benchmark-finetuned-distilbert
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4592
- Accuracy: 0.8228
- F1: 0.8214
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: 64
- eval_batch_size: 64
- 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 | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.8561 | 1.0 | 48 | 0.6834 | 0.7288 | 0.7016 |
| 0.5498 | 2.0 | 96 | 0.4948 | 0.8042 | 0.8036 |
| 0.4184 | 3.0 | 144 | 0.4592 | 0.8228 | 0.8214 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1