<!-- 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. -->
distilroberta-base-finetuned-marktextepoch_n200
This model is a fine-tuned version of distilroberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0531
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2313 | 1.0 | 1500 | 2.1592 |
| 2.1731 | 2.0 | 3000 | 2.1277 |
| 2.153 | 3.0 | 4500 | 2.1144 |
| 2.1469 | 4.0 | 6000 | 2.1141 |
| 2.1281 | 5.0 | 7500 | 2.1374 |
| 2.1043 | 6.0 | 9000 | 2.1069 |
| 2.0834 | 7.0 | 10500 | 2.0993 |
| 2.0602 | 8.0 | 12000 | 2.0817 |
| 2.024 | 9.0 | 13500 | 2.0918 |
| 2.0261 | 10.0 | 15000 | 2.0793 |
| 1.9889 | 11.0 | 16500 | 2.0567 |
| 1.9915 | 12.0 | 18000 | 2.0700 |
| 1.9532 | 13.0 | 19500 | 2.0436 |
| 1.9362 | 14.0 | 21000 | 2.0596 |
| 1.9024 | 15.0 | 22500 | 2.0189 |
| 1.9262 | 16.0 | 24000 | 2.0435 |
| 1.8883 | 17.0 | 25500 | 2.0430 |
| 1.8867 | 18.0 | 27000 | 2.0416 |
| 1.8807 | 19.0 | 28500 | 2.0051 |
| 1.8517 | 20.0 | 30000 | 2.0338 |
| 1.8357 | 21.0 | 31500 | 2.0166 |
| 1.8241 | 22.0 | 33000 | 2.0355 |
| 1.7985 | 23.0 | 34500 | 2.0073 |
| 1.8061 | 24.0 | 36000 | 2.0473 |
| 1.7996 | 25.0 | 37500 | 2.0446 |
| 1.7786 | 26.0 | 39000 | 2.0086 |
| 1.771 | 27.0 | 40500 | 2.0294 |
| 1.7549 | 28.0 | 42000 | 2.0127 |
| 1.7726 | 29.0 | 43500 | 2.0191 |
| 1.7275 | 30.0 | 45000 | 2.0182 |
| 1.708 | 31.0 | 46500 | 2.0130 |
| 1.7345 | 32.0 | 48000 | 2.0155 |
| 1.7044 | 33.0 | 49500 | 1.9898 |
| 1.7126 | 34.0 | 51000 | 2.0166 |
| 1.698 | 35.0 | 52500 | 1.9879 |
| 1.6637 | 36.0 | 54000 | 2.0311 |
| 1.6854 | 37.0 | 55500 | 2.0355 |
| 1.6585 | 38.0 | 57000 | 2.0094 |
| 1.6418 | 39.0 | 58500 | 2.0042 |
| 1.667 | 40.0 | 60000 | 2.0116 |
| 1.6507 | 41.0 | 61500 | 2.0095 |
| 1.622 | 42.0 | 63000 | 2.0158 |
| 1.6381 | 43.0 | 64500 | 2.0339 |
| 1.6099 | 44.0 | 66000 | 2.0082 |
| 1.6076 | 45.0 | 67500 | 2.0207 |
| 1.5805 | 46.0 | 69000 | 2.0172 |
| 1.5862 | 47.0 | 70500 | 2.0132 |
| 1.5806 | 48.0 | 72000 | 2.0198 |
| 1.574 | 49.0 | 73500 | 2.0181 |
| 1.5718 | 50.0 | 75000 | 2.0086 |
| 1.5591 | 51.0 | 76500 | 1.9832 |
| 1.5468 | 52.0 | 78000 | 2.0167 |
| 1.5637 | 53.0 | 79500 | 2.0118 |
| 1.5117 | 54.0 | 81000 | 2.0290 |
| 1.5363 | 55.0 | 82500 | 2.0011 |
| 1.4976 | 56.0 | 84000 | 2.0160 |
| 1.5129 | 57.0 | 85500 | 2.0224 |
| 1.4964 | 58.0 | 87000 | 2.0219 |
| 1.4906 | 59.0 | 88500 | 2.0212 |
| 1.4941 | 60.0 | 90000 | 2.0255 |
| 1.4876 | 61.0 | 91500 | 2.0116 |
| 1.4837 | 62.0 | 93000 | 2.0176 |
| 1.4661 | 63.0 | 94500 | 2.0388 |
| 1.4634 | 64.0 | 96000 | 2.0165 |
| 1.4449 | 65.0 | 97500 | 2.0185 |
| 1.468 | 66.0 | 99000 | 2.0246 |
| 1.4567 | 67.0 | 100500 | 2.0244 |
| 1.4367 | 68.0 | 102000 | 2.0093 |
| 1.4471 | 69.0 | 103500 | 2.0101 |
| 1.4255 | 70.0 | 105000 | 2.0248 |
| 1.4203 | 71.0 | 106500 | 2.0224 |
| 1.42 | 72.0 | 108000 | 2.0279 |
| 1.4239 | 73.0 | 109500 | 2.0295 |
| 1.4126 | 74.0 | 111000 | 2.0196 |
| 1.4038 | 75.0 | 112500 | 2.0225 |
| 1.3874 | 76.0 | 114000 | 2.0456 |
| 1.3758 | 77.0 | 115500 | 2.0423 |
| 1.3924 | 78.0 | 117000 | 2.0184 |
| 1.3744 | 79.0 | 118500 | 2.0555 |
| 1.3622 | 80.0 | 120000 | 2.0387 |
| 1.3653 | 81.0 | 121500 | 2.0344 |
| 1.3724 | 82.0 | 123000 | 2.0184 |
| 1.3684 | 83.0 | 124500 | 2.0285 |
| 1.3576 | 84.0 | 126000 | 2.0544 |
| 1.348 | 85.0 | 127500 | 2.0412 |
| 1.3387 | 86.0 | 129000 | 2.0459 |
| 1.3416 | 87.0 | 130500 | 2.0329 |
| 1.3421 | 88.0 | 132000 | 2.0274 |
| 1.3266 | 89.0 | 133500 | 2.0233 |
| 1.3183 | 90.0 | 135000 | 2.0319 |
| 1.322 | 91.0 | 136500 | 2.0080 |
| 1.32 | 92.0 | 138000 | 2.0472 |
| 1.304 | 93.0 | 139500 | 2.0538 |
| 1.3061 | 94.0 | 141000 | 2.0340 |
| 1.3199 | 95.0 | 142500 | 2.0456 |
| 1.2985 | 96.0 | 144000 | 2.0167 |
| 1.3021 | 97.0 | 145500 | 2.0204 |
| 1.2787 | 98.0 | 147000 | 2.0645 |
| 1.2879 | 99.0 | 148500 | 2.0345 |
| 1.2695 | 100.0 | 150000 | 2.0340 |
| 1.2884 | 101.0 | 151500 | 2.0602 |
| 1.2747 | 102.0 | 153000 | 2.0667 |
| 1.2607 | 103.0 | 154500 | 2.0551 |
| 1.2551 | 104.0 | 156000 | 2.0544 |
| 1.2557 | 105.0 | 157500 | 2.0553 |
| 1.2495 | 106.0 | 159000 | 2.0370 |
| 1.26 | 107.0 | 160500 | 2.0568 |
| 1.2499 | 108.0 | 162000 | 2.0427 |
| 1.2438 | 109.0 | 163500 | 2.0184 |
| 1.2496 | 110.0 | 165000 | 2.0227 |
| 1.2332 | 111.0 | 166500 | 2.0621 |
| 1.2231 | 112.0 | 168000 | 2.0661 |
| 1.211 | 113.0 | 169500 | 2.0673 |
| 1.217 | 114.0 | 171000 | 2.0544 |
| 1.2206 | 115.0 | 172500 | 2.0542 |
| 1.2083 | 116.0 | 174000 | 2.0592 |
| 1.2205 | 117.0 | 175500 | 2.0451 |
| 1.2065 | 118.0 | 177000 | 2.0402 |
| 1.1988 | 119.0 | 178500 | 2.0615 |
| 1.218 | 120.0 | 180000 | 2.0374 |
| 1.1917 | 121.0 | 181500 | 2.0349 |
| 1.1854 | 122.0 | 183000 | 2.0790 |
| 1.1819 | 123.0 | 184500 | 2.0766 |
| 1.2029 | 124.0 | 186000 | 2.0364 |
| 1.1851 | 125.0 | 187500 | 2.0568 |
| 1.1734 | 126.0 | 189000 | 2.0445 |
| 1.1701 | 127.0 | 190500 | 2.0770 |
| 1.1824 | 128.0 | 192000 | 2.0566 |
| 1.1604 | 129.0 | 193500 | 2.0542 |
| 1.1733 | 130.0 | 195000 | 2.0525 |
| 1.1743 | 131.0 | 196500 | 2.0577 |
| 1.1692 | 132.0 | 198000 | 2.0723 |
| 1.1519 | 133.0 | 199500 | 2.0567 |
| 1.1401 | 134.0 | 201000 | 2.0795 |
| 1.1692 | 135.0 | 202500 | 2.0625 |
| 1.157 | 136.0 | 204000 | 2.0793 |
| 1.1495 | 137.0 | 205500 | 2.0782 |
| 1.1479 | 138.0 | 207000 | 2.0392 |
| 1.1247 | 139.0 | 208500 | 2.0796 |
| 1.143 | 140.0 | 210000 | 2.0369 |
| 1.1324 | 141.0 | 211500 | 2.0699 |
| 1.1341 | 142.0 | 213000 | 2.0694 |
| 1.1317 | 143.0 | 214500 | 2.0569 |
| 1.1254 | 144.0 | 216000 | 2.0545 |
| 1.1156 | 145.0 | 217500 | 2.0708 |
| 1.1353 | 146.0 | 219000 | 2.0767 |
| 1.1312 | 147.0 | 220500 | 2.0523 |
| 1.1224 | 148.0 | 222000 | 2.0565 |
| 1.106 | 149.0 | 223500 | 2.0696 |
| 1.1069 | 150.0 | 225000 | 2.0478 |
| 1.1011 | 151.0 | 226500 | 2.0475 |
| 1.0985 | 152.0 | 228000 | 2.0888 |
| 1.1107 | 153.0 | 229500 | 2.0756 |
| 1.1058 | 154.0 | 231000 | 2.0812 |
| 1.1027 | 155.0 | 232500 | 2.0597 |
| 1.0996 | 156.0 | 234000 | 2.0684 |
| 1.0987 | 157.0 | 235500 | 2.0629 |
| 1.0881 | 158.0 | 237000 | 2.0701 |
| 1.1143 | 159.0 | 238500 | 2.0740 |
| 1.0823 | 160.0 | 240000 | 2.0869 |
| 1.0925 | 161.0 | 241500 | 2.0567 |
| 1.1034 | 162.0 | 243000 | 2.0833 |
| 1.0759 | 163.0 | 244500 | 2.0585 |
| 1.0998 | 164.0 | 246000 | 2.0293 |
| 1.0891 | 165.0 | 247500 | 2.0608 |
| 1.1036 | 166.0 | 249000 | 2.0831 |
| 1.076 | 167.0 | 250500 | 2.0979 |
| 1.0895 | 168.0 | 252000 | 2.0882 |
| 1.0825 | 169.0 | 253500 | 2.0742 |
| 1.0793 | 170.0 | 255000 | 2.0841 |
| 1.079 | 171.0 | 256500 | 2.0829 |
| 1.0653 | 172.0 | 258000 | 2.0888 |
| 1.0834 | 173.0 | 259500 | 2.0784 |
| 1.0721 | 174.0 | 261000 | 2.0859 |
| 1.0712 | 175.0 | 262500 | 2.0810 |
| 1.0494 | 176.0 | 264000 | 2.0605 |
| 1.0654 | 177.0 | 265500 | 2.0623 |
| 1.077 | 178.0 | 267000 | 2.0756 |
| 1.056 | 179.0 | 268500 | 2.0782 |
| 1.0523 | 180.0 | 270000 | 2.0966 |
| 1.0656 | 181.0 | 271500 | 2.0750 |
| 1.0636 | 182.0 | 273000 | 2.0769 |
| 1.0851 | 183.0 | 274500 | 2.0872 |
| 1.0562 | 184.0 | 276000 | 2.0893 |
| 1.0534 | 185.0 | 277500 | 2.0661 |
| 1.0514 | 186.0 | 279000 | 2.0712 |
| 1.062 | 187.0 | 280500 | 2.0769 |
| 1.0683 | 188.0 | 282000 | 2.0765 |
| 1.0606 | 189.0 | 283500 | 2.0735 |
| 1.0555 | 190.0 | 285000 | 2.0710 |
| 1.0568 | 191.0 | 286500 | 2.0860 |
| 1.0502 | 192.0 | 288000 | 2.0587 |
| 1.0437 | 193.0 | 289500 | 2.0998 |
| 1.0534 | 194.0 | 291000 | 2.0418 |
| 1.062 | 195.0 | 292500 | 2.0724 |
| 1.0457 | 196.0 | 294000 | 2.0612 |
| 1.0501 | 197.0 | 295500 | 2.1012 |
| 1.0728 | 198.0 | 297000 | 2.0721 |
| 1.0413 | 199.0 | 298500 | 2.0535 |
| 1.0461 | 200.0 | 300000 | 2.0531 |
Framework versions
- Transformers 4.21.0
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
