Downloads · 30 days
2
4% of all-time downloads
finetuned-t5-for-samsum-summarization
prabhleenbindra-personal/finetuned-t5-for-samsum-summarization
finetuned-t5-for-samsum-summarization is a machine learning model from prabhleenbindra-personal. 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
45
Public
Parameters
60.5M
6.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors242 MB · 99%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Mar 16, 2025
- Updated
- Mar 18, 2025
- SHA
- a7dd08cd
Base models
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. -->
finetuned-t5-for-samsum-summarization
This model is a fine-tuned version of google-t5/t5-small on the samsum dataset. It achieves the following results on the evaluation set:
- Loss: 1.7032
- Rouge1: 0.4349
- Rouge2: 0.2083
- Rougel: 0.3675
- Rougelsum: 0.368
- Gen Len: 17.2885
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.2134 | 1.0 | 921 | 1.8395 | 0.4067 | 0.1789 | 0.3387 | 0.3392 | 16.9731 |
| 1.9967 | 2.0 | 1842 | 1.7883 | 0.4111 | 0.1859 | 0.3447 | 0.3451 | 16.9939 |
| 1.9323 | 3.0 | 2763 | 1.7518 | 0.4228 | 0.1912 | 0.3547 | 0.3549 | 17.2164 |
| 1.8926 | 4.0 | 3684 | 1.7444 | 0.425 | 0.1989 | 0.3576 | 0.3578 | 17.3166 |
| 1.8661 | 5.0 | 4605 | 1.7257 | 0.4266 | 0.1992 | 0.3607 | 0.361 | 17.0795 |
| 1.839 | 6.0 | 5526 | 1.7169 | 0.4318 | 0.2017 | 0.3614 | 0.3616 | 17.4132 |
| 1.8294 | 7.0 | 6447 | 1.7098 | 0.4317 | 0.2061 | 0.3662 | 0.3666 | 17.2848 |
| 1.8135 | 8.0 | 7368 | 1.7058 | 0.4329 | 0.2068 | 0.3657 | 0.3659 | 17.2812 |
| 1.8111 | 9.0 | 8289 | 1.7040 | 0.4324 | 0.2074 | 0.3666 | 0.3669 | 17.2213 |
| 1.8057 | 10.0 | 9210 | 1.7032 | 0.4349 | 0.2083 | 0.3675 | 0.368 | 17.2885 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Created
- Mar 16, 2025
- Updated
- Mar 18, 2025