948694640018322e-05,
"loss": 0.7203,
"step": 172
},
{
"epoch": 0.39,
"learning_rate": 1.947921185465945e-05,
"loss": 0.7101,
"step": 173
},
{
"epoch": 0.39,
"learning_rate": 1.94714210016772e-05,
"loss": 0.7192,
"step": 174
},
{
"epoch": 0.4,
"learning_rate": 1.9463573887514902e-05,
"loss": 0.7315,
"step": 175
},
{
"epoch": 0.4,
"learning_rate": 1.9455670558785195e-05,
"loss": 0.7302,
"step": 176
},
{
"epoch": 0.4,
"learning_rate": 1.9447711062434633e-05,
"loss": 0.7454,
"step": 177
},
{
"epoch": 0.4,
"learning_rate": 1.943969544574342e-05,
"loss": 0.7678,
"step": 178
},
{
"epoch": 0.4,
"learning_rate": 1.9431623756325112e-05,
"loss": 0.7147,
"step": 179
},
{
"epoch": 0.41,
"learning_rate": 1.942349604212634e-05,
"loss": 0.728,
"step": 180
},
{
"epoch": 0.41,
"learning_rate": 1.9415312351426533e-05,
"loss": 0.7975,
"step": 181
},
{
"epoch": 0.41,
"learning_rate": 1.940707273283763e-05,
"loss": 0.7226,
"step": 182
},
{
"epoch": 0.41,
"learning_rate": 1.9398777235303783e-05,
"loss": 0.7323,
"step": 183
},
{
"epoch": 0.42,
"learning_rate": 1.9390425908101063e-05,
"loss": 0.7481,
"step": 184
},
{
"epoch": 0.42,
"learning_rate": 1.938201880083719e-05,
"loss": 0.7388,
"step": 185
},
{
"epoch": 0.42,
"learning_rate": 1.9373555963451213e-05,
"loss": 0.7761,
"step": 186
},
{
"epoch": 0.42,
"learning_rate": 1.9365037446213216e-05,
"loss": 0.7655,
"step": 187
},
{
"epoch": 0.42,
"learning_rate": 1.9356463299724047e-05,
"loss": 0.7207,
"step": 188
},
{
"epoch": 0.43,
"learning_rate": 1.9347833574914985e-05,
"loss": 0.7057,
"step": 189
},
{
"epoch": 0.43,
"learning_rate": 1.9339148323047447e-05,
"loss": 0.7628,
"step": 190
},
{
"epoch": 0.43,
"learning_rate": 1.933040759571269e-05,
"loss": 0.7443,
"step": 191
},
{
"epoch": 0.43,
"learning_rate": 1.932161144483151e-05,
"loss": 0.759,
"step": 192
},
{
"epoch": 0.44,
"learning_rate": 1.9312759922653908e-05,
"loss": 0.7464,
"step": 193
},
{
"epoch": 0.44,
"learning_rate": 1.9303853081758803e-05,
"loss": 0.7177,
"step": 194
},
{
"epoch": 0.44,
"learning_rate": 1.9294890975053713e-05,
"loss": 0.7215,
"step": 195
},
{
"epoch": 0.44,
"learning_rate": 1.9285873655774447e-05,
"loss": 0.7209,
"step": 196
},
{
"epoch": 0.44,
"learning_rate": 1.927680117748477e-05,
"loss": 0.7786,
"step": 197
},
{
"epoch": 0.45,
"learning_rate": 1.9267673594076103e-05,
"loss": 0.7363,
"step": 198
},
{
"epoch": 0.45,
"learning_rate": 1.92584909597672e-05,
"loss": 0.7411,
"step": 199
},
{
"epoch": 0.45,
"learning_rate": 1.9249253329103817e-05,
"loss": 0.7043,
"step": 200
},
{
"epoch": 0.45,
"learning_rate": 1.92399607569584e-05,
"loss": 0.6569,
"step": 201
},
{
"epoch": 0.46,
"learning_rate": 1.923061329852974e-05,
"loss": 0.8199,
"step": 202
},
{
"epoch": 0.46,
"learning_rate": 1.9221211009342677e-05,
"loss": 0.7481,
"step": 203
},
{
"epoch": 0.46,
"learning_rate": 1.921175394524773e-05,
"loss": 0.8048,
"step": 204
},
{
"epoch": 0.46,
"learning_rate": 1.920224216242081e-05,
"loss": 0.7414,
"step": 205
},
{
"epoch": 0.47,
"learning_rate": 1.9192675717362847e-05,
"loss": 0.7315,
"step": 206
},
{
"epoch": 0.47,
"learning_rate": 1.918305466689947e-05,
"loss": 0.7091,
"step": 207
},
{
"epoch": 0.47,
"learning_rate": 1.917337906818067e-05,
"loss": 0.7026,
"step": 208
},
{
"epoch": 0.47,
"learning_rate": 1.916364897868047e-05,
"loss": 0.7258,
"step": 209
},
{
"epoch": 0.47,
"learning_rate": 1.9153864456196565e-05,
"loss": 0.7535,
"step": 210
},
{
"epoch": 0.48,
"learning_rate": 1.9144025558849987e-05,
"loss": 0.7199,
"step": 211
},
{
"epoch": 0.48,
"learning_rate": 1.913413234508476e-05,
"loss": 0.746,
"step": 212
},
{
"epoch": 0.48,
"learning_rate": 1.912418487366756e-05,
"loss": 0.7275,
"step": 213
},
{
"epoch": 0.48,
"learning_rate": 1.9114183203687352e-05,
"loss": 0.7451,
"step": 214
},
{
"epoch": 0.49,
"learning_rate": 1.9104127394555044e-05,
"loss": 0.7031,
"step": 215
},
{
"epoch": 0.49,
"learning_rate": 1.9094017506003144e-05,
"loss": 0.6917,
"step": 216
},
{
"epoch": 0.49,
"learning_rate": 1.908385359808539e-05,
"loss": 0.6952,
"step": 217
},
{
"epoch": 0.49,
"learning_rate": 1.9073635731176406e-05,
"loss": 0.6967,
"step": 218
},
{
"epoch": 0.49,
"learning_rate": 1.906336396597133e-05,
"loss": 0.724,
"step": 219
},
{
"epoch": 0.5,
"learning_rate": 1.905303836348547e-05,
"loss": 0.7074,
"step": 220
},
{
"epoch": 0.5,
"learning_rate": 1.904265898505393e-05,
"loss": 0.7079,
"step": 221
},
{
"epoch": 0.5,
"learning_rate": 1.9032225892331238e-05,
"loss": 0.7189,
"step": 222
},
{
"epoch": 0.5,
"learning_rate": 1.902173914729101e-05,
"loss": 0.7507,
"step": 223
},
{
"epoch": 0.51,
"learning_rate": 1.9011198812225548e-05,
"loss": 0.7258,
"step": 224
},
{
"epoch": 0.51,
"learning_rate": 1.9000604949745484e-05,
"loss": 0.7251,
"step": 225
},
{
"epoch": 0.51,
"learning_rate": 1.898995762277942e-05,
"loss": 0.7108,
"step": 226
},
{
"epoch": 0.51,
"learning_rate": 1.8979256894573525e-05,
"loss": 0.7447,
"step": 227
},
{
"epoch": 0.51,
"learning_rate": 1.896850282869119e-05,
"loss": 0.6982,
"step": 228
},
{
"epoch": 0.52,
"learning_rate": 1.8957695489012635e-05,
"loss": 0.7926,
"step": 229
},
{
"epoch": 0.52,
"learning_rate": 1.8946834939734526e-05,
"loss": 0.7088,
"step": 230
},
{
"epoch": 0.52,
"learning_rate": 1.8935921245369606e-05,
"loss": 0.6911,
"step": 231
},
{
"epoch": 0.52,
"learning_rate": 1.8924954470746296e-05,
"loss": 0.6635,
"step": 232
},
{
"epoch": 0.53,
"learning_rate": 1.8913934681008328e-05,
"loss": 0.7868,
"step": 233
},
{
"epoch": 0.53,
"learning_rate": 1.890286194161435e-05,
"loss": 0.7063,
"step": 234
},
{
"epoch": 0.53,
"learning_rate": 1.8891736318337525e-05,
"loss": 0.6989,
"step": 235
},
{
"epoch": 0.53,
"learning_rate": 1.8880557877265165e-05,
"loss": 0.6803,
"step": 236
},
{
"epoch": 0.53,
"learning_rate": 1.8869326684798315e-05,
"loss": 0.6633,
"step": 237
},
{
"epoch": 0.54,
"learning_rate": 1.885804280765137e-05,
"loss": 0.7379,
"step": 238
},
{
"epoch": 0.54,
"learning_rate": 1.8846706312851687e-05,
"loss": 0.7677,
"step": 239
},
{
"epoch": 0.54,
"learning_rate": 1.8835317267739158e-05,
"loss": 0.8168,
"step": 240
},
{
"epoch": 0.54,
"learning_rate": 1.882387573996585e-05,
"loss": 0.7371,
"step": 241
},
{
"epoch": 0.55,
"learning_rate": 1.881238179749557e-05,
"loss": 0.6967,
"step": 242
},
{
"epoch": 0.55,
"learning_rate": 1.8800835508603478e-05,
"loss": 0.7367,
"step": 243
},
{
"epoch": 0.55,
"learning_rate": 1.878923694187567e-05,
"loss": 0.6795,
"step": 244
},
{
"epoch": 0.55,
"learning_rate": 1.8777586166208786e-05,
"loss": 0.741,
"step": 245
},
{
"epoch": 0.56,
"learning_rate": 1.8765883250809586e-05,
"loss": 0.6769,
"step": 246
},
{
"epoch": 0.56,
"learning_rate": 1.8754128265194554e-05,
"loss": 0.7383,
"step": 247
},
{
"epoch": 0.56,
"learning_rate": 1.8742321279189465e-05,
"loss": 0.7208,
"step": 248
},
{
"epoch": 0.56,
"learning_rate": 1.873046236292899e-05,
"loss": 0.7576,
"step": 249
},
{
"epoch": 0.56,
"learning_rate": 1.871855158685626e-05,
"loss": 0.6826,
"step": 250
},
{
"epoch": 0.57,
"learning_rate": 1.870658902172248e-05,
"loss": 0.7316,
"step": 251
},
{
"epoch": 0.57,
"learning_rate": 1.869457473858646e-05,
"loss": 0.7603,
"step": 252
},
{
"epoch": 0.57,
"learning_rate": 1.868250880881424e-05,
"loss": 0.6663,
"step": 253
},
{
"epoch": 0.57,
"learning_rate": 1.867039130407864e-05,
"loss": 0.7768,
"step": 254
},
{
"epoch": 0.58,
"learning_rate": 1.8658222296358834e-05,
"loss": 0.6399,
"step": 255
},
{
"epoch": 0.58,
"learning_rate": 1.864600185793994e-05,
"loss": 0.6573,
"step": 256
},
{
"epoch": 0.58,
"learning_rate": 1.8633730061412575e-05,
"loss": 0.7238,
"step": 257
},
{
"epoch": 0.58,
"learning_rate": 1.8621406979672422e-05,
"loss": 0.6909,
"step": 258
},
{
"epoch": 0.58,
"learning_rate": 1.8609032685919815e-05,
"loss": 0.7015,
"step": 259
},
{
"epoch": 0.59,
"learning_rate": 1.8596607253659283e-05,
"loss": 0.7304,
"step": 260
},
{
"epoch": 0.59,
"learning_rate": 1.8584130756699122e-05,
"loss": 0.7332,
"step": 261
},
{
"epoch": 0.59,
"learning_rate": 1.857160326915097e-05,
"loss": 0.7717,
"step": 262
},
{
"epoch": 0.59,
"learning_rate": 1.8559024865429336e-05,
"loss": 0.6973,
"step": 263
},
{
"epoch": 0.6,
"learning_rate": 1.854639562025119e-05,
"loss": 0.6558,
"step": 264
},
{
"epoch": 0.6,
"learning_rate": 1.85337156086355e-05,
"loss": 0.7278,
"step": 265
},
{
"epoch": 0.6,
"learning_rate": 1.8520984905902798e-05,
"loss": 0.6709,
"step": 266
},
{
"epoch": 0.6,
"learning_rate": 1.8508203587674713e-05,
"loss": 0.6762,
"step": 267
},
{
"epoch": 0.6,
"learning_rate": 1.8495371729873545e-05,
"loss": 0.6915,
"step": 268
},
{
"epoch": 0.61,
"learning_rate": 1.8482489408721804e-05,
"loss": 0.6745,
"step": 269
},
{
"epoch": 0.61,
"learning_rate": 1.8469556700741755e-05,
"loss": 0.7015,
"step": 270
},
{
"epoch": 0.61,
"learning_rate": 1.845657368275496e-05,
"loss": 0.6914,
"step": 271
},
{
"epoch": 0.61,
"learning_rate": 1.8443540431881842e-05,
"loss": 0.7471,
"step": 272
},
{
"epoch": 0.62,
"learning_rate": 1.8430457025541203e-05,
"loss": 0.7049,
"step": 273
},
{
"epoch": 0.62,
"learning_rate": 1.841732354144977e-05,
"loss": 0.7247,
"step": 274
},
{
"epoch": 0.62,
"learning_rate": 1.8404140057621735e-05,
"loss": 0.7045,
"step": 275
},
{
"epoch": 0.62,
"learning_rate": 1.8390906652368313e-05,
"loss": 0.7241,
"step": 276
},
{
"epoch": 0.63,
"learning_rate": 1.8377623404297236e-05,
"loss": 0.7352,
"step": 277
},
{
"epoch": 0.63,
"learning_rate": 1.8364290392312318e-05,
"loss": 0.7272,
"step": 278
},
{
"epoch": 0.63,
"learning_rate": 1.8350907695612963e-05,
"loss": 0.734,
"step": 279
},
{
"epoch": 0.63,
"learning_rate": 1.833747539369373e-05,
"loss": 0.6458,
"step": 280
},
{
"epoch": 0.63,
"learning_rate": 1.8323993566343817e-05,
"loss": 0.7287,
"step": 281
},
{
"epoch": 0.64,
"learning_rate": 1.8310462293646617e-05,
"loss": 0.7266,
"step": 282
},
{
"epoch": 0.64,
"learning_rate": 1.829688165597923e-05,
"loss": 0.6643,
"step": 283
},
{
"epoch": 0.64,
"learning_rate": 1.8283251734011994e-05,
"loss": 0.6928,
"step": 284
},
{
"epoch": 0.64,
"learning_rate": 1.8269572608707995e-05,
"loss": 0.667,
"step": 285
},
{
"epoch": 0.65,
"learning_rate": 1.8255844361322594e-05,
"loss": 0.7104,
"step": 286
},
{
"epoch": 0.65,
"learning_rate": 1.8242067073402943e-05,
"loss": 0.7399,
"step": 287
},
{
"epoch": 0.65,
"learning_rate": 1.8228240826787497e-05,
"loss": 0.6967,
"step": 288
},
{
"epoch": 0.65,
"learning_rate": 1.821436570360553e-05,
"loss": 0.6748,
"step": 289
},
{
"epoch": 0.65,
"learning_rate": 1.8200441786276655e-05,
"loss": 0.6997,
"step": 290
},
{
"epoch": 0.66,
"learning_rate": 1.818646915751032e-05,
"loss": 0.7266,
"step": 291
},
{
"epoch": 0.66,
"learning_rate": 1.8172447900305327e-05,
"loss": 0.7751,
"step": 292
},
{
"epoch": 0.66,
"learning_rate": 1.8158378097949327e-05,
"loss": 0.6918,
"step": 293
},
{
"epoch": 0.66,
"learning_rate": 1.814425983401835e-05,
"loss": 0.6871,
"step": 294
},
{
"epoch": 0.67,
"learning_rate": 1.813009319237628e-05,
"loss": 0.718,
"step": 295
},
{
"epoch": 0.67,
"learning_rate": 1.8115878257174372e-05,
"loss": 0.6978,
"step": 296
},
{
"epoch": 0.67,
"learning_rate": 1.8101615112850752e-05,
"loss": 0.714,
"step": 297
},
{
"epoch": 0.67,
"learning_rate": 1.8087303844129915e-05,
"loss": 0.7054,
"step": 298
},
{
"epoch": 0.67,
"learning_rate": 1.8072944536022213e-05,
"loss": 0.7226,
"step": 299
},
{
"epoch": 0.68,
"learning_rate": 1.805853727382336e-05,
"loss": 0.6674,
"step": 300
},
{
"epoch": 0.68,
"learning_rate": 1.8044082143113924e-05,
"loss": 0.6867,
"step": 301
},
{
"epoch": 0.68,
"learning_rate": 1.8029579229758812e-05,
"loss": 0.7246,
"step": 302
},
{
"epoch": 0.68,
"learning_rate": 1.8015028619906774e-05,
"loss": 0.7068,
"step": 303
},
{
"epoch": 0.69,
"learning_rate": 1.8000430399989866e-05,
"loss": 0.7425,
"step": 304
},
{
"epoch": 0.69,
"learning_rate": 1.798578465672297e-05,
"loss": 0.7239,
"step": 305
},
{
"epoch": 0.69,
"learning_rate": 1.797109147710325e-05,
"loss": 0.7028,
"step": 306
},
{
"epoch": 0.69,
"learning_rate": 1.7956350948409655e-05,
"loss": 0.7167,
"step": 307
},
{
"epoch": 0.7,
"learning_rate": 1.7941563158202376e-05,
"loss": 0.6964,
"step": 308
},
{
"epoch": 0.7,
"learning_rate": 1.7926728194322364e-05,
"loss": 0.7107,
"step": 309
},
{
"epoch": 0.7,
"learning_rate": 1.7911846144890772e-05,
"loss": 0.7054,
"step": 310
},
{
"epoch": 0.7,
"learning_rate": 1.7896917098308448e-05,
"loss": 0.7115,
"step": 311
},
{
"epoch": 0.7,
"learning_rate": 1.7881941143255414e-05,
"loss": 0.7805,
"step": 312
},
{
"epoch": 0.71,
"learning_rate": 1.7866918368690324e-05,
"loss": 0.6673,
"step": 313
},
{
"epoch": 0.71,
"learning_rate": 1.7851848863849948e-05,
"loss": 0.7111,
"step": 314
},
{
"epoch": 0.71,
"learning_rate": 1.7836732718248644e-05,
"loss": 0.7082,
"step": 315
},
{
"epoch": 0.71,
"learning_rate": 1.782157002167781e-05,
"loss": 0.7505,
"step": 316
},
{
"epoch": 0.72,
"learning_rate": 1.780636086420537e-05,
"loss": 0.6944,
"step": 317
},
{
"epoch": 0.72,
"learning_rate": 1.779110533617523e-05,
"loss": 0.6788,
"step": 318
},
{
"epoch": 0.72,
"learning_rate": 1.7775803528206736e-05,
"loss": 0.7136,
"step": 319
},
{
"epoch": 0.72,
"learning_rate": 1.776045553119415e-05,
"loss": 0.6588,
"step": 320
},
{
"epoch": 0.72,
"learning_rate": 1.774506143630609e-05,
"loss": 0.6321,
"step": 321
},
{
"epoch": 0.73,
"learning_rate": 1.7729621334985005e-05,
"loss": 0.7047,
"step": 322
},
{
"epoch": 0.73,
"learning_rate": 1.7714135318946637e-05,
"loss": 0.705,
"step": 323
},
{
"epoch": 0.73,
"learning_rate": 1.769860348017945e-05,
"loss": 0.6682,
"step": 324
},
{
"epoch": 0.73,
"learning_rate": 1.768302591094411e-05,
"loss": 0.677,
"step": 325
},
{
"epoch": 0.74,
"learning_rate": 1.766740270377292e-05,
"loss": 0.7102,
"step": 326
},
{
"epoch": 0.74,
"learning_rate": 1.7651733951469283e-05,
"loss": 0.7166,
"step": 327
},
{
"epoch": 0.74,
"learning_rate": 1.763601974710714e-05,
"loss": 0.7296,
"step": 328
},
{
"epoch": 0.74,
"learning_rate": 1.7620260184030422e-05,
"loss": 0.6376,
"step": 329
},
{
"epoch": 0.74,
"learning_rate": 1.7604455355852498e-05,
"loss": 0.7293,
"step": 330
},
{
"epoch": 0.75,
"learning_rate": 1.7588605356455618e-05,
"loss": 0.7007,
"step": 331
},
{
"epoch": 0.75,
"learning_rate": 1.7572710279990345e-05,
"loss": 0.7327,
"step": 332
},
{
"epoch": 0.75,
"learning_rate": 1.7556770220875014e-05,
"loss": 0.7004,
"step": 333
},
{
"epoch": 0.75,
"learning_rate": 1.7540785273795152e-05,
"loss": 0.6465,
"step": 334
},
{
"epoch": 0.76,
"learning_rate": 1.7524755533702933e-05,
"loss": 0.7309,
"step": 335
},
{
"epoch": 0.76,
"learning_rate": 1.7508681095816603e-05,
"loss": 0.6871,
"step": 336
},
{
"epoch": 0.76,
"learning_rate": 1.7492562055619916e-05,
"loss": 0.6667,
"step": 337
},
{
"epoch": 0.76,
"learning_rate": 1.747639850886157e-05,
"loss": 0.6829,
"step": 338
},
{
"epoch": 0.77,
"learning_rate": 1.7460190551554633e-05,
"loss": 0.7077,
"step": 339
},
{
"epoch": 0.77,
"learning_rate": 1.7443938279975988e-05,
"loss": 0.7125,
"step": 340
},
{
"epoch": 0.77,
"learning_rate": 1.7427641790665728e-05,
"loss": 0.6544,
"step": 341
},
{
"epoch": 0.77,
"learning_rate": 1.741130118042662e-05,
"loss": 0.6815,
"step": 342
},
{
"epoch": 0.77,
"learning_rate": 1.7394916546323514e-05,
"loss": 0.7034,
"step": 343
},
{
"epoch": 0.78,
"learning_rate": 1.7378487985682758e-05,
"loss": 0.7322,
"step": 344
},
{
"epoch": 0.78,
"learning_rate": 1.736201559609163e-05,
"loss": 0.706,
"step": 345
},
{
"epoch": 0.78,
"learning_rate": 1.7345499475397756e-05,
"loss": 0.6743,
"step": 346
},
{
"epoch": 0.78,
"learning_rate": 1.732893972170854e-05,
"loss": 0.7012,
"step": 347
},
{
"epoch": 0.79,
"learning_rate": 1.7312336433390552e-05,
"loss": 0.7028,
"step": 348
},
{
"epoch": 0.79,
"learning_rate": 1.7295689709068974e-05,
"loss": 0.6783,
"step": 349
},
{
"epoch": 0.79,
"learning_rate": 1.7278999647626998e-05,
"loss": 0.7084,
"step": 350
},
{
"epoch": 0.79,
"learning_rate": 1.7262266348205246e-05,
"loss": 0.6949,
"step": 351
},
{
"epoch": 0.79,
"learning_rate": 1.7245489910201177e-05,
"loss": 0.7032,
"step": 352
},
{
"epoch": 0.8,
"learning_rate": 1.7228670433268494e-05,
"loss": 0.6914,
"step": 353
},
{
"epoch": 0.8,
"learning_rate": 1.721180801731656e-05,
"loss": 0.6878,
"step": 354
},
{
"epoch": 0.8,
"learning_rate": 1.71949027625098e-05,
"loss": 0.6693,
"step": 355
},
{
"epoch": 0.8,
"learning_rate": 1.7177954769267098e-05,
"loss": 0.6652,
"step": 356
},
{
"epoch": 0.81,
"learning_rate": 1.7160964138261217e-05,
"loss": 0.6961,
"step": 357
},
{
"epoch": 0.81,
"learning_rate": 1.7143930970418196e-05,
"loss": 0.6733,
"step": 358
},
{
"epoch": 0.81,
"learning_rate": 1.712685536691673e-05,
"loss": 0.6693,
"step": 359
},
{
"epoch": 0.81,
"learning_rate": 1.7109737429187604e-05,
"loss": 0.7208,
"step": 360
},
{
"epoch": 0.81,
"learning_rate": 1.709257725891307e-05,
"loss": 0.691,
"step": 361
},
{
"epoch": 0.82,
"learning_rate": 1.7075374958026235e-05,
"loss": 0.6782,
"step": 362
},
{
"epoch": 0.82,
"learning_rate": 1.7058130628710473e-05,
"loss": 0.6652,
"step": 363
},
{
"epoch": 0.82,
"learning_rate": 1.704084437339881e-05,
"loss": 0.7174,
"step": 364
},
{
"epoch": 0.82,
"learning_rate": 1.7023516294773318e-05,
"loss": 0.6752,
"step": 365
},
{
"epoch": 0.83,
"learning_rate": 1.7006146495764503e-05,
"loss": 0.6904,
"step": 366
},
{
"epoch": 0.83,
"learning_rate": 1.698873507955069e-05,
"loss": 0.7341,
"step": 367
},
{
"epoch": 0.83,
"learning_rate": 1.6971282149557428e-05,
"loss": 0.7794,
"step": 368
},
{
"epoch": 0.83,
"learning_rate": 1.695378780945684e-05,
"loss": 0.7369,
"step": 369
},
{
"epoch": 0.84,
"learning_rate": 1.6936252163167048e-05,
"loss": 0.68,
"step": 370
},
{
"epoch": 0.84,
"learning_rate": 1.6918675314851524e-05,
"loss": 0.6891,
"step": 371
},
{
"epoch": 0.84,
"learning_rate": 1.6901057368918497e-05,
"loss": 0.6794,
"step": 372
},
{
"epoch": 0.84,
"learning_rate": 1.6883398430020314e-05,
"loss": 0.6611,
"step": 373
},
{
"epoch": 0.84,
"learning_rate": 1.6865698603052813e-05,
"loss": 0.7198,
"step": 374
},
{
"epoch": 0.85,
"learning_rate": 1.6847957993154734e-05,
"loss": 0.6707,
"step": 375
},
{
"epoch": 0.85,
"learning_rate": 1.683017670570705e-05,
"loss": 0.6614,
"step": 376
},
{
"epoch": 0.85,
"learning_rate": 1.6812354846332376e-05,
"loss": 0.7048,
"step": 377
},
{
"epoch": 0.85,
"learning_rate": 1.6794492520894324e-05,
"loss": 0.6672,
"step": 378
},
{
"epoch": 0.86,
"learning_rate": 1.6776589835496878e-05,
"loss": 0.6745,
"step": 379
},
{
"epoch": 0.86,
"learning_rate": 1.6758646896483762e-05,
"loss": 0.7399,
"step": 380
},
{
"epoch": 0.86,
"learning_rate": 1.674066381043782e-05,
"loss": 0.6527,
"step": 381
},
{
"epoch": 0.86,
"learning_rate": 1.6722640684180354e-05,
"loss": 0.7013,
"step": 382
},
{
"epoch": 0.86,
"learning_rate": 1.6704577624770536e-05,
"loss": 0.6649,
"step": 383
},
{
"epoch": 0.87,
"learning_rate": 1.6686474739504723e-05,
"loss": 0.6718,
"step": 384
},
{
"epoch": 0.87,
"learning_rate": 1.666833213591585e-05,
"loss": 0.708,
"step": 385
},
{
"epoch": 0.87,
"learning_rate": 1.665014992177278e-05,
"loss": 0.6771,
"step": 386
},
{
"epoch": 0.87,
"learning_rate": 1.663192820507967e-05,
"loss": 0.6808,
"step": 387
},
{
"epoch": 0.88,
"learning_rate": 1.6613667094075324e-05,
"loss": 0.6663,
"step": 388
},
{
"epoch": 0.88,
"learning_rate": 1.659536669723255e-05,
"loss": 0.6487,
"step": 389
},
{
"epoch": 0.88,
"learning_rate": 1.6577027123257522e-05,
"loss": 0.6897,
"step": 390
},
{
"epoch": 0.88,
"learning_rate": 1.655864848108913e-05,
"loss": 0.6907,
"step": 391
},
{
"epoch": 0.88,
"learning_rate": 1.6540230879898327e-05,
"loss": 0.7152,
"step": 392
},
{
"epoch": 0.89,
"learning_rate": 1.6521774429087495e-05,
"loss": 0.6911,
"step": 393
},
{
"epoch": 0.89,
"learning_rate": 1.6503279238289776e-05,
"loss": 0.6503,
"step": 394
},
{
"epoch": 0.89,
"learning_rate": 1.6484745417368446e-05,
"loss": 0.6214,
"step": 395
},
{
"epoch": 0.89,
"learning_rate": 1.646617307641623e-05,
"loss": 0.7051,
"step": 396
},
{
"epoch": 0.9,
"learning_rate": 1.6447562325754683e-05,
"loss": 0.6916,
"step": 397
},
{
"epoch": 0.9,
"learning_rate": 1.642891327593351e-05,
"loss": 0.6816,
"step": 398
},
{
"epoch": 0.9,
"learning_rate": 1.641022603772991e-05,
"loss": 0.6798,
"step": 399
},
{
"epoch": 0.9,
"learning_rate": 1.639150072214793e-05,
"loss": 0.6688,
"step": 400
},
{
"epoch": 0.91,
"learning_rate": 1.637273744041781e-05,
"loss": 0.6512,
"step": 401
},
{
"epoch": 0.91,
"learning_rate": 1.63539363039953e-05,
"loss": 0.6907,
"step": 402
},
{
"epoch": 0.91,
"learning_rate": 1.6335097424561015e-05,
"loss": 0.635,
"step": 403
},
{
"epoch": 0.91,
"learning_rate": 1.6316220914019765e-05,
"loss": 0.699,
"step": 404
},
{
"epoch": 0.91,
"learning_rate": 1.6297306884499898e-05,
"loss": 0.7085,
"step": 405
},
{
"epoch": 0.92,
"learning_rate": 1.627835544835262e-05,
"loss": 0.6628,
"step": 406
},
{
"epoch": 0.92,
"learning_rate": 1.625936671815135e-05,
"loss": 0.7145,
"step": 407
},
{
"epoch": 0.92,
"learning_rate": 1.624034080669102e-05,
"loss": 0.7012,
"step": 408
},
{
"epoch": 0.92,
"learning_rate": 1.6221277826987435e-05,
"loss": 0.7415,
"step": 409
},
{
"epoch": 0.93,
"learning_rate": 1.6202177892276588e-05,
"loss": 0.6851,
"step": 410
},
{
"epoch": 0.93,
"learning_rate": 1.6183041116013976e-05,
"loss": 0.6706,
"step": 411
},
{
"epoch": 0.93,
"learning_rate": 1.6163867611873954e-05,
"loss": 0.6832,
"step": 412
},
{
"epoch": 0.93,
"learning_rate": 1.614465749374904e-05,
"loss": 0.7037,
"step": 413
},
{
"epoch": 0.93,
"learning_rate": 1.612541087574924e-05,
"loss": 0.6591,
"step": 414
},
{
"epoch": 0.94,
"learning_rate": 1.6106127872201364e-05,
"loss": 0.6466,
"step": 415
},
{
"epoch": 0.94,
"learning_rate": 1.6086808597648377e-05,
"loss": 0.718,
"step": 416
},
{
"epoch": 0.94,
"learning_rate": 1.6067453166848682e-05,
"loss": 0.7338,
"step": 417
},
{
"epoch": 0.94,
"learning_rate": 1.6048061694775458e-05,
"loss": 0.6408,
"step": 418
},
{
"epoch": 0.95,
"learning_rate": 1.6028634296615973e-05,
"loss": 0.6511,
"step": 419
},
{
"epoch": 0.95,
"learning_rate": 1.6009171087770895e-05,
"loss": 0.6559,
"step": 420
},
{
"epoch": 0.95,
"learning_rate": 1.598967218385362e-05,
"loss": 0.7159,
"step": 421
},
{
"epoch": 0.95,
"learning_rate": 1.5970137700689567e-05,
"loss": 0.7021,
"step": 422
},
{
"epoch": 0.95,
"learning_rate": 1.5950567754315504e-05,
"loss": 0.6726,
"step": 423
},
{
"epoch": 0.96,
"learning_rate": 1.593096246097885e-05,
"loss": 0.6247,
"step": 424
},
{
"epoch": 0.96,
"learning_rate": 1.5911321937136997e-05,
"loss": 0.6916,
"step": 425
},
{
"epoch": 0.96,
"learning_rate": 1.5891646299456607e-05,
"loss": 0.6227,
"step": 426
},
{
"epoch": 0.96,
"learning_rate": 1.5871935664812913e-05,
"loss": 0.7073,
"step": 427
},
{
"epoch": 0.97,
"learning_rate": 1.585219015028904e-05,
"loss": 0.6513,
"step": 428
},
{
"epoch": 0.97,
"learning_rate": 1.58324098731753e-05,
"loss": 0.6828,
"step": 429
},
{
"epoch": 0.97,
"learning_rate": 1.581259495096851e-05,
"loss": 0.6997,
"step": 430
},
{
"epoch": 0.97,
"learning_rate": 1.5792745501371265e-05,
"loss": 0.6471,
"step": 431
},
{
"epoch": 0.98,
"learning_rate": 1.5772861642291266e-05,
"loss": 0.6449,
"step": 432
},
{
"epoch": 0.98,
"learning_rate": 1.5752943491840608e-05,
"loss": 0.646,
"step": 433
},
{
"epoch": 0.98,
"learning_rate": 1.5732991168335085e-05,
"loss": 0.6599,
"step": 434
},
{
"epoch": 0.98,
"learning_rate": 1.571300479029347e-05,
"loss": 0.7271,
"step": 435
},
{
"epoch": 0.98,
"learning_rate": 1.569298447643683e-05,
"loss": 0.6926,
"step": 436
},
{
"epoch": 0.99,
"learning_rate": 1.567293034568782e-05,
"loss": 0.6529,
"step": 437
},
{
"epoch": 0.99,
"learning_rate": 1.5652842517169968e-05,
"loss": 0.6807,
"step": 438
},
{
"epoch": 0.99,
"learning_rate": 1.563272111020696e-05,
"loss": 0.6908,
"step": 439
},
{
"epoch": 0.99,
"learning_rate": 1.5612566244321948e-05,
"loss": 0.6927,
"step": 440
},
{
"epoch": 1.0,
"learning_rate": 1.5592378039236843e-05,
"loss": 0.7129,
"step": 441
},
{
"epoch": 1.0,
"learning_rate": 1.5572156614871577e-05,
"loss": 0.6616,
"step": 442
},
{
"epoch": 1.0,
"learning_rate": 1.555190209134342e-05,
"loss": 0.6865,
"step": 443
},
{
"epoch": 1.0,
"learning_rate": 1.553161458896625e-05,
"loss": 0.4986,
"step": 444
},
{
"epoch": 1.0,
"learning_rate": 1.5511294228249845e-05,
"loss": 0.5378,
"step": 445
},
{
"epoch": 1.01,
"learning_rate": 1.549094112989916e-05,
"loss": 0.523,
"step": 446
},
{
"epoch": 1.01,
"learning_rate": 1.547055541481362e-05,
"loss": 0.5141,
"step": 447
},
{
"epoch": 1.01,
"learning_rate": 1.545013720408639e-05,
"loss": 0.4931,
"step": 448
},
{
"epoch": 1.01,
"learning_rate": 1.5429686619003672e-05,
"loss": 0.4841,
"step": 449
},
{
"epoch": 1.02,
"learning_rate": 1.5409203781043964e-05,
"loss": 0.5636,
"step": 450
},
{
"epoch": 1.02,
"learning_rate": 1.5388688811877357e-05,
"loss": 0.5198,
"step": 451
},
{
"epoch": 1.02,
"learning_rate": 1.5368141833364805e-05,
"loss": 0.4757,
"step": 452
},
{
"epoch": 1.02,
"learning_rate": 1.5347562967557395e-05,
"loss": 0.4768,
"step": 453
},
{
"epoch": 1.02,
"learning_rate": 1.5326952336695637e-05,
"loss": 0.5287,
"step": 454
},
{
"epoch": 1.03,
"learning_rate": 1.5306310063208712e-05,
"loss": 0.4694,
"step": 455
},
{
"epoch": 1.03,
"learning_rate": 1.5285636269713776e-05,
"loss": 0.5035,
"step": 456
},
{
"epoch": 1.03,
"learning_rate": 1.5264931079015216e-05,
"loss": 0.4959,
"step": 457
},
{
"epoch": 1.03,
"learning_rate": 1.5244194614103914e-05,
"loss": 0.5042,
"step": 458
},
{
"epoch": 1.04,
"learning_rate": 1.522342699815653e-05,
"loss": 0.4582,
"step": 459
},
{
"epoch": 1.04,
"learning_rate": 1.5202628354534762e-05,
"loss": 0.5145,
"step": 460
},
{
"epoch": 1.04,
"learning_rate": 1.5181798806784614e-05,
"loss": 0.4757,
"step": 461
},
{
"epoch": 1.04,
"learning_rate": 1.5160938478635667e-05,
"loss": 0.5436,
"step": 462
},
{
"epoch": 1.05,
"learning_rate": 1.5140047494000341e-05,
"loss": 0.4993,
"step": 463
},
{
"epoch": 1.05,
"learning_rate": 1.5119125976973152e-05,
"loss": 0.4807,
"step": 464
},
{
"epoch": 1.05,
"learning_rate": 1.509817405182999e-05,
"loss": 0.5208,
"step": 465
},
{
"epoch": 1.05,
"learning_rate": 1.5077191843027366e-05,
"loss": 0.4628,
"step": 466
},
{
"epoch": 1.05,
"learning_rate": 1.5056179475201683e-05,
"loss": 0.4791,
"step": 467
},
{
"epoch": 1.06,
"learning_rate": 1.5035137073168487e-05,
"loss": 0.4812,
"step": 468
},
{
"epoch": 1.06,
"learning_rate": 1.5014064761921736e-05,
"loss": 0.4742,
"step": 469
},
{
"epoch": 1.06,
"learning_rate": 1.4992962666633044e-05,
"loss": 0.4995,
"step": 470
},
{
"epoch": 1.06,
"learning_rate": 1.4971830912650953e-05,
"loss": 0.4637,
"step": 471
},
{
"epoch": 1.07,
"learning_rate": 1.4950669625500178e-05,
"loss": 0.5083,
"step": 472
},
{
"epoch": 1.07,
"learning_rate": 1.4929478930880862e-05,
"loss": 0.5213,
"step": 473
},
{
"epoch": 1.07,
"learning_rate": 1.4908258954667832e-05,
"loss": 0.4594,
"step": 474
},
{
"epoch": 1.07,
"learning_rate": 1.4887009822909853e-05,
"loss": 0.4824,
"step": 475
},
{
"epoch": 1.07,
"learning_rate": 1.486573166182887e-05,
"loss": 0.4934,
"step": 476
},
{
"epoch": 1.08,
"learning_rate": 1.4844424597819276e-05,
"loss": 0.4764,
"step": 477
},
{
"epoch": 1.08,
"learning_rate": 1.4823088757447144e-05,
"loss": 0.4725,
"step": 478
},
{
"epoch": 1.08,
"learning_rate": 1.4801724267449477e-05,
"loss": 0.5164,
"step": 479
},
{
"epoch": 1.08,
"learning_rate": 1.478033125473347e-05,
"loss": 0.5344,
"step": 480
},
{
"epoch": 1.09,
"learning_rate": 1.4758909846375736e-05,
"loss": 0.4889,
"step": 481
},
{
"epoch": 1.09,
"learning_rate": 1.4737460169621564e-05,
"loss": 0.4687,
"step": 482
},
{
"epoch": 1.09,
"learning_rate": 1.4715982351884166e-05,
"loss": 0.4993,
"step": 483
},
{
"epoch": 1.09,
"learning_rate": 1.4694476520743908e-05,
"loss": 0.4685,
"step": 484
},
{
"epoch": 1.09,
"learning_rate": 1.4672942803947556e-05,
"loss": 0.4834,
"step": 485
},
{
"epoch": 1.1,
"learning_rate": 1.4651381329407527e-05,
"loss": 0.4811,
"step": 486
},
{
"epoch": 1.1,
"learning_rate": 1.4629792225201115e-05,
"loss": 0.4497,
"step": 487
},
{
"epoch": 1.1,
"learning_rate": 1.460817561956974e-05,
"loss": 0.5004,
"step": 488
},
{
"epoch": 1.1,
"learning_rate": 1.458653164091819e-05,
"loss": 0.5071,
"step": 489
},
{
"epoch": 1.11,
"learning_rate": 1.4564860417813837e-05,
"loss": 0.5306,
"step": 490
},
{
"epoch": 1.11,
"learning_rate": 1.4543162078985898e-05,
"loss": 0.4839,
"step": 491
},
{
"epoch": 1.11,
"learning_rate": 1.4521436753324659e-05,
"loss": 0.4976,
"step": 492
},
{
"epoch": 1.11,
"learning_rate": 1.4499684569880705e-05,
"loss": 0.5096,
"step": 493
},
{
"epoch": 1.12,
"learning_rate": 1.4477905657864169e-05,
"loss": 0.47,
"step": 494
},
{
"epoch": 1.12,
"learning_rate": 1.4456100146643941e-05,
"loss": 0.4731,
"step": 495
},
{
"epoch": 1.12,
"learning_rate": 1.4434268165746925e-05,
"loss": 0.5398,
"step": 496
},
{
"epoch": 1.12,
"learning_rate": 1.441240984485725e-05,
"loss": 0.4744,
"step": 497
},
{
"epoch": 1.12,
"learning_rate": 1.4390525313815516e-05,
"loss": 0.4721,
"step": 498
},
{
"epoch": 1.13,
"learning_rate": 1.4368614702617997e-05,
"loss": 0.4635,
"step": 499
},
{
"epoch": 1.13,
"learning_rate": 1.4346678141415905e-05,
"loss": 0.4543,
"step": 500
},
{
"epoch": 1.13,
"learning_rate": 1.4324715760514588e-05,
"loss": 0.4941,
"step": 501
},
{
"epoch": 1.13,
"learning_rate": 1.4302727690372764e-05,
"loss": 0.4827,
"step": 502
},
{
"epoch": 1.14,
"learning_rate": 1.428071406160175e-05,
"loss": 0.4838,
"step": 503
},
{
"epoch": 1.14,
"learning_rate": 1.4258675004964687e-05,
"loss": 0.5128,
"step": 504
},
{
"epoch": 1.14,
"learning_rate": 1.4236610651375752e-05,
"loss": 0.5191,
"step": 505
},
{
"epoch": 1.14,
"learning_rate": 1.42145211318994e-05,
"loss": 0.4921,
"step": 506
},
{
"epoch": 1.14,
"learning_rate": 1.4192406577749562e-05,
"loss": 0.4979,
"step": 507
},
{
"epoch": 1.15,
"learning_rate": 1.4170267120288885e-05,
"loss": 0.5136,
"step": 508
},
{
"epoch": 1.15,
"learning_rate": 1.4148102891027943e-05,
"loss": 0.5089,
"step": 509
},
{
"epoch": 1.15,
"learning_rate": 1.4125914021624454e-05,
"loss": 0.504,
"step": 510
},
{
"epoch": 1.15,
"learning_rate": 1.4103700643882503e-05,
"loss": 0.4671,
"step": 511
},
{
"epoch": 1.16,
"learning_rate": 1.4081462889751756e-05,
"loss": 0.4766,
"step": 512
},
{
"epoch": 1.16,
"learning_rate": 1.4059200891326683e-05,
"loss": 0.4884,
"step": 513
},
{
"epoch": 1.16,
"learning_rate": 1.4036914780845757e-05,
"loss": 0.5225,
"step": 514
},
{
"epoch": 1.16,
"learning_rate": 1.4014604690690683e-05,
"loss": 0.4511,
"step": 515
},
{
"epoch": 1.16,
"learning_rate": 1.3992270753385614e-05,
"loss": 0.5009,
"step": 516
},
{
"epoch": 1.17,
"learning_rate": 1.3969913101596351e-05,
"loss": 0.4734,
"step": 517
},
{
"epoch": 1.17,
"learning_rate": 1.394753186812956e-05,
"loss": 0.4765,
"step": 518
},
{
"epoch": 1.17,
"learning_rate": 1.3925127185931993e-05,
"loss": 0.5218,
"step": 519
},
{
"epoch": 1.17,
"learning_rate": 1.3902699188089679e-05,
"loss": 0.4594,
"step": 520
},
{
"epoch": 1.18,
"learning_rate": 1.3880248007827151e-05,
"loss": 0.4988,
"step": 521
},
{
"epoch": 1.18,
"learning_rate": 1.3857773778506643e-05,
"loss": 0.5155,
"step": 522
},
{
"epoch": 1.18,
"learning_rate": 1.3835276633627313e-05,
"loss": 0.4867,
"step": 523
},
{
"epoch": 1.18,
"learning_rate": 1.3812756706824428e-05,
"loss": 0.5115,
"step": 524
},
{
"epoch": 1.19,
"learning_rate": 1.3790214131868588e-05,
"loss": 0.5179,
"step": 525
},
{
"epoch": 1.19,
"learning_rate": 1.3767649042664925e-05,
"loss": 0.4606,
"step": 526
},
{
"epoch": 1.19,
"learning_rate": 1.3745061573252305e-05,
"loss": 0.4803,
"step": 527
},
{
"epoch": 1.19,
"learning_rate": 1.3722451857802535e-05,
"loss": 0.4904,
"step": 528
},
{
"epoch": 1.19,
"learning_rate": 1.3699820030619569e-05,
"loss": 0.4961,
"step": 529
},
{
"epoch": 1.2,
"learning_rate": 1.3677166226138705e-05,
"loss": 0.5076,
"step": 530
},
{
"epoch": 1.2,
"learning_rate": 1.3654490578925788e-05,
"loss": 0.5081,
"step": 531
},
{
"epoch": 1.2,
"learning_rate": 1.3631793223676408e-05,
"loss": 0.4853,
"step": 532
},
{
"epoch": 1.2,
"learning_rate": 1.3609074295215113e-05,
"loss": 0.4963,
"step": 533
},
{
"epoch": 1.21,
"learning_rate": 1.3586333928494582e-05,
"loss": 0.4867,
"step": 534
},
{
"epoch": 1.21,
"learning_rate": 1.3563572258594854e-05,
"loss": 0.4955,
"step": 535
},
{
"epoch": 1.21,
"learning_rate": 1.3540789420722509e-05,
"loss": 0.4929,
"step": 536
},
{
"epoch": 1.21,
"learning_rate": 1.3517985550209859e-05,
"loss": 0.4945,
"step": 537
},
{
"epoch": 1.21,
"learning_rate": 1.3495160782514154e-05,
"loss": 0.5025,
"step": 538
},
{
"epoch": 1.22,
"learning_rate": 1.3472315253216782e-05,
"loss": 0.4861,
"step": 539
},
{
"epoch": 1.22,
"learning_rate": 1.3449449098022452e-05,
"loss": 0.4869,
"step": 540
},
{
"epoch": 1.22,
"learning_rate": 1.3426562452758391e-05,
"loss": 0.4765,
"step": 541
},
{
"epoch": 1.22,
"learning_rate": 1.3403655453373545e-05,
"loss": 0.4695,
"step": 542
},
{
"epoch": 1.23,
"learning_rate": 1.3380728235937758e-05,
"loss": 0.5029,
"step": 543
},
{
"epoch": 1.23,
"learning_rate": 1.3357780936640981e-05,
"loss": 0.4633,
"step": 544
},
{
"epoch": 1.23,
"learning_rate": 1.333481369179244e-05,
"loss": 0.5174,
"step": 545
},
{
"epoch": 1.23,
"learning_rate": 1.3311826637819856e-05,
"loss": 0.4974,
"step": 546
},
{
"epoch": 1.23,
"learning_rate": 1.32888199112686e-05,
"loss": 0.5198,
"step": 547
},
{
"epoch": 1.24,
"learning_rate": 1.3265793648800915e-05,
"loss": 0.4722,
"step": 548
},
{
"epoch": 1.24,
"learning_rate": 1.3242747987195084e-05,
"loss": 0.4951,
"step": 549
},
{
"epoch": 1.24,
"learning_rate": 1.3219683063344619e-05,
"loss": 0.4641,
"step": 550
},
{
"epoch": 1.24,
"learning_rate": 1.3196599014257459e-05,
"loss": 0.488,
"step": 551
},
{
"epoch": 1.25,
"learning_rate": 1.3173495977055142e-05,
"loss": 0.4812,
"step": 552
},
{
"epoch": 1.25,
"learning_rate": 1.3150374088972e-05,
"loss": 0.4926,
"step": 553
},
{
"epoch": 1.25,
"learning_rate": 1.3127233487354342e-05,
"loss": 0.4609,
"step": 554
},
{
"epoch": 1.25,
"learning_rate": 1.3104074309659637e-05,
"loss": 0.486,
"step": 555
},
{
"epoch": 1.26,
"learning_rate": 1.3080896693455699e-05,
"loss": 0.5201,
"step": 556
},
{
"epoch": 1.26,
"learning_rate": 1.305770077641986e-05,
"loss": 0.4515,
"step": 557
},
{
"epoch": 1.26,
"learning_rate": 1.3034486696338173e-05,
"loss": 0.531,
"step": 558
},
{
"epoch": 1.26,
"learning_rate": 1.3011254591104578e-05,
"loss": 0.5102,
"step": 559
},
{
"epoch": 1.26,
"learning_rate": 1.2988004598720083e-05,
"loss": 0.5289,
"step": 560
},
{
"epoch": 1.27,
"learning_rate": 1.2964736857291944e-05,
"loss": 0.4543,
"step": 561
},
{
"epoch": 1.27,
"learning_rate": 1.2941451505032857e-05,
"loss": 0.536,
"step": 562
},
{
"epoch": 1.27,
"learning_rate": 1.291814868026012e-05,
"loss": 0.5164,
"step": 563
},
{
"epoch": 1.27,
"learning_rate": 1.2894828521394824e-05,
"loss": 0.4949,
"step": 564
},
{
"epoch": 1.28,
"learning_rate": 1.2871491166961028e-05,
"loss": 0.5053,
"step": 565
},
{
"epoch": 1.28,
"learning_rate": 1.284813675558493e-05,
"loss": 0.4922,
"step": 566
},
{
"epoch": 1.28,
"learning_rate": 1.2824765425994047e-05,
"loss": 0.4764,
"step": 567
},
{
"epoch": 1.28,
"learning_rate": 1.2801377317016402e-05,
"loss": 0.4604,
"step": 568
},
{
"epoch": 1.28,
"learning_rate": 1.2777972567579673e-05,
"loss": 0.4804,
"step": 569
},
{
"epoch": 1.29,
"learning_rate": 1.2754551316710397e-05,
"loss": 0.4913,
"step": 570
},
{
"epoch": 1.29,
"learning_rate": 1.273111370353313e-05,
"loss": 0.4722,
"step": 571
},
{
"epoch": 1.29,
"learning_rate": 1.2707659867269613e-05,
"loss": 0.4883,
"step": 572
},
{
"epoch": 1.29,
"learning_rate": 1.2684189947237964e-05,
"loss": 0.5032,
"step": 573
},
{
"epoch": 1.3,
"learning_rate": 1.2660704082851831e-05,
"loss": 0.4544,
"step": 574
},
{
"epoch": 1.3,
"learning_rate": 1.263720241361958e-05,
"loss": 0.4866,
"step": 575
},
{
"epoch": 1.3,
"learning_rate": 1.2613685079143458e-05,
"loss": 0.4717,
"step": 576
},
{
"epoch": 1.3,
"learning_rate": 1.2590152219118762e-05,
"loss": 0.4628,
"step": 577
},
{
"epoch": 1.3,
"learning_rate": 1.2566603973333016e-05,
"loss": 0.5074,
"step": 578
},
{
"epoch": 1.31,
"learning_rate": 1.2543040481665134e-05,
"loss": 0.5163,
"step": 579
},
{
"epoch": 1.31,
"learning_rate": 1.2519461884084592e-05,
"loss": 0.4608,
"step": 580
},
{
"epoch": 1.31,
"learning_rate": 1.24958683206506e-05,
"loss": 0.4555,
"step": 581
},
{
"epoch": 1.31,
"learning_rate": 1.2472259931511265e-05,
"loss": 0.4877,
"step": 582
},
{
"epoch": 1.32,
"learning_rate": 1.244863685690276e-05,
"loss": 0.5046,
"step": 583
},
{
"epoch": 1.32,
"learning_rate": 1.242499923714849e-05,
"loss": 0.5057,
"step": 584
},
{
"epoch": 1.32,
"learning_rate": 1.240134721265826e-05,
"loss": 0.4941,
"step": 585
},
{
"epoch": 1.32,
"learning_rate": 1.237768092392744e-05,
"loss": 0.5013,
"step": 586
},
{
"epoch": 1.33,
"learning_rate": 1.2354000511536135e-05,
"loss": 0.4802,
"step": 587
},
{
"epoch": 1.33,
"learning_rate": 1.2330306116148344e-05,
"loss": 0.4923,
"step": 588
},
{
"epoch": 1.33,
"learning_rate": 1.230659787851112e-05,
"loss": 0.5112,
"step": 589
},
{
"epoch": 1.33,
"learning_rate": 1.228287593945375e-05,
"loss": 0.4823,
"step": 590
},
{
"epoch": 1.33,
"learning_rate": 1.22591404398869e-05,
"loss": 0.512,
"step": 591
},
{
"epoch": 1.34,
"learning_rate": 1.2235391520801801e-05,
"loss": 0.5106,
"step": 592
},
{
"epoch": 1.34,
"learning_rate": 1.2211629323269377e-05,
"loss": 0.4944,
"step": 593
},
{
"epoch": 1.34,
"learning_rate": 1.2187853988439442e-05,
"loss": 0.4953,
"step": 594
},
{
"epoch": 1.34,
"learning_rate": 1.2164065657539846e-05,
"loss": 0.4902,
"step": 595
},
{
"epoch": 1.35,
"learning_rate": 1.2140264471875627e-05,
"loss": 0.482,
"step": 596
},
{
"epoch": 1.35,
"learning_rate": 1.2116450572828194e-05,
"loss": 0.5075,
"step": 597
},
{
"epoch": 1.35,
"learning_rate": 1.2092624101854466e-05,
"loss": 0.5016,
"step": 598
},
{
"epoch": 1.35,
"learning_rate": 1.2068785200486044e-05,
"loss": 0.483,
"step": 599
},
{
"epoch": 1.35,
"learning_rate": 1.204493401032837e-05,
"loss": 0.4576,
"step": 600
},
{
"epoch": 1.36,
"learning_rate": 1.202107067305987e-05,
"loss": 0.4608,
"step": 601
},
{
"epoch": 1.36,
"learning_rate": 1.1997195330431141e-05,
"loss": 0.4803,
"step": 602
},
{
"epoch": 1.36,
"learning_rate": 1.1973308124264087e-05,
"loss": 0.4515,
"step": 603
},
{
"epoch": 1.36,
"learning_rate": 1.1949409196451073e-05,
"loss": 0.4808,
"step": 604
},
{
"epoch": 1.37,
"learning_rate": 1.1925498688954111e-05,
"loss": 0.4788,
"step": 605
},
{
"epoch": 1.37,
"learning_rate": 1.1901576743803984e-05,
"loss": 0.5234,
"step": 606
},
{
"epoch": 1.37,
"learning_rate": 1.1877643503099414e-05,
"loss": 0.4877,
"step": 607
},
{
"epoch": 1.37,
"learning_rate": 1.1853699109006227e-05,
"loss": 0.495,
"step": 608
},
{
"epoch": 1.37,
"learning_rate": 1.1829743703756498e-05,
"loss": 0.4853,
"step": 609
},
{
"epoch": 1.38,
"learning_rate": 1.1805777429647712e-05,
"loss": 0.5241,
"step": 610
},
{
"epoch": 1.38,
"learning_rate": 1.178180042904191e-05,
"loss": 0.4862,
"step": 611
},
{
"epoch": 1.38,
"learning_rate": 1.1757812844364855e-05,
"loss": 0.5476,
"step": 612
},
{
"epoch": 1.38,
"learning_rate": 1.173381481810518e-05,
"loss": 0.4532,
"step": 613
},
{
"epoch": 1.39,
"learning_rate": 1.1709806492813542e-05,
"loss": 0.4767,
"step": 614
},
{
"epoch": 1.39,
"learning_rate": 1.168578801110177e-05,
"loss": 0.4671,
"step": 615
},
{
"epoch": 1.39,
"learning_rate": 1.166175951564203e-05,
"loss": 0.5454,
"step": 616
},
{
"epoch": 1.39,
"learning_rate": 1.1637721149165971e-05,
"loss": 0.4776,
"step": 617
},
{
"epoch": 1.4,
"learning_rate": 1.161367305446387e-05,
"loss": 0.4916,
"step": 618
},
{
"epoch": 1.4,
"learning_rate": 1.1589615374383793e-05,
"loss": 0.4836,
"step": 619
},
{
"epoch": 1.4,
"learning_rate": 1.156554825183075e-05,
"loss": 0.46,
"step": 620
},
{
"epoch": 1.4,
"learning_rate": 1.1541471829765832e-05,
"loss": 0.5275,
"step": 621
},
{
"epoch": 1.4,
"learning_rate": 1.1517386251205375e-05,
"loss": 0.4816,
"step": 622
},
{
"epoch": 1.41,
"learning_rate": 1.1493291659220104e-05,
"loss": 0.5156,
"step": 623
},
{
"epoch": 1.41,
"learning_rate": 1.1469188196934289e-05,
"loss": 0.4918,
"step": 624
},
{
"epoch": 1.41,
"learning_rate": 1.1445076007524877e-05,
"loss": 0.4725,
"step": 625
},
{
"epoch": 1.41,
"learning_rate": 1.1420955234220675e-05,
"loss": 0.4952,
"step": 626
},
{
"epoch": 1.42,
"learning_rate": 1.1396826020301457e-05,
"loss": 0.4983,
"step": 627
},
{
"epoch": 1.42,
"learning_rate": 1.1372688509097158e-05,
"loss": 0.5061,
"step": 628
},
{
"epoch": 1.42,
"learning_rate": 1.1348542843986983e-05,
"loss": 0.4609,
"step": 629
},
{
"epoch": 1.42,
"learning_rate": 1.1324389168398576e-05,
"loss": 0.5053,
"step": 630
},
{
"epoch": 1.42,
"learning_rate": 1.1300227625807167e-05,
"loss": 0.4776,
"step": 631
},
{
"epoch": 1.43,
"learning_rate": 1.1276058359734719e-05,
"loss": 0.477,
"step": 632
},
{
"epoch": 1.43,
"learning_rate": 1.1251881513749062e-05,
"loss": 0.5003,
"step": 633
},
{
"epoch": 1.43,
"learning_rate": 1.1227697231463062e-05,
"loss": 0.5353,
"step": 634
},
{
"epoch": 1.43,
"learning_rate": 1.1203505656533756e-05,
"loss": 0.4741,
"step": 635
},
{
"epoch": 1.44,
"learning_rate": 1.1179306932661496e-05,
"loss": 0.464,
"step": 636
},
{
"epoch": 1.44,
"learning_rate": 1.1155101203589102e-05,
"loss": 0.4933,
"step": 637
},
{
"epoch": 1.44,
"learning_rate": 1.1130888613101007e-05,
"loss": 0.4678,
"step": 638
},
{
"epoch": 1.44,
"learning_rate": 1.1106669305022397e-05,
"loss": 0.5098,
"step": 639
},
{
"epoch": 1.44,
"learning_rate": 1.1082443423218366e-05,
"loss": 0.4637,
"step": 640
},
{
"epoch": 1.45,
"learning_rate": 1.1058211111593054e-05,
"loss": 0.4909,
"step": 641
},
{
"epoch": 1.45,
"learning_rate": 1.1033972514088793e-05,
"loss": 0.4746,
"step": 642
},
{
"epoch": 1.45,
"learning_rate": 1.1009727774685257e-05,
"loss": 0.5037,
"step": 643
},
{
"epoch": 1.45,
"learning_rate": 1.0985477037398606e-05,
"loss": 0.5255,
"step": 644
},
{
"epoch": 1.46,
"learning_rate": 1.096122044628062e-05,
"loss": 0.487,
"step": 645
},
{
"epoch": 1.46,
"learning_rate": 1.0936958145417858e-05,
"loss": 0.4664,
"step": 646
},
{
"epoch": 1.46,
"learning_rate": 1.0912690278930791e-05,
"loss": 0.518,
"step": 647
},
{
"epoch": 1.46,
"learning_rate": 1.0888416990972957e-05,
"loss": 0.4671,
"step": 648
},
{
"epoch": 1.47,
"learning_rate": 1.0864138425730088e-05,
"loss": 0.5023,
"step": 649
},
{
"epoch": 1.47,
"learning_rate": 1.0839854727419273e-05,
"loss": 0.4709,
"step": 650
},
{
"epoch": 1.47,
"learning_rate": 1.0815566040288088e-05,
"loss": 0.4959,
"step": 651
},
{
"epoch": 1.47,
"learning_rate": 1.0791272508613742e-05,
"loss": 0.4765,
"step": 652
},
{
"epoch": 1.47,
"learning_rate": 1.0766974276702227e-05,
"loss": 0.5163,
"step": 653
},
{
"epoch": 1.48,
"learning_rate": 1.0742671488887444e-05,
"loss": 0.503,
"step": 654
},
{
"epoch": 1.48,
"learning_rate": 1.0718364289530363e-05,
"loss": 0.5361,
"step": 655
},
{
"epoch": 1.48,
"learning_rate": 1.0694052823018164e-05,
"loss": 0.4615,
"step": 656
},
{
"epoch": 1.48,
"learning_rate": 1.0669737233763363e-05,
"loss": 0.5281,
"step": 657
},
{
"epoch": 1.49,
"learning_rate": 1.0645417666202978e-05,
"loss": 0.5149,
"step": 658
},
{
"epoch": 1.49,
"learning_rate": 1.0621094264797647e-05,
"loss": 0.4832,
"step": 659
},
{
"epoch": 1.49,
"learning_rate": 1.0596767174030786e-05,
"loss": 0.4707,
"step": 660
},
{
"epoch": 1.49,
"learning_rate": 1.0572436538407734e-05,
"loss": 0.4661,
"step": 661
},
{
"epoch": 1.49,
"learning_rate": 1.054810250245487e-05,
"loss": 0.4945,
"step": 662
},
{
"epoch": 1.5,
"learning_rate": 1.0523765210718783e-05,
"loss": 0.4644,
"step": 663
},
{
"epoch": 1.5,
"learning_rate": 1.0499424807765408e-05,
"loss": 0.4929,
"step": 664
},
{
"epoch": 1.5,
"learning_rate": 1.0475081438179143e-05,
"loss": 0.5048,
"step": 665
},
{
"epoch": 1.5,
"learning_rate": 1.045073524656202e-05,
"loss": 0.5006,
"step": 666
},
{
"epoch": 1.51,
"learning_rate": 1.0426386377532836e-05,
"loss": 0.4952,
"step": 667
},
{
"epoch": 1.51,
"learning_rate": 1.040203497572628e-05,
"loss": 0.486,
"step": 668
},
{
"epoch": 1.51,
"learning_rate": 1.0377681185792102e-05,
"loss": 0.5019,
"step": 669
},
{
"epoch": 1.51,
"learning_rate": 1.0353325152394222e-05,
"loss": 0.4907,
"step": 670
},
{
"epoch": 1.51,
"learning_rate": 1.03289670202099e-05,
"loss": 0.4565,
"step": 671
},
{
"epoch": 1.52,
"learning_rate": 1.030460693392885e-05,
"loss": 0.4783,
"step": 672
},
{
"epoch": 1.52,
"learning_rate": 1.0280245038252403e-05,
"loss": 0.4972,
"step": 673
},
{
"epoch": 1.52,
"learning_rate": 1.0255881477892639e-05,
"loss": 0.4406,
"step": 674
},
{
"epoch": 1.52,
"learning_rate": 1.0231516397571521e-05,
"loss": 0.4833,
"step": 675
},
{
"epoch": 1.53,
"learning_rate": 1.020714994202004e-05,
"loss": 0.5206,
"step": 676
},
{
"epoch": 1.53,
"learning_rate": 1.018278225597736e-05,
"loss": 0.4994,
"step": 677
},
{
"epoch": 1.53,
"learning_rate": 1.0158413484189955e-05,
"loss": 0.4812,
"step": 678
},
{
"epoch": 1.53,
"learning_rate": 1.0134043771410744e-05,
"loss": 0.4756,
"step": 679
},
{
"epoch": 1.53,
"learning_rate": 1.0109673262398234e-05,
"loss": 0.4962,
"step": 680
},
{
"epoch": 1.54,
"learning_rate": 1.0085302101915672e-05,
"loss": 0.5003,
"step": 681
},
{
"epoch": 1.54,
"learning_rate": 1.0060930434730162e-05,
"loss": 0.4872,
"step": 682
},
{
"epoch": 1.54,
"learning_rate": 1.0036558405611832e-05,
"loss": 0.4974,
"step": 683
},
{
"epoch": 1.54,
"learning_rate": 1.0012186159332944e-05,
"loss": 0.468,
"step": 684
},
{
"epoch": 1.55,
"learning_rate": 9.98781384066706e-06,
"loss": 0.5092,
"step": 685
},
{
"epoch": 1.55,
"learning_rate": 9.963441594388172e-06,
"loss": 0.4494,
"step": 686
},
{
"epoch": 1.55,
"learning_rate": 9.939069565269841e-06,
"loss": 0.4768,
"step": 687
},
{
"epoch": 1.55,
"learning_rate": 9.914697898084331e-06,
"loss": 0.4732,
"step": 688
},
{
"epoch": 1.56,
"learning_rate": 9.89032673760177e-06,
"loss": 0.4869,
"step": 689
},
{
"epoch": 1.56,
"learning_rate": 9.865956228589259e-06,
"loss": 0.5096,
"step": 690
},
{
"epoch": 1.56,
"learning_rate": 9.841586515810045e-06,
"loss": 0.4989,
"step": 691
},
{
"epoch": 1.56,
"learning_rate": 9.817217744022641e-06,
"loss": 0.4863,
"step": 692
},
{
"epoch": 1.56,
"learning_rate": 9.79285005797996e-06,
"loss": 0.4784,
"step": 693
},
{
"epoch": 1.57,
"learning_rate": 9.768483602428482e-06,
"loss": 0.4789,
"step": 694
},
{
"epoch": 1.57,
"learning_rate": 9.744118522107361e-06,
"loss": 0.5008,
"step": 695
},
{
"epoch": 1.57,
"learning_rate": 9.719754961747599e-06,
"loss": 0.4747,
"step": 696
},
{
"epoch": 1.57,
"learning_rate": 9.695393066071153e-06,
"loss": 0.5056,
"step": 697
},
{
"epoch": 1.58,
"learning_rate": 9.671032979790105e-06,
"loss": 0.4459,
"step": 698
},
{
"epoch": 1.58,
"learning_rate": 9.64667484760578e-06,
"loss": 0.4722,
"step": 699
},
{
"epoch": 1.58,
"learning_rate": 9.622318814207903e-06,
"loss": 0.4742,
"step": 700
},
{
"epoch": 1.58,
"learning_rate": 9.597965024273723e-06,
"loss": 0.4861,
"step": 701
},
{
"epoch": 1.58,
"learning_rate": 9.573613622467166e-06,
"loss": 0.4648,
"step": 702
},
{
"epoch": 1.59,
"learning_rate": 9.549264753437982e-06,
"loss": 0.447,
"step": 703
},
{
"epoch": 1.59,
"learning_rate": 9.524918561820857e-06,
"loss": 0.482,
"step": 704
},
{
"epoch": 1.59,
"learning_rate": 9.500575192234595e-06,
"loss": 0.4709,
"step": 705
},
{
"epoch": 1.59,
"learning_rate": 9.476234789281215e-06,
"loss": 0.4699,
"step": 706
},
{
"epoch": 1.6,
"learning_rate": 9.451897497545136e-06,
"loss": 0.485,
"step": 707
},
{
"epoch": 1.6,
"learning_rate": 9.427563461592271e-06,
"loss": 0.4359,
"step": 708
},
{
"epoch": 1.6,
"learning_rate": 9.403232825969217e-06,
"loss": 0.4802,
"step": 709
},
{
"epoch": 1.6,
"learning_rate": 9.378905735202356e-06,
"loss": 0.4492,
"step": 710
},
{
"epoch": 1.6,
"learning_rate": 9.354582333797027e-06,
"loss": 0.4567,
"step": 711
},
{
"epoch": 1.61,
"learning_rate": 9.330262766236638e-06,
"loss": 0.4409,
"step": 712
},
{
"epoch": 1.61,
"learning_rate": 9.305947176981843e-06,
"loss": 0.4808,
"step": 713
},
{
"epoch": 1.61,
"learning_rate": 9.281635710469639e-06,
"loss": 0.5058,
"step": 714
},
{
"epoch": 1.61,
"learning_rate": 9.25732851111256e-06,
"loss": 0.4882,
"step": 715
},
{
"epoch": 1.62,
"learning_rate": 9.233025723297776e-06,
"loss": 0.4833,
"step": 716
},
{
"epoch": 1.62,
"learning_rate": 9.208727491386258e-06,
"loss": 0.4576,
"step": 717
},
{
"epoch": 1.62,
"learning_rate": 9.184433959711916e-06,
"loss": 0.4642,
"step": 718
},
{
"epoch": 1.62,
"learning_rate": 9.160145272580729e-06,
"loss": 0.5047,
"step": 719
},
{
"epoch": 1.63,
"learning_rate": 9.135861574269917e-06,
"loss": 0.4651,
"step": 720
},
{
"epoch": 1.63,
"learning_rate": 9.111583009027048e-06,
"loss": 0.4636,
"step": 721
},
{
"epoch": 1.63,
"learning_rate": 9.087309721069214e-06,
"loss": 0.4919,
"step": 722
},
{
"epoch": 1.63,
"learning_rate": 9.063041854582145e-06,
"loss": 0.5028,
"step": 723
},
{
"epoch": 1.63,
"learning_rate": 9.038779553719386e-06,
"loss": 0.4978,
"step": 724
},
{
"epoch": 1.64,
"learning_rate": 9.014522962601398e-06,
"loss": 0.5048,
"step": 725
},
{
"epoch": 1.64,
"learning_rate": 8.990272225314743e-06,
"loss": 0.4566,
"step": 726
},
{
"epoch": 1.64,
"learning_rate": 8.96602748591121e-06,
"loss": 0.4825,
"step": 727
},
{
"epoch": 1.64,
"learning_rate": 8.941788888406948e-06,
"loss": 0.4986,
"step": 728
},
{
"epoch": 1.65,
"learning_rate": 8.917556576781638e-06,
"loss": 0.4832,
"step": 729
},
{
"epoch": 1.65,
"learning_rate": 8.893330694977606e-06,
"loss": 0.5103,
"step": 730
},
{
"epoch": 1.65,
"learning_rate": 8.869111386898997e-06,
"loss": 0.5006,
"step": 731
},
{
"epoch": 1.65,
"learning_rate": 8.844898796410901e-06,
"loss": 0.4608,
"step": 732
},
{
"epoch": 1.65,
"learning_rate": 8.820693067338507e-06,
"loss": 0.4743,
"step": 733
},
{
"epoch": 1.66,
"learning_rate": 8.796494343466247e-06,
"loss": 0.4819,
"step": 734
},
{
"epoch": 1.66,
"learning_rate": 8.772302768536943e-06,
"loss": 0.4596,
"step": 735
},
{
"epoch": 1.66,
"learning_rate": 8.748118486250942e-06,
"loss": 0.4981,
"step": 736
},
{
"epoch": 1.66,
"learning_rate": 8.723941640265283e-06,
"loss": 0.4984,
"step": 737
},
{
"epoch": 1.67,
"learning_rate": 8.699772374192835e-06,
"loss": 0.4786,
"step": 738
},
{
"epoch": 1.67,
"learning_rate": 8.675610831601424e-06,
"loss": 0.4938,
"step": 739
},
{
"epoch": 1.67,
"learning_rate": 8.65145715601302e-06,
"loss": 0.4579,
"step": 740
},
{
"epoch": 1.67,
"learning_rate": 8.627311490902843e-06,
"loss": 0.5083,
"step": 741
},
{
"epoch": 1.67,
"learning_rate": 8.603173979698544e-06,
"loss": 0.449,
"step": 742
},
{
"epoch": 1.68,
"learning_rate": 8.579044765779329e-06,
"loss": 0.5281,
"step": 743
},
{
"epoch": 1.68,
"learning_rate": 8.554923992475126e-06,
"loss": 0.5002,
"step": 744
},
{
"epoch": 1.68,
"learning_rate": 8.530811803065715e-06,
"loss": 0.4912,
"step": 745
},
{
"epoch": 1.68,
"learning_rate": 8.5067083407799e-06,
"loss": 0.4653,
"step": 746
},
{
"epoch": 1.69,
"learning_rate": 8.482613748794628e-06,
"loss": 0.5034,
"step": 747
},
{
"epoch": 1.69,
"learning_rate": 8.458528170234171e-06,
"loss": 0.4859,
"step": 748
},
{
"epoch": 1.69,
"learning_rate": 8.434451748169255e-06,
"loss": 0.4548,
"step": 749
},
{
"epoch": 1.69,
"learning_rate": 8.410384625616208e-06,
"loss": 0.4651,
"step": 750
},
{
"epoch": 1.7,
"learning_rate": 8.386326945536134e-06,
"loss": 0.5084,
"step": 751
},
{
"epoch": 1.7,
"learning_rate": 8.36227885083403e-06,
"loss": 0.4796,
"step": 752
},
{
"epoch": 1.7,
"learning_rate": 8.338240484357971e-06,
"loss": 0.489,
"step": 753
},
{
"epoch": 1.7,
"learning_rate": 8.31421198889823e-06,
"loss": 0.5035,
"step": 754
},
{
"epoch": 1.7,
"learning_rate": 8.290193507186464e-06,
"loss": 0.5213,
"step": 755
},
{
"epoch": 1.71,
"learning_rate": 8.266185181894821e-06,
"loss": 0.4585,
"step": 756
},
{
"epoch": 1.71,
"learning_rate": 8.24218715563515e-06,
"loss": 0.5318,
"step": 757
},
{
"epoch": 1.71,
"learning_rate": 8.218199570958094e-06,
"loss": 0.4694,
"step": 758
},
{
"epoch": 1.71,
"learning_rate": 8.194222570352295e-06,
"loss": 0.4996,
"step": 759
},
{
"epoch": 1.72,
"learning_rate": 8.170256296243505e-06,
"loss": 0.4922,
"step": 760
},
{
"epoch": 1.72,
"learning_rate": 8.146300890993776e-06,
"loss": 0.4919,
"step": 761
},
{
"epoch": 1.72,
"learning_rate": 8.12235649690059e-06,
"loss": 0.4518,
"step": 762
},
{
"epoch": 1.72,
"learning_rate": 8.098423256196018e-06,
"loss": 0.4359,
"step": 763
},
{
"epoch": 1.72,
"learning_rate": 8.074501311045892e-06,
"loss": 0.505,
"step": 764
},
{
"epoch": 1.73,
"learning_rate": 8.050590803548927e-06,
"loss": 0.5173,
"step": 765
},
{
"epoch": 1.73,
"learning_rate": 8.026691875735918e-06,
"loss": 0.4621,
"step": 766
},
{
"epoch": 1.73,
"learning_rate": 8.00280466956886e-06,
"loss": 0.4769,
"step": 767
},
{
"epoch": 1.73,
"learning_rate": 7.978929326940135e-06,
"loss": 0.4793,
"step": 768
},
{
"epoch": 1.74,
"learning_rate": 7.955065989671636e-06,
"loss": 0.5219,
"step": 769
},
{
"epoch": 1.74,
"learning_rate": 7.93121479951396e-06,
"loss": 0.4625,
"step": 770
},
{
"epoch": 1.74,
"learning_rate": 7.907375898145538e-06,
"loss": 0.4755,
"step": 771
},
{
"epoch": 1.74,
"learning_rate": 7.883549427171806e-06,
"loss": 0.5136,
"step": 772
},
{
"epoch": 1.74,
"learning_rate": 7.859735528124375e-06,
"loss": 0.5005,
"step": 773
},
{
"epoch": 1.75,
"learning_rate": 7.835934342460156e-06,
"loss": 0.4902,
"step": 774
},
{
"epoch": 1.75,
"learning_rate": 7.81214601156056e-06,
"loss": 0.4651,
"step": 775
},
{
"epoch": 1.75,
"learning_rate": 7.788370676730625e-06,
"loss": 0.4668,
"step": 776
},
{
"epoch": 1.75,
"learning_rate": 7.764608479198204e-06,
"loss": 0.4744,
"step": 777
},
{
"epoch": 1.76,
"learning_rate": 7.740859560113101e-06,
"loss": 0.4451,
"step": 778
},
{
"epoch": 1.76,
"learning_rate": 7.717124060546254e-06,
"loss": 0.4383,
"step": 779
},
{
"epoch": 1.76,
"learning_rate": 7.693402121488884e-06,
"loss": 0.4764,
"step": 780
},
{
"epoch": 1.76,
"learning_rate": 7.669693883851663e-06,
"loss": 0.4724,
"step": 781
},
{
"epoch": 1.77,
"learning_rate": 7.645999488463867e-06,
"loss": 0.4989,
"step": 782
},
{
"epoch": 1.77,
"learning_rate": 7.622319076072564e-06,
"loss": 0.5171,
"step": 783
},
{
"epoch": 1.77,
"learning_rate": 7.598652787341744e-06,
"loss": 0.4631,
"step": 784
},
{
"epoch": 1.77,
"learning_rate": 7.575000762851511e-06,
"loss": 0.4749,
"step": 785
},
{
"epoch": 1.77,
"learning_rate": 7.551363143097244e-06,
"loss": 0.5007,
"step": 786
},
{
"epoch": 1.78,
"learning_rate": 7.527740068488735e-06,
"loss": 0.5064,
"step": 787
},
{
"epoch": 1.78,
"learning_rate": 7.504131679349402e-06,
"loss": 0.4649,
"step": 788
},
{
"epoch": 1.78,
"learning_rate": 7.48053811591541e-06,
"loss": 0.4585,
"step": 789
},
{
"epoch": 1.78,
"learning_rate": 7.456959518334871e-06,
"loss": 0.4771,
"step": 790
},
{
"epoch": 1.79,
"learning_rate": 7.4333960266669855e-06,
"loss": 0.5022,
"step": 791
},
{
"epoch": 1.79,
"learning_rate": 7.409847780881241e-06,
"loss": 0.4676,
"step": 792
},
{
"epoch": 1.79,
"learning_rate": 7.386314920856546e-06,
"loss": 0.4744,
"step": 793
},
{
"epoch": 1.79,
"learning_rate": 7.362797586380423e-06,
"loss": 0.4726,
"step": 794
},
{
"epoch": 1.79,
"learning_rate": 7.339295917148173e-06,
"loss": 0.4457,
"step": 795
},
{
"epoch": 1.8,
"learning_rate": 7.315810052762038e-06,
"loss": 0.4901,
"step": 796
},
{
"epoch": 1.8,
"learning_rate": 7.292340132730389e-06,
"loss": 0.48,
"step": 797
},
{
"epoch": 1.8,
"learning_rate": 7.268886296466871e-06,
"loss": 0.5181,
"step": 798
},
{
"epoch": 1.8,
"learning_rate": 7.245448683289605e-06,
"loss": 0.4704,
"step": 799
},
{
"epoch": 1.81,
"learning_rate": 7.222027432420329e-06,
"loss": 0.4764,
"step": 800
},
{
"epoch": 1.81,
"learning_rate": 7.198622682983603e-06,
"loss": 0.4423,
"step": 801
},
{
"epoch": 1.81,
"learning_rate": 7.1752345740059536e-06,
"loss": 0.5054,
"step": 802
},
{
"epoch": 1.81,
"learning_rate": 7.151863244415076e-06,
"loss": 0.4999,
"step": 803
},
{
"epoch": 1.81,
"learning_rate": 7.128508833038976e-06,
"loss": 0.4793,
"step": 804
},
{
"epoch": 1.82,
"learning_rate": 7.105171478605182e-06,
"loss": 0.4865,
"step": 805
},
{
"epoch": 1.82,
"learning_rate": 7.081851319739884e-06,
"loss": 0.497,
"step": 806
},
{
"epoch": 1.82,
"learning_rate": 7.0585484949671475e-06,
"loss": 0.5078,
"step": 807
},
{
"epoch": 1.82,
"learning_rate": 7.035263142708058e-06,
"loss": 0.4804,
"step": 808
},
{
"epoch": 1.83,
"learning_rate": 7.0119954012799195e-06,
"loss": 0.4825,
"step": 809
},
{
"epoch": 1.83,
"learning_rate": 6.988745408895424e-06,
"loss": 0.44,
"step": 810
},
{
"epoch": 1.83,
"learning_rate": 6.965513303661826e-06,
"loss": 0.4784,
"step": 811
},
{
"epoch": 1.83,
"learning_rate": 6.942299223580144e-06,
"loss": 0.4694,
"step": 812
},
{
"epoch": 1.84,
"learning_rate": 6.9191033065443045e-06,
"loss": 0.4627,
"step": 813
},
{
"epoch": 1.84,
"learning_rate": 6.895925690340367e-06,
"loss": 0.4647,
"step": 814
},
{
"epoch": 1.84,
"learning_rate": 6.872766512645661e-06,
"loss": 0.5004,
"step": 815
},
{
"epoch": 1.84,
"learning_rate": 6.849625911028005e-06,
"loss": 0.4797,
"step": 816
},
{
"epoch": 1.84,
"learning_rate": 6.826504022944862e-06,
"loss": 0.4732,
"step": 817
},
{
"epoch": 1.85,
"learning_rate": 6.803400985742545e-06,
"loss": 0.4839,
"step": 818
},
{
"epoch": 1.85,
"learning_rate": 6.780316936655382e-06,
"loss": 0.4778,
"step": 819
},
{
"epoch": 1.85,
"learning_rate": 6.7572520128049164e-06,
"loss": 0.4618,
"step": 820
},
{
"epoch": 1.85,
"learning_rate": 6.734206351199086e-06,
"loss": 0.4444,
"step": 821
},
{
"epoch": 1.86,
"learning_rate": 6.7111800887314e-06,
"loss": 0.4701,
"step": 822
},
{
"epoch": 1.86,
"learning_rate": 6.688173362180148e-06,
"loss": 0.4493,
"step": 823
},
{
"epoch": 1.86,
"learning_rate": 6.665186308207562e-06,
"loss": 0.4444,
"step": 824
},
{
"epoch": 1.86,
"learning_rate": 6.642219063359023e-06,
"loss": 0.4765,
"step": 825
},
{
"epoch": 1.86,
"learning_rate": 6.619271764062244e-06,
"loss": 0.4797,
"step": 826
},
{
"epoch": 1.87,
"learning_rate": 6.596344546626461e-06,
"loss": 0.4617,
"step": 827
},
{
"epoch": 1.87,
"learning_rate": 6.5734375472416115e-06,
"loss": 0.4976,
"step": 828
},
{
"epoch": 1.87,
"learning_rate": 6.550550901977552e-06,
"loss": 0.4637,
"step": 829
},
{
"epoch": 1.87,
"learning_rate": 6.527684746783221e-06,
"loss": 0.4432,
"step": 830
},
{
"epoch": 1.88,
"learning_rate": 6.5048392174858465e-06,
"loss": 0.4758,
"step": 831
},
{
"epoch": 1.88,
"learning_rate": 6.482014449790145e-06,
"loss": 0.4736,
"step": 832
},
{
"epoch": 1.88,
"learning_rate": 6.459210579277492e-06,
"loss": 0.4679,
"step": 833
},
{
"epoch": 1.88,
"learning_rate": 6.4364277414051465e-06,
"loss": 0.4523,
"step": 834
},
{
"epoch": 1.88,
"learning_rate": 6.41366607150542e-06,
"loss": 0.4605,
"step": 835
},
{
"epoch": 1.89,
"learning_rate": 6.390925704784894e-06,
"loss": 0.4754,
"step": 836
},
{
"epoch": 1.89,
"learning_rate": 6.368206776323593e-06,
"loss": 0.4926,
"step": 837
},
{
"epoch": 1.89,
"learning_rate": 6.345509421074218e-06,
"loss": 0.4587,
"step": 838
},
{
"epoch": 1.89,
"learning_rate": 6.322833773861296e-06,
"loss": 0.4375,
"step": 839
},
{
"epoch": 1.9,
"learning_rate": 6.300179969380435e-06,
"loss": 0.4688,
"step": 840
},
{
"epoch": 1.9,
"learning_rate": 6.277548142197468e-06,
"loss": 0.4623,
"step": 841
},
{
"epoch": 1.9,
"learning_rate": 6.254938426747697e-06,
"loss": 0.4777,
"step": 842
},
{
"epoch": 1.9,
"learning_rate": 6.232350957335078e-06,
"loss": 0.4935,
"step": 843
},
{
"epoch": 1.91,
"learning_rate": 6.2097858681314115e-06,
"loss": 0.4596,
"step": 844
},
{
"epoch": 1.91,
"learning_rate": 6.187243293175573e-06,
"loss": 0.4481,
"step": 845
},
{
"epoch": 1.91,
"learning_rate": 6.164723366372688e-06,
"loss": 0.4843,
"step": 846
},
{
"epoch": 1.91,
"learning_rate": 6.142226221493359e-06,
"loss": 0.4704,
"step": 847
},
{
"epoch": 1.91,
"learning_rate": 6.119751992172853e-06,
"loss": 0.4896,
"step": 848
},
{
"epoch": 1.92,
"learning_rate": 6.097300811910327e-06,
"loss": 0.4831,
"step": 849
},
{
"epoch": 1.92,
"learning_rate": 6.07487281406801e-06,
"loss": 0.4724,
"step": 850
},
{
"epoch": 1.92,
"learning_rate": 6.052468131870444e-06,
"loss": 0.483,
"step": 851
},
{
"epoch": 1.92,
"learning_rate": 6.030086898403652e-06,
"loss": 0.4791,
"step": 852
},
{
"epoch": 1.93,
"learning_rate": 6.007729246614387e-06,
"loss": 0.4689,
"step": 853
},
{
"epoch": 1.93,
"learning_rate": 5.985395309309319e-06,
"loss": 0.4905,
"step": 854
},
{
"epoch": 1.93,
"learning_rate": 5.963085219154247e-06,
"loss": 0.4658,
"step": 855
},
{
"epoch": 1.93,
"learning_rate": 5.94079910867332e-06,
"loss": 0.4497,
"step": 856
},
{
"epoch": 1.93,
"learning_rate": 5.918537110248244e-06,
"loss": 0.4585,
"step": 857
},
{
"epoch": 1.94,
"learning_rate": 5.896299356117501e-06,
"loss": 0.4468,
"step": 858
},
{
"epoch": 1.94,
"learning_rate": 5.874085978375548e-06,
"loss": 0.4902,
"step": 859
},
{
"epoch": 1.94,
"learning_rate": 5.8518971089720626e-06,
"loss": 0.4613,
"step": 860
},
{
"epoch": 1.94,
"learning_rate": 5.829732879711116e-06,
"loss": 0.4942,
"step": 861
},
{
"epoch": 1.95,
"learning_rate": 5.807593422250441e-06,
"loss": 0.4831,
"step": 862
},
{
"epoch": 1.95,
"learning_rate": 5.785478868100604e-06,
"loss": 0.4371,
"step": 863
},
{
"epoch": 1.95,
"learning_rate": 5.763389348624251e-06,
"loss": 0.4408,
"step": 864
},
{
"epoch": 1.95,
"learning_rate": 5.741324995035318e-06,
"loss": 0.4882,
"step": 865
},
{
"epoch": 1.95,
"learning_rate": 5.719285938398254e-06,
"loss": 0.5094,
"step": 866
},
{
"epoch": 1.96,
"learning_rate": 5.69727230962724e-06,
"loss": 0.4716,
"step": 867
},
{
"epoch": 1.96,
"learning_rate": 5.675284239485415e-06,
"loss": 0.446,
"step": 868
},
{
"epoch": 1.96,
"learning_rate": 5.653321858584095e-06,
"loss": 0.4746,
"step": 869
},
{
"epoch": 1.96,
"learning_rate": 5.631385297382004e-06,
"loss": 0.4702,
"step": 870
},
{
"epoch": 1.97,
"learning_rate": 5.609474686184488e-06,
"loss": 0.4573,
"step": 871
},
{
"epoch": 1.97,
"learning_rate": 5.58759015514275e-06,
"loss": 0.4525,
"step": 872
},
{
"epoch": 1.97,
"learning_rate": 5.565731834253077e-06,
"loss": 0.47,
"step": 873
},
{
"epoch": 1.97,
"learning_rate": 5.543899853356062e-06,
"loss": 0.4843,
"step": 874
},
{
"epoch": 1.98,
"learning_rate": 5.522094342135835e-06,
"loss": 0.4608,
"step": 875
},
{
"epoch": 1.98,
"learning_rate": 5.500315430119298e-06,
"loss": 0.461,
"step": 876
},
{
"epoch": 1.98,
"learning_rate": 5.478563246675345e-06,
"loss": 0.4347,
"step": 877
},
{
"epoch": 1.98,
"learning_rate": 5.456837921014105e-06,
"loss": 0.4541,
"step": 878
},
{
"epoch": 1.98,
"learning_rate": 5.4351395821861665e-06,
"loss": 0.4586,
"step": 879
},
{
"epoch": 1.99,
"learning_rate": 5.413468359081814e-06,
"loss": 0.4841,
"step": 880
},
{
"epoch": 1.99,
"learning_rate": 5.391824380430262e-06,
"loss": 0.4803,
"step": 881
},
{
"epoch": 1.99,
"learning_rate": 5.3702077747988904e-06,
"loss": 0.4923,
"step": 882
},
{
"epoch": 1.99,
"learning_rate": 5.3486186705924785e-06,
"loss": 0.4814,
"step": 883
},
{
"epoch": 2.0,
"learning_rate": 5.327057196052449e-06,
"loss": 0.4729,
"step": 884
},
{
"epoch": 2.0,
"learning_rate": 5.305523479256096e-06,
"loss": 0.4713,
"step": 885
},
{
"epoch": 2.0,
"learning_rate": 5.284017648115837e-06,
"loss": 0.5153,
"step": 886
},
{
"epoch": 2.0,
"learning_rate": 5.262539830378438e-06,
"loss": 0.3328,
"step": 887
},
{
"epoch": 2.0,
"learning_rate": 5.241090153624264e-06,
"loss": 0.336,
"step": 888
},
{
"epoch": 2.01,
"learning_rate": 5.219668745266533e-06,
"loss": 0.2995,
"step": 889
},
{
"epoch": 2.01,
"learning_rate": 5.198275732550522e-06,
"loss": 0.3322,
"step": 890
},
{
"epoch": 2.01,
"learning_rate": 5.17691124255286e-06,
"loss": 0.3147,
"step": 891
},
{
"epoch": 2.01,
"learning_rate": 5.155575402180721e-06,
"loss": 0.3186,
"step": 892
},
{
"epoch": 2.02,
"learning_rate": 5.134268338171133e-06,
"loss": 0.3011,
"step": 893
},
{
"epoch": 2.02,
"learning_rate": 5.1129901770901525e-06,
"loss": 0.2903,
"step": 894
},
{
"epoch": 2.02,
"learning_rate": 5.091741045332173e-06,
"loss": 0.3047,
"step": 895
},
{
"epoch": 2.02,
"learning_rate": 5.070521069119143e-06,
"loss": 0.3322,
"step": 896
},
{
"epoch": 2.02,
"learning_rate": 5.049330374499826e-06,
"loss": 0.3158,
"step": 897
},
{
"epoch": 2.03,
"learning_rate": 5.028169087349051e-06,
"loss": 0.2897,
"step": 898
},
{
"epoch": 2.03,
"learning_rate": 5.0070373333669595e-06,
"loss": 0.2875,
"step": 899
},
{
"epoch": 2.03,
"learning_rate": 4.98593523807827e-06,
"loss": 0.3225,
"step": 900
},
{
"epoch": 2.03,
"learning_rate": 4.964862926831513e-06,
"loss": 0.2805,
"step": 901
},
{
"epoch": 2.04,
"learning_rate": 4.94382052479832e-06,
"loss": 0.3066,
"step": 902
},
{
"epoch": 2.04,
"learning_rate": 4.922808156972633e-06,
"loss": 0.2938,
"step": 903
},
{
"epoch": 2.04,
"learning_rate": 4.901825948170013e-06,
"loss": 0.3164,
"step": 904
},
{
"epoch": 2.04,
"learning_rate": 4.880874023026847e-06,
"loss": 0.3285,
"step": 905
},
{
"epoch": 2.05,
"learning_rate": 4.859952505999663e-06,
"loss": 0.2846,
"step": 906
},
{
"epoch": 2.05,
"learning_rate": 4.839061521364332e-06,
"loss": 0.2867,
"step": 907
},
{
"epoch": 2.05,
"learning_rate": 4.81820119321539e-06,
"loss": 0.306,
"step": 908
},
{
"epoch": 2.05,
"learning_rate": 4.79737164546524e-06,
"loss": 0.2945,
"step": 909
},
{
"epoch": 2.05,
"learning_rate": 4.776573001843475e-06,
"loss": 0.3122,
"step": 910
},
{
"epoch": 2.06,
"learning_rate": 4.75580538589609e-06,
"loss": 0.2916,
"step": 911
},
{
"epoch": 2.06,
"learning_rate": 4.735068920984786e-06,
"loss": 0.3027,
"step": 912
},
{
"epoch": 2.06,
"learning_rate": 4.714363730286227e-06,
"loss": 0.289,
"step": 913
},
{
"epoch": 2.06,
"learning_rate": 4.69368993679129e-06,
"loss": 0.3046,
"step": 914
},
{
"epoch": 2.07,
"learning_rate": 4.67304766330437e-06,
"loss": 0.2687,
"step": 915
},
{
"epoch": 2.07,
"learning_rate": 4.652437032442604e-06,
"loss": 0.2909,
"step": 916
},
{
"epoch": 2.07,
"learning_rate": 4.631858166635198e-06,
"loss": 0.2926,
"step": 917
},
{
"epoch": 2.07,
"learning_rate": 4.6113111881226425e-06,
"loss": 0.289,
"step": 918
},
{
"epoch": 2.07,
"learning_rate": 4.590796218956041e-06,
"loss": 0.3294,
"step": 919
},
{
"epoch": 2.08,
"learning_rate": 4.570313380996331e-06,
"loss": 0.2951,
"step": 920
},
{
"epoch": 2.08,
"learning_rate": 4.549862795913614e-06,
"loss": 0.3024,
"step": 921
},
{
"epoch": 2.08,
"learning_rate": 4.5294445851863824e-06,
"loss": 0.2878,
"step": 922
},
{
"epoch": 2.08,
"learning_rate": 4.50905887010084e-06,
"loss": 0.2739,
"step": 923
},
{
"epoch": 2.09,
"learning_rate": 4.488705771750155e-06,
"loss": 0.3131,
"step": 924
},
{
"epoch": 2.09,
"learning_rate": 4.468385411033749e-06,
"loss": 0.2929,
"step": 925
},
{
"epoch": 2.09,
"learning_rate": 4.44809790865658e-06,
"loss": 0.3022,
"step": 926
},
{
"epoch": 2.09,
"learning_rate": 4.427843385128424e-06,
"loss": 0.2868,
"step": 927
},
{
"epoch": 2.09,
"learning_rate": 4.407621960763163e-06,
"loss": 0.2939,
"step": 928
},
{
"epoch": 2.1,
"learning_rate": 4.3874337556780535e-06,
"loss": 0.2782,
"step": 929
},
{
"epoch": 2.1,
"learning_rate": 4.367278889793049e-06,
"loss": 0.3002,
"step": 930
},
{
"epoch": 2.1,
"learning_rate": 4.347157482830036e-06,
"loss": 0.3155,
"step": 931
},
{
"epoch": 2.1,
"learning_rate": 4.327069654312184e-06,
"loss": 0.2727,
"step": 932
},
{
"epoch": 2.11,
"learning_rate": 4.30701552356317e-06,
"loss": 0.2982,
"step": 933
},
{
"epoch": 2.11,
"learning_rate": 4.286995209706537e-06,
"loss": 0.3042,
"step": 934
},
{
"epoch": 2.11,
"learning_rate": 4.267008831664919e-06,
"loss": 0.2837,
"step": 935
},
{
"epoch": 2.11,
"learning_rate": 4.247056508159392e-06,
"loss": 0.2738,
"step": 936
},
{
"epoch": 2.12,
"learning_rate": 4.227138357708735e-06,
"loss": 0.3027,
"step": 937
},
{
"epoch": 2.12,
"learning_rate": 4.207254498628737e-06,
"loss": 0.2969,
"step": 938
},
{
"epoch": 2.12,
"learning_rate": 4.187405049031492e-06,
"loss": 0.2917,
"step": 939
},
{
"epoch": 2.12,
"learning_rate": 4.167590126824701e-06,
"loss": 0.2939,
"step": 940
},
{
"epoch": 2.12,
"learning_rate": 4.147809849710964e-06,
"loss": 0.2954,
"step": 941
},
{
"epoch": 2.13,
"learning_rate": 4.128064335187091e-06,
"loss": 0.3066,
"step": 942
},
{
"epoch": 2.13,
"learning_rate": 4.108353700543396e-06,
"loss": 0.2808,
"step": 943
},
{
"epoch": 2.13,
"learning_rate": 4.088678062863003e-06,
"loss": 0.2897,
"step": 944
},
{
"epoch": 2.13,
"learning_rate": 4.069037539021155e-06,
"loss": 0.3047,
"step": 945
},
{
"epoch": 2.14,
"learning_rate": 4.0494322456845006e-06,
"loss": 0.3304,
"step": 946
},
{
"epoch": 2.14,
"learning_rate": 4.029862299310437e-06,
"loss": 0.2965,
"step": 947
},
{
"epoch": 2.14,
"learning_rate": 4.010327816146382e-06,
"loss": 0.3029,
"step": 948
},
{
"epoch": 2.14,
"learning_rate": 3.990828912229105e-06,
"loss": 0.293,
"step": 949
},
{
"epoch": 2.14,
"learning_rate": 3.971365703384028e-06,
"loss": 0.2993,
"step": 950
},
{
"epoch": 2.15,
"learning_rate": 3.951938305224542e-06,
"loss": 0.296,
"step": 951
},
{
"epoch": 2.15,
"learning_rate": 3.932546833151318e-06,
"loss": 0.275,
"step": 952
},
{
"epoch": 2.15,
"learning_rate": 3.913191402351624e-06,
"loss": 0.3096,
"step": 953
},
{
"epoch": 2.15,
"learning_rate": 3.893872127798638e-06,
"loss": 0.2754,
"step": 954
},
{
"epoch": 2.16,
"learning_rate": 3.874589124250766e-06,
"loss": 0.3007,
"step": 955
},
{
"epoch": 2.16,
"learning_rate": 3.855342506250963e-06,
"loss": 0.284,
"step": 956
},
{
"epoch": 2.16,
"learning_rate": 3.836132388126048e-06,
"loss": 0.2944,
"step": 957
},
{
"epoch": 2.16,
"learning_rate": 3.816958883986027e-06,
"loss": 0.2914,
"step": 958
},
{
"epoch": 2.16,
"learning_rate": 3.7978221077234167e-06,
"loss": 0.2966,
"step": 959
},
{
"epoch": 2.17,
"learning_rate": 3.7787221730125668e-06,
"loss": 0.3016,
"step": 960
},
{
"epoch": 2.17,
"learning_rate": 3.759659193308981e-06,
"loss": 0.2825,
"step": 961
},
{
"epoch": 2.17,
"learning_rate": 3.740633281848652e-06,
"loss": 0.2755,
"step": 962
},
{
"epoch": 2.17,
"learning_rate": 3.7216445516473797e-06,
"loss": 0.2866,
"step": 963
},
{
"epoch": 2.18,
"learning_rate": 3.7026931155001055e-06,
"loss": 0.3103,
"step": 964
},
{
"epoch": 2.18,
"learning_rate": 3.6837790859802382e-06,
"loss": 0.3009,
"step": 965
},
{
"epoch": 2.18,
"learning_rate": 3.664902575438988e-06,
"loss": 0.2982,
"step": 966
},
{
"epoch": 2.18,
"learning_rate": 3.6460636960047024e-06,
"loss": 0.2862,
"step": 967
},
{
"epoch": 2.19,
"learning_rate": 3.627262559582191e-06,
"loss": 0.2887,
"step": 968
},
{
"epoch": 2.19,
"learning_rate": 3.60849927785207e-06,
"loss": 0.306,
"step": 969
},
{
"epoch": 2.19,
"learning_rate": 3.5897739622700944e-06,
"loss": 0.2876,
"step": 970
},
{
"epoch": 2.19,
"learning_rate": 3.571086724066494e-06,
"loss": 0.2593,
"step": 971
},
{
"epoch": 2.19,
"learning_rate": 3.552437674245317e-06,
"loss": 0.2839,
"step": 972
},
{
"epoch": 2.2,
"learning_rate": 3.5338269235837695e-06,
"loss": 0.3004,
"step": 973
},
{
"epoch": 2.2,
"learning_rate": 3.5152545826315578e-06,
"loss": 0.3222,
"step": 974
},
{
"epoch": 2.2,
"learning_rate": 3.4967207617102263e-06,
"loss": 0.3011,
"step": 975
},
{
"epoch": 2.2,
"learning_rate": 3.478225570912509e-06,
"loss": 0.2815,
"step": 976
},
{
"epoch": 2.21,
"learning_rate": 3.459769120101676e-06,
"loss": 0.2953,
"step": 977
},
{
"epoch": 2.21,
"learning_rate": 3.441351518910875e-06,
"loss": 0.282,
"step": 978
},
{
"epoch": 2.21,
"learning_rate": 3.4229728767424807e-06,
"loss": 0.2986,
"step": 979
},
{
"epoch": 2.21,
"learning_rate": 3.4046333027674536e-06,
"loss": 0.2897,
"step": 980
},
{
"epoch": 2.21,
"learning_rate": 3.386332905924681e-06,
"loss": 0.3066,
"step": 981
},
{
"epoch": 2.22,
"learning_rate": 3.36807179492033e-06,
"loss": 0.274,
"step": 982
},
{
"epoch": 2.22,
"learning_rate": 3.3498500782272224e-06,
"loss": 0.3053,
"step": 983
},
{
"epoch": 2.22,
"learning_rate": 3.3316678640841503e-06,
"loss": 0.2783,
"step": 984
},
{
"epoch": 2.22,
"learning_rate": 3.3135252604952795e-06,
"loss": 0.2766,
"step": 985
},
{
"epoch": 2.23,
"learning_rate": 3.2954223752294657e-06,
"loss": 0.3057,
"step": 986
},
{
"epoch": 2.23,
"learning_rate": 3.277359315819647e-06,
"loss": 0.2977,
"step": 987
},
{
"epoch": 2.23,
"learning_rate": 3.2593361895621865e-06,
"loss": 0.2833,
"step": 988
},
{
"epoch": 2.23,
"learning_rate": 3.2413531035162414e-06,
"loss": 0.2802,
"step": 989
},
{
"epoch": 2.23,
"learning_rate": 3.223410164503127e-06,
"loss": 0.3085,
"step": 990
},
{
"epoch": 2.24,
"learning_rate": 3.2055074791056807e-06,
"loss": 0.301,
"step": 991
},
{
"epoch": 2.24,
"learning_rate": 3.187645153667628e-06,
"loss": 0.3194,
"step": 992
},
{
"epoch": 2.24,
"learning_rate": 3.16982329429295e-06,
"loss": 0.2815,
"step": 993
},
{
"epoch": 2.24,
"learning_rate": 3.1520420068452705e-06,
"loss": 0.2839,
"step": 994
},
{
"epoch": 2.25,
"learning_rate": 3.134301396947186e-06,
"loss": 0.284,
"step": 995
},
{
"epoch": 2.25,
"learning_rate": 3.1166015699796915e-06,
"loss": 0.2983,
"step": 996
},
{
"epoch": 2.25,
"learning_rate": 3.0989426310815018e-06,
"loss": 0.3001,
"step": 997
},
{
"epoch": 2.25,
"learning_rate": 3.081324685148479e-06,
"loss": 0.2919,
"step": 998
},
{
"epoch": 2.26,
"learning_rate": 3.0637478368329543e-06,
"loss": 0.2864,
"step": 999
},
{
"epoch": 2.26,
"learning_rate": 3.046212190543165e-06,
"loss": 0.298,
"step": 1000
},
{
"epoch": 2.26,
"learning_rate": 3.028717850442575e-06,
"loss": 0.3068,
"step": 1001
},
{
"epoch": 2.26,
"learning_rate": 3.0112649204493117e-06,
"loss": 0.2924,
"step": 1002
},
{
"epoch": 2.26,
"learning_rate": 2.993853504235501e-06,
"loss": 0.2911,
"step": 1003
},
{
"epoch": 2.27,
"learning_rate": 2.976483705226683e-06,
"loss": 0.2964,
"step": 1004
},
{
"epoch": 2.27,
"learning_rate": 2.9591556266011945e-06,
"loss": 0.302,
"step": 1005
},
{
"epoch": 2.27,
"learning_rate": 2.9418693712895295e-06,
"loss": 0.3098,
"step": 1006
},
{
"epoch": 2.27,
"learning_rate": 2.92462504197377e-06,
"loss": 0.2977,
"step": 1007
},
{
"epoch": 2.28,
"learning_rate": 2.9074227410869315e-06,
"loss": 0.3239,
"step": 1008
},
{
"epoch": 2.28,
"learning_rate": 2.890262570812398e-06,
"loss": 0.3508,
"step": 1009
},
{
"epoch": 2.28,
"learning_rate": 2.8731446330832715e-06,
"loss": 0.2954,
"step": 1010
},
{
"epoch": 2.28,
"learning_rate": 2.8560690295818115e-06,
"loss": 0.298,
"step": 1011
},
{
"epoch": 2.28,
"learning_rate": 2.8390358617387836e-06,
"loss": 0.2863,
"step": 1012
},
{
"epoch": 2.29,
"learning_rate": 2.8220452307329073e-06,
"loss": 0.2827,
"step": 1013
},
{
"epoch": 2.29,
"learning_rate": 2.805097237490203e-06,
"loss": 0.3203,
"step": 1014
},
{
"epoch": 2.29,
"learning_rate": 2.7881919826834435e-06,
"loss": 0.2962,
"step": 1015
},
{
"epoch": 2.29,
"learning_rate": 2.7713295667315065e-06,
"loss": 0.2871,
"step": 1016
},
{
"epoch": 2.3,
"learning_rate": 2.754510089798824e-06,
"loss": 0.3196,
"step": 1017
},
{
"epoch": 2.3,
"learning_rate": 2.737733651794755e-06,
"loss": 0.2895,
"step": 1018
},
{
"epoch": 2.3,
"learning_rate": 2.7210003523730044e-06,
"loss": 0.3046,
"step": 1019
},
{
"epoch": 2.3,
"learning_rate": 2.7043102909310327e-06,
"loss": 0.2843,
"step": 1020
},
{
"epoch": 2.3,
"learning_rate": 2.687663566609452e-06,
"loss": 0.2951,
"step": 1021
},
{
"epoch": 2.31,
"learning_rate": 2.6710602782914664e-06,
"loss": 0.2735,
"step": 1022
},
{
"epoch": 2.31,
"learning_rate": 2.6545005246022438e-06,
"loss": 0.2864,
"step": 1023
},
{
"epoch": 2.31,
"learning_rate": 2.6379844039083758e-06,
"loss": 0.2665,
"step": 1024
},
{
"epoch": 2.31,
"learning_rate": 2.6215120143172447e-06,
"loss": 0.2963,
"step": 1025
},
{
"epoch": 2.32,
"learning_rate": 2.6050834536764903e-06,
"loss": 0.2977,
"step": 1026
},
{
"epoch": 2.32,
"learning_rate": 2.58869881957338e-06,
"loss": 0.2931,
"step": 1027
},
{
"epoch": 2.32,
"learning_rate": 2.5723582093342736e-06,
"loss": 0.2795,
"step": 1028
},
{
"epoch": 2.32,
"learning_rate": 2.5560617200240155e-06,
"loss": 0.3144,
"step": 1029
},
{
"epoch": 2.33,
"learning_rate": 2.5398094484453663e-06,
"loss": 0.3015,
"step": 1030
},
{
"epoch": 2.33,
"learning_rate": 2.523601491138432e-06,
"loss": 0.2728,
"step": 1031
},
{
"epoch": 2.33,
"learning_rate": 2.507437944380087e-06,
"loss": 0.2666,
"step": 1032
},
{
"epoch": 2.33,
"learning_rate": 2.4913189041833997e-06,
"loss": 0.3027,
"step": 1033
},
{
"epoch": 2.33,
"learning_rate": 2.47524446629707e-06,
"loss": 0.301,
"step": 1034
},
{
"epoch": 2.34,
"learning_rate": 2.4592147262048506e-06,
"loss": 0.3144,
"step": 1035
},
{
"epoch": 2.34,
"learning_rate": 2.4432297791249893e-06,
"loss": 0.2776,
"step": 1036
},
{
"epoch": 2.34,
"learning_rate": 2.42728972000966e-06,
"loss": 0.3019,
"step": 1037
},
{
"epoch": 2.34,
"learning_rate": 2.4113946435443847e-06,
"loss": 0.2819,
"step": 1038
},
{
"epoch": 2.35,
"learning_rate": 2.3955446441475027e-06,
"loss": 0.2836,
"step": 1039
},
{
"epoch": 2.35,
"learning_rate": 2.3797398159695795e-06,
"loss": 0.2949,
"step": 1040
},
{
"epoch": 2.35,
"learning_rate": 2.363980252892862e-06,
"loss": 0.3065,
"step": 1041
},
{
"epoch": 2.35,
"learning_rate": 2.3482660485307196e-06,
"loss": 0.284,
"step": 1042
},
{
"epoch": 2.35,
"learning_rate": 2.3325972962270813e-06,
"loss": 0.2691,
"step": 1043
},
{
"epoch": 2.36,
"learning_rate": 2.3169740890558922e-06,
"loss": 0.2859,
"step": 1044
},
{
"epoch": 2.36,
"learning_rate": 2.301396519820551e-06,
"loss": 0.2506,
"step": 1045
},
{
"epoch": 2.36,
"learning_rate": 2.285864681053365e-06,
"loss": 0.2671,
"step": 1046
},
{
"epoch": 2.36,
"learning_rate": 2.270378665014995e-06,
"loss": 0.3213,
"step": 1047
},
{
"epoch": 2.37,
"learning_rate": 2.2549385636939136e-06,
"loss": 0.3155,
"step": 1048
},
{
"epoch": 2.37,
"learning_rate": 2.239544468805853e-06,
"loss": 0.2639,
"step": 1049
},
{
"epoch": 2.37,
"learning_rate": 2.2241964717932652e-06,
"loss": 0.3051,
"step": 1050
},
{
"epoch": 2.37,
"learning_rate": 2.208894663824772e-06,
"loss": 0.2849,
"step": 1051
},
{
"epoch": 2.37,
"learning_rate": 2.1936391357946307e-06,
"loss": 0.2892,
"step": 1052
},
{
"epoch": 2.38,
"learning_rate": 2.178429978322193e-06,
"loss": 0.3092,
"step": 1053
},
{
"epoch": 2.38,
"learning_rate": 2.16326728175136e-06,
"loss": 0.2901,
"step": 1054
},
{
"epoch": 2.38,
"learning_rate": 2.148151136150054e-06,
"loss": 0.288,
"step": 1055
},
{
"epoch": 2.38,
"learning_rate": 2.133081631309679e-06,
"loss": 0.3126,
"step": 1056
},
{
"epoch": 2.39,
"learning_rate": 2.118058856744588e-06,
"loss": 0.3036,
"step": 1057
},
{
"epoch": 2.39,
"learning_rate": 2.103082901691552e-06,
"loss": 0.3148,
"step": 1058
},
{
"epoch": 2.39,
"learning_rate": 2.0881538551092306e-06,
"loss": 0.3272,
"step": 1059
},
{
"epoch": 2.39,
"learning_rate": 2.073271805677638e-06,
"loss": 0.3151,
"step": 1060
},
{
"epoch": 2.4,
"learning_rate": 2.0584368417976266e-06,
"loss": 0.2915,
"step": 1061
},
{
"epoch": 2.4,
"learning_rate": 2.0436490515903506e-06,
"loss": 0.255,
"step": 1062
},
{
"epoch": 2.4,
"learning_rate": 2.028908522896752e-06,
"loss": 0.292,
"step": 1063
},
{
"epoch": 2.4,
"learning_rate": 2.014215343277032e-06,
"loss": 0.2902,
"step": 1064
},
{
"epoch": 2.4,
"learning_rate": 1.999569600010136e-06,
"loss": 0.2952,
"step": 1065
},
{
"epoch": 2.41,
"learning_rate": 1.9849713800932304e-06,
"loss": 0.2664,
"step": 1066
},
{
"epoch": 2.41,
"learning_rate": 1.9704207702411892e-06,
"loss": 0.2772,
"step": 1067
},
{
"epoch": 2.41,
"learning_rate": 1.9559178568860792e-06,
"loss": 0.3004,
"step": 1068
},
{
"epoch": 2.41,
"learning_rate": 1.941462726176643e-06,
"loss": 0.2597,
"step": 1069
},
{
"epoch": 2.42,
"learning_rate": 1.9270554639777903e-06,
"loss": 0.3086,
"step": 1070
},
{
"epoch": 2.42,
"learning_rate": 1.9126961558700875e-06,
"loss": 0.3049,
"step": 1071
},
{
"epoch": 2.42,
"learning_rate": 1.8983848871492494e-06,
"loss": 0.2838,
"step": 1072
},
{
"epoch": 2.42,
"learning_rate": 1.884121742825631e-06,
"loss": 0.2994,
"step": 1073
},
{
"epoch": 2.42,
"learning_rate": 1.8699068076237215e-06,
"loss": 0.2949,
"step": 1074
},
{
"epoch": 2.43,
"learning_rate": 1.8557401659816531e-06,
"loss": 0.2738,
"step": 1075
},
{
"epoch": 2.43,
"learning_rate": 1.8416219020506732e-06,
"loss": 0.285,
"step": 1076
},
{
"epoch": 2.43,
"learning_rate": 1.8275520996946783e-06,
"loss": 0.2871,
"step": 1077
},
{
"epoch": 2.43,
"learning_rate": 1.8135308424896792e-06,
"loss": 0.2817,
"step": 1078
},
{
"epoch": 2.44,
"learning_rate": 1.799558213723347e-06,
"loss": 0.2867,
"step": 1079
},
{
"epoch": 2.44,
"learning_rate": 1.7856342963944717e-06,
"loss": 0.2913,
"step": 1080
},
{
"epoch": 2.44,
"learning_rate": 1.7717591732125072e-06,
"loss": 0.2978,
"step": 1081
},
{
"epoch": 2.44,
"learning_rate": 1.7579329265970612e-06,
"loss": 0.3074,
"step": 1082
},
{
"epoch": 2.44,
"learning_rate": 1.7441556386774095e-06,
"loss": 0.2722,
"step": 1083
},
{
"epoch": 2.45,
"learning_rate": 1.7304273912920088e-06,
"loss": 0.2807,
"step": 1084
},
{
"epoch": 2.45,
"learning_rate": 1.7167482659880098e-06,
"loss": 0.2717,
"step": 1085
},
{
"epoch": 2.45,
"learning_rate": 1.7031183440207732e-06,
"loss": 0.3116,
"step": 1086
},
{
"epoch": 2.45,
"learning_rate": 1.6895377063533848e-06,
"loss": 0.3018,
"step": 1087
},
{
"epoch": 2.46,
"learning_rate": 1.6760064336561876e-06,
"loss": 0.2963,
"step": 1088
},
{
"epoch": 2.46,
"learning_rate": 1.6625246063062717e-06,
"loss": 0.2793,
"step": 1089
},
{
"epoch": 2.46,
"learning_rate": 1.64909230438704e-06,
"loss": 0.2721,
"step": 1090
},
{
"epoch": 2.46,
"learning_rate": 1.6357096076876867e-06,
"loss": 0.2796,
"step": 1091
},
{
"epoch": 2.47,
"learning_rate": 1.6223765957027682e-06,
"loss": 0.3006,
"step": 1092
},
{
"epoch": 2.47,
"learning_rate": 1.6090933476316882e-06,
"loss": 0.299,
"step": 1093
},
{
"epoch": 2.47,
"learning_rate": 1.595859942378266e-06,
"loss": 0.28,
"step": 1094
},
{
"epoch": 2.47,
"learning_rate": 1.5826764585502341e-06,
"loss": 0.2888,
"step": 1095
},
{
"epoch": 2.47,
"learning_rate": 1.569542974458801e-06,
"loss": 0.2887,
"step": 1096
},
{
"epoch": 2.48,
"learning_rate": 1.5564595681181593e-06,
"loss": 0.2959,
"step": 1097
},
{
"epoch": 2.48,
"learning_rate": 1.5434263172450381e-06,
"loss": 0.2829,
"step": 1098
},
{
"epoch": 2.48,
"learning_rate": 1.5304432992582485e-06,
"loss": 0.2834,
"step": 1099
},
{
"epoch": 2.48,
"learning_rate": 1.5175105912781962e-06,
"loss": 0.2604,
"step": 1100
},
{
"epoch": 2.49,
"learning_rate": 1.504628270126457e-06,
"loss": 0.3021,
"step": 1101
},
{
"epoch": 2.49,
"learning_rate": 1.4917964123252881e-06,
"loss": 0.3144,
"step": 1102
},
{
"epoch": 2.49,
"learning_rate": 1.479015094097206e-06,
"loss": 0.2887,
"step": 1103
},
{
"epoch": 2.49,
"learning_rate": 1.4662843913644987e-06,
"loss": 0.2895,
"step": 1104
},
{
"epoch": 2.49,
"learning_rate": 1.4536043797488132e-06,
"loss": 0.2825,
"step": 1105
},
{
"epoch": 2.5,
"learning_rate": 1.440975134570667e-06,
"loss": 0.2911,
"step": 1106
},
{
"epoch": 2.5,
"learning_rate": 1.4283967308490366e-06,
"loss": 0.3063,
"step": 1107
},
{
"epoch": 2.5,
"learning_rate": 1.4158692433008792e-06,
"loss": 0.2862,
"step": 1108
},
{
"epoch": 2.5,
"learning_rate": 1.4033927463407204e-06,
"loss": 0.3062,
"step": 1109
},
{
"epoch": 2.51,
"learning_rate": 1.390967314080186e-06,
"loss": 0.2845,
"step": 1110
},
{
"epoch": 2.51,
"learning_rate": 1.3785930203275776e-06,
"loss": 0.2704,
"step": 1111
},
{
"epoch": 2.51,
"learning_rate": 1.3662699385874268e-06,
"loss": 0.2848,
"step": 1112
},
{
"epoch": 2.51,
"learning_rate": 1.353998142060061e-06,
"loss": 0.2747,
"step": 1113
},
{
"epoch": 2.51,
"learning_rate": 1.3417777036411693e-06,
"loss": 0.2922,
"step": 1114
},
{
"epoch": 2.52,
"learning_rate": 1.329608695921364e-06,
"loss": 0.3015,
"step": 1115
},
{
"epoch": 2.52,
"learning_rate": 1.3174911911857647e-06,
"loss": 0.2798,
"step": 1116
},
{
"epoch": 2.52,
"learning_rate": 1.3054252614135432e-06,
"loss": 0.3118,
"step": 1117
},
{
"epoch": 2.52,
"learning_rate": 1.293410978277526e-06,
"loss": 0.3089,
"step": 1118
},
{
"epoch": 2.53,
"learning_rate": 1.281448413143741e-06,
"loss": 0.3061,
"step": 1119
},
{
"epoch": 2.53,
"learning_rate": 1.2695376370710143e-06,
"loss": 0.2844,
"step": 1120
},
{
"epoch": 2.53,
"learning_rate": 1.2576787208105378e-06,
"loss": 0.2929,
"step": 1121
},
{
"epoch": 2.53,
"learning_rate": 1.2458717348054483e-06,
"loss": 0.314,
"step": 1122
},
{
"epoch": 2.53,
"learning_rate": 1.234116749190415e-06,
"loss": 0.2893,
"step": 1123
},
{
"epoch": 2.54,
"learning_rate": 1.222413833791216e-06,
"loss": 0.287,
"step": 1124
},
{
"epoch": 2.54,
"learning_rate": 1.2107630581243323e-06,
"loss": 0.2711,
"step": 1125
},
{
"epoch": 2.54,
"learning_rate": 1.199164491396525e-06,
"loss": 0.2992,
"step": 1126
},
{
"epoch": 2.54,
"learning_rate": 1.1876182025044302e-06,
"loss": 0.2997,
"step": 1127
},
{
"epoch": 2.55,
"learning_rate": 1.1761242600341504e-06,
"loss": 0.2851,
"step": 1128
},
{
"epoch": 2.55,
"learning_rate": 1.1646827322608422e-06,
"loss": 0.2938,
"step": 1129
},
{
"epoch": 2.55,
"learning_rate": 1.1532936871483169e-06,
"loss": 0.2775,
"step": 1130
},
{
"epoch": 2.55,
"learning_rate": 1.1419571923486339e-06,
"loss": 0.2771,
"step": 1131
},
{
"epoch": 2.56,
"learning_rate": 1.130673315201689e-06,
"loss": 0.2808,
"step": 1132
},
{
"epoch": 2.56,
"learning_rate": 1.1194421227348385e-06,
"loss": 0.3052,
"step": 1133
},
{
"epoch": 2.56,
"learning_rate": 1.108263681662477e-06,
"loss": 0.2956,
"step": 1134
},
{
"epoch": 2.56,
"learning_rate": 1.097138058385654e-06,
"loss": 0.2809,
"step": 1135
},
{
"epoch": 2.56,
"learning_rate": 1.0860653189916736e-06,
"loss": 0.2831,
"step": 1136
},
{
"epoch": 2.57,
"learning_rate": 1.0750455292537077e-06,
"loss": 0.2603,
"step": 1137
},
{
"epoch": 2.57,
"learning_rate": 1.0640787546303987e-06,
"loss": 0.2675,
"step": 1138
},
{
"epoch": 2.57,
"learning_rate": 1.0531650602654752e-06,
"loss": 0.3147,
"step": 1139
},
{
"epoch": 2.57,
"learning_rate": 1.0423045109873664e-06,
"loss": 0.3,
"step": 1140
},
{
"epoch": 2.58,
"learning_rate": 1.0314971713088096e-06,
"loss": 0.2749,
"step": 1141
},
{
"epoch": 2.58,
"learning_rate": 1.020743105426476e-06,
"loss": 0.3171,
"step": 1142
},
{
"epoch": 2.58,
"learning_rate": 1.0100423772205826e-06,
"loss": 0.2793,
"step": 1143
},
{
"epoch": 2.58,
"learning_rate": 9.993950502545158e-07,
"loss": 0.3008,
"step": 1144
},
{
"epoch": 2.58,
"learning_rate": 9.88801187774454e-07,
"loss": 0.3087,
"step": 1145
},
{
"epoch": 2.59,
"learning_rate": 9.78260852708991e-07,
"loss": 0.3245,
"step": 1146
},
{
"epoch": 2.59,
"learning_rate": 9.67774107668763e-07,
"loss": 0.2676,
"step": 1147
},
{
"epoch": 2.59,
"learning_rate": 9.573410149460749e-07,
"loss": 0.2714,
"step": 1148
},
{
"epoch": 2.59,
"learning_rate": 9.469616365145318e-07,
"loss": 0.2592,
"step": 1149
},
{
"epoch": 2.6,
"learning_rate": 9.366360340286718e-07,
"loss": 0.294,
"step": 1150
},
{
"epoch": 2.6,
"learning_rate": 9.263642688235963e-07,
"loss": 0.2719,
"step": 1151
},
{
"epoch": 2.6,
"learning_rate": 9.161464019146115e-07,
"loss": 0.2777,
"step": 1152
},
{
"epoch": 2.6,
"learning_rate": 9.059824939968575e-07,
"loss": 0.3025,
"step": 1153
},
{
"epoch": 2.6,
"learning_rate": 8.958726054449573e-07,
"loss": 0.273,
"step": 1154
},
{
"epoch": 2.61,
"learning_rate": 8.858167963126508e-07,
"loss": 0.3158,
"step": 1155
},
{
"epoch": 2.61,
"learning_rate": 8.75815126332441e-07,
"loss": 0.278,
"step": 1156
},
{
"epoch": 2.61,
"learning_rate": 8.658676549152411e-07,
"loss": 0.2943,
"step": 1157
},
{
"epoch": 2.61,
"learning_rate": 8.55974441150016e-07,
"loss": 0.2945,
"step": 1158
},
{
"epoch": 2.62,
"learning_rate": 8.46135543803438e-07,
"loss": 0.3105,
"step": 1159
},
{
"epoch": 2.62,
"learning_rate": 8.363510213195314e-07,
"loss": 0.2912,
"step": 1160
},
{
"epoch": 2.62,
"learning_rate": 8.266209318193319e-07,
"loss": 0.2675,
"step": 1161
},
{
"epoch": 2.62,
"learning_rate": 8.169453331005351e-07,
"loss": 0.2966,
"step": 1162
},
{
"epoch": 2.63,
"learning_rate": 8.073242826371564e-07,
"loss": 0.2678,
"step": 1163
},
{
"epoch": 2.63,
"learning_rate": 7.977578375791906e-07,
"loss": 0.3018,
"step": 1164
},
{
"epoch": 2.63,
"learning_rate": 7.882460547522708e-07,
"loss": 0.2756,
"step": 1165
},
{
"epoch": 2.63,
"learning_rate": 7.787889906573287e-07,
"loss": 0.288,
"step": 1166
},
{
"epoch": 2.63,
"learning_rate": 7.693867014702638e-07,
"loss": 0.2992,
"step": 1167
},
{
"epoch": 2.64,
"learning_rate": 7.600392430416037e-07,
"loss": 0.3164,
"step": 1168
},
{
"epoch": 2.64,
"learning_rate": 7.507466708961853e-07,
"loss": 0.2846,
"step": 1169
},
{
"epoch": 2.64,
"learning_rate": 7.415090402327996e-07,
"loss": 0.3011,
"step": 1170
},
{
"epoch": 2.64,
"learning_rate": 7.323264059238977e-07,
"loss": 0.2812,
"step": 1171
},
{
"epoch": 2.65,
"learning_rate": 7.23198822515232e-07,
"loss": 0.2828,
"step": 1172
},
{
"epoch": 2.65,
"learning_rate": 7.141263442255553e-07,
"loss": 0.3217,
"step": 1173
},
{
"epoch": 2.65,
"learning_rate": 7.051090249462878e-07,
"loss": 0.2825,
"step": 1174
},
{
"epoch": 2.65,
"learning_rate": 6.961469182411996e-07,
"loss": 0.2763,
"step": 1175
},
{
"epoch": 2.65,
"learning_rate": 6.872400773460952e-07,
"loss": 0.2807,
"step": 1176
},
{
"epoch": 2.66,
"learning_rate": 6.783885551684921e-07,
"loss": 0.2865,
"step": 1177
},
{
"epoch": 2.66,
"learning_rate": 6.695924042873092e-07,
"loss": 0.2787,
"step": 1178
},
{
"epoch": 2.66,
"learning_rate": 6.608516769525531e-07,
"loss": 0.2759,
"step": 1179
},
{
"epoch": 2.66,
"learning_rate": 6.521664250850179e-07,
"loss": 0.2884,
"step": 1180
},
{
"epoch": 2.67,
"learning_rate": 6.43536700275953e-07,
"loss": 0.2888,
"step": 1181
},
{
"epoch": 2.67,
"learning_rate": 6.349625537867854e-07,
"loss": 0.3039,
"step": 1182
},
{
"epoch": 2.67,
"learning_rate": 6.264440365487912e-07,
"loss": 0.2804,
"step": 1183
},
{
"epoch": 2.67,
"learning_rate": 6.179811991628115e-07,
"loss": 0.2713,
"step": 1184
},
{
"epoch": 2.67,
"learning_rate": 6.095740918989357e-07,
"loss": 0.3016,
"step": 1185
},
{
"epoch": 2.68,
"learning_rate": 6.012227646962198e-07,
"loss": 0.2728,
"step": 1186
},
{
"epoch": 2.68,
"learning_rate": 5.929272671623687e-07,
"loss": 0.2692,
"step": 1187
},
{
"epoch": 2.68,
"learning_rate": 5.846876485734687e-07,
"loss": 0.3005,
"step": 1188
},
{
"epoch": 2.68,
"learning_rate": 5.765039578736631e-07,
"loss": 0.3051,
"step": 1189
},
{
"epoch": 2.69,
"learning_rate": 5.683762436748919e-07,
"loss": 0.2813,
"step": 1190
},
{
"epoch": 2.69,
"learning_rate": 5.603045542565821e-07,
"loss": 0.3022,
"step": 1191
},
{
"epoch": 2.69,
"learning_rate": 5.522889375653673e-07,
"loss": 0.2969,
"step": 1192
},
{
"epoch": 2.69,
"learning_rate": 5.443294412148092e-07,
"loss": 0.2682,
"step": 1193
},
{
"epoch": 2.7,
"learning_rate": 5.364261124851011e-07,
"loss": 0.3063,
"step": 1194
},
{
"epoch": 2.7,
"learning_rate": 5.28578998322804e-07,
"loss": 0.3068,
"step": 1195
},
{
"epoch": 2.7,
"learning_rate": 5.207881453405494e-07,
"loss": 0.3001,
"step": 1196
},
{
"epoch": 2.7,
"learning_rate": 5.130535998167829e-07,
"loss": 0.2691,
"step": 1197
},
{
"epoch": 2.7,
"learning_rate": 5.053754076954653e-07,
"loss": 0.2969,
"step": 1198
},
{
"epoch": 2.71,
"learning_rate": 4.977536145858242e-07,
"loss": 0.3002,
"step": 1199
},
{
"epoch": 2.71,
"learning_rate": 4.901882657620627e-07,
"loss": 0.2921,
"step": 1200
},
{
"epoch": 2.71,
"learning_rate": 4.826794061631068e-07,
"loss": 0.2805,
"step": 1201
},
{
"epoch": 2.71,
"learning_rate": 4.752270803923231e-07,
"loss": 0.3007,
"step": 1202
},
{
"epoch": 2.72,
"learning_rate": 4.678313327172701e-07,
"loss": 0.2911,
"step": 1203
},
{
"epoch": 2.72,
"learning_rate": 4.6049220706941957e-07,
"loss": 0.2973,
"step": 1204
},
{
"epoch": 2.72,
"learning_rate": 4.5320974704390675e-07,
"loss": 0.3319,
"step": 1205
},
{
"epoch": 2.72,
"learning_rate": 4.459839958992662e-07,
"loss": 0.2788,
"step": 1206
},
{
"epoch": 2.72,
"learning_rate": 4.388149965571753e-07,
"loss": 0.3064,
"step": 1207
},
{
"epoch": 2.73,
"learning_rate": 4.317027916022043e-07,
"loss": 0.2997,
"step": 1208
},
{
"epoch": 2.73,
"learning_rate": 4.2464742328155116e-07,
"loss": 0.2933,
"step": 1209
},
{
"epoch": 2.73,
"learning_rate": 4.176489335048084e-07,
"loss": 0.3118,
"step": 1210
},
{
"epoch": 2.73,
"learning_rate": 4.1070736384369423e-07,
"loss": 0.2973,
"step": 1211
},
{
"epoch": 2.74,
"learning_rate": 4.0382275553182527e-07,
"loss": 0.2891,
"step": 1212
},
{
"epoch": 2.74,
"learning_rate": 3.9699514946445416e-07,
"loss": 0.2939,
"step": 1213
},
{
"epoch": 2.74,
"learning_rate": 3.902245861982412e-07,
"loss": 0.2576,
"step": 1214
},
{
"epoch": 2.74,
"learning_rate": 3.835111059510022e-07,
"loss": 0.2974,
"step": 1215
},
{
"epoch": 2.74,
"learning_rate": 3.768547486014751e-07,
"loss": 0.3159,
"step": 1216
},
{
"epoch": 2.75,
"learning_rate": 3.7025555368908285e-07,
"loss": 0.3023,
"step": 1217
},
{
"epoch": 2.75,
"learning_rate": 3.6371356041369874e-07,
"loss": 0.2894,
"step": 1218
},
{
"epoch": 2.75,
"learning_rate": 3.5722880763541134e-07,
"loss": 0.308,
"step": 1219
},
{
"epoch": 2.75,
"learning_rate": 3.508013338742944e-07,
"loss": 0.3221,
"step": 1220
},
{
"epoch": 2.76,
"learning_rate": 3.444311773101794e-07,
"loss": 0.2932,
"step": 1221
},
{
"epoch": 2.76,
"learning_rate": 3.38118375782428e-07,
"loss": 0.2885,
"step": 1222
},
{
"epoch": 2.76,
"learning_rate": 3.3186296678970885e-07,
"loss": 0.2764,
"step": 1223
},
{
"epoch": 2.76,
"learning_rate": 3.25664987489771e-07,
"loss": 0.2738,
"step": 1224
},
{
"epoch": 2.77,
"learning_rate": 3.1952447469922545e-07,
"loss": 0.2959,
"step": 1225
},
{
"epoch": 2.77,
"learning_rate": 3.1344146489332705e-07,
"loss": 0.2984,
"step": 1226
},
{
"epoch": 2.77,
"learning_rate": 3.074159942057586e-07,
"loss": 0.3055,
"step": 1227
},
{
"epoch": 2.77,
"learning_rate": 3.0144809842841293e-07,
"loss": 0.2668,
"step": 1228
},
{
"epoch": 2.77,
"learning_rate": 2.955378130111819e-07,
"loss": 0.3003,
"step": 1229
},
{
"epoch": 2.78,
"learning_rate": 2.896851730617489e-07,
"loss": 0.3046,
"step": 1230
},
{
"epoch": 2.78,
"learning_rate": 2.8389021334537357e-07,
"loss": 0.2622,
"step": 1231
},
{
"epoch": 2.78,
"learning_rate": 2.7815296828469286e-07,
"loss": 0.3285,
"step": 1232
},
{
"epoch": 2.78,
"learning_rate": 2.7247347195951013e-07,
"loss": 0.2749,
"step": 1233
},
{
"epoch": 2.79,
"learning_rate": 2.668517581065977e-07,
"loss": 0.2995,
"step": 1234
},
{
"epoch": 2.79,
"learning_rate": 2.612878601194935e-07,
"loss": 0.2698,
"step": 1235
},
{
"epoch": 2.79,
"learning_rate": 2.5578181104830347e-07,
"loss": 0.2906,
"step": 1236
},
{
"epoch": 2.79,
"learning_rate": 2.5033364359950406e-07,
"loss": 0.2808,
"step": 1237
},
{
"epoch": 2.79,
"learning_rate": 2.449433901357512e-07,
"loss": 0.2884,
"step": 1238
},
{
"epoch": 2.8,
"learning_rate": 2.3961108267568365e-07,
"loss": 0.3031,
"step": 1239
},
{
"epoch": 2.8,
"learning_rate": 2.343367528937379e-07,
"loss": 0.2653,
"step": 1240
},
{
"epoch": 2.8,
"learning_rate": 2.2912043211995583e-07,
"loss": 0.2826,
"step": 1241
},
{
"epoch": 2.8,
"learning_rate": 2.2396215133980047e-07,
"loss": 0.2747,
"step": 1242
},
{
"epoch": 2.81,
"learning_rate": 2.1886194119396963e-07,
"loss": 0.2681,
"step": 1243
},
{
"epoch": 2.81,
"learning_rate": 2.138198319782192e-07,
"loss": 0.2716,
"step": 1244
},
{
"epoch": 2.81,
"learning_rate": 2.088358536431767e-07,
"loss": 0.2752,
"step": 1245
},
{
"epoch": 2.81,
"learning_rate": 2.0391003579416814e-07,
"loss": 0.2873,
"step": 1246
},
{
"epoch": 2.81,
"learning_rate": 1.9904240769104022e-07,
"loss": 0.2742,
"step": 1247
},
{
"epoch": 2.82,
"learning_rate": 1.9423299824798624e-07,
"loss": 0.2888,
"step": 1248
},
{
"epoch": 2.82,
"learning_rate": 1.89481836033375e-07,
"loss": 0.3036,
"step": 1249
},
{
"epoch": 2.82,
"learning_rate": 1.8478894926958203e-07,
"loss": 0.2999,
"step": 1250
},
{
"epoch": 2.82,
"learning_rate": 1.8015436583281975e-07,
"loss": 0.3175,
"step": 1251
},
{
"epoch": 2.83,
"learning_rate": 1.7557811325297324e-07,
"loss": 0.2797,
"step": 1252
},
{
"epoch": 2.83,
"learning_rate": 1.7106021871343803e-07,
"loss": 0.2724,
"step": 1253
},
{
"epoch": 2.83,
"learning_rate": 1.666007090509525e-07,
"loss": 0.3123,
"step": 1254
},
{
"epoch": 2.83,
"learning_rate": 1.621996107554491e-07,
"loss": 0.2837,
"step": 1255
},
{
"epoch": 2.84,
"learning_rate": 1.5785694996988789e-07,
"loss": 0.2711,
"step": 1256
},
{
"epoch": 2.84,
"learning_rate": 1.5357275249010427e-07,
"loss": 0.2684,
"step": 1257
},
{
"epoch": 2.84,
"learning_rate": 1.493470437646549e-07,
"loss": 0.299,
"step": 1258
},
{
"epoch": 2.84,
"learning_rate": 1.4517984889466985e-07,
"loss": 0.2904,
"step": 1259
},
{
"epoch": 2.84,
"learning_rate": 1.410711926336994e-07,
"loss": 0.2768,
"step": 1260
},
{
"epoch": 2.85,
"learning_rate": 1.3702109938757092e-07,
"loss": 0.2866,
"step": 1261
},
{
"epoch": 2.85,
"learning_rate": 1.330295932142378e-07,
"loss": 0.2758,
"step": 1262
},
{
"epoch": 2.85,
"learning_rate": 1.2909669782364409e-07,
"loss": 0.3144,
"step": 1263
},
{
"epoch": 2.85,
"learning_rate": 1.252224365775767e-07,
"loss": 0.2735,
"step": 1264
},
{
"epoch": 2.86,
"learning_rate": 1.2140683248953345e-07,
"loss": 0.303,
"step": 1265
},
{
"epoch": 2.86,
"learning_rate": 1.1764990822458078e-07,
"loss": 0.2758,
"step": 1266
},
{
"epoch": 2.86,
"learning_rate": 1.1395168609921959e-07,
"loss": 0.2757,
"step": 1267
},
{
"epoch": 2.86,
"learning_rate": 1.1031218808125854e-07,
"loss": 0.2792,
"step": 1268
},
{
"epoch": 2.86,
"learning_rate": 1.0673143578967427e-07,
"loss": 0.2787,
"step": 1269
},
{
"epoch": 2.87,
"learning_rate": 1.0320945049449249e-07,
"loss": 0.282,
"step": 1270
},
{
"epoch": 2.87,
"learning_rate": 9.974625311665375e-08,
"loss": 0.2922,
"step": 1271
},
{
"epoch": 2.87,
"learning_rate": 9.634186422789571e-08,
"loss": 0.3034,
"step": 1272
},
{
"epoch": 2.87,
"learning_rate": 9.299630405062433e-08,
"loss": 0.263,
"step": 1273
},
{
"epoch": 2.88,
"learning_rate": 8.970959245780064e-08,
"loss": 0.2739,
"step": 1274
},
{
"epoch": 2.88,
"learning_rate": 8.648174897281425e-08,
"loss": 0.3171,
"step": 1275
},
{
"epoch": 2.88,
"learning_rate": 8.331279276937887e-08,
"loss": 0.2929,
"step": 1276
},
{
"epoch": 2.88,
"learning_rate": 8.020274267140694e-08,
"loss": 0.2954,
"step": 1277
},
{
"epoch": 2.88,
"learning_rate": 7.71516171529052e-08,
"loss": 0.2647,
"step": 1278
},
{
"epoch": 2.89,
"learning_rate": 7.415943433786043e-08,
"loss": 0.2829,
"step": 1279
},
{
"epoch": 2.89,
"learning_rate": 7.122621200013835e-08,
"loss": 0.2776,
"step": 1280
},
{
"epoch": 2.89,
"learning_rate": 6.835196756336704e-08,
"loss": 0.2831,
"step": 1281
},
{
"epoch": 2.89,
"learning_rate": 6.553671810084483e-08,
"loss": 0.2935,
"step": 1282
},
{
"epoch": 2.9,
"learning_rate": 6.278048033543371e-08,
"loss": 0.2917,
"step": 1283
},
{
"epoch": 2.9,
"learning_rate": 6.008327063945718e-08,
"loss": 0.3114,
"step": 1284
},
{
"epoch": 2.9,
"learning_rate": 5.744510503461143e-08,
"loss": 0.2911,
"step": 1285
},
{
"epoch": 2.9,
"learning_rate": 5.486599919185875e-08,
"loss": 0.2815,
"step": 1286
},
{
"epoch": 2.91,
"learning_rate": 5.234596843134543e-08,
"loss": 0.2972,
"step": 1287
},
{
"epoch": 2.91,
"learning_rate": 4.988502772230286e-08,
"loss": 0.2855,
"step": 1288
},
{
"epoch": 2.91,
"learning_rate": 4.7483191682964333e-08,
"loss": 0.2756,
"step": 1289
},
{
"epoch": 2.91,
"learning_rate": 4.514047458047288e-08,
"loss": 0.3157,
"step": 1290
},
{
"epoch": 2.91,
"learning_rate": 4.2856890330801315e-08,
"loss": 0.2999,
"step": 1291
},
{
"epoch": 2.92,
"learning_rate": 4.063245249866454e-08,
"loss": 0.3104,
"step": 1292
},
{
"epoch": 2.92,
"learning_rate": 3.84671742974474e-08,
"loss": 0.2905,
"step": 1293
},
{
"epoch": 2.92,
"learning_rate": 3.63610685891147e-08,
"loss": 0.2708,
"step": 1294
},
{
"epoch": 2.92,
"learning_rate": 3.4314147884143554e-08,
"loss": 0.3025,
"step": 1295
},
{
"epoch": 2.93,
"learning_rate": 3.2326424341445616e-08,
"loss": 0.2597,
"step": 1296
},
{
"epoch": 2.93,
"learning_rate": 3.039790976829715e-08,
"loss": 0.2829,
"step": 1297
},
{
"epoch": 2.93,
"learning_rate": 2.8528615620265766e-08,
"loss": 0.2823,
"step": 1298
},
{
"epoch": 2.93,
"learning_rate": 2.6718553001142676e-08,
"loss": 0.2978,
"step": 1299
},
{
"epoch": 2.93,
"learning_rate": 2.496773266288055e-08,
"loss": 0.2678,
"step": 1300
},
{
"epoch": 2.94,
"learning_rate": 2.3276165005524652e-08,
"loss": 0.3141,
"step": 1301
},
{
"epoch": 2.94,
"learning_rate": 2.164386007715624e-08,
"loss": 0.3082,
"step": 1302
},
{
"epoch": 2.94,
"learning_rate": 2.0070827573827055e-08,
"loss": 0.2702,
"step": 1303
},
{
"epoch": 2.94,
"learning_rate": 1.855707683950714e-08,
"loss": 0.2945,
"step": 1304
},
{
"epoch": 2.95,
"learning_rate": 1.710261686602488e-08,
"loss": 0.2835,
"step": 1305
},
{
"epoch": 2.95,
"learning_rate": 1.5707456293018177e-08,
"loss": 0.2745,
"step": 1306
},
{
"epoch": 2.95,
"learning_rate": 1.4371603407878909e-08,
"loss": 0.2926,
"step": 1307
},
{
"epoch": 2.95,
"learning_rate": 1.3095066145704105e-08,
"loss": 0.2938,
"step": 1308
},
{
"epoch": 2.95,
"learning_rate": 1.1877852089253739e-08,
"loss": 0.2948,
"step": 1309
},
{
"epoch": 2.96,
"learning_rate": 1.0719968468898556e-08,
"loss": 0.2903,
"step": 1310
},
{
"epoch": 2.96,
"learning_rate": 9.621422162583437e-09,
"loss": 0.2763,
"step": 1311
},
{
"epoch": 2.96,
"learning_rate": 8.58221969578077e-09,
"loss": 0.2563,
"step": 1312
},
{
"epoch": 2.96,
"learning_rate": 7.602367241458241e-09,
"loss": 0.2879,
"step": 1313
},
{
"epoch": 2.97,
"learning_rate": 6.681870620034448e-09,
"loss": 0.2682,
"step": 1314
},
{
"epoch": 2.97,
"learning_rate": 5.820735299352231e-09,
"loss": 0.2914,
"step": 1315
},
{
"epoch": 2.97,
"learning_rate": 5.018966394639835e-09,
"loss": 0.2929,
"step": 1316
},
{
"epoch": 2.97,
"learning_rate": 4.276568668485359e-09,
"loss": 0.2858,
"step": 1317
},
{
"epoch": 2.98,
"learning_rate": 3.59354653080346e-09,
"loss": 0.2855,
"step": 1318
},
{
"epoch": 2.98,
"learning_rate": 2.9699040388131427e-09,
"loss": 0.2827,
"step": 1319
},
{
"epoch": 2.98,
"learning_rate": 2.4056448970144474e-09,
"loss": 0.2632,
"step": 1320
},
{
"epoch": 2.98,
"learning_rate": 1.9007724571606935e-09,
"loss": 0.2817,
"step": 1321
},
{
"epoch": 2.98,
"learning_rate": 1.4552897182462667e-09,
"loss": 0.3004,
"step": 1322
},
{
"epoch": 2.99,
"learning_rate": 1.069199326481085e-09,
"loss": 0.2623,
"step": 1323
},
{
"epoch": 2.99,
"learning_rate": 7.425035752817167e-10,
"loss": 0.3205,
"step": 1324
},
{
"epoch": 2.99,
"learning_rate": 4.752044052513949e-10,
"loss": 0.2791,
"step": 1325
},
{
"epoch": 2.99,
"learning_rate": 2.673034041755784e-10,
"loss": 0.294,
"step": 1326
},
{
"epoch": 3.0,
"learning_rate": 1.1880180700640787e-10,
"loss": 0.2973,
"step": 1327
},
{
"epoch": 3.0,
"learning_rate": 2.970049585715451e-11,
"loss": 0.2872,
"step": 1328
},
{
"epoch": 3.0,
"learning_rate": 0.0,
"loss": 0.2736,
"step": 1329
},
{
"epoch": 3.0,
"step": 1329,
"total_flos": 1.2791024001451295e+18,
"train_loss": 0.5584695404458531,
"train_runtime": 25818.8582,
"train_samples_per_second": 6.584,
"train_steps_per_second": 0.051
}
],
"max_steps": 1329,
"num_train_epochs": 3,
"total_flos": 1.2791024001451295e+18,
"trial_name": null,
"trial_params": null
}