camembert-ner-finetuned-ner
This model is a fine-tuned version of Jean-Baptiste/camembert-ner on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1258
- Precision: 0.9791
- Recall: 0.9723
- F1: 0.9757
- Accuracy: 0.9775
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: 16
- 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 | 219 | 0.1130 | 0.9569 | 0.9723 | 0.9645 | 0.9687 |
No log | 2.0 | 438 | 0.1681 | 0.9528 | 0.9769 | 0.9647 | 0.9646 |
0.1656 | 3.0 | 657 | 0.1253 | 0.9693 | 0.9827 | 0.9759 | 0.9779 |
0.1656 | 4.0 | 876 | 0.1230 | 0.9692 | 0.9804 | 0.9748 | 0.9783 |
0.047 | 5.0 | 1095 | 0.1258 | 0.9791 | 0.9723 | 0.9757 | 0.9775 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1
- Downloads last month
- 14
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.