chinese-bert-wwm-ext-finetuned-QA-b8-10
This model is a fine-tuned version of hfl/chinese-bert-wwm-ext on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2029
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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7409 | 1.0 | 3460 | 0.6617 |
| 0.4568 | 2.0 | 6920 | 0.7331 |
| 0.2729 | 3.0 | 10380 | 0.9146 |
| 0.1864 | 4.0 | 13840 | 1.2475 |
| 0.1163 | 5.0 | 17300 | 1.3969 |
| 0.0825 | 6.0 | 20760 | 1.8681 |
| 0.0411 | 7.0 | 24220 | 2.0010 |
| 0.0317 | 8.0 | 27680 | 2.1313 |
| 0.0163 | 9.0 | 31140 | 2.2390 |
| 0.0053 | 10.0 | 34600 | 2.2029 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.14.5
- Tokenizers 0.13.3