Downloads · 30 days
3
1% of all-time downloads
distilbert-base-uncased-distilled-squad
arinakosovskaia/distilbert-base-uncased-distilled-squad
distilbert-base-uncased-distilled-squad is a question answering model from arinakosovskaia. Use it when the input is a question plus a passage. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
321
Public
Repo size
1.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin265 MB · 100%
At a glance
- Task
- Question Answering
- Library
- transformers
- Model type
- distilbert
- Access
- Public
- Created
- May 24, 2023
- Updated
- May 25, 2023
- SHA
- 787b416d
Try a prompt
Model card
From the Hugging Face model README
<!-- 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-distilled-squad
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0808
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.99 | 138 | 0.0777 |
| No log | 2.0 | 277 | 0.0624 |
| No log | 3.0 | 416 | 0.0641 |
| 0.0022 | 3.98 | 552 | 0.0808 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Question Answering
- Library
- transformers
- Type
- distilbert
- Created
- May 24, 2023
- Updated
- May 25, 2023