Downloads · 30 days
15
29% of all-time downloads
vit5-base-sum-v2
pmhau/vit5-base-sum-v2
vit5-base-sum-v2 is a machine learning model from pmhau. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
52
Public
Parameters
226M
13.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.8 GB · 100%
At a glance
- License
- mit
- Model type
- t5
- Access
- Public
- Created
- Apr 29, 2026
- Updated
- Apr 29, 2026
- SHA
- 0955f02d
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. -->
vit5-base-sum-v2
This model is a fine-tuned version of VietAI/vit5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2966
- Rouge1: 0.2753
- Rouge2: 0.1857
- Rougel: 0.2404
- Rougelsum: 0.2405
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: 3e-05
- train_batch_size: 128
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 1.6768 | 1.0 | 383 | 1.4861 | 0.275 | 0.1809 | 0.2387 | 0.2387 |
| 1.5386 | 2.0 | 766 | 1.4077 | 0.2761 | 0.1836 | 0.2402 | 0.2402 |
| 1.4621 | 3.0 | 1149 | 1.3745 | 0.2756 | 0.1841 | 0.24 | 0.24 |
| 1.4093 | 4.0 | 1532 | 1.3557 | 0.2759 | 0.1847 | 0.2404 | 0.2404 |
| 1.3664 | 5.0 | 1915 | 1.3314 | 0.2752 | 0.1853 | 0.2404 | 0.2404 |
| 1.32 | 6.0 | 2298 | 1.3238 | 0.2741 | 0.1844 | 0.24 | 0.24 |
| 1.2963 | 7.0 | 2681 | 1.3134 | 0.2753 | 0.1861 | 0.2413 | 0.2413 |
| 1.2629 | 8.0 | 3064 | 1.3038 | 0.2753 | 0.1858 | 0.2409 | 0.2409 |
| 1.2327 | 9.0 | 3447 | 1.3003 | 0.274 | 0.1849 | 0.2398 | 0.2398 |
| 1.2225 | 10.0 | 3830 | 1.3029 | 0.2749 | 0.1858 | 0.2403 | 0.2403 |
| 1.2041 | 11.0 | 4213 | 1.2974 | 0.2752 | 0.1859 | 0.2407 | 0.2407 |
| 1.187 | 12.0 | 4596 | 1.2929 | 0.2758 | 0.1865 | 0.2411 | 0.2411 |
| 1.1743 | 13.0 | 4979 | 1.2949 | 0.2751 | 0.1861 | 0.2406 | 0.2406 |
| 1.15 | 14.0 | 5362 | 1.2941 | 0.2745 | 0.1853 | 0.24 | 0.2401 |
| 1.1382 | 15.0 | 5745 | 1.2966 | 0.2753 | 0.1857 | 0.2404 | 0.2405 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.8.0+cu129
- Datasets 4.8.5
- Tokenizers 0.15.2
- Type
- t5
- License
- mit
- Created
- Apr 29, 2026
- Updated
- Apr 29, 2026