bert-small-finetuned-wnut17-ner-longer6
This model is a fine-tuned version of muhtasham/bert-small-finetuned-wnut17-ner on the wnut_17 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4037
- Precision: 0.5667
- Recall: 0.4270
- F1: 0.4870
- Accuracy: 0.9268
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: 8
- eval_batch_size: 8
- 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 |
---|---|---|---|---|---|---|---|
No log | 1.0 | 425 | 0.3744 | 0.5626 | 0.4139 | 0.4769 | 0.9248 |
0.085 | 2.0 | 850 | 0.3914 | 0.5814 | 0.4270 | 0.4924 | 0.9271 |
0.0652 | 3.0 | 1275 | 0.4037 | 0.5667 | 0.4270 | 0.4870 | 0.9268 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
- Downloads last month
- 10
Dataset used to train muhtasham/bert-small-finetuned-wnut17-ner-longer6
Evaluation results
- Precision on wnut_17self-reported0.567
- Recall on wnut_17self-reported0.427
- F1 on wnut_17self-reported0.487
- Accuracy on wnut_17self-reported0.927