Downloads · 30 days
4
10% of all-time downloads
flan-t5-base-qg-SQuAD-10-v2
tarek23/flan-t5-base-qg-SQuAD-10-v2
flan-t5-base-qg-SQuAD-10-v2 is a machine learning model from tarek23. 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
40
Public
Repo size
5.9 GB
Likes
0
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
- May 15, 2023
- Updated
- May 16, 2023
- SHA
- 5afd43d6
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. -->
flan-t5-base-qg-SQuAD-10-v2
This model is a fine-tuned version of sidovic/flan-t5-base-qg-SQuAD-10-v1 on the squad dataset. It achieves the following results on the evaluation set:
- Loss: 0.5635
- Rouge1: 52.7009
- Rouge2: 29.9946
- Rougel: 48.7201
- Rougelsum: 48.742
- Meteor: 47.7317
- Bleu-n: 21.2828
- Bleu-1: 52.9594
- Bleu-2: 26.9966
- Bleu-3: 17.2878
- Bleu-4: 11.6186
- Gen Len: 14.2839
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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 | Rouge1 | Rouge2 | Rougel | Rougelsum | Meteor | Bleu-n | Bleu-1 | Bleu-2 | Bleu-3 | Bleu-4 | Gen Len |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.4895 | 1.0 | 2737 | 0.5663 | 52.7114 | 30.0127 | 48.7037 | 48.7107 | 47.6616 | 21.2211 | 53.1390 | 27.0972 | 17.3604 | 11.6424 | 14.2666 |
| 0.4729 | 2.0 | 5475 | 0.5682 | 52.9216 | 30.0708 | 48.8526 | 48.878 | 47.8314 | 21.3161 | 53.2131 | 27.1690 | 17.3900 | 11.6710 | 14.2888 |
| 0.4683 | 3.0 | 8212 | 0.5692 | 52.7708 | 29.9539 | 48.737 | 48.7502 | 47.7233 | 21.2898 | 53.1600 | 27.1172 | 17.4031 | 11.6509 | 14.2627 |
| 0.4678 | 4.0 | 10950 | 0.5664 | 52.6176 | 29.8744 | 48.6503 | 48.6646 | 47.6344 | 21.2149 | 53.0211 | 26.9944 | 17.2824 | 11.6094 | 14.2477 |
| 0.4777 | 5.0 | 13685 | 0.5635 | 52.7009 | 29.9946 | 48.7201 | 48.742 | 47.7317 | 21.2828 | 52.9594 | 26.9966 | 17.2878 | 11.6186 | 14.2839 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Created
- May 15, 2023
- Updated
- May 16, 2023