Downloads · 30 days
8
10% of all-time downloads
nerel-bio-RuBioBERT-al
ekaterinatao/nerel-bio-RuBioBERT-al
nerel-bio-RuBioBERT-al is a token classification model from ekaterinatao. 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
79
Public
Parameters
178M
2.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors711 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Feb 29, 2024
- Updated
- Mar 29, 2024
- SHA
- ce18fd2b
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. -->
nerel-bio-RuBioBERT-al
This model is a fine-tuned version of alexyalunin/RuBioBERT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9899
- Precision: 0.7839
- Recall: 0.7903
- F1: 0.7871
- Accuracy: 0.8572
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.044 | 1.0 | 153 | 0.8960 | 0.7760 | 0.7814 | 0.7787 | 0.8499 |
| 0.0126 | 2.0 | 306 | 0.9091 | 0.7808 | 0.7810 | 0.7809 | 0.8505 |
| 0.0264 | 3.0 | 459 | 0.8231 | 0.7871 | 0.7896 | 0.7883 | 0.8572 |
| 0.007 | 4.0 | 612 | 0.9504 | 0.7825 | 0.7873 | 0.7849 | 0.8552 |
| 0.0027 | 5.0 | 765 | 0.9055 | 0.7838 | 0.7915 | 0.7876 | 0.8581 |
| 0.0066 | 6.0 | 918 | 0.9222 | 0.7829 | 0.7859 | 0.7844 | 0.8577 |
| 0.0005 | 7.0 | 1071 | 0.9561 | 0.7805 | 0.7903 | 0.7854 | 0.8564 |
| 0.0003 | 8.0 | 1224 | 0.9858 | 0.7816 | 0.7889 | 0.7852 | 0.8567 |
| 0.0004 | 9.0 | 1377 | 0.9904 | 0.7834 | 0.7899 | 0.7866 | 0.8572 |
| 0.0003 | 10.0 | 1530 | 0.9899 | 0.7839 | 0.7903 | 0.7871 | 0.8572 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- Created
- Feb 29, 2024
- Updated
- Mar 29, 2024