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: 1.4469
- Rouge1: 54.1048
- Rouge2: 29.4288
- Rougel: 44.7135
- Rougelsum: 49.7824
- Gen Len: 30.1333
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 |
|---|---|---|---|---|---|---|---|---|
| 1.4237 | 0.9997 | 1841 | 1.5096 | 52.578 | 27.25 | 43.167 | 47.8705 | 29.2381 |
| 1.0961 | 2.0 | 3683 | 1.4730 | 53.0543 | 28.2549 | 43.5716 | 48.5957 | 30.1355 |
| 0.8667 | 2.9997 | 5524 | 1.5579 | 52.8621 | 28.224 | 43.9952 | 48.5389 | 28.0488 |
| 0.7011 | 3.9989 | 7364 | 1.6067 | 52.4772 | 27.6106 | 43.5235 | 48.0805 | 29.8877 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1