QA_distell
This model is a fine-tuned version of StaAhmed/my_awesome_qa_model on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2595
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: 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: 12
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 14 | 0.8443 |
| No log | 2.0 | 28 | 0.6154 |
| No log | 3.0 | 42 | 0.4697 |
| No log | 4.0 | 56 | 0.3838 |
| No log | 5.0 | 70 | 0.3297 |
| No log | 6.0 | 84 | 0.3364 |
| No log | 7.0 | 98 | 0.2711 |
| No log | 8.0 | 112 | 0.3240 |
| No log | 9.0 | 126 | 0.2634 |
| No log | 10.0 | 140 | 0.2826 |
| No log | 11.0 | 154 | 0.2721 |
| No log | 12.0 | 168 | 0.2595 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2