metadata
base_model: vinai/bartpho-word-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bartpho-word-base-finetuned-ee
results: []
bartpho-word-base-finetuned-ee
This model is a fine-tuned version of vinai/bartpho-word-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0116
- Rouge1: 88.7657
- Rouge2: 79.4792
- Rougel: 88.7741
- Rougelsum: 88.763
- Gen Len: 9.7227
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: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|---|---|---|---|
| 0.0185 | 1.0 | 1492 | 0.0137 | 87.7748 | 77.4443 | 87.7942 | 87.7914 | 9.7606 |
| 0.0124 | 2.0 | 2984 | 0.0121 | 87.7891 | 77.3659 | 87.7946 | 87.7802 | 9.8511 |
| 0.0093 | 3.0 | 4476 | 0.0116 | 88.7657 | 79.4792 | 88.7741 | 88.763 | 9.7227 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1