<!-- 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-finetuned-hotpot_qa
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2565
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1396 | 1.0 | 2572 | 1.0405 |
| 0.8396 | 2.0 | 5144 | 0.9299 |
| 0.6253 | 3.0 | 7716 | 1.0625 |
| 0.4584 | 4.0 | 10288 | 1.1290 |
| 0.3432 | 5.0 | 12860 | 1.2565 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1
