Downloads · 30 days
23
3% of all-time downloads
tiny_focal_v3
kktoto/tiny_focal_v3
tiny_focal_v3 is a token classification model from kktoto. 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
801
Public
Repo size
4.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin45.3 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Jun 25, 2022
- Updated
- Jun 25, 2022
- SHA
- fa1d8738
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. -->
tiny_focal_v3
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0023
- Precision: 0.6975
- Recall: 0.6822
- F1: 0.6898
- Accuracy: 0.9515
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: 3e-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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.004 | 1.0 | 5561 | 0.0032 | 0.6900 | 0.6102 | 0.6477 | 0.9454 |
| 0.0032 | 2.0 | 11122 | 0.0028 | 0.6901 | 0.6406 | 0.6644 | 0.9477 |
| 0.0029 | 3.0 | 16683 | 0.0026 | 0.6956 | 0.6509 | 0.6725 | 0.9490 |
| 0.0025 | 4.0 | 22244 | 0.0025 | 0.6838 | 0.6764 | 0.6801 | 0.9493 |
| 0.0024 | 5.0 | 27805 | 0.0024 | 0.6954 | 0.6715 | 0.6832 | 0.9504 |
| 0.0023 | 6.0 | 33366 | 0.0024 | 0.7125 | 0.6524 | 0.6811 | 0.9512 |
| 0.0021 | 7.0 | 38927 | 0.0023 | 0.6999 | 0.6748 | 0.6872 | 0.9514 |
| 0.0019 | 8.0 | 44488 | 0.0024 | 0.6962 | 0.6820 | 0.6890 | 0.9513 |
| 0.0019 | 9.0 | 50049 | 0.0023 | 0.7005 | 0.6775 | 0.6888 | 0.9516 |
| 0.0018 | 10.0 | 55610 | 0.0023 | 0.6975 | 0.6822 | 0.6898 | 0.9515 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- Created
- Jun 25, 2022
- Updated
- Jun 25, 2022