T5_large_filipino_news_summarization
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9187
- Rouge1: 0.1576
- Rouge2: 0.0693
- Rougel: 0.1368
- Rougelsum: 0.1369
- Gen Len: 19.0
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: 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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 314 | 2.0605 | 0.1607 | 0.0706 | 0.1404 | 0.1403 | 19.0 |
| 2.2975 | 2.0 | 628 | 1.9736 | 0.1581 | 0.0686 | 0.1378 | 0.1379 | 19.0 |
| 2.2975 | 3.0 | 942 | 1.9327 | 0.158 | 0.0698 | 0.1381 | 0.1381 | 19.0 |
| 2.0777 | 4.0 | 1256 | 1.9187 | 0.1576 | 0.0693 | 0.1368 | 0.1369 | 19.0 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3