albert-base-chinese-finetuned-qqp
This model is a fine-tuned version of ckiplab/albert-base-chinese on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4448448717594147
- Accuracy: 0.95
- F1: 0.9473684210526316
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 30 | 0.517563 | 0.500000 | 0.000000 |
| No log | 2.0 | 60 | 0.416847 | 0.850000 | 0.869565 |
| No log | 3.0 | 90 | 0.444845 | 0.950000 | 0.947368 |
| No log | 4.0 | 120 | 0.430313 | 0.900000 | 0.888889 |
| No log | 5.0 | 150 | 0.439254 | 0.900000 | 0.888889 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1
- Datasets 2.9.0
- Tokenizers 0.13.0.dev0
- Downloads last month
- 1