smalldata-microsoft-deberta-base-eng-only-sentiment-single-finetuned-memes
This model is a fine-tuned version of jayantapaul888/twitter-data-microsoft-deberta-base-mnli-sentiment-finetuned-memes on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9308
- Accuracy: 0.8429
- Precision: 0.8588
- Recall: 0.8579
- F1: 0.8583
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: 5e-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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 378 | 0.3307 | 0.8407 | 0.8682 | 0.8549 | 0.8541 |
| 0.353 | 2.0 | 756 | 0.3677 | 0.8518 | 0.8669 | 0.8656 | 0.8662 |
| 0.1726 | 3.0 | 1134 | 0.5219 | 0.8392 | 0.8570 | 0.8549 | 0.8548 |
| 0.0681 | 4.0 | 1512 | 0.7194 | 0.8414 | 0.8578 | 0.8566 | 0.8572 |
| 0.0681 | 5.0 | 1890 | 0.8617 | 0.8407 | 0.8573 | 0.8560 | 0.8565 |
| 0.0233 | 6.0 | 2268 | 0.9308 | 0.8429 | 0.8588 | 0.8579 | 0.8583 |
Framework versions
- Transformers 4.24.0.dev0
- Pytorch 1.11.0+cu102
- Datasets 2.6.1
- Tokenizers 0.13.1