distilbert-base-uncased-finetuned-ner
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0614
- Precision: 0.9288
- Recall: 0.9388
- F1: 0.9338
- Accuracy: 0.9840
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: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.2456 | 1.0 | 878 | 0.0683 | 0.9151 | 0.9223 | 0.9187 | 0.9814 |
0.0542 | 2.0 | 1756 | 0.0609 | 0.9227 | 0.9335 | 0.9281 | 0.9829 |
0.0293 | 3.0 | 2634 | 0.0614 | 0.9288 | 0.9388 | 0.9338 | 0.9840 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.0+cu113
- Tokenizers 0.12.1
- Downloads last month
- 28
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.