distilBert
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: 0.2800
- Precision: 0.5530
- Recall: 0.3818
- F1: 0.4518
- Accuracy: 0.9462
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 107 | 0.2886 | 0.5599 | 0.3077 | 0.3971 | 0.9439 |
No log | 2.0 | 214 | 0.2800 | 0.5530 | 0.3818 | 0.4518 | 0.9462 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.1
- Downloads last month
- 0
Finetuned from
Dataset used to train codeSlang/distilBert
Evaluation results
- Precision on wnut_17test set self-reported0.553
- Recall on wnut_17test set self-reported0.382
- F1 on wnut_17test set self-reported0.452
- Accuracy on wnut_17test set self-reported0.946