<!-- 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. -->
my_awesome_qa_model
This model is a fine-tuned version of distilbert-base-uncased on the squad dataset. It achieves the following results on the evaluation set:
- Loss: 2.6520
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 125 | 2.5873 |
| No log | 2.0 | 250 | 1.8849 |
| No log | 3.0 | 375 | 1.6759 |
| 1.9255 | 4.0 | 500 | 1.7135 |
| 1.9255 | 5.0 | 625 | 1.7905 |
| 1.9255 | 6.0 | 750 | 1.8424 |
| 1.9255 | 7.0 | 875 | 1.9328 |
| 0.5585 | 8.0 | 1000 | 2.0979 |
| 0.5585 | 9.0 | 1125 | 2.1077 |
| 0.5585 | 10.0 | 1250 | 2.1653 |
| 0.5585 | 11.0 | 1375 | 2.2949 |
| 0.2515 | 12.0 | 1500 | 2.3491 |
| 0.2515 | 13.0 | 1625 | 2.4130 |
| 0.2515 | 14.0 | 1750 | 2.4336 |
| 0.2515 | 15.0 | 1875 | 2.5714 |
| 0.1483 | 16.0 | 2000 | 2.5859 |
| 0.1483 | 17.0 | 2125 | 2.6265 |
| 0.1483 | 18.0 | 2250 | 2.6220 |
| 0.1483 | 19.0 | 2375 | 2.6299 |
| 0.1013 | 20.0 | 2500 | 2.6520 |
Framework versions
- Transformers 4.27.2
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
