<!-- 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. -->
distilbert-base-uncased-finetuned-ner
This model is a fine-tuned version of distilbert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0603
- Precision: 0.9272
- Recall: 0.9369
- F1: 0.9320
- Accuracy: 0.9837
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 |
---|---|---|---|---|---|---|---|
0.2437 | 1.0 | 878 | 0.0672 | 0.9145 | 0.9203 | 0.9174 | 0.9813 |
0.053 | 2.0 | 1756 | 0.0597 | 0.9229 | 0.9350 | 0.9289 | 0.9832 |
0.0301 | 3.0 | 2634 | 0.0603 | 0.9272 | 0.9369 | 0.9320 | 0.9837 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2