Downloads · 30 days
4
3% of all-time downloads
rut5_base_sum_gazeta-finetuned-2
sadelja/rut5_base_sum_gazeta-finetuned-2
rut5_base_sum_gazeta-finetuned-2 is a machine learning model from sadelja. 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
131
Public
Parameters
244M
10.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors977 MB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Apr 26, 2025
- Updated
- May 11, 2025
- SHA
- a2dcafe6
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. -->
rut5_base_sum_gazeta-finetuned-2
This model is a fine-tuned version of IlyaGusev/rut5_base_sum_gazeta on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5344
- Rouge1: 13.4921
- Rouge2: 8.0952
- Rougel: 14.1723
- Rougelsum: 14.1723
- Gen Len: 174.0952
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.698 | 1.0 | 24 | 0.7425 | 7.9365 | 2.8571 | 7.9365 | 8.3333 | 172.619 |
| 0.5777 | 2.0 | 48 | 0.6144 | 13.4921 | 8.0952 | 14.1723 | 14.1723 | 185.1429 |
| 0.4761 | 3.0 | 72 | 0.5909 | 13.4921 | 8.0952 | 14.1723 | 14.1723 | 179.2381 |
| 0.4855 | 4.0 | 96 | 0.5673 | 13.4921 | 8.0952 | 14.1723 | 14.1723 | 178.6667 |
| 0.4216 | 5.0 | 120 | 0.5585 | 13.4921 | 8.0952 | 14.1723 | 14.1723 | 179.0476 |
| 0.4404 | 6.0 | 144 | 0.5504 | 13.4921 | 8.0952 | 14.1723 | 14.1723 | 174.0952 |
| 0.3968 | 7.0 | 168 | 0.5439 | 13.4921 | 8.0952 | 14.1723 | 14.1723 | 174.0952 |
| 0.393 | 8.0 | 192 | 0.5376 | 13.4921 | 8.0952 | 14.1723 | 14.1723 | 174.0952 |
| 0.3535 | 9.0 | 216 | 0.5343 | 13.4921 | 8.0952 | 14.1723 | 14.1723 | 174.0952 |
| 0.4052 | 10.0 | 240 | 0.5344 | 13.4921 | 8.0952 | 14.1723 | 14.1723 | 174.0952 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Created
- Apr 26, 2025
- Updated
- May 11, 2025