ft-facebook-bart-large-xsum-on-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: 1.5249
- Rouge1: 50.3616
- Rouge2: 25.1246
- Rougel: 41.214
- Rougelsum: 46.1946
- Gen Len: 26.423
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: 4
- total_train_batch_size: 16
- 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 | 0.11 | 100 | 1.5514 | 49.1738 | 23.682 | 40.0793 | 44.8382 | 26.0818 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.1+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 4
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for mrami010/ft-facebook-bart-large-xsum-on-samsum
Base model
facebook/bart-large-xsum