Text Generation
Transformers
PyTorch
llava
medical
histopathology
Quilt-Llava-v1.5-7b / trainer_state.json
Wisdom Oluchi Ikezogwo
updated model
1bdf5f8
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9983212087297146,
"global_step": 2679,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2.469135802469136e-07,
"loss": 1.3721,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.938271604938272e-07,
"loss": 1.3916,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 7.407407407407407e-07,
"loss": 1.4277,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 9.876543209876544e-07,
"loss": 1.3936,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 1.234567901234568e-06,
"loss": 1.374,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 1.4814814814814815e-06,
"loss": 1.4072,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 1.7283950617283952e-06,
"loss": 1.3564,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 1.9753086419753087e-06,
"loss": 1.3506,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 2.222222222222222e-06,
"loss": 1.376,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 2.469135802469136e-06,
"loss": 1.3096,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 2.7160493827160496e-06,
"loss": 1.2959,
"step": 11
},
{
"epoch": 0.01,
"learning_rate": 2.962962962962963e-06,
"loss": 1.2725,
"step": 12
},
{
"epoch": 0.01,
"learning_rate": 3.2098765432098767e-06,
"loss": 1.2432,
"step": 13
},
{
"epoch": 0.02,
"learning_rate": 3.4567901234567904e-06,
"loss": 1.2432,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 3.7037037037037037e-06,
"loss": 1.2383,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 3.9506172839506175e-06,
"loss": 1.1768,
"step": 16
},
{
"epoch": 0.02,
"learning_rate": 4.197530864197531e-06,
"loss": 1.1855,
"step": 17
},
{
"epoch": 0.02,
"learning_rate": 4.444444444444444e-06,
"loss": 1.1328,
"step": 18
},
{
"epoch": 0.02,
"learning_rate": 4.691358024691358e-06,
"loss": 1.1025,
"step": 19
},
{
"epoch": 0.02,
"learning_rate": 4.938271604938272e-06,
"loss": 1.1133,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 5.185185185185185e-06,
"loss": 1.1113,
"step": 21
},
{
"epoch": 0.02,
"learning_rate": 5.432098765432099e-06,
"loss": 1.1123,
"step": 22
},
{
"epoch": 0.03,
"learning_rate": 5.6790123456790125e-06,
"loss": 1.0576,
"step": 23
},
{
"epoch": 0.03,
"learning_rate": 5.925925925925926e-06,
"loss": 1.0757,
"step": 24
},
{
"epoch": 0.03,
"learning_rate": 6.17283950617284e-06,
"loss": 1.0684,
"step": 25
},
{
"epoch": 0.03,
"learning_rate": 6.419753086419753e-06,
"loss": 1.0513,
"step": 26
},
{
"epoch": 0.03,
"learning_rate": 6.666666666666667e-06,
"loss": 1.064,
"step": 27
},
{
"epoch": 0.03,
"learning_rate": 6.913580246913581e-06,
"loss": 0.9971,
"step": 28
},
{
"epoch": 0.03,
"learning_rate": 7.160493827160494e-06,
"loss": 1.0356,
"step": 29
},
{
"epoch": 0.03,
"learning_rate": 7.4074074074074075e-06,
"loss": 1.0156,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 7.654320987654322e-06,
"loss": 1.0317,
"step": 31
},
{
"epoch": 0.04,
"learning_rate": 7.901234567901235e-06,
"loss": 0.9897,
"step": 32
},
{
"epoch": 0.04,
"learning_rate": 8.148148148148148e-06,
"loss": 0.9897,
"step": 33
},
{
"epoch": 0.04,
"learning_rate": 8.395061728395062e-06,
"loss": 0.9902,
"step": 34
},
{
"epoch": 0.04,
"learning_rate": 8.641975308641975e-06,
"loss": 0.9795,
"step": 35
},
{
"epoch": 0.04,
"learning_rate": 8.888888888888888e-06,
"loss": 0.9375,
"step": 36
},
{
"epoch": 0.04,
"learning_rate": 9.135802469135803e-06,
"loss": 0.9336,
"step": 37
},
{
"epoch": 0.04,
"learning_rate": 9.382716049382717e-06,
"loss": 0.9463,
"step": 38
},
{
"epoch": 0.04,
"learning_rate": 9.62962962962963e-06,
"loss": 0.9336,
"step": 39
},
{
"epoch": 0.04,
"learning_rate": 9.876543209876543e-06,
"loss": 0.9512,
"step": 40
},
{
"epoch": 0.05,
"learning_rate": 1.0123456790123458e-05,
"loss": 0.9658,
"step": 41
},
{
"epoch": 0.05,
"learning_rate": 1.037037037037037e-05,
"loss": 0.9058,
"step": 42
},
{
"epoch": 0.05,
"learning_rate": 1.0617283950617285e-05,
"loss": 0.894,
"step": 43
},
{
"epoch": 0.05,
"learning_rate": 1.0864197530864198e-05,
"loss": 0.9136,
"step": 44
},
{
"epoch": 0.05,
"learning_rate": 1.1111111111111113e-05,
"loss": 0.9175,
"step": 45
},
{
"epoch": 0.05,
"learning_rate": 1.1358024691358025e-05,
"loss": 0.8613,
"step": 46
},
{
"epoch": 0.05,
"learning_rate": 1.160493827160494e-05,
"loss": 0.9106,
"step": 47
},
{
"epoch": 0.05,
"learning_rate": 1.1851851851851852e-05,
"loss": 0.9126,
"step": 48
},
{
"epoch": 0.05,
"learning_rate": 1.2098765432098767e-05,
"loss": 0.9023,
"step": 49
},
{
"epoch": 0.06,
"learning_rate": 1.234567901234568e-05,
"loss": 0.8916,
"step": 50
},
{
"epoch": 0.06,
"learning_rate": 1.2592592592592593e-05,
"loss": 0.8804,
"step": 51
},
{
"epoch": 0.06,
"learning_rate": 1.2839506172839507e-05,
"loss": 0.8911,
"step": 52
},
{
"epoch": 0.06,
"learning_rate": 1.3086419753086422e-05,
"loss": 0.8887,
"step": 53
},
{
"epoch": 0.06,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.8999,
"step": 54
},
{
"epoch": 0.06,
"learning_rate": 1.3580246913580248e-05,
"loss": 0.8643,
"step": 55
},
{
"epoch": 0.06,
"learning_rate": 1.3827160493827162e-05,
"loss": 0.8647,
"step": 56
},
{
"epoch": 0.06,
"learning_rate": 1.4074074074074075e-05,
"loss": 0.8823,
"step": 57
},
{
"epoch": 0.06,
"learning_rate": 1.4320987654320988e-05,
"loss": 0.8721,
"step": 58
},
{
"epoch": 0.07,
"learning_rate": 1.4567901234567903e-05,
"loss": 0.8481,
"step": 59
},
{
"epoch": 0.07,
"learning_rate": 1.4814814814814815e-05,
"loss": 0.8818,
"step": 60
},
{
"epoch": 0.07,
"learning_rate": 1.506172839506173e-05,
"loss": 0.8818,
"step": 61
},
{
"epoch": 0.07,
"learning_rate": 1.5308641975308643e-05,
"loss": 0.8696,
"step": 62
},
{
"epoch": 0.07,
"learning_rate": 1.555555555555556e-05,
"loss": 0.8799,
"step": 63
},
{
"epoch": 0.07,
"learning_rate": 1.580246913580247e-05,
"loss": 0.8691,
"step": 64
},
{
"epoch": 0.07,
"learning_rate": 1.6049382716049385e-05,
"loss": 0.8164,
"step": 65
},
{
"epoch": 0.07,
"learning_rate": 1.6296296296296297e-05,
"loss": 0.8613,
"step": 66
},
{
"epoch": 0.07,
"learning_rate": 1.654320987654321e-05,
"loss": 0.8608,
"step": 67
},
{
"epoch": 0.08,
"learning_rate": 1.6790123456790123e-05,
"loss": 0.8496,
"step": 68
},
{
"epoch": 0.08,
"learning_rate": 1.7037037037037038e-05,
"loss": 0.8452,
"step": 69
},
{
"epoch": 0.08,
"learning_rate": 1.728395061728395e-05,
"loss": 0.853,
"step": 70
},
{
"epoch": 0.08,
"learning_rate": 1.7530864197530865e-05,
"loss": 0.8633,
"step": 71
},
{
"epoch": 0.08,
"learning_rate": 1.7777777777777777e-05,
"loss": 0.8398,
"step": 72
},
{
"epoch": 0.08,
"learning_rate": 1.802469135802469e-05,
"loss": 0.8711,
"step": 73
},
{
"epoch": 0.08,
"learning_rate": 1.8271604938271607e-05,
"loss": 0.8467,
"step": 74
},
{
"epoch": 0.08,
"learning_rate": 1.851851851851852e-05,
"loss": 0.8237,
"step": 75
},
{
"epoch": 0.09,
"learning_rate": 1.8765432098765433e-05,
"loss": 0.8452,
"step": 76
},
{
"epoch": 0.09,
"learning_rate": 1.901234567901235e-05,
"loss": 0.832,
"step": 77
},
{
"epoch": 0.09,
"learning_rate": 1.925925925925926e-05,
"loss": 0.8442,
"step": 78
},
{
"epoch": 0.09,
"learning_rate": 1.9506172839506175e-05,
"loss": 0.8579,
"step": 79
},
{
"epoch": 0.09,
"learning_rate": 1.9753086419753087e-05,
"loss": 0.8364,
"step": 80
},
{
"epoch": 0.09,
"learning_rate": 2e-05,
"loss": 0.8354,
"step": 81
},
{
"epoch": 0.09,
"learning_rate": 1.999999268875389e-05,
"loss": 0.8535,
"step": 82
},
{
"epoch": 0.09,
"learning_rate": 1.9999970755026253e-05,
"loss": 0.8374,
"step": 83
},
{
"epoch": 0.09,
"learning_rate": 1.9999934198849154e-05,
"loss": 0.8369,
"step": 84
},
{
"epoch": 0.1,
"learning_rate": 1.999988302027605e-05,
"loss": 0.8257,
"step": 85
},
{
"epoch": 0.1,
"learning_rate": 1.9999817219381782e-05,
"loss": 0.8335,
"step": 86
},
{
"epoch": 0.1,
"learning_rate": 1.9999736796262564e-05,
"loss": 0.8306,
"step": 87
},
{
"epoch": 0.1,
"learning_rate": 1.9999641751035992e-05,
"loss": 0.8247,
"step": 88
},
{
"epoch": 0.1,
"learning_rate": 1.999953208384105e-05,
"loss": 0.8086,
"step": 89
},
{
"epoch": 0.1,
"learning_rate": 1.9999407794838095e-05,
"loss": 0.8584,
"step": 90
},
{
"epoch": 0.1,
"learning_rate": 1.9999268884208877e-05,
"loss": 0.8237,
"step": 91
},
{
"epoch": 0.1,
"learning_rate": 1.9999115352156507e-05,
"loss": 0.8281,
"step": 92
},
{
"epoch": 0.1,
"learning_rate": 1.9998947198905492e-05,
"loss": 0.8164,
"step": 93
},
{
"epoch": 0.11,
"learning_rate": 1.9998764424701714e-05,
"loss": 0.8149,
"step": 94
},
{
"epoch": 0.11,
"learning_rate": 1.9998567029812434e-05,
"loss": 0.8364,
"step": 95
},
{
"epoch": 0.11,
"learning_rate": 1.999835501452629e-05,
"loss": 0.8345,
"step": 96
},
{
"epoch": 0.11,
"learning_rate": 1.9998128379153307e-05,
"loss": 0.8096,
"step": 97
},
{
"epoch": 0.11,
"learning_rate": 1.999788712402488e-05,
"loss": 0.8159,
"step": 98
},
{
"epoch": 0.11,
"learning_rate": 1.999763124949378e-05,
"loss": 0.7959,
"step": 99
},
{
"epoch": 0.11,
"learning_rate": 1.9997360755934164e-05,
"loss": 0.8252,
"step": 100
},
{
"epoch": 0.11,
"learning_rate": 1.999707564374156e-05,
"loss": 0.8037,
"step": 101
},
{
"epoch": 0.11,
"learning_rate": 1.9996775913332875e-05,
"loss": 0.8496,
"step": 102
},
{
"epoch": 0.12,
"learning_rate": 1.9996461565146384e-05,
"loss": 0.8286,
"step": 103
},
{
"epoch": 0.12,
"learning_rate": 1.9996132599641746e-05,
"loss": 0.8188,
"step": 104
},
{
"epoch": 0.12,
"learning_rate": 1.999578901729999e-05,
"loss": 0.8145,
"step": 105
},
{
"epoch": 0.12,
"learning_rate": 1.9995430818623524e-05,
"loss": 0.8047,
"step": 106
},
{
"epoch": 0.12,
"learning_rate": 1.9995058004136112e-05,
"loss": 0.8198,
"step": 107
},
{
"epoch": 0.12,
"learning_rate": 1.9994670574382913e-05,
"loss": 0.7974,
"step": 108
},
{
"epoch": 0.12,
"learning_rate": 1.999426852993044e-05,
"loss": 0.8193,
"step": 109
},
{
"epoch": 0.12,
"learning_rate": 1.9993851871366585e-05,
"loss": 0.7954,
"step": 110
},
{
"epoch": 0.12,
"learning_rate": 1.9993420599300603e-05,
"loss": 0.8335,
"step": 111
},
{
"epoch": 0.13,
"learning_rate": 1.9992974714363124e-05,
"loss": 0.7974,
"step": 112
},
{
"epoch": 0.13,
"learning_rate": 1.9992514217206146e-05,
"loss": 0.8037,
"step": 113
},
{
"epoch": 0.13,
"learning_rate": 1.9992039108503024e-05,
"loss": 0.77,
"step": 114
},
{
"epoch": 0.13,
"learning_rate": 1.999154938894849e-05,
"loss": 0.7964,
"step": 115
},
{
"epoch": 0.13,
"learning_rate": 1.999104505925863e-05,
"loss": 0.8394,
"step": 116
},
{
"epoch": 0.13,
"learning_rate": 1.999052612017091e-05,
"loss": 0.8184,
"step": 117
},
{
"epoch": 0.13,
"learning_rate": 1.998999257244414e-05,
"loss": 0.7793,
"step": 118
},
{
"epoch": 0.13,
"learning_rate": 1.9989444416858502e-05,
"loss": 0.7944,
"step": 119
},
{
"epoch": 0.13,
"learning_rate": 1.998888165421554e-05,
"loss": 0.8237,
"step": 120
},
{
"epoch": 0.14,
"learning_rate": 1.9988304285338146e-05,
"loss": 0.7876,
"step": 121
},
{
"epoch": 0.14,
"learning_rate": 1.998771231107058e-05,
"loss": 0.7495,
"step": 122
},
{
"epoch": 0.14,
"learning_rate": 1.998710573227846e-05,
"loss": 0.8105,
"step": 123
},
{
"epoch": 0.14,
"learning_rate": 1.9986484549848746e-05,
"loss": 0.8032,
"step": 124
},
{
"epoch": 0.14,
"learning_rate": 1.9985848764689773e-05,
"loss": 0.7783,
"step": 125
},
{
"epoch": 0.14,
"learning_rate": 1.998519837773121e-05,
"loss": 0.8203,
"step": 126
},
{
"epoch": 0.14,
"learning_rate": 1.9984533389924087e-05,
"loss": 0.7886,
"step": 127
},
{
"epoch": 0.14,
"learning_rate": 1.998385380224078e-05,
"loss": 0.8149,
"step": 128
},
{
"epoch": 0.14,
"learning_rate": 1.9983159615675022e-05,
"loss": 0.8101,
"step": 129
},
{
"epoch": 0.15,
"learning_rate": 1.998245083124188e-05,
"loss": 0.7954,
"step": 130
},
{
"epoch": 0.15,
"learning_rate": 1.9981727449977772e-05,
"loss": 0.7974,
"step": 131
},
{
"epoch": 0.15,
"learning_rate": 1.9980989472940467e-05,
"loss": 0.811,
"step": 132
},
{
"epoch": 0.15,
"learning_rate": 1.998023690120907e-05,
"loss": 0.7959,
"step": 133
},
{
"epoch": 0.15,
"learning_rate": 1.9979469735884026e-05,
"loss": 0.8213,
"step": 134
},
{
"epoch": 0.15,
"learning_rate": 1.9978687978087125e-05,
"loss": 0.814,
"step": 135
},
{
"epoch": 0.15,
"learning_rate": 1.9977891628961492e-05,
"loss": 0.8228,
"step": 136
},
{
"epoch": 0.15,
"learning_rate": 1.9977080689671587e-05,
"loss": 0.7778,
"step": 137
},
{
"epoch": 0.15,
"learning_rate": 1.9976255161403203e-05,
"loss": 0.812,
"step": 138
},
{
"epoch": 0.16,
"learning_rate": 1.997541504536347e-05,
"loss": 0.7827,
"step": 139
},
{
"epoch": 0.16,
"learning_rate": 1.9974560342780848e-05,
"loss": 0.7915,
"step": 140
},
{
"epoch": 0.16,
"learning_rate": 1.997369105490512e-05,
"loss": 0.7798,
"step": 141
},
{
"epoch": 0.16,
"learning_rate": 1.9972807183007406e-05,
"loss": 0.791,
"step": 142
},
{
"epoch": 0.16,
"learning_rate": 1.997190872838015e-05,
"loss": 0.8188,
"step": 143
},
{
"epoch": 0.16,
"learning_rate": 1.9970995692337113e-05,
"loss": 0.7881,
"step": 144
},
{
"epoch": 0.16,
"learning_rate": 1.997006807621338e-05,
"loss": 0.8066,
"step": 145
},
{
"epoch": 0.16,
"learning_rate": 1.996912588136536e-05,
"loss": 0.7681,
"step": 146
},
{
"epoch": 0.16,
"learning_rate": 1.9968169109170775e-05,
"loss": 0.7861,
"step": 147
},
{
"epoch": 0.17,
"learning_rate": 1.9967197761028663e-05,
"loss": 0.7793,
"step": 148
},
{
"epoch": 0.17,
"learning_rate": 1.996621183835938e-05,
"loss": 0.8101,
"step": 149
},
{
"epoch": 0.17,
"learning_rate": 1.9965211342604586e-05,
"loss": 0.7847,
"step": 150
},
{
"epoch": 0.17,
"learning_rate": 1.9964196275227263e-05,
"loss": 0.792,
"step": 151
},
{
"epoch": 0.17,
"learning_rate": 1.996316663771168e-05,
"loss": 0.7944,
"step": 152
},
{
"epoch": 0.17,
"learning_rate": 1.996212243156344e-05,
"loss": 0.7642,
"step": 153
},
{
"epoch": 0.17,
"learning_rate": 1.996106365830942e-05,
"loss": 0.7847,
"step": 154
},
{
"epoch": 0.17,
"learning_rate": 1.9959990319497814e-05,
"loss": 0.7744,
"step": 155
},
{
"epoch": 0.17,
"learning_rate": 1.995890241669811e-05,
"loss": 0.77,
"step": 156
},
{
"epoch": 0.18,
"learning_rate": 1.9957799951501096e-05,
"loss": 0.7754,
"step": 157
},
{
"epoch": 0.18,
"learning_rate": 1.9956682925518853e-05,
"loss": 0.792,
"step": 158
},
{
"epoch": 0.18,
"learning_rate": 1.9955551340384745e-05,
"loss": 0.7573,
"step": 159
},
{
"epoch": 0.18,
"learning_rate": 1.995440519775343e-05,
"loss": 0.7803,
"step": 160
},
{
"epoch": 0.18,
"learning_rate": 1.9953244499300865e-05,
"loss": 0.7935,
"step": 161
},
{
"epoch": 0.18,
"learning_rate": 1.995206924672427e-05,
"loss": 0.7544,
"step": 162
},
{
"epoch": 0.18,
"learning_rate": 1.9950879441742158e-05,
"loss": 0.8022,
"step": 163
},
{
"epoch": 0.18,
"learning_rate": 1.9949675086094328e-05,
"loss": 0.7734,
"step": 164
},
{
"epoch": 0.18,
"learning_rate": 1.994845618154184e-05,
"loss": 0.7949,
"step": 165
},
{
"epoch": 0.19,
"learning_rate": 1.9947222729867038e-05,
"loss": 0.7695,
"step": 166
},
{
"epoch": 0.19,
"learning_rate": 1.9945974732873544e-05,
"loss": 0.7632,
"step": 167
},
{
"epoch": 0.19,
"learning_rate": 1.994471219238623e-05,
"loss": 0.7783,
"step": 168
},
{
"epoch": 0.19,
"learning_rate": 1.9943435110251247e-05,
"loss": 0.7769,
"step": 169
},
{
"epoch": 0.19,
"learning_rate": 1.9942143488336013e-05,
"loss": 0.7686,
"step": 170
},
{
"epoch": 0.19,
"learning_rate": 1.994083732852919e-05,
"loss": 0.7749,
"step": 171
},
{
"epoch": 0.19,
"learning_rate": 1.993951663274072e-05,
"loss": 0.7788,
"step": 172
},
{
"epoch": 0.19,
"learning_rate": 1.9938181402901792e-05,
"loss": 0.7681,
"step": 173
},
{
"epoch": 0.19,
"learning_rate": 1.993683164096483e-05,
"loss": 0.7754,
"step": 174
},
{
"epoch": 0.2,
"learning_rate": 1.993546734890354e-05,
"loss": 0.7827,
"step": 175
},
{
"epoch": 0.2,
"learning_rate": 1.993408852871284e-05,
"loss": 0.7637,
"step": 176
},
{
"epoch": 0.2,
"learning_rate": 1.9932695182408917e-05,
"loss": 0.7568,
"step": 177
},
{
"epoch": 0.2,
"learning_rate": 1.9931287312029192e-05,
"loss": 0.8037,
"step": 178
},
{
"epoch": 0.2,
"learning_rate": 1.9929864919632323e-05,
"loss": 0.7563,
"step": 179
},
{
"epoch": 0.2,
"learning_rate": 1.99284280072982e-05,
"loss": 0.7632,
"step": 180
},
{
"epoch": 0.2,
"learning_rate": 1.9926976577127943e-05,
"loss": 0.7671,
"step": 181
},
{
"epoch": 0.2,
"learning_rate": 1.992551063124391e-05,
"loss": 0.7788,
"step": 182
},
{
"epoch": 0.2,
"learning_rate": 1.9924030171789676e-05,
"loss": 0.7261,
"step": 183
},
{
"epoch": 0.21,
"learning_rate": 1.9922535200930046e-05,
"loss": 0.7539,
"step": 184
},
{
"epoch": 0.21,
"learning_rate": 1.9921025720851035e-05,
"loss": 0.7485,
"step": 185
},
{
"epoch": 0.21,
"learning_rate": 1.9919501733759882e-05,
"loss": 0.7617,
"step": 186
},
{
"epoch": 0.21,
"learning_rate": 1.9917963241885037e-05,
"loss": 0.7603,
"step": 187
},
{
"epoch": 0.21,
"learning_rate": 1.9916410247476158e-05,
"loss": 0.771,
"step": 188
},
{
"epoch": 0.21,
"learning_rate": 1.9914842752804106e-05,
"loss": 0.7598,
"step": 189
},
{
"epoch": 0.21,
"learning_rate": 1.991326076016095e-05,
"loss": 0.7778,
"step": 190
},
{
"epoch": 0.21,
"learning_rate": 1.9911664271859957e-05,
"loss": 0.7783,
"step": 191
},
{
"epoch": 0.21,
"learning_rate": 1.99100532902356e-05,
"loss": 0.7393,
"step": 192
},
{
"epoch": 0.22,
"learning_rate": 1.9908427817643524e-05,
"loss": 0.7622,
"step": 193
},
{
"epoch": 0.22,
"learning_rate": 1.990678785646058e-05,
"loss": 0.7769,
"step": 194
},
{
"epoch": 0.22,
"learning_rate": 1.99051334090848e-05,
"loss": 0.7627,
"step": 195
},
{
"epoch": 0.22,
"learning_rate": 1.9903464477935398e-05,
"loss": 0.769,
"step": 196
},
{
"epoch": 0.22,
"learning_rate": 1.9901781065452765e-05,
"loss": 0.748,
"step": 197
},
{
"epoch": 0.22,
"learning_rate": 1.9900083174098474e-05,
"loss": 0.7734,
"step": 198
},
{
"epoch": 0.22,
"learning_rate": 1.9898370806355264e-05,
"loss": 0.7622,
"step": 199
},
{
"epoch": 0.22,
"learning_rate": 1.989664396472704e-05,
"loss": 0.748,
"step": 200
},
{
"epoch": 0.22,
"learning_rate": 1.989490265173888e-05,
"loss": 0.7866,
"step": 201
},
{
"epoch": 0.23,
"learning_rate": 1.989314686993701e-05,
"loss": 0.7842,
"step": 202
},
{
"epoch": 0.23,
"learning_rate": 1.989137662188883e-05,
"loss": 0.7524,
"step": 203
},
{
"epoch": 0.23,
"learning_rate": 1.9889591910182878e-05,
"loss": 0.7837,
"step": 204
},
{
"epoch": 0.23,
"learning_rate": 1.9887792737428847e-05,
"loss": 0.7739,
"step": 205
},
{
"epoch": 0.23,
"learning_rate": 1.988597910625758e-05,
"loss": 0.7676,
"step": 206
},
{
"epoch": 0.23,
"learning_rate": 1.9884151019321053e-05,
"loss": 0.7705,
"step": 207
},
{
"epoch": 0.23,
"learning_rate": 1.9882308479292387e-05,
"loss": 0.7974,
"step": 208
},
{
"epoch": 0.23,
"learning_rate": 1.9880451488865838e-05,
"loss": 0.748,
"step": 209
},
{
"epoch": 0.24,
"learning_rate": 1.987858005075678e-05,
"loss": 0.752,
"step": 210
},
{
"epoch": 0.24,
"learning_rate": 1.987669416770173e-05,
"loss": 0.7388,
"step": 211
},
{
"epoch": 0.24,
"learning_rate": 1.9874793842458318e-05,
"loss": 0.7764,
"step": 212
},
{
"epoch": 0.24,
"learning_rate": 1.987287907780529e-05,
"loss": 0.7417,
"step": 213
},
{
"epoch": 0.24,
"learning_rate": 1.9870949876542512e-05,
"loss": 0.7632,
"step": 214
},
{
"epoch": 0.24,
"learning_rate": 1.9869006241490952e-05,
"loss": 0.7935,
"step": 215
},
{
"epoch": 0.24,
"learning_rate": 1.9867048175492697e-05,
"loss": 0.7856,
"step": 216
},
{
"epoch": 0.24,
"learning_rate": 1.986507568141092e-05,
"loss": 0.769,
"step": 217
},
{
"epoch": 0.24,
"learning_rate": 1.9863088762129905e-05,
"loss": 0.7681,
"step": 218
},
{
"epoch": 0.25,
"learning_rate": 1.986108742055502e-05,
"loss": 0.7471,
"step": 219
},
{
"epoch": 0.25,
"learning_rate": 1.985907165961272e-05,
"loss": 0.7539,
"step": 220
},
{
"epoch": 0.25,
"learning_rate": 1.985704148225056e-05,
"loss": 0.7656,
"step": 221
},
{
"epoch": 0.25,
"learning_rate": 1.985499689143716e-05,
"loss": 0.7632,
"step": 222
},
{
"epoch": 0.25,
"learning_rate": 1.9852937890162217e-05,
"loss": 0.7578,
"step": 223
},
{
"epoch": 0.25,
"learning_rate": 1.9850864481436517e-05,
"loss": 0.771,
"step": 224
},
{
"epoch": 0.25,
"learning_rate": 1.9848776668291885e-05,
"loss": 0.7935,
"step": 225
},
{
"epoch": 0.25,
"learning_rate": 1.9846674453781235e-05,
"loss": 0.7646,
"step": 226
},
{
"epoch": 0.25,
"learning_rate": 1.9844557840978524e-05,
"loss": 0.7432,
"step": 227
},
{
"epoch": 0.26,
"learning_rate": 1.9842426832978766e-05,
"loss": 0.7773,
"step": 228
},
{
"epoch": 0.26,
"learning_rate": 1.9840281432898033e-05,
"loss": 0.7534,
"step": 229
},
{
"epoch": 0.26,
"learning_rate": 1.9838121643873426e-05,
"loss": 0.7524,
"step": 230
},
{
"epoch": 0.26,
"learning_rate": 1.9835947469063098e-05,
"loss": 0.7441,
"step": 231
},
{
"epoch": 0.26,
"learning_rate": 1.9833758911646238e-05,
"loss": 0.7695,
"step": 232
},
{
"epoch": 0.26,
"learning_rate": 1.9831555974823055e-05,
"loss": 0.7612,
"step": 233
},
{
"epoch": 0.26,
"learning_rate": 1.9829338661814798e-05,
"loss": 0.7607,
"step": 234
},
{
"epoch": 0.26,
"learning_rate": 1.982710697586373e-05,
"loss": 0.7393,
"step": 235
},
{
"epoch": 0.26,
"learning_rate": 1.982486092023313e-05,
"loss": 0.7432,
"step": 236
},
{
"epoch": 0.27,
"learning_rate": 1.9822600498207292e-05,
"loss": 0.7573,
"step": 237
},
{
"epoch": 0.27,
"learning_rate": 1.9820325713091514e-05,
"loss": 0.7793,
"step": 238
},
{
"epoch": 0.27,
"learning_rate": 1.9818036568212108e-05,
"loss": 0.75,
"step": 239
},
{
"epoch": 0.27,
"learning_rate": 1.981573306691636e-05,
"loss": 0.7671,
"step": 240
},
{
"epoch": 0.27,
"learning_rate": 1.9813415212572574e-05,
"loss": 0.7617,
"step": 241
},
{
"epoch": 0.27,
"learning_rate": 1.981108300857003e-05,
"loss": 0.7471,
"step": 242
},
{
"epoch": 0.27,
"learning_rate": 1.9808736458318988e-05,
"loss": 0.7788,
"step": 243
},
{
"epoch": 0.27,
"learning_rate": 1.9806375565250685e-05,
"loss": 0.7437,
"step": 244
},
{
"epoch": 0.27,
"learning_rate": 1.9804000332817343e-05,
"loss": 0.752,
"step": 245
},
{
"epoch": 0.28,
"learning_rate": 1.9801610764492142e-05,
"loss": 0.7476,
"step": 246
},
{
"epoch": 0.28,
"learning_rate": 1.9799206863769225e-05,
"loss": 0.7798,
"step": 247
},
{
"epoch": 0.28,
"learning_rate": 1.9796788634163695e-05,
"loss": 0.7412,
"step": 248
},
{
"epoch": 0.28,
"learning_rate": 1.9794356079211605e-05,
"loss": 0.7612,
"step": 249
},
{
"epoch": 0.28,
"learning_rate": 1.9791909202469955e-05,
"loss": 0.7603,
"step": 250
},
{
"epoch": 0.28,
"learning_rate": 1.9789448007516698e-05,
"loss": 0.7329,
"step": 251
},
{
"epoch": 0.28,
"learning_rate": 1.97869724979507e-05,
"loss": 0.7485,
"step": 252
},
{
"epoch": 0.28,
"learning_rate": 1.9784482677391785e-05,
"loss": 0.7241,
"step": 253
},
{
"epoch": 0.28,
"learning_rate": 1.9781978549480682e-05,
"loss": 0.7451,
"step": 254
},
{
"epoch": 0.29,
"learning_rate": 1.9779460117879058e-05,
"loss": 0.7466,
"step": 255
},
{
"epoch": 0.29,
"learning_rate": 1.977692738626948e-05,
"loss": 0.7642,
"step": 256
},
{
"epoch": 0.29,
"learning_rate": 1.9774380358355442e-05,
"loss": 0.7778,
"step": 257
},
{
"epoch": 0.29,
"learning_rate": 1.9771819037861327e-05,
"loss": 0.7485,
"step": 258
},
{
"epoch": 0.29,
"learning_rate": 1.9769243428532425e-05,
"loss": 0.7461,
"step": 259
},
{
"epoch": 0.29,
"learning_rate": 1.9766653534134917e-05,
"loss": 0.7271,
"step": 260
},
{
"epoch": 0.29,
"learning_rate": 1.976404935845588e-05,
"loss": 0.7583,
"step": 261
},
{
"epoch": 0.29,
"learning_rate": 1.976143090530326e-05,
"loss": 0.7334,
"step": 262
},
{
"epoch": 0.29,
"learning_rate": 1.9758798178505894e-05,
"loss": 0.749,
"step": 263
},
{
"epoch": 0.3,
"learning_rate": 1.9756151181913483e-05,
"loss": 0.7505,
"step": 264
},
{
"epoch": 0.3,
"learning_rate": 1.9753489919396598e-05,
"loss": 0.7563,
"step": 265
},
{
"epoch": 0.3,
"learning_rate": 1.9750814394846664e-05,
"loss": 0.7573,
"step": 266
},
{
"epoch": 0.3,
"learning_rate": 1.9748124612175967e-05,
"loss": 0.7842,
"step": 267
},
{
"epoch": 0.3,
"learning_rate": 1.9745420575317636e-05,
"loss": 0.7456,
"step": 268
},
{
"epoch": 0.3,
"learning_rate": 1.9742702288225653e-05,
"loss": 0.7256,
"step": 269
},
{
"epoch": 0.3,
"learning_rate": 1.9739969754874827e-05,
"loss": 0.7222,
"step": 270
},
{
"epoch": 0.3,
"learning_rate": 1.9737222979260802e-05,
"loss": 0.7402,
"step": 271
},
{
"epoch": 0.3,
"learning_rate": 1.973446196540005e-05,
"loss": 0.7666,
"step": 272
},
{
"epoch": 0.31,
"learning_rate": 1.9731686717329866e-05,
"loss": 0.7651,
"step": 273
},
{
"epoch": 0.31,
"learning_rate": 1.9728897239108343e-05,
"loss": 0.7388,
"step": 274
},
{
"epoch": 0.31,
"learning_rate": 1.972609353481441e-05,
"loss": 0.7622,
"step": 275
},
{
"epoch": 0.31,
"learning_rate": 1.9723275608547764e-05,
"loss": 0.7236,
"step": 276
},
{
"epoch": 0.31,
"learning_rate": 1.9720443464428927e-05,
"loss": 0.7646,
"step": 277
},
{
"epoch": 0.31,
"learning_rate": 1.9717597106599192e-05,
"loss": 0.7773,
"step": 278
},
{
"epoch": 0.31,
"learning_rate": 1.971473653922065e-05,
"loss": 0.7598,
"step": 279
},
{
"epoch": 0.31,
"learning_rate": 1.971186176647616e-05,
"loss": 0.7495,
"step": 280
},
{
"epoch": 0.31,
"learning_rate": 1.9708972792569356e-05,
"loss": 0.7603,
"step": 281
},
{
"epoch": 0.32,
"learning_rate": 1.9706069621724643e-05,
"loss": 0.7349,
"step": 282
},
{
"epoch": 0.32,
"learning_rate": 1.970315225818717e-05,
"loss": 0.71,
"step": 283
},
{
"epoch": 0.32,
"learning_rate": 1.970022070622286e-05,
"loss": 0.7148,
"step": 284
},
{
"epoch": 0.32,
"learning_rate": 1.9697274970118365e-05,
"loss": 0.7559,
"step": 285
},
{
"epoch": 0.32,
"learning_rate": 1.969431505418109e-05,
"loss": 0.7681,
"step": 286
},
{
"epoch": 0.32,
"learning_rate": 1.969134096273917e-05,
"loss": 0.7344,
"step": 287
},
{
"epoch": 0.32,
"learning_rate": 1.968835270014146e-05,
"loss": 0.7637,
"step": 288
},
{
"epoch": 0.32,
"learning_rate": 1.9685350270757557e-05,
"loss": 0.7422,
"step": 289
},
{
"epoch": 0.32,
"learning_rate": 1.9682333678977758e-05,
"loss": 0.7427,
"step": 290
},
{
"epoch": 0.33,
"learning_rate": 1.967930292921306e-05,
"loss": 0.751,
"step": 291
},
{
"epoch": 0.33,
"learning_rate": 1.9676258025895188e-05,
"loss": 0.728,
"step": 292
},
{
"epoch": 0.33,
"learning_rate": 1.9673198973476543e-05,
"loss": 0.7563,
"step": 293
},
{
"epoch": 0.33,
"learning_rate": 1.967012577643023e-05,
"loss": 0.7451,
"step": 294
},
{
"epoch": 0.33,
"learning_rate": 1.9667038439250016e-05,
"loss": 0.7676,
"step": 295
},
{
"epoch": 0.33,
"learning_rate": 1.9663936966450364e-05,
"loss": 0.7188,
"step": 296
},
{
"epoch": 0.33,
"learning_rate": 1.9660821362566406e-05,
"loss": 0.7441,
"step": 297
},
{
"epoch": 0.33,
"learning_rate": 1.965769163215392e-05,
"loss": 0.7168,
"step": 298
},
{
"epoch": 0.33,
"learning_rate": 1.965454777978936e-05,
"loss": 0.7676,
"step": 299
},
{
"epoch": 0.34,
"learning_rate": 1.965138981006982e-05,
"loss": 0.7314,
"step": 300
},
{
"epoch": 0.34,
"learning_rate": 1.964821772761304e-05,
"loss": 0.7256,
"step": 301
},
{
"epoch": 0.34,
"learning_rate": 1.9645031537057392e-05,
"loss": 0.7539,
"step": 302
},
{
"epoch": 0.34,
"learning_rate": 1.9641831243061878e-05,
"loss": 0.7324,
"step": 303
},
{
"epoch": 0.34,
"learning_rate": 1.9638616850306132e-05,
"loss": 0.7559,
"step": 304
},
{
"epoch": 0.34,
"learning_rate": 1.96353883634904e-05,
"loss": 0.7183,
"step": 305
},
{
"epoch": 0.34,
"learning_rate": 1.963214578733552e-05,
"loss": 0.7222,
"step": 306
},
{
"epoch": 0.34,
"learning_rate": 1.9628889126582956e-05,
"loss": 0.7451,
"step": 307
},
{
"epoch": 0.34,
"learning_rate": 1.9625618385994764e-05,
"loss": 0.7539,
"step": 308
},
{
"epoch": 0.35,
"learning_rate": 1.962233357035357e-05,
"loss": 0.7427,
"step": 309
},
{
"epoch": 0.35,
"learning_rate": 1.9619034684462597e-05,
"loss": 0.7393,
"step": 310
},
{
"epoch": 0.35,
"learning_rate": 1.9615721733145644e-05,
"loss": 0.731,
"step": 311
},
{
"epoch": 0.35,
"learning_rate": 1.9612394721247063e-05,
"loss": 0.7612,
"step": 312
},
{
"epoch": 0.35,
"learning_rate": 1.960905365363178e-05,
"loss": 0.7178,
"step": 313
},
{
"epoch": 0.35,
"learning_rate": 1.9605698535185268e-05,
"loss": 0.7305,
"step": 314
},
{
"epoch": 0.35,
"learning_rate": 1.960232937081354e-05,
"loss": 0.7144,
"step": 315
},
{
"epoch": 0.35,
"learning_rate": 1.9598946165443165e-05,
"loss": 0.7402,
"step": 316
},
{
"epoch": 0.35,
"learning_rate": 1.9595548924021222e-05,
"loss": 0.7168,
"step": 317
},
{
"epoch": 0.36,
"learning_rate": 1.9592137651515333e-05,
"loss": 0.7466,
"step": 318
},
{
"epoch": 0.36,
"learning_rate": 1.9588712352913625e-05,
"loss": 0.6982,
"step": 319
},
{
"epoch": 0.36,
"learning_rate": 1.9585273033224735e-05,
"loss": 0.7217,
"step": 320
},
{
"epoch": 0.36,
"learning_rate": 1.9581819697477813e-05,
"loss": 0.728,
"step": 321
},
{
"epoch": 0.36,
"learning_rate": 1.957835235072249e-05,
"loss": 0.7178,
"step": 322
},
{
"epoch": 0.36,
"learning_rate": 1.9574870998028892e-05,
"loss": 0.7314,
"step": 323
},
{
"epoch": 0.36,
"learning_rate": 1.9571375644487626e-05,
"loss": 0.7256,
"step": 324
},
{
"epoch": 0.36,
"learning_rate": 1.956786629520977e-05,
"loss": 0.7354,
"step": 325
},
{
"epoch": 0.36,
"learning_rate": 1.956434295532687e-05,
"loss": 0.7314,
"step": 326
},
{
"epoch": 0.37,
"learning_rate": 1.9560805629990917e-05,
"loss": 0.7393,
"step": 327
},
{
"epoch": 0.37,
"learning_rate": 1.955725432437437e-05,
"loss": 0.7158,
"step": 328
},
{
"epoch": 0.37,
"learning_rate": 1.9553689043670127e-05,
"loss": 0.7363,
"step": 329
},
{
"epoch": 0.37,
"learning_rate": 1.955010979309151e-05,
"loss": 0.7285,
"step": 330
},
{
"epoch": 0.37,
"learning_rate": 1.9546516577872277e-05,
"loss": 0.7178,
"step": 331
},
{
"epoch": 0.37,
"learning_rate": 1.9542909403266603e-05,
"loss": 0.7241,
"step": 332
},
{
"epoch": 0.37,
"learning_rate": 1.953928827454908e-05,
"loss": 0.7261,
"step": 333
},
{
"epoch": 0.37,
"learning_rate": 1.953565319701469e-05,
"loss": 0.7168,
"step": 334
},
{
"epoch": 0.37,
"learning_rate": 1.953200417597884e-05,
"loss": 0.7324,
"step": 335
},
{
"epoch": 0.38,
"learning_rate": 1.9528341216777296e-05,
"loss": 0.7329,
"step": 336
},
{
"epoch": 0.38,
"learning_rate": 1.952466432476622e-05,
"loss": 0.7427,
"step": 337
},
{
"epoch": 0.38,
"learning_rate": 1.9520973505322144e-05,
"loss": 0.731,
"step": 338
},
{
"epoch": 0.38,
"learning_rate": 1.9517268763841965e-05,
"loss": 0.7041,
"step": 339
},
{
"epoch": 0.38,
"learning_rate": 1.951355010574294e-05,
"loss": 0.729,
"step": 340
},
{
"epoch": 0.38,
"learning_rate": 1.9509817536462673e-05,
"loss": 0.7266,
"step": 341
},
{
"epoch": 0.38,
"learning_rate": 1.950607106145911e-05,
"loss": 0.7275,
"step": 342
},
{
"epoch": 0.38,
"learning_rate": 1.9502310686210537e-05,
"loss": 0.7129,
"step": 343
},
{
"epoch": 0.39,
"learning_rate": 1.9498536416215553e-05,
"loss": 0.7012,
"step": 344
},
{
"epoch": 0.39,
"learning_rate": 1.9494748256993082e-05,
"loss": 0.7734,
"step": 345
},
{
"epoch": 0.39,
"learning_rate": 1.949094621408236e-05,
"loss": 0.7139,
"step": 346
},
{
"epoch": 0.39,
"learning_rate": 1.9487130293042917e-05,
"loss": 0.7437,
"step": 347
},
{
"epoch": 0.39,
"learning_rate": 1.9483300499454584e-05,
"loss": 0.7158,
"step": 348
},
{
"epoch": 0.39,
"learning_rate": 1.9479456838917476e-05,
"loss": 0.7012,
"step": 349
},
{
"epoch": 0.39,
"learning_rate": 1.9475599317051975e-05,
"loss": 0.6899,
"step": 350
},
{
"epoch": 0.39,
"learning_rate": 1.9471727939498746e-05,
"loss": 0.7197,
"step": 351
},
{
"epoch": 0.39,
"learning_rate": 1.9467842711918705e-05,
"loss": 0.7373,
"step": 352
},
{
"epoch": 0.4,
"learning_rate": 1.9463943639993026e-05,
"loss": 0.7148,
"step": 353
},
{
"epoch": 0.4,
"learning_rate": 1.9460030729423116e-05,
"loss": 0.7026,
"step": 354
},
{
"epoch": 0.4,
"learning_rate": 1.9456103985930633e-05,
"loss": 0.73,
"step": 355
},
{
"epoch": 0.4,
"learning_rate": 1.9452163415257457e-05,
"loss": 0.7148,
"step": 356
},
{
"epoch": 0.4,
"learning_rate": 1.9448209023165676e-05,
"loss": 0.7251,
"step": 357
},
{
"epoch": 0.4,
"learning_rate": 1.94442408154376e-05,
"loss": 0.7441,
"step": 358
},
{
"epoch": 0.4,
"learning_rate": 1.9440258797875742e-05,
"loss": 0.7559,
"step": 359
},
{
"epoch": 0.4,
"learning_rate": 1.9436262976302797e-05,
"loss": 0.7437,
"step": 360
},
{
"epoch": 0.4,
"learning_rate": 1.9432253356561658e-05,
"loss": 0.7227,
"step": 361
},
{
"epoch": 0.41,
"learning_rate": 1.942822994451538e-05,
"loss": 0.7539,
"step": 362
},
{
"epoch": 0.41,
"learning_rate": 1.9424192746047207e-05,
"loss": 0.748,
"step": 363
},
{
"epoch": 0.41,
"learning_rate": 1.942014176706052e-05,
"loss": 0.7402,
"step": 364
},
{
"epoch": 0.41,
"learning_rate": 1.941607701347886e-05,
"loss": 0.7402,
"step": 365
},
{
"epoch": 0.41,
"learning_rate": 1.9411998491245917e-05,
"loss": 0.7197,
"step": 366
},
{
"epoch": 0.41,
"learning_rate": 1.9407906206325497e-05,
"loss": 0.7246,
"step": 367
},
{
"epoch": 0.41,
"learning_rate": 1.9403800164701547e-05,
"loss": 0.7256,
"step": 368
},
{
"epoch": 0.41,
"learning_rate": 1.9399680372378122e-05,
"loss": 0.7227,
"step": 369
},
{
"epoch": 0.41,
"learning_rate": 1.9395546835379383e-05,
"loss": 0.7163,
"step": 370
},
{
"epoch": 0.42,
"learning_rate": 1.9391399559749593e-05,
"loss": 0.7188,
"step": 371
},
{
"epoch": 0.42,
"learning_rate": 1.9387238551553103e-05,
"loss": 0.7354,
"step": 372
},
{
"epoch": 0.42,
"learning_rate": 1.9383063816874342e-05,
"loss": 0.7368,
"step": 373
},
{
"epoch": 0.42,
"learning_rate": 1.9378875361817818e-05,
"loss": 0.7495,
"step": 374
},
{
"epoch": 0.42,
"learning_rate": 1.937467319250809e-05,
"loss": 0.7261,
"step": 375
},
{
"epoch": 0.42,
"learning_rate": 1.9370457315089774e-05,
"loss": 0.7056,
"step": 376
},
{
"epoch": 0.42,
"learning_rate": 1.9366227735727544e-05,
"loss": 0.7178,
"step": 377
},
{
"epoch": 0.42,
"learning_rate": 1.9361984460606093e-05,
"loss": 0.7124,
"step": 378
},
{
"epoch": 0.42,
"learning_rate": 1.9357727495930147e-05,
"loss": 0.7217,
"step": 379
},
{
"epoch": 0.43,
"learning_rate": 1.935345684792445e-05,
"loss": 0.7461,
"step": 380
},
{
"epoch": 0.43,
"learning_rate": 1.9349172522833747e-05,
"loss": 0.7153,
"step": 381
},
{
"epoch": 0.43,
"learning_rate": 1.9344874526922802e-05,
"loss": 0.7197,
"step": 382
},
{
"epoch": 0.43,
"learning_rate": 1.9340562866476346e-05,
"loss": 0.7056,
"step": 383
},
{
"epoch": 0.43,
"learning_rate": 1.9336237547799108e-05,
"loss": 0.6953,
"step": 384
},
{
"epoch": 0.43,
"learning_rate": 1.9331898577215777e-05,
"loss": 0.7148,
"step": 385
},
{
"epoch": 0.43,
"learning_rate": 1.932754596107101e-05,
"loss": 0.6855,
"step": 386
},
{
"epoch": 0.43,
"learning_rate": 1.932317970572942e-05,
"loss": 0.729,
"step": 387
},
{
"epoch": 0.43,
"learning_rate": 1.9318799817575553e-05,
"loss": 0.728,
"step": 388
},
{
"epoch": 0.44,
"learning_rate": 1.9314406303013906e-05,
"loss": 0.7144,
"step": 389
},
{
"epoch": 0.44,
"learning_rate": 1.9309999168468887e-05,
"loss": 0.7573,
"step": 390
},
{
"epoch": 0.44,
"learning_rate": 1.9305578420384824e-05,
"loss": 0.6982,
"step": 391
},
{
"epoch": 0.44,
"learning_rate": 1.930114406522596e-05,
"loss": 0.6987,
"step": 392
},
{
"epoch": 0.44,
"learning_rate": 1.9296696109476417e-05,
"loss": 0.71,
"step": 393
},
{
"epoch": 0.44,
"learning_rate": 1.9292234559640222e-05,
"loss": 0.6797,
"step": 394
},
{
"epoch": 0.44,
"learning_rate": 1.9287759422241272e-05,
"loss": 0.7178,
"step": 395
},
{
"epoch": 0.44,
"learning_rate": 1.928327070382333e-05,
"loss": 0.709,
"step": 396
},
{
"epoch": 0.44,
"learning_rate": 1.9278768410950023e-05,
"loss": 0.7119,
"step": 397
},
{
"epoch": 0.45,
"learning_rate": 1.9274252550204825e-05,
"loss": 0.7192,
"step": 398
},
{
"epoch": 0.45,
"learning_rate": 1.926972312819105e-05,
"loss": 0.7183,
"step": 399
},
{
"epoch": 0.45,
"learning_rate": 1.9265180151531838e-05,
"loss": 0.7124,
"step": 400
},
{
"epoch": 0.45,
"learning_rate": 1.9260623626870164e-05,
"loss": 0.7241,
"step": 401
},
{
"epoch": 0.45,
"learning_rate": 1.9256053560868793e-05,
"loss": 0.7124,
"step": 402
},
{
"epoch": 0.45,
"learning_rate": 1.92514699602103e-05,
"loss": 0.7456,
"step": 403
},
{
"epoch": 0.45,
"learning_rate": 1.9246872831597056e-05,
"loss": 0.7192,
"step": 404
},
{
"epoch": 0.45,
"learning_rate": 1.9242262181751207e-05,
"loss": 0.7251,
"step": 405
},
{
"epoch": 0.45,
"learning_rate": 1.9237638017414676e-05,
"loss": 0.7085,
"step": 406
},
{
"epoch": 0.46,
"learning_rate": 1.9233000345349136e-05,
"loss": 0.7109,
"step": 407
},
{
"epoch": 0.46,
"learning_rate": 1.9228349172336023e-05,
"loss": 0.7241,
"step": 408
},
{
"epoch": 0.46,
"learning_rate": 1.9223684505176518e-05,
"loss": 0.7222,
"step": 409
},
{
"epoch": 0.46,
"learning_rate": 1.9219006350691515e-05,
"loss": 0.7256,
"step": 410
},
{
"epoch": 0.46,
"learning_rate": 1.9214314715721646e-05,
"loss": 0.7114,
"step": 411
},
{
"epoch": 0.46,
"learning_rate": 1.9209609607127254e-05,
"loss": 0.7168,
"step": 412
},
{
"epoch": 0.46,
"learning_rate": 1.920489103178838e-05,
"loss": 0.7134,
"step": 413
},
{
"epoch": 0.46,
"learning_rate": 1.920015899660475e-05,
"loss": 0.7085,
"step": 414
},
{
"epoch": 0.46,
"learning_rate": 1.919541350849579e-05,
"loss": 0.7241,
"step": 415
},
{
"epoch": 0.47,
"learning_rate": 1.9190654574400577e-05,
"loss": 0.7485,
"step": 416
},
{
"epoch": 0.47,
"learning_rate": 1.918588220127786e-05,
"loss": 0.7163,
"step": 417
},
{
"epoch": 0.47,
"learning_rate": 1.9181096396106044e-05,
"loss": 0.6982,
"step": 418
},
{
"epoch": 0.47,
"learning_rate": 1.9176297165883166e-05,
"loss": 0.7305,
"step": 419
},
{
"epoch": 0.47,
"learning_rate": 1.9171484517626893e-05,
"loss": 0.7373,
"step": 420
},
{
"epoch": 0.47,
"learning_rate": 1.9166658458374518e-05,
"loss": 0.7007,
"step": 421
},
{
"epoch": 0.47,
"learning_rate": 1.9161818995182943e-05,
"loss": 0.6958,
"step": 422
},
{
"epoch": 0.47,
"learning_rate": 1.915696613512867e-05,
"loss": 0.7256,
"step": 423
},
{
"epoch": 0.47,
"learning_rate": 1.915209988530779e-05,
"loss": 0.7144,
"step": 424
},
{
"epoch": 0.48,
"learning_rate": 1.914722025283597e-05,
"loss": 0.7075,
"step": 425
},
{
"epoch": 0.48,
"learning_rate": 1.914232724484845e-05,
"loss": 0.7095,
"step": 426
},
{
"epoch": 0.48,
"learning_rate": 1.9137420868500034e-05,
"loss": 0.7036,
"step": 427
},
{
"epoch": 0.48,
"learning_rate": 1.913250113096506e-05,
"loss": 0.7007,
"step": 428
},
{
"epoch": 0.48,
"learning_rate": 1.912756803943741e-05,
"loss": 0.7202,
"step": 429
},
{
"epoch": 0.48,
"learning_rate": 1.912262160113049e-05,
"loss": 0.709,
"step": 430
},
{
"epoch": 0.48,
"learning_rate": 1.9117661823277232e-05,
"loss": 0.7168,
"step": 431
},
{
"epoch": 0.48,
"learning_rate": 1.911268871313007e-05,
"loss": 0.7192,
"step": 432
},
{
"epoch": 0.48,
"learning_rate": 1.9107702277960925e-05,
"loss": 0.7139,
"step": 433
},
{
"epoch": 0.49,
"learning_rate": 1.9102702525061207e-05,
"loss": 0.7061,
"step": 434
},
{
"epoch": 0.49,
"learning_rate": 1.9097689461741805e-05,
"loss": 0.7007,
"step": 435
},
{
"epoch": 0.49,
"learning_rate": 1.909266309533306e-05,
"loss": 0.6973,
"step": 436
},
{
"epoch": 0.49,
"learning_rate": 1.9087623433184782e-05,
"loss": 0.6978,
"step": 437
},
{
"epoch": 0.49,
"learning_rate": 1.9082570482666208e-05,
"loss": 0.71,
"step": 438
},
{
"epoch": 0.49,
"learning_rate": 1.9077504251166007e-05,
"loss": 0.7036,
"step": 439
},
{
"epoch": 0.49,
"learning_rate": 1.907242474609228e-05,
"loss": 0.6895,
"step": 440
},
{
"epoch": 0.49,
"learning_rate": 1.9067331974872524e-05,
"loss": 0.7324,
"step": 441
},
{
"epoch": 0.49,
"learning_rate": 1.9062225944953643e-05,
"loss": 0.7041,
"step": 442
},
{
"epoch": 0.5,
"learning_rate": 1.905710666380192e-05,
"loss": 0.7036,
"step": 443
},
{
"epoch": 0.5,
"learning_rate": 1.9051974138903028e-05,
"loss": 0.7363,
"step": 444
},
{
"epoch": 0.5,
"learning_rate": 1.904682837776199e-05,
"loss": 0.7119,
"step": 445
},
{
"epoch": 0.5,
"learning_rate": 1.9041669387903193e-05,
"loss": 0.7192,
"step": 446
},
{
"epoch": 0.5,
"learning_rate": 1.903649717687037e-05,
"loss": 0.7065,
"step": 447
},
{
"epoch": 0.5,
"learning_rate": 1.903131175222658e-05,
"loss": 0.687,
"step": 448
},
{
"epoch": 0.5,
"learning_rate": 1.9026113121554205e-05,
"loss": 0.7378,
"step": 449
},
{
"epoch": 0.5,
"learning_rate": 1.902090129245494e-05,
"loss": 0.7178,
"step": 450
},
{
"epoch": 0.5,
"learning_rate": 1.9015676272549774e-05,
"loss": 0.7236,
"step": 451
},
{
"epoch": 0.51,
"learning_rate": 1.9010438069478993e-05,
"loss": 0.666,
"step": 452
},
{
"epoch": 0.51,
"learning_rate": 1.9005186690902157e-05,
"loss": 0.7168,
"step": 453
},
{
"epoch": 0.51,
"learning_rate": 1.8999922144498086e-05,
"loss": 0.686,
"step": 454
},
{
"epoch": 0.51,
"learning_rate": 1.899464443796486e-05,
"loss": 0.7354,
"step": 455
},
{
"epoch": 0.51,
"learning_rate": 1.89893535790198e-05,
"loss": 0.6973,
"step": 456
},
{
"epoch": 0.51,
"learning_rate": 1.8984049575399466e-05,
"loss": 0.6924,
"step": 457
},
{
"epoch": 0.51,
"learning_rate": 1.8978732434859626e-05,
"loss": 0.6777,
"step": 458
},
{
"epoch": 0.51,
"learning_rate": 1.897340216517527e-05,
"loss": 0.6865,
"step": 459
},
{
"epoch": 0.51,
"learning_rate": 1.8968058774140576e-05,
"loss": 0.7163,
"step": 460
},
{
"epoch": 0.52,
"learning_rate": 1.8962702269568916e-05,
"loss": 0.6997,
"step": 461
},
{
"epoch": 0.52,
"learning_rate": 1.8957332659292834e-05,
"loss": 0.6963,
"step": 462
},
{
"epoch": 0.52,
"learning_rate": 1.8951949951164042e-05,
"loss": 0.7261,
"step": 463
},
{
"epoch": 0.52,
"learning_rate": 1.8946554153053395e-05,
"loss": 0.7046,
"step": 464
},
{
"epoch": 0.52,
"learning_rate": 1.8941145272850902e-05,
"loss": 0.6895,
"step": 465
},
{
"epoch": 0.52,
"learning_rate": 1.8935723318465684e-05,
"loss": 0.7373,
"step": 466
},
{
"epoch": 0.52,
"learning_rate": 1.8930288297825994e-05,
"loss": 0.6968,
"step": 467
},
{
"epoch": 0.52,
"learning_rate": 1.892484021887919e-05,
"loss": 0.7085,
"step": 468
},
{
"epoch": 0.52,
"learning_rate": 1.8919379089591718e-05,
"loss": 0.7158,
"step": 469
},
{
"epoch": 0.53,
"learning_rate": 1.891390491794911e-05,
"loss": 0.6968,
"step": 470
},
{
"epoch": 0.53,
"learning_rate": 1.8908417711955973e-05,
"loss": 0.6875,
"step": 471
},
{
"epoch": 0.53,
"learning_rate": 1.8902917479635965e-05,
"loss": 0.7065,
"step": 472
},
{
"epoch": 0.53,
"learning_rate": 1.8897404229031794e-05,
"loss": 0.7002,
"step": 473
},
{
"epoch": 0.53,
"learning_rate": 1.8891877968205213e-05,
"loss": 0.6978,
"step": 474
},
{
"epoch": 0.53,
"learning_rate": 1.8886338705236996e-05,
"loss": 0.7114,
"step": 475
},
{
"epoch": 0.53,
"learning_rate": 1.888078644822691e-05,
"loss": 0.7202,
"step": 476
},
{
"epoch": 0.53,
"learning_rate": 1.8875221205293755e-05,
"loss": 0.7153,
"step": 477
},
{
"epoch": 0.53,
"learning_rate": 1.8869642984575297e-05,
"loss": 0.7261,
"step": 478
},
{
"epoch": 0.54,
"learning_rate": 1.886405179422828e-05,
"loss": 0.7202,
"step": 479
},
{
"epoch": 0.54,
"learning_rate": 1.8858447642428426e-05,
"loss": 0.707,
"step": 480
},
{
"epoch": 0.54,
"learning_rate": 1.8852830537370396e-05,
"loss": 0.6738,
"step": 481
},
{
"epoch": 0.54,
"learning_rate": 1.8847200487267803e-05,
"loss": 0.6914,
"step": 482
},
{
"epoch": 0.54,
"learning_rate": 1.8841557500353175e-05,
"loss": 0.687,
"step": 483
},
{
"epoch": 0.54,
"learning_rate": 1.8835901584877974e-05,
"loss": 0.6851,
"step": 484
},
{
"epoch": 0.54,
"learning_rate": 1.8830232749112553e-05,
"loss": 0.6855,
"step": 485
},
{
"epoch": 0.54,
"learning_rate": 1.882455100134616e-05,
"loss": 0.7246,
"step": 486
},
{
"epoch": 0.55,
"learning_rate": 1.8818856349886935e-05,
"loss": 0.7148,
"step": 487
},
{
"epoch": 0.55,
"learning_rate": 1.881314880306187e-05,
"loss": 0.6987,
"step": 488
},
{
"epoch": 0.55,
"learning_rate": 1.8807428369216822e-05,
"loss": 0.7163,
"step": 489
},
{
"epoch": 0.55,
"learning_rate": 1.8801695056716496e-05,
"loss": 0.6802,
"step": 490
},
{
"epoch": 0.55,
"learning_rate": 1.8795948873944416e-05,
"loss": 0.6855,
"step": 491
},
{
"epoch": 0.55,
"learning_rate": 1.8790189829302943e-05,
"loss": 0.6968,
"step": 492
},
{
"epoch": 0.55,
"learning_rate": 1.8784417931213225e-05,
"loss": 0.6733,
"step": 493
},
{
"epoch": 0.55,
"learning_rate": 1.8778633188115223e-05,
"loss": 0.728,
"step": 494
},
{
"epoch": 0.55,
"learning_rate": 1.8772835608467673e-05,
"loss": 0.6997,
"step": 495
},
{
"epoch": 0.56,
"learning_rate": 1.8767025200748076e-05,
"loss": 0.6973,
"step": 496
},
{
"epoch": 0.56,
"learning_rate": 1.8761201973452698e-05,
"loss": 0.6943,
"step": 497
},
{
"epoch": 0.56,
"learning_rate": 1.875536593509655e-05,
"loss": 0.6948,
"step": 498
},
{
"epoch": 0.56,
"learning_rate": 1.8749517094213378e-05,
"loss": 0.7012,
"step": 499
},
{
"epoch": 0.56,
"learning_rate": 1.8743655459355635e-05,
"loss": 0.6929,
"step": 500
},
{
"epoch": 0.56,
"learning_rate": 1.87377810390945e-05,
"loss": 0.6973,
"step": 501
},
{
"epoch": 0.56,
"learning_rate": 1.8731893842019844e-05,
"loss": 0.6865,
"step": 502
},
{
"epoch": 0.56,
"learning_rate": 1.8725993876740206e-05,
"loss": 0.7036,
"step": 503
},
{
"epoch": 0.56,
"learning_rate": 1.872008115188281e-05,
"loss": 0.6831,
"step": 504
},
{
"epoch": 0.57,
"learning_rate": 1.871415567609353e-05,
"loss": 0.6855,
"step": 505
},
{
"epoch": 0.57,
"learning_rate": 1.8708217458036896e-05,
"loss": 0.7021,
"step": 506
},
{
"epoch": 0.57,
"learning_rate": 1.8702266506396055e-05,
"loss": 0.6997,
"step": 507
},
{
"epoch": 0.57,
"learning_rate": 1.8696302829872786e-05,
"loss": 0.7202,
"step": 508
},
{
"epoch": 0.57,
"learning_rate": 1.869032643718747e-05,
"loss": 0.6875,
"step": 509
},
{
"epoch": 0.57,
"learning_rate": 1.868433733707908e-05,
"loss": 0.7349,
"step": 510
},
{
"epoch": 0.57,
"learning_rate": 1.8678335538305175e-05,
"loss": 0.7339,
"step": 511
},
{
"epoch": 0.57,
"learning_rate": 1.867232104964188e-05,
"loss": 0.7144,
"step": 512
},
{
"epoch": 0.57,
"learning_rate": 1.8666293879883875e-05,
"loss": 0.6816,
"step": 513
},
{
"epoch": 0.58,
"learning_rate": 1.866025403784439e-05,
"loss": 0.7051,
"step": 514
},
{
"epoch": 0.58,
"learning_rate": 1.865420153235517e-05,
"loss": 0.6753,
"step": 515
},
{
"epoch": 0.58,
"learning_rate": 1.864813637226649e-05,
"loss": 0.7007,
"step": 516
},
{
"epoch": 0.58,
"learning_rate": 1.8642058566447135e-05,
"loss": 0.6958,
"step": 517
},
{
"epoch": 0.58,
"learning_rate": 1.863596812378436e-05,
"loss": 0.7036,
"step": 518
},
{
"epoch": 0.58,
"learning_rate": 1.862986505318391e-05,
"loss": 0.7012,
"step": 519
},
{
"epoch": 0.58,
"learning_rate": 1.8623749363570004e-05,
"loss": 0.7119,
"step": 520
},
{
"epoch": 0.58,
"learning_rate": 1.86176210638853e-05,
"loss": 0.6919,
"step": 521
},
{
"epoch": 0.58,
"learning_rate": 1.8611480163090897e-05,
"loss": 0.6777,
"step": 522
},
{
"epoch": 0.59,
"learning_rate": 1.8605326670166322e-05,
"loss": 0.7183,
"step": 523
},
{
"epoch": 0.59,
"learning_rate": 1.8599160594109523e-05,
"loss": 0.6909,
"step": 524
},
{
"epoch": 0.59,
"learning_rate": 1.859298194393683e-05,
"loss": 0.6968,
"step": 525
},
{
"epoch": 0.59,
"learning_rate": 1.858679072868298e-05,
"loss": 0.7061,
"step": 526
},
{
"epoch": 0.59,
"learning_rate": 1.858058695740106e-05,
"loss": 0.7139,
"step": 527
},
{
"epoch": 0.59,
"learning_rate": 1.857437063916254e-05,
"loss": 0.686,
"step": 528
},
{
"epoch": 0.59,
"learning_rate": 1.856814178305722e-05,
"loss": 0.6978,
"step": 529
},
{
"epoch": 0.59,
"learning_rate": 1.8561900398193247e-05,
"loss": 0.709,
"step": 530
},
{
"epoch": 0.59,
"learning_rate": 1.8555646493697075e-05,
"loss": 0.7148,
"step": 531
},
{
"epoch": 0.6,
"learning_rate": 1.854938007871347e-05,
"loss": 0.7095,
"step": 532
},
{
"epoch": 0.6,
"learning_rate": 1.85431011624055e-05,
"loss": 0.6963,
"step": 533
},
{
"epoch": 0.6,
"learning_rate": 1.8536809753954502e-05,
"loss": 0.7085,
"step": 534
},
{
"epoch": 0.6,
"learning_rate": 1.853050586256008e-05,
"loss": 0.7207,
"step": 535
},
{
"epoch": 0.6,
"learning_rate": 1.8524189497440096e-05,
"loss": 0.6792,
"step": 536
},
{
"epoch": 0.6,
"learning_rate": 1.851786066783065e-05,
"loss": 0.6831,
"step": 537
},
{
"epoch": 0.6,
"learning_rate": 1.8511519382986068e-05,
"loss": 0.7021,
"step": 538
},
{
"epoch": 0.6,
"learning_rate": 1.8505165652178894e-05,
"loss": 0.689,
"step": 539
},
{
"epoch": 0.6,
"learning_rate": 1.8498799484699856e-05,
"loss": 0.7056,
"step": 540
},
{
"epoch": 0.61,
"learning_rate": 1.8492420889857883e-05,
"loss": 0.6929,
"step": 541
},
{
"epoch": 0.61,
"learning_rate": 1.8486029876980073e-05,
"loss": 0.6895,
"step": 542
},
{
"epoch": 0.61,
"learning_rate": 1.847962645541168e-05,
"loss": 0.7202,
"step": 543
},
{
"epoch": 0.61,
"learning_rate": 1.847321063451609e-05,
"loss": 0.6943,
"step": 544
},
{
"epoch": 0.61,
"learning_rate": 1.8466782423674847e-05,
"loss": 0.666,
"step": 545
},
{
"epoch": 0.61,
"learning_rate": 1.846034183228759e-05,
"loss": 0.6807,
"step": 546
},
{
"epoch": 0.61,
"learning_rate": 1.845388886977207e-05,
"loss": 0.6992,
"step": 547
},
{
"epoch": 0.61,
"learning_rate": 1.8447423545564125e-05,
"loss": 0.7188,
"step": 548
},
{
"epoch": 0.61,
"learning_rate": 1.8440945869117676e-05,
"loss": 0.7227,
"step": 549
},
{
"epoch": 0.62,
"learning_rate": 1.8434455849904692e-05,
"loss": 0.6846,
"step": 550
},
{
"epoch": 0.62,
"learning_rate": 1.8427953497415204e-05,
"loss": 0.6812,
"step": 551
},
{
"epoch": 0.62,
"learning_rate": 1.842143882115727e-05,
"loss": 0.6997,
"step": 552
},
{
"epoch": 0.62,
"learning_rate": 1.8414911830656974e-05,
"loss": 0.6753,
"step": 553
},
{
"epoch": 0.62,
"learning_rate": 1.8408372535458398e-05,
"loss": 0.7134,
"step": 554
},
{
"epoch": 0.62,
"learning_rate": 1.840182094512362e-05,
"loss": 0.7397,
"step": 555
},
{
"epoch": 0.62,
"learning_rate": 1.8395257069232704e-05,
"loss": 0.7061,
"step": 556
},
{
"epoch": 0.62,
"learning_rate": 1.8388680917383666e-05,
"loss": 0.7134,
"step": 557
},
{
"epoch": 0.62,
"learning_rate": 1.8382092499192484e-05,
"loss": 0.7007,
"step": 558
},
{
"epoch": 0.63,
"learning_rate": 1.837549182429307e-05,
"loss": 0.6875,
"step": 559
},
{
"epoch": 0.63,
"learning_rate": 1.8368878902337246e-05,
"loss": 0.668,
"step": 560
},
{
"epoch": 0.63,
"learning_rate": 1.8362253742994757e-05,
"loss": 0.6841,
"step": 561
},
{
"epoch": 0.63,
"learning_rate": 1.8355616355953238e-05,
"loss": 0.7192,
"step": 562
},
{
"epoch": 0.63,
"learning_rate": 1.8348966750918205e-05,
"loss": 0.7085,
"step": 563
},
{
"epoch": 0.63,
"learning_rate": 1.8342304937613034e-05,
"loss": 0.6934,
"step": 564
},
{
"epoch": 0.63,
"learning_rate": 1.8335630925778954e-05,
"loss": 0.6714,
"step": 565
},
{
"epoch": 0.63,
"learning_rate": 1.832894472517504e-05,
"loss": 0.7207,
"step": 566
},
{
"epoch": 0.63,
"learning_rate": 1.8322246345578182e-05,
"loss": 0.6909,
"step": 567
},
{
"epoch": 0.64,
"learning_rate": 1.831553579678308e-05,
"loss": 0.7061,
"step": 568
},
{
"epoch": 0.64,
"learning_rate": 1.8308813088602227e-05,
"loss": 0.6855,
"step": 569
},
{
"epoch": 0.64,
"learning_rate": 1.8302078230865893e-05,
"loss": 0.707,
"step": 570
},
{
"epoch": 0.64,
"learning_rate": 1.829533123342213e-05,
"loss": 0.7295,
"step": 571
},
{
"epoch": 0.64,
"learning_rate": 1.8288572106136725e-05,
"loss": 0.6846,
"step": 572
},
{
"epoch": 0.64,
"learning_rate": 1.8281800858893203e-05,
"loss": 0.6885,
"step": 573
},
{
"epoch": 0.64,
"learning_rate": 1.8275017501592817e-05,
"loss": 0.6963,
"step": 574
},
{
"epoch": 0.64,
"learning_rate": 1.8268222044154526e-05,
"loss": 0.6968,
"step": 575
},
{
"epoch": 0.64,
"learning_rate": 1.8261414496514985e-05,
"loss": 0.6533,
"step": 576
},
{
"epoch": 0.65,
"learning_rate": 1.8254594868628523e-05,
"loss": 0.7129,
"step": 577
},
{
"epoch": 0.65,
"learning_rate": 1.8247763170467133e-05,
"loss": 0.6978,
"step": 578
},
{
"epoch": 0.65,
"learning_rate": 1.8240919412020467e-05,
"loss": 0.7017,
"step": 579
},
{
"epoch": 0.65,
"learning_rate": 1.82340636032958e-05,
"loss": 0.6685,
"step": 580
},
{
"epoch": 0.65,
"learning_rate": 1.822719575431803e-05,
"loss": 0.6929,
"step": 581
},
{
"epoch": 0.65,
"learning_rate": 1.8220315875129674e-05,
"loss": 0.6948,
"step": 582
},
{
"epoch": 0.65,
"learning_rate": 1.8213423975790822e-05,
"loss": 0.7056,
"step": 583
},
{
"epoch": 0.65,
"learning_rate": 1.820652006637915e-05,
"loss": 0.7188,
"step": 584
},
{
"epoch": 0.65,
"learning_rate": 1.8199604156989895e-05,
"loss": 0.7065,
"step": 585
},
{
"epoch": 0.66,
"learning_rate": 1.8192676257735843e-05,
"loss": 0.6924,
"step": 586
},
{
"epoch": 0.66,
"learning_rate": 1.8185736378747302e-05,
"loss": 0.709,
"step": 587
},
{
"epoch": 0.66,
"learning_rate": 1.817878453017211e-05,
"loss": 0.6792,
"step": 588
},
{
"epoch": 0.66,
"learning_rate": 1.8171820722175604e-05,
"loss": 0.6777,
"step": 589
},
{
"epoch": 0.66,
"learning_rate": 1.81648449649406e-05,
"loss": 0.6875,
"step": 590
},
{
"epoch": 0.66,
"learning_rate": 1.81578572686674e-05,
"loss": 0.7227,
"step": 591
},
{
"epoch": 0.66,
"learning_rate": 1.815085764357375e-05,
"loss": 0.6763,
"step": 592
},
{
"epoch": 0.66,
"learning_rate": 1.8143846099894858e-05,
"loss": 0.6626,
"step": 593
},
{
"epoch": 0.66,
"learning_rate": 1.813682264788334e-05,
"loss": 0.6807,
"step": 594
},
{
"epoch": 0.67,
"learning_rate": 1.8129787297809234e-05,
"loss": 0.6963,
"step": 595
},
{
"epoch": 0.67,
"learning_rate": 1.8122740059959976e-05,
"loss": 0.6865,
"step": 596
},
{
"epoch": 0.67,
"learning_rate": 1.8115680944640384e-05,
"loss": 0.6729,
"step": 597
},
{
"epoch": 0.67,
"learning_rate": 1.8108609962172642e-05,
"loss": 0.6953,
"step": 598
},
{
"epoch": 0.67,
"learning_rate": 1.8101527122896295e-05,
"loss": 0.6782,
"step": 599
},
{
"epoch": 0.67,
"learning_rate": 1.809443243716821e-05,
"loss": 0.6924,
"step": 600
},
{
"epoch": 0.67,
"learning_rate": 1.8087325915362594e-05,
"loss": 0.6777,
"step": 601
},
{
"epoch": 0.67,
"learning_rate": 1.8080207567870948e-05,
"loss": 0.7104,
"step": 602
},
{
"epoch": 0.67,
"learning_rate": 1.8073077405102074e-05,
"loss": 0.7065,
"step": 603
},
{
"epoch": 0.68,
"learning_rate": 1.806593543748204e-05,
"loss": 0.6714,
"step": 604
},
{
"epoch": 0.68,
"learning_rate": 1.8058781675454188e-05,
"loss": 0.6875,
"step": 605
},
{
"epoch": 0.68,
"learning_rate": 1.8051616129479102e-05,
"loss": 0.6987,
"step": 606
},
{
"epoch": 0.68,
"learning_rate": 1.8044438810034592e-05,
"loss": 0.6885,
"step": 607
},
{
"epoch": 0.68,
"learning_rate": 1.8037249727615693e-05,
"loss": 0.6733,
"step": 608
},
{
"epoch": 0.68,
"learning_rate": 1.803004889273463e-05,
"loss": 0.6685,
"step": 609
},
{
"epoch": 0.68,
"learning_rate": 1.802283631592082e-05,
"loss": 0.6875,
"step": 610
},
{
"epoch": 0.68,
"learning_rate": 1.8015612007720848e-05,
"loss": 0.6562,
"step": 611
},
{
"epoch": 0.68,
"learning_rate": 1.8008375978698452e-05,
"loss": 0.6772,
"step": 612
},
{
"epoch": 0.69,
"learning_rate": 1.8001128239434513e-05,
"loss": 0.6997,
"step": 613
},
{
"epoch": 0.69,
"learning_rate": 1.799386880052703e-05,
"loss": 0.7104,
"step": 614
},
{
"epoch": 0.69,
"learning_rate": 1.7986597672591113e-05,
"loss": 0.7109,
"step": 615
},
{
"epoch": 0.69,
"learning_rate": 1.797931486625896e-05,
"loss": 0.6685,
"step": 616
},
{
"epoch": 0.69,
"learning_rate": 1.797202039217985e-05,
"loss": 0.6821,
"step": 617
},
{
"epoch": 0.69,
"learning_rate": 1.7964714261020127e-05,
"loss": 0.6997,
"step": 618
},
{
"epoch": 0.69,
"learning_rate": 1.795739648346317e-05,
"loss": 0.6611,
"step": 619
},
{
"epoch": 0.69,
"learning_rate": 1.795006707020939e-05,
"loss": 0.6665,
"step": 620
},
{
"epoch": 0.7,
"learning_rate": 1.794272603197623e-05,
"loss": 0.6816,
"step": 621
},
{
"epoch": 0.7,
"learning_rate": 1.7935373379498103e-05,
"loss": 0.6846,
"step": 622
},
{
"epoch": 0.7,
"learning_rate": 1.7928009123526426e-05,
"loss": 0.7173,
"step": 623
},
{
"epoch": 0.7,
"learning_rate": 1.7920633274829577e-05,
"loss": 0.7007,
"step": 624
},
{
"epoch": 0.7,
"learning_rate": 1.7913245844192876e-05,
"loss": 0.6978,
"step": 625
},
{
"epoch": 0.7,
"learning_rate": 1.7905846842418603e-05,
"loss": 0.6616,
"step": 626
},
{
"epoch": 0.7,
"learning_rate": 1.789843628032593e-05,
"loss": 0.6963,
"step": 627
},
{
"epoch": 0.7,
"learning_rate": 1.7891014168750956e-05,
"loss": 0.6719,
"step": 628
},
{
"epoch": 0.7,
"learning_rate": 1.788358051854665e-05,
"loss": 0.6914,
"step": 629
},
{
"epoch": 0.71,
"learning_rate": 1.787613534058286e-05,
"loss": 0.6831,
"step": 630
},
{
"epoch": 0.71,
"learning_rate": 1.7868678645746298e-05,
"loss": 0.7207,
"step": 631
},
{
"epoch": 0.71,
"learning_rate": 1.7861210444940503e-05,
"loss": 0.6782,
"step": 632
},
{
"epoch": 0.71,
"learning_rate": 1.7853730749085856e-05,
"loss": 0.7109,
"step": 633
},
{
"epoch": 0.71,
"learning_rate": 1.784623956911953e-05,
"loss": 0.7095,
"step": 634
},
{
"epoch": 0.71,
"learning_rate": 1.7838736915995494e-05,
"loss": 0.6797,
"step": 635
},
{
"epoch": 0.71,
"learning_rate": 1.7831222800684504e-05,
"loss": 0.6655,
"step": 636
},
{
"epoch": 0.71,
"learning_rate": 1.782369723417406e-05,
"loss": 0.6616,
"step": 637
},
{
"epoch": 0.71,
"learning_rate": 1.781616022746843e-05,
"loss": 0.7021,
"step": 638
},
{
"epoch": 0.72,
"learning_rate": 1.7808611791588584e-05,
"loss": 0.6777,
"step": 639
},
{
"epoch": 0.72,
"learning_rate": 1.780105193757222e-05,
"loss": 0.6943,
"step": 640
},
{
"epoch": 0.72,
"learning_rate": 1.7793480676473726e-05,
"loss": 0.6719,
"step": 641
},
{
"epoch": 0.72,
"learning_rate": 1.7785898019364176e-05,
"loss": 0.6689,
"step": 642
},
{
"epoch": 0.72,
"learning_rate": 1.7778303977331308e-05,
"loss": 0.6821,
"step": 643
},
{
"epoch": 0.72,
"learning_rate": 1.7770698561479496e-05,
"loss": 0.6753,
"step": 644
},
{
"epoch": 0.72,
"learning_rate": 1.776308178292976e-05,
"loss": 0.6997,
"step": 645
},
{
"epoch": 0.72,
"learning_rate": 1.7755453652819722e-05,
"loss": 0.6582,
"step": 646
},
{
"epoch": 0.72,
"learning_rate": 1.7747814182303616e-05,
"loss": 0.6802,
"step": 647
},
{
"epoch": 0.73,
"learning_rate": 1.7740163382552248e-05,
"loss": 0.6797,
"step": 648
},
{
"epoch": 0.73,
"learning_rate": 1.7732501264752998e-05,
"loss": 0.6602,
"step": 649
},
{
"epoch": 0.73,
"learning_rate": 1.7724827840109785e-05,
"loss": 0.6504,
"step": 650
},
{
"epoch": 0.73,
"learning_rate": 1.7717143119843078e-05,
"loss": 0.6582,
"step": 651
},
{
"epoch": 0.73,
"learning_rate": 1.770944711518984e-05,
"loss": 0.6675,
"step": 652
},
{
"epoch": 0.73,
"learning_rate": 1.770173983740356e-05,
"loss": 0.6821,
"step": 653
},
{
"epoch": 0.73,
"learning_rate": 1.769402129775419e-05,
"loss": 0.6978,
"step": 654
},
{
"epoch": 0.73,
"learning_rate": 1.7686291507528165e-05,
"loss": 0.6807,
"step": 655
},
{
"epoch": 0.73,
"learning_rate": 1.767855047802836e-05,
"loss": 0.6729,
"step": 656
},
{
"epoch": 0.74,
"learning_rate": 1.7670798220574093e-05,
"loss": 0.6475,
"step": 657
},
{
"epoch": 0.74,
"learning_rate": 1.7663034746501097e-05,
"loss": 0.6509,
"step": 658
},
{
"epoch": 0.74,
"learning_rate": 1.7655260067161504e-05,
"loss": 0.6694,
"step": 659
},
{
"epoch": 0.74,
"learning_rate": 1.764747419392383e-05,
"loss": 0.6538,
"step": 660
},
{
"epoch": 0.74,
"learning_rate": 1.7639677138172965e-05,
"loss": 0.6694,
"step": 661
},
{
"epoch": 0.74,
"learning_rate": 1.763186891131015e-05,
"loss": 0.6797,
"step": 662
},
{
"epoch": 0.74,
"learning_rate": 1.7624049524752954e-05,
"loss": 0.6904,
"step": 663
},
{
"epoch": 0.74,
"learning_rate": 1.7616218989935274e-05,
"loss": 0.7031,
"step": 664
},
{
"epoch": 0.74,
"learning_rate": 1.76083773183073e-05,
"loss": 0.709,
"step": 665
},
{
"epoch": 0.75,
"learning_rate": 1.7600524521335512e-05,
"loss": 0.6821,
"step": 666
},
{
"epoch": 0.75,
"learning_rate": 1.759266061050265e-05,
"loss": 0.7026,
"step": 667
},
{
"epoch": 0.75,
"learning_rate": 1.758478559730772e-05,
"loss": 0.6841,
"step": 668
},
{
"epoch": 0.75,
"learning_rate": 1.7576899493265952e-05,
"loss": 0.6943,
"step": 669
},
{
"epoch": 0.75,
"learning_rate": 1.7569002309908792e-05,
"loss": 0.6953,
"step": 670
},
{
"epoch": 0.75,
"learning_rate": 1.7561094058783894e-05,
"loss": 0.6543,
"step": 671
},
{
"epoch": 0.75,
"learning_rate": 1.755317475145509e-05,
"loss": 0.7012,
"step": 672
},
{
"epoch": 0.75,
"learning_rate": 1.754524439950238e-05,
"loss": 0.6763,
"step": 673
},
{
"epoch": 0.75,
"learning_rate": 1.753730301452192e-05,
"loss": 0.6904,
"step": 674
},
{
"epoch": 0.76,
"learning_rate": 1.7529350608125985e-05,
"loss": 0.6538,
"step": 675
},
{
"epoch": 0.76,
"learning_rate": 1.752138719194298e-05,
"loss": 0.6616,
"step": 676
},
{
"epoch": 0.76,
"learning_rate": 1.7513412777617408e-05,
"loss": 0.688,
"step": 677
},
{
"epoch": 0.76,
"learning_rate": 1.7505427376809848e-05,
"loss": 0.6494,
"step": 678
},
{
"epoch": 0.76,
"learning_rate": 1.7497431001196943e-05,
"loss": 0.6982,
"step": 679
},
{
"epoch": 0.76,
"learning_rate": 1.748942366247139e-05,
"loss": 0.6909,
"step": 680
},
{
"epoch": 0.76,
"learning_rate": 1.748140537234191e-05,
"loss": 0.6973,
"step": 681
},
{
"epoch": 0.76,
"learning_rate": 1.7473376142533248e-05,
"loss": 0.6938,
"step": 682
},
{
"epoch": 0.76,
"learning_rate": 1.7465335984786128e-05,
"loss": 0.6787,
"step": 683
},
{
"epoch": 0.77,
"learning_rate": 1.745728491085728e-05,
"loss": 0.7271,
"step": 684
},
{
"epoch": 0.77,
"learning_rate": 1.7449222932519364e-05,
"loss": 0.6836,
"step": 685
},
{
"epoch": 0.77,
"learning_rate": 1.7441150061561018e-05,
"loss": 0.7017,
"step": 686
},
{
"epoch": 0.77,
"learning_rate": 1.743306630978678e-05,
"loss": 0.6855,
"step": 687
},
{
"epoch": 0.77,
"learning_rate": 1.742497168901711e-05,
"loss": 0.6895,
"step": 688
},
{
"epoch": 0.77,
"learning_rate": 1.7416866211088365e-05,
"loss": 0.6675,
"step": 689
},
{
"epoch": 0.77,
"learning_rate": 1.740874988785277e-05,
"loss": 0.6782,
"step": 690
},
{
"epoch": 0.77,
"learning_rate": 1.740062273117842e-05,
"loss": 0.6714,
"step": 691
},
{
"epoch": 0.77,
"learning_rate": 1.7392484752949236e-05,
"loss": 0.6509,
"step": 692
},
{
"epoch": 0.78,
"learning_rate": 1.7384335965064974e-05,
"loss": 0.6797,
"step": 693
},
{
"epoch": 0.78,
"learning_rate": 1.737617637944119e-05,
"loss": 0.6938,
"step": 694
},
{
"epoch": 0.78,
"learning_rate": 1.7368006008009235e-05,
"loss": 0.6758,
"step": 695
},
{
"epoch": 0.78,
"learning_rate": 1.735982486271622e-05,
"loss": 0.6602,
"step": 696
},
{
"epoch": 0.78,
"learning_rate": 1.7351632955525033e-05,
"loss": 0.6685,
"step": 697
},
{
"epoch": 0.78,
"learning_rate": 1.734343029841427e-05,
"loss": 0.6899,
"step": 698
},
{
"epoch": 0.78,
"learning_rate": 1.733521690337827e-05,
"loss": 0.6626,
"step": 699
},
{
"epoch": 0.78,
"learning_rate": 1.7326992782427058e-05,
"loss": 0.6758,
"step": 700
},
{
"epoch": 0.78,
"learning_rate": 1.7318757947586346e-05,
"loss": 0.6865,
"step": 701
},
{
"epoch": 0.79,
"learning_rate": 1.731051241089752e-05,
"loss": 0.6748,
"step": 702
},
{
"epoch": 0.79,
"learning_rate": 1.730225618441761e-05,
"loss": 0.6909,
"step": 703
},
{
"epoch": 0.79,
"learning_rate": 1.7293989280219276e-05,
"loss": 0.6865,
"step": 704
},
{
"epoch": 0.79,
"learning_rate": 1.7285711710390788e-05,
"loss": 0.666,
"step": 705
},
{
"epoch": 0.79,
"learning_rate": 1.7277423487036018e-05,
"loss": 0.6562,
"step": 706
},
{
"epoch": 0.79,
"learning_rate": 1.7269124622274418e-05,
"loss": 0.6987,
"step": 707
},
{
"epoch": 0.79,
"learning_rate": 1.726081512824099e-05,
"loss": 0.6611,
"step": 708
},
{
"epoch": 0.79,
"learning_rate": 1.72524950170863e-05,
"loss": 0.6514,
"step": 709
},
{
"epoch": 0.79,
"learning_rate": 1.72441643009764e-05,
"loss": 0.6821,
"step": 710
},
{
"epoch": 0.8,
"learning_rate": 1.723582299209289e-05,
"loss": 0.686,
"step": 711
},
{
"epoch": 0.8,
"learning_rate": 1.722747110263284e-05,
"loss": 0.6587,
"step": 712
},
{
"epoch": 0.8,
"learning_rate": 1.7219108644808792e-05,
"loss": 0.6631,
"step": 713
},
{
"epoch": 0.8,
"learning_rate": 1.7210735630848747e-05,
"loss": 0.6606,
"step": 714
},
{
"epoch": 0.8,
"learning_rate": 1.7202352072996132e-05,
"loss": 0.6724,
"step": 715
},
{
"epoch": 0.8,
"learning_rate": 1.71939579835098e-05,
"loss": 0.6719,
"step": 716
},
{
"epoch": 0.8,
"learning_rate": 1.7185553374664006e-05,
"loss": 0.6606,
"step": 717
},
{
"epoch": 0.8,
"learning_rate": 1.7177138258748375e-05,
"loss": 0.6772,
"step": 718
},
{
"epoch": 0.8,
"learning_rate": 1.716871264806791e-05,
"loss": 0.6401,
"step": 719
},
{
"epoch": 0.81,
"learning_rate": 1.7160276554942953e-05,
"loss": 0.7275,
"step": 720
},
{
"epoch": 0.81,
"learning_rate": 1.7151829991709177e-05,
"loss": 0.6646,
"step": 721
},
{
"epoch": 0.81,
"learning_rate": 1.7143372970717555e-05,
"loss": 0.6709,
"step": 722
},
{
"epoch": 0.81,
"learning_rate": 1.7134905504334365e-05,
"loss": 0.6572,
"step": 723
},
{
"epoch": 0.81,
"learning_rate": 1.712642760494115e-05,
"loss": 0.6743,
"step": 724
},
{
"epoch": 0.81,
"learning_rate": 1.711793928493471e-05,
"loss": 0.6494,
"step": 725
},
{
"epoch": 0.81,
"learning_rate": 1.7109440556727094e-05,
"loss": 0.6841,
"step": 726
},
{
"epoch": 0.81,
"learning_rate": 1.7100931432745554e-05,
"loss": 0.6372,
"step": 727
},
{
"epoch": 0.81,
"learning_rate": 1.7092411925432548e-05,
"loss": 0.6982,
"step": 728
},
{
"epoch": 0.82,
"learning_rate": 1.708388204724572e-05,
"loss": 0.687,
"step": 729
},
{
"epoch": 0.82,
"learning_rate": 1.707534181065788e-05,
"loss": 0.6685,
"step": 730
},
{
"epoch": 0.82,
"learning_rate": 1.7066791228156984e-05,
"loss": 0.6494,
"step": 731
},
{
"epoch": 0.82,
"learning_rate": 1.705823031224611e-05,
"loss": 0.6582,
"step": 732
},
{
"epoch": 0.82,
"learning_rate": 1.704965907544345e-05,
"loss": 0.6802,
"step": 733
},
{
"epoch": 0.82,
"learning_rate": 1.7041077530282296e-05,
"loss": 0.7012,
"step": 734
},
{
"epoch": 0.82,
"learning_rate": 1.7032485689310997e-05,
"loss": 0.667,
"step": 735
},
{
"epoch": 0.82,
"learning_rate": 1.702388356509297e-05,
"loss": 0.6909,
"step": 736
},
{
"epoch": 0.82,
"learning_rate": 1.7015271170206666e-05,
"loss": 0.6646,
"step": 737
},
{
"epoch": 0.83,
"learning_rate": 1.7006648517245547e-05,
"loss": 0.6504,
"step": 738
},
{
"epoch": 0.83,
"learning_rate": 1.6998015618818087e-05,
"loss": 0.6655,
"step": 739
},
{
"epoch": 0.83,
"learning_rate": 1.6989372487547733e-05,
"loss": 0.6763,
"step": 740
},
{
"epoch": 0.83,
"learning_rate": 1.6980719136072892e-05,
"loss": 0.6914,
"step": 741
},
{
"epoch": 0.83,
"learning_rate": 1.6972055577046928e-05,
"loss": 0.6831,
"step": 742
},
{
"epoch": 0.83,
"learning_rate": 1.696338182313812e-05,
"loss": 0.6709,
"step": 743
},
{
"epoch": 0.83,
"learning_rate": 1.6954697887029657e-05,
"loss": 0.6592,
"step": 744
},
{
"epoch": 0.83,
"learning_rate": 1.694600378141962e-05,
"loss": 0.666,
"step": 745
},
{
"epoch": 0.83,
"learning_rate": 1.6937299519020955e-05,
"loss": 0.665,
"step": 746
},
{
"epoch": 0.84,
"learning_rate": 1.6928585112561468e-05,
"loss": 0.6587,
"step": 747
},
{
"epoch": 0.84,
"learning_rate": 1.6919860574783786e-05,
"loss": 0.6821,
"step": 748
},
{
"epoch": 0.84,
"learning_rate": 1.6911125918445363e-05,
"loss": 0.6455,
"step": 749
},
{
"epoch": 0.84,
"learning_rate": 1.690238115631844e-05,
"loss": 0.6626,
"step": 750
},
{
"epoch": 0.84,
"learning_rate": 1.6893626301190044e-05,
"loss": 0.6709,
"step": 751
},
{
"epoch": 0.84,
"learning_rate": 1.688486136586195e-05,
"loss": 0.6812,
"step": 752
},
{
"epoch": 0.84,
"learning_rate": 1.687608636315068e-05,
"loss": 0.6421,
"step": 753
},
{
"epoch": 0.84,
"learning_rate": 1.6867301305887476e-05,
"loss": 0.6797,
"step": 754
},
{
"epoch": 0.84,
"learning_rate": 1.6858506206918278e-05,
"loss": 0.6694,
"step": 755
},
{
"epoch": 0.85,
"learning_rate": 1.6849701079103714e-05,
"loss": 0.6465,
"step": 756
},
{
"epoch": 0.85,
"learning_rate": 1.684088593531908e-05,
"loss": 0.6621,
"step": 757
},
{
"epoch": 0.85,
"learning_rate": 1.68320607884543e-05,
"loss": 0.6909,
"step": 758
},
{
"epoch": 0.85,
"learning_rate": 1.682322565141395e-05,
"loss": 0.6587,
"step": 759
},
{
"epoch": 0.85,
"learning_rate": 1.68143805371172e-05,
"loss": 0.6714,
"step": 760
},
{
"epoch": 0.85,
"learning_rate": 1.6805525458497815e-05,
"loss": 0.6621,
"step": 761
},
{
"epoch": 0.85,
"learning_rate": 1.6796660428504114e-05,
"loss": 0.6816,
"step": 762
},
{
"epoch": 0.85,
"learning_rate": 1.6787785460098994e-05,
"loss": 0.6655,
"step": 763
},
{
"epoch": 0.86,
"learning_rate": 1.6778900566259865e-05,
"loss": 0.6836,
"step": 764
},
{
"epoch": 0.86,
"learning_rate": 1.6770005759978656e-05,
"loss": 0.6631,
"step": 765
},
{
"epoch": 0.86,
"learning_rate": 1.6761101054261792e-05,
"loss": 0.6475,
"step": 766
},
{
"epoch": 0.86,
"learning_rate": 1.675218646213017e-05,
"loss": 0.6812,
"step": 767
},
{
"epoch": 0.86,
"learning_rate": 1.6743261996619145e-05,
"loss": 0.6504,
"step": 768
},
{
"epoch": 0.86,
"learning_rate": 1.6734327670778507e-05,
"loss": 0.6577,
"step": 769
},
{
"epoch": 0.86,
"learning_rate": 1.6725383497672478e-05,
"loss": 0.6675,
"step": 770
},
{
"epoch": 0.86,
"learning_rate": 1.671642949037966e-05,
"loss": 0.6592,
"step": 771
},
{
"epoch": 0.86,
"learning_rate": 1.6707465661993043e-05,
"loss": 0.6792,
"step": 772
},
{
"epoch": 0.87,
"learning_rate": 1.6698492025619983e-05,
"loss": 0.6523,
"step": 773
},
{
"epoch": 0.87,
"learning_rate": 1.668950859438216e-05,
"loss": 0.6641,
"step": 774
},
{
"epoch": 0.87,
"learning_rate": 1.668051538141561e-05,
"loss": 0.645,
"step": 775
},
{
"epoch": 0.87,
"learning_rate": 1.667151239987063e-05,
"loss": 0.6733,
"step": 776
},
{
"epoch": 0.87,
"learning_rate": 1.6662499662911843e-05,
"loss": 0.6392,
"step": 777
},
{
"epoch": 0.87,
"learning_rate": 1.66534771837181e-05,
"loss": 0.6768,
"step": 778
},
{
"epoch": 0.87,
"learning_rate": 1.6644444975482522e-05,
"loss": 0.6582,
"step": 779
},
{
"epoch": 0.87,
"learning_rate": 1.6635403051412452e-05,
"loss": 0.6587,
"step": 780
},
{
"epoch": 0.87,
"learning_rate": 1.6626351424729425e-05,
"loss": 0.6504,
"step": 781
},
{
"epoch": 0.88,
"learning_rate": 1.6617290108669188e-05,
"loss": 0.6577,
"step": 782
},
{
"epoch": 0.88,
"learning_rate": 1.6608219116481633e-05,
"loss": 0.6514,
"step": 783
},
{
"epoch": 0.88,
"learning_rate": 1.6599138461430816e-05,
"loss": 0.6763,
"step": 784
},
{
"epoch": 0.88,
"learning_rate": 1.659004815679492e-05,
"loss": 0.6675,
"step": 785
},
{
"epoch": 0.88,
"learning_rate": 1.6580948215866232e-05,
"loss": 0.6514,
"step": 786
},
{
"epoch": 0.88,
"learning_rate": 1.6571838651951132e-05,
"loss": 0.6743,
"step": 787
},
{
"epoch": 0.88,
"learning_rate": 1.6562719478370075e-05,
"loss": 0.6787,
"step": 788
},
{
"epoch": 0.88,
"learning_rate": 1.655359070845757e-05,
"loss": 0.6406,
"step": 789
},
{
"epoch": 0.88,
"learning_rate": 1.6544452355562147e-05,
"loss": 0.6582,
"step": 790
},
{
"epoch": 0.89,
"learning_rate": 1.653530443304636e-05,
"loss": 0.6484,
"step": 791
},
{
"epoch": 0.89,
"learning_rate": 1.652614695428675e-05,
"loss": 0.6592,
"step": 792
},
{
"epoch": 0.89,
"learning_rate": 1.651697993267383e-05,
"loss": 0.667,
"step": 793
},
{
"epoch": 0.89,
"learning_rate": 1.6507803381612076e-05,
"loss": 0.6743,
"step": 794
},
{
"epoch": 0.89,
"learning_rate": 1.6498617314519886e-05,
"loss": 0.6606,
"step": 795
},
{
"epoch": 0.89,
"learning_rate": 1.648942174482959e-05,
"loss": 0.6567,
"step": 796
},
{
"epoch": 0.89,
"learning_rate": 1.648021668598739e-05,
"loss": 0.6909,
"step": 797
},
{
"epoch": 0.89,
"learning_rate": 1.647100215145338e-05,
"loss": 0.667,
"step": 798
},
{
"epoch": 0.89,
"learning_rate": 1.646177815470151e-05,
"loss": 0.6685,
"step": 799
},
{
"epoch": 0.9,
"learning_rate": 1.645254470921956e-05,
"loss": 0.6357,
"step": 800
},
{
"epoch": 0.9,
"learning_rate": 1.644330182850913e-05,
"loss": 0.686,
"step": 801
},
{
"epoch": 0.9,
"learning_rate": 1.6434049526085614e-05,
"loss": 0.6855,
"step": 802
},
{
"epoch": 0.9,
"learning_rate": 1.642478781547818e-05,
"loss": 0.6699,
"step": 803
},
{
"epoch": 0.9,
"learning_rate": 1.6415516710229767e-05,
"loss": 0.6523,
"step": 804
},
{
"epoch": 0.9,
"learning_rate": 1.6406236223897033e-05,
"loss": 0.6694,
"step": 805
},
{
"epoch": 0.9,
"learning_rate": 1.639694637005036e-05,
"loss": 0.6606,
"step": 806
},
{
"epoch": 0.9,
"learning_rate": 1.6387647162273837e-05,
"loss": 0.6548,
"step": 807
},
{
"epoch": 0.9,
"learning_rate": 1.637833861416522e-05,
"loss": 0.6484,
"step": 808
},
{
"epoch": 0.91,
"learning_rate": 1.6369020739335923e-05,
"loss": 0.6714,
"step": 809
},
{
"epoch": 0.91,
"learning_rate": 1.6359693551411008e-05,
"loss": 0.6958,
"step": 810
},
{
"epoch": 0.91,
"learning_rate": 1.6350357064029142e-05,
"loss": 0.647,
"step": 811
},
{
"epoch": 0.91,
"learning_rate": 1.63410112908426e-05,
"loss": 0.6592,
"step": 812
},
{
"epoch": 0.91,
"learning_rate": 1.633165624551723e-05,
"loss": 0.6543,
"step": 813
},
{
"epoch": 0.91,
"learning_rate": 1.6322291941732444e-05,
"loss": 0.667,
"step": 814
},
{
"epoch": 0.91,
"learning_rate": 1.631291839318118e-05,
"loss": 0.6431,
"step": 815
},
{
"epoch": 0.91,
"learning_rate": 1.6303535613569908e-05,
"loss": 0.6377,
"step": 816
},
{
"epoch": 0.91,
"learning_rate": 1.629414361661859e-05,
"loss": 0.6499,
"step": 817
},
{
"epoch": 0.92,
"learning_rate": 1.628474241606066e-05,
"loss": 0.6348,
"step": 818
},
{
"epoch": 0.92,
"learning_rate": 1.627533202564303e-05,
"loss": 0.6226,
"step": 819
},
{
"epoch": 0.92,
"learning_rate": 1.626591245912602e-05,
"loss": 0.6787,
"step": 820
},
{
"epoch": 0.92,
"learning_rate": 1.6256483730283394e-05,
"loss": 0.6558,
"step": 821
},
{
"epoch": 0.92,
"learning_rate": 1.6247045852902298e-05,
"loss": 0.6626,
"step": 822
},
{
"epoch": 0.92,
"learning_rate": 1.6237598840783263e-05,
"loss": 0.6455,
"step": 823
},
{
"epoch": 0.92,
"learning_rate": 1.622814270774018e-05,
"loss": 0.6533,
"step": 824
},
{
"epoch": 0.92,
"learning_rate": 1.6218677467600264e-05,
"loss": 0.6436,
"step": 825
},
{
"epoch": 0.92,
"learning_rate": 1.6209203134204058e-05,
"loss": 0.6816,
"step": 826
},
{
"epoch": 0.93,
"learning_rate": 1.6199719721405397e-05,
"loss": 0.6719,
"step": 827
},
{
"epoch": 0.93,
"learning_rate": 1.6190227243071402e-05,
"loss": 0.6768,
"step": 828
},
{
"epoch": 0.93,
"learning_rate": 1.6180725713082436e-05,
"loss": 0.6729,
"step": 829
},
{
"epoch": 0.93,
"learning_rate": 1.61712151453321e-05,
"loss": 0.6421,
"step": 830
},
{
"epoch": 0.93,
"learning_rate": 1.6161695553727218e-05,
"loss": 0.6538,
"step": 831
},
{
"epoch": 0.93,
"learning_rate": 1.6152166952187806e-05,
"loss": 0.6689,
"step": 832
},
{
"epoch": 0.93,
"learning_rate": 1.614262935464706e-05,
"loss": 0.6309,
"step": 833
},
{
"epoch": 0.93,
"learning_rate": 1.6133082775051312e-05,
"loss": 0.6626,
"step": 834
},
{
"epoch": 0.93,
"learning_rate": 1.6123527227360048e-05,
"loss": 0.6665,
"step": 835
},
{
"epoch": 0.94,
"learning_rate": 1.6113962725545862e-05,
"loss": 0.6553,
"step": 836
},
{
"epoch": 0.94,
"learning_rate": 1.6104389283594435e-05,
"loss": 0.6304,
"step": 837
},
{
"epoch": 0.94,
"learning_rate": 1.609480691550453e-05,
"loss": 0.6484,
"step": 838
},
{
"epoch": 0.94,
"learning_rate": 1.608521563528795e-05,
"loss": 0.6353,
"step": 839
},
{
"epoch": 0.94,
"learning_rate": 1.607561545696954e-05,
"loss": 0.6812,
"step": 840
},
{
"epoch": 0.94,
"learning_rate": 1.6066006394587156e-05,
"loss": 0.6572,
"step": 841
},
{
"epoch": 0.94,
"learning_rate": 1.605638846219164e-05,
"loss": 0.6699,
"step": 842
},
{
"epoch": 0.94,
"learning_rate": 1.604676167384681e-05,
"loss": 0.6416,
"step": 843
},
{
"epoch": 0.94,
"learning_rate": 1.6037126043629424e-05,
"loss": 0.6562,
"step": 844
},
{
"epoch": 0.95,
"learning_rate": 1.6027481585629178e-05,
"loss": 0.6675,
"step": 845
},
{
"epoch": 0.95,
"learning_rate": 1.6017828313948667e-05,
"loss": 0.6514,
"step": 846
},
{
"epoch": 0.95,
"learning_rate": 1.600816624270339e-05,
"loss": 0.687,
"step": 847
},
{
"epoch": 0.95,
"learning_rate": 1.5998495386021695e-05,
"loss": 0.6538,
"step": 848
},
{
"epoch": 0.95,
"learning_rate": 1.5988815758044794e-05,
"loss": 0.6719,
"step": 849
},
{
"epoch": 0.95,
"learning_rate": 1.5979127372926704e-05,
"loss": 0.666,
"step": 850
},
{
"epoch": 0.95,
"learning_rate": 1.5969430244834266e-05,
"loss": 0.6562,
"step": 851
},
{
"epoch": 0.95,
"learning_rate": 1.59597243879471e-05,
"loss": 0.6689,
"step": 852
},
{
"epoch": 0.95,
"learning_rate": 1.5950009816457575e-05,
"loss": 0.6914,
"step": 853
},
{
"epoch": 0.96,
"learning_rate": 1.594028654457083e-05,
"loss": 0.6816,
"step": 854
},
{
"epoch": 0.96,
"learning_rate": 1.593055458650471e-05,
"loss": 0.6489,
"step": 855
},
{
"epoch": 0.96,
"learning_rate": 1.592081395648975e-05,
"loss": 0.6846,
"step": 856
},
{
"epoch": 0.96,
"learning_rate": 1.5911064668769194e-05,
"loss": 0.6646,
"step": 857
},
{
"epoch": 0.96,
"learning_rate": 1.5901306737598922e-05,
"loss": 0.6851,
"step": 858
},
{
"epoch": 0.96,
"learning_rate": 1.589154017724747e-05,
"loss": 0.6514,
"step": 859
},
{
"epoch": 0.96,
"learning_rate": 1.5881765001995967e-05,
"loss": 0.6802,
"step": 860
},
{
"epoch": 0.96,
"learning_rate": 1.5871981226138174e-05,
"loss": 0.6436,
"step": 861
},
{
"epoch": 0.96,
"learning_rate": 1.5862188863980395e-05,
"loss": 0.6479,
"step": 862
},
{
"epoch": 0.97,
"learning_rate": 1.5852387929841513e-05,
"loss": 0.6479,
"step": 863
},
{
"epoch": 0.97,
"learning_rate": 1.584257843805293e-05,
"loss": 0.6489,
"step": 864
},
{
"epoch": 0.97,
"learning_rate": 1.5832760402958573e-05,
"loss": 0.6621,
"step": 865
},
{
"epoch": 0.97,
"learning_rate": 1.5822933838914852e-05,
"loss": 0.6479,
"step": 866
},
{
"epoch": 0.97,
"learning_rate": 1.581309876029066e-05,
"loss": 0.6611,
"step": 867
},
{
"epoch": 0.97,
"learning_rate": 1.5803255181467324e-05,
"loss": 0.6729,
"step": 868
},
{
"epoch": 0.97,
"learning_rate": 1.5793403116838612e-05,
"loss": 0.627,
"step": 869
},
{
"epoch": 0.97,
"learning_rate": 1.5783542580810702e-05,
"loss": 0.6641,
"step": 870
},
{
"epoch": 0.97,
"learning_rate": 1.5773673587802153e-05,
"loss": 0.6587,
"step": 871
},
{
"epoch": 0.98,
"learning_rate": 1.5763796152243888e-05,
"loss": 0.6265,
"step": 872
},
{
"epoch": 0.98,
"learning_rate": 1.5753910288579188e-05,
"loss": 0.6646,
"step": 873
},
{
"epoch": 0.98,
"learning_rate": 1.5744016011263638e-05,
"loss": 0.6211,
"step": 874
},
{
"epoch": 0.98,
"learning_rate": 1.5734113334765152e-05,
"loss": 0.6685,
"step": 875
},
{
"epoch": 0.98,
"learning_rate": 1.5724202273563896e-05,
"loss": 0.6499,
"step": 876
},
{
"epoch": 0.98,
"learning_rate": 1.571428284215232e-05,
"loss": 0.6567,
"step": 877
},
{
"epoch": 0.98,
"learning_rate": 1.5704355055035107e-05,
"loss": 0.6763,
"step": 878
},
{
"epoch": 0.98,
"learning_rate": 1.5694418926729148e-05,
"loss": 0.665,
"step": 879
},
{
"epoch": 0.98,
"learning_rate": 1.5684474471763542e-05,
"loss": 0.6748,
"step": 880
},
{
"epoch": 0.99,
"learning_rate": 1.5674521704679565e-05,
"loss": 0.6436,
"step": 881
},
{
"epoch": 0.99,
"learning_rate": 1.566456064003064e-05,
"loss": 0.6787,
"step": 882
},
{
"epoch": 0.99,
"learning_rate": 1.5654591292382322e-05,
"loss": 0.6357,
"step": 883
},
{
"epoch": 0.99,
"learning_rate": 1.564461367631229e-05,
"loss": 0.6338,
"step": 884
},
{
"epoch": 0.99,
"learning_rate": 1.5634627806410296e-05,
"loss": 0.6538,
"step": 885
},
{
"epoch": 0.99,
"learning_rate": 1.562463369727818e-05,
"loss": 0.688,
"step": 886
},
{
"epoch": 0.99,
"learning_rate": 1.5614631363529813e-05,
"loss": 0.6646,
"step": 887
},
{
"epoch": 0.99,
"learning_rate": 1.56046208197911e-05,
"loss": 0.6543,
"step": 888
},
{
"epoch": 0.99,
"learning_rate": 1.5594602080699956e-05,
"loss": 0.6753,
"step": 889
},
{
"epoch": 1.0,
"learning_rate": 1.558457516090627e-05,
"loss": 0.6177,
"step": 890
},
{
"epoch": 1.0,
"learning_rate": 1.55745400750719e-05,
"loss": 0.6494,
"step": 891
},
{
"epoch": 1.0,
"learning_rate": 1.5564496837870645e-05,
"loss": 0.6382,
"step": 892
},
{
"epoch": 1.0,
"learning_rate": 1.5554445463988214e-05,
"loss": 0.6694,
"step": 893
},
{
"epoch": 1.0,
"learning_rate": 1.5544385968122225e-05,
"loss": 0.6201,
"step": 894
},
{
"epoch": 1.0,
"learning_rate": 1.5534318364982168e-05,
"loss": 0.5588,
"step": 895
},
{
"epoch": 1.0,
"learning_rate": 1.5524242669289383e-05,
"loss": 0.5654,
"step": 896
},
{
"epoch": 1.0,
"learning_rate": 1.5514158895777057e-05,
"loss": 0.5425,
"step": 897
},
{
"epoch": 1.01,
"learning_rate": 1.5504067059190174e-05,
"loss": 0.5542,
"step": 898
},
{
"epoch": 1.01,
"learning_rate": 1.5493967174285514e-05,
"loss": 0.5295,
"step": 899
},
{
"epoch": 1.01,
"learning_rate": 1.5483859255831628e-05,
"loss": 0.5342,
"step": 900
},
{
"epoch": 1.01,
"learning_rate": 1.547374331860881e-05,
"loss": 0.5332,
"step": 901
},
{
"epoch": 1.01,
"learning_rate": 1.5463619377409083e-05,
"loss": 0.5339,
"step": 902
},
{
"epoch": 1.01,
"learning_rate": 1.5453487447036174e-05,
"loss": 0.5347,
"step": 903
},
{
"epoch": 1.01,
"learning_rate": 1.5443347542305486e-05,
"loss": 0.5166,
"step": 904
},
{
"epoch": 1.01,
"learning_rate": 1.5433199678044088e-05,
"loss": 0.5251,
"step": 905
},
{
"epoch": 1.01,
"learning_rate": 1.5423043869090687e-05,
"loss": 0.5449,
"step": 906
},
{
"epoch": 1.02,
"learning_rate": 1.541288013029561e-05,
"loss": 0.5195,
"step": 907
},
{
"epoch": 1.02,
"learning_rate": 1.5402708476520766e-05,
"loss": 0.5442,
"step": 908
},
{
"epoch": 1.02,
"learning_rate": 1.5392528922639662e-05,
"loss": 0.5469,
"step": 909
},
{
"epoch": 1.02,
"learning_rate": 1.5382341483537336e-05,
"loss": 0.4954,
"step": 910
},
{
"epoch": 1.02,
"learning_rate": 1.5372146174110357e-05,
"loss": 0.5359,
"step": 911
},
{
"epoch": 1.02,
"learning_rate": 1.536194300926682e-05,
"loss": 0.5239,
"step": 912
},
{
"epoch": 1.02,
"learning_rate": 1.5351732003926287e-05,
"loss": 0.5518,
"step": 913
},
{
"epoch": 1.02,
"learning_rate": 1.5341513173019792e-05,
"loss": 0.5344,
"step": 914
},
{
"epoch": 1.02,
"learning_rate": 1.533128653148982e-05,
"loss": 0.5215,
"step": 915
},
{
"epoch": 1.03,
"learning_rate": 1.5321052094290258e-05,
"loss": 0.5364,
"step": 916
},
{
"epoch": 1.03,
"learning_rate": 1.5310809876386414e-05,
"loss": 0.5356,
"step": 917
},
{
"epoch": 1.03,
"learning_rate": 1.5300559892754957e-05,
"loss": 0.5347,
"step": 918
},
{
"epoch": 1.03,
"learning_rate": 1.5290302158383923e-05,
"loss": 0.52,
"step": 919
},
{
"epoch": 1.03,
"learning_rate": 1.5280036688272672e-05,
"loss": 0.5439,
"step": 920
},
{
"epoch": 1.03,
"learning_rate": 1.5269763497431882e-05,
"loss": 0.5515,
"step": 921
},
{
"epoch": 1.03,
"learning_rate": 1.5259482600883515e-05,
"loss": 0.5366,
"step": 922
},
{
"epoch": 1.03,
"learning_rate": 1.524919401366081e-05,
"loss": 0.5464,
"step": 923
},
{
"epoch": 1.03,
"learning_rate": 1.5238897750808242e-05,
"loss": 0.5208,
"step": 924
},
{
"epoch": 1.04,
"learning_rate": 1.5228593827381511e-05,
"loss": 0.5208,
"step": 925
},
{
"epoch": 1.04,
"learning_rate": 1.5218282258447522e-05,
"loss": 0.5249,
"step": 926
},
{
"epoch": 1.04,
"learning_rate": 1.520796305908436e-05,
"loss": 0.5054,
"step": 927
},
{
"epoch": 1.04,
"learning_rate": 1.5197636244381269e-05,
"loss": 0.5322,
"step": 928
},
{
"epoch": 1.04,
"learning_rate": 1.5187301829438622e-05,
"loss": 0.522,
"step": 929
},
{
"epoch": 1.04,
"learning_rate": 1.5176959829367907e-05,
"loss": 0.5181,
"step": 930
},
{
"epoch": 1.04,
"learning_rate": 1.5166610259291714e-05,
"loss": 0.5293,
"step": 931
},
{
"epoch": 1.04,
"learning_rate": 1.5156253134343683e-05,
"loss": 0.5359,
"step": 932
},
{
"epoch": 1.04,
"learning_rate": 1.5145888469668521e-05,
"loss": 0.5498,
"step": 933
},
{
"epoch": 1.05,
"learning_rate": 1.5135516280421944e-05,
"loss": 0.5325,
"step": 934
},
{
"epoch": 1.05,
"learning_rate": 1.5125136581770687e-05,
"loss": 0.5547,
"step": 935
},
{
"epoch": 1.05,
"learning_rate": 1.5114749388892445e-05,
"loss": 0.5261,
"step": 936
},
{
"epoch": 1.05,
"learning_rate": 1.5104354716975888e-05,
"loss": 0.5342,
"step": 937
},
{
"epoch": 1.05,
"learning_rate": 1.509395258122062e-05,
"loss": 0.5322,
"step": 938
},
{
"epoch": 1.05,
"learning_rate": 1.508354299683715e-05,
"loss": 0.5366,
"step": 939
},
{
"epoch": 1.05,
"learning_rate": 1.507312597904689e-05,
"loss": 0.5547,
"step": 940
},
{
"epoch": 1.05,
"learning_rate": 1.506270154308211e-05,
"loss": 0.5125,
"step": 941
},
{
"epoch": 1.05,
"learning_rate": 1.505226970418594e-05,
"loss": 0.5222,
"step": 942
},
{
"epoch": 1.06,
"learning_rate": 1.5041830477612322e-05,
"loss": 0.5312,
"step": 943
},
{
"epoch": 1.06,
"learning_rate": 1.5031383878626016e-05,
"loss": 0.531,
"step": 944
},
{
"epoch": 1.06,
"learning_rate": 1.5020929922502542e-05,
"loss": 0.5156,
"step": 945
},
{
"epoch": 1.06,
"learning_rate": 1.5010468624528196e-05,
"loss": 0.5203,
"step": 946
},
{
"epoch": 1.06,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.5532,
"step": 947
},
{
"epoch": 1.06,
"learning_rate": 1.4989524064225696e-05,
"loss": 0.5381,
"step": 948
},
{
"epoch": 1.06,
"learning_rate": 1.497904083252371e-05,
"loss": 0.5127,
"step": 949
},
{
"epoch": 1.06,
"learning_rate": 1.496855032022314e-05,
"loss": 0.5122,
"step": 950
},
{
"epoch": 1.06,
"learning_rate": 1.4958052542663728e-05,
"loss": 0.5398,
"step": 951
},
{
"epoch": 1.07,
"learning_rate": 1.4947547515195846e-05,
"loss": 0.5393,
"step": 952
},
{
"epoch": 1.07,
"learning_rate": 1.4937035253180457e-05,
"loss": 0.5486,
"step": 953
},
{
"epoch": 1.07,
"learning_rate": 1.4926515771989106e-05,
"loss": 0.5491,
"step": 954
},
{
"epoch": 1.07,
"learning_rate": 1.4915989087003901e-05,
"loss": 0.542,
"step": 955
},
{
"epoch": 1.07,
"learning_rate": 1.4905455213617481e-05,
"loss": 0.5034,
"step": 956
},
{
"epoch": 1.07,
"learning_rate": 1.4894914167232988e-05,
"loss": 0.5396,
"step": 957
},
{
"epoch": 1.07,
"learning_rate": 1.4884365963264062e-05,
"loss": 0.5425,
"step": 958
},
{
"epoch": 1.07,
"learning_rate": 1.4873810617134807e-05,
"loss": 0.5132,
"step": 959
},
{
"epoch": 1.07,
"learning_rate": 1.4863248144279769e-05,
"loss": 0.5264,
"step": 960
},
{
"epoch": 1.08,
"learning_rate": 1.4852678560143914e-05,
"loss": 0.5525,
"step": 961
},
{
"epoch": 1.08,
"learning_rate": 1.4842101880182609e-05,
"loss": 0.5005,
"step": 962
},
{
"epoch": 1.08,
"learning_rate": 1.4831518119861597e-05,
"loss": 0.5439,
"step": 963
},
{
"epoch": 1.08,
"learning_rate": 1.4820927294656973e-05,
"loss": 0.5205,
"step": 964
},
{
"epoch": 1.08,
"learning_rate": 1.481032942005516e-05,
"loss": 0.5288,
"step": 965
},
{
"epoch": 1.08,
"learning_rate": 1.4799724511552898e-05,
"loss": 0.5295,
"step": 966
},
{
"epoch": 1.08,
"learning_rate": 1.4789112584657202e-05,
"loss": 0.5298,
"step": 967
},
{
"epoch": 1.08,
"learning_rate": 1.4778493654885355e-05,
"loss": 0.5344,
"step": 968
},
{
"epoch": 1.08,
"learning_rate": 1.4767867737764877e-05,
"loss": 0.53,
"step": 969
},
{
"epoch": 1.09,
"learning_rate": 1.4757234848833509e-05,
"loss": 0.5339,
"step": 970
},
{
"epoch": 1.09,
"learning_rate": 1.4746595003639182e-05,
"loss": 0.5183,
"step": 971
},
{
"epoch": 1.09,
"learning_rate": 1.4735948217740006e-05,
"loss": 0.5129,
"step": 972
},
{
"epoch": 1.09,
"learning_rate": 1.4725294506704231e-05,
"loss": 0.531,
"step": 973
},
{
"epoch": 1.09,
"learning_rate": 1.4714633886110241e-05,
"loss": 0.5635,
"step": 974
},
{
"epoch": 1.09,
"learning_rate": 1.4703966371546519e-05,
"loss": 0.5212,
"step": 975
},
{
"epoch": 1.09,
"learning_rate": 1.4693291978611627e-05,
"loss": 0.5366,
"step": 976
},
{
"epoch": 1.09,
"learning_rate": 1.4682610722914192e-05,
"loss": 0.5105,
"step": 977
},
{
"epoch": 1.09,
"learning_rate": 1.4671922620072869e-05,
"loss": 0.54,
"step": 978
},
{
"epoch": 1.1,
"learning_rate": 1.466122768571633e-05,
"loss": 0.5205,
"step": 979
},
{
"epoch": 1.1,
"learning_rate": 1.4650525935483233e-05,
"loss": 0.5286,
"step": 980
},
{
"epoch": 1.1,
"learning_rate": 1.4639817385022206e-05,
"loss": 0.5034,
"step": 981
},
{
"epoch": 1.1,
"learning_rate": 1.4629102049991814e-05,
"loss": 0.5273,
"step": 982
},
{
"epoch": 1.1,
"learning_rate": 1.4618379946060553e-05,
"loss": 0.532,
"step": 983
},
{
"epoch": 1.1,
"learning_rate": 1.460765108890681e-05,
"loss": 0.5508,
"step": 984
},
{
"epoch": 1.1,
"learning_rate": 1.4596915494218842e-05,
"loss": 0.5354,
"step": 985
},
{
"epoch": 1.1,
"learning_rate": 1.4586173177694772e-05,
"loss": 0.5386,
"step": 986
},
{
"epoch": 1.1,
"learning_rate": 1.4575424155042537e-05,
"loss": 0.5083,
"step": 987
},
{
"epoch": 1.11,
"learning_rate": 1.4564668441979895e-05,
"loss": 0.5496,
"step": 988
},
{
"epoch": 1.11,
"learning_rate": 1.4553906054234372e-05,
"loss": 0.5183,
"step": 989
},
{
"epoch": 1.11,
"learning_rate": 1.4543137007543265e-05,
"loss": 0.5317,
"step": 990
},
{
"epoch": 1.11,
"learning_rate": 1.4532361317653603e-05,
"loss": 0.5071,
"step": 991
},
{
"epoch": 1.11,
"learning_rate": 1.4521579000322128e-05,
"loss": 0.5271,
"step": 992
},
{
"epoch": 1.11,
"learning_rate": 1.4510790071315278e-05,
"loss": 0.5178,
"step": 993
},
{
"epoch": 1.11,
"learning_rate": 1.4499994546409154e-05,
"loss": 0.5371,
"step": 994
},
{
"epoch": 1.11,
"learning_rate": 1.4489192441389507e-05,
"loss": 0.5649,
"step": 995
},
{
"epoch": 1.11,
"learning_rate": 1.4478383772051707e-05,
"loss": 0.5327,
"step": 996
},
{
"epoch": 1.12,
"learning_rate": 1.4467568554200717e-05,
"loss": 0.5168,
"step": 997
},
{
"epoch": 1.12,
"learning_rate": 1.4456746803651083e-05,
"loss": 0.5342,
"step": 998
},
{
"epoch": 1.12,
"learning_rate": 1.4445918536226904e-05,
"loss": 0.5308,
"step": 999
},
{
"epoch": 1.12,
"learning_rate": 1.4435083767761804e-05,
"loss": 0.5325,
"step": 1000
},
{
"epoch": 1.12,
"learning_rate": 1.4424242514098914e-05,
"loss": 0.5303,
"step": 1001
},
{
"epoch": 1.12,
"learning_rate": 1.441339479109085e-05,
"loss": 0.521,
"step": 1002
},
{
"epoch": 1.12,
"learning_rate": 1.4402540614599687e-05,
"loss": 0.5474,
"step": 1003
},
{
"epoch": 1.12,
"learning_rate": 1.4391680000496932e-05,
"loss": 0.5601,
"step": 1004
},
{
"epoch": 1.12,
"learning_rate": 1.4380812964663514e-05,
"loss": 0.5325,
"step": 1005
},
{
"epoch": 1.13,
"learning_rate": 1.4369939522989747e-05,
"loss": 0.5027,
"step": 1006
},
{
"epoch": 1.13,
"learning_rate": 1.4359059691375313e-05,
"loss": 0.5364,
"step": 1007
},
{
"epoch": 1.13,
"learning_rate": 1.4348173485729233e-05,
"loss": 0.54,
"step": 1008
},
{
"epoch": 1.13,
"learning_rate": 1.4337280921969858e-05,
"loss": 0.5376,
"step": 1009
},
{
"epoch": 1.13,
"learning_rate": 1.432638201602483e-05,
"loss": 0.5374,
"step": 1010
},
{
"epoch": 1.13,
"learning_rate": 1.4315476783831062e-05,
"loss": 0.5161,
"step": 1011
},
{
"epoch": 1.13,
"learning_rate": 1.4304565241334724e-05,
"loss": 0.4958,
"step": 1012
},
{
"epoch": 1.13,
"learning_rate": 1.4293647404491212e-05,
"loss": 0.5283,
"step": 1013
},
{
"epoch": 1.13,
"learning_rate": 1.4282723289265122e-05,
"loss": 0.5256,
"step": 1014
},
{
"epoch": 1.14,
"learning_rate": 1.4271792911630234e-05,
"loss": 0.5322,
"step": 1015
},
{
"epoch": 1.14,
"learning_rate": 1.4260856287569485e-05,
"loss": 0.4963,
"step": 1016
},
{
"epoch": 1.14,
"learning_rate": 1.4249913433074942e-05,
"loss": 0.5146,
"step": 1017
},
{
"epoch": 1.14,
"learning_rate": 1.4238964364147787e-05,
"loss": 0.5173,
"step": 1018
},
{
"epoch": 1.14,
"learning_rate": 1.4228009096798291e-05,
"loss": 0.5286,
"step": 1019
},
{
"epoch": 1.14,
"learning_rate": 1.4217047647045781e-05,
"loss": 0.5554,
"step": 1020
},
{
"epoch": 1.14,
"learning_rate": 1.420608003091863e-05,
"loss": 0.5222,
"step": 1021
},
{
"epoch": 1.14,
"learning_rate": 1.4195106264454224e-05,
"loss": 0.5359,
"step": 1022
},
{
"epoch": 1.14,
"learning_rate": 1.4184126363698949e-05,
"loss": 0.509,
"step": 1023
},
{
"epoch": 1.15,
"learning_rate": 1.4173140344708151e-05,
"loss": 0.5327,
"step": 1024
},
{
"epoch": 1.15,
"learning_rate": 1.4162148223546133e-05,
"loss": 0.5232,
"step": 1025
},
{
"epoch": 1.15,
"learning_rate": 1.415115001628611e-05,
"loss": 0.551,
"step": 1026
},
{
"epoch": 1.15,
"learning_rate": 1.4140145739010205e-05,
"loss": 0.5437,
"step": 1027
},
{
"epoch": 1.15,
"learning_rate": 1.4129135407809416e-05,
"loss": 0.5264,
"step": 1028
},
{
"epoch": 1.15,
"learning_rate": 1.4118119038783589e-05,
"loss": 0.5413,
"step": 1029
},
{
"epoch": 1.15,
"learning_rate": 1.41070966480414e-05,
"loss": 0.5193,
"step": 1030
},
{
"epoch": 1.15,
"learning_rate": 1.409606825170033e-05,
"loss": 0.5354,
"step": 1031
},
{
"epoch": 1.16,
"learning_rate": 1.4085033865886649e-05,
"loss": 0.5369,
"step": 1032
},
{
"epoch": 1.16,
"learning_rate": 1.4073993506735372e-05,
"loss": 0.5178,
"step": 1033
},
{
"epoch": 1.16,
"learning_rate": 1.4062947190390261e-05,
"loss": 0.5166,
"step": 1034
},
{
"epoch": 1.16,
"learning_rate": 1.4051894933003783e-05,
"loss": 0.5271,
"step": 1035
},
{
"epoch": 1.16,
"learning_rate": 1.4040836750737088e-05,
"loss": 0.5171,
"step": 1036
},
{
"epoch": 1.16,
"learning_rate": 1.4029772659760001e-05,
"loss": 0.5444,
"step": 1037
},
{
"epoch": 1.16,
"learning_rate": 1.4018702676250973e-05,
"loss": 0.5273,
"step": 1038
},
{
"epoch": 1.16,
"learning_rate": 1.4007626816397086e-05,
"loss": 0.5491,
"step": 1039
},
{
"epoch": 1.16,
"learning_rate": 1.3996545096394005e-05,
"loss": 0.5085,
"step": 1040
},
{
"epoch": 1.17,
"learning_rate": 1.3985457532445964e-05,
"loss": 0.5295,
"step": 1041
},
{
"epoch": 1.17,
"learning_rate": 1.3974364140765744e-05,
"loss": 0.522,
"step": 1042
},
{
"epoch": 1.17,
"learning_rate": 1.3963264937574654e-05,
"loss": 0.5391,
"step": 1043
},
{
"epoch": 1.17,
"learning_rate": 1.3952159939102492e-05,
"loss": 0.5349,
"step": 1044
},
{
"epoch": 1.17,
"learning_rate": 1.3941049161587532e-05,
"loss": 0.5159,
"step": 1045
},
{
"epoch": 1.17,
"learning_rate": 1.3929932621276503e-05,
"loss": 0.562,
"step": 1046
},
{
"epoch": 1.17,
"learning_rate": 1.3918810334424556e-05,
"loss": 0.5369,
"step": 1047
},
{
"epoch": 1.17,
"learning_rate": 1.3907682317295243e-05,
"loss": 0.4954,
"step": 1048
},
{
"epoch": 1.17,
"learning_rate": 1.3896548586160504e-05,
"loss": 0.5237,
"step": 1049
},
{
"epoch": 1.18,
"learning_rate": 1.3885409157300624e-05,
"loss": 0.519,
"step": 1050
},
{
"epoch": 1.18,
"learning_rate": 1.3874264047004228e-05,
"loss": 0.5352,
"step": 1051
},
{
"epoch": 1.18,
"learning_rate": 1.3863113271568243e-05,
"loss": 0.541,
"step": 1052
},
{
"epoch": 1.18,
"learning_rate": 1.3851956847297882e-05,
"loss": 0.5315,
"step": 1053
},
{
"epoch": 1.18,
"learning_rate": 1.3840794790506615e-05,
"loss": 0.5288,
"step": 1054
},
{
"epoch": 1.18,
"learning_rate": 1.3829627117516156e-05,
"loss": 0.5242,
"step": 1055
},
{
"epoch": 1.18,
"learning_rate": 1.3818453844656423e-05,
"loss": 0.5242,
"step": 1056
},
{
"epoch": 1.18,
"learning_rate": 1.3807274988265525e-05,
"loss": 0.5166,
"step": 1057
},
{
"epoch": 1.18,
"learning_rate": 1.3796090564689736e-05,
"loss": 0.5469,
"step": 1058
},
{
"epoch": 1.19,
"learning_rate": 1.3784900590283474e-05,
"loss": 0.5117,
"step": 1059
},
{
"epoch": 1.19,
"learning_rate": 1.377370508140927e-05,
"loss": 0.5105,
"step": 1060
},
{
"epoch": 1.19,
"learning_rate": 1.3762504054437744e-05,
"loss": 0.5322,
"step": 1061
},
{
"epoch": 1.19,
"learning_rate": 1.3751297525747589e-05,
"loss": 0.5273,
"step": 1062
},
{
"epoch": 1.19,
"learning_rate": 1.374008551172555e-05,
"loss": 0.5349,
"step": 1063
},
{
"epoch": 1.19,
"learning_rate": 1.3728868028766378e-05,
"loss": 0.5503,
"step": 1064
},
{
"epoch": 1.19,
"learning_rate": 1.3717645093272834e-05,
"loss": 0.531,
"step": 1065
},
{
"epoch": 1.19,
"learning_rate": 1.3706416721655637e-05,
"loss": 0.5144,
"step": 1066
},
{
"epoch": 1.19,
"learning_rate": 1.3695182930333482e-05,
"loss": 0.5237,
"step": 1067
},
{
"epoch": 1.2,
"learning_rate": 1.3683943735732956e-05,
"loss": 0.5115,
"step": 1068
},
{
"epoch": 1.2,
"learning_rate": 1.3672699154288569e-05,
"loss": 0.5156,
"step": 1069
},
{
"epoch": 1.2,
"learning_rate": 1.36614492024427e-05,
"loss": 0.5273,
"step": 1070
},
{
"epoch": 1.2,
"learning_rate": 1.3650193896645582e-05,
"loss": 0.5369,
"step": 1071
},
{
"epoch": 1.2,
"learning_rate": 1.3638933253355284e-05,
"loss": 0.5444,
"step": 1072
},
{
"epoch": 1.2,
"learning_rate": 1.362766728903766e-05,
"loss": 0.5505,
"step": 1073
},
{
"epoch": 1.2,
"learning_rate": 1.3616396020166368e-05,
"loss": 0.5435,
"step": 1074
},
{
"epoch": 1.2,
"learning_rate": 1.3605119463222808e-05,
"loss": 0.5161,
"step": 1075
},
{
"epoch": 1.2,
"learning_rate": 1.3593837634696119e-05,
"loss": 0.5269,
"step": 1076
},
{
"epoch": 1.21,
"learning_rate": 1.3582550551083143e-05,
"loss": 0.5264,
"step": 1077
},
{
"epoch": 1.21,
"learning_rate": 1.357125822888841e-05,
"loss": 0.5054,
"step": 1078
},
{
"epoch": 1.21,
"learning_rate": 1.3559960684624112e-05,
"loss": 0.5291,
"step": 1079
},
{
"epoch": 1.21,
"learning_rate": 1.354865793481007e-05,
"loss": 0.5037,
"step": 1080
},
{
"epoch": 1.21,
"learning_rate": 1.3537349995973726e-05,
"loss": 0.5266,
"step": 1081
},
{
"epoch": 1.21,
"learning_rate": 1.3526036884650096e-05,
"loss": 0.5408,
"step": 1082
},
{
"epoch": 1.21,
"learning_rate": 1.3514718617381779e-05,
"loss": 0.5352,
"step": 1083
},
{
"epoch": 1.21,
"learning_rate": 1.3503395210718898e-05,
"loss": 0.5261,
"step": 1084
},
{
"epoch": 1.21,
"learning_rate": 1.3492066681219097e-05,
"loss": 0.5132,
"step": 1085
},
{
"epoch": 1.22,
"learning_rate": 1.3480733045447505e-05,
"loss": 0.5225,
"step": 1086
},
{
"epoch": 1.22,
"learning_rate": 1.3469394319976723e-05,
"loss": 0.5195,
"step": 1087
},
{
"epoch": 1.22,
"learning_rate": 1.3458050521386801e-05,
"loss": 0.561,
"step": 1088
},
{
"epoch": 1.22,
"learning_rate": 1.3446701666265192e-05,
"loss": 0.5508,
"step": 1089
},
{
"epoch": 1.22,
"learning_rate": 1.3435347771206751e-05,
"loss": 0.5522,
"step": 1090
},
{
"epoch": 1.22,
"learning_rate": 1.3423988852813706e-05,
"loss": 0.5308,
"step": 1091
},
{
"epoch": 1.22,
"learning_rate": 1.341262492769562e-05,
"loss": 0.5413,
"step": 1092
},
{
"epoch": 1.22,
"learning_rate": 1.3401256012469395e-05,
"loss": 0.5364,
"step": 1093
},
{
"epoch": 1.22,
"learning_rate": 1.3389882123759206e-05,
"loss": 0.5359,
"step": 1094
},
{
"epoch": 1.23,
"learning_rate": 1.3378503278196522e-05,
"loss": 0.5393,
"step": 1095
},
{
"epoch": 1.23,
"learning_rate": 1.3367119492420047e-05,
"loss": 0.5403,
"step": 1096
},
{
"epoch": 1.23,
"learning_rate": 1.3355730783075714e-05,
"loss": 0.5325,
"step": 1097
},
{
"epoch": 1.23,
"learning_rate": 1.3344337166816652e-05,
"loss": 0.52,
"step": 1098
},
{
"epoch": 1.23,
"learning_rate": 1.333293866030317e-05,
"loss": 0.53,
"step": 1099
},
{
"epoch": 1.23,
"learning_rate": 1.3321535280202724e-05,
"loss": 0.5229,
"step": 1100
},
{
"epoch": 1.23,
"learning_rate": 1.33101270431899e-05,
"loss": 0.5386,
"step": 1101
},
{
"epoch": 1.23,
"learning_rate": 1.3298713965946382e-05,
"loss": 0.5217,
"step": 1102
},
{
"epoch": 1.23,
"learning_rate": 1.3287296065160931e-05,
"loss": 0.5415,
"step": 1103
},
{
"epoch": 1.24,
"learning_rate": 1.327587335752937e-05,
"loss": 0.5371,
"step": 1104
},
{
"epoch": 1.24,
"learning_rate": 1.3264445859754536e-05,
"loss": 0.5188,
"step": 1105
},
{
"epoch": 1.24,
"learning_rate": 1.3253013588546283e-05,
"loss": 0.5513,
"step": 1106
},
{
"epoch": 1.24,
"learning_rate": 1.3241576560621444e-05,
"loss": 0.5139,
"step": 1107
},
{
"epoch": 1.24,
"learning_rate": 1.3230134792703802e-05,
"loss": 0.5356,
"step": 1108
},
{
"epoch": 1.24,
"learning_rate": 1.321868830152407e-05,
"loss": 0.5193,
"step": 1109
},
{
"epoch": 1.24,
"learning_rate": 1.320723710381987e-05,
"loss": 0.5093,
"step": 1110
},
{
"epoch": 1.24,
"learning_rate": 1.3195781216335713e-05,
"loss": 0.5012,
"step": 1111
},
{
"epoch": 1.24,
"learning_rate": 1.318432065582296e-05,
"loss": 0.5349,
"step": 1112
},
{
"epoch": 1.25,
"learning_rate": 1.3172855439039802e-05,
"loss": 0.5281,
"step": 1113
},
{
"epoch": 1.25,
"learning_rate": 1.3161385582751247e-05,
"loss": 0.5027,
"step": 1114
},
{
"epoch": 1.25,
"learning_rate": 1.3149911103729082e-05,
"loss": 0.5771,
"step": 1115
},
{
"epoch": 1.25,
"learning_rate": 1.313843201875186e-05,
"loss": 0.5332,
"step": 1116
},
{
"epoch": 1.25,
"learning_rate": 1.3126948344604857e-05,
"loss": 0.5095,
"step": 1117
},
{
"epoch": 1.25,
"learning_rate": 1.3115460098080068e-05,
"loss": 0.5359,
"step": 1118
},
{
"epoch": 1.25,
"learning_rate": 1.3103967295976178e-05,
"loss": 0.5269,
"step": 1119
},
{
"epoch": 1.25,
"learning_rate": 1.3092469955098521e-05,
"loss": 0.5149,
"step": 1120
},
{
"epoch": 1.25,
"learning_rate": 1.308096809225908e-05,
"loss": 0.5256,
"step": 1121
},
{
"epoch": 1.26,
"learning_rate": 1.306946172427644e-05,
"loss": 0.5276,
"step": 1122
},
{
"epoch": 1.26,
"learning_rate": 1.3057950867975784e-05,
"loss": 0.5527,
"step": 1123
},
{
"epoch": 1.26,
"learning_rate": 1.3046435540188848e-05,
"loss": 0.5176,
"step": 1124
},
{
"epoch": 1.26,
"learning_rate": 1.3034915757753917e-05,
"loss": 0.5286,
"step": 1125
},
{
"epoch": 1.26,
"learning_rate": 1.3023391537515773e-05,
"loss": 0.5388,
"step": 1126
},
{
"epoch": 1.26,
"learning_rate": 1.3011862896325714e-05,
"loss": 0.5117,
"step": 1127
},
{
"epoch": 1.26,
"learning_rate": 1.3000329851041474e-05,
"loss": 0.5229,
"step": 1128
},
{
"epoch": 1.26,
"learning_rate": 1.2988792418527241e-05,
"loss": 0.5366,
"step": 1129
},
{
"epoch": 1.26,
"learning_rate": 1.2977250615653621e-05,
"loss": 0.5229,
"step": 1130
},
{
"epoch": 1.27,
"learning_rate": 1.2965704459297603e-05,
"loss": 0.5244,
"step": 1131
},
{
"epoch": 1.27,
"learning_rate": 1.2954153966342549e-05,
"loss": 0.5527,
"step": 1132
},
{
"epoch": 1.27,
"learning_rate": 1.2942599153678153e-05,
"loss": 0.5215,
"step": 1133
},
{
"epoch": 1.27,
"learning_rate": 1.2931040038200435e-05,
"loss": 0.5195,
"step": 1134
},
{
"epoch": 1.27,
"learning_rate": 1.29194766368117e-05,
"loss": 0.5342,
"step": 1135
},
{
"epoch": 1.27,
"learning_rate": 1.2907908966420526e-05,
"loss": 0.5315,
"step": 1136
},
{
"epoch": 1.27,
"learning_rate": 1.289633704394173e-05,
"loss": 0.5518,
"step": 1137
},
{
"epoch": 1.27,
"learning_rate": 1.2884760886296338e-05,
"loss": 0.5288,
"step": 1138
},
{
"epoch": 1.27,
"learning_rate": 1.2873180510411589e-05,
"loss": 0.5254,
"step": 1139
},
{
"epoch": 1.28,
"learning_rate": 1.2861595933220873e-05,
"loss": 0.5483,
"step": 1140
},
{
"epoch": 1.28,
"learning_rate": 1.2850007171663727e-05,
"loss": 0.5444,
"step": 1141
},
{
"epoch": 1.28,
"learning_rate": 1.2838414242685814e-05,
"loss": 0.5103,
"step": 1142
},
{
"epoch": 1.28,
"learning_rate": 1.282681716323888e-05,
"loss": 0.5288,
"step": 1143
},
{
"epoch": 1.28,
"learning_rate": 1.2815215950280753e-05,
"loss": 0.5337,
"step": 1144
},
{
"epoch": 1.28,
"learning_rate": 1.2803610620775288e-05,
"loss": 0.5381,
"step": 1145
},
{
"epoch": 1.28,
"learning_rate": 1.2792001191692375e-05,
"loss": 0.5364,
"step": 1146
},
{
"epoch": 1.28,
"learning_rate": 1.278038768000789e-05,
"loss": 0.5273,
"step": 1147
},
{
"epoch": 1.28,
"learning_rate": 1.2768770102703687e-05,
"loss": 0.5229,
"step": 1148
},
{
"epoch": 1.29,
"learning_rate": 1.2757148476767553e-05,
"loss": 0.5293,
"step": 1149
},
{
"epoch": 1.29,
"learning_rate": 1.27455228191932e-05,
"loss": 0.5415,
"step": 1150
},
{
"epoch": 1.29,
"learning_rate": 1.2733893146980248e-05,
"loss": 0.53,
"step": 1151
},
{
"epoch": 1.29,
"learning_rate": 1.2722259477134162e-05,
"loss": 0.5349,
"step": 1152
},
{
"epoch": 1.29,
"learning_rate": 1.2710621826666278e-05,
"loss": 0.5181,
"step": 1153
},
{
"epoch": 1.29,
"learning_rate": 1.269898021259373e-05,
"loss": 0.5137,
"step": 1154
},
{
"epoch": 1.29,
"learning_rate": 1.2687334651939471e-05,
"loss": 0.5398,
"step": 1155
},
{
"epoch": 1.29,
"learning_rate": 1.267568516173221e-05,
"loss": 0.5488,
"step": 1156
},
{
"epoch": 1.29,
"learning_rate": 1.2664031759006396e-05,
"loss": 0.5474,
"step": 1157
},
{
"epoch": 1.3,
"learning_rate": 1.2652374460802218e-05,
"loss": 0.5198,
"step": 1158
},
{
"epoch": 1.3,
"learning_rate": 1.2640713284165549e-05,
"loss": 0.5488,
"step": 1159
},
{
"epoch": 1.3,
"learning_rate": 1.2629048246147932e-05,
"loss": 0.5291,
"step": 1160
},
{
"epoch": 1.3,
"learning_rate": 1.2617379363806563e-05,
"loss": 0.5374,
"step": 1161
},
{
"epoch": 1.3,
"learning_rate": 1.2605706654204257e-05,
"loss": 0.5325,
"step": 1162
},
{
"epoch": 1.3,
"learning_rate": 1.2594030134409423e-05,
"loss": 0.5461,
"step": 1163
},
{
"epoch": 1.3,
"learning_rate": 1.2582349821496041e-05,
"loss": 0.5183,
"step": 1164
},
{
"epoch": 1.3,
"learning_rate": 1.2570665732543643e-05,
"loss": 0.5137,
"step": 1165
},
{
"epoch": 1.3,
"learning_rate": 1.2558977884637273e-05,
"loss": 0.5239,
"step": 1166
},
{
"epoch": 1.31,
"learning_rate": 1.2547286294867486e-05,
"loss": 0.5217,
"step": 1167
},
{
"epoch": 1.31,
"learning_rate": 1.2535590980330297e-05,
"loss": 0.52,
"step": 1168
},
{
"epoch": 1.31,
"learning_rate": 1.2523891958127167e-05,
"loss": 0.5298,
"step": 1169
},
{
"epoch": 1.31,
"learning_rate": 1.2512189245364986e-05,
"loss": 0.5339,
"step": 1170
},
{
"epoch": 1.31,
"learning_rate": 1.2500482859156034e-05,
"loss": 0.5381,
"step": 1171
},
{
"epoch": 1.31,
"learning_rate": 1.2488772816617968e-05,
"loss": 0.5195,
"step": 1172
},
{
"epoch": 1.31,
"learning_rate": 1.2477059134873784e-05,
"loss": 0.5479,
"step": 1173
},
{
"epoch": 1.31,
"learning_rate": 1.2465341831051808e-05,
"loss": 0.5144,
"step": 1174
},
{
"epoch": 1.32,
"learning_rate": 1.2453620922285658e-05,
"loss": 0.5288,
"step": 1175
},
{
"epoch": 1.32,
"learning_rate": 1.2441896425714224e-05,
"loss": 0.519,
"step": 1176
},
{
"epoch": 1.32,
"learning_rate": 1.2430168358481642e-05,
"loss": 0.5342,
"step": 1177
},
{
"epoch": 1.32,
"learning_rate": 1.2418436737737264e-05,
"loss": 0.5232,
"step": 1178
},
{
"epoch": 1.32,
"learning_rate": 1.240670158063565e-05,
"loss": 0.5164,
"step": 1179
},
{
"epoch": 1.32,
"learning_rate": 1.239496290433652e-05,
"loss": 0.5227,
"step": 1180
},
{
"epoch": 1.32,
"learning_rate": 1.2383220726004751e-05,
"loss": 0.5352,
"step": 1181
},
{
"epoch": 1.32,
"learning_rate": 1.2371475062810324e-05,
"loss": 0.5259,
"step": 1182
},
{
"epoch": 1.32,
"learning_rate": 1.2359725931928335e-05,
"loss": 0.5095,
"step": 1183
},
{
"epoch": 1.33,
"learning_rate": 1.2347973350538936e-05,
"loss": 0.5034,
"step": 1184
},
{
"epoch": 1.33,
"learning_rate": 1.2336217335827332e-05,
"loss": 0.5425,
"step": 1185
},
{
"epoch": 1.33,
"learning_rate": 1.2324457904983746e-05,
"loss": 0.5215,
"step": 1186
},
{
"epoch": 1.33,
"learning_rate": 1.2312695075203396e-05,
"loss": 0.5317,
"step": 1187
},
{
"epoch": 1.33,
"learning_rate": 1.2300928863686472e-05,
"loss": 0.54,
"step": 1188
},
{
"epoch": 1.33,
"learning_rate": 1.2289159287638107e-05,
"loss": 0.5547,
"step": 1189
},
{
"epoch": 1.33,
"learning_rate": 1.2277386364268354e-05,
"loss": 0.5378,
"step": 1190
},
{
"epoch": 1.33,
"learning_rate": 1.2265610110792161e-05,
"loss": 0.5574,
"step": 1191
},
{
"epoch": 1.33,
"learning_rate": 1.2253830544429348e-05,
"loss": 0.5034,
"step": 1192
},
{
"epoch": 1.34,
"learning_rate": 1.2242047682404575e-05,
"loss": 0.5371,
"step": 1193
},
{
"epoch": 1.34,
"learning_rate": 1.2230261541947316e-05,
"loss": 0.5154,
"step": 1194
},
{
"epoch": 1.34,
"learning_rate": 1.221847214029186e-05,
"loss": 0.4934,
"step": 1195
},
{
"epoch": 1.34,
"learning_rate": 1.2206679494677238e-05,
"loss": 0.522,
"step": 1196
},
{
"epoch": 1.34,
"learning_rate": 1.2194883622347247e-05,
"loss": 0.5239,
"step": 1197
},
{
"epoch": 1.34,
"learning_rate": 1.2183084540550379e-05,
"loss": 0.5125,
"step": 1198
},
{
"epoch": 1.34,
"learning_rate": 1.2171282266539846e-05,
"loss": 0.5273,
"step": 1199
},
{
"epoch": 1.34,
"learning_rate": 1.2159476817573506e-05,
"loss": 0.5291,
"step": 1200
},
{
"epoch": 1.34,
"learning_rate": 1.2147668210913868e-05,
"loss": 0.4978,
"step": 1201
},
{
"epoch": 1.35,
"learning_rate": 1.2135856463828059e-05,
"loss": 0.5308,
"step": 1202
},
{
"epoch": 1.35,
"learning_rate": 1.21240415935878e-05,
"loss": 0.5063,
"step": 1203
},
{
"epoch": 1.35,
"learning_rate": 1.2112223617469372e-05,
"loss": 0.5239,
"step": 1204
},
{
"epoch": 1.35,
"learning_rate": 1.21004025527536e-05,
"loss": 0.4983,
"step": 1205
},
{
"epoch": 1.35,
"learning_rate": 1.2088578416725829e-05,
"loss": 0.5403,
"step": 1206
},
{
"epoch": 1.35,
"learning_rate": 1.2076751226675898e-05,
"loss": 0.5037,
"step": 1207
},
{
"epoch": 1.35,
"learning_rate": 1.2064920999898098e-05,
"loss": 0.5505,
"step": 1208
},
{
"epoch": 1.35,
"learning_rate": 1.2053087753691173e-05,
"loss": 0.521,
"step": 1209
},
{
"epoch": 1.35,
"learning_rate": 1.2041251505358273e-05,
"loss": 0.5173,
"step": 1210
},
{
"epoch": 1.36,
"learning_rate": 1.2029412272206953e-05,
"loss": 0.5261,
"step": 1211
},
{
"epoch": 1.36,
"learning_rate": 1.2017570071549113e-05,
"loss": 0.5554,
"step": 1212
},
{
"epoch": 1.36,
"learning_rate": 1.200572492070101e-05,
"loss": 0.5349,
"step": 1213
},
{
"epoch": 1.36,
"learning_rate": 1.1993876836983198e-05,
"loss": 0.5449,
"step": 1214
},
{
"epoch": 1.36,
"learning_rate": 1.1982025837720533e-05,
"loss": 0.5349,
"step": 1215
},
{
"epoch": 1.36,
"learning_rate": 1.197017194024213e-05,
"loss": 0.5386,
"step": 1216
},
{
"epoch": 1.36,
"learning_rate": 1.1958315161881338e-05,
"loss": 0.5278,
"step": 1217
},
{
"epoch": 1.36,
"learning_rate": 1.1946455519975724e-05,
"loss": 0.5234,
"step": 1218
},
{
"epoch": 1.36,
"learning_rate": 1.1934593031867038e-05,
"loss": 0.5454,
"step": 1219
},
{
"epoch": 1.37,
"learning_rate": 1.19227277149012e-05,
"loss": 0.5278,
"step": 1220
},
{
"epoch": 1.37,
"learning_rate": 1.1910859586428258e-05,
"loss": 0.5215,
"step": 1221
},
{
"epoch": 1.37,
"learning_rate": 1.1898988663802366e-05,
"loss": 0.5139,
"step": 1222
},
{
"epoch": 1.37,
"learning_rate": 1.1887114964381783e-05,
"loss": 0.5002,
"step": 1223
},
{
"epoch": 1.37,
"learning_rate": 1.187523850552881e-05,
"loss": 0.5173,
"step": 1224
},
{
"epoch": 1.37,
"learning_rate": 1.1863359304609792e-05,
"loss": 0.5134,
"step": 1225
},
{
"epoch": 1.37,
"learning_rate": 1.1851477378995076e-05,
"loss": 0.5046,
"step": 1226
},
{
"epoch": 1.37,
"learning_rate": 1.1839592746059008e-05,
"loss": 0.5059,
"step": 1227
},
{
"epoch": 1.37,
"learning_rate": 1.1827705423179875e-05,
"loss": 0.5225,
"step": 1228
},
{
"epoch": 1.38,
"learning_rate": 1.1815815427739911e-05,
"loss": 0.5247,
"step": 1229
},
{
"epoch": 1.38,
"learning_rate": 1.1803922777125247e-05,
"loss": 0.5298,
"step": 1230
},
{
"epoch": 1.38,
"learning_rate": 1.1792027488725909e-05,
"loss": 0.5083,
"step": 1231
},
{
"epoch": 1.38,
"learning_rate": 1.1780129579935768e-05,
"loss": 0.5044,
"step": 1232
},
{
"epoch": 1.38,
"learning_rate": 1.1768229068152533e-05,
"loss": 0.5098,
"step": 1233
},
{
"epoch": 1.38,
"learning_rate": 1.1756325970777718e-05,
"loss": 0.5276,
"step": 1234
},
{
"epoch": 1.38,
"learning_rate": 1.1744420305216622e-05,
"loss": 0.5232,
"step": 1235
},
{
"epoch": 1.38,
"learning_rate": 1.1732512088878287e-05,
"loss": 0.5134,
"step": 1236
},
{
"epoch": 1.38,
"learning_rate": 1.1720601339175501e-05,
"loss": 0.5366,
"step": 1237
},
{
"epoch": 1.39,
"learning_rate": 1.1708688073524742e-05,
"loss": 0.5552,
"step": 1238
},
{
"epoch": 1.39,
"learning_rate": 1.1696772309346183e-05,
"loss": 0.5388,
"step": 1239
},
{
"epoch": 1.39,
"learning_rate": 1.1684854064063629e-05,
"loss": 0.5149,
"step": 1240
},
{
"epoch": 1.39,
"learning_rate": 1.1672933355104533e-05,
"loss": 0.5486,
"step": 1241
},
{
"epoch": 1.39,
"learning_rate": 1.1661010199899938e-05,
"loss": 0.5134,
"step": 1242
},
{
"epoch": 1.39,
"learning_rate": 1.1649084615884472e-05,
"loss": 0.5083,
"step": 1243
},
{
"epoch": 1.39,
"learning_rate": 1.1637156620496309e-05,
"loss": 0.4912,
"step": 1244
},
{
"epoch": 1.39,
"learning_rate": 1.162522623117715e-05,
"loss": 0.5469,
"step": 1245
},
{
"epoch": 1.39,
"learning_rate": 1.16132934653722e-05,
"loss": 0.5283,
"step": 1246
},
{
"epoch": 1.4,
"learning_rate": 1.1601358340530134e-05,
"loss": 0.5239,
"step": 1247
},
{
"epoch": 1.4,
"learning_rate": 1.1589420874103081e-05,
"loss": 0.5217,
"step": 1248
},
{
"epoch": 1.4,
"learning_rate": 1.1577481083546592e-05,
"loss": 0.5266,
"step": 1249
},
{
"epoch": 1.4,
"learning_rate": 1.1565538986319613e-05,
"loss": 0.5293,
"step": 1250
},
{
"epoch": 1.4,
"learning_rate": 1.1553594599884472e-05,
"loss": 0.5254,
"step": 1251
},
{
"epoch": 1.4,
"learning_rate": 1.1541647941706834e-05,
"loss": 0.5183,
"step": 1252
},
{
"epoch": 1.4,
"learning_rate": 1.1529699029255696e-05,
"loss": 0.4937,
"step": 1253
},
{
"epoch": 1.4,
"learning_rate": 1.1517747880003336e-05,
"loss": 0.5198,
"step": 1254
},
{
"epoch": 1.4,
"learning_rate": 1.1505794511425325e-05,
"loss": 0.5134,
"step": 1255
},
{
"epoch": 1.41,
"learning_rate": 1.1493838941000459e-05,
"loss": 0.5278,
"step": 1256
},
{
"epoch": 1.41,
"learning_rate": 1.1481881186210767e-05,
"loss": 0.5076,
"step": 1257
},
{
"epoch": 1.41,
"learning_rate": 1.1469921264541457e-05,
"loss": 0.5146,
"step": 1258
},
{
"epoch": 1.41,
"learning_rate": 1.1457959193480925e-05,
"loss": 0.5444,
"step": 1259
},
{
"epoch": 1.41,
"learning_rate": 1.1445994990520697e-05,
"loss": 0.5356,
"step": 1260
},
{
"epoch": 1.41,
"learning_rate": 1.1434028673155417e-05,
"loss": 0.5361,
"step": 1261
},
{
"epoch": 1.41,
"learning_rate": 1.1422060258882826e-05,
"loss": 0.512,
"step": 1262
},
{
"epoch": 1.41,
"learning_rate": 1.1410089765203724e-05,
"loss": 0.5332,
"step": 1263
},
{
"epoch": 1.41,
"learning_rate": 1.1398117209621966e-05,
"loss": 0.5278,
"step": 1264
},
{
"epoch": 1.42,
"learning_rate": 1.1386142609644406e-05,
"loss": 0.5254,
"step": 1265
},
{
"epoch": 1.42,
"learning_rate": 1.1374165982780886e-05,
"loss": 0.5278,
"step": 1266
},
{
"epoch": 1.42,
"learning_rate": 1.1362187346544234e-05,
"loss": 0.5125,
"step": 1267
},
{
"epoch": 1.42,
"learning_rate": 1.135020671845019e-05,
"loss": 0.5342,
"step": 1268
},
{
"epoch": 1.42,
"learning_rate": 1.1338224116017425e-05,
"loss": 0.4922,
"step": 1269
},
{
"epoch": 1.42,
"learning_rate": 1.1326239556767487e-05,
"loss": 0.5068,
"step": 1270
},
{
"epoch": 1.42,
"learning_rate": 1.1314253058224786e-05,
"loss": 0.5347,
"step": 1271
},
{
"epoch": 1.42,
"learning_rate": 1.1302264637916576e-05,
"loss": 0.5339,
"step": 1272
},
{
"epoch": 1.42,
"learning_rate": 1.129027431337291e-05,
"loss": 0.5278,
"step": 1273
},
{
"epoch": 1.43,
"learning_rate": 1.1278282102126635e-05,
"loss": 0.5354,
"step": 1274
},
{
"epoch": 1.43,
"learning_rate": 1.1266288021713347e-05,
"loss": 0.52,
"step": 1275
},
{
"epoch": 1.43,
"learning_rate": 1.1254292089671388e-05,
"loss": 0.5061,
"step": 1276
},
{
"epoch": 1.43,
"learning_rate": 1.1242294323541796e-05,
"loss": 0.5361,
"step": 1277
},
{
"epoch": 1.43,
"learning_rate": 1.1230294740868294e-05,
"loss": 0.5012,
"step": 1278
},
{
"epoch": 1.43,
"learning_rate": 1.1218293359197267e-05,
"loss": 0.521,
"step": 1279
},
{
"epoch": 1.43,
"learning_rate": 1.1206290196077723e-05,
"loss": 0.5085,
"step": 1280
},
{
"epoch": 1.43,
"learning_rate": 1.1194285269061277e-05,
"loss": 0.5188,
"step": 1281
},
{
"epoch": 1.43,
"learning_rate": 1.1182278595702123e-05,
"loss": 0.5032,
"step": 1282
},
{
"epoch": 1.44,
"learning_rate": 1.1170270193557015e-05,
"loss": 0.5125,
"step": 1283
},
{
"epoch": 1.44,
"learning_rate": 1.1158260080185226e-05,
"loss": 0.5259,
"step": 1284
},
{
"epoch": 1.44,
"learning_rate": 1.1146248273148537e-05,
"loss": 0.5105,
"step": 1285
},
{
"epoch": 1.44,
"learning_rate": 1.11342347900112e-05,
"loss": 0.4968,
"step": 1286
},
{
"epoch": 1.44,
"learning_rate": 1.1122219648339925e-05,
"loss": 0.5295,
"step": 1287
},
{
"epoch": 1.44,
"learning_rate": 1.1110202865703843e-05,
"loss": 0.5144,
"step": 1288
},
{
"epoch": 1.44,
"learning_rate": 1.1098184459674483e-05,
"loss": 0.5271,
"step": 1289
},
{
"epoch": 1.44,
"learning_rate": 1.108616444782575e-05,
"loss": 0.5278,
"step": 1290
},
{
"epoch": 1.44,
"learning_rate": 1.10741428477339e-05,
"loss": 0.5056,
"step": 1291
},
{
"epoch": 1.45,
"learning_rate": 1.1062119676977508e-05,
"loss": 0.5105,
"step": 1292
},
{
"epoch": 1.45,
"learning_rate": 1.1050094953137444e-05,
"loss": 0.5215,
"step": 1293
},
{
"epoch": 1.45,
"learning_rate": 1.1038068693796846e-05,
"loss": 0.511,
"step": 1294
},
{
"epoch": 1.45,
"learning_rate": 1.1026040916541115e-05,
"loss": 0.5261,
"step": 1295
},
{
"epoch": 1.45,
"learning_rate": 1.1014011638957849e-05,
"loss": 0.5056,
"step": 1296
},
{
"epoch": 1.45,
"learning_rate": 1.1001980878636854e-05,
"loss": 0.5327,
"step": 1297
},
{
"epoch": 1.45,
"learning_rate": 1.0989948653170097e-05,
"loss": 0.5425,
"step": 1298
},
{
"epoch": 1.45,
"learning_rate": 1.0977914980151692e-05,
"loss": 0.502,
"step": 1299
},
{
"epoch": 1.45,
"learning_rate": 1.0965879877177868e-05,
"loss": 0.5327,
"step": 1300
},
{
"epoch": 1.46,
"learning_rate": 1.0953843361846948e-05,
"loss": 0.5156,
"step": 1301
},
{
"epoch": 1.46,
"learning_rate": 1.0941805451759311e-05,
"loss": 0.5186,
"step": 1302
},
{
"epoch": 1.46,
"learning_rate": 1.0929766164517383e-05,
"loss": 0.5366,
"step": 1303
},
{
"epoch": 1.46,
"learning_rate": 1.0917725517725608e-05,
"loss": 0.5139,
"step": 1304
},
{
"epoch": 1.46,
"learning_rate": 1.0905683528990407e-05,
"loss": 0.5083,
"step": 1305
},
{
"epoch": 1.46,
"learning_rate": 1.0893640215920172e-05,
"loss": 0.5195,
"step": 1306
},
{
"epoch": 1.46,
"learning_rate": 1.0881595596125223e-05,
"loss": 0.501,
"step": 1307
},
{
"epoch": 1.46,
"learning_rate": 1.0869549687217802e-05,
"loss": 0.5208,
"step": 1308
},
{
"epoch": 1.47,
"learning_rate": 1.085750250681203e-05,
"loss": 0.5022,
"step": 1309
},
{
"epoch": 1.47,
"learning_rate": 1.0845454072523878e-05,
"loss": 0.5137,
"step": 1310
},
{
"epoch": 1.47,
"learning_rate": 1.083340440197117e-05,
"loss": 0.5107,
"step": 1311
},
{
"epoch": 1.47,
"learning_rate": 1.0821353512773522e-05,
"loss": 0.5037,
"step": 1312
},
{
"epoch": 1.47,
"learning_rate": 1.0809301422552343e-05,
"loss": 0.5266,
"step": 1313
},
{
"epoch": 1.47,
"learning_rate": 1.0797248148930783e-05,
"loss": 0.5225,
"step": 1314
},
{
"epoch": 1.47,
"learning_rate": 1.0785193709533739e-05,
"loss": 0.5078,
"step": 1315
},
{
"epoch": 1.47,
"learning_rate": 1.0773138121987807e-05,
"loss": 0.4995,
"step": 1316
},
{
"epoch": 1.47,
"learning_rate": 1.0761081403921255e-05,
"loss": 0.5049,
"step": 1317
},
{
"epoch": 1.48,
"learning_rate": 1.074902357296401e-05,
"loss": 0.5105,
"step": 1318
},
{
"epoch": 1.48,
"learning_rate": 1.073696464674763e-05,
"loss": 0.531,
"step": 1319
},
{
"epoch": 1.48,
"learning_rate": 1.0724904642905272e-05,
"loss": 0.5234,
"step": 1320
},
{
"epoch": 1.48,
"learning_rate": 1.071284357907166e-05,
"loss": 0.5222,
"step": 1321
},
{
"epoch": 1.48,
"learning_rate": 1.0700781472883077e-05,
"loss": 0.5054,
"step": 1322
},
{
"epoch": 1.48,
"learning_rate": 1.0688718341977336e-05,
"loss": 0.5032,
"step": 1323
},
{
"epoch": 1.48,
"learning_rate": 1.0676654203993733e-05,
"loss": 0.5354,
"step": 1324
},
{
"epoch": 1.48,
"learning_rate": 1.0664589076573047e-05,
"loss": 0.5337,
"step": 1325
},
{
"epoch": 1.48,
"learning_rate": 1.0652522977357498e-05,
"loss": 0.5127,
"step": 1326
},
{
"epoch": 1.49,
"learning_rate": 1.0640455923990735e-05,
"loss": 0.4958,
"step": 1327
},
{
"epoch": 1.49,
"learning_rate": 1.0628387934117795e-05,
"loss": 0.501,
"step": 1328
},
{
"epoch": 1.49,
"learning_rate": 1.0616319025385088e-05,
"loss": 0.5251,
"step": 1329
},
{
"epoch": 1.49,
"learning_rate": 1.0604249215440365e-05,
"loss": 0.5076,
"step": 1330
},
{
"epoch": 1.49,
"learning_rate": 1.0592178521932695e-05,
"loss": 0.5154,
"step": 1331
},
{
"epoch": 1.49,
"learning_rate": 1.0580106962512446e-05,
"loss": 0.5171,
"step": 1332
},
{
"epoch": 1.49,
"learning_rate": 1.0568034554831238e-05,
"loss": 0.5085,
"step": 1333
},
{
"epoch": 1.49,
"learning_rate": 1.0555961316541947e-05,
"loss": 0.5237,
"step": 1334
},
{
"epoch": 1.49,
"learning_rate": 1.0543887265298651e-05,
"loss": 0.5254,
"step": 1335
},
{
"epoch": 1.5,
"learning_rate": 1.0531812418756625e-05,
"loss": 0.522,
"step": 1336
},
{
"epoch": 1.5,
"learning_rate": 1.0519736794572308e-05,
"loss": 0.5291,
"step": 1337
},
{
"epoch": 1.5,
"learning_rate": 1.050766041040326e-05,
"loss": 0.4956,
"step": 1338
},
{
"epoch": 1.5,
"learning_rate": 1.0495583283908178e-05,
"loss": 0.5349,
"step": 1339
},
{
"epoch": 1.5,
"learning_rate": 1.0483505432746821e-05,
"loss": 0.5276,
"step": 1340
},
{
"epoch": 1.5,
"learning_rate": 1.0471426874580025e-05,
"loss": 0.5234,
"step": 1341
},
{
"epoch": 1.5,
"learning_rate": 1.0459347627069643e-05,
"loss": 0.5029,
"step": 1342
},
{
"epoch": 1.5,
"learning_rate": 1.0447267707878552e-05,
"loss": 0.5283,
"step": 1343
},
{
"epoch": 1.5,
"learning_rate": 1.0435187134670608e-05,
"loss": 0.512,
"step": 1344
},
{
"epoch": 1.51,
"learning_rate": 1.042310592511061e-05,
"loss": 0.499,
"step": 1345
},
{
"epoch": 1.51,
"learning_rate": 1.0411024096864302e-05,
"loss": 0.5247,
"step": 1346
},
{
"epoch": 1.51,
"learning_rate": 1.0398941667598328e-05,
"loss": 0.5059,
"step": 1347
},
{
"epoch": 1.51,
"learning_rate": 1.0386858654980214e-05,
"loss": 0.5164,
"step": 1348
},
{
"epoch": 1.51,
"learning_rate": 1.0374775076678331e-05,
"loss": 0.5276,
"step": 1349
},
{
"epoch": 1.51,
"learning_rate": 1.0362690950361882e-05,
"loss": 0.5234,
"step": 1350
},
{
"epoch": 1.51,
"learning_rate": 1.0350606293700879e-05,
"loss": 0.5308,
"step": 1351
},
{
"epoch": 1.51,
"learning_rate": 1.0338521124366087e-05,
"loss": 0.4856,
"step": 1352
},
{
"epoch": 1.51,
"learning_rate": 1.0326435460029051e-05,
"loss": 0.5229,
"step": 1353
},
{
"epoch": 1.52,
"learning_rate": 1.0314349318362015e-05,
"loss": 0.5156,
"step": 1354
},
{
"epoch": 1.52,
"learning_rate": 1.0302262717037932e-05,
"loss": 0.5386,
"step": 1355
},
{
"epoch": 1.52,
"learning_rate": 1.0290175673730426e-05,
"loss": 0.5173,
"step": 1356
},
{
"epoch": 1.52,
"learning_rate": 1.027808820611377e-05,
"loss": 0.5259,
"step": 1357
},
{
"epoch": 1.52,
"learning_rate": 1.0266000331862848e-05,
"loss": 0.5181,
"step": 1358
},
{
"epoch": 1.52,
"learning_rate": 1.0253912068653147e-05,
"loss": 0.5247,
"step": 1359
},
{
"epoch": 1.52,
"learning_rate": 1.0241823434160725e-05,
"loss": 0.5134,
"step": 1360
},
{
"epoch": 1.52,
"learning_rate": 1.0229734446062173e-05,
"loss": 0.4976,
"step": 1361
},
{
"epoch": 1.52,
"learning_rate": 1.0217645122034603e-05,
"loss": 0.5286,
"step": 1362
},
{
"epoch": 1.53,
"learning_rate": 1.0205555479755624e-05,
"loss": 0.5303,
"step": 1363
},
{
"epoch": 1.53,
"learning_rate": 1.0193465536903307e-05,
"loss": 0.5312,
"step": 1364
},
{
"epoch": 1.53,
"learning_rate": 1.0181375311156156e-05,
"loss": 0.5193,
"step": 1365
},
{
"epoch": 1.53,
"learning_rate": 1.01692848201931e-05,
"loss": 0.5259,
"step": 1366
},
{
"epoch": 1.53,
"learning_rate": 1.0157194081693446e-05,
"loss": 0.5449,
"step": 1367
},
{
"epoch": 1.53,
"learning_rate": 1.0145103113336868e-05,
"loss": 0.511,
"step": 1368
},
{
"epoch": 1.53,
"learning_rate": 1.0133011932803378e-05,
"loss": 0.51,
"step": 1369
},
{
"epoch": 1.53,
"learning_rate": 1.0120920557773288e-05,
"loss": 0.519,
"step": 1370
},
{
"epoch": 1.53,
"learning_rate": 1.010882900592721e-05,
"loss": 0.4951,
"step": 1371
},
{
"epoch": 1.54,
"learning_rate": 1.0096737294945999e-05,
"loss": 0.5078,
"step": 1372
},
{
"epoch": 1.54,
"learning_rate": 1.0084645442510759e-05,
"loss": 0.5244,
"step": 1373
},
{
"epoch": 1.54,
"learning_rate": 1.0072553466302783e-05,
"loss": 0.5032,
"step": 1374
},
{
"epoch": 1.54,
"learning_rate": 1.0060461384003559e-05,
"loss": 0.5137,
"step": 1375
},
{
"epoch": 1.54,
"learning_rate": 1.0048369213294725e-05,
"loss": 0.5317,
"step": 1376
},
{
"epoch": 1.54,
"learning_rate": 1.0036276971858043e-05,
"loss": 0.51,
"step": 1377
},
{
"epoch": 1.54,
"learning_rate": 1.0024184677375388e-05,
"loss": 0.5254,
"step": 1378
},
{
"epoch": 1.54,
"learning_rate": 1.0012092347528706e-05,
"loss": 0.5244,
"step": 1379
},
{
"epoch": 1.54,
"learning_rate": 1e-05,
"loss": 0.4954,
"step": 1380
},
{
"epoch": 1.55,
"learning_rate": 9.987907652471298e-06,
"loss": 0.5125,
"step": 1381
},
{
"epoch": 1.55,
"learning_rate": 9.975815322624615e-06,
"loss": 0.5181,
"step": 1382
},
{
"epoch": 1.55,
"learning_rate": 9.963723028141959e-06,
"loss": 0.5115,
"step": 1383
},
{
"epoch": 1.55,
"learning_rate": 9.951630786705279e-06,
"loss": 0.5032,
"step": 1384
},
{
"epoch": 1.55,
"learning_rate": 9.939538615996443e-06,
"loss": 0.5181,
"step": 1385
},
{
"epoch": 1.55,
"learning_rate": 9.927446533697218e-06,
"loss": 0.5115,
"step": 1386
},
{
"epoch": 1.55,
"learning_rate": 9.915354557489241e-06,
"loss": 0.501,
"step": 1387
},
{
"epoch": 1.55,
"learning_rate": 9.903262705054e-06,
"loss": 0.5051,
"step": 1388
},
{
"epoch": 1.55,
"learning_rate": 9.891170994072792e-06,
"loss": 0.5115,
"step": 1389
},
{
"epoch": 1.56,
"learning_rate": 9.879079442226714e-06,
"loss": 0.5037,
"step": 1390
},
{
"epoch": 1.56,
"learning_rate": 9.866988067196627e-06,
"loss": 0.5269,
"step": 1391
},
{
"epoch": 1.56,
"learning_rate": 9.854896886663134e-06,
"loss": 0.5212,
"step": 1392
},
{
"epoch": 1.56,
"learning_rate": 9.842805918306557e-06,
"loss": 0.51,
"step": 1393
},
{
"epoch": 1.56,
"learning_rate": 9.830715179806904e-06,
"loss": 0.5112,
"step": 1394
},
{
"epoch": 1.56,
"learning_rate": 9.818624688843846e-06,
"loss": 0.4939,
"step": 1395
},
{
"epoch": 1.56,
"learning_rate": 9.806534463096698e-06,
"loss": 0.5002,
"step": 1396
},
{
"epoch": 1.56,
"learning_rate": 9.794444520244378e-06,
"loss": 0.5281,
"step": 1397
},
{
"epoch": 1.56,
"learning_rate": 9.7823548779654e-06,
"loss": 0.5249,
"step": 1398
},
{
"epoch": 1.57,
"learning_rate": 9.77026555393783e-06,
"loss": 0.5168,
"step": 1399
},
{
"epoch": 1.57,
"learning_rate": 9.75817656583928e-06,
"loss": 0.5303,
"step": 1400
},
{
"epoch": 1.57,
"learning_rate": 9.746087931346853e-06,
"loss": 0.5193,
"step": 1401
},
{
"epoch": 1.57,
"learning_rate": 9.733999668137155e-06,
"loss": 0.5112,
"step": 1402
},
{
"epoch": 1.57,
"learning_rate": 9.721911793886234e-06,
"loss": 0.5254,
"step": 1403
},
{
"epoch": 1.57,
"learning_rate": 9.709824326269577e-06,
"loss": 0.5183,
"step": 1404
},
{
"epoch": 1.57,
"learning_rate": 9.697737282962073e-06,
"loss": 0.4888,
"step": 1405
},
{
"epoch": 1.57,
"learning_rate": 9.685650681637988e-06,
"loss": 0.5137,
"step": 1406
},
{
"epoch": 1.57,
"learning_rate": 9.67356453997095e-06,
"loss": 0.5171,
"step": 1407
},
{
"epoch": 1.58,
"learning_rate": 9.661478875633915e-06,
"loss": 0.4966,
"step": 1408
},
{
"epoch": 1.58,
"learning_rate": 9.649393706299128e-06,
"loss": 0.5249,
"step": 1409
},
{
"epoch": 1.58,
"learning_rate": 9.637309049638121e-06,
"loss": 0.4941,
"step": 1410
},
{
"epoch": 1.58,
"learning_rate": 9.62522492332167e-06,
"loss": 0.4883,
"step": 1411
},
{
"epoch": 1.58,
"learning_rate": 9.613141345019789e-06,
"loss": 0.5186,
"step": 1412
},
{
"epoch": 1.58,
"learning_rate": 9.601058332401674e-06,
"loss": 0.4722,
"step": 1413
},
{
"epoch": 1.58,
"learning_rate": 9.588975903135701e-06,
"loss": 0.5269,
"step": 1414
},
{
"epoch": 1.58,
"learning_rate": 9.576894074889391e-06,
"loss": 0.5137,
"step": 1415
},
{
"epoch": 1.58,
"learning_rate": 9.564812865329396e-06,
"loss": 0.5322,
"step": 1416
},
{
"epoch": 1.59,
"learning_rate": 9.55273229212145e-06,
"loss": 0.5342,
"step": 1417
},
{
"epoch": 1.59,
"learning_rate": 9.540652372930359e-06,
"loss": 0.4937,
"step": 1418
},
{
"epoch": 1.59,
"learning_rate": 9.52857312541998e-06,
"loss": 0.5059,
"step": 1419
},
{
"epoch": 1.59,
"learning_rate": 9.516494567253179e-06,
"loss": 0.5488,
"step": 1420
},
{
"epoch": 1.59,
"learning_rate": 9.504416716091825e-06,
"loss": 0.5259,
"step": 1421
},
{
"epoch": 1.59,
"learning_rate": 9.492339589596742e-06,
"loss": 0.51,
"step": 1422
},
{
"epoch": 1.59,
"learning_rate": 9.480263205427697e-06,
"loss": 0.5007,
"step": 1423
},
{
"epoch": 1.59,
"learning_rate": 9.468187581243378e-06,
"loss": 0.53,
"step": 1424
},
{
"epoch": 1.59,
"learning_rate": 9.456112734701349e-06,
"loss": 0.4922,
"step": 1425
},
{
"epoch": 1.6,
"learning_rate": 9.444038683458056e-06,
"loss": 0.5242,
"step": 1426
},
{
"epoch": 1.6,
"learning_rate": 9.431965445168763e-06,
"loss": 0.509,
"step": 1427
},
{
"epoch": 1.6,
"learning_rate": 9.41989303748756e-06,
"loss": 0.5083,
"step": 1428
},
{
"epoch": 1.6,
"learning_rate": 9.407821478067305e-06,
"loss": 0.5083,
"step": 1429
},
{
"epoch": 1.6,
"learning_rate": 9.395750784559638e-06,
"loss": 0.521,
"step": 1430
},
{
"epoch": 1.6,
"learning_rate": 9.383680974614915e-06,
"loss": 0.4961,
"step": 1431
},
{
"epoch": 1.6,
"learning_rate": 9.371612065882209e-06,
"loss": 0.5396,
"step": 1432
},
{
"epoch": 1.6,
"learning_rate": 9.35954407600927e-06,
"loss": 0.5027,
"step": 1433
},
{
"epoch": 1.6,
"learning_rate": 9.347477022642504e-06,
"loss": 0.5083,
"step": 1434
},
{
"epoch": 1.61,
"learning_rate": 9.335410923426957e-06,
"loss": 0.5029,
"step": 1435
},
{
"epoch": 1.61,
"learning_rate": 9.32334579600627e-06,
"loss": 0.5161,
"step": 1436
},
{
"epoch": 1.61,
"learning_rate": 9.31128165802267e-06,
"loss": 0.5278,
"step": 1437
},
{
"epoch": 1.61,
"learning_rate": 9.299218527116923e-06,
"loss": 0.5056,
"step": 1438
},
{
"epoch": 1.61,
"learning_rate": 9.287156420928342e-06,
"loss": 0.4934,
"step": 1439
},
{
"epoch": 1.61,
"learning_rate": 9.275095357094732e-06,
"loss": 0.5056,
"step": 1440
},
{
"epoch": 1.61,
"learning_rate": 9.263035353252372e-06,
"loss": 0.5076,
"step": 1441
},
{
"epoch": 1.61,
"learning_rate": 9.250976427035993e-06,
"loss": 0.5039,
"step": 1442
},
{
"epoch": 1.61,
"learning_rate": 9.238918596078747e-06,
"loss": 0.5127,
"step": 1443
},
{
"epoch": 1.62,
"learning_rate": 9.226861878012196e-06,
"loss": 0.5117,
"step": 1444
},
{
"epoch": 1.62,
"learning_rate": 9.214806290466265e-06,
"loss": 0.5127,
"step": 1445
},
{
"epoch": 1.62,
"learning_rate": 9.202751851069219e-06,
"loss": 0.499,
"step": 1446
},
{
"epoch": 1.62,
"learning_rate": 9.190698577447664e-06,
"loss": 0.5227,
"step": 1447
},
{
"epoch": 1.62,
"learning_rate": 9.178646487226478e-06,
"loss": 0.5166,
"step": 1448
},
{
"epoch": 1.62,
"learning_rate": 9.166595598028833e-06,
"loss": 0.5059,
"step": 1449
},
{
"epoch": 1.62,
"learning_rate": 9.154545927476125e-06,
"loss": 0.5032,
"step": 1450
},
{
"epoch": 1.62,
"learning_rate": 9.142497493187975e-06,
"loss": 0.5249,
"step": 1451
},
{
"epoch": 1.63,
"learning_rate": 9.130450312782198e-06,
"loss": 0.5044,
"step": 1452
},
{
"epoch": 1.63,
"learning_rate": 9.118404403874777e-06,
"loss": 0.5139,
"step": 1453
},
{
"epoch": 1.63,
"learning_rate": 9.106359784079832e-06,
"loss": 0.5144,
"step": 1454
},
{
"epoch": 1.63,
"learning_rate": 9.094316471009595e-06,
"loss": 0.4907,
"step": 1455
},
{
"epoch": 1.63,
"learning_rate": 9.082274482274395e-06,
"loss": 0.5051,
"step": 1456
},
{
"epoch": 1.63,
"learning_rate": 9.070233835482617e-06,
"loss": 0.5022,
"step": 1457
},
{
"epoch": 1.63,
"learning_rate": 9.058194548240694e-06,
"loss": 0.4993,
"step": 1458
},
{
"epoch": 1.63,
"learning_rate": 9.046156638153057e-06,
"loss": 0.5244,
"step": 1459
},
{
"epoch": 1.63,
"learning_rate": 9.034120122822136e-06,
"loss": 0.5039,
"step": 1460
},
{
"epoch": 1.64,
"learning_rate": 9.022085019848313e-06,
"loss": 0.5046,
"step": 1461
},
{
"epoch": 1.64,
"learning_rate": 9.010051346829905e-06,
"loss": 0.5029,
"step": 1462
},
{
"epoch": 1.64,
"learning_rate": 8.998019121363148e-06,
"loss": 0.5132,
"step": 1463
},
{
"epoch": 1.64,
"learning_rate": 8.985988361042153e-06,
"loss": 0.5303,
"step": 1464
},
{
"epoch": 1.64,
"learning_rate": 8.97395908345889e-06,
"loss": 0.5032,
"step": 1465
},
{
"epoch": 1.64,
"learning_rate": 8.961931306203154e-06,
"loss": 0.5171,
"step": 1466
},
{
"epoch": 1.64,
"learning_rate": 8.94990504686256e-06,
"loss": 0.5193,
"step": 1467
},
{
"epoch": 1.64,
"learning_rate": 8.937880323022496e-06,
"loss": 0.5334,
"step": 1468
},
{
"epoch": 1.64,
"learning_rate": 8.925857152266103e-06,
"loss": 0.5413,
"step": 1469
},
{
"epoch": 1.65,
"learning_rate": 8.913835552174251e-06,
"loss": 0.512,
"step": 1470
},
{
"epoch": 1.65,
"learning_rate": 8.901815540325517e-06,
"loss": 0.5134,
"step": 1471
},
{
"epoch": 1.65,
"learning_rate": 8.889797134296158e-06,
"loss": 0.5015,
"step": 1472
},
{
"epoch": 1.65,
"learning_rate": 8.877780351660079e-06,
"loss": 0.5195,
"step": 1473
},
{
"epoch": 1.65,
"learning_rate": 8.865765209988802e-06,
"loss": 0.4832,
"step": 1474
},
{
"epoch": 1.65,
"learning_rate": 8.853751726851467e-06,
"loss": 0.5073,
"step": 1475
},
{
"epoch": 1.65,
"learning_rate": 8.841739919814775e-06,
"loss": 0.5325,
"step": 1476
},
{
"epoch": 1.65,
"learning_rate": 8.829729806442987e-06,
"loss": 0.5154,
"step": 1477
},
{
"epoch": 1.65,
"learning_rate": 8.817721404297882e-06,
"loss": 0.5095,
"step": 1478
},
{
"epoch": 1.66,
"learning_rate": 8.805714730938728e-06,
"loss": 0.489,
"step": 1479
},
{
"epoch": 1.66,
"learning_rate": 8.793709803922279e-06,
"loss": 0.499,
"step": 1480
},
{
"epoch": 1.66,
"learning_rate": 8.781706640802734e-06,
"loss": 0.5098,
"step": 1481
},
{
"epoch": 1.66,
"learning_rate": 8.769705259131707e-06,
"loss": 0.531,
"step": 1482
},
{
"epoch": 1.66,
"learning_rate": 8.757705676458207e-06,
"loss": 0.5232,
"step": 1483
},
{
"epoch": 1.66,
"learning_rate": 8.745707910328615e-06,
"loss": 0.5256,
"step": 1484
},
{
"epoch": 1.66,
"learning_rate": 8.733711978286653e-06,
"loss": 0.5237,
"step": 1485
},
{
"epoch": 1.66,
"learning_rate": 8.721717897873369e-06,
"loss": 0.519,
"step": 1486
},
{
"epoch": 1.66,
"learning_rate": 8.709725686627093e-06,
"loss": 0.4944,
"step": 1487
},
{
"epoch": 1.67,
"learning_rate": 8.697735362083428e-06,
"loss": 0.521,
"step": 1488
},
{
"epoch": 1.67,
"learning_rate": 8.685746941775219e-06,
"loss": 0.5107,
"step": 1489
},
{
"epoch": 1.67,
"learning_rate": 8.673760443232518e-06,
"loss": 0.511,
"step": 1490
},
{
"epoch": 1.67,
"learning_rate": 8.661775883982577e-06,
"loss": 0.5161,
"step": 1491
},
{
"epoch": 1.67,
"learning_rate": 8.649793281549812e-06,
"loss": 0.5247,
"step": 1492
},
{
"epoch": 1.67,
"learning_rate": 8.637812653455771e-06,
"loss": 0.5042,
"step": 1493
},
{
"epoch": 1.67,
"learning_rate": 8.625834017219114e-06,
"loss": 0.5029,
"step": 1494
},
{
"epoch": 1.67,
"learning_rate": 8.613857390355598e-06,
"loss": 0.5129,
"step": 1495
},
{
"epoch": 1.67,
"learning_rate": 8.601882790378036e-06,
"loss": 0.5093,
"step": 1496
},
{
"epoch": 1.68,
"learning_rate": 8.589910234796277e-06,
"loss": 0.5144,
"step": 1497
},
{
"epoch": 1.68,
"learning_rate": 8.577939741117179e-06,
"loss": 0.489,
"step": 1498
},
{
"epoch": 1.68,
"learning_rate": 8.565971326844584e-06,
"loss": 0.5232,
"step": 1499
},
{
"epoch": 1.68,
"learning_rate": 8.554005009479307e-06,
"loss": 0.4941,
"step": 1500
},
{
"epoch": 1.68,
"learning_rate": 8.542040806519078e-06,
"loss": 0.5159,
"step": 1501
},
{
"epoch": 1.68,
"learning_rate": 8.530078735458545e-06,
"loss": 0.5149,
"step": 1502
},
{
"epoch": 1.68,
"learning_rate": 8.518118813789238e-06,
"loss": 0.5139,
"step": 1503
},
{
"epoch": 1.68,
"learning_rate": 8.506161058999541e-06,
"loss": 0.5217,
"step": 1504
},
{
"epoch": 1.68,
"learning_rate": 8.494205488574677e-06,
"loss": 0.5198,
"step": 1505
},
{
"epoch": 1.69,
"learning_rate": 8.482252119996666e-06,
"loss": 0.5181,
"step": 1506
},
{
"epoch": 1.69,
"learning_rate": 8.470300970744309e-06,
"loss": 0.5154,
"step": 1507
},
{
"epoch": 1.69,
"learning_rate": 8.458352058293165e-06,
"loss": 0.512,
"step": 1508
},
{
"epoch": 1.69,
"learning_rate": 8.44640540011553e-06,
"loss": 0.4866,
"step": 1509
},
{
"epoch": 1.69,
"learning_rate": 8.434461013680389e-06,
"loss": 0.4905,
"step": 1510
},
{
"epoch": 1.69,
"learning_rate": 8.422518916453411e-06,
"loss": 0.5347,
"step": 1511
},
{
"epoch": 1.69,
"learning_rate": 8.410579125896924e-06,
"loss": 0.5425,
"step": 1512
},
{
"epoch": 1.69,
"learning_rate": 8.398641659469868e-06,
"loss": 0.5195,
"step": 1513
},
{
"epoch": 1.69,
"learning_rate": 8.386706534627805e-06,
"loss": 0.4951,
"step": 1514
},
{
"epoch": 1.7,
"learning_rate": 8.374773768822852e-06,
"loss": 0.4951,
"step": 1515
},
{
"epoch": 1.7,
"learning_rate": 8.362843379503696e-06,
"loss": 0.5183,
"step": 1516
},
{
"epoch": 1.7,
"learning_rate": 8.35091538411553e-06,
"loss": 0.5151,
"step": 1517
},
{
"epoch": 1.7,
"learning_rate": 8.338989800100065e-06,
"loss": 0.4978,
"step": 1518
},
{
"epoch": 1.7,
"learning_rate": 8.327066644895469e-06,
"loss": 0.4937,
"step": 1519
},
{
"epoch": 1.7,
"learning_rate": 8.315145935936374e-06,
"loss": 0.4788,
"step": 1520
},
{
"epoch": 1.7,
"learning_rate": 8.303227690653824e-06,
"loss": 0.498,
"step": 1521
},
{
"epoch": 1.7,
"learning_rate": 8.29131192647526e-06,
"loss": 0.5417,
"step": 1522
},
{
"epoch": 1.7,
"learning_rate": 8.2793986608245e-06,
"loss": 0.5132,
"step": 1523
},
{
"epoch": 1.71,
"learning_rate": 8.267487911121714e-06,
"loss": 0.5188,
"step": 1524
},
{
"epoch": 1.71,
"learning_rate": 8.255579694783385e-06,
"loss": 0.5198,
"step": 1525
},
{
"epoch": 1.71,
"learning_rate": 8.243674029222285e-06,
"loss": 0.4961,
"step": 1526
},
{
"epoch": 1.71,
"learning_rate": 8.231770931847469e-06,
"loss": 0.5032,
"step": 1527
},
{
"epoch": 1.71,
"learning_rate": 8.219870420064235e-06,
"loss": 0.5273,
"step": 1528
},
{
"epoch": 1.71,
"learning_rate": 8.207972511274096e-06,
"loss": 0.519,
"step": 1529
},
{
"epoch": 1.71,
"learning_rate": 8.196077222874755e-06,
"loss": 0.5044,
"step": 1530
},
{
"epoch": 1.71,
"learning_rate": 8.184184572260092e-06,
"loss": 0.4976,
"step": 1531
},
{
"epoch": 1.71,
"learning_rate": 8.172294576820126e-06,
"loss": 0.4976,
"step": 1532
},
{
"epoch": 1.72,
"learning_rate": 8.160407253940996e-06,
"loss": 0.4915,
"step": 1533
},
{
"epoch": 1.72,
"learning_rate": 8.148522621004926e-06,
"loss": 0.5247,
"step": 1534
},
{
"epoch": 1.72,
"learning_rate": 8.136640695390213e-06,
"loss": 0.4922,
"step": 1535
},
{
"epoch": 1.72,
"learning_rate": 8.124761494471191e-06,
"loss": 0.49,
"step": 1536
},
{
"epoch": 1.72,
"learning_rate": 8.112885035618219e-06,
"loss": 0.4951,
"step": 1537
},
{
"epoch": 1.72,
"learning_rate": 8.101011336197635e-06,
"loss": 0.4851,
"step": 1538
},
{
"epoch": 1.72,
"learning_rate": 8.089140413571747e-06,
"loss": 0.5073,
"step": 1539
},
{
"epoch": 1.72,
"learning_rate": 8.077272285098803e-06,
"loss": 0.511,
"step": 1540
},
{
"epoch": 1.72,
"learning_rate": 8.06540696813296e-06,
"loss": 0.5166,
"step": 1541
},
{
"epoch": 1.73,
"learning_rate": 8.05354448002428e-06,
"loss": 0.4905,
"step": 1542
},
{
"epoch": 1.73,
"learning_rate": 8.041684838118665e-06,
"loss": 0.5085,
"step": 1543
},
{
"epoch": 1.73,
"learning_rate": 8.029828059757875e-06,
"loss": 0.5098,
"step": 1544
},
{
"epoch": 1.73,
"learning_rate": 8.017974162279469e-06,
"loss": 0.4919,
"step": 1545
},
{
"epoch": 1.73,
"learning_rate": 8.006123163016804e-06,
"loss": 0.4985,
"step": 1546
},
{
"epoch": 1.73,
"learning_rate": 7.994275079298993e-06,
"loss": 0.5176,
"step": 1547
},
{
"epoch": 1.73,
"learning_rate": 7.982429928450888e-06,
"loss": 0.5134,
"step": 1548
},
{
"epoch": 1.73,
"learning_rate": 7.97058772779305e-06,
"loss": 0.4932,
"step": 1549
},
{
"epoch": 1.73,
"learning_rate": 7.958748494641725e-06,
"loss": 0.4893,
"step": 1550
},
{
"epoch": 1.74,
"learning_rate": 7.94691224630883e-06,
"loss": 0.5291,
"step": 1551
},
{
"epoch": 1.74,
"learning_rate": 7.935079000101907e-06,
"loss": 0.5063,
"step": 1552
},
{
"epoch": 1.74,
"learning_rate": 7.923248773324107e-06,
"loss": 0.5017,
"step": 1553
},
{
"epoch": 1.74,
"learning_rate": 7.91142158327417e-06,
"loss": 0.5288,
"step": 1554
},
{
"epoch": 1.74,
"learning_rate": 7.899597447246401e-06,
"loss": 0.4973,
"step": 1555
},
{
"epoch": 1.74,
"learning_rate": 7.887776382530632e-06,
"loss": 0.5044,
"step": 1556
},
{
"epoch": 1.74,
"learning_rate": 7.875958406412206e-06,
"loss": 0.4934,
"step": 1557
},
{
"epoch": 1.74,
"learning_rate": 7.864143536171944e-06,
"loss": 0.499,
"step": 1558
},
{
"epoch": 1.74,
"learning_rate": 7.852331789086135e-06,
"loss": 0.501,
"step": 1559
},
{
"epoch": 1.75,
"learning_rate": 7.840523182426497e-06,
"loss": 0.5327,
"step": 1560
},
{
"epoch": 1.75,
"learning_rate": 7.828717733460159e-06,
"loss": 0.5149,
"step": 1561
},
{
"epoch": 1.75,
"learning_rate": 7.816915459449624e-06,
"loss": 0.5139,
"step": 1562
},
{
"epoch": 1.75,
"learning_rate": 7.80511637765276e-06,
"loss": 0.5317,
"step": 1563
},
{
"epoch": 1.75,
"learning_rate": 7.793320505322762e-06,
"loss": 0.5066,
"step": 1564
},
{
"epoch": 1.75,
"learning_rate": 7.781527859708142e-06,
"loss": 0.5076,
"step": 1565
},
{
"epoch": 1.75,
"learning_rate": 7.769738458052685e-06,
"loss": 0.4885,
"step": 1566
},
{
"epoch": 1.75,
"learning_rate": 7.75795231759543e-06,
"loss": 0.4951,
"step": 1567
},
{
"epoch": 1.75,
"learning_rate": 7.746169455570654e-06,
"loss": 0.5359,
"step": 1568
},
{
"epoch": 1.76,
"learning_rate": 7.73438988920784e-06,
"loss": 0.4963,
"step": 1569
},
{
"epoch": 1.76,
"learning_rate": 7.72261363573165e-06,
"loss": 0.5022,
"step": 1570
},
{
"epoch": 1.76,
"learning_rate": 7.710840712361895e-06,
"loss": 0.5015,
"step": 1571
},
{
"epoch": 1.76,
"learning_rate": 7.699071136313532e-06,
"loss": 0.4985,
"step": 1572
},
{
"epoch": 1.76,
"learning_rate": 7.687304924796605e-06,
"loss": 0.4722,
"step": 1573
},
{
"epoch": 1.76,
"learning_rate": 7.675542095016257e-06,
"loss": 0.5063,
"step": 1574
},
{
"epoch": 1.76,
"learning_rate": 7.663782664172671e-06,
"loss": 0.4832,
"step": 1575
},
{
"epoch": 1.76,
"learning_rate": 7.652026649461069e-06,
"loss": 0.5273,
"step": 1576
},
{
"epoch": 1.76,
"learning_rate": 7.64027406807167e-06,
"loss": 0.5193,
"step": 1577
},
{
"epoch": 1.77,
"learning_rate": 7.628524937189678e-06,
"loss": 0.4912,
"step": 1578
},
{
"epoch": 1.77,
"learning_rate": 7.616779273995252e-06,
"loss": 0.5015,
"step": 1579
},
{
"epoch": 1.77,
"learning_rate": 7.605037095663481e-06,
"loss": 0.4941,
"step": 1580
},
{
"epoch": 1.77,
"learning_rate": 7.593298419364355e-06,
"loss": 0.4841,
"step": 1581
},
{
"epoch": 1.77,
"learning_rate": 7.581563262262738e-06,
"loss": 0.5022,
"step": 1582
},
{
"epoch": 1.77,
"learning_rate": 7.569831641518361e-06,
"loss": 0.5029,
"step": 1583
},
{
"epoch": 1.77,
"learning_rate": 7.558103574285779e-06,
"loss": 0.5049,
"step": 1584
},
{
"epoch": 1.77,
"learning_rate": 7.546379077714345e-06,
"loss": 0.5134,
"step": 1585
},
{
"epoch": 1.78,
"learning_rate": 7.534658168948195e-06,
"loss": 0.5063,
"step": 1586
},
{
"epoch": 1.78,
"learning_rate": 7.522940865126218e-06,
"loss": 0.5066,
"step": 1587
},
{
"epoch": 1.78,
"learning_rate": 7.511227183382035e-06,
"loss": 0.5291,
"step": 1588
},
{
"epoch": 1.78,
"learning_rate": 7.499517140843969e-06,
"loss": 0.5027,
"step": 1589
},
{
"epoch": 1.78,
"learning_rate": 7.4878107546350184e-06,
"loss": 0.5115,
"step": 1590
},
{
"epoch": 1.78,
"learning_rate": 7.476108041872836e-06,
"loss": 0.5132,
"step": 1591
},
{
"epoch": 1.78,
"learning_rate": 7.464409019669705e-06,
"loss": 0.5,
"step": 1592
},
{
"epoch": 1.78,
"learning_rate": 7.452713705132515e-06,
"loss": 0.5173,
"step": 1593
},
{
"epoch": 1.78,
"learning_rate": 7.441022115362729e-06,
"loss": 0.5134,
"step": 1594
},
{
"epoch": 1.79,
"learning_rate": 7.42933426745636e-06,
"loss": 0.5017,
"step": 1595
},
{
"epoch": 1.79,
"learning_rate": 7.417650178503959e-06,
"loss": 0.4944,
"step": 1596
},
{
"epoch": 1.79,
"learning_rate": 7.4059698655905795e-06,
"loss": 0.5139,
"step": 1597
},
{
"epoch": 1.79,
"learning_rate": 7.394293345795746e-06,
"loss": 0.5317,
"step": 1598
},
{
"epoch": 1.79,
"learning_rate": 7.382620636193438e-06,
"loss": 0.4995,
"step": 1599
},
{
"epoch": 1.79,
"learning_rate": 7.370951753852071e-06,
"loss": 0.5007,
"step": 1600
},
{
"epoch": 1.79,
"learning_rate": 7.359286715834453e-06,
"loss": 0.5081,
"step": 1601
},
{
"epoch": 1.79,
"learning_rate": 7.347625539197785e-06,
"loss": 0.532,
"step": 1602
},
{
"epoch": 1.79,
"learning_rate": 7.335968240993605e-06,
"loss": 0.5015,
"step": 1603
},
{
"epoch": 1.8,
"learning_rate": 7.324314838267796e-06,
"loss": 0.5171,
"step": 1604
},
{
"epoch": 1.8,
"learning_rate": 7.312665348060533e-06,
"loss": 0.5229,
"step": 1605
},
{
"epoch": 1.8,
"learning_rate": 7.301019787406269e-06,
"loss": 0.5083,
"step": 1606
},
{
"epoch": 1.8,
"learning_rate": 7.2893781733337254e-06,
"loss": 0.5032,
"step": 1607
},
{
"epoch": 1.8,
"learning_rate": 7.2777405228658405e-06,
"loss": 0.5244,
"step": 1608
},
{
"epoch": 1.8,
"learning_rate": 7.266106853019759e-06,
"loss": 0.5044,
"step": 1609
},
{
"epoch": 1.8,
"learning_rate": 7.2544771808067984e-06,
"loss": 0.5007,
"step": 1610
},
{
"epoch": 1.8,
"learning_rate": 7.242851523232448e-06,
"loss": 0.5,
"step": 1611
},
{
"epoch": 1.8,
"learning_rate": 7.231229897296316e-06,
"loss": 0.5137,
"step": 1612
},
{
"epoch": 1.81,
"learning_rate": 7.219612319992112e-06,
"loss": 0.489,
"step": 1613
},
{
"epoch": 1.81,
"learning_rate": 7.207998808307628e-06,
"loss": 0.5156,
"step": 1614
},
{
"epoch": 1.81,
"learning_rate": 7.196389379224715e-06,
"loss": 0.5107,
"step": 1615
},
{
"epoch": 1.81,
"learning_rate": 7.1847840497192515e-06,
"loss": 0.5239,
"step": 1616
},
{
"epoch": 1.81,
"learning_rate": 7.173182836761121e-06,
"loss": 0.4849,
"step": 1617
},
{
"epoch": 1.81,
"learning_rate": 7.161585757314191e-06,
"loss": 0.4927,
"step": 1618
},
{
"epoch": 1.81,
"learning_rate": 7.149992828336274e-06,
"loss": 0.5073,
"step": 1619
},
{
"epoch": 1.81,
"learning_rate": 7.13840406677913e-06,
"loss": 0.5278,
"step": 1620
},
{
"epoch": 1.81,
"learning_rate": 7.126819489588414e-06,
"loss": 0.5151,
"step": 1621
},
{
"epoch": 1.82,
"learning_rate": 7.115239113703666e-06,
"loss": 0.5381,
"step": 1622
},
{
"epoch": 1.82,
"learning_rate": 7.103662956058277e-06,
"loss": 0.4873,
"step": 1623
},
{
"epoch": 1.82,
"learning_rate": 7.092091033579475e-06,
"loss": 0.5061,
"step": 1624
},
{
"epoch": 1.82,
"learning_rate": 7.080523363188301e-06,
"loss": 0.4946,
"step": 1625
},
{
"epoch": 1.82,
"learning_rate": 7.068959961799569e-06,
"loss": 0.4961,
"step": 1626
},
{
"epoch": 1.82,
"learning_rate": 7.057400846321849e-06,
"loss": 0.5542,
"step": 1627
},
{
"epoch": 1.82,
"learning_rate": 7.045846033657456e-06,
"loss": 0.499,
"step": 1628
},
{
"epoch": 1.82,
"learning_rate": 7.034295540702398e-06,
"loss": 0.5122,
"step": 1629
},
{
"epoch": 1.82,
"learning_rate": 7.022749384346383e-06,
"loss": 0.4998,
"step": 1630
},
{
"epoch": 1.83,
"learning_rate": 7.011207581472762e-06,
"loss": 0.5349,
"step": 1631
},
{
"epoch": 1.83,
"learning_rate": 6.999670148958533e-06,
"loss": 0.4856,
"step": 1632
},
{
"epoch": 1.83,
"learning_rate": 6.988137103674289e-06,
"loss": 0.4888,
"step": 1633
},
{
"epoch": 1.83,
"learning_rate": 6.9766084624842265e-06,
"loss": 0.498,
"step": 1634
},
{
"epoch": 1.83,
"learning_rate": 6.9650842422460875e-06,
"loss": 0.4968,
"step": 1635
},
{
"epoch": 1.83,
"learning_rate": 6.953564459811155e-06,
"loss": 0.4905,
"step": 1636
},
{
"epoch": 1.83,
"learning_rate": 6.9420491320242215e-06,
"loss": 0.5012,
"step": 1637
},
{
"epoch": 1.83,
"learning_rate": 6.930538275723562e-06,
"loss": 0.4934,
"step": 1638
},
{
"epoch": 1.83,
"learning_rate": 6.9190319077409226e-06,
"loss": 0.5044,
"step": 1639
},
{
"epoch": 1.84,
"learning_rate": 6.9075300449014816e-06,
"loss": 0.5168,
"step": 1640
},
{
"epoch": 1.84,
"learning_rate": 6.896032704023828e-06,
"loss": 0.51,
"step": 1641
},
{
"epoch": 1.84,
"learning_rate": 6.884539901919934e-06,
"loss": 0.5115,
"step": 1642
},
{
"epoch": 1.84,
"learning_rate": 6.873051655395147e-06,
"loss": 0.5183,
"step": 1643
},
{
"epoch": 1.84,
"learning_rate": 6.861567981248143e-06,
"loss": 0.5002,
"step": 1644
},
{
"epoch": 1.84,
"learning_rate": 6.85008889627092e-06,
"loss": 0.4866,
"step": 1645
},
{
"epoch": 1.84,
"learning_rate": 6.838614417248758e-06,
"loss": 0.4927,
"step": 1646
},
{
"epoch": 1.84,
"learning_rate": 6.827144560960201e-06,
"loss": 0.5212,
"step": 1647
},
{
"epoch": 1.84,
"learning_rate": 6.815679344177042e-06,
"loss": 0.5217,
"step": 1648
},
{
"epoch": 1.85,
"learning_rate": 6.804218783664289e-06,
"loss": 0.4985,
"step": 1649
},
{
"epoch": 1.85,
"learning_rate": 6.792762896180133e-06,
"loss": 0.5161,
"step": 1650
},
{
"epoch": 1.85,
"learning_rate": 6.781311698475934e-06,
"loss": 0.4954,
"step": 1651
},
{
"epoch": 1.85,
"learning_rate": 6.7698652072962005e-06,
"loss": 0.4844,
"step": 1652
},
{
"epoch": 1.85,
"learning_rate": 6.758423439378556e-06,
"loss": 0.4993,
"step": 1653
},
{
"epoch": 1.85,
"learning_rate": 6.746986411453717e-06,
"loss": 0.5054,
"step": 1654
},
{
"epoch": 1.85,
"learning_rate": 6.735554140245466e-06,
"loss": 0.5354,
"step": 1655
},
{
"epoch": 1.85,
"learning_rate": 6.7241266424706365e-06,
"loss": 0.5095,
"step": 1656
},
{
"epoch": 1.85,
"learning_rate": 6.71270393483907e-06,
"loss": 0.4888,
"step": 1657
},
{
"epoch": 1.86,
"learning_rate": 6.701286034053622e-06,
"loss": 0.5115,
"step": 1658
},
{
"epoch": 1.86,
"learning_rate": 6.689872956810103e-06,
"loss": 0.5186,
"step": 1659
},
{
"epoch": 1.86,
"learning_rate": 6.678464719797279e-06,
"loss": 0.5122,
"step": 1660
},
{
"epoch": 1.86,
"learning_rate": 6.667061339696832e-06,
"loss": 0.49,
"step": 1661
},
{
"epoch": 1.86,
"learning_rate": 6.655662833183352e-06,
"loss": 0.5039,
"step": 1662
},
{
"epoch": 1.86,
"learning_rate": 6.644269216924289e-06,
"loss": 0.4927,
"step": 1663
},
{
"epoch": 1.86,
"learning_rate": 6.632880507579958e-06,
"loss": 0.4841,
"step": 1664
},
{
"epoch": 1.86,
"learning_rate": 6.621496721803482e-06,
"loss": 0.48,
"step": 1665
},
{
"epoch": 1.86,
"learning_rate": 6.610117876240795e-06,
"loss": 0.5142,
"step": 1666
},
{
"epoch": 1.87,
"learning_rate": 6.598743987530607e-06,
"loss": 0.4983,
"step": 1667
},
{
"epoch": 1.87,
"learning_rate": 6.5873750723043805e-06,
"loss": 0.5103,
"step": 1668
},
{
"epoch": 1.87,
"learning_rate": 6.5760111471863e-06,
"loss": 0.4895,
"step": 1669
},
{
"epoch": 1.87,
"learning_rate": 6.564652228793251e-06,
"loss": 0.4905,
"step": 1670
},
{
"epoch": 1.87,
"learning_rate": 6.553298333734812e-06,
"loss": 0.4805,
"step": 1671
},
{
"epoch": 1.87,
"learning_rate": 6.541949478613202e-06,
"loss": 0.5012,
"step": 1672
},
{
"epoch": 1.87,
"learning_rate": 6.530605680023279e-06,
"loss": 0.4895,
"step": 1673
},
{
"epoch": 1.87,
"learning_rate": 6.519266954552501e-06,
"loss": 0.5112,
"step": 1674
},
{
"epoch": 1.87,
"learning_rate": 6.507933318780907e-06,
"loss": 0.5017,
"step": 1675
},
{
"epoch": 1.88,
"learning_rate": 6.496604789281102e-06,
"loss": 0.4978,
"step": 1676
},
{
"epoch": 1.88,
"learning_rate": 6.485281382618222e-06,
"loss": 0.5183,
"step": 1677
},
{
"epoch": 1.88,
"learning_rate": 6.473963115349906e-06,
"loss": 0.4958,
"step": 1678
},
{
"epoch": 1.88,
"learning_rate": 6.46265000402628e-06,
"loss": 0.4773,
"step": 1679
},
{
"epoch": 1.88,
"learning_rate": 6.451342065189932e-06,
"loss": 0.4834,
"step": 1680
},
{
"epoch": 1.88,
"learning_rate": 6.440039315375893e-06,
"loss": 0.4827,
"step": 1681
},
{
"epoch": 1.88,
"learning_rate": 6.428741771111593e-06,
"loss": 0.5098,
"step": 1682
},
{
"epoch": 1.88,
"learning_rate": 6.41744944891686e-06,
"loss": 0.4885,
"step": 1683
},
{
"epoch": 1.88,
"learning_rate": 6.406162365303882e-06,
"loss": 0.5051,
"step": 1684
},
{
"epoch": 1.89,
"learning_rate": 6.394880536777193e-06,
"loss": 0.4939,
"step": 1685
},
{
"epoch": 1.89,
"learning_rate": 6.383603979833635e-06,
"loss": 0.4973,
"step": 1686
},
{
"epoch": 1.89,
"learning_rate": 6.3723327109623415e-06,
"loss": 0.5037,
"step": 1687
},
{
"epoch": 1.89,
"learning_rate": 6.361066746644722e-06,
"loss": 0.511,
"step": 1688
},
{
"epoch": 1.89,
"learning_rate": 6.349806103354417e-06,
"loss": 0.5212,
"step": 1689
},
{
"epoch": 1.89,
"learning_rate": 6.338550797557303e-06,
"loss": 0.4924,
"step": 1690
},
{
"epoch": 1.89,
"learning_rate": 6.327300845711434e-06,
"loss": 0.5137,
"step": 1691
},
{
"epoch": 1.89,
"learning_rate": 6.316056264267048e-06,
"loss": 0.4871,
"step": 1692
},
{
"epoch": 1.89,
"learning_rate": 6.3048170696665245e-06,
"loss": 0.4761,
"step": 1693
},
{
"epoch": 1.9,
"learning_rate": 6.293583278344362e-06,
"loss": 0.4907,
"step": 1694
},
{
"epoch": 1.9,
"learning_rate": 6.282354906727171e-06,
"loss": 0.468,
"step": 1695
},
{
"epoch": 1.9,
"learning_rate": 6.271131971233626e-06,
"loss": 0.4907,
"step": 1696
},
{
"epoch": 1.9,
"learning_rate": 6.259914488274455e-06,
"loss": 0.5078,
"step": 1697
},
{
"epoch": 1.9,
"learning_rate": 6.24870247425241e-06,
"loss": 0.5293,
"step": 1698
},
{
"epoch": 1.9,
"learning_rate": 6.23749594556226e-06,
"loss": 0.5112,
"step": 1699
},
{
"epoch": 1.9,
"learning_rate": 6.226294918590733e-06,
"loss": 0.5142,
"step": 1700
},
{
"epoch": 1.9,
"learning_rate": 6.215099409716527e-06,
"loss": 0.519,
"step": 1701
},
{
"epoch": 1.9,
"learning_rate": 6.203909435310267e-06,
"loss": 0.5139,
"step": 1702
},
{
"epoch": 1.91,
"learning_rate": 6.192725011734477e-06,
"loss": 0.4956,
"step": 1703
},
{
"epoch": 1.91,
"learning_rate": 6.1815461553435784e-06,
"loss": 0.4968,
"step": 1704
},
{
"epoch": 1.91,
"learning_rate": 6.170372882483847e-06,
"loss": 0.5061,
"step": 1705
},
{
"epoch": 1.91,
"learning_rate": 6.159205209493388e-06,
"loss": 0.5054,
"step": 1706
},
{
"epoch": 1.91,
"learning_rate": 6.1480431527021235e-06,
"loss": 0.4895,
"step": 1707
},
{
"epoch": 1.91,
"learning_rate": 6.136886728431759e-06,
"loss": 0.4634,
"step": 1708
},
{
"epoch": 1.91,
"learning_rate": 6.125735952995775e-06,
"loss": 0.479,
"step": 1709
},
{
"epoch": 1.91,
"learning_rate": 6.114590842699379e-06,
"loss": 0.4822,
"step": 1710
},
{
"epoch": 1.91,
"learning_rate": 6.103451413839499e-06,
"loss": 0.5217,
"step": 1711
},
{
"epoch": 1.92,
"learning_rate": 6.092317682704757e-06,
"loss": 0.4985,
"step": 1712
},
{
"epoch": 1.92,
"learning_rate": 6.081189665575447e-06,
"loss": 0.5054,
"step": 1713
},
{
"epoch": 1.92,
"learning_rate": 6.0700673787235006e-06,
"loss": 0.5127,
"step": 1714
},
{
"epoch": 1.92,
"learning_rate": 6.058950838412469e-06,
"loss": 0.5371,
"step": 1715
},
{
"epoch": 1.92,
"learning_rate": 6.047840060897512e-06,
"loss": 0.5188,
"step": 1716
},
{
"epoch": 1.92,
"learning_rate": 6.036735062425347e-06,
"loss": 0.4788,
"step": 1717
},
{
"epoch": 1.92,
"learning_rate": 6.025635859234258e-06,
"loss": 0.5034,
"step": 1718
},
{
"epoch": 1.92,
"learning_rate": 6.01454246755404e-06,
"loss": 0.5095,
"step": 1719
},
{
"epoch": 1.93,
"learning_rate": 6.003454903606001e-06,
"loss": 0.5061,
"step": 1720
},
{
"epoch": 1.93,
"learning_rate": 5.992373183602915e-06,
"loss": 0.4895,
"step": 1721
},
{
"epoch": 1.93,
"learning_rate": 5.981297323749028e-06,
"loss": 0.4937,
"step": 1722
},
{
"epoch": 1.93,
"learning_rate": 5.970227340240002e-06,
"loss": 0.498,
"step": 1723
},
{
"epoch": 1.93,
"learning_rate": 5.9591632492629136e-06,
"loss": 0.4934,
"step": 1724
},
{
"epoch": 1.93,
"learning_rate": 5.948105066996221e-06,
"loss": 0.4951,
"step": 1725
},
{
"epoch": 1.93,
"learning_rate": 5.937052809609741e-06,
"loss": 0.5242,
"step": 1726
},
{
"epoch": 1.93,
"learning_rate": 5.92600649326463e-06,
"loss": 0.5002,
"step": 1727
},
{
"epoch": 1.93,
"learning_rate": 5.914966134113354e-06,
"loss": 0.5134,
"step": 1728
},
{
"epoch": 1.94,
"learning_rate": 5.903931748299674e-06,
"loss": 0.5007,
"step": 1729
},
{
"epoch": 1.94,
"learning_rate": 5.892903351958607e-06,
"loss": 0.5054,
"step": 1730
},
{
"epoch": 1.94,
"learning_rate": 5.8818809612164155e-06,
"loss": 0.4983,
"step": 1731
},
{
"epoch": 1.94,
"learning_rate": 5.870864592190586e-06,
"loss": 0.5168,
"step": 1732
},
{
"epoch": 1.94,
"learning_rate": 5.859854260989797e-06,
"loss": 0.5071,
"step": 1733
},
{
"epoch": 1.94,
"learning_rate": 5.848849983713894e-06,
"loss": 0.4812,
"step": 1734
},
{
"epoch": 1.94,
"learning_rate": 5.83785177645387e-06,
"loss": 0.522,
"step": 1735
},
{
"epoch": 1.94,
"learning_rate": 5.826859655291852e-06,
"loss": 0.5068,
"step": 1736
},
{
"epoch": 1.94,
"learning_rate": 5.815873636301053e-06,
"loss": 0.4758,
"step": 1737
},
{
"epoch": 1.95,
"learning_rate": 5.804893735545777e-06,
"loss": 0.4963,
"step": 1738
},
{
"epoch": 1.95,
"learning_rate": 5.793919969081374e-06,
"loss": 0.4988,
"step": 1739
},
{
"epoch": 1.95,
"learning_rate": 5.7829523529542185e-06,
"loss": 0.4954,
"step": 1740
},
{
"epoch": 1.95,
"learning_rate": 5.77199090320171e-06,
"loss": 0.4941,
"step": 1741
},
{
"epoch": 1.95,
"learning_rate": 5.7610356358522144e-06,
"loss": 0.5029,
"step": 1742
},
{
"epoch": 1.95,
"learning_rate": 5.7500865669250625e-06,
"loss": 0.4985,
"step": 1743
},
{
"epoch": 1.95,
"learning_rate": 5.7391437124305214e-06,
"loss": 0.4919,
"step": 1744
},
{
"epoch": 1.95,
"learning_rate": 5.72820708836977e-06,
"loss": 0.5129,
"step": 1745
},
{
"epoch": 1.95,
"learning_rate": 5.717276710734879e-06,
"loss": 0.4951,
"step": 1746
},
{
"epoch": 1.96,
"learning_rate": 5.706352595508791e-06,
"loss": 0.4932,
"step": 1747
},
{
"epoch": 1.96,
"learning_rate": 5.695434758665279e-06,
"loss": 0.5164,
"step": 1748
},
{
"epoch": 1.96,
"learning_rate": 5.68452321616894e-06,
"loss": 0.502,
"step": 1749
},
{
"epoch": 1.96,
"learning_rate": 5.6736179839751745e-06,
"loss": 0.4998,
"step": 1750
},
{
"epoch": 1.96,
"learning_rate": 5.662719078030146e-06,
"loss": 0.5083,
"step": 1751
},
{
"epoch": 1.96,
"learning_rate": 5.651826514270773e-06,
"loss": 0.5149,
"step": 1752
},
{
"epoch": 1.96,
"learning_rate": 5.640940308624692e-06,
"loss": 0.4761,
"step": 1753
},
{
"epoch": 1.96,
"learning_rate": 5.630060477010253e-06,
"loss": 0.4897,
"step": 1754
},
{
"epoch": 1.96,
"learning_rate": 5.619187035336486e-06,
"loss": 0.5137,
"step": 1755
},
{
"epoch": 1.97,
"learning_rate": 5.608319999503071e-06,
"loss": 0.4998,
"step": 1756
},
{
"epoch": 1.97,
"learning_rate": 5.597459385400319e-06,
"loss": 0.4951,
"step": 1757
},
{
"epoch": 1.97,
"learning_rate": 5.586605208909155e-06,
"loss": 0.4954,
"step": 1758
},
{
"epoch": 1.97,
"learning_rate": 5.575757485901089e-06,
"loss": 0.4944,
"step": 1759
},
{
"epoch": 1.97,
"learning_rate": 5.5649162322382e-06,
"loss": 0.5034,
"step": 1760
},
{
"epoch": 1.97,
"learning_rate": 5.554081463773098e-06,
"loss": 0.4819,
"step": 1761
},
{
"epoch": 1.97,
"learning_rate": 5.543253196348919e-06,
"loss": 0.4744,
"step": 1762
},
{
"epoch": 1.97,
"learning_rate": 5.532431445799284e-06,
"loss": 0.4919,
"step": 1763
},
{
"epoch": 1.97,
"learning_rate": 5.521616227948297e-06,
"loss": 0.5022,
"step": 1764
},
{
"epoch": 1.98,
"learning_rate": 5.510807558610495e-06,
"loss": 0.4675,
"step": 1765
},
{
"epoch": 1.98,
"learning_rate": 5.500005453590849e-06,
"loss": 0.4861,
"step": 1766
},
{
"epoch": 1.98,
"learning_rate": 5.489209928684728e-06,
"loss": 0.5044,
"step": 1767
},
{
"epoch": 1.98,
"learning_rate": 5.478420999677876e-06,
"loss": 0.4968,
"step": 1768
},
{
"epoch": 1.98,
"learning_rate": 5.467638682346404e-06,
"loss": 0.5098,
"step": 1769
},
{
"epoch": 1.98,
"learning_rate": 5.456862992456738e-06,
"loss": 0.5134,
"step": 1770
},
{
"epoch": 1.98,
"learning_rate": 5.446093945765631e-06,
"loss": 0.4927,
"step": 1771
},
{
"epoch": 1.98,
"learning_rate": 5.435331558020109e-06,
"loss": 0.481,
"step": 1772
},
{
"epoch": 1.98,
"learning_rate": 5.424575844957463e-06,
"loss": 0.5112,
"step": 1773
},
{
"epoch": 1.99,
"learning_rate": 5.413826822305232e-06,
"loss": 0.4873,
"step": 1774
},
{
"epoch": 1.99,
"learning_rate": 5.403084505781162e-06,
"loss": 0.4963,
"step": 1775
},
{
"epoch": 1.99,
"learning_rate": 5.392348911093198e-06,
"loss": 0.5061,
"step": 1776
},
{
"epoch": 1.99,
"learning_rate": 5.38162005393945e-06,
"loss": 0.4812,
"step": 1777
},
{
"epoch": 1.99,
"learning_rate": 5.370897950008186e-06,
"loss": 0.4971,
"step": 1778
},
{
"epoch": 1.99,
"learning_rate": 5.360182614977797e-06,
"loss": 0.4817,
"step": 1779
},
{
"epoch": 1.99,
"learning_rate": 5.349474064516771e-06,
"loss": 0.5044,
"step": 1780
},
{
"epoch": 1.99,
"learning_rate": 5.3387723142836745e-06,
"loss": 0.4753,
"step": 1781
},
{
"epoch": 1.99,
"learning_rate": 5.328077379927133e-06,
"loss": 0.4731,
"step": 1782
},
{
"epoch": 2.0,
"learning_rate": 5.317389277085811e-06,
"loss": 0.4973,
"step": 1783
},
{
"epoch": 2.0,
"learning_rate": 5.306708021388378e-06,
"loss": 0.5012,
"step": 1784
},
{
"epoch": 2.0,
"learning_rate": 5.296033628453484e-06,
"loss": 0.5122,
"step": 1785
},
{
"epoch": 2.0,
"learning_rate": 5.285366113889759e-06,
"loss": 0.481,
"step": 1786
},
{
"epoch": 2.0,
"learning_rate": 5.274705493295769e-06,
"loss": 0.4971,
"step": 1787
},
{
"epoch": 2.0,
"learning_rate": 5.264051782259996e-06,
"loss": 0.3633,
"step": 1788
},
{
"epoch": 2.0,
"learning_rate": 5.25340499636082e-06,
"loss": 0.3528,
"step": 1789
},
{
"epoch": 2.0,
"learning_rate": 5.2427651511664965e-06,
"loss": 0.3604,
"step": 1790
},
{
"epoch": 2.0,
"learning_rate": 5.232132262235126e-06,
"loss": 0.3506,
"step": 1791
},
{
"epoch": 2.01,
"learning_rate": 5.22150634511465e-06,
"loss": 0.3479,
"step": 1792
},
{
"epoch": 2.01,
"learning_rate": 5.2108874153427995e-06,
"loss": 0.3552,
"step": 1793
},
{
"epoch": 2.01,
"learning_rate": 5.200275488447104e-06,
"loss": 0.3589,
"step": 1794
},
{
"epoch": 2.01,
"learning_rate": 5.189670579944841e-06,
"loss": 0.3538,
"step": 1795
},
{
"epoch": 2.01,
"learning_rate": 5.179072705343029e-06,
"loss": 0.3657,
"step": 1796
},
{
"epoch": 2.01,
"learning_rate": 5.168481880138405e-06,
"loss": 0.333,
"step": 1797
},
{
"epoch": 2.01,
"learning_rate": 5.157898119817395e-06,
"loss": 0.3557,
"step": 1798
},
{
"epoch": 2.01,
"learning_rate": 5.147321439856091e-06,
"loss": 0.3491,
"step": 1799
},
{
"epoch": 2.01,
"learning_rate": 5.136751855720235e-06,
"loss": 0.3418,
"step": 1800
},
{
"epoch": 2.02,
"learning_rate": 5.126189382865197e-06,
"loss": 0.3301,
"step": 1801
},
{
"epoch": 2.02,
"learning_rate": 5.115634036735938e-06,
"loss": 0.3459,
"step": 1802
},
{
"epoch": 2.02,
"learning_rate": 5.105085832767014e-06,
"loss": 0.3542,
"step": 1803
},
{
"epoch": 2.02,
"learning_rate": 5.094544786382522e-06,
"loss": 0.3428,
"step": 1804
},
{
"epoch": 2.02,
"learning_rate": 5.0840109129960995e-06,
"loss": 0.3552,
"step": 1805
},
{
"epoch": 2.02,
"learning_rate": 5.073484228010897e-06,
"loss": 0.3367,
"step": 1806
},
{
"epoch": 2.02,
"learning_rate": 5.0629647468195496e-06,
"loss": 0.3394,
"step": 1807
},
{
"epoch": 2.02,
"learning_rate": 5.05245248480416e-06,
"loss": 0.3479,
"step": 1808
},
{
"epoch": 2.02,
"learning_rate": 5.041947457336273e-06,
"loss": 0.3467,
"step": 1809
},
{
"epoch": 2.03,
"learning_rate": 5.03144967977686e-06,
"loss": 0.3433,
"step": 1810
},
{
"epoch": 2.03,
"learning_rate": 5.020959167476291e-06,
"loss": 0.3547,
"step": 1811
},
{
"epoch": 2.03,
"learning_rate": 5.010475935774306e-06,
"loss": 0.3594,
"step": 1812
},
{
"epoch": 2.03,
"learning_rate": 5.000000000000003e-06,
"loss": 0.3218,
"step": 1813
},
{
"epoch": 2.03,
"learning_rate": 4.989531375471805e-06,
"loss": 0.3416,
"step": 1814
},
{
"epoch": 2.03,
"learning_rate": 4.979070077497461e-06,
"loss": 0.3518,
"step": 1815
},
{
"epoch": 2.03,
"learning_rate": 4.96861612137399e-06,
"loss": 0.345,
"step": 1816
},
{
"epoch": 2.03,
"learning_rate": 4.958169522387678e-06,
"loss": 0.3342,
"step": 1817
},
{
"epoch": 2.03,
"learning_rate": 4.947730295814063e-06,
"loss": 0.3584,
"step": 1818
},
{
"epoch": 2.04,
"learning_rate": 4.937298456917889e-06,
"loss": 0.3474,
"step": 1819
},
{
"epoch": 2.04,
"learning_rate": 4.926874020953113e-06,
"loss": 0.3523,
"step": 1820
},
{
"epoch": 2.04,
"learning_rate": 4.9164570031628525e-06,
"loss": 0.3318,
"step": 1821
},
{
"epoch": 2.04,
"learning_rate": 4.906047418779384e-06,
"loss": 0.3586,
"step": 1822
},
{
"epoch": 2.04,
"learning_rate": 4.895645283024116e-06,
"loss": 0.3293,
"step": 1823
},
{
"epoch": 2.04,
"learning_rate": 4.885250611107558e-06,
"loss": 0.3281,
"step": 1824
},
{
"epoch": 2.04,
"learning_rate": 4.874863418229319e-06,
"loss": 0.344,
"step": 1825
},
{
"epoch": 2.04,
"learning_rate": 4.864483719578055e-06,
"loss": 0.3447,
"step": 1826
},
{
"epoch": 2.04,
"learning_rate": 4.854111530331482e-06,
"loss": 0.3445,
"step": 1827
},
{
"epoch": 2.05,
"learning_rate": 4.843746865656317e-06,
"loss": 0.3579,
"step": 1828
},
{
"epoch": 2.05,
"learning_rate": 4.83338974070829e-06,
"loss": 0.3491,
"step": 1829
},
{
"epoch": 2.05,
"learning_rate": 4.823040170632095e-06,
"loss": 0.3323,
"step": 1830
},
{
"epoch": 2.05,
"learning_rate": 4.812698170561384e-06,
"loss": 0.364,
"step": 1831
},
{
"epoch": 2.05,
"learning_rate": 4.802363755618737e-06,
"loss": 0.345,
"step": 1832
},
{
"epoch": 2.05,
"learning_rate": 4.792036940915642e-06,
"loss": 0.3354,
"step": 1833
},
{
"epoch": 2.05,
"learning_rate": 4.78171774155248e-06,
"loss": 0.3562,
"step": 1834
},
{
"epoch": 2.05,
"learning_rate": 4.771406172618494e-06,
"loss": 0.3552,
"step": 1835
},
{
"epoch": 2.05,
"learning_rate": 4.761102249191763e-06,
"loss": 0.343,
"step": 1836
},
{
"epoch": 2.06,
"learning_rate": 4.750805986339191e-06,
"loss": 0.3269,
"step": 1837
},
{
"epoch": 2.06,
"learning_rate": 4.7405173991164855e-06,
"loss": 0.3398,
"step": 1838
},
{
"epoch": 2.06,
"learning_rate": 4.730236502568121e-06,
"loss": 0.3232,
"step": 1839
},
{
"epoch": 2.06,
"learning_rate": 4.719963311727331e-06,
"loss": 0.3403,
"step": 1840
},
{
"epoch": 2.06,
"learning_rate": 4.7096978416160785e-06,
"loss": 0.3286,
"step": 1841
},
{
"epoch": 2.06,
"learning_rate": 4.699440107245041e-06,
"loss": 0.3589,
"step": 1842
},
{
"epoch": 2.06,
"learning_rate": 4.689190123613587e-06,
"loss": 0.3486,
"step": 1843
},
{
"epoch": 2.06,
"learning_rate": 4.678947905709744e-06,
"loss": 0.3464,
"step": 1844
},
{
"epoch": 2.06,
"learning_rate": 4.668713468510187e-06,
"loss": 0.3477,
"step": 1845
},
{
"epoch": 2.07,
"learning_rate": 4.6584868269802134e-06,
"loss": 0.3408,
"step": 1846
},
{
"epoch": 2.07,
"learning_rate": 4.648267996073717e-06,
"loss": 0.3528,
"step": 1847
},
{
"epoch": 2.07,
"learning_rate": 4.638056990733184e-06,
"loss": 0.3386,
"step": 1848
},
{
"epoch": 2.07,
"learning_rate": 4.627853825889642e-06,
"loss": 0.3379,
"step": 1849
},
{
"epoch": 2.07,
"learning_rate": 4.617658516462668e-06,
"loss": 0.3398,
"step": 1850
},
{
"epoch": 2.07,
"learning_rate": 4.607471077360337e-06,
"loss": 0.3223,
"step": 1851
},
{
"epoch": 2.07,
"learning_rate": 4.5972915234792325e-06,
"loss": 0.3301,
"step": 1852
},
{
"epoch": 2.07,
"learning_rate": 4.587119869704395e-06,
"loss": 0.3564,
"step": 1853
},
{
"epoch": 2.07,
"learning_rate": 4.576956130909317e-06,
"loss": 0.3218,
"step": 1854
},
{
"epoch": 2.08,
"learning_rate": 4.566800321955918e-06,
"loss": 0.3313,
"step": 1855
},
{
"epoch": 2.08,
"learning_rate": 4.5566524576945185e-06,
"loss": 0.3328,
"step": 1856
},
{
"epoch": 2.08,
"learning_rate": 4.546512552963831e-06,
"loss": 0.3494,
"step": 1857
},
{
"epoch": 2.08,
"learning_rate": 4.536380622590918e-06,
"loss": 0.3538,
"step": 1858
},
{
"epoch": 2.08,
"learning_rate": 4.526256681391192e-06,
"loss": 0.324,
"step": 1859
},
{
"epoch": 2.08,
"learning_rate": 4.516140744168376e-06,
"loss": 0.3315,
"step": 1860
},
{
"epoch": 2.08,
"learning_rate": 4.506032825714488e-06,
"loss": 0.3582,
"step": 1861
},
{
"epoch": 2.08,
"learning_rate": 4.49593294080983e-06,
"loss": 0.3386,
"step": 1862
},
{
"epoch": 2.09,
"learning_rate": 4.485841104222946e-06,
"loss": 0.3306,
"step": 1863
},
{
"epoch": 2.09,
"learning_rate": 4.47575733071062e-06,
"loss": 0.324,
"step": 1864
},
{
"epoch": 2.09,
"learning_rate": 4.465681635017836e-06,
"loss": 0.3291,
"step": 1865
},
{
"epoch": 2.09,
"learning_rate": 4.455614031877775e-06,
"loss": 0.3369,
"step": 1866
},
{
"epoch": 2.09,
"learning_rate": 4.445554536011788e-06,
"loss": 0.3423,
"step": 1867
},
{
"epoch": 2.09,
"learning_rate": 4.435503162129358e-06,
"loss": 0.3398,
"step": 1868
},
{
"epoch": 2.09,
"learning_rate": 4.425459924928102e-06,
"loss": 0.3503,
"step": 1869
},
{
"epoch": 2.09,
"learning_rate": 4.41542483909373e-06,
"loss": 0.3333,
"step": 1870
},
{
"epoch": 2.09,
"learning_rate": 4.405397919300046e-06,
"loss": 0.3491,
"step": 1871
},
{
"epoch": 2.1,
"learning_rate": 4.395379180208904e-06,
"loss": 0.323,
"step": 1872
},
{
"epoch": 2.1,
"learning_rate": 4.385368636470191e-06,
"loss": 0.3335,
"step": 1873
},
{
"epoch": 2.1,
"learning_rate": 4.375366302721825e-06,
"loss": 0.3179,
"step": 1874
},
{
"epoch": 2.1,
"learning_rate": 4.365372193589704e-06,
"loss": 0.3557,
"step": 1875
},
{
"epoch": 2.1,
"learning_rate": 4.355386323687714e-06,
"loss": 0.3445,
"step": 1876
},
{
"epoch": 2.1,
"learning_rate": 4.345408707617681e-06,
"loss": 0.3394,
"step": 1877
},
{
"epoch": 2.1,
"learning_rate": 4.335439359969367e-06,
"loss": 0.3489,
"step": 1878
},
{
"epoch": 2.1,
"learning_rate": 4.325478295320438e-06,
"loss": 0.3345,
"step": 1879
},
{
"epoch": 2.1,
"learning_rate": 4.31552552823646e-06,
"loss": 0.314,
"step": 1880
},
{
"epoch": 2.11,
"learning_rate": 4.3055810732708584e-06,
"loss": 0.3289,
"step": 1881
},
{
"epoch": 2.11,
"learning_rate": 4.295644944964897e-06,
"loss": 0.3259,
"step": 1882
},
{
"epoch": 2.11,
"learning_rate": 4.285717157847683e-06,
"loss": 0.3411,
"step": 1883
},
{
"epoch": 2.11,
"learning_rate": 4.275797726436105e-06,
"loss": 0.3342,
"step": 1884
},
{
"epoch": 2.11,
"learning_rate": 4.265886665234853e-06,
"loss": 0.3472,
"step": 1885
},
{
"epoch": 2.11,
"learning_rate": 4.255983988736363e-06,
"loss": 0.3418,
"step": 1886
},
{
"epoch": 2.11,
"learning_rate": 4.246089711420817e-06,
"loss": 0.3279,
"step": 1887
},
{
"epoch": 2.11,
"learning_rate": 4.236203847756116e-06,
"loss": 0.3276,
"step": 1888
},
{
"epoch": 2.11,
"learning_rate": 4.226326412197851e-06,
"loss": 0.3438,
"step": 1889
},
{
"epoch": 2.12,
"learning_rate": 4.216457419189298e-06,
"loss": 0.3425,
"step": 1890
},
{
"epoch": 2.12,
"learning_rate": 4.206596883161388e-06,
"loss": 0.3582,
"step": 1891
},
{
"epoch": 2.12,
"learning_rate": 4.19674481853268e-06,
"loss": 0.343,
"step": 1892
},
{
"epoch": 2.12,
"learning_rate": 4.186901239709342e-06,
"loss": 0.3459,
"step": 1893
},
{
"epoch": 2.12,
"learning_rate": 4.177066161085149e-06,
"loss": 0.3215,
"step": 1894
},
{
"epoch": 2.12,
"learning_rate": 4.16723959704143e-06,
"loss": 0.3413,
"step": 1895
},
{
"epoch": 2.12,
"learning_rate": 4.157421561947075e-06,
"loss": 0.3333,
"step": 1896
},
{
"epoch": 2.12,
"learning_rate": 4.147612070158491e-06,
"loss": 0.3335,
"step": 1897
},
{
"epoch": 2.12,
"learning_rate": 4.1378111360196064e-06,
"loss": 0.3208,
"step": 1898
},
{
"epoch": 2.13,
"learning_rate": 4.12801877386183e-06,
"loss": 0.3479,
"step": 1899
},
{
"epoch": 2.13,
"learning_rate": 4.1182349980040335e-06,
"loss": 0.3418,
"step": 1900
},
{
"epoch": 2.13,
"learning_rate": 4.108459822752538e-06,
"loss": 0.3281,
"step": 1901
},
{
"epoch": 2.13,
"learning_rate": 4.0986932624010775e-06,
"loss": 0.342,
"step": 1902
},
{
"epoch": 2.13,
"learning_rate": 4.0889353312308075e-06,
"loss": 0.3491,
"step": 1903
},
{
"epoch": 2.13,
"learning_rate": 4.079186043510253e-06,
"loss": 0.3386,
"step": 1904
},
{
"epoch": 2.13,
"learning_rate": 4.0694454134952956e-06,
"loss": 0.3311,
"step": 1905
},
{
"epoch": 2.13,
"learning_rate": 4.059713455429172e-06,
"loss": 0.3513,
"step": 1906
},
{
"epoch": 2.13,
"learning_rate": 4.049990183542424e-06,
"loss": 0.3499,
"step": 1907
},
{
"epoch": 2.14,
"learning_rate": 4.040275612052905e-06,
"loss": 0.354,
"step": 1908
},
{
"epoch": 2.14,
"learning_rate": 4.030569755165736e-06,
"loss": 0.3569,
"step": 1909
},
{
"epoch": 2.14,
"learning_rate": 4.0208726270733e-06,
"loss": 0.3823,
"step": 1910
},
{
"epoch": 2.14,
"learning_rate": 4.011184241955212e-06,
"loss": 0.3425,
"step": 1911
},
{
"epoch": 2.14,
"learning_rate": 4.0015046139783055e-06,
"loss": 0.3479,
"step": 1912
},
{
"epoch": 2.14,
"learning_rate": 3.991833757296615e-06,
"loss": 0.342,
"step": 1913
},
{
"epoch": 2.14,
"learning_rate": 3.982171686051333e-06,
"loss": 0.3237,
"step": 1914
},
{
"epoch": 2.14,
"learning_rate": 3.972518414370827e-06,
"loss": 0.3376,
"step": 1915
},
{
"epoch": 2.14,
"learning_rate": 3.9628739563705775e-06,
"loss": 0.322,
"step": 1916
},
{
"epoch": 2.15,
"learning_rate": 3.953238326153193e-06,
"loss": 0.3501,
"step": 1917
},
{
"epoch": 2.15,
"learning_rate": 3.9436115378083604e-06,
"loss": 0.3428,
"step": 1918
},
{
"epoch": 2.15,
"learning_rate": 3.933993605412847e-06,
"loss": 0.3315,
"step": 1919
},
{
"epoch": 2.15,
"learning_rate": 3.924384543030464e-06,
"loss": 0.3411,
"step": 1920
},
{
"epoch": 2.15,
"learning_rate": 3.914784364712055e-06,
"loss": 0.3384,
"step": 1921
},
{
"epoch": 2.15,
"learning_rate": 3.905193084495473e-06,
"loss": 0.3323,
"step": 1922
},
{
"epoch": 2.15,
"learning_rate": 3.895610716405565e-06,
"loss": 0.332,
"step": 1923
},
{
"epoch": 2.15,
"learning_rate": 3.886037274454141e-06,
"loss": 0.3501,
"step": 1924
},
{
"epoch": 2.15,
"learning_rate": 3.8764727726399545e-06,
"loss": 0.335,
"step": 1925
},
{
"epoch": 2.16,
"learning_rate": 3.86691722494869e-06,
"loss": 0.3247,
"step": 1926
},
{
"epoch": 2.16,
"learning_rate": 3.857370645352945e-06,
"loss": 0.3376,
"step": 1927
},
{
"epoch": 2.16,
"learning_rate": 3.847833047812196e-06,
"loss": 0.3372,
"step": 1928
},
{
"epoch": 2.16,
"learning_rate": 3.838304446272782e-06,
"loss": 0.3455,
"step": 1929
},
{
"epoch": 2.16,
"learning_rate": 3.828784854667904e-06,
"loss": 0.3242,
"step": 1930
},
{
"epoch": 2.16,
"learning_rate": 3.819274286917567e-06,
"loss": 0.3455,
"step": 1931
},
{
"epoch": 2.16,
"learning_rate": 3.8097727569286003e-06,
"loss": 0.3638,
"step": 1932
},
{
"epoch": 2.16,
"learning_rate": 3.8002802785946037e-06,
"loss": 0.3484,
"step": 1933
},
{
"epoch": 2.16,
"learning_rate": 3.7907968657959473e-06,
"loss": 0.3435,
"step": 1934
},
{
"epoch": 2.17,
"learning_rate": 3.7813225323997395e-06,
"loss": 0.335,
"step": 1935
},
{
"epoch": 2.17,
"learning_rate": 3.771857292259825e-06,
"loss": 0.3396,
"step": 1936
},
{
"epoch": 2.17,
"learning_rate": 3.76240115921674e-06,
"loss": 0.3423,
"step": 1937
},
{
"epoch": 2.17,
"learning_rate": 3.7529541470977037e-06,
"loss": 0.3296,
"step": 1938
},
{
"epoch": 2.17,
"learning_rate": 3.7435162697166105e-06,
"loss": 0.3552,
"step": 1939
},
{
"epoch": 2.17,
"learning_rate": 3.7340875408739805e-06,
"loss": 0.3325,
"step": 1940
},
{
"epoch": 2.17,
"learning_rate": 3.7246679743569737e-06,
"loss": 0.3264,
"step": 1941
},
{
"epoch": 2.17,
"learning_rate": 3.7152575839393403e-06,
"loss": 0.3533,
"step": 1942
},
{
"epoch": 2.17,
"learning_rate": 3.705856383381414e-06,
"loss": 0.3418,
"step": 1943
},
{
"epoch": 2.18,
"learning_rate": 3.696464386430093e-06,
"loss": 0.3318,
"step": 1944
},
{
"epoch": 2.18,
"learning_rate": 3.687081606818823e-06,
"loss": 0.3333,
"step": 1945
},
{
"epoch": 2.18,
"learning_rate": 3.6777080582675584e-06,
"loss": 0.335,
"step": 1946
},
{
"epoch": 2.18,
"learning_rate": 3.6683437544827704e-06,
"loss": 0.3214,
"step": 1947
},
{
"epoch": 2.18,
"learning_rate": 3.658988709157403e-06,
"loss": 0.3389,
"step": 1948
},
{
"epoch": 2.18,
"learning_rate": 3.6496429359708596e-06,
"loss": 0.3228,
"step": 1949
},
{
"epoch": 2.18,
"learning_rate": 3.640306448588996e-06,
"loss": 0.3403,
"step": 1950
},
{
"epoch": 2.18,
"learning_rate": 3.6309792606640804e-06,
"loss": 0.3359,
"step": 1951
},
{
"epoch": 2.18,
"learning_rate": 3.621661385834787e-06,
"loss": 0.3345,
"step": 1952
},
{
"epoch": 2.19,
"learning_rate": 3.6123528377261663e-06,
"loss": 0.3396,
"step": 1953
},
{
"epoch": 2.19,
"learning_rate": 3.60305362994964e-06,
"loss": 0.3464,
"step": 1954
},
{
"epoch": 2.19,
"learning_rate": 3.593763776102971e-06,
"loss": 0.3215,
"step": 1955
},
{
"epoch": 2.19,
"learning_rate": 3.5844832897702363e-06,
"loss": 0.3547,
"step": 1956
},
{
"epoch": 2.19,
"learning_rate": 3.57521218452182e-06,
"loss": 0.3289,
"step": 1957
},
{
"epoch": 2.19,
"learning_rate": 3.565950473914387e-06,
"loss": 0.3386,
"step": 1958
},
{
"epoch": 2.19,
"learning_rate": 3.556698171490871e-06,
"loss": 0.3374,
"step": 1959
},
{
"epoch": 2.19,
"learning_rate": 3.5474552907804415e-06,
"loss": 0.3359,
"step": 1960
},
{
"epoch": 2.19,
"learning_rate": 3.5382218452984895e-06,
"loss": 0.3354,
"step": 1961
},
{
"epoch": 2.2,
"learning_rate": 3.5289978485466224e-06,
"loss": 0.3555,
"step": 1962
},
{
"epoch": 2.2,
"learning_rate": 3.5197833140126127e-06,
"loss": 0.3398,
"step": 1963
},
{
"epoch": 2.2,
"learning_rate": 3.510578255170415e-06,
"loss": 0.3293,
"step": 1964
},
{
"epoch": 2.2,
"learning_rate": 3.501382685480116e-06,
"loss": 0.3474,
"step": 1965
},
{
"epoch": 2.2,
"learning_rate": 3.4921966183879297e-06,
"loss": 0.3345,
"step": 1966
},
{
"epoch": 2.2,
"learning_rate": 3.4830200673261716e-06,
"loss": 0.3406,
"step": 1967
},
{
"epoch": 2.2,
"learning_rate": 3.473853045713255e-06,
"loss": 0.3621,
"step": 1968
},
{
"epoch": 2.2,
"learning_rate": 3.464695566953644e-06,
"loss": 0.3672,
"step": 1969
},
{
"epoch": 2.2,
"learning_rate": 3.455547644437853e-06,
"loss": 0.3511,
"step": 1970
},
{
"epoch": 2.21,
"learning_rate": 3.4464092915424328e-06,
"loss": 0.3564,
"step": 1971
},
{
"epoch": 2.21,
"learning_rate": 3.4372805216299245e-06,
"loss": 0.2961,
"step": 1972
},
{
"epoch": 2.21,
"learning_rate": 3.428161348048871e-06,
"loss": 0.3455,
"step": 1973
},
{
"epoch": 2.21,
"learning_rate": 3.419051784133773e-06,
"loss": 0.3784,
"step": 1974
},
{
"epoch": 2.21,
"learning_rate": 3.409951843205086e-06,
"loss": 0.3442,
"step": 1975
},
{
"epoch": 2.21,
"learning_rate": 3.400861538569189e-06,
"loss": 0.322,
"step": 1976
},
{
"epoch": 2.21,
"learning_rate": 3.3917808835183707e-06,
"loss": 0.3352,
"step": 1977
},
{
"epoch": 2.21,
"learning_rate": 3.3827098913308145e-06,
"loss": 0.3337,
"step": 1978
},
{
"epoch": 2.21,
"learning_rate": 3.373648575270576e-06,
"loss": 0.3464,
"step": 1979
},
{
"epoch": 2.22,
"learning_rate": 3.3645969485875528e-06,
"loss": 0.3391,
"step": 1980
},
{
"epoch": 2.22,
"learning_rate": 3.3555550245174774e-06,
"loss": 0.3481,
"step": 1981
},
{
"epoch": 2.22,
"learning_rate": 3.3465228162819017e-06,
"loss": 0.3442,
"step": 1982
},
{
"epoch": 2.22,
"learning_rate": 3.337500337088162e-06,
"loss": 0.3391,
"step": 1983
},
{
"epoch": 2.22,
"learning_rate": 3.328487600129371e-06,
"loss": 0.3308,
"step": 1984
},
{
"epoch": 2.22,
"learning_rate": 3.3194846185843943e-06,
"loss": 0.3276,
"step": 1985
},
{
"epoch": 2.22,
"learning_rate": 3.3104914056178406e-06,
"loss": 0.3484,
"step": 1986
},
{
"epoch": 2.22,
"learning_rate": 3.3015079743800217e-06,
"loss": 0.3337,
"step": 1987
},
{
"epoch": 2.22,
"learning_rate": 3.2925343380069597e-06,
"loss": 0.3108,
"step": 1988
},
{
"epoch": 2.23,
"learning_rate": 3.283570509620344e-06,
"loss": 0.3379,
"step": 1989
},
{
"epoch": 2.23,
"learning_rate": 3.2746165023275268e-06,
"loss": 0.3179,
"step": 1990
},
{
"epoch": 2.23,
"learning_rate": 3.265672329221493e-06,
"loss": 0.3474,
"step": 1991
},
{
"epoch": 2.23,
"learning_rate": 3.2567380033808603e-06,
"loss": 0.3464,
"step": 1992
},
{
"epoch": 2.23,
"learning_rate": 3.247813537869837e-06,
"loss": 0.325,
"step": 1993
},
{
"epoch": 2.23,
"learning_rate": 3.2388989457382124e-06,
"loss": 0.3425,
"step": 1994
},
{
"epoch": 2.23,
"learning_rate": 3.2299942400213447e-06,
"loss": 0.3254,
"step": 1995
},
{
"epoch": 2.23,
"learning_rate": 3.2210994337401356e-06,
"loss": 0.3169,
"step": 1996
},
{
"epoch": 2.24,
"learning_rate": 3.2122145399010074e-06,
"loss": 0.321,
"step": 1997
},
{
"epoch": 2.24,
"learning_rate": 3.203339571495887e-06,
"loss": 0.3152,
"step": 1998
},
{
"epoch": 2.24,
"learning_rate": 3.194474541502192e-06,
"loss": 0.3352,
"step": 1999
},
{
"epoch": 2.24,
"learning_rate": 3.1856194628827995e-06,
"loss": 0.3271,
"step": 2000
},
{
"epoch": 2.24,
"learning_rate": 3.1767743485860514e-06,
"loss": 0.3125,
"step": 2001
},
{
"epoch": 2.24,
"learning_rate": 3.167939211545701e-06,
"loss": 0.3389,
"step": 2002
},
{
"epoch": 2.24,
"learning_rate": 3.159114064680926e-06,
"loss": 0.3364,
"step": 2003
},
{
"epoch": 2.24,
"learning_rate": 3.1502989208962854e-06,
"loss": 0.3369,
"step": 2004
},
{
"epoch": 2.24,
"learning_rate": 3.1414937930817236e-06,
"loss": 0.3291,
"step": 2005
},
{
"epoch": 2.25,
"learning_rate": 3.132698694112526e-06,
"loss": 0.3354,
"step": 2006
},
{
"epoch": 2.25,
"learning_rate": 3.123913636849322e-06,
"loss": 0.3438,
"step": 2007
},
{
"epoch": 2.25,
"learning_rate": 3.115138634138053e-06,
"loss": 0.3176,
"step": 2008
},
{
"epoch": 2.25,
"learning_rate": 3.106373698809958e-06,
"loss": 0.3398,
"step": 2009
},
{
"epoch": 2.25,
"learning_rate": 3.097618843681558e-06,
"loss": 0.3069,
"step": 2010
},
{
"epoch": 2.25,
"learning_rate": 3.088874081554638e-06,
"loss": 0.3372,
"step": 2011
},
{
"epoch": 2.25,
"learning_rate": 3.0801394252162163e-06,
"loss": 0.3164,
"step": 2012
},
{
"epoch": 2.25,
"learning_rate": 3.0714148874385376e-06,
"loss": 0.3379,
"step": 2013
},
{
"epoch": 2.25,
"learning_rate": 3.062700480979046e-06,
"loss": 0.3469,
"step": 2014
},
{
"epoch": 2.26,
"learning_rate": 3.053996218580384e-06,
"loss": 0.3459,
"step": 2015
},
{
"epoch": 2.26,
"learning_rate": 3.0453021129703465e-06,
"loss": 0.3318,
"step": 2016
},
{
"epoch": 2.26,
"learning_rate": 3.036618176861882e-06,
"loss": 0.3181,
"step": 2017
},
{
"epoch": 2.26,
"learning_rate": 3.027944422953074e-06,
"loss": 0.335,
"step": 2018
},
{
"epoch": 2.26,
"learning_rate": 3.0192808639271065e-06,
"loss": 0.3284,
"step": 2019
},
{
"epoch": 2.26,
"learning_rate": 3.0106275124522697e-06,
"loss": 0.3352,
"step": 2020
},
{
"epoch": 2.26,
"learning_rate": 3.001984381181915e-06,
"loss": 0.3376,
"step": 2021
},
{
"epoch": 2.26,
"learning_rate": 2.993351482754455e-06,
"loss": 0.3381,
"step": 2022
},
{
"epoch": 2.26,
"learning_rate": 2.9847288297933364e-06,
"loss": 0.3293,
"step": 2023
},
{
"epoch": 2.27,
"learning_rate": 2.9761164349070316e-06,
"loss": 0.3259,
"step": 2024
},
{
"epoch": 2.27,
"learning_rate": 2.967514310689006e-06,
"loss": 0.3127,
"step": 2025
},
{
"epoch": 2.27,
"learning_rate": 2.9589224697177065e-06,
"loss": 0.3337,
"step": 2026
},
{
"epoch": 2.27,
"learning_rate": 2.9503409245565508e-06,
"loss": 0.3132,
"step": 2027
},
{
"epoch": 2.27,
"learning_rate": 2.9417696877538913e-06,
"loss": 0.3386,
"step": 2028
},
{
"epoch": 2.27,
"learning_rate": 2.933208771843018e-06,
"loss": 0.3357,
"step": 2029
},
{
"epoch": 2.27,
"learning_rate": 2.9246581893421212e-06,
"loss": 0.3235,
"step": 2030
},
{
"epoch": 2.27,
"learning_rate": 2.9161179527542827e-06,
"loss": 0.3462,
"step": 2031
},
{
"epoch": 2.27,
"learning_rate": 2.9075880745674545e-06,
"loss": 0.3374,
"step": 2032
},
{
"epoch": 2.28,
"learning_rate": 2.8990685672544503e-06,
"loss": 0.3442,
"step": 2033
},
{
"epoch": 2.28,
"learning_rate": 2.890559443272906e-06,
"loss": 0.3345,
"step": 2034
},
{
"epoch": 2.28,
"learning_rate": 2.882060715065289e-06,
"loss": 0.342,
"step": 2035
},
{
"epoch": 2.28,
"learning_rate": 2.8735723950588534e-06,
"loss": 0.344,
"step": 2036
},
{
"epoch": 2.28,
"learning_rate": 2.865094495665638e-06,
"loss": 0.3594,
"step": 2037
},
{
"epoch": 2.28,
"learning_rate": 2.8566270292824474e-06,
"loss": 0.3389,
"step": 2038
},
{
"epoch": 2.28,
"learning_rate": 2.8481700082908272e-06,
"loss": 0.3425,
"step": 2039
},
{
"epoch": 2.28,
"learning_rate": 2.839723445057049e-06,
"loss": 0.345,
"step": 2040
},
{
"epoch": 2.28,
"learning_rate": 2.8312873519320893e-06,
"loss": 0.3308,
"step": 2041
},
{
"epoch": 2.29,
"learning_rate": 2.822861741251627e-06,
"loss": 0.3188,
"step": 2042
},
{
"epoch": 2.29,
"learning_rate": 2.814446625335997e-06,
"loss": 0.2976,
"step": 2043
},
{
"epoch": 2.29,
"learning_rate": 2.8060420164902015e-06,
"loss": 0.3472,
"step": 2044
},
{
"epoch": 2.29,
"learning_rate": 2.7976479270038714e-06,
"loss": 0.325,
"step": 2045
},
{
"epoch": 2.29,
"learning_rate": 2.7892643691512555e-06,
"loss": 0.3518,
"step": 2046
},
{
"epoch": 2.29,
"learning_rate": 2.780891355191209e-06,
"loss": 0.3296,
"step": 2047
},
{
"epoch": 2.29,
"learning_rate": 2.7725288973671615e-06,
"loss": 0.3379,
"step": 2048
},
{
"epoch": 2.29,
"learning_rate": 2.764177007907113e-06,
"loss": 0.3533,
"step": 2049
},
{
"epoch": 2.29,
"learning_rate": 2.7558356990236013e-06,
"loss": 0.3389,
"step": 2050
},
{
"epoch": 2.3,
"learning_rate": 2.7475049829137046e-06,
"loss": 0.3123,
"step": 2051
},
{
"epoch": 2.3,
"learning_rate": 2.7391848717590074e-06,
"loss": 0.3286,
"step": 2052
},
{
"epoch": 2.3,
"learning_rate": 2.7308753777255836e-06,
"loss": 0.3223,
"step": 2053
},
{
"epoch": 2.3,
"learning_rate": 2.7225765129639835e-06,
"loss": 0.3633,
"step": 2054
},
{
"epoch": 2.3,
"learning_rate": 2.714288289609217e-06,
"loss": 0.3379,
"step": 2055
},
{
"epoch": 2.3,
"learning_rate": 2.7060107197807285e-06,
"loss": 0.3501,
"step": 2056
},
{
"epoch": 2.3,
"learning_rate": 2.697743815582393e-06,
"loss": 0.3267,
"step": 2057
},
{
"epoch": 2.3,
"learning_rate": 2.6894875891024796e-06,
"loss": 0.3359,
"step": 2058
},
{
"epoch": 2.3,
"learning_rate": 2.681242052413656e-06,
"loss": 0.3369,
"step": 2059
},
{
"epoch": 2.31,
"learning_rate": 2.673007217572945e-06,
"loss": 0.3311,
"step": 2060
},
{
"epoch": 2.31,
"learning_rate": 2.6647830966217323e-06,
"loss": 0.3386,
"step": 2061
},
{
"epoch": 2.31,
"learning_rate": 2.6565697015857315e-06,
"loss": 0.3401,
"step": 2062
},
{
"epoch": 2.31,
"learning_rate": 2.648367044474971e-06,
"loss": 0.3091,
"step": 2063
},
{
"epoch": 2.31,
"learning_rate": 2.6401751372837815e-06,
"loss": 0.3234,
"step": 2064
},
{
"epoch": 2.31,
"learning_rate": 2.63199399199077e-06,
"loss": 0.3333,
"step": 2065
},
{
"epoch": 2.31,
"learning_rate": 2.623823620558811e-06,
"loss": 0.3156,
"step": 2066
},
{
"epoch": 2.31,
"learning_rate": 2.6156640349350282e-06,
"loss": 0.3496,
"step": 2067
},
{
"epoch": 2.31,
"learning_rate": 2.607515247050766e-06,
"loss": 0.3567,
"step": 2068
},
{
"epoch": 2.32,
"learning_rate": 2.59937726882158e-06,
"loss": 0.3403,
"step": 2069
},
{
"epoch": 2.32,
"learning_rate": 2.5912501121472287e-06,
"loss": 0.3259,
"step": 2070
},
{
"epoch": 2.32,
"learning_rate": 2.5831337889116383e-06,
"loss": 0.3486,
"step": 2071
},
{
"epoch": 2.32,
"learning_rate": 2.5750283109828944e-06,
"loss": 0.3286,
"step": 2072
},
{
"epoch": 2.32,
"learning_rate": 2.5669336902132236e-06,
"loss": 0.3325,
"step": 2073
},
{
"epoch": 2.32,
"learning_rate": 2.5588499384389863e-06,
"loss": 0.3345,
"step": 2074
},
{
"epoch": 2.32,
"learning_rate": 2.550777067480634e-06,
"loss": 0.3445,
"step": 2075
},
{
"epoch": 2.32,
"learning_rate": 2.542715089142723e-06,
"loss": 0.3342,
"step": 2076
},
{
"epoch": 2.32,
"learning_rate": 2.5346640152138725e-06,
"loss": 0.3403,
"step": 2077
},
{
"epoch": 2.33,
"learning_rate": 2.526623857466758e-06,
"loss": 0.3396,
"step": 2078
},
{
"epoch": 2.33,
"learning_rate": 2.518594627658092e-06,
"loss": 0.3357,
"step": 2079
},
{
"epoch": 2.33,
"learning_rate": 2.510576337528614e-06,
"loss": 0.3599,
"step": 2080
},
{
"epoch": 2.33,
"learning_rate": 2.502568998803061e-06,
"loss": 0.3447,
"step": 2081
},
{
"epoch": 2.33,
"learning_rate": 2.4945726231901535e-06,
"loss": 0.3325,
"step": 2082
},
{
"epoch": 2.33,
"learning_rate": 2.486587222382589e-06,
"loss": 0.3491,
"step": 2083
},
{
"epoch": 2.33,
"learning_rate": 2.478612808057018e-06,
"loss": 0.3213,
"step": 2084
},
{
"epoch": 2.33,
"learning_rate": 2.470649391874017e-06,
"loss": 0.3237,
"step": 2085
},
{
"epoch": 2.33,
"learning_rate": 2.462696985478086e-06,
"loss": 0.3359,
"step": 2086
},
{
"epoch": 2.34,
"learning_rate": 2.4547556004976235e-06,
"loss": 0.3145,
"step": 2087
},
{
"epoch": 2.34,
"learning_rate": 2.446825248544913e-06,
"loss": 0.3323,
"step": 2088
},
{
"epoch": 2.34,
"learning_rate": 2.4389059412161085e-06,
"loss": 0.3438,
"step": 2089
},
{
"epoch": 2.34,
"learning_rate": 2.430997690091208e-06,
"loss": 0.3103,
"step": 2090
},
{
"epoch": 2.34,
"learning_rate": 2.4231005067340507e-06,
"loss": 0.3416,
"step": 2091
},
{
"epoch": 2.34,
"learning_rate": 2.415214402692282e-06,
"loss": 0.333,
"step": 2092
},
{
"epoch": 2.34,
"learning_rate": 2.4073393894973497e-06,
"loss": 0.333,
"step": 2093
},
{
"epoch": 2.34,
"learning_rate": 2.3994754786644925e-06,
"loss": 0.3208,
"step": 2094
},
{
"epoch": 2.34,
"learning_rate": 2.3916226816927037e-06,
"loss": 0.3376,
"step": 2095
},
{
"epoch": 2.35,
"learning_rate": 2.3837810100647297e-06,
"loss": 0.3174,
"step": 2096
},
{
"epoch": 2.35,
"learning_rate": 2.3759504752470463e-06,
"loss": 0.3271,
"step": 2097
},
{
"epoch": 2.35,
"learning_rate": 2.3681310886898532e-06,
"loss": 0.3237,
"step": 2098
},
{
"epoch": 2.35,
"learning_rate": 2.3603228618270357e-06,
"loss": 0.3408,
"step": 2099
},
{
"epoch": 2.35,
"learning_rate": 2.3525258060761734e-06,
"loss": 0.3381,
"step": 2100
},
{
"epoch": 2.35,
"learning_rate": 2.3447399328385014e-06,
"loss": 0.3333,
"step": 2101
},
{
"epoch": 2.35,
"learning_rate": 2.3369652534989052e-06,
"loss": 0.322,
"step": 2102
},
{
"epoch": 2.35,
"learning_rate": 2.329201779425909e-06,
"loss": 0.3472,
"step": 2103
},
{
"epoch": 2.35,
"learning_rate": 2.3214495219716437e-06,
"loss": 0.3408,
"step": 2104
},
{
"epoch": 2.36,
"learning_rate": 2.3137084924718413e-06,
"loss": 0.3267,
"step": 2105
},
{
"epoch": 2.36,
"learning_rate": 2.3059787022458137e-06,
"loss": 0.3396,
"step": 2106
},
{
"epoch": 2.36,
"learning_rate": 2.298260162596443e-06,
"loss": 0.3335,
"step": 2107
},
{
"epoch": 2.36,
"learning_rate": 2.290552884810162e-06,
"loss": 0.3059,
"step": 2108
},
{
"epoch": 2.36,
"learning_rate": 2.2828568801569286e-06,
"loss": 0.3782,
"step": 2109
},
{
"epoch": 2.36,
"learning_rate": 2.275172159890218e-06,
"loss": 0.323,
"step": 2110
},
{
"epoch": 2.36,
"learning_rate": 2.2674987352470046e-06,
"loss": 0.323,
"step": 2111
},
{
"epoch": 2.36,
"learning_rate": 2.2598366174477527e-06,
"loss": 0.3311,
"step": 2112
},
{
"epoch": 2.36,
"learning_rate": 2.2521858176963864e-06,
"loss": 0.335,
"step": 2113
},
{
"epoch": 2.37,
"learning_rate": 2.2445463471802786e-06,
"loss": 0.3218,
"step": 2114
},
{
"epoch": 2.37,
"learning_rate": 2.236918217070244e-06,
"loss": 0.3391,
"step": 2115
},
{
"epoch": 2.37,
"learning_rate": 2.2293014385205046e-06,
"loss": 0.3347,
"step": 2116
},
{
"epoch": 2.37,
"learning_rate": 2.2216960226686957e-06,
"loss": 0.3428,
"step": 2117
},
{
"epoch": 2.37,
"learning_rate": 2.2141019806358254e-06,
"loss": 0.344,
"step": 2118
},
{
"epoch": 2.37,
"learning_rate": 2.2065193235262784e-06,
"loss": 0.3279,
"step": 2119
},
{
"epoch": 2.37,
"learning_rate": 2.198948062427785e-06,
"loss": 0.3201,
"step": 2120
},
{
"epoch": 2.37,
"learning_rate": 2.191388208411421e-06,
"loss": 0.3469,
"step": 2121
},
{
"epoch": 2.37,
"learning_rate": 2.183839772531573e-06,
"loss": 0.3403,
"step": 2122
},
{
"epoch": 2.38,
"learning_rate": 2.1763027658259393e-06,
"loss": 0.3091,
"step": 2123
},
{
"epoch": 2.38,
"learning_rate": 2.1687771993155006e-06,
"loss": 0.3318,
"step": 2124
},
{
"epoch": 2.38,
"learning_rate": 2.161263084004507e-06,
"loss": 0.3423,
"step": 2125
},
{
"epoch": 2.38,
"learning_rate": 2.1537604308804737e-06,
"loss": 0.3459,
"step": 2126
},
{
"epoch": 2.38,
"learning_rate": 2.146269250914147e-06,
"loss": 0.323,
"step": 2127
},
{
"epoch": 2.38,
"learning_rate": 2.1387895550594995e-06,
"loss": 0.3174,
"step": 2128
},
{
"epoch": 2.38,
"learning_rate": 2.131321354253706e-06,
"loss": 0.3201,
"step": 2129
},
{
"epoch": 2.38,
"learning_rate": 2.123864659417144e-06,
"loss": 0.3276,
"step": 2130
},
{
"epoch": 2.39,
"learning_rate": 2.1164194814533545e-06,
"loss": 0.3364,
"step": 2131
},
{
"epoch": 2.39,
"learning_rate": 2.1089858312490476e-06,
"loss": 0.3274,
"step": 2132
},
{
"epoch": 2.39,
"learning_rate": 2.101563719674071e-06,
"loss": 0.3384,
"step": 2133
},
{
"epoch": 2.39,
"learning_rate": 2.0941531575813988e-06,
"loss": 0.3259,
"step": 2134
},
{
"epoch": 2.39,
"learning_rate": 2.0867541558071236e-06,
"loss": 0.3345,
"step": 2135
},
{
"epoch": 2.39,
"learning_rate": 2.0793667251704296e-06,
"loss": 0.3357,
"step": 2136
},
{
"epoch": 2.39,
"learning_rate": 2.0719908764735797e-06,
"loss": 0.3196,
"step": 2137
},
{
"epoch": 2.39,
"learning_rate": 2.0646266205019006e-06,
"loss": 0.3186,
"step": 2138
},
{
"epoch": 2.39,
"learning_rate": 2.0572739680237718e-06,
"loss": 0.3147,
"step": 2139
},
{
"epoch": 2.4,
"learning_rate": 2.049932929790608e-06,
"loss": 0.3438,
"step": 2140
},
{
"epoch": 2.4,
"learning_rate": 2.042603516536834e-06,
"loss": 0.3591,
"step": 2141
},
{
"epoch": 2.4,
"learning_rate": 2.0352857389798765e-06,
"loss": 0.3259,
"step": 2142
},
{
"epoch": 2.4,
"learning_rate": 2.027979607820152e-06,
"loss": 0.3396,
"step": 2143
},
{
"epoch": 2.4,
"learning_rate": 2.0206851337410418e-06,
"loss": 0.3162,
"step": 2144
},
{
"epoch": 2.4,
"learning_rate": 2.01340232740889e-06,
"loss": 0.3074,
"step": 2145
},
{
"epoch": 2.4,
"learning_rate": 2.0061311994729704e-06,
"loss": 0.3245,
"step": 2146
},
{
"epoch": 2.4,
"learning_rate": 1.9988717605654873e-06,
"loss": 0.3071,
"step": 2147
},
{
"epoch": 2.4,
"learning_rate": 1.9916240213015458e-06,
"loss": 0.3376,
"step": 2148
},
{
"epoch": 2.41,
"learning_rate": 1.9843879922791533e-06,
"loss": 0.3306,
"step": 2149
},
{
"epoch": 2.41,
"learning_rate": 1.9771636840791818e-06,
"loss": 0.3357,
"step": 2150
},
{
"epoch": 2.41,
"learning_rate": 1.9699511072653733e-06,
"loss": 0.3257,
"step": 2151
},
{
"epoch": 2.41,
"learning_rate": 1.9627502723843117e-06,
"loss": 0.3318,
"step": 2152
},
{
"epoch": 2.41,
"learning_rate": 1.9555611899654093e-06,
"loss": 0.3457,
"step": 2153
},
{
"epoch": 2.41,
"learning_rate": 1.948383870520901e-06,
"loss": 0.3374,
"step": 2154
},
{
"epoch": 2.41,
"learning_rate": 1.941218324545813e-06,
"loss": 0.3584,
"step": 2155
},
{
"epoch": 2.41,
"learning_rate": 1.9340645625179634e-06,
"loss": 0.3062,
"step": 2156
},
{
"epoch": 2.41,
"learning_rate": 1.926922594897932e-06,
"loss": 0.324,
"step": 2157
},
{
"epoch": 2.42,
"learning_rate": 1.919792432129054e-06,
"loss": 0.3181,
"step": 2158
},
{
"epoch": 2.42,
"learning_rate": 1.912674084637409e-06,
"loss": 0.3464,
"step": 2159
},
{
"epoch": 2.42,
"learning_rate": 1.9055675628317926e-06,
"loss": 0.3259,
"step": 2160
},
{
"epoch": 2.42,
"learning_rate": 1.8984728771037108e-06,
"loss": 0.3469,
"step": 2161
},
{
"epoch": 2.42,
"learning_rate": 1.8913900378273587e-06,
"loss": 0.3275,
"step": 2162
},
{
"epoch": 2.42,
"learning_rate": 1.8843190553596168e-06,
"loss": 0.3301,
"step": 2163
},
{
"epoch": 2.42,
"learning_rate": 1.877259940040026e-06,
"loss": 0.3457,
"step": 2164
},
{
"epoch": 2.42,
"learning_rate": 1.870212702190769e-06,
"loss": 0.3352,
"step": 2165
},
{
"epoch": 2.42,
"learning_rate": 1.863177352116664e-06,
"loss": 0.3474,
"step": 2166
},
{
"epoch": 2.43,
"learning_rate": 1.8561539001051432e-06,
"loss": 0.3345,
"step": 2167
},
{
"epoch": 2.43,
"learning_rate": 1.849142356426249e-06,
"loss": 0.302,
"step": 2168
},
{
"epoch": 2.43,
"learning_rate": 1.8421427313326046e-06,
"loss": 0.3645,
"step": 2169
},
{
"epoch": 2.43,
"learning_rate": 1.8351550350594016e-06,
"loss": 0.3359,
"step": 2170
},
{
"epoch": 2.43,
"learning_rate": 1.828179277824398e-06,
"loss": 0.3296,
"step": 2171
},
{
"epoch": 2.43,
"learning_rate": 1.8212154698278906e-06,
"loss": 0.3425,
"step": 2172
},
{
"epoch": 2.43,
"learning_rate": 1.8142636212526998e-06,
"loss": 0.3162,
"step": 2173
},
{
"epoch": 2.43,
"learning_rate": 1.807323742264162e-06,
"loss": 0.3276,
"step": 2174
},
{
"epoch": 2.43,
"learning_rate": 1.8003958430101087e-06,
"loss": 0.3259,
"step": 2175
},
{
"epoch": 2.44,
"learning_rate": 1.7934799336208519e-06,
"loss": 0.3318,
"step": 2176
},
{
"epoch": 2.44,
"learning_rate": 1.7865760242091822e-06,
"loss": 0.3301,
"step": 2177
},
{
"epoch": 2.44,
"learning_rate": 1.7796841248703277e-06,
"loss": 0.3323,
"step": 2178
},
{
"epoch": 2.44,
"learning_rate": 1.7728042456819706e-06,
"loss": 0.322,
"step": 2179
},
{
"epoch": 2.44,
"learning_rate": 1.7659363967042054e-06,
"loss": 0.3347,
"step": 2180
},
{
"epoch": 2.44,
"learning_rate": 1.7590805879795358e-06,
"loss": 0.3367,
"step": 2181
},
{
"epoch": 2.44,
"learning_rate": 1.7522368295328684e-06,
"loss": 0.3201,
"step": 2182
},
{
"epoch": 2.44,
"learning_rate": 1.7454051313714815e-06,
"loss": 0.3328,
"step": 2183
},
{
"epoch": 2.44,
"learning_rate": 1.7385855034850185e-06,
"loss": 0.3352,
"step": 2184
},
{
"epoch": 2.45,
"learning_rate": 1.731777955845475e-06,
"loss": 0.3398,
"step": 2185
},
{
"epoch": 2.45,
"learning_rate": 1.7249824984071861e-06,
"loss": 0.3274,
"step": 2186
},
{
"epoch": 2.45,
"learning_rate": 1.7181991411067989e-06,
"loss": 0.3093,
"step": 2187
},
{
"epoch": 2.45,
"learning_rate": 1.711427893863279e-06,
"loss": 0.3171,
"step": 2188
},
{
"epoch": 2.45,
"learning_rate": 1.7046687665778717e-06,
"loss": 0.3337,
"step": 2189
},
{
"epoch": 2.45,
"learning_rate": 1.6979217691341054e-06,
"loss": 0.3557,
"step": 2190
},
{
"epoch": 2.45,
"learning_rate": 1.6911869113977775e-06,
"loss": 0.3069,
"step": 2191
},
{
"epoch": 2.45,
"learning_rate": 1.6844642032169234e-06,
"loss": 0.3496,
"step": 2192
},
{
"epoch": 2.45,
"learning_rate": 1.677753654421821e-06,
"loss": 0.322,
"step": 2193
},
{
"epoch": 2.46,
"learning_rate": 1.6710552748249598e-06,
"loss": 0.3254,
"step": 2194
},
{
"epoch": 2.46,
"learning_rate": 1.664369074221045e-06,
"loss": 0.3184,
"step": 2195
},
{
"epoch": 2.46,
"learning_rate": 1.6576950623869682e-06,
"loss": 0.3333,
"step": 2196
},
{
"epoch": 2.46,
"learning_rate": 1.651033249081797e-06,
"loss": 0.3533,
"step": 2197
},
{
"epoch": 2.46,
"learning_rate": 1.644383644046764e-06,
"loss": 0.3381,
"step": 2198
},
{
"epoch": 2.46,
"learning_rate": 1.6377462570052438e-06,
"loss": 0.3088,
"step": 2199
},
{
"epoch": 2.46,
"learning_rate": 1.6311210976627579e-06,
"loss": 0.3379,
"step": 2200
},
{
"epoch": 2.46,
"learning_rate": 1.6245081757069358e-06,
"loss": 0.3542,
"step": 2201
},
{
"epoch": 2.46,
"learning_rate": 1.6179075008075162e-06,
"loss": 0.3291,
"step": 2202
},
{
"epoch": 2.47,
"learning_rate": 1.611319082616335e-06,
"loss": 0.3396,
"step": 2203
},
{
"epoch": 2.47,
"learning_rate": 1.6047429307672979e-06,
"loss": 0.3389,
"step": 2204
},
{
"epoch": 2.47,
"learning_rate": 1.598179054876382e-06,
"loss": 0.3293,
"step": 2205
},
{
"epoch": 2.47,
"learning_rate": 1.5916274645416062e-06,
"loss": 0.3218,
"step": 2206
},
{
"epoch": 2.47,
"learning_rate": 1.5850881693430308e-06,
"loss": 0.3284,
"step": 2207
},
{
"epoch": 2.47,
"learning_rate": 1.5785611788427336e-06,
"loss": 0.3191,
"step": 2208
},
{
"epoch": 2.47,
"learning_rate": 1.5720465025847986e-06,
"loss": 0.325,
"step": 2209
},
{
"epoch": 2.47,
"learning_rate": 1.5655441500953117e-06,
"loss": 0.3271,
"step": 2210
},
{
"epoch": 2.47,
"learning_rate": 1.559054130882327e-06,
"loss": 0.3262,
"step": 2211
},
{
"epoch": 2.48,
"learning_rate": 1.5525764544358767e-06,
"loss": 0.322,
"step": 2212
},
{
"epoch": 2.48,
"learning_rate": 1.546111130227932e-06,
"loss": 0.3337,
"step": 2213
},
{
"epoch": 2.48,
"learning_rate": 1.5396581677124123e-06,
"loss": 0.3337,
"step": 2214
},
{
"epoch": 2.48,
"learning_rate": 1.5332175763251556e-06,
"loss": 0.3357,
"step": 2215
},
{
"epoch": 2.48,
"learning_rate": 1.5267893654839127e-06,
"loss": 0.3215,
"step": 2216
},
{
"epoch": 2.48,
"learning_rate": 1.5203735445883284e-06,
"loss": 0.3422,
"step": 2217
},
{
"epoch": 2.48,
"learning_rate": 1.5139701230199287e-06,
"loss": 0.3438,
"step": 2218
},
{
"epoch": 2.48,
"learning_rate": 1.5075791101421167e-06,
"loss": 0.3242,
"step": 2219
},
{
"epoch": 2.48,
"learning_rate": 1.5012005153001463e-06,
"loss": 0.3298,
"step": 2220
},
{
"epoch": 2.49,
"learning_rate": 1.4948343478211102e-06,
"loss": 0.3262,
"step": 2221
},
{
"epoch": 2.49,
"learning_rate": 1.4884806170139342e-06,
"loss": 0.3396,
"step": 2222
},
{
"epoch": 2.49,
"learning_rate": 1.4821393321693523e-06,
"loss": 0.3398,
"step": 2223
},
{
"epoch": 2.49,
"learning_rate": 1.4758105025599067e-06,
"loss": 0.333,
"step": 2224
},
{
"epoch": 2.49,
"learning_rate": 1.469494137439924e-06,
"loss": 0.3267,
"step": 2225
},
{
"epoch": 2.49,
"learning_rate": 1.4631902460455005e-06,
"loss": 0.3433,
"step": 2226
},
{
"epoch": 2.49,
"learning_rate": 1.4568988375944993e-06,
"loss": 0.3162,
"step": 2227
},
{
"epoch": 2.49,
"learning_rate": 1.450619921286529e-06,
"loss": 0.3396,
"step": 2228
},
{
"epoch": 2.49,
"learning_rate": 1.444353506302928e-06,
"loss": 0.3267,
"step": 2229
},
{
"epoch": 2.5,
"learning_rate": 1.438099601806756e-06,
"loss": 0.3293,
"step": 2230
},
{
"epoch": 2.5,
"learning_rate": 1.431858216942782e-06,
"loss": 0.3335,
"step": 2231
},
{
"epoch": 2.5,
"learning_rate": 1.4256293608374627e-06,
"loss": 0.325,
"step": 2232
},
{
"epoch": 2.5,
"learning_rate": 1.4194130425989427e-06,
"loss": 0.3333,
"step": 2233
},
{
"epoch": 2.5,
"learning_rate": 1.4132092713170243e-06,
"loss": 0.3552,
"step": 2234
},
{
"epoch": 2.5,
"learning_rate": 1.4070180560631708e-06,
"loss": 0.3596,
"step": 2235
},
{
"epoch": 2.5,
"learning_rate": 1.4008394058904784e-06,
"loss": 0.3413,
"step": 2236
},
{
"epoch": 2.5,
"learning_rate": 1.3946733298336779e-06,
"loss": 0.3362,
"step": 2237
},
{
"epoch": 2.5,
"learning_rate": 1.3885198369091057e-06,
"loss": 0.3318,
"step": 2238
},
{
"epoch": 2.51,
"learning_rate": 1.3823789361147045e-06,
"loss": 0.3303,
"step": 2239
},
{
"epoch": 2.51,
"learning_rate": 1.3762506364299987e-06,
"loss": 0.3142,
"step": 2240
},
{
"epoch": 2.51,
"learning_rate": 1.3701349468160908e-06,
"loss": 0.3323,
"step": 2241
},
{
"epoch": 2.51,
"learning_rate": 1.3640318762156446e-06,
"loss": 0.3203,
"step": 2242
},
{
"epoch": 2.51,
"learning_rate": 1.3579414335528673e-06,
"loss": 0.3489,
"step": 2243
},
{
"epoch": 2.51,
"learning_rate": 1.3518636277335085e-06,
"loss": 0.3301,
"step": 2244
},
{
"epoch": 2.51,
"learning_rate": 1.3457984676448332e-06,
"loss": 0.3447,
"step": 2245
},
{
"epoch": 2.51,
"learning_rate": 1.339745962155613e-06,
"loss": 0.3159,
"step": 2246
},
{
"epoch": 2.51,
"learning_rate": 1.333706120116126e-06,
"loss": 0.3306,
"step": 2247
},
{
"epoch": 2.52,
"learning_rate": 1.3276789503581233e-06,
"loss": 0.3508,
"step": 2248
},
{
"epoch": 2.52,
"learning_rate": 1.3216644616948282e-06,
"loss": 0.3191,
"step": 2249
},
{
"epoch": 2.52,
"learning_rate": 1.3156626629209224e-06,
"loss": 0.313,
"step": 2250
},
{
"epoch": 2.52,
"learning_rate": 1.3096735628125311e-06,
"loss": 0.3184,
"step": 2251
},
{
"epoch": 2.52,
"learning_rate": 1.3036971701272138e-06,
"loss": 0.3319,
"step": 2252
},
{
"epoch": 2.52,
"learning_rate": 1.2977334936039454e-06,
"loss": 0.333,
"step": 2253
},
{
"epoch": 2.52,
"learning_rate": 1.291782541963107e-06,
"loss": 0.3386,
"step": 2254
},
{
"epoch": 2.52,
"learning_rate": 1.2858443239064699e-06,
"loss": 0.3425,
"step": 2255
},
{
"epoch": 2.52,
"learning_rate": 1.2799188481171931e-06,
"loss": 0.3223,
"step": 2256
},
{
"epoch": 2.53,
"learning_rate": 1.2740061232597978e-06,
"loss": 0.3323,
"step": 2257
},
{
"epoch": 2.53,
"learning_rate": 1.268106157980158e-06,
"loss": 0.3247,
"step": 2258
},
{
"epoch": 2.53,
"learning_rate": 1.262218960905498e-06,
"loss": 0.3245,
"step": 2259
},
{
"epoch": 2.53,
"learning_rate": 1.2563445406443642e-06,
"loss": 0.3296,
"step": 2260
},
{
"epoch": 2.53,
"learning_rate": 1.2504829057866252e-06,
"loss": 0.3201,
"step": 2261
},
{
"epoch": 2.53,
"learning_rate": 1.2446340649034517e-06,
"loss": 0.3311,
"step": 2262
},
{
"epoch": 2.53,
"learning_rate": 1.2387980265473054e-06,
"loss": 0.3135,
"step": 2263
},
{
"epoch": 2.53,
"learning_rate": 1.232974799251927e-06,
"loss": 0.3535,
"step": 2264
},
{
"epoch": 2.53,
"learning_rate": 1.2271643915323316e-06,
"loss": 0.3577,
"step": 2265
},
{
"epoch": 2.54,
"learning_rate": 1.22136681188478e-06,
"loss": 0.323,
"step": 2266
},
{
"epoch": 2.54,
"learning_rate": 1.2155820687867759e-06,
"loss": 0.323,
"step": 2267
},
{
"epoch": 2.54,
"learning_rate": 1.209810170697061e-06,
"loss": 0.3247,
"step": 2268
},
{
"epoch": 2.54,
"learning_rate": 1.2040511260555831e-06,
"loss": 0.3235,
"step": 2269
},
{
"epoch": 2.54,
"learning_rate": 1.198304943283507e-06,
"loss": 0.3167,
"step": 2270
},
{
"epoch": 2.54,
"learning_rate": 1.1925716307831792e-06,
"loss": 0.3328,
"step": 2271
},
{
"epoch": 2.54,
"learning_rate": 1.1868511969381347e-06,
"loss": 0.3257,
"step": 2272
},
{
"epoch": 2.54,
"learning_rate": 1.1811436501130702e-06,
"loss": 0.3113,
"step": 2273
},
{
"epoch": 2.55,
"learning_rate": 1.175448998653842e-06,
"loss": 0.3135,
"step": 2274
},
{
"epoch": 2.55,
"learning_rate": 1.1697672508874502e-06,
"loss": 0.3264,
"step": 2275
},
{
"epoch": 2.55,
"learning_rate": 1.1640984151220291e-06,
"loss": 0.3394,
"step": 2276
},
{
"epoch": 2.55,
"learning_rate": 1.1584424996468269e-06,
"loss": 0.3381,
"step": 2277
},
{
"epoch": 2.55,
"learning_rate": 1.152799512732199e-06,
"loss": 0.3296,
"step": 2278
},
{
"epoch": 2.55,
"learning_rate": 1.1471694626296049e-06,
"loss": 0.3286,
"step": 2279
},
{
"epoch": 2.55,
"learning_rate": 1.1415523575715758e-06,
"loss": 0.3425,
"step": 2280
},
{
"epoch": 2.55,
"learning_rate": 1.135948205771722e-06,
"loss": 0.3147,
"step": 2281
},
{
"epoch": 2.55,
"learning_rate": 1.1303570154247058e-06,
"loss": 0.3298,
"step": 2282
},
{
"epoch": 2.56,
"learning_rate": 1.124778794706245e-06,
"loss": 0.3333,
"step": 2283
},
{
"epoch": 2.56,
"learning_rate": 1.1192135517730884e-06,
"loss": 0.3191,
"step": 2284
},
{
"epoch": 2.56,
"learning_rate": 1.1136612947630088e-06,
"loss": 0.333,
"step": 2285
},
{
"epoch": 2.56,
"learning_rate": 1.1081220317947871e-06,
"loss": 0.3357,
"step": 2286
},
{
"epoch": 2.56,
"learning_rate": 1.1025957709682056e-06,
"loss": 0.3149,
"step": 2287
},
{
"epoch": 2.56,
"learning_rate": 1.097082520364039e-06,
"loss": 0.3379,
"step": 2288
},
{
"epoch": 2.56,
"learning_rate": 1.0915822880440309e-06,
"loss": 0.3289,
"step": 2289
},
{
"epoch": 2.56,
"learning_rate": 1.0860950820508898e-06,
"loss": 0.3169,
"step": 2290
},
{
"epoch": 2.56,
"learning_rate": 1.0806209104082831e-06,
"loss": 0.3318,
"step": 2291
},
{
"epoch": 2.57,
"learning_rate": 1.0751597811208104e-06,
"loss": 0.3262,
"step": 2292
},
{
"epoch": 2.57,
"learning_rate": 1.0697117021740066e-06,
"loss": 0.3262,
"step": 2293
},
{
"epoch": 2.57,
"learning_rate": 1.0642766815343197e-06,
"loss": 0.3176,
"step": 2294
},
{
"epoch": 2.57,
"learning_rate": 1.0588547271491033e-06,
"loss": 0.3411,
"step": 2295
},
{
"epoch": 2.57,
"learning_rate": 1.053445846946608e-06,
"loss": 0.3325,
"step": 2296
},
{
"epoch": 2.57,
"learning_rate": 1.0480500488359601e-06,
"loss": 0.3452,
"step": 2297
},
{
"epoch": 2.57,
"learning_rate": 1.0426673407071674e-06,
"loss": 0.314,
"step": 2298
},
{
"epoch": 2.57,
"learning_rate": 1.037297730431085e-06,
"loss": 0.3135,
"step": 2299
},
{
"epoch": 2.57,
"learning_rate": 1.0319412258594263e-06,
"loss": 0.3171,
"step": 2300
},
{
"epoch": 2.58,
"learning_rate": 1.0265978348247319e-06,
"loss": 0.3335,
"step": 2301
},
{
"epoch": 2.58,
"learning_rate": 1.0212675651403759e-06,
"loss": 0.3406,
"step": 2302
},
{
"epoch": 2.58,
"learning_rate": 1.0159504246005369e-06,
"loss": 0.3193,
"step": 2303
},
{
"epoch": 2.58,
"learning_rate": 1.0106464209802013e-06,
"loss": 0.3083,
"step": 2304
},
{
"epoch": 2.58,
"learning_rate": 1.0053555620351441e-06,
"loss": 0.3518,
"step": 2305
},
{
"epoch": 2.58,
"learning_rate": 1.0000778555019164e-06,
"loss": 0.3113,
"step": 2306
},
{
"epoch": 2.58,
"learning_rate": 9.94813309097844e-07,
"loss": 0.3174,
"step": 2307
},
{
"epoch": 2.58,
"learning_rate": 9.89561930521007e-07,
"loss": 0.3215,
"step": 2308
},
{
"epoch": 2.58,
"learning_rate": 9.843237274502281e-07,
"loss": 0.3218,
"step": 2309
},
{
"epoch": 2.59,
"learning_rate": 9.790987075450652e-07,
"loss": 0.3525,
"step": 2310
},
{
"epoch": 2.59,
"learning_rate": 9.738868784457978e-07,
"loss": 0.3352,
"step": 2311
},
{
"epoch": 2.59,
"learning_rate": 9.686882477734228e-07,
"loss": 0.3298,
"step": 2312
},
{
"epoch": 2.59,
"learning_rate": 9.635028231296328e-07,
"loss": 0.3279,
"step": 2313
},
{
"epoch": 2.59,
"learning_rate": 9.583306120968073e-07,
"loss": 0.3186,
"step": 2314
},
{
"epoch": 2.59,
"learning_rate": 9.531716222380106e-07,
"loss": 0.3274,
"step": 2315
},
{
"epoch": 2.59,
"learning_rate": 9.480258610969739e-07,
"loss": 0.3206,
"step": 2316
},
{
"epoch": 2.59,
"learning_rate": 9.428933361980797e-07,
"loss": 0.3347,
"step": 2317
},
{
"epoch": 2.59,
"learning_rate": 9.377740550463599e-07,
"loss": 0.3169,
"step": 2318
},
{
"epoch": 2.6,
"learning_rate": 9.326680251274778e-07,
"loss": 0.3213,
"step": 2319
},
{
"epoch": 2.6,
"learning_rate": 9.27575253907721e-07,
"loss": 0.3376,
"step": 2320
},
{
"epoch": 2.6,
"learning_rate": 9.224957488339936e-07,
"loss": 0.3379,
"step": 2321
},
{
"epoch": 2.6,
"learning_rate": 9.174295173337965e-07,
"loss": 0.3181,
"step": 2322
},
{
"epoch": 2.6,
"learning_rate": 9.123765668152196e-07,
"loss": 0.3201,
"step": 2323
},
{
"epoch": 2.6,
"learning_rate": 9.0733690466694e-07,
"loss": 0.3145,
"step": 2324
},
{
"epoch": 2.6,
"learning_rate": 9.023105382581976e-07,
"loss": 0.335,
"step": 2325
},
{
"epoch": 2.6,
"learning_rate": 8.972974749387952e-07,
"loss": 0.3486,
"step": 2326
},
{
"epoch": 2.6,
"learning_rate": 8.922977220390783e-07,
"loss": 0.3196,
"step": 2327
},
{
"epoch": 2.61,
"learning_rate": 8.873112868699329e-07,
"loss": 0.3323,
"step": 2328
},
{
"epoch": 2.61,
"learning_rate": 8.823381767227668e-07,
"loss": 0.3279,
"step": 2329
},
{
"epoch": 2.61,
"learning_rate": 8.773783988695117e-07,
"loss": 0.3096,
"step": 2330
},
{
"epoch": 2.61,
"learning_rate": 8.724319605625942e-07,
"loss": 0.3225,
"step": 2331
},
{
"epoch": 2.61,
"learning_rate": 8.67498869034944e-07,
"loss": 0.3469,
"step": 2332
},
{
"epoch": 2.61,
"learning_rate": 8.625791314999687e-07,
"loss": 0.3347,
"step": 2333
},
{
"epoch": 2.61,
"learning_rate": 8.576727551515473e-07,
"loss": 0.3359,
"step": 2334
},
{
"epoch": 2.61,
"learning_rate": 8.527797471640309e-07,
"loss": 0.3276,
"step": 2335
},
{
"epoch": 2.61,
"learning_rate": 8.479001146922127e-07,
"loss": 0.3131,
"step": 2336
},
{
"epoch": 2.62,
"learning_rate": 8.430338648713332e-07,
"loss": 0.3281,
"step": 2337
},
{
"epoch": 2.62,
"learning_rate": 8.381810048170591e-07,
"loss": 0.3188,
"step": 2338
},
{
"epoch": 2.62,
"learning_rate": 8.333415416254831e-07,
"loss": 0.2993,
"step": 2339
},
{
"epoch": 2.62,
"learning_rate": 8.285154823731101e-07,
"loss": 0.3418,
"step": 2340
},
{
"epoch": 2.62,
"learning_rate": 8.237028341168373e-07,
"loss": 0.3308,
"step": 2341
},
{
"epoch": 2.62,
"learning_rate": 8.189036038939568e-07,
"loss": 0.3289,
"step": 2342
},
{
"epoch": 2.62,
"learning_rate": 8.141177987221394e-07,
"loss": 0.3159,
"step": 2343
},
{
"epoch": 2.62,
"learning_rate": 8.093454255994248e-07,
"loss": 0.3223,
"step": 2344
},
{
"epoch": 2.62,
"learning_rate": 8.045864915042134e-07,
"loss": 0.3154,
"step": 2345
},
{
"epoch": 2.63,
"learning_rate": 7.998410033952497e-07,
"loss": 0.3301,
"step": 2346
},
{
"epoch": 2.63,
"learning_rate": 7.951089682116242e-07,
"loss": 0.3411,
"step": 2347
},
{
"epoch": 2.63,
"learning_rate": 7.903903928727463e-07,
"loss": 0.355,
"step": 2348
},
{
"epoch": 2.63,
"learning_rate": 7.856852842783546e-07,
"loss": 0.3318,
"step": 2349
},
{
"epoch": 2.63,
"learning_rate": 7.80993649308488e-07,
"loss": 0.3281,
"step": 2350
},
{
"epoch": 2.63,
"learning_rate": 7.763154948234863e-07,
"loss": 0.342,
"step": 2351
},
{
"epoch": 2.63,
"learning_rate": 7.716508276639756e-07,
"loss": 0.3198,
"step": 2352
},
{
"epoch": 2.63,
"learning_rate": 7.669996546508651e-07,
"loss": 0.3442,
"step": 2353
},
{
"epoch": 2.63,
"learning_rate": 7.623619825853268e-07,
"loss": 0.3228,
"step": 2354
},
{
"epoch": 2.64,
"learning_rate": 7.577378182487927e-07,
"loss": 0.3376,
"step": 2355
},
{
"epoch": 2.64,
"learning_rate": 7.531271684029451e-07,
"loss": 0.342,
"step": 2356
},
{
"epoch": 2.64,
"learning_rate": 7.485300397897e-07,
"loss": 0.3176,
"step": 2357
},
{
"epoch": 2.64,
"learning_rate": 7.439464391312102e-07,
"loss": 0.3141,
"step": 2358
},
{
"epoch": 2.64,
"learning_rate": 7.393763731298386e-07,
"loss": 0.3403,
"step": 2359
},
{
"epoch": 2.64,
"learning_rate": 7.348198484681624e-07,
"loss": 0.3154,
"step": 2360
},
{
"epoch": 2.64,
"learning_rate": 7.302768718089548e-07,
"loss": 0.3271,
"step": 2361
},
{
"epoch": 2.64,
"learning_rate": 7.257474497951788e-07,
"loss": 0.3267,
"step": 2362
},
{
"epoch": 2.64,
"learning_rate": 7.212315890499799e-07,
"loss": 0.3254,
"step": 2363
},
{
"epoch": 2.65,
"learning_rate": 7.167292961766726e-07,
"loss": 0.3201,
"step": 2364
},
{
"epoch": 2.65,
"learning_rate": 7.122405777587315e-07,
"loss": 0.3342,
"step": 2365
},
{
"epoch": 2.65,
"learning_rate": 7.077654403597789e-07,
"loss": 0.3242,
"step": 2366
},
{
"epoch": 2.65,
"learning_rate": 7.033038905235845e-07,
"loss": 0.3206,
"step": 2367
},
{
"epoch": 2.65,
"learning_rate": 6.988559347740431e-07,
"loss": 0.3074,
"step": 2368
},
{
"epoch": 2.65,
"learning_rate": 6.944215796151765e-07,
"loss": 0.3342,
"step": 2369
},
{
"epoch": 2.65,
"learning_rate": 6.900008315311147e-07,
"loss": 0.3154,
"step": 2370
},
{
"epoch": 2.65,
"learning_rate": 6.855936969860943e-07,
"loss": 0.3335,
"step": 2371
},
{
"epoch": 2.65,
"learning_rate": 6.812001824244463e-07,
"loss": 0.2922,
"step": 2372
},
{
"epoch": 2.66,
"learning_rate": 6.768202942705837e-07,
"loss": 0.321,
"step": 2373
},
{
"epoch": 2.66,
"learning_rate": 6.724540389289913e-07,
"loss": 0.3267,
"step": 2374
},
{
"epoch": 2.66,
"learning_rate": 6.681014227842253e-07,
"loss": 0.3391,
"step": 2375
},
{
"epoch": 2.66,
"learning_rate": 6.637624522008934e-07,
"loss": 0.3516,
"step": 2376
},
{
"epoch": 2.66,
"learning_rate": 6.594371335236538e-07,
"loss": 0.3379,
"step": 2377
},
{
"epoch": 2.66,
"learning_rate": 6.551254730772005e-07,
"loss": 0.3181,
"step": 2378
},
{
"epoch": 2.66,
"learning_rate": 6.508274771662526e-07,
"loss": 0.3157,
"step": 2379
},
{
"epoch": 2.66,
"learning_rate": 6.465431520755539e-07,
"loss": 0.3291,
"step": 2380
},
{
"epoch": 2.66,
"learning_rate": 6.422725040698563e-07,
"loss": 0.3164,
"step": 2381
},
{
"epoch": 2.67,
"learning_rate": 6.380155393939092e-07,
"loss": 0.3259,
"step": 2382
},
{
"epoch": 2.67,
"learning_rate": 6.337722642724575e-07,
"loss": 0.3311,
"step": 2383
},
{
"epoch": 2.67,
"learning_rate": 6.295426849102271e-07,
"loss": 0.3384,
"step": 2384
},
{
"epoch": 2.67,
"learning_rate": 6.253268074919139e-07,
"loss": 0.3335,
"step": 2385
},
{
"epoch": 2.67,
"learning_rate": 6.211246381821857e-07,
"loss": 0.3269,
"step": 2386
},
{
"epoch": 2.67,
"learning_rate": 6.169361831256581e-07,
"loss": 0.3264,
"step": 2387
},
{
"epoch": 2.67,
"learning_rate": 6.127614484468991e-07,
"loss": 0.3159,
"step": 2388
},
{
"epoch": 2.67,
"learning_rate": 6.086004402504097e-07,
"loss": 0.3481,
"step": 2389
},
{
"epoch": 2.67,
"learning_rate": 6.044531646206186e-07,
"loss": 0.3325,
"step": 2390
},
{
"epoch": 2.68,
"learning_rate": 6.003196276218815e-07,
"loss": 0.3318,
"step": 2391
},
{
"epoch": 2.68,
"learning_rate": 5.961998352984555e-07,
"loss": 0.312,
"step": 2392
},
{
"epoch": 2.68,
"learning_rate": 5.920937936745064e-07,
"loss": 0.3645,
"step": 2393
},
{
"epoch": 2.68,
"learning_rate": 5.880015087540858e-07,
"loss": 0.3259,
"step": 2394
},
{
"epoch": 2.68,
"learning_rate": 5.839229865211393e-07,
"loss": 0.312,
"step": 2395
},
{
"epoch": 2.68,
"learning_rate": 5.798582329394808e-07,
"loss": 0.3132,
"step": 2396
},
{
"epoch": 2.68,
"learning_rate": 5.758072539527937e-07,
"loss": 0.334,
"step": 2397
},
{
"epoch": 2.68,
"learning_rate": 5.717700554846195e-07,
"loss": 0.3428,
"step": 2398
},
{
"epoch": 2.68,
"learning_rate": 5.677466434383449e-07,
"loss": 0.3206,
"step": 2399
},
{
"epoch": 2.69,
"learning_rate": 5.63737023697205e-07,
"loss": 0.3347,
"step": 2400
},
{
"epoch": 2.69,
"learning_rate": 5.59741202124261e-07,
"loss": 0.3284,
"step": 2401
},
{
"epoch": 2.69,
"learning_rate": 5.557591845624e-07,
"loss": 0.3325,
"step": 2402
},
{
"epoch": 2.69,
"learning_rate": 5.517909768343255e-07,
"loss": 0.3247,
"step": 2403
},
{
"epoch": 2.69,
"learning_rate": 5.478365847425449e-07,
"loss": 0.332,
"step": 2404
},
{
"epoch": 2.69,
"learning_rate": 5.438960140693661e-07,
"loss": 0.3264,
"step": 2405
},
{
"epoch": 2.69,
"learning_rate": 5.399692705768844e-07,
"loss": 0.3171,
"step": 2406
},
{
"epoch": 2.69,
"learning_rate": 5.360563600069779e-07,
"loss": 0.3208,
"step": 2407
},
{
"epoch": 2.7,
"learning_rate": 5.321572880812965e-07,
"loss": 0.3225,
"step": 2408
},
{
"epoch": 2.7,
"learning_rate": 5.28272060501256e-07,
"loss": 0.3315,
"step": 2409
},
{
"epoch": 2.7,
"learning_rate": 5.244006829480275e-07,
"loss": 0.3342,
"step": 2410
},
{
"epoch": 2.7,
"learning_rate": 5.205431610825274e-07,
"loss": 0.3242,
"step": 2411
},
{
"epoch": 2.7,
"learning_rate": 5.166995005454167e-07,
"loss": 0.3237,
"step": 2412
},
{
"epoch": 2.7,
"learning_rate": 5.128697069570832e-07,
"loss": 0.3428,
"step": 2413
},
{
"epoch": 2.7,
"learning_rate": 5.090537859176426e-07,
"loss": 0.304,
"step": 2414
},
{
"epoch": 2.7,
"learning_rate": 5.052517430069204e-07,
"loss": 0.3186,
"step": 2415
},
{
"epoch": 2.7,
"learning_rate": 5.014635837844506e-07,
"loss": 0.3306,
"step": 2416
},
{
"epoch": 2.71,
"learning_rate": 4.976893137894645e-07,
"loss": 0.3372,
"step": 2417
},
{
"epoch": 2.71,
"learning_rate": 4.939289385408896e-07,
"loss": 0.3137,
"step": 2418
},
{
"epoch": 2.71,
"learning_rate": 4.901824635373275e-07,
"loss": 0.3235,
"step": 2419
},
{
"epoch": 2.71,
"learning_rate": 4.864498942570628e-07,
"loss": 0.3088,
"step": 2420
},
{
"epoch": 2.71,
"learning_rate": 4.827312361580383e-07,
"loss": 0.3354,
"step": 2421
},
{
"epoch": 2.71,
"learning_rate": 4.7902649467786e-07,
"loss": 0.3137,
"step": 2422
},
{
"epoch": 2.71,
"learning_rate": 4.753356752337834e-07,
"loss": 0.3262,
"step": 2423
},
{
"epoch": 2.71,
"learning_rate": 4.716587832227071e-07,
"loss": 0.3303,
"step": 2424
},
{
"epoch": 2.71,
"learning_rate": 4.679958240211635e-07,
"loss": 0.3198,
"step": 2425
},
{
"epoch": 2.72,
"learning_rate": 4.643468029853093e-07,
"loss": 0.3357,
"step": 2426
},
{
"epoch": 2.72,
"learning_rate": 4.6071172545092414e-07,
"loss": 0.3279,
"step": 2427
},
{
"epoch": 2.72,
"learning_rate": 4.570905967333994e-07,
"loss": 0.312,
"step": 2428
},
{
"epoch": 2.72,
"learning_rate": 4.5348342212772625e-07,
"loss": 0.3228,
"step": 2429
},
{
"epoch": 2.72,
"learning_rate": 4.4989020690849315e-07,
"loss": 0.3127,
"step": 2430
},
{
"epoch": 2.72,
"learning_rate": 4.4631095632987397e-07,
"loss": 0.3391,
"step": 2431
},
{
"epoch": 2.72,
"learning_rate": 4.4274567562562875e-07,
"loss": 0.3191,
"step": 2432
},
{
"epoch": 2.72,
"learning_rate": 4.391943700090839e-07,
"loss": 0.3223,
"step": 2433
},
{
"epoch": 2.72,
"learning_rate": 4.3565704467313565e-07,
"loss": 0.3137,
"step": 2434
},
{
"epoch": 2.73,
"learning_rate": 4.3213370479023074e-07,
"loss": 0.3306,
"step": 2435
},
{
"epoch": 2.73,
"learning_rate": 4.286243555123737e-07,
"loss": 0.3313,
"step": 2436
},
{
"epoch": 2.73,
"learning_rate": 4.2512900197110853e-07,
"loss": 0.3513,
"step": 2437
},
{
"epoch": 2.73,
"learning_rate": 4.2164764927751236e-07,
"loss": 0.333,
"step": 2438
},
{
"epoch": 2.73,
"learning_rate": 4.1818030252218976e-07,
"loss": 0.3093,
"step": 2439
},
{
"epoch": 2.73,
"learning_rate": 4.1472696677526513e-07,
"loss": 0.335,
"step": 2440
},
{
"epoch": 2.73,
"learning_rate": 4.1128764708637583e-07,
"loss": 0.3381,
"step": 2441
},
{
"epoch": 2.73,
"learning_rate": 4.0786234848466775e-07,
"loss": 0.3247,
"step": 2442
},
{
"epoch": 2.73,
"learning_rate": 4.0445107597877673e-07,
"loss": 0.334,
"step": 2443
},
{
"epoch": 2.74,
"learning_rate": 4.010538345568371e-07,
"loss": 0.3423,
"step": 2444
},
{
"epoch": 2.74,
"learning_rate": 3.976706291864596e-07,
"loss": 0.334,
"step": 2445
},
{
"epoch": 2.74,
"learning_rate": 3.9430146481473584e-07,
"loss": 0.3115,
"step": 2446
},
{
"epoch": 2.74,
"learning_rate": 3.909463463682228e-07,
"loss": 0.325,
"step": 2447
},
{
"epoch": 2.74,
"learning_rate": 3.8760527875293943e-07,
"loss": 0.3289,
"step": 2448
},
{
"epoch": 2.74,
"learning_rate": 3.842782668543599e-07,
"loss": 0.3247,
"step": 2449
},
{
"epoch": 2.74,
"learning_rate": 3.809653155374038e-07,
"loss": 0.3137,
"step": 2450
},
{
"epoch": 2.74,
"learning_rate": 3.7766642964643165e-07,
"loss": 0.3311,
"step": 2451
},
{
"epoch": 2.74,
"learning_rate": 3.743816140052392e-07,
"loss": 0.3208,
"step": 2452
},
{
"epoch": 2.75,
"learning_rate": 3.711108734170432e-07,
"loss": 0.3286,
"step": 2453
},
{
"epoch": 2.75,
"learning_rate": 3.678542126644813e-07,
"loss": 0.3496,
"step": 2454
},
{
"epoch": 2.75,
"learning_rate": 3.646116365096053e-07,
"loss": 0.3323,
"step": 2455
},
{
"epoch": 2.75,
"learning_rate": 3.613831496938691e-07,
"loss": 0.3396,
"step": 2456
},
{
"epoch": 2.75,
"learning_rate": 3.5816875693812316e-07,
"loss": 0.3425,
"step": 2457
},
{
"epoch": 2.75,
"learning_rate": 3.5496846294261203e-07,
"loss": 0.3398,
"step": 2458
},
{
"epoch": 2.75,
"learning_rate": 3.517822723869635e-07,
"loss": 0.3245,
"step": 2459
},
{
"epoch": 2.75,
"learning_rate": 3.486101899301797e-07,
"loss": 0.3469,
"step": 2460
},
{
"epoch": 2.75,
"learning_rate": 3.454522202106403e-07,
"loss": 0.3289,
"step": 2461
},
{
"epoch": 2.76,
"learning_rate": 3.4230836784608036e-07,
"loss": 0.3201,
"step": 2462
},
{
"epoch": 2.76,
"learning_rate": 3.3917863743359815e-07,
"loss": 0.3445,
"step": 2463
},
{
"epoch": 2.76,
"learning_rate": 3.360630335496362e-07,
"loss": 0.3303,
"step": 2464
},
{
"epoch": 2.76,
"learning_rate": 3.32961560749987e-07,
"loss": 0.3354,
"step": 2465
},
{
"epoch": 2.76,
"learning_rate": 3.298742235697749e-07,
"loss": 0.3379,
"step": 2466
},
{
"epoch": 2.76,
"learning_rate": 3.268010265234567e-07,
"loss": 0.3359,
"step": 2467
},
{
"epoch": 2.76,
"learning_rate": 3.23741974104812e-07,
"loss": 0.3379,
"step": 2468
},
{
"epoch": 2.76,
"learning_rate": 3.206970707869406e-07,
"loss": 0.3423,
"step": 2469
},
{
"epoch": 2.76,
"learning_rate": 3.176663210222475e-07,
"loss": 0.3264,
"step": 2470
},
{
"epoch": 2.77,
"learning_rate": 3.1464972924244333e-07,
"loss": 0.3237,
"step": 2471
},
{
"epoch": 2.77,
"learning_rate": 3.116472998585396e-07,
"loss": 0.3198,
"step": 2472
},
{
"epoch": 2.77,
"learning_rate": 3.0865903726083333e-07,
"loss": 0.3423,
"step": 2473
},
{
"epoch": 2.77,
"learning_rate": 3.056849458189115e-07,
"loss": 0.3542,
"step": 2474
},
{
"epoch": 2.77,
"learning_rate": 3.0272502988163645e-07,
"loss": 0.3223,
"step": 2475
},
{
"epoch": 2.77,
"learning_rate": 2.9977929377714376e-07,
"loss": 0.3262,
"step": 2476
},
{
"epoch": 2.77,
"learning_rate": 2.968477418128324e-07,
"loss": 0.3308,
"step": 2477
},
{
"epoch": 2.77,
"learning_rate": 2.939303782753611e-07,
"loss": 0.3198,
"step": 2478
},
{
"epoch": 2.77,
"learning_rate": 2.910272074306453e-07,
"loss": 0.3179,
"step": 2479
},
{
"epoch": 2.78,
"learning_rate": 2.8813823352384253e-07,
"loss": 0.3364,
"step": 2480
},
{
"epoch": 2.78,
"learning_rate": 2.8526346077935253e-07,
"loss": 0.3354,
"step": 2481
},
{
"epoch": 2.78,
"learning_rate": 2.8240289340080937e-07,
"loss": 0.3406,
"step": 2482
},
{
"epoch": 2.78,
"learning_rate": 2.795565355710761e-07,
"loss": 0.343,
"step": 2483
},
{
"epoch": 2.78,
"learning_rate": 2.767243914522377e-07,
"loss": 0.3174,
"step": 2484
},
{
"epoch": 2.78,
"learning_rate": 2.7390646518559496e-07,
"loss": 0.3318,
"step": 2485
},
{
"epoch": 2.78,
"learning_rate": 2.711027608916561e-07,
"loss": 0.3401,
"step": 2486
},
{
"epoch": 2.78,
"learning_rate": 2.6831328267013625e-07,
"loss": 0.313,
"step": 2487
},
{
"epoch": 2.78,
"learning_rate": 2.655380345999503e-07,
"loss": 0.3337,
"step": 2488
},
{
"epoch": 2.79,
"learning_rate": 2.6277702073919995e-07,
"loss": 0.3264,
"step": 2489
},
{
"epoch": 2.79,
"learning_rate": 2.6003024512517683e-07,
"loss": 0.3169,
"step": 2490
},
{
"epoch": 2.79,
"learning_rate": 2.5729771177435023e-07,
"loss": 0.3262,
"step": 2491
},
{
"epoch": 2.79,
"learning_rate": 2.5457942468236516e-07,
"loss": 0.3132,
"step": 2492
},
{
"epoch": 2.79,
"learning_rate": 2.5187538782403653e-07,
"loss": 0.3237,
"step": 2493
},
{
"epoch": 2.79,
"learning_rate": 2.4918560515333924e-07,
"loss": 0.311,
"step": 2494
},
{
"epoch": 2.79,
"learning_rate": 2.4651008060340486e-07,
"loss": 0.3384,
"step": 2495
},
{
"epoch": 2.79,
"learning_rate": 2.4384881808651727e-07,
"loss": 0.3328,
"step": 2496
},
{
"epoch": 2.79,
"learning_rate": 2.41201821494107e-07,
"loss": 0.3218,
"step": 2497
},
{
"epoch": 2.8,
"learning_rate": 2.385690946967423e-07,
"loss": 0.3335,
"step": 2498
},
{
"epoch": 2.8,
"learning_rate": 2.3595064154412374e-07,
"loss": 0.3196,
"step": 2499
},
{
"epoch": 2.8,
"learning_rate": 2.3334646586508525e-07,
"loss": 0.3411,
"step": 2500
},
{
"epoch": 2.8,
"learning_rate": 2.3075657146757858e-07,
"loss": 0.3496,
"step": 2501
},
{
"epoch": 2.8,
"learning_rate": 2.2818096213867657e-07,
"loss": 0.3433,
"step": 2502
},
{
"epoch": 2.8,
"learning_rate": 2.2561964164456108e-07,
"loss": 0.3203,
"step": 2503
},
{
"epoch": 2.8,
"learning_rate": 2.2307261373052058e-07,
"loss": 0.3376,
"step": 2504
},
{
"epoch": 2.8,
"learning_rate": 2.205398821209459e-07,
"loss": 0.3423,
"step": 2505
},
{
"epoch": 2.8,
"learning_rate": 2.1802145051932012e-07,
"loss": 0.3237,
"step": 2506
},
{
"epoch": 2.81,
"learning_rate": 2.1551732260821856e-07,
"loss": 0.3562,
"step": 2507
},
{
"epoch": 2.81,
"learning_rate": 2.1302750204930112e-07,
"loss": 0.3447,
"step": 2508
},
{
"epoch": 2.81,
"learning_rate": 2.105519924833055e-07,
"loss": 0.3179,
"step": 2509
},
{
"epoch": 2.81,
"learning_rate": 2.080907975300439e-07,
"loss": 0.3203,
"step": 2510
},
{
"epoch": 2.81,
"learning_rate": 2.0564392078839647e-07,
"loss": 0.3503,
"step": 2511
},
{
"epoch": 2.81,
"learning_rate": 2.0321136583630663e-07,
"loss": 0.3213,
"step": 2512
},
{
"epoch": 2.81,
"learning_rate": 2.0079313623077577e-07,
"loss": 0.3411,
"step": 2513
},
{
"epoch": 2.81,
"learning_rate": 1.9838923550785872e-07,
"loss": 0.3276,
"step": 2514
},
{
"epoch": 2.81,
"learning_rate": 1.9599966718265696e-07,
"loss": 0.3142,
"step": 2515
},
{
"epoch": 2.82,
"learning_rate": 1.9362443474931547e-07,
"loss": 0.3179,
"step": 2516
},
{
"epoch": 2.82,
"learning_rate": 1.91263541681016e-07,
"loss": 0.3442,
"step": 2517
},
{
"epoch": 2.82,
"learning_rate": 1.8891699142997266e-07,
"loss": 0.3198,
"step": 2518
},
{
"epoch": 2.82,
"learning_rate": 1.8658478742742624e-07,
"loss": 0.3457,
"step": 2519
},
{
"epoch": 2.82,
"learning_rate": 1.8426693308364108e-07,
"loss": 0.3257,
"step": 2520
},
{
"epoch": 2.82,
"learning_rate": 1.819634317878971e-07,
"loss": 0.3145,
"step": 2521
},
{
"epoch": 2.82,
"learning_rate": 1.7967428690848665e-07,
"loss": 0.3214,
"step": 2522
},
{
"epoch": 2.82,
"learning_rate": 1.7739950179271103e-07,
"loss": 0.3357,
"step": 2523
},
{
"epoch": 2.82,
"learning_rate": 1.7513907976687283e-07,
"loss": 0.3408,
"step": 2524
},
{
"epoch": 2.83,
"learning_rate": 1.728930241362725e-07,
"loss": 0.3218,
"step": 2525
},
{
"epoch": 2.83,
"learning_rate": 1.7066133818520402e-07,
"loss": 0.3259,
"step": 2526
},
{
"epoch": 2.83,
"learning_rate": 1.6844402517694702e-07,
"loss": 0.3247,
"step": 2527
},
{
"epoch": 2.83,
"learning_rate": 1.6624108835376685e-07,
"loss": 0.322,
"step": 2528
},
{
"epoch": 2.83,
"learning_rate": 1.6405253093690344e-07,
"loss": 0.3396,
"step": 2529
},
{
"epoch": 2.83,
"learning_rate": 1.6187835612657688e-07,
"loss": 0.3315,
"step": 2530
},
{
"epoch": 2.83,
"learning_rate": 1.5971856710196966e-07,
"loss": 0.3269,
"step": 2531
},
{
"epoch": 2.83,
"learning_rate": 1.5757316702123326e-07,
"loss": 0.325,
"step": 2532
},
{
"epoch": 2.83,
"learning_rate": 1.554421590214772e-07,
"loss": 0.3354,
"step": 2533
},
{
"epoch": 2.84,
"learning_rate": 1.5332554621876661e-07,
"loss": 0.3269,
"step": 2534
},
{
"epoch": 2.84,
"learning_rate": 1.5122333170811577e-07,
"loss": 0.3218,
"step": 2535
},
{
"epoch": 2.84,
"learning_rate": 1.4913551856348686e-07,
"loss": 0.3408,
"step": 2536
},
{
"epoch": 2.84,
"learning_rate": 1.4706210983778223e-07,
"loss": 0.3579,
"step": 2537
},
{
"epoch": 2.84,
"learning_rate": 1.4500310856284337e-07,
"loss": 0.3018,
"step": 2538
},
{
"epoch": 2.84,
"learning_rate": 1.429585177494419e-07,
"loss": 0.3364,
"step": 2539
},
{
"epoch": 2.84,
"learning_rate": 1.4092834038728077e-07,
"loss": 0.3245,
"step": 2540
},
{
"epoch": 2.84,
"learning_rate": 1.3891257944498416e-07,
"loss": 0.3337,
"step": 2541
},
{
"epoch": 2.84,
"learning_rate": 1.3691123787009764e-07,
"loss": 0.3269,
"step": 2542
},
{
"epoch": 2.85,
"learning_rate": 1.3492431858908027e-07,
"loss": 0.3125,
"step": 2543
},
{
"epoch": 2.85,
"learning_rate": 1.3295182450730472e-07,
"loss": 0.3284,
"step": 2544
},
{
"epoch": 2.85,
"learning_rate": 1.3099375850904815e-07,
"loss": 0.3389,
"step": 2545
},
{
"epoch": 2.85,
"learning_rate": 1.2905012345749147e-07,
"loss": 0.3372,
"step": 2546
},
{
"epoch": 2.85,
"learning_rate": 1.2712092219471228e-07,
"loss": 0.3308,
"step": 2547
},
{
"epoch": 2.85,
"learning_rate": 1.2520615754168408e-07,
"loss": 0.3074,
"step": 2548
},
{
"epoch": 2.85,
"learning_rate": 1.2330583229827053e-07,
"loss": 0.3357,
"step": 2549
},
{
"epoch": 2.85,
"learning_rate": 1.214199492432211e-07,
"loss": 0.3215,
"step": 2550
},
{
"epoch": 2.86,
"learning_rate": 1.1954851113416653e-07,
"loss": 0.3372,
"step": 2551
},
{
"epoch": 2.86,
"learning_rate": 1.1769152070761458e-07,
"loss": 0.3384,
"step": 2552
},
{
"epoch": 2.86,
"learning_rate": 1.1584898067894867e-07,
"loss": 0.3557,
"step": 2553
},
{
"epoch": 2.86,
"learning_rate": 1.1402089374242365e-07,
"loss": 0.3132,
"step": 2554
},
{
"epoch": 2.86,
"learning_rate": 1.1220726257115455e-07,
"loss": 0.3313,
"step": 2555
},
{
"epoch": 2.86,
"learning_rate": 1.1040808981712448e-07,
"loss": 0.3274,
"step": 2556
},
{
"epoch": 2.86,
"learning_rate": 1.0862337811117118e-07,
"loss": 0.335,
"step": 2557
},
{
"epoch": 2.86,
"learning_rate": 1.0685313006299047e-07,
"loss": 0.3416,
"step": 2558
},
{
"epoch": 2.86,
"learning_rate": 1.0509734826112395e-07,
"loss": 0.3242,
"step": 2559
},
{
"epoch": 2.87,
"learning_rate": 1.0335603527296123e-07,
"loss": 0.3223,
"step": 2560
},
{
"epoch": 2.87,
"learning_rate": 1.0162919364473778e-07,
"loss": 0.3311,
"step": 2561
},
{
"epoch": 2.87,
"learning_rate": 9.991682590152707e-08,
"loss": 0.3125,
"step": 2562
},
{
"epoch": 2.87,
"learning_rate": 9.821893454723508e-08,
"loss": 0.3521,
"step": 2563
},
{
"epoch": 2.87,
"learning_rate": 9.65355220646036e-08,
"loss": 0.332,
"step": 2564
},
{
"epoch": 2.87,
"learning_rate": 9.486659091520244e-08,
"loss": 0.3303,
"step": 2565
},
{
"epoch": 2.87,
"learning_rate": 9.321214353942177e-08,
"loss": 0.3301,
"step": 2566
},
{
"epoch": 2.87,
"learning_rate": 9.157218235647746e-08,
"loss": 0.322,
"step": 2567
},
{
"epoch": 2.87,
"learning_rate": 8.994670976440357e-08,
"loss": 0.3259,
"step": 2568
},
{
"epoch": 2.88,
"learning_rate": 8.833572814004321e-08,
"loss": 0.3374,
"step": 2569
},
{
"epoch": 2.88,
"learning_rate": 8.67392398390532e-08,
"loss": 0.3323,
"step": 2570
},
{
"epoch": 2.88,
"learning_rate": 8.515724719589835e-08,
"loss": 0.3289,
"step": 2571
},
{
"epoch": 2.88,
"learning_rate": 8.358975252384604e-08,
"loss": 0.3167,
"step": 2572
},
{
"epoch": 2.88,
"learning_rate": 8.203675811496503e-08,
"loss": 0.3105,
"step": 2573
},
{
"epoch": 2.88,
"learning_rate": 8.04982662401188e-08,
"loss": 0.3242,
"step": 2574
},
{
"epoch": 2.88,
"learning_rate": 7.89742791489656e-08,
"loss": 0.3313,
"step": 2575
},
{
"epoch": 2.88,
"learning_rate": 7.746479906995618e-08,
"loss": 0.3223,
"step": 2576
},
{
"epoch": 2.88,
"learning_rate": 7.596982821032495e-08,
"loss": 0.3071,
"step": 2577
},
{
"epoch": 2.89,
"learning_rate": 7.448936875609214e-08,
"loss": 0.3323,
"step": 2578
},
{
"epoch": 2.89,
"learning_rate": 7.302342287205944e-08,
"loss": 0.3369,
"step": 2579
},
{
"epoch": 2.89,
"learning_rate": 7.157199270180326e-08,
"loss": 0.3293,
"step": 2580
},
{
"epoch": 2.89,
"learning_rate": 7.013508036767813e-08,
"loss": 0.3438,
"step": 2581
},
{
"epoch": 2.89,
"learning_rate": 6.871268797080777e-08,
"loss": 0.3328,
"step": 2582
},
{
"epoch": 2.89,
"learning_rate": 6.730481759108287e-08,
"loss": 0.3308,
"step": 2583
},
{
"epoch": 2.89,
"learning_rate": 6.591147128716225e-08,
"loss": 0.3105,
"step": 2584
},
{
"epoch": 2.89,
"learning_rate": 6.4532651096465e-08,
"loss": 0.3276,
"step": 2585
},
{
"epoch": 2.89,
"learning_rate": 6.316835903516949e-08,
"loss": 0.3154,
"step": 2586
},
{
"epoch": 2.9,
"learning_rate": 6.181859709821103e-08,
"loss": 0.342,
"step": 2587
},
{
"epoch": 2.9,
"learning_rate": 6.048336725927751e-08,
"loss": 0.3296,
"step": 2588
},
{
"epoch": 2.9,
"learning_rate": 5.9162671470809343e-08,
"loss": 0.3376,
"step": 2589
},
{
"epoch": 2.9,
"learning_rate": 5.785651166399064e-08,
"loss": 0.3281,
"step": 2590
},
{
"epoch": 2.9,
"learning_rate": 5.656488974875474e-08,
"loss": 0.3188,
"step": 2591
},
{
"epoch": 2.9,
"learning_rate": 5.528780761377306e-08,
"loss": 0.3225,
"step": 2592
},
{
"epoch": 2.9,
"learning_rate": 5.4025267126459615e-08,
"loss": 0.3093,
"step": 2593
},
{
"epoch": 2.9,
"learning_rate": 5.277727013296097e-08,
"loss": 0.3071,
"step": 2594
},
{
"epoch": 2.9,
"learning_rate": 5.15438184581607e-08,
"loss": 0.343,
"step": 2595
},
{
"epoch": 2.91,
"learning_rate": 5.0324913905674955e-08,
"loss": 0.3135,
"step": 2596
},
{
"epoch": 2.91,
"learning_rate": 4.912055825784245e-08,
"loss": 0.3289,
"step": 2597
},
{
"epoch": 2.91,
"learning_rate": 4.7930753275733376e-08,
"loss": 0.3184,
"step": 2598
},
{
"epoch": 2.91,
"learning_rate": 4.675550069913826e-08,
"loss": 0.3354,
"step": 2599
},
{
"epoch": 2.91,
"learning_rate": 4.559480224656909e-08,
"loss": 0.3191,
"step": 2600
},
{
"epoch": 2.91,
"learning_rate": 4.444865961525824e-08,
"loss": 0.333,
"step": 2601
},
{
"epoch": 2.91,
"learning_rate": 4.331707448114952e-08,
"loss": 0.3584,
"step": 2602
},
{
"epoch": 2.91,
"learning_rate": 4.220004849890269e-08,
"loss": 0.3301,
"step": 2603
},
{
"epoch": 2.91,
"learning_rate": 4.109758330188895e-08,
"loss": 0.324,
"step": 2604
},
{
"epoch": 2.92,
"learning_rate": 4.000968050218657e-08,
"loss": 0.314,
"step": 2605
},
{
"epoch": 2.92,
"learning_rate": 3.893634169058192e-08,
"loss": 0.3066,
"step": 2606
},
{
"epoch": 2.92,
"learning_rate": 3.787756843656287e-08,
"loss": 0.3396,
"step": 2607
},
{
"epoch": 2.92,
"learning_rate": 3.68333622883188e-08,
"loss": 0.3167,
"step": 2608
},
{
"epoch": 2.92,
"learning_rate": 3.580372477274052e-08,
"loss": 0.3303,
"step": 2609
},
{
"epoch": 2.92,
"learning_rate": 3.4788657395414813e-08,
"loss": 0.3411,
"step": 2610
},
{
"epoch": 2.92,
"learning_rate": 3.378816164062326e-08,
"loss": 0.333,
"step": 2611
},
{
"epoch": 2.92,
"learning_rate": 3.280223897133894e-08,
"loss": 0.3352,
"step": 2612
},
{
"epoch": 2.92,
"learning_rate": 3.1830890829226416e-08,
"loss": 0.334,
"step": 2613
},
{
"epoch": 2.93,
"learning_rate": 3.087411863464063e-08,
"loss": 0.3452,
"step": 2614
},
{
"epoch": 2.93,
"learning_rate": 2.993192378662024e-08,
"loss": 0.3643,
"step": 2615
},
{
"epoch": 2.93,
"learning_rate": 2.9004307662887642e-08,
"loss": 0.3086,
"step": 2616
},
{
"epoch": 2.93,
"learning_rate": 2.8091271619850036e-08,
"loss": 0.3384,
"step": 2617
},
{
"epoch": 2.93,
"learning_rate": 2.7192816992592798e-08,
"loss": 0.3367,
"step": 2618
},
{
"epoch": 2.93,
"learning_rate": 2.6308945094880577e-08,
"loss": 0.3123,
"step": 2619
},
{
"epoch": 2.93,
"learning_rate": 2.54396572191562e-08,
"loss": 0.3232,
"step": 2620
},
{
"epoch": 2.93,
"learning_rate": 2.4584954636532875e-08,
"loss": 0.3193,
"step": 2621
},
{
"epoch": 2.93,
"learning_rate": 2.3744838596799767e-08,
"loss": 0.3203,
"step": 2622
},
{
"epoch": 2.94,
"learning_rate": 2.2919310328416433e-08,
"loss": 0.3167,
"step": 2623
},
{
"epoch": 2.94,
"learning_rate": 2.210837103850949e-08,
"loss": 0.3298,
"step": 2624
},
{
"epoch": 2.94,
"learning_rate": 2.1312021912875957e-08,
"loss": 0.3303,
"step": 2625
},
{
"epoch": 2.94,
"learning_rate": 2.0530264115974362e-08,
"loss": 0.3301,
"step": 2626
},
{
"epoch": 2.94,
"learning_rate": 1.9763098790932524e-08,
"loss": 0.3201,
"step": 2627
},
{
"epoch": 2.94,
"learning_rate": 1.901052705953532e-08,
"loss": 0.3268,
"step": 2628
},
{
"epoch": 2.94,
"learning_rate": 1.8272550022230274e-08,
"loss": 0.3369,
"step": 2629
},
{
"epoch": 2.94,
"learning_rate": 1.754916875812529e-08,
"loss": 0.3296,
"step": 2630
},
{
"epoch": 2.94,
"learning_rate": 1.684038432498092e-08,
"loss": 0.3223,
"step": 2631
},
{
"epoch": 2.95,
"learning_rate": 1.6146197759220328e-08,
"loss": 0.3286,
"step": 2632
},
{
"epoch": 2.95,
"learning_rate": 1.5466610075914878e-08,
"loss": 0.3345,
"step": 2633
},
{
"epoch": 2.95,
"learning_rate": 1.4801622268791893e-08,
"loss": 0.312,
"step": 2634
},
{
"epoch": 2.95,
"learning_rate": 1.4151235310229105e-08,
"loss": 0.3267,
"step": 2635
},
{
"epoch": 2.95,
"learning_rate": 1.351545015125466e-08,
"loss": 0.3347,
"step": 2636
},
{
"epoch": 2.95,
"learning_rate": 1.2894267721543786e-08,
"loss": 0.3416,
"step": 2637
},
{
"epoch": 2.95,
"learning_rate": 1.2287688929422115e-08,
"loss": 0.3142,
"step": 2638
},
{
"epoch": 2.95,
"learning_rate": 1.1695714661856817e-08,
"loss": 0.3096,
"step": 2639
},
{
"epoch": 2.95,
"learning_rate": 1.1118345784463247e-08,
"loss": 0.3347,
"step": 2640
},
{
"epoch": 2.96,
"learning_rate": 1.0555583141498293e-08,
"loss": 0.314,
"step": 2641
},
{
"epoch": 2.96,
"learning_rate": 1.0007427555861483e-08,
"loss": 0.3503,
"step": 2642
},
{
"epoch": 2.96,
"learning_rate": 9.473879829091648e-09,
"loss": 0.3418,
"step": 2643
},
{
"epoch": 2.96,
"learning_rate": 8.954940741369156e-09,
"loss": 0.314,
"step": 2644
},
{
"epoch": 2.96,
"learning_rate": 8.45061105151257e-09,
"loss": 0.3491,
"step": 2645
},
{
"epoch": 2.96,
"learning_rate": 7.960891496977541e-09,
"loss": 0.3481,
"step": 2646
},
{
"epoch": 2.96,
"learning_rate": 7.485782793856811e-09,
"loss": 0.3237,
"step": 2647
},
{
"epoch": 2.96,
"learning_rate": 7.025285636876877e-09,
"loss": 0.3406,
"step": 2648
},
{
"epoch": 2.96,
"learning_rate": 6.579400699397998e-09,
"loss": 0.3235,
"step": 2649
},
{
"epoch": 2.97,
"learning_rate": 6.148128633417516e-09,
"loss": 0.3264,
"step": 2650
},
{
"epoch": 2.97,
"learning_rate": 5.731470069562095e-09,
"loss": 0.3047,
"step": 2651
},
{
"epoch": 2.97,
"learning_rate": 5.329425617088824e-09,
"loss": 0.3169,
"step": 2652
},
{
"epoch": 2.97,
"learning_rate": 4.941995863888549e-09,
"loss": 0.3152,
"step": 2653
},
{
"epoch": 2.97,
"learning_rate": 4.569181376480325e-09,
"loss": 0.3291,
"step": 2654
},
{
"epoch": 2.97,
"learning_rate": 4.2109827000103024e-09,
"loss": 0.3372,
"step": 2655
},
{
"epoch": 2.97,
"learning_rate": 3.867400358255058e-09,
"loss": 0.3174,
"step": 2656
},
{
"epoch": 2.97,
"learning_rate": 3.5384348536182667e-09,
"loss": 0.3242,
"step": 2657
},
{
"epoch": 2.97,
"learning_rate": 3.224086667128479e-09,
"loss": 0.3501,
"step": 2658
},
{
"epoch": 2.98,
"learning_rate": 2.924356258440231e-09,
"loss": 0.3191,
"step": 2659
},
{
"epoch": 2.98,
"learning_rate": 2.6392440658362663e-09,
"loss": 0.3186,
"step": 2660
},
{
"epoch": 2.98,
"learning_rate": 2.3687505062208737e-09,
"loss": 0.3013,
"step": 2661
},
{
"epoch": 2.98,
"learning_rate": 2.112875975122108e-09,
"loss": 0.3193,
"step": 2662
},
{
"epoch": 2.98,
"learning_rate": 1.871620846694011e-09,
"loss": 0.3206,
"step": 2663
},
{
"epoch": 2.98,
"learning_rate": 1.644985473709948e-09,
"loss": 0.3323,
"step": 2664
},
{
"epoch": 2.98,
"learning_rate": 1.4329701875681613e-09,
"loss": 0.3333,
"step": 2665
},
{
"epoch": 2.98,
"learning_rate": 1.2355752982884383e-09,
"loss": 0.3464,
"step": 2666
},
{
"epoch": 2.98,
"learning_rate": 1.0528010945098921e-09,
"loss": 0.3174,
"step": 2667
},
{
"epoch": 2.99,
"learning_rate": 8.846478434942906e-10,
"loss": 0.3157,
"step": 2668
},
{
"epoch": 2.99,
"learning_rate": 7.311157911249478e-10,
"loss": 0.3379,
"step": 2669
},
{
"epoch": 2.99,
"learning_rate": 5.922051619033919e-10,
"loss": 0.3276,
"step": 2670
},
{
"epoch": 2.99,
"learning_rate": 4.679161589504766e-10,
"loss": 0.3271,
"step": 2671
},
{
"epoch": 2.99,
"learning_rate": 3.5824896400860064e-10,
"loss": 0.3296,
"step": 2672
},
{
"epoch": 2.99,
"learning_rate": 2.632037374383778e-10,
"loss": 0.3157,
"step": 2673
},
{
"epoch": 2.99,
"learning_rate": 1.8278061821863647e-10,
"loss": 0.3359,
"step": 2674
},
{
"epoch": 2.99,
"learning_rate": 1.1697972394975055e-10,
"loss": 0.3118,
"step": 2675
},
{
"epoch": 2.99,
"learning_rate": 6.580115084919847e-11,
"loss": 0.3196,
"step": 2676
},
{
"epoch": 3.0,
"learning_rate": 2.924497375045299e-11,
"loss": 0.3159,
"step": 2677
},
{
"epoch": 3.0,
"learning_rate": 7.311246110752735e-12,
"loss": 0.3318,
"step": 2678
},
{
"epoch": 3.0,
"learning_rate": 0.0,
"loss": 0.345,
"step": 2679
},
{
"epoch": 3.0,
"step": 2679,
"total_flos": 3647990011527168.0,
"train_loss": 0.5298004663003919,
"train_runtime": 43027.8391,
"train_samples_per_second": 7.972,
"train_steps_per_second": 0.062
}
],
"max_steps": 2679,
"num_train_epochs": 3,
"total_flos": 3647990011527168.0,
"trial_name": null,
"trial_params": null
}