<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilbert-base-uncased-qa
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: 3.4871
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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 66 | 3.2096 |
| No log | 2.0 | 132 | 2.8592 |
| No log | 3.0 | 198 | 2.8928 |
| No log | 4.0 | 264 | 2.6908 |
| No log | 5.0 | 330 | 2.5923 |
| No log | 6.0 | 396 | 2.7418 |
| No log | 7.0 | 462 | 2.9204 |
| 2.1971 | 8.0 | 528 | 3.0142 |
| 2.1971 | 9.0 | 594 | 3.1064 |
| 2.1971 | 10.0 | 660 | 3.2017 |
| 2.1971 | 11.0 | 726 | 3.4628 |
| 2.1971 | 12.0 | 792 | 3.3789 |
| 2.1971 | 13.0 | 858 | 3.3585 |
| 2.1971 | 14.0 | 924 | 3.4515 |
| 2.1971 | 15.0 | 990 | 3.4871 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
