distilbert-base-uncased-finetuned-hateful-meme
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8740
- Accuracy: 0.542
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5786 | 1.0 | 532 | 0.7902 | 0.56 |
| 0.5077 | 2.0 | 1064 | 0.8275 | 0.566 |
| 0.4534 | 3.0 | 1596 | 0.9469 | 0.544 |
| 0.3998 | 4.0 | 2128 | 1.1139 | 0.538 |
| 0.3527 | 5.0 | 2660 | 1.2128 | 0.542 |
| 0.3219 | 6.0 | 3192 | 1.2232 | 0.546 |
| 0.3051 | 7.0 | 3724 | 1.5492 | 0.538 |
| 0.2789 | 8.0 | 4256 | 1.6341 | 0.542 |
| 0.267 | 9.0 | 4788 | 1.7046 | 0.54 |
| 0.2521 | 10.0 | 5320 | 1.8740 | 0.542 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.3
- Tokenizers 0.13.3