metadata
library_name: transformers
license: mit
base_model: facebook/bart-large-cnn
tags:
- generated_from_trainer
datasets:
- samsum
model-index:
- name: PEFT_expo
results: []
PEFT_expo
This model is a fine-tuned version of facebook/bart-large-cnn on the samsum dataset. It achieves the following results on the evaluation set:
- Loss: 0.2656
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8694 | 1.0 | 19 | 0.2720 |
| 0.1839 | 2.0 | 38 | 0.2656 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1