Downloads · 30 days
7
16% of all-time downloads
pegasus-samsum-2
aplnestrella/pegasus-samsum-2
pegasus-samsum-2 is a machine learning model from aplnestrella. 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
45
Public
Repo size
4.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin2.3 GB · 100%
At a glance
- Library
- transformers
- Model type
- pegasus
- Access
- Public
- Created
- Jan 6, 2023
- Updated
- Jan 6, 2023
- SHA
- dd1ff0cb
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. -->
pegasus-samsum-2
This model is a fine-tuned version of google/pegasus-cnn_dailymail on the samsum dataset. It achieves the following results on the evaluation set:
- Loss: 1.3928
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: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8437 | 0.14 | 500 | 1.5538 |
| 1.6136 | 0.27 | 1000 | 1.4801 |
| 1.5287 | 0.41 | 1500 | 1.4405 |
| 1.6311 | 0.54 | 2000 | 1.4238 |
| 1.6707 | 0.68 | 2500 | 1.4052 |
| 1.7293 | 0.81 | 3000 | 1.3998 |
| 1.5427 | 0.95 | 3500 | 1.3928 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
- Library
- transformers
- Type
- pegasus
- Created
- Jan 6, 2023
- Updated
- Jan 6, 2023