Downloads · 30 days
12
14% of all-time downloads
bart-base-xsum-rouge-3-loss-differentiable-10-cnt-supervised-sequential
taiypeo/bart-base-xsum-rouge-3-loss-differentiable-10-cnt-supervised-sequential
bart-base-xsum-rouge-3-loss-differentiable-10-cnt-supervised-sequential is a machine learning model from taiypeo. 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
84
Public
Parameters
139M
12.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors558 MB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- bart
- Access
- Public
- Created
- Dec 5, 2025
- Updated
- Dec 6, 2025
- SHA
- 80e00131
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. -->
bart-base-xsum-rouge-3-loss-differentiable-10-cnt-supervised-sequential
This model is a fine-tuned version of taiypeo/bart-base-xsum-sentence-paraphrased-10-cnt-supervised-basic on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3049
- Rouge1: 0.2431
- Rouge2: 0.0637
- Rougel: 0.1841
- Rougelsum: 0.1841
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 1.1137 | 0.0032 | 2 | 2.2976 | 0.2422 | 0.0629 | 0.1832 | 0.1832 |
| 1.2046 | 0.0064 | 4 | 2.2984 | 0.2426 | 0.0633 | 0.1836 | 0.1837 |
| 1.1645 | 0.0096 | 6 | 2.2999 | 0.2423 | 0.0632 | 0.1834 | 0.1834 |
| 1.1997 | 0.0128 | 8 | 2.3020 | 0.2425 | 0.0633 | 0.1836 | 0.1837 |
| 1.2864 | 0.0160 | 10 | 2.3049 | 0.2431 | 0.0637 | 0.1841 | 0.1841 |
| 1.1815 | 0.0192 | 12 | 2.3084 | 0.2429 | 0.0632 | 0.1836 | 0.1836 |
| 1.079 | 0.0224 | 14 | 2.3127 | 0.2428 | 0.0632 | 0.1835 | 0.1835 |
| 1.0862 | 0.0256 | 16 | 2.3179 | 0.2426 | 0.0625 | 0.1832 | 0.1831 |
| 1.0948 | 0.0288 | 18 | 2.3240 | 0.2415 | 0.0618 | 0.182 | 0.182 |
| 1.1651 | 0.0320 | 20 | 2.3314 | 0.2402 | 0.0609 | 0.1811 | 0.1809 |
| 1.0771 | 0.0352 | 22 | 2.3401 | 0.2406 | 0.0607 | 0.1817 | 0.1817 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.1+cu128
- Datasets 3.6.0
- Tokenizers 0.22.1
- Library
- transformers
- Type
- bart
- License
- apache-2.0
- Created
- Dec 5, 2025
- Updated
- Dec 6, 2025