<!-- 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. -->
ernie-finetuned-qqp
This model is a fine-tuned version of nghuyong/ernie-2.0-en on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.4381
- Accuracy: 0.9157
- F1: 0.8861
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 |
|---|---|---|---|---|---|
| 0.2522 | 1.0 | 22741 | 0.2505 | 0.8997 | 0.8633 |
| 0.1903 | 2.0 | 45482 | 0.2645 | 0.9071 | 0.8761 |
| 0.1599 | 3.0 | 68223 | 0.2986 | 0.9115 | 0.8816 |
| 0.1214 | 4.0 | 90964 | 0.3640 | 0.9133 | 0.8828 |
| 0.0809 | 5.0 | 113705 | 0.4381 | 0.9157 | 0.8861 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6
