<!-- 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. -->
Erlangshen-Longformer-110M-finetuning-wallstreetcn-morning-news-close-000001.SH-v2
This model is a fine-tuned version of IDEA-CCNL/Erlangshen-Longformer-110M on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6936
- Accuracy: 0.44
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: 5e-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 | 38 | 0.6894 | 0.56 |
| No log | 2.0 | 76 | 0.7096 | 0.44 |
| No log | 3.0 | 114 | 0.6915 | 0.56 |
| No log | 4.0 | 152 | 0.6872 | 0.56 |
| No log | 5.0 | 190 | 0.6881 | 0.56 |
| No log | 6.0 | 228 | 0.7079 | 0.44 |
| No log | 7.0 | 266 | 0.7026 | 0.44 |
| No log | 8.0 | 304 | 0.6914 | 0.56 |
| No log | 9.0 | 342 | 0.7012 | 0.44 |
| No log | 10.0 | 380 | 0.6936 | 0.44 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
