<!-- 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-bigbird-wwm-base-4096-wallstreetcn-morning-news-market-overview-open-000001SH-v1
This model is a fine-tuned version of Lowin/chinese-bigbird-wwm-base-4096 on the dataset of Wallstreetcn Morning News Market Overview with overnight index (000001.SH) movement labels. It achieves the following results on the evaluation set:
- Loss: 0.955115795135498
- Accuracy: 0.6896551724137931
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 75 | 0.6903 | 0.5862 |
| No log | 2.0 | 150 | 0.6608 | 0.6552 |
| No log | 3.0 | 225 | 0.9551 | 0.6897 |
| No log | 4.0 | 300 | 1.8075 | 0.5862 |
| No log | 5.0 | 375 | 1.7461 | 0.6552 |
| No log | 6.0 | 450 | 2.2845 | 0.5862 |
| 0.3813 | 7.0 | 525 | 2.2898 | 0.5862 |
| 0.3813 | 8.0 | 600 | 2.0169 | 0.6552 |
| 0.3813 | 9.0 | 675 | 2.2466 | 0.6552 |
| 0.3813 | 10.0 | 750 | 2.2800 | 0.6552 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.2
- Tokenizers 0.13.3
