<!-- 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-lert-base-wallstreetcn-morning-news-market-overview-SSEC-f1-3
This model is a fine-tuned version of hfl/chinese-lert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1227
- F1: 0.7333
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 | F1 |
|---|---|---|---|---|
| No log | 1.0 | 34 | 3.8212 | 0.6 |
| No log | 2.0 | 68 | 2.6125 | 0.6875 |
| No log | 3.0 | 102 | 2.5793 | 0.6154 |
| No log | 4.0 | 136 | 2.9560 | 0.4762 |
| No log | 5.0 | 170 | 2.9874 | 0.6875 |
| No log | 6.0 | 204 | 2.0140 | 0.6923 |
| No log | 7.0 | 238 | 3.0157 | 0.6667 |
| No log | 8.0 | 272 | 2.8225 | 0.6857 |
| No log | 9.0 | 306 | 2.1322 | 0.7333 |
| No log | 10.0 | 340 | 2.1227 | 0.7333 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
