bert-finetuned-ner-Colab
This model is a fine-tuned version of Babelscape/wikineural-multilingual-ner on the wnut_17 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3577
- Precision: 0.6570
- Recall: 0.4856
- F1: 0.5585
- Accuracy: 0.9340
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 | 0.3191 | 0.6465 | 0.4091 | 0.5011 | 0.9273 |
0.1595 | 2.0 | 850 | 0.3320 | 0.6719 | 0.4629 | 0.5482 | 0.9316 |
0.0681 | 3.0 | 1275 | 0.3577 | 0.6570 | 0.4856 | 0.5585 | 0.9340 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 4
Inference API (serverless) is not available, repository is disabled.
Model tree for TiffanyTiffany/bert-finetuned-ner-Colab
Base model
Babelscape/wikineural-multilingual-ner
Finetuned
this model
Dataset used to train TiffanyTiffany/bert-finetuned-ner-Colab
Evaluation results
- Precision on wnut_17validation set self-reported0.657
- Recall on wnut_17validation set self-reported0.486
- F1 on wnut_17validation set self-reported0.558
- Accuracy on wnut_17validation set self-reported0.934