dima806's picture
Upload folder using huggingface_hub
751b029
raw
history blame
No virus
83.5 kB
{
"best_metric": 1.560390591621399,
"best_model_checkpoint": "multiple_accent_classification/checkpoint-695",
"epoch": 1.0,
"global_step": 695,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2.0000000000000002e-07,
"loss": 1.7809,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.0000000000000003e-07,
"loss": 1.7236,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 6.000000000000001e-07,
"loss": 1.8205,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 8.000000000000001e-07,
"loss": 1.7999,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.8185,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 1.2000000000000002e-06,
"loss": 1.7794,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 1.4000000000000001e-06,
"loss": 1.782,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 1.6000000000000001e-06,
"loss": 1.7723,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 1.8000000000000001e-06,
"loss": 1.8171,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.8095,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 2.2e-06,
"loss": 1.7817,
"step": 11
},
{
"epoch": 0.02,
"learning_rate": 2.4000000000000003e-06,
"loss": 1.8079,
"step": 12
},
{
"epoch": 0.02,
"learning_rate": 2.6e-06,
"loss": 1.8265,
"step": 13
},
{
"epoch": 0.02,
"learning_rate": 2.8000000000000003e-06,
"loss": 1.6441,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 3e-06,
"loss": 1.8041,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 3.2000000000000003e-06,
"loss": 1.8014,
"step": 16
},
{
"epoch": 0.02,
"learning_rate": 3.4000000000000005e-06,
"loss": 1.7949,
"step": 17
},
{
"epoch": 0.03,
"learning_rate": 3.6000000000000003e-06,
"loss": 1.8021,
"step": 18
},
{
"epoch": 0.03,
"learning_rate": 3.8000000000000005e-06,
"loss": 1.9434,
"step": 19
},
{
"epoch": 0.03,
"learning_rate": 4.000000000000001e-06,
"loss": 1.7863,
"step": 20
},
{
"epoch": 0.03,
"learning_rate": 4.2000000000000004e-06,
"loss": 1.7931,
"step": 21
},
{
"epoch": 0.03,
"learning_rate": 4.4e-06,
"loss": 1.7781,
"step": 22
},
{
"epoch": 0.03,
"learning_rate": 4.600000000000001e-06,
"loss": 1.7805,
"step": 23
},
{
"epoch": 0.03,
"learning_rate": 4.800000000000001e-06,
"loss": 1.7841,
"step": 24
},
{
"epoch": 0.04,
"learning_rate": 5e-06,
"loss": 1.7882,
"step": 25
},
{
"epoch": 0.04,
"learning_rate": 5.2e-06,
"loss": 1.7881,
"step": 26
},
{
"epoch": 0.04,
"learning_rate": 5.400000000000001e-06,
"loss": 1.7823,
"step": 27
},
{
"epoch": 0.04,
"learning_rate": 5.600000000000001e-06,
"loss": 1.7948,
"step": 28
},
{
"epoch": 0.04,
"learning_rate": 5.8e-06,
"loss": 1.7905,
"step": 29
},
{
"epoch": 0.04,
"learning_rate": 6e-06,
"loss": 1.8093,
"step": 30
},
{
"epoch": 0.04,
"learning_rate": 6.200000000000001e-06,
"loss": 1.7993,
"step": 31
},
{
"epoch": 0.05,
"learning_rate": 6.4000000000000006e-06,
"loss": 1.8261,
"step": 32
},
{
"epoch": 0.05,
"learning_rate": 6.600000000000001e-06,
"loss": 1.8076,
"step": 33
},
{
"epoch": 0.05,
"learning_rate": 6.800000000000001e-06,
"loss": 1.7184,
"step": 34
},
{
"epoch": 0.05,
"learning_rate": 7e-06,
"loss": 1.7999,
"step": 35
},
{
"epoch": 0.05,
"learning_rate": 7.2000000000000005e-06,
"loss": 1.8002,
"step": 36
},
{
"epoch": 0.05,
"learning_rate": 7.4e-06,
"loss": 1.7983,
"step": 37
},
{
"epoch": 0.05,
"learning_rate": 7.600000000000001e-06,
"loss": 1.7646,
"step": 38
},
{
"epoch": 0.06,
"learning_rate": 7.800000000000002e-06,
"loss": 1.7974,
"step": 39
},
{
"epoch": 0.06,
"learning_rate": 8.000000000000001e-06,
"loss": 1.7775,
"step": 40
},
{
"epoch": 0.06,
"learning_rate": 8.2e-06,
"loss": 1.7991,
"step": 41
},
{
"epoch": 0.06,
"learning_rate": 8.400000000000001e-06,
"loss": 1.7888,
"step": 42
},
{
"epoch": 0.06,
"learning_rate": 8.6e-06,
"loss": 1.7765,
"step": 43
},
{
"epoch": 0.06,
"learning_rate": 8.8e-06,
"loss": 1.7836,
"step": 44
},
{
"epoch": 0.06,
"learning_rate": 9e-06,
"loss": 1.7949,
"step": 45
},
{
"epoch": 0.07,
"learning_rate": 9.200000000000002e-06,
"loss": 1.7724,
"step": 46
},
{
"epoch": 0.07,
"learning_rate": 9.4e-06,
"loss": 1.8043,
"step": 47
},
{
"epoch": 0.07,
"learning_rate": 9.600000000000001e-06,
"loss": 1.7796,
"step": 48
},
{
"epoch": 0.07,
"learning_rate": 9.800000000000001e-06,
"loss": 1.7891,
"step": 49
},
{
"epoch": 0.07,
"learning_rate": 1e-05,
"loss": 1.7836,
"step": 50
},
{
"epoch": 0.07,
"learning_rate": 9.998550724637682e-06,
"loss": 1.8004,
"step": 51
},
{
"epoch": 0.07,
"learning_rate": 9.997101449275363e-06,
"loss": 1.7932,
"step": 52
},
{
"epoch": 0.08,
"learning_rate": 9.995652173913044e-06,
"loss": 1.8642,
"step": 53
},
{
"epoch": 0.08,
"learning_rate": 9.994202898550725e-06,
"loss": 1.7733,
"step": 54
},
{
"epoch": 0.08,
"learning_rate": 9.992753623188408e-06,
"loss": 1.8387,
"step": 55
},
{
"epoch": 0.08,
"learning_rate": 9.991304347826087e-06,
"loss": 1.8016,
"step": 56
},
{
"epoch": 0.08,
"learning_rate": 9.98985507246377e-06,
"loss": 1.8028,
"step": 57
},
{
"epoch": 0.08,
"learning_rate": 9.98840579710145e-06,
"loss": 1.7867,
"step": 58
},
{
"epoch": 0.08,
"learning_rate": 9.986956521739132e-06,
"loss": 1.8025,
"step": 59
},
{
"epoch": 0.09,
"learning_rate": 9.985507246376813e-06,
"loss": 1.8052,
"step": 60
},
{
"epoch": 0.09,
"learning_rate": 9.984057971014494e-06,
"loss": 1.7862,
"step": 61
},
{
"epoch": 0.09,
"learning_rate": 9.982608695652175e-06,
"loss": 1.7925,
"step": 62
},
{
"epoch": 0.09,
"learning_rate": 9.981159420289856e-06,
"loss": 1.8018,
"step": 63
},
{
"epoch": 0.09,
"learning_rate": 9.979710144927537e-06,
"loss": 1.7766,
"step": 64
},
{
"epoch": 0.09,
"learning_rate": 9.978260869565218e-06,
"loss": 1.7993,
"step": 65
},
{
"epoch": 0.09,
"learning_rate": 9.9768115942029e-06,
"loss": 1.8006,
"step": 66
},
{
"epoch": 0.1,
"learning_rate": 9.97536231884058e-06,
"loss": 1.789,
"step": 67
},
{
"epoch": 0.1,
"learning_rate": 9.973913043478262e-06,
"loss": 1.7795,
"step": 68
},
{
"epoch": 0.1,
"learning_rate": 9.972463768115943e-06,
"loss": 1.7781,
"step": 69
},
{
"epoch": 0.1,
"learning_rate": 9.971014492753624e-06,
"loss": 1.773,
"step": 70
},
{
"epoch": 0.1,
"learning_rate": 9.969565217391305e-06,
"loss": 1.7694,
"step": 71
},
{
"epoch": 0.1,
"learning_rate": 9.968115942028986e-06,
"loss": 1.7751,
"step": 72
},
{
"epoch": 0.11,
"learning_rate": 9.966666666666667e-06,
"loss": 1.7843,
"step": 73
},
{
"epoch": 0.11,
"learning_rate": 9.965217391304348e-06,
"loss": 1.7965,
"step": 74
},
{
"epoch": 0.11,
"learning_rate": 9.96376811594203e-06,
"loss": 1.9398,
"step": 75
},
{
"epoch": 0.11,
"learning_rate": 9.962318840579712e-06,
"loss": 1.7804,
"step": 76
},
{
"epoch": 0.11,
"learning_rate": 9.960869565217393e-06,
"loss": 1.7993,
"step": 77
},
{
"epoch": 0.11,
"learning_rate": 9.959420289855072e-06,
"loss": 1.8129,
"step": 78
},
{
"epoch": 0.11,
"learning_rate": 9.957971014492755e-06,
"loss": 1.7988,
"step": 79
},
{
"epoch": 0.12,
"learning_rate": 9.956521739130436e-06,
"loss": 1.8938,
"step": 80
},
{
"epoch": 0.12,
"learning_rate": 9.955072463768117e-06,
"loss": 1.7894,
"step": 81
},
{
"epoch": 0.12,
"learning_rate": 9.953623188405798e-06,
"loss": 1.7984,
"step": 82
},
{
"epoch": 0.12,
"learning_rate": 9.952173913043479e-06,
"loss": 1.8354,
"step": 83
},
{
"epoch": 0.12,
"learning_rate": 9.95072463768116e-06,
"loss": 1.7562,
"step": 84
},
{
"epoch": 0.12,
"learning_rate": 9.949275362318841e-06,
"loss": 1.7773,
"step": 85
},
{
"epoch": 0.12,
"learning_rate": 9.947826086956522e-06,
"loss": 1.7774,
"step": 86
},
{
"epoch": 0.13,
"learning_rate": 9.946376811594205e-06,
"loss": 1.7808,
"step": 87
},
{
"epoch": 0.13,
"learning_rate": 9.944927536231886e-06,
"loss": 1.7769,
"step": 88
},
{
"epoch": 0.13,
"learning_rate": 9.943478260869565e-06,
"loss": 1.8332,
"step": 89
},
{
"epoch": 0.13,
"learning_rate": 9.942028985507248e-06,
"loss": 1.7777,
"step": 90
},
{
"epoch": 0.13,
"learning_rate": 9.940579710144929e-06,
"loss": 1.8006,
"step": 91
},
{
"epoch": 0.13,
"learning_rate": 9.93913043478261e-06,
"loss": 1.8033,
"step": 92
},
{
"epoch": 0.13,
"learning_rate": 9.93768115942029e-06,
"loss": 1.7584,
"step": 93
},
{
"epoch": 0.14,
"learning_rate": 9.936231884057972e-06,
"loss": 1.8261,
"step": 94
},
{
"epoch": 0.14,
"learning_rate": 9.934782608695653e-06,
"loss": 1.8463,
"step": 95
},
{
"epoch": 0.14,
"learning_rate": 9.933333333333334e-06,
"loss": 1.7987,
"step": 96
},
{
"epoch": 0.14,
"learning_rate": 9.931884057971015e-06,
"loss": 1.7971,
"step": 97
},
{
"epoch": 0.14,
"learning_rate": 9.930434782608697e-06,
"loss": 1.8483,
"step": 98
},
{
"epoch": 0.14,
"learning_rate": 9.928985507246378e-06,
"loss": 1.8237,
"step": 99
},
{
"epoch": 0.14,
"learning_rate": 9.927536231884058e-06,
"loss": 1.8163,
"step": 100
},
{
"epoch": 0.15,
"learning_rate": 9.92608695652174e-06,
"loss": 1.7806,
"step": 101
},
{
"epoch": 0.15,
"learning_rate": 9.924637681159421e-06,
"loss": 1.7938,
"step": 102
},
{
"epoch": 0.15,
"learning_rate": 9.923188405797102e-06,
"loss": 1.7786,
"step": 103
},
{
"epoch": 0.15,
"learning_rate": 9.921739130434783e-06,
"loss": 1.7904,
"step": 104
},
{
"epoch": 0.15,
"learning_rate": 9.920289855072464e-06,
"loss": 1.7967,
"step": 105
},
{
"epoch": 0.15,
"learning_rate": 9.918840579710145e-06,
"loss": 1.807,
"step": 106
},
{
"epoch": 0.15,
"learning_rate": 9.917391304347826e-06,
"loss": 1.8079,
"step": 107
},
{
"epoch": 0.16,
"learning_rate": 9.915942028985507e-06,
"loss": 1.8145,
"step": 108
},
{
"epoch": 0.16,
"learning_rate": 9.91449275362319e-06,
"loss": 1.7979,
"step": 109
},
{
"epoch": 0.16,
"learning_rate": 9.913043478260871e-06,
"loss": 1.7861,
"step": 110
},
{
"epoch": 0.16,
"learning_rate": 9.911594202898552e-06,
"loss": 1.7905,
"step": 111
},
{
"epoch": 0.16,
"learning_rate": 9.910144927536233e-06,
"loss": 1.8235,
"step": 112
},
{
"epoch": 0.16,
"learning_rate": 9.908695652173914e-06,
"loss": 1.8008,
"step": 113
},
{
"epoch": 0.16,
"learning_rate": 9.907246376811595e-06,
"loss": 1.7062,
"step": 114
},
{
"epoch": 0.17,
"learning_rate": 9.905797101449276e-06,
"loss": 1.7784,
"step": 115
},
{
"epoch": 0.17,
"learning_rate": 9.904347826086957e-06,
"loss": 1.7804,
"step": 116
},
{
"epoch": 0.17,
"learning_rate": 9.902898550724638e-06,
"loss": 1.7892,
"step": 117
},
{
"epoch": 0.17,
"learning_rate": 9.901449275362319e-06,
"loss": 1.7925,
"step": 118
},
{
"epoch": 0.17,
"learning_rate": 9.9e-06,
"loss": 1.8087,
"step": 119
},
{
"epoch": 0.17,
"learning_rate": 9.898550724637683e-06,
"loss": 1.7866,
"step": 120
},
{
"epoch": 0.17,
"learning_rate": 9.897101449275364e-06,
"loss": 1.77,
"step": 121
},
{
"epoch": 0.18,
"learning_rate": 9.895652173913045e-06,
"loss": 1.8127,
"step": 122
},
{
"epoch": 0.18,
"learning_rate": 9.894202898550726e-06,
"loss": 1.7999,
"step": 123
},
{
"epoch": 0.18,
"learning_rate": 9.892753623188407e-06,
"loss": 1.7879,
"step": 124
},
{
"epoch": 0.18,
"learning_rate": 9.891304347826088e-06,
"loss": 1.8021,
"step": 125
},
{
"epoch": 0.18,
"learning_rate": 9.889855072463769e-06,
"loss": 1.7853,
"step": 126
},
{
"epoch": 0.18,
"learning_rate": 9.88840579710145e-06,
"loss": 1.7957,
"step": 127
},
{
"epoch": 0.18,
"learning_rate": 9.886956521739132e-06,
"loss": 1.7958,
"step": 128
},
{
"epoch": 0.19,
"learning_rate": 9.885507246376812e-06,
"loss": 1.7858,
"step": 129
},
{
"epoch": 0.19,
"learning_rate": 9.884057971014493e-06,
"loss": 1.7753,
"step": 130
},
{
"epoch": 0.19,
"learning_rate": 9.882608695652175e-06,
"loss": 1.7965,
"step": 131
},
{
"epoch": 0.19,
"learning_rate": 9.881159420289856e-06,
"loss": 1.784,
"step": 132
},
{
"epoch": 0.19,
"learning_rate": 9.879710144927537e-06,
"loss": 1.7682,
"step": 133
},
{
"epoch": 0.19,
"learning_rate": 9.878260869565218e-06,
"loss": 1.7961,
"step": 134
},
{
"epoch": 0.19,
"learning_rate": 9.8768115942029e-06,
"loss": 1.7959,
"step": 135
},
{
"epoch": 0.2,
"learning_rate": 9.87536231884058e-06,
"loss": 1.7965,
"step": 136
},
{
"epoch": 0.2,
"learning_rate": 9.873913043478261e-06,
"loss": 1.7975,
"step": 137
},
{
"epoch": 0.2,
"learning_rate": 9.872463768115942e-06,
"loss": 1.7583,
"step": 138
},
{
"epoch": 0.2,
"learning_rate": 9.871014492753625e-06,
"loss": 1.8122,
"step": 139
},
{
"epoch": 0.2,
"learning_rate": 9.869565217391304e-06,
"loss": 1.773,
"step": 140
},
{
"epoch": 0.2,
"learning_rate": 9.868115942028986e-06,
"loss": 1.7903,
"step": 141
},
{
"epoch": 0.2,
"learning_rate": 9.866666666666668e-06,
"loss": 1.7876,
"step": 142
},
{
"epoch": 0.21,
"learning_rate": 9.865217391304348e-06,
"loss": 1.7727,
"step": 143
},
{
"epoch": 0.21,
"learning_rate": 9.86376811594203e-06,
"loss": 1.7971,
"step": 144
},
{
"epoch": 0.21,
"learning_rate": 9.862318840579711e-06,
"loss": 1.7969,
"step": 145
},
{
"epoch": 0.21,
"learning_rate": 9.860869565217392e-06,
"loss": 1.7716,
"step": 146
},
{
"epoch": 0.21,
"learning_rate": 9.859420289855073e-06,
"loss": 1.7936,
"step": 147
},
{
"epoch": 0.21,
"learning_rate": 9.857971014492754e-06,
"loss": 1.8433,
"step": 148
},
{
"epoch": 0.21,
"learning_rate": 9.856521739130435e-06,
"loss": 1.7925,
"step": 149
},
{
"epoch": 0.22,
"learning_rate": 9.855072463768118e-06,
"loss": 1.7885,
"step": 150
},
{
"epoch": 0.22,
"learning_rate": 9.853623188405797e-06,
"loss": 1.7897,
"step": 151
},
{
"epoch": 0.22,
"learning_rate": 9.852173913043478e-06,
"loss": 1.7979,
"step": 152
},
{
"epoch": 0.22,
"learning_rate": 9.850724637681161e-06,
"loss": 1.7937,
"step": 153
},
{
"epoch": 0.22,
"learning_rate": 9.84927536231884e-06,
"loss": 1.8094,
"step": 154
},
{
"epoch": 0.22,
"learning_rate": 9.847826086956523e-06,
"loss": 1.7972,
"step": 155
},
{
"epoch": 0.22,
"learning_rate": 9.846376811594204e-06,
"loss": 1.7988,
"step": 156
},
{
"epoch": 0.23,
"learning_rate": 9.844927536231885e-06,
"loss": 1.8043,
"step": 157
},
{
"epoch": 0.23,
"learning_rate": 9.843478260869566e-06,
"loss": 1.7802,
"step": 158
},
{
"epoch": 0.23,
"learning_rate": 9.842028985507247e-06,
"loss": 1.8084,
"step": 159
},
{
"epoch": 0.23,
"learning_rate": 9.840579710144928e-06,
"loss": 1.7994,
"step": 160
},
{
"epoch": 0.23,
"learning_rate": 9.83913043478261e-06,
"loss": 1.7958,
"step": 161
},
{
"epoch": 0.23,
"learning_rate": 9.83768115942029e-06,
"loss": 1.799,
"step": 162
},
{
"epoch": 0.23,
"learning_rate": 9.836231884057973e-06,
"loss": 1.8047,
"step": 163
},
{
"epoch": 0.24,
"learning_rate": 9.834782608695654e-06,
"loss": 1.792,
"step": 164
},
{
"epoch": 0.24,
"learning_rate": 9.833333333333333e-06,
"loss": 1.7957,
"step": 165
},
{
"epoch": 0.24,
"learning_rate": 9.831884057971016e-06,
"loss": 1.8003,
"step": 166
},
{
"epoch": 0.24,
"learning_rate": 9.830434782608697e-06,
"loss": 1.7996,
"step": 167
},
{
"epoch": 0.24,
"learning_rate": 9.828985507246378e-06,
"loss": 1.7828,
"step": 168
},
{
"epoch": 0.24,
"learning_rate": 9.827536231884059e-06,
"loss": 1.806,
"step": 169
},
{
"epoch": 0.24,
"learning_rate": 9.82608695652174e-06,
"loss": 1.7795,
"step": 170
},
{
"epoch": 0.25,
"learning_rate": 9.82463768115942e-06,
"loss": 1.7812,
"step": 171
},
{
"epoch": 0.25,
"learning_rate": 9.823188405797103e-06,
"loss": 1.7793,
"step": 172
},
{
"epoch": 0.25,
"learning_rate": 9.821739130434783e-06,
"loss": 1.7826,
"step": 173
},
{
"epoch": 0.25,
"learning_rate": 9.820289855072465e-06,
"loss": 1.794,
"step": 174
},
{
"epoch": 0.25,
"learning_rate": 9.818840579710146e-06,
"loss": 1.8022,
"step": 175
},
{
"epoch": 0.25,
"learning_rate": 9.817391304347826e-06,
"loss": 1.8022,
"step": 176
},
{
"epoch": 0.25,
"learning_rate": 9.815942028985508e-06,
"loss": 1.7854,
"step": 177
},
{
"epoch": 0.26,
"learning_rate": 9.81449275362319e-06,
"loss": 1.8071,
"step": 178
},
{
"epoch": 0.26,
"learning_rate": 9.81304347826087e-06,
"loss": 1.7822,
"step": 179
},
{
"epoch": 0.26,
"learning_rate": 9.811594202898551e-06,
"loss": 1.7871,
"step": 180
},
{
"epoch": 0.26,
"learning_rate": 9.810144927536232e-06,
"loss": 1.818,
"step": 181
},
{
"epoch": 0.26,
"learning_rate": 9.808695652173913e-06,
"loss": 1.7898,
"step": 182
},
{
"epoch": 0.26,
"learning_rate": 9.807246376811596e-06,
"loss": 1.7978,
"step": 183
},
{
"epoch": 0.26,
"learning_rate": 9.805797101449275e-06,
"loss": 1.7966,
"step": 184
},
{
"epoch": 0.27,
"learning_rate": 9.804347826086958e-06,
"loss": 1.7753,
"step": 185
},
{
"epoch": 0.27,
"learning_rate": 9.802898550724639e-06,
"loss": 1.7773,
"step": 186
},
{
"epoch": 0.27,
"learning_rate": 9.801449275362318e-06,
"loss": 1.7989,
"step": 187
},
{
"epoch": 0.27,
"learning_rate": 9.800000000000001e-06,
"loss": 1.778,
"step": 188
},
{
"epoch": 0.27,
"learning_rate": 9.798550724637682e-06,
"loss": 1.7772,
"step": 189
},
{
"epoch": 0.27,
"learning_rate": 9.797101449275363e-06,
"loss": 1.7873,
"step": 190
},
{
"epoch": 0.27,
"learning_rate": 9.795652173913044e-06,
"loss": 1.784,
"step": 191
},
{
"epoch": 0.28,
"learning_rate": 9.794202898550725e-06,
"loss": 1.8003,
"step": 192
},
{
"epoch": 0.28,
"learning_rate": 9.792753623188406e-06,
"loss": 1.8156,
"step": 193
},
{
"epoch": 0.28,
"learning_rate": 9.791304347826089e-06,
"loss": 1.7934,
"step": 194
},
{
"epoch": 0.28,
"learning_rate": 9.789855072463768e-06,
"loss": 1.8066,
"step": 195
},
{
"epoch": 0.28,
"learning_rate": 9.78840579710145e-06,
"loss": 1.7851,
"step": 196
},
{
"epoch": 0.28,
"learning_rate": 9.786956521739132e-06,
"loss": 1.7973,
"step": 197
},
{
"epoch": 0.28,
"learning_rate": 9.785507246376813e-06,
"loss": 1.7799,
"step": 198
},
{
"epoch": 0.29,
"learning_rate": 9.784057971014494e-06,
"loss": 1.7895,
"step": 199
},
{
"epoch": 0.29,
"learning_rate": 9.782608695652175e-06,
"loss": 1.7787,
"step": 200
},
{
"epoch": 0.29,
"learning_rate": 9.781159420289856e-06,
"loss": 1.8015,
"step": 201
},
{
"epoch": 0.29,
"learning_rate": 9.779710144927537e-06,
"loss": 1.8044,
"step": 202
},
{
"epoch": 0.29,
"learning_rate": 9.778260869565218e-06,
"loss": 1.8018,
"step": 203
},
{
"epoch": 0.29,
"learning_rate": 9.776811594202899e-06,
"loss": 1.7978,
"step": 204
},
{
"epoch": 0.29,
"learning_rate": 9.77536231884058e-06,
"loss": 1.7901,
"step": 205
},
{
"epoch": 0.3,
"learning_rate": 9.77391304347826e-06,
"loss": 1.796,
"step": 206
},
{
"epoch": 0.3,
"learning_rate": 9.772463768115943e-06,
"loss": 1.7673,
"step": 207
},
{
"epoch": 0.3,
"learning_rate": 9.771014492753624e-06,
"loss": 1.7454,
"step": 208
},
{
"epoch": 0.3,
"learning_rate": 9.769565217391305e-06,
"loss": 1.7707,
"step": 209
},
{
"epoch": 0.3,
"learning_rate": 9.768115942028986e-06,
"loss": 1.8148,
"step": 210
},
{
"epoch": 0.3,
"learning_rate": 9.766666666666667e-06,
"loss": 1.7759,
"step": 211
},
{
"epoch": 0.31,
"learning_rate": 9.765217391304348e-06,
"loss": 1.7986,
"step": 212
},
{
"epoch": 0.31,
"learning_rate": 9.76376811594203e-06,
"loss": 1.7843,
"step": 213
},
{
"epoch": 0.31,
"learning_rate": 9.76231884057971e-06,
"loss": 1.7875,
"step": 214
},
{
"epoch": 0.31,
"learning_rate": 9.760869565217393e-06,
"loss": 1.7955,
"step": 215
},
{
"epoch": 0.31,
"learning_rate": 9.759420289855072e-06,
"loss": 1.7922,
"step": 216
},
{
"epoch": 0.31,
"learning_rate": 9.757971014492753e-06,
"loss": 1.7892,
"step": 217
},
{
"epoch": 0.31,
"learning_rate": 9.756521739130436e-06,
"loss": 1.7968,
"step": 218
},
{
"epoch": 0.32,
"learning_rate": 9.755072463768117e-06,
"loss": 1.7844,
"step": 219
},
{
"epoch": 0.32,
"learning_rate": 9.753623188405798e-06,
"loss": 1.7768,
"step": 220
},
{
"epoch": 0.32,
"learning_rate": 9.75217391304348e-06,
"loss": 1.7621,
"step": 221
},
{
"epoch": 0.32,
"learning_rate": 9.75072463768116e-06,
"loss": 1.7873,
"step": 222
},
{
"epoch": 0.32,
"learning_rate": 9.749275362318841e-06,
"loss": 1.801,
"step": 223
},
{
"epoch": 0.32,
"learning_rate": 9.747826086956522e-06,
"loss": 1.7861,
"step": 224
},
{
"epoch": 0.32,
"learning_rate": 9.746376811594203e-06,
"loss": 1.7778,
"step": 225
},
{
"epoch": 0.33,
"learning_rate": 9.744927536231886e-06,
"loss": 1.773,
"step": 226
},
{
"epoch": 0.33,
"learning_rate": 9.743478260869565e-06,
"loss": 1.8384,
"step": 227
},
{
"epoch": 0.33,
"learning_rate": 9.742028985507246e-06,
"loss": 1.7723,
"step": 228
},
{
"epoch": 0.33,
"learning_rate": 9.740579710144929e-06,
"loss": 1.7699,
"step": 229
},
{
"epoch": 0.33,
"learning_rate": 9.73913043478261e-06,
"loss": 1.7861,
"step": 230
},
{
"epoch": 0.33,
"learning_rate": 9.737681159420291e-06,
"loss": 1.8091,
"step": 231
},
{
"epoch": 0.33,
"learning_rate": 9.736231884057972e-06,
"loss": 1.8037,
"step": 232
},
{
"epoch": 0.34,
"learning_rate": 9.734782608695653e-06,
"loss": 1.7961,
"step": 233
},
{
"epoch": 0.34,
"learning_rate": 9.733333333333334e-06,
"loss": 1.7821,
"step": 234
},
{
"epoch": 0.34,
"learning_rate": 9.731884057971015e-06,
"loss": 1.7605,
"step": 235
},
{
"epoch": 0.34,
"learning_rate": 9.730434782608696e-06,
"loss": 1.7963,
"step": 236
},
{
"epoch": 0.34,
"learning_rate": 9.728985507246379e-06,
"loss": 1.8122,
"step": 237
},
{
"epoch": 0.34,
"learning_rate": 9.727536231884058e-06,
"loss": 1.7776,
"step": 238
},
{
"epoch": 0.34,
"learning_rate": 9.726086956521739e-06,
"loss": 1.7968,
"step": 239
},
{
"epoch": 0.35,
"learning_rate": 9.724637681159422e-06,
"loss": 1.8013,
"step": 240
},
{
"epoch": 0.35,
"learning_rate": 9.723188405797103e-06,
"loss": 1.7907,
"step": 241
},
{
"epoch": 0.35,
"learning_rate": 9.721739130434784e-06,
"loss": 1.7574,
"step": 242
},
{
"epoch": 0.35,
"learning_rate": 9.720289855072465e-06,
"loss": 1.7799,
"step": 243
},
{
"epoch": 0.35,
"learning_rate": 9.718840579710146e-06,
"loss": 1.7939,
"step": 244
},
{
"epoch": 0.35,
"learning_rate": 9.717391304347827e-06,
"loss": 1.7531,
"step": 245
},
{
"epoch": 0.35,
"learning_rate": 9.715942028985508e-06,
"loss": 1.7878,
"step": 246
},
{
"epoch": 0.36,
"learning_rate": 9.714492753623189e-06,
"loss": 1.7804,
"step": 247
},
{
"epoch": 0.36,
"learning_rate": 9.713043478260871e-06,
"loss": 1.79,
"step": 248
},
{
"epoch": 0.36,
"learning_rate": 9.71159420289855e-06,
"loss": 1.8005,
"step": 249
},
{
"epoch": 0.36,
"learning_rate": 9.710144927536233e-06,
"loss": 1.7805,
"step": 250
},
{
"epoch": 0.36,
"learning_rate": 9.708695652173914e-06,
"loss": 1.7825,
"step": 251
},
{
"epoch": 0.36,
"learning_rate": 9.707246376811595e-06,
"loss": 1.822,
"step": 252
},
{
"epoch": 0.36,
"learning_rate": 9.705797101449276e-06,
"loss": 1.7619,
"step": 253
},
{
"epoch": 0.37,
"learning_rate": 9.704347826086957e-06,
"loss": 1.7642,
"step": 254
},
{
"epoch": 0.37,
"learning_rate": 9.702898550724638e-06,
"loss": 1.7656,
"step": 255
},
{
"epoch": 0.37,
"learning_rate": 9.701449275362321e-06,
"loss": 1.7751,
"step": 256
},
{
"epoch": 0.37,
"learning_rate": 9.7e-06,
"loss": 1.7816,
"step": 257
},
{
"epoch": 0.37,
"learning_rate": 9.698550724637681e-06,
"loss": 1.752,
"step": 258
},
{
"epoch": 0.37,
"learning_rate": 9.697101449275364e-06,
"loss": 1.7537,
"step": 259
},
{
"epoch": 0.37,
"learning_rate": 9.695652173913043e-06,
"loss": 1.7902,
"step": 260
},
{
"epoch": 0.38,
"learning_rate": 9.694202898550726e-06,
"loss": 1.8062,
"step": 261
},
{
"epoch": 0.38,
"learning_rate": 9.692753623188407e-06,
"loss": 1.6422,
"step": 262
},
{
"epoch": 0.38,
"learning_rate": 9.691304347826088e-06,
"loss": 1.7912,
"step": 263
},
{
"epoch": 0.38,
"learning_rate": 9.689855072463769e-06,
"loss": 1.7721,
"step": 264
},
{
"epoch": 0.38,
"learning_rate": 9.68840579710145e-06,
"loss": 1.7612,
"step": 265
},
{
"epoch": 0.38,
"learning_rate": 9.686956521739131e-06,
"loss": 1.7566,
"step": 266
},
{
"epoch": 0.38,
"learning_rate": 9.685507246376812e-06,
"loss": 1.8152,
"step": 267
},
{
"epoch": 0.39,
"learning_rate": 9.684057971014493e-06,
"loss": 1.7972,
"step": 268
},
{
"epoch": 0.39,
"learning_rate": 9.682608695652174e-06,
"loss": 1.8002,
"step": 269
},
{
"epoch": 0.39,
"learning_rate": 9.681159420289857e-06,
"loss": 1.7958,
"step": 270
},
{
"epoch": 0.39,
"learning_rate": 9.679710144927536e-06,
"loss": 1.7978,
"step": 271
},
{
"epoch": 0.39,
"learning_rate": 9.678260869565219e-06,
"loss": 1.7986,
"step": 272
},
{
"epoch": 0.39,
"learning_rate": 9.6768115942029e-06,
"loss": 1.813,
"step": 273
},
{
"epoch": 0.39,
"learning_rate": 9.67536231884058e-06,
"loss": 1.7639,
"step": 274
},
{
"epoch": 0.4,
"learning_rate": 9.673913043478262e-06,
"loss": 1.7617,
"step": 275
},
{
"epoch": 0.4,
"learning_rate": 9.672463768115943e-06,
"loss": 1.794,
"step": 276
},
{
"epoch": 0.4,
"learning_rate": 9.671014492753624e-06,
"loss": 1.7577,
"step": 277
},
{
"epoch": 0.4,
"learning_rate": 9.669565217391305e-06,
"loss": 1.7905,
"step": 278
},
{
"epoch": 0.4,
"learning_rate": 9.668115942028986e-06,
"loss": 1.7782,
"step": 279
},
{
"epoch": 0.4,
"learning_rate": 9.666666666666667e-06,
"loss": 1.7855,
"step": 280
},
{
"epoch": 0.4,
"learning_rate": 9.66521739130435e-06,
"loss": 1.7611,
"step": 281
},
{
"epoch": 0.41,
"learning_rate": 9.663768115942029e-06,
"loss": 1.7801,
"step": 282
},
{
"epoch": 0.41,
"learning_rate": 9.662318840579711e-06,
"loss": 1.8409,
"step": 283
},
{
"epoch": 0.41,
"learning_rate": 9.660869565217392e-06,
"loss": 1.7867,
"step": 284
},
{
"epoch": 0.41,
"learning_rate": 9.659420289855073e-06,
"loss": 1.7686,
"step": 285
},
{
"epoch": 0.41,
"learning_rate": 9.657971014492754e-06,
"loss": 1.7582,
"step": 286
},
{
"epoch": 0.41,
"learning_rate": 9.656521739130435e-06,
"loss": 1.7462,
"step": 287
},
{
"epoch": 0.41,
"learning_rate": 9.655072463768116e-06,
"loss": 1.7532,
"step": 288
},
{
"epoch": 0.42,
"learning_rate": 9.653623188405797e-06,
"loss": 1.7801,
"step": 289
},
{
"epoch": 0.42,
"learning_rate": 9.652173913043478e-06,
"loss": 1.7927,
"step": 290
},
{
"epoch": 0.42,
"learning_rate": 9.650724637681161e-06,
"loss": 1.7035,
"step": 291
},
{
"epoch": 0.42,
"learning_rate": 9.649275362318842e-06,
"loss": 1.8057,
"step": 292
},
{
"epoch": 0.42,
"learning_rate": 9.647826086956521e-06,
"loss": 1.8014,
"step": 293
},
{
"epoch": 0.42,
"learning_rate": 9.646376811594204e-06,
"loss": 1.7877,
"step": 294
},
{
"epoch": 0.42,
"learning_rate": 9.644927536231885e-06,
"loss": 1.7719,
"step": 295
},
{
"epoch": 0.43,
"learning_rate": 9.643478260869566e-06,
"loss": 1.8537,
"step": 296
},
{
"epoch": 0.43,
"learning_rate": 9.642028985507247e-06,
"loss": 1.8251,
"step": 297
},
{
"epoch": 0.43,
"learning_rate": 9.640579710144928e-06,
"loss": 1.7511,
"step": 298
},
{
"epoch": 0.43,
"learning_rate": 9.639130434782609e-06,
"loss": 1.7622,
"step": 299
},
{
"epoch": 0.43,
"learning_rate": 9.63768115942029e-06,
"loss": 1.8174,
"step": 300
},
{
"epoch": 0.43,
"learning_rate": 9.636231884057971e-06,
"loss": 1.8452,
"step": 301
},
{
"epoch": 0.43,
"learning_rate": 9.634782608695654e-06,
"loss": 1.7472,
"step": 302
},
{
"epoch": 0.44,
"learning_rate": 9.633333333333335e-06,
"loss": 1.8054,
"step": 303
},
{
"epoch": 0.44,
"learning_rate": 9.631884057971014e-06,
"loss": 1.7485,
"step": 304
},
{
"epoch": 0.44,
"learning_rate": 9.630434782608697e-06,
"loss": 1.804,
"step": 305
},
{
"epoch": 0.44,
"learning_rate": 9.628985507246378e-06,
"loss": 1.7905,
"step": 306
},
{
"epoch": 0.44,
"learning_rate": 9.627536231884059e-06,
"loss": 1.7839,
"step": 307
},
{
"epoch": 0.44,
"learning_rate": 9.62608695652174e-06,
"loss": 1.8166,
"step": 308
},
{
"epoch": 0.44,
"learning_rate": 9.624637681159421e-06,
"loss": 1.7956,
"step": 309
},
{
"epoch": 0.45,
"learning_rate": 9.623188405797102e-06,
"loss": 1.7903,
"step": 310
},
{
"epoch": 0.45,
"learning_rate": 9.621739130434783e-06,
"loss": 1.7935,
"step": 311
},
{
"epoch": 0.45,
"learning_rate": 9.620289855072464e-06,
"loss": 1.7804,
"step": 312
},
{
"epoch": 0.45,
"learning_rate": 9.618840579710147e-06,
"loss": 1.8251,
"step": 313
},
{
"epoch": 0.45,
"learning_rate": 9.617391304347828e-06,
"loss": 1.8077,
"step": 314
},
{
"epoch": 0.45,
"learning_rate": 9.615942028985507e-06,
"loss": 1.804,
"step": 315
},
{
"epoch": 0.45,
"learning_rate": 9.61449275362319e-06,
"loss": 1.8511,
"step": 316
},
{
"epoch": 0.46,
"learning_rate": 9.61304347826087e-06,
"loss": 1.7939,
"step": 317
},
{
"epoch": 0.46,
"learning_rate": 9.611594202898552e-06,
"loss": 1.8087,
"step": 318
},
{
"epoch": 0.46,
"learning_rate": 9.610144927536233e-06,
"loss": 1.808,
"step": 319
},
{
"epoch": 0.46,
"learning_rate": 9.608695652173914e-06,
"loss": 1.828,
"step": 320
},
{
"epoch": 0.46,
"learning_rate": 9.607246376811595e-06,
"loss": 1.7458,
"step": 321
},
{
"epoch": 0.46,
"learning_rate": 9.605797101449276e-06,
"loss": 1.8063,
"step": 322
},
{
"epoch": 0.46,
"learning_rate": 9.604347826086957e-06,
"loss": 1.7583,
"step": 323
},
{
"epoch": 0.47,
"learning_rate": 9.60289855072464e-06,
"loss": 1.7572,
"step": 324
},
{
"epoch": 0.47,
"learning_rate": 9.60144927536232e-06,
"loss": 1.7583,
"step": 325
},
{
"epoch": 0.47,
"learning_rate": 9.600000000000001e-06,
"loss": 1.7465,
"step": 326
},
{
"epoch": 0.47,
"learning_rate": 9.598550724637682e-06,
"loss": 1.7986,
"step": 327
},
{
"epoch": 0.47,
"learning_rate": 9.597101449275363e-06,
"loss": 1.7838,
"step": 328
},
{
"epoch": 0.47,
"learning_rate": 9.595652173913044e-06,
"loss": 1.8339,
"step": 329
},
{
"epoch": 0.47,
"learning_rate": 9.594202898550725e-06,
"loss": 1.7616,
"step": 330
},
{
"epoch": 0.48,
"learning_rate": 9.592753623188406e-06,
"loss": 1.8175,
"step": 331
},
{
"epoch": 0.48,
"learning_rate": 9.591304347826087e-06,
"loss": 1.7892,
"step": 332
},
{
"epoch": 0.48,
"learning_rate": 9.589855072463768e-06,
"loss": 1.8266,
"step": 333
},
{
"epoch": 0.48,
"learning_rate": 9.58840579710145e-06,
"loss": 1.7261,
"step": 334
},
{
"epoch": 0.48,
"learning_rate": 9.586956521739132e-06,
"loss": 1.7498,
"step": 335
},
{
"epoch": 0.48,
"learning_rate": 9.585507246376813e-06,
"loss": 1.7778,
"step": 336
},
{
"epoch": 0.48,
"learning_rate": 9.584057971014494e-06,
"loss": 1.8263,
"step": 337
},
{
"epoch": 0.49,
"learning_rate": 9.582608695652175e-06,
"loss": 1.9147,
"step": 338
},
{
"epoch": 0.49,
"learning_rate": 9.581159420289856e-06,
"loss": 1.7922,
"step": 339
},
{
"epoch": 0.49,
"learning_rate": 9.579710144927537e-06,
"loss": 1.8063,
"step": 340
},
{
"epoch": 0.49,
"learning_rate": 9.578260869565218e-06,
"loss": 1.7929,
"step": 341
},
{
"epoch": 0.49,
"learning_rate": 9.576811594202899e-06,
"loss": 1.788,
"step": 342
},
{
"epoch": 0.49,
"learning_rate": 9.575362318840582e-06,
"loss": 1.7505,
"step": 343
},
{
"epoch": 0.49,
"learning_rate": 9.573913043478261e-06,
"loss": 1.7945,
"step": 344
},
{
"epoch": 0.5,
"learning_rate": 9.572463768115942e-06,
"loss": 1.8055,
"step": 345
},
{
"epoch": 0.5,
"learning_rate": 9.571014492753625e-06,
"loss": 1.7758,
"step": 346
},
{
"epoch": 0.5,
"learning_rate": 9.569565217391306e-06,
"loss": 1.7891,
"step": 347
},
{
"epoch": 0.5,
"learning_rate": 9.568115942028987e-06,
"loss": 1.7642,
"step": 348
},
{
"epoch": 0.5,
"learning_rate": 9.566666666666668e-06,
"loss": 1.8232,
"step": 349
},
{
"epoch": 0.5,
"learning_rate": 9.565217391304349e-06,
"loss": 1.802,
"step": 350
},
{
"epoch": 0.51,
"learning_rate": 9.56376811594203e-06,
"loss": 1.7589,
"step": 351
},
{
"epoch": 0.51,
"learning_rate": 9.56231884057971e-06,
"loss": 1.7147,
"step": 352
},
{
"epoch": 0.51,
"learning_rate": 9.560869565217392e-06,
"loss": 1.7982,
"step": 353
},
{
"epoch": 0.51,
"learning_rate": 9.559420289855074e-06,
"loss": 1.7565,
"step": 354
},
{
"epoch": 0.51,
"learning_rate": 9.557971014492754e-06,
"loss": 1.7405,
"step": 355
},
{
"epoch": 0.51,
"learning_rate": 9.556521739130435e-06,
"loss": 1.7587,
"step": 356
},
{
"epoch": 0.51,
"learning_rate": 9.555072463768117e-06,
"loss": 1.7871,
"step": 357
},
{
"epoch": 0.52,
"learning_rate": 9.553623188405798e-06,
"loss": 1.7503,
"step": 358
},
{
"epoch": 0.52,
"learning_rate": 9.55217391304348e-06,
"loss": 1.7435,
"step": 359
},
{
"epoch": 0.52,
"learning_rate": 9.55072463768116e-06,
"loss": 1.7851,
"step": 360
},
{
"epoch": 0.52,
"learning_rate": 9.549275362318841e-06,
"loss": 1.7478,
"step": 361
},
{
"epoch": 0.52,
"learning_rate": 9.547826086956522e-06,
"loss": 1.82,
"step": 362
},
{
"epoch": 0.52,
"learning_rate": 9.546376811594203e-06,
"loss": 1.7634,
"step": 363
},
{
"epoch": 0.52,
"learning_rate": 9.544927536231884e-06,
"loss": 1.8127,
"step": 364
},
{
"epoch": 0.53,
"learning_rate": 9.543478260869567e-06,
"loss": 1.7303,
"step": 365
},
{
"epoch": 0.53,
"learning_rate": 9.542028985507246e-06,
"loss": 1.8087,
"step": 366
},
{
"epoch": 0.53,
"learning_rate": 9.540579710144927e-06,
"loss": 1.8442,
"step": 367
},
{
"epoch": 0.53,
"learning_rate": 9.53913043478261e-06,
"loss": 1.7595,
"step": 368
},
{
"epoch": 0.53,
"learning_rate": 9.537681159420291e-06,
"loss": 1.7638,
"step": 369
},
{
"epoch": 0.53,
"learning_rate": 9.536231884057972e-06,
"loss": 1.8031,
"step": 370
},
{
"epoch": 0.53,
"learning_rate": 9.534782608695653e-06,
"loss": 1.793,
"step": 371
},
{
"epoch": 0.54,
"learning_rate": 9.533333333333334e-06,
"loss": 1.7709,
"step": 372
},
{
"epoch": 0.54,
"learning_rate": 9.531884057971015e-06,
"loss": 1.7846,
"step": 373
},
{
"epoch": 0.54,
"learning_rate": 9.530434782608696e-06,
"loss": 1.7332,
"step": 374
},
{
"epoch": 0.54,
"learning_rate": 9.528985507246377e-06,
"loss": 1.7891,
"step": 375
},
{
"epoch": 0.54,
"learning_rate": 9.52753623188406e-06,
"loss": 1.7546,
"step": 376
},
{
"epoch": 0.54,
"learning_rate": 9.526086956521739e-06,
"loss": 1.7659,
"step": 377
},
{
"epoch": 0.54,
"learning_rate": 9.524637681159422e-06,
"loss": 1.8536,
"step": 378
},
{
"epoch": 0.55,
"learning_rate": 9.523188405797103e-06,
"loss": 1.7542,
"step": 379
},
{
"epoch": 0.55,
"learning_rate": 9.521739130434784e-06,
"loss": 1.8001,
"step": 380
},
{
"epoch": 0.55,
"learning_rate": 9.520289855072465e-06,
"loss": 1.7604,
"step": 381
},
{
"epoch": 0.55,
"learning_rate": 9.518840579710146e-06,
"loss": 1.7424,
"step": 382
},
{
"epoch": 0.55,
"learning_rate": 9.517391304347827e-06,
"loss": 1.778,
"step": 383
},
{
"epoch": 0.55,
"learning_rate": 9.515942028985508e-06,
"loss": 1.8946,
"step": 384
},
{
"epoch": 0.55,
"learning_rate": 9.514492753623189e-06,
"loss": 1.7935,
"step": 385
},
{
"epoch": 0.56,
"learning_rate": 9.51304347826087e-06,
"loss": 1.817,
"step": 386
},
{
"epoch": 0.56,
"learning_rate": 9.511594202898553e-06,
"loss": 1.754,
"step": 387
},
{
"epoch": 0.56,
"learning_rate": 9.510144927536232e-06,
"loss": 1.7728,
"step": 388
},
{
"epoch": 0.56,
"learning_rate": 9.508695652173915e-06,
"loss": 1.7988,
"step": 389
},
{
"epoch": 0.56,
"learning_rate": 9.507246376811596e-06,
"loss": 1.7612,
"step": 390
},
{
"epoch": 0.56,
"learning_rate": 9.505797101449275e-06,
"loss": 1.7944,
"step": 391
},
{
"epoch": 0.56,
"learning_rate": 9.504347826086958e-06,
"loss": 1.7624,
"step": 392
},
{
"epoch": 0.57,
"learning_rate": 9.502898550724639e-06,
"loss": 1.7135,
"step": 393
},
{
"epoch": 0.57,
"learning_rate": 9.50144927536232e-06,
"loss": 1.8313,
"step": 394
},
{
"epoch": 0.57,
"learning_rate": 9.5e-06,
"loss": 1.7822,
"step": 395
},
{
"epoch": 0.57,
"learning_rate": 9.498550724637682e-06,
"loss": 1.7591,
"step": 396
},
{
"epoch": 0.57,
"learning_rate": 9.497101449275363e-06,
"loss": 1.7854,
"step": 397
},
{
"epoch": 0.57,
"learning_rate": 9.495652173913045e-06,
"loss": 1.7905,
"step": 398
},
{
"epoch": 0.57,
"learning_rate": 9.494202898550725e-06,
"loss": 1.7267,
"step": 399
},
{
"epoch": 0.58,
"learning_rate": 9.492753623188407e-06,
"loss": 1.7959,
"step": 400
},
{
"epoch": 0.58,
"learning_rate": 9.491304347826088e-06,
"loss": 1.7904,
"step": 401
},
{
"epoch": 0.58,
"learning_rate": 9.489855072463768e-06,
"loss": 1.798,
"step": 402
},
{
"epoch": 0.58,
"learning_rate": 9.48840579710145e-06,
"loss": 1.7562,
"step": 403
},
{
"epoch": 0.58,
"learning_rate": 9.486956521739131e-06,
"loss": 1.7432,
"step": 404
},
{
"epoch": 0.58,
"learning_rate": 9.485507246376812e-06,
"loss": 1.7399,
"step": 405
},
{
"epoch": 0.58,
"learning_rate": 9.484057971014493e-06,
"loss": 1.834,
"step": 406
},
{
"epoch": 0.59,
"learning_rate": 9.482608695652174e-06,
"loss": 1.7601,
"step": 407
},
{
"epoch": 0.59,
"learning_rate": 9.481159420289855e-06,
"loss": 1.7044,
"step": 408
},
{
"epoch": 0.59,
"learning_rate": 9.479710144927538e-06,
"loss": 1.7983,
"step": 409
},
{
"epoch": 0.59,
"learning_rate": 9.478260869565217e-06,
"loss": 1.7584,
"step": 410
},
{
"epoch": 0.59,
"learning_rate": 9.4768115942029e-06,
"loss": 1.7515,
"step": 411
},
{
"epoch": 0.59,
"learning_rate": 9.475362318840581e-06,
"loss": 1.7249,
"step": 412
},
{
"epoch": 0.59,
"learning_rate": 9.473913043478262e-06,
"loss": 1.7837,
"step": 413
},
{
"epoch": 0.6,
"learning_rate": 9.472463768115943e-06,
"loss": 1.7713,
"step": 414
},
{
"epoch": 0.6,
"learning_rate": 9.471014492753624e-06,
"loss": 1.7265,
"step": 415
},
{
"epoch": 0.6,
"learning_rate": 9.469565217391305e-06,
"loss": 1.7714,
"step": 416
},
{
"epoch": 0.6,
"learning_rate": 9.468115942028986e-06,
"loss": 1.6978,
"step": 417
},
{
"epoch": 0.6,
"learning_rate": 9.466666666666667e-06,
"loss": 1.7585,
"step": 418
},
{
"epoch": 0.6,
"learning_rate": 9.46521739130435e-06,
"loss": 1.7676,
"step": 419
},
{
"epoch": 0.6,
"learning_rate": 9.46376811594203e-06,
"loss": 1.7695,
"step": 420
},
{
"epoch": 0.61,
"learning_rate": 9.46231884057971e-06,
"loss": 1.7101,
"step": 421
},
{
"epoch": 0.61,
"learning_rate": 9.460869565217393e-06,
"loss": 1.7459,
"step": 422
},
{
"epoch": 0.61,
"learning_rate": 9.459420289855074e-06,
"loss": 1.759,
"step": 423
},
{
"epoch": 0.61,
"learning_rate": 9.457971014492755e-06,
"loss": 1.7008,
"step": 424
},
{
"epoch": 0.61,
"learning_rate": 9.456521739130436e-06,
"loss": 1.7623,
"step": 425
},
{
"epoch": 0.61,
"learning_rate": 9.455072463768117e-06,
"loss": 1.7589,
"step": 426
},
{
"epoch": 0.61,
"learning_rate": 9.453623188405798e-06,
"loss": 1.6821,
"step": 427
},
{
"epoch": 0.62,
"learning_rate": 9.452173913043479e-06,
"loss": 1.7601,
"step": 428
},
{
"epoch": 0.62,
"learning_rate": 9.45072463768116e-06,
"loss": 1.6942,
"step": 429
},
{
"epoch": 0.62,
"learning_rate": 9.449275362318842e-06,
"loss": 1.6735,
"step": 430
},
{
"epoch": 0.62,
"learning_rate": 9.447826086956523e-06,
"loss": 1.6923,
"step": 431
},
{
"epoch": 0.62,
"learning_rate": 9.446376811594203e-06,
"loss": 1.643,
"step": 432
},
{
"epoch": 0.62,
"learning_rate": 9.444927536231885e-06,
"loss": 1.7404,
"step": 433
},
{
"epoch": 0.62,
"learning_rate": 9.443478260869566e-06,
"loss": 1.7223,
"step": 434
},
{
"epoch": 0.63,
"learning_rate": 9.442028985507247e-06,
"loss": 1.7114,
"step": 435
},
{
"epoch": 0.63,
"learning_rate": 9.440579710144928e-06,
"loss": 1.6646,
"step": 436
},
{
"epoch": 0.63,
"learning_rate": 9.43913043478261e-06,
"loss": 1.8709,
"step": 437
},
{
"epoch": 0.63,
"learning_rate": 9.43768115942029e-06,
"loss": 1.6551,
"step": 438
},
{
"epoch": 0.63,
"learning_rate": 9.436231884057971e-06,
"loss": 1.803,
"step": 439
},
{
"epoch": 0.63,
"learning_rate": 9.434782608695652e-06,
"loss": 1.7061,
"step": 440
},
{
"epoch": 0.63,
"learning_rate": 9.433333333333335e-06,
"loss": 1.7442,
"step": 441
},
{
"epoch": 0.64,
"learning_rate": 9.431884057971016e-06,
"loss": 1.5954,
"step": 442
},
{
"epoch": 0.64,
"learning_rate": 9.430434782608695e-06,
"loss": 1.873,
"step": 443
},
{
"epoch": 0.64,
"learning_rate": 9.428985507246378e-06,
"loss": 1.744,
"step": 444
},
{
"epoch": 0.64,
"learning_rate": 9.427536231884059e-06,
"loss": 1.7217,
"step": 445
},
{
"epoch": 0.64,
"learning_rate": 9.42608695652174e-06,
"loss": 1.8362,
"step": 446
},
{
"epoch": 0.64,
"learning_rate": 9.424637681159421e-06,
"loss": 1.5976,
"step": 447
},
{
"epoch": 0.64,
"learning_rate": 9.423188405797102e-06,
"loss": 1.7857,
"step": 448
},
{
"epoch": 0.65,
"learning_rate": 9.421739130434783e-06,
"loss": 1.8564,
"step": 449
},
{
"epoch": 0.65,
"learning_rate": 9.420289855072464e-06,
"loss": 1.6733,
"step": 450
},
{
"epoch": 0.65,
"learning_rate": 9.418840579710145e-06,
"loss": 1.7016,
"step": 451
},
{
"epoch": 0.65,
"learning_rate": 9.417391304347828e-06,
"loss": 1.6946,
"step": 452
},
{
"epoch": 0.65,
"learning_rate": 9.415942028985507e-06,
"loss": 1.7693,
"step": 453
},
{
"epoch": 0.65,
"learning_rate": 9.41449275362319e-06,
"loss": 1.9134,
"step": 454
},
{
"epoch": 0.65,
"learning_rate": 9.41304347826087e-06,
"loss": 1.8033,
"step": 455
},
{
"epoch": 0.66,
"learning_rate": 9.411594202898552e-06,
"loss": 1.8767,
"step": 456
},
{
"epoch": 0.66,
"learning_rate": 9.410144927536233e-06,
"loss": 1.8345,
"step": 457
},
{
"epoch": 0.66,
"learning_rate": 9.408695652173914e-06,
"loss": 1.7909,
"step": 458
},
{
"epoch": 0.66,
"learning_rate": 9.407246376811595e-06,
"loss": 1.7373,
"step": 459
},
{
"epoch": 0.66,
"learning_rate": 9.405797101449276e-06,
"loss": 1.7614,
"step": 460
},
{
"epoch": 0.66,
"learning_rate": 9.404347826086957e-06,
"loss": 1.7336,
"step": 461
},
{
"epoch": 0.66,
"learning_rate": 9.402898550724638e-06,
"loss": 1.7612,
"step": 462
},
{
"epoch": 0.67,
"learning_rate": 9.40144927536232e-06,
"loss": 1.6613,
"step": 463
},
{
"epoch": 0.67,
"learning_rate": 9.4e-06,
"loss": 1.6221,
"step": 464
},
{
"epoch": 0.67,
"learning_rate": 9.398550724637682e-06,
"loss": 1.6708,
"step": 465
},
{
"epoch": 0.67,
"learning_rate": 9.397101449275363e-06,
"loss": 1.7306,
"step": 466
},
{
"epoch": 0.67,
"learning_rate": 9.395652173913044e-06,
"loss": 1.6663,
"step": 467
},
{
"epoch": 0.67,
"learning_rate": 9.394202898550725e-06,
"loss": 1.6109,
"step": 468
},
{
"epoch": 0.67,
"learning_rate": 9.392753623188406e-06,
"loss": 1.7376,
"step": 469
},
{
"epoch": 0.68,
"learning_rate": 9.391304347826087e-06,
"loss": 1.6614,
"step": 470
},
{
"epoch": 0.68,
"learning_rate": 9.38985507246377e-06,
"loss": 1.7024,
"step": 471
},
{
"epoch": 0.68,
"learning_rate": 9.38840579710145e-06,
"loss": 1.7758,
"step": 472
},
{
"epoch": 0.68,
"learning_rate": 9.38695652173913e-06,
"loss": 1.8538,
"step": 473
},
{
"epoch": 0.68,
"learning_rate": 9.385507246376813e-06,
"loss": 1.7568,
"step": 474
},
{
"epoch": 0.68,
"learning_rate": 9.384057971014492e-06,
"loss": 1.671,
"step": 475
},
{
"epoch": 0.68,
"learning_rate": 9.382608695652175e-06,
"loss": 1.7339,
"step": 476
},
{
"epoch": 0.69,
"learning_rate": 9.381159420289856e-06,
"loss": 1.8321,
"step": 477
},
{
"epoch": 0.69,
"learning_rate": 9.379710144927537e-06,
"loss": 1.7613,
"step": 478
},
{
"epoch": 0.69,
"learning_rate": 9.378260869565218e-06,
"loss": 1.7558,
"step": 479
},
{
"epoch": 0.69,
"learning_rate": 9.3768115942029e-06,
"loss": 1.7601,
"step": 480
},
{
"epoch": 0.69,
"learning_rate": 9.37536231884058e-06,
"loss": 1.6581,
"step": 481
},
{
"epoch": 0.69,
"learning_rate": 9.373913043478263e-06,
"loss": 1.7532,
"step": 482
},
{
"epoch": 0.69,
"learning_rate": 9.372463768115942e-06,
"loss": 1.8625,
"step": 483
},
{
"epoch": 0.7,
"learning_rate": 9.371014492753623e-06,
"loss": 1.7552,
"step": 484
},
{
"epoch": 0.7,
"learning_rate": 9.369565217391306e-06,
"loss": 1.6593,
"step": 485
},
{
"epoch": 0.7,
"learning_rate": 9.368115942028985e-06,
"loss": 1.7272,
"step": 486
},
{
"epoch": 0.7,
"learning_rate": 9.366666666666668e-06,
"loss": 1.6921,
"step": 487
},
{
"epoch": 0.7,
"learning_rate": 9.365217391304349e-06,
"loss": 1.9005,
"step": 488
},
{
"epoch": 0.7,
"learning_rate": 9.36376811594203e-06,
"loss": 1.6615,
"step": 489
},
{
"epoch": 0.71,
"learning_rate": 9.362318840579711e-06,
"loss": 1.6557,
"step": 490
},
{
"epoch": 0.71,
"learning_rate": 9.360869565217392e-06,
"loss": 1.7617,
"step": 491
},
{
"epoch": 0.71,
"learning_rate": 9.359420289855073e-06,
"loss": 1.6262,
"step": 492
},
{
"epoch": 0.71,
"learning_rate": 9.357971014492756e-06,
"loss": 1.6038,
"step": 493
},
{
"epoch": 0.71,
"learning_rate": 9.356521739130435e-06,
"loss": 1.7017,
"step": 494
},
{
"epoch": 0.71,
"learning_rate": 9.355072463768116e-06,
"loss": 1.6771,
"step": 495
},
{
"epoch": 0.71,
"learning_rate": 9.353623188405799e-06,
"loss": 1.7926,
"step": 496
},
{
"epoch": 0.72,
"learning_rate": 9.352173913043478e-06,
"loss": 1.7765,
"step": 497
},
{
"epoch": 0.72,
"learning_rate": 9.35072463768116e-06,
"loss": 1.6132,
"step": 498
},
{
"epoch": 0.72,
"learning_rate": 9.349275362318842e-06,
"loss": 1.7929,
"step": 499
},
{
"epoch": 0.72,
"learning_rate": 9.347826086956523e-06,
"loss": 1.7747,
"step": 500
},
{
"epoch": 0.72,
"learning_rate": 9.346376811594204e-06,
"loss": 1.7371,
"step": 501
},
{
"epoch": 0.72,
"learning_rate": 9.344927536231885e-06,
"loss": 1.7765,
"step": 502
},
{
"epoch": 0.72,
"learning_rate": 9.343478260869566e-06,
"loss": 1.7343,
"step": 503
},
{
"epoch": 0.73,
"learning_rate": 9.342028985507248e-06,
"loss": 1.7641,
"step": 504
},
{
"epoch": 0.73,
"learning_rate": 9.340579710144928e-06,
"loss": 1.66,
"step": 505
},
{
"epoch": 0.73,
"learning_rate": 9.33913043478261e-06,
"loss": 1.4669,
"step": 506
},
{
"epoch": 0.73,
"learning_rate": 9.337681159420291e-06,
"loss": 1.6771,
"step": 507
},
{
"epoch": 0.73,
"learning_rate": 9.33623188405797e-06,
"loss": 1.7796,
"step": 508
},
{
"epoch": 0.73,
"learning_rate": 9.334782608695653e-06,
"loss": 1.6644,
"step": 509
},
{
"epoch": 0.73,
"learning_rate": 9.333333333333334e-06,
"loss": 1.6729,
"step": 510
},
{
"epoch": 0.74,
"learning_rate": 9.331884057971015e-06,
"loss": 1.5036,
"step": 511
},
{
"epoch": 0.74,
"learning_rate": 9.330434782608696e-06,
"loss": 1.7212,
"step": 512
},
{
"epoch": 0.74,
"learning_rate": 9.328985507246377e-06,
"loss": 1.7362,
"step": 513
},
{
"epoch": 0.74,
"learning_rate": 9.327536231884058e-06,
"loss": 1.7772,
"step": 514
},
{
"epoch": 0.74,
"learning_rate": 9.32608695652174e-06,
"loss": 1.6804,
"step": 515
},
{
"epoch": 0.74,
"learning_rate": 9.32463768115942e-06,
"loss": 1.6967,
"step": 516
},
{
"epoch": 0.74,
"learning_rate": 9.323188405797103e-06,
"loss": 1.9051,
"step": 517
},
{
"epoch": 0.75,
"learning_rate": 9.321739130434784e-06,
"loss": 1.7633,
"step": 518
},
{
"epoch": 0.75,
"learning_rate": 9.320289855072463e-06,
"loss": 1.5182,
"step": 519
},
{
"epoch": 0.75,
"learning_rate": 9.318840579710146e-06,
"loss": 1.7184,
"step": 520
},
{
"epoch": 0.75,
"learning_rate": 9.317391304347827e-06,
"loss": 2.2586,
"step": 521
},
{
"epoch": 0.75,
"learning_rate": 9.315942028985508e-06,
"loss": 1.5746,
"step": 522
},
{
"epoch": 0.75,
"learning_rate": 9.314492753623189e-06,
"loss": 1.8775,
"step": 523
},
{
"epoch": 0.75,
"learning_rate": 9.31304347826087e-06,
"loss": 1.607,
"step": 524
},
{
"epoch": 0.76,
"learning_rate": 9.311594202898551e-06,
"loss": 1.8892,
"step": 525
},
{
"epoch": 0.76,
"learning_rate": 9.310144927536232e-06,
"loss": 1.7163,
"step": 526
},
{
"epoch": 0.76,
"learning_rate": 9.308695652173913e-06,
"loss": 1.7406,
"step": 527
},
{
"epoch": 0.76,
"learning_rate": 9.307246376811596e-06,
"loss": 1.8209,
"step": 528
},
{
"epoch": 0.76,
"learning_rate": 9.305797101449277e-06,
"loss": 2.2019,
"step": 529
},
{
"epoch": 0.76,
"learning_rate": 9.304347826086956e-06,
"loss": 1.6532,
"step": 530
},
{
"epoch": 0.76,
"learning_rate": 9.302898550724639e-06,
"loss": 1.7642,
"step": 531
},
{
"epoch": 0.77,
"learning_rate": 9.30144927536232e-06,
"loss": 1.734,
"step": 532
},
{
"epoch": 0.77,
"learning_rate": 9.3e-06,
"loss": 1.7189,
"step": 533
},
{
"epoch": 0.77,
"learning_rate": 9.298550724637682e-06,
"loss": 1.6603,
"step": 534
},
{
"epoch": 0.77,
"learning_rate": 9.297101449275363e-06,
"loss": 1.8562,
"step": 535
},
{
"epoch": 0.77,
"learning_rate": 9.295652173913044e-06,
"loss": 1.5545,
"step": 536
},
{
"epoch": 0.77,
"learning_rate": 9.294202898550725e-06,
"loss": 1.7548,
"step": 537
},
{
"epoch": 0.77,
"learning_rate": 9.292753623188406e-06,
"loss": 1.6227,
"step": 538
},
{
"epoch": 0.78,
"learning_rate": 9.291304347826088e-06,
"loss": 1.5726,
"step": 539
},
{
"epoch": 0.78,
"learning_rate": 9.28985507246377e-06,
"loss": 1.8771,
"step": 540
},
{
"epoch": 0.78,
"learning_rate": 9.28840579710145e-06,
"loss": 1.773,
"step": 541
},
{
"epoch": 0.78,
"learning_rate": 9.286956521739131e-06,
"loss": 1.7309,
"step": 542
},
{
"epoch": 0.78,
"learning_rate": 9.285507246376812e-06,
"loss": 1.5423,
"step": 543
},
{
"epoch": 0.78,
"learning_rate": 9.284057971014493e-06,
"loss": 1.7325,
"step": 544
},
{
"epoch": 0.78,
"learning_rate": 9.282608695652174e-06,
"loss": 1.8245,
"step": 545
},
{
"epoch": 0.79,
"learning_rate": 9.281159420289855e-06,
"loss": 1.8336,
"step": 546
},
{
"epoch": 0.79,
"learning_rate": 9.279710144927536e-06,
"loss": 1.6275,
"step": 547
},
{
"epoch": 0.79,
"learning_rate": 9.278260869565217e-06,
"loss": 1.7493,
"step": 548
},
{
"epoch": 0.79,
"learning_rate": 9.276811594202898e-06,
"loss": 1.7878,
"step": 549
},
{
"epoch": 0.79,
"learning_rate": 9.275362318840581e-06,
"loss": 1.8985,
"step": 550
},
{
"epoch": 0.79,
"learning_rate": 9.273913043478262e-06,
"loss": 1.5902,
"step": 551
},
{
"epoch": 0.79,
"learning_rate": 9.272463768115943e-06,
"loss": 1.6755,
"step": 552
},
{
"epoch": 0.8,
"learning_rate": 9.271014492753624e-06,
"loss": 1.4542,
"step": 553
},
{
"epoch": 0.8,
"learning_rate": 9.269565217391305e-06,
"loss": 2.0015,
"step": 554
},
{
"epoch": 0.8,
"learning_rate": 9.268115942028986e-06,
"loss": 1.6533,
"step": 555
},
{
"epoch": 0.8,
"learning_rate": 9.266666666666667e-06,
"loss": 1.3897,
"step": 556
},
{
"epoch": 0.8,
"learning_rate": 9.265217391304348e-06,
"loss": 1.5342,
"step": 557
},
{
"epoch": 0.8,
"learning_rate": 9.263768115942031e-06,
"loss": 1.5419,
"step": 558
},
{
"epoch": 0.8,
"learning_rate": 9.26231884057971e-06,
"loss": 1.6568,
"step": 559
},
{
"epoch": 0.81,
"learning_rate": 9.260869565217391e-06,
"loss": 1.6842,
"step": 560
},
{
"epoch": 0.81,
"learning_rate": 9.259420289855074e-06,
"loss": 1.6922,
"step": 561
},
{
"epoch": 0.81,
"learning_rate": 9.257971014492755e-06,
"loss": 1.7124,
"step": 562
},
{
"epoch": 0.81,
"learning_rate": 9.256521739130436e-06,
"loss": 1.6837,
"step": 563
},
{
"epoch": 0.81,
"learning_rate": 9.255072463768117e-06,
"loss": 1.6708,
"step": 564
},
{
"epoch": 0.81,
"learning_rate": 9.253623188405798e-06,
"loss": 1.6237,
"step": 565
},
{
"epoch": 0.81,
"learning_rate": 9.252173913043479e-06,
"loss": 1.6164,
"step": 566
},
{
"epoch": 0.82,
"learning_rate": 9.25072463768116e-06,
"loss": 2.0735,
"step": 567
},
{
"epoch": 0.82,
"learning_rate": 9.249275362318841e-06,
"loss": 1.7095,
"step": 568
},
{
"epoch": 0.82,
"learning_rate": 9.247826086956524e-06,
"loss": 1.6885,
"step": 569
},
{
"epoch": 0.82,
"learning_rate": 9.246376811594203e-06,
"loss": 1.6518,
"step": 570
},
{
"epoch": 0.82,
"learning_rate": 9.244927536231884e-06,
"loss": 1.6327,
"step": 571
},
{
"epoch": 0.82,
"learning_rate": 9.243478260869567e-06,
"loss": 1.6598,
"step": 572
},
{
"epoch": 0.82,
"learning_rate": 9.242028985507248e-06,
"loss": 1.6891,
"step": 573
},
{
"epoch": 0.83,
"learning_rate": 9.240579710144929e-06,
"loss": 1.6103,
"step": 574
},
{
"epoch": 0.83,
"learning_rate": 9.23913043478261e-06,
"loss": 1.5785,
"step": 575
},
{
"epoch": 0.83,
"learning_rate": 9.23768115942029e-06,
"loss": 1.9188,
"step": 576
},
{
"epoch": 0.83,
"learning_rate": 9.236231884057972e-06,
"loss": 1.575,
"step": 577
},
{
"epoch": 0.83,
"learning_rate": 9.234782608695653e-06,
"loss": 2.0226,
"step": 578
},
{
"epoch": 0.83,
"learning_rate": 9.233333333333334e-06,
"loss": 1.6416,
"step": 579
},
{
"epoch": 0.83,
"learning_rate": 9.231884057971016e-06,
"loss": 1.7377,
"step": 580
},
{
"epoch": 0.84,
"learning_rate": 9.230434782608696e-06,
"loss": 1.5323,
"step": 581
},
{
"epoch": 0.84,
"learning_rate": 9.228985507246377e-06,
"loss": 1.6688,
"step": 582
},
{
"epoch": 0.84,
"learning_rate": 9.22753623188406e-06,
"loss": 1.6499,
"step": 583
},
{
"epoch": 0.84,
"learning_rate": 9.22608695652174e-06,
"loss": 1.6245,
"step": 584
},
{
"epoch": 0.84,
"learning_rate": 9.224637681159421e-06,
"loss": 1.7317,
"step": 585
},
{
"epoch": 0.84,
"learning_rate": 9.223188405797102e-06,
"loss": 1.6601,
"step": 586
},
{
"epoch": 0.84,
"learning_rate": 9.221739130434783e-06,
"loss": 1.6956,
"step": 587
},
{
"epoch": 0.85,
"learning_rate": 9.220289855072464e-06,
"loss": 1.6712,
"step": 588
},
{
"epoch": 0.85,
"learning_rate": 9.218840579710145e-06,
"loss": 1.6764,
"step": 589
},
{
"epoch": 0.85,
"learning_rate": 9.217391304347826e-06,
"loss": 1.7504,
"step": 590
},
{
"epoch": 0.85,
"learning_rate": 9.215942028985509e-06,
"loss": 1.6428,
"step": 591
},
{
"epoch": 0.85,
"learning_rate": 9.214492753623188e-06,
"loss": 1.9458,
"step": 592
},
{
"epoch": 0.85,
"learning_rate": 9.213043478260871e-06,
"loss": 1.6619,
"step": 593
},
{
"epoch": 0.85,
"learning_rate": 9.211594202898552e-06,
"loss": 1.5026,
"step": 594
},
{
"epoch": 0.86,
"learning_rate": 9.210144927536233e-06,
"loss": 1.9632,
"step": 595
},
{
"epoch": 0.86,
"learning_rate": 9.208695652173914e-06,
"loss": 1.8338,
"step": 596
},
{
"epoch": 0.86,
"learning_rate": 9.207246376811595e-06,
"loss": 1.5195,
"step": 597
},
{
"epoch": 0.86,
"learning_rate": 9.205797101449276e-06,
"loss": 1.9442,
"step": 598
},
{
"epoch": 0.86,
"learning_rate": 9.204347826086957e-06,
"loss": 1.6933,
"step": 599
},
{
"epoch": 0.86,
"learning_rate": 9.202898550724638e-06,
"loss": 1.6615,
"step": 600
},
{
"epoch": 0.86,
"learning_rate": 9.201449275362319e-06,
"loss": 1.3086,
"step": 601
},
{
"epoch": 0.87,
"learning_rate": 9.200000000000002e-06,
"loss": 1.6395,
"step": 602
},
{
"epoch": 0.87,
"learning_rate": 9.198550724637681e-06,
"loss": 1.692,
"step": 603
},
{
"epoch": 0.87,
"learning_rate": 9.197101449275364e-06,
"loss": 1.3012,
"step": 604
},
{
"epoch": 0.87,
"learning_rate": 9.195652173913045e-06,
"loss": 1.4745,
"step": 605
},
{
"epoch": 0.87,
"learning_rate": 9.194202898550726e-06,
"loss": 1.665,
"step": 606
},
{
"epoch": 0.87,
"learning_rate": 9.192753623188407e-06,
"loss": 1.9095,
"step": 607
},
{
"epoch": 0.87,
"learning_rate": 9.191304347826088e-06,
"loss": 1.9521,
"step": 608
},
{
"epoch": 0.88,
"learning_rate": 9.189855072463769e-06,
"loss": 1.7353,
"step": 609
},
{
"epoch": 0.88,
"learning_rate": 9.18840579710145e-06,
"loss": 1.6643,
"step": 610
},
{
"epoch": 0.88,
"learning_rate": 9.18695652173913e-06,
"loss": 1.4785,
"step": 611
},
{
"epoch": 0.88,
"learning_rate": 9.185507246376812e-06,
"loss": 1.6211,
"step": 612
},
{
"epoch": 0.88,
"learning_rate": 9.184057971014494e-06,
"loss": 1.9069,
"step": 613
},
{
"epoch": 0.88,
"learning_rate": 9.182608695652174e-06,
"loss": 1.7239,
"step": 614
},
{
"epoch": 0.88,
"learning_rate": 9.181159420289856e-06,
"loss": 1.918,
"step": 615
},
{
"epoch": 0.89,
"learning_rate": 9.179710144927537e-06,
"loss": 1.3954,
"step": 616
},
{
"epoch": 0.89,
"learning_rate": 9.178260869565218e-06,
"loss": 1.6497,
"step": 617
},
{
"epoch": 0.89,
"learning_rate": 9.1768115942029e-06,
"loss": 1.7112,
"step": 618
},
{
"epoch": 0.89,
"learning_rate": 9.17536231884058e-06,
"loss": 1.3031,
"step": 619
},
{
"epoch": 0.89,
"learning_rate": 9.173913043478261e-06,
"loss": 1.6014,
"step": 620
},
{
"epoch": 0.89,
"learning_rate": 9.172463768115942e-06,
"loss": 1.5809,
"step": 621
},
{
"epoch": 0.89,
"learning_rate": 9.171014492753623e-06,
"loss": 1.6354,
"step": 622
},
{
"epoch": 0.9,
"learning_rate": 9.169565217391304e-06,
"loss": 1.5894,
"step": 623
},
{
"epoch": 0.9,
"learning_rate": 9.168115942028987e-06,
"loss": 1.5135,
"step": 624
},
{
"epoch": 0.9,
"learning_rate": 9.166666666666666e-06,
"loss": 1.802,
"step": 625
},
{
"epoch": 0.9,
"learning_rate": 9.165217391304349e-06,
"loss": 1.8681,
"step": 626
},
{
"epoch": 0.9,
"learning_rate": 9.16376811594203e-06,
"loss": 1.3531,
"step": 627
},
{
"epoch": 0.9,
"learning_rate": 9.162318840579711e-06,
"loss": 1.4468,
"step": 628
},
{
"epoch": 0.91,
"learning_rate": 9.160869565217392e-06,
"loss": 1.6508,
"step": 629
},
{
"epoch": 0.91,
"learning_rate": 9.159420289855073e-06,
"loss": 1.2979,
"step": 630
},
{
"epoch": 0.91,
"learning_rate": 9.157971014492754e-06,
"loss": 1.7596,
"step": 631
},
{
"epoch": 0.91,
"learning_rate": 9.156521739130435e-06,
"loss": 1.7862,
"step": 632
},
{
"epoch": 0.91,
"learning_rate": 9.155072463768116e-06,
"loss": 1.7375,
"step": 633
},
{
"epoch": 0.91,
"learning_rate": 9.153623188405799e-06,
"loss": 1.6296,
"step": 634
},
{
"epoch": 0.91,
"learning_rate": 9.15217391304348e-06,
"loss": 1.8474,
"step": 635
},
{
"epoch": 0.92,
"learning_rate": 9.150724637681159e-06,
"loss": 1.5052,
"step": 636
},
{
"epoch": 0.92,
"learning_rate": 9.149275362318842e-06,
"loss": 1.6135,
"step": 637
},
{
"epoch": 0.92,
"learning_rate": 9.147826086956523e-06,
"loss": 1.7252,
"step": 638
},
{
"epoch": 0.92,
"learning_rate": 9.146376811594204e-06,
"loss": 1.7536,
"step": 639
},
{
"epoch": 0.92,
"learning_rate": 9.144927536231885e-06,
"loss": 1.469,
"step": 640
},
{
"epoch": 0.92,
"learning_rate": 9.143478260869566e-06,
"loss": 1.6801,
"step": 641
},
{
"epoch": 0.92,
"learning_rate": 9.142028985507247e-06,
"loss": 1.6273,
"step": 642
},
{
"epoch": 0.93,
"learning_rate": 9.140579710144928e-06,
"loss": 1.6722,
"step": 643
},
{
"epoch": 0.93,
"learning_rate": 9.139130434782609e-06,
"loss": 1.7045,
"step": 644
},
{
"epoch": 0.93,
"learning_rate": 9.137681159420292e-06,
"loss": 1.4982,
"step": 645
},
{
"epoch": 0.93,
"learning_rate": 9.136231884057973e-06,
"loss": 1.6666,
"step": 646
},
{
"epoch": 0.93,
"learning_rate": 9.134782608695652e-06,
"loss": 1.4154,
"step": 647
},
{
"epoch": 0.93,
"learning_rate": 9.133333333333335e-06,
"loss": 1.4674,
"step": 648
},
{
"epoch": 0.93,
"learning_rate": 9.131884057971016e-06,
"loss": 1.6787,
"step": 649
},
{
"epoch": 0.94,
"learning_rate": 9.130434782608697e-06,
"loss": 1.7374,
"step": 650
},
{
"epoch": 0.94,
"learning_rate": 9.128985507246378e-06,
"loss": 2.0465,
"step": 651
},
{
"epoch": 0.94,
"learning_rate": 9.127536231884059e-06,
"loss": 1.6424,
"step": 652
},
{
"epoch": 0.94,
"learning_rate": 9.12608695652174e-06,
"loss": 1.6249,
"step": 653
},
{
"epoch": 0.94,
"learning_rate": 9.12463768115942e-06,
"loss": 1.6703,
"step": 654
},
{
"epoch": 0.94,
"learning_rate": 9.123188405797102e-06,
"loss": 1.8832,
"step": 655
},
{
"epoch": 0.94,
"learning_rate": 9.121739130434784e-06,
"loss": 1.6985,
"step": 656
},
{
"epoch": 0.95,
"learning_rate": 9.120289855072465e-06,
"loss": 1.9327,
"step": 657
},
{
"epoch": 0.95,
"learning_rate": 9.118840579710145e-06,
"loss": 1.6431,
"step": 658
},
{
"epoch": 0.95,
"learning_rate": 9.117391304347827e-06,
"loss": 1.3707,
"step": 659
},
{
"epoch": 0.95,
"learning_rate": 9.115942028985508e-06,
"loss": 1.671,
"step": 660
},
{
"epoch": 0.95,
"learning_rate": 9.11449275362319e-06,
"loss": 1.6511,
"step": 661
},
{
"epoch": 0.95,
"learning_rate": 9.11304347826087e-06,
"loss": 2.3661,
"step": 662
},
{
"epoch": 0.95,
"learning_rate": 9.111594202898551e-06,
"loss": 1.4736,
"step": 663
},
{
"epoch": 0.96,
"learning_rate": 9.110144927536232e-06,
"loss": 1.702,
"step": 664
},
{
"epoch": 0.96,
"learning_rate": 9.108695652173913e-06,
"loss": 1.6404,
"step": 665
},
{
"epoch": 0.96,
"learning_rate": 9.107246376811594e-06,
"loss": 1.7918,
"step": 666
},
{
"epoch": 0.96,
"learning_rate": 9.105797101449277e-06,
"loss": 1.6485,
"step": 667
},
{
"epoch": 0.96,
"learning_rate": 9.104347826086958e-06,
"loss": 1.6458,
"step": 668
},
{
"epoch": 0.96,
"learning_rate": 9.102898550724639e-06,
"loss": 1.73,
"step": 669
},
{
"epoch": 0.96,
"learning_rate": 9.10144927536232e-06,
"loss": 1.6779,
"step": 670
},
{
"epoch": 0.97,
"learning_rate": 9.100000000000001e-06,
"loss": 1.7368,
"step": 671
},
{
"epoch": 0.97,
"learning_rate": 9.098550724637682e-06,
"loss": 1.6192,
"step": 672
},
{
"epoch": 0.97,
"learning_rate": 9.097101449275363e-06,
"loss": 1.6573,
"step": 673
},
{
"epoch": 0.97,
"learning_rate": 9.095652173913044e-06,
"loss": 1.6685,
"step": 674
},
{
"epoch": 0.97,
"learning_rate": 9.094202898550725e-06,
"loss": 1.6459,
"step": 675
},
{
"epoch": 0.97,
"learning_rate": 9.092753623188406e-06,
"loss": 1.96,
"step": 676
},
{
"epoch": 0.97,
"learning_rate": 9.091304347826087e-06,
"loss": 1.2422,
"step": 677
},
{
"epoch": 0.98,
"learning_rate": 9.08985507246377e-06,
"loss": 1.2432,
"step": 678
},
{
"epoch": 0.98,
"learning_rate": 9.08840579710145e-06,
"loss": 2.4282,
"step": 679
},
{
"epoch": 0.98,
"learning_rate": 9.086956521739132e-06,
"loss": 1.651,
"step": 680
},
{
"epoch": 0.98,
"learning_rate": 9.085507246376813e-06,
"loss": 1.6602,
"step": 681
},
{
"epoch": 0.98,
"learning_rate": 9.084057971014494e-06,
"loss": 1.4327,
"step": 682
},
{
"epoch": 0.98,
"learning_rate": 9.082608695652175e-06,
"loss": 1.4728,
"step": 683
},
{
"epoch": 0.98,
"learning_rate": 9.081159420289856e-06,
"loss": 1.677,
"step": 684
},
{
"epoch": 0.99,
"learning_rate": 9.079710144927537e-06,
"loss": 1.7016,
"step": 685
},
{
"epoch": 0.99,
"learning_rate": 9.07826086956522e-06,
"loss": 1.7507,
"step": 686
},
{
"epoch": 0.99,
"learning_rate": 9.076811594202899e-06,
"loss": 1.5511,
"step": 687
},
{
"epoch": 0.99,
"learning_rate": 9.07536231884058e-06,
"loss": 1.4525,
"step": 688
},
{
"epoch": 0.99,
"learning_rate": 9.073913043478262e-06,
"loss": 1.6997,
"step": 689
},
{
"epoch": 0.99,
"learning_rate": 9.072463768115943e-06,
"loss": 1.6878,
"step": 690
},
{
"epoch": 0.99,
"learning_rate": 9.071014492753624e-06,
"loss": 1.6826,
"step": 691
},
{
"epoch": 1.0,
"learning_rate": 9.069565217391305e-06,
"loss": 1.4774,
"step": 692
},
{
"epoch": 1.0,
"learning_rate": 9.068115942028986e-06,
"loss": 1.7614,
"step": 693
},
{
"epoch": 1.0,
"learning_rate": 9.066666666666667e-06,
"loss": 1.6491,
"step": 694
},
{
"epoch": 1.0,
"learning_rate": 9.065217391304348e-06,
"loss": 1.3832,
"step": 695
},
{
"epoch": 1.0,
"eval_accuracy": 0.3107913669064748,
"eval_loss": 1.560390591621399,
"eval_roc_auc": 0.7616650252630864,
"eval_runtime": 84.9159,
"eval_samples_per_second": 8.185,
"eval_steps_per_second": 2.049,
"step": 695
}
],
"max_steps": 6950,
"num_train_epochs": 10,
"total_flos": 2.01838354884096e+17,
"trial_name": null,
"trial_params": null
}