Downloads · 30 days
5
2% of all-time downloads
pegasus-samsum
math-hiyoko/pegasus-samsum
pegasus-samsum is a machine learning model from math-hiyoko. 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.
should probably proofread and complete it, then remove this comment. --
All-time downloads
328
Public
Parameters
768M
46.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 100%
At a glance
- Library
- transformers
- Model type
- pegasus
- Access
- Public
- Created
- Mar 3, 2026
- Updated
- Mar 5, 2026
- SHA
- 36d7577e
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. -->
pegasus-samsum
This model is a fine-tuned version of google/pegasus-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.3808
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.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_steps: 0.03
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 10.1416 | 0.0543 | 50 | 9.0038 |
| 7.2975 | 0.1086 | 100 | 6.9577 |
| 6.6494 | 0.1629 | 150 | 6.4694 |
| 6.3485 | 0.2172 | 200 | 6.0914 |
| 6.2067 | 0.2714 | 250 | 5.9083 |
| 6.0546 | 0.3257 | 300 | 5.7273 |
| 5.7634 | 0.3800 | 350 | 5.5655 |
| 5.6814 | 0.4343 | 400 | 5.4076 |
| 5.5820 | 0.4886 | 450 | 5.2923 |
| 5.5560 | 0.5429 | 500 | 5.1935 |
| 5.4320 | 0.5972 | 550 | 5.1080 |
| 5.2887 | 0.6515 | 600 | 5.0736 |
| 5.2464 | 0.7058 | 650 | 4.9919 |
| 5.2768 | 0.7600 | 700 | 4.9644 |
| 5.1517 | 0.8143 | 750 | 4.9259 |
| 5.0148 | 0.8686 | 800 | 4.8774 |
| 5.1010 | 0.9229 | 850 | 4.8530 |
| 5.1226 | 0.9772 | 900 | 4.8073 |
| 4.9871 | 1.0315 | 950 | 4.7904 |
| 4.8798 | 1.0858 | 1000 | 4.7541 |
| 4.9009 | 1.1401 | 1050 | 4.7370 |
| 4.8557 | 1.1944 | 1100 | 4.7059 |
| 4.9027 | 1.2486 | 1150 | 4.7020 |
| 4.7607 | 1.3029 | 1200 | 4.6803 |
| 4.7571 | 1.3572 | 1250 | 4.6586 |
| 4.7108 | 1.4115 | 1300 | 4.6308 |
| 4.7526 | 1.4658 | 1350 | 4.6088 |
| 4.8717 | 1.5201 | 1400 | 4.6057 |
| 4.7538 | 1.5744 | 1450 | 4.5733 |
| 4.7194 | 1.6287 | 1500 | 4.5682 |
| 4.7925 | 1.6830 | 1550 | 4.5835 |
| 4.6265 | 1.7372 | 1600 | 4.5304 |
| 4.6995 | 1.7915 | 1650 | 4.5141 |
| 4.6283 | 1.8458 | 1700 | 4.5023 |
| 4.6318 | 1.9001 | 1750 | 4.5037 |
| 4.6695 | 1.9544 | 1800 | 4.4839 |
| 4.5459 | 2.0087 | 1850 | 4.4732 |
| 4.5429 | 2.0630 | 1900 | 4.4729 |
| 4.6058 | 2.1173 | 1950 | 4.4593 |
| 4.5019 | 2.1716 | 2000 | 4.4685 |
| 4.4840 | 2.2258 | 2050 | 4.4491 |
| 4.3926 | 2.2801 | 2100 | 4.4450 |
| 4.4211 | 2.3344 | 2150 | 4.4310 |
| 4.5584 | 2.3887 | 2200 | 4.4319 |
| 4.5634 | 2.4430 | 2250 | 4.4124 |
| 4.4529 | 2.4973 | 2300 | 4.4226 |
| 4.5400 | 2.5516 | 2350 | 4.4082 |
| 4.4832 | 2.6059 | 2400 | 4.4071 |
| 4.5666 | 2.6602 | 2450 | 4.3956 |
| 4.6406 | 2.7144 | 2500 | 4.3879 |
| 4.4164 | 2.7687 | 2550 | 4.3936 |
| 4.4306 | 2.8230 | 2600 | 4.3943 |
| 4.4838 | 2.8773 | 2650 | 4.3845 |
| 4.5805 | 2.9316 | 2700 | 4.3815 |
| 4.4251 | 2.9859 | 2750 | 4.3808 |
Framework versions
- Transformers 5.3.0
- Pytorch 2.10.0+cu128
- Datasets 3.6.0
- Tokenizers 0.22.2
- Library
- transformers
- Type
- pegasus
- Created
- Mar 3, 2026
- Updated
- Mar 5, 2026