pert-qa
This model is a fine-tuned version of hfl/chinese-pert-large on the cmrc2018 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6942
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: 3e-05
- 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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1273 | 1.0 | 1200 | 0.7088 |
| 0.6132 | 2.0 | 2400 | 0.6942 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.10.0+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1