<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bart-ingredients-extract
This model is a fine-tuned version of sshleifer/distilbart-xsum-12-6 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3434
- Rouge1: 44.3464
- Rouge2: 25.67
- Rougel: 44.3032
- Rougelsum: 44.3007
- Gen Len: 16.2697
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: 2
- eval_batch_size: 2
- seed: 42
- 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 |
|---|---|---|---|---|---|---|---|---|
| 0.7151 | 1.0 | 1552 | 0.5275 | 53.7819 | 31.247 | 53.7202 | 53.7078 | 12.9069 |
| 0.5151 | 2.0 | 3104 | 0.4429 | 49.9951 | 28.9098 | 49.9357 | 49.9016 | 13.4797 |
| 0.4237 | 3.0 | 4656 | 0.3622 | 52.4925 | 31.4498 | 52.4645 | 52.4606 | 13.5396 |
| 0.3644 | 4.0 | 6208 | 0.3434 | 44.3464 | 25.67 | 44.3032 | 44.3007 | 16.2697 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
