<!-- 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. -->
chinese-roberta-wwm-ext-finetuned
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: 0.2139
- Accuracy: 1.0
- F1: 1.0
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.0107 | 1.0 | 1 | 0.8782 | 0.6 | 0.4500 |
| 0.8418 | 2.0 | 2 | 0.7816 | 0.6 | 0.4500 |
| 0.7572 | 3.0 | 3 | 0.7080 | 0.6 | 0.4500 |
| 0.6794 | 4.0 | 4 | 0.6487 | 0.8 | 0.7810 |
| 0.7444 | 5.0 | 5 | 0.5972 | 0.8 | 0.7810 |
| 0.68 | 6.0 | 6 | 0.5516 | 0.9 | 0.8967 |
| 0.5622 | 7.0 | 7 | 0.5103 | 0.9 | 0.8967 |
| 0.5131 | 8.0 | 8 | 0.4692 | 0.9 | 0.8967 |
| 0.5941 | 9.0 | 9 | 0.4285 | 1.0 | 1.0 |
| 0.5093 | 10.0 | 10 | 0.3899 | 1.0 | 1.0 |
| 0.4149 | 11.0 | 11 | 0.3549 | 1.0 | 1.0 |
| 0.4634 | 12.0 | 12 | 0.3248 | 1.0 | 1.0 |
| 0.3982 | 13.0 | 13 | 0.2985 | 1.0 | 1.0 |
| 0.352 | 14.0 | 14 | 0.2756 | 1.0 | 1.0 |
| 0.3633 | 15.0 | 15 | 0.2570 | 1.0 | 1.0 |
| 0.3729 | 16.0 | 16 | 0.2420 | 1.0 | 1.0 |
| 0.2934 | 17.0 | 17 | 0.2303 | 1.0 | 1.0 |
| 0.308 | 18.0 | 18 | 0.2220 | 1.0 | 1.0 |
| 0.2977 | 19.0 | 19 | 0.2166 | 1.0 | 1.0 |
| 0.2969 | 20.0 | 20 | 0.2139 | 1.0 | 1.0 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.12.0+cu102
- Datasets 1.18.4
- Tokenizers 0.12.1
