my_awesome_wnut_model
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: 0.2926
- Precision: 0.5485
- Recall: 0.3930
- F1: 0.4579
- Accuracy: 0.9461
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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 213 | 0.2744 | 0.6308 | 0.2660 | 0.3742 | 0.9396 |
No log | 2.0 | 426 | 0.2644 | 0.6006 | 0.3457 | 0.4388 | 0.9438 |
0.1817 | 3.0 | 639 | 0.2953 | 0.6426 | 0.3466 | 0.4503 | 0.9456 |
0.1817 | 4.0 | 852 | 0.3107 | 0.5796 | 0.3577 | 0.4424 | 0.9455 |
0.0532 | 5.0 | 1065 | 0.2926 | 0.5485 | 0.3930 | 0.4579 | 0.9461 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 7
Finetuned from
Dataset used to train Spleonard1/my_awesome_wnut_model
Evaluation results
- Precision on wnut_17test set self-reported0.549
- Recall on wnut_17test set self-reported0.393
- F1 on wnut_17test set self-reported0.458
- Accuracy on wnut_17test set self-reported0.946