metadata
license: mit
base_model: facebook/bart-large-cnn
tags:
- generated_from_trainer
datasets:
- samsum
model-index:
- name: bart-large-cnn-samsum
results: []
bart-large-cnn-samsum
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: 1.3710
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3477 | 0.8686 | 400 | 1.3732 |
| 1.1696 | 1.7372 | 800 | 1.3704 |
| 1.136 | 2.6059 | 1200 | 1.3714 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1