metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: classification_tnews_eda_aug
results: []
classification_tnews_eda_aug
This model is a fine-tuned version of hfl/chinese-roberta-wwm-ext on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4212
- Accuracy: 0.6533
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: 2e-05
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4947 | 1.0 | 135 | 1.3206 | 0.6267 |
| 0.1659 | 2.0 | 270 | 1.2521 | 0.68 |
| 0.0274 | 3.0 | 405 | 1.3476 | 0.66 |
| 0.0161 | 4.0 | 540 | 1.3907 | 0.66 |
| 0.0136 | 5.0 | 675 | 1.4212 | 0.6533 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2