bert-small-finetuned-ner-to-multilabel-wnut-17-new
This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2039
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: 3e-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: constant
- num_epochs: 40
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2006 | 1.18 | 500 | 0.2043 |
| 0.1247 | 2.35 | 1000 | 0.1960 |
| 0.0935 | 3.53 | 1500 | 0.1893 |
| 0.0742 | 4.71 | 2000 | 0.2003 |
| 0.0552 | 5.88 | 2500 | 0.2106 |
| 0.0405 | 7.06 | 3000 | 0.2039 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1