metadata
license: mit
base_model: VietAI/vit5-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: ViT5_Dialogue_Summarization
results: []
ViT5_Dialogue_Summarization
This model is a fine-tuned version of VietAI/vit5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6228
- Rouge1: 52.8317
- Rouge2: 29.8327
- Rougel: 41.7287
- Rougelsum: 46.3648
- Gen Len: 16.8071
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: 5e-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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.8522 | 1.0 | 3683 | 1.6994 | 52.1383 | 28.4438 | 41.2886 | 45.7379 | 16.6484 |
| 1.496 | 2.0 | 7366 | 1.6228 | 52.8317 | 29.8327 | 41.7287 | 46.3648 | 16.8071 |
| 1.1959 | 3.0 | 11049 | 1.6419 | 53.6738 | 30.2857 | 42.5458 | 47.2315 | 16.906 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2