bert_wnut_model
This model is a fine-tuned version of bert-base-cased on the wnut_17 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3346
- Precision: 0.5291
- Recall: 0.3791
- F1: 0.4417
- Accuracy: 0.9477
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 213 | 0.2607 | 0.5443 | 0.2901 | 0.3785 | 0.9411 |
| No log | 2.0 | 426 | 0.2689 | 0.5474 | 0.3318 | 0.4132 | 0.9453 |
| 0.1554 | 3.0 | 639 | 0.2896 | 0.5253 | 0.3753 | 0.4378 | 0.9475 |
| 0.1554 | 4.0 | 852 | 0.3009 | 0.5079 | 0.3865 | 0.4389 | 0.9474 |
| 0.0349 | 5.0 | 1065 | 0.3195 | 0.5109 | 0.3920 | 0.4436 | 0.9486 |
| 0.0349 | 6.0 | 1278 | 0.3346 | 0.5291 | 0.3791 | 0.4417 | 0.9477 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1