Downloads · 30 days
6
12% of all-time downloads
bart_samsum
Mahesh9/bart_samsum
bart_samsum is a machine learning model from Mahesh9. 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 mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
49
Public
Parameters
406M
1.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.6 GB · 100%
At a glance
- Library
- transformers
- License
- mit
- Model type
- bart
- Access
- Public
- Created
- Feb 23, 2024
- Updated
- Feb 24, 2024
- SHA
- 3adc3860
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_samsum
This model is a fine-tuned version of facebook/bart-large-cnn on SAMSUM dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4966
- Rouge1: 41.4888
- Rouge2: 21.4374
- Rougel: 32.0455
- Rougelsum: 38.5273
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- 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 | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 0.525 | 0.54 | 500 | 0.5377 | 39.9053 | 20.1597 | 30.8845 | 37.3644 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.17.1
- Tokenizers 0.15.2
- Library
- transformers
- Type
- bart
- License
- mit
- Created
- Feb 23, 2024
- Updated
- Feb 24, 2024