G-LLaVA-7B-align / trainer_state.json
renjiepi's picture
Upload folder using huggingface_hub
828a018 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"global_step": 2512,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.3157894736842107e-07,
"loss": 1.9096,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 2.6315789473684213e-07,
"loss": 1.7895,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 3.9473684210526315e-07,
"loss": 1.7674,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 5.263157894736843e-07,
"loss": 1.8161,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 6.578947368421053e-07,
"loss": 1.861,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 7.894736842105263e-07,
"loss": 1.7389,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 9.210526315789474e-07,
"loss": 1.7427,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 1.0526315789473685e-06,
"loss": 1.7529,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 1.1842105263157894e-06,
"loss": 1.8856,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 1.3157894736842106e-06,
"loss": 1.8248,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 1.4473684210526317e-06,
"loss": 1.7304,
"step": 11
},
{
"epoch": 0.01,
"learning_rate": 1.5789473684210526e-06,
"loss": 1.8436,
"step": 12
},
{
"epoch": 0.01,
"learning_rate": 1.710526315789474e-06,
"loss": 1.7879,
"step": 13
},
{
"epoch": 0.01,
"learning_rate": 1.8421052631578948e-06,
"loss": 1.7983,
"step": 14
},
{
"epoch": 0.01,
"learning_rate": 1.973684210526316e-06,
"loss": 1.7863,
"step": 15
},
{
"epoch": 0.01,
"learning_rate": 2.105263157894737e-06,
"loss": 1.8264,
"step": 16
},
{
"epoch": 0.01,
"learning_rate": 2.236842105263158e-06,
"loss": 1.8144,
"step": 17
},
{
"epoch": 0.01,
"learning_rate": 2.368421052631579e-06,
"loss": 1.6971,
"step": 18
},
{
"epoch": 0.02,
"learning_rate": 2.5e-06,
"loss": 1.8065,
"step": 19
},
{
"epoch": 0.02,
"learning_rate": 2.631578947368421e-06,
"loss": 1.7789,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 2.7631578947368424e-06,
"loss": 1.654,
"step": 21
},
{
"epoch": 0.02,
"learning_rate": 2.8947368421052634e-06,
"loss": 1.7642,
"step": 22
},
{
"epoch": 0.02,
"learning_rate": 3.0263157894736843e-06,
"loss": 1.7605,
"step": 23
},
{
"epoch": 0.02,
"learning_rate": 3.157894736842105e-06,
"loss": 1.7897,
"step": 24
},
{
"epoch": 0.02,
"learning_rate": 3.289473684210527e-06,
"loss": 1.6944,
"step": 25
},
{
"epoch": 0.02,
"learning_rate": 3.421052631578948e-06,
"loss": 1.76,
"step": 26
},
{
"epoch": 0.02,
"learning_rate": 3.5526315789473687e-06,
"loss": 1.7299,
"step": 27
},
{
"epoch": 0.02,
"learning_rate": 3.6842105263157896e-06,
"loss": 1.6637,
"step": 28
},
{
"epoch": 0.02,
"learning_rate": 3.815789473684211e-06,
"loss": 1.6473,
"step": 29
},
{
"epoch": 0.02,
"learning_rate": 3.947368421052632e-06,
"loss": 1.6013,
"step": 30
},
{
"epoch": 0.02,
"learning_rate": 4.078947368421053e-06,
"loss": 1.6703,
"step": 31
},
{
"epoch": 0.03,
"learning_rate": 4.210526315789474e-06,
"loss": 1.6416,
"step": 32
},
{
"epoch": 0.03,
"learning_rate": 4.342105263157895e-06,
"loss": 1.5413,
"step": 33
},
{
"epoch": 0.03,
"learning_rate": 4.473684210526316e-06,
"loss": 1.5209,
"step": 34
},
{
"epoch": 0.03,
"learning_rate": 4.605263157894737e-06,
"loss": 1.5649,
"step": 35
},
{
"epoch": 0.03,
"learning_rate": 4.736842105263158e-06,
"loss": 1.5414,
"step": 36
},
{
"epoch": 0.03,
"learning_rate": 4.8684210526315795e-06,
"loss": 1.5195,
"step": 37
},
{
"epoch": 0.03,
"learning_rate": 5e-06,
"loss": 1.5981,
"step": 38
},
{
"epoch": 0.03,
"learning_rate": 5.131578947368422e-06,
"loss": 1.538,
"step": 39
},
{
"epoch": 0.03,
"learning_rate": 5.263157894736842e-06,
"loss": 1.5652,
"step": 40
},
{
"epoch": 0.03,
"learning_rate": 5.394736842105264e-06,
"loss": 1.4379,
"step": 41
},
{
"epoch": 0.03,
"learning_rate": 5.526315789473685e-06,
"loss": 1.5151,
"step": 42
},
{
"epoch": 0.03,
"learning_rate": 5.657894736842106e-06,
"loss": 1.4917,
"step": 43
},
{
"epoch": 0.04,
"learning_rate": 5.789473684210527e-06,
"loss": 1.4322,
"step": 44
},
{
"epoch": 0.04,
"learning_rate": 5.921052631578948e-06,
"loss": 1.5429,
"step": 45
},
{
"epoch": 0.04,
"learning_rate": 6.0526315789473685e-06,
"loss": 1.5271,
"step": 46
},
{
"epoch": 0.04,
"learning_rate": 6.18421052631579e-06,
"loss": 1.3388,
"step": 47
},
{
"epoch": 0.04,
"learning_rate": 6.31578947368421e-06,
"loss": 1.4339,
"step": 48
},
{
"epoch": 0.04,
"learning_rate": 6.447368421052632e-06,
"loss": 1.4225,
"step": 49
},
{
"epoch": 0.04,
"learning_rate": 6.578947368421054e-06,
"loss": 1.4432,
"step": 50
},
{
"epoch": 0.04,
"learning_rate": 6.710526315789474e-06,
"loss": 1.3634,
"step": 51
},
{
"epoch": 0.04,
"learning_rate": 6.842105263157896e-06,
"loss": 1.3453,
"step": 52
},
{
"epoch": 0.04,
"learning_rate": 6.973684210526316e-06,
"loss": 1.5263,
"step": 53
},
{
"epoch": 0.04,
"learning_rate": 7.1052631578947375e-06,
"loss": 1.3758,
"step": 54
},
{
"epoch": 0.04,
"learning_rate": 7.236842105263158e-06,
"loss": 1.3686,
"step": 55
},
{
"epoch": 0.04,
"learning_rate": 7.368421052631579e-06,
"loss": 1.371,
"step": 56
},
{
"epoch": 0.05,
"learning_rate": 7.500000000000001e-06,
"loss": 1.3006,
"step": 57
},
{
"epoch": 0.05,
"learning_rate": 7.631578947368423e-06,
"loss": 1.3173,
"step": 58
},
{
"epoch": 0.05,
"learning_rate": 7.763157894736843e-06,
"loss": 1.3707,
"step": 59
},
{
"epoch": 0.05,
"learning_rate": 7.894736842105265e-06,
"loss": 1.3439,
"step": 60
},
{
"epoch": 0.05,
"learning_rate": 8.026315789473685e-06,
"loss": 1.3437,
"step": 61
},
{
"epoch": 0.05,
"learning_rate": 8.157894736842106e-06,
"loss": 1.3132,
"step": 62
},
{
"epoch": 0.05,
"learning_rate": 8.289473684210526e-06,
"loss": 1.3197,
"step": 63
},
{
"epoch": 0.05,
"learning_rate": 8.421052631578948e-06,
"loss": 1.3114,
"step": 64
},
{
"epoch": 0.05,
"learning_rate": 8.552631578947368e-06,
"loss": 1.3067,
"step": 65
},
{
"epoch": 0.05,
"learning_rate": 8.68421052631579e-06,
"loss": 1.3287,
"step": 66
},
{
"epoch": 0.05,
"learning_rate": 8.81578947368421e-06,
"loss": 1.3312,
"step": 67
},
{
"epoch": 0.05,
"learning_rate": 8.947368421052632e-06,
"loss": 1.3152,
"step": 68
},
{
"epoch": 0.05,
"learning_rate": 9.078947368421054e-06,
"loss": 1.2531,
"step": 69
},
{
"epoch": 0.06,
"learning_rate": 9.210526315789474e-06,
"loss": 1.259,
"step": 70
},
{
"epoch": 0.06,
"learning_rate": 9.342105263157895e-06,
"loss": 1.386,
"step": 71
},
{
"epoch": 0.06,
"learning_rate": 9.473684210526315e-06,
"loss": 1.2616,
"step": 72
},
{
"epoch": 0.06,
"learning_rate": 9.605263157894737e-06,
"loss": 1.2636,
"step": 73
},
{
"epoch": 0.06,
"learning_rate": 9.736842105263159e-06,
"loss": 1.3086,
"step": 74
},
{
"epoch": 0.06,
"learning_rate": 9.868421052631579e-06,
"loss": 1.2298,
"step": 75
},
{
"epoch": 0.06,
"learning_rate": 1e-05,
"loss": 1.2715,
"step": 76
},
{
"epoch": 0.06,
"learning_rate": 9.999995841993864e-06,
"loss": 1.2272,
"step": 77
},
{
"epoch": 0.06,
"learning_rate": 9.99998336798237e-06,
"loss": 1.3275,
"step": 78
},
{
"epoch": 0.06,
"learning_rate": 9.999962577986266e-06,
"loss": 1.1967,
"step": 79
},
{
"epoch": 0.06,
"learning_rate": 9.999933472040129e-06,
"loss": 1.196,
"step": 80
},
{
"epoch": 0.06,
"learning_rate": 9.999896050192367e-06,
"loss": 1.2514,
"step": 81
},
{
"epoch": 0.07,
"learning_rate": 9.999850312505222e-06,
"loss": 1.22,
"step": 82
},
{
"epoch": 0.07,
"learning_rate": 9.999796259054765e-06,
"loss": 1.2993,
"step": 83
},
{
"epoch": 0.07,
"learning_rate": 9.999733889930897e-06,
"loss": 1.2381,
"step": 84
},
{
"epoch": 0.07,
"learning_rate": 9.999663205237351e-06,
"loss": 1.2636,
"step": 85
},
{
"epoch": 0.07,
"learning_rate": 9.99958420509169e-06,
"loss": 1.2688,
"step": 86
},
{
"epoch": 0.07,
"learning_rate": 9.999496889625307e-06,
"loss": 1.1651,
"step": 87
},
{
"epoch": 0.07,
"learning_rate": 9.999401258983426e-06,
"loss": 1.206,
"step": 88
},
{
"epoch": 0.07,
"learning_rate": 9.999297313325098e-06,
"loss": 1.2952,
"step": 89
},
{
"epoch": 0.07,
"learning_rate": 9.999185052823207e-06,
"loss": 1.2808,
"step": 90
},
{
"epoch": 0.07,
"learning_rate": 9.999064477664466e-06,
"loss": 1.1621,
"step": 91
},
{
"epoch": 0.07,
"learning_rate": 9.998935588049414e-06,
"loss": 1.1724,
"step": 92
},
{
"epoch": 0.07,
"learning_rate": 9.998798384192421e-06,
"loss": 1.2104,
"step": 93
},
{
"epoch": 0.07,
"learning_rate": 9.998652866321688e-06,
"loss": 1.171,
"step": 94
},
{
"epoch": 0.08,
"learning_rate": 9.998499034679235e-06,
"loss": 1.1804,
"step": 95
},
{
"epoch": 0.08,
"learning_rate": 9.99833688952092e-06,
"loss": 1.226,
"step": 96
},
{
"epoch": 0.08,
"learning_rate": 9.998166431116421e-06,
"loss": 1.1335,
"step": 97
},
{
"epoch": 0.08,
"learning_rate": 9.997987659749244e-06,
"loss": 1.1959,
"step": 98
},
{
"epoch": 0.08,
"learning_rate": 9.997800575716725e-06,
"loss": 1.1748,
"step": 99
},
{
"epoch": 0.08,
"learning_rate": 9.997605179330018e-06,
"loss": 1.1665,
"step": 100
},
{
"epoch": 0.08,
"learning_rate": 9.997401470914113e-06,
"loss": 1.1913,
"step": 101
},
{
"epoch": 0.08,
"learning_rate": 9.997189450807812e-06,
"loss": 1.1672,
"step": 102
},
{
"epoch": 0.08,
"learning_rate": 9.99696911936375e-06,
"loss": 1.2224,
"step": 103
},
{
"epoch": 0.08,
"learning_rate": 9.996740476948386e-06,
"loss": 1.2338,
"step": 104
},
{
"epoch": 0.08,
"learning_rate": 9.996503523941994e-06,
"loss": 1.1217,
"step": 105
},
{
"epoch": 0.08,
"learning_rate": 9.996258260738676e-06,
"loss": 1.1587,
"step": 106
},
{
"epoch": 0.09,
"learning_rate": 9.996004687746355e-06,
"loss": 1.2114,
"step": 107
},
{
"epoch": 0.09,
"learning_rate": 9.995742805386775e-06,
"loss": 1.166,
"step": 108
},
{
"epoch": 0.09,
"learning_rate": 9.995472614095496e-06,
"loss": 1.2078,
"step": 109
},
{
"epoch": 0.09,
"learning_rate": 9.995194114321905e-06,
"loss": 1.1291,
"step": 110
},
{
"epoch": 0.09,
"learning_rate": 9.994907306529203e-06,
"loss": 1.1723,
"step": 111
},
{
"epoch": 0.09,
"learning_rate": 9.994612191194407e-06,
"loss": 1.15,
"step": 112
},
{
"epoch": 0.09,
"learning_rate": 9.994308768808354e-06,
"loss": 1.1623,
"step": 113
},
{
"epoch": 0.09,
"learning_rate": 9.993997039875699e-06,
"loss": 1.1367,
"step": 114
},
{
"epoch": 0.09,
"learning_rate": 9.993677004914906e-06,
"loss": 1.1586,
"step": 115
},
{
"epoch": 0.09,
"learning_rate": 9.993348664458263e-06,
"loss": 1.2289,
"step": 116
},
{
"epoch": 0.09,
"learning_rate": 9.993012019051865e-06,
"loss": 1.1846,
"step": 117
},
{
"epoch": 0.09,
"learning_rate": 9.99266706925562e-06,
"loss": 1.2305,
"step": 118
},
{
"epoch": 0.09,
"learning_rate": 9.992313815643251e-06,
"loss": 1.1496,
"step": 119
},
{
"epoch": 0.1,
"learning_rate": 9.991952258802288e-06,
"loss": 1.1278,
"step": 120
},
{
"epoch": 0.1,
"learning_rate": 9.991582399334076e-06,
"loss": 1.1333,
"step": 121
},
{
"epoch": 0.1,
"learning_rate": 9.991204237853766e-06,
"loss": 1.166,
"step": 122
},
{
"epoch": 0.1,
"learning_rate": 9.990817774990314e-06,
"loss": 1.1745,
"step": 123
},
{
"epoch": 0.1,
"learning_rate": 9.990423011386489e-06,
"loss": 1.1175,
"step": 124
},
{
"epoch": 0.1,
"learning_rate": 9.990019947698864e-06,
"loss": 1.1515,
"step": 125
},
{
"epoch": 0.1,
"learning_rate": 9.98960858459781e-06,
"loss": 1.2142,
"step": 126
},
{
"epoch": 0.1,
"learning_rate": 9.989188922767511e-06,
"loss": 1.1063,
"step": 127
},
{
"epoch": 0.1,
"learning_rate": 9.98876096290595e-06,
"loss": 1.0081,
"step": 128
},
{
"epoch": 0.1,
"learning_rate": 9.988324705724912e-06,
"loss": 1.1138,
"step": 129
},
{
"epoch": 0.1,
"learning_rate": 9.987880151949976e-06,
"loss": 1.087,
"step": 130
},
{
"epoch": 0.1,
"learning_rate": 9.987427302320529e-06,
"loss": 1.181,
"step": 131
},
{
"epoch": 0.11,
"learning_rate": 9.986966157589751e-06,
"loss": 1.1462,
"step": 132
},
{
"epoch": 0.11,
"learning_rate": 9.986496718524616e-06,
"loss": 1.1764,
"step": 133
},
{
"epoch": 0.11,
"learning_rate": 9.986018985905901e-06,
"loss": 1.2727,
"step": 134
},
{
"epoch": 0.11,
"learning_rate": 9.98553296052817e-06,
"loss": 1.1027,
"step": 135
},
{
"epoch": 0.11,
"learning_rate": 9.98503864319978e-06,
"loss": 1.1371,
"step": 136
},
{
"epoch": 0.11,
"learning_rate": 9.984536034742885e-06,
"loss": 1.1024,
"step": 137
},
{
"epoch": 0.11,
"learning_rate": 9.98402513599342e-06,
"loss": 1.1805,
"step": 138
},
{
"epoch": 0.11,
"learning_rate": 9.983505947801115e-06,
"loss": 1.1541,
"step": 139
},
{
"epoch": 0.11,
"learning_rate": 9.982978471029485e-06,
"loss": 1.2375,
"step": 140
},
{
"epoch": 0.11,
"learning_rate": 9.98244270655583e-06,
"loss": 1.1972,
"step": 141
},
{
"epoch": 0.11,
"learning_rate": 9.981898655271237e-06,
"loss": 1.1323,
"step": 142
},
{
"epoch": 0.11,
"learning_rate": 9.98134631808057e-06,
"loss": 1.1029,
"step": 143
},
{
"epoch": 0.11,
"learning_rate": 9.980785695902481e-06,
"loss": 1.1839,
"step": 144
},
{
"epoch": 0.12,
"learning_rate": 9.980216789669396e-06,
"loss": 1.1372,
"step": 145
},
{
"epoch": 0.12,
"learning_rate": 9.979639600327522e-06,
"loss": 1.0931,
"step": 146
},
{
"epoch": 0.12,
"learning_rate": 9.979054128836842e-06,
"loss": 1.0312,
"step": 147
},
{
"epoch": 0.12,
"learning_rate": 9.978460376171113e-06,
"loss": 1.1165,
"step": 148
},
{
"epoch": 0.12,
"learning_rate": 9.977858343317866e-06,
"loss": 1.1863,
"step": 149
},
{
"epoch": 0.12,
"learning_rate": 9.977248031278402e-06,
"loss": 1.1508,
"step": 150
},
{
"epoch": 0.12,
"learning_rate": 9.976629441067797e-06,
"loss": 1.0961,
"step": 151
},
{
"epoch": 0.12,
"learning_rate": 9.97600257371489e-06,
"loss": 1.1266,
"step": 152
},
{
"epoch": 0.12,
"learning_rate": 9.975367430262289e-06,
"loss": 1.1104,
"step": 153
},
{
"epoch": 0.12,
"learning_rate": 9.974724011766364e-06,
"loss": 1.166,
"step": 154
},
{
"epoch": 0.12,
"learning_rate": 9.97407231929725e-06,
"loss": 1.043,
"step": 155
},
{
"epoch": 0.12,
"learning_rate": 9.973412353938847e-06,
"loss": 1.1267,
"step": 156
},
{
"epoch": 0.12,
"learning_rate": 9.972744116788809e-06,
"loss": 1.1855,
"step": 157
},
{
"epoch": 0.13,
"learning_rate": 9.972067608958549e-06,
"loss": 1.1046,
"step": 158
},
{
"epoch": 0.13,
"learning_rate": 9.971382831573239e-06,
"loss": 1.1616,
"step": 159
},
{
"epoch": 0.13,
"learning_rate": 9.970689785771798e-06,
"loss": 1.1339,
"step": 160
},
{
"epoch": 0.13,
"learning_rate": 9.969988472706906e-06,
"loss": 1.1121,
"step": 161
},
{
"epoch": 0.13,
"learning_rate": 9.969278893544986e-06,
"loss": 1.1369,
"step": 162
},
{
"epoch": 0.13,
"learning_rate": 9.968561049466214e-06,
"loss": 1.118,
"step": 163
},
{
"epoch": 0.13,
"learning_rate": 9.967834941664508e-06,
"loss": 1.1546,
"step": 164
},
{
"epoch": 0.13,
"learning_rate": 9.967100571347533e-06,
"loss": 1.1586,
"step": 165
},
{
"epoch": 0.13,
"learning_rate": 9.966357939736692e-06,
"loss": 1.0914,
"step": 166
},
{
"epoch": 0.13,
"learning_rate": 9.965607048067138e-06,
"loss": 1.15,
"step": 167
},
{
"epoch": 0.13,
"learning_rate": 9.964847897587753e-06,
"loss": 1.1036,
"step": 168
},
{
"epoch": 0.13,
"learning_rate": 9.96408048956116e-06,
"loss": 1.0865,
"step": 169
},
{
"epoch": 0.14,
"learning_rate": 9.963304825263708e-06,
"loss": 1.1427,
"step": 170
},
{
"epoch": 0.14,
"learning_rate": 9.96252090598549e-06,
"loss": 1.1223,
"step": 171
},
{
"epoch": 0.14,
"learning_rate": 9.961728733030318e-06,
"loss": 1.0203,
"step": 172
},
{
"epoch": 0.14,
"learning_rate": 9.96092830771574e-06,
"loss": 1.1482,
"step": 173
},
{
"epoch": 0.14,
"learning_rate": 9.960119631373023e-06,
"loss": 1.1408,
"step": 174
},
{
"epoch": 0.14,
"learning_rate": 9.95930270534716e-06,
"loss": 1.0959,
"step": 175
},
{
"epoch": 0.14,
"learning_rate": 9.958477530996862e-06,
"loss": 1.1635,
"step": 176
},
{
"epoch": 0.14,
"learning_rate": 9.957644109694566e-06,
"loss": 1.1219,
"step": 177
},
{
"epoch": 0.14,
"learning_rate": 9.956802442826417e-06,
"loss": 1.0862,
"step": 178
},
{
"epoch": 0.14,
"learning_rate": 9.955952531792276e-06,
"loss": 1.0523,
"step": 179
},
{
"epoch": 0.14,
"learning_rate": 9.955094378005723e-06,
"loss": 1.136,
"step": 180
},
{
"epoch": 0.14,
"learning_rate": 9.954227982894034e-06,
"loss": 1.1909,
"step": 181
},
{
"epoch": 0.14,
"learning_rate": 9.953353347898205e-06,
"loss": 1.1085,
"step": 182
},
{
"epoch": 0.15,
"learning_rate": 9.952470474472928e-06,
"loss": 1.0729,
"step": 183
},
{
"epoch": 0.15,
"learning_rate": 9.951579364086603e-06,
"loss": 1.1528,
"step": 184
},
{
"epoch": 0.15,
"learning_rate": 9.950680018221325e-06,
"loss": 1.149,
"step": 185
},
{
"epoch": 0.15,
"learning_rate": 9.949772438372887e-06,
"loss": 1.1447,
"step": 186
},
{
"epoch": 0.15,
"learning_rate": 9.948856626050781e-06,
"loss": 1.15,
"step": 187
},
{
"epoch": 0.15,
"learning_rate": 9.947932582778188e-06,
"loss": 1.1779,
"step": 188
},
{
"epoch": 0.15,
"learning_rate": 9.947000310091977e-06,
"loss": 1.1417,
"step": 189
},
{
"epoch": 0.15,
"learning_rate": 9.946059809542706e-06,
"loss": 1.1171,
"step": 190
},
{
"epoch": 0.15,
"learning_rate": 9.945111082694621e-06,
"loss": 1.112,
"step": 191
},
{
"epoch": 0.15,
"learning_rate": 9.944154131125643e-06,
"loss": 1.2276,
"step": 192
},
{
"epoch": 0.15,
"learning_rate": 9.94318895642738e-06,
"loss": 1.1303,
"step": 193
},
{
"epoch": 0.15,
"learning_rate": 9.94221556020511e-06,
"loss": 1.0859,
"step": 194
},
{
"epoch": 0.16,
"learning_rate": 9.941233944077789e-06,
"loss": 1.0862,
"step": 195
},
{
"epoch": 0.16,
"learning_rate": 9.940244109678043e-06,
"loss": 1.0687,
"step": 196
},
{
"epoch": 0.16,
"learning_rate": 9.939246058652168e-06,
"loss": 1.0305,
"step": 197
},
{
"epoch": 0.16,
"learning_rate": 9.938239792660124e-06,
"loss": 1.0904,
"step": 198
},
{
"epoch": 0.16,
"learning_rate": 9.937225313375536e-06,
"loss": 1.0233,
"step": 199
},
{
"epoch": 0.16,
"learning_rate": 9.936202622485687e-06,
"loss": 1.0595,
"step": 200
},
{
"epoch": 0.16,
"learning_rate": 9.93517172169152e-06,
"loss": 1.1331,
"step": 201
},
{
"epoch": 0.16,
"learning_rate": 9.934132612707631e-06,
"loss": 1.1293,
"step": 202
},
{
"epoch": 0.16,
"learning_rate": 9.933085297262271e-06,
"loss": 1.1696,
"step": 203
},
{
"epoch": 0.16,
"learning_rate": 9.932029777097333e-06,
"loss": 1.2274,
"step": 204
},
{
"epoch": 0.16,
"learning_rate": 9.930966053968364e-06,
"loss": 1.1059,
"step": 205
},
{
"epoch": 0.16,
"learning_rate": 9.929894129644552e-06,
"loss": 1.1457,
"step": 206
},
{
"epoch": 0.16,
"learning_rate": 9.928814005908723e-06,
"loss": 1.0404,
"step": 207
},
{
"epoch": 0.17,
"learning_rate": 9.927725684557339e-06,
"loss": 1.0712,
"step": 208
},
{
"epoch": 0.17,
"learning_rate": 9.9266291674005e-06,
"loss": 1.1276,
"step": 209
},
{
"epoch": 0.17,
"learning_rate": 9.92552445626194e-06,
"loss": 1.0669,
"step": 210
},
{
"epoch": 0.17,
"learning_rate": 9.924411552979011e-06,
"loss": 1.1271,
"step": 211
},
{
"epoch": 0.17,
"learning_rate": 9.923290459402701e-06,
"loss": 1.169,
"step": 212
},
{
"epoch": 0.17,
"learning_rate": 9.922161177397616e-06,
"loss": 1.1502,
"step": 213
},
{
"epoch": 0.17,
"learning_rate": 9.921023708841975e-06,
"loss": 1.0752,
"step": 214
},
{
"epoch": 0.17,
"learning_rate": 9.919878055627625e-06,
"loss": 1.1248,
"step": 215
},
{
"epoch": 0.17,
"learning_rate": 9.918724219660013e-06,
"loss": 1.122,
"step": 216
},
{
"epoch": 0.17,
"learning_rate": 9.917562202858208e-06,
"loss": 1.1606,
"step": 217
},
{
"epoch": 0.17,
"learning_rate": 9.916392007154877e-06,
"loss": 1.2091,
"step": 218
},
{
"epoch": 0.17,
"learning_rate": 9.91521363449629e-06,
"loss": 1.0147,
"step": 219
},
{
"epoch": 0.18,
"learning_rate": 9.914027086842323e-06,
"loss": 1.073,
"step": 220
},
{
"epoch": 0.18,
"learning_rate": 9.912832366166443e-06,
"loss": 1.0787,
"step": 221
},
{
"epoch": 0.18,
"learning_rate": 9.911629474455711e-06,
"loss": 1.0806,
"step": 222
},
{
"epoch": 0.18,
"learning_rate": 9.91041841371078e-06,
"loss": 1.072,
"step": 223
},
{
"epoch": 0.18,
"learning_rate": 9.909199185945893e-06,
"loss": 1.0945,
"step": 224
},
{
"epoch": 0.18,
"learning_rate": 9.907971793188867e-06,
"loss": 1.1365,
"step": 225
},
{
"epoch": 0.18,
"learning_rate": 9.90673623748111e-06,
"loss": 1.1344,
"step": 226
},
{
"epoch": 0.18,
"learning_rate": 9.905492520877595e-06,
"loss": 1.0786,
"step": 227
},
{
"epoch": 0.18,
"learning_rate": 9.90424064544688e-06,
"loss": 1.0629,
"step": 228
},
{
"epoch": 0.18,
"learning_rate": 9.902980613271087e-06,
"loss": 1.0197,
"step": 229
},
{
"epoch": 0.18,
"learning_rate": 9.901712426445901e-06,
"loss": 1.0872,
"step": 230
},
{
"epoch": 0.18,
"learning_rate": 9.900436087080577e-06,
"loss": 1.1475,
"step": 231
},
{
"epoch": 0.18,
"learning_rate": 9.899151597297923e-06,
"loss": 1.0718,
"step": 232
},
{
"epoch": 0.19,
"learning_rate": 9.897858959234308e-06,
"loss": 1.0523,
"step": 233
},
{
"epoch": 0.19,
"learning_rate": 9.89655817503965e-06,
"loss": 1.0833,
"step": 234
},
{
"epoch": 0.19,
"learning_rate": 9.895249246877414e-06,
"loss": 1.1371,
"step": 235
},
{
"epoch": 0.19,
"learning_rate": 9.893932176924616e-06,
"loss": 1.0822,
"step": 236
},
{
"epoch": 0.19,
"learning_rate": 9.892606967371808e-06,
"loss": 1.1967,
"step": 237
},
{
"epoch": 0.19,
"learning_rate": 9.891273620423083e-06,
"loss": 1.0473,
"step": 238
},
{
"epoch": 0.19,
"learning_rate": 9.889932138296066e-06,
"loss": 1.0572,
"step": 239
},
{
"epoch": 0.19,
"learning_rate": 9.888582523221912e-06,
"loss": 1.0952,
"step": 240
},
{
"epoch": 0.19,
"learning_rate": 9.887224777445308e-06,
"loss": 1.0858,
"step": 241
},
{
"epoch": 0.19,
"learning_rate": 9.885858903224457e-06,
"loss": 1.0932,
"step": 242
},
{
"epoch": 0.19,
"learning_rate": 9.884484902831086e-06,
"loss": 1.1343,
"step": 243
},
{
"epoch": 0.19,
"learning_rate": 9.883102778550434e-06,
"loss": 1.0996,
"step": 244
},
{
"epoch": 0.2,
"learning_rate": 9.881712532681255e-06,
"loss": 1.0662,
"step": 245
},
{
"epoch": 0.2,
"learning_rate": 9.88031416753581e-06,
"loss": 1.0779,
"step": 246
},
{
"epoch": 0.2,
"learning_rate": 9.878907685439861e-06,
"loss": 1.0927,
"step": 247
},
{
"epoch": 0.2,
"learning_rate": 9.877493088732672e-06,
"loss": 1.0257,
"step": 248
},
{
"epoch": 0.2,
"learning_rate": 9.876070379767008e-06,
"loss": 1.0676,
"step": 249
},
{
"epoch": 0.2,
"learning_rate": 9.874639560909118e-06,
"loss": 1.0262,
"step": 250
},
{
"epoch": 0.2,
"learning_rate": 9.873200634538746e-06,
"loss": 1.1446,
"step": 251
},
{
"epoch": 0.2,
"learning_rate": 9.871753603049117e-06,
"loss": 1.0247,
"step": 252
},
{
"epoch": 0.2,
"learning_rate": 9.870298468846937e-06,
"loss": 1.1437,
"step": 253
},
{
"epoch": 0.2,
"learning_rate": 9.868835234352387e-06,
"loss": 1.0372,
"step": 254
},
{
"epoch": 0.2,
"learning_rate": 9.867363901999124e-06,
"loss": 1.0885,
"step": 255
},
{
"epoch": 0.2,
"learning_rate": 9.865884474234275e-06,
"loss": 1.0781,
"step": 256
},
{
"epoch": 0.2,
"learning_rate": 9.864396953518423e-06,
"loss": 1.0391,
"step": 257
},
{
"epoch": 0.21,
"learning_rate": 9.862901342325617e-06,
"loss": 1.0226,
"step": 258
},
{
"epoch": 0.21,
"learning_rate": 9.861397643143362e-06,
"loss": 1.1351,
"step": 259
},
{
"epoch": 0.21,
"learning_rate": 9.859885858472614e-06,
"loss": 1.0662,
"step": 260
},
{
"epoch": 0.21,
"learning_rate": 9.858365990827777e-06,
"loss": 1.1253,
"step": 261
},
{
"epoch": 0.21,
"learning_rate": 9.856838042736698e-06,
"loss": 1.0478,
"step": 262
},
{
"epoch": 0.21,
"learning_rate": 9.855302016740667e-06,
"loss": 1.0347,
"step": 263
},
{
"epoch": 0.21,
"learning_rate": 9.853757915394403e-06,
"loss": 1.1221,
"step": 264
},
{
"epoch": 0.21,
"learning_rate": 9.852205741266058e-06,
"loss": 1.1591,
"step": 265
},
{
"epoch": 0.21,
"learning_rate": 9.850645496937215e-06,
"loss": 1.0885,
"step": 266
},
{
"epoch": 0.21,
"learning_rate": 9.849077185002876e-06,
"loss": 1.1684,
"step": 267
},
{
"epoch": 0.21,
"learning_rate": 9.847500808071458e-06,
"loss": 1.1073,
"step": 268
},
{
"epoch": 0.21,
"learning_rate": 9.845916368764798e-06,
"loss": 1.0828,
"step": 269
},
{
"epoch": 0.21,
"learning_rate": 9.844323869718139e-06,
"loss": 1.0432,
"step": 270
},
{
"epoch": 0.22,
"learning_rate": 9.84272331358013e-06,
"loss": 1.1308,
"step": 271
},
{
"epoch": 0.22,
"learning_rate": 9.841114703012817e-06,
"loss": 1.1546,
"step": 272
},
{
"epoch": 0.22,
"learning_rate": 9.839498040691648e-06,
"loss": 1.1321,
"step": 273
},
{
"epoch": 0.22,
"learning_rate": 9.837873329305458e-06,
"loss": 1.0834,
"step": 274
},
{
"epoch": 0.22,
"learning_rate": 9.836240571556473e-06,
"loss": 1.0396,
"step": 275
},
{
"epoch": 0.22,
"learning_rate": 9.834599770160296e-06,
"loss": 1.0746,
"step": 276
},
{
"epoch": 0.22,
"learning_rate": 9.832950927845915e-06,
"loss": 1.0821,
"step": 277
},
{
"epoch": 0.22,
"learning_rate": 9.831294047355688e-06,
"loss": 1.0473,
"step": 278
},
{
"epoch": 0.22,
"learning_rate": 9.829629131445342e-06,
"loss": 1.1288,
"step": 279
},
{
"epoch": 0.22,
"learning_rate": 9.82795618288397e-06,
"loss": 1.0281,
"step": 280
},
{
"epoch": 0.22,
"learning_rate": 9.826275204454024e-06,
"loss": 1.1674,
"step": 281
},
{
"epoch": 0.22,
"learning_rate": 9.824586198951311e-06,
"loss": 1.0675,
"step": 282
},
{
"epoch": 0.23,
"learning_rate": 9.82288916918499e-06,
"loss": 1.182,
"step": 283
},
{
"epoch": 0.23,
"learning_rate": 9.821184117977564e-06,
"loss": 1.0502,
"step": 284
},
{
"epoch": 0.23,
"learning_rate": 9.819471048164877e-06,
"loss": 1.0769,
"step": 285
},
{
"epoch": 0.23,
"learning_rate": 9.817749962596115e-06,
"loss": 0.9965,
"step": 286
},
{
"epoch": 0.23,
"learning_rate": 9.816020864133789e-06,
"loss": 1.0156,
"step": 287
},
{
"epoch": 0.23,
"learning_rate": 9.81428375565374e-06,
"loss": 0.965,
"step": 288
},
{
"epoch": 0.23,
"learning_rate": 9.812538640045133e-06,
"loss": 1.0054,
"step": 289
},
{
"epoch": 0.23,
"learning_rate": 9.810785520210445e-06,
"loss": 1.0555,
"step": 290
},
{
"epoch": 0.23,
"learning_rate": 9.809024399065471e-06,
"loss": 1.0493,
"step": 291
},
{
"epoch": 0.23,
"learning_rate": 9.807255279539313e-06,
"loss": 1.0076,
"step": 292
},
{
"epoch": 0.23,
"learning_rate": 9.805478164574374e-06,
"loss": 1.0697,
"step": 293
},
{
"epoch": 0.23,
"learning_rate": 9.803693057126355e-06,
"loss": 1.0899,
"step": 294
},
{
"epoch": 0.23,
"learning_rate": 9.801899960164254e-06,
"loss": 1.0309,
"step": 295
},
{
"epoch": 0.24,
"learning_rate": 9.80009887667035e-06,
"loss": 0.9801,
"step": 296
},
{
"epoch": 0.24,
"learning_rate": 9.798289809640214e-06,
"loss": 1.0204,
"step": 297
},
{
"epoch": 0.24,
"learning_rate": 9.796472762082687e-06,
"loss": 1.053,
"step": 298
},
{
"epoch": 0.24,
"learning_rate": 9.79464773701989e-06,
"loss": 0.9875,
"step": 299
},
{
"epoch": 0.24,
"learning_rate": 9.792814737487207e-06,
"loss": 1.1371,
"step": 300
},
{
"epoch": 0.24,
"learning_rate": 9.790973766533288e-06,
"loss": 1.0503,
"step": 301
},
{
"epoch": 0.24,
"learning_rate": 9.789124827220042e-06,
"loss": 1.0593,
"step": 302
},
{
"epoch": 0.24,
"learning_rate": 9.787267922622625e-06,
"loss": 1.0153,
"step": 303
},
{
"epoch": 0.24,
"learning_rate": 9.78540305582945e-06,
"loss": 0.9451,
"step": 304
},
{
"epoch": 0.24,
"learning_rate": 9.783530229942166e-06,
"loss": 1.0352,
"step": 305
},
{
"epoch": 0.24,
"learning_rate": 9.781649448075662e-06,
"loss": 0.9173,
"step": 306
},
{
"epoch": 0.24,
"learning_rate": 9.77976071335806e-06,
"loss": 1.021,
"step": 307
},
{
"epoch": 0.25,
"learning_rate": 9.777864028930705e-06,
"loss": 1.0055,
"step": 308
},
{
"epoch": 0.25,
"learning_rate": 9.77595939794817e-06,
"loss": 1.0795,
"step": 309
},
{
"epoch": 0.25,
"learning_rate": 9.77404682357824e-06,
"loss": 1.0911,
"step": 310
},
{
"epoch": 0.25,
"learning_rate": 9.772126309001916e-06,
"loss": 1.0438,
"step": 311
},
{
"epoch": 0.25,
"learning_rate": 9.7701978574134e-06,
"loss": 0.992,
"step": 312
},
{
"epoch": 0.25,
"learning_rate": 9.7682614720201e-06,
"loss": 0.9984,
"step": 313
},
{
"epoch": 0.25,
"learning_rate": 9.766317156042615e-06,
"loss": 1.0756,
"step": 314
},
{
"epoch": 0.25,
"learning_rate": 9.764364912714736e-06,
"loss": 1.0361,
"step": 315
},
{
"epoch": 0.25,
"learning_rate": 9.762404745283439e-06,
"loss": 1.069,
"step": 316
},
{
"epoch": 0.25,
"learning_rate": 9.76043665700888e-06,
"loss": 1.0074,
"step": 317
},
{
"epoch": 0.25,
"learning_rate": 9.75846065116439e-06,
"loss": 0.9915,
"step": 318
},
{
"epoch": 0.25,
"learning_rate": 9.756476731036462e-06,
"loss": 1.0771,
"step": 319
},
{
"epoch": 0.25,
"learning_rate": 9.754484899924762e-06,
"loss": 1.0227,
"step": 320
},
{
"epoch": 0.26,
"learning_rate": 9.752485161142103e-06,
"loss": 1.0294,
"step": 321
},
{
"epoch": 0.26,
"learning_rate": 9.75047751801446e-06,
"loss": 1.1858,
"step": 322
},
{
"epoch": 0.26,
"learning_rate": 9.748461973880949e-06,
"loss": 1.0588,
"step": 323
},
{
"epoch": 0.26,
"learning_rate": 9.746438532093827e-06,
"loss": 1.0637,
"step": 324
},
{
"epoch": 0.26,
"learning_rate": 9.744407196018488e-06,
"loss": 1.0571,
"step": 325
},
{
"epoch": 0.26,
"learning_rate": 9.742367969033456e-06,
"loss": 0.977,
"step": 326
},
{
"epoch": 0.26,
"learning_rate": 9.740320854530373e-06,
"loss": 1.0543,
"step": 327
},
{
"epoch": 0.26,
"learning_rate": 9.738265855914014e-06,
"loss": 1.0536,
"step": 328
},
{
"epoch": 0.26,
"learning_rate": 9.73620297660225e-06,
"loss": 1.051,
"step": 329
},
{
"epoch": 0.26,
"learning_rate": 9.734132220026071e-06,
"loss": 1.0033,
"step": 330
},
{
"epoch": 0.26,
"learning_rate": 9.732053589629563e-06,
"loss": 0.9871,
"step": 331
},
{
"epoch": 0.26,
"learning_rate": 9.729967088869907e-06,
"loss": 1.0849,
"step": 332
},
{
"epoch": 0.27,
"learning_rate": 9.72787272121738e-06,
"loss": 1.046,
"step": 333
},
{
"epoch": 0.27,
"learning_rate": 9.725770490155338e-06,
"loss": 0.9778,
"step": 334
},
{
"epoch": 0.27,
"learning_rate": 9.723660399180216e-06,
"loss": 1.1281,
"step": 335
},
{
"epoch": 0.27,
"learning_rate": 9.721542451801526e-06,
"loss": 1.1218,
"step": 336
},
{
"epoch": 0.27,
"learning_rate": 9.719416651541839e-06,
"loss": 1.0368,
"step": 337
},
{
"epoch": 0.27,
"learning_rate": 9.717283001936793e-06,
"loss": 0.986,
"step": 338
},
{
"epoch": 0.27,
"learning_rate": 9.715141506535077e-06,
"loss": 0.9853,
"step": 339
},
{
"epoch": 0.27,
"learning_rate": 9.712992168898436e-06,
"loss": 1.0921,
"step": 340
},
{
"epoch": 0.27,
"learning_rate": 9.71083499260165e-06,
"loss": 1.0483,
"step": 341
},
{
"epoch": 0.27,
"learning_rate": 9.708669981232542e-06,
"loss": 1.0383,
"step": 342
},
{
"epoch": 0.27,
"learning_rate": 9.70649713839196e-06,
"loss": 1.0096,
"step": 343
},
{
"epoch": 0.27,
"learning_rate": 9.704316467693789e-06,
"loss": 1.0816,
"step": 344
},
{
"epoch": 0.27,
"learning_rate": 9.702127972764919e-06,
"loss": 1.1065,
"step": 345
},
{
"epoch": 0.28,
"learning_rate": 9.699931657245264e-06,
"loss": 1.0441,
"step": 346
},
{
"epoch": 0.28,
"learning_rate": 9.697727524787739e-06,
"loss": 0.9917,
"step": 347
},
{
"epoch": 0.28,
"learning_rate": 9.695515579058265e-06,
"loss": 1.0232,
"step": 348
},
{
"epoch": 0.28,
"learning_rate": 9.693295823735754e-06,
"loss": 1.0987,
"step": 349
},
{
"epoch": 0.28,
"learning_rate": 9.691068262512107e-06,
"loss": 0.9973,
"step": 350
},
{
"epoch": 0.28,
"learning_rate": 9.688832899092213e-06,
"loss": 0.9969,
"step": 351
},
{
"epoch": 0.28,
"learning_rate": 9.686589737193929e-06,
"loss": 0.9518,
"step": 352
},
{
"epoch": 0.28,
"learning_rate": 9.684338780548093e-06,
"loss": 1.0782,
"step": 353
},
{
"epoch": 0.28,
"learning_rate": 9.682080032898499e-06,
"loss": 1.0175,
"step": 354
},
{
"epoch": 0.28,
"learning_rate": 9.6798134980019e-06,
"loss": 0.9618,
"step": 355
},
{
"epoch": 0.28,
"learning_rate": 9.677539179628005e-06,
"loss": 1.0574,
"step": 356
},
{
"epoch": 0.28,
"learning_rate": 9.675257081559465e-06,
"loss": 1.0432,
"step": 357
},
{
"epoch": 0.29,
"learning_rate": 9.67296720759187e-06,
"loss": 1.0427,
"step": 358
},
{
"epoch": 0.29,
"learning_rate": 9.670669561533747e-06,
"loss": 1.0749,
"step": 359
},
{
"epoch": 0.29,
"learning_rate": 9.668364147206542e-06,
"loss": 0.9584,
"step": 360
},
{
"epoch": 0.29,
"learning_rate": 9.666050968444631e-06,
"loss": 1.0241,
"step": 361
},
{
"epoch": 0.29,
"learning_rate": 9.663730029095293e-06,
"loss": 1.0936,
"step": 362
},
{
"epoch": 0.29,
"learning_rate": 9.661401333018725e-06,
"loss": 1.0723,
"step": 363
},
{
"epoch": 0.29,
"learning_rate": 9.659064884088017e-06,
"loss": 1.0509,
"step": 364
},
{
"epoch": 0.29,
"learning_rate": 9.656720686189158e-06,
"loss": 1.0593,
"step": 365
},
{
"epoch": 0.29,
"learning_rate": 9.654368743221022e-06,
"loss": 1.0852,
"step": 366
},
{
"epoch": 0.29,
"learning_rate": 9.652009059095369e-06,
"loss": 1.0968,
"step": 367
},
{
"epoch": 0.29,
"learning_rate": 9.649641637736829e-06,
"loss": 1.0108,
"step": 368
},
{
"epoch": 0.29,
"learning_rate": 9.647266483082904e-06,
"loss": 0.9848,
"step": 369
},
{
"epoch": 0.29,
"learning_rate": 9.644883599083959e-06,
"loss": 1.103,
"step": 370
},
{
"epoch": 0.3,
"learning_rate": 9.642492989703209e-06,
"loss": 1.0246,
"step": 371
},
{
"epoch": 0.3,
"learning_rate": 9.640094658916723e-06,
"loss": 1.0461,
"step": 372
},
{
"epoch": 0.3,
"learning_rate": 9.63768861071341e-06,
"loss": 1.0334,
"step": 373
},
{
"epoch": 0.3,
"learning_rate": 9.635274849095016e-06,
"loss": 1.0197,
"step": 374
},
{
"epoch": 0.3,
"learning_rate": 9.632853378076118e-06,
"loss": 0.9961,
"step": 375
},
{
"epoch": 0.3,
"learning_rate": 9.630424201684105e-06,
"loss": 1.11,
"step": 376
},
{
"epoch": 0.3,
"learning_rate": 9.627987323959195e-06,
"loss": 0.9763,
"step": 377
},
{
"epoch": 0.3,
"learning_rate": 9.62554274895441e-06,
"loss": 1.0283,
"step": 378
},
{
"epoch": 0.3,
"learning_rate": 9.62309048073557e-06,
"loss": 1.0279,
"step": 379
},
{
"epoch": 0.3,
"learning_rate": 9.620630523381295e-06,
"loss": 1.0258,
"step": 380
},
{
"epoch": 0.3,
"learning_rate": 9.618162880982992e-06,
"loss": 1.0384,
"step": 381
},
{
"epoch": 0.3,
"learning_rate": 9.615687557644848e-06,
"loss": 1.0378,
"step": 382
},
{
"epoch": 0.3,
"learning_rate": 9.613204557483829e-06,
"loss": 1.1032,
"step": 383
},
{
"epoch": 0.31,
"learning_rate": 9.610713884629667e-06,
"loss": 1.0695,
"step": 384
},
{
"epoch": 0.31,
"learning_rate": 9.608215543224853e-06,
"loss": 0.9388,
"step": 385
},
{
"epoch": 0.31,
"learning_rate": 9.605709537424637e-06,
"loss": 1.0445,
"step": 386
},
{
"epoch": 0.31,
"learning_rate": 9.603195871397013e-06,
"loss": 1.089,
"step": 387
},
{
"epoch": 0.31,
"learning_rate": 9.600674549322716e-06,
"loss": 1.0164,
"step": 388
},
{
"epoch": 0.31,
"learning_rate": 9.598145575395217e-06,
"loss": 1.0001,
"step": 389
},
{
"epoch": 0.31,
"learning_rate": 9.59560895382071e-06,
"loss": 1.0003,
"step": 390
},
{
"epoch": 0.31,
"learning_rate": 9.59306468881811e-06,
"loss": 1.027,
"step": 391
},
{
"epoch": 0.31,
"learning_rate": 9.590512784619045e-06,
"loss": 0.9207,
"step": 392
},
{
"epoch": 0.31,
"learning_rate": 9.58795324546785e-06,
"loss": 1.0454,
"step": 393
},
{
"epoch": 0.31,
"learning_rate": 9.585386075621553e-06,
"loss": 1.0488,
"step": 394
},
{
"epoch": 0.31,
"learning_rate": 9.582811279349881e-06,
"loss": 1.074,
"step": 395
},
{
"epoch": 0.32,
"learning_rate": 9.580228860935242e-06,
"loss": 1.0608,
"step": 396
},
{
"epoch": 0.32,
"learning_rate": 9.577638824672716e-06,
"loss": 1.0219,
"step": 397
},
{
"epoch": 0.32,
"learning_rate": 9.575041174870062e-06,
"loss": 1.1376,
"step": 398
},
{
"epoch": 0.32,
"learning_rate": 9.572435915847695e-06,
"loss": 1.0647,
"step": 399
},
{
"epoch": 0.32,
"learning_rate": 9.569823051938689e-06,
"loss": 0.9149,
"step": 400
},
{
"epoch": 0.32,
"learning_rate": 9.567202587488767e-06,
"loss": 1.0271,
"step": 401
},
{
"epoch": 0.32,
"learning_rate": 9.56457452685629e-06,
"loss": 1.0845,
"step": 402
},
{
"epoch": 0.32,
"learning_rate": 9.561938874412255e-06,
"loss": 1.0224,
"step": 403
},
{
"epoch": 0.32,
"learning_rate": 9.559295634540287e-06,
"loss": 1.0094,
"step": 404
},
{
"epoch": 0.32,
"learning_rate": 9.556644811636628e-06,
"loss": 1.0921,
"step": 405
},
{
"epoch": 0.32,
"learning_rate": 9.553986410110135e-06,
"loss": 1.0707,
"step": 406
},
{
"epoch": 0.32,
"learning_rate": 9.551320434382266e-06,
"loss": 0.9548,
"step": 407
},
{
"epoch": 0.32,
"learning_rate": 9.548646888887076e-06,
"loss": 1.0605,
"step": 408
},
{
"epoch": 0.33,
"learning_rate": 9.545965778071218e-06,
"loss": 1.0158,
"step": 409
},
{
"epoch": 0.33,
"learning_rate": 9.543277106393917e-06,
"loss": 1.0951,
"step": 410
},
{
"epoch": 0.33,
"learning_rate": 9.540580878326984e-06,
"loss": 1.0614,
"step": 411
},
{
"epoch": 0.33,
"learning_rate": 9.537877098354787e-06,
"loss": 1.0521,
"step": 412
},
{
"epoch": 0.33,
"learning_rate": 9.53516577097426e-06,
"loss": 0.9205,
"step": 413
},
{
"epoch": 0.33,
"learning_rate": 9.532446900694891e-06,
"loss": 1.0189,
"step": 414
},
{
"epoch": 0.33,
"learning_rate": 9.529720492038713e-06,
"loss": 1.0282,
"step": 415
},
{
"epoch": 0.33,
"learning_rate": 9.526986549540292e-06,
"loss": 1.0467,
"step": 416
},
{
"epoch": 0.33,
"learning_rate": 9.524245077746731e-06,
"loss": 1.022,
"step": 417
},
{
"epoch": 0.33,
"learning_rate": 9.521496081217652e-06,
"loss": 1.0382,
"step": 418
},
{
"epoch": 0.33,
"learning_rate": 9.51873956452519e-06,
"loss": 0.9866,
"step": 419
},
{
"epoch": 0.33,
"learning_rate": 9.515975532253994e-06,
"loss": 0.9835,
"step": 420
},
{
"epoch": 0.34,
"learning_rate": 9.513203989001208e-06,
"loss": 1.0294,
"step": 421
},
{
"epoch": 0.34,
"learning_rate": 9.510424939376468e-06,
"loss": 0.9826,
"step": 422
},
{
"epoch": 0.34,
"learning_rate": 9.5076383880019e-06,
"loss": 1.0178,
"step": 423
},
{
"epoch": 0.34,
"learning_rate": 9.504844339512096e-06,
"loss": 0.9408,
"step": 424
},
{
"epoch": 0.34,
"learning_rate": 9.502042798554133e-06,
"loss": 1.0434,
"step": 425
},
{
"epoch": 0.34,
"learning_rate": 9.499233769787534e-06,
"loss": 0.9745,
"step": 426
},
{
"epoch": 0.34,
"learning_rate": 9.496417257884286e-06,
"loss": 0.9747,
"step": 427
},
{
"epoch": 0.34,
"learning_rate": 9.493593267528818e-06,
"loss": 0.9948,
"step": 428
},
{
"epoch": 0.34,
"learning_rate": 9.490761803417998e-06,
"loss": 0.9304,
"step": 429
},
{
"epoch": 0.34,
"learning_rate": 9.487922870261123e-06,
"loss": 1.0428,
"step": 430
},
{
"epoch": 0.34,
"learning_rate": 9.485076472779913e-06,
"loss": 1.0282,
"step": 431
},
{
"epoch": 0.34,
"learning_rate": 9.482222615708506e-06,
"loss": 1.0405,
"step": 432
},
{
"epoch": 0.34,
"learning_rate": 9.479361303793441e-06,
"loss": 1.0055,
"step": 433
},
{
"epoch": 0.35,
"learning_rate": 9.47649254179366e-06,
"loss": 1.0004,
"step": 434
},
{
"epoch": 0.35,
"learning_rate": 9.473616334480496e-06,
"loss": 0.9685,
"step": 435
},
{
"epoch": 0.35,
"learning_rate": 9.470732686637665e-06,
"loss": 1.0345,
"step": 436
},
{
"epoch": 0.35,
"learning_rate": 9.467841603061255e-06,
"loss": 1.0279,
"step": 437
},
{
"epoch": 0.35,
"learning_rate": 9.464943088559721e-06,
"loss": 0.942,
"step": 438
},
{
"epoch": 0.35,
"learning_rate": 9.462037147953886e-06,
"loss": 1.0122,
"step": 439
},
{
"epoch": 0.35,
"learning_rate": 9.459123786076911e-06,
"loss": 0.9687,
"step": 440
},
{
"epoch": 0.35,
"learning_rate": 9.456203007774312e-06,
"loss": 0.978,
"step": 441
},
{
"epoch": 0.35,
"learning_rate": 9.453274817903932e-06,
"loss": 1.026,
"step": 442
},
{
"epoch": 0.35,
"learning_rate": 9.450339221335942e-06,
"loss": 1.0437,
"step": 443
},
{
"epoch": 0.35,
"learning_rate": 9.447396222952837e-06,
"loss": 0.9844,
"step": 444
},
{
"epoch": 0.35,
"learning_rate": 9.444445827649415e-06,
"loss": 0.9842,
"step": 445
},
{
"epoch": 0.36,
"learning_rate": 9.441488040332787e-06,
"loss": 1.0356,
"step": 446
},
{
"epoch": 0.36,
"learning_rate": 9.438522865922344e-06,
"loss": 0.9665,
"step": 447
},
{
"epoch": 0.36,
"learning_rate": 9.435550309349776e-06,
"loss": 1.004,
"step": 448
},
{
"epoch": 0.36,
"learning_rate": 9.432570375559048e-06,
"loss": 1.0795,
"step": 449
},
{
"epoch": 0.36,
"learning_rate": 9.429583069506392e-06,
"loss": 1.0246,
"step": 450
},
{
"epoch": 0.36,
"learning_rate": 9.426588396160299e-06,
"loss": 1.0101,
"step": 451
},
{
"epoch": 0.36,
"learning_rate": 9.423586360501521e-06,
"loss": 1.0299,
"step": 452
},
{
"epoch": 0.36,
"learning_rate": 9.420576967523049e-06,
"loss": 1.1005,
"step": 453
},
{
"epoch": 0.36,
"learning_rate": 9.417560222230115e-06,
"loss": 0.9716,
"step": 454
},
{
"epoch": 0.36,
"learning_rate": 9.414536129640176e-06,
"loss": 1.0859,
"step": 455
},
{
"epoch": 0.36,
"learning_rate": 9.411504694782909e-06,
"loss": 1.021,
"step": 456
},
{
"epoch": 0.36,
"learning_rate": 9.408465922700207e-06,
"loss": 1.0768,
"step": 457
},
{
"epoch": 0.36,
"learning_rate": 9.40541981844616e-06,
"loss": 1.0081,
"step": 458
},
{
"epoch": 0.37,
"learning_rate": 9.402366387087057e-06,
"loss": 0.9655,
"step": 459
},
{
"epoch": 0.37,
"learning_rate": 9.399305633701372e-06,
"loss": 1.0204,
"step": 460
},
{
"epoch": 0.37,
"learning_rate": 9.396237563379761e-06,
"loss": 0.9182,
"step": 461
},
{
"epoch": 0.37,
"learning_rate": 9.393162181225041e-06,
"loss": 0.9341,
"step": 462
},
{
"epoch": 0.37,
"learning_rate": 9.3900794923522e-06,
"loss": 1.0168,
"step": 463
},
{
"epoch": 0.37,
"learning_rate": 9.38698950188837e-06,
"loss": 0.975,
"step": 464
},
{
"epoch": 0.37,
"learning_rate": 9.383892214972832e-06,
"loss": 0.9907,
"step": 465
},
{
"epoch": 0.37,
"learning_rate": 9.380787636757002e-06,
"loss": 1.0495,
"step": 466
},
{
"epoch": 0.37,
"learning_rate": 9.377675772404422e-06,
"loss": 1.0096,
"step": 467
},
{
"epoch": 0.37,
"learning_rate": 9.374556627090749e-06,
"loss": 1.0008,
"step": 468
},
{
"epoch": 0.37,
"learning_rate": 9.371430206003758e-06,
"loss": 0.999,
"step": 469
},
{
"epoch": 0.37,
"learning_rate": 9.368296514343317e-06,
"loss": 1.0286,
"step": 470
},
{
"epoch": 0.38,
"learning_rate": 9.365155557321392e-06,
"loss": 0.9907,
"step": 471
},
{
"epoch": 0.38,
"learning_rate": 9.36200734016203e-06,
"loss": 0.9684,
"step": 472
},
{
"epoch": 0.38,
"learning_rate": 9.35885186810135e-06,
"loss": 1.0258,
"step": 473
},
{
"epoch": 0.38,
"learning_rate": 9.355689146387545e-06,
"loss": 0.9621,
"step": 474
},
{
"epoch": 0.38,
"learning_rate": 9.352519180280862e-06,
"loss": 1.0117,
"step": 475
},
{
"epoch": 0.38,
"learning_rate": 9.349341975053593e-06,
"loss": 1.0217,
"step": 476
},
{
"epoch": 0.38,
"learning_rate": 9.346157535990075e-06,
"loss": 0.9566,
"step": 477
},
{
"epoch": 0.38,
"learning_rate": 9.342965868386674e-06,
"loss": 1.002,
"step": 478
},
{
"epoch": 0.38,
"learning_rate": 9.33976697755178e-06,
"loss": 1.001,
"step": 479
},
{
"epoch": 0.38,
"learning_rate": 9.336560868805799e-06,
"loss": 1.0475,
"step": 480
},
{
"epoch": 0.38,
"learning_rate": 9.333347547481136e-06,
"loss": 1.0055,
"step": 481
},
{
"epoch": 0.38,
"learning_rate": 9.330127018922195e-06,
"loss": 0.9685,
"step": 482
},
{
"epoch": 0.38,
"learning_rate": 9.326899288485366e-06,
"loss": 0.9863,
"step": 483
},
{
"epoch": 0.39,
"learning_rate": 9.32366436153902e-06,
"loss": 1.0164,
"step": 484
},
{
"epoch": 0.39,
"learning_rate": 9.320422243463496e-06,
"loss": 1.0031,
"step": 485
},
{
"epoch": 0.39,
"learning_rate": 9.31717293965109e-06,
"loss": 1.005,
"step": 486
},
{
"epoch": 0.39,
"learning_rate": 9.313916455506056e-06,
"loss": 0.9584,
"step": 487
},
{
"epoch": 0.39,
"learning_rate": 9.310652796444581e-06,
"loss": 0.8807,
"step": 488
},
{
"epoch": 0.39,
"learning_rate": 9.307381967894798e-06,
"loss": 1.0282,
"step": 489
},
{
"epoch": 0.39,
"learning_rate": 9.30410397529675e-06,
"loss": 0.9391,
"step": 490
},
{
"epoch": 0.39,
"learning_rate": 9.300818824102405e-06,
"loss": 0.9694,
"step": 491
},
{
"epoch": 0.39,
"learning_rate": 9.297526519775637e-06,
"loss": 0.9769,
"step": 492
},
{
"epoch": 0.39,
"learning_rate": 9.294227067792211e-06,
"loss": 0.9723,
"step": 493
},
{
"epoch": 0.39,
"learning_rate": 9.290920473639786e-06,
"loss": 0.9809,
"step": 494
},
{
"epoch": 0.39,
"learning_rate": 9.287606742817897e-06,
"loss": 1.0553,
"step": 495
},
{
"epoch": 0.39,
"learning_rate": 9.284285880837947e-06,
"loss": 1.0297,
"step": 496
},
{
"epoch": 0.4,
"learning_rate": 9.280957893223204e-06,
"loss": 1.0475,
"step": 497
},
{
"epoch": 0.4,
"learning_rate": 9.277622785508786e-06,
"loss": 1.0698,
"step": 498
},
{
"epoch": 0.4,
"learning_rate": 9.27428056324165e-06,
"loss": 0.977,
"step": 499
},
{
"epoch": 0.4,
"learning_rate": 9.27093123198059e-06,
"loss": 0.9679,
"step": 500
},
{
"epoch": 0.4,
"learning_rate": 9.267574797296224e-06,
"loss": 1.007,
"step": 501
},
{
"epoch": 0.4,
"learning_rate": 9.264211264770977e-06,
"loss": 1.0202,
"step": 502
},
{
"epoch": 0.4,
"learning_rate": 9.26084063999909e-06,
"loss": 0.9689,
"step": 503
},
{
"epoch": 0.4,
"learning_rate": 9.257462928586589e-06,
"loss": 0.9298,
"step": 504
},
{
"epoch": 0.4,
"learning_rate": 9.254078136151295e-06,
"loss": 1.0152,
"step": 505
},
{
"epoch": 0.4,
"learning_rate": 9.250686268322803e-06,
"loss": 1.0065,
"step": 506
},
{
"epoch": 0.4,
"learning_rate": 9.247287330742476e-06,
"loss": 0.8586,
"step": 507
},
{
"epoch": 0.4,
"learning_rate": 9.243881329063436e-06,
"loss": 0.9745,
"step": 508
},
{
"epoch": 0.41,
"learning_rate": 9.240468268950552e-06,
"loss": 1.0093,
"step": 509
},
{
"epoch": 0.41,
"learning_rate": 9.237048156080433e-06,
"loss": 1.0132,
"step": 510
},
{
"epoch": 0.41,
"learning_rate": 9.233620996141421e-06,
"loss": 1.0144,
"step": 511
},
{
"epoch": 0.41,
"learning_rate": 9.230186794833578e-06,
"loss": 0.8766,
"step": 512
},
{
"epoch": 0.41,
"learning_rate": 9.226745557868673e-06,
"loss": 1.0329,
"step": 513
},
{
"epoch": 0.41,
"learning_rate": 9.22329729097018e-06,
"loss": 1.017,
"step": 514
},
{
"epoch": 0.41,
"learning_rate": 9.219841999873266e-06,
"loss": 0.9508,
"step": 515
},
{
"epoch": 0.41,
"learning_rate": 9.216379690324782e-06,
"loss": 0.9191,
"step": 516
},
{
"epoch": 0.41,
"learning_rate": 9.212910368083246e-06,
"loss": 0.9361,
"step": 517
},
{
"epoch": 0.41,
"learning_rate": 9.209434038918845e-06,
"loss": 1.0377,
"step": 518
},
{
"epoch": 0.41,
"learning_rate": 9.205950708613418e-06,
"loss": 1.0485,
"step": 519
},
{
"epoch": 0.41,
"learning_rate": 9.202460382960449e-06,
"loss": 1.0058,
"step": 520
},
{
"epoch": 0.41,
"learning_rate": 9.198963067765055e-06,
"loss": 0.984,
"step": 521
},
{
"epoch": 0.42,
"learning_rate": 9.195458768843978e-06,
"loss": 1.0101,
"step": 522
},
{
"epoch": 0.42,
"learning_rate": 9.191947492025582e-06,
"loss": 1.0331,
"step": 523
},
{
"epoch": 0.42,
"learning_rate": 9.188429243149824e-06,
"loss": 1.0262,
"step": 524
},
{
"epoch": 0.42,
"learning_rate": 9.18490402806827e-06,
"loss": 0.9342,
"step": 525
},
{
"epoch": 0.42,
"learning_rate": 9.181371852644063e-06,
"loss": 0.9173,
"step": 526
},
{
"epoch": 0.42,
"learning_rate": 9.17783272275193e-06,
"loss": 0.998,
"step": 527
},
{
"epoch": 0.42,
"learning_rate": 9.174286644278154e-06,
"loss": 0.9776,
"step": 528
},
{
"epoch": 0.42,
"learning_rate": 9.170733623120586e-06,
"loss": 1.0258,
"step": 529
},
{
"epoch": 0.42,
"learning_rate": 9.167173665188618e-06,
"loss": 1.0333,
"step": 530
},
{
"epoch": 0.42,
"learning_rate": 9.163606776403182e-06,
"loss": 0.9464,
"step": 531
},
{
"epoch": 0.42,
"learning_rate": 9.160032962696734e-06,
"loss": 0.9419,
"step": 532
},
{
"epoch": 0.42,
"learning_rate": 9.156452230013254e-06,
"loss": 0.9048,
"step": 533
},
{
"epoch": 0.43,
"learning_rate": 9.152864584308221e-06,
"loss": 1.0164,
"step": 534
},
{
"epoch": 0.43,
"learning_rate": 9.149270031548616e-06,
"loss": 0.9177,
"step": 535
},
{
"epoch": 0.43,
"learning_rate": 9.145668577712911e-06,
"loss": 0.9351,
"step": 536
},
{
"epoch": 0.43,
"learning_rate": 9.142060228791052e-06,
"loss": 0.9808,
"step": 537
},
{
"epoch": 0.43,
"learning_rate": 9.138444990784455e-06,
"loss": 1.0187,
"step": 538
},
{
"epoch": 0.43,
"learning_rate": 9.134822869705988e-06,
"loss": 0.988,
"step": 539
},
{
"epoch": 0.43,
"learning_rate": 9.131193871579975e-06,
"loss": 0.9441,
"step": 540
},
{
"epoch": 0.43,
"learning_rate": 9.127558002442174e-06,
"loss": 1.0184,
"step": 541
},
{
"epoch": 0.43,
"learning_rate": 9.123915268339774e-06,
"loss": 1.0037,
"step": 542
},
{
"epoch": 0.43,
"learning_rate": 9.120265675331375e-06,
"loss": 1.0293,
"step": 543
},
{
"epoch": 0.43,
"learning_rate": 9.116609229486992e-06,
"loss": 0.8625,
"step": 544
},
{
"epoch": 0.43,
"learning_rate": 9.112945936888034e-06,
"loss": 0.9787,
"step": 545
},
{
"epoch": 0.43,
"learning_rate": 9.109275803627297e-06,
"loss": 0.8611,
"step": 546
},
{
"epoch": 0.44,
"learning_rate": 9.105598835808957e-06,
"loss": 0.9648,
"step": 547
},
{
"epoch": 0.44,
"learning_rate": 9.101915039548557e-06,
"loss": 1.0126,
"step": 548
},
{
"epoch": 0.44,
"learning_rate": 9.098224420972992e-06,
"loss": 0.9729,
"step": 549
},
{
"epoch": 0.44,
"learning_rate": 9.094526986220513e-06,
"loss": 1.0238,
"step": 550
},
{
"epoch": 0.44,
"learning_rate": 9.0908227414407e-06,
"loss": 0.9573,
"step": 551
},
{
"epoch": 0.44,
"learning_rate": 9.08711169279446e-06,
"loss": 1.0235,
"step": 552
},
{
"epoch": 0.44,
"learning_rate": 9.08339384645402e-06,
"loss": 0.9485,
"step": 553
},
{
"epoch": 0.44,
"learning_rate": 9.079669208602914e-06,
"loss": 0.988,
"step": 554
},
{
"epoch": 0.44,
"learning_rate": 9.075937785435964e-06,
"loss": 0.9113,
"step": 555
},
{
"epoch": 0.44,
"learning_rate": 9.072199583159285e-06,
"loss": 0.9556,
"step": 556
},
{
"epoch": 0.44,
"learning_rate": 9.068454607990265e-06,
"loss": 0.948,
"step": 557
},
{
"epoch": 0.44,
"learning_rate": 9.064702866157554e-06,
"loss": 0.9561,
"step": 558
},
{
"epoch": 0.45,
"learning_rate": 9.060944363901057e-06,
"loss": 0.9285,
"step": 559
},
{
"epoch": 0.45,
"learning_rate": 9.057179107471926e-06,
"loss": 0.9914,
"step": 560
},
{
"epoch": 0.45,
"learning_rate": 9.053407103132546e-06,
"loss": 0.902,
"step": 561
},
{
"epoch": 0.45,
"learning_rate": 9.049628357156522e-06,
"loss": 0.9552,
"step": 562
},
{
"epoch": 0.45,
"learning_rate": 9.045842875828673e-06,
"loss": 0.9575,
"step": 563
},
{
"epoch": 0.45,
"learning_rate": 9.042050665445024e-06,
"loss": 1.0739,
"step": 564
},
{
"epoch": 0.45,
"learning_rate": 9.038251732312784e-06,
"loss": 1.0014,
"step": 565
},
{
"epoch": 0.45,
"learning_rate": 9.034446082750352e-06,
"loss": 0.9041,
"step": 566
},
{
"epoch": 0.45,
"learning_rate": 9.030633723087292e-06,
"loss": 0.9235,
"step": 567
},
{
"epoch": 0.45,
"learning_rate": 9.026814659664331e-06,
"loss": 0.9725,
"step": 568
},
{
"epoch": 0.45,
"learning_rate": 9.022988898833342e-06,
"loss": 0.9593,
"step": 569
},
{
"epoch": 0.45,
"learning_rate": 9.019156446957343e-06,
"loss": 0.9728,
"step": 570
},
{
"epoch": 0.45,
"learning_rate": 9.015317310410475e-06,
"loss": 1.0154,
"step": 571
},
{
"epoch": 0.46,
"learning_rate": 9.011471495578e-06,
"loss": 0.9476,
"step": 572
},
{
"epoch": 0.46,
"learning_rate": 9.007619008856287e-06,
"loss": 1.011,
"step": 573
},
{
"epoch": 0.46,
"learning_rate": 9.003759856652803e-06,
"loss": 1.0303,
"step": 574
},
{
"epoch": 0.46,
"learning_rate": 8.999894045386096e-06,
"loss": 0.9888,
"step": 575
},
{
"epoch": 0.46,
"learning_rate": 8.996021581485795e-06,
"loss": 0.9626,
"step": 576
},
{
"epoch": 0.46,
"learning_rate": 8.992142471392592e-06,
"loss": 0.9007,
"step": 577
},
{
"epoch": 0.46,
"learning_rate": 8.988256721558228e-06,
"loss": 0.9686,
"step": 578
},
{
"epoch": 0.46,
"learning_rate": 8.984364338445499e-06,
"loss": 0.9644,
"step": 579
},
{
"epoch": 0.46,
"learning_rate": 8.98046532852822e-06,
"loss": 1.0087,
"step": 580
},
{
"epoch": 0.46,
"learning_rate": 8.976559698291237e-06,
"loss": 0.9995,
"step": 581
},
{
"epoch": 0.46,
"learning_rate": 8.972647454230401e-06,
"loss": 1.0102,
"step": 582
},
{
"epoch": 0.46,
"learning_rate": 8.96872860285257e-06,
"loss": 0.9684,
"step": 583
},
{
"epoch": 0.46,
"learning_rate": 8.964803150675583e-06,
"loss": 0.9453,
"step": 584
},
{
"epoch": 0.47,
"learning_rate": 8.960871104228266e-06,
"loss": 0.8587,
"step": 585
},
{
"epoch": 0.47,
"learning_rate": 8.956932470050405e-06,
"loss": 1.0305,
"step": 586
},
{
"epoch": 0.47,
"learning_rate": 8.952987254692746e-06,
"loss": 0.975,
"step": 587
},
{
"epoch": 0.47,
"learning_rate": 8.949035464716984e-06,
"loss": 0.9516,
"step": 588
},
{
"epoch": 0.47,
"learning_rate": 8.945077106695742e-06,
"loss": 0.9245,
"step": 589
},
{
"epoch": 0.47,
"learning_rate": 8.941112187212573e-06,
"loss": 0.9781,
"step": 590
},
{
"epoch": 0.47,
"learning_rate": 8.93714071286194e-06,
"loss": 0.9916,
"step": 591
},
{
"epoch": 0.47,
"learning_rate": 8.93316269024921e-06,
"loss": 0.9166,
"step": 592
},
{
"epoch": 0.47,
"learning_rate": 8.929178125990639e-06,
"loss": 0.9847,
"step": 593
},
{
"epoch": 0.47,
"learning_rate": 8.925187026713363e-06,
"loss": 0.9598,
"step": 594
},
{
"epoch": 0.47,
"learning_rate": 8.92118939905539e-06,
"loss": 0.9246,
"step": 595
},
{
"epoch": 0.47,
"learning_rate": 8.917185249665583e-06,
"loss": 0.9224,
"step": 596
},
{
"epoch": 0.48,
"learning_rate": 8.913174585203654e-06,
"loss": 1.0663,
"step": 597
},
{
"epoch": 0.48,
"learning_rate": 8.90915741234015e-06,
"loss": 0.8766,
"step": 598
},
{
"epoch": 0.48,
"learning_rate": 8.905133737756441e-06,
"loss": 0.9436,
"step": 599
},
{
"epoch": 0.48,
"learning_rate": 8.901103568144715e-06,
"loss": 0.9516,
"step": 600
},
{
"epoch": 0.48,
"learning_rate": 8.897066910207958e-06,
"loss": 0.9652,
"step": 601
},
{
"epoch": 0.48,
"learning_rate": 8.893023770659953e-06,
"loss": 1.0295,
"step": 602
},
{
"epoch": 0.48,
"learning_rate": 8.888974156225252e-06,
"loss": 0.9571,
"step": 603
},
{
"epoch": 0.48,
"learning_rate": 8.88491807363919e-06,
"loss": 1.0408,
"step": 604
},
{
"epoch": 0.48,
"learning_rate": 8.880855529647854e-06,
"loss": 1.0757,
"step": 605
},
{
"epoch": 0.48,
"learning_rate": 8.876786531008073e-06,
"loss": 0.9703,
"step": 606
},
{
"epoch": 0.48,
"learning_rate": 8.872711084487419e-06,
"loss": 0.9327,
"step": 607
},
{
"epoch": 0.48,
"learning_rate": 8.868629196864182e-06,
"loss": 0.9997,
"step": 608
},
{
"epoch": 0.48,
"learning_rate": 8.86454087492737e-06,
"loss": 1.0445,
"step": 609
},
{
"epoch": 0.49,
"learning_rate": 8.860446125476688e-06,
"loss": 0.9464,
"step": 610
},
{
"epoch": 0.49,
"learning_rate": 8.856344955322534e-06,
"loss": 0.98,
"step": 611
},
{
"epoch": 0.49,
"learning_rate": 8.852237371285984e-06,
"loss": 0.9653,
"step": 612
},
{
"epoch": 0.49,
"learning_rate": 8.848123380198784e-06,
"loss": 1.0405,
"step": 613
},
{
"epoch": 0.49,
"learning_rate": 8.84400298890333e-06,
"loss": 0.9658,
"step": 614
},
{
"epoch": 0.49,
"learning_rate": 8.83987620425267e-06,
"loss": 1.0248,
"step": 615
},
{
"epoch": 0.49,
"learning_rate": 8.835743033110482e-06,
"loss": 0.9848,
"step": 616
},
{
"epoch": 0.49,
"learning_rate": 8.831603482351067e-06,
"loss": 0.9764,
"step": 617
},
{
"epoch": 0.49,
"learning_rate": 8.827457558859335e-06,
"loss": 1.0505,
"step": 618
},
{
"epoch": 0.49,
"learning_rate": 8.823305269530796e-06,
"loss": 0.9721,
"step": 619
},
{
"epoch": 0.49,
"learning_rate": 8.819146621271546e-06,
"loss": 0.997,
"step": 620
},
{
"epoch": 0.49,
"learning_rate": 8.814981620998262e-06,
"loss": 0.9455,
"step": 621
},
{
"epoch": 0.5,
"learning_rate": 8.810810275638183e-06,
"loss": 1.0087,
"step": 622
},
{
"epoch": 0.5,
"learning_rate": 8.806632592129099e-06,
"loss": 0.9419,
"step": 623
},
{
"epoch": 0.5,
"learning_rate": 8.802448577419343e-06,
"loss": 1.0243,
"step": 624
},
{
"epoch": 0.5,
"learning_rate": 8.79825823846778e-06,
"loss": 0.9743,
"step": 625
},
{
"epoch": 0.5,
"learning_rate": 8.794061582243791e-06,
"loss": 1.0318,
"step": 626
},
{
"epoch": 0.5,
"learning_rate": 8.789858615727266e-06,
"loss": 0.9445,
"step": 627
},
{
"epoch": 0.5,
"learning_rate": 8.78564934590859e-06,
"loss": 0.9819,
"step": 628
},
{
"epoch": 0.5,
"learning_rate": 8.781433779788627e-06,
"loss": 0.9906,
"step": 629
},
{
"epoch": 0.5,
"learning_rate": 8.777211924378719e-06,
"loss": 0.9835,
"step": 630
},
{
"epoch": 0.5,
"learning_rate": 8.772983786700668e-06,
"loss": 0.8629,
"step": 631
},
{
"epoch": 0.5,
"learning_rate": 8.768749373786722e-06,
"loss": 0.9758,
"step": 632
},
{
"epoch": 0.5,
"learning_rate": 8.764508692679567e-06,
"loss": 0.9149,
"step": 633
},
{
"epoch": 0.5,
"learning_rate": 8.760261750432312e-06,
"loss": 0.9694,
"step": 634
},
{
"epoch": 0.51,
"learning_rate": 8.756008554108485e-06,
"loss": 0.9747,
"step": 635
},
{
"epoch": 0.51,
"learning_rate": 8.751749110782013e-06,
"loss": 1.0099,
"step": 636
},
{
"epoch": 0.51,
"learning_rate": 8.74748342753721e-06,
"loss": 0.9305,
"step": 637
},
{
"epoch": 0.51,
"learning_rate": 8.74321151146877e-06,
"loss": 1.0515,
"step": 638
},
{
"epoch": 0.51,
"learning_rate": 8.738933369681757e-06,
"loss": 0.9553,
"step": 639
},
{
"epoch": 0.51,
"learning_rate": 8.734649009291586e-06,
"loss": 0.9973,
"step": 640
},
{
"epoch": 0.51,
"learning_rate": 8.730358437424013e-06,
"loss": 0.9374,
"step": 641
},
{
"epoch": 0.51,
"learning_rate": 8.726061661215134e-06,
"loss": 0.9578,
"step": 642
},
{
"epoch": 0.51,
"learning_rate": 8.721758687811353e-06,
"loss": 0.9785,
"step": 643
},
{
"epoch": 0.51,
"learning_rate": 8.717449524369386e-06,
"loss": 0.9317,
"step": 644
},
{
"epoch": 0.51,
"learning_rate": 8.713134178056245e-06,
"loss": 1.0164,
"step": 645
},
{
"epoch": 0.51,
"learning_rate": 8.708812656049227e-06,
"loss": 0.9072,
"step": 646
},
{
"epoch": 0.52,
"learning_rate": 8.704484965535893e-06,
"loss": 0.9825,
"step": 647
},
{
"epoch": 0.52,
"learning_rate": 8.700151113714071e-06,
"loss": 0.9637,
"step": 648
},
{
"epoch": 0.52,
"learning_rate": 8.695811107791836e-06,
"loss": 1.027,
"step": 649
},
{
"epoch": 0.52,
"learning_rate": 8.691464954987494e-06,
"loss": 1.0122,
"step": 650
},
{
"epoch": 0.52,
"learning_rate": 8.687112662529577e-06,
"loss": 0.9927,
"step": 651
},
{
"epoch": 0.52,
"learning_rate": 8.68275423765683e-06,
"loss": 0.956,
"step": 652
},
{
"epoch": 0.52,
"learning_rate": 8.678389687618195e-06,
"loss": 0.9571,
"step": 653
},
{
"epoch": 0.52,
"learning_rate": 8.674019019672803e-06,
"loss": 0.9482,
"step": 654
},
{
"epoch": 0.52,
"learning_rate": 8.66964224108996e-06,
"loss": 1.0009,
"step": 655
},
{
"epoch": 0.52,
"learning_rate": 8.665259359149132e-06,
"loss": 1.0333,
"step": 656
},
{
"epoch": 0.52,
"learning_rate": 8.660870381139944e-06,
"loss": 1.026,
"step": 657
},
{
"epoch": 0.52,
"learning_rate": 8.656475314362149e-06,
"loss": 0.9684,
"step": 658
},
{
"epoch": 0.52,
"learning_rate": 8.652074166125636e-06,
"loss": 0.9523,
"step": 659
},
{
"epoch": 0.53,
"learning_rate": 8.647666943750405e-06,
"loss": 0.9551,
"step": 660
},
{
"epoch": 0.53,
"learning_rate": 8.64325365456656e-06,
"loss": 1.0712,
"step": 661
},
{
"epoch": 0.53,
"learning_rate": 8.638834305914296e-06,
"loss": 0.9544,
"step": 662
},
{
"epoch": 0.53,
"learning_rate": 8.634408905143882e-06,
"loss": 1.0169,
"step": 663
},
{
"epoch": 0.53,
"learning_rate": 8.629977459615655e-06,
"loss": 1.0655,
"step": 664
},
{
"epoch": 0.53,
"learning_rate": 8.625539976700008e-06,
"loss": 0.9983,
"step": 665
},
{
"epoch": 0.53,
"learning_rate": 8.62109646377737e-06,
"loss": 0.9529,
"step": 666
},
{
"epoch": 0.53,
"learning_rate": 8.616646928238207e-06,
"loss": 1.0483,
"step": 667
},
{
"epoch": 0.53,
"learning_rate": 8.612191377482995e-06,
"loss": 0.9576,
"step": 668
},
{
"epoch": 0.53,
"learning_rate": 8.607729818922217e-06,
"loss": 1.0571,
"step": 669
},
{
"epoch": 0.53,
"learning_rate": 8.603262259976348e-06,
"loss": 0.939,
"step": 670
},
{
"epoch": 0.53,
"learning_rate": 8.598788708075844e-06,
"loss": 0.9576,
"step": 671
},
{
"epoch": 0.54,
"learning_rate": 8.594309170661128e-06,
"loss": 0.949,
"step": 672
},
{
"epoch": 0.54,
"learning_rate": 8.589823655182577e-06,
"loss": 0.8669,
"step": 673
},
{
"epoch": 0.54,
"learning_rate": 8.58533216910051e-06,
"loss": 0.9937,
"step": 674
},
{
"epoch": 0.54,
"learning_rate": 8.580834719885178e-06,
"loss": 0.9375,
"step": 675
},
{
"epoch": 0.54,
"learning_rate": 8.576331315016753e-06,
"loss": 0.9795,
"step": 676
},
{
"epoch": 0.54,
"learning_rate": 8.571821961985304e-06,
"loss": 0.9518,
"step": 677
},
{
"epoch": 0.54,
"learning_rate": 8.567306668290801e-06,
"loss": 1.0169,
"step": 678
},
{
"epoch": 0.54,
"learning_rate": 8.562785441443092e-06,
"loss": 0.958,
"step": 679
},
{
"epoch": 0.54,
"learning_rate": 8.558258288961887e-06,
"loss": 0.9082,
"step": 680
},
{
"epoch": 0.54,
"learning_rate": 8.553725218376767e-06,
"loss": 0.9563,
"step": 681
},
{
"epoch": 0.54,
"learning_rate": 8.549186237227138e-06,
"loss": 1.0165,
"step": 682
},
{
"epoch": 0.54,
"learning_rate": 8.544641353062248e-06,
"loss": 0.9465,
"step": 683
},
{
"epoch": 0.54,
"learning_rate": 8.540090573441159e-06,
"loss": 1.004,
"step": 684
},
{
"epoch": 0.55,
"learning_rate": 8.535533905932739e-06,
"loss": 0.9116,
"step": 685
},
{
"epoch": 0.55,
"learning_rate": 8.530971358115648e-06,
"loss": 0.9643,
"step": 686
},
{
"epoch": 0.55,
"learning_rate": 8.526402937578327e-06,
"loss": 0.9792,
"step": 687
},
{
"epoch": 0.55,
"learning_rate": 8.521828651918983e-06,
"loss": 0.9597,
"step": 688
},
{
"epoch": 0.55,
"learning_rate": 8.517248508745581e-06,
"loss": 1.0267,
"step": 689
},
{
"epoch": 0.55,
"learning_rate": 8.512662515675825e-06,
"loss": 1.0214,
"step": 690
},
{
"epoch": 0.55,
"learning_rate": 8.508070680337153e-06,
"loss": 0.9209,
"step": 691
},
{
"epoch": 0.55,
"learning_rate": 8.503473010366713e-06,
"loss": 0.9817,
"step": 692
},
{
"epoch": 0.55,
"learning_rate": 8.498869513411363e-06,
"loss": 0.9649,
"step": 693
},
{
"epoch": 0.55,
"learning_rate": 8.49426019712765e-06,
"loss": 0.9583,
"step": 694
},
{
"epoch": 0.55,
"learning_rate": 8.4896450691818e-06,
"loss": 1.0142,
"step": 695
},
{
"epoch": 0.55,
"learning_rate": 8.485024137249705e-06,
"loss": 0.9303,
"step": 696
},
{
"epoch": 0.55,
"learning_rate": 8.480397409016909e-06,
"loss": 0.9241,
"step": 697
},
{
"epoch": 0.56,
"learning_rate": 8.475764892178601e-06,
"loss": 1.0448,
"step": 698
},
{
"epoch": 0.56,
"learning_rate": 8.471126594439591e-06,
"loss": 0.9126,
"step": 699
},
{
"epoch": 0.56,
"learning_rate": 8.46648252351431e-06,
"loss": 0.9227,
"step": 700
},
{
"epoch": 0.56,
"learning_rate": 8.461832687126788e-06,
"loss": 1.0116,
"step": 701
},
{
"epoch": 0.56,
"learning_rate": 8.457177093010643e-06,
"loss": 0.9347,
"step": 702
},
{
"epoch": 0.56,
"learning_rate": 8.45251574890907e-06,
"loss": 0.9106,
"step": 703
},
{
"epoch": 0.56,
"learning_rate": 8.447848662574828e-06,
"loss": 0.9415,
"step": 704
},
{
"epoch": 0.56,
"learning_rate": 8.443175841770229e-06,
"loss": 1.0284,
"step": 705
},
{
"epoch": 0.56,
"learning_rate": 8.438497294267117e-06,
"loss": 0.9701,
"step": 706
},
{
"epoch": 0.56,
"learning_rate": 8.433813027846866e-06,
"loss": 0.9301,
"step": 707
},
{
"epoch": 0.56,
"learning_rate": 8.429123050300357e-06,
"loss": 0.9845,
"step": 708
},
{
"epoch": 0.56,
"learning_rate": 8.424427369427974e-06,
"loss": 0.8639,
"step": 709
},
{
"epoch": 0.57,
"learning_rate": 8.419725993039586e-06,
"loss": 0.9965,
"step": 710
},
{
"epoch": 0.57,
"learning_rate": 8.41501892895453e-06,
"loss": 0.8618,
"step": 711
},
{
"epoch": 0.57,
"learning_rate": 8.41030618500161e-06,
"loss": 0.9514,
"step": 712
},
{
"epoch": 0.57,
"learning_rate": 8.405587769019072e-06,
"loss": 0.9172,
"step": 713
},
{
"epoch": 0.57,
"learning_rate": 8.400863688854598e-06,
"loss": 1.0158,
"step": 714
},
{
"epoch": 0.57,
"learning_rate": 8.396133952365288e-06,
"loss": 1.0166,
"step": 715
},
{
"epoch": 0.57,
"learning_rate": 8.391398567417653e-06,
"loss": 0.8894,
"step": 716
},
{
"epoch": 0.57,
"learning_rate": 8.386657541887595e-06,
"loss": 0.9929,
"step": 717
},
{
"epoch": 0.57,
"learning_rate": 8.3819108836604e-06,
"loss": 1.0236,
"step": 718
},
{
"epoch": 0.57,
"learning_rate": 8.377158600630723e-06,
"loss": 0.9707,
"step": 719
},
{
"epoch": 0.57,
"learning_rate": 8.372400700702569e-06,
"loss": 0.9814,
"step": 720
},
{
"epoch": 0.57,
"learning_rate": 8.367637191789297e-06,
"loss": 0.9425,
"step": 721
},
{
"epoch": 0.57,
"learning_rate": 8.362868081813577e-06,
"loss": 0.9752,
"step": 722
},
{
"epoch": 0.58,
"learning_rate": 8.35809337870741e-06,
"loss": 0.873,
"step": 723
},
{
"epoch": 0.58,
"learning_rate": 8.353313090412093e-06,
"loss": 0.9165,
"step": 724
},
{
"epoch": 0.58,
"learning_rate": 8.348527224878213e-06,
"loss": 0.9189,
"step": 725
},
{
"epoch": 0.58,
"learning_rate": 8.343735790065633e-06,
"loss": 0.9854,
"step": 726
},
{
"epoch": 0.58,
"learning_rate": 8.338938793943478e-06,
"loss": 1.0055,
"step": 727
},
{
"epoch": 0.58,
"learning_rate": 8.334136244490128e-06,
"loss": 0.9452,
"step": 728
},
{
"epoch": 0.58,
"learning_rate": 8.32932814969319e-06,
"loss": 0.9697,
"step": 729
},
{
"epoch": 0.58,
"learning_rate": 8.3245145175495e-06,
"loss": 0.9609,
"step": 730
},
{
"epoch": 0.58,
"learning_rate": 8.319695356065108e-06,
"loss": 0.9628,
"step": 731
},
{
"epoch": 0.58,
"learning_rate": 8.314870673255248e-06,
"loss": 1.0534,
"step": 732
},
{
"epoch": 0.58,
"learning_rate": 8.310040477144348e-06,
"loss": 1.0188,
"step": 733
},
{
"epoch": 0.58,
"learning_rate": 8.305204775766003e-06,
"loss": 1.0202,
"step": 734
},
{
"epoch": 0.59,
"learning_rate": 8.30036357716296e-06,
"loss": 0.9342,
"step": 735
},
{
"epoch": 0.59,
"learning_rate": 8.295516889387115e-06,
"loss": 0.9605,
"step": 736
},
{
"epoch": 0.59,
"learning_rate": 8.290664720499491e-06,
"loss": 0.8812,
"step": 737
},
{
"epoch": 0.59,
"learning_rate": 8.285807078570224e-06,
"loss": 0.9426,
"step": 738
},
{
"epoch": 0.59,
"learning_rate": 8.280943971678562e-06,
"loss": 0.9643,
"step": 739
},
{
"epoch": 0.59,
"learning_rate": 8.276075407912831e-06,
"loss": 0.9286,
"step": 740
},
{
"epoch": 0.59,
"learning_rate": 8.27120139537044e-06,
"loss": 1.0147,
"step": 741
},
{
"epoch": 0.59,
"learning_rate": 8.26632194215786e-06,
"loss": 0.9886,
"step": 742
},
{
"epoch": 0.59,
"learning_rate": 8.261437056390607e-06,
"loss": 1.0174,
"step": 743
},
{
"epoch": 0.59,
"learning_rate": 8.256546746193237e-06,
"loss": 1.0278,
"step": 744
},
{
"epoch": 0.59,
"learning_rate": 8.251651019699324e-06,
"loss": 0.9625,
"step": 745
},
{
"epoch": 0.59,
"learning_rate": 8.246749885051453e-06,
"loss": 0.9236,
"step": 746
},
{
"epoch": 0.59,
"learning_rate": 8.241843350401203e-06,
"loss": 0.9789,
"step": 747
},
{
"epoch": 0.6,
"learning_rate": 8.23693142390914e-06,
"loss": 0.9445,
"step": 748
},
{
"epoch": 0.6,
"learning_rate": 8.232014113744783e-06,
"loss": 0.939,
"step": 749
},
{
"epoch": 0.6,
"learning_rate": 8.22709142808662e-06,
"loss": 1.005,
"step": 750
},
{
"epoch": 0.6,
"learning_rate": 8.222163375122072e-06,
"loss": 0.9245,
"step": 751
},
{
"epoch": 0.6,
"learning_rate": 8.21722996304749e-06,
"loss": 0.9749,
"step": 752
},
{
"epoch": 0.6,
"learning_rate": 8.212291200068135e-06,
"loss": 0.9337,
"step": 753
},
{
"epoch": 0.6,
"learning_rate": 8.207347094398173e-06,
"loss": 1.0165,
"step": 754
},
{
"epoch": 0.6,
"learning_rate": 8.202397654260649e-06,
"loss": 1.0016,
"step": 755
},
{
"epoch": 0.6,
"learning_rate": 8.197442887887488e-06,
"loss": 0.9445,
"step": 756
},
{
"epoch": 0.6,
"learning_rate": 8.192482803519464e-06,
"loss": 0.9012,
"step": 757
},
{
"epoch": 0.6,
"learning_rate": 8.187517409406206e-06,
"loss": 0.968,
"step": 758
},
{
"epoch": 0.6,
"learning_rate": 8.182546713806172e-06,
"loss": 0.95,
"step": 759
},
{
"epoch": 0.61,
"learning_rate": 8.177570724986627e-06,
"loss": 0.9631,
"step": 760
},
{
"epoch": 0.61,
"learning_rate": 8.172589451223655e-06,
"loss": 1.03,
"step": 761
},
{
"epoch": 0.61,
"learning_rate": 8.167602900802121e-06,
"loss": 0.9084,
"step": 762
},
{
"epoch": 0.61,
"learning_rate": 8.162611082015665e-06,
"loss": 0.8581,
"step": 763
},
{
"epoch": 0.61,
"learning_rate": 8.157614003166695e-06,
"loss": 0.9843,
"step": 764
},
{
"epoch": 0.61,
"learning_rate": 8.152611672566363e-06,
"loss": 0.9626,
"step": 765
},
{
"epoch": 0.61,
"learning_rate": 8.14760409853456e-06,
"loss": 0.9804,
"step": 766
},
{
"epoch": 0.61,
"learning_rate": 8.142591289399895e-06,
"loss": 0.9367,
"step": 767
},
{
"epoch": 0.61,
"learning_rate": 8.137573253499683e-06,
"loss": 0.982,
"step": 768
},
{
"epoch": 0.61,
"learning_rate": 8.132549999179934e-06,
"loss": 0.943,
"step": 769
},
{
"epoch": 0.61,
"learning_rate": 8.127521534795338e-06,
"loss": 0.9657,
"step": 770
},
{
"epoch": 0.61,
"learning_rate": 8.122487868709245e-06,
"loss": 0.9541,
"step": 771
},
{
"epoch": 0.61,
"learning_rate": 8.117449009293668e-06,
"loss": 0.9622,
"step": 772
},
{
"epoch": 0.62,
"learning_rate": 8.112404964929245e-06,
"loss": 0.9335,
"step": 773
},
{
"epoch": 0.62,
"learning_rate": 8.107355744005247e-06,
"loss": 0.9842,
"step": 774
},
{
"epoch": 0.62,
"learning_rate": 8.102301354919544e-06,
"loss": 0.9534,
"step": 775
},
{
"epoch": 0.62,
"learning_rate": 8.097241806078616e-06,
"loss": 0.9584,
"step": 776
},
{
"epoch": 0.62,
"learning_rate": 8.092177105897512e-06,
"loss": 0.9604,
"step": 777
},
{
"epoch": 0.62,
"learning_rate": 8.087107262799856e-06,
"loss": 0.9336,
"step": 778
},
{
"epoch": 0.62,
"learning_rate": 8.08203228521782e-06,
"loss": 0.9532,
"step": 779
},
{
"epoch": 0.62,
"learning_rate": 8.076952181592125e-06,
"loss": 0.9256,
"step": 780
},
{
"epoch": 0.62,
"learning_rate": 8.07186696037201e-06,
"loss": 0.9901,
"step": 781
},
{
"epoch": 0.62,
"learning_rate": 8.066776630015225e-06,
"loss": 0.9293,
"step": 782
},
{
"epoch": 0.62,
"learning_rate": 8.06168119898802e-06,
"loss": 0.9688,
"step": 783
},
{
"epoch": 0.62,
"learning_rate": 8.05658067576513e-06,
"loss": 0.9245,
"step": 784
},
{
"epoch": 0.62,
"learning_rate": 8.051475068829757e-06,
"loss": 0.9827,
"step": 785
},
{
"epoch": 0.63,
"learning_rate": 8.046364386673559e-06,
"loss": 0.9309,
"step": 786
},
{
"epoch": 0.63,
"learning_rate": 8.041248637796637e-06,
"loss": 0.9588,
"step": 787
},
{
"epoch": 0.63,
"learning_rate": 8.036127830707515e-06,
"loss": 0.9682,
"step": 788
},
{
"epoch": 0.63,
"learning_rate": 8.031001973923132e-06,
"loss": 0.9561,
"step": 789
},
{
"epoch": 0.63,
"learning_rate": 8.025871075968828e-06,
"loss": 1.0204,
"step": 790
},
{
"epoch": 0.63,
"learning_rate": 8.02073514537832e-06,
"loss": 0.9321,
"step": 791
},
{
"epoch": 0.63,
"learning_rate": 8.015594190693705e-06,
"loss": 0.9826,
"step": 792
},
{
"epoch": 0.63,
"learning_rate": 8.01044822046543e-06,
"loss": 0.9558,
"step": 793
},
{
"epoch": 0.63,
"learning_rate": 8.005297243252283e-06,
"loss": 0.9384,
"step": 794
},
{
"epoch": 0.63,
"learning_rate": 8.000141267621386e-06,
"loss": 0.9344,
"step": 795
},
{
"epoch": 0.63,
"learning_rate": 7.99498030214817e-06,
"loss": 0.9229,
"step": 796
},
{
"epoch": 0.63,
"learning_rate": 7.989814355416362e-06,
"loss": 0.9628,
"step": 797
},
{
"epoch": 0.64,
"learning_rate": 7.98464343601798e-06,
"loss": 0.9263,
"step": 798
},
{
"epoch": 0.64,
"learning_rate": 7.979467552553309e-06,
"loss": 0.9304,
"step": 799
},
{
"epoch": 0.64,
"learning_rate": 7.97428671363089e-06,
"loss": 0.8755,
"step": 800
},
{
"epoch": 0.64,
"learning_rate": 7.969100927867508e-06,
"loss": 0.9722,
"step": 801
},
{
"epoch": 0.64,
"learning_rate": 7.963910203888177e-06,
"loss": 0.9208,
"step": 802
},
{
"epoch": 0.64,
"learning_rate": 7.958714550326117e-06,
"loss": 1.0001,
"step": 803
},
{
"epoch": 0.64,
"learning_rate": 7.953513975822755e-06,
"loss": 0.9704,
"step": 804
},
{
"epoch": 0.64,
"learning_rate": 7.948308489027701e-06,
"loss": 0.9419,
"step": 805
},
{
"epoch": 0.64,
"learning_rate": 7.94309809859873e-06,
"loss": 0.92,
"step": 806
},
{
"epoch": 0.64,
"learning_rate": 7.937882813201775e-06,
"loss": 1.0373,
"step": 807
},
{
"epoch": 0.64,
"learning_rate": 7.932662641510915e-06,
"loss": 0.9124,
"step": 808
},
{
"epoch": 0.64,
"learning_rate": 7.927437592208353e-06,
"loss": 0.8897,
"step": 809
},
{
"epoch": 0.64,
"learning_rate": 7.922207673984398e-06,
"loss": 1.0237,
"step": 810
},
{
"epoch": 0.65,
"learning_rate": 7.916972895537471e-06,
"loss": 0.8803,
"step": 811
},
{
"epoch": 0.65,
"learning_rate": 7.911733265574061e-06,
"loss": 0.9365,
"step": 812
},
{
"epoch": 0.65,
"learning_rate": 7.906488792808737e-06,
"loss": 0.8495,
"step": 813
},
{
"epoch": 0.65,
"learning_rate": 7.90123948596412e-06,
"loss": 1.0119,
"step": 814
},
{
"epoch": 0.65,
"learning_rate": 7.895985353770867e-06,
"loss": 0.9863,
"step": 815
},
{
"epoch": 0.65,
"learning_rate": 7.890726404967665e-06,
"loss": 0.9813,
"step": 816
},
{
"epoch": 0.65,
"learning_rate": 7.885462648301212e-06,
"loss": 0.9047,
"step": 817
},
{
"epoch": 0.65,
"learning_rate": 7.8801940925262e-06,
"loss": 0.8829,
"step": 818
},
{
"epoch": 0.65,
"learning_rate": 7.8749207464053e-06,
"loss": 0.9333,
"step": 819
},
{
"epoch": 0.65,
"learning_rate": 7.869642618709162e-06,
"loss": 0.9161,
"step": 820
},
{
"epoch": 0.65,
"learning_rate": 7.864359718216375e-06,
"loss": 0.8827,
"step": 821
},
{
"epoch": 0.65,
"learning_rate": 7.859072053713472e-06,
"loss": 0.9311,
"step": 822
},
{
"epoch": 0.66,
"learning_rate": 7.853779633994913e-06,
"loss": 0.9812,
"step": 823
},
{
"epoch": 0.66,
"learning_rate": 7.848482467863062e-06,
"loss": 0.9601,
"step": 824
},
{
"epoch": 0.66,
"learning_rate": 7.843180564128178e-06,
"loss": 0.9399,
"step": 825
},
{
"epoch": 0.66,
"learning_rate": 7.8378739316084e-06,
"loss": 0.9454,
"step": 826
},
{
"epoch": 0.66,
"learning_rate": 7.832562579129736e-06,
"loss": 1.0028,
"step": 827
},
{
"epoch": 0.66,
"learning_rate": 7.827246515526035e-06,
"loss": 0.9037,
"step": 828
},
{
"epoch": 0.66,
"learning_rate": 7.82192574963899e-06,
"loss": 0.9378,
"step": 829
},
{
"epoch": 0.66,
"learning_rate": 7.81660029031811e-06,
"loss": 0.9219,
"step": 830
},
{
"epoch": 0.66,
"learning_rate": 7.811270146420716e-06,
"loss": 0.9757,
"step": 831
},
{
"epoch": 0.66,
"learning_rate": 7.805935326811913e-06,
"loss": 0.8946,
"step": 832
},
{
"epoch": 0.66,
"learning_rate": 7.800595840364586e-06,
"loss": 0.921,
"step": 833
},
{
"epoch": 0.66,
"learning_rate": 7.795251695959385e-06,
"loss": 0.9434,
"step": 834
},
{
"epoch": 0.66,
"learning_rate": 7.789902902484701e-06,
"loss": 1.0398,
"step": 835
},
{
"epoch": 0.67,
"learning_rate": 7.78454946883666e-06,
"loss": 0.9448,
"step": 836
},
{
"epoch": 0.67,
"learning_rate": 7.779191403919108e-06,
"loss": 0.9529,
"step": 837
},
{
"epoch": 0.67,
"learning_rate": 7.773828716643592e-06,
"loss": 0.9514,
"step": 838
},
{
"epoch": 0.67,
"learning_rate": 7.768461415929344e-06,
"loss": 0.9234,
"step": 839
},
{
"epoch": 0.67,
"learning_rate": 7.763089510703276e-06,
"loss": 1.0664,
"step": 840
},
{
"epoch": 0.67,
"learning_rate": 7.757713009899949e-06,
"loss": 0.9573,
"step": 841
},
{
"epoch": 0.67,
"learning_rate": 7.752331922461579e-06,
"loss": 0.9709,
"step": 842
},
{
"epoch": 0.67,
"learning_rate": 7.746946257337996e-06,
"loss": 0.8698,
"step": 843
},
{
"epoch": 0.67,
"learning_rate": 7.741556023486655e-06,
"loss": 0.934,
"step": 844
},
{
"epoch": 0.67,
"learning_rate": 7.736161229872608e-06,
"loss": 0.9063,
"step": 845
},
{
"epoch": 0.67,
"learning_rate": 7.730761885468486e-06,
"loss": 0.8884,
"step": 846
},
{
"epoch": 0.67,
"learning_rate": 7.725357999254493e-06,
"loss": 0.9,
"step": 847
},
{
"epoch": 0.68,
"learning_rate": 7.719949580218387e-06,
"loss": 0.8779,
"step": 848
},
{
"epoch": 0.68,
"learning_rate": 7.714536637355461e-06,
"loss": 0.9516,
"step": 849
},
{
"epoch": 0.68,
"learning_rate": 7.709119179668538e-06,
"loss": 0.8764,
"step": 850
},
{
"epoch": 0.68,
"learning_rate": 7.703697216167945e-06,
"loss": 1.0554,
"step": 851
},
{
"epoch": 0.68,
"learning_rate": 7.698270755871506e-06,
"loss": 0.8845,
"step": 852
},
{
"epoch": 0.68,
"learning_rate": 7.692839807804522e-06,
"loss": 0.9281,
"step": 853
},
{
"epoch": 0.68,
"learning_rate": 7.687404380999761e-06,
"loss": 0.8501,
"step": 854
},
{
"epoch": 0.68,
"learning_rate": 7.681964484497435e-06,
"loss": 0.9133,
"step": 855
},
{
"epoch": 0.68,
"learning_rate": 7.676520127345198e-06,
"loss": 0.8862,
"step": 856
},
{
"epoch": 0.68,
"learning_rate": 7.671071318598112e-06,
"loss": 0.9157,
"step": 857
},
{
"epoch": 0.68,
"learning_rate": 7.665618067318654e-06,
"loss": 0.9264,
"step": 858
},
{
"epoch": 0.68,
"learning_rate": 7.660160382576683e-06,
"loss": 0.9418,
"step": 859
},
{
"epoch": 0.68,
"learning_rate": 7.654698273449435e-06,
"loss": 0.9436,
"step": 860
},
{
"epoch": 0.69,
"learning_rate": 7.649231749021502e-06,
"loss": 0.9358,
"step": 861
},
{
"epoch": 0.69,
"learning_rate": 7.64376081838482e-06,
"loss": 0.9155,
"step": 862
},
{
"epoch": 0.69,
"learning_rate": 7.638285490638658e-06,
"loss": 0.9185,
"step": 863
},
{
"epoch": 0.69,
"learning_rate": 7.632805774889589e-06,
"loss": 0.9843,
"step": 864
},
{
"epoch": 0.69,
"learning_rate": 7.627321680251494e-06,
"loss": 0.9591,
"step": 865
},
{
"epoch": 0.69,
"learning_rate": 7.621833215845531e-06,
"loss": 0.8885,
"step": 866
},
{
"epoch": 0.69,
"learning_rate": 7.616340390800127e-06,
"loss": 0.9289,
"step": 867
},
{
"epoch": 0.69,
"learning_rate": 7.610843214250964e-06,
"loss": 0.9757,
"step": 868
},
{
"epoch": 0.69,
"learning_rate": 7.605341695340959e-06,
"loss": 0.9703,
"step": 869
},
{
"epoch": 0.69,
"learning_rate": 7.599835843220252e-06,
"loss": 0.8989,
"step": 870
},
{
"epoch": 0.69,
"learning_rate": 7.5943256670461865e-06,
"loss": 0.9159,
"step": 871
},
{
"epoch": 0.69,
"learning_rate": 7.588811175983305e-06,
"loss": 0.8707,
"step": 872
},
{
"epoch": 0.7,
"learning_rate": 7.5832923792033195e-06,
"loss": 0.9822,
"step": 873
},
{
"epoch": 0.7,
"learning_rate": 7.57776928588511e-06,
"loss": 0.9647,
"step": 874
},
{
"epoch": 0.7,
"learning_rate": 7.572241905214695e-06,
"loss": 0.9064,
"step": 875
},
{
"epoch": 0.7,
"learning_rate": 7.5667102463852314e-06,
"loss": 0.8757,
"step": 876
},
{
"epoch": 0.7,
"learning_rate": 7.561174318596984e-06,
"loss": 0.8976,
"step": 877
},
{
"epoch": 0.7,
"learning_rate": 7.555634131057323e-06,
"loss": 0.8472,
"step": 878
},
{
"epoch": 0.7,
"learning_rate": 7.550089692980702e-06,
"loss": 0.9366,
"step": 879
},
{
"epoch": 0.7,
"learning_rate": 7.5445410135886455e-06,
"loss": 0.9412,
"step": 880
},
{
"epoch": 0.7,
"learning_rate": 7.538988102109728e-06,
"loss": 0.965,
"step": 881
},
{
"epoch": 0.7,
"learning_rate": 7.533430967779567e-06,
"loss": 1.0199,
"step": 882
},
{
"epoch": 0.7,
"learning_rate": 7.527869619840802e-06,
"loss": 0.9256,
"step": 883
},
{
"epoch": 0.7,
"learning_rate": 7.522304067543082e-06,
"loss": 0.9755,
"step": 884
},
{
"epoch": 0.7,
"learning_rate": 7.516734320143044e-06,
"loss": 0.9175,
"step": 885
},
{
"epoch": 0.71,
"learning_rate": 7.511160386904306e-06,
"loss": 0.928,
"step": 886
},
{
"epoch": 0.71,
"learning_rate": 7.505582277097449e-06,
"loss": 0.9293,
"step": 887
},
{
"epoch": 0.71,
"learning_rate": 7.500000000000001e-06,
"loss": 1.0327,
"step": 888
},
{
"epoch": 0.71,
"learning_rate": 7.494413564896414e-06,
"loss": 0.9214,
"step": 889
},
{
"epoch": 0.71,
"learning_rate": 7.488822981078063e-06,
"loss": 0.9205,
"step": 890
},
{
"epoch": 0.71,
"learning_rate": 7.483228257843222e-06,
"loss": 0.8722,
"step": 891
},
{
"epoch": 0.71,
"learning_rate": 7.477629404497048e-06,
"loss": 0.9112,
"step": 892
},
{
"epoch": 0.71,
"learning_rate": 7.4720264303515646e-06,
"loss": 0.9491,
"step": 893
},
{
"epoch": 0.71,
"learning_rate": 7.466419344725656e-06,
"loss": 0.914,
"step": 894
},
{
"epoch": 0.71,
"learning_rate": 7.4608081569450365e-06,
"loss": 0.9134,
"step": 895
},
{
"epoch": 0.71,
"learning_rate": 7.455192876342253e-06,
"loss": 0.94,
"step": 896
},
{
"epoch": 0.71,
"learning_rate": 7.4495735122566496e-06,
"loss": 0.9755,
"step": 897
},
{
"epoch": 0.71,
"learning_rate": 7.4439500740343685e-06,
"loss": 0.9057,
"step": 898
},
{
"epoch": 0.72,
"learning_rate": 7.438322571028325e-06,
"loss": 0.9776,
"step": 899
},
{
"epoch": 0.72,
"learning_rate": 7.432691012598196e-06,
"loss": 0.9298,
"step": 900
},
{
"epoch": 0.72,
"learning_rate": 7.427055408110403e-06,
"loss": 0.9292,
"step": 901
},
{
"epoch": 0.72,
"learning_rate": 7.421415766938098e-06,
"loss": 1.0008,
"step": 902
},
{
"epoch": 0.72,
"learning_rate": 7.415772098461147e-06,
"loss": 0.8985,
"step": 903
},
{
"epoch": 0.72,
"learning_rate": 7.4101244120661105e-06,
"loss": 1.0097,
"step": 904
},
{
"epoch": 0.72,
"learning_rate": 7.404472717146236e-06,
"loss": 0.9571,
"step": 905
},
{
"epoch": 0.72,
"learning_rate": 7.398817023101438e-06,
"loss": 0.9144,
"step": 906
},
{
"epoch": 0.72,
"learning_rate": 7.393157339338277e-06,
"loss": 0.9685,
"step": 907
},
{
"epoch": 0.72,
"learning_rate": 7.387493675269955e-06,
"loss": 1.0668,
"step": 908
},
{
"epoch": 0.72,
"learning_rate": 7.381826040316294e-06,
"loss": 0.9495,
"step": 909
},
{
"epoch": 0.72,
"learning_rate": 7.376154443903714e-06,
"loss": 0.8553,
"step": 910
},
{
"epoch": 0.73,
"learning_rate": 7.370478895465231e-06,
"loss": 0.9203,
"step": 911
},
{
"epoch": 0.73,
"learning_rate": 7.36479940444043e-06,
"loss": 0.992,
"step": 912
},
{
"epoch": 0.73,
"learning_rate": 7.3591159802754555e-06,
"loss": 0.9764,
"step": 913
},
{
"epoch": 0.73,
"learning_rate": 7.353428632422992e-06,
"loss": 0.9688,
"step": 914
},
{
"epoch": 0.73,
"learning_rate": 7.34773737034225e-06,
"loss": 0.9164,
"step": 915
},
{
"epoch": 0.73,
"learning_rate": 7.342042203498952e-06,
"loss": 0.8751,
"step": 916
},
{
"epoch": 0.73,
"learning_rate": 7.336343141365311e-06,
"loss": 0.8973,
"step": 917
},
{
"epoch": 0.73,
"learning_rate": 7.330640193420022e-06,
"loss": 0.9985,
"step": 918
},
{
"epoch": 0.73,
"learning_rate": 7.324933369148244e-06,
"loss": 0.9863,
"step": 919
},
{
"epoch": 0.73,
"learning_rate": 7.319222678041578e-06,
"loss": 0.9137,
"step": 920
},
{
"epoch": 0.73,
"learning_rate": 7.313508129598062e-06,
"loss": 0.9314,
"step": 921
},
{
"epoch": 0.73,
"learning_rate": 7.307789733322146e-06,
"loss": 0.9262,
"step": 922
},
{
"epoch": 0.73,
"learning_rate": 7.302067498724681e-06,
"loss": 0.9756,
"step": 923
},
{
"epoch": 0.74,
"learning_rate": 7.2963414353229e-06,
"loss": 0.9765,
"step": 924
},
{
"epoch": 0.74,
"learning_rate": 7.29061155264041e-06,
"loss": 0.9518,
"step": 925
},
{
"epoch": 0.74,
"learning_rate": 7.28487786020716e-06,
"loss": 0.919,
"step": 926
},
{
"epoch": 0.74,
"learning_rate": 7.2791403675594465e-06,
"loss": 0.9294,
"step": 927
},
{
"epoch": 0.74,
"learning_rate": 7.273399084239878e-06,
"loss": 0.8459,
"step": 928
},
{
"epoch": 0.74,
"learning_rate": 7.267654019797373e-06,
"loss": 0.9585,
"step": 929
},
{
"epoch": 0.74,
"learning_rate": 7.261905183787136e-06,
"loss": 0.9393,
"step": 930
},
{
"epoch": 0.74,
"learning_rate": 7.256152585770644e-06,
"loss": 0.9567,
"step": 931
},
{
"epoch": 0.74,
"learning_rate": 7.250396235315634e-06,
"loss": 0.9386,
"step": 932
},
{
"epoch": 0.74,
"learning_rate": 7.244636141996083e-06,
"loss": 0.9159,
"step": 933
},
{
"epoch": 0.74,
"learning_rate": 7.238872315392189e-06,
"loss": 0.9589,
"step": 934
},
{
"epoch": 0.74,
"learning_rate": 7.233104765090365e-06,
"loss": 0.8355,
"step": 935
},
{
"epoch": 0.75,
"learning_rate": 7.2273335006832144e-06,
"loss": 0.9921,
"step": 936
},
{
"epoch": 0.75,
"learning_rate": 7.221558531769519e-06,
"loss": 0.9954,
"step": 937
},
{
"epoch": 0.75,
"learning_rate": 7.215779867954219e-06,
"loss": 0.956,
"step": 938
},
{
"epoch": 0.75,
"learning_rate": 7.2099975188484036e-06,
"loss": 0.9303,
"step": 939
},
{
"epoch": 0.75,
"learning_rate": 7.204211494069292e-06,
"loss": 0.9707,
"step": 940
},
{
"epoch": 0.75,
"learning_rate": 7.198421803240212e-06,
"loss": 0.9236,
"step": 941
},
{
"epoch": 0.75,
"learning_rate": 7.192628455990592e-06,
"loss": 0.8074,
"step": 942
},
{
"epoch": 0.75,
"learning_rate": 7.186831461955943e-06,
"loss": 0.8876,
"step": 943
},
{
"epoch": 0.75,
"learning_rate": 7.181030830777838e-06,
"loss": 0.935,
"step": 944
},
{
"epoch": 0.75,
"learning_rate": 7.175226572103902e-06,
"loss": 0.8765,
"step": 945
},
{
"epoch": 0.75,
"learning_rate": 7.169418695587791e-06,
"loss": 0.9171,
"step": 946
},
{
"epoch": 0.75,
"learning_rate": 7.163607210889182e-06,
"loss": 0.8807,
"step": 947
},
{
"epoch": 0.75,
"learning_rate": 7.157792127673747e-06,
"loss": 0.9335,
"step": 948
},
{
"epoch": 0.76,
"learning_rate": 7.1519734556131505e-06,
"loss": 0.9485,
"step": 949
},
{
"epoch": 0.76,
"learning_rate": 7.146151204385019e-06,
"loss": 0.947,
"step": 950
},
{
"epoch": 0.76,
"learning_rate": 7.140325383672938e-06,
"loss": 0.8895,
"step": 951
},
{
"epoch": 0.76,
"learning_rate": 7.134496003166423e-06,
"loss": 0.897,
"step": 952
},
{
"epoch": 0.76,
"learning_rate": 7.128663072560917e-06,
"loss": 0.8937,
"step": 953
},
{
"epoch": 0.76,
"learning_rate": 7.1228266015577645e-06,
"loss": 0.9605,
"step": 954
},
{
"epoch": 0.76,
"learning_rate": 7.116986599864197e-06,
"loss": 0.9326,
"step": 955
},
{
"epoch": 0.76,
"learning_rate": 7.111143077193321e-06,
"loss": 0.908,
"step": 956
},
{
"epoch": 0.76,
"learning_rate": 7.105296043264096e-06,
"loss": 0.917,
"step": 957
},
{
"epoch": 0.76,
"learning_rate": 7.099445507801324e-06,
"loss": 0.9042,
"step": 958
},
{
"epoch": 0.76,
"learning_rate": 7.093591480535631e-06,
"loss": 0.9203,
"step": 959
},
{
"epoch": 0.76,
"learning_rate": 7.087733971203448e-06,
"loss": 0.9306,
"step": 960
},
{
"epoch": 0.77,
"learning_rate": 7.081872989546999e-06,
"loss": 0.9433,
"step": 961
},
{
"epoch": 0.77,
"learning_rate": 7.076008545314284e-06,
"loss": 0.9931,
"step": 962
},
{
"epoch": 0.77,
"learning_rate": 7.0701406482590595e-06,
"loss": 0.871,
"step": 963
},
{
"epoch": 0.77,
"learning_rate": 7.06426930814083e-06,
"loss": 0.9224,
"step": 964
},
{
"epoch": 0.77,
"learning_rate": 7.058394534724819e-06,
"loss": 0.8956,
"step": 965
},
{
"epoch": 0.77,
"learning_rate": 7.052516337781964e-06,
"loss": 0.8891,
"step": 966
},
{
"epoch": 0.77,
"learning_rate": 7.046634727088898e-06,
"loss": 0.977,
"step": 967
},
{
"epoch": 0.77,
"learning_rate": 7.040749712427932e-06,
"loss": 0.9069,
"step": 968
},
{
"epoch": 0.77,
"learning_rate": 7.034861303587034e-06,
"loss": 0.9459,
"step": 969
},
{
"epoch": 0.77,
"learning_rate": 7.028969510359821e-06,
"loss": 0.9447,
"step": 970
},
{
"epoch": 0.77,
"learning_rate": 7.0230743425455375e-06,
"loss": 0.9804,
"step": 971
},
{
"epoch": 0.77,
"learning_rate": 7.017175809949044e-06,
"loss": 1.0003,
"step": 972
},
{
"epoch": 0.77,
"learning_rate": 7.011273922380789e-06,
"loss": 0.985,
"step": 973
},
{
"epoch": 0.78,
"learning_rate": 7.005368689656811e-06,
"loss": 0.9482,
"step": 974
},
{
"epoch": 0.78,
"learning_rate": 6.999460121598704e-06,
"loss": 1.0002,
"step": 975
},
{
"epoch": 0.78,
"learning_rate": 6.993548228033618e-06,
"loss": 0.9105,
"step": 976
},
{
"epoch": 0.78,
"learning_rate": 6.987633018794225e-06,
"loss": 0.9659,
"step": 977
},
{
"epoch": 0.78,
"learning_rate": 6.981714503718715e-06,
"loss": 0.8686,
"step": 978
},
{
"epoch": 0.78,
"learning_rate": 6.975792692650778e-06,
"loss": 0.9836,
"step": 979
},
{
"epoch": 0.78,
"learning_rate": 6.969867595439586e-06,
"loss": 0.9405,
"step": 980
},
{
"epoch": 0.78,
"learning_rate": 6.963939221939773e-06,
"loss": 0.9308,
"step": 981
},
{
"epoch": 0.78,
"learning_rate": 6.9580075820114255e-06,
"loss": 1.0028,
"step": 982
},
{
"epoch": 0.78,
"learning_rate": 6.952072685520062e-06,
"loss": 1.0094,
"step": 983
},
{
"epoch": 0.78,
"learning_rate": 6.946134542336615e-06,
"loss": 0.8799,
"step": 984
},
{
"epoch": 0.78,
"learning_rate": 6.940193162337421e-06,
"loss": 0.9199,
"step": 985
},
{
"epoch": 0.79,
"learning_rate": 6.934248555404197e-06,
"loss": 1.0061,
"step": 986
},
{
"epoch": 0.79,
"learning_rate": 6.928300731424028e-06,
"loss": 0.9179,
"step": 987
},
{
"epoch": 0.79,
"learning_rate": 6.922349700289348e-06,
"loss": 0.8848,
"step": 988
},
{
"epoch": 0.79,
"learning_rate": 6.916395471897928e-06,
"loss": 0.9381,
"step": 989
},
{
"epoch": 0.79,
"learning_rate": 6.910438056152857e-06,
"loss": 0.8307,
"step": 990
},
{
"epoch": 0.79,
"learning_rate": 6.904477462962521e-06,
"loss": 0.8958,
"step": 991
},
{
"epoch": 0.79,
"learning_rate": 6.898513702240592e-06,
"loss": 1.0148,
"step": 992
},
{
"epoch": 0.79,
"learning_rate": 6.892546783906016e-06,
"loss": 0.9053,
"step": 993
},
{
"epoch": 0.79,
"learning_rate": 6.886576717882982e-06,
"loss": 0.9437,
"step": 994
},
{
"epoch": 0.79,
"learning_rate": 6.880603514100921e-06,
"loss": 0.9596,
"step": 995
},
{
"epoch": 0.79,
"learning_rate": 6.8746271824944774e-06,
"loss": 0.848,
"step": 996
},
{
"epoch": 0.79,
"learning_rate": 6.8686477330035025e-06,
"loss": 0.8931,
"step": 997
},
{
"epoch": 0.79,
"learning_rate": 6.862665175573033e-06,
"loss": 0.9898,
"step": 998
},
{
"epoch": 0.8,
"learning_rate": 6.856679520153271e-06,
"loss": 0.95,
"step": 999
},
{
"epoch": 0.8,
"learning_rate": 6.850690776699574e-06,
"loss": 0.9234,
"step": 1000
},
{
"epoch": 0.8,
"learning_rate": 6.844698955172432e-06,
"loss": 0.9853,
"step": 1001
},
{
"epoch": 0.8,
"learning_rate": 6.838704065537461e-06,
"loss": 0.9687,
"step": 1002
},
{
"epoch": 0.8,
"learning_rate": 6.8327061177653755e-06,
"loss": 0.9596,
"step": 1003
},
{
"epoch": 0.8,
"learning_rate": 6.8267051218319766e-06,
"loss": 0.96,
"step": 1004
},
{
"epoch": 0.8,
"learning_rate": 6.820701087718135e-06,
"loss": 0.9805,
"step": 1005
},
{
"epoch": 0.8,
"learning_rate": 6.814694025409773e-06,
"loss": 0.9105,
"step": 1006
},
{
"epoch": 0.8,
"learning_rate": 6.808683944897856e-06,
"loss": 0.9411,
"step": 1007
},
{
"epoch": 0.8,
"learning_rate": 6.802670856178362e-06,
"loss": 0.8915,
"step": 1008
},
{
"epoch": 0.8,
"learning_rate": 6.796654769252275e-06,
"loss": 0.9779,
"step": 1009
},
{
"epoch": 0.8,
"learning_rate": 6.790635694125565e-06,
"loss": 0.8997,
"step": 1010
},
{
"epoch": 0.8,
"learning_rate": 6.784613640809172e-06,
"loss": 0.8871,
"step": 1011
},
{
"epoch": 0.81,
"learning_rate": 6.7785886193189936e-06,
"loss": 0.9228,
"step": 1012
},
{
"epoch": 0.81,
"learning_rate": 6.772560639675856e-06,
"loss": 0.8715,
"step": 1013
},
{
"epoch": 0.81,
"learning_rate": 6.766529711905513e-06,
"loss": 0.9903,
"step": 1014
},
{
"epoch": 0.81,
"learning_rate": 6.760495846038615e-06,
"loss": 0.9143,
"step": 1015
},
{
"epoch": 0.81,
"learning_rate": 6.754459052110707e-06,
"loss": 0.9244,
"step": 1016
},
{
"epoch": 0.81,
"learning_rate": 6.748419340162196e-06,
"loss": 0.9183,
"step": 1017
},
{
"epoch": 0.81,
"learning_rate": 6.742376720238346e-06,
"loss": 0.8995,
"step": 1018
},
{
"epoch": 0.81,
"learning_rate": 6.736331202389258e-06,
"loss": 0.9758,
"step": 1019
},
{
"epoch": 0.81,
"learning_rate": 6.730282796669853e-06,
"loss": 0.9087,
"step": 1020
},
{
"epoch": 0.81,
"learning_rate": 6.724231513139853e-06,
"loss": 0.962,
"step": 1021
},
{
"epoch": 0.81,
"learning_rate": 6.718177361863768e-06,
"loss": 0.8679,
"step": 1022
},
{
"epoch": 0.81,
"learning_rate": 6.712120352910877e-06,
"loss": 0.8923,
"step": 1023
},
{
"epoch": 0.82,
"learning_rate": 6.7060604963552125e-06,
"loss": 0.9082,
"step": 1024
},
{
"epoch": 0.82,
"learning_rate": 6.699997802275544e-06,
"loss": 0.9333,
"step": 1025
},
{
"epoch": 0.82,
"learning_rate": 6.693932280755357e-06,
"loss": 0.9202,
"step": 1026
},
{
"epoch": 0.82,
"learning_rate": 6.687863941882842e-06,
"loss": 0.9046,
"step": 1027
},
{
"epoch": 0.82,
"learning_rate": 6.681792795750876e-06,
"loss": 0.942,
"step": 1028
},
{
"epoch": 0.82,
"learning_rate": 6.675718852457005e-06,
"loss": 0.8929,
"step": 1029
},
{
"epoch": 0.82,
"learning_rate": 6.669642122103423e-06,
"loss": 1.0093,
"step": 1030
},
{
"epoch": 0.82,
"learning_rate": 6.663562614796969e-06,
"loss": 0.839,
"step": 1031
},
{
"epoch": 0.82,
"learning_rate": 6.657480340649088e-06,
"loss": 0.9226,
"step": 1032
},
{
"epoch": 0.82,
"learning_rate": 6.651395309775837e-06,
"loss": 0.9413,
"step": 1033
},
{
"epoch": 0.82,
"learning_rate": 6.645307532297851e-06,
"loss": 0.8776,
"step": 1034
},
{
"epoch": 0.82,
"learning_rate": 6.639217018340342e-06,
"loss": 0.8646,
"step": 1035
},
{
"epoch": 0.82,
"learning_rate": 6.633123778033061e-06,
"loss": 0.9316,
"step": 1036
},
{
"epoch": 0.83,
"learning_rate": 6.6270278215103054e-06,
"loss": 0.8989,
"step": 1037
},
{
"epoch": 0.83,
"learning_rate": 6.620929158910884e-06,
"loss": 0.9424,
"step": 1038
},
{
"epoch": 0.83,
"learning_rate": 6.614827800378108e-06,
"loss": 0.8276,
"step": 1039
},
{
"epoch": 0.83,
"learning_rate": 6.608723756059768e-06,
"loss": 0.9241,
"step": 1040
},
{
"epoch": 0.83,
"learning_rate": 6.602617036108128e-06,
"loss": 0.9257,
"step": 1041
},
{
"epoch": 0.83,
"learning_rate": 6.5965076506799e-06,
"loss": 0.9541,
"step": 1042
},
{
"epoch": 0.83,
"learning_rate": 6.59039560993623e-06,
"loss": 0.9079,
"step": 1043
},
{
"epoch": 0.83,
"learning_rate": 6.5842809240426765e-06,
"loss": 0.8319,
"step": 1044
},
{
"epoch": 0.83,
"learning_rate": 6.578163603169202e-06,
"loss": 0.9597,
"step": 1045
},
{
"epoch": 0.83,
"learning_rate": 6.572043657490148e-06,
"loss": 0.8797,
"step": 1046
},
{
"epoch": 0.83,
"learning_rate": 6.565921097184226e-06,
"loss": 0.9193,
"step": 1047
},
{
"epoch": 0.83,
"learning_rate": 6.559795932434489e-06,
"loss": 0.9378,
"step": 1048
},
{
"epoch": 0.84,
"learning_rate": 6.553668173428329e-06,
"loss": 0.9196,
"step": 1049
},
{
"epoch": 0.84,
"learning_rate": 6.54753783035745e-06,
"loss": 0.8252,
"step": 1050
},
{
"epoch": 0.84,
"learning_rate": 6.541404913417853e-06,
"loss": 0.9413,
"step": 1051
},
{
"epoch": 0.84,
"learning_rate": 6.535269432809821e-06,
"loss": 0.8502,
"step": 1052
},
{
"epoch": 0.84,
"learning_rate": 6.5291313987379e-06,
"loss": 0.9641,
"step": 1053
},
{
"epoch": 0.84,
"learning_rate": 6.522990821410881e-06,
"loss": 1.0134,
"step": 1054
},
{
"epoch": 0.84,
"learning_rate": 6.516847711041792e-06,
"loss": 0.9184,
"step": 1055
},
{
"epoch": 0.84,
"learning_rate": 6.510702077847864e-06,
"loss": 1.0006,
"step": 1056
},
{
"epoch": 0.84,
"learning_rate": 6.5045539320505345e-06,
"loss": 0.9518,
"step": 1057
},
{
"epoch": 0.84,
"learning_rate": 6.498403283875411e-06,
"loss": 0.876,
"step": 1058
},
{
"epoch": 0.84,
"learning_rate": 6.492250143552267e-06,
"loss": 0.8996,
"step": 1059
},
{
"epoch": 0.84,
"learning_rate": 6.486094521315022e-06,
"loss": 0.8945,
"step": 1060
},
{
"epoch": 0.84,
"learning_rate": 6.479936427401722e-06,
"loss": 0.9358,
"step": 1061
},
{
"epoch": 0.85,
"learning_rate": 6.473775872054522e-06,
"loss": 1.0191,
"step": 1062
},
{
"epoch": 0.85,
"learning_rate": 6.467612865519674e-06,
"loss": 0.9325,
"step": 1063
},
{
"epoch": 0.85,
"learning_rate": 6.461447418047506e-06,
"loss": 0.9144,
"step": 1064
},
{
"epoch": 0.85,
"learning_rate": 6.455279539892407e-06,
"loss": 0.9047,
"step": 1065
},
{
"epoch": 0.85,
"learning_rate": 6.449109241312803e-06,
"loss": 0.9676,
"step": 1066
},
{
"epoch": 0.85,
"learning_rate": 6.4429365325711515e-06,
"loss": 0.8912,
"step": 1067
},
{
"epoch": 0.85,
"learning_rate": 6.4367614239339185e-06,
"loss": 0.9312,
"step": 1068
},
{
"epoch": 0.85,
"learning_rate": 6.430583925671558e-06,
"loss": 0.9417,
"step": 1069
},
{
"epoch": 0.85,
"learning_rate": 6.424404048058501e-06,
"loss": 0.9649,
"step": 1070
},
{
"epoch": 0.85,
"learning_rate": 6.4182218013731345e-06,
"loss": 1.0194,
"step": 1071
},
{
"epoch": 0.85,
"learning_rate": 6.412037195897786e-06,
"loss": 0.8995,
"step": 1072
},
{
"epoch": 0.85,
"learning_rate": 6.405850241918707e-06,
"loss": 0.9153,
"step": 1073
},
{
"epoch": 0.86,
"learning_rate": 6.399660949726058e-06,
"loss": 0.8852,
"step": 1074
},
{
"epoch": 0.86,
"learning_rate": 6.393469329613879e-06,
"loss": 0.8692,
"step": 1075
},
{
"epoch": 0.86,
"learning_rate": 6.387275391880091e-06,
"loss": 0.9361,
"step": 1076
},
{
"epoch": 0.86,
"learning_rate": 6.3810791468264654e-06,
"loss": 0.9782,
"step": 1077
},
{
"epoch": 0.86,
"learning_rate": 6.3748806047586155e-06,
"loss": 0.8515,
"step": 1078
},
{
"epoch": 0.86,
"learning_rate": 6.368679775985966e-06,
"loss": 0.9394,
"step": 1079
},
{
"epoch": 0.86,
"learning_rate": 6.362476670821755e-06,
"loss": 0.9521,
"step": 1080
},
{
"epoch": 0.86,
"learning_rate": 6.356271299582999e-06,
"loss": 0.9828,
"step": 1081
},
{
"epoch": 0.86,
"learning_rate": 6.35006367259049e-06,
"loss": 0.8822,
"step": 1082
},
{
"epoch": 0.86,
"learning_rate": 6.343853800168767e-06,
"loss": 0.9339,
"step": 1083
},
{
"epoch": 0.86,
"learning_rate": 6.337641692646106e-06,
"loss": 0.8646,
"step": 1084
},
{
"epoch": 0.86,
"learning_rate": 6.331427360354495e-06,
"loss": 0.934,
"step": 1085
},
{
"epoch": 0.86,
"learning_rate": 6.325210813629632e-06,
"loss": 0.9504,
"step": 1086
},
{
"epoch": 0.87,
"learning_rate": 6.318992062810891e-06,
"loss": 0.9878,
"step": 1087
},
{
"epoch": 0.87,
"learning_rate": 6.312771118241314e-06,
"loss": 0.9683,
"step": 1088
},
{
"epoch": 0.87,
"learning_rate": 6.30654799026759e-06,
"loss": 0.8836,
"step": 1089
},
{
"epoch": 0.87,
"learning_rate": 6.300322689240042e-06,
"loss": 0.8702,
"step": 1090
},
{
"epoch": 0.87,
"learning_rate": 6.294095225512604e-06,
"loss": 0.9722,
"step": 1091
},
{
"epoch": 0.87,
"learning_rate": 6.287865609442812e-06,
"loss": 0.9279,
"step": 1092
},
{
"epoch": 0.87,
"learning_rate": 6.2816338513917775e-06,
"loss": 0.9317,
"step": 1093
},
{
"epoch": 0.87,
"learning_rate": 6.275399961724174e-06,
"loss": 0.9745,
"step": 1094
},
{
"epoch": 0.87,
"learning_rate": 6.2691639508082235e-06,
"loss": 0.9059,
"step": 1095
},
{
"epoch": 0.87,
"learning_rate": 6.262925829015675e-06,
"loss": 0.931,
"step": 1096
},
{
"epoch": 0.87,
"learning_rate": 6.256685606721788e-06,
"loss": 0.9687,
"step": 1097
},
{
"epoch": 0.87,
"learning_rate": 6.250443294305315e-06,
"loss": 0.8957,
"step": 1098
},
{
"epoch": 0.88,
"learning_rate": 6.2441989021484865e-06,
"loss": 0.9165,
"step": 1099
},
{
"epoch": 0.88,
"learning_rate": 6.23795244063699e-06,
"loss": 0.863,
"step": 1100
},
{
"epoch": 0.88,
"learning_rate": 6.2317039201599535e-06,
"loss": 0.9528,
"step": 1101
},
{
"epoch": 0.88,
"learning_rate": 6.2254533511099345e-06,
"loss": 0.9155,
"step": 1102
},
{
"epoch": 0.88,
"learning_rate": 6.219200743882894e-06,
"loss": 0.9798,
"step": 1103
},
{
"epoch": 0.88,
"learning_rate": 6.212946108878185e-06,
"loss": 0.8869,
"step": 1104
},
{
"epoch": 0.88,
"learning_rate": 6.206689456498529e-06,
"loss": 0.8526,
"step": 1105
},
{
"epoch": 0.88,
"learning_rate": 6.200430797150008e-06,
"loss": 0.91,
"step": 1106
},
{
"epoch": 0.88,
"learning_rate": 6.194170141242036e-06,
"loss": 0.8831,
"step": 1107
},
{
"epoch": 0.88,
"learning_rate": 6.187907499187357e-06,
"loss": 0.8326,
"step": 1108
},
{
"epoch": 0.88,
"learning_rate": 6.181642881402008e-06,
"loss": 0.9433,
"step": 1109
},
{
"epoch": 0.88,
"learning_rate": 6.1753762983053185e-06,
"loss": 0.9686,
"step": 1110
},
{
"epoch": 0.88,
"learning_rate": 6.169107760319885e-06,
"loss": 0.9517,
"step": 1111
},
{
"epoch": 0.89,
"learning_rate": 6.162837277871553e-06,
"loss": 0.9198,
"step": 1112
},
{
"epoch": 0.89,
"learning_rate": 6.156564861389407e-06,
"loss": 0.9522,
"step": 1113
},
{
"epoch": 0.89,
"learning_rate": 6.150290521305746e-06,
"loss": 0.9259,
"step": 1114
},
{
"epoch": 0.89,
"learning_rate": 6.144014268056065e-06,
"loss": 0.9114,
"step": 1115
},
{
"epoch": 0.89,
"learning_rate": 6.1377361120790445e-06,
"loss": 0.8806,
"step": 1116
},
{
"epoch": 0.89,
"learning_rate": 6.131456063816531e-06,
"loss": 0.9392,
"step": 1117
},
{
"epoch": 0.89,
"learning_rate": 6.1251741337135155e-06,
"loss": 0.9938,
"step": 1118
},
{
"epoch": 0.89,
"learning_rate": 6.118890332218117e-06,
"loss": 0.882,
"step": 1119
},
{
"epoch": 0.89,
"learning_rate": 6.112604669781572e-06,
"loss": 0.9548,
"step": 1120
},
{
"epoch": 0.89,
"learning_rate": 6.10631715685821e-06,
"loss": 0.9481,
"step": 1121
},
{
"epoch": 0.89,
"learning_rate": 6.100027803905437e-06,
"loss": 0.8668,
"step": 1122
},
{
"epoch": 0.89,
"learning_rate": 6.0937366213837216e-06,
"loss": 0.9188,
"step": 1123
},
{
"epoch": 0.89,
"learning_rate": 6.08744361975657e-06,
"loss": 0.9269,
"step": 1124
},
{
"epoch": 0.9,
"learning_rate": 6.081148809490522e-06,
"loss": 0.871,
"step": 1125
},
{
"epoch": 0.9,
"learning_rate": 6.074852201055121e-06,
"loss": 0.8839,
"step": 1126
},
{
"epoch": 0.9,
"learning_rate": 6.068553804922901e-06,
"loss": 0.8696,
"step": 1127
},
{
"epoch": 0.9,
"learning_rate": 6.062253631569368e-06,
"loss": 0.9151,
"step": 1128
},
{
"epoch": 0.9,
"learning_rate": 6.055951691472989e-06,
"loss": 0.8892,
"step": 1129
},
{
"epoch": 0.9,
"learning_rate": 6.0496479951151645e-06,
"loss": 0.9579,
"step": 1130
},
{
"epoch": 0.9,
"learning_rate": 6.043342552980218e-06,
"loss": 0.9824,
"step": 1131
},
{
"epoch": 0.9,
"learning_rate": 6.037035375555376e-06,
"loss": 0.9618,
"step": 1132
},
{
"epoch": 0.9,
"learning_rate": 6.0307264733307515e-06,
"loss": 0.9329,
"step": 1133
},
{
"epoch": 0.9,
"learning_rate": 6.024415856799327e-06,
"loss": 0.8678,
"step": 1134
},
{
"epoch": 0.9,
"learning_rate": 6.018103536456936e-06,
"loss": 0.9659,
"step": 1135
},
{
"epoch": 0.9,
"learning_rate": 6.011789522802242e-06,
"loss": 0.9619,
"step": 1136
},
{
"epoch": 0.91,
"learning_rate": 6.005473826336733e-06,
"loss": 1.0153,
"step": 1137
},
{
"epoch": 0.91,
"learning_rate": 5.9991564575646855e-06,
"loss": 0.853,
"step": 1138
},
{
"epoch": 0.91,
"learning_rate": 5.992837426993167e-06,
"loss": 0.8995,
"step": 1139
},
{
"epoch": 0.91,
"learning_rate": 5.986516745132e-06,
"loss": 0.8912,
"step": 1140
},
{
"epoch": 0.91,
"learning_rate": 5.9801944224937645e-06,
"loss": 0.9225,
"step": 1141
},
{
"epoch": 0.91,
"learning_rate": 5.973870469593757e-06,
"loss": 0.9412,
"step": 1142
},
{
"epoch": 0.91,
"learning_rate": 5.967544896949995e-06,
"loss": 0.988,
"step": 1143
},
{
"epoch": 0.91,
"learning_rate": 5.961217715083185e-06,
"loss": 0.8921,
"step": 1144
},
{
"epoch": 0.91,
"learning_rate": 5.954888934516712e-06,
"loss": 0.8698,
"step": 1145
},
{
"epoch": 0.91,
"learning_rate": 5.9485585657766196e-06,
"loss": 0.8876,
"step": 1146
},
{
"epoch": 0.91,
"learning_rate": 5.942226619391592e-06,
"loss": 0.9192,
"step": 1147
},
{
"epoch": 0.91,
"learning_rate": 5.935893105892938e-06,
"loss": 0.9613,
"step": 1148
},
{
"epoch": 0.91,
"learning_rate": 5.929558035814574e-06,
"loss": 0.9458,
"step": 1149
},
{
"epoch": 0.92,
"learning_rate": 5.923221419693002e-06,
"loss": 0.9128,
"step": 1150
},
{
"epoch": 0.92,
"learning_rate": 5.916883268067298e-06,
"loss": 0.9055,
"step": 1151
},
{
"epoch": 0.92,
"learning_rate": 5.9105435914790935e-06,
"loss": 0.933,
"step": 1152
},
{
"epoch": 0.92,
"learning_rate": 5.904202400472553e-06,
"loss": 0.9982,
"step": 1153
},
{
"epoch": 0.92,
"learning_rate": 5.8978597055943585e-06,
"loss": 0.9179,
"step": 1154
},
{
"epoch": 0.92,
"learning_rate": 5.891515517393699e-06,
"loss": 0.8633,
"step": 1155
},
{
"epoch": 0.92,
"learning_rate": 5.885169846422242e-06,
"loss": 0.9462,
"step": 1156
},
{
"epoch": 0.92,
"learning_rate": 5.878822703234125e-06,
"loss": 0.9273,
"step": 1157
},
{
"epoch": 0.92,
"learning_rate": 5.872474098385929e-06,
"loss": 0.9906,
"step": 1158
},
{
"epoch": 0.92,
"learning_rate": 5.866124042436674e-06,
"loss": 0.9052,
"step": 1159
},
{
"epoch": 0.92,
"learning_rate": 5.859772545947782e-06,
"loss": 0.8482,
"step": 1160
},
{
"epoch": 0.92,
"learning_rate": 5.853419619483083e-06,
"loss": 0.9119,
"step": 1161
},
{
"epoch": 0.93,
"learning_rate": 5.847065273608777e-06,
"loss": 0.9303,
"step": 1162
},
{
"epoch": 0.93,
"learning_rate": 5.840709518893431e-06,
"loss": 0.9131,
"step": 1163
},
{
"epoch": 0.93,
"learning_rate": 5.834352365907946e-06,
"loss": 0.9129,
"step": 1164
},
{
"epoch": 0.93,
"learning_rate": 5.8279938252255605e-06,
"loss": 0.8941,
"step": 1165
},
{
"epoch": 0.93,
"learning_rate": 5.821633907421812e-06,
"loss": 0.8972,
"step": 1166
},
{
"epoch": 0.93,
"learning_rate": 5.8152726230745325e-06,
"loss": 0.9263,
"step": 1167
},
{
"epoch": 0.93,
"learning_rate": 5.808909982763825e-06,
"loss": 0.989,
"step": 1168
},
{
"epoch": 0.93,
"learning_rate": 5.802545997072048e-06,
"loss": 0.8805,
"step": 1169
},
{
"epoch": 0.93,
"learning_rate": 5.796180676583798e-06,
"loss": 0.9361,
"step": 1170
},
{
"epoch": 0.93,
"learning_rate": 5.789814031885895e-06,
"loss": 0.9548,
"step": 1171
},
{
"epoch": 0.93,
"learning_rate": 5.783446073567353e-06,
"loss": 0.9096,
"step": 1172
},
{
"epoch": 0.93,
"learning_rate": 5.777076812219378e-06,
"loss": 0.838,
"step": 1173
},
{
"epoch": 0.93,
"learning_rate": 5.770706258435342e-06,
"loss": 0.9242,
"step": 1174
},
{
"epoch": 0.94,
"learning_rate": 5.764334422810767e-06,
"loss": 0.9656,
"step": 1175
},
{
"epoch": 0.94,
"learning_rate": 5.757961315943303e-06,
"loss": 0.8904,
"step": 1176
},
{
"epoch": 0.94,
"learning_rate": 5.751586948432716e-06,
"loss": 0.9503,
"step": 1177
},
{
"epoch": 0.94,
"learning_rate": 5.745211330880872e-06,
"loss": 0.9858,
"step": 1178
},
{
"epoch": 0.94,
"learning_rate": 5.738834473891716e-06,
"loss": 0.9489,
"step": 1179
},
{
"epoch": 0.94,
"learning_rate": 5.732456388071247e-06,
"loss": 0.9327,
"step": 1180
},
{
"epoch": 0.94,
"learning_rate": 5.726077084027517e-06,
"loss": 0.9933,
"step": 1181
},
{
"epoch": 0.94,
"learning_rate": 5.719696572370596e-06,
"loss": 0.9344,
"step": 1182
},
{
"epoch": 0.94,
"learning_rate": 5.713314863712571e-06,
"loss": 0.9244,
"step": 1183
},
{
"epoch": 0.94,
"learning_rate": 5.706931968667514e-06,
"loss": 0.9736,
"step": 1184
},
{
"epoch": 0.94,
"learning_rate": 5.700547897851471e-06,
"loss": 0.9391,
"step": 1185
},
{
"epoch": 0.94,
"learning_rate": 5.6941626618824445e-06,
"loss": 0.9024,
"step": 1186
},
{
"epoch": 0.95,
"learning_rate": 5.6877762713803745e-06,
"loss": 0.9383,
"step": 1187
},
{
"epoch": 0.95,
"learning_rate": 5.681388736967124e-06,
"loss": 0.9616,
"step": 1188
},
{
"epoch": 0.95,
"learning_rate": 5.675000069266451e-06,
"loss": 0.8896,
"step": 1189
},
{
"epoch": 0.95,
"learning_rate": 5.668610278904007e-06,
"loss": 0.9437,
"step": 1190
},
{
"epoch": 0.95,
"learning_rate": 5.6622193765073056e-06,
"loss": 0.8794,
"step": 1191
},
{
"epoch": 0.95,
"learning_rate": 5.655827372705712e-06,
"loss": 0.9374,
"step": 1192
},
{
"epoch": 0.95,
"learning_rate": 5.6494342781304224e-06,
"loss": 0.9211,
"step": 1193
},
{
"epoch": 0.95,
"learning_rate": 5.643040103414448e-06,
"loss": 0.846,
"step": 1194
},
{
"epoch": 0.95,
"learning_rate": 5.636644859192594e-06,
"loss": 0.9038,
"step": 1195
},
{
"epoch": 0.95,
"learning_rate": 5.630248556101448e-06,
"loss": 0.882,
"step": 1196
},
{
"epoch": 0.95,
"learning_rate": 5.623851204779356e-06,
"loss": 0.9116,
"step": 1197
},
{
"epoch": 0.95,
"learning_rate": 5.61745281586641e-06,
"loss": 0.8525,
"step": 1198
},
{
"epoch": 0.95,
"learning_rate": 5.611053400004424e-06,
"loss": 0.9156,
"step": 1199
},
{
"epoch": 0.96,
"learning_rate": 5.604652967836922e-06,
"loss": 0.9139,
"step": 1200
},
{
"epoch": 0.96,
"learning_rate": 5.598251530009121e-06,
"loss": 0.952,
"step": 1201
},
{
"epoch": 0.96,
"learning_rate": 5.591849097167908e-06,
"loss": 0.8933,
"step": 1202
},
{
"epoch": 0.96,
"learning_rate": 5.585445679961823e-06,
"loss": 0.8379,
"step": 1203
},
{
"epoch": 0.96,
"learning_rate": 5.579041289041045e-06,
"loss": 0.9164,
"step": 1204
},
{
"epoch": 0.96,
"learning_rate": 5.572635935057374e-06,
"loss": 0.9636,
"step": 1205
},
{
"epoch": 0.96,
"learning_rate": 5.5662296286642115e-06,
"loss": 0.918,
"step": 1206
},
{
"epoch": 0.96,
"learning_rate": 5.559822380516539e-06,
"loss": 0.8735,
"step": 1207
},
{
"epoch": 0.96,
"learning_rate": 5.55341420127091e-06,
"loss": 0.8444,
"step": 1208
},
{
"epoch": 0.96,
"learning_rate": 5.547005101585423e-06,
"loss": 0.8574,
"step": 1209
},
{
"epoch": 0.96,
"learning_rate": 5.540595092119709e-06,
"loss": 0.9776,
"step": 1210
},
{
"epoch": 0.96,
"learning_rate": 5.534184183534911e-06,
"loss": 0.8826,
"step": 1211
},
{
"epoch": 0.96,
"learning_rate": 5.527772386493667e-06,
"loss": 0.8529,
"step": 1212
},
{
"epoch": 0.97,
"learning_rate": 5.521359711660094e-06,
"loss": 0.9447,
"step": 1213
},
{
"epoch": 0.97,
"learning_rate": 5.51494616969977e-06,
"loss": 0.9126,
"step": 1214
},
{
"epoch": 0.97,
"learning_rate": 5.508531771279711e-06,
"loss": 0.9227,
"step": 1215
},
{
"epoch": 0.97,
"learning_rate": 5.502116527068363e-06,
"loss": 0.918,
"step": 1216
},
{
"epoch": 0.97,
"learning_rate": 5.495700447735572e-06,
"loss": 0.869,
"step": 1217
},
{
"epoch": 0.97,
"learning_rate": 5.489283543952583e-06,
"loss": 0.8982,
"step": 1218
},
{
"epoch": 0.97,
"learning_rate": 5.482865826392001e-06,
"loss": 0.9065,
"step": 1219
},
{
"epoch": 0.97,
"learning_rate": 5.4764473057277925e-06,
"loss": 1.0072,
"step": 1220
},
{
"epoch": 0.97,
"learning_rate": 5.4700279926352536e-06,
"loss": 0.81,
"step": 1221
},
{
"epoch": 0.97,
"learning_rate": 5.463607897791006e-06,
"loss": 0.8906,
"step": 1222
},
{
"epoch": 0.97,
"learning_rate": 5.457187031872962e-06,
"loss": 0.9194,
"step": 1223
},
{
"epoch": 0.97,
"learning_rate": 5.450765405560328e-06,
"loss": 0.9402,
"step": 1224
},
{
"epoch": 0.98,
"learning_rate": 5.444343029533562e-06,
"loss": 0.9412,
"step": 1225
},
{
"epoch": 0.98,
"learning_rate": 5.437919914474379e-06,
"loss": 0.9097,
"step": 1226
},
{
"epoch": 0.98,
"learning_rate": 5.431496071065719e-06,
"loss": 0.8355,
"step": 1227
},
{
"epoch": 0.98,
"learning_rate": 5.425071509991737e-06,
"loss": 0.9557,
"step": 1228
},
{
"epoch": 0.98,
"learning_rate": 5.4186462419377735e-06,
"loss": 0.9314,
"step": 1229
},
{
"epoch": 0.98,
"learning_rate": 5.412220277590354e-06,
"loss": 0.8696,
"step": 1230
},
{
"epoch": 0.98,
"learning_rate": 5.405793627637157e-06,
"loss": 0.8432,
"step": 1231
},
{
"epoch": 0.98,
"learning_rate": 5.399366302767003e-06,
"loss": 0.9937,
"step": 1232
},
{
"epoch": 0.98,
"learning_rate": 5.392938313669832e-06,
"loss": 0.95,
"step": 1233
},
{
"epoch": 0.98,
"learning_rate": 5.386509671036695e-06,
"loss": 1.0336,
"step": 1234
},
{
"epoch": 0.98,
"learning_rate": 5.380080385559723e-06,
"loss": 0.9884,
"step": 1235
},
{
"epoch": 0.98,
"learning_rate": 5.373650467932122e-06,
"loss": 0.9238,
"step": 1236
},
{
"epoch": 0.98,
"learning_rate": 5.3672199288481454e-06,
"loss": 0.8645,
"step": 1237
},
{
"epoch": 0.99,
"learning_rate": 5.360788779003082e-06,
"loss": 0.8379,
"step": 1238
},
{
"epoch": 0.99,
"learning_rate": 5.3543570290932336e-06,
"loss": 0.95,
"step": 1239
},
{
"epoch": 0.99,
"learning_rate": 5.347924689815906e-06,
"loss": 1.0034,
"step": 1240
},
{
"epoch": 0.99,
"learning_rate": 5.341491771869381e-06,
"loss": 0.8912,
"step": 1241
},
{
"epoch": 0.99,
"learning_rate": 5.335058285952902e-06,
"loss": 0.9127,
"step": 1242
},
{
"epoch": 0.99,
"learning_rate": 5.328624242766661e-06,
"loss": 0.8537,
"step": 1243
},
{
"epoch": 0.99,
"learning_rate": 5.32218965301177e-06,
"loss": 0.9362,
"step": 1244
},
{
"epoch": 0.99,
"learning_rate": 5.3157545273902585e-06,
"loss": 0.9389,
"step": 1245
},
{
"epoch": 0.99,
"learning_rate": 5.309318876605043e-06,
"loss": 0.876,
"step": 1246
},
{
"epoch": 0.99,
"learning_rate": 5.302882711359912e-06,
"loss": 0.981,
"step": 1247
},
{
"epoch": 0.99,
"learning_rate": 5.296446042359512e-06,
"loss": 0.9369,
"step": 1248
},
{
"epoch": 0.99,
"learning_rate": 5.2900088803093265e-06,
"loss": 0.9091,
"step": 1249
},
{
"epoch": 1.0,
"learning_rate": 5.283571235915659e-06,
"loss": 0.9329,
"step": 1250
},
{
"epoch": 1.0,
"learning_rate": 5.277133119885617e-06,
"loss": 0.8107,
"step": 1251
},
{
"epoch": 1.0,
"learning_rate": 5.270694542927089e-06,
"loss": 0.9338,
"step": 1252
},
{
"epoch": 1.0,
"learning_rate": 5.264255515748732e-06,
"loss": 0.9185,
"step": 1253
},
{
"epoch": 1.0,
"learning_rate": 5.257816049059953e-06,
"loss": 1.006,
"step": 1254
},
{
"epoch": 1.0,
"learning_rate": 5.25137615357089e-06,
"loss": 0.8864,
"step": 1255
},
{
"epoch": 1.0,
"learning_rate": 5.2449358399923885e-06,
"loss": 0.9692,
"step": 1256
},
{
"epoch": 1.0,
"learning_rate": 5.2384951190359986e-06,
"loss": 0.8562,
"step": 1257
},
{
"epoch": 1.0,
"learning_rate": 5.2320540014139405e-06,
"loss": 0.8663,
"step": 1258
},
{
"epoch": 1.0,
"learning_rate": 5.225612497839099e-06,
"loss": 0.8874,
"step": 1259
},
{
"epoch": 1.0,
"learning_rate": 5.219170619024996e-06,
"loss": 0.9504,
"step": 1260
},
{
"epoch": 1.0,
"learning_rate": 5.212728375685782e-06,
"loss": 0.866,
"step": 1261
},
{
"epoch": 1.0,
"learning_rate": 5.206285778536211e-06,
"loss": 0.877,
"step": 1262
},
{
"epoch": 1.01,
"learning_rate": 5.199842838291628e-06,
"loss": 0.8824,
"step": 1263
},
{
"epoch": 1.01,
"learning_rate": 5.193399565667945e-06,
"loss": 0.9856,
"step": 1264
},
{
"epoch": 1.01,
"learning_rate": 5.18695597138163e-06,
"loss": 0.9051,
"step": 1265
},
{
"epoch": 1.01,
"learning_rate": 5.180512066149682e-06,
"loss": 0.8695,
"step": 1266
},
{
"epoch": 1.01,
"learning_rate": 5.1740678606896255e-06,
"loss": 0.8683,
"step": 1267
},
{
"epoch": 1.01,
"learning_rate": 5.167623365719474e-06,
"loss": 0.9111,
"step": 1268
},
{
"epoch": 1.01,
"learning_rate": 5.1611785919577314e-06,
"loss": 0.9182,
"step": 1269
},
{
"epoch": 1.01,
"learning_rate": 5.154733550123357e-06,
"loss": 0.9373,
"step": 1270
},
{
"epoch": 1.01,
"learning_rate": 5.148288250935762e-06,
"loss": 0.7927,
"step": 1271
},
{
"epoch": 1.01,
"learning_rate": 5.1418427051147855e-06,
"loss": 0.9037,
"step": 1272
},
{
"epoch": 1.01,
"learning_rate": 5.1353969233806735e-06,
"loss": 0.9636,
"step": 1273
},
{
"epoch": 1.01,
"learning_rate": 5.128950916454066e-06,
"loss": 0.8784,
"step": 1274
},
{
"epoch": 1.02,
"learning_rate": 5.1225046950559765e-06,
"loss": 0.8737,
"step": 1275
},
{
"epoch": 1.02,
"learning_rate": 5.116058269907779e-06,
"loss": 0.8715,
"step": 1276
},
{
"epoch": 1.02,
"learning_rate": 5.109611651731182e-06,
"loss": 0.8734,
"step": 1277
},
{
"epoch": 1.02,
"learning_rate": 5.103164851248216e-06,
"loss": 0.9069,
"step": 1278
},
{
"epoch": 1.02,
"learning_rate": 5.096717879181217e-06,
"loss": 0.8666,
"step": 1279
},
{
"epoch": 1.02,
"learning_rate": 5.090270746252803e-06,
"loss": 0.7915,
"step": 1280
},
{
"epoch": 1.02,
"learning_rate": 5.083823463185863e-06,
"loss": 0.9624,
"step": 1281
},
{
"epoch": 1.02,
"learning_rate": 5.077376040703533e-06,
"loss": 0.9096,
"step": 1282
},
{
"epoch": 1.02,
"learning_rate": 5.0709284895291825e-06,
"loss": 0.9386,
"step": 1283
},
{
"epoch": 1.02,
"learning_rate": 5.0644808203863926e-06,
"loss": 0.987,
"step": 1284
},
{
"epoch": 1.02,
"learning_rate": 5.058033043998947e-06,
"loss": 0.8786,
"step": 1285
},
{
"epoch": 1.02,
"learning_rate": 5.0515851710907974e-06,
"loss": 0.8391,
"step": 1286
},
{
"epoch": 1.02,
"learning_rate": 5.045137212386065e-06,
"loss": 0.9529,
"step": 1287
},
{
"epoch": 1.03,
"learning_rate": 5.038689178609011e-06,
"loss": 0.9858,
"step": 1288
},
{
"epoch": 1.03,
"learning_rate": 5.032241080484021e-06,
"loss": 0.9431,
"step": 1289
},
{
"epoch": 1.03,
"learning_rate": 5.0257929287355846e-06,
"loss": 0.9128,
"step": 1290
},
{
"epoch": 1.03,
"learning_rate": 5.019344734088287e-06,
"loss": 0.9709,
"step": 1291
},
{
"epoch": 1.03,
"learning_rate": 5.012896507266779e-06,
"loss": 0.919,
"step": 1292
},
{
"epoch": 1.03,
"learning_rate": 5.006448258995771e-06,
"loss": 0.9056,
"step": 1293
},
{
"epoch": 1.03,
"learning_rate": 5e-06,
"loss": 0.8634,
"step": 1294
},
{
"epoch": 1.03,
"learning_rate": 4.993551741004232e-06,
"loss": 0.954,
"step": 1295
},
{
"epoch": 1.03,
"learning_rate": 4.987103492733221e-06,
"loss": 0.9311,
"step": 1296
},
{
"epoch": 1.03,
"learning_rate": 4.9806552659117135e-06,
"loss": 0.8877,
"step": 1297
},
{
"epoch": 1.03,
"learning_rate": 4.974207071264417e-06,
"loss": 0.9134,
"step": 1298
},
{
"epoch": 1.03,
"learning_rate": 4.967758919515983e-06,
"loss": 0.9263,
"step": 1299
},
{
"epoch": 1.04,
"learning_rate": 4.96131082139099e-06,
"loss": 0.8682,
"step": 1300
},
{
"epoch": 1.04,
"learning_rate": 4.954862787613937e-06,
"loss": 0.9235,
"step": 1301
},
{
"epoch": 1.04,
"learning_rate": 4.948414828909204e-06,
"loss": 0.8528,
"step": 1302
},
{
"epoch": 1.04,
"learning_rate": 4.9419669560010565e-06,
"loss": 0.8754,
"step": 1303
},
{
"epoch": 1.04,
"learning_rate": 4.935519179613607e-06,
"loss": 0.8549,
"step": 1304
},
{
"epoch": 1.04,
"learning_rate": 4.92907151047082e-06,
"loss": 0.8851,
"step": 1305
},
{
"epoch": 1.04,
"learning_rate": 4.922623959296469e-06,
"loss": 0.8713,
"step": 1306
},
{
"epoch": 1.04,
"learning_rate": 4.916176536814139e-06,
"loss": 0.9294,
"step": 1307
},
{
"epoch": 1.04,
"learning_rate": 4.909729253747197e-06,
"loss": 0.9601,
"step": 1308
},
{
"epoch": 1.04,
"learning_rate": 4.903282120818785e-06,
"loss": 0.9152,
"step": 1309
},
{
"epoch": 1.04,
"learning_rate": 4.896835148751785e-06,
"loss": 0.877,
"step": 1310
},
{
"epoch": 1.04,
"learning_rate": 4.890388348268821e-06,
"loss": 0.911,
"step": 1311
},
{
"epoch": 1.04,
"learning_rate": 4.883941730092222e-06,
"loss": 0.8679,
"step": 1312
},
{
"epoch": 1.05,
"learning_rate": 4.877495304944024e-06,
"loss": 0.8541,
"step": 1313
},
{
"epoch": 1.05,
"learning_rate": 4.8710490835459355e-06,
"loss": 0.8612,
"step": 1314
},
{
"epoch": 1.05,
"learning_rate": 4.864603076619329e-06,
"loss": 0.915,
"step": 1315
},
{
"epoch": 1.05,
"learning_rate": 4.858157294885215e-06,
"loss": 0.9357,
"step": 1316
},
{
"epoch": 1.05,
"learning_rate": 4.851711749064239e-06,
"loss": 0.9767,
"step": 1317
},
{
"epoch": 1.05,
"learning_rate": 4.845266449876646e-06,
"loss": 0.8453,
"step": 1318
},
{
"epoch": 1.05,
"learning_rate": 4.838821408042271e-06,
"loss": 0.9077,
"step": 1319
},
{
"epoch": 1.05,
"learning_rate": 4.832376634280526e-06,
"loss": 0.9924,
"step": 1320
},
{
"epoch": 1.05,
"learning_rate": 4.825932139310376e-06,
"loss": 0.9128,
"step": 1321
},
{
"epoch": 1.05,
"learning_rate": 4.819487933850319e-06,
"loss": 0.8297,
"step": 1322
},
{
"epoch": 1.05,
"learning_rate": 4.8130440286183725e-06,
"loss": 0.8884,
"step": 1323
},
{
"epoch": 1.05,
"learning_rate": 4.806600434332056e-06,
"loss": 0.8599,
"step": 1324
},
{
"epoch": 1.05,
"learning_rate": 4.800157161708374e-06,
"loss": 0.9049,
"step": 1325
},
{
"epoch": 1.06,
"learning_rate": 4.7937142214637905e-06,
"loss": 0.9394,
"step": 1326
},
{
"epoch": 1.06,
"learning_rate": 4.78727162431422e-06,
"loss": 0.8673,
"step": 1327
},
{
"epoch": 1.06,
"learning_rate": 4.780829380975004e-06,
"loss": 0.8871,
"step": 1328
},
{
"epoch": 1.06,
"learning_rate": 4.774387502160902e-06,
"loss": 0.9284,
"step": 1329
},
{
"epoch": 1.06,
"learning_rate": 4.76794599858606e-06,
"loss": 0.9013,
"step": 1330
},
{
"epoch": 1.06,
"learning_rate": 4.761504880964002e-06,
"loss": 0.8401,
"step": 1331
},
{
"epoch": 1.06,
"learning_rate": 4.755064160007612e-06,
"loss": 0.8625,
"step": 1332
},
{
"epoch": 1.06,
"learning_rate": 4.748623846429112e-06,
"loss": 0.9154,
"step": 1333
},
{
"epoch": 1.06,
"learning_rate": 4.742183950940049e-06,
"loss": 0.8603,
"step": 1334
},
{
"epoch": 1.06,
"learning_rate": 4.735744484251271e-06,
"loss": 0.9855,
"step": 1335
},
{
"epoch": 1.06,
"learning_rate": 4.729305457072913e-06,
"loss": 0.9263,
"step": 1336
},
{
"epoch": 1.06,
"learning_rate": 4.7228668801143844e-06,
"loss": 0.8474,
"step": 1337
},
{
"epoch": 1.07,
"learning_rate": 4.7164287640843425e-06,
"loss": 0.9168,
"step": 1338
},
{
"epoch": 1.07,
"learning_rate": 4.709991119690677e-06,
"loss": 0.8575,
"step": 1339
},
{
"epoch": 1.07,
"learning_rate": 4.70355395764049e-06,
"loss": 0.9192,
"step": 1340
},
{
"epoch": 1.07,
"learning_rate": 4.697117288640089e-06,
"loss": 0.8942,
"step": 1341
},
{
"epoch": 1.07,
"learning_rate": 4.690681123394959e-06,
"loss": 0.8794,
"step": 1342
},
{
"epoch": 1.07,
"learning_rate": 4.684245472609743e-06,
"loss": 0.8626,
"step": 1343
},
{
"epoch": 1.07,
"learning_rate": 4.677810346988231e-06,
"loss": 0.7888,
"step": 1344
},
{
"epoch": 1.07,
"learning_rate": 4.6713757572333405e-06,
"loss": 0.851,
"step": 1345
},
{
"epoch": 1.07,
"learning_rate": 4.6649417140471e-06,
"loss": 0.9346,
"step": 1346
},
{
"epoch": 1.07,
"learning_rate": 4.658508228130621e-06,
"loss": 0.8427,
"step": 1347
},
{
"epoch": 1.07,
"learning_rate": 4.6520753101840945e-06,
"loss": 0.9015,
"step": 1348
},
{
"epoch": 1.07,
"learning_rate": 4.645642970906767e-06,
"loss": 0.9607,
"step": 1349
},
{
"epoch": 1.07,
"learning_rate": 4.6392112209969205e-06,
"loss": 0.9491,
"step": 1350
},
{
"epoch": 1.08,
"learning_rate": 4.632780071151855e-06,
"loss": 0.9369,
"step": 1351
},
{
"epoch": 1.08,
"learning_rate": 4.626349532067879e-06,
"loss": 0.9021,
"step": 1352
},
{
"epoch": 1.08,
"learning_rate": 4.619919614440278e-06,
"loss": 0.8813,
"step": 1353
},
{
"epoch": 1.08,
"learning_rate": 4.613490328963307e-06,
"loss": 0.9553,
"step": 1354
},
{
"epoch": 1.08,
"learning_rate": 4.607061686330168e-06,
"loss": 0.9516,
"step": 1355
},
{
"epoch": 1.08,
"learning_rate": 4.600633697232999e-06,
"loss": 0.9494,
"step": 1356
},
{
"epoch": 1.08,
"learning_rate": 4.594206372362845e-06,
"loss": 0.8781,
"step": 1357
},
{
"epoch": 1.08,
"learning_rate": 4.5877797224096474e-06,
"loss": 0.8745,
"step": 1358
},
{
"epoch": 1.08,
"learning_rate": 4.581353758062226e-06,
"loss": 0.8857,
"step": 1359
},
{
"epoch": 1.08,
"learning_rate": 4.574928490008264e-06,
"loss": 0.8977,
"step": 1360
},
{
"epoch": 1.08,
"learning_rate": 4.568503928934282e-06,
"loss": 0.813,
"step": 1361
},
{
"epoch": 1.08,
"learning_rate": 4.562080085525622e-06,
"loss": 0.9215,
"step": 1362
},
{
"epoch": 1.09,
"learning_rate": 4.55565697046644e-06,
"loss": 0.9122,
"step": 1363
},
{
"epoch": 1.09,
"learning_rate": 4.549234594439674e-06,
"loss": 0.8708,
"step": 1364
},
{
"epoch": 1.09,
"learning_rate": 4.542812968127039e-06,
"loss": 0.8508,
"step": 1365
},
{
"epoch": 1.09,
"learning_rate": 4.536392102208998e-06,
"loss": 0.8162,
"step": 1366
},
{
"epoch": 1.09,
"learning_rate": 4.529972007364747e-06,
"loss": 0.9013,
"step": 1367
},
{
"epoch": 1.09,
"learning_rate": 4.523552694272208e-06,
"loss": 0.8827,
"step": 1368
},
{
"epoch": 1.09,
"learning_rate": 4.517134173608001e-06,
"loss": 0.9028,
"step": 1369
},
{
"epoch": 1.09,
"learning_rate": 4.510716456047419e-06,
"loss": 0.8612,
"step": 1370
},
{
"epoch": 1.09,
"learning_rate": 4.504299552264428e-06,
"loss": 0.8662,
"step": 1371
},
{
"epoch": 1.09,
"learning_rate": 4.497883472931639e-06,
"loss": 0.9186,
"step": 1372
},
{
"epoch": 1.09,
"learning_rate": 4.491468228720291e-06,
"loss": 0.894,
"step": 1373
},
{
"epoch": 1.09,
"learning_rate": 4.4850538303002334e-06,
"loss": 1.0182,
"step": 1374
},
{
"epoch": 1.09,
"learning_rate": 4.478640288339907e-06,
"loss": 0.9212,
"step": 1375
},
{
"epoch": 1.1,
"learning_rate": 4.472227613506334e-06,
"loss": 0.889,
"step": 1376
},
{
"epoch": 1.1,
"learning_rate": 4.465815816465091e-06,
"loss": 0.9701,
"step": 1377
},
{
"epoch": 1.1,
"learning_rate": 4.459404907880293e-06,
"loss": 0.953,
"step": 1378
},
{
"epoch": 1.1,
"learning_rate": 4.452994898414576e-06,
"loss": 0.8633,
"step": 1379
},
{
"epoch": 1.1,
"learning_rate": 4.446585798729091e-06,
"loss": 0.9221,
"step": 1380
},
{
"epoch": 1.1,
"learning_rate": 4.4401776194834615e-06,
"loss": 0.9436,
"step": 1381
},
{
"epoch": 1.1,
"learning_rate": 4.43377037133579e-06,
"loss": 0.897,
"step": 1382
},
{
"epoch": 1.1,
"learning_rate": 4.427364064942626e-06,
"loss": 0.9363,
"step": 1383
},
{
"epoch": 1.1,
"learning_rate": 4.4209587109589565e-06,
"loss": 0.9038,
"step": 1384
},
{
"epoch": 1.1,
"learning_rate": 4.414554320038179e-06,
"loss": 0.8744,
"step": 1385
},
{
"epoch": 1.1,
"learning_rate": 4.408150902832094e-06,
"loss": 0.8175,
"step": 1386
},
{
"epoch": 1.1,
"learning_rate": 4.401748469990879e-06,
"loss": 0.9567,
"step": 1387
},
{
"epoch": 1.11,
"learning_rate": 4.395347032163079e-06,
"loss": 0.8476,
"step": 1388
},
{
"epoch": 1.11,
"learning_rate": 4.3889465999955786e-06,
"loss": 0.9139,
"step": 1389
},
{
"epoch": 1.11,
"learning_rate": 4.382547184133593e-06,
"loss": 0.8429,
"step": 1390
},
{
"epoch": 1.11,
"learning_rate": 4.376148795220645e-06,
"loss": 0.953,
"step": 1391
},
{
"epoch": 1.11,
"learning_rate": 4.369751443898554e-06,
"loss": 0.8425,
"step": 1392
},
{
"epoch": 1.11,
"learning_rate": 4.363355140807408e-06,
"loss": 0.8561,
"step": 1393
},
{
"epoch": 1.11,
"learning_rate": 4.356959896585555e-06,
"loss": 0.9047,
"step": 1394
},
{
"epoch": 1.11,
"learning_rate": 4.3505657218695775e-06,
"loss": 0.892,
"step": 1395
},
{
"epoch": 1.11,
"learning_rate": 4.3441726272942895e-06,
"loss": 0.8905,
"step": 1396
},
{
"epoch": 1.11,
"learning_rate": 4.337780623492696e-06,
"loss": 0.9132,
"step": 1397
},
{
"epoch": 1.11,
"learning_rate": 4.331389721095995e-06,
"loss": 0.8586,
"step": 1398
},
{
"epoch": 1.11,
"learning_rate": 4.32499993073355e-06,
"loss": 0.8824,
"step": 1399
},
{
"epoch": 1.11,
"learning_rate": 4.318611263032878e-06,
"loss": 0.8852,
"step": 1400
},
{
"epoch": 1.12,
"learning_rate": 4.312223728619626e-06,
"loss": 0.9751,
"step": 1401
},
{
"epoch": 1.12,
"learning_rate": 4.305837338117557e-06,
"loss": 0.8849,
"step": 1402
},
{
"epoch": 1.12,
"learning_rate": 4.29945210214853e-06,
"loss": 0.9519,
"step": 1403
},
{
"epoch": 1.12,
"learning_rate": 4.293068031332488e-06,
"loss": 0.9342,
"step": 1404
},
{
"epoch": 1.12,
"learning_rate": 4.286685136287431e-06,
"loss": 0.8704,
"step": 1405
},
{
"epoch": 1.12,
"learning_rate": 4.280303427629404e-06,
"loss": 0.898,
"step": 1406
},
{
"epoch": 1.12,
"learning_rate": 4.2739229159724845e-06,
"loss": 0.8963,
"step": 1407
},
{
"epoch": 1.12,
"learning_rate": 4.267543611928755e-06,
"loss": 0.8876,
"step": 1408
},
{
"epoch": 1.12,
"learning_rate": 4.261165526108287e-06,
"loss": 0.8471,
"step": 1409
},
{
"epoch": 1.12,
"learning_rate": 4.254788669119127e-06,
"loss": 0.8675,
"step": 1410
},
{
"epoch": 1.12,
"learning_rate": 4.248413051567286e-06,
"loss": 0.8578,
"step": 1411
},
{
"epoch": 1.12,
"learning_rate": 4.2420386840567e-06,
"loss": 0.9145,
"step": 1412
},
{
"epoch": 1.12,
"learning_rate": 4.2356655771892355e-06,
"loss": 0.8537,
"step": 1413
},
{
"epoch": 1.13,
"learning_rate": 4.229293741564658e-06,
"loss": 0.8562,
"step": 1414
},
{
"epoch": 1.13,
"learning_rate": 4.222923187780623e-06,
"loss": 0.9368,
"step": 1415
},
{
"epoch": 1.13,
"learning_rate": 4.2165539264326495e-06,
"loss": 0.8736,
"step": 1416
},
{
"epoch": 1.13,
"learning_rate": 4.210185968114109e-06,
"loss": 0.898,
"step": 1417
},
{
"epoch": 1.13,
"learning_rate": 4.2038193234162025e-06,
"loss": 0.8649,
"step": 1418
},
{
"epoch": 1.13,
"learning_rate": 4.197454002927954e-06,
"loss": 0.9227,
"step": 1419
},
{
"epoch": 1.13,
"learning_rate": 4.191090017236177e-06,
"loss": 0.9591,
"step": 1420
},
{
"epoch": 1.13,
"learning_rate": 4.184727376925469e-06,
"loss": 0.9197,
"step": 1421
},
{
"epoch": 1.13,
"learning_rate": 4.178366092578188e-06,
"loss": 0.8792,
"step": 1422
},
{
"epoch": 1.13,
"learning_rate": 4.17200617477444e-06,
"loss": 0.8064,
"step": 1423
},
{
"epoch": 1.13,
"learning_rate": 4.165647634092055e-06,
"loss": 0.8764,
"step": 1424
},
{
"epoch": 1.13,
"learning_rate": 4.159290481106572e-06,
"loss": 0.8491,
"step": 1425
},
{
"epoch": 1.14,
"learning_rate": 4.152934726391223e-06,
"loss": 0.88,
"step": 1426
},
{
"epoch": 1.14,
"learning_rate": 4.146580380516918e-06,
"loss": 0.8872,
"step": 1427
},
{
"epoch": 1.14,
"learning_rate": 4.14022745405222e-06,
"loss": 0.8068,
"step": 1428
},
{
"epoch": 1.14,
"learning_rate": 4.133875957563329e-06,
"loss": 0.9183,
"step": 1429
},
{
"epoch": 1.14,
"learning_rate": 4.127525901614071e-06,
"loss": 0.8519,
"step": 1430
},
{
"epoch": 1.14,
"learning_rate": 4.1211772967658764e-06,
"loss": 0.8881,
"step": 1431
},
{
"epoch": 1.14,
"learning_rate": 4.114830153577759e-06,
"loss": 0.921,
"step": 1432
},
{
"epoch": 1.14,
"learning_rate": 4.108484482606303e-06,
"loss": 0.9354,
"step": 1433
},
{
"epoch": 1.14,
"learning_rate": 4.1021402944056415e-06,
"loss": 0.8642,
"step": 1434
},
{
"epoch": 1.14,
"learning_rate": 4.095797599527449e-06,
"loss": 0.8813,
"step": 1435
},
{
"epoch": 1.14,
"learning_rate": 4.089456408520908e-06,
"loss": 0.8674,
"step": 1436
},
{
"epoch": 1.14,
"learning_rate": 4.0831167319327024e-06,
"loss": 0.9218,
"step": 1437
},
{
"epoch": 1.14,
"learning_rate": 4.076778580306999e-06,
"loss": 0.8531,
"step": 1438
},
{
"epoch": 1.15,
"learning_rate": 4.070441964185428e-06,
"loss": 0.9124,
"step": 1439
},
{
"epoch": 1.15,
"learning_rate": 4.064106894107064e-06,
"loss": 0.9445,
"step": 1440
},
{
"epoch": 1.15,
"learning_rate": 4.057773380608411e-06,
"loss": 0.9069,
"step": 1441
},
{
"epoch": 1.15,
"learning_rate": 4.051441434223381e-06,
"loss": 0.8527,
"step": 1442
},
{
"epoch": 1.15,
"learning_rate": 4.0451110654832885e-06,
"loss": 0.8253,
"step": 1443
},
{
"epoch": 1.15,
"learning_rate": 4.0387822849168165e-06,
"loss": 0.8339,
"step": 1444
},
{
"epoch": 1.15,
"learning_rate": 4.032455103050007e-06,
"loss": 0.9031,
"step": 1445
},
{
"epoch": 1.15,
"learning_rate": 4.026129530406244e-06,
"loss": 0.8865,
"step": 1446
},
{
"epoch": 1.15,
"learning_rate": 4.019805577506237e-06,
"loss": 0.8954,
"step": 1447
},
{
"epoch": 1.15,
"learning_rate": 4.013483254868001e-06,
"loss": 0.8326,
"step": 1448
},
{
"epoch": 1.15,
"learning_rate": 4.007162573006836e-06,
"loss": 0.8963,
"step": 1449
},
{
"epoch": 1.15,
"learning_rate": 4.000843542435315e-06,
"loss": 0.8994,
"step": 1450
},
{
"epoch": 1.16,
"learning_rate": 3.994526173663269e-06,
"loss": 0.8105,
"step": 1451
},
{
"epoch": 1.16,
"learning_rate": 3.9882104771977585e-06,
"loss": 0.9716,
"step": 1452
},
{
"epoch": 1.16,
"learning_rate": 3.981896463543067e-06,
"loss": 0.857,
"step": 1453
},
{
"epoch": 1.16,
"learning_rate": 3.975584143200673e-06,
"loss": 0.8877,
"step": 1454
},
{
"epoch": 1.16,
"learning_rate": 3.969273526669249e-06,
"loss": 0.9217,
"step": 1455
},
{
"epoch": 1.16,
"learning_rate": 3.962964624444625e-06,
"loss": 0.9472,
"step": 1456
},
{
"epoch": 1.16,
"learning_rate": 3.956657447019784e-06,
"loss": 0.8835,
"step": 1457
},
{
"epoch": 1.16,
"learning_rate": 3.950352004884836e-06,
"loss": 0.9163,
"step": 1458
},
{
"epoch": 1.16,
"learning_rate": 3.944048308527012e-06,
"loss": 0.9337,
"step": 1459
},
{
"epoch": 1.16,
"learning_rate": 3.937746368430633e-06,
"loss": 0.8698,
"step": 1460
},
{
"epoch": 1.16,
"learning_rate": 3.9314461950771e-06,
"loss": 0.9036,
"step": 1461
},
{
"epoch": 1.16,
"learning_rate": 3.92514779894488e-06,
"loss": 0.8868,
"step": 1462
},
{
"epoch": 1.16,
"learning_rate": 3.9188511905094785e-06,
"loss": 0.9028,
"step": 1463
},
{
"epoch": 1.17,
"learning_rate": 3.912556380243431e-06,
"loss": 0.8319,
"step": 1464
},
{
"epoch": 1.17,
"learning_rate": 3.906263378616279e-06,
"loss": 0.8562,
"step": 1465
},
{
"epoch": 1.17,
"learning_rate": 3.899972196094564e-06,
"loss": 0.9035,
"step": 1466
},
{
"epoch": 1.17,
"learning_rate": 3.893682843141791e-06,
"loss": 0.9058,
"step": 1467
},
{
"epoch": 1.17,
"learning_rate": 3.887395330218429e-06,
"loss": 0.8597,
"step": 1468
},
{
"epoch": 1.17,
"learning_rate": 3.881109667781884e-06,
"loss": 0.8862,
"step": 1469
},
{
"epoch": 1.17,
"learning_rate": 3.874825866286486e-06,
"loss": 0.9041,
"step": 1470
},
{
"epoch": 1.17,
"learning_rate": 3.86854393618347e-06,
"loss": 0.855,
"step": 1471
},
{
"epoch": 1.17,
"learning_rate": 3.862263887920957e-06,
"loss": 0.9132,
"step": 1472
},
{
"epoch": 1.17,
"learning_rate": 3.855985731943936e-06,
"loss": 0.8779,
"step": 1473
},
{
"epoch": 1.17,
"learning_rate": 3.849709478694256e-06,
"loss": 0.9496,
"step": 1474
},
{
"epoch": 1.17,
"learning_rate": 3.843435138610594e-06,
"loss": 0.9204,
"step": 1475
},
{
"epoch": 1.18,
"learning_rate": 3.8371627221284495e-06,
"loss": 0.8573,
"step": 1476
},
{
"epoch": 1.18,
"learning_rate": 3.830892239680117e-06,
"loss": 0.8619,
"step": 1477
},
{
"epoch": 1.18,
"learning_rate": 3.824623701694683e-06,
"loss": 0.9007,
"step": 1478
},
{
"epoch": 1.18,
"learning_rate": 3.818357118597994e-06,
"loss": 0.9481,
"step": 1479
},
{
"epoch": 1.18,
"learning_rate": 3.8120925008126457e-06,
"loss": 0.8173,
"step": 1480
},
{
"epoch": 1.18,
"learning_rate": 3.8058298587579638e-06,
"loss": 0.9241,
"step": 1481
},
{
"epoch": 1.18,
"learning_rate": 3.7995692028499936e-06,
"loss": 0.8508,
"step": 1482
},
{
"epoch": 1.18,
"learning_rate": 3.7933105435014727e-06,
"loss": 0.8834,
"step": 1483
},
{
"epoch": 1.18,
"learning_rate": 3.7870538911218176e-06,
"loss": 1.014,
"step": 1484
},
{
"epoch": 1.18,
"learning_rate": 3.780799256117106e-06,
"loss": 0.8991,
"step": 1485
},
{
"epoch": 1.18,
"learning_rate": 3.7745466488900663e-06,
"loss": 0.9228,
"step": 1486
},
{
"epoch": 1.18,
"learning_rate": 3.7682960798400477e-06,
"loss": 0.9041,
"step": 1487
},
{
"epoch": 1.18,
"learning_rate": 3.762047559363013e-06,
"loss": 0.8916,
"step": 1488
},
{
"epoch": 1.19,
"learning_rate": 3.7558010978515143e-06,
"loss": 0.9196,
"step": 1489
},
{
"epoch": 1.19,
"learning_rate": 3.7495567056946856e-06,
"loss": 0.8969,
"step": 1490
},
{
"epoch": 1.19,
"learning_rate": 3.7433143932782124e-06,
"loss": 0.957,
"step": 1491
},
{
"epoch": 1.19,
"learning_rate": 3.7370741709843263e-06,
"loss": 0.861,
"step": 1492
},
{
"epoch": 1.19,
"learning_rate": 3.7308360491917773e-06,
"loss": 0.8915,
"step": 1493
},
{
"epoch": 1.19,
"learning_rate": 3.724600038275827e-06,
"loss": 0.9123,
"step": 1494
},
{
"epoch": 1.19,
"learning_rate": 3.7183661486082246e-06,
"loss": 0.8787,
"step": 1495
},
{
"epoch": 1.19,
"learning_rate": 3.7121343905571897e-06,
"loss": 0.8771,
"step": 1496
},
{
"epoch": 1.19,
"learning_rate": 3.705904774487396e-06,
"loss": 0.9192,
"step": 1497
},
{
"epoch": 1.19,
"learning_rate": 3.6996773107599605e-06,
"loss": 0.8531,
"step": 1498
},
{
"epoch": 1.19,
"learning_rate": 3.6934520097324113e-06,
"loss": 0.8853,
"step": 1499
},
{
"epoch": 1.19,
"learning_rate": 3.6872288817586883e-06,
"loss": 0.8394,
"step": 1500
},
{
"epoch": 1.2,
"learning_rate": 3.6810079371891093e-06,
"loss": 0.9241,
"step": 1501
},
{
"epoch": 1.2,
"learning_rate": 3.674789186370369e-06,
"loss": 0.8916,
"step": 1502
},
{
"epoch": 1.2,
"learning_rate": 3.6685726396455067e-06,
"loss": 0.8931,
"step": 1503
},
{
"epoch": 1.2,
"learning_rate": 3.662358307353897e-06,
"loss": 0.9234,
"step": 1504
},
{
"epoch": 1.2,
"learning_rate": 3.6561461998312333e-06,
"loss": 0.8673,
"step": 1505
},
{
"epoch": 1.2,
"learning_rate": 3.64993632740951e-06,
"loss": 0.8789,
"step": 1506
},
{
"epoch": 1.2,
"learning_rate": 3.643728700417002e-06,
"loss": 0.8801,
"step": 1507
},
{
"epoch": 1.2,
"learning_rate": 3.637523329178247e-06,
"loss": 0.8801,
"step": 1508
},
{
"epoch": 1.2,
"learning_rate": 3.6313202240140344e-06,
"loss": 0.9101,
"step": 1509
},
{
"epoch": 1.2,
"learning_rate": 3.6251193952413866e-06,
"loss": 0.8809,
"step": 1510
},
{
"epoch": 1.2,
"learning_rate": 3.6189208531735354e-06,
"loss": 0.9166,
"step": 1511
},
{
"epoch": 1.2,
"learning_rate": 3.6127246081199107e-06,
"loss": 0.9166,
"step": 1512
},
{
"epoch": 1.2,
"learning_rate": 3.6065306703861214e-06,
"loss": 0.876,
"step": 1513
},
{
"epoch": 1.21,
"learning_rate": 3.6003390502739436e-06,
"loss": 0.8992,
"step": 1514
},
{
"epoch": 1.21,
"learning_rate": 3.5941497580812935e-06,
"loss": 0.9612,
"step": 1515
},
{
"epoch": 1.21,
"learning_rate": 3.587962804102214e-06,
"loss": 0.9288,
"step": 1516
},
{
"epoch": 1.21,
"learning_rate": 3.5817781986268675e-06,
"loss": 0.9282,
"step": 1517
},
{
"epoch": 1.21,
"learning_rate": 3.5755959519415008e-06,
"loss": 0.9664,
"step": 1518
},
{
"epoch": 1.21,
"learning_rate": 3.5694160743284444e-06,
"loss": 0.8126,
"step": 1519
},
{
"epoch": 1.21,
"learning_rate": 3.5632385760660828e-06,
"loss": 0.8372,
"step": 1520
},
{
"epoch": 1.21,
"learning_rate": 3.5570634674288498e-06,
"loss": 0.846,
"step": 1521
},
{
"epoch": 1.21,
"learning_rate": 3.550890758687199e-06,
"loss": 0.8519,
"step": 1522
},
{
"epoch": 1.21,
"learning_rate": 3.544720460107596e-06,
"loss": 0.9087,
"step": 1523
},
{
"epoch": 1.21,
"learning_rate": 3.5385525819524933e-06,
"loss": 0.9393,
"step": 1524
},
{
"epoch": 1.21,
"learning_rate": 3.532387134480327e-06,
"loss": 0.9208,
"step": 1525
},
{
"epoch": 1.21,
"learning_rate": 3.526224127945479e-06,
"loss": 0.9268,
"step": 1526
},
{
"epoch": 1.22,
"learning_rate": 3.5200635725982805e-06,
"loss": 0.8869,
"step": 1527
},
{
"epoch": 1.22,
"learning_rate": 3.5139054786849787e-06,
"loss": 0.8606,
"step": 1528
},
{
"epoch": 1.22,
"learning_rate": 3.5077498564477343e-06,
"loss": 0.9599,
"step": 1529
},
{
"epoch": 1.22,
"learning_rate": 3.5015967161245914e-06,
"loss": 0.8053,
"step": 1530
},
{
"epoch": 1.22,
"learning_rate": 3.4954460679494684e-06,
"loss": 0.9228,
"step": 1531
},
{
"epoch": 1.22,
"learning_rate": 3.489297922152136e-06,
"loss": 0.8796,
"step": 1532
},
{
"epoch": 1.22,
"learning_rate": 3.4831522889582104e-06,
"loss": 0.9674,
"step": 1533
},
{
"epoch": 1.22,
"learning_rate": 3.4770091785891207e-06,
"loss": 0.8731,
"step": 1534
},
{
"epoch": 1.22,
"learning_rate": 3.470868601262103e-06,
"loss": 0.9454,
"step": 1535
},
{
"epoch": 1.22,
"learning_rate": 3.4647305671901797e-06,
"loss": 0.9752,
"step": 1536
},
{
"epoch": 1.22,
"learning_rate": 3.4585950865821475e-06,
"loss": 0.9448,
"step": 1537
},
{
"epoch": 1.22,
"learning_rate": 3.452462169642551e-06,
"loss": 0.8653,
"step": 1538
},
{
"epoch": 1.23,
"learning_rate": 3.446331826571672e-06,
"loss": 0.9302,
"step": 1539
},
{
"epoch": 1.23,
"learning_rate": 3.440204067565511e-06,
"loss": 0.8132,
"step": 1540
},
{
"epoch": 1.23,
"learning_rate": 3.4340789028157764e-06,
"loss": 0.9272,
"step": 1541
},
{
"epoch": 1.23,
"learning_rate": 3.427956342509853e-06,
"loss": 0.8901,
"step": 1542
},
{
"epoch": 1.23,
"learning_rate": 3.4218363968308e-06,
"loss": 0.9209,
"step": 1543
},
{
"epoch": 1.23,
"learning_rate": 3.4157190759573243e-06,
"loss": 0.8337,
"step": 1544
},
{
"epoch": 1.23,
"learning_rate": 3.409604390063771e-06,
"loss": 0.9198,
"step": 1545
},
{
"epoch": 1.23,
"learning_rate": 3.403492349320101e-06,
"loss": 0.9384,
"step": 1546
},
{
"epoch": 1.23,
"learning_rate": 3.3973829638918744e-06,
"loss": 0.8695,
"step": 1547
},
{
"epoch": 1.23,
"learning_rate": 3.391276243940234e-06,
"loss": 0.7575,
"step": 1548
},
{
"epoch": 1.23,
"learning_rate": 3.3851721996218944e-06,
"loss": 0.8965,
"step": 1549
},
{
"epoch": 1.23,
"learning_rate": 3.379070841089117e-06,
"loss": 0.9077,
"step": 1550
},
{
"epoch": 1.23,
"learning_rate": 3.3729721784896962e-06,
"loss": 0.9432,
"step": 1551
},
{
"epoch": 1.24,
"learning_rate": 3.3668762219669393e-06,
"loss": 0.9537,
"step": 1552
},
{
"epoch": 1.24,
"learning_rate": 3.360782981659659e-06,
"loss": 1.0006,
"step": 1553
},
{
"epoch": 1.24,
"learning_rate": 3.35469246770215e-06,
"loss": 0.8399,
"step": 1554
},
{
"epoch": 1.24,
"learning_rate": 3.3486046902241663e-06,
"loss": 0.905,
"step": 1555
},
{
"epoch": 1.24,
"learning_rate": 3.3425196593509135e-06,
"loss": 0.8382,
"step": 1556
},
{
"epoch": 1.24,
"learning_rate": 3.336437385203033e-06,
"loss": 0.8907,
"step": 1557
},
{
"epoch": 1.24,
"learning_rate": 3.330357877896577e-06,
"loss": 0.8906,
"step": 1558
},
{
"epoch": 1.24,
"learning_rate": 3.3242811475429977e-06,
"loss": 0.8863,
"step": 1559
},
{
"epoch": 1.24,
"learning_rate": 3.3182072042491244e-06,
"loss": 0.8637,
"step": 1560
},
{
"epoch": 1.24,
"learning_rate": 3.3121360581171596e-06,
"loss": 0.8723,
"step": 1561
},
{
"epoch": 1.24,
"learning_rate": 3.306067719244645e-06,
"loss": 0.8564,
"step": 1562
},
{
"epoch": 1.24,
"learning_rate": 3.300002197724459e-06,
"loss": 0.9109,
"step": 1563
},
{
"epoch": 1.25,
"learning_rate": 3.293939503644788e-06,
"loss": 0.84,
"step": 1564
},
{
"epoch": 1.25,
"learning_rate": 3.2878796470891242e-06,
"loss": 0.9125,
"step": 1565
},
{
"epoch": 1.25,
"learning_rate": 3.281822638136233e-06,
"loss": 0.9171,
"step": 1566
},
{
"epoch": 1.25,
"learning_rate": 3.275768486860149e-06,
"loss": 0.8451,
"step": 1567
},
{
"epoch": 1.25,
"learning_rate": 3.2697172033301485e-06,
"loss": 0.919,
"step": 1568
},
{
"epoch": 1.25,
"learning_rate": 3.2636687976107433e-06,
"loss": 0.9181,
"step": 1569
},
{
"epoch": 1.25,
"learning_rate": 3.2576232797616556e-06,
"loss": 0.883,
"step": 1570
},
{
"epoch": 1.25,
"learning_rate": 3.251580659837805e-06,
"loss": 0.8358,
"step": 1571
},
{
"epoch": 1.25,
"learning_rate": 3.245540947889294e-06,
"loss": 0.9213,
"step": 1572
},
{
"epoch": 1.25,
"learning_rate": 3.239504153961386e-06,
"loss": 0.8926,
"step": 1573
},
{
"epoch": 1.25,
"learning_rate": 3.233470288094489e-06,
"loss": 0.9109,
"step": 1574
},
{
"epoch": 1.25,
"learning_rate": 3.227439360324145e-06,
"loss": 0.8961,
"step": 1575
},
{
"epoch": 1.25,
"learning_rate": 3.2214113806810077e-06,
"loss": 0.8941,
"step": 1576
},
{
"epoch": 1.26,
"learning_rate": 3.2153863591908292e-06,
"loss": 0.8483,
"step": 1577
},
{
"epoch": 1.26,
"learning_rate": 3.2093643058744384e-06,
"loss": 0.8657,
"step": 1578
},
{
"epoch": 1.26,
"learning_rate": 3.2033452307477275e-06,
"loss": 0.898,
"step": 1579
},
{
"epoch": 1.26,
"learning_rate": 3.197329143821639e-06,
"loss": 0.9542,
"step": 1580
},
{
"epoch": 1.26,
"learning_rate": 3.191316055102146e-06,
"loss": 0.8403,
"step": 1581
},
{
"epoch": 1.26,
"learning_rate": 3.1853059745902287e-06,
"loss": 0.8383,
"step": 1582
},
{
"epoch": 1.26,
"learning_rate": 3.1792989122818672e-06,
"loss": 0.829,
"step": 1583
},
{
"epoch": 1.26,
"learning_rate": 3.173294878168025e-06,
"loss": 0.9548,
"step": 1584
},
{
"epoch": 1.26,
"learning_rate": 3.167293882234626e-06,
"loss": 0.9415,
"step": 1585
},
{
"epoch": 1.26,
"learning_rate": 3.161295934462541e-06,
"loss": 0.8679,
"step": 1586
},
{
"epoch": 1.26,
"learning_rate": 3.155301044827569e-06,
"loss": 0.8945,
"step": 1587
},
{
"epoch": 1.26,
"learning_rate": 3.149309223300428e-06,
"loss": 0.935,
"step": 1588
},
{
"epoch": 1.27,
"learning_rate": 3.143320479846731e-06,
"loss": 0.9312,
"step": 1589
},
{
"epoch": 1.27,
"learning_rate": 3.137334824426969e-06,
"loss": 0.9351,
"step": 1590
},
{
"epoch": 1.27,
"learning_rate": 3.1313522669964975e-06,
"loss": 0.8472,
"step": 1591
},
{
"epoch": 1.27,
"learning_rate": 3.1253728175055242e-06,
"loss": 0.7966,
"step": 1592
},
{
"epoch": 1.27,
"learning_rate": 3.119396485899081e-06,
"loss": 0.9066,
"step": 1593
},
{
"epoch": 1.27,
"learning_rate": 3.1134232821170202e-06,
"loss": 0.9717,
"step": 1594
},
{
"epoch": 1.27,
"learning_rate": 3.107453216093985e-06,
"loss": 0.8848,
"step": 1595
},
{
"epoch": 1.27,
"learning_rate": 3.1014862977594083e-06,
"loss": 0.839,
"step": 1596
},
{
"epoch": 1.27,
"learning_rate": 3.095522537037481e-06,
"loss": 0.8969,
"step": 1597
},
{
"epoch": 1.27,
"learning_rate": 3.0895619438471445e-06,
"loss": 0.8717,
"step": 1598
},
{
"epoch": 1.27,
"learning_rate": 3.0836045281020716e-06,
"loss": 0.8822,
"step": 1599
},
{
"epoch": 1.27,
"learning_rate": 3.0776502997106526e-06,
"loss": 0.996,
"step": 1600
},
{
"epoch": 1.27,
"learning_rate": 3.071699268575974e-06,
"loss": 0.8553,
"step": 1601
},
{
"epoch": 1.28,
"learning_rate": 3.0657514445958055e-06,
"loss": 0.9065,
"step": 1602
},
{
"epoch": 1.28,
"learning_rate": 3.05980683766258e-06,
"loss": 1.0094,
"step": 1603
},
{
"epoch": 1.28,
"learning_rate": 3.0538654576633865e-06,
"loss": 0.895,
"step": 1604
},
{
"epoch": 1.28,
"learning_rate": 3.0479273144799406e-06,
"loss": 0.9133,
"step": 1605
},
{
"epoch": 1.28,
"learning_rate": 3.041992417988577e-06,
"loss": 0.9557,
"step": 1606
},
{
"epoch": 1.28,
"learning_rate": 3.036060778060228e-06,
"loss": 0.895,
"step": 1607
},
{
"epoch": 1.28,
"learning_rate": 3.0301324045604163e-06,
"loss": 0.8372,
"step": 1608
},
{
"epoch": 1.28,
"learning_rate": 3.0242073073492238e-06,
"loss": 0.8768,
"step": 1609
},
{
"epoch": 1.28,
"learning_rate": 3.018285496281287e-06,
"loss": 0.8515,
"step": 1610
},
{
"epoch": 1.28,
"learning_rate": 3.0123669812057766e-06,
"loss": 0.9035,
"step": 1611
},
{
"epoch": 1.28,
"learning_rate": 3.0064517719663833e-06,
"loss": 0.9016,
"step": 1612
},
{
"epoch": 1.28,
"learning_rate": 3.000539878401296e-06,
"loss": 0.9298,
"step": 1613
},
{
"epoch": 1.29,
"learning_rate": 2.9946313103431906e-06,
"loss": 0.9467,
"step": 1614
},
{
"epoch": 1.29,
"learning_rate": 2.988726077619211e-06,
"loss": 0.8935,
"step": 1615
},
{
"epoch": 1.29,
"learning_rate": 2.982824190050958e-06,
"loss": 0.8939,
"step": 1616
},
{
"epoch": 1.29,
"learning_rate": 2.9769256574544637e-06,
"loss": 0.9179,
"step": 1617
},
{
"epoch": 1.29,
"learning_rate": 2.9710304896401803e-06,
"loss": 0.9248,
"step": 1618
},
{
"epoch": 1.29,
"learning_rate": 2.9651386964129662e-06,
"loss": 0.8301,
"step": 1619
},
{
"epoch": 1.29,
"learning_rate": 2.959250287572069e-06,
"loss": 0.9291,
"step": 1620
},
{
"epoch": 1.29,
"learning_rate": 2.9533652729111027e-06,
"loss": 0.8621,
"step": 1621
},
{
"epoch": 1.29,
"learning_rate": 2.9474836622180377e-06,
"loss": 0.9292,
"step": 1622
},
{
"epoch": 1.29,
"learning_rate": 2.9416054652751834e-06,
"loss": 0.8903,
"step": 1623
},
{
"epoch": 1.29,
"learning_rate": 2.935730691859172e-06,
"loss": 0.8001,
"step": 1624
},
{
"epoch": 1.29,
"learning_rate": 2.9298593517409418e-06,
"loss": 0.8609,
"step": 1625
},
{
"epoch": 1.29,
"learning_rate": 2.923991454685719e-06,
"loss": 0.867,
"step": 1626
},
{
"epoch": 1.3,
"learning_rate": 2.9181270104530017e-06,
"loss": 0.8811,
"step": 1627
},
{
"epoch": 1.3,
"learning_rate": 2.912266028796554e-06,
"loss": 0.8131,
"step": 1628
},
{
"epoch": 1.3,
"learning_rate": 2.906408519464372e-06,
"loss": 0.8947,
"step": 1629
},
{
"epoch": 1.3,
"learning_rate": 2.9005544921986774e-06,
"loss": 0.9369,
"step": 1630
},
{
"epoch": 1.3,
"learning_rate": 2.894703956735906e-06,
"loss": 0.9602,
"step": 1631
},
{
"epoch": 1.3,
"learning_rate": 2.888856922806682e-06,
"loss": 0.819,
"step": 1632
},
{
"epoch": 1.3,
"learning_rate": 2.8830134001358057e-06,
"loss": 0.916,
"step": 1633
},
{
"epoch": 1.3,
"learning_rate": 2.8771733984422368e-06,
"loss": 0.9208,
"step": 1634
},
{
"epoch": 1.3,
"learning_rate": 2.871336927439082e-06,
"loss": 0.8902,
"step": 1635
},
{
"epoch": 1.3,
"learning_rate": 2.8655039968335774e-06,
"loss": 0.8991,
"step": 1636
},
{
"epoch": 1.3,
"learning_rate": 2.8596746163270646e-06,
"loss": 0.8917,
"step": 1637
},
{
"epoch": 1.3,
"learning_rate": 2.8538487956149813e-06,
"loss": 0.9087,
"step": 1638
},
{
"epoch": 1.3,
"learning_rate": 2.848026544386851e-06,
"loss": 0.8882,
"step": 1639
},
{
"epoch": 1.31,
"learning_rate": 2.842207872326255e-06,
"loss": 0.912,
"step": 1640
},
{
"epoch": 1.31,
"learning_rate": 2.836392789110821e-06,
"loss": 0.8991,
"step": 1641
},
{
"epoch": 1.31,
"learning_rate": 2.83058130441221e-06,
"loss": 0.7748,
"step": 1642
},
{
"epoch": 1.31,
"learning_rate": 2.824773427896098e-06,
"loss": 0.8675,
"step": 1643
},
{
"epoch": 1.31,
"learning_rate": 2.8189691692221627e-06,
"loss": 0.9373,
"step": 1644
},
{
"epoch": 1.31,
"learning_rate": 2.813168538044059e-06,
"loss": 0.8855,
"step": 1645
},
{
"epoch": 1.31,
"learning_rate": 2.8073715440094073e-06,
"loss": 0.8755,
"step": 1646
},
{
"epoch": 1.31,
"learning_rate": 2.8015781967597887e-06,
"loss": 0.8753,
"step": 1647
},
{
"epoch": 1.31,
"learning_rate": 2.7957885059307097e-06,
"loss": 0.8939,
"step": 1648
},
{
"epoch": 1.31,
"learning_rate": 2.790002481151598e-06,
"loss": 0.8612,
"step": 1649
},
{
"epoch": 1.31,
"learning_rate": 2.784220132045782e-06,
"loss": 0.8212,
"step": 1650
},
{
"epoch": 1.31,
"learning_rate": 2.778441468230483e-06,
"loss": 0.9118,
"step": 1651
},
{
"epoch": 1.32,
"learning_rate": 2.7726664993167864e-06,
"loss": 0.9352,
"step": 1652
},
{
"epoch": 1.32,
"learning_rate": 2.7668952349096363e-06,
"loss": 0.8962,
"step": 1653
},
{
"epoch": 1.32,
"learning_rate": 2.761127684607811e-06,
"loss": 0.9048,
"step": 1654
},
{
"epoch": 1.32,
"learning_rate": 2.7553638580039187e-06,
"loss": 0.9235,
"step": 1655
},
{
"epoch": 1.32,
"learning_rate": 2.749603764684367e-06,
"loss": 0.9464,
"step": 1656
},
{
"epoch": 1.32,
"learning_rate": 2.743847414229358e-06,
"loss": 0.8401,
"step": 1657
},
{
"epoch": 1.32,
"learning_rate": 2.738094816212866e-06,
"loss": 0.858,
"step": 1658
},
{
"epoch": 1.32,
"learning_rate": 2.7323459802026293e-06,
"loss": 0.8967,
"step": 1659
},
{
"epoch": 1.32,
"learning_rate": 2.7266009157601226e-06,
"loss": 0.9346,
"step": 1660
},
{
"epoch": 1.32,
"learning_rate": 2.7208596324405556e-06,
"loss": 0.8556,
"step": 1661
},
{
"epoch": 1.32,
"learning_rate": 2.7151221397928394e-06,
"loss": 0.9181,
"step": 1662
},
{
"epoch": 1.32,
"learning_rate": 2.709388447359592e-06,
"loss": 0.901,
"step": 1663
},
{
"epoch": 1.32,
"learning_rate": 2.703658564677101e-06,
"loss": 0.8942,
"step": 1664
},
{
"epoch": 1.33,
"learning_rate": 2.6979325012753214e-06,
"loss": 0.8482,
"step": 1665
},
{
"epoch": 1.33,
"learning_rate": 2.692210266677855e-06,
"loss": 0.8746,
"step": 1666
},
{
"epoch": 1.33,
"learning_rate": 2.6864918704019396e-06,
"loss": 0.8776,
"step": 1667
},
{
"epoch": 1.33,
"learning_rate": 2.680777321958424e-06,
"loss": 0.918,
"step": 1668
},
{
"epoch": 1.33,
"learning_rate": 2.6750666308517576e-06,
"loss": 0.8951,
"step": 1669
},
{
"epoch": 1.33,
"learning_rate": 2.6693598065799773e-06,
"loss": 0.9084,
"step": 1670
},
{
"epoch": 1.33,
"learning_rate": 2.66365685863469e-06,
"loss": 0.9156,
"step": 1671
},
{
"epoch": 1.33,
"learning_rate": 2.65795779650105e-06,
"loss": 0.9008,
"step": 1672
},
{
"epoch": 1.33,
"learning_rate": 2.6522626296577514e-06,
"loss": 0.8842,
"step": 1673
},
{
"epoch": 1.33,
"learning_rate": 2.646571367577009e-06,
"loss": 0.8379,
"step": 1674
},
{
"epoch": 1.33,
"learning_rate": 2.6408840197245454e-06,
"loss": 0.9456,
"step": 1675
},
{
"epoch": 1.33,
"learning_rate": 2.6352005955595715e-06,
"loss": 0.9455,
"step": 1676
},
{
"epoch": 1.34,
"learning_rate": 2.6295211045347724e-06,
"loss": 0.9023,
"step": 1677
},
{
"epoch": 1.34,
"learning_rate": 2.6238455560962884e-06,
"loss": 0.9092,
"step": 1678
},
{
"epoch": 1.34,
"learning_rate": 2.6181739596837075e-06,
"loss": 0.9582,
"step": 1679
},
{
"epoch": 1.34,
"learning_rate": 2.612506324730046e-06,
"loss": 0.8551,
"step": 1680
},
{
"epoch": 1.34,
"learning_rate": 2.6068426606617254e-06,
"loss": 0.8278,
"step": 1681
},
{
"epoch": 1.34,
"learning_rate": 2.6011829768985637e-06,
"loss": 0.8126,
"step": 1682
},
{
"epoch": 1.34,
"learning_rate": 2.5955272828537648e-06,
"loss": 0.9451,
"step": 1683
},
{
"epoch": 1.34,
"learning_rate": 2.589875587933892e-06,
"loss": 0.9407,
"step": 1684
},
{
"epoch": 1.34,
"learning_rate": 2.584227901538855e-06,
"loss": 0.9175,
"step": 1685
},
{
"epoch": 1.34,
"learning_rate": 2.5785842330619038e-06,
"loss": 0.9931,
"step": 1686
},
{
"epoch": 1.34,
"learning_rate": 2.572944591889598e-06,
"loss": 0.8906,
"step": 1687
},
{
"epoch": 1.34,
"learning_rate": 2.567308987401806e-06,
"loss": 0.9729,
"step": 1688
},
{
"epoch": 1.34,
"learning_rate": 2.561677428971676e-06,
"loss": 0.9097,
"step": 1689
},
{
"epoch": 1.35,
"learning_rate": 2.5560499259656323e-06,
"loss": 0.9269,
"step": 1690
},
{
"epoch": 1.35,
"learning_rate": 2.5504264877433517e-06,
"loss": 0.8575,
"step": 1691
},
{
"epoch": 1.35,
"learning_rate": 2.5448071236577493e-06,
"loss": 0.8795,
"step": 1692
},
{
"epoch": 1.35,
"learning_rate": 2.5391918430549635e-06,
"loss": 0.8863,
"step": 1693
},
{
"epoch": 1.35,
"learning_rate": 2.5335806552743463e-06,
"loss": 0.8542,
"step": 1694
},
{
"epoch": 1.35,
"learning_rate": 2.5279735696484375e-06,
"loss": 0.891,
"step": 1695
},
{
"epoch": 1.35,
"learning_rate": 2.522370595502954e-06,
"loss": 0.8795,
"step": 1696
},
{
"epoch": 1.35,
"learning_rate": 2.5167717421567773e-06,
"loss": 0.9436,
"step": 1697
},
{
"epoch": 1.35,
"learning_rate": 2.5111770189219365e-06,
"loss": 0.8353,
"step": 1698
},
{
"epoch": 1.35,
"learning_rate": 2.505586435103587e-06,
"loss": 0.8643,
"step": 1699
},
{
"epoch": 1.35,
"learning_rate": 2.5000000000000015e-06,
"loss": 0.8996,
"step": 1700
},
{
"epoch": 1.35,
"learning_rate": 2.49441772290255e-06,
"loss": 0.9319,
"step": 1701
},
{
"epoch": 1.36,
"learning_rate": 2.488839613095695e-06,
"loss": 0.9001,
"step": 1702
},
{
"epoch": 1.36,
"learning_rate": 2.4832656798569586e-06,
"loss": 0.938,
"step": 1703
},
{
"epoch": 1.36,
"learning_rate": 2.4776959324569193e-06,
"loss": 0.9285,
"step": 1704
},
{
"epoch": 1.36,
"learning_rate": 2.472130380159199e-06,
"loss": 0.8687,
"step": 1705
},
{
"epoch": 1.36,
"learning_rate": 2.466569032220433e-06,
"loss": 0.8986,
"step": 1706
},
{
"epoch": 1.36,
"learning_rate": 2.4610118978902732e-06,
"loss": 0.9299,
"step": 1707
},
{
"epoch": 1.36,
"learning_rate": 2.4554589864113566e-06,
"loss": 0.9046,
"step": 1708
},
{
"epoch": 1.36,
"learning_rate": 2.4499103070192982e-06,
"loss": 0.9966,
"step": 1709
},
{
"epoch": 1.36,
"learning_rate": 2.4443658689426788e-06,
"loss": 0.8124,
"step": 1710
},
{
"epoch": 1.36,
"learning_rate": 2.438825681403019e-06,
"loss": 0.9331,
"step": 1711
},
{
"epoch": 1.36,
"learning_rate": 2.4332897536147728e-06,
"loss": 0.9306,
"step": 1712
},
{
"epoch": 1.36,
"learning_rate": 2.4277580947853064e-06,
"loss": 0.8475,
"step": 1713
},
{
"epoch": 1.36,
"learning_rate": 2.422230714114891e-06,
"loss": 0.8832,
"step": 1714
},
{
"epoch": 1.37,
"learning_rate": 2.4167076207966813e-06,
"loss": 0.8375,
"step": 1715
},
{
"epoch": 1.37,
"learning_rate": 2.411188824016697e-06,
"loss": 0.867,
"step": 1716
},
{
"epoch": 1.37,
"learning_rate": 2.405674332953814e-06,
"loss": 0.8952,
"step": 1717
},
{
"epoch": 1.37,
"learning_rate": 2.40016415677975e-06,
"loss": 0.8323,
"step": 1718
},
{
"epoch": 1.37,
"learning_rate": 2.394658304659042e-06,
"loss": 0.914,
"step": 1719
},
{
"epoch": 1.37,
"learning_rate": 2.3891567857490373e-06,
"loss": 0.9318,
"step": 1720
},
{
"epoch": 1.37,
"learning_rate": 2.383659609199873e-06,
"loss": 0.9017,
"step": 1721
},
{
"epoch": 1.37,
"learning_rate": 2.378166784154471e-06,
"loss": 0.8366,
"step": 1722
},
{
"epoch": 1.37,
"learning_rate": 2.372678319748507e-06,
"loss": 0.8567,
"step": 1723
},
{
"epoch": 1.37,
"learning_rate": 2.3671942251104125e-06,
"loss": 0.8963,
"step": 1724
},
{
"epoch": 1.37,
"learning_rate": 2.3617145093613436e-06,
"loss": 0.8521,
"step": 1725
},
{
"epoch": 1.37,
"learning_rate": 2.3562391816151807e-06,
"loss": 0.843,
"step": 1726
},
{
"epoch": 1.38,
"learning_rate": 2.3507682509785003e-06,
"loss": 0.8769,
"step": 1727
},
{
"epoch": 1.38,
"learning_rate": 2.345301726550567e-06,
"loss": 0.8601,
"step": 1728
},
{
"epoch": 1.38,
"learning_rate": 2.339839617423318e-06,
"loss": 0.9377,
"step": 1729
},
{
"epoch": 1.38,
"learning_rate": 2.3343819326813475e-06,
"loss": 0.8625,
"step": 1730
},
{
"epoch": 1.38,
"learning_rate": 2.3289286814018884e-06,
"loss": 0.8909,
"step": 1731
},
{
"epoch": 1.38,
"learning_rate": 2.323479872654805e-06,
"loss": 0.8255,
"step": 1732
},
{
"epoch": 1.38,
"learning_rate": 2.318035515502565e-06,
"loss": 0.8222,
"step": 1733
},
{
"epoch": 1.38,
"learning_rate": 2.312595619000241e-06,
"loss": 0.8979,
"step": 1734
},
{
"epoch": 1.38,
"learning_rate": 2.3071601921954797e-06,
"loss": 0.9277,
"step": 1735
},
{
"epoch": 1.38,
"learning_rate": 2.301729244128496e-06,
"loss": 0.8893,
"step": 1736
},
{
"epoch": 1.38,
"learning_rate": 2.2963027838320557e-06,
"loss": 0.9507,
"step": 1737
},
{
"epoch": 1.38,
"learning_rate": 2.2908808203314637e-06,
"loss": 0.8812,
"step": 1738
},
{
"epoch": 1.38,
"learning_rate": 2.285463362644541e-06,
"loss": 0.803,
"step": 1739
},
{
"epoch": 1.39,
"learning_rate": 2.2800504197816147e-06,
"loss": 0.8423,
"step": 1740
},
{
"epoch": 1.39,
"learning_rate": 2.2746420007455073e-06,
"loss": 0.8713,
"step": 1741
},
{
"epoch": 1.39,
"learning_rate": 2.269238114531515e-06,
"loss": 0.8891,
"step": 1742
},
{
"epoch": 1.39,
"learning_rate": 2.2638387701273947e-06,
"loss": 0.8946,
"step": 1743
},
{
"epoch": 1.39,
"learning_rate": 2.2584439765133453e-06,
"loss": 0.9424,
"step": 1744
},
{
"epoch": 1.39,
"learning_rate": 2.253053742662006e-06,
"loss": 0.9199,
"step": 1745
},
{
"epoch": 1.39,
"learning_rate": 2.247668077538424e-06,
"loss": 0.8261,
"step": 1746
},
{
"epoch": 1.39,
"learning_rate": 2.242286990100052e-06,
"loss": 0.812,
"step": 1747
},
{
"epoch": 1.39,
"learning_rate": 2.2369104892967253e-06,
"loss": 0.885,
"step": 1748
},
{
"epoch": 1.39,
"learning_rate": 2.2315385840706548e-06,
"loss": 0.8365,
"step": 1749
},
{
"epoch": 1.39,
"learning_rate": 2.226171283356409e-06,
"loss": 0.8108,
"step": 1750
},
{
"epoch": 1.39,
"learning_rate": 2.2208085960808936e-06,
"loss": 0.8988,
"step": 1751
},
{
"epoch": 1.39,
"learning_rate": 2.2154505311633406e-06,
"loss": 0.8626,
"step": 1752
},
{
"epoch": 1.4,
"learning_rate": 2.210097097515301e-06,
"loss": 0.8751,
"step": 1753
},
{
"epoch": 1.4,
"learning_rate": 2.2047483040406175e-06,
"loss": 0.8351,
"step": 1754
},
{
"epoch": 1.4,
"learning_rate": 2.199404159635416e-06,
"loss": 0.8659,
"step": 1755
},
{
"epoch": 1.4,
"learning_rate": 2.1940646731880887e-06,
"loss": 0.9469,
"step": 1756
},
{
"epoch": 1.4,
"learning_rate": 2.1887298535792863e-06,
"loss": 0.8008,
"step": 1757
},
{
"epoch": 1.4,
"learning_rate": 2.1833997096818897e-06,
"loss": 0.8938,
"step": 1758
},
{
"epoch": 1.4,
"learning_rate": 2.178074250361012e-06,
"loss": 0.9093,
"step": 1759
},
{
"epoch": 1.4,
"learning_rate": 2.1727534844739658e-06,
"loss": 0.9271,
"step": 1760
},
{
"epoch": 1.4,
"learning_rate": 2.1674374208702658e-06,
"loss": 0.9098,
"step": 1761
},
{
"epoch": 1.4,
"learning_rate": 2.162126068391601e-06,
"loss": 0.9154,
"step": 1762
},
{
"epoch": 1.4,
"learning_rate": 2.156819435871824e-06,
"loss": 0.9049,
"step": 1763
},
{
"epoch": 1.4,
"learning_rate": 2.151517532136939e-06,
"loss": 0.8597,
"step": 1764
},
{
"epoch": 1.41,
"learning_rate": 2.1462203660050884e-06,
"loss": 0.9009,
"step": 1765
},
{
"epoch": 1.41,
"learning_rate": 2.140927946286528e-06,
"loss": 0.8945,
"step": 1766
},
{
"epoch": 1.41,
"learning_rate": 2.135640281783627e-06,
"loss": 0.8909,
"step": 1767
},
{
"epoch": 1.41,
"learning_rate": 2.1303573812908383e-06,
"loss": 0.8572,
"step": 1768
},
{
"epoch": 1.41,
"learning_rate": 2.1250792535946995e-06,
"loss": 0.8466,
"step": 1769
},
{
"epoch": 1.41,
"learning_rate": 2.1198059074738027e-06,
"loss": 0.8732,
"step": 1770
},
{
"epoch": 1.41,
"learning_rate": 2.11453735169879e-06,
"loss": 0.787,
"step": 1771
},
{
"epoch": 1.41,
"learning_rate": 2.109273595032335e-06,
"loss": 0.8027,
"step": 1772
},
{
"epoch": 1.41,
"learning_rate": 2.104014646229134e-06,
"loss": 0.9616,
"step": 1773
},
{
"epoch": 1.41,
"learning_rate": 2.0987605140358823e-06,
"loss": 0.8506,
"step": 1774
},
{
"epoch": 1.41,
"learning_rate": 2.0935112071912635e-06,
"loss": 0.894,
"step": 1775
},
{
"epoch": 1.41,
"learning_rate": 2.0882667344259384e-06,
"loss": 0.836,
"step": 1776
},
{
"epoch": 1.41,
"learning_rate": 2.08302710446253e-06,
"loss": 0.8574,
"step": 1777
},
{
"epoch": 1.42,
"learning_rate": 2.077792326015602e-06,
"loss": 0.8811,
"step": 1778
},
{
"epoch": 1.42,
"learning_rate": 2.0725624077916497e-06,
"loss": 0.8808,
"step": 1779
},
{
"epoch": 1.42,
"learning_rate": 2.0673373584890847e-06,
"loss": 0.8835,
"step": 1780
},
{
"epoch": 1.42,
"learning_rate": 2.062117186798226e-06,
"loss": 0.8645,
"step": 1781
},
{
"epoch": 1.42,
"learning_rate": 2.056901901401273e-06,
"loss": 0.8593,
"step": 1782
},
{
"epoch": 1.42,
"learning_rate": 2.0516915109723003e-06,
"loss": 0.9399,
"step": 1783
},
{
"epoch": 1.42,
"learning_rate": 2.0464860241772454e-06,
"loss": 0.8664,
"step": 1784
},
{
"epoch": 1.42,
"learning_rate": 2.0412854496738828e-06,
"loss": 0.8152,
"step": 1785
},
{
"epoch": 1.42,
"learning_rate": 2.036089796111825e-06,
"loss": 0.9524,
"step": 1786
},
{
"epoch": 1.42,
"learning_rate": 2.030899072132493e-06,
"loss": 0.9013,
"step": 1787
},
{
"epoch": 1.42,
"learning_rate": 2.0257132863691108e-06,
"loss": 0.9072,
"step": 1788
},
{
"epoch": 1.42,
"learning_rate": 2.020532447446693e-06,
"loss": 0.8783,
"step": 1789
},
{
"epoch": 1.43,
"learning_rate": 2.0153565639820228e-06,
"loss": 0.8766,
"step": 1790
},
{
"epoch": 1.43,
"learning_rate": 2.010185644583641e-06,
"loss": 0.91,
"step": 1791
},
{
"epoch": 1.43,
"learning_rate": 2.0050196978518323e-06,
"loss": 0.8544,
"step": 1792
},
{
"epoch": 1.43,
"learning_rate": 1.9998587323786135e-06,
"loss": 0.8631,
"step": 1793
},
{
"epoch": 1.43,
"learning_rate": 1.9947027567477175e-06,
"loss": 0.9516,
"step": 1794
},
{
"epoch": 1.43,
"learning_rate": 1.989551779534571e-06,
"loss": 0.9283,
"step": 1795
},
{
"epoch": 1.43,
"learning_rate": 1.9844058093062962e-06,
"loss": 0.9573,
"step": 1796
},
{
"epoch": 1.43,
"learning_rate": 1.9792648546216816e-06,
"loss": 0.891,
"step": 1797
},
{
"epoch": 1.43,
"learning_rate": 1.9741289240311757e-06,
"loss": 0.8577,
"step": 1798
},
{
"epoch": 1.43,
"learning_rate": 1.968998026076868e-06,
"loss": 0.9657,
"step": 1799
},
{
"epoch": 1.43,
"learning_rate": 1.963872169292486e-06,
"loss": 0.8454,
"step": 1800
},
{
"epoch": 1.43,
"learning_rate": 1.9587513622033647e-06,
"loss": 0.8984,
"step": 1801
},
{
"epoch": 1.43,
"learning_rate": 1.9536356133264407e-06,
"loss": 0.913,
"step": 1802
},
{
"epoch": 1.44,
"learning_rate": 1.9485249311702426e-06,
"loss": 0.9037,
"step": 1803
},
{
"epoch": 1.44,
"learning_rate": 1.943419324234871e-06,
"loss": 0.883,
"step": 1804
},
{
"epoch": 1.44,
"learning_rate": 1.9383188010119818e-06,
"loss": 0.8536,
"step": 1805
},
{
"epoch": 1.44,
"learning_rate": 1.933223369984778e-06,
"loss": 0.8417,
"step": 1806
},
{
"epoch": 1.44,
"learning_rate": 1.9281330396279914e-06,
"loss": 0.9231,
"step": 1807
},
{
"epoch": 1.44,
"learning_rate": 1.923047818407875e-06,
"loss": 0.9426,
"step": 1808
},
{
"epoch": 1.44,
"learning_rate": 1.91796771478218e-06,
"loss": 0.8662,
"step": 1809
},
{
"epoch": 1.44,
"learning_rate": 1.9128927372001456e-06,
"loss": 0.8832,
"step": 1810
},
{
"epoch": 1.44,
"learning_rate": 1.9078228941024897e-06,
"loss": 0.9414,
"step": 1811
},
{
"epoch": 1.44,
"learning_rate": 1.9027581939213852e-06,
"loss": 0.9393,
"step": 1812
},
{
"epoch": 1.44,
"learning_rate": 1.8976986450804564e-06,
"loss": 0.8451,
"step": 1813
},
{
"epoch": 1.44,
"learning_rate": 1.8926442559947561e-06,
"loss": 0.8935,
"step": 1814
},
{
"epoch": 1.45,
"learning_rate": 1.887595035070755e-06,
"loss": 0.9561,
"step": 1815
},
{
"epoch": 1.45,
"learning_rate": 1.8825509907063328e-06,
"loss": 0.9104,
"step": 1816
},
{
"epoch": 1.45,
"learning_rate": 1.8775121312907552e-06,
"loss": 0.8605,
"step": 1817
},
{
"epoch": 1.45,
"learning_rate": 1.8724784652046656e-06,
"loss": 0.9227,
"step": 1818
},
{
"epoch": 1.45,
"learning_rate": 1.8674500008200675e-06,
"loss": 0.9957,
"step": 1819
},
{
"epoch": 1.45,
"learning_rate": 1.8624267465003176e-06,
"loss": 0.9188,
"step": 1820
},
{
"epoch": 1.45,
"learning_rate": 1.857408710600106e-06,
"loss": 0.8946,
"step": 1821
},
{
"epoch": 1.45,
"learning_rate": 1.852395901465441e-06,
"loss": 0.8488,
"step": 1822
},
{
"epoch": 1.45,
"learning_rate": 1.8473883274336362e-06,
"loss": 0.8315,
"step": 1823
},
{
"epoch": 1.45,
"learning_rate": 1.8423859968333063e-06,
"loss": 0.9671,
"step": 1824
},
{
"epoch": 1.45,
"learning_rate": 1.8373889179843373e-06,
"loss": 0.8945,
"step": 1825
},
{
"epoch": 1.45,
"learning_rate": 1.8323970991978823e-06,
"loss": 0.869,
"step": 1826
},
{
"epoch": 1.45,
"learning_rate": 1.8274105487763461e-06,
"loss": 0.8515,
"step": 1827
},
{
"epoch": 1.46,
"learning_rate": 1.8224292750133743e-06,
"loss": 0.9006,
"step": 1828
},
{
"epoch": 1.46,
"learning_rate": 1.8174532861938299e-06,
"loss": 0.9097,
"step": 1829
},
{
"epoch": 1.46,
"learning_rate": 1.8124825905937938e-06,
"loss": 0.8922,
"step": 1830
},
{
"epoch": 1.46,
"learning_rate": 1.8075171964805355e-06,
"loss": 0.8624,
"step": 1831
},
{
"epoch": 1.46,
"learning_rate": 1.8025571121125141e-06,
"loss": 0.9009,
"step": 1832
},
{
"epoch": 1.46,
"learning_rate": 1.797602345739352e-06,
"loss": 0.7672,
"step": 1833
},
{
"epoch": 1.46,
"learning_rate": 1.79265290560183e-06,
"loss": 0.8658,
"step": 1834
},
{
"epoch": 1.46,
"learning_rate": 1.787708799931866e-06,
"loss": 0.8412,
"step": 1835
},
{
"epoch": 1.46,
"learning_rate": 1.7827700369525125e-06,
"loss": 0.896,
"step": 1836
},
{
"epoch": 1.46,
"learning_rate": 1.777836624877929e-06,
"loss": 0.9508,
"step": 1837
},
{
"epoch": 1.46,
"learning_rate": 1.7729085719133815e-06,
"loss": 0.8568,
"step": 1838
},
{
"epoch": 1.46,
"learning_rate": 1.7679858862552175e-06,
"loss": 0.8507,
"step": 1839
},
{
"epoch": 1.46,
"learning_rate": 1.7630685760908623e-06,
"loss": 0.8878,
"step": 1840
},
{
"epoch": 1.47,
"learning_rate": 1.7581566495987961e-06,
"loss": 0.8705,
"step": 1841
},
{
"epoch": 1.47,
"learning_rate": 1.7532501149485487e-06,
"loss": 0.9159,
"step": 1842
},
{
"epoch": 1.47,
"learning_rate": 1.7483489803006775e-06,
"loss": 0.9908,
"step": 1843
},
{
"epoch": 1.47,
"learning_rate": 1.7434532538067655e-06,
"loss": 0.8236,
"step": 1844
},
{
"epoch": 1.47,
"learning_rate": 1.7385629436093958e-06,
"loss": 0.8849,
"step": 1845
},
{
"epoch": 1.47,
"learning_rate": 1.733678057842142e-06,
"loss": 0.8587,
"step": 1846
},
{
"epoch": 1.47,
"learning_rate": 1.7287986046295597e-06,
"loss": 0.9574,
"step": 1847
},
{
"epoch": 1.47,
"learning_rate": 1.72392459208717e-06,
"loss": 0.8744,
"step": 1848
},
{
"epoch": 1.47,
"learning_rate": 1.7190560283214396e-06,
"loss": 0.8578,
"step": 1849
},
{
"epoch": 1.47,
"learning_rate": 1.7141929214297753e-06,
"loss": 0.8139,
"step": 1850
},
{
"epoch": 1.47,
"learning_rate": 1.7093352795005108e-06,
"loss": 0.8799,
"step": 1851
},
{
"epoch": 1.47,
"learning_rate": 1.7044831106128867e-06,
"loss": 0.8495,
"step": 1852
},
{
"epoch": 1.48,
"learning_rate": 1.6996364228370426e-06,
"loss": 0.9133,
"step": 1853
},
{
"epoch": 1.48,
"learning_rate": 1.6947952242339993e-06,
"loss": 0.8391,
"step": 1854
},
{
"epoch": 1.48,
"learning_rate": 1.689959522855652e-06,
"loss": 0.8352,
"step": 1855
},
{
"epoch": 1.48,
"learning_rate": 1.6851293267447527e-06,
"loss": 0.9387,
"step": 1856
},
{
"epoch": 1.48,
"learning_rate": 1.680304643934894e-06,
"loss": 0.8622,
"step": 1857
},
{
"epoch": 1.48,
"learning_rate": 1.675485482450499e-06,
"loss": 0.8768,
"step": 1858
},
{
"epoch": 1.48,
"learning_rate": 1.6706718503068115e-06,
"loss": 0.8867,
"step": 1859
},
{
"epoch": 1.48,
"learning_rate": 1.6658637555098744e-06,
"loss": 0.8578,
"step": 1860
},
{
"epoch": 1.48,
"learning_rate": 1.6610612060565235e-06,
"loss": 0.8234,
"step": 1861
},
{
"epoch": 1.48,
"learning_rate": 1.6562642099343684e-06,
"loss": 0.8725,
"step": 1862
},
{
"epoch": 1.48,
"learning_rate": 1.651472775121789e-06,
"loss": 0.8507,
"step": 1863
},
{
"epoch": 1.48,
"learning_rate": 1.6466869095879079e-06,
"loss": 0.8931,
"step": 1864
},
{
"epoch": 1.48,
"learning_rate": 1.6419066212925911e-06,
"loss": 0.8915,
"step": 1865
},
{
"epoch": 1.49,
"learning_rate": 1.6371319181864232e-06,
"loss": 0.8682,
"step": 1866
},
{
"epoch": 1.49,
"learning_rate": 1.6323628082107052e-06,
"loss": 0.8803,
"step": 1867
},
{
"epoch": 1.49,
"learning_rate": 1.627599299297431e-06,
"loss": 0.909,
"step": 1868
},
{
"epoch": 1.49,
"learning_rate": 1.6228413993692798e-06,
"loss": 0.928,
"step": 1869
},
{
"epoch": 1.49,
"learning_rate": 1.6180891163396013e-06,
"loss": 0.8652,
"step": 1870
},
{
"epoch": 1.49,
"learning_rate": 1.6133424581124073e-06,
"loss": 0.9208,
"step": 1871
},
{
"epoch": 1.49,
"learning_rate": 1.6086014325823485e-06,
"loss": 0.8921,
"step": 1872
},
{
"epoch": 1.49,
"learning_rate": 1.6038660476347135e-06,
"loss": 0.8421,
"step": 1873
},
{
"epoch": 1.49,
"learning_rate": 1.5991363111454023e-06,
"loss": 0.9365,
"step": 1874
},
{
"epoch": 1.49,
"learning_rate": 1.594412230980928e-06,
"loss": 0.8777,
"step": 1875
},
{
"epoch": 1.49,
"learning_rate": 1.589693814998391e-06,
"loss": 0.8669,
"step": 1876
},
{
"epoch": 1.49,
"learning_rate": 1.584981071045471e-06,
"loss": 0.8823,
"step": 1877
},
{
"epoch": 1.5,
"learning_rate": 1.580274006960415e-06,
"loss": 0.8564,
"step": 1878
},
{
"epoch": 1.5,
"learning_rate": 1.5755726305720266e-06,
"loss": 0.9287,
"step": 1879
},
{
"epoch": 1.5,
"learning_rate": 1.5708769496996445e-06,
"loss": 0.8237,
"step": 1880
},
{
"epoch": 1.5,
"learning_rate": 1.5661869721531354e-06,
"loss": 0.8806,
"step": 1881
},
{
"epoch": 1.5,
"learning_rate": 1.561502705732883e-06,
"loss": 0.9072,
"step": 1882
},
{
"epoch": 1.5,
"learning_rate": 1.5568241582297717e-06,
"loss": 0.909,
"step": 1883
},
{
"epoch": 1.5,
"learning_rate": 1.552151337425173e-06,
"loss": 0.9087,
"step": 1884
},
{
"epoch": 1.5,
"learning_rate": 1.5474842510909321e-06,
"loss": 0.8432,
"step": 1885
},
{
"epoch": 1.5,
"learning_rate": 1.5428229069893586e-06,
"loss": 0.8462,
"step": 1886
},
{
"epoch": 1.5,
"learning_rate": 1.5381673128732132e-06,
"loss": 0.8692,
"step": 1887
},
{
"epoch": 1.5,
"learning_rate": 1.533517476485691e-06,
"loss": 0.8646,
"step": 1888
},
{
"epoch": 1.5,
"learning_rate": 1.5288734055604087e-06,
"loss": 0.8793,
"step": 1889
},
{
"epoch": 1.5,
"learning_rate": 1.5242351078214008e-06,
"loss": 0.8331,
"step": 1890
},
{
"epoch": 1.51,
"learning_rate": 1.5196025909830913e-06,
"loss": 0.8764,
"step": 1891
},
{
"epoch": 1.51,
"learning_rate": 1.514975862750297e-06,
"loss": 0.8904,
"step": 1892
},
{
"epoch": 1.51,
"learning_rate": 1.5103549308182024e-06,
"loss": 0.8782,
"step": 1893
},
{
"epoch": 1.51,
"learning_rate": 1.5057398028723514e-06,
"loss": 0.9421,
"step": 1894
},
{
"epoch": 1.51,
"learning_rate": 1.5011304865886383e-06,
"loss": 0.8947,
"step": 1895
},
{
"epoch": 1.51,
"learning_rate": 1.4965269896332884e-06,
"loss": 0.8684,
"step": 1896
},
{
"epoch": 1.51,
"learning_rate": 1.4919293196628492e-06,
"loss": 0.8384,
"step": 1897
},
{
"epoch": 1.51,
"learning_rate": 1.487337484324175e-06,
"loss": 0.8883,
"step": 1898
},
{
"epoch": 1.51,
"learning_rate": 1.4827514912544194e-06,
"loss": 0.9006,
"step": 1899
},
{
"epoch": 1.51,
"learning_rate": 1.4781713480810184e-06,
"loss": 0.8926,
"step": 1900
},
{
"epoch": 1.51,
"learning_rate": 1.4735970624216756e-06,
"loss": 0.8742,
"step": 1901
},
{
"epoch": 1.51,
"learning_rate": 1.4690286418843535e-06,
"loss": 0.9139,
"step": 1902
},
{
"epoch": 1.52,
"learning_rate": 1.4644660940672628e-06,
"loss": 0.8898,
"step": 1903
},
{
"epoch": 1.52,
"learning_rate": 1.4599094265588432e-06,
"loss": 0.8688,
"step": 1904
},
{
"epoch": 1.52,
"learning_rate": 1.455358646937753e-06,
"loss": 0.8665,
"step": 1905
},
{
"epoch": 1.52,
"learning_rate": 1.450813762772863e-06,
"loss": 0.8588,
"step": 1906
},
{
"epoch": 1.52,
"learning_rate": 1.4462747816232353e-06,
"loss": 0.8355,
"step": 1907
},
{
"epoch": 1.52,
"learning_rate": 1.4417417110381126e-06,
"loss": 0.9556,
"step": 1908
},
{
"epoch": 1.52,
"learning_rate": 1.4372145585569098e-06,
"loss": 0.8626,
"step": 1909
},
{
"epoch": 1.52,
"learning_rate": 1.4326933317092e-06,
"loss": 0.9052,
"step": 1910
},
{
"epoch": 1.52,
"learning_rate": 1.4281780380146976e-06,
"loss": 0.9067,
"step": 1911
},
{
"epoch": 1.52,
"learning_rate": 1.4236686849832497e-06,
"loss": 0.9509,
"step": 1912
},
{
"epoch": 1.52,
"learning_rate": 1.419165280114822e-06,
"loss": 0.8797,
"step": 1913
},
{
"epoch": 1.52,
"learning_rate": 1.4146678308994916e-06,
"loss": 0.8559,
"step": 1914
},
{
"epoch": 1.52,
"learning_rate": 1.410176344817425e-06,
"loss": 0.9217,
"step": 1915
},
{
"epoch": 1.53,
"learning_rate": 1.405690829338872e-06,
"loss": 0.8645,
"step": 1916
},
{
"epoch": 1.53,
"learning_rate": 1.4012112919241562e-06,
"loss": 0.928,
"step": 1917
},
{
"epoch": 1.53,
"learning_rate": 1.3967377400236515e-06,
"loss": 0.8554,
"step": 1918
},
{
"epoch": 1.53,
"learning_rate": 1.3922701810777838e-06,
"loss": 0.9346,
"step": 1919
},
{
"epoch": 1.53,
"learning_rate": 1.3878086225170067e-06,
"loss": 0.9426,
"step": 1920
},
{
"epoch": 1.53,
"learning_rate": 1.3833530717617938e-06,
"loss": 0.9003,
"step": 1921
},
{
"epoch": 1.53,
"learning_rate": 1.3789035362226305e-06,
"loss": 0.8739,
"step": 1922
},
{
"epoch": 1.53,
"learning_rate": 1.374460023299995e-06,
"loss": 0.7927,
"step": 1923
},
{
"epoch": 1.53,
"learning_rate": 1.370022540384347e-06,
"loss": 0.8163,
"step": 1924
},
{
"epoch": 1.53,
"learning_rate": 1.365591094856119e-06,
"loss": 0.9116,
"step": 1925
},
{
"epoch": 1.53,
"learning_rate": 1.3611656940857037e-06,
"loss": 0.8204,
"step": 1926
},
{
"epoch": 1.53,
"learning_rate": 1.356746345433439e-06,
"loss": 0.8936,
"step": 1927
},
{
"epoch": 1.54,
"learning_rate": 1.352333056249595e-06,
"loss": 0.9018,
"step": 1928
},
{
"epoch": 1.54,
"learning_rate": 1.3479258338743644e-06,
"loss": 0.9078,
"step": 1929
},
{
"epoch": 1.54,
"learning_rate": 1.3435246856378524e-06,
"loss": 0.9513,
"step": 1930
},
{
"epoch": 1.54,
"learning_rate": 1.3391296188600594e-06,
"loss": 0.9226,
"step": 1931
},
{
"epoch": 1.54,
"learning_rate": 1.3347406408508695e-06,
"loss": 0.8697,
"step": 1932
},
{
"epoch": 1.54,
"learning_rate": 1.330357758910042e-06,
"loss": 0.8938,
"step": 1933
},
{
"epoch": 1.54,
"learning_rate": 1.3259809803271984e-06,
"loss": 0.9313,
"step": 1934
},
{
"epoch": 1.54,
"learning_rate": 1.3216103123818047e-06,
"loss": 0.9496,
"step": 1935
},
{
"epoch": 1.54,
"learning_rate": 1.3172457623431706e-06,
"loss": 0.8629,
"step": 1936
},
{
"epoch": 1.54,
"learning_rate": 1.3128873374704227e-06,
"loss": 0.8945,
"step": 1937
},
{
"epoch": 1.54,
"learning_rate": 1.3085350450125073e-06,
"loss": 0.878,
"step": 1938
},
{
"epoch": 1.54,
"learning_rate": 1.3041888922081658e-06,
"loss": 0.8276,
"step": 1939
},
{
"epoch": 1.54,
"learning_rate": 1.2998488862859305e-06,
"loss": 0.9612,
"step": 1940
},
{
"epoch": 1.55,
"learning_rate": 1.2955150344641087e-06,
"loss": 0.8824,
"step": 1941
},
{
"epoch": 1.55,
"learning_rate": 1.2911873439507766e-06,
"loss": 0.7609,
"step": 1942
},
{
"epoch": 1.55,
"learning_rate": 1.2868658219437558e-06,
"loss": 0.8623,
"step": 1943
},
{
"epoch": 1.55,
"learning_rate": 1.2825504756306156e-06,
"loss": 0.8333,
"step": 1944
},
{
"epoch": 1.55,
"learning_rate": 1.2782413121886483e-06,
"loss": 0.8056,
"step": 1945
},
{
"epoch": 1.55,
"learning_rate": 1.2739383387848674e-06,
"loss": 0.9044,
"step": 1946
},
{
"epoch": 1.55,
"learning_rate": 1.2696415625759871e-06,
"loss": 0.8801,
"step": 1947
},
{
"epoch": 1.55,
"learning_rate": 1.2653509907084171e-06,
"loss": 0.9357,
"step": 1948
},
{
"epoch": 1.55,
"learning_rate": 1.2610666303182444e-06,
"loss": 0.8892,
"step": 1949
},
{
"epoch": 1.55,
"learning_rate": 1.256788488531232e-06,
"loss": 0.877,
"step": 1950
},
{
"epoch": 1.55,
"learning_rate": 1.2525165724627937e-06,
"loss": 0.865,
"step": 1951
},
{
"epoch": 1.55,
"learning_rate": 1.2482508892179884e-06,
"loss": 0.8387,
"step": 1952
},
{
"epoch": 1.55,
"learning_rate": 1.2439914458915137e-06,
"loss": 0.8767,
"step": 1953
},
{
"epoch": 1.56,
"learning_rate": 1.2397382495676873e-06,
"loss": 0.9064,
"step": 1954
},
{
"epoch": 1.56,
"learning_rate": 1.2354913073204345e-06,
"loss": 0.8876,
"step": 1955
},
{
"epoch": 1.56,
"learning_rate": 1.2312506262132795e-06,
"loss": 0.8744,
"step": 1956
},
{
"epoch": 1.56,
"learning_rate": 1.2270162132993325e-06,
"loss": 0.9406,
"step": 1957
},
{
"epoch": 1.56,
"learning_rate": 1.2227880756212824e-06,
"loss": 0.9655,
"step": 1958
},
{
"epoch": 1.56,
"learning_rate": 1.2185662202113764e-06,
"loss": 0.8192,
"step": 1959
},
{
"epoch": 1.56,
"learning_rate": 1.214350654091413e-06,
"loss": 0.8152,
"step": 1960
},
{
"epoch": 1.56,
"learning_rate": 1.2101413842727345e-06,
"loss": 0.9139,
"step": 1961
},
{
"epoch": 1.56,
"learning_rate": 1.20593841775621e-06,
"loss": 0.8756,
"step": 1962
},
{
"epoch": 1.56,
"learning_rate": 1.201741761532222e-06,
"loss": 0.8885,
"step": 1963
},
{
"epoch": 1.56,
"learning_rate": 1.1975514225806573e-06,
"loss": 0.849,
"step": 1964
},
{
"epoch": 1.56,
"learning_rate": 1.1933674078709022e-06,
"loss": 0.9096,
"step": 1965
},
{
"epoch": 1.57,
"learning_rate": 1.1891897243618184e-06,
"loss": 0.9313,
"step": 1966
},
{
"epoch": 1.57,
"learning_rate": 1.185018379001739e-06,
"loss": 0.8715,
"step": 1967
},
{
"epoch": 1.57,
"learning_rate": 1.1808533787284543e-06,
"loss": 0.8757,
"step": 1968
},
{
"epoch": 1.57,
"learning_rate": 1.1766947304692061e-06,
"loss": 0.9065,
"step": 1969
},
{
"epoch": 1.57,
"learning_rate": 1.1725424411406656e-06,
"loss": 0.8848,
"step": 1970
},
{
"epoch": 1.57,
"learning_rate": 1.1683965176489336e-06,
"loss": 0.9633,
"step": 1971
},
{
"epoch": 1.57,
"learning_rate": 1.1642569668895171e-06,
"loss": 0.8551,
"step": 1972
},
{
"epoch": 1.57,
"learning_rate": 1.16012379574733e-06,
"loss": 0.8829,
"step": 1973
},
{
"epoch": 1.57,
"learning_rate": 1.1559970110966707e-06,
"loss": 0.9781,
"step": 1974
},
{
"epoch": 1.57,
"learning_rate": 1.1518766198012188e-06,
"loss": 0.8799,
"step": 1975
},
{
"epoch": 1.57,
"learning_rate": 1.1477626287140164e-06,
"loss": 0.8579,
"step": 1976
},
{
"epoch": 1.57,
"learning_rate": 1.143655044677468e-06,
"loss": 0.911,
"step": 1977
},
{
"epoch": 1.57,
"learning_rate": 1.139553874523313e-06,
"loss": 0.8528,
"step": 1978
},
{
"epoch": 1.58,
"learning_rate": 1.1354591250726316e-06,
"loss": 0.9328,
"step": 1979
},
{
"epoch": 1.58,
"learning_rate": 1.1313708031358183e-06,
"loss": 0.8545,
"step": 1980
},
{
"epoch": 1.58,
"learning_rate": 1.1272889155125821e-06,
"loss": 0.9764,
"step": 1981
},
{
"epoch": 1.58,
"learning_rate": 1.1232134689919277e-06,
"loss": 0.8959,
"step": 1982
},
{
"epoch": 1.58,
"learning_rate": 1.1191444703521482e-06,
"loss": 0.8564,
"step": 1983
},
{
"epoch": 1.58,
"learning_rate": 1.1150819263608098e-06,
"loss": 0.8947,
"step": 1984
},
{
"epoch": 1.58,
"learning_rate": 1.111025843774749e-06,
"loss": 0.865,
"step": 1985
},
{
"epoch": 1.58,
"learning_rate": 1.1069762293400505e-06,
"loss": 0.9693,
"step": 1986
},
{
"epoch": 1.58,
"learning_rate": 1.102933089792042e-06,
"loss": 0.8741,
"step": 1987
},
{
"epoch": 1.58,
"learning_rate": 1.0988964318552848e-06,
"loss": 0.8856,
"step": 1988
},
{
"epoch": 1.58,
"learning_rate": 1.0948662622435591e-06,
"loss": 0.899,
"step": 1989
},
{
"epoch": 1.58,
"learning_rate": 1.0908425876598512e-06,
"loss": 0.8277,
"step": 1990
},
{
"epoch": 1.59,
"learning_rate": 1.0868254147963475e-06,
"loss": 0.9063,
"step": 1991
},
{
"epoch": 1.59,
"learning_rate": 1.0828147503344177e-06,
"loss": 0.9319,
"step": 1992
},
{
"epoch": 1.59,
"learning_rate": 1.078810600944612e-06,
"loss": 0.8727,
"step": 1993
},
{
"epoch": 1.59,
"learning_rate": 1.0748129732866391e-06,
"loss": 0.9081,
"step": 1994
},
{
"epoch": 1.59,
"learning_rate": 1.0708218740093634e-06,
"loss": 0.9884,
"step": 1995
},
{
"epoch": 1.59,
"learning_rate": 1.0668373097507922e-06,
"loss": 0.8373,
"step": 1996
},
{
"epoch": 1.59,
"learning_rate": 1.0628592871380611e-06,
"loss": 0.8809,
"step": 1997
},
{
"epoch": 1.59,
"learning_rate": 1.0588878127874285e-06,
"loss": 0.8358,
"step": 1998
},
{
"epoch": 1.59,
"learning_rate": 1.05492289330426e-06,
"loss": 0.8481,
"step": 1999
},
{
"epoch": 1.59,
"learning_rate": 1.0509645352830178e-06,
"loss": 0.8597,
"step": 2000
},
{
"epoch": 1.59,
"learning_rate": 1.047012745307255e-06,
"loss": 0.8825,
"step": 2001
},
{
"epoch": 1.59,
"learning_rate": 1.0430675299495973e-06,
"loss": 0.8977,
"step": 2002
},
{
"epoch": 1.59,
"learning_rate": 1.0391288957717366e-06,
"loss": 0.9173,
"step": 2003
},
{
"epoch": 1.6,
"learning_rate": 1.035196849324418e-06,
"loss": 0.9116,
"step": 2004
},
{
"epoch": 1.6,
"learning_rate": 1.0312713971474308e-06,
"loss": 0.8774,
"step": 2005
},
{
"epoch": 1.6,
"learning_rate": 1.0273525457696e-06,
"loss": 0.8691,
"step": 2006
},
{
"epoch": 1.6,
"learning_rate": 1.0234403017087658e-06,
"loss": 0.8745,
"step": 2007
},
{
"epoch": 1.6,
"learning_rate": 1.0195346714717813e-06,
"loss": 0.8955,
"step": 2008
},
{
"epoch": 1.6,
"learning_rate": 1.0156356615545033e-06,
"loss": 0.8971,
"step": 2009
},
{
"epoch": 1.6,
"learning_rate": 1.011743278441773e-06,
"loss": 0.8774,
"step": 2010
},
{
"epoch": 1.6,
"learning_rate": 1.0078575286074116e-06,
"loss": 0.8591,
"step": 2011
},
{
"epoch": 1.6,
"learning_rate": 1.0039784185142065e-06,
"loss": 0.8368,
"step": 2012
},
{
"epoch": 1.6,
"learning_rate": 1.0001059546139057e-06,
"loss": 0.8482,
"step": 2013
},
{
"epoch": 1.6,
"learning_rate": 9.962401433471985e-07,
"loss": 0.8362,
"step": 2014
},
{
"epoch": 1.6,
"learning_rate": 9.92380991143712e-07,
"loss": 0.7863,
"step": 2015
},
{
"epoch": 1.61,
"learning_rate": 9.88528504422e-07,
"loss": 0.8868,
"step": 2016
},
{
"epoch": 1.61,
"learning_rate": 9.84682689589526e-07,
"loss": 0.8384,
"step": 2017
},
{
"epoch": 1.61,
"learning_rate": 9.808435530426586e-07,
"loss": 0.9315,
"step": 2018
},
{
"epoch": 1.61,
"learning_rate": 9.770111011666582e-07,
"loss": 0.8653,
"step": 2019
},
{
"epoch": 1.61,
"learning_rate": 9.731853403356705e-07,
"loss": 0.8441,
"step": 2020
},
{
"epoch": 1.61,
"learning_rate": 9.693662769127094e-07,
"loss": 0.8936,
"step": 2021
},
{
"epoch": 1.61,
"learning_rate": 9.65553917249648e-07,
"loss": 0.9151,
"step": 2022
},
{
"epoch": 1.61,
"learning_rate": 9.617482676872164e-07,
"loss": 0.8551,
"step": 2023
},
{
"epoch": 1.61,
"learning_rate": 9.579493345549772e-07,
"loss": 0.9124,
"step": 2024
},
{
"epoch": 1.61,
"learning_rate": 9.541571241713277e-07,
"loss": 0.88,
"step": 2025
},
{
"epoch": 1.61,
"learning_rate": 9.5037164284348e-07,
"loss": 0.8565,
"step": 2026
},
{
"epoch": 1.61,
"learning_rate": 9.465928968674548e-07,
"loss": 0.8486,
"step": 2027
},
{
"epoch": 1.61,
"learning_rate": 9.428208925280746e-07,
"loss": 0.9031,
"step": 2028
},
{
"epoch": 1.62,
"learning_rate": 9.39055636098945e-07,
"loss": 0.8071,
"step": 2029
},
{
"epoch": 1.62,
"learning_rate": 9.352971338424494e-07,
"loss": 0.8865,
"step": 2030
},
{
"epoch": 1.62,
"learning_rate": 9.315453920097367e-07,
"loss": 0.936,
"step": 2031
},
{
"epoch": 1.62,
"learning_rate": 9.278004168407151e-07,
"loss": 0.8704,
"step": 2032
},
{
"epoch": 1.62,
"learning_rate": 9.240622145640365e-07,
"loss": 0.8508,
"step": 2033
},
{
"epoch": 1.62,
"learning_rate": 9.203307913970877e-07,
"loss": 0.8704,
"step": 2034
},
{
"epoch": 1.62,
"learning_rate": 9.166061535459797e-07,
"loss": 0.9539,
"step": 2035
},
{
"epoch": 1.62,
"learning_rate": 9.128883072055411e-07,
"loss": 0.8939,
"step": 2036
},
{
"epoch": 1.62,
"learning_rate": 9.091772585593023e-07,
"loss": 0.8871,
"step": 2037
},
{
"epoch": 1.62,
"learning_rate": 9.054730137794887e-07,
"loss": 0.9191,
"step": 2038
},
{
"epoch": 1.62,
"learning_rate": 9.017755790270083e-07,
"loss": 0.9131,
"step": 2039
},
{
"epoch": 1.62,
"learning_rate": 8.980849604514453e-07,
"loss": 0.8545,
"step": 2040
},
{
"epoch": 1.62,
"learning_rate": 8.944011641910433e-07,
"loss": 0.9527,
"step": 2041
},
{
"epoch": 1.63,
"learning_rate": 8.907241963727037e-07,
"loss": 0.9689,
"step": 2042
},
{
"epoch": 1.63,
"learning_rate": 8.870540631119667e-07,
"loss": 0.7993,
"step": 2043
},
{
"epoch": 1.63,
"learning_rate": 8.833907705130091e-07,
"loss": 0.8738,
"step": 2044
},
{
"epoch": 1.63,
"learning_rate": 8.797343246686263e-07,
"loss": 0.9382,
"step": 2045
},
{
"epoch": 1.63,
"learning_rate": 8.760847316602284e-07,
"loss": 0.8865,
"step": 2046
},
{
"epoch": 1.63,
"learning_rate": 8.724419975578258e-07,
"loss": 0.8119,
"step": 2047
},
{
"epoch": 1.63,
"learning_rate": 8.688061284200266e-07,
"loss": 0.9008,
"step": 2048
},
{
"epoch": 1.63,
"learning_rate": 8.651771302940132e-07,
"loss": 0.8282,
"step": 2049
},
{
"epoch": 1.63,
"learning_rate": 8.615550092155478e-07,
"loss": 0.9318,
"step": 2050
},
{
"epoch": 1.63,
"learning_rate": 8.579397712089477e-07,
"loss": 0.9086,
"step": 2051
},
{
"epoch": 1.63,
"learning_rate": 8.543314222870891e-07,
"loss": 0.8198,
"step": 2052
},
{
"epoch": 1.63,
"learning_rate": 8.507299684513847e-07,
"loss": 0.8369,
"step": 2053
},
{
"epoch": 1.64,
"learning_rate": 8.471354156917816e-07,
"loss": 0.8522,
"step": 2054
},
{
"epoch": 1.64,
"learning_rate": 8.435477699867478e-07,
"loss": 0.8483,
"step": 2055
},
{
"epoch": 1.64,
"learning_rate": 8.399670373032665e-07,
"loss": 0.9178,
"step": 2056
},
{
"epoch": 1.64,
"learning_rate": 8.363932235968198e-07,
"loss": 0.8813,
"step": 2057
},
{
"epoch": 1.64,
"learning_rate": 8.328263348113829e-07,
"loss": 0.945,
"step": 2058
},
{
"epoch": 1.64,
"learning_rate": 8.292663768794145e-07,
"loss": 0.8877,
"step": 2059
},
{
"epoch": 1.64,
"learning_rate": 8.257133557218471e-07,
"loss": 0.8916,
"step": 2060
},
{
"epoch": 1.64,
"learning_rate": 8.221672772480727e-07,
"loss": 0.8885,
"step": 2061
},
{
"epoch": 1.64,
"learning_rate": 8.186281473559382e-07,
"loss": 0.8749,
"step": 2062
},
{
"epoch": 1.64,
"learning_rate": 8.150959719317309e-07,
"loss": 0.8098,
"step": 2063
},
{
"epoch": 1.64,
"learning_rate": 8.115707568501768e-07,
"loss": 0.9063,
"step": 2064
},
{
"epoch": 1.64,
"learning_rate": 8.080525079744211e-07,
"loss": 0.846,
"step": 2065
},
{
"epoch": 1.64,
"learning_rate": 8.045412311560225e-07,
"loss": 0.8991,
"step": 2066
},
{
"epoch": 1.65,
"learning_rate": 8.010369322349459e-07,
"loss": 0.8998,
"step": 2067
},
{
"epoch": 1.65,
"learning_rate": 7.975396170395522e-07,
"loss": 0.9192,
"step": 2068
},
{
"epoch": 1.65,
"learning_rate": 7.940492913865833e-07,
"loss": 0.9194,
"step": 2069
},
{
"epoch": 1.65,
"learning_rate": 7.90565961081155e-07,
"loss": 0.8603,
"step": 2070
},
{
"epoch": 1.65,
"learning_rate": 7.870896319167548e-07,
"loss": 0.9234,
"step": 2071
},
{
"epoch": 1.65,
"learning_rate": 7.836203096752193e-07,
"loss": 0.849,
"step": 2072
},
{
"epoch": 1.65,
"learning_rate": 7.801580001267345e-07,
"loss": 0.8679,
"step": 2073
},
{
"epoch": 1.65,
"learning_rate": 7.767027090298207e-07,
"loss": 0.8567,
"step": 2074
},
{
"epoch": 1.65,
"learning_rate": 7.732544421313293e-07,
"loss": 0.8332,
"step": 2075
},
{
"epoch": 1.65,
"learning_rate": 7.698132051664236e-07,
"loss": 0.8448,
"step": 2076
},
{
"epoch": 1.65,
"learning_rate": 7.663790038585794e-07,
"loss": 0.8942,
"step": 2077
},
{
"epoch": 1.65,
"learning_rate": 7.629518439195671e-07,
"loss": 0.9302,
"step": 2078
},
{
"epoch": 1.66,
"learning_rate": 7.595317310494494e-07,
"loss": 0.8426,
"step": 2079
},
{
"epoch": 1.66,
"learning_rate": 7.561186709365653e-07,
"loss": 0.8465,
"step": 2080
},
{
"epoch": 1.66,
"learning_rate": 7.527126692575248e-07,
"loss": 0.8726,
"step": 2081
},
{
"epoch": 1.66,
"learning_rate": 7.493137316771976e-07,
"loss": 0.8424,
"step": 2082
},
{
"epoch": 1.66,
"learning_rate": 7.459218638487065e-07,
"loss": 0.8959,
"step": 2083
},
{
"epoch": 1.66,
"learning_rate": 7.425370714134122e-07,
"loss": 0.9217,
"step": 2084
},
{
"epoch": 1.66,
"learning_rate": 7.391593600009123e-07,
"loss": 0.9006,
"step": 2085
},
{
"epoch": 1.66,
"learning_rate": 7.357887352290227e-07,
"loss": 0.8974,
"step": 2086
},
{
"epoch": 1.66,
"learning_rate": 7.32425202703777e-07,
"loss": 0.9754,
"step": 2087
},
{
"epoch": 1.66,
"learning_rate": 7.290687680194092e-07,
"loss": 0.9941,
"step": 2088
},
{
"epoch": 1.66,
"learning_rate": 7.257194367583503e-07,
"loss": 0.9323,
"step": 2089
},
{
"epoch": 1.66,
"learning_rate": 7.223772144912144e-07,
"loss": 0.9311,
"step": 2090
},
{
"epoch": 1.66,
"learning_rate": 7.190421067767966e-07,
"loss": 0.8551,
"step": 2091
},
{
"epoch": 1.67,
"learning_rate": 7.157141191620548e-07,
"loss": 0.9572,
"step": 2092
},
{
"epoch": 1.67,
"learning_rate": 7.123932571821051e-07,
"loss": 0.8672,
"step": 2093
},
{
"epoch": 1.67,
"learning_rate": 7.090795263602146e-07,
"loss": 0.8657,
"step": 2094
},
{
"epoch": 1.67,
"learning_rate": 7.057729322077899e-07,
"loss": 0.8035,
"step": 2095
},
{
"epoch": 1.67,
"learning_rate": 7.024734802243649e-07,
"loss": 0.8657,
"step": 2096
},
{
"epoch": 1.67,
"learning_rate": 6.991811758975959e-07,
"loss": 0.9294,
"step": 2097
},
{
"epoch": 1.67,
"learning_rate": 6.958960247032515e-07,
"loss": 0.8689,
"step": 2098
},
{
"epoch": 1.67,
"learning_rate": 6.926180321052045e-07,
"loss": 0.8825,
"step": 2099
},
{
"epoch": 1.67,
"learning_rate": 6.8934720355542e-07,
"loss": 0.8921,
"step": 2100
},
{
"epoch": 1.67,
"learning_rate": 6.860835444939457e-07,
"loss": 0.8866,
"step": 2101
},
{
"epoch": 1.67,
"learning_rate": 6.828270603489113e-07,
"loss": 0.7983,
"step": 2102
},
{
"epoch": 1.67,
"learning_rate": 6.795777565365053e-07,
"loss": 0.7545,
"step": 2103
},
{
"epoch": 1.68,
"learning_rate": 6.763356384609809e-07,
"loss": 0.8629,
"step": 2104
},
{
"epoch": 1.68,
"learning_rate": 6.731007115146354e-07,
"loss": 0.7896,
"step": 2105
},
{
"epoch": 1.68,
"learning_rate": 6.698729810778065e-07,
"loss": 0.9401,
"step": 2106
},
{
"epoch": 1.68,
"learning_rate": 6.666524525188656e-07,
"loss": 0.7726,
"step": 2107
},
{
"epoch": 1.68,
"learning_rate": 6.634391311942024e-07,
"loss": 0.8642,
"step": 2108
},
{
"epoch": 1.68,
"learning_rate": 6.602330224482206e-07,
"loss": 0.8452,
"step": 2109
},
{
"epoch": 1.68,
"learning_rate": 6.570341316133272e-07,
"loss": 0.8566,
"step": 2110
},
{
"epoch": 1.68,
"learning_rate": 6.538424640099267e-07,
"loss": 0.9493,
"step": 2111
},
{
"epoch": 1.68,
"learning_rate": 6.506580249464089e-07,
"loss": 0.947,
"step": 2112
},
{
"epoch": 1.68,
"learning_rate": 6.474808197191401e-07,
"loss": 0.8866,
"step": 2113
},
{
"epoch": 1.68,
"learning_rate": 6.443108536124548e-07,
"loss": 0.8622,
"step": 2114
},
{
"epoch": 1.68,
"learning_rate": 6.411481318986507e-07,
"loss": 0.7916,
"step": 2115
},
{
"epoch": 1.68,
"learning_rate": 6.379926598379727e-07,
"loss": 0.8858,
"step": 2116
},
{
"epoch": 1.69,
"learning_rate": 6.348444426786099e-07,
"loss": 0.9083,
"step": 2117
},
{
"epoch": 1.69,
"learning_rate": 6.31703485656684e-07,
"loss": 0.8526,
"step": 2118
},
{
"epoch": 1.69,
"learning_rate": 6.285697939962437e-07,
"loss": 0.9428,
"step": 2119
},
{
"epoch": 1.69,
"learning_rate": 6.254433729092518e-07,
"loss": 0.9146,
"step": 2120
},
{
"epoch": 1.69,
"learning_rate": 6.223242275955804e-07,
"loss": 0.9047,
"step": 2121
},
{
"epoch": 1.69,
"learning_rate": 6.192123632429986e-07,
"loss": 0.8202,
"step": 2122
},
{
"epoch": 1.69,
"learning_rate": 6.161077850271685e-07,
"loss": 0.9169,
"step": 2123
},
{
"epoch": 1.69,
"learning_rate": 6.130104981116314e-07,
"loss": 0.8406,
"step": 2124
},
{
"epoch": 1.69,
"learning_rate": 6.099205076478005e-07,
"loss": 0.8065,
"step": 2125
},
{
"epoch": 1.69,
"learning_rate": 6.06837818774959e-07,
"loss": 0.8433,
"step": 2126
},
{
"epoch": 1.69,
"learning_rate": 6.037624366202405e-07,
"loss": 0.9026,
"step": 2127
},
{
"epoch": 1.69,
"learning_rate": 6.006943662986275e-07,
"loss": 0.8524,
"step": 2128
},
{
"epoch": 1.7,
"learning_rate": 5.976336129129429e-07,
"loss": 0.8909,
"step": 2129
},
{
"epoch": 1.7,
"learning_rate": 5.945801815538411e-07,
"loss": 0.8545,
"step": 2130
},
{
"epoch": 1.7,
"learning_rate": 5.915340772997941e-07,
"loss": 0.8562,
"step": 2131
},
{
"epoch": 1.7,
"learning_rate": 5.884953052170917e-07,
"loss": 0.9254,
"step": 2132
},
{
"epoch": 1.7,
"learning_rate": 5.854638703598247e-07,
"loss": 0.8313,
"step": 2133
},
{
"epoch": 1.7,
"learning_rate": 5.824397777698859e-07,
"loss": 0.8573,
"step": 2134
},
{
"epoch": 1.7,
"learning_rate": 5.794230324769518e-07,
"loss": 0.9347,
"step": 2135
},
{
"epoch": 1.7,
"learning_rate": 5.764136394984809e-07,
"loss": 0.894,
"step": 2136
},
{
"epoch": 1.7,
"learning_rate": 5.734116038397019e-07,
"loss": 0.8478,
"step": 2137
},
{
"epoch": 1.7,
"learning_rate": 5.704169304936097e-07,
"loss": 0.842,
"step": 2138
},
{
"epoch": 1.7,
"learning_rate": 5.674296244409522e-07,
"loss": 0.9381,
"step": 2139
},
{
"epoch": 1.7,
"learning_rate": 5.644496906502233e-07,
"loss": 0.8549,
"step": 2140
},
{
"epoch": 1.7,
"learning_rate": 5.614771340776559e-07,
"loss": 0.8539,
"step": 2141
},
{
"epoch": 1.71,
"learning_rate": 5.585119596672151e-07,
"loss": 0.8798,
"step": 2142
},
{
"epoch": 1.71,
"learning_rate": 5.555541723505853e-07,
"loss": 0.9246,
"step": 2143
},
{
"epoch": 1.71,
"learning_rate": 5.526037770471649e-07,
"loss": 0.8765,
"step": 2144
},
{
"epoch": 1.71,
"learning_rate": 5.496607786640584e-07,
"loss": 0.8799,
"step": 2145
},
{
"epoch": 1.71,
"learning_rate": 5.4672518209607e-07,
"loss": 0.8678,
"step": 2146
},
{
"epoch": 1.71,
"learning_rate": 5.437969922256886e-07,
"loss": 0.8849,
"step": 2147
},
{
"epoch": 1.71,
"learning_rate": 5.408762139230889e-07,
"loss": 0.8714,
"step": 2148
},
{
"epoch": 1.71,
"learning_rate": 5.37962852046115e-07,
"loss": 0.8789,
"step": 2149
},
{
"epoch": 1.71,
"learning_rate": 5.350569114402787e-07,
"loss": 0.9203,
"step": 2150
},
{
"epoch": 1.71,
"learning_rate": 5.321583969387473e-07,
"loss": 0.9611,
"step": 2151
},
{
"epoch": 1.71,
"learning_rate": 5.292673133623372e-07,
"loss": 0.8945,
"step": 2152
},
{
"epoch": 1.71,
"learning_rate": 5.263836655195042e-07,
"loss": 0.8383,
"step": 2153
},
{
"epoch": 1.71,
"learning_rate": 5.235074582063409e-07,
"loss": 0.9132,
"step": 2154
},
{
"epoch": 1.72,
"learning_rate": 5.206386962065601e-07,
"loss": 0.847,
"step": 2155
},
{
"epoch": 1.72,
"learning_rate": 5.177773842914963e-07,
"loss": 0.8559,
"step": 2156
},
{
"epoch": 1.72,
"learning_rate": 5.149235272200876e-07,
"loss": 0.8331,
"step": 2157
},
{
"epoch": 1.72,
"learning_rate": 5.120771297388788e-07,
"loss": 0.8884,
"step": 2158
},
{
"epoch": 1.72,
"learning_rate": 5.092381965820036e-07,
"loss": 0.8995,
"step": 2159
},
{
"epoch": 1.72,
"learning_rate": 5.064067324711836e-07,
"loss": 0.8274,
"step": 2160
},
{
"epoch": 1.72,
"learning_rate": 5.035827421157147e-07,
"loss": 0.807,
"step": 2161
},
{
"epoch": 1.72,
"learning_rate": 5.007662302124671e-07,
"loss": 0.8517,
"step": 2162
},
{
"epoch": 1.72,
"learning_rate": 4.9795720144587e-07,
"loss": 0.9641,
"step": 2163
},
{
"epoch": 1.72,
"learning_rate": 4.951556604879049e-07,
"loss": 0.8704,
"step": 2164
},
{
"epoch": 1.72,
"learning_rate": 4.923616119981029e-07,
"loss": 0.8861,
"step": 2165
},
{
"epoch": 1.72,
"learning_rate": 4.895750606235333e-07,
"loss": 0.9192,
"step": 2166
},
{
"epoch": 1.73,
"learning_rate": 4.86796010998794e-07,
"loss": 0.9121,
"step": 2167
},
{
"epoch": 1.73,
"learning_rate": 4.840244677460076e-07,
"loss": 0.859,
"step": 2168
},
{
"epoch": 1.73,
"learning_rate": 4.812604354748107e-07,
"loss": 0.9112,
"step": 2169
},
{
"epoch": 1.73,
"learning_rate": 4.785039187823503e-07,
"loss": 0.92,
"step": 2170
},
{
"epoch": 1.73,
"learning_rate": 4.7575492225327034e-07,
"loss": 0.9217,
"step": 2171
},
{
"epoch": 1.73,
"learning_rate": 4.730134504597084e-07,
"loss": 0.9069,
"step": 2172
},
{
"epoch": 1.73,
"learning_rate": 4.7027950796128764e-07,
"loss": 0.8608,
"step": 2173
},
{
"epoch": 1.73,
"learning_rate": 4.6755309930510915e-07,
"loss": 0.8202,
"step": 2174
},
{
"epoch": 1.73,
"learning_rate": 4.648342290257413e-07,
"loss": 0.8692,
"step": 2175
},
{
"epoch": 1.73,
"learning_rate": 4.6212290164521554e-07,
"loss": 0.8897,
"step": 2176
},
{
"epoch": 1.73,
"learning_rate": 4.594191216730176e-07,
"loss": 0.915,
"step": 2177
},
{
"epoch": 1.73,
"learning_rate": 4.5672289360608303e-07,
"loss": 0.894,
"step": 2178
},
{
"epoch": 1.73,
"learning_rate": 4.5403422192878355e-07,
"loss": 0.8847,
"step": 2179
},
{
"epoch": 1.74,
"learning_rate": 4.5135311111292435e-07,
"loss": 0.872,
"step": 2180
},
{
"epoch": 1.74,
"learning_rate": 4.486795656177362e-07,
"loss": 0.8267,
"step": 2181
},
{
"epoch": 1.74,
"learning_rate": 4.46013589889866e-07,
"loss": 0.887,
"step": 2182
},
{
"epoch": 1.74,
"learning_rate": 4.433551883633719e-07,
"loss": 0.8695,
"step": 2183
},
{
"epoch": 1.74,
"learning_rate": 4.407043654597126e-07,
"loss": 0.8679,
"step": 2184
},
{
"epoch": 1.74,
"learning_rate": 4.3806112558774483e-07,
"loss": 0.8409,
"step": 2185
},
{
"epoch": 1.74,
"learning_rate": 4.3542547314371133e-07,
"loss": 0.8593,
"step": 2186
},
{
"epoch": 1.74,
"learning_rate": 4.327974125112344e-07,
"loss": 0.8467,
"step": 2187
},
{
"epoch": 1.74,
"learning_rate": 4.3017694806131163e-07,
"loss": 0.8997,
"step": 2188
},
{
"epoch": 1.74,
"learning_rate": 4.2756408415230657e-07,
"loss": 0.9254,
"step": 2189
},
{
"epoch": 1.74,
"learning_rate": 4.2495882512993913e-07,
"loss": 0.8865,
"step": 2190
},
{
"epoch": 1.74,
"learning_rate": 4.223611753272849e-07,
"loss": 0.8745,
"step": 2191
},
{
"epoch": 1.75,
"learning_rate": 4.1977113906475965e-07,
"loss": 0.8618,
"step": 2192
},
{
"epoch": 1.75,
"learning_rate": 4.171887206501191e-07,
"loss": 0.8651,
"step": 2193
},
{
"epoch": 1.75,
"learning_rate": 4.146139243784475e-07,
"loss": 0.8905,
"step": 2194
},
{
"epoch": 1.75,
"learning_rate": 4.1204675453215217e-07,
"loss": 0.8168,
"step": 2195
},
{
"epoch": 1.75,
"learning_rate": 4.0948721538095593e-07,
"loss": 0.7985,
"step": 2196
},
{
"epoch": 1.75,
"learning_rate": 4.069353111818913e-07,
"loss": 0.8915,
"step": 2197
},
{
"epoch": 1.75,
"learning_rate": 4.0439104617929217e-07,
"loss": 0.7901,
"step": 2198
},
{
"epoch": 1.75,
"learning_rate": 4.01854424604784e-07,
"loss": 0.9197,
"step": 2199
},
{
"epoch": 1.75,
"learning_rate": 3.9932545067728366e-07,
"loss": 0.8896,
"step": 2200
},
{
"epoch": 1.75,
"learning_rate": 3.9680412860298777e-07,
"loss": 0.8946,
"step": 2201
},
{
"epoch": 1.75,
"learning_rate": 3.9429046257536407e-07,
"loss": 0.8453,
"step": 2202
},
{
"epoch": 1.75,
"learning_rate": 3.9178445677514833e-07,
"loss": 0.9033,
"step": 2203
},
{
"epoch": 1.75,
"learning_rate": 3.8928611537033424e-07,
"loss": 0.8587,
"step": 2204
},
{
"epoch": 1.76,
"learning_rate": 3.8679544251617185e-07,
"loss": 0.9043,
"step": 2205
},
{
"epoch": 1.76,
"learning_rate": 3.8431244235515366e-07,
"loss": 0.8758,
"step": 2206
},
{
"epoch": 1.76,
"learning_rate": 3.818371190170095e-07,
"loss": 0.946,
"step": 2207
},
{
"epoch": 1.76,
"learning_rate": 3.7936947661870616e-07,
"loss": 0.8744,
"step": 2208
},
{
"epoch": 1.76,
"learning_rate": 3.769095192644301e-07,
"loss": 0.9636,
"step": 2209
},
{
"epoch": 1.76,
"learning_rate": 3.744572510455902e-07,
"loss": 0.838,
"step": 2210
},
{
"epoch": 1.76,
"learning_rate": 3.7201267604080436e-07,
"loss": 0.8476,
"step": 2211
},
{
"epoch": 1.76,
"learning_rate": 3.695757983158954e-07,
"loss": 0.8304,
"step": 2212
},
{
"epoch": 1.76,
"learning_rate": 3.6714662192388507e-07,
"loss": 0.9107,
"step": 2213
},
{
"epoch": 1.76,
"learning_rate": 3.647251509049848e-07,
"loss": 0.9021,
"step": 2214
},
{
"epoch": 1.76,
"learning_rate": 3.6231138928659204e-07,
"loss": 0.9027,
"step": 2215
},
{
"epoch": 1.76,
"learning_rate": 3.5990534108327926e-07,
"loss": 0.8272,
"step": 2216
},
{
"epoch": 1.77,
"learning_rate": 3.575070102967926e-07,
"loss": 0.9452,
"step": 2217
},
{
"epoch": 1.77,
"learning_rate": 3.5511640091604293e-07,
"loss": 0.8079,
"step": 2218
},
{
"epoch": 1.77,
"learning_rate": 3.5273351691709703e-07,
"loss": 0.8537,
"step": 2219
},
{
"epoch": 1.77,
"learning_rate": 3.5035836226317177e-07,
"loss": 0.8954,
"step": 2220
},
{
"epoch": 1.77,
"learning_rate": 3.4799094090463225e-07,
"loss": 0.93,
"step": 2221
},
{
"epoch": 1.77,
"learning_rate": 3.4563125677897936e-07,
"loss": 0.8685,
"step": 2222
},
{
"epoch": 1.77,
"learning_rate": 3.4327931381084424e-07,
"loss": 0.8014,
"step": 2223
},
{
"epoch": 1.77,
"learning_rate": 3.409351159119845e-07,
"loss": 0.8241,
"step": 2224
},
{
"epoch": 1.77,
"learning_rate": 3.385986669812769e-07,
"loss": 0.8603,
"step": 2225
},
{
"epoch": 1.77,
"learning_rate": 3.3626997090470793e-07,
"loss": 0.9309,
"step": 2226
},
{
"epoch": 1.77,
"learning_rate": 3.3394903155537116e-07,
"loss": 0.9224,
"step": 2227
},
{
"epoch": 1.77,
"learning_rate": 3.3163585279345823e-07,
"loss": 0.8813,
"step": 2228
},
{
"epoch": 1.77,
"learning_rate": 3.2933043846625437e-07,
"loss": 0.907,
"step": 2229
},
{
"epoch": 1.78,
"learning_rate": 3.270327924081301e-07,
"loss": 0.8753,
"step": 2230
},
{
"epoch": 1.78,
"learning_rate": 3.2474291844053594e-07,
"loss": 0.9061,
"step": 2231
},
{
"epoch": 1.78,
"learning_rate": 3.224608203719953e-07,
"loss": 0.8846,
"step": 2232
},
{
"epoch": 1.78,
"learning_rate": 3.201865019981004e-07,
"loss": 0.8706,
"step": 2233
},
{
"epoch": 1.78,
"learning_rate": 3.179199671015015e-07,
"loss": 0.9665,
"step": 2234
},
{
"epoch": 1.78,
"learning_rate": 3.156612194519071e-07,
"loss": 0.8054,
"step": 2235
},
{
"epoch": 1.78,
"learning_rate": 3.134102628060698e-07,
"loss": 0.8955,
"step": 2236
},
{
"epoch": 1.78,
"learning_rate": 3.1116710090778825e-07,
"loss": 0.7931,
"step": 2237
},
{
"epoch": 1.78,
"learning_rate": 3.0893173748789363e-07,
"loss": 0.8697,
"step": 2238
},
{
"epoch": 1.78,
"learning_rate": 3.067041762642475e-07,
"loss": 0.8756,
"step": 2239
},
{
"epoch": 1.78,
"learning_rate": 3.0448442094173634e-07,
"loss": 0.843,
"step": 2240
},
{
"epoch": 1.78,
"learning_rate": 3.022724752122619e-07,
"loss": 0.8402,
"step": 2241
},
{
"epoch": 1.79,
"learning_rate": 3.000683427547374e-07,
"loss": 0.8822,
"step": 2242
},
{
"epoch": 1.79,
"learning_rate": 2.9787202723508155e-07,
"loss": 0.8836,
"step": 2243
},
{
"epoch": 1.79,
"learning_rate": 2.9568353230621185e-07,
"loss": 0.9124,
"step": 2244
},
{
"epoch": 1.79,
"learning_rate": 2.935028616080393e-07,
"loss": 0.8594,
"step": 2245
},
{
"epoch": 1.79,
"learning_rate": 2.9133001876746004e-07,
"loss": 0.8523,
"step": 2246
},
{
"epoch": 1.79,
"learning_rate": 2.891650073983504e-07,
"loss": 0.8683,
"step": 2247
},
{
"epoch": 1.79,
"learning_rate": 2.8700783110156507e-07,
"loss": 0.8413,
"step": 2248
},
{
"epoch": 1.79,
"learning_rate": 2.848584934649234e-07,
"loss": 0.8456,
"step": 2249
},
{
"epoch": 1.79,
"learning_rate": 2.827169980632094e-07,
"loss": 0.8851,
"step": 2250
},
{
"epoch": 1.79,
"learning_rate": 2.8058334845816214e-07,
"loss": 0.8836,
"step": 2251
},
{
"epoch": 1.79,
"learning_rate": 2.784575481984747e-07,
"loss": 0.9566,
"step": 2252
},
{
"epoch": 1.79,
"learning_rate": 2.763396008197833e-07,
"loss": 0.8815,
"step": 2253
},
{
"epoch": 1.79,
"learning_rate": 2.742295098446623e-07,
"loss": 0.8886,
"step": 2254
},
{
"epoch": 1.8,
"learning_rate": 2.7212727878262013e-07,
"loss": 0.8254,
"step": 2255
},
{
"epoch": 1.8,
"learning_rate": 2.700329111300937e-07,
"loss": 0.8218,
"step": 2256
},
{
"epoch": 1.8,
"learning_rate": 2.6794641037043987e-07,
"loss": 0.8986,
"step": 2257
},
{
"epoch": 1.8,
"learning_rate": 2.6586777997393175e-07,
"loss": 0.8581,
"step": 2258
},
{
"epoch": 1.8,
"learning_rate": 2.637970233977516e-07,
"loss": 0.8049,
"step": 2259
},
{
"epoch": 1.8,
"learning_rate": 2.617341440859883e-07,
"loss": 0.9392,
"step": 2260
},
{
"epoch": 1.8,
"learning_rate": 2.596791454696262e-07,
"loss": 0.9382,
"step": 2261
},
{
"epoch": 1.8,
"learning_rate": 2.5763203096654645e-07,
"loss": 0.8477,
"step": 2262
},
{
"epoch": 1.8,
"learning_rate": 2.5559280398151253e-07,
"loss": 0.9056,
"step": 2263
},
{
"epoch": 1.8,
"learning_rate": 2.535614679061732e-07,
"loss": 0.8472,
"step": 2264
},
{
"epoch": 1.8,
"learning_rate": 2.515380261190514e-07,
"loss": 0.9141,
"step": 2265
},
{
"epoch": 1.8,
"learning_rate": 2.4952248198554075e-07,
"loss": 0.8692,
"step": 2266
},
{
"epoch": 1.8,
"learning_rate": 2.475148388578974e-07,
"loss": 0.7692,
"step": 2267
},
{
"epoch": 1.81,
"learning_rate": 2.4551510007524035e-07,
"loss": 0.8342,
"step": 2268
},
{
"epoch": 1.81,
"learning_rate": 2.435232689635386e-07,
"loss": 0.8437,
"step": 2269
},
{
"epoch": 1.81,
"learning_rate": 2.4153934883561213e-07,
"loss": 0.9395,
"step": 2270
},
{
"epoch": 1.81,
"learning_rate": 2.395633429911198e-07,
"loss": 0.8459,
"step": 2271
},
{
"epoch": 1.81,
"learning_rate": 2.3759525471656163e-07,
"loss": 0.8281,
"step": 2272
},
{
"epoch": 1.81,
"learning_rate": 2.356350872852653e-07,
"loss": 0.8597,
"step": 2273
},
{
"epoch": 1.81,
"learning_rate": 2.3368284395738684e-07,
"loss": 0.8854,
"step": 2274
},
{
"epoch": 1.81,
"learning_rate": 2.3173852797990114e-07,
"loss": 0.8382,
"step": 2275
},
{
"epoch": 1.81,
"learning_rate": 2.2980214258660038e-07,
"loss": 0.8406,
"step": 2276
},
{
"epoch": 1.81,
"learning_rate": 2.2787369099808553e-07,
"loss": 0.8876,
"step": 2277
},
{
"epoch": 1.81,
"learning_rate": 2.259531764217604e-07,
"loss": 0.9042,
"step": 2278
},
{
"epoch": 1.81,
"learning_rate": 2.2404060205183098e-07,
"loss": 0.9029,
"step": 2279
},
{
"epoch": 1.82,
"learning_rate": 2.2213597106929608e-07,
"loss": 0.8189,
"step": 2280
},
{
"epoch": 1.82,
"learning_rate": 2.2023928664194229e-07,
"loss": 0.8558,
"step": 2281
},
{
"epoch": 1.82,
"learning_rate": 2.1835055192433895e-07,
"loss": 0.8607,
"step": 2282
},
{
"epoch": 1.82,
"learning_rate": 2.1646977005783442e-07,
"loss": 0.9275,
"step": 2283
},
{
"epoch": 1.82,
"learning_rate": 2.1459694417055033e-07,
"loss": 0.8366,
"step": 2284
},
{
"epoch": 1.82,
"learning_rate": 2.1273207737737556e-07,
"loss": 0.8536,
"step": 2285
},
{
"epoch": 1.82,
"learning_rate": 2.1087517277996017e-07,
"loss": 0.8472,
"step": 2286
},
{
"epoch": 1.82,
"learning_rate": 2.090262334667126e-07,
"loss": 0.9018,
"step": 2287
},
{
"epoch": 1.82,
"learning_rate": 2.0718526251279346e-07,
"loss": 0.9807,
"step": 2288
},
{
"epoch": 1.82,
"learning_rate": 2.053522629801108e-07,
"loss": 0.8324,
"step": 2289
},
{
"epoch": 1.82,
"learning_rate": 2.0352723791731366e-07,
"loss": 0.8703,
"step": 2290
},
{
"epoch": 1.82,
"learning_rate": 2.0171019035978677e-07,
"loss": 0.9002,
"step": 2291
},
{
"epoch": 1.82,
"learning_rate": 1.999011233296505e-07,
"loss": 0.8768,
"step": 2292
},
{
"epoch": 1.83,
"learning_rate": 1.98100039835748e-07,
"loss": 0.8328,
"step": 2293
},
{
"epoch": 1.83,
"learning_rate": 1.9630694287364584e-07,
"loss": 0.8989,
"step": 2294
},
{
"epoch": 1.83,
"learning_rate": 1.9452183542562785e-07,
"loss": 0.8982,
"step": 2295
},
{
"epoch": 1.83,
"learning_rate": 1.9274472046068805e-07,
"loss": 0.9584,
"step": 2296
},
{
"epoch": 1.83,
"learning_rate": 1.9097560093452982e-07,
"loss": 0.8306,
"step": 2297
},
{
"epoch": 1.83,
"learning_rate": 1.892144797895562e-07,
"loss": 0.929,
"step": 2298
},
{
"epoch": 1.83,
"learning_rate": 1.8746135995486857e-07,
"loss": 0.8214,
"step": 2299
},
{
"epoch": 1.83,
"learning_rate": 1.857162443462601e-07,
"loss": 0.8576,
"step": 2300
},
{
"epoch": 1.83,
"learning_rate": 1.8397913586621186e-07,
"loss": 0.8243,
"step": 2301
},
{
"epoch": 1.83,
"learning_rate": 1.8225003740388546e-07,
"loss": 0.9136,
"step": 2302
},
{
"epoch": 1.83,
"learning_rate": 1.8052895183512276e-07,
"loss": 0.855,
"step": 2303
},
{
"epoch": 1.83,
"learning_rate": 1.7881588202243782e-07,
"loss": 0.9246,
"step": 2304
},
{
"epoch": 1.84,
"learning_rate": 1.7711083081501158e-07,
"loss": 0.9281,
"step": 2305
},
{
"epoch": 1.84,
"learning_rate": 1.7541380104868944e-07,
"loss": 0.9574,
"step": 2306
},
{
"epoch": 1.84,
"learning_rate": 1.7372479554597642e-07,
"loss": 0.8736,
"step": 2307
},
{
"epoch": 1.84,
"learning_rate": 1.7204381711603046e-07,
"loss": 0.8682,
"step": 2308
},
{
"epoch": 1.84,
"learning_rate": 1.7037086855465902e-07,
"loss": 0.8652,
"step": 2309
},
{
"epoch": 1.84,
"learning_rate": 1.68705952644313e-07,
"loss": 0.908,
"step": 2310
},
{
"epoch": 1.84,
"learning_rate": 1.6704907215408572e-07,
"loss": 0.8941,
"step": 2311
},
{
"epoch": 1.84,
"learning_rate": 1.6540022983970505e-07,
"loss": 0.9593,
"step": 2312
},
{
"epoch": 1.84,
"learning_rate": 1.63759428443529e-07,
"loss": 0.8594,
"step": 2313
},
{
"epoch": 1.84,
"learning_rate": 1.621266706945429e-07,
"loss": 0.9055,
"step": 2314
},
{
"epoch": 1.84,
"learning_rate": 1.605019593083529e-07,
"loss": 0.857,
"step": 2315
},
{
"epoch": 1.84,
"learning_rate": 1.5888529698718347e-07,
"loss": 0.9012,
"step": 2316
},
{
"epoch": 1.84,
"learning_rate": 1.572766864198716e-07,
"loss": 0.9062,
"step": 2317
},
{
"epoch": 1.85,
"learning_rate": 1.55676130281861e-07,
"loss": 0.9482,
"step": 2318
},
{
"epoch": 1.85,
"learning_rate": 1.540836312352023e-07,
"loss": 0.8455,
"step": 2319
},
{
"epoch": 1.85,
"learning_rate": 1.524991919285429e-07,
"loss": 0.8554,
"step": 2320
},
{
"epoch": 1.85,
"learning_rate": 1.5092281499712647e-07,
"loss": 0.8495,
"step": 2321
},
{
"epoch": 1.85,
"learning_rate": 1.4935450306278632e-07,
"loss": 0.8736,
"step": 2322
},
{
"epoch": 1.85,
"learning_rate": 1.477942587339426e-07,
"loss": 0.8955,
"step": 2323
},
{
"epoch": 1.85,
"learning_rate": 1.4624208460559897e-07,
"loss": 0.8251,
"step": 2324
},
{
"epoch": 1.85,
"learning_rate": 1.4469798325933481e-07,
"loss": 0.8696,
"step": 2325
},
{
"epoch": 1.85,
"learning_rate": 1.431619572633014e-07,
"loss": 0.863,
"step": 2326
},
{
"epoch": 1.85,
"learning_rate": 1.4163400917222347e-07,
"loss": 0.8622,
"step": 2327
},
{
"epoch": 1.85,
"learning_rate": 1.401141415273871e-07,
"loss": 0.8597,
"step": 2328
},
{
"epoch": 1.85,
"learning_rate": 1.3860235685663915e-07,
"loss": 0.8588,
"step": 2329
},
{
"epoch": 1.86,
"learning_rate": 1.3709865767438434e-07,
"loss": 0.8281,
"step": 2330
},
{
"epoch": 1.86,
"learning_rate": 1.356030464815783e-07,
"loss": 0.9346,
"step": 2331
},
{
"epoch": 1.86,
"learning_rate": 1.3411552576572562e-07,
"loss": 0.8081,
"step": 2332
},
{
"epoch": 1.86,
"learning_rate": 1.3263609800087507e-07,
"loss": 0.8475,
"step": 2333
},
{
"epoch": 1.86,
"learning_rate": 1.3116476564761338e-07,
"loss": 0.9042,
"step": 2334
},
{
"epoch": 1.86,
"learning_rate": 1.2970153115306473e-07,
"loss": 0.9026,
"step": 2335
},
{
"epoch": 1.86,
"learning_rate": 1.2824639695088403e-07,
"loss": 0.8531,
"step": 2336
},
{
"epoch": 1.86,
"learning_rate": 1.2679936546125483e-07,
"loss": 0.8124,
"step": 2337
},
{
"epoch": 1.86,
"learning_rate": 1.253604390908819e-07,
"loss": 0.8983,
"step": 2338
},
{
"epoch": 1.86,
"learning_rate": 1.2392962023299316e-07,
"loss": 0.9694,
"step": 2339
},
{
"epoch": 1.86,
"learning_rate": 1.2250691126732772e-07,
"loss": 0.9262,
"step": 2340
},
{
"epoch": 1.86,
"learning_rate": 1.210923145601406e-07,
"loss": 0.838,
"step": 2341
},
{
"epoch": 1.86,
"learning_rate": 1.1968583246419142e-07,
"loss": 0.8883,
"step": 2342
},
{
"epoch": 1.87,
"learning_rate": 1.1828746731874562e-07,
"loss": 0.8778,
"step": 2343
},
{
"epoch": 1.87,
"learning_rate": 1.1689722144956672e-07,
"loss": 0.8607,
"step": 2344
},
{
"epoch": 1.87,
"learning_rate": 1.1551509716891562e-07,
"loss": 0.8677,
"step": 2345
},
{
"epoch": 1.87,
"learning_rate": 1.1414109677554352e-07,
"loss": 0.8241,
"step": 2346
},
{
"epoch": 1.87,
"learning_rate": 1.1277522255469297e-07,
"loss": 0.9351,
"step": 2347
},
{
"epoch": 1.87,
"learning_rate": 1.1141747677808845e-07,
"loss": 0.9662,
"step": 2348
},
{
"epoch": 1.87,
"learning_rate": 1.100678617039358e-07,
"loss": 0.8889,
"step": 2349
},
{
"epoch": 1.87,
"learning_rate": 1.0872637957691834e-07,
"loss": 0.8074,
"step": 2350
},
{
"epoch": 1.87,
"learning_rate": 1.0739303262819301e-07,
"loss": 0.884,
"step": 2351
},
{
"epoch": 1.87,
"learning_rate": 1.0606782307538532e-07,
"loss": 0.8048,
"step": 2352
},
{
"epoch": 1.87,
"learning_rate": 1.0475075312258664e-07,
"loss": 0.9298,
"step": 2353
},
{
"epoch": 1.87,
"learning_rate": 1.0344182496035193e-07,
"loss": 0.8777,
"step": 2354
},
{
"epoch": 1.88,
"learning_rate": 1.0214104076569309e-07,
"loss": 0.8517,
"step": 2355
},
{
"epoch": 1.88,
"learning_rate": 1.008484027020773e-07,
"loss": 0.8646,
"step": 2356
},
{
"epoch": 1.88,
"learning_rate": 9.95639129194237e-08,
"loss": 0.8309,
"step": 2357
},
{
"epoch": 1.88,
"learning_rate": 9.82875735540989e-08,
"loss": 0.8433,
"step": 2358
},
{
"epoch": 1.88,
"learning_rate": 9.701938672891375e-08,
"loss": 0.8967,
"step": 2359
},
{
"epoch": 1.88,
"learning_rate": 9.575935455311935e-08,
"loss": 0.8505,
"step": 2360
},
{
"epoch": 1.88,
"learning_rate": 9.450747912240433e-08,
"loss": 0.8897,
"step": 2361
},
{
"epoch": 1.88,
"learning_rate": 9.326376251889202e-08,
"loss": 0.8911,
"step": 2362
},
{
"epoch": 1.88,
"learning_rate": 9.202820681113334e-08,
"loss": 0.7741,
"step": 2363
},
{
"epoch": 1.88,
"learning_rate": 9.08008140541089e-08,
"loss": 0.8743,
"step": 2364
},
{
"epoch": 1.88,
"learning_rate": 8.95815862892202e-08,
"loss": 0.9098,
"step": 2365
},
{
"epoch": 1.88,
"learning_rate": 8.837052554429071e-08,
"loss": 0.8462,
"step": 2366
},
{
"epoch": 1.88,
"learning_rate": 8.716763383355863e-08,
"loss": 0.8497,
"step": 2367
},
{
"epoch": 1.89,
"learning_rate": 8.597291315767808e-08,
"loss": 0.8659,
"step": 2368
},
{
"epoch": 1.89,
"learning_rate": 8.478636550370956e-08,
"loss": 0.9795,
"step": 2369
},
{
"epoch": 1.89,
"learning_rate": 8.360799284512333e-08,
"loss": 0.8147,
"step": 2370
},
{
"epoch": 1.89,
"learning_rate": 8.243779714179168e-08,
"loss": 0.9064,
"step": 2371
},
{
"epoch": 1.89,
"learning_rate": 8.127578033998663e-08,
"loss": 0.8614,
"step": 2372
},
{
"epoch": 1.89,
"learning_rate": 8.012194437237664e-08,
"loss": 0.8489,
"step": 2373
},
{
"epoch": 1.89,
"learning_rate": 7.897629115802553e-08,
"loss": 0.8856,
"step": 2374
},
{
"epoch": 1.89,
"learning_rate": 7.783882260238573e-08,
"loss": 0.9197,
"step": 2375
},
{
"epoch": 1.89,
"learning_rate": 7.670954059729896e-08,
"loss": 0.8246,
"step": 2376
},
{
"epoch": 1.89,
"learning_rate": 7.558844702098833e-08,
"loss": 0.8531,
"step": 2377
},
{
"epoch": 1.89,
"learning_rate": 7.44755437380612e-08,
"loss": 0.9846,
"step": 2378
},
{
"epoch": 1.89,
"learning_rate": 7.337083259949918e-08,
"loss": 0.9117,
"step": 2379
},
{
"epoch": 1.89,
"learning_rate": 7.227431544266194e-08,
"loss": 0.835,
"step": 2380
},
{
"epoch": 1.9,
"learning_rate": 7.118599409127847e-08,
"loss": 0.8644,
"step": 2381
},
{
"epoch": 1.9,
"learning_rate": 7.010587035544859e-08,
"loss": 0.9109,
"step": 2382
},
{
"epoch": 1.9,
"learning_rate": 6.903394603163582e-08,
"loss": 0.9001,
"step": 2383
},
{
"epoch": 1.9,
"learning_rate": 6.797022290266741e-08,
"loss": 0.8842,
"step": 2384
},
{
"epoch": 1.9,
"learning_rate": 6.691470273773038e-08,
"loss": 0.858,
"step": 2385
},
{
"epoch": 1.9,
"learning_rate": 6.58673872923693e-08,
"loss": 0.8723,
"step": 2386
},
{
"epoch": 1.9,
"learning_rate": 6.482827830848082e-08,
"loss": 0.8455,
"step": 2387
},
{
"epoch": 1.9,
"learning_rate": 6.379737751431415e-08,
"loss": 0.8271,
"step": 2388
},
{
"epoch": 1.9,
"learning_rate": 6.277468662446496e-08,
"loss": 0.8942,
"step": 2389
},
{
"epoch": 1.9,
"learning_rate": 6.176020733987654e-08,
"loss": 0.8902,
"step": 2390
},
{
"epoch": 1.9,
"learning_rate": 6.075394134783252e-08,
"loss": 0.8566,
"step": 2391
},
{
"epoch": 1.9,
"learning_rate": 5.97558903219575e-08,
"loss": 0.8454,
"step": 2392
},
{
"epoch": 1.91,
"learning_rate": 5.8766055922211965e-08,
"loss": 0.8614,
"step": 2393
},
{
"epoch": 1.91,
"learning_rate": 5.7784439794891234e-08,
"loss": 0.8814,
"step": 2394
},
{
"epoch": 1.91,
"learning_rate": 5.6811043572621016e-08,
"loss": 0.8854,
"step": 2395
},
{
"epoch": 1.91,
"learning_rate": 5.584586887435739e-08,
"loss": 0.899,
"step": 2396
},
{
"epoch": 1.91,
"learning_rate": 5.488891730538015e-08,
"loss": 0.8953,
"step": 2397
},
{
"epoch": 1.91,
"learning_rate": 5.3940190457294486e-08,
"loss": 0.8449,
"step": 2398
},
{
"epoch": 1.91,
"learning_rate": 5.299968990802484e-08,
"loss": 0.8708,
"step": 2399
},
{
"epoch": 1.91,
"learning_rate": 5.206741722181385e-08,
"loss": 0.9039,
"step": 2400
},
{
"epoch": 1.91,
"learning_rate": 5.114337394921953e-08,
"loss": 0.9379,
"step": 2401
},
{
"epoch": 1.91,
"learning_rate": 5.0227561627113065e-08,
"loss": 0.8779,
"step": 2402
},
{
"epoch": 1.91,
"learning_rate": 4.9319981778676586e-08,
"loss": 0.8902,
"step": 2403
},
{
"epoch": 1.91,
"learning_rate": 4.842063591339763e-08,
"loss": 0.9483,
"step": 2404
},
{
"epoch": 1.91,
"learning_rate": 4.752952552707191e-08,
"loss": 0.9208,
"step": 2405
},
{
"epoch": 1.92,
"learning_rate": 4.664665210179553e-08,
"loss": 0.8263,
"step": 2406
},
{
"epoch": 1.92,
"learning_rate": 4.577201710596613e-08,
"loss": 0.8979,
"step": 2407
},
{
"epoch": 1.92,
"learning_rate": 4.490562199427839e-08,
"loss": 0.8719,
"step": 2408
},
{
"epoch": 1.92,
"learning_rate": 4.404746820772354e-08,
"loss": 0.8567,
"step": 2409
},
{
"epoch": 1.92,
"learning_rate": 4.3197557173584317e-08,
"loss": 0.8219,
"step": 2410
},
{
"epoch": 1.92,
"learning_rate": 4.235589030543496e-08,
"loss": 0.8768,
"step": 2411
},
{
"epoch": 1.92,
"learning_rate": 4.1522469003137946e-08,
"loss": 0.8877,
"step": 2412
},
{
"epoch": 1.92,
"learning_rate": 4.069729465284167e-08,
"loss": 0.8458,
"step": 2413
},
{
"epoch": 1.92,
"learning_rate": 3.98803686269783e-08,
"loss": 0.8403,
"step": 2414
},
{
"epoch": 1.92,
"learning_rate": 3.9071692284260997e-08,
"loss": 0.9086,
"step": 2415
},
{
"epoch": 1.92,
"learning_rate": 3.82712669696822e-08,
"loss": 0.8457,
"step": 2416
},
{
"epoch": 1.92,
"learning_rate": 3.747909401451144e-08,
"loss": 0.7857,
"step": 2417
},
{
"epoch": 1.93,
"learning_rate": 3.669517473629258e-08,
"loss": 0.8273,
"step": 2418
},
{
"epoch": 1.93,
"learning_rate": 3.591951043884212e-08,
"loss": 0.9321,
"step": 2419
},
{
"epoch": 1.93,
"learning_rate": 3.515210241224698e-08,
"loss": 0.9061,
"step": 2420
},
{
"epoch": 1.93,
"learning_rate": 3.439295193286174e-08,
"loss": 0.8496,
"step": 2421
},
{
"epoch": 1.93,
"learning_rate": 3.364206026330752e-08,
"loss": 0.8863,
"step": 2422
},
{
"epoch": 1.93,
"learning_rate": 3.28994286524692e-08,
"loss": 0.8362,
"step": 2423
},
{
"epoch": 1.93,
"learning_rate": 3.216505833549377e-08,
"loss": 0.8981,
"step": 2424
},
{
"epoch": 1.93,
"learning_rate": 3.143895053378698e-08,
"loss": 0.8538,
"step": 2425
},
{
"epoch": 1.93,
"learning_rate": 3.072110645501392e-08,
"loss": 0.8543,
"step": 2426
},
{
"epoch": 1.93,
"learning_rate": 3.001152729309453e-08,
"loss": 0.8858,
"step": 2427
},
{
"epoch": 1.93,
"learning_rate": 2.9310214228202016e-08,
"loss": 0.9019,
"step": 2428
},
{
"epoch": 1.93,
"learning_rate": 2.861716842676221e-08,
"loss": 0.8664,
"step": 2429
},
{
"epoch": 1.93,
"learning_rate": 2.79323910414514e-08,
"loss": 0.8384,
"step": 2430
},
{
"epoch": 1.94,
"learning_rate": 2.725588321119188e-08,
"loss": 0.9123,
"step": 2431
},
{
"epoch": 1.94,
"learning_rate": 2.6587646061153604e-08,
"loss": 0.8808,
"step": 2432
},
{
"epoch": 1.94,
"learning_rate": 2.5927680702750314e-08,
"loss": 0.8085,
"step": 2433
},
{
"epoch": 1.94,
"learning_rate": 2.527598823363786e-08,
"loss": 0.8947,
"step": 2434
},
{
"epoch": 1.94,
"learning_rate": 2.463256973771311e-08,
"loss": 0.8725,
"step": 2435
},
{
"epoch": 1.94,
"learning_rate": 2.3997426285110592e-08,
"loss": 0.849,
"step": 2436
},
{
"epoch": 1.94,
"learning_rate": 2.3370558932203635e-08,
"loss": 0.8599,
"step": 2437
},
{
"epoch": 1.94,
"learning_rate": 2.2751968721598237e-08,
"loss": 0.8854,
"step": 2438
},
{
"epoch": 1.94,
"learning_rate": 2.214165668213586e-08,
"loss": 0.8745,
"step": 2439
},
{
"epoch": 1.94,
"learning_rate": 2.153962382888841e-08,
"loss": 0.9252,
"step": 2440
},
{
"epoch": 1.94,
"learning_rate": 2.094587116315938e-08,
"loss": 0.8819,
"step": 2441
},
{
"epoch": 1.94,
"learning_rate": 2.0360399672478826e-08,
"loss": 0.8677,
"step": 2442
},
{
"epoch": 1.95,
"learning_rate": 1.978321033060504e-08,
"loss": 0.9498,
"step": 2443
},
{
"epoch": 1.95,
"learning_rate": 1.921430409752012e-08,
"loss": 0.8499,
"step": 2444
},
{
"epoch": 1.95,
"learning_rate": 1.865368191943051e-08,
"loss": 0.8519,
"step": 2445
},
{
"epoch": 1.95,
"learning_rate": 1.8101344728764236e-08,
"loss": 0.8803,
"step": 2446
},
{
"epoch": 1.95,
"learning_rate": 1.7557293444170343e-08,
"loss": 0.8351,
"step": 2447
},
{
"epoch": 1.95,
"learning_rate": 1.702152897051612e-08,
"loss": 0.8551,
"step": 2448
},
{
"epoch": 1.95,
"learning_rate": 1.6494052198886557e-08,
"loss": 0.8903,
"step": 2449
},
{
"epoch": 1.95,
"learning_rate": 1.5974864006581547e-08,
"loss": 0.8478,
"step": 2450
},
{
"epoch": 1.95,
"learning_rate": 1.5463965257116465e-08,
"loss": 0.824,
"step": 2451
},
{
"epoch": 1.95,
"learning_rate": 1.496135680021993e-08,
"loss": 0.8984,
"step": 2452
},
{
"epoch": 1.95,
"learning_rate": 1.4467039471831035e-08,
"loss": 0.8713,
"step": 2453
},
{
"epoch": 1.95,
"learning_rate": 1.3981014094099354e-08,
"loss": 0.9329,
"step": 2454
},
{
"epoch": 1.95,
"learning_rate": 1.3503281475383822e-08,
"loss": 0.8464,
"step": 2455
},
{
"epoch": 1.96,
"learning_rate": 1.3033842410251074e-08,
"loss": 0.9199,
"step": 2456
},
{
"epoch": 1.96,
"learning_rate": 1.2572697679472113e-08,
"loss": 0.8556,
"step": 2457
},
{
"epoch": 1.96,
"learning_rate": 1.2119848050025084e-08,
"loss": 0.8992,
"step": 2458
},
{
"epoch": 1.96,
"learning_rate": 1.1675294275089732e-08,
"loss": 0.8964,
"step": 2459
},
{
"epoch": 1.96,
"learning_rate": 1.123903709404961e-08,
"loss": 0.8375,
"step": 2460
},
{
"epoch": 1.96,
"learning_rate": 1.0811077232488754e-08,
"loss": 0.8903,
"step": 2461
},
{
"epoch": 1.96,
"learning_rate": 1.0391415402190575e-08,
"loss": 0.7948,
"step": 2462
},
{
"epoch": 1.96,
"learning_rate": 9.980052301137854e-09,
"loss": 0.8435,
"step": 2463
},
{
"epoch": 1.96,
"learning_rate": 9.576988613511084e-09,
"loss": 0.8212,
"step": 2464
},
{
"epoch": 1.96,
"learning_rate": 9.182225009686242e-09,
"loss": 0.8801,
"step": 2465
},
{
"epoch": 1.96,
"learning_rate": 8.795762146234787e-09,
"loss": 0.8739,
"step": 2466
},
{
"epoch": 1.96,
"learning_rate": 8.417600665923676e-09,
"loss": 0.8064,
"step": 2467
},
{
"epoch": 1.96,
"learning_rate": 8.04774119771201e-09,
"loss": 0.8006,
"step": 2468
},
{
"epoch": 1.97,
"learning_rate": 7.686184356749948e-09,
"loss": 0.8835,
"step": 2469
},
{
"epoch": 1.97,
"learning_rate": 7.332930744380906e-09,
"loss": 0.8921,
"step": 2470
},
{
"epoch": 1.97,
"learning_rate": 6.98798094813602e-09,
"loss": 0.9091,
"step": 2471
},
{
"epoch": 1.97,
"learning_rate": 6.65133554173747e-09,
"loss": 0.9006,
"step": 2472
},
{
"epoch": 1.97,
"learning_rate": 6.3229950850940414e-09,
"loss": 0.8948,
"step": 2473
},
{
"epoch": 1.97,
"learning_rate": 6.002960124303348e-09,
"loss": 0.8685,
"step": 2474
},
{
"epoch": 1.97,
"learning_rate": 5.691231191647384e-09,
"loss": 0.8543,
"step": 2475
},
{
"epoch": 1.97,
"learning_rate": 5.387808805594752e-09,
"loss": 0.8505,
"step": 2476
},
{
"epoch": 1.97,
"learning_rate": 5.092693470798438e-09,
"loss": 0.8679,
"step": 2477
},
{
"epoch": 1.97,
"learning_rate": 4.805885678095257e-09,
"loss": 0.8765,
"step": 2478
},
{
"epoch": 1.97,
"learning_rate": 4.527385904504189e-09,
"loss": 0.8962,
"step": 2479
},
{
"epoch": 1.97,
"learning_rate": 4.257194613226379e-09,
"loss": 0.8874,
"step": 2480
},
{
"epoch": 1.98,
"learning_rate": 3.995312253645689e-09,
"loss": 0.894,
"step": 2481
},
{
"epoch": 1.98,
"learning_rate": 3.741739261324817e-09,
"loss": 0.8676,
"step": 2482
},
{
"epoch": 1.98,
"learning_rate": 3.496476058006959e-09,
"loss": 0.7602,
"step": 2483
},
{
"epoch": 1.98,
"learning_rate": 3.2595230516152543e-09,
"loss": 0.8756,
"step": 2484
},
{
"epoch": 1.98,
"learning_rate": 3.0308806362494557e-09,
"loss": 0.8742,
"step": 2485
},
{
"epoch": 1.98,
"learning_rate": 2.8105491921887053e-09,
"loss": 0.7928,
"step": 2486
},
{
"epoch": 1.98,
"learning_rate": 2.598529085888757e-09,
"loss": 0.9008,
"step": 2487
},
{
"epoch": 1.98,
"learning_rate": 2.3948206699819787e-09,
"loss": 0.8378,
"step": 2488
},
{
"epoch": 1.98,
"learning_rate": 2.1994242832767965e-09,
"loss": 0.9583,
"step": 2489
},
{
"epoch": 1.98,
"learning_rate": 2.012340250756584e-09,
"loss": 0.9575,
"step": 2490
},
{
"epoch": 1.98,
"learning_rate": 1.8335688835802169e-09,
"loss": 0.8766,
"step": 2491
},
{
"epoch": 1.98,
"learning_rate": 1.6631104790809648e-09,
"loss": 0.845,
"step": 2492
},
{
"epoch": 1.98,
"learning_rate": 1.5009653207653795e-09,
"loss": 0.8746,
"step": 2493
},
{
"epoch": 1.99,
"learning_rate": 1.347133678313295e-09,
"loss": 0.8497,
"step": 2494
},
{
"epoch": 1.99,
"learning_rate": 1.2016158075789375e-09,
"loss": 0.8675,
"step": 2495
},
{
"epoch": 1.99,
"learning_rate": 1.0644119505864858e-09,
"loss": 0.8674,
"step": 2496
},
{
"epoch": 1.99,
"learning_rate": 9.355223355350662e-10,
"loss": 0.8104,
"step": 2497
},
{
"epoch": 1.99,
"learning_rate": 8.149471767937567e-10,
"loss": 0.8601,
"step": 2498
},
{
"epoch": 1.99,
"learning_rate": 7.026866749032524e-10,
"loss": 0.9253,
"step": 2499
},
{
"epoch": 1.99,
"learning_rate": 5.987410165758656e-10,
"loss": 0.8789,
"step": 2500
},
{
"epoch": 1.99,
"learning_rate": 5.031103746938604e-10,
"loss": 0.8577,
"step": 2501
},
{
"epoch": 1.99,
"learning_rate": 4.1579490831056277e-10,
"loss": 0.9354,
"step": 2502
},
{
"epoch": 1.99,
"learning_rate": 3.367947626498058e-10,
"loss": 0.8464,
"step": 2503
},
{
"epoch": 1.99,
"learning_rate": 2.6611006910370884e-10,
"loss": 0.8752,
"step": 2504
},
{
"epoch": 1.99,
"learning_rate": 2.0374094523600841e-10,
"loss": 0.9075,
"step": 2505
},
{
"epoch": 2.0,
"learning_rate": 1.4968749477872746e-10,
"loss": 0.8231,
"step": 2506
},
{
"epoch": 2.0,
"learning_rate": 1.0394980763384077e-10,
"loss": 0.8359,
"step": 2507
},
{
"epoch": 2.0,
"learning_rate": 6.652795987271975e-11,
"loss": 0.9356,
"step": 2508
},
{
"epoch": 2.0,
"learning_rate": 3.7422013735577414e-11,
"loss": 0.9649,
"step": 2509
},
{
"epoch": 2.0,
"learning_rate": 1.6632017630358045e-11,
"loss": 0.9309,
"step": 2510
},
{
"epoch": 2.0,
"learning_rate": 4.158006136623094e-12,
"loss": 0.8281,
"step": 2511
},
{
"epoch": 2.0,
"learning_rate": 0.0,
"loss": 0.8381,
"step": 2512
},
{
"epoch": 2.0,
"step": 2512,
"total_flos": 63824688046080.0,
"train_loss": 0.9549549028135029,
"train_runtime": 11239.963,
"train_samples_per_second": 10.721,
"train_steps_per_second": 0.223
}
],
"max_steps": 2512,
"num_train_epochs": 2,
"total_flos": 63824688046080.0,
"trial_name": null,
"trial_params": null
}