extract-mt-small
This model is a fine-tuned version of arfu/cn-mt-small on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.3417
- Rouge1: 5.4167
- Rouge2: 5.0
- Rougel: 5.0
- Rougelsum: 5.4167
- Gen Len: 5.7667
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: 0.0001
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.1434 | 1.0 | 127 | 0.5071 | 5.8333 | 5.8333 | 5.8333 | 5.8333 | 6.2083 |
| 0.5765 | 2.0 | 254 | 0.4069 | 5.4167 | 5.0 | 5.0 | 5.4167 | 5.7167 |
| 0.4662 | 3.0 | 381 | 0.3842 | 5.4167 | 5.0 | 5.0 | 5.4167 | 5.725 |
| 0.4183 | 4.0 | 508 | 0.3748 | 5.4167 | 5.0 | 5.0 | 5.4167 | 5.85 |
| 0.3703 | 5.0 | 635 | 0.3417 | 5.4167 | 5.0 | 5.0 | 5.4167 | 5.7667 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2