TransCore-M / trainer_state.json
PCIResearch's picture
Upload 11 files
8496cd6 verified
raw
history blame
314 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"global_step": 2598,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2.564102564102564e-07,
"loss": 0.648,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 5.128205128205128e-07,
"loss": 1.7349,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 7.692307692307694e-07,
"loss": 1.7002,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 1.0256410256410257e-06,
"loss": 1.686,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 1.282051282051282e-06,
"loss": 1.8245,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 1.5384615384615387e-06,
"loss": 1.6814,
"step": 6
},
{
"epoch": 0.0,
"learning_rate": 1.794871794871795e-06,
"loss": 1.78,
"step": 7
},
{
"epoch": 0.0,
"learning_rate": 2.0512820512820513e-06,
"loss": 1.6451,
"step": 8
},
{
"epoch": 0.0,
"learning_rate": 2.307692307692308e-06,
"loss": 0.6627,
"step": 9
},
{
"epoch": 0.0,
"learning_rate": 2.564102564102564e-06,
"loss": 1.5181,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 2.8205128205128207e-06,
"loss": 1.4828,
"step": 11
},
{
"epoch": 0.0,
"learning_rate": 3.0769230769230774e-06,
"loss": 1.45,
"step": 12
},
{
"epoch": 0.01,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.4031,
"step": 13
},
{
"epoch": 0.01,
"learning_rate": 3.58974358974359e-06,
"loss": 1.3097,
"step": 14
},
{
"epoch": 0.01,
"learning_rate": 3.846153846153847e-06,
"loss": 1.2769,
"step": 15
},
{
"epoch": 0.01,
"learning_rate": 4.102564102564103e-06,
"loss": 1.2231,
"step": 16
},
{
"epoch": 0.01,
"learning_rate": 4.358974358974359e-06,
"loss": 0.6147,
"step": 17
},
{
"epoch": 0.01,
"learning_rate": 4.615384615384616e-06,
"loss": 1.2407,
"step": 18
},
{
"epoch": 0.01,
"learning_rate": 4.871794871794872e-06,
"loss": 1.1589,
"step": 19
},
{
"epoch": 0.01,
"learning_rate": 5.128205128205128e-06,
"loss": 1.1669,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 5.384615384615385e-06,
"loss": 1.2003,
"step": 21
},
{
"epoch": 0.01,
"learning_rate": 5.641025641025641e-06,
"loss": 1.1342,
"step": 22
},
{
"epoch": 0.01,
"learning_rate": 5.897435897435898e-06,
"loss": 1.2334,
"step": 23
},
{
"epoch": 0.01,
"learning_rate": 6.153846153846155e-06,
"loss": 1.166,
"step": 24
},
{
"epoch": 0.01,
"learning_rate": 6.410256410256412e-06,
"loss": 1.1219,
"step": 25
},
{
"epoch": 0.01,
"learning_rate": 6.666666666666667e-06,
"loss": 1.0922,
"step": 26
},
{
"epoch": 0.01,
"learning_rate": 6.923076923076923e-06,
"loss": 1.1758,
"step": 27
},
{
"epoch": 0.01,
"learning_rate": 7.17948717948718e-06,
"loss": 1.0372,
"step": 28
},
{
"epoch": 0.01,
"learning_rate": 7.435897435897437e-06,
"loss": 1.1278,
"step": 29
},
{
"epoch": 0.01,
"learning_rate": 7.692307692307694e-06,
"loss": 1.08,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 7.948717948717949e-06,
"loss": 1.127,
"step": 31
},
{
"epoch": 0.01,
"learning_rate": 8.205128205128205e-06,
"loss": 1.0931,
"step": 32
},
{
"epoch": 0.01,
"learning_rate": 8.461538461538462e-06,
"loss": 1.0967,
"step": 33
},
{
"epoch": 0.01,
"learning_rate": 8.717948717948719e-06,
"loss": 1.0641,
"step": 34
},
{
"epoch": 0.01,
"learning_rate": 8.974358974358976e-06,
"loss": 1.0469,
"step": 35
},
{
"epoch": 0.01,
"learning_rate": 9.230769230769232e-06,
"loss": 0.6605,
"step": 36
},
{
"epoch": 0.01,
"learning_rate": 9.487179487179487e-06,
"loss": 1.0509,
"step": 37
},
{
"epoch": 0.01,
"learning_rate": 9.743589743589744e-06,
"loss": 1.0466,
"step": 38
},
{
"epoch": 0.02,
"learning_rate": 1e-05,
"loss": 1.0597,
"step": 39
},
{
"epoch": 0.02,
"learning_rate": 1.0256410256410256e-05,
"loss": 1.0216,
"step": 40
},
{
"epoch": 0.02,
"learning_rate": 1.0512820512820514e-05,
"loss": 1.0282,
"step": 41
},
{
"epoch": 0.02,
"learning_rate": 1.076923076923077e-05,
"loss": 1.0795,
"step": 42
},
{
"epoch": 0.02,
"learning_rate": 1.1025641025641028e-05,
"loss": 1.0704,
"step": 43
},
{
"epoch": 0.02,
"learning_rate": 1.1282051282051283e-05,
"loss": 1.0148,
"step": 44
},
{
"epoch": 0.02,
"learning_rate": 1.1538461538461538e-05,
"loss": 1.0049,
"step": 45
},
{
"epoch": 0.02,
"learning_rate": 1.1794871794871796e-05,
"loss": 1.007,
"step": 46
},
{
"epoch": 0.02,
"learning_rate": 1.2051282051282051e-05,
"loss": 1.0287,
"step": 47
},
{
"epoch": 0.02,
"learning_rate": 1.230769230769231e-05,
"loss": 1.0209,
"step": 48
},
{
"epoch": 0.02,
"learning_rate": 1.2564102564102565e-05,
"loss": 0.9719,
"step": 49
},
{
"epoch": 0.02,
"learning_rate": 1.2820512820512823e-05,
"loss": 1.0209,
"step": 50
},
{
"epoch": 0.02,
"learning_rate": 1.3076923076923078e-05,
"loss": 1.0162,
"step": 51
},
{
"epoch": 0.02,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.9977,
"step": 52
},
{
"epoch": 0.02,
"learning_rate": 1.3589743589743592e-05,
"loss": 0.6224,
"step": 53
},
{
"epoch": 0.02,
"learning_rate": 1.3846153846153847e-05,
"loss": 0.9841,
"step": 54
},
{
"epoch": 0.02,
"learning_rate": 1.4102564102564105e-05,
"loss": 0.9982,
"step": 55
},
{
"epoch": 0.02,
"learning_rate": 1.435897435897436e-05,
"loss": 0.618,
"step": 56
},
{
"epoch": 0.02,
"learning_rate": 1.4615384615384615e-05,
"loss": 0.9979,
"step": 57
},
{
"epoch": 0.02,
"learning_rate": 1.4871794871794874e-05,
"loss": 1.0005,
"step": 58
},
{
"epoch": 0.02,
"learning_rate": 1.5128205128205129e-05,
"loss": 1.0021,
"step": 59
},
{
"epoch": 0.02,
"learning_rate": 1.5384615384615387e-05,
"loss": 0.9906,
"step": 60
},
{
"epoch": 0.02,
"learning_rate": 1.5641025641025644e-05,
"loss": 1.0083,
"step": 61
},
{
"epoch": 0.02,
"learning_rate": 1.5897435897435897e-05,
"loss": 0.9794,
"step": 62
},
{
"epoch": 0.02,
"learning_rate": 1.6153846153846154e-05,
"loss": 0.9865,
"step": 63
},
{
"epoch": 0.02,
"learning_rate": 1.641025641025641e-05,
"loss": 0.986,
"step": 64
},
{
"epoch": 0.03,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.9982,
"step": 65
},
{
"epoch": 0.03,
"learning_rate": 1.6923076923076924e-05,
"loss": 0.5456,
"step": 66
},
{
"epoch": 0.03,
"learning_rate": 1.717948717948718e-05,
"loss": 1.0044,
"step": 67
},
{
"epoch": 0.03,
"learning_rate": 1.7435897435897438e-05,
"loss": 0.9874,
"step": 68
},
{
"epoch": 0.03,
"learning_rate": 1.7692307692307694e-05,
"loss": 0.9612,
"step": 69
},
{
"epoch": 0.03,
"learning_rate": 1.794871794871795e-05,
"loss": 0.9846,
"step": 70
},
{
"epoch": 0.03,
"learning_rate": 1.8205128205128208e-05,
"loss": 0.9917,
"step": 71
},
{
"epoch": 0.03,
"learning_rate": 1.8461538461538465e-05,
"loss": 0.9761,
"step": 72
},
{
"epoch": 0.03,
"learning_rate": 1.8717948717948718e-05,
"loss": 0.9827,
"step": 73
},
{
"epoch": 0.03,
"learning_rate": 1.8974358974358975e-05,
"loss": 0.9471,
"step": 74
},
{
"epoch": 0.03,
"learning_rate": 1.923076923076923e-05,
"loss": 0.5853,
"step": 75
},
{
"epoch": 0.03,
"learning_rate": 1.9487179487179488e-05,
"loss": 0.9703,
"step": 76
},
{
"epoch": 0.03,
"learning_rate": 1.9743589743589745e-05,
"loss": 0.5575,
"step": 77
},
{
"epoch": 0.03,
"learning_rate": 2e-05,
"loss": 0.9747,
"step": 78
},
{
"epoch": 0.03,
"learning_rate": 1.9999992229148463e-05,
"loss": 0.921,
"step": 79
},
{
"epoch": 0.03,
"learning_rate": 1.999996891660592e-05,
"loss": 0.9652,
"step": 80
},
{
"epoch": 0.03,
"learning_rate": 1.9999930062408612e-05,
"loss": 0.9893,
"step": 81
},
{
"epoch": 0.03,
"learning_rate": 1.9999875666616918e-05,
"loss": 0.9493,
"step": 82
},
{
"epoch": 0.03,
"learning_rate": 1.9999805729315383e-05,
"loss": 0.9308,
"step": 83
},
{
"epoch": 0.03,
"learning_rate": 1.99997202506127e-05,
"loss": 0.9586,
"step": 84
},
{
"epoch": 0.03,
"learning_rate": 1.9999619230641714e-05,
"loss": 0.9536,
"step": 85
},
{
"epoch": 0.03,
"learning_rate": 1.9999502669559432e-05,
"loss": 0.9554,
"step": 86
},
{
"epoch": 0.03,
"learning_rate": 1.9999370567547008e-05,
"loss": 0.5618,
"step": 87
},
{
"epoch": 0.03,
"learning_rate": 1.999922292480975e-05,
"loss": 0.9836,
"step": 88
},
{
"epoch": 0.03,
"learning_rate": 1.999905974157712e-05,
"loss": 0.9221,
"step": 89
},
{
"epoch": 0.03,
"learning_rate": 1.9998881018102735e-05,
"loss": 0.9779,
"step": 90
},
{
"epoch": 0.04,
"learning_rate": 1.999868675466436e-05,
"loss": 1.0245,
"step": 91
},
{
"epoch": 0.04,
"learning_rate": 1.9998476951563914e-05,
"loss": 0.9407,
"step": 92
},
{
"epoch": 0.04,
"learning_rate": 1.9998251609127465e-05,
"loss": 1.0011,
"step": 93
},
{
"epoch": 0.04,
"learning_rate": 1.9998010727705237e-05,
"loss": 0.9672,
"step": 94
},
{
"epoch": 0.04,
"learning_rate": 1.9997754307671597e-05,
"loss": 0.905,
"step": 95
},
{
"epoch": 0.04,
"learning_rate": 1.999748234942507e-05,
"loss": 0.954,
"step": 96
},
{
"epoch": 0.04,
"learning_rate": 1.9997194853388316e-05,
"loss": 0.9457,
"step": 97
},
{
"epoch": 0.04,
"learning_rate": 1.9996891820008165e-05,
"loss": 0.9702,
"step": 98
},
{
"epoch": 0.04,
"learning_rate": 1.9996573249755573e-05,
"loss": 0.9869,
"step": 99
},
{
"epoch": 0.04,
"learning_rate": 1.999623914312566e-05,
"loss": 0.952,
"step": 100
},
{
"epoch": 0.04,
"learning_rate": 1.999588950063768e-05,
"loss": 0.9384,
"step": 101
},
{
"epoch": 0.04,
"learning_rate": 1.9995524322835035e-05,
"loss": 0.9303,
"step": 102
},
{
"epoch": 0.04,
"learning_rate": 1.9995143610285275e-05,
"loss": 0.9592,
"step": 103
},
{
"epoch": 0.04,
"learning_rate": 1.99947473635801e-05,
"loss": 0.8807,
"step": 104
},
{
"epoch": 0.04,
"learning_rate": 1.9994335583335336e-05,
"loss": 0.9772,
"step": 105
},
{
"epoch": 0.04,
"learning_rate": 1.999390827019096e-05,
"loss": 0.9564,
"step": 106
},
{
"epoch": 0.04,
"learning_rate": 1.999346542481109e-05,
"loss": 0.9735,
"step": 107
},
{
"epoch": 0.04,
"learning_rate": 1.9993007047883988e-05,
"loss": 0.9965,
"step": 108
},
{
"epoch": 0.04,
"learning_rate": 1.9992533140122044e-05,
"loss": 0.9713,
"step": 109
},
{
"epoch": 0.04,
"learning_rate": 1.9992043702261795e-05,
"loss": 0.955,
"step": 110
},
{
"epoch": 0.04,
"learning_rate": 1.9991538735063906e-05,
"loss": 0.9983,
"step": 111
},
{
"epoch": 0.04,
"learning_rate": 1.999101823931319e-05,
"loss": 0.965,
"step": 112
},
{
"epoch": 0.04,
"learning_rate": 1.999048221581858e-05,
"loss": 0.9535,
"step": 113
},
{
"epoch": 0.04,
"learning_rate": 1.9989930665413148e-05,
"loss": 0.9575,
"step": 114
},
{
"epoch": 0.04,
"learning_rate": 1.99893635889541e-05,
"loss": 0.9432,
"step": 115
},
{
"epoch": 0.04,
"learning_rate": 1.998878098732277e-05,
"loss": 0.9705,
"step": 116
},
{
"epoch": 0.05,
"learning_rate": 1.9988182861424613e-05,
"loss": 0.953,
"step": 117
},
{
"epoch": 0.05,
"learning_rate": 1.9987569212189224e-05,
"loss": 0.9786,
"step": 118
},
{
"epoch": 0.05,
"learning_rate": 1.9986940040570323e-05,
"loss": 0.9862,
"step": 119
},
{
"epoch": 0.05,
"learning_rate": 1.9986295347545738e-05,
"loss": 0.9144,
"step": 120
},
{
"epoch": 0.05,
"learning_rate": 1.9985635134117445e-05,
"loss": 0.9724,
"step": 121
},
{
"epoch": 0.05,
"learning_rate": 1.998495940131152e-05,
"loss": 1.0098,
"step": 122
},
{
"epoch": 0.05,
"learning_rate": 1.998426815017817e-05,
"loss": 1.0334,
"step": 123
},
{
"epoch": 0.05,
"learning_rate": 1.998356138179171e-05,
"loss": 0.9668,
"step": 124
},
{
"epoch": 0.05,
"learning_rate": 1.9982839097250588e-05,
"loss": 0.999,
"step": 125
},
{
"epoch": 0.05,
"learning_rate": 1.998210129767735e-05,
"loss": 0.9832,
"step": 126
},
{
"epoch": 0.05,
"learning_rate": 1.998134798421867e-05,
"loss": 0.9348,
"step": 127
},
{
"epoch": 0.05,
"learning_rate": 1.9980579158045322e-05,
"loss": 0.9054,
"step": 128
},
{
"epoch": 0.05,
"learning_rate": 1.9979794820352187e-05,
"loss": 0.9669,
"step": 129
},
{
"epoch": 0.05,
"learning_rate": 1.9978994972358265e-05,
"loss": 0.8979,
"step": 130
},
{
"epoch": 0.05,
"learning_rate": 1.9978179615306658e-05,
"loss": 0.9879,
"step": 131
},
{
"epoch": 0.05,
"learning_rate": 1.997734875046456e-05,
"loss": 0.9653,
"step": 132
},
{
"epoch": 0.05,
"learning_rate": 1.997650237912329e-05,
"loss": 0.9044,
"step": 133
},
{
"epoch": 0.05,
"learning_rate": 1.9975640502598243e-05,
"loss": 0.9236,
"step": 134
},
{
"epoch": 0.05,
"learning_rate": 1.9974763122228927e-05,
"loss": 0.8966,
"step": 135
},
{
"epoch": 0.05,
"learning_rate": 1.9973870239378938e-05,
"loss": 0.919,
"step": 136
},
{
"epoch": 0.05,
"learning_rate": 1.997296185543597e-05,
"loss": 0.9478,
"step": 137
},
{
"epoch": 0.05,
"learning_rate": 1.9972037971811802e-05,
"loss": 0.9218,
"step": 138
},
{
"epoch": 0.05,
"learning_rate": 1.9971098589942314e-05,
"loss": 0.9373,
"step": 139
},
{
"epoch": 0.05,
"learning_rate": 1.997014371128746e-05,
"loss": 0.9371,
"step": 140
},
{
"epoch": 0.05,
"learning_rate": 1.9969173337331283e-05,
"loss": 0.9364,
"step": 141
},
{
"epoch": 0.05,
"learning_rate": 1.996818746958191e-05,
"loss": 0.9156,
"step": 142
},
{
"epoch": 0.06,
"learning_rate": 1.996718610957155e-05,
"loss": 0.9496,
"step": 143
},
{
"epoch": 0.06,
"learning_rate": 1.9966169258856488e-05,
"loss": 0.9473,
"step": 144
},
{
"epoch": 0.06,
"learning_rate": 1.996513691901708e-05,
"loss": 0.9913,
"step": 145
},
{
"epoch": 0.06,
"learning_rate": 1.996408909165776e-05,
"loss": 0.9785,
"step": 146
},
{
"epoch": 0.06,
"learning_rate": 1.996302577840703e-05,
"loss": 0.9583,
"step": 147
},
{
"epoch": 0.06,
"learning_rate": 1.9961946980917457e-05,
"loss": 0.9646,
"step": 148
},
{
"epoch": 0.06,
"learning_rate": 1.996085270086568e-05,
"loss": 0.8624,
"step": 149
},
{
"epoch": 0.06,
"learning_rate": 1.9959742939952393e-05,
"loss": 0.9569,
"step": 150
},
{
"epoch": 0.06,
"learning_rate": 1.9958617699902354e-05,
"loss": 0.9349,
"step": 151
},
{
"epoch": 0.06,
"learning_rate": 1.9957476982464382e-05,
"loss": 0.996,
"step": 152
},
{
"epoch": 0.06,
"learning_rate": 1.9956320789411338e-05,
"loss": 0.9056,
"step": 153
},
{
"epoch": 0.06,
"learning_rate": 1.995514912254015e-05,
"loss": 0.9501,
"step": 154
},
{
"epoch": 0.06,
"learning_rate": 1.9953961983671792e-05,
"loss": 0.9791,
"step": 155
},
{
"epoch": 0.06,
"learning_rate": 1.9952759374651266e-05,
"loss": 0.9525,
"step": 156
},
{
"epoch": 0.06,
"learning_rate": 1.9951541297347642e-05,
"loss": 0.911,
"step": 157
},
{
"epoch": 0.06,
"learning_rate": 1.9950307753654016e-05,
"loss": 0.8856,
"step": 158
},
{
"epoch": 0.06,
"learning_rate": 1.9949058745487524e-05,
"loss": 0.9375,
"step": 159
},
{
"epoch": 0.06,
"learning_rate": 1.994779427478934e-05,
"loss": 0.9635,
"step": 160
},
{
"epoch": 0.06,
"learning_rate": 1.994651434352467e-05,
"loss": 0.9354,
"step": 161
},
{
"epoch": 0.06,
"learning_rate": 1.9945218953682736e-05,
"loss": 0.9833,
"step": 162
},
{
"epoch": 0.06,
"learning_rate": 1.99439081072768e-05,
"loss": 0.8755,
"step": 163
},
{
"epoch": 0.06,
"learning_rate": 1.994258180634414e-05,
"loss": 0.905,
"step": 164
},
{
"epoch": 0.06,
"learning_rate": 1.9941240052946055e-05,
"loss": 0.9355,
"step": 165
},
{
"epoch": 0.06,
"learning_rate": 1.9939882849167853e-05,
"loss": 0.9105,
"step": 166
},
{
"epoch": 0.06,
"learning_rate": 1.9938510197118868e-05,
"loss": 0.9164,
"step": 167
},
{
"epoch": 0.06,
"learning_rate": 1.9937122098932428e-05,
"loss": 0.9327,
"step": 168
},
{
"epoch": 0.07,
"learning_rate": 1.9935718556765878e-05,
"loss": 0.9686,
"step": 169
},
{
"epoch": 0.07,
"learning_rate": 1.9934299572800556e-05,
"loss": 0.9397,
"step": 170
},
{
"epoch": 0.07,
"learning_rate": 1.9932865149241813e-05,
"loss": 0.8699,
"step": 171
},
{
"epoch": 0.07,
"learning_rate": 1.9931415288318985e-05,
"loss": 0.9449,
"step": 172
},
{
"epoch": 0.07,
"learning_rate": 1.9929949992285397e-05,
"loss": 0.9045,
"step": 173
},
{
"epoch": 0.07,
"learning_rate": 1.9928469263418376e-05,
"loss": 0.9435,
"step": 174
},
{
"epoch": 0.07,
"learning_rate": 1.992697310401922e-05,
"loss": 0.9106,
"step": 175
},
{
"epoch": 0.07,
"learning_rate": 1.9925461516413224e-05,
"loss": 0.9802,
"step": 176
},
{
"epoch": 0.07,
"learning_rate": 1.9923934502949645e-05,
"loss": 0.9675,
"step": 177
},
{
"epoch": 0.07,
"learning_rate": 1.9922392066001724e-05,
"loss": 0.9181,
"step": 178
},
{
"epoch": 0.07,
"learning_rate": 1.992083420796667e-05,
"loss": 0.918,
"step": 179
},
{
"epoch": 0.07,
"learning_rate": 1.9919260931265666e-05,
"loss": 0.9138,
"step": 180
},
{
"epoch": 0.07,
"learning_rate": 1.991767223834384e-05,
"loss": 0.9227,
"step": 181
},
{
"epoch": 0.07,
"learning_rate": 1.9916068131670302e-05,
"loss": 0.9432,
"step": 182
},
{
"epoch": 0.07,
"learning_rate": 1.9914448613738107e-05,
"loss": 0.9281,
"step": 183
},
{
"epoch": 0.07,
"learning_rate": 1.9912813687064255e-05,
"loss": 0.895,
"step": 184
},
{
"epoch": 0.07,
"learning_rate": 1.9911163354189702e-05,
"loss": 0.9806,
"step": 185
},
{
"epoch": 0.07,
"learning_rate": 1.990949761767935e-05,
"loss": 0.897,
"step": 186
},
{
"epoch": 0.07,
"learning_rate": 1.9907816480122032e-05,
"loss": 0.9612,
"step": 187
},
{
"epoch": 0.07,
"learning_rate": 1.9906119944130527e-05,
"loss": 0.5405,
"step": 188
},
{
"epoch": 0.07,
"learning_rate": 1.9904408012341542e-05,
"loss": 0.5667,
"step": 189
},
{
"epoch": 0.07,
"learning_rate": 1.9902680687415704e-05,
"loss": 0.9762,
"step": 190
},
{
"epoch": 0.07,
"learning_rate": 1.9900937972037577e-05,
"loss": 0.9409,
"step": 191
},
{
"epoch": 0.07,
"learning_rate": 1.989917986891563e-05,
"loss": 0.9927,
"step": 192
},
{
"epoch": 0.07,
"learning_rate": 1.9897406380782262e-05,
"loss": 0.9468,
"step": 193
},
{
"epoch": 0.07,
"learning_rate": 1.9895617510393773e-05,
"loss": 0.9373,
"step": 194
},
{
"epoch": 0.08,
"learning_rate": 1.9893813260530368e-05,
"loss": 0.947,
"step": 195
},
{
"epoch": 0.08,
"learning_rate": 1.9891993633996164e-05,
"loss": 0.9893,
"step": 196
},
{
"epoch": 0.08,
"learning_rate": 1.989015863361917e-05,
"loss": 0.917,
"step": 197
},
{
"epoch": 0.08,
"learning_rate": 1.9888308262251286e-05,
"loss": 0.9198,
"step": 198
},
{
"epoch": 0.08,
"learning_rate": 1.988644252276831e-05,
"loss": 0.9752,
"step": 199
},
{
"epoch": 0.08,
"learning_rate": 1.988456141806991e-05,
"loss": 0.9563,
"step": 200
},
{
"epoch": 0.08,
"learning_rate": 1.9882664951079652e-05,
"loss": 0.9396,
"step": 201
},
{
"epoch": 0.08,
"learning_rate": 1.9880753124744964e-05,
"loss": 0.9505,
"step": 202
},
{
"epoch": 0.08,
"learning_rate": 1.9878825942037147e-05,
"loss": 0.958,
"step": 203
},
{
"epoch": 0.08,
"learning_rate": 1.9876883405951378e-05,
"loss": 0.9475,
"step": 204
},
{
"epoch": 0.08,
"learning_rate": 1.9874925519506686e-05,
"loss": 0.9756,
"step": 205
},
{
"epoch": 0.08,
"learning_rate": 1.9872952285745958e-05,
"loss": 0.9586,
"step": 206
},
{
"epoch": 0.08,
"learning_rate": 1.987096370773594e-05,
"loss": 0.9442,
"step": 207
},
{
"epoch": 0.08,
"learning_rate": 1.9868959788567213e-05,
"loss": 0.9476,
"step": 208
},
{
"epoch": 0.08,
"learning_rate": 1.9866940531354214e-05,
"loss": 0.9333,
"step": 209
},
{
"epoch": 0.08,
"learning_rate": 1.9864905939235215e-05,
"loss": 0.9319,
"step": 210
},
{
"epoch": 0.08,
"learning_rate": 1.9862856015372315e-05,
"loss": 0.9492,
"step": 211
},
{
"epoch": 0.08,
"learning_rate": 1.9860790762951447e-05,
"loss": 0.9509,
"step": 212
},
{
"epoch": 0.08,
"learning_rate": 1.985871018518236e-05,
"loss": 0.8775,
"step": 213
},
{
"epoch": 0.08,
"learning_rate": 1.985661428529863e-05,
"loss": 0.9001,
"step": 214
},
{
"epoch": 0.08,
"learning_rate": 1.9854503066557646e-05,
"loss": 0.9082,
"step": 215
},
{
"epoch": 0.08,
"learning_rate": 1.9852376532240594e-05,
"loss": 0.887,
"step": 216
},
{
"epoch": 0.08,
"learning_rate": 1.9850234685652478e-05,
"loss": 0.9474,
"step": 217
},
{
"epoch": 0.08,
"learning_rate": 1.9848077530122083e-05,
"loss": 0.892,
"step": 218
},
{
"epoch": 0.08,
"learning_rate": 1.9845905069002004e-05,
"loss": 0.9298,
"step": 219
},
{
"epoch": 0.08,
"learning_rate": 1.984371730566861e-05,
"loss": 0.9282,
"step": 220
},
{
"epoch": 0.09,
"learning_rate": 1.9841514243522065e-05,
"loss": 0.9366,
"step": 221
},
{
"epoch": 0.09,
"learning_rate": 1.98392958859863e-05,
"loss": 0.9337,
"step": 222
},
{
"epoch": 0.09,
"learning_rate": 1.9837062236509013e-05,
"loss": 0.8938,
"step": 223
},
{
"epoch": 0.09,
"learning_rate": 1.9834813298561686e-05,
"loss": 0.9093,
"step": 224
},
{
"epoch": 0.09,
"learning_rate": 1.983254907563955e-05,
"loss": 0.9396,
"step": 225
},
{
"epoch": 0.09,
"learning_rate": 1.9830269571261585e-05,
"loss": 0.9203,
"step": 226
},
{
"epoch": 0.09,
"learning_rate": 1.9827974788970536e-05,
"loss": 0.9253,
"step": 227
},
{
"epoch": 0.09,
"learning_rate": 1.9825664732332886e-05,
"loss": 0.9498,
"step": 228
},
{
"epoch": 0.09,
"learning_rate": 1.982333940493885e-05,
"loss": 0.961,
"step": 229
},
{
"epoch": 0.09,
"learning_rate": 1.982099881040239e-05,
"loss": 0.9401,
"step": 230
},
{
"epoch": 0.09,
"learning_rate": 1.9818642952361188e-05,
"loss": 0.9005,
"step": 231
},
{
"epoch": 0.09,
"learning_rate": 1.9816271834476642e-05,
"loss": 0.9133,
"step": 232
},
{
"epoch": 0.09,
"learning_rate": 1.981388546043388e-05,
"loss": 0.8884,
"step": 233
},
{
"epoch": 0.09,
"learning_rate": 1.9811483833941726e-05,
"loss": 0.906,
"step": 234
},
{
"epoch": 0.09,
"learning_rate": 1.9809066958732727e-05,
"loss": 0.9244,
"step": 235
},
{
"epoch": 0.09,
"learning_rate": 1.9806634838563113e-05,
"loss": 0.9291,
"step": 236
},
{
"epoch": 0.09,
"learning_rate": 1.980418747721281e-05,
"loss": 0.9076,
"step": 237
},
{
"epoch": 0.09,
"learning_rate": 1.9801724878485438e-05,
"loss": 0.8733,
"step": 238
},
{
"epoch": 0.09,
"learning_rate": 1.9799247046208297e-05,
"loss": 0.9003,
"step": 239
},
{
"epoch": 0.09,
"learning_rate": 1.9796753984232357e-05,
"loss": 0.9652,
"step": 240
},
{
"epoch": 0.09,
"learning_rate": 1.9794245696432262e-05,
"loss": 0.9279,
"step": 241
},
{
"epoch": 0.09,
"learning_rate": 1.9791722186706318e-05,
"loss": 0.9353,
"step": 242
},
{
"epoch": 0.09,
"learning_rate": 1.9789183458976485e-05,
"loss": 0.8998,
"step": 243
},
{
"epoch": 0.09,
"learning_rate": 1.9786629517188384e-05,
"loss": 0.8778,
"step": 244
},
{
"epoch": 0.09,
"learning_rate": 1.9784060365311276e-05,
"loss": 0.9177,
"step": 245
},
{
"epoch": 0.09,
"learning_rate": 1.9781476007338058e-05,
"loss": 0.8939,
"step": 246
},
{
"epoch": 0.1,
"learning_rate": 1.9778876447285264e-05,
"loss": 0.9426,
"step": 247
},
{
"epoch": 0.1,
"learning_rate": 1.977626168919305e-05,
"loss": 0.9377,
"step": 248
},
{
"epoch": 0.1,
"learning_rate": 1.9773631737125192e-05,
"loss": 0.9296,
"step": 249
},
{
"epoch": 0.1,
"learning_rate": 1.9770986595169096e-05,
"loss": 0.9214,
"step": 250
},
{
"epoch": 0.1,
"learning_rate": 1.976832626743575e-05,
"loss": 0.8777,
"step": 251
},
{
"epoch": 0.1,
"learning_rate": 1.9765650758059766e-05,
"loss": 0.9165,
"step": 252
},
{
"epoch": 0.1,
"learning_rate": 1.9762960071199334e-05,
"loss": 0.8875,
"step": 253
},
{
"epoch": 0.1,
"learning_rate": 1.9760254211036245e-05,
"loss": 0.9514,
"step": 254
},
{
"epoch": 0.1,
"learning_rate": 1.9757533181775865e-05,
"loss": 0.9052,
"step": 255
},
{
"epoch": 0.1,
"learning_rate": 1.9754796987647134e-05,
"loss": 0.8907,
"step": 256
},
{
"epoch": 0.1,
"learning_rate": 1.9752045632902567e-05,
"loss": 0.9673,
"step": 257
},
{
"epoch": 0.1,
"learning_rate": 1.9749279121818235e-05,
"loss": 0.9203,
"step": 258
},
{
"epoch": 0.1,
"learning_rate": 1.9746497458693776e-05,
"loss": 0.9387,
"step": 259
},
{
"epoch": 0.1,
"learning_rate": 1.9743700647852356e-05,
"loss": 0.9233,
"step": 260
},
{
"epoch": 0.1,
"learning_rate": 1.9740888693640698e-05,
"loss": 0.9125,
"step": 261
},
{
"epoch": 0.1,
"learning_rate": 1.9738061600429062e-05,
"loss": 0.9244,
"step": 262
},
{
"epoch": 0.1,
"learning_rate": 1.9735219372611232e-05,
"loss": 0.9364,
"step": 263
},
{
"epoch": 0.1,
"learning_rate": 1.9732362014604515e-05,
"loss": 0.9147,
"step": 264
},
{
"epoch": 0.1,
"learning_rate": 1.972948953084973e-05,
"loss": 0.9622,
"step": 265
},
{
"epoch": 0.1,
"learning_rate": 1.9726601925811204e-05,
"loss": 0.8888,
"step": 266
},
{
"epoch": 0.1,
"learning_rate": 1.9723699203976768e-05,
"loss": 0.936,
"step": 267
},
{
"epoch": 0.1,
"learning_rate": 1.9720781369857747e-05,
"loss": 0.916,
"step": 268
},
{
"epoch": 0.1,
"learning_rate": 1.9717848427988954e-05,
"loss": 0.9258,
"step": 269
},
{
"epoch": 0.1,
"learning_rate": 1.9714900382928674e-05,
"loss": 0.9358,
"step": 270
},
{
"epoch": 0.1,
"learning_rate": 1.971193723925868e-05,
"loss": 0.9236,
"step": 271
},
{
"epoch": 0.1,
"learning_rate": 1.9708959001584197e-05,
"loss": 0.9458,
"step": 272
},
{
"epoch": 0.11,
"learning_rate": 1.970596567453391e-05,
"loss": 0.9147,
"step": 273
},
{
"epoch": 0.11,
"learning_rate": 1.9702957262759964e-05,
"loss": 0.9324,
"step": 274
},
{
"epoch": 0.11,
"learning_rate": 1.9699933770937948e-05,
"loss": 0.9434,
"step": 275
},
{
"epoch": 0.11,
"learning_rate": 1.969689520376687e-05,
"loss": 0.9016,
"step": 276
},
{
"epoch": 0.11,
"learning_rate": 1.969384156596919e-05,
"loss": 0.9425,
"step": 277
},
{
"epoch": 0.11,
"learning_rate": 1.969077286229078e-05,
"loss": 0.9318,
"step": 278
},
{
"epoch": 0.11,
"learning_rate": 1.9687689097500927e-05,
"loss": 0.9581,
"step": 279
},
{
"epoch": 0.11,
"learning_rate": 1.968459027639233e-05,
"loss": 0.984,
"step": 280
},
{
"epoch": 0.11,
"learning_rate": 1.968147640378108e-05,
"loss": 0.9282,
"step": 281
},
{
"epoch": 0.11,
"learning_rate": 1.9678347484506667e-05,
"loss": 0.9275,
"step": 282
},
{
"epoch": 0.11,
"learning_rate": 1.9675203523431964e-05,
"loss": 0.9041,
"step": 283
},
{
"epoch": 0.11,
"learning_rate": 1.9672044525443222e-05,
"loss": 0.929,
"step": 284
},
{
"epoch": 0.11,
"learning_rate": 1.9668870495450064e-05,
"loss": 0.938,
"step": 285
},
{
"epoch": 0.11,
"learning_rate": 1.9665681438385475e-05,
"loss": 0.9001,
"step": 286
},
{
"epoch": 0.11,
"learning_rate": 1.9662477359205786e-05,
"loss": 0.9003,
"step": 287
},
{
"epoch": 0.11,
"learning_rate": 1.9659258262890683e-05,
"loss": 0.8997,
"step": 288
},
{
"epoch": 0.11,
"learning_rate": 1.9656024154443195e-05,
"loss": 0.963,
"step": 289
},
{
"epoch": 0.11,
"learning_rate": 1.9652775038889676e-05,
"loss": 0.9038,
"step": 290
},
{
"epoch": 0.11,
"learning_rate": 1.9649510921279803e-05,
"loss": 0.9347,
"step": 291
},
{
"epoch": 0.11,
"learning_rate": 1.9646231806686566e-05,
"loss": 0.8706,
"step": 292
},
{
"epoch": 0.11,
"learning_rate": 1.964293770020628e-05,
"loss": 0.9247,
"step": 293
},
{
"epoch": 0.11,
"learning_rate": 1.9639628606958535e-05,
"loss": 0.8828,
"step": 294
},
{
"epoch": 0.11,
"learning_rate": 1.963630453208623e-05,
"loss": 0.8638,
"step": 295
},
{
"epoch": 0.11,
"learning_rate": 1.963296548075555e-05,
"loss": 0.8798,
"step": 296
},
{
"epoch": 0.11,
"learning_rate": 1.9629611458155936e-05,
"loss": 0.8973,
"step": 297
},
{
"epoch": 0.11,
"learning_rate": 1.962624246950012e-05,
"loss": 0.8965,
"step": 298
},
{
"epoch": 0.12,
"learning_rate": 1.9622858520024087e-05,
"loss": 0.8971,
"step": 299
},
{
"epoch": 0.12,
"learning_rate": 1.961945961498706e-05,
"loss": 0.9111,
"step": 300
},
{
"epoch": 0.12,
"learning_rate": 1.9616045759671524e-05,
"loss": 0.8716,
"step": 301
},
{
"epoch": 0.12,
"learning_rate": 1.961261695938319e-05,
"loss": 0.9467,
"step": 302
},
{
"epoch": 0.12,
"learning_rate": 1.9609173219450998e-05,
"loss": 0.9547,
"step": 303
},
{
"epoch": 0.12,
"learning_rate": 1.9605714545227105e-05,
"loss": 0.9387,
"step": 304
},
{
"epoch": 0.12,
"learning_rate": 1.960224094208688e-05,
"loss": 0.882,
"step": 305
},
{
"epoch": 0.12,
"learning_rate": 1.9598752415428893e-05,
"loss": 0.949,
"step": 306
},
{
"epoch": 0.12,
"learning_rate": 1.959524897067491e-05,
"loss": 0.9323,
"step": 307
},
{
"epoch": 0.12,
"learning_rate": 1.9591730613269878e-05,
"loss": 0.8853,
"step": 308
},
{
"epoch": 0.12,
"learning_rate": 1.958819734868193e-05,
"loss": 0.5747,
"step": 309
},
{
"epoch": 0.12,
"learning_rate": 1.9584649182402358e-05,
"loss": 0.9299,
"step": 310
},
{
"epoch": 0.12,
"learning_rate": 1.9581086119945615e-05,
"loss": 0.9236,
"step": 311
},
{
"epoch": 0.12,
"learning_rate": 1.9577508166849308e-05,
"loss": 0.9159,
"step": 312
},
{
"epoch": 0.12,
"learning_rate": 1.957391532867418e-05,
"loss": 0.9221,
"step": 313
},
{
"epoch": 0.12,
"learning_rate": 1.9570307611004124e-05,
"loss": 0.9602,
"step": 314
},
{
"epoch": 0.12,
"learning_rate": 1.956668501944614e-05,
"loss": 0.8748,
"step": 315
},
{
"epoch": 0.12,
"learning_rate": 1.9563047559630356e-05,
"loss": 0.9508,
"step": 316
},
{
"epoch": 0.12,
"learning_rate": 1.9559395237210002e-05,
"loss": 0.8912,
"step": 317
},
{
"epoch": 0.12,
"learning_rate": 1.955572805786141e-05,
"loss": 0.9539,
"step": 318
},
{
"epoch": 0.12,
"learning_rate": 1.9552046027284e-05,
"loss": 0.556,
"step": 319
},
{
"epoch": 0.12,
"learning_rate": 1.9548349151200275e-05,
"loss": 0.9701,
"step": 320
},
{
"epoch": 0.12,
"learning_rate": 1.954463743535581e-05,
"loss": 0.9084,
"step": 321
},
{
"epoch": 0.12,
"learning_rate": 1.9540910885519243e-05,
"loss": 0.9177,
"step": 322
},
{
"epoch": 0.12,
"learning_rate": 1.953716950748227e-05,
"loss": 0.9115,
"step": 323
},
{
"epoch": 0.12,
"learning_rate": 1.953341330705963e-05,
"loss": 0.9375,
"step": 324
},
{
"epoch": 0.13,
"learning_rate": 1.952964229008909e-05,
"loss": 0.9108,
"step": 325
},
{
"epoch": 0.13,
"learning_rate": 1.9525856462431463e-05,
"loss": 0.8967,
"step": 326
},
{
"epoch": 0.13,
"learning_rate": 1.9522055829970564e-05,
"loss": 0.8699,
"step": 327
},
{
"epoch": 0.13,
"learning_rate": 1.9518240398613226e-05,
"loss": 0.9365,
"step": 328
},
{
"epoch": 0.13,
"learning_rate": 1.951441017428928e-05,
"loss": 0.5237,
"step": 329
},
{
"epoch": 0.13,
"learning_rate": 1.9510565162951538e-05,
"loss": 0.9261,
"step": 330
},
{
"epoch": 0.13,
"learning_rate": 1.950670537057581e-05,
"loss": 0.9202,
"step": 331
},
{
"epoch": 0.13,
"learning_rate": 1.9502830803160873e-05,
"loss": 0.8738,
"step": 332
},
{
"epoch": 0.13,
"learning_rate": 1.9498941466728462e-05,
"loss": 0.9331,
"step": 333
},
{
"epoch": 0.13,
"learning_rate": 1.9495037367323264e-05,
"loss": 0.9661,
"step": 334
},
{
"epoch": 0.13,
"learning_rate": 1.949111851101292e-05,
"loss": 0.8956,
"step": 335
},
{
"epoch": 0.13,
"learning_rate": 1.9487184903888e-05,
"loss": 0.9858,
"step": 336
},
{
"epoch": 0.13,
"learning_rate": 1.9483236552061996e-05,
"loss": 0.8821,
"step": 337
},
{
"epoch": 0.13,
"learning_rate": 1.947927346167132e-05,
"loss": 0.5162,
"step": 338
},
{
"epoch": 0.13,
"learning_rate": 1.947529563887529e-05,
"loss": 0.9899,
"step": 339
},
{
"epoch": 0.13,
"learning_rate": 1.947130308985612e-05,
"loss": 0.9348,
"step": 340
},
{
"epoch": 0.13,
"learning_rate": 1.9467295820818913e-05,
"loss": 0.8704,
"step": 341
},
{
"epoch": 0.13,
"learning_rate": 1.9463273837991643e-05,
"loss": 0.8878,
"step": 342
},
{
"epoch": 0.13,
"learning_rate": 1.945923714762516e-05,
"loss": 0.8918,
"step": 343
},
{
"epoch": 0.13,
"learning_rate": 1.945518575599317e-05,
"loss": 0.9101,
"step": 344
},
{
"epoch": 0.13,
"learning_rate": 1.945111966939222e-05,
"loss": 0.9219,
"step": 345
},
{
"epoch": 0.13,
"learning_rate": 1.9447038894141707e-05,
"loss": 0.92,
"step": 346
},
{
"epoch": 0.13,
"learning_rate": 1.9442943436583845e-05,
"loss": 0.8876,
"step": 347
},
{
"epoch": 0.13,
"learning_rate": 1.9438833303083677e-05,
"loss": 0.8821,
"step": 348
},
{
"epoch": 0.13,
"learning_rate": 1.943470850002905e-05,
"loss": 0.9127,
"step": 349
},
{
"epoch": 0.13,
"learning_rate": 1.9430569033830606e-05,
"loss": 0.8744,
"step": 350
},
{
"epoch": 0.14,
"learning_rate": 1.9426414910921785e-05,
"loss": 0.8855,
"step": 351
},
{
"epoch": 0.14,
"learning_rate": 1.94222461377588e-05,
"loss": 0.8857,
"step": 352
},
{
"epoch": 0.14,
"learning_rate": 1.9418062720820636e-05,
"loss": 0.5281,
"step": 353
},
{
"epoch": 0.14,
"learning_rate": 1.9413864666609036e-05,
"loss": 0.904,
"step": 354
},
{
"epoch": 0.14,
"learning_rate": 1.9409651981648486e-05,
"loss": 0.9623,
"step": 355
},
{
"epoch": 0.14,
"learning_rate": 1.9405424672486218e-05,
"loss": 0.9236,
"step": 356
},
{
"epoch": 0.14,
"learning_rate": 1.940118274569219e-05,
"loss": 0.8914,
"step": 357
},
{
"epoch": 0.14,
"learning_rate": 1.9396926207859085e-05,
"loss": 0.8844,
"step": 358
},
{
"epoch": 0.14,
"learning_rate": 1.939265506560228e-05,
"loss": 0.9457,
"step": 359
},
{
"epoch": 0.14,
"learning_rate": 1.9388369325559862e-05,
"loss": 0.8771,
"step": 360
},
{
"epoch": 0.14,
"learning_rate": 1.93840689943926e-05,
"loss": 0.9142,
"step": 361
},
{
"epoch": 0.14,
"learning_rate": 1.937975407878394e-05,
"loss": 0.8972,
"step": 362
},
{
"epoch": 0.14,
"learning_rate": 1.9375424585439994e-05,
"loss": 0.8925,
"step": 363
},
{
"epoch": 0.14,
"learning_rate": 1.9371080521089536e-05,
"loss": 0.9136,
"step": 364
},
{
"epoch": 0.14,
"learning_rate": 1.9366721892483976e-05,
"loss": 0.9143,
"step": 365
},
{
"epoch": 0.14,
"learning_rate": 1.9362348706397374e-05,
"loss": 0.9098,
"step": 366
},
{
"epoch": 0.14,
"learning_rate": 1.9357960969626398e-05,
"loss": 0.9174,
"step": 367
},
{
"epoch": 0.14,
"learning_rate": 1.935355868899034e-05,
"loss": 0.8297,
"step": 368
},
{
"epoch": 0.14,
"learning_rate": 1.93491418713311e-05,
"loss": 0.9265,
"step": 369
},
{
"epoch": 0.14,
"learning_rate": 1.9344710523513157e-05,
"loss": 0.9247,
"step": 370
},
{
"epoch": 0.14,
"learning_rate": 1.9340264652423584e-05,
"loss": 0.8901,
"step": 371
},
{
"epoch": 0.14,
"learning_rate": 1.9335804264972018e-05,
"loss": 0.892,
"step": 372
},
{
"epoch": 0.14,
"learning_rate": 1.9331329368090664e-05,
"loss": 0.9164,
"step": 373
},
{
"epoch": 0.14,
"learning_rate": 1.9326839968734278e-05,
"loss": 0.913,
"step": 374
},
{
"epoch": 0.14,
"learning_rate": 1.9322336073880143e-05,
"loss": 0.9193,
"step": 375
},
{
"epoch": 0.14,
"learning_rate": 1.9317817690528086e-05,
"loss": 0.9139,
"step": 376
},
{
"epoch": 0.15,
"learning_rate": 1.931328482570044e-05,
"loss": 0.9349,
"step": 377
},
{
"epoch": 0.15,
"learning_rate": 1.9308737486442045e-05,
"loss": 0.8632,
"step": 378
},
{
"epoch": 0.15,
"learning_rate": 1.9304175679820247e-05,
"loss": 0.9109,
"step": 379
},
{
"epoch": 0.15,
"learning_rate": 1.929959941292487e-05,
"loss": 0.9403,
"step": 380
},
{
"epoch": 0.15,
"learning_rate": 1.929500869286821e-05,
"loss": 0.8986,
"step": 381
},
{
"epoch": 0.15,
"learning_rate": 1.9290403526785025e-05,
"loss": 0.957,
"step": 382
},
{
"epoch": 0.15,
"learning_rate": 1.9285783921832537e-05,
"loss": 0.9141,
"step": 383
},
{
"epoch": 0.15,
"learning_rate": 1.928114988519039e-05,
"loss": 0.9417,
"step": 384
},
{
"epoch": 0.15,
"learning_rate": 1.927650142406067e-05,
"loss": 0.9126,
"step": 385
},
{
"epoch": 0.15,
"learning_rate": 1.9271838545667876e-05,
"loss": 0.9244,
"step": 386
},
{
"epoch": 0.15,
"learning_rate": 1.9267161257258916e-05,
"loss": 0.9678,
"step": 387
},
{
"epoch": 0.15,
"learning_rate": 1.926246956610309e-05,
"loss": 0.9344,
"step": 388
},
{
"epoch": 0.15,
"learning_rate": 1.9257763479492086e-05,
"loss": 0.9138,
"step": 389
},
{
"epoch": 0.15,
"learning_rate": 1.9253043004739967e-05,
"loss": 0.5353,
"step": 390
},
{
"epoch": 0.15,
"learning_rate": 1.9248308149183155e-05,
"loss": 0.9034,
"step": 391
},
{
"epoch": 0.15,
"learning_rate": 1.9243558920180417e-05,
"loss": 0.9288,
"step": 392
},
{
"epoch": 0.15,
"learning_rate": 1.9238795325112867e-05,
"loss": 0.8591,
"step": 393
},
{
"epoch": 0.15,
"learning_rate": 1.9234017371383946e-05,
"loss": 0.9184,
"step": 394
},
{
"epoch": 0.15,
"learning_rate": 1.92292250664194e-05,
"loss": 0.9052,
"step": 395
},
{
"epoch": 0.15,
"learning_rate": 1.9224418417667295e-05,
"loss": 0.8203,
"step": 396
},
{
"epoch": 0.15,
"learning_rate": 1.9219597432597975e-05,
"loss": 0.9193,
"step": 397
},
{
"epoch": 0.15,
"learning_rate": 1.921476211870408e-05,
"loss": 0.8953,
"step": 398
},
{
"epoch": 0.15,
"learning_rate": 1.92099124835005e-05,
"loss": 0.8475,
"step": 399
},
{
"epoch": 0.15,
"learning_rate": 1.9205048534524405e-05,
"loss": 0.9065,
"step": 400
},
{
"epoch": 0.15,
"learning_rate": 1.9200170279335194e-05,
"loss": 0.5018,
"step": 401
},
{
"epoch": 0.15,
"learning_rate": 1.919527772551451e-05,
"loss": 0.9371,
"step": 402
},
{
"epoch": 0.16,
"learning_rate": 1.9190370880666206e-05,
"loss": 0.8923,
"step": 403
},
{
"epoch": 0.16,
"learning_rate": 1.9185449752416367e-05,
"loss": 0.9033,
"step": 404
},
{
"epoch": 0.16,
"learning_rate": 1.918051434841326e-05,
"loss": 0.9119,
"step": 405
},
{
"epoch": 0.16,
"learning_rate": 1.917556467632734e-05,
"loss": 0.9009,
"step": 406
},
{
"epoch": 0.16,
"learning_rate": 1.917060074385124e-05,
"loss": 0.9489,
"step": 407
},
{
"epoch": 0.16,
"learning_rate": 1.9165622558699763e-05,
"loss": 0.936,
"step": 408
},
{
"epoch": 0.16,
"learning_rate": 1.916063012860985e-05,
"loss": 0.9072,
"step": 409
},
{
"epoch": 0.16,
"learning_rate": 1.9155623461340594e-05,
"loss": 0.9102,
"step": 410
},
{
"epoch": 0.16,
"learning_rate": 1.91506025646732e-05,
"loss": 0.9021,
"step": 411
},
{
"epoch": 0.16,
"learning_rate": 1.9145567446411003e-05,
"loss": 0.8585,
"step": 412
},
{
"epoch": 0.16,
"learning_rate": 1.9140518114379433e-05,
"loss": 0.9304,
"step": 413
},
{
"epoch": 0.16,
"learning_rate": 1.913545457642601e-05,
"loss": 0.4854,
"step": 414
},
{
"epoch": 0.16,
"learning_rate": 1.9130376840420337e-05,
"loss": 0.933,
"step": 415
},
{
"epoch": 0.16,
"learning_rate": 1.912528491425408e-05,
"loss": 0.9025,
"step": 416
},
{
"epoch": 0.16,
"learning_rate": 1.9120178805840956e-05,
"loss": 0.9667,
"step": 417
},
{
"epoch": 0.16,
"learning_rate": 1.9115058523116734e-05,
"loss": 0.9265,
"step": 418
},
{
"epoch": 0.16,
"learning_rate": 1.9109924074039198e-05,
"loss": 0.8362,
"step": 419
},
{
"epoch": 0.16,
"learning_rate": 1.9104775466588162e-05,
"loss": 0.8986,
"step": 420
},
{
"epoch": 0.16,
"learning_rate": 1.9099612708765432e-05,
"loss": 0.8994,
"step": 421
},
{
"epoch": 0.16,
"learning_rate": 1.9094435808594823e-05,
"loss": 0.8984,
"step": 422
},
{
"epoch": 0.16,
"learning_rate": 1.908924477412211e-05,
"loss": 0.8451,
"step": 423
},
{
"epoch": 0.16,
"learning_rate": 1.9084039613415052e-05,
"loss": 0.8936,
"step": 424
},
{
"epoch": 0.16,
"learning_rate": 1.9078820334563346e-05,
"loss": 0.8076,
"step": 425
},
{
"epoch": 0.16,
"learning_rate": 1.907358694567865e-05,
"loss": 0.8956,
"step": 426
},
{
"epoch": 0.16,
"learning_rate": 1.9068339454894536e-05,
"loss": 0.8681,
"step": 427
},
{
"epoch": 0.16,
"learning_rate": 1.9063077870366504e-05,
"loss": 0.9438,
"step": 428
},
{
"epoch": 0.17,
"learning_rate": 1.9057802200271943e-05,
"loss": 0.5382,
"step": 429
},
{
"epoch": 0.17,
"learning_rate": 1.905251245281015e-05,
"loss": 0.9373,
"step": 430
},
{
"epoch": 0.17,
"learning_rate": 1.904720863620229e-05,
"loss": 0.9174,
"step": 431
},
{
"epoch": 0.17,
"learning_rate": 1.9041890758691403e-05,
"loss": 0.8777,
"step": 432
},
{
"epoch": 0.17,
"learning_rate": 1.903655882854237e-05,
"loss": 0.9043,
"step": 433
},
{
"epoch": 0.17,
"learning_rate": 1.903121285404192e-05,
"loss": 0.8973,
"step": 434
},
{
"epoch": 0.17,
"learning_rate": 1.902585284349861e-05,
"loss": 0.8552,
"step": 435
},
{
"epoch": 0.17,
"learning_rate": 1.9020478805242803e-05,
"loss": 0.9315,
"step": 436
},
{
"epoch": 0.17,
"learning_rate": 1.901509074762668e-05,
"loss": 0.8307,
"step": 437
},
{
"epoch": 0.17,
"learning_rate": 1.900968867902419e-05,
"loss": 0.9107,
"step": 438
},
{
"epoch": 0.17,
"learning_rate": 1.9004272607831077e-05,
"loss": 0.9146,
"step": 439
},
{
"epoch": 0.17,
"learning_rate": 1.8998842542464833e-05,
"loss": 0.9299,
"step": 440
},
{
"epoch": 0.17,
"learning_rate": 1.8993398491364702e-05,
"loss": 0.9313,
"step": 441
},
{
"epoch": 0.17,
"learning_rate": 1.8987940462991673e-05,
"loss": 0.9323,
"step": 442
},
{
"epoch": 0.17,
"learning_rate": 1.898246846582844e-05,
"loss": 0.8922,
"step": 443
},
{
"epoch": 0.17,
"learning_rate": 1.8976982508379436e-05,
"loss": 0.8736,
"step": 444
},
{
"epoch": 0.17,
"learning_rate": 1.897148259917076e-05,
"loss": 0.9393,
"step": 445
},
{
"epoch": 0.17,
"learning_rate": 1.896596874675021e-05,
"loss": 0.8878,
"step": 446
},
{
"epoch": 0.17,
"learning_rate": 1.8960440959687254e-05,
"loss": 0.8951,
"step": 447
},
{
"epoch": 0.17,
"learning_rate": 1.895489924657301e-05,
"loss": 0.9113,
"step": 448
},
{
"epoch": 0.17,
"learning_rate": 1.894934361602025e-05,
"loss": 0.8734,
"step": 449
},
{
"epoch": 0.17,
"learning_rate": 1.8943774076663372e-05,
"loss": 0.8875,
"step": 450
},
{
"epoch": 0.17,
"learning_rate": 1.8938190637158377e-05,
"loss": 0.9194,
"step": 451
},
{
"epoch": 0.17,
"learning_rate": 1.893259330618289e-05,
"loss": 0.9078,
"step": 452
},
{
"epoch": 0.17,
"learning_rate": 1.8926982092436117e-05,
"loss": 0.9762,
"step": 453
},
{
"epoch": 0.17,
"learning_rate": 1.8921357004638837e-05,
"loss": 0.9122,
"step": 454
},
{
"epoch": 0.18,
"learning_rate": 1.891571805153339e-05,
"loss": 0.9292,
"step": 455
},
{
"epoch": 0.18,
"learning_rate": 1.891006524188368e-05,
"loss": 0.8813,
"step": 456
},
{
"epoch": 0.18,
"learning_rate": 1.890439858447513e-05,
"loss": 0.942,
"step": 457
},
{
"epoch": 0.18,
"learning_rate": 1.8898718088114688e-05,
"loss": 0.932,
"step": 458
},
{
"epoch": 0.18,
"learning_rate": 1.8893023761630816e-05,
"loss": 0.9543,
"step": 459
},
{
"epoch": 0.18,
"learning_rate": 1.888731561387347e-05,
"loss": 0.907,
"step": 460
},
{
"epoch": 0.18,
"learning_rate": 1.8881593653714075e-05,
"loss": 0.5361,
"step": 461
},
{
"epoch": 0.18,
"learning_rate": 1.8875857890045544e-05,
"loss": 0.9164,
"step": 462
},
{
"epoch": 0.18,
"learning_rate": 1.887010833178222e-05,
"loss": 0.8746,
"step": 463
},
{
"epoch": 0.18,
"learning_rate": 1.8864344987859898e-05,
"loss": 0.9097,
"step": 464
},
{
"epoch": 0.18,
"learning_rate": 1.88585678672358e-05,
"loss": 0.9165,
"step": 465
},
{
"epoch": 0.18,
"learning_rate": 1.885277697888855e-05,
"loss": 0.8637,
"step": 466
},
{
"epoch": 0.18,
"learning_rate": 1.8846972331818182e-05,
"loss": 0.858,
"step": 467
},
{
"epoch": 0.18,
"learning_rate": 1.8841153935046098e-05,
"loss": 0.9376,
"step": 468
},
{
"epoch": 0.18,
"learning_rate": 1.8835321797615083e-05,
"loss": 0.9073,
"step": 469
},
{
"epoch": 0.18,
"learning_rate": 1.8829475928589272e-05,
"loss": 0.9183,
"step": 470
},
{
"epoch": 0.18,
"learning_rate": 1.8823616337054136e-05,
"loss": 0.5241,
"step": 471
},
{
"epoch": 0.18,
"learning_rate": 1.8817743032116483e-05,
"loss": 0.8663,
"step": 472
},
{
"epoch": 0.18,
"learning_rate": 1.8811856022904423e-05,
"loss": 0.9224,
"step": 473
},
{
"epoch": 0.18,
"learning_rate": 1.880595531856738e-05,
"loss": 0.8416,
"step": 474
},
{
"epoch": 0.18,
"learning_rate": 1.880004092827605e-05,
"loss": 0.8766,
"step": 475
},
{
"epoch": 0.18,
"learning_rate": 1.87941128612224e-05,
"loss": 0.9088,
"step": 476
},
{
"epoch": 0.18,
"learning_rate": 1.8788171126619653e-05,
"loss": 0.9792,
"step": 477
},
{
"epoch": 0.18,
"learning_rate": 1.8782215733702286e-05,
"loss": 0.8949,
"step": 478
},
{
"epoch": 0.18,
"learning_rate": 1.8776246691725988e-05,
"loss": 0.9193,
"step": 479
},
{
"epoch": 0.18,
"learning_rate": 1.8770264009967667e-05,
"loss": 0.5605,
"step": 480
},
{
"epoch": 0.19,
"learning_rate": 1.8764267697725432e-05,
"loss": 0.9187,
"step": 481
},
{
"epoch": 0.19,
"learning_rate": 1.8758257764318566e-05,
"loss": 0.9423,
"step": 482
},
{
"epoch": 0.19,
"learning_rate": 1.8752234219087538e-05,
"loss": 0.9276,
"step": 483
},
{
"epoch": 0.19,
"learning_rate": 1.874619707139396e-05,
"loss": 0.8958,
"step": 484
},
{
"epoch": 0.19,
"learning_rate": 1.8740146330620584e-05,
"loss": 0.946,
"step": 485
},
{
"epoch": 0.19,
"learning_rate": 1.87340820061713e-05,
"loss": 0.8761,
"step": 486
},
{
"epoch": 0.19,
"learning_rate": 1.872800410747109e-05,
"loss": 0.5089,
"step": 487
},
{
"epoch": 0.19,
"learning_rate": 1.8721912643966055e-05,
"loss": 0.929,
"step": 488
},
{
"epoch": 0.19,
"learning_rate": 1.871580762512336e-05,
"loss": 0.865,
"step": 489
},
{
"epoch": 0.19,
"learning_rate": 1.8709689060431242e-05,
"loss": 0.9029,
"step": 490
},
{
"epoch": 0.19,
"learning_rate": 1.8703556959398998e-05,
"loss": 0.8679,
"step": 491
},
{
"epoch": 0.19,
"learning_rate": 1.8697411331556958e-05,
"loss": 0.9128,
"step": 492
},
{
"epoch": 0.19,
"learning_rate": 1.8691252186456465e-05,
"loss": 0.89,
"step": 493
},
{
"epoch": 0.19,
"learning_rate": 1.868507953366989e-05,
"loss": 0.5244,
"step": 494
},
{
"epoch": 0.19,
"learning_rate": 1.8678893382790583e-05,
"loss": 0.8852,
"step": 495
},
{
"epoch": 0.19,
"learning_rate": 1.8672693743432875e-05,
"loss": 0.8803,
"step": 496
},
{
"epoch": 0.19,
"learning_rate": 1.866648062523206e-05,
"loss": 0.8579,
"step": 497
},
{
"epoch": 0.19,
"learning_rate": 1.866025403784439e-05,
"loss": 0.8799,
"step": 498
},
{
"epoch": 0.19,
"learning_rate": 1.865401399094703e-05,
"loss": 0.9456,
"step": 499
},
{
"epoch": 0.19,
"learning_rate": 1.8647760494238082e-05,
"loss": 0.9081,
"step": 500
},
{
"epoch": 0.19,
"learning_rate": 1.864149355743655e-05,
"loss": 0.8983,
"step": 501
},
{
"epoch": 0.19,
"learning_rate": 1.8635213190282312e-05,
"loss": 0.8568,
"step": 502
},
{
"epoch": 0.19,
"learning_rate": 1.862891940253613e-05,
"loss": 0.8979,
"step": 503
},
{
"epoch": 0.19,
"learning_rate": 1.8622612203979628e-05,
"loss": 0.9133,
"step": 504
},
{
"epoch": 0.19,
"learning_rate": 1.861629160441526e-05,
"loss": 0.9133,
"step": 505
},
{
"epoch": 0.19,
"learning_rate": 1.8609957613666316e-05,
"loss": 0.89,
"step": 506
},
{
"epoch": 0.2,
"learning_rate": 1.86036102415769e-05,
"loss": 0.8955,
"step": 507
},
{
"epoch": 0.2,
"learning_rate": 1.8597249498011906e-05,
"loss": 0.8835,
"step": 508
},
{
"epoch": 0.2,
"learning_rate": 1.8590875392857008e-05,
"loss": 0.9725,
"step": 509
},
{
"epoch": 0.2,
"learning_rate": 1.8584487936018663e-05,
"loss": 0.9053,
"step": 510
},
{
"epoch": 0.2,
"learning_rate": 1.8578087137424057e-05,
"loss": 0.8705,
"step": 511
},
{
"epoch": 0.2,
"learning_rate": 1.8571673007021124e-05,
"loss": 0.8434,
"step": 512
},
{
"epoch": 0.2,
"learning_rate": 1.8565245554778516e-05,
"loss": 0.9204,
"step": 513
},
{
"epoch": 0.2,
"learning_rate": 1.855880479068559e-05,
"loss": 0.8988,
"step": 514
},
{
"epoch": 0.2,
"learning_rate": 1.8552350724752383e-05,
"loss": 0.8536,
"step": 515
},
{
"epoch": 0.2,
"learning_rate": 1.854588336700962e-05,
"loss": 0.8627,
"step": 516
},
{
"epoch": 0.2,
"learning_rate": 1.853940272750867e-05,
"loss": 0.8819,
"step": 517
},
{
"epoch": 0.2,
"learning_rate": 1.8532908816321557e-05,
"loss": 0.8719,
"step": 518
},
{
"epoch": 0.2,
"learning_rate": 1.8526401643540924e-05,
"loss": 0.9026,
"step": 519
},
{
"epoch": 0.2,
"learning_rate": 1.851988121928002e-05,
"loss": 0.894,
"step": 520
},
{
"epoch": 0.2,
"learning_rate": 1.85133475536727e-05,
"loss": 0.928,
"step": 521
},
{
"epoch": 0.2,
"learning_rate": 1.8506800656873397e-05,
"loss": 0.9062,
"step": 522
},
{
"epoch": 0.2,
"learning_rate": 1.8500240539057093e-05,
"loss": 0.8914,
"step": 523
},
{
"epoch": 0.2,
"learning_rate": 1.8493667210419337e-05,
"loss": 0.9183,
"step": 524
},
{
"epoch": 0.2,
"learning_rate": 1.8487080681176195e-05,
"loss": 0.8668,
"step": 525
},
{
"epoch": 0.2,
"learning_rate": 1.848048096156426e-05,
"loss": 0.9261,
"step": 526
},
{
"epoch": 0.2,
"learning_rate": 1.8473868061840617e-05,
"loss": 0.8928,
"step": 527
},
{
"epoch": 0.2,
"learning_rate": 1.8467241992282842e-05,
"loss": 0.5563,
"step": 528
},
{
"epoch": 0.2,
"learning_rate": 1.8460602763188974e-05,
"loss": 0.911,
"step": 529
},
{
"epoch": 0.2,
"learning_rate": 1.8453950384877504e-05,
"loss": 0.8859,
"step": 530
},
{
"epoch": 0.2,
"learning_rate": 1.844728486768736e-05,
"loss": 0.5338,
"step": 531
},
{
"epoch": 0.2,
"learning_rate": 1.8440606221977893e-05,
"loss": 0.9592,
"step": 532
},
{
"epoch": 0.21,
"learning_rate": 1.843391445812886e-05,
"loss": 0.9059,
"step": 533
},
{
"epoch": 0.21,
"learning_rate": 1.8427209586540392e-05,
"loss": 0.8898,
"step": 534
},
{
"epoch": 0.21,
"learning_rate": 1.842049161763301e-05,
"loss": 0.8868,
"step": 535
},
{
"epoch": 0.21,
"learning_rate": 1.841376056184758e-05,
"loss": 0.8872,
"step": 536
},
{
"epoch": 0.21,
"learning_rate": 1.8407016429645305e-05,
"loss": 0.8784,
"step": 537
},
{
"epoch": 0.21,
"learning_rate": 1.8400259231507716e-05,
"loss": 0.4883,
"step": 538
},
{
"epoch": 0.21,
"learning_rate": 1.8393488977936654e-05,
"loss": 0.8524,
"step": 539
},
{
"epoch": 0.21,
"learning_rate": 1.8386705679454243e-05,
"loss": 0.8987,
"step": 540
},
{
"epoch": 0.21,
"learning_rate": 1.837990934660288e-05,
"loss": 0.931,
"step": 541
},
{
"epoch": 0.21,
"learning_rate": 1.8373099989945236e-05,
"loss": 0.8945,
"step": 542
},
{
"epoch": 0.21,
"learning_rate": 1.83662776200642e-05,
"loss": 0.8721,
"step": 543
},
{
"epoch": 0.21,
"learning_rate": 1.8359442247562896e-05,
"loss": 0.8665,
"step": 544
},
{
"epoch": 0.21,
"learning_rate": 1.8352593883064664e-05,
"loss": 0.9093,
"step": 545
},
{
"epoch": 0.21,
"learning_rate": 1.834573253721303e-05,
"loss": 0.8907,
"step": 546
},
{
"epoch": 0.21,
"learning_rate": 1.8338858220671683e-05,
"loss": 0.9047,
"step": 547
},
{
"epoch": 0.21,
"learning_rate": 1.833197094412449e-05,
"loss": 0.8712,
"step": 548
},
{
"epoch": 0.21,
"learning_rate": 1.8325070718275452e-05,
"loss": 0.859,
"step": 549
},
{
"epoch": 0.21,
"learning_rate": 1.8318157553848694e-05,
"loss": 0.8817,
"step": 550
},
{
"epoch": 0.21,
"learning_rate": 1.8311231461588446e-05,
"loss": 0.5356,
"step": 551
},
{
"epoch": 0.21,
"learning_rate": 1.8304292452259037e-05,
"loss": 0.8777,
"step": 552
},
{
"epoch": 0.21,
"learning_rate": 1.8297340536644877e-05,
"loss": 0.9291,
"step": 553
},
{
"epoch": 0.21,
"learning_rate": 1.8290375725550417e-05,
"loss": 0.5386,
"step": 554
},
{
"epoch": 0.21,
"learning_rate": 1.8283398029800167e-05,
"loss": 0.8627,
"step": 555
},
{
"epoch": 0.21,
"learning_rate": 1.827640746023865e-05,
"loss": 0.873,
"step": 556
},
{
"epoch": 0.21,
"learning_rate": 1.82694040277304e-05,
"loss": 0.9523,
"step": 557
},
{
"epoch": 0.21,
"learning_rate": 1.826238774315995e-05,
"loss": 0.8628,
"step": 558
},
{
"epoch": 0.22,
"learning_rate": 1.82553586174318e-05,
"loss": 0.5254,
"step": 559
},
{
"epoch": 0.22,
"learning_rate": 1.82483166614704e-05,
"loss": 0.9072,
"step": 560
},
{
"epoch": 0.22,
"learning_rate": 1.8241261886220155e-05,
"loss": 0.8929,
"step": 561
},
{
"epoch": 0.22,
"learning_rate": 1.8234194302645393e-05,
"loss": 0.8949,
"step": 562
},
{
"epoch": 0.22,
"learning_rate": 1.8227113921730336e-05,
"loss": 0.9065,
"step": 563
},
{
"epoch": 0.22,
"learning_rate": 1.8220020754479104e-05,
"loss": 0.8788,
"step": 564
},
{
"epoch": 0.22,
"learning_rate": 1.821291481191568e-05,
"loss": 0.886,
"step": 565
},
{
"epoch": 0.22,
"learning_rate": 1.8205796105083917e-05,
"loss": 0.8961,
"step": 566
},
{
"epoch": 0.22,
"learning_rate": 1.8198664645047496e-05,
"loss": 0.937,
"step": 567
},
{
"epoch": 0.22,
"learning_rate": 1.819152044288992e-05,
"loss": 0.8671,
"step": 568
},
{
"epoch": 0.22,
"learning_rate": 1.8184363509714494e-05,
"loss": 0.8842,
"step": 569
},
{
"epoch": 0.22,
"learning_rate": 1.8177193856644315e-05,
"loss": 0.9122,
"step": 570
},
{
"epoch": 0.22,
"learning_rate": 1.8170011494822242e-05,
"loss": 0.893,
"step": 571
},
{
"epoch": 0.22,
"learning_rate": 1.8162816435410892e-05,
"loss": 0.9596,
"step": 572
},
{
"epoch": 0.22,
"learning_rate": 1.8155608689592604e-05,
"loss": 0.8951,
"step": 573
},
{
"epoch": 0.22,
"learning_rate": 1.8148388268569453e-05,
"loss": 0.8771,
"step": 574
},
{
"epoch": 0.22,
"learning_rate": 1.8141155183563195e-05,
"loss": 0.9018,
"step": 575
},
{
"epoch": 0.22,
"learning_rate": 1.8133909445815277e-05,
"loss": 0.8799,
"step": 576
},
{
"epoch": 0.22,
"learning_rate": 1.8126651066586818e-05,
"loss": 0.8765,
"step": 577
},
{
"epoch": 0.22,
"learning_rate": 1.811938005715857e-05,
"loss": 0.8626,
"step": 578
},
{
"epoch": 0.22,
"learning_rate": 1.8112096428830912e-05,
"loss": 0.9336,
"step": 579
},
{
"epoch": 0.22,
"learning_rate": 1.8104800192923856e-05,
"loss": 0.8916,
"step": 580
},
{
"epoch": 0.22,
"learning_rate": 1.8097491360776987e-05,
"loss": 0.925,
"step": 581
},
{
"epoch": 0.22,
"learning_rate": 1.8090169943749477e-05,
"loss": 0.9243,
"step": 582
},
{
"epoch": 0.22,
"learning_rate": 1.8082835953220055e-05,
"loss": 0.9669,
"step": 583
},
{
"epoch": 0.22,
"learning_rate": 1.8075489400586993e-05,
"loss": 0.8705,
"step": 584
},
{
"epoch": 0.23,
"learning_rate": 1.806813029726808e-05,
"loss": 0.8802,
"step": 585
},
{
"epoch": 0.23,
"learning_rate": 1.8060758654700622e-05,
"loss": 0.511,
"step": 586
},
{
"epoch": 0.23,
"learning_rate": 1.8053374484341403e-05,
"loss": 0.915,
"step": 587
},
{
"epoch": 0.23,
"learning_rate": 1.8045977797666685e-05,
"loss": 0.9005,
"step": 588
},
{
"epoch": 0.23,
"learning_rate": 1.8038568606172172e-05,
"loss": 0.8856,
"step": 589
},
{
"epoch": 0.23,
"learning_rate": 1.803114692137302e-05,
"loss": 0.9009,
"step": 590
},
{
"epoch": 0.23,
"learning_rate": 1.8023712754803783e-05,
"loss": 0.9451,
"step": 591
},
{
"epoch": 0.23,
"learning_rate": 1.801626611801842e-05,
"loss": 0.9038,
"step": 592
},
{
"epoch": 0.23,
"learning_rate": 1.8008807022590283e-05,
"loss": 0.8473,
"step": 593
},
{
"epoch": 0.23,
"learning_rate": 1.8001335480112067e-05,
"loss": 0.8999,
"step": 594
},
{
"epoch": 0.23,
"learning_rate": 1.7993851502195822e-05,
"loss": 0.913,
"step": 595
},
{
"epoch": 0.23,
"learning_rate": 1.798635510047293e-05,
"loss": 0.8696,
"step": 596
},
{
"epoch": 0.23,
"learning_rate": 1.7978846286594073e-05,
"loss": 0.9142,
"step": 597
},
{
"epoch": 0.23,
"learning_rate": 1.7971325072229227e-05,
"loss": 0.9072,
"step": 598
},
{
"epoch": 0.23,
"learning_rate": 1.7963791469067637e-05,
"loss": 0.8375,
"step": 599
},
{
"epoch": 0.23,
"learning_rate": 1.795624548881781e-05,
"loss": 0.8958,
"step": 600
},
{
"epoch": 0.23,
"learning_rate": 1.7948687143207485e-05,
"loss": 0.9091,
"step": 601
},
{
"epoch": 0.23,
"learning_rate": 1.7941116443983612e-05,
"loss": 0.8773,
"step": 602
},
{
"epoch": 0.23,
"learning_rate": 1.7933533402912354e-05,
"loss": 0.908,
"step": 603
},
{
"epoch": 0.23,
"learning_rate": 1.7925938031779044e-05,
"loss": 0.863,
"step": 604
},
{
"epoch": 0.23,
"learning_rate": 1.7918330342388183e-05,
"loss": 0.8563,
"step": 605
},
{
"epoch": 0.23,
"learning_rate": 1.7910710346563417e-05,
"loss": 0.86,
"step": 606
},
{
"epoch": 0.23,
"learning_rate": 1.7903078056147515e-05,
"loss": 0.9226,
"step": 607
},
{
"epoch": 0.23,
"learning_rate": 1.7895433483002356e-05,
"loss": 0.8989,
"step": 608
},
{
"epoch": 0.23,
"learning_rate": 1.7887776639008912e-05,
"loss": 0.9434,
"step": 609
},
{
"epoch": 0.23,
"learning_rate": 1.788010753606722e-05,
"loss": 0.9133,
"step": 610
},
{
"epoch": 0.24,
"learning_rate": 1.7872426186096374e-05,
"loss": 0.887,
"step": 611
},
{
"epoch": 0.24,
"learning_rate": 1.78647326010345e-05,
"loss": 0.9623,
"step": 612
},
{
"epoch": 0.24,
"learning_rate": 1.785702679283874e-05,
"loss": 0.9354,
"step": 613
},
{
"epoch": 0.24,
"learning_rate": 1.7849308773485226e-05,
"loss": 0.8619,
"step": 614
},
{
"epoch": 0.24,
"learning_rate": 1.784157855496908e-05,
"loss": 0.9506,
"step": 615
},
{
"epoch": 0.24,
"learning_rate": 1.783383614930438e-05,
"loss": 0.938,
"step": 616
},
{
"epoch": 0.24,
"learning_rate": 1.782608156852414e-05,
"loss": 0.8665,
"step": 617
},
{
"epoch": 0.24,
"learning_rate": 1.78183148246803e-05,
"loss": 0.8925,
"step": 618
},
{
"epoch": 0.24,
"learning_rate": 1.7810535929843703e-05,
"loss": 0.8743,
"step": 619
},
{
"epoch": 0.24,
"learning_rate": 1.780274489610407e-05,
"loss": 0.8503,
"step": 620
},
{
"epoch": 0.24,
"learning_rate": 1.7794941735570005e-05,
"loss": 0.8939,
"step": 621
},
{
"epoch": 0.24,
"learning_rate": 1.778712646036894e-05,
"loss": 0.8885,
"step": 622
},
{
"epoch": 0.24,
"learning_rate": 1.777929908264715e-05,
"loss": 0.8777,
"step": 623
},
{
"epoch": 0.24,
"learning_rate": 1.777145961456971e-05,
"loss": 0.8978,
"step": 624
},
{
"epoch": 0.24,
"learning_rate": 1.7763608068320487e-05,
"loss": 0.9075,
"step": 625
},
{
"epoch": 0.24,
"learning_rate": 1.7755744456102123e-05,
"loss": 0.8777,
"step": 626
},
{
"epoch": 0.24,
"learning_rate": 1.7747868790136012e-05,
"loss": 0.8998,
"step": 627
},
{
"epoch": 0.24,
"learning_rate": 1.7739981082662275e-05,
"loss": 0.8841,
"step": 628
},
{
"epoch": 0.24,
"learning_rate": 1.773208134593976e-05,
"loss": 0.8815,
"step": 629
},
{
"epoch": 0.24,
"learning_rate": 1.7724169592245996e-05,
"loss": 0.9678,
"step": 630
},
{
"epoch": 0.24,
"learning_rate": 1.7716245833877202e-05,
"loss": 0.927,
"step": 631
},
{
"epoch": 0.24,
"learning_rate": 1.7708310083148242e-05,
"loss": 0.8792,
"step": 632
},
{
"epoch": 0.24,
"learning_rate": 1.7700362352392632e-05,
"loss": 0.8743,
"step": 633
},
{
"epoch": 0.24,
"learning_rate": 1.769240265396249e-05,
"loss": 0.8688,
"step": 634
},
{
"epoch": 0.24,
"learning_rate": 1.7684431000228548e-05,
"loss": 0.8821,
"step": 635
},
{
"epoch": 0.24,
"learning_rate": 1.7676447403580114e-05,
"loss": 0.916,
"step": 636
},
{
"epoch": 0.25,
"learning_rate": 1.7668451876425056e-05,
"loss": 0.8818,
"step": 637
},
{
"epoch": 0.25,
"learning_rate": 1.766044443118978e-05,
"loss": 0.9088,
"step": 638
},
{
"epoch": 0.25,
"learning_rate": 1.765242508031923e-05,
"loss": 0.9006,
"step": 639
},
{
"epoch": 0.25,
"learning_rate": 1.7644393836276832e-05,
"loss": 0.8906,
"step": 640
},
{
"epoch": 0.25,
"learning_rate": 1.7636350711544518e-05,
"loss": 0.8931,
"step": 641
},
{
"epoch": 0.25,
"learning_rate": 1.7628295718622666e-05,
"loss": 0.8569,
"step": 642
},
{
"epoch": 0.25,
"learning_rate": 1.762022887003011e-05,
"loss": 0.931,
"step": 643
},
{
"epoch": 0.25,
"learning_rate": 1.7612150178304102e-05,
"loss": 0.9096,
"step": 644
},
{
"epoch": 0.25,
"learning_rate": 1.7604059656000313e-05,
"loss": 0.8752,
"step": 645
},
{
"epoch": 0.25,
"learning_rate": 1.7595957315692782e-05,
"loss": 0.8783,
"step": 646
},
{
"epoch": 0.25,
"learning_rate": 1.7587843169973934e-05,
"loss": 0.8981,
"step": 647
},
{
"epoch": 0.25,
"learning_rate": 1.757971723145453e-05,
"loss": 0.9271,
"step": 648
},
{
"epoch": 0.25,
"learning_rate": 1.7571579512763665e-05,
"loss": 0.8727,
"step": 649
},
{
"epoch": 0.25,
"learning_rate": 1.7563430026548737e-05,
"loss": 0.9332,
"step": 650
},
{
"epoch": 0.25,
"learning_rate": 1.7555268785475438e-05,
"loss": 0.8984,
"step": 651
},
{
"epoch": 0.25,
"learning_rate": 1.7547095802227723e-05,
"loss": 0.92,
"step": 652
},
{
"epoch": 0.25,
"learning_rate": 1.75389110895078e-05,
"loss": 0.8865,
"step": 653
},
{
"epoch": 0.25,
"learning_rate": 1.7530714660036112e-05,
"loss": 0.8978,
"step": 654
},
{
"epoch": 0.25,
"learning_rate": 1.7522506526551303e-05,
"loss": 0.9332,
"step": 655
},
{
"epoch": 0.25,
"learning_rate": 1.7514286701810203e-05,
"loss": 0.8781,
"step": 656
},
{
"epoch": 0.25,
"learning_rate": 1.7506055198587835e-05,
"loss": 0.8619,
"step": 657
},
{
"epoch": 0.25,
"learning_rate": 1.7497812029677344e-05,
"loss": 0.8391,
"step": 658
},
{
"epoch": 0.25,
"learning_rate": 1.7489557207890025e-05,
"loss": 0.9003,
"step": 659
},
{
"epoch": 0.25,
"learning_rate": 1.748129074605527e-05,
"loss": 0.9166,
"step": 660
},
{
"epoch": 0.25,
"learning_rate": 1.7473012657020577e-05,
"loss": 0.9169,
"step": 661
},
{
"epoch": 0.25,
"learning_rate": 1.7464722953651504e-05,
"loss": 0.8693,
"step": 662
},
{
"epoch": 0.26,
"learning_rate": 1.7456421648831658e-05,
"loss": 0.8749,
"step": 663
},
{
"epoch": 0.26,
"learning_rate": 1.7448108755462684e-05,
"loss": 0.8579,
"step": 664
},
{
"epoch": 0.26,
"learning_rate": 1.7439784286464234e-05,
"loss": 0.8715,
"step": 665
},
{
"epoch": 0.26,
"learning_rate": 1.7431448254773943e-05,
"loss": 0.9222,
"step": 666
},
{
"epoch": 0.26,
"learning_rate": 1.7423100673347435e-05,
"loss": 0.8893,
"step": 667
},
{
"epoch": 0.26,
"learning_rate": 1.741474155515827e-05,
"loss": 0.8319,
"step": 668
},
{
"epoch": 0.26,
"learning_rate": 1.7406370913197938e-05,
"loss": 0.9221,
"step": 669
},
{
"epoch": 0.26,
"learning_rate": 1.7397988760475842e-05,
"loss": 0.9094,
"step": 670
},
{
"epoch": 0.26,
"learning_rate": 1.738959511001928e-05,
"loss": 0.8699,
"step": 671
},
{
"epoch": 0.26,
"learning_rate": 1.738118997487341e-05,
"loss": 0.8779,
"step": 672
},
{
"epoch": 0.26,
"learning_rate": 1.737277336810124e-05,
"loss": 0.8861,
"step": 673
},
{
"epoch": 0.26,
"learning_rate": 1.736434530278362e-05,
"loss": 0.9344,
"step": 674
},
{
"epoch": 0.26,
"learning_rate": 1.7355905792019195e-05,
"loss": 0.9017,
"step": 675
},
{
"epoch": 0.26,
"learning_rate": 1.73474548489244e-05,
"loss": 0.864,
"step": 676
},
{
"epoch": 0.26,
"learning_rate": 1.7338992486633438e-05,
"loss": 0.8845,
"step": 677
},
{
"epoch": 0.26,
"learning_rate": 1.7330518718298263e-05,
"loss": 0.898,
"step": 678
},
{
"epoch": 0.26,
"learning_rate": 1.732203355708856e-05,
"loss": 0.9048,
"step": 679
},
{
"epoch": 0.26,
"learning_rate": 1.7313537016191706e-05,
"loss": 0.8683,
"step": 680
},
{
"epoch": 0.26,
"learning_rate": 1.7305029108812777e-05,
"loss": 0.8473,
"step": 681
},
{
"epoch": 0.26,
"learning_rate": 1.729650984817451e-05,
"loss": 0.8785,
"step": 682
},
{
"epoch": 0.26,
"learning_rate": 1.7287979247517285e-05,
"loss": 0.8901,
"step": 683
},
{
"epoch": 0.26,
"learning_rate": 1.727943732009911e-05,
"loss": 0.9042,
"step": 684
},
{
"epoch": 0.26,
"learning_rate": 1.7270884079195596e-05,
"loss": 0.8431,
"step": 685
},
{
"epoch": 0.26,
"learning_rate": 1.726231953809993e-05,
"loss": 0.9176,
"step": 686
},
{
"epoch": 0.26,
"learning_rate": 1.7253743710122877e-05,
"loss": 0.9041,
"step": 687
},
{
"epoch": 0.26,
"learning_rate": 1.7245156608592727e-05,
"loss": 0.8737,
"step": 688
},
{
"epoch": 0.27,
"learning_rate": 1.7236558246855303e-05,
"loss": 0.8737,
"step": 689
},
{
"epoch": 0.27,
"learning_rate": 1.7227948638273918e-05,
"loss": 0.829,
"step": 690
},
{
"epoch": 0.27,
"learning_rate": 1.721932779622937e-05,
"loss": 0.906,
"step": 691
},
{
"epoch": 0.27,
"learning_rate": 1.7210695734119926e-05,
"loss": 0.8928,
"step": 692
},
{
"epoch": 0.27,
"learning_rate": 1.7202052465361268e-05,
"loss": 0.8822,
"step": 693
},
{
"epoch": 0.27,
"learning_rate": 1.7193398003386514e-05,
"loss": 0.8984,
"step": 694
},
{
"epoch": 0.27,
"learning_rate": 1.7184732361646168e-05,
"loss": 0.8403,
"step": 695
},
{
"epoch": 0.27,
"learning_rate": 1.717605555360812e-05,
"loss": 0.536,
"step": 696
},
{
"epoch": 0.27,
"learning_rate": 1.71673675927576e-05,
"loss": 0.528,
"step": 697
},
{
"epoch": 0.27,
"learning_rate": 1.7158668492597186e-05,
"loss": 0.8459,
"step": 698
},
{
"epoch": 0.27,
"learning_rate": 1.7149958266646756e-05,
"loss": 0.8998,
"step": 699
},
{
"epoch": 0.27,
"learning_rate": 1.7141236928443482e-05,
"loss": 0.9531,
"step": 700
},
{
"epoch": 0.27,
"learning_rate": 1.713250449154182e-05,
"loss": 0.5769,
"step": 701
},
{
"epoch": 0.27,
"learning_rate": 1.712376096951345e-05,
"loss": 0.8712,
"step": 702
},
{
"epoch": 0.27,
"learning_rate": 1.7115006375947304e-05,
"loss": 0.8944,
"step": 703
},
{
"epoch": 0.27,
"learning_rate": 1.7106240724449507e-05,
"loss": 0.9298,
"step": 704
},
{
"epoch": 0.27,
"learning_rate": 1.7097464028643376e-05,
"loss": 0.8186,
"step": 705
},
{
"epoch": 0.27,
"learning_rate": 1.7088676302169394e-05,
"loss": 0.8778,
"step": 706
},
{
"epoch": 0.27,
"learning_rate": 1.7079877558685178e-05,
"loss": 0.8909,
"step": 707
},
{
"epoch": 0.27,
"learning_rate": 1.7071067811865477e-05,
"loss": 0.8497,
"step": 708
},
{
"epoch": 0.27,
"learning_rate": 1.7062247075402137e-05,
"loss": 0.8797,
"step": 709
},
{
"epoch": 0.27,
"learning_rate": 1.705341536300409e-05,
"loss": 0.9125,
"step": 710
},
{
"epoch": 0.27,
"learning_rate": 1.7044572688397316e-05,
"loss": 0.8411,
"step": 711
},
{
"epoch": 0.27,
"learning_rate": 1.7035719065324837e-05,
"loss": 0.9036,
"step": 712
},
{
"epoch": 0.27,
"learning_rate": 1.7026854507546694e-05,
"loss": 0.8938,
"step": 713
},
{
"epoch": 0.27,
"learning_rate": 1.7017979028839918e-05,
"loss": 0.9,
"step": 714
},
{
"epoch": 0.28,
"learning_rate": 1.700909264299851e-05,
"loss": 0.8785,
"step": 715
},
{
"epoch": 0.28,
"learning_rate": 1.7000195363833434e-05,
"loss": 0.906,
"step": 716
},
{
"epoch": 0.28,
"learning_rate": 1.6991287205172575e-05,
"loss": 0.9128,
"step": 717
},
{
"epoch": 0.28,
"learning_rate": 1.698236818086073e-05,
"loss": 0.9069,
"step": 718
},
{
"epoch": 0.28,
"learning_rate": 1.697343830475958e-05,
"loss": 0.9117,
"step": 719
},
{
"epoch": 0.28,
"learning_rate": 1.696449759074767e-05,
"loss": 0.9349,
"step": 720
},
{
"epoch": 0.28,
"learning_rate": 1.6955546052720398e-05,
"loss": 0.83,
"step": 721
},
{
"epoch": 0.28,
"learning_rate": 1.6946583704589973e-05,
"loss": 0.887,
"step": 722
},
{
"epoch": 0.28,
"learning_rate": 1.693761056028542e-05,
"loss": 0.8619,
"step": 723
},
{
"epoch": 0.28,
"learning_rate": 1.692862663375252e-05,
"loss": 0.86,
"step": 724
},
{
"epoch": 0.28,
"learning_rate": 1.6919631938953835e-05,
"loss": 0.8904,
"step": 725
},
{
"epoch": 0.28,
"learning_rate": 1.691062648986865e-05,
"loss": 0.8949,
"step": 726
},
{
"epoch": 0.28,
"learning_rate": 1.6901610300492963e-05,
"loss": 0.869,
"step": 727
},
{
"epoch": 0.28,
"learning_rate": 1.689258338483947e-05,
"loss": 0.8872,
"step": 728
},
{
"epoch": 0.28,
"learning_rate": 1.688354575693754e-05,
"loss": 0.8885,
"step": 729
},
{
"epoch": 0.28,
"learning_rate": 1.6874497430833182e-05,
"loss": 0.8516,
"step": 730
},
{
"epoch": 0.28,
"learning_rate": 1.6865438420589036e-05,
"loss": 0.9103,
"step": 731
},
{
"epoch": 0.28,
"learning_rate": 1.6856368740284342e-05,
"loss": 0.9095,
"step": 732
},
{
"epoch": 0.28,
"learning_rate": 1.6847288404014937e-05,
"loss": 0.8777,
"step": 733
},
{
"epoch": 0.28,
"learning_rate": 1.68381974258932e-05,
"loss": 0.8585,
"step": 734
},
{
"epoch": 0.28,
"learning_rate": 1.682909582004807e-05,
"loss": 0.8837,
"step": 735
},
{
"epoch": 0.28,
"learning_rate": 1.6819983600624986e-05,
"loss": 0.8589,
"step": 736
},
{
"epoch": 0.28,
"learning_rate": 1.681086078178589e-05,
"loss": 0.8803,
"step": 737
},
{
"epoch": 0.28,
"learning_rate": 1.6801727377709195e-05,
"loss": 0.5364,
"step": 738
},
{
"epoch": 0.28,
"learning_rate": 1.679258340258977e-05,
"loss": 0.8914,
"step": 739
},
{
"epoch": 0.28,
"learning_rate": 1.6783428870638904e-05,
"loss": 0.8793,
"step": 740
},
{
"epoch": 0.29,
"learning_rate": 1.6774263796084304e-05,
"loss": 0.9121,
"step": 741
},
{
"epoch": 0.29,
"learning_rate": 1.6765088193170055e-05,
"loss": 0.8822,
"step": 742
},
{
"epoch": 0.29,
"learning_rate": 1.6755902076156606e-05,
"loss": 0.9175,
"step": 743
},
{
"epoch": 0.29,
"learning_rate": 1.6746705459320746e-05,
"loss": 0.926,
"step": 744
},
{
"epoch": 0.29,
"learning_rate": 1.6737498356955586e-05,
"loss": 0.975,
"step": 745
},
{
"epoch": 0.29,
"learning_rate": 1.672828078337053e-05,
"loss": 0.8403,
"step": 746
},
{
"epoch": 0.29,
"learning_rate": 1.6719052752891262e-05,
"loss": 0.9081,
"step": 747
},
{
"epoch": 0.29,
"learning_rate": 1.67098142798597e-05,
"loss": 0.88,
"step": 748
},
{
"epoch": 0.29,
"learning_rate": 1.6700565378634022e-05,
"loss": 0.8966,
"step": 749
},
{
"epoch": 0.29,
"learning_rate": 1.6691306063588583e-05,
"loss": 0.8831,
"step": 750
},
{
"epoch": 0.29,
"learning_rate": 1.668203634911394e-05,
"loss": 0.8518,
"step": 751
},
{
"epoch": 0.29,
"learning_rate": 1.667275624961681e-05,
"loss": 0.9,
"step": 752
},
{
"epoch": 0.29,
"learning_rate": 1.6663465779520042e-05,
"loss": 0.5714,
"step": 753
},
{
"epoch": 0.29,
"learning_rate": 1.6654164953262614e-05,
"loss": 0.868,
"step": 754
},
{
"epoch": 0.29,
"learning_rate": 1.6644853785299592e-05,
"loss": 0.8603,
"step": 755
},
{
"epoch": 0.29,
"learning_rate": 1.6635532290102114e-05,
"loss": 0.8463,
"step": 756
},
{
"epoch": 0.29,
"learning_rate": 1.6626200482157378e-05,
"loss": 0.9042,
"step": 757
},
{
"epoch": 0.29,
"learning_rate": 1.6616858375968596e-05,
"loss": 0.9209,
"step": 758
},
{
"epoch": 0.29,
"learning_rate": 1.6607505986054998e-05,
"loss": 0.8909,
"step": 759
},
{
"epoch": 0.29,
"learning_rate": 1.6598143326951784e-05,
"loss": 0.8822,
"step": 760
},
{
"epoch": 0.29,
"learning_rate": 1.6588770413210126e-05,
"loss": 0.8193,
"step": 761
},
{
"epoch": 0.29,
"learning_rate": 1.657938725939713e-05,
"loss": 0.835,
"step": 762
},
{
"epoch": 0.29,
"learning_rate": 1.6569993880095807e-05,
"loss": 0.8528,
"step": 763
},
{
"epoch": 0.29,
"learning_rate": 1.6560590289905074e-05,
"loss": 0.8887,
"step": 764
},
{
"epoch": 0.29,
"learning_rate": 1.6551176503439713e-05,
"loss": 0.8615,
"step": 765
},
{
"epoch": 0.29,
"learning_rate": 1.6541752535330345e-05,
"loss": 0.8986,
"step": 766
},
{
"epoch": 0.3,
"learning_rate": 1.6532318400223427e-05,
"loss": 0.8963,
"step": 767
},
{
"epoch": 0.3,
"learning_rate": 1.6522874112781213e-05,
"loss": 0.8762,
"step": 768
},
{
"epoch": 0.3,
"learning_rate": 1.651341968768173e-05,
"loss": 0.8802,
"step": 769
},
{
"epoch": 0.3,
"learning_rate": 1.6503955139618765e-05,
"loss": 0.9022,
"step": 770
},
{
"epoch": 0.3,
"learning_rate": 1.6494480483301836e-05,
"loss": 0.8704,
"step": 771
},
{
"epoch": 0.3,
"learning_rate": 1.6484995733456178e-05,
"loss": 0.8608,
"step": 772
},
{
"epoch": 0.3,
"learning_rate": 1.6475500904822707e-05,
"loss": 0.9179,
"step": 773
},
{
"epoch": 0.3,
"learning_rate": 1.6465996012157996e-05,
"loss": 0.918,
"step": 774
},
{
"epoch": 0.3,
"learning_rate": 1.6456481070234277e-05,
"loss": 0.8964,
"step": 775
},
{
"epoch": 0.3,
"learning_rate": 1.6446956093839385e-05,
"loss": 0.8542,
"step": 776
},
{
"epoch": 0.3,
"learning_rate": 1.6437421097776754e-05,
"loss": 0.9209,
"step": 777
},
{
"epoch": 0.3,
"learning_rate": 1.6427876096865394e-05,
"loss": 0.9108,
"step": 778
},
{
"epoch": 0.3,
"learning_rate": 1.6418321105939863e-05,
"loss": 0.8861,
"step": 779
},
{
"epoch": 0.3,
"learning_rate": 1.6408756139850243e-05,
"loss": 0.8948,
"step": 780
},
{
"epoch": 0.3,
"learning_rate": 1.639918121346212e-05,
"loss": 0.8634,
"step": 781
},
{
"epoch": 0.3,
"learning_rate": 1.638959634165656e-05,
"loss": 0.7939,
"step": 782
},
{
"epoch": 0.3,
"learning_rate": 1.6380001539330088e-05,
"loss": 0.8795,
"step": 783
},
{
"epoch": 0.3,
"learning_rate": 1.637039682139466e-05,
"loss": 0.8289,
"step": 784
},
{
"epoch": 0.3,
"learning_rate": 1.636078220277764e-05,
"loss": 0.902,
"step": 785
},
{
"epoch": 0.3,
"learning_rate": 1.635115769842179e-05,
"loss": 0.8561,
"step": 786
},
{
"epoch": 0.3,
"learning_rate": 1.634152332328522e-05,
"loss": 0.9473,
"step": 787
},
{
"epoch": 0.3,
"learning_rate": 1.6331879092341402e-05,
"loss": 0.87,
"step": 788
},
{
"epoch": 0.3,
"learning_rate": 1.63222250205791e-05,
"loss": 0.8711,
"step": 789
},
{
"epoch": 0.3,
"learning_rate": 1.631256112300239e-05,
"loss": 0.847,
"step": 790
},
{
"epoch": 0.3,
"learning_rate": 1.630288741463062e-05,
"loss": 0.9375,
"step": 791
},
{
"epoch": 0.3,
"learning_rate": 1.6293203910498375e-05,
"loss": 0.932,
"step": 792
},
{
"epoch": 0.31,
"learning_rate": 1.6283510625655474e-05,
"loss": 0.8857,
"step": 793
},
{
"epoch": 0.31,
"learning_rate": 1.6273807575166927e-05,
"loss": 0.8855,
"step": 794
},
{
"epoch": 0.31,
"learning_rate": 1.626409477411293e-05,
"loss": 0.8641,
"step": 795
},
{
"epoch": 0.31,
"learning_rate": 1.625437223758883e-05,
"loss": 0.887,
"step": 796
},
{
"epoch": 0.31,
"learning_rate": 1.6244639980705104e-05,
"loss": 0.8808,
"step": 797
},
{
"epoch": 0.31,
"learning_rate": 1.6234898018587336e-05,
"loss": 0.9019,
"step": 798
},
{
"epoch": 0.31,
"learning_rate": 1.6225146366376198e-05,
"loss": 0.8378,
"step": 799
},
{
"epoch": 0.31,
"learning_rate": 1.621538503922741e-05,
"loss": 0.8884,
"step": 800
},
{
"epoch": 0.31,
"learning_rate": 1.620561405231175e-05,
"loss": 0.9275,
"step": 801
},
{
"epoch": 0.31,
"learning_rate": 1.6195833420814983e-05,
"loss": 0.8799,
"step": 802
},
{
"epoch": 0.31,
"learning_rate": 1.6186043159937884e-05,
"loss": 0.8963,
"step": 803
},
{
"epoch": 0.31,
"learning_rate": 1.617624328489618e-05,
"loss": 0.876,
"step": 804
},
{
"epoch": 0.31,
"learning_rate": 1.616643381092055e-05,
"loss": 0.8724,
"step": 805
},
{
"epoch": 0.31,
"learning_rate": 1.6156614753256583e-05,
"loss": 0.844,
"step": 806
},
{
"epoch": 0.31,
"learning_rate": 1.6146786127164773e-05,
"loss": 0.8668,
"step": 807
},
{
"epoch": 0.31,
"learning_rate": 1.6136947947920477e-05,
"loss": 0.897,
"step": 808
},
{
"epoch": 0.31,
"learning_rate": 1.6127100230813897e-05,
"loss": 0.8683,
"step": 809
},
{
"epoch": 0.31,
"learning_rate": 1.6117242991150064e-05,
"loss": 0.8871,
"step": 810
},
{
"epoch": 0.31,
"learning_rate": 1.610737624424881e-05,
"loss": 0.8571,
"step": 811
},
{
"epoch": 0.31,
"learning_rate": 1.609750000544474e-05,
"loss": 0.8615,
"step": 812
},
{
"epoch": 0.31,
"learning_rate": 1.608761429008721e-05,
"loss": 0.8389,
"step": 813
},
{
"epoch": 0.31,
"learning_rate": 1.6077719113540303e-05,
"loss": 0.8929,
"step": 814
},
{
"epoch": 0.31,
"learning_rate": 1.6067814491182806e-05,
"loss": 0.8702,
"step": 815
},
{
"epoch": 0.31,
"learning_rate": 1.60579004384082e-05,
"loss": 0.8846,
"step": 816
},
{
"epoch": 0.31,
"learning_rate": 1.6047976970624603e-05,
"loss": 0.9292,
"step": 817
},
{
"epoch": 0.31,
"learning_rate": 1.6038044103254775e-05,
"loss": 0.8599,
"step": 818
},
{
"epoch": 0.32,
"learning_rate": 1.6028101851736083e-05,
"loss": 0.8348,
"step": 819
},
{
"epoch": 0.32,
"learning_rate": 1.6018150231520486e-05,
"loss": 0.8829,
"step": 820
},
{
"epoch": 0.32,
"learning_rate": 1.6008189258074483e-05,
"loss": 0.8909,
"step": 821
},
{
"epoch": 0.32,
"learning_rate": 1.599821894687914e-05,
"loss": 0.8918,
"step": 822
},
{
"epoch": 0.32,
"learning_rate": 1.5988239313430004e-05,
"loss": 0.8396,
"step": 823
},
{
"epoch": 0.32,
"learning_rate": 1.5978250373237132e-05,
"loss": 0.9114,
"step": 824
},
{
"epoch": 0.32,
"learning_rate": 1.5968252141825038e-05,
"loss": 0.8772,
"step": 825
},
{
"epoch": 0.32,
"learning_rate": 1.5958244634732673e-05,
"loss": 0.9785,
"step": 826
},
{
"epoch": 0.32,
"learning_rate": 1.5948227867513416e-05,
"loss": 0.8708,
"step": 827
},
{
"epoch": 0.32,
"learning_rate": 1.5938201855735017e-05,
"loss": 0.8699,
"step": 828
},
{
"epoch": 0.32,
"learning_rate": 1.5928166614979613e-05,
"loss": 0.8657,
"step": 829
},
{
"epoch": 0.32,
"learning_rate": 1.591812216084368e-05,
"loss": 0.8795,
"step": 830
},
{
"epoch": 0.32,
"learning_rate": 1.5908068508938e-05,
"loss": 0.8754,
"step": 831
},
{
"epoch": 0.32,
"learning_rate": 1.5898005674887673e-05,
"loss": 0.8328,
"step": 832
},
{
"epoch": 0.32,
"learning_rate": 1.5887933674332048e-05,
"loss": 0.8456,
"step": 833
},
{
"epoch": 0.32,
"learning_rate": 1.5877852522924733e-05,
"loss": 0.8681,
"step": 834
},
{
"epoch": 0.32,
"learning_rate": 1.5867762236333553e-05,
"loss": 0.8674,
"step": 835
},
{
"epoch": 0.32,
"learning_rate": 1.585766283024053e-05,
"loss": 0.8906,
"step": 836
},
{
"epoch": 0.32,
"learning_rate": 1.5847554320341865e-05,
"loss": 0.897,
"step": 837
},
{
"epoch": 0.32,
"learning_rate": 1.5837436722347902e-05,
"loss": 0.9093,
"step": 838
},
{
"epoch": 0.32,
"learning_rate": 1.582731005198311e-05,
"loss": 0.8506,
"step": 839
},
{
"epoch": 0.32,
"learning_rate": 1.581717432498606e-05,
"loss": 0.9222,
"step": 840
},
{
"epoch": 0.32,
"learning_rate": 1.5807029557109398e-05,
"loss": 0.9318,
"step": 841
},
{
"epoch": 0.32,
"learning_rate": 1.5796875764119826e-05,
"loss": 0.9061,
"step": 842
},
{
"epoch": 0.32,
"learning_rate": 1.578671296179806e-05,
"loss": 0.8311,
"step": 843
},
{
"epoch": 0.32,
"learning_rate": 1.577654116593883e-05,
"loss": 0.8681,
"step": 844
},
{
"epoch": 0.33,
"learning_rate": 1.5766360392350837e-05,
"loss": 0.8796,
"step": 845
},
{
"epoch": 0.33,
"learning_rate": 1.575617065685674e-05,
"loss": 0.908,
"step": 846
},
{
"epoch": 0.33,
"learning_rate": 1.5745971975293114e-05,
"loss": 0.8281,
"step": 847
},
{
"epoch": 0.33,
"learning_rate": 1.573576436351046e-05,
"loss": 0.5652,
"step": 848
},
{
"epoch": 0.33,
"learning_rate": 1.5725547837373142e-05,
"loss": 0.8872,
"step": 849
},
{
"epoch": 0.33,
"learning_rate": 1.5715322412759374e-05,
"loss": 0.849,
"step": 850
},
{
"epoch": 0.33,
"learning_rate": 1.5705088105561217e-05,
"loss": 0.9182,
"step": 851
},
{
"epoch": 0.33,
"learning_rate": 1.569484493168452e-05,
"loss": 0.8939,
"step": 852
},
{
"epoch": 0.33,
"learning_rate": 1.5684592907048925e-05,
"loss": 0.884,
"step": 853
},
{
"epoch": 0.33,
"learning_rate": 1.567433204758782e-05,
"loss": 0.8353,
"step": 854
},
{
"epoch": 0.33,
"learning_rate": 1.566406236924833e-05,
"loss": 0.9299,
"step": 855
},
{
"epoch": 0.33,
"learning_rate": 1.5653783887991282e-05,
"loss": 0.8406,
"step": 856
},
{
"epoch": 0.33,
"learning_rate": 1.564349661979119e-05,
"loss": 0.8894,
"step": 857
},
{
"epoch": 0.33,
"learning_rate": 1.563320058063622e-05,
"loss": 0.9122,
"step": 858
},
{
"epoch": 0.33,
"learning_rate": 1.5622895786528173e-05,
"loss": 0.8575,
"step": 859
},
{
"epoch": 0.33,
"learning_rate": 1.5612582253482444e-05,
"loss": 0.8794,
"step": 860
},
{
"epoch": 0.33,
"learning_rate": 1.5602259997528028e-05,
"loss": 0.8531,
"step": 861
},
{
"epoch": 0.33,
"learning_rate": 1.5591929034707468e-05,
"loss": 0.8732,
"step": 862
},
{
"epoch": 0.33,
"learning_rate": 1.5581589381076843e-05,
"loss": 0.8713,
"step": 863
},
{
"epoch": 0.33,
"learning_rate": 1.5571241052705724e-05,
"loss": 0.8796,
"step": 864
},
{
"epoch": 0.33,
"learning_rate": 1.5560884065677188e-05,
"loss": 0.8418,
"step": 865
},
{
"epoch": 0.33,
"learning_rate": 1.5550518436087753e-05,
"loss": 0.8547,
"step": 866
},
{
"epoch": 0.33,
"learning_rate": 1.5540144180047367e-05,
"loss": 0.9132,
"step": 867
},
{
"epoch": 0.33,
"learning_rate": 1.5529761313679396e-05,
"loss": 0.8965,
"step": 868
},
{
"epoch": 0.33,
"learning_rate": 1.5519369853120584e-05,
"loss": 0.5408,
"step": 869
},
{
"epoch": 0.33,
"learning_rate": 1.5508969814521026e-05,
"loss": 0.9203,
"step": 870
},
{
"epoch": 0.34,
"learning_rate": 1.549856121404416e-05,
"loss": 0.874,
"step": 871
},
{
"epoch": 0.34,
"learning_rate": 1.548814406786671e-05,
"loss": 0.8309,
"step": 872
},
{
"epoch": 0.34,
"learning_rate": 1.5477718392178716e-05,
"loss": 0.821,
"step": 873
},
{
"epoch": 0.34,
"learning_rate": 1.5467284203183437e-05,
"loss": 0.8698,
"step": 874
},
{
"epoch": 0.34,
"learning_rate": 1.5456841517097385e-05,
"loss": 0.9225,
"step": 875
},
{
"epoch": 0.34,
"learning_rate": 1.5446390350150272e-05,
"loss": 0.9114,
"step": 876
},
{
"epoch": 0.34,
"learning_rate": 1.5435930718584993e-05,
"loss": 0.8255,
"step": 877
},
{
"epoch": 0.34,
"learning_rate": 1.5425462638657597e-05,
"loss": 0.8601,
"step": 878
},
{
"epoch": 0.34,
"learning_rate": 1.541498612663726e-05,
"loss": 0.9335,
"step": 879
},
{
"epoch": 0.34,
"learning_rate": 1.5404501198806267e-05,
"loss": 0.8763,
"step": 880
},
{
"epoch": 0.34,
"learning_rate": 1.5394007871459983e-05,
"loss": 0.9281,
"step": 881
},
{
"epoch": 0.34,
"learning_rate": 1.5383506160906826e-05,
"loss": 0.9014,
"step": 882
},
{
"epoch": 0.34,
"learning_rate": 1.5372996083468242e-05,
"loss": 0.8665,
"step": 883
},
{
"epoch": 0.34,
"learning_rate": 1.5362477655478677e-05,
"loss": 0.5207,
"step": 884
},
{
"epoch": 0.34,
"learning_rate": 1.535195089328557e-05,
"loss": 0.8806,
"step": 885
},
{
"epoch": 0.34,
"learning_rate": 1.534141581324929e-05,
"loss": 0.8998,
"step": 886
},
{
"epoch": 0.34,
"learning_rate": 1.533087243174315e-05,
"loss": 0.8764,
"step": 887
},
{
"epoch": 0.34,
"learning_rate": 1.5320320765153367e-05,
"loss": 0.8872,
"step": 888
},
{
"epoch": 0.34,
"learning_rate": 1.530976082987902e-05,
"loss": 0.9017,
"step": 889
},
{
"epoch": 0.34,
"learning_rate": 1.529919264233205e-05,
"loss": 0.8895,
"step": 890
},
{
"epoch": 0.34,
"learning_rate": 1.528861621893722e-05,
"loss": 0.8689,
"step": 891
},
{
"epoch": 0.34,
"learning_rate": 1.527803157613209e-05,
"loss": 0.8682,
"step": 892
},
{
"epoch": 0.34,
"learning_rate": 1.526743873036701e-05,
"loss": 0.5303,
"step": 893
},
{
"epoch": 0.34,
"learning_rate": 1.5256837698105047e-05,
"loss": 0.899,
"step": 894
},
{
"epoch": 0.34,
"learning_rate": 1.5246228495822025e-05,
"loss": 0.891,
"step": 895
},
{
"epoch": 0.34,
"learning_rate": 1.5235611140006446e-05,
"loss": 0.8557,
"step": 896
},
{
"epoch": 0.35,
"learning_rate": 1.5224985647159489e-05,
"loss": 0.8625,
"step": 897
},
{
"epoch": 0.35,
"learning_rate": 1.5214352033794981e-05,
"loss": 0.8553,
"step": 898
},
{
"epoch": 0.35,
"learning_rate": 1.5203710316439368e-05,
"loss": 0.8447,
"step": 899
},
{
"epoch": 0.35,
"learning_rate": 1.5193060511631692e-05,
"loss": 0.8765,
"step": 900
},
{
"epoch": 0.35,
"learning_rate": 1.518240263592356e-05,
"loss": 0.8731,
"step": 901
},
{
"epoch": 0.35,
"learning_rate": 1.5171736705879127e-05,
"loss": 0.8746,
"step": 902
},
{
"epoch": 0.35,
"learning_rate": 1.5161062738075068e-05,
"loss": 0.8607,
"step": 903
},
{
"epoch": 0.35,
"learning_rate": 1.5150380749100545e-05,
"loss": 0.8992,
"step": 904
},
{
"epoch": 0.35,
"learning_rate": 1.5139690755557186e-05,
"loss": 0.8691,
"step": 905
},
{
"epoch": 0.35,
"learning_rate": 1.5128992774059063e-05,
"loss": 0.8883,
"step": 906
},
{
"epoch": 0.35,
"learning_rate": 1.5118286821232661e-05,
"loss": 0.8423,
"step": 907
},
{
"epoch": 0.35,
"learning_rate": 1.5107572913716859e-05,
"loss": 0.8632,
"step": 908
},
{
"epoch": 0.35,
"learning_rate": 1.5096851068162885e-05,
"loss": 0.8625,
"step": 909
},
{
"epoch": 0.35,
"learning_rate": 1.5086121301234318e-05,
"loss": 0.9051,
"step": 910
},
{
"epoch": 0.35,
"learning_rate": 1.5075383629607043e-05,
"loss": 0.8803,
"step": 911
},
{
"epoch": 0.35,
"learning_rate": 1.5064638069969228e-05,
"loss": 0.8409,
"step": 912
},
{
"epoch": 0.35,
"learning_rate": 1.505388463902131e-05,
"loss": 0.851,
"step": 913
},
{
"epoch": 0.35,
"learning_rate": 1.5043123353475944e-05,
"loss": 0.9177,
"step": 914
},
{
"epoch": 0.35,
"learning_rate": 1.5032354230058004e-05,
"loss": 0.845,
"step": 915
},
{
"epoch": 0.35,
"learning_rate": 1.5021577285504538e-05,
"loss": 0.8879,
"step": 916
},
{
"epoch": 0.35,
"learning_rate": 1.5010792536564762e-05,
"loss": 0.8431,
"step": 917
},
{
"epoch": 0.35,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.8097,
"step": 918
},
{
"epoch": 0.35,
"learning_rate": 1.4989199692583705e-05,
"loss": 0.5239,
"step": 919
},
{
"epoch": 0.35,
"learning_rate": 1.4978391631101383e-05,
"loss": 0.8715,
"step": 920
},
{
"epoch": 0.35,
"learning_rate": 1.4967575832350614e-05,
"loss": 0.8708,
"step": 921
},
{
"epoch": 0.35,
"learning_rate": 1.4956752313140978e-05,
"loss": 0.9136,
"step": 922
},
{
"epoch": 0.36,
"learning_rate": 1.4945921090294076e-05,
"loss": 0.8954,
"step": 923
},
{
"epoch": 0.36,
"learning_rate": 1.493508218064347e-05,
"loss": 0.5236,
"step": 924
},
{
"epoch": 0.36,
"learning_rate": 1.4924235601034673e-05,
"loss": 0.8127,
"step": 925
},
{
"epoch": 0.36,
"learning_rate": 1.4913381368325115e-05,
"loss": 0.8545,
"step": 926
},
{
"epoch": 0.36,
"learning_rate": 1.4902519499384122e-05,
"loss": 0.8685,
"step": 927
},
{
"epoch": 0.36,
"learning_rate": 1.4891650011092896e-05,
"loss": 0.8505,
"step": 928
},
{
"epoch": 0.36,
"learning_rate": 1.488077292034446e-05,
"loss": 0.9138,
"step": 929
},
{
"epoch": 0.36,
"learning_rate": 1.4869888244043674e-05,
"loss": 0.9066,
"step": 930
},
{
"epoch": 0.36,
"learning_rate": 1.4858995999107175e-05,
"loss": 0.8613,
"step": 931
},
{
"epoch": 0.36,
"learning_rate": 1.4848096202463373e-05,
"loss": 0.911,
"step": 932
},
{
"epoch": 0.36,
"learning_rate": 1.4837188871052399e-05,
"loss": 0.5259,
"step": 933
},
{
"epoch": 0.36,
"learning_rate": 1.482627402182611e-05,
"loss": 0.5336,
"step": 934
},
{
"epoch": 0.36,
"learning_rate": 1.4815351671748039e-05,
"loss": 0.9009,
"step": 935
},
{
"epoch": 0.36,
"learning_rate": 1.4804421837793379e-05,
"loss": 0.9066,
"step": 936
},
{
"epoch": 0.36,
"learning_rate": 1.479348453694895e-05,
"loss": 0.8977,
"step": 937
},
{
"epoch": 0.36,
"learning_rate": 1.4782539786213184e-05,
"loss": 0.8687,
"step": 938
},
{
"epoch": 0.36,
"learning_rate": 1.4771587602596085e-05,
"loss": 0.858,
"step": 939
},
{
"epoch": 0.36,
"learning_rate": 1.4760628003119213e-05,
"loss": 0.8456,
"step": 940
},
{
"epoch": 0.36,
"learning_rate": 1.4749661004815654e-05,
"loss": 0.9003,
"step": 941
},
{
"epoch": 0.36,
"learning_rate": 1.4738686624729987e-05,
"loss": 0.8561,
"step": 942
},
{
"epoch": 0.36,
"learning_rate": 1.4727704879918272e-05,
"loss": 0.8643,
"step": 943
},
{
"epoch": 0.36,
"learning_rate": 1.4716715787448007e-05,
"loss": 0.8954,
"step": 944
},
{
"epoch": 0.36,
"learning_rate": 1.4705719364398117e-05,
"loss": 0.8798,
"step": 945
},
{
"epoch": 0.36,
"learning_rate": 1.469471562785891e-05,
"loss": 0.8165,
"step": 946
},
{
"epoch": 0.36,
"learning_rate": 1.4683704594932072e-05,
"loss": 0.9189,
"step": 947
},
{
"epoch": 0.36,
"learning_rate": 1.4672686282730622e-05,
"loss": 0.9168,
"step": 948
},
{
"epoch": 0.37,
"learning_rate": 1.4661660708378893e-05,
"loss": 0.8845,
"step": 949
},
{
"epoch": 0.37,
"learning_rate": 1.4650627889012507e-05,
"loss": 0.8155,
"step": 950
},
{
"epoch": 0.37,
"learning_rate": 1.4639587841778342e-05,
"loss": 0.853,
"step": 951
},
{
"epoch": 0.37,
"learning_rate": 1.4628540583834511e-05,
"loss": 0.9197,
"step": 952
},
{
"epoch": 0.37,
"learning_rate": 1.4617486132350343e-05,
"loss": 0.8593,
"step": 953
},
{
"epoch": 0.37,
"learning_rate": 1.4606424504506325e-05,
"loss": 0.9077,
"step": 954
},
{
"epoch": 0.37,
"learning_rate": 1.4595355717494118e-05,
"loss": 0.8864,
"step": 955
},
{
"epoch": 0.37,
"learning_rate": 1.45842797885165e-05,
"loss": 0.8848,
"step": 956
},
{
"epoch": 0.37,
"learning_rate": 1.4573196734787357e-05,
"loss": 0.8401,
"step": 957
},
{
"epoch": 0.37,
"learning_rate": 1.4562106573531632e-05,
"loss": 0.8838,
"step": 958
},
{
"epoch": 0.37,
"learning_rate": 1.455100932198533e-05,
"loss": 0.887,
"step": 959
},
{
"epoch": 0.37,
"learning_rate": 1.4539904997395468e-05,
"loss": 0.8779,
"step": 960
},
{
"epoch": 0.37,
"learning_rate": 1.4528793617020063e-05,
"loss": 0.903,
"step": 961
},
{
"epoch": 0.37,
"learning_rate": 1.4517675198128086e-05,
"loss": 0.8314,
"step": 962
},
{
"epoch": 0.37,
"learning_rate": 1.4506549757999456e-05,
"loss": 0.8254,
"step": 963
},
{
"epoch": 0.37,
"learning_rate": 1.4495417313924996e-05,
"loss": 0.8615,
"step": 964
},
{
"epoch": 0.37,
"learning_rate": 1.4484277883206433e-05,
"loss": 0.8976,
"step": 965
},
{
"epoch": 0.37,
"learning_rate": 1.4473131483156326e-05,
"loss": 0.5527,
"step": 966
},
{
"epoch": 0.37,
"learning_rate": 1.4461978131098089e-05,
"loss": 0.8547,
"step": 967
},
{
"epoch": 0.37,
"learning_rate": 1.4450817844365924e-05,
"loss": 0.752,
"step": 968
},
{
"epoch": 0.37,
"learning_rate": 1.4439650640304822e-05,
"loss": 0.8278,
"step": 969
},
{
"epoch": 0.37,
"learning_rate": 1.4428476536270517e-05,
"loss": 0.8244,
"step": 970
},
{
"epoch": 0.37,
"learning_rate": 1.4417295549629469e-05,
"loss": 0.8898,
"step": 971
},
{
"epoch": 0.37,
"learning_rate": 1.4406107697758838e-05,
"loss": 0.9323,
"step": 972
},
{
"epoch": 0.37,
"learning_rate": 1.4394912998046451e-05,
"loss": 0.9031,
"step": 973
},
{
"epoch": 0.37,
"learning_rate": 1.4383711467890776e-05,
"loss": 0.8226,
"step": 974
},
{
"epoch": 0.38,
"learning_rate": 1.4372503124700899e-05,
"loss": 0.8964,
"step": 975
},
{
"epoch": 0.38,
"learning_rate": 1.4361287985896495e-05,
"loss": 0.8153,
"step": 976
},
{
"epoch": 0.38,
"learning_rate": 1.43500660689078e-05,
"loss": 0.5194,
"step": 977
},
{
"epoch": 0.38,
"learning_rate": 1.4338837391175582e-05,
"loss": 0.8368,
"step": 978
},
{
"epoch": 0.38,
"learning_rate": 1.4327601970151122e-05,
"loss": 0.9196,
"step": 979
},
{
"epoch": 0.38,
"learning_rate": 1.4316359823296174e-05,
"loss": 0.9178,
"step": 980
},
{
"epoch": 0.38,
"learning_rate": 1.4305110968082953e-05,
"loss": 0.8373,
"step": 981
},
{
"epoch": 0.38,
"learning_rate": 1.4293855421994094e-05,
"loss": 0.8527,
"step": 982
},
{
"epoch": 0.38,
"learning_rate": 1.4282593202522627e-05,
"loss": 0.5184,
"step": 983
},
{
"epoch": 0.38,
"learning_rate": 1.4271324327171969e-05,
"loss": 0.8353,
"step": 984
},
{
"epoch": 0.38,
"learning_rate": 1.4260048813455867e-05,
"loss": 0.9045,
"step": 985
},
{
"epoch": 0.38,
"learning_rate": 1.4248766678898386e-05,
"loss": 0.52,
"step": 986
},
{
"epoch": 0.38,
"learning_rate": 1.4237477941033888e-05,
"loss": 0.8782,
"step": 987
},
{
"epoch": 0.38,
"learning_rate": 1.4226182617406996e-05,
"loss": 0.7991,
"step": 988
},
{
"epoch": 0.38,
"learning_rate": 1.4214880725572563e-05,
"loss": 0.8552,
"step": 989
},
{
"epoch": 0.38,
"learning_rate": 1.4203572283095657e-05,
"loss": 0.8695,
"step": 990
},
{
"epoch": 0.38,
"learning_rate": 1.419225730755152e-05,
"loss": 0.8202,
"step": 991
},
{
"epoch": 0.38,
"learning_rate": 1.4180935816525554e-05,
"loss": 0.8589,
"step": 992
},
{
"epoch": 0.38,
"learning_rate": 1.4169607827613284e-05,
"loss": 0.8271,
"step": 993
},
{
"epoch": 0.38,
"learning_rate": 1.415827335842033e-05,
"loss": 0.8566,
"step": 994
},
{
"epoch": 0.38,
"learning_rate": 1.4146932426562391e-05,
"loss": 0.8802,
"step": 995
},
{
"epoch": 0.38,
"learning_rate": 1.4135585049665207e-05,
"loss": 0.8984,
"step": 996
},
{
"epoch": 0.38,
"learning_rate": 1.4124231245364534e-05,
"loss": 0.8862,
"step": 997
},
{
"epoch": 0.38,
"learning_rate": 1.4112871031306118e-05,
"loss": 0.8615,
"step": 998
},
{
"epoch": 0.38,
"learning_rate": 1.4101504425145662e-05,
"loss": 0.8665,
"step": 999
},
{
"epoch": 0.38,
"learning_rate": 1.4090131444548814e-05,
"loss": 0.8332,
"step": 1000
},
{
"epoch": 0.39,
"learning_rate": 1.4078752107191118e-05,
"loss": 0.876,
"step": 1001
},
{
"epoch": 0.39,
"learning_rate": 1.4067366430758004e-05,
"loss": 0.8862,
"step": 1002
},
{
"epoch": 0.39,
"learning_rate": 1.4055974432944753e-05,
"loss": 0.8641,
"step": 1003
},
{
"epoch": 0.39,
"learning_rate": 1.4044576131456466e-05,
"loss": 0.8777,
"step": 1004
},
{
"epoch": 0.39,
"learning_rate": 1.4033171544008053e-05,
"loss": 0.8787,
"step": 1005
},
{
"epoch": 0.39,
"learning_rate": 1.4021760688324175e-05,
"loss": 0.9283,
"step": 1006
},
{
"epoch": 0.39,
"learning_rate": 1.4010343582139252e-05,
"loss": 0.8521,
"step": 1007
},
{
"epoch": 0.39,
"learning_rate": 1.3998920243197408e-05,
"loss": 0.8186,
"step": 1008
},
{
"epoch": 0.39,
"learning_rate": 1.3987490689252463e-05,
"loss": 0.829,
"step": 1009
},
{
"epoch": 0.39,
"learning_rate": 1.3976054938067885e-05,
"loss": 0.8339,
"step": 1010
},
{
"epoch": 0.39,
"learning_rate": 1.3964613007416777e-05,
"loss": 0.8602,
"step": 1011
},
{
"epoch": 0.39,
"learning_rate": 1.3953164915081852e-05,
"loss": 0.8671,
"step": 1012
},
{
"epoch": 0.39,
"learning_rate": 1.3941710678855396e-05,
"loss": 0.812,
"step": 1013
},
{
"epoch": 0.39,
"learning_rate": 1.3930250316539237e-05,
"loss": 0.9106,
"step": 1014
},
{
"epoch": 0.39,
"learning_rate": 1.3918783845944737e-05,
"loss": 0.882,
"step": 1015
},
{
"epoch": 0.39,
"learning_rate": 1.3907311284892737e-05,
"loss": 0.8676,
"step": 1016
},
{
"epoch": 0.39,
"learning_rate": 1.389583265121356e-05,
"loss": 0.8368,
"step": 1017
},
{
"epoch": 0.39,
"learning_rate": 1.3884347962746949e-05,
"loss": 0.8632,
"step": 1018
},
{
"epoch": 0.39,
"learning_rate": 1.3872857237342067e-05,
"loss": 0.538,
"step": 1019
},
{
"epoch": 0.39,
"learning_rate": 1.3861360492857464e-05,
"loss": 0.8983,
"step": 1020
},
{
"epoch": 0.39,
"learning_rate": 1.3849857747161036e-05,
"loss": 0.8893,
"step": 1021
},
{
"epoch": 0.39,
"learning_rate": 1.3838349018130007e-05,
"loss": 0.8685,
"step": 1022
},
{
"epoch": 0.39,
"learning_rate": 1.3826834323650899e-05,
"loss": 0.8768,
"step": 1023
},
{
"epoch": 0.39,
"learning_rate": 1.3815313681619515e-05,
"loss": 0.8271,
"step": 1024
},
{
"epoch": 0.39,
"learning_rate": 1.3803787109940891e-05,
"loss": 0.8494,
"step": 1025
},
{
"epoch": 0.39,
"learning_rate": 1.3792254626529286e-05,
"loss": 0.8395,
"step": 1026
},
{
"epoch": 0.4,
"learning_rate": 1.378071624930814e-05,
"loss": 0.859,
"step": 1027
},
{
"epoch": 0.4,
"learning_rate": 1.3769171996210053e-05,
"loss": 0.8262,
"step": 1028
},
{
"epoch": 0.4,
"learning_rate": 1.3757621885176768e-05,
"loss": 0.8608,
"step": 1029
},
{
"epoch": 0.4,
"learning_rate": 1.3746065934159123e-05,
"loss": 0.8376,
"step": 1030
},
{
"epoch": 0.4,
"learning_rate": 1.3734504161117028e-05,
"loss": 0.8784,
"step": 1031
},
{
"epoch": 0.4,
"learning_rate": 1.3722936584019453e-05,
"loss": 0.901,
"step": 1032
},
{
"epoch": 0.4,
"learning_rate": 1.371136322084438e-05,
"loss": 0.8544,
"step": 1033
},
{
"epoch": 0.4,
"learning_rate": 1.3699784089578791e-05,
"loss": 0.8584,
"step": 1034
},
{
"epoch": 0.4,
"learning_rate": 1.3688199208218623e-05,
"loss": 0.8386,
"step": 1035
},
{
"epoch": 0.4,
"learning_rate": 1.3676608594768754e-05,
"loss": 0.8561,
"step": 1036
},
{
"epoch": 0.4,
"learning_rate": 1.3665012267242974e-05,
"loss": 0.8954,
"step": 1037
},
{
"epoch": 0.4,
"learning_rate": 1.3653410243663953e-05,
"loss": 0.8809,
"step": 1038
},
{
"epoch": 0.4,
"learning_rate": 1.3641802542063208e-05,
"loss": 0.5321,
"step": 1039
},
{
"epoch": 0.4,
"learning_rate": 1.3630189180481083e-05,
"loss": 0.9037,
"step": 1040
},
{
"epoch": 0.4,
"learning_rate": 1.3618570176966723e-05,
"loss": 0.9011,
"step": 1041
},
{
"epoch": 0.4,
"learning_rate": 1.3606945549578039e-05,
"loss": 0.9181,
"step": 1042
},
{
"epoch": 0.4,
"learning_rate": 1.3595315316381676e-05,
"loss": 0.8615,
"step": 1043
},
{
"epoch": 0.4,
"learning_rate": 1.3583679495453e-05,
"loss": 0.8552,
"step": 1044
},
{
"epoch": 0.4,
"learning_rate": 1.3572038104876066e-05,
"loss": 0.9019,
"step": 1045
},
{
"epoch": 0.4,
"learning_rate": 1.356039116274357e-05,
"loss": 0.8085,
"step": 1046
},
{
"epoch": 0.4,
"learning_rate": 1.3548738687156839e-05,
"loss": 0.864,
"step": 1047
},
{
"epoch": 0.4,
"learning_rate": 1.3537080696225815e-05,
"loss": 0.918,
"step": 1048
},
{
"epoch": 0.4,
"learning_rate": 1.3525417208068996e-05,
"loss": 0.9073,
"step": 1049
},
{
"epoch": 0.4,
"learning_rate": 1.3513748240813429e-05,
"loss": 0.8603,
"step": 1050
},
{
"epoch": 0.4,
"learning_rate": 1.3502073812594677e-05,
"loss": 0.8696,
"step": 1051
},
{
"epoch": 0.4,
"learning_rate": 1.3490393941556787e-05,
"loss": 0.5007,
"step": 1052
},
{
"epoch": 0.41,
"learning_rate": 1.3478708645852272e-05,
"loss": 0.9066,
"step": 1053
},
{
"epoch": 0.41,
"learning_rate": 1.3467017943642074e-05,
"loss": 0.8505,
"step": 1054
},
{
"epoch": 0.41,
"learning_rate": 1.3455321853095527e-05,
"loss": 0.8833,
"step": 1055
},
{
"epoch": 0.41,
"learning_rate": 1.3443620392390352e-05,
"loss": 0.8459,
"step": 1056
},
{
"epoch": 0.41,
"learning_rate": 1.3431913579712612e-05,
"loss": 0.8155,
"step": 1057
},
{
"epoch": 0.41,
"learning_rate": 1.342020143325669e-05,
"loss": 0.8735,
"step": 1058
},
{
"epoch": 0.41,
"learning_rate": 1.340848397122525e-05,
"loss": 0.8401,
"step": 1059
},
{
"epoch": 0.41,
"learning_rate": 1.3396761211829229e-05,
"loss": 0.8444,
"step": 1060
},
{
"epoch": 0.41,
"learning_rate": 1.338503317328779e-05,
"loss": 0.8739,
"step": 1061
},
{
"epoch": 0.41,
"learning_rate": 1.3373299873828303e-05,
"loss": 0.9276,
"step": 1062
},
{
"epoch": 0.41,
"learning_rate": 1.336156133168631e-05,
"loss": 0.8547,
"step": 1063
},
{
"epoch": 0.41,
"learning_rate": 1.3349817565105507e-05,
"loss": 0.9098,
"step": 1064
},
{
"epoch": 0.41,
"learning_rate": 1.333806859233771e-05,
"loss": 0.8636,
"step": 1065
},
{
"epoch": 0.41,
"learning_rate": 1.3326314431642821e-05,
"loss": 0.8756,
"step": 1066
},
{
"epoch": 0.41,
"learning_rate": 1.3314555101288808e-05,
"loss": 0.8354,
"step": 1067
},
{
"epoch": 0.41,
"learning_rate": 1.3302790619551673e-05,
"loss": 0.5004,
"step": 1068
},
{
"epoch": 0.41,
"learning_rate": 1.3291021004715423e-05,
"loss": 0.8558,
"step": 1069
},
{
"epoch": 0.41,
"learning_rate": 1.3279246275072046e-05,
"loss": 0.8887,
"step": 1070
},
{
"epoch": 0.41,
"learning_rate": 1.3267466448921475e-05,
"loss": 0.5109,
"step": 1071
},
{
"epoch": 0.41,
"learning_rate": 1.3255681544571568e-05,
"loss": 0.8771,
"step": 1072
},
{
"epoch": 0.41,
"learning_rate": 1.3243891580338074e-05,
"loss": 0.8257,
"step": 1073
},
{
"epoch": 0.41,
"learning_rate": 1.3232096574544602e-05,
"loss": 0.8571,
"step": 1074
},
{
"epoch": 0.41,
"learning_rate": 1.3220296545522601e-05,
"loss": 0.8516,
"step": 1075
},
{
"epoch": 0.41,
"learning_rate": 1.320849151161133e-05,
"loss": 0.8521,
"step": 1076
},
{
"epoch": 0.41,
"learning_rate": 1.3196681491157816e-05,
"loss": 0.8233,
"step": 1077
},
{
"epoch": 0.41,
"learning_rate": 1.3184866502516846e-05,
"loss": 0.8597,
"step": 1078
},
{
"epoch": 0.42,
"learning_rate": 1.3173046564050923e-05,
"loss": 0.8071,
"step": 1079
},
{
"epoch": 0.42,
"learning_rate": 1.3161221694130247e-05,
"loss": 0.8741,
"step": 1080
},
{
"epoch": 0.42,
"learning_rate": 1.3149391911132674e-05,
"loss": 0.819,
"step": 1081
},
{
"epoch": 0.42,
"learning_rate": 1.3137557233443707e-05,
"loss": 0.8282,
"step": 1082
},
{
"epoch": 0.42,
"learning_rate": 1.3125717679456447e-05,
"loss": 0.5354,
"step": 1083
},
{
"epoch": 0.42,
"learning_rate": 1.3113873267571577e-05,
"loss": 0.8752,
"step": 1084
},
{
"epoch": 0.42,
"learning_rate": 1.3102024016197337e-05,
"loss": 0.868,
"step": 1085
},
{
"epoch": 0.42,
"learning_rate": 1.3090169943749475e-05,
"loss": 0.8654,
"step": 1086
},
{
"epoch": 0.42,
"learning_rate": 1.3078311068651241e-05,
"loss": 0.5444,
"step": 1087
},
{
"epoch": 0.42,
"learning_rate": 1.3066447409333345e-05,
"loss": 0.9021,
"step": 1088
},
{
"epoch": 0.42,
"learning_rate": 1.3054578984233935e-05,
"loss": 0.8758,
"step": 1089
},
{
"epoch": 0.42,
"learning_rate": 1.3042705811798565e-05,
"loss": 0.4946,
"step": 1090
},
{
"epoch": 0.42,
"learning_rate": 1.3030827910480167e-05,
"loss": 0.8591,
"step": 1091
},
{
"epoch": 0.42,
"learning_rate": 1.3018945298739022e-05,
"loss": 0.8476,
"step": 1092
},
{
"epoch": 0.42,
"learning_rate": 1.300705799504273e-05,
"loss": 0.546,
"step": 1093
},
{
"epoch": 0.42,
"learning_rate": 1.2995166017866194e-05,
"loss": 0.8489,
"step": 1094
},
{
"epoch": 0.42,
"learning_rate": 1.2983269385691562e-05,
"loss": 0.9023,
"step": 1095
},
{
"epoch": 0.42,
"learning_rate": 1.2971368117008232e-05,
"loss": 0.8744,
"step": 1096
},
{
"epoch": 0.42,
"learning_rate": 1.29594622303128e-05,
"loss": 0.8665,
"step": 1097
},
{
"epoch": 0.42,
"learning_rate": 1.2947551744109044e-05,
"loss": 0.8566,
"step": 1098
},
{
"epoch": 0.42,
"learning_rate": 1.2935636676907886e-05,
"loss": 0.8716,
"step": 1099
},
{
"epoch": 0.42,
"learning_rate": 1.2923717047227368e-05,
"loss": 0.8999,
"step": 1100
},
{
"epoch": 0.42,
"learning_rate": 1.2911792873592628e-05,
"loss": 0.8204,
"step": 1101
},
{
"epoch": 0.42,
"learning_rate": 1.2899864174535863e-05,
"loss": 0.8665,
"step": 1102
},
{
"epoch": 0.42,
"learning_rate": 1.28879309685963e-05,
"loss": 0.8267,
"step": 1103
},
{
"epoch": 0.42,
"learning_rate": 1.2875993274320173e-05,
"loss": 0.8746,
"step": 1104
},
{
"epoch": 0.43,
"learning_rate": 1.2864051110260697e-05,
"loss": 0.8871,
"step": 1105
},
{
"epoch": 0.43,
"learning_rate": 1.2852104494978024e-05,
"loss": 0.8394,
"step": 1106
},
{
"epoch": 0.43,
"learning_rate": 1.284015344703923e-05,
"loss": 0.8159,
"step": 1107
},
{
"epoch": 0.43,
"learning_rate": 1.2828197985018276e-05,
"loss": 0.8453,
"step": 1108
},
{
"epoch": 0.43,
"learning_rate": 1.281623812749599e-05,
"loss": 0.8732,
"step": 1109
},
{
"epoch": 0.43,
"learning_rate": 1.2804273893060028e-05,
"loss": 0.8338,
"step": 1110
},
{
"epoch": 0.43,
"learning_rate": 1.2792305300304848e-05,
"loss": 0.8708,
"step": 1111
},
{
"epoch": 0.43,
"learning_rate": 1.2780332367831678e-05,
"loss": 0.8328,
"step": 1112
},
{
"epoch": 0.43,
"learning_rate": 1.2768355114248493e-05,
"loss": 0.8807,
"step": 1113
},
{
"epoch": 0.43,
"learning_rate": 1.2756373558169992e-05,
"loss": 0.8381,
"step": 1114
},
{
"epoch": 0.43,
"learning_rate": 1.274438771821755e-05,
"loss": 0.8468,
"step": 1115
},
{
"epoch": 0.43,
"learning_rate": 1.2732397613019203e-05,
"loss": 0.8774,
"step": 1116
},
{
"epoch": 0.43,
"learning_rate": 1.2720403261209615e-05,
"loss": 0.8839,
"step": 1117
},
{
"epoch": 0.43,
"learning_rate": 1.2708404681430054e-05,
"loss": 0.843,
"step": 1118
},
{
"epoch": 0.43,
"learning_rate": 1.2696401892328356e-05,
"loss": 0.8961,
"step": 1119
},
{
"epoch": 0.43,
"learning_rate": 1.2684394912558898e-05,
"loss": 0.8229,
"step": 1120
},
{
"epoch": 0.43,
"learning_rate": 1.267238376078257e-05,
"loss": 0.8529,
"step": 1121
},
{
"epoch": 0.43,
"learning_rate": 1.2660368455666752e-05,
"loss": 0.8857,
"step": 1122
},
{
"epoch": 0.43,
"learning_rate": 1.2648349015885272e-05,
"loss": 0.8881,
"step": 1123
},
{
"epoch": 0.43,
"learning_rate": 1.2636325460118388e-05,
"loss": 0.539,
"step": 1124
},
{
"epoch": 0.43,
"learning_rate": 1.262429780705275e-05,
"loss": 0.8763,
"step": 1125
},
{
"epoch": 0.43,
"learning_rate": 1.2612266075381385e-05,
"loss": 0.8284,
"step": 1126
},
{
"epoch": 0.43,
"learning_rate": 1.2600230283803648e-05,
"loss": 0.8458,
"step": 1127
},
{
"epoch": 0.43,
"learning_rate": 1.2588190451025209e-05,
"loss": 0.8873,
"step": 1128
},
{
"epoch": 0.43,
"learning_rate": 1.2576146595758019e-05,
"loss": 0.8386,
"step": 1129
},
{
"epoch": 0.43,
"learning_rate": 1.2564098736720286e-05,
"loss": 0.9003,
"step": 1130
},
{
"epoch": 0.44,
"learning_rate": 1.2552046892636427e-05,
"loss": 0.5204,
"step": 1131
},
{
"epoch": 0.44,
"learning_rate": 1.2539991082237062e-05,
"loss": 0.8256,
"step": 1132
},
{
"epoch": 0.44,
"learning_rate": 1.2527931324258975e-05,
"loss": 0.8547,
"step": 1133
},
{
"epoch": 0.44,
"learning_rate": 1.2515867637445088e-05,
"loss": 0.855,
"step": 1134
},
{
"epoch": 0.44,
"learning_rate": 1.2503800040544417e-05,
"loss": 0.8765,
"step": 1135
},
{
"epoch": 0.44,
"learning_rate": 1.2491728552312066e-05,
"loss": 0.8693,
"step": 1136
},
{
"epoch": 0.44,
"learning_rate": 1.2479653191509182e-05,
"loss": 0.8748,
"step": 1137
},
{
"epoch": 0.44,
"learning_rate": 1.2467573976902936e-05,
"loss": 0.8182,
"step": 1138
},
{
"epoch": 0.44,
"learning_rate": 1.2455490927266485e-05,
"loss": 0.8901,
"step": 1139
},
{
"epoch": 0.44,
"learning_rate": 1.2443404061378941e-05,
"loss": 0.8367,
"step": 1140
},
{
"epoch": 0.44,
"learning_rate": 1.2431313398025356e-05,
"loss": 0.876,
"step": 1141
},
{
"epoch": 0.44,
"learning_rate": 1.2419218955996677e-05,
"loss": 0.8472,
"step": 1142
},
{
"epoch": 0.44,
"learning_rate": 1.2407120754089733e-05,
"loss": 0.8705,
"step": 1143
},
{
"epoch": 0.44,
"learning_rate": 1.239501881110718e-05,
"loss": 0.8745,
"step": 1144
},
{
"epoch": 0.44,
"learning_rate": 1.2382913145857507e-05,
"loss": 0.8842,
"step": 1145
},
{
"epoch": 0.44,
"learning_rate": 1.2370803777154976e-05,
"loss": 0.8511,
"step": 1146
},
{
"epoch": 0.44,
"learning_rate": 1.2358690723819611e-05,
"loss": 0.8264,
"step": 1147
},
{
"epoch": 0.44,
"learning_rate": 1.2346574004677154e-05,
"loss": 0.885,
"step": 1148
},
{
"epoch": 0.44,
"learning_rate": 1.2334453638559057e-05,
"loss": 0.8749,
"step": 1149
},
{
"epoch": 0.44,
"learning_rate": 1.2322329644302426e-05,
"loss": 0.8954,
"step": 1150
},
{
"epoch": 0.44,
"learning_rate": 1.2310202040750022e-05,
"loss": 0.8571,
"step": 1151
},
{
"epoch": 0.44,
"learning_rate": 1.2298070846750197e-05,
"loss": 0.8336,
"step": 1152
},
{
"epoch": 0.44,
"learning_rate": 1.2285936081156897e-05,
"loss": 0.8598,
"step": 1153
},
{
"epoch": 0.44,
"learning_rate": 1.2273797762829615e-05,
"loss": 0.8833,
"step": 1154
},
{
"epoch": 0.44,
"learning_rate": 1.2261655910633365e-05,
"loss": 0.8734,
"step": 1155
},
{
"epoch": 0.44,
"learning_rate": 1.2249510543438652e-05,
"loss": 0.8715,
"step": 1156
},
{
"epoch": 0.45,
"learning_rate": 1.2237361680121445e-05,
"loss": 0.8535,
"step": 1157
},
{
"epoch": 0.45,
"learning_rate": 1.2225209339563144e-05,
"loss": 0.8942,
"step": 1158
},
{
"epoch": 0.45,
"learning_rate": 1.2213053540650566e-05,
"loss": 0.5012,
"step": 1159
},
{
"epoch": 0.45,
"learning_rate": 1.2200894302275878e-05,
"loss": 0.8708,
"step": 1160
},
{
"epoch": 0.45,
"learning_rate": 1.2188731643336615e-05,
"loss": 0.8768,
"step": 1161
},
{
"epoch": 0.45,
"learning_rate": 1.2176565582735624e-05,
"loss": 0.8569,
"step": 1162
},
{
"epoch": 0.45,
"learning_rate": 1.2164396139381029e-05,
"loss": 0.8571,
"step": 1163
},
{
"epoch": 0.45,
"learning_rate": 1.2152223332186222e-05,
"loss": 0.888,
"step": 1164
},
{
"epoch": 0.45,
"learning_rate": 1.2140047180069814e-05,
"loss": 0.8511,
"step": 1165
},
{
"epoch": 0.45,
"learning_rate": 1.2127867701955622e-05,
"loss": 0.5221,
"step": 1166
},
{
"epoch": 0.45,
"learning_rate": 1.211568491677263e-05,
"loss": 0.9039,
"step": 1167
},
{
"epoch": 0.45,
"learning_rate": 1.210349884345496e-05,
"loss": 0.8267,
"step": 1168
},
{
"epoch": 0.45,
"learning_rate": 1.2091309500941841e-05,
"loss": 0.8958,
"step": 1169
},
{
"epoch": 0.45,
"learning_rate": 1.2079116908177592e-05,
"loss": 0.8354,
"step": 1170
},
{
"epoch": 0.45,
"learning_rate": 1.2066921084111582e-05,
"loss": 0.8336,
"step": 1171
},
{
"epoch": 0.45,
"learning_rate": 1.2054722047698192e-05,
"loss": 0.8159,
"step": 1172
},
{
"epoch": 0.45,
"learning_rate": 1.2042519817896805e-05,
"loss": 0.851,
"step": 1173
},
{
"epoch": 0.45,
"learning_rate": 1.2030314413671763e-05,
"loss": 0.8799,
"step": 1174
},
{
"epoch": 0.45,
"learning_rate": 1.2018105853992346e-05,
"loss": 0.8335,
"step": 1175
},
{
"epoch": 0.45,
"learning_rate": 1.200589415783273e-05,
"loss": 0.8362,
"step": 1176
},
{
"epoch": 0.45,
"learning_rate": 1.1993679344171973e-05,
"loss": 0.8359,
"step": 1177
},
{
"epoch": 0.45,
"learning_rate": 1.1981461431993978e-05,
"loss": 0.8871,
"step": 1178
},
{
"epoch": 0.45,
"learning_rate": 1.1969240440287457e-05,
"loss": 0.8154,
"step": 1179
},
{
"epoch": 0.45,
"learning_rate": 1.1957016388045917e-05,
"loss": 0.9055,
"step": 1180
},
{
"epoch": 0.45,
"learning_rate": 1.1944789294267614e-05,
"loss": 0.8797,
"step": 1181
},
{
"epoch": 0.45,
"learning_rate": 1.1932559177955533e-05,
"loss": 0.8529,
"step": 1182
},
{
"epoch": 0.46,
"learning_rate": 1.1920326058117364e-05,
"loss": 0.9053,
"step": 1183
},
{
"epoch": 0.46,
"learning_rate": 1.190808995376545e-05,
"loss": 0.8247,
"step": 1184
},
{
"epoch": 0.46,
"learning_rate": 1.1895850883916786e-05,
"loss": 0.8553,
"step": 1185
},
{
"epoch": 0.46,
"learning_rate": 1.188360886759297e-05,
"loss": 0.8282,
"step": 1186
},
{
"epoch": 0.46,
"learning_rate": 1.1871363923820182e-05,
"loss": 0.8162,
"step": 1187
},
{
"epoch": 0.46,
"learning_rate": 1.1859116071629148e-05,
"loss": 0.8572,
"step": 1188
},
{
"epoch": 0.46,
"learning_rate": 1.1846865330055115e-05,
"loss": 0.5207,
"step": 1189
},
{
"epoch": 0.46,
"learning_rate": 1.1834611718137825e-05,
"loss": 0.5261,
"step": 1190
},
{
"epoch": 0.46,
"learning_rate": 1.1822355254921478e-05,
"loss": 0.8788,
"step": 1191
},
{
"epoch": 0.46,
"learning_rate": 1.18100959594547e-05,
"loss": 0.8602,
"step": 1192
},
{
"epoch": 0.46,
"learning_rate": 1.1797833850790527e-05,
"loss": 0.8711,
"step": 1193
},
{
"epoch": 0.46,
"learning_rate": 1.1785568947986368e-05,
"loss": 0.8495,
"step": 1194
},
{
"epoch": 0.46,
"learning_rate": 1.1773301270103968e-05,
"loss": 0.9103,
"step": 1195
},
{
"epoch": 0.46,
"learning_rate": 1.1761030836209384e-05,
"loss": 0.8298,
"step": 1196
},
{
"epoch": 0.46,
"learning_rate": 1.1748757665372965e-05,
"loss": 0.8474,
"step": 1197
},
{
"epoch": 0.46,
"learning_rate": 1.1736481776669307e-05,
"loss": 0.8817,
"step": 1198
},
{
"epoch": 0.46,
"learning_rate": 1.1724203189177228e-05,
"loss": 0.8135,
"step": 1199
},
{
"epoch": 0.46,
"learning_rate": 1.1711921921979754e-05,
"loss": 0.8088,
"step": 1200
},
{
"epoch": 0.46,
"learning_rate": 1.1699637994164053e-05,
"loss": 0.8779,
"step": 1201
},
{
"epoch": 0.46,
"learning_rate": 1.1687351424821448e-05,
"loss": 0.8633,
"step": 1202
},
{
"epoch": 0.46,
"learning_rate": 1.1675062233047365e-05,
"loss": 0.9241,
"step": 1203
},
{
"epoch": 0.46,
"learning_rate": 1.1662770437941293e-05,
"loss": 0.8698,
"step": 1204
},
{
"epoch": 0.46,
"learning_rate": 1.1650476058606776e-05,
"loss": 0.5414,
"step": 1205
},
{
"epoch": 0.46,
"learning_rate": 1.1638179114151378e-05,
"loss": 0.8649,
"step": 1206
},
{
"epoch": 0.46,
"learning_rate": 1.162587962368664e-05,
"loss": 0.8521,
"step": 1207
},
{
"epoch": 0.46,
"learning_rate": 1.1613577606328068e-05,
"loss": 0.8744,
"step": 1208
},
{
"epoch": 0.47,
"learning_rate": 1.1601273081195087e-05,
"loss": 0.8655,
"step": 1209
},
{
"epoch": 0.47,
"learning_rate": 1.1588966067411033e-05,
"loss": 0.9152,
"step": 1210
},
{
"epoch": 0.47,
"learning_rate": 1.1576656584103097e-05,
"loss": 0.8713,
"step": 1211
},
{
"epoch": 0.47,
"learning_rate": 1.156434465040231e-05,
"loss": 0.8436,
"step": 1212
},
{
"epoch": 0.47,
"learning_rate": 1.1552030285443516e-05,
"loss": 0.8311,
"step": 1213
},
{
"epoch": 0.47,
"learning_rate": 1.1539713508365336e-05,
"loss": 0.8604,
"step": 1214
},
{
"epoch": 0.47,
"learning_rate": 1.152739433831014e-05,
"loss": 0.88,
"step": 1215
},
{
"epoch": 0.47,
"learning_rate": 1.1515072794424013e-05,
"loss": 0.8926,
"step": 1216
},
{
"epoch": 0.47,
"learning_rate": 1.1502748895856737e-05,
"loss": 0.8373,
"step": 1217
},
{
"epoch": 0.47,
"learning_rate": 1.1490422661761744e-05,
"loss": 0.8599,
"step": 1218
},
{
"epoch": 0.47,
"learning_rate": 1.1478094111296109e-05,
"loss": 0.8347,
"step": 1219
},
{
"epoch": 0.47,
"learning_rate": 1.146576326362049e-05,
"loss": 0.8625,
"step": 1220
},
{
"epoch": 0.47,
"learning_rate": 1.1453430137899129e-05,
"loss": 0.8408,
"step": 1221
},
{
"epoch": 0.47,
"learning_rate": 1.1441094753299802e-05,
"loss": 0.5013,
"step": 1222
},
{
"epoch": 0.47,
"learning_rate": 1.1428757128993801e-05,
"loss": 0.8719,
"step": 1223
},
{
"epoch": 0.47,
"learning_rate": 1.1416417284155892e-05,
"loss": 0.8245,
"step": 1224
},
{
"epoch": 0.47,
"learning_rate": 1.1404075237964296e-05,
"loss": 0.8273,
"step": 1225
},
{
"epoch": 0.47,
"learning_rate": 1.1391731009600655e-05,
"loss": 0.8434,
"step": 1226
},
{
"epoch": 0.47,
"learning_rate": 1.1379384618250002e-05,
"loss": 0.827,
"step": 1227
},
{
"epoch": 0.47,
"learning_rate": 1.1367036083100735e-05,
"loss": 0.8296,
"step": 1228
},
{
"epoch": 0.47,
"learning_rate": 1.1354685423344577e-05,
"loss": 0.9187,
"step": 1229
},
{
"epoch": 0.47,
"learning_rate": 1.1342332658176556e-05,
"loss": 0.8629,
"step": 1230
},
{
"epoch": 0.47,
"learning_rate": 1.1329977806794976e-05,
"loss": 0.8346,
"step": 1231
},
{
"epoch": 0.47,
"learning_rate": 1.1317620888401379e-05,
"loss": 0.8461,
"step": 1232
},
{
"epoch": 0.47,
"learning_rate": 1.130526192220052e-05,
"loss": 0.5115,
"step": 1233
},
{
"epoch": 0.47,
"learning_rate": 1.1292900927400334e-05,
"loss": 0.9109,
"step": 1234
},
{
"epoch": 0.48,
"learning_rate": 1.1280537923211919e-05,
"loss": 0.8595,
"step": 1235
},
{
"epoch": 0.48,
"learning_rate": 1.1268172928849486e-05,
"loss": 0.8773,
"step": 1236
},
{
"epoch": 0.48,
"learning_rate": 1.1255805963530339e-05,
"loss": 0.8635,
"step": 1237
},
{
"epoch": 0.48,
"learning_rate": 1.1243437046474854e-05,
"loss": 0.8894,
"step": 1238
},
{
"epoch": 0.48,
"learning_rate": 1.123106619690643e-05,
"loss": 0.8693,
"step": 1239
},
{
"epoch": 0.48,
"learning_rate": 1.1218693434051475e-05,
"loss": 0.4959,
"step": 1240
},
{
"epoch": 0.48,
"learning_rate": 1.120631877713937e-05,
"loss": 0.884,
"step": 1241
},
{
"epoch": 0.48,
"learning_rate": 1.1193942245402443e-05,
"loss": 0.8717,
"step": 1242
},
{
"epoch": 0.48,
"learning_rate": 1.118156385807593e-05,
"loss": 0.8711,
"step": 1243
},
{
"epoch": 0.48,
"learning_rate": 1.1169183634397948e-05,
"loss": 0.8937,
"step": 1244
},
{
"epoch": 0.48,
"learning_rate": 1.1156801593609479e-05,
"loss": 0.8669,
"step": 1245
},
{
"epoch": 0.48,
"learning_rate": 1.114441775495432e-05,
"loss": 0.8479,
"step": 1246
},
{
"epoch": 0.48,
"learning_rate": 1.113203213767907e-05,
"loss": 0.8537,
"step": 1247
},
{
"epoch": 0.48,
"learning_rate": 1.1119644761033079e-05,
"loss": 0.8958,
"step": 1248
},
{
"epoch": 0.48,
"learning_rate": 1.1107255644268448e-05,
"loss": 0.8483,
"step": 1249
},
{
"epoch": 0.48,
"learning_rate": 1.1094864806639971e-05,
"loss": 0.8148,
"step": 1250
},
{
"epoch": 0.48,
"learning_rate": 1.1082472267405123e-05,
"loss": 0.8608,
"step": 1251
},
{
"epoch": 0.48,
"learning_rate": 1.1070078045824014e-05,
"loss": 0.8041,
"step": 1252
},
{
"epoch": 0.48,
"learning_rate": 1.105768216115938e-05,
"loss": 0.5182,
"step": 1253
},
{
"epoch": 0.48,
"learning_rate": 1.1045284632676535e-05,
"loss": 0.5352,
"step": 1254
},
{
"epoch": 0.48,
"learning_rate": 1.1032885479643351e-05,
"loss": 0.8201,
"step": 1255
},
{
"epoch": 0.48,
"learning_rate": 1.1020484721330227e-05,
"loss": 0.9187,
"step": 1256
},
{
"epoch": 0.48,
"learning_rate": 1.1008082377010045e-05,
"loss": 0.8911,
"step": 1257
},
{
"epoch": 0.48,
"learning_rate": 1.0995678465958168e-05,
"loss": 0.8558,
"step": 1258
},
{
"epoch": 0.48,
"learning_rate": 1.098327300745238e-05,
"loss": 0.8417,
"step": 1259
},
{
"epoch": 0.48,
"learning_rate": 1.0970866020772884e-05,
"loss": 0.859,
"step": 1260
},
{
"epoch": 0.49,
"learning_rate": 1.0958457525202241e-05,
"loss": 0.8535,
"step": 1261
},
{
"epoch": 0.49,
"learning_rate": 1.0946047540025373e-05,
"loss": 0.8503,
"step": 1262
},
{
"epoch": 0.49,
"learning_rate": 1.0933636084529507e-05,
"loss": 0.886,
"step": 1263
},
{
"epoch": 0.49,
"learning_rate": 1.0921223178004163e-05,
"loss": 0.8722,
"step": 1264
},
{
"epoch": 0.49,
"learning_rate": 1.0908808839741108e-05,
"loss": 0.8338,
"step": 1265
},
{
"epoch": 0.49,
"learning_rate": 1.0896393089034336e-05,
"loss": 0.5156,
"step": 1266
},
{
"epoch": 0.49,
"learning_rate": 1.0883975945180043e-05,
"loss": 0.8287,
"step": 1267
},
{
"epoch": 0.49,
"learning_rate": 1.0871557427476585e-05,
"loss": 0.8306,
"step": 1268
},
{
"epoch": 0.49,
"learning_rate": 1.0859137555224448e-05,
"loss": 0.8303,
"step": 1269
},
{
"epoch": 0.49,
"learning_rate": 1.0846716347726233e-05,
"loss": 0.8492,
"step": 1270
},
{
"epoch": 0.49,
"learning_rate": 1.0834293824286612e-05,
"loss": 0.8708,
"step": 1271
},
{
"epoch": 0.49,
"learning_rate": 1.0821870004212305e-05,
"loss": 0.8592,
"step": 1272
},
{
"epoch": 0.49,
"learning_rate": 1.0809444906812034e-05,
"loss": 0.8372,
"step": 1273
},
{
"epoch": 0.49,
"learning_rate": 1.0797018551396527e-05,
"loss": 0.8547,
"step": 1274
},
{
"epoch": 0.49,
"learning_rate": 1.0784590957278452e-05,
"loss": 0.8727,
"step": 1275
},
{
"epoch": 0.49,
"learning_rate": 1.0772162143772407e-05,
"loss": 0.8948,
"step": 1276
},
{
"epoch": 0.49,
"learning_rate": 1.0759732130194887e-05,
"loss": 0.8542,
"step": 1277
},
{
"epoch": 0.49,
"learning_rate": 1.0747300935864245e-05,
"loss": 0.8514,
"step": 1278
},
{
"epoch": 0.49,
"learning_rate": 1.0734868580100677e-05,
"loss": 0.8678,
"step": 1279
},
{
"epoch": 0.49,
"learning_rate": 1.0722435082226186e-05,
"loss": 0.8619,
"step": 1280
},
{
"epoch": 0.49,
"learning_rate": 1.0710000461564535e-05,
"loss": 0.8043,
"step": 1281
},
{
"epoch": 0.49,
"learning_rate": 1.0697564737441254e-05,
"loss": 0.86,
"step": 1282
},
{
"epoch": 0.49,
"learning_rate": 1.0685127929183567e-05,
"loss": 0.8485,
"step": 1283
},
{
"epoch": 0.49,
"learning_rate": 1.0672690056120398e-05,
"loss": 0.8907,
"step": 1284
},
{
"epoch": 0.49,
"learning_rate": 1.0660251137582316e-05,
"loss": 0.8514,
"step": 1285
},
{
"epoch": 0.49,
"learning_rate": 1.0647811192901518e-05,
"loss": 0.855,
"step": 1286
},
{
"epoch": 0.5,
"learning_rate": 1.0635370241411803e-05,
"loss": 0.8964,
"step": 1287
},
{
"epoch": 0.5,
"learning_rate": 1.0622928302448523e-05,
"loss": 0.8658,
"step": 1288
},
{
"epoch": 0.5,
"learning_rate": 1.0610485395348571e-05,
"loss": 0.8232,
"step": 1289
},
{
"epoch": 0.5,
"learning_rate": 1.0598041539450344e-05,
"loss": 0.9034,
"step": 1290
},
{
"epoch": 0.5,
"learning_rate": 1.0585596754093712e-05,
"loss": 0.8578,
"step": 1291
},
{
"epoch": 0.5,
"learning_rate": 1.0573151058619994e-05,
"loss": 0.8235,
"step": 1292
},
{
"epoch": 0.5,
"learning_rate": 1.0560704472371919e-05,
"loss": 0.8744,
"step": 1293
},
{
"epoch": 0.5,
"learning_rate": 1.0548257014693602e-05,
"loss": 0.8868,
"step": 1294
},
{
"epoch": 0.5,
"learning_rate": 1.053580870493051e-05,
"loss": 0.8943,
"step": 1295
},
{
"epoch": 0.5,
"learning_rate": 1.0523359562429441e-05,
"loss": 0.8839,
"step": 1296
},
{
"epoch": 0.5,
"learning_rate": 1.0510909606538478e-05,
"loss": 0.8379,
"step": 1297
},
{
"epoch": 0.5,
"learning_rate": 1.0498458856606972e-05,
"loss": 0.8748,
"step": 1298
},
{
"epoch": 0.5,
"learning_rate": 1.0486007331985516e-05,
"loss": 0.8309,
"step": 1299
},
{
"epoch": 0.5,
"learning_rate": 1.0473555052025893e-05,
"loss": 0.8258,
"step": 1300
},
{
"epoch": 0.5,
"learning_rate": 1.0461102036081069e-05,
"loss": 0.8882,
"step": 1301
},
{
"epoch": 0.5,
"learning_rate": 1.044864830350515e-05,
"loss": 0.8384,
"step": 1302
},
{
"epoch": 0.5,
"learning_rate": 1.0436193873653362e-05,
"loss": 0.8206,
"step": 1303
},
{
"epoch": 0.5,
"learning_rate": 1.0423738765882006e-05,
"loss": 0.8356,
"step": 1304
},
{
"epoch": 0.5,
"learning_rate": 1.0411282999548442e-05,
"loss": 0.8242,
"step": 1305
},
{
"epoch": 0.5,
"learning_rate": 1.039882659401105e-05,
"loss": 0.8816,
"step": 1306
},
{
"epoch": 0.5,
"learning_rate": 1.0386369568629209e-05,
"loss": 0.8317,
"step": 1307
},
{
"epoch": 0.5,
"learning_rate": 1.037391194276326e-05,
"loss": 0.8778,
"step": 1308
},
{
"epoch": 0.5,
"learning_rate": 1.0361453735774467e-05,
"loss": 0.8821,
"step": 1309
},
{
"epoch": 0.5,
"learning_rate": 1.0348994967025012e-05,
"loss": 0.8749,
"step": 1310
},
{
"epoch": 0.5,
"learning_rate": 1.0336535655877942e-05,
"loss": 0.8505,
"step": 1311
},
{
"epoch": 0.51,
"learning_rate": 1.0324075821697146e-05,
"loss": 0.8412,
"step": 1312
},
{
"epoch": 0.51,
"learning_rate": 1.0311615483847333e-05,
"loss": 0.8007,
"step": 1313
},
{
"epoch": 0.51,
"learning_rate": 1.0299154661693987e-05,
"loss": 0.8785,
"step": 1314
},
{
"epoch": 0.51,
"learning_rate": 1.0286693374603347e-05,
"loss": 0.8359,
"step": 1315
},
{
"epoch": 0.51,
"learning_rate": 1.0274231641942378e-05,
"loss": 0.8245,
"step": 1316
},
{
"epoch": 0.51,
"learning_rate": 1.0261769483078734e-05,
"loss": 0.8757,
"step": 1317
},
{
"epoch": 0.51,
"learning_rate": 1.0249306917380731e-05,
"loss": 0.828,
"step": 1318
},
{
"epoch": 0.51,
"learning_rate": 1.0236843964217317e-05,
"loss": 0.8453,
"step": 1319
},
{
"epoch": 0.51,
"learning_rate": 1.0224380642958052e-05,
"loss": 0.847,
"step": 1320
},
{
"epoch": 0.51,
"learning_rate": 1.0211916972973048e-05,
"loss": 0.8368,
"step": 1321
},
{
"epoch": 0.51,
"learning_rate": 1.0199452973632982e-05,
"loss": 0.826,
"step": 1322
},
{
"epoch": 0.51,
"learning_rate": 1.0186988664309023e-05,
"loss": 0.8776,
"step": 1323
},
{
"epoch": 0.51,
"learning_rate": 1.0174524064372837e-05,
"loss": 0.8739,
"step": 1324
},
{
"epoch": 0.51,
"learning_rate": 1.016205919319653e-05,
"loss": 0.8416,
"step": 1325
},
{
"epoch": 0.51,
"learning_rate": 1.0149594070152638e-05,
"loss": 0.8718,
"step": 1326
},
{
"epoch": 0.51,
"learning_rate": 1.0137128714614082e-05,
"loss": 0.8304,
"step": 1327
},
{
"epoch": 0.51,
"learning_rate": 1.0124663145954152e-05,
"loss": 0.8159,
"step": 1328
},
{
"epoch": 0.51,
"learning_rate": 1.011219738354646e-05,
"loss": 0.8546,
"step": 1329
},
{
"epoch": 0.51,
"learning_rate": 1.0099731446764927e-05,
"loss": 0.8531,
"step": 1330
},
{
"epoch": 0.51,
"learning_rate": 1.008726535498374e-05,
"loss": 0.8101,
"step": 1331
},
{
"epoch": 0.51,
"learning_rate": 1.007479912757733e-05,
"loss": 0.8634,
"step": 1332
},
{
"epoch": 0.51,
"learning_rate": 1.0062332783920337e-05,
"loss": 0.9042,
"step": 1333
},
{
"epoch": 0.51,
"learning_rate": 1.0049866343387582e-05,
"loss": 0.8071,
"step": 1334
},
{
"epoch": 0.51,
"learning_rate": 1.0037399825354036e-05,
"loss": 0.8676,
"step": 1335
},
{
"epoch": 0.51,
"learning_rate": 1.0024933249194792e-05,
"loss": 0.8069,
"step": 1336
},
{
"epoch": 0.51,
"learning_rate": 1.0012466634285034e-05,
"loss": 0.8292,
"step": 1337
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 0.8839,
"step": 1338
},
{
"epoch": 0.52,
"learning_rate": 9.987533365714968e-06,
"loss": 0.8331,
"step": 1339
},
{
"epoch": 0.52,
"learning_rate": 9.97506675080521e-06,
"loss": 0.4868,
"step": 1340
},
{
"epoch": 0.52,
"learning_rate": 9.962600174645968e-06,
"loss": 0.8906,
"step": 1341
},
{
"epoch": 0.52,
"learning_rate": 9.950133656612421e-06,
"loss": 0.8617,
"step": 1342
},
{
"epoch": 0.52,
"learning_rate": 9.937667216079665e-06,
"loss": 0.8464,
"step": 1343
},
{
"epoch": 0.52,
"learning_rate": 9.925200872422671e-06,
"loss": 0.8401,
"step": 1344
},
{
"epoch": 0.52,
"learning_rate": 9.912734645016262e-06,
"loss": 0.8407,
"step": 1345
},
{
"epoch": 0.52,
"learning_rate": 9.900268553235077e-06,
"loss": 0.5092,
"step": 1346
},
{
"epoch": 0.52,
"learning_rate": 9.887802616453543e-06,
"loss": 0.83,
"step": 1347
},
{
"epoch": 0.52,
"learning_rate": 9.87533685404585e-06,
"loss": 0.8385,
"step": 1348
},
{
"epoch": 0.52,
"learning_rate": 9.862871285385921e-06,
"loss": 0.8838,
"step": 1349
},
{
"epoch": 0.52,
"learning_rate": 9.850405929847367e-06,
"loss": 0.866,
"step": 1350
},
{
"epoch": 0.52,
"learning_rate": 9.837940806803474e-06,
"loss": 0.8815,
"step": 1351
},
{
"epoch": 0.52,
"learning_rate": 9.825475935627165e-06,
"loss": 0.886,
"step": 1352
},
{
"epoch": 0.52,
"learning_rate": 9.81301133569098e-06,
"loss": 0.8214,
"step": 1353
},
{
"epoch": 0.52,
"learning_rate": 9.800547026367022e-06,
"loss": 0.8291,
"step": 1354
},
{
"epoch": 0.52,
"learning_rate": 9.788083027026953e-06,
"loss": 0.8129,
"step": 1355
},
{
"epoch": 0.52,
"learning_rate": 9.775619357041952e-06,
"loss": 0.8256,
"step": 1356
},
{
"epoch": 0.52,
"learning_rate": 9.763156035782686e-06,
"loss": 0.823,
"step": 1357
},
{
"epoch": 0.52,
"learning_rate": 9.750693082619274e-06,
"loss": 0.8743,
"step": 1358
},
{
"epoch": 0.52,
"learning_rate": 9.738230516921272e-06,
"loss": 0.8591,
"step": 1359
},
{
"epoch": 0.52,
"learning_rate": 9.725768358057625e-06,
"loss": 0.8946,
"step": 1360
},
{
"epoch": 0.52,
"learning_rate": 9.713306625396658e-06,
"loss": 0.8476,
"step": 1361
},
{
"epoch": 0.52,
"learning_rate": 9.700845338306018e-06,
"loss": 0.8741,
"step": 1362
},
{
"epoch": 0.52,
"learning_rate": 9.68838451615267e-06,
"loss": 0.8653,
"step": 1363
},
{
"epoch": 0.53,
"learning_rate": 9.675924178302857e-06,
"loss": 0.8979,
"step": 1364
},
{
"epoch": 0.53,
"learning_rate": 9.663464344122064e-06,
"loss": 0.8395,
"step": 1365
},
{
"epoch": 0.53,
"learning_rate": 9.651005032974994e-06,
"loss": 0.8411,
"step": 1366
},
{
"epoch": 0.53,
"learning_rate": 9.638546264225538e-06,
"loss": 0.8273,
"step": 1367
},
{
"epoch": 0.53,
"learning_rate": 9.626088057236745e-06,
"loss": 0.8962,
"step": 1368
},
{
"epoch": 0.53,
"learning_rate": 9.613630431370794e-06,
"loss": 0.8633,
"step": 1369
},
{
"epoch": 0.53,
"learning_rate": 9.601173405988955e-06,
"loss": 0.7949,
"step": 1370
},
{
"epoch": 0.53,
"learning_rate": 9.588717000451563e-06,
"loss": 0.8577,
"step": 1371
},
{
"epoch": 0.53,
"learning_rate": 9.576261234117998e-06,
"loss": 0.882,
"step": 1372
},
{
"epoch": 0.53,
"learning_rate": 9.563806126346643e-06,
"loss": 0.8436,
"step": 1373
},
{
"epoch": 0.53,
"learning_rate": 9.551351696494854e-06,
"loss": 0.8639,
"step": 1374
},
{
"epoch": 0.53,
"learning_rate": 9.538897963918936e-06,
"loss": 0.8897,
"step": 1375
},
{
"epoch": 0.53,
"learning_rate": 9.526444947974112e-06,
"loss": 0.8636,
"step": 1376
},
{
"epoch": 0.53,
"learning_rate": 9.51399266801449e-06,
"loss": 0.8462,
"step": 1377
},
{
"epoch": 0.53,
"learning_rate": 9.501541143393028e-06,
"loss": 0.8472,
"step": 1378
},
{
"epoch": 0.53,
"learning_rate": 9.489090393461523e-06,
"loss": 0.8718,
"step": 1379
},
{
"epoch": 0.53,
"learning_rate": 9.476640437570562e-06,
"loss": 0.5081,
"step": 1380
},
{
"epoch": 0.53,
"learning_rate": 9.46419129506949e-06,
"loss": 0.8497,
"step": 1381
},
{
"epoch": 0.53,
"learning_rate": 9.4517429853064e-06,
"loss": 0.8359,
"step": 1382
},
{
"epoch": 0.53,
"learning_rate": 9.439295527628083e-06,
"loss": 0.5094,
"step": 1383
},
{
"epoch": 0.53,
"learning_rate": 9.426848941380007e-06,
"loss": 0.8912,
"step": 1384
},
{
"epoch": 0.53,
"learning_rate": 9.41440324590629e-06,
"loss": 0.8272,
"step": 1385
},
{
"epoch": 0.53,
"learning_rate": 9.401958460549658e-06,
"loss": 0.8657,
"step": 1386
},
{
"epoch": 0.53,
"learning_rate": 9.38951460465143e-06,
"loss": 0.8251,
"step": 1387
},
{
"epoch": 0.53,
"learning_rate": 9.377071697551479e-06,
"loss": 0.8302,
"step": 1388
},
{
"epoch": 0.53,
"learning_rate": 9.364629758588199e-06,
"loss": 0.8951,
"step": 1389
},
{
"epoch": 0.54,
"learning_rate": 9.352188807098482e-06,
"loss": 0.8167,
"step": 1390
},
{
"epoch": 0.54,
"learning_rate": 9.339748862417686e-06,
"loss": 0.8593,
"step": 1391
},
{
"epoch": 0.54,
"learning_rate": 9.327309943879604e-06,
"loss": 0.8252,
"step": 1392
},
{
"epoch": 0.54,
"learning_rate": 9.314872070816435e-06,
"loss": 0.8514,
"step": 1393
},
{
"epoch": 0.54,
"learning_rate": 9.302435262558748e-06,
"loss": 0.8774,
"step": 1394
},
{
"epoch": 0.54,
"learning_rate": 9.289999538435463e-06,
"loss": 0.7968,
"step": 1395
},
{
"epoch": 0.54,
"learning_rate": 9.277564917773816e-06,
"loss": 0.7773,
"step": 1396
},
{
"epoch": 0.54,
"learning_rate": 9.265131419899325e-06,
"loss": 0.8597,
"step": 1397
},
{
"epoch": 0.54,
"learning_rate": 9.252699064135759e-06,
"loss": 0.877,
"step": 1398
},
{
"epoch": 0.54,
"learning_rate": 9.240267869805118e-06,
"loss": 0.488,
"step": 1399
},
{
"epoch": 0.54,
"learning_rate": 9.227837856227594e-06,
"loss": 0.8518,
"step": 1400
},
{
"epoch": 0.54,
"learning_rate": 9.215409042721553e-06,
"loss": 0.8375,
"step": 1401
},
{
"epoch": 0.54,
"learning_rate": 9.202981448603477e-06,
"loss": 0.8757,
"step": 1402
},
{
"epoch": 0.54,
"learning_rate": 9.190555093187968e-06,
"loss": 0.8578,
"step": 1403
},
{
"epoch": 0.54,
"learning_rate": 9.178129995787698e-06,
"loss": 0.5016,
"step": 1404
},
{
"epoch": 0.54,
"learning_rate": 9.165706175713391e-06,
"loss": 0.8361,
"step": 1405
},
{
"epoch": 0.54,
"learning_rate": 9.153283652273768e-06,
"loss": 0.8853,
"step": 1406
},
{
"epoch": 0.54,
"learning_rate": 9.140862444775554e-06,
"loss": 0.8708,
"step": 1407
},
{
"epoch": 0.54,
"learning_rate": 9.128442572523418e-06,
"loss": 0.8125,
"step": 1408
},
{
"epoch": 0.54,
"learning_rate": 9.11602405481996e-06,
"loss": 0.8154,
"step": 1409
},
{
"epoch": 0.54,
"learning_rate": 9.103606910965666e-06,
"loss": 0.8166,
"step": 1410
},
{
"epoch": 0.54,
"learning_rate": 9.091191160258895e-06,
"loss": 0.8541,
"step": 1411
},
{
"epoch": 0.54,
"learning_rate": 9.078776821995839e-06,
"loss": 0.8282,
"step": 1412
},
{
"epoch": 0.54,
"learning_rate": 9.066363915470494e-06,
"loss": 0.8512,
"step": 1413
},
{
"epoch": 0.54,
"learning_rate": 9.05395245997463e-06,
"loss": 0.8293,
"step": 1414
},
{
"epoch": 0.54,
"learning_rate": 9.04154247479776e-06,
"loss": 0.8242,
"step": 1415
},
{
"epoch": 0.55,
"learning_rate": 9.02913397922712e-06,
"loss": 0.8315,
"step": 1416
},
{
"epoch": 0.55,
"learning_rate": 9.016726992547621e-06,
"loss": 0.8225,
"step": 1417
},
{
"epoch": 0.55,
"learning_rate": 9.004321534041836e-06,
"loss": 0.8251,
"step": 1418
},
{
"epoch": 0.55,
"learning_rate": 8.991917622989957e-06,
"loss": 0.848,
"step": 1419
},
{
"epoch": 0.55,
"learning_rate": 8.979515278669776e-06,
"loss": 0.8302,
"step": 1420
},
{
"epoch": 0.55,
"learning_rate": 8.967114520356652e-06,
"loss": 0.8076,
"step": 1421
},
{
"epoch": 0.55,
"learning_rate": 8.954715367323468e-06,
"loss": 0.8489,
"step": 1422
},
{
"epoch": 0.55,
"learning_rate": 8.942317838840625e-06,
"loss": 0.8635,
"step": 1423
},
{
"epoch": 0.55,
"learning_rate": 8.92992195417599e-06,
"loss": 0.5441,
"step": 1424
},
{
"epoch": 0.55,
"learning_rate": 8.917527732594882e-06,
"loss": 0.8599,
"step": 1425
},
{
"epoch": 0.55,
"learning_rate": 8.905135193360032e-06,
"loss": 0.8394,
"step": 1426
},
{
"epoch": 0.55,
"learning_rate": 8.892744355731555e-06,
"loss": 0.4997,
"step": 1427
},
{
"epoch": 0.55,
"learning_rate": 8.880355238966923e-06,
"loss": 0.8423,
"step": 1428
},
{
"epoch": 0.55,
"learning_rate": 8.867967862320935e-06,
"loss": 0.842,
"step": 1429
},
{
"epoch": 0.55,
"learning_rate": 8.855582245045682e-06,
"loss": 0.8942,
"step": 1430
},
{
"epoch": 0.55,
"learning_rate": 8.843198406390524e-06,
"loss": 0.8698,
"step": 1431
},
{
"epoch": 0.55,
"learning_rate": 8.830816365602053e-06,
"loss": 0.8414,
"step": 1432
},
{
"epoch": 0.55,
"learning_rate": 8.818436141924072e-06,
"loss": 0.8785,
"step": 1433
},
{
"epoch": 0.55,
"learning_rate": 8.806057754597559e-06,
"loss": 0.8354,
"step": 1434
},
{
"epoch": 0.55,
"learning_rate": 8.793681222860631e-06,
"loss": 0.8259,
"step": 1435
},
{
"epoch": 0.55,
"learning_rate": 8.781306565948528e-06,
"loss": 0.8606,
"step": 1436
},
{
"epoch": 0.55,
"learning_rate": 8.768933803093573e-06,
"loss": 0.8211,
"step": 1437
},
{
"epoch": 0.55,
"learning_rate": 8.756562953525151e-06,
"loss": 0.8926,
"step": 1438
},
{
"epoch": 0.55,
"learning_rate": 8.744194036469665e-06,
"loss": 0.5443,
"step": 1439
},
{
"epoch": 0.55,
"learning_rate": 8.731827071150519e-06,
"loss": 0.8073,
"step": 1440
},
{
"epoch": 0.55,
"learning_rate": 8.719462076788085e-06,
"loss": 0.8779,
"step": 1441
},
{
"epoch": 0.56,
"learning_rate": 8.70709907259967e-06,
"loss": 0.8652,
"step": 1442
},
{
"epoch": 0.56,
"learning_rate": 8.694738077799487e-06,
"loss": 0.5149,
"step": 1443
},
{
"epoch": 0.56,
"learning_rate": 8.682379111598626e-06,
"loss": 0.907,
"step": 1444
},
{
"epoch": 0.56,
"learning_rate": 8.670022193205027e-06,
"loss": 0.8329,
"step": 1445
},
{
"epoch": 0.56,
"learning_rate": 8.657667341823449e-06,
"loss": 0.8677,
"step": 1446
},
{
"epoch": 0.56,
"learning_rate": 8.645314576655428e-06,
"loss": 0.828,
"step": 1447
},
{
"epoch": 0.56,
"learning_rate": 8.632963916899268e-06,
"loss": 0.827,
"step": 1448
},
{
"epoch": 0.56,
"learning_rate": 8.62061538175e-06,
"loss": 0.8425,
"step": 1449
},
{
"epoch": 0.56,
"learning_rate": 8.60826899039935e-06,
"loss": 0.86,
"step": 1450
},
{
"epoch": 0.56,
"learning_rate": 8.59592476203571e-06,
"loss": 0.7656,
"step": 1451
},
{
"epoch": 0.56,
"learning_rate": 8.583582715844113e-06,
"loss": 0.8517,
"step": 1452
},
{
"epoch": 0.56,
"learning_rate": 8.571242871006202e-06,
"loss": 0.8507,
"step": 1453
},
{
"epoch": 0.56,
"learning_rate": 8.558905246700202e-06,
"loss": 0.8464,
"step": 1454
},
{
"epoch": 0.56,
"learning_rate": 8.546569862100876e-06,
"loss": 0.8576,
"step": 1455
},
{
"epoch": 0.56,
"learning_rate": 8.534236736379515e-06,
"loss": 0.8863,
"step": 1456
},
{
"epoch": 0.56,
"learning_rate": 8.521905888703894e-06,
"loss": 0.8481,
"step": 1457
},
{
"epoch": 0.56,
"learning_rate": 8.509577338238255e-06,
"loss": 0.8556,
"step": 1458
},
{
"epoch": 0.56,
"learning_rate": 8.497251104143263e-06,
"loss": 0.833,
"step": 1459
},
{
"epoch": 0.56,
"learning_rate": 8.484927205575985e-06,
"loss": 0.8997,
"step": 1460
},
{
"epoch": 0.56,
"learning_rate": 8.472605661689863e-06,
"loss": 0.8512,
"step": 1461
},
{
"epoch": 0.56,
"learning_rate": 8.460286491634664e-06,
"loss": 0.8689,
"step": 1462
},
{
"epoch": 0.56,
"learning_rate": 8.447969714556484e-06,
"loss": 0.8146,
"step": 1463
},
{
"epoch": 0.56,
"learning_rate": 8.43565534959769e-06,
"loss": 0.8476,
"step": 1464
},
{
"epoch": 0.56,
"learning_rate": 8.423343415896904e-06,
"loss": 0.8289,
"step": 1465
},
{
"epoch": 0.56,
"learning_rate": 8.411033932588969e-06,
"loss": 0.8738,
"step": 1466
},
{
"epoch": 0.56,
"learning_rate": 8.398726918804911e-06,
"loss": 0.8641,
"step": 1467
},
{
"epoch": 0.57,
"learning_rate": 8.386422393671934e-06,
"loss": 0.8353,
"step": 1468
},
{
"epoch": 0.57,
"learning_rate": 8.374120376313362e-06,
"loss": 0.7995,
"step": 1469
},
{
"epoch": 0.57,
"learning_rate": 8.361820885848623e-06,
"loss": 0.8071,
"step": 1470
},
{
"epoch": 0.57,
"learning_rate": 8.349523941393224e-06,
"loss": 0.5275,
"step": 1471
},
{
"epoch": 0.57,
"learning_rate": 8.337229562058707e-06,
"loss": 0.836,
"step": 1472
},
{
"epoch": 0.57,
"learning_rate": 8.324937766952638e-06,
"loss": 0.829,
"step": 1473
},
{
"epoch": 0.57,
"learning_rate": 8.312648575178552e-06,
"loss": 0.814,
"step": 1474
},
{
"epoch": 0.57,
"learning_rate": 8.300362005835947e-06,
"loss": 0.8389,
"step": 1475
},
{
"epoch": 0.57,
"learning_rate": 8.28807807802025e-06,
"loss": 0.8265,
"step": 1476
},
{
"epoch": 0.57,
"learning_rate": 8.275796810822774e-06,
"loss": 0.8771,
"step": 1477
},
{
"epoch": 0.57,
"learning_rate": 8.263518223330698e-06,
"loss": 0.8341,
"step": 1478
},
{
"epoch": 0.57,
"learning_rate": 8.251242334627039e-06,
"loss": 0.8276,
"step": 1479
},
{
"epoch": 0.57,
"learning_rate": 8.238969163790617e-06,
"loss": 0.7782,
"step": 1480
},
{
"epoch": 0.57,
"learning_rate": 8.226698729896036e-06,
"loss": 0.8082,
"step": 1481
},
{
"epoch": 0.57,
"learning_rate": 8.214431052013636e-06,
"loss": 0.8035,
"step": 1482
},
{
"epoch": 0.57,
"learning_rate": 8.202166149209475e-06,
"loss": 0.8104,
"step": 1483
},
{
"epoch": 0.57,
"learning_rate": 8.189904040545302e-06,
"loss": 0.8652,
"step": 1484
},
{
"epoch": 0.57,
"learning_rate": 8.177644745078525e-06,
"loss": 0.8609,
"step": 1485
},
{
"epoch": 0.57,
"learning_rate": 8.165388281862177e-06,
"loss": 0.853,
"step": 1486
},
{
"epoch": 0.57,
"learning_rate": 8.153134669944887e-06,
"loss": 0.8484,
"step": 1487
},
{
"epoch": 0.57,
"learning_rate": 8.140883928370855e-06,
"loss": 0.8217,
"step": 1488
},
{
"epoch": 0.57,
"learning_rate": 8.12863607617982e-06,
"loss": 0.889,
"step": 1489
},
{
"epoch": 0.57,
"learning_rate": 8.116391132407033e-06,
"loss": 0.8456,
"step": 1490
},
{
"epoch": 0.57,
"learning_rate": 8.104149116083216e-06,
"loss": 0.866,
"step": 1491
},
{
"epoch": 0.57,
"learning_rate": 8.091910046234552e-06,
"loss": 0.8521,
"step": 1492
},
{
"epoch": 0.57,
"learning_rate": 8.079673941882639e-06,
"loss": 0.8547,
"step": 1493
},
{
"epoch": 0.58,
"learning_rate": 8.06744082204447e-06,
"loss": 0.8857,
"step": 1494
},
{
"epoch": 0.58,
"learning_rate": 8.055210705732391e-06,
"loss": 0.5206,
"step": 1495
},
{
"epoch": 0.58,
"learning_rate": 8.042983611954087e-06,
"loss": 0.8447,
"step": 1496
},
{
"epoch": 0.58,
"learning_rate": 8.030759559712545e-06,
"loss": 0.8532,
"step": 1497
},
{
"epoch": 0.58,
"learning_rate": 8.018538568006027e-06,
"loss": 0.8654,
"step": 1498
},
{
"epoch": 0.58,
"learning_rate": 8.00632065582803e-06,
"loss": 0.818,
"step": 1499
},
{
"epoch": 0.58,
"learning_rate": 7.994105842167274e-06,
"loss": 0.8684,
"step": 1500
},
{
"epoch": 0.58,
"learning_rate": 7.981894146007658e-06,
"loss": 0.8599,
"step": 1501
},
{
"epoch": 0.58,
"learning_rate": 7.96968558632824e-06,
"loss": 0.8519,
"step": 1502
},
{
"epoch": 0.58,
"learning_rate": 7.957480182103198e-06,
"loss": 0.795,
"step": 1503
},
{
"epoch": 0.58,
"learning_rate": 7.945277952301811e-06,
"loss": 0.8247,
"step": 1504
},
{
"epoch": 0.58,
"learning_rate": 7.93307891588842e-06,
"loss": 0.8942,
"step": 1505
},
{
"epoch": 0.58,
"learning_rate": 7.92088309182241e-06,
"loss": 0.896,
"step": 1506
},
{
"epoch": 0.58,
"learning_rate": 7.908690499058162e-06,
"loss": 0.8889,
"step": 1507
},
{
"epoch": 0.58,
"learning_rate": 7.896501156545044e-06,
"loss": 0.4789,
"step": 1508
},
{
"epoch": 0.58,
"learning_rate": 7.884315083227373e-06,
"loss": 0.8654,
"step": 1509
},
{
"epoch": 0.58,
"learning_rate": 7.872132298044382e-06,
"loss": 0.8226,
"step": 1510
},
{
"epoch": 0.58,
"learning_rate": 7.859952819930188e-06,
"loss": 0.8489,
"step": 1511
},
{
"epoch": 0.58,
"learning_rate": 7.847776667813782e-06,
"loss": 0.8326,
"step": 1512
},
{
"epoch": 0.58,
"learning_rate": 7.835603860618973e-06,
"loss": 0.8231,
"step": 1513
},
{
"epoch": 0.58,
"learning_rate": 7.823434417264378e-06,
"loss": 0.8318,
"step": 1514
},
{
"epoch": 0.58,
"learning_rate": 7.811268356663387e-06,
"loss": 0.823,
"step": 1515
},
{
"epoch": 0.58,
"learning_rate": 7.799105697724127e-06,
"loss": 0.8589,
"step": 1516
},
{
"epoch": 0.58,
"learning_rate": 7.786946459349441e-06,
"loss": 0.8716,
"step": 1517
},
{
"epoch": 0.58,
"learning_rate": 7.774790660436857e-06,
"loss": 0.8845,
"step": 1518
},
{
"epoch": 0.58,
"learning_rate": 7.76263831987856e-06,
"loss": 0.7881,
"step": 1519
},
{
"epoch": 0.59,
"learning_rate": 7.750489456561351e-06,
"loss": 0.8155,
"step": 1520
},
{
"epoch": 0.59,
"learning_rate": 7.738344089366638e-06,
"loss": 0.809,
"step": 1521
},
{
"epoch": 0.59,
"learning_rate": 7.726202237170387e-06,
"loss": 0.5464,
"step": 1522
},
{
"epoch": 0.59,
"learning_rate": 7.714063918843106e-06,
"loss": 0.8646,
"step": 1523
},
{
"epoch": 0.59,
"learning_rate": 7.701929153249808e-06,
"loss": 0.8451,
"step": 1524
},
{
"epoch": 0.59,
"learning_rate": 7.689797959249984e-06,
"loss": 0.8276,
"step": 1525
},
{
"epoch": 0.59,
"learning_rate": 7.677670355697577e-06,
"loss": 0.8766,
"step": 1526
},
{
"epoch": 0.59,
"learning_rate": 7.66554636144095e-06,
"loss": 0.8275,
"step": 1527
},
{
"epoch": 0.59,
"learning_rate": 7.653425995322852e-06,
"loss": 0.8531,
"step": 1528
},
{
"epoch": 0.59,
"learning_rate": 7.641309276180394e-06,
"loss": 0.5328,
"step": 1529
},
{
"epoch": 0.59,
"learning_rate": 7.629196222845027e-06,
"loss": 0.8907,
"step": 1530
},
{
"epoch": 0.59,
"learning_rate": 7.617086854142498e-06,
"loss": 0.8945,
"step": 1531
},
{
"epoch": 0.59,
"learning_rate": 7.6049811888928235e-06,
"loss": 0.7942,
"step": 1532
},
{
"epoch": 0.59,
"learning_rate": 7.592879245910273e-06,
"loss": 0.8066,
"step": 1533
},
{
"epoch": 0.59,
"learning_rate": 7.580781044003324e-06,
"loss": 0.8142,
"step": 1534
},
{
"epoch": 0.59,
"learning_rate": 7.5686866019746444e-06,
"loss": 0.8512,
"step": 1535
},
{
"epoch": 0.59,
"learning_rate": 7.556595938621058e-06,
"loss": 0.8098,
"step": 1536
},
{
"epoch": 0.59,
"learning_rate": 7.544509072733515e-06,
"loss": 0.8542,
"step": 1537
},
{
"epoch": 0.59,
"learning_rate": 7.532426023097063e-06,
"loss": 0.8947,
"step": 1538
},
{
"epoch": 0.59,
"learning_rate": 7.5203468084908185e-06,
"loss": 0.8118,
"step": 1539
},
{
"epoch": 0.59,
"learning_rate": 7.508271447687936e-06,
"loss": 0.8369,
"step": 1540
},
{
"epoch": 0.59,
"learning_rate": 7.496199959455584e-06,
"loss": 0.8259,
"step": 1541
},
{
"epoch": 0.59,
"learning_rate": 7.484132362554915e-06,
"loss": 0.7937,
"step": 1542
},
{
"epoch": 0.59,
"learning_rate": 7.472068675741024e-06,
"loss": 0.8296,
"step": 1543
},
{
"epoch": 0.59,
"learning_rate": 7.4600089177629384e-06,
"loss": 0.8347,
"step": 1544
},
{
"epoch": 0.59,
"learning_rate": 7.447953107363574e-06,
"loss": 0.5039,
"step": 1545
},
{
"epoch": 0.6,
"learning_rate": 7.435901263279717e-06,
"loss": 0.8,
"step": 1546
},
{
"epoch": 0.6,
"learning_rate": 7.4238534042419805e-06,
"loss": 0.8513,
"step": 1547
},
{
"epoch": 0.6,
"learning_rate": 7.411809548974792e-06,
"loss": 0.8231,
"step": 1548
},
{
"epoch": 0.6,
"learning_rate": 7.399769716196353e-06,
"loss": 0.8394,
"step": 1549
},
{
"epoch": 0.6,
"learning_rate": 7.387733924618617e-06,
"loss": 0.8508,
"step": 1550
},
{
"epoch": 0.6,
"learning_rate": 7.3757021929472495e-06,
"loss": 0.8342,
"step": 1551
},
{
"epoch": 0.6,
"learning_rate": 7.3636745398816135e-06,
"loss": 0.8491,
"step": 1552
},
{
"epoch": 0.6,
"learning_rate": 7.3516509841147276e-06,
"loss": 0.7637,
"step": 1553
},
{
"epoch": 0.6,
"learning_rate": 7.33963154433325e-06,
"loss": 0.8091,
"step": 1554
},
{
"epoch": 0.6,
"learning_rate": 7.327616239217432e-06,
"loss": 0.9055,
"step": 1555
},
{
"epoch": 0.6,
"learning_rate": 7.315605087441107e-06,
"loss": 0.8439,
"step": 1556
},
{
"epoch": 0.6,
"learning_rate": 7.303598107671648e-06,
"loss": 0.8875,
"step": 1557
},
{
"epoch": 0.6,
"learning_rate": 7.291595318569951e-06,
"loss": 0.8422,
"step": 1558
},
{
"epoch": 0.6,
"learning_rate": 7.279596738790389e-06,
"loss": 0.8529,
"step": 1559
},
{
"epoch": 0.6,
"learning_rate": 7.267602386980801e-06,
"loss": 0.8541,
"step": 1560
},
{
"epoch": 0.6,
"learning_rate": 7.255612281782451e-06,
"loss": 0.8591,
"step": 1561
},
{
"epoch": 0.6,
"learning_rate": 7.243626441830009e-06,
"loss": 0.8605,
"step": 1562
},
{
"epoch": 0.6,
"learning_rate": 7.2316448857515076e-06,
"loss": 0.8495,
"step": 1563
},
{
"epoch": 0.6,
"learning_rate": 7.219667632168326e-06,
"loss": 0.875,
"step": 1564
},
{
"epoch": 0.6,
"learning_rate": 7.207694699695155e-06,
"loss": 0.8204,
"step": 1565
},
{
"epoch": 0.6,
"learning_rate": 7.1957261069399745e-06,
"loss": 0.8458,
"step": 1566
},
{
"epoch": 0.6,
"learning_rate": 7.183761872504011e-06,
"loss": 0.8435,
"step": 1567
},
{
"epoch": 0.6,
"learning_rate": 7.171802014981726e-06,
"loss": 0.5275,
"step": 1568
},
{
"epoch": 0.6,
"learning_rate": 7.159846552960774e-06,
"loss": 0.8104,
"step": 1569
},
{
"epoch": 0.6,
"learning_rate": 7.14789550502198e-06,
"loss": 0.8256,
"step": 1570
},
{
"epoch": 0.6,
"learning_rate": 7.135948889739307e-06,
"loss": 0.8468,
"step": 1571
},
{
"epoch": 0.61,
"learning_rate": 7.124006725679828e-06,
"loss": 0.8661,
"step": 1572
},
{
"epoch": 0.61,
"learning_rate": 7.112069031403704e-06,
"loss": 0.7977,
"step": 1573
},
{
"epoch": 0.61,
"learning_rate": 7.100135825464138e-06,
"loss": 0.854,
"step": 1574
},
{
"epoch": 0.61,
"learning_rate": 7.088207126407374e-06,
"loss": 0.8597,
"step": 1575
},
{
"epoch": 0.61,
"learning_rate": 7.076282952772634e-06,
"loss": 0.8071,
"step": 1576
},
{
"epoch": 0.61,
"learning_rate": 7.064363323092117e-06,
"loss": 0.8434,
"step": 1577
},
{
"epoch": 0.61,
"learning_rate": 7.052448255890958e-06,
"loss": 0.7792,
"step": 1578
},
{
"epoch": 0.61,
"learning_rate": 7.040537769687204e-06,
"loss": 0.9226,
"step": 1579
},
{
"epoch": 0.61,
"learning_rate": 7.028631882991771e-06,
"loss": 0.8671,
"step": 1580
},
{
"epoch": 0.61,
"learning_rate": 7.01673061430844e-06,
"loss": 0.8254,
"step": 1581
},
{
"epoch": 0.61,
"learning_rate": 7.004833982133808e-06,
"loss": 0.7768,
"step": 1582
},
{
"epoch": 0.61,
"learning_rate": 6.992942004957271e-06,
"loss": 0.8513,
"step": 1583
},
{
"epoch": 0.61,
"learning_rate": 6.981054701260981e-06,
"loss": 0.8329,
"step": 1584
},
{
"epoch": 0.61,
"learning_rate": 6.969172089519836e-06,
"loss": 0.8212,
"step": 1585
},
{
"epoch": 0.61,
"learning_rate": 6.957294188201438e-06,
"loss": 0.8267,
"step": 1586
},
{
"epoch": 0.61,
"learning_rate": 6.9454210157660694e-06,
"loss": 0.8492,
"step": 1587
},
{
"epoch": 0.61,
"learning_rate": 6.933552590666659e-06,
"loss": 0.8721,
"step": 1588
},
{
"epoch": 0.61,
"learning_rate": 6.921688931348762e-06,
"loss": 0.8933,
"step": 1589
},
{
"epoch": 0.61,
"learning_rate": 6.909830056250527e-06,
"loss": 0.8972,
"step": 1590
},
{
"epoch": 0.61,
"learning_rate": 6.8979759838026676e-06,
"loss": 0.8697,
"step": 1591
},
{
"epoch": 0.61,
"learning_rate": 6.886126732428424e-06,
"loss": 0.8663,
"step": 1592
},
{
"epoch": 0.61,
"learning_rate": 6.874282320543557e-06,
"loss": 0.5365,
"step": 1593
},
{
"epoch": 0.61,
"learning_rate": 6.862442766556297e-06,
"loss": 0.8295,
"step": 1594
},
{
"epoch": 0.61,
"learning_rate": 6.850608088867332e-06,
"loss": 0.8423,
"step": 1595
},
{
"epoch": 0.61,
"learning_rate": 6.83877830586976e-06,
"loss": 0.8916,
"step": 1596
},
{
"epoch": 0.61,
"learning_rate": 6.826953435949081e-06,
"loss": 0.8457,
"step": 1597
},
{
"epoch": 0.62,
"learning_rate": 6.815133497483157e-06,
"loss": 0.7969,
"step": 1598
},
{
"epoch": 0.62,
"learning_rate": 6.8033185088421874e-06,
"loss": 0.7993,
"step": 1599
},
{
"epoch": 0.62,
"learning_rate": 6.791508488388675e-06,
"loss": 0.8572,
"step": 1600
},
{
"epoch": 0.62,
"learning_rate": 6.779703454477402e-06,
"loss": 0.7807,
"step": 1601
},
{
"epoch": 0.62,
"learning_rate": 6.767903425455402e-06,
"loss": 0.7936,
"step": 1602
},
{
"epoch": 0.62,
"learning_rate": 6.7561084196619306e-06,
"loss": 0.7997,
"step": 1603
},
{
"epoch": 0.62,
"learning_rate": 6.744318455428436e-06,
"loss": 0.8296,
"step": 1604
},
{
"epoch": 0.62,
"learning_rate": 6.732533551078528e-06,
"loss": 0.8136,
"step": 1605
},
{
"epoch": 0.62,
"learning_rate": 6.720753724927957e-06,
"loss": 0.9095,
"step": 1606
},
{
"epoch": 0.62,
"learning_rate": 6.708978995284581e-06,
"loss": 0.8546,
"step": 1607
},
{
"epoch": 0.62,
"learning_rate": 6.697209380448333e-06,
"loss": 0.8192,
"step": 1608
},
{
"epoch": 0.62,
"learning_rate": 6.685444898711196e-06,
"loss": 0.8562,
"step": 1609
},
{
"epoch": 0.62,
"learning_rate": 6.673685568357182e-06,
"loss": 0.8762,
"step": 1610
},
{
"epoch": 0.62,
"learning_rate": 6.661931407662292e-06,
"loss": 0.7822,
"step": 1611
},
{
"epoch": 0.62,
"learning_rate": 6.650182434894496e-06,
"loss": 0.8784,
"step": 1612
},
{
"epoch": 0.62,
"learning_rate": 6.638438668313695e-06,
"loss": 0.8075,
"step": 1613
},
{
"epoch": 0.62,
"learning_rate": 6.6267001261717015e-06,
"loss": 0.8312,
"step": 1614
},
{
"epoch": 0.62,
"learning_rate": 6.614966826712212e-06,
"loss": 0.8501,
"step": 1615
},
{
"epoch": 0.62,
"learning_rate": 6.603238788170771e-06,
"loss": 0.8515,
"step": 1616
},
{
"epoch": 0.62,
"learning_rate": 6.59151602877475e-06,
"loss": 0.5416,
"step": 1617
},
{
"epoch": 0.62,
"learning_rate": 6.579798566743314e-06,
"loss": 0.861,
"step": 1618
},
{
"epoch": 0.62,
"learning_rate": 6.568086420287389e-06,
"loss": 0.804,
"step": 1619
},
{
"epoch": 0.62,
"learning_rate": 6.5563796076096484e-06,
"loss": 0.8597,
"step": 1620
},
{
"epoch": 0.62,
"learning_rate": 6.544678146904475e-06,
"loss": 0.8268,
"step": 1621
},
{
"epoch": 0.62,
"learning_rate": 6.532982056357928e-06,
"loss": 0.8031,
"step": 1622
},
{
"epoch": 0.62,
"learning_rate": 6.521291354147727e-06,
"loss": 0.8418,
"step": 1623
},
{
"epoch": 0.63,
"learning_rate": 6.5096060584432134e-06,
"loss": 0.8093,
"step": 1624
},
{
"epoch": 0.63,
"learning_rate": 6.497926187405326e-06,
"loss": 0.8265,
"step": 1625
},
{
"epoch": 0.63,
"learning_rate": 6.486251759186573e-06,
"loss": 0.8336,
"step": 1626
},
{
"epoch": 0.63,
"learning_rate": 6.474582791931006e-06,
"loss": 0.8737,
"step": 1627
},
{
"epoch": 0.63,
"learning_rate": 6.462919303774186e-06,
"loss": 0.8284,
"step": 1628
},
{
"epoch": 0.63,
"learning_rate": 6.45126131284316e-06,
"loss": 0.819,
"step": 1629
},
{
"epoch": 0.63,
"learning_rate": 6.439608837256432e-06,
"loss": 0.8755,
"step": 1630
},
{
"epoch": 0.63,
"learning_rate": 6.427961895123935e-06,
"loss": 0.8314,
"step": 1631
},
{
"epoch": 0.63,
"learning_rate": 6.4163205045469975e-06,
"loss": 0.8054,
"step": 1632
},
{
"epoch": 0.63,
"learning_rate": 6.404684683618325e-06,
"loss": 0.4785,
"step": 1633
},
{
"epoch": 0.63,
"learning_rate": 6.393054450421963e-06,
"loss": 0.8329,
"step": 1634
},
{
"epoch": 0.63,
"learning_rate": 6.381429823033281e-06,
"loss": 0.8627,
"step": 1635
},
{
"epoch": 0.63,
"learning_rate": 6.36981081951892e-06,
"loss": 0.8286,
"step": 1636
},
{
"epoch": 0.63,
"learning_rate": 6.358197457936796e-06,
"loss": 0.8119,
"step": 1637
},
{
"epoch": 0.63,
"learning_rate": 6.34658975633605e-06,
"loss": 0.8733,
"step": 1638
},
{
"epoch": 0.63,
"learning_rate": 6.334987732757028e-06,
"loss": 0.91,
"step": 1639
},
{
"epoch": 0.63,
"learning_rate": 6.32339140523125e-06,
"loss": 0.7728,
"step": 1640
},
{
"epoch": 0.63,
"learning_rate": 6.311800791781381e-06,
"loss": 0.7941,
"step": 1641
},
{
"epoch": 0.63,
"learning_rate": 6.300215910421212e-06,
"loss": 0.8419,
"step": 1642
},
{
"epoch": 0.63,
"learning_rate": 6.288636779155621e-06,
"loss": 0.8396,
"step": 1643
},
{
"epoch": 0.63,
"learning_rate": 6.277063415980549e-06,
"loss": 0.8452,
"step": 1644
},
{
"epoch": 0.63,
"learning_rate": 6.265495838882973e-06,
"loss": 0.8259,
"step": 1645
},
{
"epoch": 0.63,
"learning_rate": 6.25393406584088e-06,
"loss": 0.8239,
"step": 1646
},
{
"epoch": 0.63,
"learning_rate": 6.2423781148232345e-06,
"loss": 0.8078,
"step": 1647
},
{
"epoch": 0.63,
"learning_rate": 6.230828003789949e-06,
"loss": 0.8397,
"step": 1648
},
{
"epoch": 0.63,
"learning_rate": 6.219283750691864e-06,
"loss": 0.8218,
"step": 1649
},
{
"epoch": 0.64,
"learning_rate": 6.207745373470717e-06,
"loss": 0.8344,
"step": 1650
},
{
"epoch": 0.64,
"learning_rate": 6.196212890059111e-06,
"loss": 0.858,
"step": 1651
},
{
"epoch": 0.64,
"learning_rate": 6.184686318380488e-06,
"loss": 0.8168,
"step": 1652
},
{
"epoch": 0.64,
"learning_rate": 6.173165676349103e-06,
"loss": 0.8253,
"step": 1653
},
{
"epoch": 0.64,
"learning_rate": 6.1616509818699975e-06,
"loss": 0.8323,
"step": 1654
},
{
"epoch": 0.64,
"learning_rate": 6.150142252838967e-06,
"loss": 0.8636,
"step": 1655
},
{
"epoch": 0.64,
"learning_rate": 6.138639507142539e-06,
"loss": 0.8543,
"step": 1656
},
{
"epoch": 0.64,
"learning_rate": 6.127142762657934e-06,
"loss": 0.8679,
"step": 1657
},
{
"epoch": 0.64,
"learning_rate": 6.115652037253054e-06,
"loss": 0.8004,
"step": 1658
},
{
"epoch": 0.64,
"learning_rate": 6.104167348786443e-06,
"loss": 0.8453,
"step": 1659
},
{
"epoch": 0.64,
"learning_rate": 6.092688715107265e-06,
"loss": 0.8605,
"step": 1660
},
{
"epoch": 0.64,
"learning_rate": 6.0812161540552675e-06,
"loss": 0.8044,
"step": 1661
},
{
"epoch": 0.64,
"learning_rate": 6.069749683460765e-06,
"loss": 0.8257,
"step": 1662
},
{
"epoch": 0.64,
"learning_rate": 6.058289321144608e-06,
"loss": 0.8188,
"step": 1663
},
{
"epoch": 0.64,
"learning_rate": 6.046835084918152e-06,
"loss": 0.8202,
"step": 1664
},
{
"epoch": 0.64,
"learning_rate": 6.0353869925832255e-06,
"loss": 0.5113,
"step": 1665
},
{
"epoch": 0.64,
"learning_rate": 6.023945061932119e-06,
"loss": 0.8375,
"step": 1666
},
{
"epoch": 0.64,
"learning_rate": 6.0125093107475385e-06,
"loss": 0.8721,
"step": 1667
},
{
"epoch": 0.64,
"learning_rate": 6.001079756802592e-06,
"loss": 0.8489,
"step": 1668
},
{
"epoch": 0.64,
"learning_rate": 5.98965641786075e-06,
"loss": 0.875,
"step": 1669
},
{
"epoch": 0.64,
"learning_rate": 5.978239311675826e-06,
"loss": 0.8094,
"step": 1670
},
{
"epoch": 0.64,
"learning_rate": 5.966828455991951e-06,
"loss": 0.8366,
"step": 1671
},
{
"epoch": 0.64,
"learning_rate": 5.955423868543537e-06,
"loss": 0.8308,
"step": 1672
},
{
"epoch": 0.64,
"learning_rate": 5.944025567055251e-06,
"loss": 0.8191,
"step": 1673
},
{
"epoch": 0.64,
"learning_rate": 5.932633569242e-06,
"loss": 0.8319,
"step": 1674
},
{
"epoch": 0.64,
"learning_rate": 5.921247892808886e-06,
"loss": 0.8442,
"step": 1675
},
{
"epoch": 0.65,
"learning_rate": 5.909868555451191e-06,
"loss": 0.8351,
"step": 1676
},
{
"epoch": 0.65,
"learning_rate": 5.898495574854342e-06,
"loss": 0.8254,
"step": 1677
},
{
"epoch": 0.65,
"learning_rate": 5.887128968693887e-06,
"loss": 0.7905,
"step": 1678
},
{
"epoch": 0.65,
"learning_rate": 5.875768754635469e-06,
"loss": 0.8828,
"step": 1679
},
{
"epoch": 0.65,
"learning_rate": 5.864414950334796e-06,
"loss": 0.8005,
"step": 1680
},
{
"epoch": 0.65,
"learning_rate": 5.853067573437612e-06,
"loss": 0.8053,
"step": 1681
},
{
"epoch": 0.65,
"learning_rate": 5.8417266415796745e-06,
"loss": 0.8173,
"step": 1682
},
{
"epoch": 0.65,
"learning_rate": 5.830392172386723e-06,
"loss": 0.856,
"step": 1683
},
{
"epoch": 0.65,
"learning_rate": 5.819064183474451e-06,
"loss": 0.8186,
"step": 1684
},
{
"epoch": 0.65,
"learning_rate": 5.807742692448483e-06,
"loss": 0.8678,
"step": 1685
},
{
"epoch": 0.65,
"learning_rate": 5.796427716904347e-06,
"loss": 0.8254,
"step": 1686
},
{
"epoch": 0.65,
"learning_rate": 5.78511927442744e-06,
"loss": 0.8273,
"step": 1687
},
{
"epoch": 0.65,
"learning_rate": 5.773817382593008e-06,
"loss": 0.8137,
"step": 1688
},
{
"epoch": 0.65,
"learning_rate": 5.7625220589661136e-06,
"loss": 0.4583,
"step": 1689
},
{
"epoch": 0.65,
"learning_rate": 5.751233321101617e-06,
"loss": 0.8436,
"step": 1690
},
{
"epoch": 0.65,
"learning_rate": 5.739951186544141e-06,
"loss": 0.8438,
"step": 1691
},
{
"epoch": 0.65,
"learning_rate": 5.728675672828037e-06,
"loss": 0.9084,
"step": 1692
},
{
"epoch": 0.65,
"learning_rate": 5.717406797477371e-06,
"loss": 0.8533,
"step": 1693
},
{
"epoch": 0.65,
"learning_rate": 5.706144578005908e-06,
"loss": 0.8318,
"step": 1694
},
{
"epoch": 0.65,
"learning_rate": 5.694889031917047e-06,
"loss": 0.8904,
"step": 1695
},
{
"epoch": 0.65,
"learning_rate": 5.683640176703824e-06,
"loss": 0.7744,
"step": 1696
},
{
"epoch": 0.65,
"learning_rate": 5.672398029848881e-06,
"loss": 0.8234,
"step": 1697
},
{
"epoch": 0.65,
"learning_rate": 5.66116260882442e-06,
"loss": 0.5094,
"step": 1698
},
{
"epoch": 0.65,
"learning_rate": 5.6499339310922015e-06,
"loss": 0.7991,
"step": 1699
},
{
"epoch": 0.65,
"learning_rate": 5.638712014103507e-06,
"loss": 0.8497,
"step": 1700
},
{
"epoch": 0.65,
"learning_rate": 5.627496875299102e-06,
"loss": 0.8079,
"step": 1701
},
{
"epoch": 0.66,
"learning_rate": 5.616288532109225e-06,
"loss": 0.4728,
"step": 1702
},
{
"epoch": 0.66,
"learning_rate": 5.6050870019535496e-06,
"loss": 0.7996,
"step": 1703
},
{
"epoch": 0.66,
"learning_rate": 5.5938923022411615e-06,
"loss": 0.8307,
"step": 1704
},
{
"epoch": 0.66,
"learning_rate": 5.582704450370533e-06,
"loss": 0.8378,
"step": 1705
},
{
"epoch": 0.66,
"learning_rate": 5.571523463729487e-06,
"loss": 0.5149,
"step": 1706
},
{
"epoch": 0.66,
"learning_rate": 5.560349359695181e-06,
"loss": 0.8414,
"step": 1707
},
{
"epoch": 0.66,
"learning_rate": 5.549182155634076e-06,
"loss": 0.8434,
"step": 1708
},
{
"epoch": 0.66,
"learning_rate": 5.5380218689019125e-06,
"loss": 0.7946,
"step": 1709
},
{
"epoch": 0.66,
"learning_rate": 5.526868516843673e-06,
"loss": 0.8329,
"step": 1710
},
{
"epoch": 0.66,
"learning_rate": 5.51572211679357e-06,
"loss": 0.8058,
"step": 1711
},
{
"epoch": 0.66,
"learning_rate": 5.504582686075002e-06,
"loss": 0.8925,
"step": 1712
},
{
"epoch": 0.66,
"learning_rate": 5.493450242000546e-06,
"loss": 0.801,
"step": 1713
},
{
"epoch": 0.66,
"learning_rate": 5.4823248018719184e-06,
"loss": 0.7975,
"step": 1714
},
{
"epoch": 0.66,
"learning_rate": 5.471206382979941e-06,
"loss": 0.8508,
"step": 1715
},
{
"epoch": 0.66,
"learning_rate": 5.460095002604533e-06,
"loss": 0.8737,
"step": 1716
},
{
"epoch": 0.66,
"learning_rate": 5.4489906780146716e-06,
"loss": 0.7582,
"step": 1717
},
{
"epoch": 0.66,
"learning_rate": 5.43789342646837e-06,
"loss": 0.8324,
"step": 1718
},
{
"epoch": 0.66,
"learning_rate": 5.4268032652126465e-06,
"loss": 0.4972,
"step": 1719
},
{
"epoch": 0.66,
"learning_rate": 5.415720211483499e-06,
"loss": 0.8792,
"step": 1720
},
{
"epoch": 0.66,
"learning_rate": 5.404644282505882e-06,
"loss": 0.7883,
"step": 1721
},
{
"epoch": 0.66,
"learning_rate": 5.393575495493679e-06,
"loss": 0.851,
"step": 1722
},
{
"epoch": 0.66,
"learning_rate": 5.382513867649663e-06,
"loss": 0.8772,
"step": 1723
},
{
"epoch": 0.66,
"learning_rate": 5.37145941616549e-06,
"loss": 0.7866,
"step": 1724
},
{
"epoch": 0.66,
"learning_rate": 5.360412158221661e-06,
"loss": 0.833,
"step": 1725
},
{
"epoch": 0.66,
"learning_rate": 5.349372110987496e-06,
"loss": 0.8625,
"step": 1726
},
{
"epoch": 0.66,
"learning_rate": 5.338339291621109e-06,
"loss": 0.8337,
"step": 1727
},
{
"epoch": 0.67,
"learning_rate": 5.32731371726938e-06,
"loss": 0.8286,
"step": 1728
},
{
"epoch": 0.67,
"learning_rate": 5.316295405067929e-06,
"loss": 0.8562,
"step": 1729
},
{
"epoch": 0.67,
"learning_rate": 5.305284372141095e-06,
"loss": 0.8193,
"step": 1730
},
{
"epoch": 0.67,
"learning_rate": 5.294280635601889e-06,
"loss": 0.8361,
"step": 1731
},
{
"epoch": 0.67,
"learning_rate": 5.283284212551997e-06,
"loss": 0.8122,
"step": 1732
},
{
"epoch": 0.67,
"learning_rate": 5.2722951200817315e-06,
"loss": 0.8422,
"step": 1733
},
{
"epoch": 0.67,
"learning_rate": 5.2613133752700145e-06,
"loss": 0.5154,
"step": 1734
},
{
"epoch": 0.67,
"learning_rate": 5.250338995184348e-06,
"loss": 0.8111,
"step": 1735
},
{
"epoch": 0.67,
"learning_rate": 5.239371996880786e-06,
"loss": 0.8327,
"step": 1736
},
{
"epoch": 0.67,
"learning_rate": 5.228412397403916e-06,
"loss": 0.8328,
"step": 1737
},
{
"epoch": 0.67,
"learning_rate": 5.217460213786822e-06,
"loss": 0.85,
"step": 1738
},
{
"epoch": 0.67,
"learning_rate": 5.206515463051054e-06,
"loss": 0.8307,
"step": 1739
},
{
"epoch": 0.67,
"learning_rate": 5.195578162206627e-06,
"loss": 0.8209,
"step": 1740
},
{
"epoch": 0.67,
"learning_rate": 5.184648328251965e-06,
"loss": 0.8481,
"step": 1741
},
{
"epoch": 0.67,
"learning_rate": 5.1737259781738934e-06,
"loss": 0.8653,
"step": 1742
},
{
"epoch": 0.67,
"learning_rate": 5.1628111289476025e-06,
"loss": 0.8427,
"step": 1743
},
{
"epoch": 0.67,
"learning_rate": 5.151903797536631e-06,
"loss": 0.8501,
"step": 1744
},
{
"epoch": 0.67,
"learning_rate": 5.141004000892824e-06,
"loss": 0.8589,
"step": 1745
},
{
"epoch": 0.67,
"learning_rate": 5.130111755956327e-06,
"loss": 0.8398,
"step": 1746
},
{
"epoch": 0.67,
"learning_rate": 5.119227079655544e-06,
"loss": 0.8622,
"step": 1747
},
{
"epoch": 0.67,
"learning_rate": 5.108349988907111e-06,
"loss": 0.8168,
"step": 1748
},
{
"epoch": 0.67,
"learning_rate": 5.097480500615879e-06,
"loss": 0.8008,
"step": 1749
},
{
"epoch": 0.67,
"learning_rate": 5.086618631674888e-06,
"loss": 0.8386,
"step": 1750
},
{
"epoch": 0.67,
"learning_rate": 5.075764398965331e-06,
"loss": 0.8593,
"step": 1751
},
{
"epoch": 0.67,
"learning_rate": 5.064917819356532e-06,
"loss": 0.8883,
"step": 1752
},
{
"epoch": 0.67,
"learning_rate": 5.054078909705926e-06,
"loss": 0.8353,
"step": 1753
},
{
"epoch": 0.68,
"learning_rate": 5.043247686859024e-06,
"loss": 0.8129,
"step": 1754
},
{
"epoch": 0.68,
"learning_rate": 5.032424167649394e-06,
"loss": 0.849,
"step": 1755
},
{
"epoch": 0.68,
"learning_rate": 5.021608368898621e-06,
"loss": 0.8477,
"step": 1756
},
{
"epoch": 0.68,
"learning_rate": 5.0108003074163005e-06,
"loss": 0.809,
"step": 1757
},
{
"epoch": 0.68,
"learning_rate": 5.000000000000003e-06,
"loss": 0.7932,
"step": 1758
},
{
"epoch": 0.68,
"learning_rate": 4.989207463435244e-06,
"loss": 0.8594,
"step": 1759
},
{
"epoch": 0.68,
"learning_rate": 4.978422714495465e-06,
"loss": 0.7674,
"step": 1760
},
{
"epoch": 0.68,
"learning_rate": 4.967645769942e-06,
"loss": 0.8336,
"step": 1761
},
{
"epoch": 0.68,
"learning_rate": 4.956876646524059e-06,
"loss": 0.8607,
"step": 1762
},
{
"epoch": 0.68,
"learning_rate": 4.946115360978696e-06,
"loss": 0.8148,
"step": 1763
},
{
"epoch": 0.68,
"learning_rate": 4.935361930030774e-06,
"loss": 0.8198,
"step": 1764
},
{
"epoch": 0.68,
"learning_rate": 4.924616370392962e-06,
"loss": 0.8726,
"step": 1765
},
{
"epoch": 0.68,
"learning_rate": 4.9138786987656865e-06,
"loss": 0.8201,
"step": 1766
},
{
"epoch": 0.68,
"learning_rate": 4.9031489318371195e-06,
"loss": 0.8544,
"step": 1767
},
{
"epoch": 0.68,
"learning_rate": 4.892427086283147e-06,
"loss": 0.8161,
"step": 1768
},
{
"epoch": 0.68,
"learning_rate": 4.881713178767341e-06,
"loss": 0.8415,
"step": 1769
},
{
"epoch": 0.68,
"learning_rate": 4.87100722594094e-06,
"loss": 0.8476,
"step": 1770
},
{
"epoch": 0.68,
"learning_rate": 4.860309244442821e-06,
"loss": 0.5125,
"step": 1771
},
{
"epoch": 0.68,
"learning_rate": 4.849619250899458e-06,
"loss": 0.8295,
"step": 1772
},
{
"epoch": 0.68,
"learning_rate": 4.838937261924933e-06,
"loss": 0.8108,
"step": 1773
},
{
"epoch": 0.68,
"learning_rate": 4.8282632941208725e-06,
"loss": 0.7609,
"step": 1774
},
{
"epoch": 0.68,
"learning_rate": 4.817597364076441e-06,
"loss": 0.8272,
"step": 1775
},
{
"epoch": 0.68,
"learning_rate": 4.806939488368308e-06,
"loss": 0.8241,
"step": 1776
},
{
"epoch": 0.68,
"learning_rate": 4.796289683560631e-06,
"loss": 0.8099,
"step": 1777
},
{
"epoch": 0.68,
"learning_rate": 4.78564796620502e-06,
"loss": 0.8273,
"step": 1778
},
{
"epoch": 0.68,
"learning_rate": 4.775014352840512e-06,
"loss": 0.863,
"step": 1779
},
{
"epoch": 0.69,
"learning_rate": 4.764388859993556e-06,
"loss": 0.7832,
"step": 1780
},
{
"epoch": 0.69,
"learning_rate": 4.753771504177976e-06,
"loss": 0.7912,
"step": 1781
},
{
"epoch": 0.69,
"learning_rate": 4.743162301894952e-06,
"loss": 0.791,
"step": 1782
},
{
"epoch": 0.69,
"learning_rate": 4.732561269632992e-06,
"loss": 0.8029,
"step": 1783
},
{
"epoch": 0.69,
"learning_rate": 4.7219684238679066e-06,
"loss": 0.8108,
"step": 1784
},
{
"epoch": 0.69,
"learning_rate": 4.711383781062779e-06,
"loss": 0.8929,
"step": 1785
},
{
"epoch": 0.69,
"learning_rate": 4.700807357667953e-06,
"loss": 0.8093,
"step": 1786
},
{
"epoch": 0.69,
"learning_rate": 4.6902391701209826e-06,
"loss": 0.7939,
"step": 1787
},
{
"epoch": 0.69,
"learning_rate": 4.679679234846636e-06,
"loss": 0.4957,
"step": 1788
},
{
"epoch": 0.69,
"learning_rate": 4.669127568256851e-06,
"loss": 0.8292,
"step": 1789
},
{
"epoch": 0.69,
"learning_rate": 4.658584186750713e-06,
"loss": 0.8351,
"step": 1790
},
{
"epoch": 0.69,
"learning_rate": 4.648049106714434e-06,
"loss": 0.8088,
"step": 1791
},
{
"epoch": 0.69,
"learning_rate": 4.637522344521323e-06,
"loss": 0.8187,
"step": 1792
},
{
"epoch": 0.69,
"learning_rate": 4.627003916531761e-06,
"loss": 0.8389,
"step": 1793
},
{
"epoch": 0.69,
"learning_rate": 4.616493839093179e-06,
"loss": 0.5279,
"step": 1794
},
{
"epoch": 0.69,
"learning_rate": 4.60599212854002e-06,
"loss": 0.8359,
"step": 1795
},
{
"epoch": 0.69,
"learning_rate": 4.595498801193736e-06,
"loss": 0.7855,
"step": 1796
},
{
"epoch": 0.69,
"learning_rate": 4.5850138733627435e-06,
"loss": 0.8085,
"step": 1797
},
{
"epoch": 0.69,
"learning_rate": 4.5745373613424075e-06,
"loss": 0.7926,
"step": 1798
},
{
"epoch": 0.69,
"learning_rate": 4.564069281415009e-06,
"loss": 0.8768,
"step": 1799
},
{
"epoch": 0.69,
"learning_rate": 4.5536096498497295e-06,
"loss": 0.8511,
"step": 1800
},
{
"epoch": 0.69,
"learning_rate": 4.543158482902617e-06,
"loss": 0.7458,
"step": 1801
},
{
"epoch": 0.69,
"learning_rate": 4.532715796816565e-06,
"loss": 0.8359,
"step": 1802
},
{
"epoch": 0.69,
"learning_rate": 4.522281607821288e-06,
"loss": 0.851,
"step": 1803
},
{
"epoch": 0.69,
"learning_rate": 4.511855932133289e-06,
"loss": 0.7905,
"step": 1804
},
{
"epoch": 0.69,
"learning_rate": 4.501438785955845e-06,
"loss": 0.8258,
"step": 1805
},
{
"epoch": 0.7,
"learning_rate": 4.491030185478976e-06,
"loss": 0.8081,
"step": 1806
},
{
"epoch": 0.7,
"learning_rate": 4.480630146879419e-06,
"loss": 0.8185,
"step": 1807
},
{
"epoch": 0.7,
"learning_rate": 4.470238686320606e-06,
"loss": 0.8572,
"step": 1808
},
{
"epoch": 0.7,
"learning_rate": 4.459855819952635e-06,
"loss": 0.8495,
"step": 1809
},
{
"epoch": 0.7,
"learning_rate": 4.449481563912252e-06,
"loss": 0.8127,
"step": 1810
},
{
"epoch": 0.7,
"learning_rate": 4.439115934322816e-06,
"loss": 0.5001,
"step": 1811
},
{
"epoch": 0.7,
"learning_rate": 4.428758947294278e-06,
"loss": 0.7979,
"step": 1812
},
{
"epoch": 0.7,
"learning_rate": 4.418410618923163e-06,
"loss": 0.838,
"step": 1813
},
{
"epoch": 0.7,
"learning_rate": 4.408070965292534e-06,
"loss": 0.8432,
"step": 1814
},
{
"epoch": 0.7,
"learning_rate": 4.397740002471973e-06,
"loss": 0.8181,
"step": 1815
},
{
"epoch": 0.7,
"learning_rate": 4.387417746517557e-06,
"loss": 0.8129,
"step": 1816
},
{
"epoch": 0.7,
"learning_rate": 4.377104213471831e-06,
"loss": 0.8579,
"step": 1817
},
{
"epoch": 0.7,
"learning_rate": 4.3667994193637794e-06,
"loss": 0.5257,
"step": 1818
},
{
"epoch": 0.7,
"learning_rate": 4.356503380208812e-06,
"loss": 0.8257,
"step": 1819
},
{
"epoch": 0.7,
"learning_rate": 4.34621611200872e-06,
"loss": 0.8203,
"step": 1820
},
{
"epoch": 0.7,
"learning_rate": 4.335937630751675e-06,
"loss": 0.7671,
"step": 1821
},
{
"epoch": 0.7,
"learning_rate": 4.325667952412184e-06,
"loss": 0.8625,
"step": 1822
},
{
"epoch": 0.7,
"learning_rate": 4.315407092951078e-06,
"loss": 0.4756,
"step": 1823
},
{
"epoch": 0.7,
"learning_rate": 4.305155068315481e-06,
"loss": 0.8201,
"step": 1824
},
{
"epoch": 0.7,
"learning_rate": 4.2949118944387846e-06,
"loss": 0.8704,
"step": 1825
},
{
"epoch": 0.7,
"learning_rate": 4.284677587240625e-06,
"loss": 0.8506,
"step": 1826
},
{
"epoch": 0.7,
"learning_rate": 4.27445216262686e-06,
"loss": 0.8038,
"step": 1827
},
{
"epoch": 0.7,
"learning_rate": 4.264235636489542e-06,
"loss": 0.8091,
"step": 1828
},
{
"epoch": 0.7,
"learning_rate": 4.254028024706887e-06,
"loss": 0.8041,
"step": 1829
},
{
"epoch": 0.7,
"learning_rate": 4.2438293431432665e-06,
"loss": 0.4873,
"step": 1830
},
{
"epoch": 0.7,
"learning_rate": 4.233639607649168e-06,
"loss": 0.7692,
"step": 1831
},
{
"epoch": 0.71,
"learning_rate": 4.223458834061175e-06,
"loss": 0.808,
"step": 1832
},
{
"epoch": 0.71,
"learning_rate": 4.213287038201943e-06,
"loss": 0.8754,
"step": 1833
},
{
"epoch": 0.71,
"learning_rate": 4.203124235880179e-06,
"loss": 0.8248,
"step": 1834
},
{
"epoch": 0.71,
"learning_rate": 4.192970442890602e-06,
"loss": 0.5239,
"step": 1835
},
{
"epoch": 0.71,
"learning_rate": 4.182825675013945e-06,
"loss": 0.808,
"step": 1836
},
{
"epoch": 0.71,
"learning_rate": 4.172689948016896e-06,
"loss": 0.8279,
"step": 1837
},
{
"epoch": 0.71,
"learning_rate": 4.162563277652104e-06,
"loss": 0.8564,
"step": 1838
},
{
"epoch": 0.71,
"learning_rate": 4.152445679658139e-06,
"loss": 0.8235,
"step": 1839
},
{
"epoch": 0.71,
"learning_rate": 4.142337169759472e-06,
"loss": 0.8481,
"step": 1840
},
{
"epoch": 0.71,
"learning_rate": 4.132237763666451e-06,
"loss": 0.5102,
"step": 1841
},
{
"epoch": 0.71,
"learning_rate": 4.12214747707527e-06,
"loss": 0.855,
"step": 1842
},
{
"epoch": 0.71,
"learning_rate": 4.112066325667954e-06,
"loss": 0.8544,
"step": 1843
},
{
"epoch": 0.71,
"learning_rate": 4.101994325112332e-06,
"loss": 0.829,
"step": 1844
},
{
"epoch": 0.71,
"learning_rate": 4.0919314910620025e-06,
"loss": 0.7968,
"step": 1845
},
{
"epoch": 0.71,
"learning_rate": 4.0818778391563255e-06,
"loss": 0.814,
"step": 1846
},
{
"epoch": 0.71,
"learning_rate": 4.07183338502039e-06,
"loss": 0.8611,
"step": 1847
},
{
"epoch": 0.71,
"learning_rate": 4.061798144264986e-06,
"loss": 0.8031,
"step": 1848
},
{
"epoch": 0.71,
"learning_rate": 4.051772132486589e-06,
"loss": 0.7974,
"step": 1849
},
{
"epoch": 0.71,
"learning_rate": 4.041755365267323e-06,
"loss": 0.826,
"step": 1850
},
{
"epoch": 0.71,
"learning_rate": 4.0317478581749644e-06,
"loss": 0.7745,
"step": 1851
},
{
"epoch": 0.71,
"learning_rate": 4.021749626762869e-06,
"loss": 0.8446,
"step": 1852
},
{
"epoch": 0.71,
"learning_rate": 4.0117606865699975e-06,
"loss": 0.8693,
"step": 1853
},
{
"epoch": 0.71,
"learning_rate": 4.001781053120863e-06,
"loss": 0.8765,
"step": 1854
},
{
"epoch": 0.71,
"learning_rate": 3.991810741925515e-06,
"loss": 0.8733,
"step": 1855
},
{
"epoch": 0.71,
"learning_rate": 3.981849768479516e-06,
"loss": 0.8093,
"step": 1856
},
{
"epoch": 0.71,
"learning_rate": 3.971898148263915e-06,
"loss": 0.7663,
"step": 1857
},
{
"epoch": 0.72,
"learning_rate": 3.961955896745224e-06,
"loss": 0.8143,
"step": 1858
},
{
"epoch": 0.72,
"learning_rate": 3.9520230293754e-06,
"loss": 0.8613,
"step": 1859
},
{
"epoch": 0.72,
"learning_rate": 3.942099561591802e-06,
"loss": 0.9011,
"step": 1860
},
{
"epoch": 0.72,
"learning_rate": 3.9321855088171934e-06,
"loss": 0.8005,
"step": 1861
},
{
"epoch": 0.72,
"learning_rate": 3.922280886459701e-06,
"loss": 0.8379,
"step": 1862
},
{
"epoch": 0.72,
"learning_rate": 3.912385709912794e-06,
"loss": 0.8579,
"step": 1863
},
{
"epoch": 0.72,
"learning_rate": 3.902499994555261e-06,
"loss": 0.8407,
"step": 1864
},
{
"epoch": 0.72,
"learning_rate": 3.892623755751189e-06,
"loss": 0.8478,
"step": 1865
},
{
"epoch": 0.72,
"learning_rate": 3.882757008849936e-06,
"loss": 0.8591,
"step": 1866
},
{
"epoch": 0.72,
"learning_rate": 3.872899769186107e-06,
"loss": 0.8082,
"step": 1867
},
{
"epoch": 0.72,
"learning_rate": 3.8630520520795275e-06,
"loss": 0.7783,
"step": 1868
},
{
"epoch": 0.72,
"learning_rate": 3.853213872835229e-06,
"loss": 0.7968,
"step": 1869
},
{
"epoch": 0.72,
"learning_rate": 3.8433852467434175e-06,
"loss": 0.8571,
"step": 1870
},
{
"epoch": 0.72,
"learning_rate": 3.833566189079453e-06,
"loss": 0.7985,
"step": 1871
},
{
"epoch": 0.72,
"learning_rate": 3.823756715103822e-06,
"loss": 0.8592,
"step": 1872
},
{
"epoch": 0.72,
"learning_rate": 3.8139568400621184e-06,
"loss": 0.7612,
"step": 1873
},
{
"epoch": 0.72,
"learning_rate": 3.804166579185018e-06,
"loss": 0.8571,
"step": 1874
},
{
"epoch": 0.72,
"learning_rate": 3.794385947688255e-06,
"loss": 0.7763,
"step": 1875
},
{
"epoch": 0.72,
"learning_rate": 3.78461496077259e-06,
"loss": 0.7914,
"step": 1876
},
{
"epoch": 0.72,
"learning_rate": 3.774853633623806e-06,
"loss": 0.8328,
"step": 1877
},
{
"epoch": 0.72,
"learning_rate": 3.7651019814126656e-06,
"loss": 0.8077,
"step": 1878
},
{
"epoch": 0.72,
"learning_rate": 3.755360019294898e-06,
"loss": 0.8593,
"step": 1879
},
{
"epoch": 0.72,
"learning_rate": 3.7456277624111725e-06,
"loss": 0.8416,
"step": 1880
},
{
"epoch": 0.72,
"learning_rate": 3.735905225887072e-06,
"loss": 0.8539,
"step": 1881
},
{
"epoch": 0.72,
"learning_rate": 3.726192424833075e-06,
"loss": 0.8339,
"step": 1882
},
{
"epoch": 0.72,
"learning_rate": 3.7164893743445274e-06,
"loss": 0.4814,
"step": 1883
},
{
"epoch": 0.73,
"learning_rate": 3.7067960895016277e-06,
"loss": 0.8246,
"step": 1884
},
{
"epoch": 0.73,
"learning_rate": 3.6971125853693834e-06,
"loss": 0.7767,
"step": 1885
},
{
"epoch": 0.73,
"learning_rate": 3.687438876997612e-06,
"loss": 0.8107,
"step": 1886
},
{
"epoch": 0.73,
"learning_rate": 3.677774979420904e-06,
"loss": 0.7852,
"step": 1887
},
{
"epoch": 0.73,
"learning_rate": 3.6681209076586035e-06,
"loss": 0.8255,
"step": 1888
},
{
"epoch": 0.73,
"learning_rate": 3.6584766767147796e-06,
"loss": 0.8184,
"step": 1889
},
{
"epoch": 0.73,
"learning_rate": 3.6488423015782128e-06,
"loss": 0.8432,
"step": 1890
},
{
"epoch": 0.73,
"learning_rate": 3.6392177972223596e-06,
"loss": 0.8353,
"step": 1891
},
{
"epoch": 0.73,
"learning_rate": 3.6296031786053455e-06,
"loss": 0.8169,
"step": 1892
},
{
"epoch": 0.73,
"learning_rate": 3.619998460669916e-06,
"loss": 0.8265,
"step": 1893
},
{
"epoch": 0.73,
"learning_rate": 3.610403658343443e-06,
"loss": 0.8232,
"step": 1894
},
{
"epoch": 0.73,
"learning_rate": 3.600818786537883e-06,
"loss": 0.8147,
"step": 1895
},
{
"epoch": 0.73,
"learning_rate": 3.591243860149759e-06,
"loss": 0.7944,
"step": 1896
},
{
"epoch": 0.73,
"learning_rate": 3.5816788940601387e-06,
"loss": 0.8357,
"step": 1897
},
{
"epoch": 0.73,
"learning_rate": 3.5721239031346067e-06,
"loss": 0.7999,
"step": 1898
},
{
"epoch": 0.73,
"learning_rate": 3.5625789022232473e-06,
"loss": 0.8818,
"step": 1899
},
{
"epoch": 0.73,
"learning_rate": 3.5530439061606202e-06,
"loss": 0.4688,
"step": 1900
},
{
"epoch": 0.73,
"learning_rate": 3.5435189297657267e-06,
"loss": 0.8882,
"step": 1901
},
{
"epoch": 0.73,
"learning_rate": 3.534003987842005e-06,
"loss": 0.846,
"step": 1902
},
{
"epoch": 0.73,
"learning_rate": 3.5244990951772972e-06,
"loss": 0.8499,
"step": 1903
},
{
"epoch": 0.73,
"learning_rate": 3.5150042665438233e-06,
"loss": 0.4869,
"step": 1904
},
{
"epoch": 0.73,
"learning_rate": 3.505519516698165e-06,
"loss": 0.8291,
"step": 1905
},
{
"epoch": 0.73,
"learning_rate": 3.496044860381238e-06,
"loss": 0.4901,
"step": 1906
},
{
"epoch": 0.73,
"learning_rate": 3.486580312318273e-06,
"loss": 0.8271,
"step": 1907
},
{
"epoch": 0.73,
"learning_rate": 3.4771258872187917e-06,
"loss": 0.8087,
"step": 1908
},
{
"epoch": 0.73,
"learning_rate": 3.4676815997765756e-06,
"loss": 0.8771,
"step": 1909
},
{
"epoch": 0.74,
"learning_rate": 3.4582474646696575e-06,
"loss": 0.8519,
"step": 1910
},
{
"epoch": 0.74,
"learning_rate": 3.448823496560292e-06,
"loss": 0.8893,
"step": 1911
},
{
"epoch": 0.74,
"learning_rate": 3.4394097100949286e-06,
"loss": 0.7988,
"step": 1912
},
{
"epoch": 0.74,
"learning_rate": 3.4300061199041967e-06,
"loss": 0.8397,
"step": 1913
},
{
"epoch": 0.74,
"learning_rate": 3.4206127406028744e-06,
"loss": 0.8442,
"step": 1914
},
{
"epoch": 0.74,
"learning_rate": 3.411229586789876e-06,
"loss": 0.8356,
"step": 1915
},
{
"epoch": 0.74,
"learning_rate": 3.401856673048217e-06,
"loss": 0.8044,
"step": 1916
},
{
"epoch": 0.74,
"learning_rate": 3.392494013945009e-06,
"loss": 0.8457,
"step": 1917
},
{
"epoch": 0.74,
"learning_rate": 3.3831416240314085e-06,
"loss": 0.8038,
"step": 1918
},
{
"epoch": 0.74,
"learning_rate": 3.3737995178426276e-06,
"loss": 0.8761,
"step": 1919
},
{
"epoch": 0.74,
"learning_rate": 3.3644677098978894e-06,
"loss": 0.868,
"step": 1920
},
{
"epoch": 0.74,
"learning_rate": 3.3551462147004132e-06,
"loss": 0.7971,
"step": 1921
},
{
"epoch": 0.74,
"learning_rate": 3.3458350467373914e-06,
"loss": 0.854,
"step": 1922
},
{
"epoch": 0.74,
"learning_rate": 3.3365342204799613e-06,
"loss": 0.8594,
"step": 1923
},
{
"epoch": 0.74,
"learning_rate": 3.3272437503831945e-06,
"loss": 0.8414,
"step": 1924
},
{
"epoch": 0.74,
"learning_rate": 3.3179636508860645e-06,
"loss": 0.7949,
"step": 1925
},
{
"epoch": 0.74,
"learning_rate": 3.308693936411421e-06,
"loss": 0.8251,
"step": 1926
},
{
"epoch": 0.74,
"learning_rate": 3.2994346213659824e-06,
"loss": 0.8031,
"step": 1927
},
{
"epoch": 0.74,
"learning_rate": 3.290185720140301e-06,
"loss": 0.8427,
"step": 1928
},
{
"epoch": 0.74,
"learning_rate": 3.280947247108741e-06,
"loss": 0.8298,
"step": 1929
},
{
"epoch": 0.74,
"learning_rate": 3.2717192166294685e-06,
"loss": 0.8492,
"step": 1930
},
{
"epoch": 0.74,
"learning_rate": 3.262501643044417e-06,
"loss": 0.8038,
"step": 1931
},
{
"epoch": 0.74,
"learning_rate": 3.2532945406792573e-06,
"loss": 0.8333,
"step": 1932
},
{
"epoch": 0.74,
"learning_rate": 3.2440979238433977e-06,
"loss": 0.8221,
"step": 1933
},
{
"epoch": 0.74,
"learning_rate": 3.234911806829948e-06,
"loss": 0.8058,
"step": 1934
},
{
"epoch": 0.74,
"learning_rate": 3.225736203915698e-06,
"loss": 0.8429,
"step": 1935
},
{
"epoch": 0.75,
"learning_rate": 3.216571129361097e-06,
"loss": 0.7628,
"step": 1936
},
{
"epoch": 0.75,
"learning_rate": 3.2074165974102324e-06,
"loss": 0.8643,
"step": 1937
},
{
"epoch": 0.75,
"learning_rate": 3.1982726222908046e-06,
"loss": 0.8193,
"step": 1938
},
{
"epoch": 0.75,
"learning_rate": 3.1891392182141103e-06,
"loss": 0.788,
"step": 1939
},
{
"epoch": 0.75,
"learning_rate": 3.1800163993750166e-06,
"loss": 0.7811,
"step": 1940
},
{
"epoch": 0.75,
"learning_rate": 3.1709041799519312e-06,
"loss": 0.8353,
"step": 1941
},
{
"epoch": 0.75,
"learning_rate": 3.161802574106799e-06,
"loss": 0.819,
"step": 1942
},
{
"epoch": 0.75,
"learning_rate": 3.152711595985065e-06,
"loss": 0.4839,
"step": 1943
},
{
"epoch": 0.75,
"learning_rate": 3.143631259715658e-06,
"loss": 0.7979,
"step": 1944
},
{
"epoch": 0.75,
"learning_rate": 3.134561579410966e-06,
"loss": 0.4872,
"step": 1945
},
{
"epoch": 0.75,
"learning_rate": 3.1255025691668184e-06,
"loss": 0.7817,
"step": 1946
},
{
"epoch": 0.75,
"learning_rate": 3.116454243062459e-06,
"loss": 0.7814,
"step": 1947
},
{
"epoch": 0.75,
"learning_rate": 3.10741661516053e-06,
"loss": 0.8505,
"step": 1948
},
{
"epoch": 0.75,
"learning_rate": 3.0983896995070397e-06,
"loss": 0.8649,
"step": 1949
},
{
"epoch": 0.75,
"learning_rate": 3.089373510131354e-06,
"loss": 0.8511,
"step": 1950
},
{
"epoch": 0.75,
"learning_rate": 3.0803680610461674e-06,
"loss": 0.8524,
"step": 1951
},
{
"epoch": 0.75,
"learning_rate": 3.071373366247482e-06,
"loss": 0.828,
"step": 1952
},
{
"epoch": 0.75,
"learning_rate": 3.0623894397145837e-06,
"loss": 0.8005,
"step": 1953
},
{
"epoch": 0.75,
"learning_rate": 3.0534162954100264e-06,
"loss": 0.8224,
"step": 1954
},
{
"epoch": 0.75,
"learning_rate": 3.044453947279603e-06,
"loss": 0.8271,
"step": 1955
},
{
"epoch": 0.75,
"learning_rate": 3.0355024092523334e-06,
"loss": 0.84,
"step": 1956
},
{
"epoch": 0.75,
"learning_rate": 3.0265616952404252e-06,
"loss": 0.8317,
"step": 1957
},
{
"epoch": 0.75,
"learning_rate": 3.017631819139273e-06,
"loss": 0.8508,
"step": 1958
},
{
"epoch": 0.75,
"learning_rate": 3.0087127948274264e-06,
"loss": 0.8899,
"step": 1959
},
{
"epoch": 0.75,
"learning_rate": 2.999804636166567e-06,
"loss": 0.8118,
"step": 1960
},
{
"epoch": 0.75,
"learning_rate": 2.990907357001491e-06,
"loss": 0.823,
"step": 1961
},
{
"epoch": 0.76,
"learning_rate": 2.9820209711600858e-06,
"loss": 0.861,
"step": 1962
},
{
"epoch": 0.76,
"learning_rate": 2.9731454924533086e-06,
"loss": 0.8411,
"step": 1963
},
{
"epoch": 0.76,
"learning_rate": 2.9642809346751677e-06,
"loss": 0.8447,
"step": 1964
},
{
"epoch": 0.76,
"learning_rate": 2.9554273116026887e-06,
"loss": 0.8297,
"step": 1965
},
{
"epoch": 0.76,
"learning_rate": 2.9465846369959126e-06,
"loss": 0.8524,
"step": 1966
},
{
"epoch": 0.76,
"learning_rate": 2.937752924597864e-06,
"loss": 0.8151,
"step": 1967
},
{
"epoch": 0.76,
"learning_rate": 2.9289321881345257e-06,
"loss": 0.8403,
"step": 1968
},
{
"epoch": 0.76,
"learning_rate": 2.9201224413148254e-06,
"loss": 0.8133,
"step": 1969
},
{
"epoch": 0.76,
"learning_rate": 2.91132369783061e-06,
"loss": 0.8351,
"step": 1970
},
{
"epoch": 0.76,
"learning_rate": 2.902535971356625e-06,
"loss": 0.8682,
"step": 1971
},
{
"epoch": 0.76,
"learning_rate": 2.893759275550494e-06,
"loss": 0.8431,
"step": 1972
},
{
"epoch": 0.76,
"learning_rate": 2.884993624052701e-06,
"loss": 0.8146,
"step": 1973
},
{
"epoch": 0.76,
"learning_rate": 2.876239030486554e-06,
"loss": 0.8527,
"step": 1974
},
{
"epoch": 0.76,
"learning_rate": 2.867495508458186e-06,
"loss": 0.8386,
"step": 1975
},
{
"epoch": 0.76,
"learning_rate": 2.8587630715565185e-06,
"loss": 0.8019,
"step": 1976
},
{
"epoch": 0.76,
"learning_rate": 2.850041733353247e-06,
"loss": 0.8191,
"step": 1977
},
{
"epoch": 0.76,
"learning_rate": 2.8413315074028157e-06,
"loss": 0.8639,
"step": 1978
},
{
"epoch": 0.76,
"learning_rate": 2.8326324072423994e-06,
"loss": 0.8734,
"step": 1979
},
{
"epoch": 0.76,
"learning_rate": 2.823944446391881e-06,
"loss": 0.8505,
"step": 1980
},
{
"epoch": 0.76,
"learning_rate": 2.8152676383538346e-06,
"loss": 0.822,
"step": 1981
},
{
"epoch": 0.76,
"learning_rate": 2.8066019966134907e-06,
"loss": 0.8248,
"step": 1982
},
{
"epoch": 0.76,
"learning_rate": 2.7979475346387363e-06,
"loss": 0.7957,
"step": 1983
},
{
"epoch": 0.76,
"learning_rate": 2.7893042658800793e-06,
"loss": 0.8148,
"step": 1984
},
{
"epoch": 0.76,
"learning_rate": 2.78067220377063e-06,
"loss": 0.8088,
"step": 1985
},
{
"epoch": 0.76,
"learning_rate": 2.7720513617260857e-06,
"loss": 0.8438,
"step": 1986
},
{
"epoch": 0.76,
"learning_rate": 2.763441753144701e-06,
"loss": 0.8292,
"step": 1987
},
{
"epoch": 0.77,
"learning_rate": 2.7548433914072736e-06,
"loss": 0.8019,
"step": 1988
},
{
"epoch": 0.77,
"learning_rate": 2.746256289877126e-06,
"loss": 0.8649,
"step": 1989
},
{
"epoch": 0.77,
"learning_rate": 2.7376804619000706e-06,
"loss": 0.821,
"step": 1990
},
{
"epoch": 0.77,
"learning_rate": 2.729115920804408e-06,
"loss": 0.8332,
"step": 1991
},
{
"epoch": 0.77,
"learning_rate": 2.720562679900892e-06,
"loss": 0.8081,
"step": 1992
},
{
"epoch": 0.77,
"learning_rate": 2.712020752482717e-06,
"loss": 0.8665,
"step": 1993
},
{
"epoch": 0.77,
"learning_rate": 2.703490151825492e-06,
"loss": 0.8331,
"step": 1994
},
{
"epoch": 0.77,
"learning_rate": 2.694970891187225e-06,
"loss": 0.7824,
"step": 1995
},
{
"epoch": 0.77,
"learning_rate": 2.6864629838082957e-06,
"loss": 0.8365,
"step": 1996
},
{
"epoch": 0.77,
"learning_rate": 2.6779664429114448e-06,
"loss": 0.8333,
"step": 1997
},
{
"epoch": 0.77,
"learning_rate": 2.669481281701739e-06,
"loss": 0.8054,
"step": 1998
},
{
"epoch": 0.77,
"learning_rate": 2.661007513366567e-06,
"loss": 0.5291,
"step": 1999
},
{
"epoch": 0.77,
"learning_rate": 2.652545151075606e-06,
"loss": 0.8403,
"step": 2000
},
{
"epoch": 0.77,
"learning_rate": 2.6440942079808096e-06,
"loss": 0.8004,
"step": 2001
},
{
"epoch": 0.77,
"learning_rate": 2.635654697216382e-06,
"loss": 0.8261,
"step": 2002
},
{
"epoch": 0.77,
"learning_rate": 2.6272266318987606e-06,
"loss": 0.8203,
"step": 2003
},
{
"epoch": 0.77,
"learning_rate": 2.6188100251265947e-06,
"loss": 0.83,
"step": 2004
},
{
"epoch": 0.77,
"learning_rate": 2.6104048899807243e-06,
"loss": 0.8247,
"step": 2005
},
{
"epoch": 0.77,
"learning_rate": 2.6020112395241627e-06,
"loss": 0.8182,
"step": 2006
},
{
"epoch": 0.77,
"learning_rate": 2.5936290868020685e-06,
"loss": 0.8198,
"step": 2007
},
{
"epoch": 0.77,
"learning_rate": 2.5852584448417327e-06,
"loss": 0.8352,
"step": 2008
},
{
"epoch": 0.77,
"learning_rate": 2.5768993266525653e-06,
"loss": 0.8661,
"step": 2009
},
{
"epoch": 0.77,
"learning_rate": 2.5685517452260566e-06,
"loss": 0.8433,
"step": 2010
},
{
"epoch": 0.77,
"learning_rate": 2.5602157135357697e-06,
"loss": 0.8156,
"step": 2011
},
{
"epoch": 0.77,
"learning_rate": 2.55189124453732e-06,
"loss": 0.8242,
"step": 2012
},
{
"epoch": 0.77,
"learning_rate": 2.5435783511683444e-06,
"loss": 0.7887,
"step": 2013
},
{
"epoch": 0.78,
"learning_rate": 2.5352770463484986e-06,
"loss": 0.8347,
"step": 2014
},
{
"epoch": 0.78,
"learning_rate": 2.5269873429794235e-06,
"loss": 0.5293,
"step": 2015
},
{
"epoch": 0.78,
"learning_rate": 2.51870925394473e-06,
"loss": 0.785,
"step": 2016
},
{
"epoch": 0.78,
"learning_rate": 2.5104427921099783e-06,
"loss": 0.7728,
"step": 2017
},
{
"epoch": 0.78,
"learning_rate": 2.502187970322657e-06,
"loss": 0.8222,
"step": 2018
},
{
"epoch": 0.78,
"learning_rate": 2.493944801412167e-06,
"loss": 0.7992,
"step": 2019
},
{
"epoch": 0.78,
"learning_rate": 2.485713298189798e-06,
"loss": 0.8143,
"step": 2020
},
{
"epoch": 0.78,
"learning_rate": 2.4774934734487034e-06,
"loss": 0.8258,
"step": 2021
},
{
"epoch": 0.78,
"learning_rate": 2.469285339963892e-06,
"loss": 0.7719,
"step": 2022
},
{
"epoch": 0.78,
"learning_rate": 2.461088910492202e-06,
"loss": 0.8112,
"step": 2023
},
{
"epoch": 0.78,
"learning_rate": 2.45290419777228e-06,
"loss": 0.8531,
"step": 2024
},
{
"epoch": 0.78,
"learning_rate": 2.444731214524565e-06,
"loss": 0.8452,
"step": 2025
},
{
"epoch": 0.78,
"learning_rate": 2.436569973451264e-06,
"loss": 0.8492,
"step": 2026
},
{
"epoch": 0.78,
"learning_rate": 2.428420487236336e-06,
"loss": 0.791,
"step": 2027
},
{
"epoch": 0.78,
"learning_rate": 2.420282768545469e-06,
"loss": 0.7948,
"step": 2028
},
{
"epoch": 0.78,
"learning_rate": 2.412156830026069e-06,
"loss": 0.8226,
"step": 2029
},
{
"epoch": 0.78,
"learning_rate": 2.4040426843072206e-06,
"loss": 0.8655,
"step": 2030
},
{
"epoch": 0.78,
"learning_rate": 2.395940343999691e-06,
"loss": 0.7668,
"step": 2031
},
{
"epoch": 0.78,
"learning_rate": 2.387849821695899e-06,
"loss": 0.4941,
"step": 2032
},
{
"epoch": 0.78,
"learning_rate": 2.3797711299698924e-06,
"loss": 0.8522,
"step": 2033
},
{
"epoch": 0.78,
"learning_rate": 2.371704281377335e-06,
"loss": 0.7689,
"step": 2034
},
{
"epoch": 0.78,
"learning_rate": 2.363649288455482e-06,
"loss": 0.7811,
"step": 2035
},
{
"epoch": 0.78,
"learning_rate": 2.3556061637231653e-06,
"loss": 0.8554,
"step": 2036
},
{
"epoch": 0.78,
"learning_rate": 2.347574919680773e-06,
"loss": 0.7832,
"step": 2037
},
{
"epoch": 0.78,
"learning_rate": 2.339555568810221e-06,
"loss": 0.8419,
"step": 2038
},
{
"epoch": 0.78,
"learning_rate": 2.3315481235749484e-06,
"loss": 0.4843,
"step": 2039
},
{
"epoch": 0.79,
"learning_rate": 2.323552596419889e-06,
"loss": 0.7955,
"step": 2040
},
{
"epoch": 0.79,
"learning_rate": 2.315568999771455e-06,
"loss": 0.8179,
"step": 2041
},
{
"epoch": 0.79,
"learning_rate": 2.3075973460375134e-06,
"loss": 0.7795,
"step": 2042
},
{
"epoch": 0.79,
"learning_rate": 2.2996376476073724e-06,
"loss": 0.7676,
"step": 2043
},
{
"epoch": 0.79,
"learning_rate": 2.291689916851758e-06,
"loss": 0.8369,
"step": 2044
},
{
"epoch": 0.79,
"learning_rate": 2.2837541661228024e-06,
"loss": 0.8247,
"step": 2045
},
{
"epoch": 0.79,
"learning_rate": 2.275830407754006e-06,
"loss": 0.8145,
"step": 2046
},
{
"epoch": 0.79,
"learning_rate": 2.267918654060244e-06,
"loss": 0.821,
"step": 2047
},
{
"epoch": 0.79,
"learning_rate": 2.2600189173377263e-06,
"loss": 0.8439,
"step": 2048
},
{
"epoch": 0.79,
"learning_rate": 2.2521312098639914e-06,
"loss": 0.8452,
"step": 2049
},
{
"epoch": 0.79,
"learning_rate": 2.2442555438978774e-06,
"loss": 0.7917,
"step": 2050
},
{
"epoch": 0.79,
"learning_rate": 2.2363919316795135e-06,
"loss": 0.8105,
"step": 2051
},
{
"epoch": 0.79,
"learning_rate": 2.2285403854302912e-06,
"loss": 0.8481,
"step": 2052
},
{
"epoch": 0.79,
"learning_rate": 2.2207009173528528e-06,
"loss": 0.8743,
"step": 2053
},
{
"epoch": 0.79,
"learning_rate": 2.2128735396310606e-06,
"loss": 0.7856,
"step": 2054
},
{
"epoch": 0.79,
"learning_rate": 2.2050582644299976e-06,
"loss": 0.8127,
"step": 2055
},
{
"epoch": 0.79,
"learning_rate": 2.1972551038959313e-06,
"loss": 0.4972,
"step": 2056
},
{
"epoch": 0.79,
"learning_rate": 2.189464070156302e-06,
"loss": 0.8138,
"step": 2057
},
{
"epoch": 0.79,
"learning_rate": 2.1816851753197023e-06,
"loss": 0.8064,
"step": 2058
},
{
"epoch": 0.79,
"learning_rate": 2.173918431475861e-06,
"loss": 0.8203,
"step": 2059
},
{
"epoch": 0.79,
"learning_rate": 2.1661638506956208e-06,
"loss": 0.8127,
"step": 2060
},
{
"epoch": 0.79,
"learning_rate": 2.1584214450309194e-06,
"loss": 0.8002,
"step": 2061
},
{
"epoch": 0.79,
"learning_rate": 2.1506912265147772e-06,
"loss": 0.831,
"step": 2062
},
{
"epoch": 0.79,
"learning_rate": 2.1429732071612653e-06,
"loss": 0.8569,
"step": 2063
},
{
"epoch": 0.79,
"learning_rate": 2.1352673989655026e-06,
"loss": 0.78,
"step": 2064
},
{
"epoch": 0.79,
"learning_rate": 2.1275738139036274e-06,
"loss": 0.7801,
"step": 2065
},
{
"epoch": 0.8,
"learning_rate": 2.119892463932781e-06,
"loss": 0.7639,
"step": 2066
},
{
"epoch": 0.8,
"learning_rate": 2.1122233609910903e-06,
"loss": 0.8255,
"step": 2067
},
{
"epoch": 0.8,
"learning_rate": 2.104566516997647e-06,
"loss": 0.8069,
"step": 2068
},
{
"epoch": 0.8,
"learning_rate": 2.096921943852489e-06,
"loss": 0.8845,
"step": 2069
},
{
"epoch": 0.8,
"learning_rate": 2.08928965343659e-06,
"loss": 0.8301,
"step": 2070
},
{
"epoch": 0.8,
"learning_rate": 2.0816696576118223e-06,
"loss": 0.7725,
"step": 2071
},
{
"epoch": 0.8,
"learning_rate": 2.0740619682209607e-06,
"loss": 0.8073,
"step": 2072
},
{
"epoch": 0.8,
"learning_rate": 2.0664665970876496e-06,
"loss": 0.772,
"step": 2073
},
{
"epoch": 0.8,
"learning_rate": 2.05888355601639e-06,
"loss": 0.4878,
"step": 2074
},
{
"epoch": 0.8,
"learning_rate": 2.0513128567925177e-06,
"loss": 0.8157,
"step": 2075
},
{
"epoch": 0.8,
"learning_rate": 2.043754511182191e-06,
"loss": 0.8075,
"step": 2076
},
{
"epoch": 0.8,
"learning_rate": 2.036208530932363e-06,
"loss": 0.8218,
"step": 2077
},
{
"epoch": 0.8,
"learning_rate": 2.0286749277707783e-06,
"loss": 0.8472,
"step": 2078
},
{
"epoch": 0.8,
"learning_rate": 2.021153713405931e-06,
"loss": 0.8571,
"step": 2079
},
{
"epoch": 0.8,
"learning_rate": 2.013644899527074e-06,
"loss": 0.8083,
"step": 2080
},
{
"epoch": 0.8,
"learning_rate": 2.0061484978041813e-06,
"loss": 0.8247,
"step": 2081
},
{
"epoch": 0.8,
"learning_rate": 1.9986645198879385e-06,
"loss": 0.8455,
"step": 2082
},
{
"epoch": 0.8,
"learning_rate": 1.9911929774097216e-06,
"loss": 0.7972,
"step": 2083
},
{
"epoch": 0.8,
"learning_rate": 1.983733881981581e-06,
"loss": 0.7759,
"step": 2084
},
{
"epoch": 0.8,
"learning_rate": 1.9762872451962214e-06,
"loss": 0.7785,
"step": 2085
},
{
"epoch": 0.8,
"learning_rate": 1.9688530786269854e-06,
"loss": 0.8426,
"step": 2086
},
{
"epoch": 0.8,
"learning_rate": 1.961431393827827e-06,
"loss": 0.8434,
"step": 2087
},
{
"epoch": 0.8,
"learning_rate": 1.9540222023333165e-06,
"loss": 0.477,
"step": 2088
},
{
"epoch": 0.8,
"learning_rate": 1.9466255156585965e-06,
"loss": 0.4784,
"step": 2089
},
{
"epoch": 0.8,
"learning_rate": 1.9392413452993787e-06,
"loss": 0.83,
"step": 2090
},
{
"epoch": 0.8,
"learning_rate": 1.93186970273192e-06,
"loss": 0.8118,
"step": 2091
},
{
"epoch": 0.81,
"learning_rate": 1.9245105994130086e-06,
"loss": 0.8562,
"step": 2092
},
{
"epoch": 0.81,
"learning_rate": 1.9171640467799478e-06,
"loss": 0.7784,
"step": 2093
},
{
"epoch": 0.81,
"learning_rate": 1.9098300562505266e-06,
"loss": 0.7444,
"step": 2094
},
{
"epoch": 0.81,
"learning_rate": 1.9025086392230163e-06,
"loss": 0.8067,
"step": 2095
},
{
"epoch": 0.81,
"learning_rate": 1.895199807076148e-06,
"loss": 0.8454,
"step": 2096
},
{
"epoch": 0.81,
"learning_rate": 1.8879035711690897e-06,
"loss": 0.8361,
"step": 2097
},
{
"epoch": 0.81,
"learning_rate": 1.880619942841435e-06,
"loss": 0.8475,
"step": 2098
},
{
"epoch": 0.81,
"learning_rate": 1.8733489334131827e-06,
"loss": 0.8263,
"step": 2099
},
{
"epoch": 0.81,
"learning_rate": 1.8660905541847208e-06,
"loss": 0.7891,
"step": 2100
},
{
"epoch": 0.81,
"learning_rate": 1.858844816436809e-06,
"loss": 0.8511,
"step": 2101
},
{
"epoch": 0.81,
"learning_rate": 1.8516117314305526e-06,
"loss": 0.8568,
"step": 2102
},
{
"epoch": 0.81,
"learning_rate": 1.8443913104073984e-06,
"loss": 0.7897,
"step": 2103
},
{
"epoch": 0.81,
"learning_rate": 1.8371835645891134e-06,
"loss": 0.7898,
"step": 2104
},
{
"epoch": 0.81,
"learning_rate": 1.82998850517776e-06,
"loss": 0.7789,
"step": 2105
},
{
"epoch": 0.81,
"learning_rate": 1.8228061433556866e-06,
"loss": 0.8452,
"step": 2106
},
{
"epoch": 0.81,
"learning_rate": 1.815636490285506e-06,
"loss": 0.8092,
"step": 2107
},
{
"epoch": 0.81,
"learning_rate": 1.808479557110081e-06,
"loss": 0.8029,
"step": 2108
},
{
"epoch": 0.81,
"learning_rate": 1.801335354952507e-06,
"loss": 0.7677,
"step": 2109
},
{
"epoch": 0.81,
"learning_rate": 1.7942038949160857e-06,
"loss": 0.7387,
"step": 2110
},
{
"epoch": 0.81,
"learning_rate": 1.7870851880843233e-06,
"loss": 0.7764,
"step": 2111
},
{
"epoch": 0.81,
"learning_rate": 1.7799792455209019e-06,
"loss": 0.8268,
"step": 2112
},
{
"epoch": 0.81,
"learning_rate": 1.7728860782696666e-06,
"loss": 0.7917,
"step": 2113
},
{
"epoch": 0.81,
"learning_rate": 1.765805697354608e-06,
"loss": 0.8275,
"step": 2114
},
{
"epoch": 0.81,
"learning_rate": 1.7587381137798432e-06,
"loss": 0.8148,
"step": 2115
},
{
"epoch": 0.81,
"learning_rate": 1.7516833385296016e-06,
"loss": 0.8215,
"step": 2116
},
{
"epoch": 0.81,
"learning_rate": 1.744641382568204e-06,
"loss": 0.8777,
"step": 2117
},
{
"epoch": 0.82,
"learning_rate": 1.7376122568400533e-06,
"loss": 0.8522,
"step": 2118
},
{
"epoch": 0.82,
"learning_rate": 1.730595972269602e-06,
"loss": 0.8358,
"step": 2119
},
{
"epoch": 0.82,
"learning_rate": 1.7235925397613529e-06,
"loss": 0.8097,
"step": 2120
},
{
"epoch": 0.82,
"learning_rate": 1.716601970199836e-06,
"loss": 0.8506,
"step": 2121
},
{
"epoch": 0.82,
"learning_rate": 1.709624274449584e-06,
"loss": 0.8169,
"step": 2122
},
{
"epoch": 0.82,
"learning_rate": 1.7026594633551252e-06,
"loss": 0.816,
"step": 2123
},
{
"epoch": 0.82,
"learning_rate": 1.6957075477409623e-06,
"loss": 0.8464,
"step": 2124
},
{
"epoch": 0.82,
"learning_rate": 1.688768538411556e-06,
"loss": 0.502,
"step": 2125
},
{
"epoch": 0.82,
"learning_rate": 1.6818424461513129e-06,
"loss": 0.8273,
"step": 2126
},
{
"epoch": 0.82,
"learning_rate": 1.674929281724551e-06,
"loss": 0.8628,
"step": 2127
},
{
"epoch": 0.82,
"learning_rate": 1.6680290558755119e-06,
"loss": 0.7727,
"step": 2128
},
{
"epoch": 0.82,
"learning_rate": 1.6611417793283192e-06,
"loss": 0.8284,
"step": 2129
},
{
"epoch": 0.82,
"learning_rate": 1.6542674627869738e-06,
"loss": 0.8123,
"step": 2130
},
{
"epoch": 0.82,
"learning_rate": 1.6474061169353362e-06,
"loss": 0.8061,
"step": 2131
},
{
"epoch": 0.82,
"learning_rate": 1.640557752437103e-06,
"loss": 0.8416,
"step": 2132
},
{
"epoch": 0.82,
"learning_rate": 1.6337223799358025e-06,
"loss": 0.8451,
"step": 2133
},
{
"epoch": 0.82,
"learning_rate": 1.6269000100547682e-06,
"loss": 0.8518,
"step": 2134
},
{
"epoch": 0.82,
"learning_rate": 1.6200906533971206e-06,
"loss": 0.7849,
"step": 2135
},
{
"epoch": 0.82,
"learning_rate": 1.6132943205457607e-06,
"loss": 0.8346,
"step": 2136
},
{
"epoch": 0.82,
"learning_rate": 1.6065110220633495e-06,
"loss": 0.8215,
"step": 2137
},
{
"epoch": 0.82,
"learning_rate": 1.599740768492286e-06,
"loss": 0.8492,
"step": 2138
},
{
"epoch": 0.82,
"learning_rate": 1.5929835703546992e-06,
"loss": 0.7678,
"step": 2139
},
{
"epoch": 0.82,
"learning_rate": 1.5862394381524239e-06,
"loss": 0.8145,
"step": 2140
},
{
"epoch": 0.82,
"learning_rate": 1.579508382366992e-06,
"loss": 0.8521,
"step": 2141
},
{
"epoch": 0.82,
"learning_rate": 1.5727904134596084e-06,
"loss": 0.785,
"step": 2142
},
{
"epoch": 0.82,
"learning_rate": 1.566085541871145e-06,
"loss": 0.8333,
"step": 2143
},
{
"epoch": 0.83,
"learning_rate": 1.5593937780221092e-06,
"loss": 0.8107,
"step": 2144
},
{
"epoch": 0.83,
"learning_rate": 1.5527151323126422e-06,
"loss": 0.7868,
"step": 2145
},
{
"epoch": 0.83,
"learning_rate": 1.5460496151225002e-06,
"loss": 0.7772,
"step": 2146
},
{
"epoch": 0.83,
"learning_rate": 1.5393972368110287e-06,
"loss": 0.8197,
"step": 2147
},
{
"epoch": 0.83,
"learning_rate": 1.5327580077171589e-06,
"loss": 0.8281,
"step": 2148
},
{
"epoch": 0.83,
"learning_rate": 1.5261319381593831e-06,
"loss": 0.8643,
"step": 2149
},
{
"epoch": 0.83,
"learning_rate": 1.5195190384357405e-06,
"loss": 0.7744,
"step": 2150
},
{
"epoch": 0.83,
"learning_rate": 1.5129193188238068e-06,
"loss": 0.4969,
"step": 2151
},
{
"epoch": 0.83,
"learning_rate": 1.5063327895806668e-06,
"loss": 0.8029,
"step": 2152
},
{
"epoch": 0.83,
"learning_rate": 1.499759460942909e-06,
"loss": 0.4915,
"step": 2153
},
{
"epoch": 0.83,
"learning_rate": 1.4931993431266056e-06,
"loss": 0.8224,
"step": 2154
},
{
"epoch": 0.83,
"learning_rate": 1.486652446327299e-06,
"loss": 0.811,
"step": 2155
},
{
"epoch": 0.83,
"learning_rate": 1.48011878071998e-06,
"loss": 0.4869,
"step": 2156
},
{
"epoch": 0.83,
"learning_rate": 1.4735983564590784e-06,
"loss": 0.7721,
"step": 2157
},
{
"epoch": 0.83,
"learning_rate": 1.467091183678444e-06,
"loss": 0.8051,
"step": 2158
},
{
"epoch": 0.83,
"learning_rate": 1.460597272491333e-06,
"loss": 0.7672,
"step": 2159
},
{
"epoch": 0.83,
"learning_rate": 1.4541166329903856e-06,
"loss": 0.4894,
"step": 2160
},
{
"epoch": 0.83,
"learning_rate": 1.4476492752476223e-06,
"loss": 0.4869,
"step": 2161
},
{
"epoch": 0.83,
"learning_rate": 1.4411952093144167e-06,
"loss": 0.8018,
"step": 2162
},
{
"epoch": 0.83,
"learning_rate": 1.4347544452214869e-06,
"loss": 0.799,
"step": 2163
},
{
"epoch": 0.83,
"learning_rate": 1.4283269929788779e-06,
"loss": 0.4932,
"step": 2164
},
{
"epoch": 0.83,
"learning_rate": 1.4219128625759426e-06,
"loss": 0.7975,
"step": 2165
},
{
"epoch": 0.83,
"learning_rate": 1.4155120639813392e-06,
"loss": 0.8453,
"step": 2166
},
{
"epoch": 0.83,
"learning_rate": 1.409124607142992e-06,
"loss": 0.828,
"step": 2167
},
{
"epoch": 0.83,
"learning_rate": 1.4027505019880972e-06,
"loss": 0.8042,
"step": 2168
},
{
"epoch": 0.83,
"learning_rate": 1.3963897584231023e-06,
"loss": 0.8083,
"step": 2169
},
{
"epoch": 0.84,
"learning_rate": 1.3900423863336842e-06,
"loss": 0.8342,
"step": 2170
},
{
"epoch": 0.84,
"learning_rate": 1.3837083955847418e-06,
"loss": 0.8269,
"step": 2171
},
{
"epoch": 0.84,
"learning_rate": 1.377387796020374e-06,
"loss": 0.8272,
"step": 2172
},
{
"epoch": 0.84,
"learning_rate": 1.3710805974638697e-06,
"loss": 0.8402,
"step": 2173
},
{
"epoch": 0.84,
"learning_rate": 1.364786809717692e-06,
"loss": 0.8514,
"step": 2174
},
{
"epoch": 0.84,
"learning_rate": 1.3585064425634542e-06,
"loss": 0.7994,
"step": 2175
},
{
"epoch": 0.84,
"learning_rate": 1.3522395057619186e-06,
"loss": 0.8427,
"step": 2176
},
{
"epoch": 0.84,
"learning_rate": 1.345986009052972e-06,
"loss": 0.807,
"step": 2177
},
{
"epoch": 0.84,
"learning_rate": 1.339745962155613e-06,
"loss": 0.7869,
"step": 2178
},
{
"epoch": 0.84,
"learning_rate": 1.3335193747679387e-06,
"loss": 0.8509,
"step": 2179
},
{
"epoch": 0.84,
"learning_rate": 1.3273062565671258e-06,
"loss": 0.7687,
"step": 2180
},
{
"epoch": 0.84,
"learning_rate": 1.3211066172094178e-06,
"loss": 0.8119,
"step": 2181
},
{
"epoch": 0.84,
"learning_rate": 1.3149204663301118e-06,
"loss": 0.7874,
"step": 2182
},
{
"epoch": 0.84,
"learning_rate": 1.3087478135435361e-06,
"loss": 0.8036,
"step": 2183
},
{
"epoch": 0.84,
"learning_rate": 1.3025886684430467e-06,
"loss": 0.8262,
"step": 2184
},
{
"epoch": 0.84,
"learning_rate": 1.2964430406010032e-06,
"loss": 0.8352,
"step": 2185
},
{
"epoch": 0.84,
"learning_rate": 1.2903109395687597e-06,
"loss": 0.8265,
"step": 2186
},
{
"epoch": 0.84,
"learning_rate": 1.2841923748766427e-06,
"loss": 0.864,
"step": 2187
},
{
"epoch": 0.84,
"learning_rate": 1.278087356033947e-06,
"loss": 0.7911,
"step": 2188
},
{
"epoch": 0.84,
"learning_rate": 1.271995892528909e-06,
"loss": 0.8151,
"step": 2189
},
{
"epoch": 0.84,
"learning_rate": 1.2659179938287035e-06,
"loss": 0.491,
"step": 2190
},
{
"epoch": 0.84,
"learning_rate": 1.2598536693794171e-06,
"loss": 0.4777,
"step": 2191
},
{
"epoch": 0.84,
"learning_rate": 1.2538029286060428e-06,
"loss": 0.8469,
"step": 2192
},
{
"epoch": 0.84,
"learning_rate": 1.2477657809124632e-06,
"loss": 0.7725,
"step": 2193
},
{
"epoch": 0.84,
"learning_rate": 1.2417422356814345e-06,
"loss": 0.7924,
"step": 2194
},
{
"epoch": 0.84,
"learning_rate": 1.2357323022745716e-06,
"loss": 0.8112,
"step": 2195
},
{
"epoch": 0.85,
"learning_rate": 1.2297359900323346e-06,
"loss": 0.8067,
"step": 2196
},
{
"epoch": 0.85,
"learning_rate": 1.2237533082740127e-06,
"loss": 0.7921,
"step": 2197
},
{
"epoch": 0.85,
"learning_rate": 1.2177842662977136e-06,
"loss": 0.7807,
"step": 2198
},
{
"epoch": 0.85,
"learning_rate": 1.2118288733803474e-06,
"loss": 0.8041,
"step": 2199
},
{
"epoch": 0.85,
"learning_rate": 1.2058871387776039e-06,
"loss": 0.8351,
"step": 2200
},
{
"epoch": 0.85,
"learning_rate": 1.199959071723953e-06,
"loss": 0.7815,
"step": 2201
},
{
"epoch": 0.85,
"learning_rate": 1.19404468143262e-06,
"loss": 0.8114,
"step": 2202
},
{
"epoch": 0.85,
"learning_rate": 1.188143977095576e-06,
"loss": 0.8285,
"step": 2203
},
{
"epoch": 0.85,
"learning_rate": 1.1822569678835195e-06,
"loss": 0.7731,
"step": 2204
},
{
"epoch": 0.85,
"learning_rate": 1.176383662945866e-06,
"loss": 0.8204,
"step": 2205
},
{
"epoch": 0.85,
"learning_rate": 1.1705240714107301e-06,
"loss": 0.7652,
"step": 2206
},
{
"epoch": 0.85,
"learning_rate": 1.164678202384919e-06,
"loss": 0.4939,
"step": 2207
},
{
"epoch": 0.85,
"learning_rate": 1.1588460649539036e-06,
"loss": 0.8612,
"step": 2208
},
{
"epoch": 0.85,
"learning_rate": 1.153027668181821e-06,
"loss": 0.8123,
"step": 2209
},
{
"epoch": 0.85,
"learning_rate": 1.1472230211114498e-06,
"loss": 0.8316,
"step": 2210
},
{
"epoch": 0.85,
"learning_rate": 1.1414321327642019e-06,
"loss": 0.7921,
"step": 2211
},
{
"epoch": 0.85,
"learning_rate": 1.1356550121401033e-06,
"loss": 0.8466,
"step": 2212
},
{
"epoch": 0.85,
"learning_rate": 1.129891668217783e-06,
"loss": 0.7993,
"step": 2213
},
{
"epoch": 0.85,
"learning_rate": 1.124142109954459e-06,
"loss": 0.8102,
"step": 2214
},
{
"epoch": 0.85,
"learning_rate": 1.1184063462859262e-06,
"loss": 0.8438,
"step": 2215
},
{
"epoch": 0.85,
"learning_rate": 1.1126843861265347e-06,
"loss": 0.7655,
"step": 2216
},
{
"epoch": 0.85,
"learning_rate": 1.1069762383691862e-06,
"loss": 0.8193,
"step": 2217
},
{
"epoch": 0.85,
"learning_rate": 1.1012819118853147e-06,
"loss": 0.8165,
"step": 2218
},
{
"epoch": 0.85,
"learning_rate": 1.095601415524874e-06,
"loss": 0.8335,
"step": 2219
},
{
"epoch": 0.85,
"learning_rate": 1.0899347581163222e-06,
"loss": 0.8013,
"step": 2220
},
{
"epoch": 0.85,
"learning_rate": 1.08428194846661e-06,
"loss": 0.7644,
"step": 2221
},
{
"epoch": 0.86,
"learning_rate": 1.0786429953611665e-06,
"loss": 0.842,
"step": 2222
},
{
"epoch": 0.86,
"learning_rate": 1.073017907563887e-06,
"loss": 0.7963,
"step": 2223
},
{
"epoch": 0.86,
"learning_rate": 1.0674066938171123e-06,
"loss": 0.8173,
"step": 2224
},
{
"epoch": 0.86,
"learning_rate": 1.061809362841626e-06,
"loss": 0.777,
"step": 2225
},
{
"epoch": 0.86,
"learning_rate": 1.0562259233366334e-06,
"loss": 0.7787,
"step": 2226
},
{
"epoch": 0.86,
"learning_rate": 1.0506563839797501e-06,
"loss": 0.471,
"step": 2227
},
{
"epoch": 0.86,
"learning_rate": 1.0451007534269908e-06,
"loss": 0.8596,
"step": 2228
},
{
"epoch": 0.86,
"learning_rate": 1.0395590403127487e-06,
"loss": 0.8401,
"step": 2229
},
{
"epoch": 0.86,
"learning_rate": 1.034031253249792e-06,
"loss": 0.8405,
"step": 2230
},
{
"epoch": 0.86,
"learning_rate": 1.0285174008292431e-06,
"loss": 0.7813,
"step": 2231
},
{
"epoch": 0.86,
"learning_rate": 1.0230174916205681e-06,
"loss": 0.8579,
"step": 2232
},
{
"epoch": 0.86,
"learning_rate": 1.0175315341715598e-06,
"loss": 0.7799,
"step": 2233
},
{
"epoch": 0.86,
"learning_rate": 1.012059537008332e-06,
"loss": 0.8284,
"step": 2234
},
{
"epoch": 0.86,
"learning_rate": 1.0066015086353e-06,
"loss": 0.7732,
"step": 2235
},
{
"epoch": 0.86,
"learning_rate": 1.0011574575351702e-06,
"loss": 0.4506,
"step": 2236
},
{
"epoch": 0.86,
"learning_rate": 9.957273921689237e-07,
"loss": 0.5178,
"step": 2237
},
{
"epoch": 0.86,
"learning_rate": 9.903113209758098e-07,
"loss": 0.8221,
"step": 2238
},
{
"epoch": 0.86,
"learning_rate": 9.849092523733217e-07,
"loss": 0.7906,
"step": 2239
},
{
"epoch": 0.86,
"learning_rate": 9.795211947571993e-07,
"loss": 0.831,
"step": 2240
},
{
"epoch": 0.86,
"learning_rate": 9.74147156501396e-07,
"loss": 0.7958,
"step": 2241
},
{
"epoch": 0.86,
"learning_rate": 9.687871459580845e-07,
"loss": 0.7831,
"step": 2242
},
{
"epoch": 0.86,
"learning_rate": 9.634411714576353e-07,
"loss": 0.7718,
"step": 2243
},
{
"epoch": 0.86,
"learning_rate": 9.58109241308599e-07,
"loss": 0.8138,
"step": 2244
},
{
"epoch": 0.86,
"learning_rate": 9.527913637977093e-07,
"loss": 0.8373,
"step": 2245
},
{
"epoch": 0.86,
"learning_rate": 9.474875471898526e-07,
"loss": 0.4855,
"step": 2246
},
{
"epoch": 0.86,
"learning_rate": 9.421977997280596e-07,
"loss": 0.8287,
"step": 2247
},
{
"epoch": 0.87,
"learning_rate": 9.369221296335007e-07,
"loss": 0.8252,
"step": 2248
},
{
"epoch": 0.87,
"learning_rate": 9.31660545105465e-07,
"loss": 0.8478,
"step": 2249
},
{
"epoch": 0.87,
"learning_rate": 9.264130543213512e-07,
"loss": 0.8331,
"step": 2250
},
{
"epoch": 0.87,
"learning_rate": 9.211796654366545e-07,
"loss": 0.7407,
"step": 2251
},
{
"epoch": 0.87,
"learning_rate": 9.15960386584952e-07,
"loss": 0.8608,
"step": 2252
},
{
"epoch": 0.87,
"learning_rate": 9.107552258778907e-07,
"loss": 0.8155,
"step": 2253
},
{
"epoch": 0.87,
"learning_rate": 9.055641914051783e-07,
"loss": 0.8499,
"step": 2254
},
{
"epoch": 0.87,
"learning_rate": 9.00387291234569e-07,
"loss": 0.7835,
"step": 2255
},
{
"epoch": 0.87,
"learning_rate": 8.952245334118415e-07,
"loss": 0.8627,
"step": 2256
},
{
"epoch": 0.87,
"learning_rate": 8.900759259608038e-07,
"loss": 0.8401,
"step": 2257
},
{
"epoch": 0.87,
"learning_rate": 8.849414768832687e-07,
"loss": 0.8001,
"step": 2258
},
{
"epoch": 0.87,
"learning_rate": 8.79821194159044e-07,
"loss": 0.7839,
"step": 2259
},
{
"epoch": 0.87,
"learning_rate": 8.747150857459219e-07,
"loss": 0.8321,
"step": 2260
},
{
"epoch": 0.87,
"learning_rate": 8.696231595796633e-07,
"loss": 0.8552,
"step": 2261
},
{
"epoch": 0.87,
"learning_rate": 8.645454235739903e-07,
"loss": 0.8632,
"step": 2262
},
{
"epoch": 0.87,
"learning_rate": 8.5948188562057e-07,
"loss": 0.7714,
"step": 2263
},
{
"epoch": 0.87,
"learning_rate": 8.544325535889997e-07,
"loss": 0.8033,
"step": 2264
},
{
"epoch": 0.87,
"learning_rate": 8.493974353268019e-07,
"loss": 0.835,
"step": 2265
},
{
"epoch": 0.87,
"learning_rate": 8.443765386594094e-07,
"loss": 0.8,
"step": 2266
},
{
"epoch": 0.87,
"learning_rate": 8.393698713901499e-07,
"loss": 0.874,
"step": 2267
},
{
"epoch": 0.87,
"learning_rate": 8.343774413002382e-07,
"loss": 0.8059,
"step": 2268
},
{
"epoch": 0.87,
"learning_rate": 8.293992561487596e-07,
"loss": 0.8024,
"step": 2269
},
{
"epoch": 0.87,
"learning_rate": 8.24435323672661e-07,
"loss": 0.4836,
"step": 2270
},
{
"epoch": 0.87,
"learning_rate": 8.194856515867433e-07,
"loss": 0.8593,
"step": 2271
},
{
"epoch": 0.87,
"learning_rate": 8.145502475836331e-07,
"loss": 0.8345,
"step": 2272
},
{
"epoch": 0.87,
"learning_rate": 8.096291193337935e-07,
"loss": 0.7923,
"step": 2273
},
{
"epoch": 0.88,
"learning_rate": 8.047222744854943e-07,
"loss": 0.8045,
"step": 2274
},
{
"epoch": 0.88,
"learning_rate": 7.998297206648075e-07,
"loss": 0.8224,
"step": 2275
},
{
"epoch": 0.88,
"learning_rate": 7.949514654755963e-07,
"loss": 0.793,
"step": 2276
},
{
"epoch": 0.88,
"learning_rate": 7.900875164995003e-07,
"loss": 0.8005,
"step": 2277
},
{
"epoch": 0.88,
"learning_rate": 7.852378812959227e-07,
"loss": 0.828,
"step": 2278
},
{
"epoch": 0.88,
"learning_rate": 7.804025674020266e-07,
"loss": 0.7816,
"step": 2279
},
{
"epoch": 0.88,
"learning_rate": 7.755815823327084e-07,
"loss": 0.8652,
"step": 2280
},
{
"epoch": 0.88,
"learning_rate": 7.707749335806014e-07,
"loss": 0.8665,
"step": 2281
},
{
"epoch": 0.88,
"learning_rate": 7.659826286160565e-07,
"loss": 0.7886,
"step": 2282
},
{
"epoch": 0.88,
"learning_rate": 7.612046748871327e-07,
"loss": 0.7599,
"step": 2283
},
{
"epoch": 0.88,
"learning_rate": 7.564410798195832e-07,
"loss": 0.5242,
"step": 2284
},
{
"epoch": 0.88,
"learning_rate": 7.516918508168469e-07,
"loss": 0.8143,
"step": 2285
},
{
"epoch": 0.88,
"learning_rate": 7.46956995260033e-07,
"loss": 0.8239,
"step": 2286
},
{
"epoch": 0.88,
"learning_rate": 7.422365205079141e-07,
"loss": 0.8278,
"step": 2287
},
{
"epoch": 0.88,
"learning_rate": 7.375304338969135e-07,
"loss": 0.82,
"step": 2288
},
{
"epoch": 0.88,
"learning_rate": 7.328387427410877e-07,
"loss": 0.7748,
"step": 2289
},
{
"epoch": 0.88,
"learning_rate": 7.281614543321269e-07,
"loss": 0.7899,
"step": 2290
},
{
"epoch": 0.88,
"learning_rate": 7.234985759393321e-07,
"loss": 0.4919,
"step": 2291
},
{
"epoch": 0.88,
"learning_rate": 7.188501148096117e-07,
"loss": 0.8143,
"step": 2292
},
{
"epoch": 0.88,
"learning_rate": 7.142160781674645e-07,
"loss": 0.8459,
"step": 2293
},
{
"epoch": 0.88,
"learning_rate": 7.095964732149741e-07,
"loss": 0.8162,
"step": 2294
},
{
"epoch": 0.88,
"learning_rate": 7.049913071317927e-07,
"loss": 0.818,
"step": 2295
},
{
"epoch": 0.88,
"learning_rate": 7.004005870751341e-07,
"loss": 0.7728,
"step": 2296
},
{
"epoch": 0.88,
"learning_rate": 6.958243201797554e-07,
"loss": 0.8708,
"step": 2297
},
{
"epoch": 0.88,
"learning_rate": 6.912625135579587e-07,
"loss": 0.8033,
"step": 2298
},
{
"epoch": 0.88,
"learning_rate": 6.867151742995659e-07,
"loss": 0.8372,
"step": 2299
},
{
"epoch": 0.89,
"learning_rate": 6.821823094719171e-07,
"loss": 0.8844,
"step": 2300
},
{
"epoch": 0.89,
"learning_rate": 6.776639261198581e-07,
"loss": 0.77,
"step": 2301
},
{
"epoch": 0.89,
"learning_rate": 6.731600312657238e-07,
"loss": 0.8401,
"step": 2302
},
{
"epoch": 0.89,
"learning_rate": 6.68670631909335e-07,
"loss": 0.8162,
"step": 2303
},
{
"epoch": 0.89,
"learning_rate": 6.641957350279838e-07,
"loss": 0.8534,
"step": 2304
},
{
"epoch": 0.89,
"learning_rate": 6.597353475764201e-07,
"loss": 0.7843,
"step": 2305
},
{
"epoch": 0.89,
"learning_rate": 6.552894764868456e-07,
"loss": 0.8712,
"step": 2306
},
{
"epoch": 0.89,
"learning_rate": 6.508581286689031e-07,
"loss": 0.8264,
"step": 2307
},
{
"epoch": 0.89,
"learning_rate": 6.464413110096601e-07,
"loss": 0.8414,
"step": 2308
},
{
"epoch": 0.89,
"learning_rate": 6.420390303736034e-07,
"loss": 0.8507,
"step": 2309
},
{
"epoch": 0.89,
"learning_rate": 6.37651293602628e-07,
"loss": 0.8113,
"step": 2310
},
{
"epoch": 0.89,
"learning_rate": 6.332781075160244e-07,
"loss": 0.7824,
"step": 2311
},
{
"epoch": 0.89,
"learning_rate": 6.28919478910468e-07,
"loss": 0.7984,
"step": 2312
},
{
"epoch": 0.89,
"learning_rate": 6.245754145600091e-07,
"loss": 0.4884,
"step": 2313
},
{
"epoch": 0.89,
"learning_rate": 6.202459212160638e-07,
"loss": 0.8063,
"step": 2314
},
{
"epoch": 0.89,
"learning_rate": 6.15931005607403e-07,
"loss": 0.8403,
"step": 2315
},
{
"epoch": 0.89,
"learning_rate": 6.116306744401391e-07,
"loss": 0.8273,
"step": 2316
},
{
"epoch": 0.89,
"learning_rate": 6.073449343977211e-07,
"loss": 0.8196,
"step": 2317
},
{
"epoch": 0.89,
"learning_rate": 6.030737921409169e-07,
"loss": 0.8066,
"step": 2318
},
{
"epoch": 0.89,
"learning_rate": 5.988172543078097e-07,
"loss": 0.8108,
"step": 2319
},
{
"epoch": 0.89,
"learning_rate": 5.945753275137844e-07,
"loss": 0.777,
"step": 2320
},
{
"epoch": 0.89,
"learning_rate": 5.903480183515197e-07,
"loss": 0.8331,
"step": 2321
},
{
"epoch": 0.89,
"learning_rate": 5.861353333909692e-07,
"loss": 0.7749,
"step": 2322
},
{
"epoch": 0.89,
"learning_rate": 5.819372791793654e-07,
"loss": 0.7966,
"step": 2323
},
{
"epoch": 0.89,
"learning_rate": 5.777538622412005e-07,
"loss": 0.8202,
"step": 2324
},
{
"epoch": 0.89,
"learning_rate": 5.735850890782158e-07,
"loss": 0.8066,
"step": 2325
},
{
"epoch": 0.9,
"learning_rate": 5.694309661693942e-07,
"loss": 0.8352,
"step": 2326
},
{
"epoch": 0.9,
"learning_rate": 5.652914999709535e-07,
"loss": 0.8195,
"step": 2327
},
{
"epoch": 0.9,
"learning_rate": 5.611666969163243e-07,
"loss": 0.4911,
"step": 2328
},
{
"epoch": 0.9,
"learning_rate": 5.570565634161562e-07,
"loss": 0.8184,
"step": 2329
},
{
"epoch": 0.9,
"learning_rate": 5.529611058582951e-07,
"loss": 0.7963,
"step": 2330
},
{
"epoch": 0.9,
"learning_rate": 5.488803306077806e-07,
"loss": 0.8005,
"step": 2331
},
{
"epoch": 0.9,
"learning_rate": 5.448142440068316e-07,
"loss": 0.8813,
"step": 2332
},
{
"epoch": 0.9,
"learning_rate": 5.407628523748398e-07,
"loss": 0.7487,
"step": 2333
},
{
"epoch": 0.9,
"learning_rate": 5.367261620083575e-07,
"loss": 0.5022,
"step": 2334
},
{
"epoch": 0.9,
"learning_rate": 5.327041791810905e-07,
"loss": 0.806,
"step": 2335
},
{
"epoch": 0.9,
"learning_rate": 5.286969101438821e-07,
"loss": 0.8323,
"step": 2336
},
{
"epoch": 0.9,
"learning_rate": 5.247043611247127e-07,
"loss": 0.8082,
"step": 2337
},
{
"epoch": 0.9,
"learning_rate": 5.207265383286831e-07,
"loss": 0.7932,
"step": 2338
},
{
"epoch": 0.9,
"learning_rate": 5.167634479380068e-07,
"loss": 0.8027,
"step": 2339
},
{
"epoch": 0.9,
"learning_rate": 5.128150961120026e-07,
"loss": 0.7963,
"step": 2340
},
{
"epoch": 0.9,
"learning_rate": 5.088814889870808e-07,
"loss": 0.8298,
"step": 2341
},
{
"epoch": 0.9,
"learning_rate": 5.049626326767366e-07,
"loss": 0.7728,
"step": 2342
},
{
"epoch": 0.9,
"learning_rate": 5.010585332715401e-07,
"loss": 0.8694,
"step": 2343
},
{
"epoch": 0.9,
"learning_rate": 4.97169196839129e-07,
"loss": 0.7744,
"step": 2344
},
{
"epoch": 0.9,
"learning_rate": 4.932946294241903e-07,
"loss": 0.866,
"step": 2345
},
{
"epoch": 0.9,
"learning_rate": 4.894348370484648e-07,
"loss": 0.7379,
"step": 2346
},
{
"epoch": 0.9,
"learning_rate": 4.855898257107261e-07,
"loss": 0.8159,
"step": 2347
},
{
"epoch": 0.9,
"learning_rate": 4.817596013867765e-07,
"loss": 0.8182,
"step": 2348
},
{
"epoch": 0.9,
"learning_rate": 4.779441700294362e-07,
"loss": 0.8279,
"step": 2349
},
{
"epoch": 0.9,
"learning_rate": 4.7414353756853773e-07,
"loss": 0.4827,
"step": 2350
},
{
"epoch": 0.9,
"learning_rate": 4.703577099109091e-07,
"loss": 0.8702,
"step": 2351
},
{
"epoch": 0.91,
"learning_rate": 4.6658669294037393e-07,
"loss": 0.7584,
"step": 2352
},
{
"epoch": 0.91,
"learning_rate": 4.628304925177318e-07,
"loss": 0.7875,
"step": 2353
},
{
"epoch": 0.91,
"learning_rate": 4.5908911448075746e-07,
"loss": 0.8029,
"step": 2354
},
{
"epoch": 0.91,
"learning_rate": 4.553625646441928e-07,
"loss": 0.8438,
"step": 2355
},
{
"epoch": 0.91,
"learning_rate": 4.5165084879972844e-07,
"loss": 0.8336,
"step": 2356
},
{
"epoch": 0.91,
"learning_rate": 4.4795397271600314e-07,
"loss": 0.7736,
"step": 2357
},
{
"epoch": 0.91,
"learning_rate": 4.4427194213859216e-07,
"loss": 0.7928,
"step": 2358
},
{
"epoch": 0.91,
"learning_rate": 4.4060476278999897e-07,
"loss": 0.7723,
"step": 2359
},
{
"epoch": 0.91,
"learning_rate": 4.3695244036964567e-07,
"loss": 0.7744,
"step": 2360
},
{
"epoch": 0.91,
"learning_rate": 4.3331498055386057e-07,
"loss": 0.8106,
"step": 2361
},
{
"epoch": 0.91,
"learning_rate": 4.296923889958771e-07,
"loss": 0.7723,
"step": 2362
},
{
"epoch": 0.91,
"learning_rate": 4.2608467132581934e-07,
"loss": 0.7991,
"step": 2363
},
{
"epoch": 0.91,
"learning_rate": 4.224918331506955e-07,
"loss": 0.8098,
"step": 2364
},
{
"epoch": 0.91,
"learning_rate": 4.189138800543868e-07,
"loss": 0.8698,
"step": 2365
},
{
"epoch": 0.91,
"learning_rate": 4.1535081759764286e-07,
"loss": 0.8269,
"step": 2366
},
{
"epoch": 0.91,
"learning_rate": 4.118026513180695e-07,
"loss": 0.8146,
"step": 2367
},
{
"epoch": 0.91,
"learning_rate": 4.082693867301224e-07,
"loss": 0.8146,
"step": 2368
},
{
"epoch": 0.91,
"learning_rate": 4.0475102932509336e-07,
"loss": 0.5372,
"step": 2369
},
{
"epoch": 0.91,
"learning_rate": 4.012475845711106e-07,
"loss": 0.8302,
"step": 2370
},
{
"epoch": 0.91,
"learning_rate": 3.9775905791312407e-07,
"loss": 0.8175,
"step": 2371
},
{
"epoch": 0.91,
"learning_rate": 3.9428545477289913e-07,
"loss": 0.8343,
"step": 2372
},
{
"epoch": 0.91,
"learning_rate": 3.908267805490051e-07,
"loss": 0.81,
"step": 2373
},
{
"epoch": 0.91,
"learning_rate": 3.8738304061681107e-07,
"loss": 0.7906,
"step": 2374
},
{
"epoch": 0.91,
"learning_rate": 3.8395424032847686e-07,
"loss": 0.4735,
"step": 2375
},
{
"epoch": 0.91,
"learning_rate": 3.8054038501294077e-07,
"loss": 0.8389,
"step": 2376
},
{
"epoch": 0.91,
"learning_rate": 3.7714147997591655e-07,
"loss": 0.4738,
"step": 2377
},
{
"epoch": 0.92,
"learning_rate": 3.7375753049987974e-07,
"loss": 0.8735,
"step": 2378
},
{
"epoch": 0.92,
"learning_rate": 3.703885418440656e-07,
"loss": 0.8059,
"step": 2379
},
{
"epoch": 0.92,
"learning_rate": 3.6703451924445467e-07,
"loss": 0.7998,
"step": 2380
},
{
"epoch": 0.92,
"learning_rate": 3.6369546791377054e-07,
"loss": 0.8492,
"step": 2381
},
{
"epoch": 0.92,
"learning_rate": 3.603713930414676e-07,
"loss": 0.7875,
"step": 2382
},
{
"epoch": 0.92,
"learning_rate": 3.570622997937234e-07,
"loss": 0.7776,
"step": 2383
},
{
"epoch": 0.92,
"learning_rate": 3.5376819331343404e-07,
"loss": 0.5133,
"step": 2384
},
{
"epoch": 0.92,
"learning_rate": 3.50489078720202e-07,
"loss": 0.8181,
"step": 2385
},
{
"epoch": 0.92,
"learning_rate": 3.472249611103273e-07,
"loss": 0.8195,
"step": 2386
},
{
"epoch": 0.92,
"learning_rate": 3.4397584555680653e-07,
"loss": 0.804,
"step": 2387
},
{
"epoch": 0.92,
"learning_rate": 3.4074173710931804e-07,
"loss": 0.7472,
"step": 2388
},
{
"epoch": 0.92,
"learning_rate": 3.375226407942178e-07,
"loss": 0.8335,
"step": 2389
},
{
"epoch": 0.92,
"learning_rate": 3.3431856161452835e-07,
"loss": 0.8488,
"step": 2390
},
{
"epoch": 0.92,
"learning_rate": 3.3112950454993633e-07,
"loss": 0.7797,
"step": 2391
},
{
"epoch": 0.92,
"learning_rate": 3.2795547455677813e-07,
"loss": 0.768,
"step": 2392
},
{
"epoch": 0.92,
"learning_rate": 3.247964765680389e-07,
"loss": 0.8127,
"step": 2393
},
{
"epoch": 0.92,
"learning_rate": 3.2165251549333585e-07,
"loss": 0.8515,
"step": 2394
},
{
"epoch": 0.92,
"learning_rate": 3.185235962189237e-07,
"loss": 0.8182,
"step": 2395
},
{
"epoch": 0.92,
"learning_rate": 3.1540972360767254e-07,
"loss": 0.7946,
"step": 2396
},
{
"epoch": 0.92,
"learning_rate": 3.1231090249907336e-07,
"loss": 0.819,
"step": 2397
},
{
"epoch": 0.92,
"learning_rate": 3.0922713770922155e-07,
"loss": 0.8226,
"step": 2398
},
{
"epoch": 0.92,
"learning_rate": 3.06158434030811e-07,
"loss": 0.8381,
"step": 2399
},
{
"epoch": 0.92,
"learning_rate": 3.0310479623313125e-07,
"loss": 0.8178,
"step": 2400
},
{
"epoch": 0.92,
"learning_rate": 3.0006622906205707e-07,
"loss": 0.8369,
"step": 2401
},
{
"epoch": 0.92,
"learning_rate": 2.970427372400353e-07,
"loss": 0.8411,
"step": 2402
},
{
"epoch": 0.92,
"learning_rate": 2.940343254660905e-07,
"loss": 0.8044,
"step": 2403
},
{
"epoch": 0.93,
"learning_rate": 2.910409984158058e-07,
"loss": 0.8099,
"step": 2404
},
{
"epoch": 0.93,
"learning_rate": 2.880627607413211e-07,
"loss": 0.8355,
"step": 2405
},
{
"epoch": 0.93,
"learning_rate": 2.8509961707132496e-07,
"loss": 0.7825,
"step": 2406
},
{
"epoch": 0.93,
"learning_rate": 2.821515720110479e-07,
"loss": 0.873,
"step": 2407
},
{
"epoch": 0.93,
"learning_rate": 2.7921863014225504e-07,
"loss": 0.826,
"step": 2408
},
{
"epoch": 0.93,
"learning_rate": 2.7630079602323447e-07,
"loss": 0.8422,
"step": 2409
},
{
"epoch": 0.93,
"learning_rate": 2.733980741887987e-07,
"loss": 0.8713,
"step": 2410
},
{
"epoch": 0.93,
"learning_rate": 2.7051046915027244e-07,
"loss": 0.8447,
"step": 2411
},
{
"epoch": 0.93,
"learning_rate": 2.676379853954858e-07,
"loss": 0.7975,
"step": 2412
},
{
"epoch": 0.93,
"learning_rate": 2.6478062738876654e-07,
"loss": 0.4894,
"step": 2413
},
{
"epoch": 0.93,
"learning_rate": 2.6193839957093683e-07,
"loss": 0.8184,
"step": 2414
},
{
"epoch": 0.93,
"learning_rate": 2.5911130635930203e-07,
"loss": 0.8046,
"step": 2415
},
{
"epoch": 0.93,
"learning_rate": 2.5629935214764866e-07,
"loss": 0.8101,
"step": 2416
},
{
"epoch": 0.93,
"learning_rate": 2.5350254130622866e-07,
"loss": 0.8306,
"step": 2417
},
{
"epoch": 0.93,
"learning_rate": 2.507208781817638e-07,
"loss": 0.8408,
"step": 2418
},
{
"epoch": 0.93,
"learning_rate": 2.4795436709743384e-07,
"loss": 0.5281,
"step": 2419
},
{
"epoch": 0.93,
"learning_rate": 2.45203012352867e-07,
"loss": 0.7802,
"step": 2420
},
{
"epoch": 0.93,
"learning_rate": 2.424668182241363e-07,
"loss": 0.8248,
"step": 2421
},
{
"epoch": 0.93,
"learning_rate": 2.3974578896375555e-07,
"loss": 0.4799,
"step": 2422
},
{
"epoch": 0.93,
"learning_rate": 2.370399288006664e-07,
"loss": 0.8124,
"step": 2423
},
{
"epoch": 0.93,
"learning_rate": 2.3434924194023712e-07,
"loss": 0.8307,
"step": 2424
},
{
"epoch": 0.93,
"learning_rate": 2.3167373256425152e-07,
"loss": 0.8308,
"step": 2425
},
{
"epoch": 0.93,
"learning_rate": 2.2901340483090785e-07,
"loss": 0.8248,
"step": 2426
},
{
"epoch": 0.93,
"learning_rate": 2.2636826287480872e-07,
"loss": 0.823,
"step": 2427
},
{
"epoch": 0.93,
"learning_rate": 2.2373831080695463e-07,
"loss": 0.8117,
"step": 2428
},
{
"epoch": 0.93,
"learning_rate": 2.211235527147404e-07,
"loss": 0.8033,
"step": 2429
},
{
"epoch": 0.94,
"learning_rate": 2.1852399266194312e-07,
"loss": 0.8153,
"step": 2430
},
{
"epoch": 0.94,
"learning_rate": 2.1593963468872435e-07,
"loss": 0.8124,
"step": 2431
},
{
"epoch": 0.94,
"learning_rate": 2.1337048281161565e-07,
"loss": 0.8423,
"step": 2432
},
{
"epoch": 0.94,
"learning_rate": 2.1081654102351634e-07,
"loss": 0.8594,
"step": 2433
},
{
"epoch": 0.94,
"learning_rate": 2.082778132936858e-07,
"loss": 0.8445,
"step": 2434
},
{
"epoch": 0.94,
"learning_rate": 2.057543035677412e-07,
"loss": 0.793,
"step": 2435
},
{
"epoch": 0.94,
"learning_rate": 2.0324601576764525e-07,
"loss": 0.8134,
"step": 2436
},
{
"epoch": 0.94,
"learning_rate": 2.0075295379170413e-07,
"loss": 0.8195,
"step": 2437
},
{
"epoch": 0.94,
"learning_rate": 1.9827512151456175e-07,
"loss": 0.803,
"step": 2438
},
{
"epoch": 0.94,
"learning_rate": 1.95812522787191e-07,
"loss": 0.8535,
"step": 2439
},
{
"epoch": 0.94,
"learning_rate": 1.933651614368892e-07,
"loss": 0.8002,
"step": 2440
},
{
"epoch": 0.94,
"learning_rate": 1.9093304126727497e-07,
"loss": 0.8376,
"step": 2441
},
{
"epoch": 0.94,
"learning_rate": 1.885161660582746e-07,
"loss": 0.8369,
"step": 2442
},
{
"epoch": 0.94,
"learning_rate": 1.8611453956612346e-07,
"loss": 0.8574,
"step": 2443
},
{
"epoch": 0.94,
"learning_rate": 1.8372816552336025e-07,
"loss": 0.7934,
"step": 2444
},
{
"epoch": 0.94,
"learning_rate": 1.81357047638816e-07,
"loss": 0.8525,
"step": 2445
},
{
"epoch": 0.94,
"learning_rate": 1.7900118959761181e-07,
"loss": 0.8181,
"step": 2446
},
{
"epoch": 0.94,
"learning_rate": 1.7666059506115108e-07,
"loss": 0.8293,
"step": 2447
},
{
"epoch": 0.94,
"learning_rate": 1.7433526766711727e-07,
"loss": 0.7693,
"step": 2448
},
{
"epoch": 0.94,
"learning_rate": 1.7202521102946624e-07,
"loss": 0.8356,
"step": 2449
},
{
"epoch": 0.94,
"learning_rate": 1.6973042873841827e-07,
"loss": 0.8157,
"step": 2450
},
{
"epoch": 0.94,
"learning_rate": 1.6745092436045495e-07,
"loss": 0.8402,
"step": 2451
},
{
"epoch": 0.94,
"learning_rate": 1.651867014383146e-07,
"loss": 0.7747,
"step": 2452
},
{
"epoch": 0.94,
"learning_rate": 1.629377634909868e-07,
"loss": 0.7947,
"step": 2453
},
{
"epoch": 0.94,
"learning_rate": 1.6070411401370335e-07,
"loss": 0.8697,
"step": 2454
},
{
"epoch": 0.94,
"learning_rate": 1.584857564779363e-07,
"loss": 0.8112,
"step": 2455
},
{
"epoch": 0.95,
"learning_rate": 1.5628269433139e-07,
"loss": 0.7758,
"step": 2456
},
{
"epoch": 0.95,
"learning_rate": 1.5409493099799888e-07,
"loss": 0.7565,
"step": 2457
},
{
"epoch": 0.95,
"learning_rate": 1.519224698779198e-07,
"loss": 0.7838,
"step": 2458
},
{
"epoch": 0.95,
"learning_rate": 1.497653143475275e-07,
"loss": 0.8005,
"step": 2459
},
{
"epoch": 0.95,
"learning_rate": 1.4762346775940794e-07,
"loss": 0.8251,
"step": 2460
},
{
"epoch": 0.95,
"learning_rate": 1.4549693344235726e-07,
"loss": 0.8144,
"step": 2461
},
{
"epoch": 0.95,
"learning_rate": 1.4338571470137063e-07,
"loss": 0.816,
"step": 2462
},
{
"epoch": 0.95,
"learning_rate": 1.4128981481764115e-07,
"loss": 0.8427,
"step": 2463
},
{
"epoch": 0.95,
"learning_rate": 1.3920923704855648e-07,
"loss": 0.793,
"step": 2464
},
{
"epoch": 0.95,
"learning_rate": 1.3714398462768563e-07,
"loss": 0.8264,
"step": 2465
},
{
"epoch": 0.95,
"learning_rate": 1.350940607647866e-07,
"loss": 0.7944,
"step": 2466
},
{
"epoch": 0.95,
"learning_rate": 1.3305946864578645e-07,
"loss": 0.8278,
"step": 2467
},
{
"epoch": 0.95,
"learning_rate": 1.3104021143278911e-07,
"loss": 0.8069,
"step": 2468
},
{
"epoch": 0.95,
"learning_rate": 1.2903629226406423e-07,
"loss": 0.8126,
"step": 2469
},
{
"epoch": 0.95,
"learning_rate": 1.2704771425404382e-07,
"loss": 0.8391,
"step": 2470
},
{
"epoch": 0.95,
"learning_rate": 1.2507448049331571e-07,
"loss": 0.7708,
"step": 2471
},
{
"epoch": 0.95,
"learning_rate": 1.231165940486234e-07,
"loss": 0.8163,
"step": 2472
},
{
"epoch": 0.95,
"learning_rate": 1.2117405796285286e-07,
"loss": 0.7858,
"step": 2473
},
{
"epoch": 0.95,
"learning_rate": 1.192468752550402e-07,
"loss": 0.8456,
"step": 2474
},
{
"epoch": 0.95,
"learning_rate": 1.1733504892035064e-07,
"loss": 0.8079,
"step": 2475
},
{
"epoch": 0.95,
"learning_rate": 1.1543858193009183e-07,
"loss": 0.7816,
"step": 2476
},
{
"epoch": 0.95,
"learning_rate": 1.1355747723169386e-07,
"loss": 0.4955,
"step": 2477
},
{
"epoch": 0.95,
"learning_rate": 1.1169173774871478e-07,
"loss": 0.8101,
"step": 2478
},
{
"epoch": 0.95,
"learning_rate": 1.0984136638083176e-07,
"loss": 0.763,
"step": 2479
},
{
"epoch": 0.95,
"learning_rate": 1.0800636600383662e-07,
"loss": 0.8495,
"step": 2480
},
{
"epoch": 0.95,
"learning_rate": 1.0618673946963365e-07,
"loss": 0.8214,
"step": 2481
},
{
"epoch": 0.96,
"learning_rate": 1.0438248960623065e-07,
"loss": 0.4982,
"step": 2482
},
{
"epoch": 0.96,
"learning_rate": 1.0259361921774014e-07,
"loss": 0.7913,
"step": 2483
},
{
"epoch": 0.96,
"learning_rate": 1.0082013108437038e-07,
"loss": 0.8148,
"step": 2484
},
{
"epoch": 0.96,
"learning_rate": 9.906202796242547e-08,
"loss": 0.8002,
"step": 2485
},
{
"epoch": 0.96,
"learning_rate": 9.731931258429638e-08,
"loss": 0.8558,
"step": 2486
},
{
"epoch": 0.96,
"learning_rate": 9.55919876584599e-08,
"loss": 0.8039,
"step": 2487
},
{
"epoch": 0.96,
"learning_rate": 9.388005586947191e-08,
"loss": 0.8417,
"step": 2488
},
{
"epoch": 0.96,
"learning_rate": 9.218351987796859e-08,
"loss": 0.7932,
"step": 2489
},
{
"epoch": 0.96,
"learning_rate": 9.0502382320653e-08,
"loss": 0.8019,
"step": 2490
},
{
"epoch": 0.96,
"learning_rate": 8.88366458102996e-08,
"loss": 0.814,
"step": 2491
},
{
"epoch": 0.96,
"learning_rate": 8.718631293574753e-08,
"loss": 0.8073,
"step": 2492
},
{
"epoch": 0.96,
"learning_rate": 8.555138626189619e-08,
"loss": 0.7756,
"step": 2493
},
{
"epoch": 0.96,
"learning_rate": 8.393186832969746e-08,
"loss": 0.8157,
"step": 2494
},
{
"epoch": 0.96,
"learning_rate": 8.232776165616019e-08,
"loss": 0.7871,
"step": 2495
},
{
"epoch": 0.96,
"learning_rate": 8.07390687343379e-08,
"loss": 0.519,
"step": 2496
},
{
"epoch": 0.96,
"learning_rate": 7.916579203333107e-08,
"loss": 0.8568,
"step": 2497
},
{
"epoch": 0.96,
"learning_rate": 7.760793399827937e-08,
"loss": 0.839,
"step": 2498
},
{
"epoch": 0.96,
"learning_rate": 7.606549705035937e-08,
"loss": 0.8158,
"step": 2499
},
{
"epoch": 0.96,
"learning_rate": 7.453848358678018e-08,
"loss": 0.4901,
"step": 2500
},
{
"epoch": 0.96,
"learning_rate": 7.302689598078117e-08,
"loss": 0.809,
"step": 2501
},
{
"epoch": 0.96,
"learning_rate": 7.153073658162646e-08,
"loss": 0.8524,
"step": 2502
},
{
"epoch": 0.96,
"learning_rate": 7.00500077146038e-08,
"loss": 0.8103,
"step": 2503
},
{
"epoch": 0.96,
"learning_rate": 6.858471168101788e-08,
"loss": 0.8243,
"step": 2504
},
{
"epoch": 0.96,
"learning_rate": 6.713485075818815e-08,
"loss": 0.798,
"step": 2505
},
{
"epoch": 0.96,
"learning_rate": 6.570042719944436e-08,
"loss": 0.7815,
"step": 2506
},
{
"epoch": 0.96,
"learning_rate": 6.428144323412544e-08,
"loss": 0.8051,
"step": 2507
},
{
"epoch": 0.97,
"learning_rate": 6.287790106757396e-08,
"loss": 0.7581,
"step": 2508
},
{
"epoch": 0.97,
"learning_rate": 6.148980288113504e-08,
"loss": 0.7736,
"step": 2509
},
{
"epoch": 0.97,
"learning_rate": 6.011715083214742e-08,
"loss": 0.7862,
"step": 2510
},
{
"epoch": 0.97,
"learning_rate": 5.875994705394794e-08,
"loss": 0.87,
"step": 2511
},
{
"epoch": 0.97,
"learning_rate": 5.7418193655861545e-08,
"loss": 0.7777,
"step": 2512
},
{
"epoch": 0.97,
"learning_rate": 5.609189272320237e-08,
"loss": 0.8179,
"step": 2513
},
{
"epoch": 0.97,
"learning_rate": 5.4781046317267103e-08,
"loss": 0.8027,
"step": 2514
},
{
"epoch": 0.97,
"learning_rate": 5.348565647533388e-08,
"loss": 0.8835,
"step": 2515
},
{
"epoch": 0.97,
"learning_rate": 5.220572521066003e-08,
"loss": 0.8141,
"step": 2516
},
{
"epoch": 0.97,
"learning_rate": 5.094125451247656e-08,
"loss": 0.8071,
"step": 2517
},
{
"epoch": 0.97,
"learning_rate": 4.9692246345985905e-08,
"loss": 0.8116,
"step": 2518
},
{
"epoch": 0.97,
"learning_rate": 4.8458702652359744e-08,
"loss": 0.7982,
"step": 2519
},
{
"epoch": 0.97,
"learning_rate": 4.7240625348735636e-08,
"loss": 0.7833,
"step": 2520
},
{
"epoch": 0.97,
"learning_rate": 4.603801632821148e-08,
"loss": 0.8336,
"step": 2521
},
{
"epoch": 0.97,
"learning_rate": 4.485087745984884e-08,
"loss": 0.8003,
"step": 2522
},
{
"epoch": 0.97,
"learning_rate": 4.367921058866187e-08,
"loss": 0.8765,
"step": 2523
},
{
"epoch": 0.97,
"learning_rate": 4.252301753562171e-08,
"loss": 0.7803,
"step": 2524
},
{
"epoch": 0.97,
"learning_rate": 4.1382300097647655e-08,
"loss": 0.799,
"step": 2525
},
{
"epoch": 0.97,
"learning_rate": 4.025706004760932e-08,
"loss": 0.4608,
"step": 2526
},
{
"epoch": 0.97,
"learning_rate": 3.914729913432336e-08,
"loss": 0.8339,
"step": 2527
},
{
"epoch": 0.97,
"learning_rate": 3.805301908254455e-08,
"loss": 0.8093,
"step": 2528
},
{
"epoch": 0.97,
"learning_rate": 3.697422159297248e-08,
"loss": 0.7801,
"step": 2529
},
{
"epoch": 0.97,
"learning_rate": 3.591090834224153e-08,
"loss": 0.7839,
"step": 2530
},
{
"epoch": 0.97,
"learning_rate": 3.4863080982919794e-08,
"loss": 0.8646,
"step": 2531
},
{
"epoch": 0.97,
"learning_rate": 3.383074114351237e-08,
"loss": 0.8019,
"step": 2532
},
{
"epoch": 0.97,
"learning_rate": 3.281389042844918e-08,
"loss": 0.8134,
"step": 2533
},
{
"epoch": 0.98,
"learning_rate": 3.181253041809052e-08,
"loss": 0.8585,
"step": 2534
},
{
"epoch": 0.98,
"learning_rate": 3.082666266872036e-08,
"loss": 0.7895,
"step": 2535
},
{
"epoch": 0.98,
"learning_rate": 2.9856288712544204e-08,
"loss": 0.8697,
"step": 2536
},
{
"epoch": 0.98,
"learning_rate": 2.8901410057688982e-08,
"loss": 0.8097,
"step": 2537
},
{
"epoch": 0.98,
"learning_rate": 2.796202818819871e-08,
"loss": 0.8414,
"step": 2538
},
{
"epoch": 0.98,
"learning_rate": 2.7038144564033307e-08,
"loss": 0.7905,
"step": 2539
},
{
"epoch": 0.98,
"learning_rate": 2.6129760621063095e-08,
"loss": 0.7991,
"step": 2540
},
{
"epoch": 0.98,
"learning_rate": 2.5236877771074308e-08,
"loss": 0.8479,
"step": 2541
},
{
"epoch": 0.98,
"learning_rate": 2.4359497401758026e-08,
"loss": 0.8301,
"step": 2542
},
{
"epoch": 0.98,
"learning_rate": 2.349762087671126e-08,
"loss": 0.4958,
"step": 2543
},
{
"epoch": 0.98,
"learning_rate": 2.265124953543918e-08,
"loss": 0.8188,
"step": 2544
},
{
"epoch": 0.98,
"learning_rate": 2.182038469334513e-08,
"loss": 0.8134,
"step": 2545
},
{
"epoch": 0.98,
"learning_rate": 2.1005027641736176e-08,
"loss": 0.8231,
"step": 2546
},
{
"epoch": 0.98,
"learning_rate": 2.020517964781532e-08,
"loss": 0.8054,
"step": 2547
},
{
"epoch": 0.98,
"learning_rate": 1.9420841954681525e-08,
"loss": 0.8296,
"step": 2548
},
{
"epoch": 0.98,
"learning_rate": 1.86520157813308e-08,
"loss": 0.7894,
"step": 2549
},
{
"epoch": 0.98,
"learning_rate": 1.7898702322648453e-08,
"loss": 0.7646,
"step": 2550
},
{
"epoch": 0.98,
"learning_rate": 1.716090274941351e-08,
"loss": 0.8276,
"step": 2551
},
{
"epoch": 0.98,
"learning_rate": 1.6438618208290957e-08,
"loss": 0.752,
"step": 2552
},
{
"epoch": 0.98,
"learning_rate": 1.5731849821833955e-08,
"loss": 0.8243,
"step": 2553
},
{
"epoch": 0.98,
"learning_rate": 1.5040598688482732e-08,
"loss": 0.8475,
"step": 2554
},
{
"epoch": 0.98,
"learning_rate": 1.436486588255681e-08,
"loss": 0.7762,
"step": 2555
},
{
"epoch": 0.98,
"learning_rate": 1.370465245426167e-08,
"loss": 0.7958,
"step": 2556
},
{
"epoch": 0.98,
"learning_rate": 1.3059959429679859e-08,
"loss": 0.8699,
"step": 2557
},
{
"epoch": 0.98,
"learning_rate": 1.2430787810776556e-08,
"loss": 0.7931,
"step": 2558
},
{
"epoch": 0.98,
"learning_rate": 1.1817138575389576e-08,
"loss": 0.8323,
"step": 2559
},
{
"epoch": 0.99,
"learning_rate": 1.1219012677234908e-08,
"loss": 0.858,
"step": 2560
},
{
"epoch": 0.99,
"learning_rate": 1.0636411045902296e-08,
"loss": 0.8137,
"step": 2561
},
{
"epoch": 0.99,
"learning_rate": 1.0069334586854106e-08,
"loss": 0.8837,
"step": 2562
},
{
"epoch": 0.99,
"learning_rate": 9.517784181422018e-09,
"loss": 0.8235,
"step": 2563
},
{
"epoch": 0.99,
"learning_rate": 8.981760686811448e-09,
"loss": 0.8417,
"step": 2564
},
{
"epoch": 0.99,
"learning_rate": 8.461264936093783e-09,
"loss": 0.7896,
"step": 2565
},
{
"epoch": 0.99,
"learning_rate": 7.956297738207496e-09,
"loss": 0.7776,
"step": 2566
},
{
"epoch": 0.99,
"learning_rate": 7.466859877958143e-09,
"loss": 0.8202,
"step": 2567
},
{
"epoch": 0.99,
"learning_rate": 6.992952116013918e-09,
"loss": 0.8124,
"step": 2568
},
{
"epoch": 0.99,
"learning_rate": 6.534575188911208e-09,
"loss": 0.8604,
"step": 2569
},
{
"epoch": 0.99,
"learning_rate": 6.091729809042379e-09,
"loss": 0.831,
"step": 2570
},
{
"epoch": 0.99,
"learning_rate": 5.664416664666883e-09,
"loss": 0.8391,
"step": 2571
},
{
"epoch": 0.99,
"learning_rate": 5.252636419902368e-09,
"loss": 0.8315,
"step": 2572
},
{
"epoch": 0.99,
"learning_rate": 4.856389714723575e-09,
"loss": 0.7749,
"step": 2573
},
{
"epoch": 0.99,
"learning_rate": 4.475677164966774e-09,
"loss": 0.773,
"step": 2574
},
{
"epoch": 0.99,
"learning_rate": 4.110499362323106e-09,
"loss": 0.8566,
"step": 2575
},
{
"epoch": 0.99,
"learning_rate": 3.760856874341912e-09,
"loss": 0.8656,
"step": 2576
},
{
"epoch": 0.99,
"learning_rate": 3.4267502444274013e-09,
"loss": 0.8594,
"step": 2577
},
{
"epoch": 0.99,
"learning_rate": 3.1081799918375454e-09,
"loss": 0.8013,
"step": 2578
},
{
"epoch": 0.99,
"learning_rate": 2.805146611684073e-09,
"loss": 0.8146,
"step": 2579
},
{
"epoch": 0.99,
"learning_rate": 2.5176505749346937e-09,
"loss": 0.8185,
"step": 2580
},
{
"epoch": 0.99,
"learning_rate": 2.245692328404214e-09,
"loss": 0.8598,
"step": 2581
},
{
"epoch": 0.99,
"learning_rate": 1.9892722947645328e-09,
"loss": 0.865,
"step": 2582
},
{
"epoch": 0.99,
"learning_rate": 1.7483908725357546e-09,
"loss": 0.7913,
"step": 2583
},
{
"epoch": 0.99,
"learning_rate": 1.5230484360873043e-09,
"loss": 0.8033,
"step": 2584
},
{
"epoch": 0.99,
"learning_rate": 1.3132453356412556e-09,
"loss": 0.8055,
"step": 2585
},
{
"epoch": 1.0,
"learning_rate": 1.1189818972656697e-09,
"loss": 0.7976,
"step": 2586
},
{
"epoch": 1.0,
"learning_rate": 9.40258422880147e-10,
"loss": 0.8633,
"step": 2587
},
{
"epoch": 1.0,
"learning_rate": 7.770751902513862e-10,
"loss": 0.7946,
"step": 2588
},
{
"epoch": 1.0,
"learning_rate": 6.294324529942942e-10,
"loss": 0.8237,
"step": 2589
},
{
"epoch": 1.0,
"learning_rate": 4.973304405697654e-10,
"loss": 0.5347,
"step": 2590
},
{
"epoch": 1.0,
"learning_rate": 3.807693582869032e-10,
"loss": 0.8082,
"step": 2591
},
{
"epoch": 1.0,
"learning_rate": 2.797493873019086e-10,
"loss": 0.8466,
"step": 2592
},
{
"epoch": 1.0,
"learning_rate": 1.9427068461808086e-10,
"loss": 0.4832,
"step": 2593
},
{
"epoch": 1.0,
"learning_rate": 1.2433338308137645e-10,
"loss": 0.8262,
"step": 2594
},
{
"epoch": 1.0,
"learning_rate": 6.99375913892908e-11,
"loss": 0.8375,
"step": 2595
},
{
"epoch": 1.0,
"learning_rate": 3.108339407975613e-11,
"loss": 0.8153,
"step": 2596
},
{
"epoch": 1.0,
"learning_rate": 7.770851538912993e-12,
"loss": 0.683,
"step": 2597
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 0.4739,
"step": 2598
},
{
"epoch": 1.0,
"step": 2598,
"total_flos": 9838907568422912.0,
"train_loss": 0.845769656998456,
"train_runtime": 64701.5853,
"train_samples_per_second": 10.279,
"train_steps_per_second": 0.04
}
],
"max_steps": 2598,
"num_train_epochs": 1,
"total_flos": 9838907568422912.0,
"trial_name": null,
"trial_params": null
}