Downloads · 30 days
8
1% of all-time downloads
bert-swe-skills-ner
RJuro/bert-swe-skills-ner
bert-swe-skills-ner is a token classification model from RJuro. Use it when you need labels on individual words, such as names. It is set up for transformers.
All-time downloads
650
Public
Repo size
4.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin496 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Mar 30, 2023
- Updated
- Apr 21, 2023
- SHA
- 373d5ce6
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. -->
bert-swe-skills-ner
This model is a fine-tuned version of RJuro/bert-swe-skills-ner on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0486
- Precision: 0.8194
- Recall: 0.8710
- F1: 0.8444
- Accuracy: 0.9856
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 39 | 0.1509 | 0.5872 | 0.6636 | 0.6231 | 0.9492 |
| No log | 2.0 | 78 | 0.1069 | 0.6750 | 0.7544 | 0.7125 | 0.9660 |
| No log | 3.0 | 117 | 0.0688 | 0.7692 | 0.8050 | 0.7867 | 0.9785 |
| No log | 4.0 | 156 | 0.0529 | 0.8239 | 0.8452 | 0.8344 | 0.9842 |
| No log | 5.0 | 195 | 0.0486 | 0.8194 | 0.8710 | 0.8444 | 0.9856 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- Created
- Mar 30, 2023
- Updated
- Apr 21, 2023