Downloads · 30 days
2
11% of all-time downloads
BERT_AugV8_k5_task1_organization_sp020_lw010_fold1
genki10/BERT_AugV8_k5_task1_organization_sp020_lw010_fold1
BERT_AugV8_k5_task1_organization_sp020_lw010_fold1 is a text classification model from genki10. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
19
Public
Repo size
34.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin876 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Mar 25, 2025
- Updated
- Mar 25, 2025
- SHA
- fb5925cd
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- 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_AugV8_k5_task1_organization_sp020_lw010_fold1
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1409
- Qwk: 0.2260
- Mse: 1.1395
- Rmse: 1.0675
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 150
Training results
| Training Loss | Epoch | Step | Validation Loss | Qwk | Mse | Rmse |
|---|---|---|---|---|---|---|
| No log | 1.0 | 4 | 9.5925 | 0.0 | 9.5899 | 3.0968 |
| No log | 2.0 | 8 | 7.1833 | 0.0 | 7.1810 | 2.6797 |
| No log | 3.0 | 12 | 4.7035 | 0.0040 | 4.7014 | 2.1683 |
| No log | 4.0 | 16 | 2.7695 | 0.0 | 2.7677 | 1.6636 |
| No log | 5.0 | 20 | 1.3644 | 0.0106 | 1.3630 | 1.1675 |
| No log | 6.0 | 24 | 1.0797 | 0.0 | 1.0783 | 1.0384 |
| No log | 7.0 | 28 | 0.8933 | 0.2081 | 0.8920 | 0.9445 |
| No log | 8.0 | 32 | 1.2094 | 0.0315 | 1.2079 | 1.0991 |
| No log | 9.0 | 36 | 0.8573 | 0.2553 | 0.8561 | 0.9252 |
| No log | 10.0 | 40 | 1.1538 | 0.1277 | 1.1524 | 1.0735 |
| No log | 11.0 | 44 | 1.6550 | 0.0321 | 1.6532 | 1.2858 |
| No log | 12.0 | 48 | 1.0212 | 0.1941 | 1.0196 | 1.0098 |
| No log | 13.0 | 52 | 1.1793 | 0.1653 | 1.1776 | 1.0852 |
| No log | 14.0 | 56 | 1.3121 | 0.0998 | 1.3107 | 1.1449 |
| No log | 15.0 | 60 | 1.0868 | 0.1833 | 1.0852 | 1.0417 |
| No log | 16.0 | 64 | 1.3628 | 0.1718 | 1.3612 | 1.1667 |
| No log | 17.0 | 68 | 1.1416 | 0.2516 | 1.1404 | 1.0679 |
| No log | 18.0 | 72 | 1.0877 | 0.3133 | 1.0866 | 1.0424 |
| No log | 19.0 | 76 | 1.9281 | 0.1063 | 1.9263 | 1.3879 |
| No log | 20.0 | 80 | 1.1144 | 0.2742 | 1.1133 | 1.0551 |
| No log | 21.0 | 84 | 1.1998 | 0.2743 | 1.1987 | 1.0949 |
| No log | 22.0 | 88 | 1.5812 | 0.1487 | 1.5801 | 1.2570 |
| No log | 23.0 | 92 | 1.2605 | 0.2387 | 1.2593 | 1.1222 |
| No log | 24.0 | 96 | 1.2252 | 0.2585 | 1.2240 | 1.1064 |
| No log | 25.0 | 100 | 1.5562 | 0.1782 | 1.5547 | 1.2469 |
| No log | 26.0 | 104 | 1.3537 | 0.2167 | 1.3523 | 1.1629 |
| No log | 27.0 | 108 | 1.2386 | 0.2479 | 1.2373 | 1.1123 |
| No log | 28.0 | 112 | 1.6362 | 0.1697 | 1.6346 | 1.2785 |
| No log | 29.0 | 116 | 1.0913 | 0.3006 | 1.0902 | 1.0441 |
| No log | 30.0 | 120 | 1.5837 | 0.1853 | 1.5821 | 1.2578 |
| No log | 31.0 | 124 | 0.9838 | 0.3349 | 0.9826 | 0.9913 |
| No log | 32.0 | 128 | 1.3612 | 0.2245 | 1.3595 | 1.1660 |
| No log | 33.0 | 132 | 1.4710 | 0.2028 | 1.4693 | 1.2121 |
| No log | 34.0 | 136 | 1.2410 | 0.2643 | 1.2394 | 1.1133 |
| No log | 35.0 | 140 | 1.1889 | 0.2833 | 1.1874 | 1.0897 |
| No log | 36.0 | 144 | 1.1914 | 0.2692 | 1.1899 | 1.0908 |
| No log | 37.0 | 148 | 1.3554 | 0.2358 | 1.3539 | 1.1636 |
| No log | 38.0 | 152 | 1.2932 | 0.2523 | 1.2917 | 1.1365 |
| No log | 39.0 | 156 | 0.9307 | 0.3616 | 0.9297 | 0.9642 |
| No log | 40.0 | 160 | 1.3267 | 0.2145 | 1.3253 | 1.1512 |
| No log | 41.0 | 164 | 1.0991 | 0.2576 | 1.0981 | 1.0479 |
| No log | 42.0 | 168 | 1.6710 | 0.1526 | 1.6697 | 1.2922 |
| No log | 43.0 | 172 | 1.1649 | 0.2792 | 1.1638 | 1.0788 |
| No log | 44.0 | 176 | 1.4090 | 0.1917 | 1.4076 | 1.1864 |
| No log | 45.0 | 180 | 1.3119 | 0.2068 | 1.3105 | 1.1448 |
| No log | 46.0 | 184 | 1.2129 | 0.2346 | 1.2114 | 1.1006 |
| No log | 47.0 | 188 | 1.1763 | 0.2662 | 1.1749 | 1.0839 |
| No log | 48.0 | 192 | 1.2245 | 0.2433 | 1.2231 | 1.1059 |
| No log | 49.0 | 196 | 1.1032 | 0.2606 | 1.1019 | 1.0497 |
| No log | 50.0 | 200 | 1.5014 | 0.1660 | 1.4997 | 1.2246 |
| No log | 51.0 | 204 | 1.0665 | 0.3000 | 1.0651 | 1.0321 |
| No log | 52.0 | 208 | 1.4760 | 0.2040 | 1.4744 | 1.2142 |
| No log | 53.0 | 212 | 0.9048 | 0.3767 | 0.9038 | 0.9507 |
| No log | 54.0 | 216 | 1.3685 | 0.2111 | 1.3671 | 1.1692 |
| No log | 55.0 | 220 | 0.9099 | 0.3359 | 0.9088 | 0.9533 |
| No log | 56.0 | 224 | 1.2634 | 0.2237 | 1.2620 | 1.1234 |
| No log | 57.0 | 228 | 1.0734 | 0.2780 | 1.0720 | 1.0354 |
| No log | 58.0 | 232 | 1.2005 | 0.2319 | 1.1989 | 1.0949 |
| No log | 59.0 | 236 | 1.2346 | 0.2372 | 1.2332 | 1.1105 |
| No log | 60.0 | 240 | 1.2461 | 0.2125 | 1.2445 | 1.1156 |
| No log | 61.0 | 244 | 0.9977 | 0.2918 | 0.9964 | 0.9982 |
| No log | 62.0 | 248 | 1.3505 | 0.1876 | 1.3490 | 1.1615 |
| No log | 63.0 | 252 | 1.1685 | 0.2472 | 1.1672 | 1.0804 |
| No log | 64.0 | 256 | 1.2135 | 0.2378 | 1.2121 | 1.1010 |
| No log | 65.0 | 260 | 1.0967 | 0.2616 | 1.0954 | 1.0466 |
| No log | 66.0 | 264 | 1.2991 | 0.1931 | 1.2977 | 1.1392 |
| No log | 67.0 | 268 | 1.2155 | 0.2059 | 1.2141 | 1.1019 |
| No log | 68.0 | 272 | 1.1409 | 0.2260 | 1.1395 | 1.0675 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Mar 25, 2025
- Updated
- Mar 25, 2025