Downloads · 30 days
15
3% of all-time downloads
t5-base-msmarco-squad-query-generation-longp-v2
jmvcoelho/t5-base-msmarco-squad-query-generation-longp-v2
t5-base-msmarco-squad-query-generation-longp-v2 is a machine learning model from jmvcoelho. 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 wtfpl.
t5-base-msmarco-squad-query-generation-longp-v2
All-time downloads
522
Public
Repo size
2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin990 MB · 100%
At a glance
- Library
- transformers
- License
- wtfpl
- Model type
- longt5
- Access
- Public
- Created
- Apr 5, 2023
- Updated
- Apr 5, 2023
- SHA
- bee38d15
Model card
From the Hugging Face model README
Model
t5-base-msmarco-squad-query-generation-longp-v2
Task: query generation Architecture: LongT5
Base model: google/long-t5-tglobal-base
Note: This is supposed to be a baseline model.
Prompt:
"Generate Query: {document}. Query:"
Sequence length:
1536 tokens
Training details
Hyperparameters
Batch size: 8;
Gradient acc: 8;
LR: 3e-4, linear scheduler, 400 warmup steps.
Data
Total: 252059 pairs (document, query)
From MARCO-V2: 165238 From SQuAD: 86821
The remaining queries from MARCO-V2 train split were not used.
Evaluation
This model is supposed to be used for data augmentation. Hence, meaningful evaluation will come from downstream tasks.
MARCO-V2 Dev1: BLEU: 0.102 ROUGE: 0.447
MARCO-V2 Dev2: BLEU: 0.1691 ROUGE: 0.5013
- Library
- transformers
- Type
- longt5
- License
- wtfpl
- Languages
- en
- Created
- Apr 5, 2023
- Updated
- Apr 5, 2023