metadata
license: mit
base_model: facebook/bart-large-xsum
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart_samsum
results: []
bart_samsum
This model is a fine-tuned version of facebook/bart-large-xsum on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4704
- Rouge1: 54.8232
- Rouge2: 30.1114
- Rougel: 45.2666
- Rougelsum: 50.7533
- Gen Len: 30.3399
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.3807 | 0.9997 | 1841 | 1.5203 | 52.4158 | 27.5034 | 42.8274 | 48.0361 | 31.4664 |
| 1.077 | 2.0 | 3683 | 1.5038 | 53.5277 | 28.5946 | 44.2315 | 49.5696 | 30.768 |
| 0.831 | 2.9997 | 5524 | 1.5362 | 52.9008 | 27.7041 | 43.5637 | 48.3921 | 29.9243 |
| 0.6919 | 3.9989 | 7364 | 1.6272 | 52.8716 | 27.9183 | 43.8019 | 48.6547 | 30.2002 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1