mt5_thaisum_model
This model is a fine-tuned version of google/mt5-base on the thaisum dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3039
- Rouge1: 0.2017
- Rouge2: 0.0806
- Rougel: 0.2016
- Rougelsum: 0.2017
- Gen Len: 18.9995
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: 0.0002
- 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
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
Rouge1 |
Rouge2 |
Rougel |
Rougelsum |
Gen Len |
| 2.0742 |
1.0 |
5000 |
0.3272 |
0.1713 |
0.055 |
0.1703 |
0.1716 |
18.9945 |
| 1.7874 |
2.0 |
10000 |
0.3073 |
0.194 |
0.0742 |
0.1942 |
0.194 |
18.997 |
| 1.6341 |
3.0 |
15000 |
0.3035 |
0.2002 |
0.0804 |
0.1999 |
0.2002 |
19.0 |
| 1.4501 |
4.0 |
20000 |
0.3039 |
0.2017 |
0.0806 |
0.2016 |
0.2017 |
18.9995 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
