distilbert_base_lda_train_book_qqp
This model is a fine-tuned version of gokulsrinivasagan/distilbert_base_lda_train_book on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.2736
- Accuracy: 0.8914
- F1: 0.8572
- Combined Score: 0.8743
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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.3567 | 1.0 | 1422 | 0.2876 | 0.8732 | 0.8265 | 0.8499 |
| 0.2454 | 2.0 | 2844 | 0.2781 | 0.8787 | 0.8462 | 0.8625 |
| 0.1798 | 3.0 | 4266 | 0.2736 | 0.8914 | 0.8572 | 0.8743 |
| 0.1297 | 4.0 | 5688 | 0.2963 | 0.8938 | 0.8564 | 0.8751 |
| 0.097 | 5.0 | 7110 | 0.3225 | 0.8938 | 0.8588 | 0.8763 |
| 0.0742 | 6.0 | 8532 | 0.3526 | 0.8935 | 0.8579 | 0.8757 |
| 0.0596 | 7.0 | 9954 | 0.3946 | 0.8946 | 0.8591 | 0.8768 |
| 0.049 | 8.0 | 11376 | 0.4326 | 0.8925 | 0.8592 | 0.8759 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3