flan-t5-xl-twitter-sentiment-analysis-lora
This model is a fine-tuned version of google/flan-t5-xl on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1619
- Accuracy: 0.8859
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: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|
| 0.1546 | 1.0 | 14999 | 0.1402 | 0.8833 |
| 0.1539 | 2.0 | 29998 | 0.1364 | 0.8872 |
| 0.1393 | 3.0 | 44997 | 0.1374 | 0.8886 |
| 0.1392 | 4.0 | 59996 | 0.1396 | 0.8874 |
| 0.1299 | 5.0 | 74995 | 0.1437 | 0.8897 |
| 0.1315 | 6.0 | 89994 | 0.1476 | 0.8874 |
| 0.1287 | 7.0 | 104993 | 0.1499 | 0.8897 |
| 0.1188 | 8.0 | 119992 | 0.1525 | 0.8884 |
| 0.1172 | 9.0 | 134991 | 0.1523 | 0.8900 |
| 0.1131 | 10.0 | 149990 | 0.1554 | 0.8906 |
Framework versions
- Transformers 4.27.1
- Pytorch 2.0.1
- Datasets 2.9.0
- Tokenizers 0.13.3