<!-- 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. -->
bart-base-chinese-wallstreetcn-morning-news-market-overview-SSE50-f1-9
This model is a fine-tuned version of fnlp/bart-base-chinese on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.9099
- F1: 0.5161
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 | 68 | 4.0931 | 0.6923 |
| No log | 2.0 | 136 | 4.2342 | 0.6923 |
| No log | 3.0 | 204 | 4.4335 | 0.3529 |
| No log | 4.0 | 272 | 4.6575 | 0.5455 |
| No log | 5.0 | 340 | 4.6009 | 0.4348 |
| No log | 6.0 | 408 | 4.2793 | 0.6154 |
| No log | 7.0 | 476 | 4.9954 | 0.5 |
| 0.0657 | 8.0 | 544 | 5.1372 | 0.5 |
| 0.0657 | 9.0 | 612 | 5.0386 | 0.5161 |
| 0.0657 | 10.0 | 680 | 4.9099 | 0.5161 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
