Downloads · 30 days
3
5% of all-time downloads
eecs487-squad-trained
nkhess/eecs487-squad-trained
eecs487-squad-trained is a question answering model from nkhess. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
55
Public
Parameters
66.4M
27.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors265 MB · 100%
At a glance
- Task
- Question Answering
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Dec 12, 2023
- Updated
- Dec 12, 2023
- SHA
- 8a7a9088
Try a prompt
Base models
Datasets
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. -->
eecs487-squad-trained
This model is a fine-tuned version of distilbert-base-uncased on the squad_v2 dataset. It achieves the following results on the evaluation set:
- Loss: 1.3826
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.22 | 1.0 | 8235 | 1.3225 |
| 0.9388 | 2.0 | 16470 | 1.2340 |
| 0.7479 | 3.0 | 24705 | 1.3826 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Task
- Question Answering
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Created
- Dec 12, 2023
- Updated
- Dec 12, 2023