distilbert-base-uncased-finetuned-squad-finetuned-thread
This model is a fine-tuned version of ashtrevi/distilbert-base-uncased-finetuned-squad on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4546
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-06
- 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.219 | 0.6 | 100 | 2.7337 |
| 3.3141 | 1.19 | 200 | 2.5648 |
| 3.1199 | 1.79 | 300 | 2.4972 |
| 3.1278 | 2.38 | 400 | 2.4569 |
| 2.9679 | 2.98 | 500 | 2.4546 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3