<!-- 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-finetuned2
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: 0.1448
- 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: 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 | F1 |
---|---|---|---|---|---|
1.4081 | 1.0 | 3 | 0.9711 | 0.7273 | 0.6573 |
0.9516 | 2.0 | 6 | 0.8174 | 0.8182 | 0.8160 |
0.8945 | 3.0 | 9 | 0.6617 | 0.9091 | 0.9124 |
0.7042 | 4.0 | 12 | 0.5308 | 1.0 | 1.0 |
0.6641 | 5.0 | 15 | 0.4649 | 1.0 | 1.0 |
0.5731 | 6.0 | 18 | 0.4046 | 1.0 | 1.0 |
0.5132 | 7.0 | 21 | 0.3527 | 1.0 | 1.0 |
0.3999 | 8.0 | 24 | 0.3070 | 1.0 | 1.0 |
0.4198 | 9.0 | 27 | 0.2673 | 1.0 | 1.0 |
0.3677 | 10.0 | 30 | 0.2378 | 1.0 | 1.0 |
0.3545 | 11.0 | 33 | 0.2168 | 1.0 | 1.0 |
0.3237 | 12.0 | 36 | 0.1980 | 1.0 | 1.0 |
0.3122 | 13.0 | 39 | 0.1860 | 1.0 | 1.0 |
0.2802 | 14.0 | 42 | 0.1759 | 1.0 | 1.0 |
0.2552 | 15.0 | 45 | 0.1671 | 1.0 | 1.0 |
0.2475 | 16.0 | 48 | 0.1598 | 1.0 | 1.0 |
0.2259 | 17.0 | 51 | 0.1541 | 1.0 | 1.0 |
0.201 | 18.0 | 54 | 0.1492 | 1.0 | 1.0 |
0.2083 | 19.0 | 57 | 0.1461 | 1.0 | 1.0 |
0.2281 | 20.0 | 60 | 0.1448 | 1.0 | 1.0 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.12.0+cu102
- Datasets 2.1.0
- Tokenizers 0.12.1