metadata
base_model: bert-base-chinese
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert-finetuned-weibo-luobokuaipao
results: []
bert-finetuned-weibo-luobokuaipao
This model is a fine-tuned version of bert-base-chinese on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.2677
- Accuracy: 0.6348
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 198 | 2.5581 | 0.5919 |
| No log | 2.0 | 396 | 2.2918 | 0.6348 |
| 0.2014 | 3.0 | 594 | 1.9679 | 0.6348 |
| 0.2014 | 4.0 | 792 | 2.9800 | 0.6196 |
| 0.2014 | 5.0 | 990 | 2.6793 | 0.6398 |
| 0.1375 | 6.0 | 1188 | 2.8340 | 0.6247 |
| 0.1375 | 7.0 | 1386 | 2.5889 | 0.6247 |
| 0.1278 | 8.0 | 1584 | 2.3041 | 0.6725 |
| 0.1278 | 9.0 | 1782 | 2.5275 | 0.6524 |
| 0.1278 | 10.0 | 1980 | 3.1778 | 0.6171 |
| 0.0614 | 11.0 | 2178 | 2.8898 | 0.6196 |
| 0.0614 | 12.0 | 2376 | 2.7480 | 0.6322 |
| 0.028 | 13.0 | 2574 | 3.0678 | 0.6322 |
| 0.028 | 14.0 | 2772 | 3.0487 | 0.6448 |
| 0.028 | 15.0 | 2970 | 3.2878 | 0.6373 |
| 0.0177 | 16.0 | 3168 | 3.1296 | 0.6373 |
| 0.0177 | 17.0 | 3366 | 3.2056 | 0.6297 |
| 0.0193 | 18.0 | 3564 | 3.2349 | 0.6247 |
| 0.0193 | 19.0 | 3762 | 3.2624 | 0.6247 |
| 0.0193 | 20.0 | 3960 | 3.2677 | 0.6348 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1