Downloads · 30 days
13
26% of all-time downloads
conv-bert-base
TunahanGokcimen/conv-bert-base
conv-bert-base is a token classification model from TunahanGokcimen. Use it when you need labels on individual words, such as names. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
50
Public
Parameters
106M
2.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors423 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- convbert
- Access
- Public
- Created
- Jan 28, 2024
- Updated
- Jan 28, 2024
- SHA
- 492fb809
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. -->
conv-bert-base
This model is a fine-tuned version of YituTech/conv-bert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2024
- Precision: 0.7686
- Recall: 0.8278
- F1: 0.7971
- Accuracy: 0.9376
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2235 | 1.0 | 2078 | 0.2225 | 0.7307 | 0.7996 | 0.7636 | 0.9301 |
| 0.1814 | 2.0 | 4156 | 0.1946 | 0.7539 | 0.8257 | 0.7881 | 0.9363 |
| 0.1469 | 3.0 | 6234 | 0.2024 | 0.7686 | 0.8278 | 0.7971 | 0.9376 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
- Task
- Token Classification
- Library
- transformers
- Type
- convbert
- Created
- Jan 28, 2024
- Updated
- Jan 28, 2024