metadata
license: apache-2.0
base_model: sshleifer/distilbart-cnn-6-6
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: plain-bart-on-presummarized-tod-wcep
results: []
plain-bart-on-presummarized-tod-wcep
This model is a fine-tuned version of sshleifer/distilbart-cnn-6-6 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3043
- Rouge1: 34.5939
- Rouge2: 13.9925
- Rougel: 24.4982
- Rougelsum: 27.7893
- Gen Len: 66.2392
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.4866 | 1.0 | 510 | 2.3191 | 34.0155 | 13.6965 | 24.0706 | 27.3858 | 66.8784 |
| 2.1347 | 2.0 | 1020 | 2.2952 | 34.1203 | 13.7453 | 24.0993 | 27.4503 | 67.0735 |
| 1.9605 | 3.0 | 1530 | 2.3043 | 34.5939 | 13.9925 | 24.4982 | 27.7893 | 66.2392 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2