ft-facebook-bart-large-xsum-on-samsum
This model is a fine-tuned version of facebook/bart-large-xsum on the Samsum dataset.
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: 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
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 0.22 | 100 | 1.5051 | 49.5382 | 24.4845 | 40.7456 | 45.3284 | 26.1722 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.2
- Datasets 2.17.0
- Tokenizers 0.15.1