Downloads · 30 days
8
32% of all-time downloads
uniBERT.distilBERT.2
dbala02/uniBERT.distilBERT.2
uniBERT.distilBERT.2 is a token classification model from dbala02. 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
25
Public
Parameters
66.4M
266 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors266 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Apr 5, 2024
- Updated
- Apr 5, 2024
- SHA
- 1e522c1e
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. -->
uniBERT.distilBERT.2
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6169
- Accuracy: (0.5361930294906166,)
- F1: (0.5387444240059887,)
- Precision: (0.5567514462203529,)
- Recall: 0.5362
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: 64
- 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 | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 3.0538 | 1.0 | 187 | 2.7787 | (0.225201072386059,) | (0.18836848263830908,) | (0.3149708790620786,) | 0.2252 |
| 2.198 | 2.0 | 374 | 2.2031 | (0.3753351206434316,) | (0.3631236683415291,) | (0.42784864295242175,) | 0.3753 |
| 1.7009 | 3.0 | 561 | 1.9210 | (0.4410187667560322,) | (0.4323447164030645,) | (0.46798465231264463,) | 0.4410 |
| 1.3871 | 4.0 | 748 | 1.7879 | (0.47050938337801607,) | (0.46788445138156415,) | (0.4993274459424259,) | 0.4705 |
| 1.0832 | 5.0 | 935 | 1.7004 | (0.5067024128686327,) | (0.5103273615495704,) | (0.5379322201073571,) | 0.5067 |
| 0.8772 | 6.0 | 1122 | 1.6449 | (0.5120643431635389,) | (0.5113608061573298,) | (0.534501997594668,) | 0.5121 |
| 0.695 | 7.0 | 1309 | 1.6427 | (0.5254691689008043,) | (0.5284135185976587,) | (0.5461241615837267,) | 0.5255 |
| 0.5712 | 8.0 | 1496 | 1.6336 | (0.5241286863270778,) | (0.5266745245913999,) | (0.5544118981578735,) | 0.5241 |
| 0.5588 | 9.0 | 1683 | 1.6163 | (0.5348525469168901,) | (0.5375963439943585,) | (0.5584699977736378,) | 0.5349 |
| 0.4567 | 10.0 | 1870 | 1.6169 | (0.5361930294906166,) | (0.5387444240059887,) | (0.5567514462203529,) | 0.5362 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Token Classification
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Created
- Apr 5, 2024
- Updated
- Apr 5, 2024