<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bert-base-uncased-sst-2-32-21
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0145
- Accuracy: 0.875
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 150
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 2 | 1.0499 | 0.8125 |
| No log | 2.0 | 4 | 1.0524 | 0.8125 |
| No log | 3.0 | 6 | 1.0539 | 0.8125 |
| No log | 4.0 | 8 | 1.0539 | 0.8125 |
| 0.5899 | 5.0 | 10 | 1.0528 | 0.8125 |
| 0.5899 | 6.0 | 12 | 1.0524 | 0.8125 |
| 0.5899 | 7.0 | 14 | 1.0483 | 0.8125 |
| 0.5899 | 8.0 | 16 | 1.0416 | 0.8125 |
| 0.5899 | 9.0 | 18 | 1.0345 | 0.8125 |
| 0.4445 | 10.0 | 20 | 1.0251 | 0.8125 |
| 0.4445 | 11.0 | 22 | 1.0193 | 0.8125 |
| 0.4445 | 12.0 | 24 | 1.0143 | 0.8125 |
| 0.4445 | 13.0 | 26 | 1.0063 | 0.8281 |
| 0.4445 | 14.0 | 28 | 1.0024 | 0.8281 |
| 0.3304 | 15.0 | 30 | 0.9919 | 0.8281 |
| 0.3304 | 16.0 | 32 | 0.9848 | 0.8281 |
| 0.3304 | 17.0 | 34 | 0.9719 | 0.8281 |
| 0.3304 | 18.0 | 36 | 0.9605 | 0.8281 |
| 0.3304 | 19.0 | 38 | 0.9521 | 0.8281 |
| 0.2653 | 20.0 | 40 | 0.9440 | 0.8438 |
| 0.2653 | 21.0 | 42 | 0.9354 | 0.8594 |
| 0.2653 | 22.0 | 44 | 0.9302 | 0.8594 |
| 0.2653 | 23.0 | 46 | 0.9207 | 0.8594 |
| 0.2653 | 24.0 | 48 | 0.9098 | 0.8438 |
| 0.1597 | 25.0 | 50 | 0.9013 | 0.8438 |
| 0.1597 | 26.0 | 52 | 0.8944 | 0.8438 |
| 0.1597 | 27.0 | 54 | 0.8902 | 0.8438 |
| 0.1597 | 28.0 | 56 | 0.8888 | 0.8438 |
| 0.1597 | 29.0 | 58 | 0.8933 | 0.8438 |
| 0.1221 | 30.0 | 60 | 0.9068 | 0.8438 |
| 0.1221 | 31.0 | 62 | 0.9171 | 0.8438 |
| 0.1221 | 32.0 | 64 | 0.9209 | 0.8438 |
| 0.1221 | 33.0 | 66 | 0.9141 | 0.8438 |
| 0.1221 | 34.0 | 68 | 0.9113 | 0.8438 |
| 0.0292 | 35.0 | 70 | 0.9097 | 0.8438 |
| 0.0292 | 36.0 | 72 | 0.9044 | 0.8438 |
| 0.0292 | 37.0 | 74 | 0.8901 | 0.8438 |
| 0.0292 | 38.0 | 76 | 0.8745 | 0.8438 |
| 0.0292 | 39.0 | 78 | 0.8628 | 0.8594 |
| 0.0277 | 40.0 | 80 | 0.8533 | 0.8594 |
| 0.0277 | 41.0 | 82 | 0.8514 | 0.8594 |
| 0.0277 | 42.0 | 84 | 0.8535 | 0.8594 |
| 0.0277 | 43.0 | 86 | 0.8577 | 0.8594 |
| 0.0277 | 44.0 | 88 | 0.8616 | 0.8594 |
| 0.0058 | 45.0 | 90 | 0.8620 | 0.8594 |
| 0.0058 | 46.0 | 92 | 0.8650 | 0.8594 |
| 0.0058 | 47.0 | 94 | 0.8639 | 0.8594 |
| 0.0058 | 48.0 | 96 | 0.8666 | 0.8594 |
| 0.0058 | 49.0 | 98 | 0.8689 | 0.8594 |
| 0.0029 | 50.0 | 100 | 0.8701 | 0.8594 |
| 0.0029 | 51.0 | 102 | 0.8718 | 0.8594 |
| 0.0029 | 52.0 | 104 | 0.8821 | 0.8438 |
| 0.0029 | 53.0 | 106 | 0.9051 | 0.8438 |
| 0.0029 | 54.0 | 108 | 0.9265 | 0.8438 |
| 0.0024 | 55.0 | 110 | 0.9354 | 0.8438 |
| 0.0024 | 56.0 | 112 | 0.9213 | 0.8438 |
| 0.0024 | 57.0 | 114 | 0.8944 | 0.8438 |
| 0.0024 | 58.0 | 116 | 0.8806 | 0.875 |
| 0.0024 | 59.0 | 118 | 0.8787 | 0.875 |
| 0.0017 | 60.0 | 120 | 0.8820 | 0.875 |
| 0.0017 | 61.0 | 122 | 0.8880 | 0.8594 |
| 0.0017 | 62.0 | 124 | 0.8931 | 0.8594 |
| 0.0017 | 63.0 | 126 | 0.8966 | 0.8594 |
| 0.0017 | 64.0 | 128 | 0.8997 | 0.8594 |
| 0.0011 | 65.0 | 130 | 0.9026 | 0.8594 |
| 0.0011 | 66.0 | 132 | 0.9050 | 0.8594 |
| 0.0011 | 67.0 | 134 | 0.9065 | 0.8594 |
| 0.0011 | 68.0 | 136 | 0.9028 | 0.8594 |
| 0.0011 | 69.0 | 138 | 0.8963 | 0.8594 |
| 0.0013 | 70.0 | 140 | 0.8943 | 0.875 |
| 0.0013 | 71.0 | 142 | 0.8951 | 0.875 |
| 0.0013 | 72.0 | 144 | 0.8971 | 0.875 |
| 0.0013 | 73.0 | 146 | 0.9001 | 0.875 |
| 0.0013 | 74.0 | 148 | 0.9047 | 0.875 |
| 0.0073 | 75.0 | 150 | 0.9117 | 0.875 |
| 0.0073 | 76.0 | 152 | 0.9202 | 0.8438 |
| 0.0073 | 77.0 | 154 | 0.9281 | 0.8438 |
| 0.0073 | 78.0 | 156 | 0.9347 | 0.8438 |
| 0.0073 | 79.0 | 158 | 0.9403 | 0.8438 |
| 0.0008 | 80.0 | 160 | 0.9438 | 0.8438 |
| 0.0008 | 81.0 | 162 | 0.9421 | 0.8438 |
| 0.0008 | 82.0 | 164 | 0.9401 | 0.8438 |
| 0.0008 | 83.0 | 166 | 0.9382 | 0.8438 |
| 0.0008 | 84.0 | 168 | 0.9363 | 0.8438 |
| 0.0008 | 85.0 | 170 | 0.9341 | 0.8438 |
| 0.0008 | 86.0 | 172 | 0.9313 | 0.8594 |
| 0.0008 | 87.0 | 174 | 0.9280 | 0.8594 |
| 0.0008 | 88.0 | 176 | 0.9261 | 0.875 |
| 0.0008 | 89.0 | 178 | 0.9251 | 0.875 |
| 0.0007 | 90.0 | 180 | 0.9246 | 0.875 |
| 0.0007 | 91.0 | 182 | 0.9245 | 0.875 |
| 0.0007 | 92.0 | 184 | 0.9251 | 0.875 |
| 0.0007 | 93.0 | 186 | 0.9260 | 0.875 |
| 0.0007 | 94.0 | 188 | 0.9272 | 0.875 |
| 0.0006 | 95.0 | 190 | 0.9285 | 0.875 |
| 0.0006 | 96.0 | 192 | 0.9292 | 0.875 |
| 0.0006 | 97.0 | 194 | 0.9301 | 0.875 |
| 0.0006 | 98.0 | 196 | 0.9310 | 0.875 |
| 0.0006 | 99.0 | 198 | 0.9332 | 0.875 |
| 0.0009 | 100.0 | 200 | 0.9397 | 0.8594 |
| 0.0009 | 101.0 | 202 | 0.9488 | 0.8594 |
| 0.0009 | 102.0 | 204 | 0.9563 | 0.8594 |
| 0.0009 | 103.0 | 206 | 0.9610 | 0.8594 |
| 0.0009 | 104.0 | 208 | 0.9633 | 0.8594 |
| 0.0006 | 105.0 | 210 | 0.9627 | 0.8594 |
| 0.0006 | 106.0 | 212 | 0.9614 | 0.8594 |
| 0.0006 | 107.0 | 214 | 0.9602 | 0.8594 |
| 0.0006 | 108.0 | 216 | 0.9592 | 0.8594 |
| 0.0006 | 109.0 | 218 | 0.9584 | 0.8594 |
| 0.0005 | 110.0 | 220 | 0.9580 | 0.8594 |
| 0.0005 | 111.0 | 222 | 0.9580 | 0.8594 |
| 0.0005 | 112.0 | 224 | 0.9585 | 0.875 |
| 0.0005 | 113.0 | 226 | 0.9596 | 0.875 |
| 0.0005 | 114.0 | 228 | 0.9605 | 0.875 |
| 0.0004 | 115.0 | 230 | 0.9614 | 0.875 |
| 0.0004 | 116.0 | 232 | 0.9621 | 0.875 |
| 0.0004 | 117.0 | 234 | 0.9635 | 0.875 |
| 0.0004 | 118.0 | 236 | 0.9650 | 0.875 |
| 0.0004 | 119.0 | 238 | 0.9665 | 0.875 |
| 0.0004 | 120.0 | 240 | 0.9681 | 0.875 |
| 0.0004 | 121.0 | 242 | 0.9697 | 0.875 |
| 0.0004 | 122.0 | 244 | 0.9713 | 0.875 |
| 0.0004 | 123.0 | 246 | 0.9729 | 0.875 |
| 0.0004 | 124.0 | 248 | 0.9745 | 0.875 |
| 0.0004 | 125.0 | 250 | 0.9761 | 0.875 |
| 0.0004 | 126.0 | 252 | 0.9777 | 0.875 |
| 0.0004 | 127.0 | 254 | 0.9794 | 0.875 |
| 0.0004 | 128.0 | 256 | 0.9810 | 0.875 |
| 0.0004 | 129.0 | 258 | 0.9827 | 0.875 |
| 0.0004 | 130.0 | 260 | 0.9844 | 0.875 |
| 0.0004 | 131.0 | 262 | 0.9861 | 0.875 |
| 0.0004 | 132.0 | 264 | 0.9877 | 0.875 |
| 0.0004 | 133.0 | 266 | 0.9893 | 0.875 |
| 0.0004 | 134.0 | 268 | 0.9909 | 0.875 |
| 0.0003 | 135.0 | 270 | 0.9925 | 0.875 |
| 0.0003 | 136.0 | 272 | 0.9941 | 0.875 |
| 0.0003 | 137.0 | 274 | 0.9957 | 0.875 |
| 0.0003 | 138.0 | 276 | 0.9973 | 0.875 |
| 0.0003 | 139.0 | 278 | 0.9989 | 0.875 |
| 0.0003 | 140.0 | 280 | 1.0004 | 0.875 |
| 0.0003 | 141.0 | 282 | 1.0018 | 0.875 |
| 0.0003 | 142.0 | 284 | 1.0033 | 0.875 |
| 0.0003 | 143.0 | 286 | 1.0047 | 0.875 |
| 0.0003 | 144.0 | 288 | 1.0062 | 0.875 |
| 0.0003 | 145.0 | 290 | 1.0076 | 0.875 |
| 0.0003 | 146.0 | 292 | 1.0090 | 0.875 |
| 0.0003 | 147.0 | 294 | 1.0105 | 0.875 |
| 0.0003 | 148.0 | 296 | 1.0118 | 0.875 |
| 0.0003 | 149.0 | 298 | 1.0132 | 0.875 |
| 0.0003 | 150.0 | 300 | 1.0145 | 0.875 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.4.0
- Tokenizers 0.13.3
