distilbert_wnut_model
This model is a fine-tuned version of distilbert/distilbert-base-uncased on the wnut_17 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3052
- Precision: 0.5218
- Recall: 0.3874
- F1: 0.4447
- Accuracy: 0.9463
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 | 0.2801 | 0.5586 | 0.2428 | 0.3385 | 0.9384 |
| No log | 2.0 | 426 | 0.2573 | 0.5228 | 0.2975 | 0.3792 | 0.9425 |
| 0.1769 | 3.0 | 639 | 0.2859 | 0.5510 | 0.3253 | 0.4091 | 0.9450 |
| 0.1769 | 4.0 | 852 | 0.2965 | 0.5499 | 0.3522 | 0.4294 | 0.9462 |
| 0.0496 | 5.0 | 1065 | 0.2951 | 0.5123 | 0.3846 | 0.4394 | 0.9458 |
| 0.0496 | 6.0 | 1278 | 0.3052 | 0.5218 | 0.3874 | 0.4447 | 0.9463 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1