Downloads · 30 days
7
1% of all-time downloads
flan-t5-base-quora-question-answer
toughdata/flan-t5-base-quora-question-answer
flan-t5-base-quora-question-answer is a machine learning model from toughdata. Use it for the machine learning task on the model card, and read the license before you ship it in a product. 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
874
Public
Repo size
2 GB
Likes
3
Public
Repo makeup
Click a slice to open those files.
.bin990 MB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Aug 23, 2023
- Updated
- Aug 23, 2023
- SHA
- 99e8c355
Base models
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. -->
results
This model is a fine-tuned version of google/flan-t5-base on question/answer pairs scraped from Quora. It achieves the following results on the evaluation set:
- Loss: 2.9379
Intended uses & limitations
Closed book question answering. Prefix the inputs with "answer the question: "
Training and evaluation data
50,000 question/answer pairs scraped from Quora
Training procedure
Seq2Seq training described here: https://huggingface.co/docs/evaluate/transformers_integrations
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.158 | 1.0 | 5641 | 2.9785 |
| 3.0283 | 2.0 | 11282 | 2.9379 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.0
- Datasets 2.14.4
- Tokenizers 0.13.3
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Created
- Aug 23, 2023
- Updated
- Aug 23, 2023