|
--- |
|
library_name: transformers |
|
base_model: bert-base-chinese |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: bert-base-chinese-finetuned-question-answering-8 |
|
results: [] |
|
--- |
|
|
|
<!-- 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-question-answering-8 |
|
|
|
This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0682 |
|
|
|
## 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: 5e-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: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.6873 | 0.1842 | 500 | 1.1089 | |
|
| 1.1046 | 0.3683 | 1000 | 0.9349 | |
|
| 0.9793 | 0.5525 | 1500 | 0.9402 | |
|
| 0.9477 | 0.7366 | 2000 | 0.8424 | |
|
| 0.8951 | 0.9208 | 2500 | 0.8333 | |
|
| 0.6411 | 1.1050 | 3000 | 0.9014 | |
|
| 0.4946 | 1.2891 | 3500 | 0.9121 | |
|
| 0.4887 | 1.4733 | 4000 | 0.8586 | |
|
| 0.4875 | 1.6575 | 4500 | 0.9060 | |
|
| 0.4483 | 1.8416 | 5000 | 0.7990 | |
|
| 0.4079 | 2.0258 | 5500 | 0.9980 | |
|
| 0.2337 | 2.2099 | 6000 | 1.0852 | |
|
| 0.2342 | 2.3941 | 6500 | 1.0850 | |
|
| 0.2239 | 2.5783 | 7000 | 1.0937 | |
|
| 0.1853 | 2.7624 | 7500 | 1.1032 | |
|
| 0.2009 | 2.9466 | 8000 | 1.0682 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.0 |
|
- Tokenizers 0.19.1 |
|
|
