BART-base_readme_summarizer
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4470
- Rouge1: 0.5488
- Rouge2: 0.4108
- Rougel: 0.5211
- Rougelsum: 0.521
- Gen Len: 15.3616
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.6549 | 1.0 | 785 | 1.8488 | 0.5118 | 0.368 | 0.4814 | 0.4809 | 15.2238 |
| 1.8191 | 2.0 | 1570 | 1.5999 | 0.5355 | 0.3952 | 0.507 | 0.5073 | 15.1631 |
| 1.6592 | 3.0 | 2355 | 1.4853 | 0.5363 | 0.4 | 0.509 | 0.5095 | 15.3085 |
| 1.3785 | 4.0 | 3140 | 1.4470 | 0.5488 | 0.4108 | 0.5211 | 0.521 | 15.3616 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1