Downloads · 30 days
3
2% of all-time downloads
nekta_help_tc
webstels/nekta_help_tc
nekta_help_tc is a text classification model from webstels. Use it when you need a label for a piece of text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
139
Public
Repo size
30.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin268 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- distilbert
- Access
- Public
- Created
- Jun 16, 2023
- Updated
- Jun 22, 2023
- SHA
- 4c518e6c
Try a prompt
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. -->
nekta_help_tc
This model is a fine-tuned version of webstels/nekta_help_tc on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0145
- Accuracy: 0.9933
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 341 | 0.7823 | 0.7767 |
| 1.61 | 2.0 | 682 | 0.5028 | 0.8367 |
| 0.6434 | 3.0 | 1023 | 0.3594 | 0.8667 |
| 0.6434 | 4.0 | 1364 | 0.2428 | 0.9133 |
| 0.3982 | 5.0 | 1705 | 0.1740 | 0.94 |
| 0.2816 | 6.0 | 2046 | 0.1388 | 0.9367 |
| 0.2816 | 7.0 | 2387 | 0.0960 | 0.97 |
| 0.1886 | 8.0 | 2728 | 0.0430 | 0.99 |
| 0.1388 | 9.0 | 3069 | 0.0490 | 0.9833 |
| 0.1388 | 10.0 | 3410 | 0.0332 | 0.9867 |
| 0.1009 | 11.0 | 3751 | 0.0222 | 0.9933 |
| 0.0718 | 12.0 | 4092 | 0.0253 | 0.9867 |
| 0.0718 | 13.0 | 4433 | 0.0156 | 0.9933 |
| 0.0572 | 14.0 | 4774 | 0.0162 | 0.9967 |
| 0.0476 | 15.0 | 5115 | 0.0211 | 0.9933 |
| 0.0476 | 16.0 | 5456 | 0.0135 | 0.9933 |
| 0.0369 | 17.0 | 5797 | 0.0125 | 0.9967 |
| 0.0309 | 18.0 | 6138 | 0.0206 | 0.9933 |
| 0.0309 | 19.0 | 6479 | 0.0159 | 0.9933 |
| 0.0248 | 20.0 | 6820 | 0.0145 | 0.9933 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3
- Task
- Text Classification
- Library
- transformers
- Type
- distilbert
- Created
- Jun 16, 2023
- Updated
- Jun 22, 2023