Downloads · 30 days
12
29% of all-time downloads
flan-t5-base-SQuAD-qag-ep8
Zekunli/flan-t5-base-SQuAD-qag-ep8
flan-t5-base-SQuAD-qag-ep8 is a machine learning model from Zekunli. 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
42
Public
Repo size
9.9 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
- Jun 7, 2023
- Updated
- Jun 7, 2023
- SHA
- 3325bc20
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-SQuAD-qag-ep8
This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9551
- Rouge1: 39.487
- Rouge2: 18.1089
- Rougel: 36.0418
- Rougelsum: 36.0741
- F1: 19.5455
- Exact Match: 13.7397
- Gen Len: 18.4233
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: 72
- eval_batch_size: 144
- seed: 1799
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | F1 | Exact Match | Gen Len |
|---|---|---|---|---|---|---|---|---|---|---|
| 1.2252 | 0.76 | 200 | 0.9938 | 38.6398 | 17.1928 | 35.2146 | 35.1936 | 17.2662 | 11.9981 | 18.5075 |
| 1.107 | 1.52 | 400 | 0.9772 | 38.6809 | 17.2381 | 35.1093 | 35.1221 | 16.6281 | 11.8529 | 18.5128 |
| 1.0804 | 2.28 | 600 | 0.9676 | 38.3959 | 17.2286 | 34.9647 | 34.9807 | 17.5379 | 12.5786 | 18.4935 |
| 1.0658 | 3.04 | 800 | 0.9648 | 38.7751 | 17.4478 | 35.3216 | 35.3479 | 17.7663 | 12.627 | 18.4785 |
| 1.0548 | 3.8 | 1000 | 0.9605 | 39.2758 | 17.9529 | 35.8118 | 35.8389 | 18.2213 | 13.014 | 18.4577 |
| 1.0334 | 4.56 | 1200 | 0.9593 | 39.3076 | 17.9033 | 35.7966 | 35.8114 | 18.4676 | 13.014 | 18.4509 |
| 1.0374 | 5.32 | 1400 | 0.9571 | 39.247 | 17.9242 | 35.7772 | 35.8175 | 18.8109 | 13.1108 | 18.4335 |
| 1.0234 | 6.08 | 1600 | 0.9570 | 39.107 | 17.8715 | 35.7158 | 35.7526 | 19.1988 | 13.5946 | 18.4277 |
| 1.0171 | 6.84 | 1800 | 0.9556 | 39.3609 | 18.0643 | 35.9274 | 35.9571 | 19.2928 | 13.643 | 18.4257 |
| 1.0188 | 7.6 | 2000 | 0.9551 | 39.487 | 18.1089 | 36.0418 | 36.0741 | 19.5455 | 13.7397 | 18.4233 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Created
- Jun 7, 2023
- Updated
- Jun 7, 2023