<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bert-base-chinese-finetuned-QA-b8
This model is a fine-tuned version of ckiplab/bert-base-chinese on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2136
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- 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 |
|---|---|---|---|
| 1.3406 | 0.29 | 1000 | 0.8157 |
| 0.7651 | 0.58 | 2000 | 0.7385 |
| 0.7172 | 0.87 | 3000 | 0.6328 |
| 0.5028 | 1.16 | 4000 | 0.6747 |
| 0.405 | 1.45 | 5000 | 0.6796 |
| 0.4005 | 1.73 | 6000 | 0.6860 |
| 0.3522 | 2.02 | 7000 | 0.8813 |
| 0.2048 | 2.31 | 8000 | 0.9346 |
| 0.1929 | 2.6 | 9000 | 1.0987 |
| 0.2032 | 2.89 | 10000 | 1.0005 |
| 0.142 | 3.18 | 11000 | 1.1372 |
| 0.0938 | 3.47 | 12000 | 1.2476 |
| 0.0953 | 3.76 | 13000 | 1.2136 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.13.1+cu116
- Datasets 2.14.5
- Tokenizers 0.14.1
