tsbpp's picture
Upload folder using huggingface_hub
e087fa5 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 1440,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 9.090909090909091e-07,
"loss": 5.3453,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 1.8181818181818183e-06,
"loss": 5.1253,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 2.7272727272727272e-06,
"loss": 4.0702,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 3.6363636363636366e-06,
"loss": 3.2529,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 4.5454545454545455e-06,
"loss": 2.6966,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 5.4545454545454545e-06,
"loss": 2.356,
"step": 6
},
{
"epoch": 0.0,
"learning_rate": 6.363636363636364e-06,
"loss": 2.0962,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 7.272727272727273e-06,
"loss": 1.8203,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 8.181818181818183e-06,
"loss": 1.8258,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 9.090909090909091e-06,
"loss": 1.5451,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 1e-05,
"loss": 1.6561,
"step": 11
},
{
"epoch": 0.01,
"learning_rate": 1.0909090909090909e-05,
"loss": 1.4911,
"step": 12
},
{
"epoch": 0.01,
"learning_rate": 1.181818181818182e-05,
"loss": 1.4147,
"step": 13
},
{
"epoch": 0.01,
"learning_rate": 1.2727272727272728e-05,
"loss": 1.2877,
"step": 14
},
{
"epoch": 0.01,
"learning_rate": 1.3636363636363637e-05,
"loss": 1.2451,
"step": 15
},
{
"epoch": 0.01,
"learning_rate": 1.4545454545454546e-05,
"loss": 1.2441,
"step": 16
},
{
"epoch": 0.01,
"learning_rate": 1.5454545454545454e-05,
"loss": 1.1645,
"step": 17
},
{
"epoch": 0.01,
"learning_rate": 1.6363636363636366e-05,
"loss": 1.1415,
"step": 18
},
{
"epoch": 0.01,
"learning_rate": 1.7272727272727274e-05,
"loss": 1.1302,
"step": 19
},
{
"epoch": 0.01,
"learning_rate": 1.8181818181818182e-05,
"loss": 1.1778,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 1.9090909090909094e-05,
"loss": 1.1079,
"step": 21
},
{
"epoch": 0.02,
"learning_rate": 2e-05,
"loss": 1.0115,
"step": 22
},
{
"epoch": 0.02,
"learning_rate": 2.090909090909091e-05,
"loss": 1.0145,
"step": 23
},
{
"epoch": 0.02,
"learning_rate": 2.1818181818181818e-05,
"loss": 1.0783,
"step": 24
},
{
"epoch": 0.02,
"learning_rate": 2.2727272727272733e-05,
"loss": 0.9615,
"step": 25
},
{
"epoch": 0.02,
"learning_rate": 2.363636363636364e-05,
"loss": 0.9959,
"step": 26
},
{
"epoch": 0.02,
"learning_rate": 2.454545454545455e-05,
"loss": 0.9886,
"step": 27
},
{
"epoch": 0.02,
"learning_rate": 2.5454545454545457e-05,
"loss": 1.0258,
"step": 28
},
{
"epoch": 0.02,
"learning_rate": 2.6363636363636365e-05,
"loss": 1.0281,
"step": 29
},
{
"epoch": 0.02,
"learning_rate": 2.7272727272727273e-05,
"loss": 0.9637,
"step": 30
},
{
"epoch": 0.02,
"learning_rate": 2.8181818181818185e-05,
"loss": 0.8955,
"step": 31
},
{
"epoch": 0.02,
"learning_rate": 2.9090909090909093e-05,
"loss": 0.9715,
"step": 32
},
{
"epoch": 0.02,
"learning_rate": 3.0000000000000004e-05,
"loss": 0.9293,
"step": 33
},
{
"epoch": 0.02,
"learning_rate": 3.090909090909091e-05,
"loss": 0.9427,
"step": 34
},
{
"epoch": 0.02,
"learning_rate": 3.181818181818182e-05,
"loss": 0.9209,
"step": 35
},
{
"epoch": 0.03,
"learning_rate": 3.272727272727273e-05,
"loss": 0.834,
"step": 36
},
{
"epoch": 0.03,
"learning_rate": 3.363636363636364e-05,
"loss": 0.913,
"step": 37
},
{
"epoch": 0.03,
"learning_rate": 3.454545454545455e-05,
"loss": 0.9118,
"step": 38
},
{
"epoch": 0.03,
"learning_rate": 3.545454545454546e-05,
"loss": 0.8955,
"step": 39
},
{
"epoch": 0.03,
"learning_rate": 3.6363636363636364e-05,
"loss": 0.9402,
"step": 40
},
{
"epoch": 0.03,
"learning_rate": 3.7272727272727276e-05,
"loss": 0.8874,
"step": 41
},
{
"epoch": 0.03,
"learning_rate": 3.818181818181819e-05,
"loss": 0.937,
"step": 42
},
{
"epoch": 0.03,
"learning_rate": 3.909090909090909e-05,
"loss": 0.8717,
"step": 43
},
{
"epoch": 0.03,
"learning_rate": 4e-05,
"loss": 0.9261,
"step": 44
},
{
"epoch": 0.03,
"learning_rate": 3.999994935591541e-05,
"loss": 0.8902,
"step": 45
},
{
"epoch": 0.03,
"learning_rate": 3.999979742391812e-05,
"loss": 0.9618,
"step": 46
},
{
"epoch": 0.03,
"learning_rate": 3.999954420477757e-05,
"loss": 0.885,
"step": 47
},
{
"epoch": 0.03,
"learning_rate": 3.9999189699776166e-05,
"loss": 0.9618,
"step": 48
},
{
"epoch": 0.03,
"learning_rate": 3.9998733910709277e-05,
"loss": 0.8465,
"step": 49
},
{
"epoch": 0.03,
"learning_rate": 3.9998176839885196e-05,
"loss": 0.8727,
"step": 50
},
{
"epoch": 0.04,
"learning_rate": 3.9997518490125166e-05,
"loss": 0.8631,
"step": 51
},
{
"epoch": 0.04,
"learning_rate": 3.999675886476332e-05,
"loss": 0.9446,
"step": 52
},
{
"epoch": 0.04,
"learning_rate": 3.9995897967646725e-05,
"loss": 0.9174,
"step": 53
},
{
"epoch": 0.04,
"learning_rate": 3.999493580313532e-05,
"loss": 0.8519,
"step": 54
},
{
"epoch": 0.04,
"learning_rate": 3.9993872376101894e-05,
"loss": 0.9058,
"step": 55
},
{
"epoch": 0.04,
"learning_rate": 3.9992707691932067e-05,
"loss": 0.8916,
"step": 56
},
{
"epoch": 0.04,
"learning_rate": 3.999144175652428e-05,
"loss": 0.8741,
"step": 57
},
{
"epoch": 0.04,
"learning_rate": 3.999007457628976e-05,
"loss": 0.9009,
"step": 58
},
{
"epoch": 0.04,
"learning_rate": 3.998860615815246e-05,
"loss": 0.9116,
"step": 59
},
{
"epoch": 0.04,
"learning_rate": 3.9987036509549034e-05,
"loss": 0.9136,
"step": 60
},
{
"epoch": 0.04,
"learning_rate": 3.998536563842884e-05,
"loss": 0.885,
"step": 61
},
{
"epoch": 0.04,
"learning_rate": 3.998359355325384e-05,
"loss": 0.9093,
"step": 62
},
{
"epoch": 0.04,
"learning_rate": 3.998172026299861e-05,
"loss": 0.9417,
"step": 63
},
{
"epoch": 0.04,
"learning_rate": 3.997974577715026e-05,
"loss": 0.8605,
"step": 64
},
{
"epoch": 0.05,
"learning_rate": 3.9977670105708377e-05,
"loss": 0.8808,
"step": 65
},
{
"epoch": 0.05,
"learning_rate": 3.997549325918501e-05,
"loss": 0.9404,
"step": 66
},
{
"epoch": 0.05,
"learning_rate": 3.997321524860461e-05,
"loss": 0.8573,
"step": 67
},
{
"epoch": 0.05,
"learning_rate": 3.997083608550395e-05,
"loss": 0.8496,
"step": 68
},
{
"epoch": 0.05,
"learning_rate": 3.996835578193208e-05,
"loss": 0.8745,
"step": 69
},
{
"epoch": 0.05,
"learning_rate": 3.996577435045027e-05,
"loss": 0.8816,
"step": 70
},
{
"epoch": 0.05,
"learning_rate": 3.996309180413195e-05,
"loss": 0.9461,
"step": 71
},
{
"epoch": 0.05,
"learning_rate": 3.996030815656262e-05,
"loss": 0.8635,
"step": 72
},
{
"epoch": 0.05,
"learning_rate": 3.995742342183982e-05,
"loss": 0.9098,
"step": 73
},
{
"epoch": 0.05,
"learning_rate": 3.9954437614573015e-05,
"loss": 0.8337,
"step": 74
},
{
"epoch": 0.05,
"learning_rate": 3.9951350749883555e-05,
"loss": 0.8332,
"step": 75
},
{
"epoch": 0.05,
"learning_rate": 3.994816284340459e-05,
"loss": 0.8349,
"step": 76
},
{
"epoch": 0.05,
"learning_rate": 3.9944873911280976e-05,
"loss": 0.7963,
"step": 77
},
{
"epoch": 0.05,
"learning_rate": 3.99414839701692e-05,
"loss": 0.8643,
"step": 78
},
{
"epoch": 0.05,
"learning_rate": 3.993799303723733e-05,
"loss": 0.8545,
"step": 79
},
{
"epoch": 0.06,
"learning_rate": 3.993440113016485e-05,
"loss": 0.8697,
"step": 80
},
{
"epoch": 0.06,
"learning_rate": 3.993070826714267e-05,
"loss": 0.9175,
"step": 81
},
{
"epoch": 0.06,
"learning_rate": 3.9926914466872936e-05,
"loss": 0.8908,
"step": 82
},
{
"epoch": 0.06,
"learning_rate": 3.9923019748569015e-05,
"loss": 0.8888,
"step": 83
},
{
"epoch": 0.06,
"learning_rate": 3.991902413195535e-05,
"loss": 0.8426,
"step": 84
},
{
"epoch": 0.06,
"learning_rate": 3.9914927637267366e-05,
"loss": 0.9248,
"step": 85
},
{
"epoch": 0.06,
"learning_rate": 3.991073028525139e-05,
"loss": 0.8102,
"step": 86
},
{
"epoch": 0.06,
"learning_rate": 3.990643209716454e-05,
"loss": 0.8807,
"step": 87
},
{
"epoch": 0.06,
"learning_rate": 3.990203309477457e-05,
"loss": 0.9009,
"step": 88
},
{
"epoch": 0.06,
"learning_rate": 3.989753330035985e-05,
"loss": 0.8692,
"step": 89
},
{
"epoch": 0.06,
"learning_rate": 3.989293273670916e-05,
"loss": 0.907,
"step": 90
},
{
"epoch": 0.06,
"learning_rate": 3.988823142712165e-05,
"loss": 0.8408,
"step": 91
},
{
"epoch": 0.06,
"learning_rate": 3.9883429395406666e-05,
"loss": 0.9196,
"step": 92
},
{
"epoch": 0.06,
"learning_rate": 3.987852666588364e-05,
"loss": 0.889,
"step": 93
},
{
"epoch": 0.07,
"learning_rate": 3.9873523263382015e-05,
"loss": 0.887,
"step": 94
},
{
"epoch": 0.07,
"learning_rate": 3.9868419213241064e-05,
"loss": 0.8858,
"step": 95
},
{
"epoch": 0.07,
"learning_rate": 3.986321454130978e-05,
"loss": 0.8356,
"step": 96
},
{
"epoch": 0.07,
"learning_rate": 3.9857909273946747e-05,
"loss": 0.9009,
"step": 97
},
{
"epoch": 0.07,
"learning_rate": 3.985250343802e-05,
"loss": 0.8281,
"step": 98
},
{
"epoch": 0.07,
"learning_rate": 3.984699706090691e-05,
"loss": 0.9562,
"step": 99
},
{
"epoch": 0.07,
"learning_rate": 3.9841390170494024e-05,
"loss": 0.8976,
"step": 100
},
{
"epoch": 0.07,
"learning_rate": 3.9835682795176905e-05,
"loss": 0.8766,
"step": 101
},
{
"epoch": 0.07,
"learning_rate": 3.982987496386004e-05,
"loss": 0.9062,
"step": 102
},
{
"epoch": 0.07,
"learning_rate": 3.982396670595668e-05,
"loss": 0.8528,
"step": 103
},
{
"epoch": 0.07,
"learning_rate": 3.9817958051388624e-05,
"loss": 0.8474,
"step": 104
},
{
"epoch": 0.07,
"learning_rate": 3.981184903058618e-05,
"loss": 0.8442,
"step": 105
},
{
"epoch": 0.07,
"learning_rate": 3.980563967448791e-05,
"loss": 0.8862,
"step": 106
},
{
"epoch": 0.07,
"learning_rate": 3.979933001454053e-05,
"loss": 0.8997,
"step": 107
},
{
"epoch": 0.07,
"learning_rate": 3.979292008269874e-05,
"loss": 0.8431,
"step": 108
},
{
"epoch": 0.08,
"learning_rate": 3.978640991142505e-05,
"loss": 0.8364,
"step": 109
},
{
"epoch": 0.08,
"learning_rate": 3.9779799533689634e-05,
"loss": 0.8622,
"step": 110
},
{
"epoch": 0.08,
"learning_rate": 3.9773088982970135e-05,
"loss": 0.8664,
"step": 111
},
{
"epoch": 0.08,
"learning_rate": 3.9766278293251526e-05,
"loss": 0.8795,
"step": 112
},
{
"epoch": 0.08,
"learning_rate": 3.9759367499025924e-05,
"loss": 0.8836,
"step": 113
},
{
"epoch": 0.08,
"learning_rate": 3.9752356635292405e-05,
"loss": 0.9004,
"step": 114
},
{
"epoch": 0.08,
"learning_rate": 3.974524573755686e-05,
"loss": 0.8744,
"step": 115
},
{
"epoch": 0.08,
"learning_rate": 3.9738034841831776e-05,
"loss": 0.8366,
"step": 116
},
{
"epoch": 0.08,
"learning_rate": 3.9730723984636064e-05,
"loss": 0.9257,
"step": 117
},
{
"epoch": 0.08,
"learning_rate": 3.9723313202994904e-05,
"loss": 0.8926,
"step": 118
},
{
"epoch": 0.08,
"learning_rate": 3.971580253443951e-05,
"loss": 0.8977,
"step": 119
},
{
"epoch": 0.08,
"learning_rate": 3.970819201700699e-05,
"loss": 0.8388,
"step": 120
},
{
"epoch": 0.08,
"learning_rate": 3.970048168924009e-05,
"loss": 0.8462,
"step": 121
},
{
"epoch": 0.08,
"learning_rate": 3.9692671590187093e-05,
"loss": 0.8618,
"step": 122
},
{
"epoch": 0.09,
"learning_rate": 3.96847617594015e-05,
"loss": 0.8218,
"step": 123
},
{
"epoch": 0.09,
"learning_rate": 3.967675223694193e-05,
"loss": 0.8435,
"step": 124
},
{
"epoch": 0.09,
"learning_rate": 3.966864306337189e-05,
"loss": 0.8531,
"step": 125
},
{
"epoch": 0.09,
"learning_rate": 3.9660434279759536e-05,
"loss": 0.8747,
"step": 126
},
{
"epoch": 0.09,
"learning_rate": 3.965212592767751e-05,
"loss": 0.8339,
"step": 127
},
{
"epoch": 0.09,
"learning_rate": 3.964371804920269e-05,
"loss": 0.8393,
"step": 128
},
{
"epoch": 0.09,
"learning_rate": 3.9635210686916016e-05,
"loss": 0.7817,
"step": 129
},
{
"epoch": 0.09,
"learning_rate": 3.962660388390224e-05,
"loss": 0.8619,
"step": 130
},
{
"epoch": 0.09,
"learning_rate": 3.9617897683749726e-05,
"loss": 0.8984,
"step": 131
},
{
"epoch": 0.09,
"learning_rate": 3.960909213055023e-05,
"loss": 0.8824,
"step": 132
},
{
"epoch": 0.09,
"learning_rate": 3.960018726889868e-05,
"loss": 0.9039,
"step": 133
},
{
"epoch": 0.09,
"learning_rate": 3.959118314389291e-05,
"loss": 0.8326,
"step": 134
},
{
"epoch": 0.09,
"learning_rate": 3.958207980113351e-05,
"loss": 0.864,
"step": 135
},
{
"epoch": 0.09,
"learning_rate": 3.957287728672352e-05,
"loss": 0.8431,
"step": 136
},
{
"epoch": 0.1,
"learning_rate": 3.956357564726822e-05,
"loss": 0.8844,
"step": 137
},
{
"epoch": 0.1,
"learning_rate": 3.955417492987493e-05,
"loss": 0.8725,
"step": 138
},
{
"epoch": 0.1,
"learning_rate": 3.95446751821527e-05,
"loss": 0.8425,
"step": 139
},
{
"epoch": 0.1,
"learning_rate": 3.9535076452212156e-05,
"loss": 0.8689,
"step": 140
},
{
"epoch": 0.1,
"learning_rate": 3.952537878866517e-05,
"loss": 0.8242,
"step": 141
},
{
"epoch": 0.1,
"learning_rate": 3.951558224062469e-05,
"loss": 0.8405,
"step": 142
},
{
"epoch": 0.1,
"learning_rate": 3.9505686857704416e-05,
"loss": 0.8483,
"step": 143
},
{
"epoch": 0.1,
"learning_rate": 3.949569269001861e-05,
"loss": 0.8366,
"step": 144
},
{
"epoch": 0.1,
"learning_rate": 3.948559978818184e-05,
"loss": 0.8115,
"step": 145
},
{
"epoch": 0.1,
"learning_rate": 3.947540820330867e-05,
"loss": 0.8556,
"step": 146
},
{
"epoch": 0.1,
"learning_rate": 3.9465117987013445e-05,
"loss": 0.8732,
"step": 147
},
{
"epoch": 0.1,
"learning_rate": 3.9454729191410025e-05,
"loss": 0.8313,
"step": 148
},
{
"epoch": 0.1,
"learning_rate": 3.944424186911152e-05,
"loss": 0.8261,
"step": 149
},
{
"epoch": 0.1,
"learning_rate": 3.943365607323001e-05,
"loss": 0.7932,
"step": 150
},
{
"epoch": 0.1,
"learning_rate": 3.9422971857376296e-05,
"loss": 0.8509,
"step": 151
},
{
"epoch": 0.11,
"learning_rate": 3.941218927565959e-05,
"loss": 0.8507,
"step": 152
},
{
"epoch": 0.11,
"learning_rate": 3.9401308382687324e-05,
"loss": 0.8531,
"step": 153
},
{
"epoch": 0.11,
"learning_rate": 3.9390329233564755e-05,
"loss": 0.8784,
"step": 154
},
{
"epoch": 0.11,
"learning_rate": 3.9379251883894795e-05,
"loss": 0.8322,
"step": 155
},
{
"epoch": 0.11,
"learning_rate": 3.9368076389777655e-05,
"loss": 0.779,
"step": 156
},
{
"epoch": 0.11,
"learning_rate": 3.9356802807810613e-05,
"loss": 0.8962,
"step": 157
},
{
"epoch": 0.11,
"learning_rate": 3.934543119508769e-05,
"loss": 0.8136,
"step": 158
},
{
"epoch": 0.11,
"learning_rate": 3.933396160919938e-05,
"loss": 0.8781,
"step": 159
},
{
"epoch": 0.11,
"learning_rate": 3.932239410823233e-05,
"loss": 0.8504,
"step": 160
},
{
"epoch": 0.11,
"learning_rate": 3.931072875076912e-05,
"loss": 0.8629,
"step": 161
},
{
"epoch": 0.11,
"learning_rate": 3.929896559588786e-05,
"loss": 0.9032,
"step": 162
},
{
"epoch": 0.11,
"learning_rate": 3.9287104703162005e-05,
"loss": 0.8775,
"step": 163
},
{
"epoch": 0.11,
"learning_rate": 3.927514613265992e-05,
"loss": 0.7987,
"step": 164
},
{
"epoch": 0.11,
"learning_rate": 3.9263089944944715e-05,
"loss": 0.8382,
"step": 165
},
{
"epoch": 0.12,
"learning_rate": 3.925093620107384e-05,
"loss": 0.7977,
"step": 166
},
{
"epoch": 0.12,
"learning_rate": 3.923868496259882e-05,
"loss": 0.8018,
"step": 167
},
{
"epoch": 0.12,
"learning_rate": 3.9226336291564935e-05,
"loss": 0.8569,
"step": 168
},
{
"epoch": 0.12,
"learning_rate": 3.92138902505109e-05,
"loss": 0.8138,
"step": 169
},
{
"epoch": 0.12,
"learning_rate": 3.920134690246854e-05,
"loss": 0.8295,
"step": 170
},
{
"epoch": 0.12,
"learning_rate": 3.91887063109625e-05,
"loss": 0.844,
"step": 171
},
{
"epoch": 0.12,
"learning_rate": 3.91759685400099e-05,
"loss": 0.8282,
"step": 172
},
{
"epoch": 0.12,
"learning_rate": 3.916313365412002e-05,
"loss": 0.8479,
"step": 173
},
{
"epoch": 0.12,
"learning_rate": 3.915020171829395e-05,
"loss": 0.8491,
"step": 174
},
{
"epoch": 0.12,
"learning_rate": 3.9137172798024304e-05,
"loss": 0.8506,
"step": 175
},
{
"epoch": 0.12,
"learning_rate": 3.912404695929486e-05,
"loss": 0.8526,
"step": 176
},
{
"epoch": 0.12,
"learning_rate": 3.9110824268580206e-05,
"loss": 0.8261,
"step": 177
},
{
"epoch": 0.12,
"learning_rate": 3.909750479284548e-05,
"loss": 0.848,
"step": 178
},
{
"epoch": 0.12,
"learning_rate": 3.908408859954593e-05,
"loss": 0.8922,
"step": 179
},
{
"epoch": 0.12,
"learning_rate": 3.907057575662663e-05,
"loss": 0.8434,
"step": 180
},
{
"epoch": 0.13,
"learning_rate": 3.905696633252216e-05,
"loss": 0.8844,
"step": 181
},
{
"epoch": 0.13,
"learning_rate": 3.904326039615618e-05,
"loss": 0.8673,
"step": 182
},
{
"epoch": 0.13,
"learning_rate": 3.902945801694117e-05,
"loss": 0.9093,
"step": 183
},
{
"epoch": 0.13,
"learning_rate": 3.9015559264777994e-05,
"loss": 0.8459,
"step": 184
},
{
"epoch": 0.13,
"learning_rate": 3.9001564210055624e-05,
"loss": 0.7868,
"step": 185
},
{
"epoch": 0.13,
"learning_rate": 3.898747292365073e-05,
"loss": 0.8708,
"step": 186
},
{
"epoch": 0.13,
"learning_rate": 3.897328547692735e-05,
"loss": 0.8418,
"step": 187
},
{
"epoch": 0.13,
"learning_rate": 3.89590019417365e-05,
"loss": 0.8855,
"step": 188
},
{
"epoch": 0.13,
"learning_rate": 3.8944622390415835e-05,
"loss": 0.9164,
"step": 189
},
{
"epoch": 0.13,
"learning_rate": 3.893014689578928e-05,
"loss": 0.8924,
"step": 190
},
{
"epoch": 0.13,
"learning_rate": 3.891557553116665e-05,
"loss": 0.8503,
"step": 191
},
{
"epoch": 0.13,
"learning_rate": 3.89009083703433e-05,
"loss": 0.8782,
"step": 192
},
{
"epoch": 0.13,
"learning_rate": 3.888614548759971e-05,
"loss": 0.8387,
"step": 193
},
{
"epoch": 0.13,
"learning_rate": 3.8871286957701146e-05,
"loss": 0.8102,
"step": 194
},
{
"epoch": 0.14,
"learning_rate": 3.8856332855897286e-05,
"loss": 0.8152,
"step": 195
},
{
"epoch": 0.14,
"learning_rate": 3.8841283257921794e-05,
"loss": 0.8356,
"step": 196
},
{
"epoch": 0.14,
"learning_rate": 3.882613823999199e-05,
"loss": 0.7964,
"step": 197
},
{
"epoch": 0.14,
"learning_rate": 3.881089787880843e-05,
"loss": 0.8404,
"step": 198
},
{
"epoch": 0.14,
"learning_rate": 3.879556225155453e-05,
"loss": 0.8714,
"step": 199
},
{
"epoch": 0.14,
"learning_rate": 3.878013143589617e-05,
"loss": 0.858,
"step": 200
},
{
"epoch": 0.14,
"learning_rate": 3.87646055099813e-05,
"loss": 0.8691,
"step": 201
},
{
"epoch": 0.14,
"learning_rate": 3.874898455243955e-05,
"loss": 0.8866,
"step": 202
},
{
"epoch": 0.14,
"learning_rate": 3.873326864238183e-05,
"loss": 0.8454,
"step": 203
},
{
"epoch": 0.14,
"learning_rate": 3.871745785939993e-05,
"loss": 0.8179,
"step": 204
},
{
"epoch": 0.14,
"learning_rate": 3.870155228356611e-05,
"loss": 0.816,
"step": 205
},
{
"epoch": 0.14,
"learning_rate": 3.8685551995432713e-05,
"loss": 0.8513,
"step": 206
},
{
"epoch": 0.14,
"learning_rate": 3.866945707603172e-05,
"loss": 0.8317,
"step": 207
},
{
"epoch": 0.14,
"learning_rate": 3.8653267606874395e-05,
"loss": 0.8817,
"step": 208
},
{
"epoch": 0.15,
"learning_rate": 3.863698366995079e-05,
"loss": 0.8439,
"step": 209
},
{
"epoch": 0.15,
"learning_rate": 3.862060534772945e-05,
"loss": 0.9013,
"step": 210
},
{
"epoch": 0.15,
"learning_rate": 3.8604132723156865e-05,
"loss": 0.8878,
"step": 211
},
{
"epoch": 0.15,
"learning_rate": 3.858756587965714e-05,
"loss": 0.8673,
"step": 212
},
{
"epoch": 0.15,
"learning_rate": 3.8570904901131544e-05,
"loss": 0.8213,
"step": 213
},
{
"epoch": 0.15,
"learning_rate": 3.855414987195807e-05,
"loss": 0.8217,
"step": 214
},
{
"epoch": 0.15,
"learning_rate": 3.853730087699103e-05,
"loss": 0.8459,
"step": 215
},
{
"epoch": 0.15,
"learning_rate": 3.852035800156062e-05,
"loss": 0.8144,
"step": 216
},
{
"epoch": 0.15,
"learning_rate": 3.850332133147248e-05,
"loss": 0.8527,
"step": 217
},
{
"epoch": 0.15,
"learning_rate": 3.848619095300726e-05,
"loss": 0.8272,
"step": 218
},
{
"epoch": 0.15,
"learning_rate": 3.8468966952920205e-05,
"loss": 0.829,
"step": 219
},
{
"epoch": 0.15,
"learning_rate": 3.845164941844068e-05,
"loss": 0.8333,
"step": 220
},
{
"epoch": 0.15,
"learning_rate": 3.843423843727176e-05,
"loss": 0.8904,
"step": 221
},
{
"epoch": 0.15,
"learning_rate": 3.8416734097589756e-05,
"loss": 0.821,
"step": 222
},
{
"epoch": 0.15,
"learning_rate": 3.83991364880438e-05,
"loss": 0.8658,
"step": 223
},
{
"epoch": 0.16,
"learning_rate": 3.8381445697755365e-05,
"loss": 0.8412,
"step": 224
},
{
"epoch": 0.16,
"learning_rate": 3.836366181631785e-05,
"loss": 0.7737,
"step": 225
},
{
"epoch": 0.16,
"learning_rate": 3.8345784933796095e-05,
"loss": 0.7934,
"step": 226
},
{
"epoch": 0.16,
"learning_rate": 3.832781514072593e-05,
"loss": 0.8491,
"step": 227
},
{
"epoch": 0.16,
"learning_rate": 3.8309752528113725e-05,
"loss": 0.861,
"step": 228
},
{
"epoch": 0.16,
"learning_rate": 3.8291597187435926e-05,
"loss": 0.8469,
"step": 229
},
{
"epoch": 0.16,
"learning_rate": 3.827334921063861e-05,
"loss": 0.8436,
"step": 230
},
{
"epoch": 0.16,
"learning_rate": 3.825500869013697e-05,
"loss": 0.8847,
"step": 231
},
{
"epoch": 0.16,
"learning_rate": 3.82365757188149e-05,
"loss": 0.835,
"step": 232
},
{
"epoch": 0.16,
"learning_rate": 3.821805039002449e-05,
"loss": 0.8713,
"step": 233
},
{
"epoch": 0.16,
"learning_rate": 3.8199432797585576e-05,
"loss": 0.8586,
"step": 234
},
{
"epoch": 0.16,
"learning_rate": 3.8180723035785246e-05,
"loss": 0.8109,
"step": 235
},
{
"epoch": 0.16,
"learning_rate": 3.816192119937738e-05,
"loss": 0.8649,
"step": 236
},
{
"epoch": 0.16,
"learning_rate": 3.814302738358216e-05,
"loss": 0.7888,
"step": 237
},
{
"epoch": 0.17,
"learning_rate": 3.812404168408558e-05,
"loss": 0.8084,
"step": 238
},
{
"epoch": 0.17,
"learning_rate": 3.810496419703898e-05,
"loss": 0.8355,
"step": 239
},
{
"epoch": 0.17,
"learning_rate": 3.808579501905856e-05,
"loss": 0.8504,
"step": 240
},
{
"epoch": 0.17,
"learning_rate": 3.806653424722484e-05,
"loss": 0.8201,
"step": 241
},
{
"epoch": 0.17,
"learning_rate": 3.804718197908225e-05,
"loss": 0.8333,
"step": 242
},
{
"epoch": 0.17,
"learning_rate": 3.802773831263859e-05,
"loss": 0.9149,
"step": 243
},
{
"epoch": 0.17,
"learning_rate": 3.800820334636452e-05,
"loss": 0.8633,
"step": 244
},
{
"epoch": 0.17,
"learning_rate": 3.798857717919308e-05,
"loss": 0.8118,
"step": 245
},
{
"epoch": 0.17,
"learning_rate": 3.7968859910519215e-05,
"loss": 0.8572,
"step": 246
},
{
"epoch": 0.17,
"learning_rate": 3.7949051640199216e-05,
"loss": 0.8042,
"step": 247
},
{
"epoch": 0.17,
"learning_rate": 3.7929152468550245e-05,
"loss": 0.8955,
"step": 248
},
{
"epoch": 0.17,
"learning_rate": 3.790916249634986e-05,
"loss": 0.8322,
"step": 249
},
{
"epoch": 0.17,
"learning_rate": 3.788908182483542e-05,
"loss": 0.8807,
"step": 250
},
{
"epoch": 0.17,
"learning_rate": 3.786891055570367e-05,
"loss": 0.8413,
"step": 251
},
{
"epoch": 0.17,
"learning_rate": 3.784864879111013e-05,
"loss": 0.8295,
"step": 252
},
{
"epoch": 0.18,
"learning_rate": 3.782829663366868e-05,
"loss": 0.8388,
"step": 253
},
{
"epoch": 0.18,
"learning_rate": 3.780785418645095e-05,
"loss": 0.871,
"step": 254
},
{
"epoch": 0.18,
"learning_rate": 3.7787321552985826e-05,
"loss": 0.8851,
"step": 255
},
{
"epoch": 0.18,
"learning_rate": 3.776669883725897e-05,
"loss": 0.8205,
"step": 256
},
{
"epoch": 0.18,
"learning_rate": 3.774598614371223e-05,
"loss": 0.868,
"step": 257
},
{
"epoch": 0.18,
"learning_rate": 3.7725183577243144e-05,
"loss": 0.8309,
"step": 258
},
{
"epoch": 0.18,
"learning_rate": 3.7704291243204416e-05,
"loss": 0.8393,
"step": 259
},
{
"epoch": 0.18,
"learning_rate": 3.7683309247403345e-05,
"loss": 0.8583,
"step": 260
},
{
"epoch": 0.18,
"learning_rate": 3.766223769610134e-05,
"loss": 0.8307,
"step": 261
},
{
"epoch": 0.18,
"learning_rate": 3.764107669601333e-05,
"loss": 0.8309,
"step": 262
},
{
"epoch": 0.18,
"learning_rate": 3.761982635430729e-05,
"loss": 0.8072,
"step": 263
},
{
"epoch": 0.18,
"learning_rate": 3.759848677860359e-05,
"loss": 0.8157,
"step": 264
},
{
"epoch": 0.18,
"learning_rate": 3.7577058076974595e-05,
"loss": 0.83,
"step": 265
},
{
"epoch": 0.18,
"learning_rate": 3.755554035794398e-05,
"loss": 0.8347,
"step": 266
},
{
"epoch": 0.19,
"learning_rate": 3.7533933730486276e-05,
"loss": 0.8153,
"step": 267
},
{
"epoch": 0.19,
"learning_rate": 3.751223830402627e-05,
"loss": 0.7839,
"step": 268
},
{
"epoch": 0.19,
"learning_rate": 3.749045418843844e-05,
"loss": 0.807,
"step": 269
},
{
"epoch": 0.19,
"learning_rate": 3.746858149404648e-05,
"loss": 0.8652,
"step": 270
},
{
"epoch": 0.19,
"learning_rate": 3.744662033162262e-05,
"loss": 0.816,
"step": 271
},
{
"epoch": 0.19,
"learning_rate": 3.742457081238717e-05,
"loss": 0.8061,
"step": 272
},
{
"epoch": 0.19,
"learning_rate": 3.740243304800791e-05,
"loss": 0.7827,
"step": 273
},
{
"epoch": 0.19,
"learning_rate": 3.738020715059951e-05,
"loss": 0.844,
"step": 274
},
{
"epoch": 0.19,
"learning_rate": 3.7357893232722984e-05,
"loss": 0.8804,
"step": 275
},
{
"epoch": 0.19,
"learning_rate": 3.733549140738514e-05,
"loss": 0.8649,
"step": 276
},
{
"epoch": 0.19,
"learning_rate": 3.731300178803797e-05,
"loss": 0.8539,
"step": 277
},
{
"epoch": 0.19,
"learning_rate": 3.7290424488578094e-05,
"loss": 0.8661,
"step": 278
},
{
"epoch": 0.19,
"learning_rate": 3.726775962334617e-05,
"loss": 0.9292,
"step": 279
},
{
"epoch": 0.19,
"learning_rate": 3.7245007307126346e-05,
"loss": 0.8529,
"step": 280
},
{
"epoch": 0.2,
"learning_rate": 3.7222167655145636e-05,
"loss": 0.8056,
"step": 281
},
{
"epoch": 0.2,
"learning_rate": 3.7199240783073365e-05,
"loss": 0.782,
"step": 282
},
{
"epoch": 0.2,
"learning_rate": 3.717622680702058e-05,
"loss": 0.836,
"step": 283
},
{
"epoch": 0.2,
"learning_rate": 3.7153125843539455e-05,
"loss": 0.8523,
"step": 284
},
{
"epoch": 0.2,
"learning_rate": 3.712993800962271e-05,
"loss": 0.8084,
"step": 285
},
{
"epoch": 0.2,
"learning_rate": 3.7106663422703004e-05,
"loss": 0.8995,
"step": 286
},
{
"epoch": 0.2,
"learning_rate": 3.708330220065235e-05,
"loss": 0.8668,
"step": 287
},
{
"epoch": 0.2,
"learning_rate": 3.7059854461781514e-05,
"loss": 0.8394,
"step": 288
},
{
"epoch": 0.2,
"learning_rate": 3.7036320324839444e-05,
"loss": 0.8429,
"step": 289
},
{
"epoch": 0.2,
"learning_rate": 3.70126999090126e-05,
"loss": 0.8279,
"step": 290
},
{
"epoch": 0.2,
"learning_rate": 3.698899333392442e-05,
"loss": 0.8192,
"step": 291
},
{
"epoch": 0.2,
"learning_rate": 3.696520071963469e-05,
"loss": 0.8271,
"step": 292
},
{
"epoch": 0.2,
"learning_rate": 3.6941322186638924e-05,
"loss": 0.8461,
"step": 293
},
{
"epoch": 0.2,
"learning_rate": 3.691735785586777e-05,
"loss": 0.8143,
"step": 294
},
{
"epoch": 0.2,
"learning_rate": 3.6893307848686376e-05,
"loss": 0.8848,
"step": 295
},
{
"epoch": 0.21,
"learning_rate": 3.686917228689382e-05,
"loss": 0.8238,
"step": 296
},
{
"epoch": 0.21,
"learning_rate": 3.684495129272242e-05,
"loss": 0.843,
"step": 297
},
{
"epoch": 0.21,
"learning_rate": 3.682064498883721e-05,
"loss": 0.8044,
"step": 298
},
{
"epoch": 0.21,
"learning_rate": 3.679625349833523e-05,
"loss": 0.8657,
"step": 299
},
{
"epoch": 0.21,
"learning_rate": 3.677177694474495e-05,
"loss": 0.86,
"step": 300
},
{
"epoch": 0.21,
"learning_rate": 3.674721545202563e-05,
"loss": 0.7954,
"step": 301
},
{
"epoch": 0.21,
"learning_rate": 3.672256914456671e-05,
"loss": 0.814,
"step": 302
},
{
"epoch": 0.21,
"learning_rate": 3.669783814718716e-05,
"loss": 0.8229,
"step": 303
},
{
"epoch": 0.21,
"learning_rate": 3.667302258513484e-05,
"loss": 0.8065,
"step": 304
},
{
"epoch": 0.21,
"learning_rate": 3.6648122584085907e-05,
"loss": 0.8178,
"step": 305
},
{
"epoch": 0.21,
"learning_rate": 3.662313827014412e-05,
"loss": 0.7951,
"step": 306
},
{
"epoch": 0.21,
"learning_rate": 3.659806976984026e-05,
"loss": 0.8523,
"step": 307
},
{
"epoch": 0.21,
"learning_rate": 3.657291721013146e-05,
"loss": 0.8448,
"step": 308
},
{
"epoch": 0.21,
"learning_rate": 3.6547680718400546e-05,
"loss": 0.8641,
"step": 309
},
{
"epoch": 0.22,
"learning_rate": 3.652236042245542e-05,
"loss": 0.7991,
"step": 310
},
{
"epoch": 0.22,
"learning_rate": 3.64969564505284e-05,
"loss": 0.822,
"step": 311
},
{
"epoch": 0.22,
"learning_rate": 3.647146893127559e-05,
"loss": 0.8534,
"step": 312
},
{
"epoch": 0.22,
"learning_rate": 3.644589799377618e-05,
"loss": 0.8344,
"step": 313
},
{
"epoch": 0.22,
"learning_rate": 3.642024376753186e-05,
"loss": 0.7497,
"step": 314
},
{
"epoch": 0.22,
"learning_rate": 3.639450638246611e-05,
"loss": 0.8136,
"step": 315
},
{
"epoch": 0.22,
"learning_rate": 3.636868596892353e-05,
"loss": 0.8569,
"step": 316
},
{
"epoch": 0.22,
"learning_rate": 3.634278265766928e-05,
"loss": 0.7764,
"step": 317
},
{
"epoch": 0.22,
"learning_rate": 3.631679657988829e-05,
"loss": 0.7942,
"step": 318
},
{
"epoch": 0.22,
"learning_rate": 3.6290727867184676e-05,
"loss": 0.8018,
"step": 319
},
{
"epoch": 0.22,
"learning_rate": 3.6264576651581036e-05,
"loss": 0.8227,
"step": 320
},
{
"epoch": 0.22,
"learning_rate": 3.623834306551782e-05,
"loss": 0.8527,
"step": 321
},
{
"epoch": 0.22,
"learning_rate": 3.6212027241852625e-05,
"loss": 0.8485,
"step": 322
},
{
"epoch": 0.22,
"learning_rate": 3.618562931385952e-05,
"loss": 0.8357,
"step": 323
},
{
"epoch": 0.23,
"learning_rate": 3.6159149415228403e-05,
"loss": 0.8113,
"step": 324
},
{
"epoch": 0.23,
"learning_rate": 3.613258768006429e-05,
"loss": 0.8526,
"step": 325
},
{
"epoch": 0.23,
"learning_rate": 3.6105944242886674e-05,
"loss": 0.8364,
"step": 326
},
{
"epoch": 0.23,
"learning_rate": 3.607921923862878e-05,
"loss": 0.8492,
"step": 327
},
{
"epoch": 0.23,
"learning_rate": 3.605241280263696e-05,
"loss": 0.8274,
"step": 328
},
{
"epoch": 0.23,
"learning_rate": 3.6025525070669955e-05,
"loss": 0.8139,
"step": 329
},
{
"epoch": 0.23,
"learning_rate": 3.599855617889822e-05,
"loss": 0.8624,
"step": 330
},
{
"epoch": 0.23,
"learning_rate": 3.5971506263903234e-05,
"loss": 0.8356,
"step": 331
},
{
"epoch": 0.23,
"learning_rate": 3.594437546267682e-05,
"loss": 0.7985,
"step": 332
},
{
"epoch": 0.23,
"learning_rate": 3.591716391262044e-05,
"loss": 0.8091,
"step": 333
},
{
"epoch": 0.23,
"learning_rate": 3.588987175154449e-05,
"loss": 0.8186,
"step": 334
},
{
"epoch": 0.23,
"learning_rate": 3.586249911766763e-05,
"loss": 0.8289,
"step": 335
},
{
"epoch": 0.23,
"learning_rate": 3.583504614961605e-05,
"loss": 0.8673,
"step": 336
},
{
"epoch": 0.23,
"learning_rate": 3.58075129864228e-05,
"loss": 0.8079,
"step": 337
},
{
"epoch": 0.23,
"learning_rate": 3.5779899767527064e-05,
"loss": 0.8728,
"step": 338
},
{
"epoch": 0.24,
"learning_rate": 3.575220663277346e-05,
"loss": 0.8202,
"step": 339
},
{
"epoch": 0.24,
"learning_rate": 3.572443372241134e-05,
"loss": 0.7843,
"step": 340
},
{
"epoch": 0.24,
"learning_rate": 3.569658117709406e-05,
"loss": 0.875,
"step": 341
},
{
"epoch": 0.24,
"learning_rate": 3.5668649137878275e-05,
"loss": 0.8502,
"step": 342
},
{
"epoch": 0.24,
"learning_rate": 3.5640637746223253e-05,
"loss": 0.7904,
"step": 343
},
{
"epoch": 0.24,
"learning_rate": 3.561254714399013e-05,
"loss": 0.7822,
"step": 344
},
{
"epoch": 0.24,
"learning_rate": 3.5584377473441187e-05,
"loss": 0.8292,
"step": 345
},
{
"epoch": 0.24,
"learning_rate": 3.5556128877239125e-05,
"loss": 0.8291,
"step": 346
},
{
"epoch": 0.24,
"learning_rate": 3.552780149844639e-05,
"loss": 0.8436,
"step": 347
},
{
"epoch": 0.24,
"learning_rate": 3.5499395480524394e-05,
"loss": 0.8243,
"step": 348
},
{
"epoch": 0.24,
"learning_rate": 3.5470910967332815e-05,
"loss": 0.7633,
"step": 349
},
{
"epoch": 0.24,
"learning_rate": 3.544234810312886e-05,
"loss": 0.8086,
"step": 350
},
{
"epoch": 0.24,
"learning_rate": 3.541370703256654e-05,
"loss": 0.8119,
"step": 351
},
{
"epoch": 0.24,
"learning_rate": 3.538498790069594e-05,
"loss": 0.8378,
"step": 352
},
{
"epoch": 0.25,
"learning_rate": 3.5356190852962474e-05,
"loss": 0.7859,
"step": 353
},
{
"epoch": 0.25,
"learning_rate": 3.5327316035206145e-05,
"loss": 0.8696,
"step": 354
},
{
"epoch": 0.25,
"learning_rate": 3.5298363593660835e-05,
"loss": 0.7902,
"step": 355
},
{
"epoch": 0.25,
"learning_rate": 3.526933367495353e-05,
"loss": 0.7689,
"step": 356
},
{
"epoch": 0.25,
"learning_rate": 3.5240226426103596e-05,
"loss": 0.8603,
"step": 357
},
{
"epoch": 0.25,
"learning_rate": 3.521104199452203e-05,
"loss": 0.8757,
"step": 358
},
{
"epoch": 0.25,
"learning_rate": 3.5181780528010715e-05,
"loss": 0.8077,
"step": 359
},
{
"epoch": 0.25,
"learning_rate": 3.515244217476166e-05,
"loss": 0.8267,
"step": 360
},
{
"epoch": 0.25,
"learning_rate": 3.5123027083356285e-05,
"loss": 0.8673,
"step": 361
},
{
"epoch": 0.25,
"learning_rate": 3.509353540276462e-05,
"loss": 0.8911,
"step": 362
},
{
"epoch": 0.25,
"learning_rate": 3.506396728234459e-05,
"loss": 0.8427,
"step": 363
},
{
"epoch": 0.25,
"learning_rate": 3.503432287184121e-05,
"loss": 0.8095,
"step": 364
},
{
"epoch": 0.25,
"learning_rate": 3.500460232138591e-05,
"loss": 0.8234,
"step": 365
},
{
"epoch": 0.25,
"learning_rate": 3.497480578149569e-05,
"loss": 0.8326,
"step": 366
},
{
"epoch": 0.25,
"learning_rate": 3.4944933403072387e-05,
"loss": 0.8699,
"step": 367
},
{
"epoch": 0.26,
"learning_rate": 3.491498533740193e-05,
"loss": 0.878,
"step": 368
},
{
"epoch": 0.26,
"learning_rate": 3.488496173615358e-05,
"loss": 0.862,
"step": 369
},
{
"epoch": 0.26,
"learning_rate": 3.485486275137909e-05,
"loss": 0.8394,
"step": 370
},
{
"epoch": 0.26,
"learning_rate": 3.482468853551202e-05,
"loss": 0.8331,
"step": 371
},
{
"epoch": 0.26,
"learning_rate": 3.479443924136693e-05,
"loss": 0.8177,
"step": 372
},
{
"epoch": 0.26,
"learning_rate": 3.47641150221386e-05,
"loss": 0.9065,
"step": 373
},
{
"epoch": 0.26,
"learning_rate": 3.473371603140125e-05,
"loss": 0.8353,
"step": 374
},
{
"epoch": 0.26,
"learning_rate": 3.47032424231078e-05,
"loss": 0.8161,
"step": 375
},
{
"epoch": 0.26,
"learning_rate": 3.4672694351589046e-05,
"loss": 0.8526,
"step": 376
},
{
"epoch": 0.26,
"learning_rate": 3.46420719715529e-05,
"loss": 0.8444,
"step": 377
},
{
"epoch": 0.26,
"learning_rate": 3.46113754380836e-05,
"loss": 0.7855,
"step": 378
},
{
"epoch": 0.26,
"learning_rate": 3.4580604906640936e-05,
"loss": 0.8773,
"step": 379
},
{
"epoch": 0.26,
"learning_rate": 3.454976053305943e-05,
"loss": 0.8161,
"step": 380
},
{
"epoch": 0.26,
"learning_rate": 3.4518842473547614e-05,
"loss": 0.8728,
"step": 381
},
{
"epoch": 0.27,
"learning_rate": 3.4487850884687155e-05,
"loss": 0.876,
"step": 382
},
{
"epoch": 0.27,
"learning_rate": 3.445678592343212e-05,
"loss": 0.8488,
"step": 383
},
{
"epoch": 0.27,
"learning_rate": 3.442564774710816e-05,
"loss": 0.8647,
"step": 384
},
{
"epoch": 0.27,
"learning_rate": 3.439443651341172e-05,
"loss": 0.8296,
"step": 385
},
{
"epoch": 0.27,
"learning_rate": 3.436315238040924e-05,
"loss": 0.8066,
"step": 386
},
{
"epoch": 0.27,
"learning_rate": 3.4331795506536336e-05,
"loss": 0.7785,
"step": 387
},
{
"epoch": 0.27,
"learning_rate": 3.430036605059704e-05,
"loss": 0.8146,
"step": 388
},
{
"epoch": 0.27,
"learning_rate": 3.426886417176294e-05,
"loss": 0.7821,
"step": 389
},
{
"epoch": 0.27,
"learning_rate": 3.423729002957244e-05,
"loss": 0.8071,
"step": 390
},
{
"epoch": 0.27,
"learning_rate": 3.4205643783929875e-05,
"loss": 0.8695,
"step": 391
},
{
"epoch": 0.27,
"learning_rate": 3.417392559510475e-05,
"loss": 0.8498,
"step": 392
},
{
"epoch": 0.27,
"learning_rate": 3.4142135623730954e-05,
"loss": 0.7896,
"step": 393
},
{
"epoch": 0.27,
"learning_rate": 3.411027403080587e-05,
"loss": 0.8189,
"step": 394
},
{
"epoch": 0.27,
"learning_rate": 3.407834097768962e-05,
"loss": 0.8379,
"step": 395
},
{
"epoch": 0.28,
"learning_rate": 3.4046336626104235e-05,
"loss": 0.8001,
"step": 396
},
{
"epoch": 0.28,
"learning_rate": 3.401426113813282e-05,
"loss": 0.8554,
"step": 397
},
{
"epoch": 0.28,
"learning_rate": 3.398211467621875e-05,
"loss": 0.8433,
"step": 398
},
{
"epoch": 0.28,
"learning_rate": 3.394989740316484e-05,
"loss": 0.8396,
"step": 399
},
{
"epoch": 0.28,
"learning_rate": 3.391760948213251e-05,
"loss": 0.8039,
"step": 400
},
{
"epoch": 0.28,
"learning_rate": 3.388525107664099e-05,
"loss": 0.8514,
"step": 401
},
{
"epoch": 0.28,
"learning_rate": 3.3852822350566455e-05,
"loss": 0.837,
"step": 402
},
{
"epoch": 0.28,
"learning_rate": 3.382032346814123e-05,
"loss": 0.7992,
"step": 403
},
{
"epoch": 0.28,
"learning_rate": 3.378775459395292e-05,
"loss": 0.7983,
"step": 404
},
{
"epoch": 0.28,
"learning_rate": 3.3755115892943616e-05,
"loss": 0.7946,
"step": 405
},
{
"epoch": 0.28,
"learning_rate": 3.372240753040902e-05,
"loss": 0.8011,
"step": 406
},
{
"epoch": 0.28,
"learning_rate": 3.368962967199765e-05,
"loss": 0.839,
"step": 407
},
{
"epoch": 0.28,
"learning_rate": 3.3656782483709966e-05,
"loss": 0.8005,
"step": 408
},
{
"epoch": 0.28,
"learning_rate": 3.3623866131897554e-05,
"loss": 0.8083,
"step": 409
},
{
"epoch": 0.28,
"learning_rate": 3.3590880783262245e-05,
"loss": 0.8144,
"step": 410
},
{
"epoch": 0.29,
"learning_rate": 3.3557826604855335e-05,
"loss": 0.824,
"step": 411
},
{
"epoch": 0.29,
"learning_rate": 3.3524703764076684e-05,
"loss": 0.8649,
"step": 412
},
{
"epoch": 0.29,
"learning_rate": 3.3491512428673877e-05,
"loss": 0.827,
"step": 413
},
{
"epoch": 0.29,
"learning_rate": 3.345825276674139e-05,
"loss": 0.8021,
"step": 414
},
{
"epoch": 0.29,
"learning_rate": 3.342492494671976e-05,
"loss": 0.8174,
"step": 415
},
{
"epoch": 0.29,
"learning_rate": 3.339152913739466e-05,
"loss": 0.815,
"step": 416
},
{
"epoch": 0.29,
"learning_rate": 3.335806550789611e-05,
"loss": 0.8287,
"step": 417
},
{
"epoch": 0.29,
"learning_rate": 3.332453422769762e-05,
"loss": 0.8148,
"step": 418
},
{
"epoch": 0.29,
"learning_rate": 3.329093546661526e-05,
"loss": 0.82,
"step": 419
},
{
"epoch": 0.29,
"learning_rate": 3.3257269394806894e-05,
"loss": 0.7929,
"step": 420
},
{
"epoch": 0.29,
"learning_rate": 3.322353618277126e-05,
"loss": 0.7813,
"step": 421
},
{
"epoch": 0.29,
"learning_rate": 3.3189736001347125e-05,
"loss": 0.84,
"step": 422
},
{
"epoch": 0.29,
"learning_rate": 3.315586902171241e-05,
"loss": 0.8143,
"step": 423
},
{
"epoch": 0.29,
"learning_rate": 3.3121935415383325e-05,
"loss": 0.7428,
"step": 424
},
{
"epoch": 0.3,
"learning_rate": 3.308793535421353e-05,
"loss": 0.7875,
"step": 425
},
{
"epoch": 0.3,
"learning_rate": 3.305386901039321e-05,
"loss": 0.8642,
"step": 426
},
{
"epoch": 0.3,
"learning_rate": 3.301973655644825e-05,
"loss": 0.791,
"step": 427
},
{
"epoch": 0.3,
"learning_rate": 3.298553816523934e-05,
"loss": 0.8921,
"step": 428
},
{
"epoch": 0.3,
"learning_rate": 3.2951274009961094e-05,
"loss": 0.7889,
"step": 429
},
{
"epoch": 0.3,
"learning_rate": 3.29169442641412e-05,
"loss": 0.8362,
"step": 430
},
{
"epoch": 0.3,
"learning_rate": 3.288254910163951e-05,
"loss": 0.9359,
"step": 431
},
{
"epoch": 0.3,
"learning_rate": 3.284808869664716e-05,
"loss": 0.8452,
"step": 432
},
{
"epoch": 0.3,
"learning_rate": 3.281356322368575e-05,
"loss": 0.853,
"step": 433
},
{
"epoch": 0.3,
"learning_rate": 3.277897285760635e-05,
"loss": 0.8384,
"step": 434
},
{
"epoch": 0.3,
"learning_rate": 3.2744317773588696e-05,
"loss": 0.9152,
"step": 435
},
{
"epoch": 0.3,
"learning_rate": 3.270959814714032e-05,
"loss": 0.8546,
"step": 436
},
{
"epoch": 0.3,
"learning_rate": 3.267481415409557e-05,
"loss": 0.863,
"step": 437
},
{
"epoch": 0.3,
"learning_rate": 3.26399659706148e-05,
"loss": 0.7749,
"step": 438
},
{
"epoch": 0.3,
"learning_rate": 3.260505377318344e-05,
"loss": 0.8642,
"step": 439
},
{
"epoch": 0.31,
"learning_rate": 3.257007773861113e-05,
"loss": 0.7798,
"step": 440
},
{
"epoch": 0.31,
"learning_rate": 3.253503804403079e-05,
"loss": 0.8633,
"step": 441
},
{
"epoch": 0.31,
"learning_rate": 3.249993486689774e-05,
"loss": 0.8072,
"step": 442
},
{
"epoch": 0.31,
"learning_rate": 3.246476838498881e-05,
"loss": 0.8294,
"step": 443
},
{
"epoch": 0.31,
"learning_rate": 3.242953877640142e-05,
"loss": 0.8413,
"step": 444
},
{
"epoch": 0.31,
"learning_rate": 3.2394246219552724e-05,
"loss": 0.8278,
"step": 445
},
{
"epoch": 0.31,
"learning_rate": 3.2358890893178617e-05,
"loss": 0.8499,
"step": 446
},
{
"epoch": 0.31,
"learning_rate": 3.2323472976332926e-05,
"loss": 0.8102,
"step": 447
},
{
"epoch": 0.31,
"learning_rate": 3.228799264838645e-05,
"loss": 0.8742,
"step": 448
},
{
"epoch": 0.31,
"learning_rate": 3.225245008902606e-05,
"loss": 0.8428,
"step": 449
},
{
"epoch": 0.31,
"learning_rate": 3.221684547825379e-05,
"loss": 0.8184,
"step": 450
},
{
"epoch": 0.31,
"learning_rate": 3.218117899638594e-05,
"loss": 0.8215,
"step": 451
},
{
"epoch": 0.31,
"learning_rate": 3.214545082405213e-05,
"loss": 0.8455,
"step": 452
},
{
"epoch": 0.31,
"learning_rate": 3.210966114219444e-05,
"loss": 0.7611,
"step": 453
},
{
"epoch": 0.32,
"learning_rate": 3.2073810132066414e-05,
"loss": 0.8466,
"step": 454
},
{
"epoch": 0.32,
"learning_rate": 3.2037897975232216e-05,
"loss": 0.7962,
"step": 455
},
{
"epoch": 0.32,
"learning_rate": 3.200192485356569e-05,
"loss": 0.8637,
"step": 456
},
{
"epoch": 0.32,
"learning_rate": 3.1965890949249405e-05,
"loss": 0.7954,
"step": 457
},
{
"epoch": 0.32,
"learning_rate": 3.192979644477378e-05,
"loss": 0.8429,
"step": 458
},
{
"epoch": 0.32,
"learning_rate": 3.189364152293612e-05,
"loss": 0.815,
"step": 459
},
{
"epoch": 0.32,
"learning_rate": 3.185742636683972e-05,
"loss": 0.7545,
"step": 460
},
{
"epoch": 0.32,
"learning_rate": 3.1821151159892924e-05,
"loss": 0.8232,
"step": 461
},
{
"epoch": 0.32,
"learning_rate": 3.1784816085808196e-05,
"loss": 0.8387,
"step": 462
},
{
"epoch": 0.32,
"learning_rate": 3.17484213286012e-05,
"loss": 0.8085,
"step": 463
},
{
"epoch": 0.32,
"learning_rate": 3.171196707258984e-05,
"loss": 0.8662,
"step": 464
},
{
"epoch": 0.32,
"learning_rate": 3.167545350239336e-05,
"loss": 0.8275,
"step": 465
},
{
"epoch": 0.32,
"learning_rate": 3.16388808029314e-05,
"loss": 0.8161,
"step": 466
},
{
"epoch": 0.32,
"learning_rate": 3.1602249159423054e-05,
"loss": 0.8135,
"step": 467
},
{
"epoch": 0.33,
"learning_rate": 3.1565558757385914e-05,
"loss": 0.7875,
"step": 468
},
{
"epoch": 0.33,
"learning_rate": 3.152880978263517e-05,
"loss": 0.8395,
"step": 469
},
{
"epoch": 0.33,
"learning_rate": 3.149200242128263e-05,
"loss": 0.8248,
"step": 470
},
{
"epoch": 0.33,
"learning_rate": 3.145513685973583e-05,
"loss": 0.8178,
"step": 471
},
{
"epoch": 0.33,
"learning_rate": 3.1418213284697e-05,
"loss": 0.8125,
"step": 472
},
{
"epoch": 0.33,
"learning_rate": 3.138123188316224e-05,
"loss": 0.8206,
"step": 473
},
{
"epoch": 0.33,
"learning_rate": 3.1344192842420435e-05,
"loss": 0.8056,
"step": 474
},
{
"epoch": 0.33,
"learning_rate": 3.130709635005245e-05,
"loss": 0.7943,
"step": 475
},
{
"epoch": 0.33,
"learning_rate": 3.1269942593930055e-05,
"loss": 0.8119,
"step": 476
},
{
"epoch": 0.33,
"learning_rate": 3.123273176221506e-05,
"loss": 0.7791,
"step": 477
},
{
"epoch": 0.33,
"learning_rate": 3.119546404335831e-05,
"loss": 0.8233,
"step": 478
},
{
"epoch": 0.33,
"learning_rate": 3.115813962609874e-05,
"loss": 0.8061,
"step": 479
},
{
"epoch": 0.33,
"learning_rate": 3.112075869946247e-05,
"loss": 0.8151,
"step": 480
},
{
"epoch": 0.33,
"learning_rate": 3.108332145276177e-05,
"loss": 0.8585,
"step": 481
},
{
"epoch": 0.33,
"learning_rate": 3.104582807559414e-05,
"loss": 0.8304,
"step": 482
},
{
"epoch": 0.34,
"learning_rate": 3.100827875784138e-05,
"loss": 0.8178,
"step": 483
},
{
"epoch": 0.34,
"learning_rate": 3.097067368966855e-05,
"loss": 0.8209,
"step": 484
},
{
"epoch": 0.34,
"learning_rate": 3.093301306152308e-05,
"loss": 0.8377,
"step": 485
},
{
"epoch": 0.34,
"learning_rate": 3.089529706413378e-05,
"loss": 0.8457,
"step": 486
},
{
"epoch": 0.34,
"learning_rate": 3.085752588850986e-05,
"loss": 0.8678,
"step": 487
},
{
"epoch": 0.34,
"learning_rate": 3.081969972593999e-05,
"loss": 0.8514,
"step": 488
},
{
"epoch": 0.34,
"learning_rate": 3.0781818767991295e-05,
"loss": 0.8139,
"step": 489
},
{
"epoch": 0.34,
"learning_rate": 3.074388320650843e-05,
"loss": 0.8543,
"step": 490
},
{
"epoch": 0.34,
"learning_rate": 3.070589323361257e-05,
"loss": 0.8243,
"step": 491
},
{
"epoch": 0.34,
"learning_rate": 3.0667849041700454e-05,
"loss": 0.812,
"step": 492
},
{
"epoch": 0.34,
"learning_rate": 3.062975082344341e-05,
"loss": 0.7881,
"step": 493
},
{
"epoch": 0.34,
"learning_rate": 3.059159877178638e-05,
"loss": 0.854,
"step": 494
},
{
"epoch": 0.34,
"learning_rate": 3.055339307994693e-05,
"loss": 0.8448,
"step": 495
},
{
"epoch": 0.34,
"learning_rate": 3.0515133941414294e-05,
"loss": 0.8635,
"step": 496
},
{
"epoch": 0.35,
"learning_rate": 3.0476821549948376e-05,
"loss": 0.8091,
"step": 497
},
{
"epoch": 0.35,
"learning_rate": 3.0438456099578775e-05,
"loss": 0.841,
"step": 498
},
{
"epoch": 0.35,
"learning_rate": 3.0400037784603805e-05,
"loss": 0.7998,
"step": 499
},
{
"epoch": 0.35,
"learning_rate": 3.0361566799589498e-05,
"loss": 0.8385,
"step": 500
},
{
"epoch": 0.35,
"learning_rate": 3.0323043339368648e-05,
"loss": 0.8134,
"step": 501
},
{
"epoch": 0.35,
"learning_rate": 3.028446759903978e-05,
"loss": 0.8323,
"step": 502
},
{
"epoch": 0.35,
"learning_rate": 3.0245839773966206e-05,
"loss": 0.8362,
"step": 503
},
{
"epoch": 0.35,
"learning_rate": 3.020716005977501e-05,
"loss": 0.7849,
"step": 504
},
{
"epoch": 0.35,
"learning_rate": 3.0168428652356066e-05,
"loss": 0.8164,
"step": 505
},
{
"epoch": 0.35,
"learning_rate": 3.0129645747861032e-05,
"loss": 0.8086,
"step": 506
},
{
"epoch": 0.35,
"learning_rate": 3.0090811542702388e-05,
"loss": 0.8498,
"step": 507
},
{
"epoch": 0.35,
"learning_rate": 3.0051926233552405e-05,
"loss": 0.8631,
"step": 508
},
{
"epoch": 0.35,
"learning_rate": 3.0012990017342178e-05,
"loss": 0.7868,
"step": 509
},
{
"epoch": 0.35,
"learning_rate": 2.99740030912606e-05,
"loss": 0.7553,
"step": 510
},
{
"epoch": 0.35,
"learning_rate": 2.9934965652753396e-05,
"loss": 0.7878,
"step": 511
},
{
"epoch": 0.36,
"learning_rate": 2.989587789952211e-05,
"loss": 0.817,
"step": 512
},
{
"epoch": 0.36,
"learning_rate": 2.9856740029523067e-05,
"loss": 0.8051,
"step": 513
},
{
"epoch": 0.36,
"learning_rate": 2.981755224096644e-05,
"loss": 0.8372,
"step": 514
},
{
"epoch": 0.36,
"learning_rate": 2.9778314732315193e-05,
"loss": 0.86,
"step": 515
},
{
"epoch": 0.36,
"learning_rate": 2.9739027702284102e-05,
"loss": 0.8183,
"step": 516
},
{
"epoch": 0.36,
"learning_rate": 2.969969134983873e-05,
"loss": 0.8166,
"step": 517
},
{
"epoch": 0.36,
"learning_rate": 2.966030587419444e-05,
"loss": 0.8159,
"step": 518
},
{
"epoch": 0.36,
"learning_rate": 2.9620871474815357e-05,
"loss": 0.8123,
"step": 519
},
{
"epoch": 0.36,
"learning_rate": 2.9581388351413395e-05,
"loss": 0.817,
"step": 520
},
{
"epoch": 0.36,
"learning_rate": 2.954185670394721e-05,
"loss": 0.7659,
"step": 521
},
{
"epoch": 0.36,
"learning_rate": 2.9502276732621224e-05,
"loss": 0.8125,
"step": 522
},
{
"epoch": 0.36,
"learning_rate": 2.9462648637884567e-05,
"loss": 0.775,
"step": 523
},
{
"epoch": 0.36,
"learning_rate": 2.9422972620430105e-05,
"loss": 0.8004,
"step": 524
},
{
"epoch": 0.36,
"learning_rate": 2.9383248881193398e-05,
"loss": 0.8445,
"step": 525
},
{
"epoch": 0.37,
"learning_rate": 2.9343477621351676e-05,
"loss": 0.7917,
"step": 526
},
{
"epoch": 0.37,
"learning_rate": 2.9303659042322848e-05,
"loss": 0.8048,
"step": 527
},
{
"epoch": 0.37,
"learning_rate": 2.926379334576447e-05,
"loss": 0.769,
"step": 528
},
{
"epoch": 0.37,
"learning_rate": 2.9223880733572706e-05,
"loss": 0.818,
"step": 529
},
{
"epoch": 0.37,
"learning_rate": 2.9183921407881324e-05,
"loss": 0.8458,
"step": 530
},
{
"epoch": 0.37,
"learning_rate": 2.9143915571060684e-05,
"loss": 0.8264,
"step": 531
},
{
"epoch": 0.37,
"learning_rate": 2.910386342571667e-05,
"loss": 0.8269,
"step": 532
},
{
"epoch": 0.37,
"learning_rate": 2.906376517468972e-05,
"loss": 0.8368,
"step": 533
},
{
"epoch": 0.37,
"learning_rate": 2.9023621021053738e-05,
"loss": 0.7787,
"step": 534
},
{
"epoch": 0.37,
"learning_rate": 2.8983431168115124e-05,
"loss": 0.7991,
"step": 535
},
{
"epoch": 0.37,
"learning_rate": 2.8943195819411715e-05,
"loss": 0.7683,
"step": 536
},
{
"epoch": 0.37,
"learning_rate": 2.8902915178711746e-05,
"loss": 0.8276,
"step": 537
},
{
"epoch": 0.37,
"learning_rate": 2.886258945001283e-05,
"loss": 0.782,
"step": 538
},
{
"epoch": 0.37,
"learning_rate": 2.8822218837540936e-05,
"loss": 0.8099,
"step": 539
},
{
"epoch": 0.38,
"learning_rate": 2.8781803545749336e-05,
"loss": 0.8173,
"step": 540
},
{
"epoch": 0.38,
"learning_rate": 2.8741343779317565e-05,
"loss": 0.808,
"step": 541
},
{
"epoch": 0.38,
"learning_rate": 2.870083974315042e-05,
"loss": 0.8211,
"step": 542
},
{
"epoch": 0.38,
"learning_rate": 2.8660291642376874e-05,
"loss": 0.7793,
"step": 543
},
{
"epoch": 0.38,
"learning_rate": 2.8619699682349075e-05,
"loss": 0.8168,
"step": 544
},
{
"epoch": 0.38,
"learning_rate": 2.8579064068641297e-05,
"loss": 0.899,
"step": 545
},
{
"epoch": 0.38,
"learning_rate": 2.853838500704887e-05,
"loss": 0.8731,
"step": 546
},
{
"epoch": 0.38,
"learning_rate": 2.8497662703587185e-05,
"loss": 0.7993,
"step": 547
},
{
"epoch": 0.38,
"learning_rate": 2.845689736449062e-05,
"loss": 0.8024,
"step": 548
},
{
"epoch": 0.38,
"learning_rate": 2.841608919621151e-05,
"loss": 0.7873,
"step": 549
},
{
"epoch": 0.38,
"learning_rate": 2.8375238405419076e-05,
"loss": 0.7908,
"step": 550
},
{
"epoch": 0.38,
"learning_rate": 2.8334345198998418e-05,
"loss": 0.8356,
"step": 551
},
{
"epoch": 0.38,
"learning_rate": 2.8293409784049428e-05,
"loss": 0.803,
"step": 552
},
{
"epoch": 0.38,
"learning_rate": 2.8252432367885777e-05,
"loss": 0.8394,
"step": 553
},
{
"epoch": 0.38,
"learning_rate": 2.821141315803383e-05,
"loss": 0.8209,
"step": 554
},
{
"epoch": 0.39,
"learning_rate": 2.8170352362231623e-05,
"loss": 0.831,
"step": 555
},
{
"epoch": 0.39,
"learning_rate": 2.81292501884278e-05,
"loss": 0.7913,
"step": 556
},
{
"epoch": 0.39,
"learning_rate": 2.808810684478056e-05,
"loss": 0.8403,
"step": 557
},
{
"epoch": 0.39,
"learning_rate": 2.8046922539656594e-05,
"loss": 0.8512,
"step": 558
},
{
"epoch": 0.39,
"learning_rate": 2.8005697481630046e-05,
"loss": 0.7872,
"step": 559
},
{
"epoch": 0.39,
"learning_rate": 2.7964431879481452e-05,
"loss": 0.8268,
"step": 560
},
{
"epoch": 0.39,
"learning_rate": 2.7923125942196674e-05,
"loss": 0.8223,
"step": 561
},
{
"epoch": 0.39,
"learning_rate": 2.788177987896585e-05,
"loss": 0.8072,
"step": 562
},
{
"epoch": 0.39,
"learning_rate": 2.7840393899182333e-05,
"loss": 0.8717,
"step": 563
},
{
"epoch": 0.39,
"learning_rate": 2.779896821244163e-05,
"loss": 0.8287,
"step": 564
},
{
"epoch": 0.39,
"learning_rate": 2.775750302854034e-05,
"loss": 0.8165,
"step": 565
},
{
"epoch": 0.39,
"learning_rate": 2.771599855747509e-05,
"loss": 0.8381,
"step": 566
},
{
"epoch": 0.39,
"learning_rate": 2.7674455009441477e-05,
"loss": 0.808,
"step": 567
},
{
"epoch": 0.39,
"learning_rate": 2.763287259483299e-05,
"loss": 0.808,
"step": 568
},
{
"epoch": 0.4,
"learning_rate": 2.7591251524239974e-05,
"loss": 0.8203,
"step": 569
},
{
"epoch": 0.4,
"learning_rate": 2.7549592008448516e-05,
"loss": 0.8468,
"step": 570
},
{
"epoch": 0.4,
"learning_rate": 2.7507894258439427e-05,
"loss": 0.8421,
"step": 571
},
{
"epoch": 0.4,
"learning_rate": 2.7466158485387145e-05,
"loss": 0.7499,
"step": 572
},
{
"epoch": 0.4,
"learning_rate": 2.7424384900658675e-05,
"loss": 0.8043,
"step": 573
},
{
"epoch": 0.4,
"learning_rate": 2.7382573715812508e-05,
"loss": 0.7767,
"step": 574
},
{
"epoch": 0.4,
"learning_rate": 2.7340725142597562e-05,
"loss": 0.8238,
"step": 575
},
{
"epoch": 0.4,
"learning_rate": 2.7298839392952113e-05,
"loss": 0.79,
"step": 576
},
{
"epoch": 0.4,
"learning_rate": 2.72569166790027e-05,
"loss": 0.8484,
"step": 577
},
{
"epoch": 0.4,
"learning_rate": 2.7214957213063066e-05,
"loss": 0.8194,
"step": 578
},
{
"epoch": 0.4,
"learning_rate": 2.717296120763309e-05,
"loss": 0.797,
"step": 579
},
{
"epoch": 0.4,
"learning_rate": 2.71309288753977e-05,
"loss": 0.8005,
"step": 580
},
{
"epoch": 0.4,
"learning_rate": 2.7088860429225792e-05,
"loss": 0.8013,
"step": 581
},
{
"epoch": 0.4,
"learning_rate": 2.704675608216915e-05,
"loss": 0.8068,
"step": 582
},
{
"epoch": 0.4,
"learning_rate": 2.7004616047461407e-05,
"loss": 0.8102,
"step": 583
},
{
"epoch": 0.41,
"learning_rate": 2.6962440538516897e-05,
"loss": 0.8346,
"step": 584
},
{
"epoch": 0.41,
"learning_rate": 2.6920229768929628e-05,
"loss": 0.7862,
"step": 585
},
{
"epoch": 0.41,
"learning_rate": 2.6877983952472174e-05,
"loss": 0.8009,
"step": 586
},
{
"epoch": 0.41,
"learning_rate": 2.6835703303094612e-05,
"loss": 0.8275,
"step": 587
},
{
"epoch": 0.41,
"learning_rate": 2.6793388034923416e-05,
"loss": 0.8401,
"step": 588
},
{
"epoch": 0.41,
"learning_rate": 2.675103836226039e-05,
"loss": 0.7392,
"step": 589
},
{
"epoch": 0.41,
"learning_rate": 2.6708654499581572e-05,
"loss": 0.7857,
"step": 590
},
{
"epoch": 0.41,
"learning_rate": 2.6666236661536165e-05,
"loss": 0.8182,
"step": 591
},
{
"epoch": 0.41,
"learning_rate": 2.662378506294541e-05,
"loss": 0.8645,
"step": 592
},
{
"epoch": 0.41,
"learning_rate": 2.6581299918801554e-05,
"loss": 0.8258,
"step": 593
},
{
"epoch": 0.41,
"learning_rate": 2.6538781444266716e-05,
"loss": 0.833,
"step": 594
},
{
"epoch": 0.41,
"learning_rate": 2.6496229854671817e-05,
"loss": 0.833,
"step": 595
},
{
"epoch": 0.41,
"learning_rate": 2.645364536551549e-05,
"loss": 0.7763,
"step": 596
},
{
"epoch": 0.41,
"learning_rate": 2.641102819246298e-05,
"loss": 0.8006,
"step": 597
},
{
"epoch": 0.42,
"learning_rate": 2.6368378551345065e-05,
"loss": 0.8213,
"step": 598
},
{
"epoch": 0.42,
"learning_rate": 2.632569665815694e-05,
"loss": 0.8386,
"step": 599
},
{
"epoch": 0.42,
"learning_rate": 2.628298272905715e-05,
"loss": 0.8102,
"step": 600
},
{
"epoch": 0.42,
"learning_rate": 2.6240236980366475e-05,
"loss": 0.8366,
"step": 601
},
{
"epoch": 0.42,
"learning_rate": 2.6197459628566852e-05,
"loss": 0.8363,
"step": 602
},
{
"epoch": 0.42,
"learning_rate": 2.6154650890300266e-05,
"loss": 0.8156,
"step": 603
},
{
"epoch": 0.42,
"learning_rate": 2.6111810982367643e-05,
"loss": 0.8154,
"step": 604
},
{
"epoch": 0.42,
"learning_rate": 2.6068940121727782e-05,
"loss": 0.8362,
"step": 605
},
{
"epoch": 0.42,
"learning_rate": 2.6026038525496223e-05,
"loss": 0.7732,
"step": 606
},
{
"epoch": 0.42,
"learning_rate": 2.5983106410944182e-05,
"loss": 0.8074,
"step": 607
},
{
"epoch": 0.42,
"learning_rate": 2.5940143995497423e-05,
"loss": 0.8294,
"step": 608
},
{
"epoch": 0.42,
"learning_rate": 2.589715149673517e-05,
"loss": 0.7937,
"step": 609
},
{
"epoch": 0.42,
"learning_rate": 2.5854129132388986e-05,
"loss": 0.8494,
"step": 610
},
{
"epoch": 0.42,
"learning_rate": 2.581107712034171e-05,
"loss": 0.8465,
"step": 611
},
{
"epoch": 0.42,
"learning_rate": 2.57679956786263e-05,
"loss": 0.8149,
"step": 612
},
{
"epoch": 0.43,
"learning_rate": 2.572488502542479e-05,
"loss": 0.86,
"step": 613
},
{
"epoch": 0.43,
"learning_rate": 2.5681745379067124e-05,
"loss": 0.8503,
"step": 614
},
{
"epoch": 0.43,
"learning_rate": 2.5638576958030096e-05,
"loss": 0.8016,
"step": 615
},
{
"epoch": 0.43,
"learning_rate": 2.5595379980936227e-05,
"loss": 0.804,
"step": 616
},
{
"epoch": 0.43,
"learning_rate": 2.5552154666552652e-05,
"loss": 0.8164,
"step": 617
},
{
"epoch": 0.43,
"learning_rate": 2.5508901233790013e-05,
"loss": 0.8054,
"step": 618
},
{
"epoch": 0.43,
"learning_rate": 2.546561990170137e-05,
"loss": 0.7889,
"step": 619
},
{
"epoch": 0.43,
"learning_rate": 2.5422310889481058e-05,
"loss": 0.8306,
"step": 620
},
{
"epoch": 0.43,
"learning_rate": 2.537897441646361e-05,
"loss": 0.7946,
"step": 621
},
{
"epoch": 0.43,
"learning_rate": 2.5335610702122628e-05,
"loss": 0.8092,
"step": 622
},
{
"epoch": 0.43,
"learning_rate": 2.5292219966069666e-05,
"loss": 0.7738,
"step": 623
},
{
"epoch": 0.43,
"learning_rate": 2.5248802428053148e-05,
"loss": 0.816,
"step": 624
},
{
"epoch": 0.43,
"learning_rate": 2.5205358307957205e-05,
"loss": 0.8472,
"step": 625
},
{
"epoch": 0.43,
"learning_rate": 2.5161887825800618e-05,
"loss": 0.8091,
"step": 626
},
{
"epoch": 0.44,
"learning_rate": 2.511839120173566e-05,
"loss": 0.8092,
"step": 627
},
{
"epoch": 0.44,
"learning_rate": 2.5074868656047003e-05,
"loss": 0.8786,
"step": 628
},
{
"epoch": 0.44,
"learning_rate": 2.5031320409150595e-05,
"loss": 0.859,
"step": 629
},
{
"epoch": 0.44,
"learning_rate": 2.4987746681592543e-05,
"loss": 0.8142,
"step": 630
},
{
"epoch": 0.44,
"learning_rate": 2.494414769404801e-05,
"loss": 0.7988,
"step": 631
},
{
"epoch": 0.44,
"learning_rate": 2.4900523667320067e-05,
"loss": 0.7934,
"step": 632
},
{
"epoch": 0.44,
"learning_rate": 2.485687482233861e-05,
"loss": 0.8161,
"step": 633
},
{
"epoch": 0.44,
"learning_rate": 2.4813201380159216e-05,
"loss": 0.8511,
"step": 634
},
{
"epoch": 0.44,
"learning_rate": 2.476950356196204e-05,
"loss": 0.8234,
"step": 635
},
{
"epoch": 0.44,
"learning_rate": 2.4725781589050684e-05,
"loss": 0.8144,
"step": 636
},
{
"epoch": 0.44,
"learning_rate": 2.468203568285106e-05,
"loss": 0.8494,
"step": 637
},
{
"epoch": 0.44,
"learning_rate": 2.4638266064910328e-05,
"loss": 0.7909,
"step": 638
},
{
"epoch": 0.44,
"learning_rate": 2.4594472956895695e-05,
"loss": 0.7822,
"step": 639
},
{
"epoch": 0.44,
"learning_rate": 2.4550656580593355e-05,
"loss": 0.8195,
"step": 640
},
{
"epoch": 0.45,
"learning_rate": 2.4506817157907335e-05,
"loss": 0.8412,
"step": 641
},
{
"epoch": 0.45,
"learning_rate": 2.446295491085837e-05,
"loss": 0.7965,
"step": 642
},
{
"epoch": 0.45,
"learning_rate": 2.4419070061582808e-05,
"loss": 0.8382,
"step": 643
},
{
"epoch": 0.45,
"learning_rate": 2.4375162832331443e-05,
"loss": 0.8502,
"step": 644
},
{
"epoch": 0.45,
"learning_rate": 2.4331233445468422e-05,
"loss": 0.8548,
"step": 645
},
{
"epoch": 0.45,
"learning_rate": 2.4287282123470097e-05,
"loss": 0.7867,
"step": 646
},
{
"epoch": 0.45,
"learning_rate": 2.424330908892392e-05,
"loss": 0.84,
"step": 647
},
{
"epoch": 0.45,
"learning_rate": 2.4199314564527302e-05,
"loss": 0.7803,
"step": 648
},
{
"epoch": 0.45,
"learning_rate": 2.4155298773086476e-05,
"loss": 0.8249,
"step": 649
},
{
"epoch": 0.45,
"learning_rate": 2.4111261937515393e-05,
"loss": 0.8718,
"step": 650
},
{
"epoch": 0.45,
"learning_rate": 2.4067204280834576e-05,
"loss": 0.7704,
"step": 651
},
{
"epoch": 0.45,
"learning_rate": 2.4023126026169993e-05,
"loss": 0.7933,
"step": 652
},
{
"epoch": 0.45,
"learning_rate": 2.3979027396751936e-05,
"loss": 0.7884,
"step": 653
},
{
"epoch": 0.45,
"learning_rate": 2.3934908615913867e-05,
"loss": 0.7676,
"step": 654
},
{
"epoch": 0.45,
"learning_rate": 2.389076990709132e-05,
"loss": 0.7941,
"step": 655
},
{
"epoch": 0.46,
"learning_rate": 2.3846611493820743e-05,
"loss": 0.7417,
"step": 656
},
{
"epoch": 0.46,
"learning_rate": 2.3802433599738376e-05,
"loss": 0.7911,
"step": 657
},
{
"epoch": 0.46,
"learning_rate": 2.3758236448579126e-05,
"loss": 0.8625,
"step": 658
},
{
"epoch": 0.46,
"learning_rate": 2.371402026417541e-05,
"loss": 0.8415,
"step": 659
},
{
"epoch": 0.46,
"learning_rate": 2.366978527045605e-05,
"loss": 0.8154,
"step": 660
},
{
"epoch": 0.46,
"learning_rate": 2.3625531691445122e-05,
"loss": 0.7642,
"step": 661
},
{
"epoch": 0.46,
"learning_rate": 2.3581259751260824e-05,
"loss": 0.8275,
"step": 662
},
{
"epoch": 0.46,
"learning_rate": 2.3536969674114353e-05,
"loss": 0.8064,
"step": 663
},
{
"epoch": 0.46,
"learning_rate": 2.3492661684308743e-05,
"loss": 0.7934,
"step": 664
},
{
"epoch": 0.46,
"learning_rate": 2.3448336006237753e-05,
"loss": 0.7891,
"step": 665
},
{
"epoch": 0.46,
"learning_rate": 2.3403992864384725e-05,
"loss": 0.8232,
"step": 666
},
{
"epoch": 0.46,
"learning_rate": 2.3359632483321438e-05,
"loss": 0.8195,
"step": 667
},
{
"epoch": 0.46,
"learning_rate": 2.3315255087706982e-05,
"loss": 0.7624,
"step": 668
},
{
"epoch": 0.46,
"learning_rate": 2.3270860902286616e-05,
"loss": 0.8377,
"step": 669
},
{
"epoch": 0.47,
"learning_rate": 2.322645015189063e-05,
"loss": 0.8417,
"step": 670
},
{
"epoch": 0.47,
"learning_rate": 2.31820230614332e-05,
"loss": 0.812,
"step": 671
},
{
"epoch": 0.47,
"learning_rate": 2.313757985591126e-05,
"loss": 0.7848,
"step": 672
},
{
"epoch": 0.47,
"learning_rate": 2.309312076040336e-05,
"loss": 0.8258,
"step": 673
},
{
"epoch": 0.47,
"learning_rate": 2.3048646000068512e-05,
"loss": 0.8316,
"step": 674
},
{
"epoch": 0.47,
"learning_rate": 2.300415580014507e-05,
"loss": 0.7765,
"step": 675
},
{
"epoch": 0.47,
"learning_rate": 2.2959650385949583e-05,
"loss": 0.7435,
"step": 676
},
{
"epoch": 0.47,
"learning_rate": 2.291512998287565e-05,
"loss": 0.8527,
"step": 677
},
{
"epoch": 0.47,
"learning_rate": 2.2870594816392765e-05,
"loss": 0.7999,
"step": 678
},
{
"epoch": 0.47,
"learning_rate": 2.282604511204521e-05,
"loss": 0.8366,
"step": 679
},
{
"epoch": 0.47,
"learning_rate": 2.2781481095450886e-05,
"loss": 0.7775,
"step": 680
},
{
"epoch": 0.47,
"learning_rate": 2.2736902992300176e-05,
"loss": 0.8267,
"step": 681
},
{
"epoch": 0.47,
"learning_rate": 2.26923110283548e-05,
"loss": 0.7988,
"step": 682
},
{
"epoch": 0.47,
"learning_rate": 2.264770542944667e-05,
"loss": 0.8329,
"step": 683
},
{
"epoch": 0.47,
"learning_rate": 2.2603086421476766e-05,
"loss": 0.7767,
"step": 684
},
{
"epoch": 0.48,
"learning_rate": 2.2558454230413977e-05,
"loss": 0.8338,
"step": 685
},
{
"epoch": 0.48,
"learning_rate": 2.2513809082293932e-05,
"loss": 0.8196,
"step": 686
},
{
"epoch": 0.48,
"learning_rate": 2.2469151203217913e-05,
"loss": 0.8036,
"step": 687
},
{
"epoch": 0.48,
"learning_rate": 2.242448081935165e-05,
"loss": 0.7718,
"step": 688
},
{
"epoch": 0.48,
"learning_rate": 2.2379798156924214e-05,
"loss": 0.8044,
"step": 689
},
{
"epoch": 0.48,
"learning_rate": 2.233510344222687e-05,
"loss": 0.7716,
"step": 690
},
{
"epoch": 0.48,
"learning_rate": 2.2290396901611896e-05,
"loss": 0.7822,
"step": 691
},
{
"epoch": 0.48,
"learning_rate": 2.2245678761491475e-05,
"loss": 0.8671,
"step": 692
},
{
"epoch": 0.48,
"learning_rate": 2.2200949248336538e-05,
"loss": 0.7857,
"step": 693
},
{
"epoch": 0.48,
"learning_rate": 2.215620858867561e-05,
"loss": 0.8142,
"step": 694
},
{
"epoch": 0.48,
"learning_rate": 2.211145700909367e-05,
"loss": 0.7763,
"step": 695
},
{
"epoch": 0.48,
"learning_rate": 2.206669473623099e-05,
"loss": 0.7718,
"step": 696
},
{
"epoch": 0.48,
"learning_rate": 2.2021921996782007e-05,
"loss": 0.8657,
"step": 697
},
{
"epoch": 0.48,
"learning_rate": 2.197713901749415e-05,
"loss": 0.7712,
"step": 698
},
{
"epoch": 0.49,
"learning_rate": 2.1932346025166734e-05,
"loss": 0.8315,
"step": 699
},
{
"epoch": 0.49,
"learning_rate": 2.1887543246649768e-05,
"loss": 0.7904,
"step": 700
},
{
"epoch": 0.49,
"learning_rate": 2.1842730908842807e-05,
"loss": 0.8018,
"step": 701
},
{
"epoch": 0.49,
"learning_rate": 2.179790923869385e-05,
"loss": 0.7698,
"step": 702
},
{
"epoch": 0.49,
"learning_rate": 2.1753078463198138e-05,
"loss": 0.8146,
"step": 703
},
{
"epoch": 0.49,
"learning_rate": 2.170823880939702e-05,
"loss": 0.8029,
"step": 704
},
{
"epoch": 0.49,
"learning_rate": 2.166339050437683e-05,
"loss": 0.7725,
"step": 705
},
{
"epoch": 0.49,
"learning_rate": 2.1618533775267698e-05,
"loss": 0.741,
"step": 706
},
{
"epoch": 0.49,
"learning_rate": 2.157366884924242e-05,
"loss": 0.7853,
"step": 707
},
{
"epoch": 0.49,
"learning_rate": 2.1528795953515315e-05,
"loss": 0.8232,
"step": 708
},
{
"epoch": 0.49,
"learning_rate": 2.1483915315341046e-05,
"loss": 0.8487,
"step": 709
},
{
"epoch": 0.49,
"learning_rate": 2.1439027162013503e-05,
"loss": 0.8066,
"step": 710
},
{
"epoch": 0.49,
"learning_rate": 2.139413172086463e-05,
"loss": 0.8007,
"step": 711
},
{
"epoch": 0.49,
"learning_rate": 2.134922921926327e-05,
"loss": 0.7902,
"step": 712
},
{
"epoch": 0.5,
"learning_rate": 2.130431988461404e-05,
"loss": 0.8026,
"step": 713
},
{
"epoch": 0.5,
"learning_rate": 2.125940394435616e-05,
"loss": 0.8095,
"step": 714
},
{
"epoch": 0.5,
"learning_rate": 2.121448162596229e-05,
"loss": 0.7573,
"step": 715
},
{
"epoch": 0.5,
"learning_rate": 2.1169553156937397e-05,
"loss": 0.8209,
"step": 716
},
{
"epoch": 0.5,
"learning_rate": 2.11246187648176e-05,
"loss": 0.8102,
"step": 717
},
{
"epoch": 0.5,
"learning_rate": 2.1079678677169018e-05,
"loss": 0.802,
"step": 718
},
{
"epoch": 0.5,
"learning_rate": 2.103473312158661e-05,
"loss": 0.785,
"step": 719
},
{
"epoch": 0.5,
"learning_rate": 2.098978232569303e-05,
"loss": 0.8313,
"step": 720
},
{
"epoch": 0.5,
"learning_rate": 2.0944826517137468e-05,
"loss": 0.7707,
"step": 721
},
{
"epoch": 0.5,
"learning_rate": 2.0899865923594497e-05,
"loss": 0.8222,
"step": 722
},
{
"epoch": 0.5,
"learning_rate": 2.0854900772762926e-05,
"loss": 0.7831,
"step": 723
},
{
"epoch": 0.5,
"learning_rate": 2.080993129236466e-05,
"loss": 0.7989,
"step": 724
},
{
"epoch": 0.5,
"learning_rate": 2.0764957710143503e-05,
"loss": 0.8165,
"step": 725
},
{
"epoch": 0.5,
"learning_rate": 2.0719980253864045e-05,
"loss": 0.7626,
"step": 726
},
{
"epoch": 0.5,
"learning_rate": 2.06749991513105e-05,
"loss": 0.8205,
"step": 727
},
{
"epoch": 0.51,
"learning_rate": 2.0630014630285543e-05,
"loss": 0.8251,
"step": 728
},
{
"epoch": 0.51,
"learning_rate": 2.058502691860916e-05,
"loss": 0.8449,
"step": 729
},
{
"epoch": 0.51,
"learning_rate": 2.0540036244117506e-05,
"loss": 0.8018,
"step": 730
},
{
"epoch": 0.51,
"learning_rate": 2.0495042834661727e-05,
"loss": 0.8113,
"step": 731
},
{
"epoch": 0.51,
"learning_rate": 2.0450046918106833e-05,
"loss": 0.8152,
"step": 732
},
{
"epoch": 0.51,
"learning_rate": 2.040504872233051e-05,
"loss": 0.8538,
"step": 733
},
{
"epoch": 0.51,
"learning_rate": 2.036004847522202e-05,
"loss": 0.8253,
"step": 734
},
{
"epoch": 0.51,
"learning_rate": 2.0315046404680982e-05,
"loss": 0.8688,
"step": 735
},
{
"epoch": 0.51,
"learning_rate": 2.0270042738616276e-05,
"loss": 0.8398,
"step": 736
},
{
"epoch": 0.51,
"learning_rate": 2.022503770494483e-05,
"loss": 0.8609,
"step": 737
},
{
"epoch": 0.51,
"learning_rate": 2.018003153159053e-05,
"loss": 0.7594,
"step": 738
},
{
"epoch": 0.51,
"learning_rate": 2.0135024446483018e-05,
"loss": 0.8282,
"step": 739
},
{
"epoch": 0.51,
"learning_rate": 2.009001667755656e-05,
"loss": 0.7923,
"step": 740
},
{
"epoch": 0.51,
"learning_rate": 2.004500845274888e-05,
"loss": 0.8154,
"step": 741
},
{
"epoch": 0.52,
"learning_rate": 2e-05,
"loss": 0.8124,
"step": 742
},
{
"epoch": 0.52,
"learning_rate": 1.9954991547251124e-05,
"loss": 0.8072,
"step": 743
},
{
"epoch": 0.52,
"learning_rate": 1.9909983322443448e-05,
"loss": 0.7879,
"step": 744
},
{
"epoch": 0.52,
"learning_rate": 1.986497555351698e-05,
"loss": 0.7698,
"step": 745
},
{
"epoch": 0.52,
"learning_rate": 1.9819968468409476e-05,
"loss": 0.8014,
"step": 746
},
{
"epoch": 0.52,
"learning_rate": 1.9774962295055175e-05,
"loss": 0.7969,
"step": 747
},
{
"epoch": 0.52,
"learning_rate": 1.972995726138373e-05,
"loss": 0.7744,
"step": 748
},
{
"epoch": 0.52,
"learning_rate": 1.9684953595319018e-05,
"loss": 0.7597,
"step": 749
},
{
"epoch": 0.52,
"learning_rate": 1.9639951524777986e-05,
"loss": 0.773,
"step": 750
},
{
"epoch": 0.52,
"learning_rate": 1.959495127766949e-05,
"loss": 0.8625,
"step": 751
},
{
"epoch": 0.52,
"learning_rate": 1.9549953081893177e-05,
"loss": 0.7468,
"step": 752
},
{
"epoch": 0.52,
"learning_rate": 1.9504957165338273e-05,
"loss": 0.7796,
"step": 753
},
{
"epoch": 0.52,
"learning_rate": 1.9459963755882497e-05,
"loss": 0.7703,
"step": 754
},
{
"epoch": 0.52,
"learning_rate": 1.941497308139084e-05,
"loss": 0.8079,
"step": 755
},
{
"epoch": 0.53,
"learning_rate": 1.9369985369714464e-05,
"loss": 0.8194,
"step": 756
},
{
"epoch": 0.53,
"learning_rate": 1.9325000848689502e-05,
"loss": 0.815,
"step": 757
},
{
"epoch": 0.53,
"learning_rate": 1.9280019746135962e-05,
"loss": 0.7926,
"step": 758
},
{
"epoch": 0.53,
"learning_rate": 1.9235042289856504e-05,
"loss": 0.8226,
"step": 759
},
{
"epoch": 0.53,
"learning_rate": 1.9190068707635346e-05,
"loss": 0.8123,
"step": 760
},
{
"epoch": 0.53,
"learning_rate": 1.9145099227237074e-05,
"loss": 0.7513,
"step": 761
},
{
"epoch": 0.53,
"learning_rate": 1.9100134076405513e-05,
"loss": 0.7926,
"step": 762
},
{
"epoch": 0.53,
"learning_rate": 1.905517348286254e-05,
"loss": 0.8738,
"step": 763
},
{
"epoch": 0.53,
"learning_rate": 1.9010217674306978e-05,
"loss": 0.8426,
"step": 764
},
{
"epoch": 0.53,
"learning_rate": 1.8965266878413393e-05,
"loss": 0.787,
"step": 765
},
{
"epoch": 0.53,
"learning_rate": 1.8920321322830992e-05,
"loss": 0.7579,
"step": 766
},
{
"epoch": 0.53,
"learning_rate": 1.8875381235182405e-05,
"loss": 0.8149,
"step": 767
},
{
"epoch": 0.53,
"learning_rate": 1.8830446843062617e-05,
"loss": 0.8015,
"step": 768
},
{
"epoch": 0.53,
"learning_rate": 1.8785518374037716e-05,
"loss": 0.7897,
"step": 769
},
{
"epoch": 0.53,
"learning_rate": 1.8740596055643848e-05,
"loss": 0.7561,
"step": 770
},
{
"epoch": 0.54,
"learning_rate": 1.8695680115385962e-05,
"loss": 0.8149,
"step": 771
},
{
"epoch": 0.54,
"learning_rate": 1.8650770780736735e-05,
"loss": 0.7569,
"step": 772
},
{
"epoch": 0.54,
"learning_rate": 1.860586827913538e-05,
"loss": 0.7364,
"step": 773
},
{
"epoch": 0.54,
"learning_rate": 1.8560972837986507e-05,
"loss": 0.8061,
"step": 774
},
{
"epoch": 0.54,
"learning_rate": 1.851608468465896e-05,
"loss": 0.8148,
"step": 775
},
{
"epoch": 0.54,
"learning_rate": 1.84712040464847e-05,
"loss": 0.7717,
"step": 776
},
{
"epoch": 0.54,
"learning_rate": 1.8426331150757585e-05,
"loss": 0.7927,
"step": 777
},
{
"epoch": 0.54,
"learning_rate": 1.8381466224732315e-05,
"loss": 0.8235,
"step": 778
},
{
"epoch": 0.54,
"learning_rate": 1.8336609495623177e-05,
"loss": 0.8203,
"step": 779
},
{
"epoch": 0.54,
"learning_rate": 1.829176119060299e-05,
"loss": 0.7764,
"step": 780
},
{
"epoch": 0.54,
"learning_rate": 1.824692153680187e-05,
"loss": 0.7995,
"step": 781
},
{
"epoch": 0.54,
"learning_rate": 1.820209076130615e-05,
"loss": 0.7576,
"step": 782
},
{
"epoch": 0.54,
"learning_rate": 1.8157269091157196e-05,
"loss": 0.8403,
"step": 783
},
{
"epoch": 0.54,
"learning_rate": 1.8112456753350235e-05,
"loss": 0.7891,
"step": 784
},
{
"epoch": 0.55,
"learning_rate": 1.806765397483327e-05,
"loss": 0.8589,
"step": 785
},
{
"epoch": 0.55,
"learning_rate": 1.802286098250585e-05,
"loss": 0.7905,
"step": 786
},
{
"epoch": 0.55,
"learning_rate": 1.7978078003218003e-05,
"loss": 0.8142,
"step": 787
},
{
"epoch": 0.55,
"learning_rate": 1.793330526376901e-05,
"loss": 0.7758,
"step": 788
},
{
"epoch": 0.55,
"learning_rate": 1.7888542990906333e-05,
"loss": 0.8048,
"step": 789
},
{
"epoch": 0.55,
"learning_rate": 1.784379141132439e-05,
"loss": 0.7883,
"step": 790
},
{
"epoch": 0.55,
"learning_rate": 1.7799050751663465e-05,
"loss": 0.8716,
"step": 791
},
{
"epoch": 0.55,
"learning_rate": 1.7754321238508528e-05,
"loss": 0.7454,
"step": 792
},
{
"epoch": 0.55,
"learning_rate": 1.770960309838811e-05,
"loss": 0.7661,
"step": 793
},
{
"epoch": 0.55,
"learning_rate": 1.7664896557773134e-05,
"loss": 0.7394,
"step": 794
},
{
"epoch": 0.55,
"learning_rate": 1.762020184307579e-05,
"loss": 0.7659,
"step": 795
},
{
"epoch": 0.55,
"learning_rate": 1.7575519180648353e-05,
"loss": 0.8107,
"step": 796
},
{
"epoch": 0.55,
"learning_rate": 1.7530848796782094e-05,
"loss": 0.7729,
"step": 797
},
{
"epoch": 0.55,
"learning_rate": 1.7486190917706068e-05,
"loss": 0.8004,
"step": 798
},
{
"epoch": 0.55,
"learning_rate": 1.7441545769586033e-05,
"loss": 0.846,
"step": 799
},
{
"epoch": 0.56,
"learning_rate": 1.7396913578523234e-05,
"loss": 0.7584,
"step": 800
},
{
"epoch": 0.56,
"learning_rate": 1.7352294570553336e-05,
"loss": 0.7958,
"step": 801
},
{
"epoch": 0.56,
"learning_rate": 1.7307688971645206e-05,
"loss": 0.7743,
"step": 802
},
{
"epoch": 0.56,
"learning_rate": 1.726309700769983e-05,
"loss": 0.8074,
"step": 803
},
{
"epoch": 0.56,
"learning_rate": 1.7218518904549117e-05,
"loss": 0.7645,
"step": 804
},
{
"epoch": 0.56,
"learning_rate": 1.7173954887954792e-05,
"loss": 0.7918,
"step": 805
},
{
"epoch": 0.56,
"learning_rate": 1.712940518360724e-05,
"loss": 0.776,
"step": 806
},
{
"epoch": 0.56,
"learning_rate": 1.708487001712436e-05,
"loss": 0.7624,
"step": 807
},
{
"epoch": 0.56,
"learning_rate": 1.704034961405042e-05,
"loss": 0.7552,
"step": 808
},
{
"epoch": 0.56,
"learning_rate": 1.6995844199854938e-05,
"loss": 0.7646,
"step": 809
},
{
"epoch": 0.56,
"learning_rate": 1.6951353999931495e-05,
"loss": 0.7813,
"step": 810
},
{
"epoch": 0.56,
"learning_rate": 1.690687923959665e-05,
"loss": 0.8008,
"step": 811
},
{
"epoch": 0.56,
"learning_rate": 1.6862420144088742e-05,
"loss": 0.7559,
"step": 812
},
{
"epoch": 0.56,
"learning_rate": 1.6817976938566805e-05,
"loss": 0.7952,
"step": 813
},
{
"epoch": 0.57,
"learning_rate": 1.6773549848109372e-05,
"loss": 0.8163,
"step": 814
},
{
"epoch": 0.57,
"learning_rate": 1.672913909771339e-05,
"loss": 0.8387,
"step": 815
},
{
"epoch": 0.57,
"learning_rate": 1.6684744912293024e-05,
"loss": 0.7715,
"step": 816
},
{
"epoch": 0.57,
"learning_rate": 1.664036751667857e-05,
"loss": 0.7939,
"step": 817
},
{
"epoch": 0.57,
"learning_rate": 1.659600713561528e-05,
"loss": 0.768,
"step": 818
},
{
"epoch": 0.57,
"learning_rate": 1.6551663993762257e-05,
"loss": 0.7705,
"step": 819
},
{
"epoch": 0.57,
"learning_rate": 1.6507338315691264e-05,
"loss": 0.7931,
"step": 820
},
{
"epoch": 0.57,
"learning_rate": 1.6463030325885647e-05,
"loss": 0.7978,
"step": 821
},
{
"epoch": 0.57,
"learning_rate": 1.641874024873918e-05,
"loss": 0.825,
"step": 822
},
{
"epoch": 0.57,
"learning_rate": 1.637446830855488e-05,
"loss": 0.7979,
"step": 823
},
{
"epoch": 0.57,
"learning_rate": 1.6330214729543958e-05,
"loss": 0.7823,
"step": 824
},
{
"epoch": 0.57,
"learning_rate": 1.6285979735824598e-05,
"loss": 0.8234,
"step": 825
},
{
"epoch": 0.57,
"learning_rate": 1.624176355142088e-05,
"loss": 0.777,
"step": 826
},
{
"epoch": 0.57,
"learning_rate": 1.6197566400261627e-05,
"loss": 0.8426,
"step": 827
},
{
"epoch": 0.57,
"learning_rate": 1.6153388506179263e-05,
"loss": 0.7633,
"step": 828
},
{
"epoch": 0.58,
"learning_rate": 1.610923009290868e-05,
"loss": 0.8119,
"step": 829
},
{
"epoch": 0.58,
"learning_rate": 1.6065091384086136e-05,
"loss": 0.8027,
"step": 830
},
{
"epoch": 0.58,
"learning_rate": 1.6020972603248067e-05,
"loss": 0.7507,
"step": 831
},
{
"epoch": 0.58,
"learning_rate": 1.597687397383001e-05,
"loss": 0.7968,
"step": 832
},
{
"epoch": 0.58,
"learning_rate": 1.5932795719165427e-05,
"loss": 0.7848,
"step": 833
},
{
"epoch": 0.58,
"learning_rate": 1.5888738062484614e-05,
"loss": 0.7945,
"step": 834
},
{
"epoch": 0.58,
"learning_rate": 1.5844701226913527e-05,
"loss": 0.7554,
"step": 835
},
{
"epoch": 0.58,
"learning_rate": 1.5800685435472708e-05,
"loss": 0.8169,
"step": 836
},
{
"epoch": 0.58,
"learning_rate": 1.5756690911076086e-05,
"loss": 0.818,
"step": 837
},
{
"epoch": 0.58,
"learning_rate": 1.5712717876529907e-05,
"loss": 0.7843,
"step": 838
},
{
"epoch": 0.58,
"learning_rate": 1.5668766554531588e-05,
"loss": 0.7772,
"step": 839
},
{
"epoch": 0.58,
"learning_rate": 1.5624837167668564e-05,
"loss": 0.7861,
"step": 840
},
{
"epoch": 0.58,
"learning_rate": 1.5580929938417195e-05,
"loss": 0.7886,
"step": 841
},
{
"epoch": 0.58,
"learning_rate": 1.5537045089141636e-05,
"loss": 0.7902,
"step": 842
},
{
"epoch": 0.59,
"learning_rate": 1.5493182842092672e-05,
"loss": 0.7838,
"step": 843
},
{
"epoch": 0.59,
"learning_rate": 1.5449343419406655e-05,
"loss": 0.7591,
"step": 844
},
{
"epoch": 0.59,
"learning_rate": 1.5405527043104308e-05,
"loss": 0.8451,
"step": 845
},
{
"epoch": 0.59,
"learning_rate": 1.5361733935089682e-05,
"loss": 0.7582,
"step": 846
},
{
"epoch": 0.59,
"learning_rate": 1.5317964317148942e-05,
"loss": 0.7827,
"step": 847
},
{
"epoch": 0.59,
"learning_rate": 1.527421841094933e-05,
"loss": 0.7755,
"step": 848
},
{
"epoch": 0.59,
"learning_rate": 1.5230496438037964e-05,
"loss": 0.7779,
"step": 849
},
{
"epoch": 0.59,
"learning_rate": 1.5186798619840787e-05,
"loss": 0.8324,
"step": 850
},
{
"epoch": 0.59,
"learning_rate": 1.5143125177661396e-05,
"loss": 0.8044,
"step": 851
},
{
"epoch": 0.59,
"learning_rate": 1.5099476332679943e-05,
"loss": 0.7323,
"step": 852
},
{
"epoch": 0.59,
"learning_rate": 1.5055852305951998e-05,
"loss": 0.8008,
"step": 853
},
{
"epoch": 0.59,
"learning_rate": 1.5012253318407466e-05,
"loss": 0.8291,
"step": 854
},
{
"epoch": 0.59,
"learning_rate": 1.4968679590849413e-05,
"loss": 0.7875,
"step": 855
},
{
"epoch": 0.59,
"learning_rate": 1.4925131343953007e-05,
"loss": 0.7624,
"step": 856
},
{
"epoch": 0.6,
"learning_rate": 1.4881608798264346e-05,
"loss": 0.7589,
"step": 857
},
{
"epoch": 0.6,
"learning_rate": 1.483811217419939e-05,
"loss": 0.807,
"step": 858
},
{
"epoch": 0.6,
"learning_rate": 1.4794641692042797e-05,
"loss": 0.8163,
"step": 859
},
{
"epoch": 0.6,
"learning_rate": 1.4751197571946858e-05,
"loss": 0.815,
"step": 860
},
{
"epoch": 0.6,
"learning_rate": 1.470778003393034e-05,
"loss": 0.8091,
"step": 861
},
{
"epoch": 0.6,
"learning_rate": 1.4664389297877377e-05,
"loss": 0.7663,
"step": 862
},
{
"epoch": 0.6,
"learning_rate": 1.4621025583536398e-05,
"loss": 0.8202,
"step": 863
},
{
"epoch": 0.6,
"learning_rate": 1.4577689110518942e-05,
"loss": 0.7866,
"step": 864
},
{
"epoch": 0.6,
"learning_rate": 1.4534380098298637e-05,
"loss": 0.8161,
"step": 865
},
{
"epoch": 0.6,
"learning_rate": 1.4491098766209985e-05,
"loss": 0.737,
"step": 866
},
{
"epoch": 0.6,
"learning_rate": 1.4447845333447355e-05,
"loss": 0.8086,
"step": 867
},
{
"epoch": 0.6,
"learning_rate": 1.4404620019063771e-05,
"loss": 0.8112,
"step": 868
},
{
"epoch": 0.6,
"learning_rate": 1.4361423041969906e-05,
"loss": 0.8221,
"step": 869
},
{
"epoch": 0.6,
"learning_rate": 1.4318254620932881e-05,
"loss": 0.7961,
"step": 870
},
{
"epoch": 0.6,
"learning_rate": 1.4275114974575218e-05,
"loss": 0.7996,
"step": 871
},
{
"epoch": 0.61,
"learning_rate": 1.4232004321373702e-05,
"loss": 0.7915,
"step": 872
},
{
"epoch": 0.61,
"learning_rate": 1.41889228796583e-05,
"loss": 0.7745,
"step": 873
},
{
"epoch": 0.61,
"learning_rate": 1.4145870867611016e-05,
"loss": 0.7326,
"step": 874
},
{
"epoch": 0.61,
"learning_rate": 1.4102848503264837e-05,
"loss": 0.7862,
"step": 875
},
{
"epoch": 0.61,
"learning_rate": 1.4059856004502575e-05,
"loss": 0.7666,
"step": 876
},
{
"epoch": 0.61,
"learning_rate": 1.401689358905582e-05,
"loss": 0.7905,
"step": 877
},
{
"epoch": 0.61,
"learning_rate": 1.3973961474503778e-05,
"loss": 0.8005,
"step": 878
},
{
"epoch": 0.61,
"learning_rate": 1.3931059878272231e-05,
"loss": 0.83,
"step": 879
},
{
"epoch": 0.61,
"learning_rate": 1.3888189017632363e-05,
"loss": 0.8095,
"step": 880
},
{
"epoch": 0.61,
"learning_rate": 1.3845349109699742e-05,
"loss": 0.7519,
"step": 881
},
{
"epoch": 0.61,
"learning_rate": 1.3802540371433151e-05,
"loss": 0.7793,
"step": 882
},
{
"epoch": 0.61,
"learning_rate": 1.3759763019633528e-05,
"loss": 0.8405,
"step": 883
},
{
"epoch": 0.61,
"learning_rate": 1.3717017270942856e-05,
"loss": 0.7853,
"step": 884
},
{
"epoch": 0.61,
"learning_rate": 1.3674303341843069e-05,
"loss": 0.7407,
"step": 885
},
{
"epoch": 0.62,
"learning_rate": 1.3631621448654939e-05,
"loss": 0.7935,
"step": 886
},
{
"epoch": 0.62,
"learning_rate": 1.3588971807537026e-05,
"loss": 0.7762,
"step": 887
},
{
"epoch": 0.62,
"learning_rate": 1.3546354634484514e-05,
"loss": 0.791,
"step": 888
},
{
"epoch": 0.62,
"learning_rate": 1.3503770145328193e-05,
"loss": 0.795,
"step": 889
},
{
"epoch": 0.62,
"learning_rate": 1.3461218555733289e-05,
"loss": 0.7646,
"step": 890
},
{
"epoch": 0.62,
"learning_rate": 1.3418700081198454e-05,
"loss": 0.8193,
"step": 891
},
{
"epoch": 0.62,
"learning_rate": 1.3376214937054593e-05,
"loss": 0.8281,
"step": 892
},
{
"epoch": 0.62,
"learning_rate": 1.3333763338463844e-05,
"loss": 0.8483,
"step": 893
},
{
"epoch": 0.62,
"learning_rate": 1.3291345500418431e-05,
"loss": 0.7613,
"step": 894
},
{
"epoch": 0.62,
"learning_rate": 1.3248961637739615e-05,
"loss": 0.8438,
"step": 895
},
{
"epoch": 0.62,
"learning_rate": 1.320661196507659e-05,
"loss": 0.7495,
"step": 896
},
{
"epoch": 0.62,
"learning_rate": 1.3164296696905398e-05,
"loss": 0.758,
"step": 897
},
{
"epoch": 0.62,
"learning_rate": 1.312201604752783e-05,
"loss": 0.7928,
"step": 898
},
{
"epoch": 0.62,
"learning_rate": 1.3079770231070374e-05,
"loss": 0.7727,
"step": 899
},
{
"epoch": 0.62,
"learning_rate": 1.303755946148311e-05,
"loss": 0.819,
"step": 900
},
{
"epoch": 0.63,
"learning_rate": 1.2995383952538593e-05,
"loss": 0.7794,
"step": 901
},
{
"epoch": 0.63,
"learning_rate": 1.2953243917830852e-05,
"loss": 0.6981,
"step": 902
},
{
"epoch": 0.63,
"learning_rate": 1.2911139570774211e-05,
"loss": 0.7838,
"step": 903
},
{
"epoch": 0.63,
"learning_rate": 1.2869071124602307e-05,
"loss": 0.7864,
"step": 904
},
{
"epoch": 0.63,
"learning_rate": 1.2827038792366913e-05,
"loss": 0.8227,
"step": 905
},
{
"epoch": 0.63,
"learning_rate": 1.2785042786936943e-05,
"loss": 0.8392,
"step": 906
},
{
"epoch": 0.63,
"learning_rate": 1.2743083320997305e-05,
"loss": 0.7655,
"step": 907
},
{
"epoch": 0.63,
"learning_rate": 1.2701160607047893e-05,
"loss": 0.7921,
"step": 908
},
{
"epoch": 0.63,
"learning_rate": 1.2659274857402438e-05,
"loss": 0.7902,
"step": 909
},
{
"epoch": 0.63,
"learning_rate": 1.2617426284187497e-05,
"loss": 0.7646,
"step": 910
},
{
"epoch": 0.63,
"learning_rate": 1.2575615099341326e-05,
"loss": 0.7696,
"step": 911
},
{
"epoch": 0.63,
"learning_rate": 1.2533841514612859e-05,
"loss": 0.8269,
"step": 912
},
{
"epoch": 0.63,
"learning_rate": 1.2492105741560576e-05,
"loss": 0.7662,
"step": 913
},
{
"epoch": 0.63,
"learning_rate": 1.2450407991551492e-05,
"loss": 0.7592,
"step": 914
},
{
"epoch": 0.64,
"learning_rate": 1.2408748475760031e-05,
"loss": 0.8541,
"step": 915
},
{
"epoch": 0.64,
"learning_rate": 1.2367127405167012e-05,
"loss": 0.7765,
"step": 916
},
{
"epoch": 0.64,
"learning_rate": 1.232554499055853e-05,
"loss": 0.7909,
"step": 917
},
{
"epoch": 0.64,
"learning_rate": 1.2284001442524917e-05,
"loss": 0.795,
"step": 918
},
{
"epoch": 0.64,
"learning_rate": 1.2242496971459664e-05,
"loss": 0.7857,
"step": 919
},
{
"epoch": 0.64,
"learning_rate": 1.2201031787558377e-05,
"loss": 0.7808,
"step": 920
},
{
"epoch": 0.64,
"learning_rate": 1.2159606100817674e-05,
"loss": 0.7612,
"step": 921
},
{
"epoch": 0.64,
"learning_rate": 1.211822012103416e-05,
"loss": 0.7825,
"step": 922
},
{
"epoch": 0.64,
"learning_rate": 1.2076874057803334e-05,
"loss": 0.777,
"step": 923
},
{
"epoch": 0.64,
"learning_rate": 1.203556812051856e-05,
"loss": 0.8015,
"step": 924
},
{
"epoch": 0.64,
"learning_rate": 1.199430251836996e-05,
"loss": 0.762,
"step": 925
},
{
"epoch": 0.64,
"learning_rate": 1.1953077460343416e-05,
"loss": 0.7894,
"step": 926
},
{
"epoch": 0.64,
"learning_rate": 1.1911893155219443e-05,
"loss": 0.7636,
"step": 927
},
{
"epoch": 0.64,
"learning_rate": 1.1870749811572205e-05,
"loss": 0.7123,
"step": 928
},
{
"epoch": 0.65,
"learning_rate": 1.182964763776838e-05,
"loss": 0.8114,
"step": 929
},
{
"epoch": 0.65,
"learning_rate": 1.178858684196618e-05,
"loss": 0.7997,
"step": 930
},
{
"epoch": 0.65,
"learning_rate": 1.174756763211423e-05,
"loss": 0.7846,
"step": 931
},
{
"epoch": 0.65,
"learning_rate": 1.1706590215950579e-05,
"loss": 0.7879,
"step": 932
},
{
"epoch": 0.65,
"learning_rate": 1.1665654801001589e-05,
"loss": 0.7947,
"step": 933
},
{
"epoch": 0.65,
"learning_rate": 1.162476159458093e-05,
"loss": 0.763,
"step": 934
},
{
"epoch": 0.65,
"learning_rate": 1.1583910803788497e-05,
"loss": 0.7682,
"step": 935
},
{
"epoch": 0.65,
"learning_rate": 1.1543102635509383e-05,
"loss": 0.7942,
"step": 936
},
{
"epoch": 0.65,
"learning_rate": 1.150233729641282e-05,
"loss": 0.8287,
"step": 937
},
{
"epoch": 0.65,
"learning_rate": 1.1461614992951136e-05,
"loss": 0.8185,
"step": 938
},
{
"epoch": 0.65,
"learning_rate": 1.1420935931358713e-05,
"loss": 0.8088,
"step": 939
},
{
"epoch": 0.65,
"learning_rate": 1.1380300317650925e-05,
"loss": 0.809,
"step": 940
},
{
"epoch": 0.65,
"learning_rate": 1.1339708357623129e-05,
"loss": 0.7634,
"step": 941
},
{
"epoch": 0.65,
"learning_rate": 1.1299160256849584e-05,
"loss": 0.7734,
"step": 942
},
{
"epoch": 0.65,
"learning_rate": 1.1258656220682436e-05,
"loss": 0.7769,
"step": 943
},
{
"epoch": 0.66,
"learning_rate": 1.1218196454250667e-05,
"loss": 0.7674,
"step": 944
},
{
"epoch": 0.66,
"learning_rate": 1.1177781162459062e-05,
"loss": 0.7303,
"step": 945
},
{
"epoch": 0.66,
"learning_rate": 1.1137410549987168e-05,
"loss": 0.7964,
"step": 946
},
{
"epoch": 0.66,
"learning_rate": 1.1097084821288264e-05,
"loss": 0.7874,
"step": 947
},
{
"epoch": 0.66,
"learning_rate": 1.1056804180588285e-05,
"loss": 0.8144,
"step": 948
},
{
"epoch": 0.66,
"learning_rate": 1.1016568831884884e-05,
"loss": 0.791,
"step": 949
},
{
"epoch": 0.66,
"learning_rate": 1.0976378978946266e-05,
"loss": 0.7549,
"step": 950
},
{
"epoch": 0.66,
"learning_rate": 1.0936234825310294e-05,
"loss": 0.7632,
"step": 951
},
{
"epoch": 0.66,
"learning_rate": 1.0896136574283326e-05,
"loss": 0.7906,
"step": 952
},
{
"epoch": 0.66,
"learning_rate": 1.0856084428939325e-05,
"loss": 0.8008,
"step": 953
},
{
"epoch": 0.66,
"learning_rate": 1.0816078592118671e-05,
"loss": 0.8094,
"step": 954
},
{
"epoch": 0.66,
"learning_rate": 1.0776119266427302e-05,
"loss": 0.7468,
"step": 955
},
{
"epoch": 0.66,
"learning_rate": 1.0736206654235537e-05,
"loss": 0.7629,
"step": 956
},
{
"epoch": 0.66,
"learning_rate": 1.0696340957677159e-05,
"loss": 0.7739,
"step": 957
},
{
"epoch": 0.67,
"learning_rate": 1.0656522378648333e-05,
"loss": 0.7884,
"step": 958
},
{
"epoch": 0.67,
"learning_rate": 1.0616751118806614e-05,
"loss": 0.7808,
"step": 959
},
{
"epoch": 0.67,
"learning_rate": 1.0577027379569902e-05,
"loss": 0.763,
"step": 960
},
{
"epoch": 0.67,
"learning_rate": 1.053735136211544e-05,
"loss": 0.8075,
"step": 961
},
{
"epoch": 0.67,
"learning_rate": 1.0497723267378783e-05,
"loss": 0.7836,
"step": 962
},
{
"epoch": 0.67,
"learning_rate": 1.0458143296052796e-05,
"loss": 0.8088,
"step": 963
},
{
"epoch": 0.67,
"learning_rate": 1.0418611648586615e-05,
"loss": 0.7689,
"step": 964
},
{
"epoch": 0.67,
"learning_rate": 1.0379128525184653e-05,
"loss": 0.8099,
"step": 965
},
{
"epoch": 0.67,
"learning_rate": 1.0339694125805569e-05,
"loss": 0.7245,
"step": 966
},
{
"epoch": 0.67,
"learning_rate": 1.0300308650161273e-05,
"loss": 0.7537,
"step": 967
},
{
"epoch": 0.67,
"learning_rate": 1.0260972297715903e-05,
"loss": 0.7615,
"step": 968
},
{
"epoch": 0.67,
"learning_rate": 1.0221685267684812e-05,
"loss": 0.7464,
"step": 969
},
{
"epoch": 0.67,
"learning_rate": 1.0182447759033569e-05,
"loss": 0.7864,
"step": 970
},
{
"epoch": 0.67,
"learning_rate": 1.0143259970476948e-05,
"loss": 0.7871,
"step": 971
},
{
"epoch": 0.68,
"learning_rate": 1.01041221004779e-05,
"loss": 0.8078,
"step": 972
},
{
"epoch": 0.68,
"learning_rate": 1.0065034347246612e-05,
"loss": 0.8155,
"step": 973
},
{
"epoch": 0.68,
"learning_rate": 1.0025996908739402e-05,
"loss": 0.7864,
"step": 974
},
{
"epoch": 0.68,
"learning_rate": 9.987009982657827e-06,
"loss": 0.7814,
"step": 975
},
{
"epoch": 0.68,
"learning_rate": 9.948073766447596e-06,
"loss": 0.7666,
"step": 976
},
{
"epoch": 0.68,
"learning_rate": 9.909188457297613e-06,
"loss": 0.7531,
"step": 977
},
{
"epoch": 0.68,
"learning_rate": 9.87035425213897e-06,
"loss": 0.7418,
"step": 978
},
{
"epoch": 0.68,
"learning_rate": 9.83157134764394e-06,
"loss": 0.7451,
"step": 979
},
{
"epoch": 0.68,
"learning_rate": 9.792839940224998e-06,
"loss": 0.774,
"step": 980
},
{
"epoch": 0.68,
"learning_rate": 9.754160226033796e-06,
"loss": 0.7596,
"step": 981
},
{
"epoch": 0.68,
"learning_rate": 9.71553240096023e-06,
"loss": 0.7897,
"step": 982
},
{
"epoch": 0.68,
"learning_rate": 9.676956660631354e-06,
"loss": 0.7478,
"step": 983
},
{
"epoch": 0.68,
"learning_rate": 9.638433200410509e-06,
"loss": 0.8086,
"step": 984
},
{
"epoch": 0.68,
"learning_rate": 9.599962215396195e-06,
"loss": 0.7688,
"step": 985
},
{
"epoch": 0.68,
"learning_rate": 9.561543900421231e-06,
"loss": 0.8001,
"step": 986
},
{
"epoch": 0.69,
"learning_rate": 9.523178450051623e-06,
"loss": 0.7879,
"step": 987
},
{
"epoch": 0.69,
"learning_rate": 9.484866058585711e-06,
"loss": 0.7919,
"step": 988
},
{
"epoch": 0.69,
"learning_rate": 9.446606920053076e-06,
"loss": 0.7978,
"step": 989
},
{
"epoch": 0.69,
"learning_rate": 9.408401228213626e-06,
"loss": 0.7544,
"step": 990
},
{
"epoch": 0.69,
"learning_rate": 9.370249176556594e-06,
"loss": 0.7778,
"step": 991
},
{
"epoch": 0.69,
"learning_rate": 9.332150958299551e-06,
"loss": 0.7629,
"step": 992
},
{
"epoch": 0.69,
"learning_rate": 9.294106766387434e-06,
"loss": 0.8152,
"step": 993
},
{
"epoch": 0.69,
"learning_rate": 9.256116793491574e-06,
"loss": 0.8245,
"step": 994
},
{
"epoch": 0.69,
"learning_rate": 9.21818123200871e-06,
"loss": 0.8205,
"step": 995
},
{
"epoch": 0.69,
"learning_rate": 9.180300274060018e-06,
"loss": 0.8006,
"step": 996
},
{
"epoch": 0.69,
"learning_rate": 9.142474111490147e-06,
"loss": 0.7923,
"step": 997
},
{
"epoch": 0.69,
"learning_rate": 9.10470293586623e-06,
"loss": 0.7735,
"step": 998
},
{
"epoch": 0.69,
"learning_rate": 9.06698693847693e-06,
"loss": 0.7726,
"step": 999
},
{
"epoch": 0.69,
"learning_rate": 9.029326310331462e-06,
"loss": 0.7929,
"step": 1000
},
{
"epoch": 0.7,
"learning_rate": 8.99172124215863e-06,
"loss": 0.782,
"step": 1001
},
{
"epoch": 0.7,
"learning_rate": 8.954171924405862e-06,
"loss": 0.7682,
"step": 1002
},
{
"epoch": 0.7,
"learning_rate": 8.916678547238238e-06,
"loss": 0.7994,
"step": 1003
},
{
"epoch": 0.7,
"learning_rate": 8.879241300537542e-06,
"loss": 0.794,
"step": 1004
},
{
"epoch": 0.7,
"learning_rate": 8.841860373901263e-06,
"loss": 0.7927,
"step": 1005
},
{
"epoch": 0.7,
"learning_rate": 8.804535956641708e-06,
"loss": 0.7599,
"step": 1006
},
{
"epoch": 0.7,
"learning_rate": 8.767268237784944e-06,
"loss": 0.7992,
"step": 1007
},
{
"epoch": 0.7,
"learning_rate": 8.730057406069952e-06,
"loss": 0.757,
"step": 1008
},
{
"epoch": 0.7,
"learning_rate": 8.692903649947553e-06,
"loss": 0.7561,
"step": 1009
},
{
"epoch": 0.7,
"learning_rate": 8.65580715757957e-06,
"loss": 0.8289,
"step": 1010
},
{
"epoch": 0.7,
"learning_rate": 8.618768116837768e-06,
"loss": 0.7548,
"step": 1011
},
{
"epoch": 0.7,
"learning_rate": 8.581786715303005e-06,
"loss": 0.7754,
"step": 1012
},
{
"epoch": 0.7,
"learning_rate": 8.544863140264184e-06,
"loss": 0.8103,
"step": 1013
},
{
"epoch": 0.7,
"learning_rate": 8.507997578717366e-06,
"loss": 0.7558,
"step": 1014
},
{
"epoch": 0.7,
"learning_rate": 8.47119021736484e-06,
"loss": 0.7868,
"step": 1015
},
{
"epoch": 0.71,
"learning_rate": 8.434441242614086e-06,
"loss": 0.7858,
"step": 1016
},
{
"epoch": 0.71,
"learning_rate": 8.397750840576955e-06,
"loss": 0.8038,
"step": 1017
},
{
"epoch": 0.71,
"learning_rate": 8.361119197068594e-06,
"loss": 0.7306,
"step": 1018
},
{
"epoch": 0.71,
"learning_rate": 8.324546497606644e-06,
"loss": 0.7937,
"step": 1019
},
{
"epoch": 0.71,
"learning_rate": 8.288032927410162e-06,
"loss": 0.7598,
"step": 1020
},
{
"epoch": 0.71,
"learning_rate": 8.251578671398808e-06,
"loss": 0.7605,
"step": 1021
},
{
"epoch": 0.71,
"learning_rate": 8.215183914191807e-06,
"loss": 0.7532,
"step": 1022
},
{
"epoch": 0.71,
"learning_rate": 8.17884884010708e-06,
"loss": 0.7985,
"step": 1023
},
{
"epoch": 0.71,
"learning_rate": 8.142573633160284e-06,
"loss": 0.7851,
"step": 1024
},
{
"epoch": 0.71,
"learning_rate": 8.106358477063887e-06,
"loss": 0.7754,
"step": 1025
},
{
"epoch": 0.71,
"learning_rate": 8.070203555226225e-06,
"loss": 0.7745,
"step": 1026
},
{
"epoch": 0.71,
"learning_rate": 8.034109050750599e-06,
"loss": 0.7723,
"step": 1027
},
{
"epoch": 0.71,
"learning_rate": 7.998075146434314e-06,
"loss": 0.7337,
"step": 1028
},
{
"epoch": 0.71,
"learning_rate": 7.962102024767786e-06,
"loss": 0.793,
"step": 1029
},
{
"epoch": 0.72,
"learning_rate": 7.926189867933594e-06,
"loss": 0.7627,
"step": 1030
},
{
"epoch": 0.72,
"learning_rate": 7.890338857805568e-06,
"loss": 0.7815,
"step": 1031
},
{
"epoch": 0.72,
"learning_rate": 7.85454917594787e-06,
"loss": 0.7777,
"step": 1032
},
{
"epoch": 0.72,
"learning_rate": 7.818821003614065e-06,
"loss": 0.7555,
"step": 1033
},
{
"epoch": 0.72,
"learning_rate": 7.783154521746213e-06,
"loss": 0.8484,
"step": 1034
},
{
"epoch": 0.72,
"learning_rate": 7.747549910973946e-06,
"loss": 0.7242,
"step": 1035
},
{
"epoch": 0.72,
"learning_rate": 7.712007351613554e-06,
"loss": 0.7838,
"step": 1036
},
{
"epoch": 0.72,
"learning_rate": 7.676527023667084e-06,
"loss": 0.7679,
"step": 1037
},
{
"epoch": 0.72,
"learning_rate": 7.641109106821387e-06,
"loss": 0.7788,
"step": 1038
},
{
"epoch": 0.72,
"learning_rate": 7.6057537804472916e-06,
"loss": 0.7958,
"step": 1039
},
{
"epoch": 0.72,
"learning_rate": 7.57046122359858e-06,
"loss": 0.8117,
"step": 1040
},
{
"epoch": 0.72,
"learning_rate": 7.535231615011205e-06,
"loss": 0.7883,
"step": 1041
},
{
"epoch": 0.72,
"learning_rate": 7.500065133102267e-06,
"loss": 0.7954,
"step": 1042
},
{
"epoch": 0.72,
"learning_rate": 7.464961955969223e-06,
"loss": 0.7861,
"step": 1043
},
{
"epoch": 0.72,
"learning_rate": 7.429922261388871e-06,
"loss": 0.7537,
"step": 1044
},
{
"epoch": 0.73,
"learning_rate": 7.394946226816564e-06,
"loss": 0.8053,
"step": 1045
},
{
"epoch": 0.73,
"learning_rate": 7.360034029385208e-06,
"loss": 0.8173,
"step": 1046
},
{
"epoch": 0.73,
"learning_rate": 7.325185845904436e-06,
"loss": 0.8343,
"step": 1047
},
{
"epoch": 0.73,
"learning_rate": 7.290401852859688e-06,
"loss": 0.773,
"step": 1048
},
{
"epoch": 0.73,
"learning_rate": 7.255682226411304e-06,
"loss": 0.8063,
"step": 1049
},
{
"epoch": 0.73,
"learning_rate": 7.221027142393664e-06,
"loss": 0.7649,
"step": 1050
},
{
"epoch": 0.73,
"learning_rate": 7.186436776314261e-06,
"loss": 0.8313,
"step": 1051
},
{
"epoch": 0.73,
"learning_rate": 7.151911303352841e-06,
"loss": 0.7479,
"step": 1052
},
{
"epoch": 0.73,
"learning_rate": 7.117450898360494e-06,
"loss": 0.7734,
"step": 1053
},
{
"epoch": 0.73,
"learning_rate": 7.083055735858806e-06,
"loss": 0.8207,
"step": 1054
},
{
"epoch": 0.73,
"learning_rate": 7.04872599003891e-06,
"loss": 0.7609,
"step": 1055
},
{
"epoch": 0.73,
"learning_rate": 7.014461834760664e-06,
"loss": 0.8108,
"step": 1056
},
{
"epoch": 0.73,
"learning_rate": 6.980263443551753e-06,
"loss": 0.7583,
"step": 1057
},
{
"epoch": 0.73,
"learning_rate": 6.9461309896067915e-06,
"loss": 0.7807,
"step": 1058
},
{
"epoch": 0.74,
"learning_rate": 6.912064645786474e-06,
"loss": 0.7417,
"step": 1059
},
{
"epoch": 0.74,
"learning_rate": 6.878064584616677e-06,
"loss": 0.8283,
"step": 1060
},
{
"epoch": 0.74,
"learning_rate": 6.844130978287598e-06,
"loss": 0.7096,
"step": 1061
},
{
"epoch": 0.74,
"learning_rate": 6.810263998652879e-06,
"loss": 0.8489,
"step": 1062
},
{
"epoch": 0.74,
"learning_rate": 6.776463817228742e-06,
"loss": 0.7785,
"step": 1063
},
{
"epoch": 0.74,
"learning_rate": 6.742730605193109e-06,
"loss": 0.7914,
"step": 1064
},
{
"epoch": 0.74,
"learning_rate": 6.709064533384743e-06,
"loss": 0.7792,
"step": 1065
},
{
"epoch": 0.74,
"learning_rate": 6.6754657723023855e-06,
"loss": 0.7666,
"step": 1066
},
{
"epoch": 0.74,
"learning_rate": 6.641934492103885e-06,
"loss": 0.806,
"step": 1067
},
{
"epoch": 0.74,
"learning_rate": 6.6084708626053405e-06,
"loss": 0.7701,
"step": 1068
},
{
"epoch": 0.74,
"learning_rate": 6.575075053280242e-06,
"loss": 0.7447,
"step": 1069
},
{
"epoch": 0.74,
"learning_rate": 6.541747233258613e-06,
"loss": 0.7677,
"step": 1070
},
{
"epoch": 0.74,
"learning_rate": 6.50848757132613e-06,
"loss": 0.8028,
"step": 1071
},
{
"epoch": 0.74,
"learning_rate": 6.47529623592333e-06,
"loss": 0.7969,
"step": 1072
},
{
"epoch": 0.75,
"learning_rate": 6.4421733951446665e-06,
"loss": 0.7647,
"step": 1073
},
{
"epoch": 0.75,
"learning_rate": 6.409119216737763e-06,
"loss": 0.7917,
"step": 1074
},
{
"epoch": 0.75,
"learning_rate": 6.376133868102452e-06,
"loss": 0.7785,
"step": 1075
},
{
"epoch": 0.75,
"learning_rate": 6.343217516290039e-06,
"loss": 0.7938,
"step": 1076
},
{
"epoch": 0.75,
"learning_rate": 6.310370328002351e-06,
"loss": 0.7862,
"step": 1077
},
{
"epoch": 0.75,
"learning_rate": 6.277592469590987e-06,
"loss": 0.7743,
"step": 1078
},
{
"epoch": 0.75,
"learning_rate": 6.244884107056395e-06,
"loss": 0.7592,
"step": 1079
},
{
"epoch": 0.75,
"learning_rate": 6.2122454060470884e-06,
"loss": 0.7975,
"step": 1080
},
{
"epoch": 0.75,
"learning_rate": 6.1796765318587804e-06,
"loss": 0.7565,
"step": 1081
},
{
"epoch": 0.75,
"learning_rate": 6.147177649433554e-06,
"loss": 0.7834,
"step": 1082
},
{
"epoch": 0.75,
"learning_rate": 6.11474892335902e-06,
"loss": 0.8119,
"step": 1083
},
{
"epoch": 0.75,
"learning_rate": 6.082390517867498e-06,
"loss": 0.8007,
"step": 1084
},
{
"epoch": 0.75,
"learning_rate": 6.05010259683517e-06,
"loss": 0.7437,
"step": 1085
},
{
"epoch": 0.75,
"learning_rate": 6.017885323781254e-06,
"loss": 0.7879,
"step": 1086
},
{
"epoch": 0.75,
"learning_rate": 5.985738861867183e-06,
"loss": 0.7449,
"step": 1087
},
{
"epoch": 0.76,
"learning_rate": 5.953663373895768e-06,
"loss": 0.8034,
"step": 1088
},
{
"epoch": 0.76,
"learning_rate": 5.921659022310382e-06,
"loss": 0.8002,
"step": 1089
},
{
"epoch": 0.76,
"learning_rate": 5.889725969194136e-06,
"loss": 0.7183,
"step": 1090
},
{
"epoch": 0.76,
"learning_rate": 5.857864376269051e-06,
"loss": 0.7852,
"step": 1091
},
{
"epoch": 0.76,
"learning_rate": 5.82607440489525e-06,
"loss": 0.8002,
"step": 1092
},
{
"epoch": 0.76,
"learning_rate": 5.794356216070134e-06,
"loss": 0.7577,
"step": 1093
},
{
"epoch": 0.76,
"learning_rate": 5.762709970427565e-06,
"loss": 0.8143,
"step": 1094
},
{
"epoch": 0.76,
"learning_rate": 5.7311358282370574e-06,
"loss": 0.805,
"step": 1095
},
{
"epoch": 0.76,
"learning_rate": 5.699633949402965e-06,
"loss": 0.7356,
"step": 1096
},
{
"epoch": 0.76,
"learning_rate": 5.668204493463667e-06,
"loss": 0.79,
"step": 1097
},
{
"epoch": 0.76,
"learning_rate": 5.636847619590768e-06,
"loss": 0.7449,
"step": 1098
},
{
"epoch": 0.76,
"learning_rate": 5.605563486588286e-06,
"loss": 0.8123,
"step": 1099
},
{
"epoch": 0.76,
"learning_rate": 5.574352252891846e-06,
"loss": 0.7784,
"step": 1100
},
{
"epoch": 0.76,
"learning_rate": 5.543214076567884e-06,
"loss": 0.7796,
"step": 1101
},
{
"epoch": 0.77,
"learning_rate": 5.512149115312848e-06,
"loss": 0.7578,
"step": 1102
},
{
"epoch": 0.77,
"learning_rate": 5.481157526452387e-06,
"loss": 0.7897,
"step": 1103
},
{
"epoch": 0.77,
"learning_rate": 5.450239466940568e-06,
"loss": 0.8222,
"step": 1104
},
{
"epoch": 0.77,
"learning_rate": 5.419395093359074e-06,
"loss": 0.7731,
"step": 1105
},
{
"epoch": 0.77,
"learning_rate": 5.3886245619164e-06,
"loss": 0.8105,
"step": 1106
},
{
"epoch": 0.77,
"learning_rate": 5.357928028447106e-06,
"loss": 0.7853,
"step": 1107
},
{
"epoch": 0.77,
"learning_rate": 5.327305648410952e-06,
"loss": 0.827,
"step": 1108
},
{
"epoch": 0.77,
"learning_rate": 5.2967575768922045e-06,
"loss": 0.7749,
"step": 1109
},
{
"epoch": 0.77,
"learning_rate": 5.266283968598749e-06,
"loss": 0.7981,
"step": 1110
},
{
"epoch": 0.77,
"learning_rate": 5.23588497786141e-06,
"loss": 0.8192,
"step": 1111
},
{
"epoch": 0.77,
"learning_rate": 5.205560758633071e-06,
"loss": 0.8082,
"step": 1112
},
{
"epoch": 0.77,
"learning_rate": 5.1753114644879845e-06,
"loss": 0.784,
"step": 1113
},
{
"epoch": 0.77,
"learning_rate": 5.145137248620917e-06,
"loss": 0.8031,
"step": 1114
},
{
"epoch": 0.77,
"learning_rate": 5.115038263846425e-06,
"loss": 0.7641,
"step": 1115
},
{
"epoch": 0.78,
"learning_rate": 5.085014662598067e-06,
"loss": 0.7811,
"step": 1116
},
{
"epoch": 0.78,
"learning_rate": 5.05506659692762e-06,
"loss": 0.7498,
"step": 1117
},
{
"epoch": 0.78,
"learning_rate": 5.0251942185043215e-06,
"loss": 0.7795,
"step": 1118
},
{
"epoch": 0.78,
"learning_rate": 4.995397678614095e-06,
"loss": 0.793,
"step": 1119
},
{
"epoch": 0.78,
"learning_rate": 4.965677128158795e-06,
"loss": 0.7539,
"step": 1120
},
{
"epoch": 0.78,
"learning_rate": 4.936032717655424e-06,
"loss": 0.7487,
"step": 1121
},
{
"epoch": 0.78,
"learning_rate": 4.906464597235385e-06,
"loss": 0.7732,
"step": 1122
},
{
"epoch": 0.78,
"learning_rate": 4.8769729166437184e-06,
"loss": 0.7976,
"step": 1123
},
{
"epoch": 0.78,
"learning_rate": 4.847557825238343e-06,
"loss": 0.7732,
"step": 1124
},
{
"epoch": 0.78,
"learning_rate": 4.818219471989294e-06,
"loss": 0.7266,
"step": 1125
},
{
"epoch": 0.78,
"learning_rate": 4.7889580054779776e-06,
"loss": 0.6976,
"step": 1126
},
{
"epoch": 0.78,
"learning_rate": 4.759773573896409e-06,
"loss": 0.7099,
"step": 1127
},
{
"epoch": 0.78,
"learning_rate": 4.730666325046473e-06,
"loss": 0.7493,
"step": 1128
},
{
"epoch": 0.78,
"learning_rate": 4.701636406339172e-06,
"loss": 0.7564,
"step": 1129
},
{
"epoch": 0.78,
"learning_rate": 4.672683964793856e-06,
"loss": 0.7633,
"step": 1130
},
{
"epoch": 0.79,
"learning_rate": 4.64380914703753e-06,
"loss": 0.7857,
"step": 1131
},
{
"epoch": 0.79,
"learning_rate": 4.615012099304062e-06,
"loss": 0.7481,
"step": 1132
},
{
"epoch": 0.79,
"learning_rate": 4.586292967433461e-06,
"loss": 0.791,
"step": 1133
},
{
"epoch": 0.79,
"learning_rate": 4.5576518968711425e-06,
"loss": 0.7702,
"step": 1134
},
{
"epoch": 0.79,
"learning_rate": 4.529089032667189e-06,
"loss": 0.785,
"step": 1135
},
{
"epoch": 0.79,
"learning_rate": 4.500604519475606e-06,
"loss": 0.7844,
"step": 1136
},
{
"epoch": 0.79,
"learning_rate": 4.472198501553611e-06,
"loss": 0.7193,
"step": 1137
},
{
"epoch": 0.79,
"learning_rate": 4.443871122760881e-06,
"loss": 0.773,
"step": 1138
},
{
"epoch": 0.79,
"learning_rate": 4.4156225265588184e-06,
"loss": 0.729,
"step": 1139
},
{
"epoch": 0.79,
"learning_rate": 4.387452856009873e-06,
"loss": 0.7696,
"step": 1140
},
{
"epoch": 0.79,
"learning_rate": 4.359362253776742e-06,
"loss": 0.7479,
"step": 1141
},
{
"epoch": 0.79,
"learning_rate": 4.331350862121733e-06,
"loss": 0.7337,
"step": 1142
},
{
"epoch": 0.79,
"learning_rate": 4.303418822905949e-06,
"loss": 0.8416,
"step": 1143
},
{
"epoch": 0.79,
"learning_rate": 4.27556627758867e-06,
"loss": 0.7895,
"step": 1144
},
{
"epoch": 0.8,
"learning_rate": 4.2477933672265385e-06,
"loss": 0.8002,
"step": 1145
},
{
"epoch": 0.8,
"learning_rate": 4.220100232472941e-06,
"loss": 0.7552,
"step": 1146
},
{
"epoch": 0.8,
"learning_rate": 4.192487013577204e-06,
"loss": 0.7286,
"step": 1147
},
{
"epoch": 0.8,
"learning_rate": 4.164953850383955e-06,
"loss": 0.7237,
"step": 1148
},
{
"epoch": 0.8,
"learning_rate": 4.137500882332379e-06,
"loss": 0.7969,
"step": 1149
},
{
"epoch": 0.8,
"learning_rate": 4.110128248455516e-06,
"loss": 0.7603,
"step": 1150
},
{
"epoch": 0.8,
"learning_rate": 4.082836087379569e-06,
"loss": 0.747,
"step": 1151
},
{
"epoch": 0.8,
"learning_rate": 4.055624537323184e-06,
"loss": 0.7578,
"step": 1152
},
{
"epoch": 0.8,
"learning_rate": 4.02849373609677e-06,
"loss": 0.8148,
"step": 1153
},
{
"epoch": 0.8,
"learning_rate": 4.001443821101787e-06,
"loss": 0.7434,
"step": 1154
},
{
"epoch": 0.8,
"learning_rate": 3.974474929330048e-06,
"loss": 0.7454,
"step": 1155
},
{
"epoch": 0.8,
"learning_rate": 3.947587197363041e-06,
"loss": 0.7858,
"step": 1156
},
{
"epoch": 0.8,
"learning_rate": 3.920780761371221e-06,
"loss": 0.7812,
"step": 1157
},
{
"epoch": 0.8,
"learning_rate": 3.8940557571133305e-06,
"loss": 0.7849,
"step": 1158
},
{
"epoch": 0.8,
"learning_rate": 3.867412319935708e-06,
"loss": 0.7772,
"step": 1159
},
{
"epoch": 0.81,
"learning_rate": 3.840850584771601e-06,
"loss": 0.7856,
"step": 1160
},
{
"epoch": 0.81,
"learning_rate": 3.814370686140483e-06,
"loss": 0.7886,
"step": 1161
},
{
"epoch": 0.81,
"learning_rate": 3.7879727581473846e-06,
"loss": 0.7794,
"step": 1162
},
{
"epoch": 0.81,
"learning_rate": 3.761656934482181e-06,
"loss": 0.8123,
"step": 1163
},
{
"epoch": 0.81,
"learning_rate": 3.7354233484189716e-06,
"loss": 0.8103,
"step": 1164
},
{
"epoch": 0.81,
"learning_rate": 3.7092721328153314e-06,
"loss": 0.7291,
"step": 1165
},
{
"epoch": 0.81,
"learning_rate": 3.6832034201117184e-06,
"loss": 0.7654,
"step": 1166
},
{
"epoch": 0.81,
"learning_rate": 3.657217342330721e-06,
"loss": 0.712,
"step": 1167
},
{
"epoch": 0.81,
"learning_rate": 3.6313140310764714e-06,
"loss": 0.7329,
"step": 1168
},
{
"epoch": 0.81,
"learning_rate": 3.6054936175338972e-06,
"loss": 0.8089,
"step": 1169
},
{
"epoch": 0.81,
"learning_rate": 3.5797562324681365e-06,
"loss": 0.7439,
"step": 1170
},
{
"epoch": 0.81,
"learning_rate": 3.5541020062238207e-06,
"loss": 0.7588,
"step": 1171
},
{
"epoch": 0.81,
"learning_rate": 3.52853106872441e-06,
"loss": 0.7867,
"step": 1172
},
{
"epoch": 0.81,
"learning_rate": 3.503043549471603e-06,
"loss": 0.741,
"step": 1173
},
{
"epoch": 0.82,
"learning_rate": 3.4776395775445827e-06,
"loss": 0.8362,
"step": 1174
},
{
"epoch": 0.82,
"learning_rate": 3.4523192815994612e-06,
"loss": 0.7991,
"step": 1175
},
{
"epoch": 0.82,
"learning_rate": 3.427082789868541e-06,
"loss": 0.7958,
"step": 1176
},
{
"epoch": 0.82,
"learning_rate": 3.4019302301597425e-06,
"loss": 0.7306,
"step": 1177
},
{
"epoch": 0.82,
"learning_rate": 3.3768617298558825e-06,
"loss": 0.7471,
"step": 1178
},
{
"epoch": 0.82,
"learning_rate": 3.3518774159141065e-06,
"loss": 0.7806,
"step": 1179
},
{
"epoch": 0.82,
"learning_rate": 3.326977414865169e-06,
"loss": 0.7311,
"step": 1180
},
{
"epoch": 0.82,
"learning_rate": 3.3021618528128505e-06,
"loss": 0.7693,
"step": 1181
},
{
"epoch": 0.82,
"learning_rate": 3.2774308554332967e-06,
"loss": 0.7391,
"step": 1182
},
{
"epoch": 0.82,
"learning_rate": 3.252784547974377e-06,
"loss": 0.785,
"step": 1183
},
{
"epoch": 0.82,
"learning_rate": 3.2282230552550596e-06,
"loss": 0.8035,
"step": 1184
},
{
"epoch": 0.82,
"learning_rate": 3.2037465016647772e-06,
"loss": 0.8031,
"step": 1185
},
{
"epoch": 0.82,
"learning_rate": 3.1793550111627946e-06,
"loss": 0.7579,
"step": 1186
},
{
"epoch": 0.82,
"learning_rate": 3.1550487072775816e-06,
"loss": 0.7638,
"step": 1187
},
{
"epoch": 0.82,
"learning_rate": 3.13082771310619e-06,
"loss": 0.7906,
"step": 1188
},
{
"epoch": 0.83,
"learning_rate": 3.106692151313626e-06,
"loss": 0.7518,
"step": 1189
},
{
"epoch": 0.83,
"learning_rate": 3.0826421441322374e-06,
"loss": 0.7858,
"step": 1190
},
{
"epoch": 0.83,
"learning_rate": 3.0586778133610795e-06,
"loss": 0.731,
"step": 1191
},
{
"epoch": 0.83,
"learning_rate": 3.0347992803653127e-06,
"loss": 0.7767,
"step": 1192
},
{
"epoch": 0.83,
"learning_rate": 3.0110066660755823e-06,
"loss": 0.7294,
"step": 1193
},
{
"epoch": 0.83,
"learning_rate": 2.987300090987406e-06,
"loss": 0.7666,
"step": 1194
},
{
"epoch": 0.83,
"learning_rate": 2.9636796751605667e-06,
"loss": 0.7564,
"step": 1195
},
{
"epoch": 0.83,
"learning_rate": 2.940145538218484e-06,
"loss": 0.7985,
"step": 1196
},
{
"epoch": 0.83,
"learning_rate": 2.9166977993476584e-06,
"loss": 0.7576,
"step": 1197
},
{
"epoch": 0.83,
"learning_rate": 2.8933365772970014e-06,
"loss": 0.7249,
"step": 1198
},
{
"epoch": 0.83,
"learning_rate": 2.8700619903772975e-06,
"loss": 0.7719,
"step": 1199
},
{
"epoch": 0.83,
"learning_rate": 2.8468741564605484e-06,
"loss": 0.7855,
"step": 1200
},
{
"epoch": 0.83,
"learning_rate": 2.8237731929794286e-06,
"loss": 0.786,
"step": 1201
},
{
"epoch": 0.83,
"learning_rate": 2.8007592169266407e-06,
"loss": 0.8147,
"step": 1202
},
{
"epoch": 0.84,
"learning_rate": 2.777832344854374e-06,
"loss": 0.7504,
"step": 1203
},
{
"epoch": 0.84,
"learning_rate": 2.754992692873659e-06,
"loss": 0.743,
"step": 1204
},
{
"epoch": 0.84,
"learning_rate": 2.7322403766538317e-06,
"loss": 0.7547,
"step": 1205
},
{
"epoch": 0.84,
"learning_rate": 2.7095755114219093e-06,
"loss": 0.7871,
"step": 1206
},
{
"epoch": 0.84,
"learning_rate": 2.6869982119620306e-06,
"loss": 0.779,
"step": 1207
},
{
"epoch": 0.84,
"learning_rate": 2.664508592614863e-06,
"loss": 0.8054,
"step": 1208
},
{
"epoch": 0.84,
"learning_rate": 2.6421067672770172e-06,
"loss": 0.7631,
"step": 1209
},
{
"epoch": 0.84,
"learning_rate": 2.6197928494004997e-06,
"loss": 0.7559,
"step": 1210
},
{
"epoch": 0.84,
"learning_rate": 2.597566951992092e-06,
"loss": 0.7742,
"step": 1211
},
{
"epoch": 0.84,
"learning_rate": 2.57542918761283e-06,
"loss": 0.7585,
"step": 1212
},
{
"epoch": 0.84,
"learning_rate": 2.5533796683773827e-06,
"loss": 0.7966,
"step": 1213
},
{
"epoch": 0.84,
"learning_rate": 2.531418505953529e-06,
"loss": 0.7987,
"step": 1214
},
{
"epoch": 0.84,
"learning_rate": 2.5095458115615622e-06,
"loss": 0.7576,
"step": 1215
},
{
"epoch": 0.84,
"learning_rate": 2.487761695973743e-06,
"loss": 0.8164,
"step": 1216
},
{
"epoch": 0.85,
"learning_rate": 2.466066269513727e-06,
"loss": 0.7751,
"step": 1217
},
{
"epoch": 0.85,
"learning_rate": 2.4444596420560206e-06,
"loss": 0.7673,
"step": 1218
},
{
"epoch": 0.85,
"learning_rate": 2.4229419230254104e-06,
"loss": 0.7913,
"step": 1219
},
{
"epoch": 0.85,
"learning_rate": 2.40151322139641e-06,
"loss": 0.8152,
"step": 1220
},
{
"epoch": 0.85,
"learning_rate": 2.3801736456927206e-06,
"loss": 0.7643,
"step": 1221
},
{
"epoch": 0.85,
"learning_rate": 2.3589233039866688e-06,
"loss": 0.7461,
"step": 1222
},
{
"epoch": 0.85,
"learning_rate": 2.337762303898665e-06,
"loss": 0.7957,
"step": 1223
},
{
"epoch": 0.85,
"learning_rate": 2.3166907525966577e-06,
"loss": 0.7635,
"step": 1224
},
{
"epoch": 0.85,
"learning_rate": 2.2957087567955896e-06,
"loss": 0.7998,
"step": 1225
},
{
"epoch": 0.85,
"learning_rate": 2.274816422756858e-06,
"loss": 0.7912,
"step": 1226
},
{
"epoch": 0.85,
"learning_rate": 2.2540138562877733e-06,
"loss": 0.7563,
"step": 1227
},
{
"epoch": 0.85,
"learning_rate": 2.2333011627410374e-06,
"loss": 0.7496,
"step": 1228
},
{
"epoch": 0.85,
"learning_rate": 2.212678447014176e-06,
"loss": 0.8048,
"step": 1229
},
{
"epoch": 0.85,
"learning_rate": 2.19214581354906e-06,
"loss": 0.7752,
"step": 1230
},
{
"epoch": 0.85,
"learning_rate": 2.171703366331319e-06,
"loss": 0.7662,
"step": 1231
},
{
"epoch": 0.86,
"learning_rate": 2.1513512088898715e-06,
"loss": 0.8155,
"step": 1232
},
{
"epoch": 0.86,
"learning_rate": 2.131089444296337e-06,
"loss": 0.8172,
"step": 1233
},
{
"epoch": 0.86,
"learning_rate": 2.110918175164585e-06,
"loss": 0.7429,
"step": 1234
},
{
"epoch": 0.86,
"learning_rate": 2.090837503650147e-06,
"loss": 0.7755,
"step": 1235
},
{
"epoch": 0.86,
"learning_rate": 2.070847531449758e-06,
"loss": 0.7616,
"step": 1236
},
{
"epoch": 0.86,
"learning_rate": 2.050948359800795e-06,
"loss": 0.75,
"step": 1237
},
{
"epoch": 0.86,
"learning_rate": 2.031140089480792e-06,
"loss": 0.7984,
"step": 1238
},
{
"epoch": 0.86,
"learning_rate": 2.011422820806921e-06,
"loss": 0.7814,
"step": 1239
},
{
"epoch": 0.86,
"learning_rate": 1.991796653635485e-06,
"loss": 0.7494,
"step": 1240
},
{
"epoch": 0.86,
"learning_rate": 1.972261687361412e-06,
"loss": 0.7862,
"step": 1241
},
{
"epoch": 0.86,
"learning_rate": 1.9528180209177482e-06,
"loss": 0.8141,
"step": 1242
},
{
"epoch": 0.86,
"learning_rate": 1.933465752775163e-06,
"loss": 0.7867,
"step": 1243
},
{
"epoch": 0.86,
"learning_rate": 1.9142049809414476e-06,
"loss": 0.7609,
"step": 1244
},
{
"epoch": 0.86,
"learning_rate": 1.8950358029610183e-06,
"loss": 0.7096,
"step": 1245
},
{
"epoch": 0.87,
"learning_rate": 1.8759583159144235e-06,
"loss": 0.77,
"step": 1246
},
{
"epoch": 0.87,
"learning_rate": 1.8569726164178447e-06,
"loss": 0.7317,
"step": 1247
},
{
"epoch": 0.87,
"learning_rate": 1.8380788006226247e-06,
"loss": 0.7808,
"step": 1248
},
{
"epoch": 0.87,
"learning_rate": 1.81927696421476e-06,
"loss": 0.7177,
"step": 1249
},
{
"epoch": 0.87,
"learning_rate": 1.8005672024144337e-06,
"loss": 0.8107,
"step": 1250
},
{
"epoch": 0.87,
"learning_rate": 1.7819496099755174e-06,
"loss": 0.8117,
"step": 1251
},
{
"epoch": 0.87,
"learning_rate": 1.7634242811851087e-06,
"loss": 0.7021,
"step": 1252
},
{
"epoch": 0.87,
"learning_rate": 1.7449913098630355e-06,
"loss": 0.7882,
"step": 1253
},
{
"epoch": 0.87,
"learning_rate": 1.7266507893613949e-06,
"loss": 0.7588,
"step": 1254
},
{
"epoch": 0.87,
"learning_rate": 1.7084028125640738e-06,
"loss": 0.746,
"step": 1255
},
{
"epoch": 0.87,
"learning_rate": 1.6902474718862794e-06,
"loss": 0.7609,
"step": 1256
},
{
"epoch": 0.87,
"learning_rate": 1.6721848592740752e-06,
"loss": 0.7877,
"step": 1257
},
{
"epoch": 0.87,
"learning_rate": 1.6542150662039081e-06,
"loss": 0.7745,
"step": 1258
},
{
"epoch": 0.87,
"learning_rate": 1.6363381836821512e-06,
"loss": 0.793,
"step": 1259
},
{
"epoch": 0.88,
"learning_rate": 1.618554302244637e-06,
"loss": 0.7712,
"step": 1260
},
{
"epoch": 0.88,
"learning_rate": 1.6008635119562099e-06,
"loss": 0.7551,
"step": 1261
},
{
"epoch": 0.88,
"learning_rate": 1.583265902410247e-06,
"loss": 0.7487,
"step": 1262
},
{
"epoch": 0.88,
"learning_rate": 1.5657615627282453e-06,
"loss": 0.8202,
"step": 1263
},
{
"epoch": 0.88,
"learning_rate": 1.5483505815593169e-06,
"loss": 0.7444,
"step": 1264
},
{
"epoch": 0.88,
"learning_rate": 1.5310330470797974e-06,
"loss": 0.7839,
"step": 1265
},
{
"epoch": 0.88,
"learning_rate": 1.513809046992738e-06,
"loss": 0.8033,
"step": 1266
},
{
"epoch": 0.88,
"learning_rate": 1.496678668527527e-06,
"loss": 0.7631,
"step": 1267
},
{
"epoch": 0.88,
"learning_rate": 1.4796419984393828e-06,
"loss": 0.7653,
"step": 1268
},
{
"epoch": 0.88,
"learning_rate": 1.4626991230089748e-06,
"loss": 0.7568,
"step": 1269
},
{
"epoch": 0.88,
"learning_rate": 1.4458501280419323e-06,
"loss": 0.7946,
"step": 1270
},
{
"epoch": 0.88,
"learning_rate": 1.4290950988684604e-06,
"loss": 0.7518,
"step": 1271
},
{
"epoch": 0.88,
"learning_rate": 1.4124341203428604e-06,
"loss": 0.7764,
"step": 1272
},
{
"epoch": 0.88,
"learning_rate": 1.395867276843139e-06,
"loss": 0.8182,
"step": 1273
},
{
"epoch": 0.88,
"learning_rate": 1.3793946522705558e-06,
"loss": 0.7464,
"step": 1274
},
{
"epoch": 0.89,
"learning_rate": 1.3630163300492095e-06,
"loss": 0.8357,
"step": 1275
},
{
"epoch": 0.89,
"learning_rate": 1.346732393125616e-06,
"loss": 0.7408,
"step": 1276
},
{
"epoch": 0.89,
"learning_rate": 1.330542923968281e-06,
"loss": 0.7617,
"step": 1277
},
{
"epoch": 0.89,
"learning_rate": 1.3144480045672903e-06,
"loss": 0.7786,
"step": 1278
},
{
"epoch": 0.89,
"learning_rate": 1.2984477164338905e-06,
"loss": 0.741,
"step": 1279
},
{
"epoch": 0.89,
"learning_rate": 1.2825421406000737e-06,
"loss": 0.7631,
"step": 1280
},
{
"epoch": 0.89,
"learning_rate": 1.266731357618176e-06,
"loss": 0.7541,
"step": 1281
},
{
"epoch": 0.89,
"learning_rate": 1.2510154475604576e-06,
"loss": 0.7119,
"step": 1282
},
{
"epoch": 0.89,
"learning_rate": 1.2353944900187086e-06,
"loss": 0.7771,
"step": 1283
},
{
"epoch": 0.89,
"learning_rate": 1.2198685641038366e-06,
"loss": 0.7781,
"step": 1284
},
{
"epoch": 0.89,
"learning_rate": 1.204437748445475e-06,
"loss": 0.7447,
"step": 1285
},
{
"epoch": 0.89,
"learning_rate": 1.1891021211915721e-06,
"loss": 0.7533,
"step": 1286
},
{
"epoch": 0.89,
"learning_rate": 1.173861760008015e-06,
"loss": 0.7663,
"step": 1287
},
{
"epoch": 0.89,
"learning_rate": 1.158716742078212e-06,
"loss": 0.7735,
"step": 1288
},
{
"epoch": 0.9,
"learning_rate": 1.1436671441027203e-06,
"loss": 0.7499,
"step": 1289
},
{
"epoch": 0.9,
"learning_rate": 1.128713042298857e-06,
"loss": 0.772,
"step": 1290
},
{
"epoch": 0.9,
"learning_rate": 1.1138545124002942e-06,
"loss": 0.7745,
"step": 1291
},
{
"epoch": 0.9,
"learning_rate": 1.099091629656701e-06,
"loss": 0.741,
"step": 1292
},
{
"epoch": 0.9,
"learning_rate": 1.0844244688333472e-06,
"loss": 0.7522,
"step": 1293
},
{
"epoch": 0.9,
"learning_rate": 1.0698531042107207e-06,
"loss": 0.8015,
"step": 1294
},
{
"epoch": 0.9,
"learning_rate": 1.0553776095841672e-06,
"loss": 0.7981,
"step": 1295
},
{
"epoch": 0.9,
"learning_rate": 1.040998058263507e-06,
"loss": 0.7982,
"step": 1296
},
{
"epoch": 0.9,
"learning_rate": 1.026714523072654e-06,
"loss": 0.7458,
"step": 1297
},
{
"epoch": 0.9,
"learning_rate": 1.0125270763492724e-06,
"loss": 0.8068,
"step": 1298
},
{
"epoch": 0.9,
"learning_rate": 9.984357899443786e-07,
"loss": 0.7651,
"step": 1299
},
{
"epoch": 0.9,
"learning_rate": 9.84440735222012e-07,
"loss": 0.7323,
"step": 1300
},
{
"epoch": 0.9,
"learning_rate": 9.705419830588391e-07,
"loss": 0.7736,
"step": 1301
},
{
"epoch": 0.9,
"learning_rate": 9.567396038438236e-07,
"loss": 0.7559,
"step": 1302
},
{
"epoch": 0.9,
"learning_rate": 9.430336674778462e-07,
"loss": 0.7574,
"step": 1303
},
{
"epoch": 0.91,
"learning_rate": 9.294242433733714e-07,
"loss": 0.797,
"step": 1304
},
{
"epoch": 0.91,
"learning_rate": 9.159114004540793e-07,
"loss": 0.7547,
"step": 1305
},
{
"epoch": 0.91,
"learning_rate": 9.024952071545256e-07,
"loss": 0.7295,
"step": 1306
},
{
"epoch": 0.91,
"learning_rate": 8.891757314197957e-07,
"loss": 0.7732,
"step": 1307
},
{
"epoch": 0.91,
"learning_rate": 8.759530407051509e-07,
"loss": 0.7974,
"step": 1308
},
{
"epoch": 0.91,
"learning_rate": 8.628272019757022e-07,
"loss": 0.7526,
"step": 1309
},
{
"epoch": 0.91,
"learning_rate": 8.497982817060558e-07,
"loss": 0.7197,
"step": 1310
},
{
"epoch": 0.91,
"learning_rate": 8.368663458799875e-07,
"loss": 0.7813,
"step": 1311
},
{
"epoch": 0.91,
"learning_rate": 8.240314599901e-07,
"loss": 0.8086,
"step": 1312
},
{
"epoch": 0.91,
"learning_rate": 8.112936890375001e-07,
"loss": 0.7934,
"step": 1313
},
{
"epoch": 0.91,
"learning_rate": 7.986530975314633e-07,
"loss": 0.8004,
"step": 1314
},
{
"epoch": 0.91,
"learning_rate": 7.861097494891057e-07,
"loss": 0.7636,
"step": 1315
},
{
"epoch": 0.91,
"learning_rate": 7.736637084350663e-07,
"loss": 0.7495,
"step": 1316
},
{
"epoch": 0.91,
"learning_rate": 7.613150374011801e-07,
"loss": 0.7361,
"step": 1317
},
{
"epoch": 0.92,
"learning_rate": 7.49063798926164e-07,
"loss": 0.7515,
"step": 1318
},
{
"epoch": 0.92,
"learning_rate": 7.36910055055291e-07,
"loss": 0.7086,
"step": 1319
},
{
"epoch": 0.92,
"learning_rate": 7.248538673400873e-07,
"loss": 0.7529,
"step": 1320
},
{
"epoch": 0.92,
"learning_rate": 7.128952968380032e-07,
"loss": 0.7837,
"step": 1321
},
{
"epoch": 0.92,
"learning_rate": 7.010344041121375e-07,
"loss": 0.7951,
"step": 1322
},
{
"epoch": 0.92,
"learning_rate": 6.892712492308851e-07,
"loss": 0.781,
"step": 1323
},
{
"epoch": 0.92,
"learning_rate": 6.77605891767672e-07,
"loss": 0.7664,
"step": 1324
},
{
"epoch": 0.92,
"learning_rate": 6.660383908006318e-07,
"loss": 0.7097,
"step": 1325
},
{
"epoch": 0.92,
"learning_rate": 6.545688049123145e-07,
"loss": 0.7589,
"step": 1326
},
{
"epoch": 0.92,
"learning_rate": 6.431971921893886e-07,
"loss": 0.7926,
"step": 1327
},
{
"epoch": 0.92,
"learning_rate": 6.319236102223447e-07,
"loss": 0.767,
"step": 1328
},
{
"epoch": 0.92,
"learning_rate": 6.20748116105212e-07,
"loss": 0.7754,
"step": 1329
},
{
"epoch": 0.92,
"learning_rate": 6.096707664352442e-07,
"loss": 0.7962,
"step": 1330
},
{
"epoch": 0.92,
"learning_rate": 5.986916173126811e-07,
"loss": 0.7408,
"step": 1331
},
{
"epoch": 0.93,
"learning_rate": 5.87810724340403e-07,
"loss": 0.7743,
"step": 1332
},
{
"epoch": 0.93,
"learning_rate": 5.770281426237101e-07,
"loss": 0.7632,
"step": 1333
},
{
"epoch": 0.93,
"learning_rate": 5.6634392676999e-07,
"loss": 0.7106,
"step": 1334
},
{
"epoch": 0.93,
"learning_rate": 5.557581308884819e-07,
"loss": 0.7534,
"step": 1335
},
{
"epoch": 0.93,
"learning_rate": 5.452708085899749e-07,
"loss": 0.7582,
"step": 1336
},
{
"epoch": 0.93,
"learning_rate": 5.348820129865595e-07,
"loss": 0.7671,
"step": 1337
},
{
"epoch": 0.93,
"learning_rate": 5.245917966913361e-07,
"loss": 0.7722,
"step": 1338
},
{
"epoch": 0.93,
"learning_rate": 5.144002118181624e-07,
"loss": 0.7941,
"step": 1339
},
{
"epoch": 0.93,
"learning_rate": 5.043073099813889e-07,
"loss": 0.785,
"step": 1340
},
{
"epoch": 0.93,
"learning_rate": 4.943131422955905e-07,
"loss": 0.7854,
"step": 1341
},
{
"epoch": 0.93,
"learning_rate": 4.844177593753175e-07,
"loss": 0.7659,
"step": 1342
},
{
"epoch": 0.93,
"learning_rate": 4.746212113348292e-07,
"loss": 0.7877,
"step": 1343
},
{
"epoch": 0.93,
"learning_rate": 4.6492354778784775e-07,
"loss": 0.712,
"step": 1344
},
{
"epoch": 0.93,
"learning_rate": 4.553248178473002e-07,
"loss": 0.8188,
"step": 1345
},
{
"epoch": 0.93,
"learning_rate": 4.458250701250788e-07,
"loss": 0.7575,
"step": 1346
},
{
"epoch": 0.94,
"learning_rate": 4.364243527317835e-07,
"loss": 0.8208,
"step": 1347
},
{
"epoch": 0.94,
"learning_rate": 4.2712271327648656e-07,
"loss": 0.8279,
"step": 1348
},
{
"epoch": 0.94,
"learning_rate": 4.179201988664927e-07,
"loss": 0.7698,
"step": 1349
},
{
"epoch": 0.94,
"learning_rate": 4.0881685610709044e-07,
"loss": 0.7556,
"step": 1350
},
{
"epoch": 0.94,
"learning_rate": 3.9981273110133e-07,
"loss": 0.8139,
"step": 1351
},
{
"epoch": 0.94,
"learning_rate": 3.9090786944977476e-07,
"loss": 0.8067,
"step": 1352
},
{
"epoch": 0.94,
"learning_rate": 3.821023162502813e-07,
"loss": 0.7791,
"step": 1353
},
{
"epoch": 0.94,
"learning_rate": 3.733961160977684e-07,
"loss": 0.7793,
"step": 1354
},
{
"epoch": 0.94,
"learning_rate": 3.6478931308399303e-07,
"loss": 0.8175,
"step": 1355
},
{
"epoch": 0.94,
"learning_rate": 3.5628195079731253e-07,
"loss": 0.7709,
"step": 1356
},
{
"epoch": 0.94,
"learning_rate": 3.4787407232249605e-07,
"loss": 0.7549,
"step": 1357
},
{
"epoch": 0.94,
"learning_rate": 3.395657202404645e-07,
"loss": 0.7628,
"step": 1358
},
{
"epoch": 0.94,
"learning_rate": 3.313569366281133e-07,
"loss": 0.7724,
"step": 1359
},
{
"epoch": 0.94,
"learning_rate": 3.2324776305806996e-07,
"loss": 0.7551,
"step": 1360
},
{
"epoch": 0.95,
"learning_rate": 3.1523824059850774e-07,
"loss": 0.7838,
"step": 1361
},
{
"epoch": 0.95,
"learning_rate": 3.0732840981291476e-07,
"loss": 0.8142,
"step": 1362
},
{
"epoch": 0.95,
"learning_rate": 2.995183107599053e-07,
"loss": 0.7815,
"step": 1363
},
{
"epoch": 0.95,
"learning_rate": 2.9180798299301537e-07,
"loss": 0.7485,
"step": 1364
},
{
"epoch": 0.95,
"learning_rate": 2.8419746556048957e-07,
"loss": 0.7683,
"step": 1365
},
{
"epoch": 0.95,
"learning_rate": 2.7668679700509903e-07,
"loss": 0.7238,
"step": 1366
},
{
"epoch": 0.95,
"learning_rate": 2.692760153639373e-07,
"loss": 0.7599,
"step": 1367
},
{
"epoch": 0.95,
"learning_rate": 2.619651581682292e-07,
"loss": 0.7714,
"step": 1368
},
{
"epoch": 0.95,
"learning_rate": 2.547542624431398e-07,
"loss": 0.7906,
"step": 1369
},
{
"epoch": 0.95,
"learning_rate": 2.4764336470759485e-07,
"loss": 0.7459,
"step": 1370
},
{
"epoch": 0.95,
"learning_rate": 2.406325009740829e-07,
"loss": 0.8234,
"step": 1371
},
{
"epoch": 0.95,
"learning_rate": 2.3372170674847982e-07,
"loss": 0.7585,
"step": 1372
},
{
"epoch": 0.95,
"learning_rate": 2.269110170298694e-07,
"loss": 0.7465,
"step": 1373
},
{
"epoch": 0.95,
"learning_rate": 2.2020046631037185e-07,
"loss": 0.7177,
"step": 1374
},
{
"epoch": 0.95,
"learning_rate": 2.135900885749509e-07,
"loss": 0.7576,
"step": 1375
},
{
"epoch": 0.96,
"learning_rate": 2.0707991730126277e-07,
"loss": 0.7536,
"step": 1376
},
{
"epoch": 0.96,
"learning_rate": 2.0066998545947404e-07,
"loss": 0.7663,
"step": 1377
},
{
"epoch": 0.96,
"learning_rate": 1.9436032551209517e-07,
"loss": 0.752,
"step": 1378
},
{
"epoch": 0.96,
"learning_rate": 1.8815096941382504e-07,
"loss": 0.7763,
"step": 1379
},
{
"epoch": 0.96,
"learning_rate": 1.820419486113778e-07,
"loss": 0.7792,
"step": 1380
},
{
"epoch": 0.96,
"learning_rate": 1.7603329404332736e-07,
"loss": 0.8057,
"step": 1381
},
{
"epoch": 0.96,
"learning_rate": 1.701250361399587e-07,
"loss": 0.7546,
"step": 1382
},
{
"epoch": 0.96,
"learning_rate": 1.643172048231012e-07,
"loss": 0.7226,
"step": 1383
},
{
"epoch": 0.96,
"learning_rate": 1.5860982950598458e-07,
"loss": 0.7752,
"step": 1384
},
{
"epoch": 0.96,
"learning_rate": 1.5300293909308982e-07,
"loss": 0.7669,
"step": 1385
},
{
"epoch": 0.96,
"learning_rate": 1.474965619800006e-07,
"loss": 0.7603,
"step": 1386
},
{
"epoch": 0.96,
"learning_rate": 1.4209072605325668e-07,
"loss": 0.7679,
"step": 1387
},
{
"epoch": 0.96,
"learning_rate": 1.3678545869022286e-07,
"loss": 0.7906,
"step": 1388
},
{
"epoch": 0.96,
"learning_rate": 1.3158078675893581e-07,
"loss": 0.7499,
"step": 1389
},
{
"epoch": 0.97,
"learning_rate": 1.2647673661798642e-07,
"loss": 0.6939,
"step": 1390
},
{
"epoch": 0.97,
"learning_rate": 1.214733341163621e-07,
"loss": 0.7708,
"step": 1391
},
{
"epoch": 0.97,
"learning_rate": 1.1657060459334457e-07,
"loss": 0.7595,
"step": 1392
},
{
"epoch": 0.97,
"learning_rate": 1.1176857287835019e-07,
"loss": 0.704,
"step": 1393
},
{
"epoch": 0.97,
"learning_rate": 1.070672632908365e-07,
"loss": 0.7394,
"step": 1394
},
{
"epoch": 0.97,
"learning_rate": 1.0246669964015132e-07,
"loss": 0.7594,
"step": 1395
},
{
"epoch": 0.97,
"learning_rate": 9.796690522543062e-08,
"loss": 0.766,
"step": 1396
},
{
"epoch": 0.97,
"learning_rate": 9.356790283546746e-08,
"loss": 0.6862,
"step": 1397
},
{
"epoch": 0.97,
"learning_rate": 8.926971474861213e-08,
"loss": 0.7008,
"step": 1398
},
{
"epoch": 0.97,
"learning_rate": 8.507236273263886e-08,
"loss": 0.6989,
"step": 1399
},
{
"epoch": 0.97,
"learning_rate": 8.097586804465707e-08,
"loss": 0.7851,
"step": 1400
},
{
"epoch": 0.97,
"learning_rate": 7.698025143098698e-08,
"loss": 0.7277,
"step": 1401
},
{
"epoch": 0.97,
"learning_rate": 7.308553312706412e-08,
"loss": 0.7671,
"step": 1402
},
{
"epoch": 0.97,
"learning_rate": 6.929173285733504e-08,
"loss": 0.7477,
"step": 1403
},
{
"epoch": 0.97,
"learning_rate": 6.55988698351484e-08,
"loss": 0.7709,
"step": 1404
},
{
"epoch": 0.98,
"learning_rate": 6.200696276267515e-08,
"loss": 0.7862,
"step": 1405
},
{
"epoch": 0.98,
"learning_rate": 5.8516029830799626e-08,
"loss": 0.7338,
"step": 1406
},
{
"epoch": 0.98,
"learning_rate": 5.512608871902858e-08,
"loss": 0.8179,
"step": 1407
},
{
"epoch": 0.98,
"learning_rate": 5.183715659541344e-08,
"loss": 0.7814,
"step": 1408
},
{
"epoch": 0.98,
"learning_rate": 4.864925011644595e-08,
"loss": 0.7275,
"step": 1409
},
{
"epoch": 0.98,
"learning_rate": 4.556238542698932e-08,
"loss": 0.7541,
"step": 1410
},
{
"epoch": 0.98,
"learning_rate": 4.257657816018501e-08,
"loss": 0.7548,
"step": 1411
},
{
"epoch": 0.98,
"learning_rate": 3.969184343738164e-08,
"loss": 0.7559,
"step": 1412
},
{
"epoch": 0.98,
"learning_rate": 3.690819586805505e-08,
"loss": 0.7748,
"step": 1413
},
{
"epoch": 0.98,
"learning_rate": 3.422564954973284e-08,
"loss": 0.7858,
"step": 1414
},
{
"epoch": 0.98,
"learning_rate": 3.16442180679255e-08,
"loss": 0.7226,
"step": 1415
},
{
"epoch": 0.98,
"learning_rate": 2.9163914496053157e-08,
"loss": 0.7889,
"step": 1416
},
{
"epoch": 0.98,
"learning_rate": 2.678475139539227e-08,
"loss": 0.7514,
"step": 1417
},
{
"epoch": 0.98,
"learning_rate": 2.450674081499127e-08,
"loss": 0.7846,
"step": 1418
},
{
"epoch": 0.99,
"learning_rate": 2.2329894291630573e-08,
"loss": 0.7633,
"step": 1419
},
{
"epoch": 0.99,
"learning_rate": 2.0254222849744874e-08,
"loss": 0.7099,
"step": 1420
},
{
"epoch": 0.99,
"learning_rate": 1.8279737001387633e-08,
"loss": 0.7785,
"step": 1421
},
{
"epoch": 0.99,
"learning_rate": 1.6406446746157767e-08,
"loss": 0.78,
"step": 1422
},
{
"epoch": 0.99,
"learning_rate": 1.4634361571164158e-08,
"loss": 0.807,
"step": 1423
},
{
"epoch": 0.99,
"learning_rate": 1.2963490450970117e-08,
"loss": 0.7456,
"step": 1424
},
{
"epoch": 0.99,
"learning_rate": 1.1393841847548992e-08,
"loss": 0.7775,
"step": 1425
},
{
"epoch": 0.99,
"learning_rate": 9.925423710241966e-09,
"loss": 0.7651,
"step": 1426
},
{
"epoch": 0.99,
"learning_rate": 8.558243475718098e-09,
"loss": 0.7914,
"step": 1427
},
{
"epoch": 0.99,
"learning_rate": 7.292308067936571e-09,
"loss": 0.7452,
"step": 1428
},
{
"epoch": 0.99,
"learning_rate": 6.127623898113388e-09,
"loss": 0.7337,
"step": 1429
},
{
"epoch": 0.99,
"learning_rate": 5.064196864683624e-09,
"loss": 0.7905,
"step": 1430
},
{
"epoch": 0.99,
"learning_rate": 4.102032353274776e-09,
"loss": 0.7679,
"step": 1431
},
{
"epoch": 0.99,
"learning_rate": 3.2411352366823466e-09,
"loss": 0.7972,
"step": 1432
},
{
"epoch": 1.0,
"learning_rate": 2.4815098748409704e-09,
"loss": 0.7841,
"step": 1433
},
{
"epoch": 1.0,
"learning_rate": 1.8231601148044342e-09,
"loss": 0.7393,
"step": 1434
},
{
"epoch": 1.0,
"learning_rate": 1.2660892907234713e-09,
"loss": 0.7755,
"step": 1435
},
{
"epoch": 1.0,
"learning_rate": 8.103002238324387e-10,
"loss": 0.7471,
"step": 1436
},
{
"epoch": 1.0,
"learning_rate": 4.557952224337747e-10,
"loss": 0.7687,
"step": 1437
},
{
"epoch": 1.0,
"learning_rate": 2.0257608188467558e-10,
"loss": 0.7396,
"step": 1438
},
{
"epoch": 1.0,
"learning_rate": 5.0644084592654796e-11,
"loss": 0.7622,
"step": 1439
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 0.7531,
"step": 1440
},
{
"epoch": 1.0,
"step": 1440,
"total_flos": 1.43244675514368e+16,
"train_loss": 0.8262585242175393,
"train_runtime": 11720.0335,
"train_samples_per_second": 0.983,
"train_steps_per_second": 0.123
}
],
"logging_steps": 1.0,
"max_steps": 1440,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100000,
"total_flos": 1.43244675514368e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}