Comment_Score_By_douban_-finetuned-financial_data
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: 0.8968
- Mse: 0.8968
- Rmse: 0.9470
- Mae: 0.7104
- R2: 0.4941
- Smape: 24.0094
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: 128
- eval_batch_size: 20
- 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 | Mse | Rmse | Mae | R2 | Smape |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 169 | 0.8968 | 0.8968 | 0.9470 | 0.7104 | 0.4941 | 24.0094 |
| No log | 2.0 | 338 | 0.6792 | 0.6792 | 0.8241 | 0.6188 | 0.6169 | 21.1323 |
| 0.8399 | 3.0 | 507 | 0.6845 | 0.6845 | 0.8274 | 0.6031 | 0.6138 | 20.6587 |
| 0.8399 | 4.0 | 676 | 0.6598 | 0.6598 | 0.8123 | 0.5881 | 0.6278 | 20.1132 |
| 0.8399 | 5.0 | 845 | 0.6820 | 0.6820 | 0.8258 | 0.5909 | 0.6153 | 20.1342 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.12.1+cu113
- Datasets 2.9.0
- Tokenizers 0.13.2