bert-small-finetuned-ner-to-multilabel-wnut-17
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: 0.2186
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1987 | 1.18 | 500 | 0.2114 |
| 0.1235 | 2.35 | 1000 | 0.1894 |
| 0.0924 | 3.53 | 1500 | 0.1890 |
| 0.0735 | 4.71 | 2000 | 0.1958 |
| 0.0534 | 5.88 | 2500 | 0.1993 |
| 0.0401 | 7.06 | 3000 | 0.2186 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1