Downloads · 30 days
8
5% of all-time downloads
annoctr_bert_uncased
priamai/annoctr_bert_uncased
annoctr_bert_uncased is a token classification model from priamai. 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
155
Public
Parameters
109M
436 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors436 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Jul 2, 2024
- Updated
- Jul 2, 2024
- SHA
- 62c0ae34
Try a prompt
Base models
Datasets
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. -->
annoctr_bert_uncased
This model is a fine-tuned version of bert-base-uncased on the anno_ctr dataset. It achieves the following results on the evaluation set:
- Loss: 0.3322
- Precision: 0.7928
- Recall: 0.7810
- F1: 0.7869
- Accuracy: 0.9365
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: 1e-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 |
|---|---|---|---|---|---|---|---|
| 0.54 | 1.0 | 474 | 0.3452 | 0.6983 | 0.6601 | 0.6786 | 0.9137 |
| 0.3013 | 2.0 | 948 | 0.3466 | 0.7774 | 0.7018 | 0.7376 | 0.9240 |
| 0.0392 | 3.0 | 1422 | 0.3071 | 0.7851 | 0.7517 | 0.7680 | 0.9303 |
| 0.5695 | 4.0 | 1896 | 0.2941 | 0.7810 | 0.7617 | 0.7712 | 0.9334 |
| 0.0021 | 5.0 | 2370 | 0.3109 | 0.7928 | 0.7720 | 0.7823 | 0.9351 |
| 0.0419 | 6.0 | 2844 | 0.3020 | 0.7772 | 0.7796 | 0.7784 | 0.9341 |
| 0.2979 | 7.0 | 3318 | 0.3169 | 0.8019 | 0.7814 | 0.7915 | 0.9374 |
| 0.0017 | 8.0 | 3792 | 0.3260 | 0.7972 | 0.7778 | 0.7874 | 0.9365 |
| 0.0166 | 9.0 | 4266 | 0.3349 | 0.7935 | 0.7789 | 0.7861 | 0.9364 |
| 0.0685 | 10.0 | 4740 | 0.3322 | 0.7928 | 0.7810 | 0.7869 | 0.9365 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Jul 2, 2024
- Updated
- Jul 2, 2024