metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: best_model-yelp_polarity-32-13
results: []
best_model-yelp_polarity-32-13
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7343
- Accuracy: 0.9219
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 | 0.5150 | 0.9375 |
No log | 2.0 | 4 | 0.5183 | 0.9375 |
No log | 3.0 | 6 | 0.5239 | 0.9375 |
No log | 4.0 | 8 | 0.5297 | 0.9375 |
0.121 | 5.0 | 10 | 0.5354 | 0.9375 |
0.121 | 6.0 | 12 | 0.5416 | 0.9375 |
0.121 | 7.0 | 14 | 0.5505 | 0.9375 |
0.121 | 8.0 | 16 | 0.5631 | 0.9219 |
0.121 | 9.0 | 18 | 0.5919 | 0.9219 |
0.0647 | 10.0 | 20 | 0.6157 | 0.9219 |
0.0647 | 11.0 | 22 | 0.6462 | 0.9062 |
0.0647 | 12.0 | 24 | 0.6650 | 0.9062 |
0.0647 | 13.0 | 26 | 0.6774 | 0.9062 |
0.0647 | 14.0 | 28 | 0.6785 | 0.9062 |
0.0493 | 15.0 | 30 | 0.6712 | 0.9062 |
0.0493 | 16.0 | 32 | 0.6561 | 0.9062 |
0.0493 | 17.0 | 34 | 0.6397 | 0.9219 |
0.0493 | 18.0 | 36 | 0.6254 | 0.9219 |
0.0493 | 19.0 | 38 | 0.6044 | 0.9219 |
0.0344 | 20.0 | 40 | 0.5844 | 0.9219 |
0.0344 | 21.0 | 42 | 0.5757 | 0.9219 |
0.0344 | 22.0 | 44 | 0.5695 | 0.9219 |
0.0344 | 23.0 | 46 | 0.5683 | 0.9219 |
0.0344 | 24.0 | 48 | 0.5848 | 0.9219 |
0.0002 | 25.0 | 50 | 0.6016 | 0.9219 |
0.0002 | 26.0 | 52 | 0.6158 | 0.9219 |
0.0002 | 27.0 | 54 | 0.6269 | 0.9219 |
0.0002 | 28.0 | 56 | 0.6424 | 0.9219 |
0.0002 | 29.0 | 58 | 0.6560 | 0.9219 |
0.0039 | 30.0 | 60 | 0.6640 | 0.9219 |
0.0039 | 31.0 | 62 | 0.6670 | 0.9219 |
0.0039 | 32.0 | 64 | 0.6696 | 0.9219 |
0.0039 | 33.0 | 66 | 0.6720 | 0.9219 |
0.0039 | 34.0 | 68 | 0.6731 | 0.9219 |
0.0002 | 35.0 | 70 | 0.6740 | 0.9219 |
0.0002 | 36.0 | 72 | 0.6748 | 0.9219 |
0.0002 | 37.0 | 74 | 0.6735 | 0.9219 |
0.0002 | 38.0 | 76 | 0.6727 | 0.9219 |
0.0002 | 39.0 | 78 | 0.6710 | 0.9219 |
0.0001 | 40.0 | 80 | 0.6682 | 0.9219 |
0.0001 | 41.0 | 82 | 0.6650 | 0.9219 |
0.0001 | 42.0 | 84 | 0.6767 | 0.9219 |
0.0001 | 43.0 | 86 | 0.6856 | 0.9219 |
0.0001 | 44.0 | 88 | 0.6906 | 0.9219 |
0.0001 | 45.0 | 90 | 0.6949 | 0.9219 |
0.0001 | 46.0 | 92 | 0.6931 | 0.9219 |
0.0001 | 47.0 | 94 | 0.6904 | 0.9219 |
0.0001 | 48.0 | 96 | 0.6855 | 0.9219 |
0.0001 | 49.0 | 98 | 0.6793 | 0.9219 |
0.0002 | 50.0 | 100 | 0.6721 | 0.9219 |
0.0002 | 51.0 | 102 | 0.6642 | 0.9219 |
0.0002 | 52.0 | 104 | 0.6566 | 0.9219 |
0.0002 | 53.0 | 106 | 0.6494 | 0.9219 |
0.0002 | 54.0 | 108 | 0.6429 | 0.9219 |
0.0001 | 55.0 | 110 | 0.6377 | 0.9219 |
0.0001 | 56.0 | 112 | 0.6401 | 0.9219 |
0.0001 | 57.0 | 114 | 0.6488 | 0.9219 |
0.0001 | 58.0 | 116 | 0.6571 | 0.9219 |
0.0001 | 59.0 | 118 | 0.6641 | 0.9219 |
0.0001 | 60.0 | 120 | 0.6696 | 0.9219 |
0.0001 | 61.0 | 122 | 0.6740 | 0.9219 |
0.0001 | 62.0 | 124 | 0.6776 | 0.9219 |
0.0001 | 63.0 | 126 | 0.6806 | 0.9219 |
0.0001 | 64.0 | 128 | 0.6831 | 0.9219 |
0.0001 | 65.0 | 130 | 0.6851 | 0.9219 |
0.0001 | 66.0 | 132 | 0.6871 | 0.9219 |
0.0001 | 67.0 | 134 | 0.6893 | 0.9219 |
0.0001 | 68.0 | 136 | 0.6912 | 0.9219 |
0.0001 | 69.0 | 138 | 0.6925 | 0.9219 |
0.0001 | 70.0 | 140 | 0.6936 | 0.9219 |
0.0001 | 71.0 | 142 | 0.6946 | 0.9219 |
0.0001 | 72.0 | 144 | 0.6956 | 0.9219 |
0.0001 | 73.0 | 146 | 0.6963 | 0.9219 |
0.0001 | 74.0 | 148 | 0.6969 | 0.9219 |
0.0001 | 75.0 | 150 | 0.6972 | 0.9219 |
0.0001 | 76.0 | 152 | 0.6977 | 0.9219 |
0.0001 | 77.0 | 154 | 0.6982 | 0.9219 |
0.0001 | 78.0 | 156 | 0.6984 | 0.9219 |
0.0001 | 79.0 | 158 | 0.6989 | 0.9219 |
0.0001 | 80.0 | 160 | 0.6996 | 0.9219 |
0.0001 | 81.0 | 162 | 0.7006 | 0.9219 |
0.0001 | 82.0 | 164 | 0.7011 | 0.9219 |
0.0001 | 83.0 | 166 | 0.7016 | 0.9219 |
0.0001 | 84.0 | 168 | 0.7024 | 0.9219 |
0.0001 | 85.0 | 170 | 0.7030 | 0.9219 |
0.0001 | 86.0 | 172 | 0.7038 | 0.9219 |
0.0001 | 87.0 | 174 | 0.7051 | 0.9219 |
0.0001 | 88.0 | 176 | 0.7061 | 0.9219 |
0.0001 | 89.0 | 178 | 0.7072 | 0.9219 |
0.0001 | 90.0 | 180 | 0.7082 | 0.9219 |
0.0001 | 91.0 | 182 | 0.7091 | 0.9219 |
0.0001 | 92.0 | 184 | 0.7099 | 0.9219 |
0.0001 | 93.0 | 186 | 0.7107 | 0.9219 |
0.0001 | 94.0 | 188 | 0.7116 | 0.9219 |
0.0001 | 95.0 | 190 | 0.7126 | 0.9219 |
0.0001 | 96.0 | 192 | 0.7136 | 0.9219 |
0.0001 | 97.0 | 194 | 0.7146 | 0.9219 |
0.0001 | 98.0 | 196 | 0.7156 | 0.9219 |
0.0001 | 99.0 | 198 | 0.7165 | 0.9219 |
0.0001 | 100.0 | 200 | 0.7172 | 0.9219 |
0.0001 | 101.0 | 202 | 0.7172 | 0.9219 |
0.0001 | 102.0 | 204 | 0.7174 | 0.9219 |
0.0001 | 103.0 | 206 | 0.7178 | 0.9219 |
0.0001 | 104.0 | 208 | 0.7188 | 0.9219 |
0.0001 | 105.0 | 210 | 0.7195 | 0.9219 |
0.0001 | 106.0 | 212 | 0.7203 | 0.9219 |
0.0001 | 107.0 | 214 | 0.7212 | 0.9219 |
0.0001 | 108.0 | 216 | 0.7220 | 0.9219 |
0.0001 | 109.0 | 218 | 0.7230 | 0.9219 |
0.0001 | 110.0 | 220 | 0.7247 | 0.9219 |
0.0001 | 111.0 | 222 | 0.7264 | 0.9219 |
0.0001 | 112.0 | 224 | 0.7280 | 0.9219 |
0.0001 | 113.0 | 226 | 0.7294 | 0.9219 |
0.0001 | 114.0 | 228 | 0.7313 | 0.9219 |
0.0001 | 115.0 | 230 | 0.7328 | 0.9219 |
0.0001 | 116.0 | 232 | 0.7343 | 0.9219 |
0.0001 | 117.0 | 234 | 0.7357 | 0.9219 |
0.0001 | 118.0 | 236 | 0.7369 | 0.9219 |
0.0001 | 119.0 | 238 | 0.7378 | 0.9219 |
0.0001 | 120.0 | 240 | 0.7387 | 0.9219 |
0.0001 | 121.0 | 242 | 0.7394 | 0.9219 |
0.0001 | 122.0 | 244 | 0.7401 | 0.9219 |
0.0001 | 123.0 | 246 | 0.7409 | 0.9219 |
0.0001 | 124.0 | 248 | 0.7418 | 0.9219 |
0.0 | 125.0 | 250 | 0.7427 | 0.9219 |
0.0 | 126.0 | 252 | 0.7438 | 0.9219 |
0.0 | 127.0 | 254 | 0.7451 | 0.9219 |
0.0 | 128.0 | 256 | 0.7463 | 0.9219 |
0.0 | 129.0 | 258 | 0.7474 | 0.9219 |
0.0 | 130.0 | 260 | 0.7486 | 0.9219 |
0.0 | 131.0 | 262 | 0.7500 | 0.9219 |
0.0 | 132.0 | 264 | 0.7514 | 0.9219 |
0.0 | 133.0 | 266 | 0.7528 | 0.9219 |
0.0 | 134.0 | 268 | 0.8507 | 0.8906 |
0.0001 | 135.0 | 270 | 1.0733 | 0.8906 |
0.0001 | 136.0 | 272 | 1.2689 | 0.8594 |
0.0001 | 137.0 | 274 | 0.9691 | 0.8906 |
0.0001 | 138.0 | 276 | 0.7454 | 0.9062 |
0.0001 | 139.0 | 278 | 0.7415 | 0.9219 |
0.0136 | 140.0 | 280 | 0.7437 | 0.9219 |
0.0136 | 141.0 | 282 | 0.7095 | 0.9219 |
0.0136 | 142.0 | 284 | 0.6249 | 0.9219 |
0.0136 | 143.0 | 286 | 0.5231 | 0.9375 |
0.0136 | 144.0 | 288 | 0.4934 | 0.9531 |
0.0 | 145.0 | 290 | 0.4934 | 0.9531 |
0.0 | 146.0 | 292 | 0.6506 | 0.9219 |
0.0 | 147.0 | 294 | 0.7018 | 0.9219 |
0.0 | 148.0 | 296 | 0.6696 | 0.9219 |
0.0 | 149.0 | 298 | 0.7124 | 0.9219 |
0.022 | 150.0 | 300 | 0.7343 | 0.9219 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.4.0
- Tokenizers 0.13.3