metadata
base_model: fnlp/bart-base-chinese
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bart-base-chinese-wallstreetcn-morning-news-market-overview-SSE50-v10
results: []
bart-base-chinese-wallstreetcn-morning-news-market-overview-SSE50-v10
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: 2.5150
- Accuracy: 0.6970
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 | 68 | 3.2639 | 0.7273 |
| No log | 2.0 | 136 | 3.3479 | 0.6970 |
| No log | 3.0 | 204 | 1.0812 | 0.8182 |
| No log | 4.0 | 272 | 3.1943 | 0.7576 |
| No log | 5.0 | 340 | 2.3106 | 0.7576 |
| No log | 6.0 | 408 | 2.7138 | 0.7576 |
| No log | 7.0 | 476 | 2.2989 | 0.7879 |
| 0.0578 | 8.0 | 544 | 2.6486 | 0.6970 |
| 0.0578 | 9.0 | 612 | 2.2460 | 0.7576 |
| 0.0578 | 10.0 | 680 | 2.5150 | 0.6970 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3