Downloads · 30 days
8
26% of all-time downloads
tab-anonymizer-v2
madaanpulkit/tab-anonymizer-v2
tab-anonymizer-v2 is a token classification model from madaanpulkit. Use it when you need labels on individual words, such as names. 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
31
Public
Repo size
2.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin266 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Nov 2, 2023
- Updated
- Nov 2, 2023
- SHA
- efb1a9dc
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. -->
tab-anonymizer-v2
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1163
- Recall Direct: 0.9069
- Recall Quasi: 0.8510
- Precision Direct: 0.9623
- Precision Quasi: 0.8630
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Recall Direct | Recall Quasi | Precision Direct | Precision Quasi |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 64 | 0.2676 | 0.0 | 0.6497 | nan | 0.7835 |
| No log | 2.0 | 128 | 0.1674 | 0.7479 | 0.7933 | 0.7118 | 0.8331 |
| No log | 3.0 | 192 | 0.1350 | 0.8173 | 0.8374 | 0.9271 | 0.8501 |
| No log | 4.0 | 256 | 0.1271 | 0.8714 | 0.8428 | 0.9381 | 0.8606 |
| No log | 5.0 | 320 | 0.1197 | 0.9002 | 0.8456 | 0.9333 | 0.8563 |
| No log | 6.0 | 384 | 0.1176 | 0.8985 | 0.8351 | 0.9499 | 0.8644 |
| No log | 7.0 | 448 | 0.1212 | 0.8934 | 0.8079 | 0.9670 | 0.8697 |
| 0.2055 | 8.0 | 512 | 0.1171 | 0.9069 | 0.8538 | 0.9606 | 0.8605 |
| 0.2055 | 9.0 | 576 | 0.1166 | 0.9069 | 0.8613 | 0.9623 | 0.8543 |
| 0.2055 | 10.0 | 640 | 0.1163 | 0.9069 | 0.8510 | 0.9623 | 0.8630 |
Framework versions
- Transformers 4.32.0
- Pytorch 1.12.0
- Datasets 2.10.1
- Tokenizers 0.13.3
- Task
- Token Classification
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Created
- Nov 2, 2023
- Updated
- Nov 2, 2023