faq_qa_model
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: 3.5354
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 6 | 4.9320 |
| No log | 2.0 | 12 | 3.9422 |
| No log | 3.0 | 18 | 3.2712 |
| No log | 4.0 | 24 | 3.0726 |
| No log | 5.0 | 30 | 2.9938 |
| No log | 6.0 | 36 | 3.1028 |
| No log | 7.0 | 42 | 2.8811 |
| No log | 8.0 | 48 | 3.2465 |
| No log | 9.0 | 54 | 3.3097 |
| No log | 10.0 | 60 | 3.2337 |
| No log | 11.0 | 66 | 3.3950 |
| No log | 12.0 | 72 | 3.3698 |
| No log | 13.0 | 78 | 3.3528 |
| No log | 14.0 | 84 | 3.4233 |
| No log | 15.0 | 90 | 3.4698 |
| No log | 16.0 | 96 | 3.4321 |
| No log | 17.0 | 102 | 3.4550 |
| No log | 18.0 | 108 | 3.5227 |
| No log | 19.0 | 114 | 3.5257 |
| No log | 20.0 | 120 | 3.5354 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 2