<!-- 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-finetuned-ner
This model is a fine-tuned version of distilbert-base-uncased on the wnut_17 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2716
- Precision: 0.5441
- Recall: 0.3716
- F1: 0.4416
- Accuracy: 0.9455
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: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 213 | 0.2780 | 0.6 | 0.2502 | 0.3532 | 0.9384 |
No log | 2.0 | 426 | 0.2514 | 0.5389 | 0.3531 | 0.4267 | 0.9431 |
0.191 | 3.0 | 639 | 0.2576 | 0.5453 | 0.3735 | 0.4433 | 0.9454 |
0.191 | 4.0 | 852 | 0.2716 | 0.5441 | 0.3716 | 0.4416 | 0.9455 |
Framework versions
- Transformers 4.34.1
- Pytorch 1.13.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1