flan-t5-small-twitter-sentiment-analysis-zero-shot
This model is a fine-tuned version of google/flan-t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1810
- Accuracy: 0.8484
It achieves the following results on the test set:
- Loss: 0.1899
- Accuracy: 0.8423
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: 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: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.213 | 1.0 | 1875 | 0.1922 | 0.8268 |
| 0.1963 | 2.0 | 3750 | 0.1863 | 0.8374 |
| 0.188 | 3.0 | 5625 | 0.1817 | 0.8413 |
| 0.1835 | 4.0 | 7500 | 0.1795 | 0.8438 |
| 0.1754 | 5.0 | 9375 | 0.1786 | 0.8459 |
| 0.1715 | 6.0 | 11250 | 0.1806 | 0.8464 |
| 0.1692 | 7.0 | 13125 | 0.1799 | 0.8478 |
| 0.1646 | 8.0 | 15000 | 0.1810 | 0.8484 |
| 0.1664 | 9.0 | 16875 | 0.1810 | 0.8484 |
| 0.1622 | 10.0 | 18750 | 0.1803 | 0.8484 |
Framework versions
- Transformers 4.27.1
- Pytorch 2.0.1
- Datasets 2.9.0
- Tokenizers 0.13.3