metadata
tags:
- generated_from_trainer
model-index:
- name: Comment_Score_By_douban_-finetuned-financial_data
results: []
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: 0.7806
- Mse: 0.7806
- Rmse: 0.8835
- Mae: 0.6603
- R2: 0.5667
- Smape: 22.5571
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 | 0.7806 | 0.7806 | 0.8835 | 0.6603 | 0.5667 | 22.5571 |
| No log | 2.0 | 338 | 0.6650 | 0.6650 | 0.8155 | 0.6101 | 0.6309 | 21.0106 |
| 0.8495 | 3.0 | 507 | 0.6534 | 0.6534 | 0.8083 | 0.5901 | 0.6373 | 20.3481 |
| 0.8495 | 4.0 | 676 | 0.6608 | 0.6608 | 0.8129 | 0.5881 | 0.6332 | 20.2336 |
| 0.8495 | 5.0 | 845 | 0.6619 | 0.6619 | 0.8136 | 0.5855 | 0.6326 | 20.1610 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.12.1+cu113
- Datasets 2.9.0
- Tokenizers 0.13.2