bert_tiny_lda_100_v1_book_cola
This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_lda_100_v1_book on the GLUE COLA dataset. It achieves the following results on the evaluation set:
- Loss: 0.5875
- Matthews Correlation: 0.1996
- Accuracy: 0.6932
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 | Matthews Correlation | Accuracy |
|---|---|---|---|---|---|
| 0.6112 | 1.0 | 34 | 0.6112 | 0.0 | 0.6913 |
| 0.5906 | 2.0 | 68 | 0.5992 | 0.0844 | 0.6951 |
| 0.5465 | 3.0 | 102 | 0.5875 | 0.1996 | 0.6932 |
| 0.4903 | 4.0 | 136 | 0.5887 | 0.1992 | 0.6913 |
| 0.4275 | 5.0 | 170 | 0.6417 | 0.2174 | 0.7095 |
| 0.3786 | 6.0 | 204 | 0.6495 | 0.2711 | 0.7210 |
| 0.3295 | 7.0 | 238 | 0.6801 | 0.2401 | 0.7028 |
| 0.2891 | 8.0 | 272 | 0.7395 | 0.2701 | 0.7152 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
- Downloads last month
- 4
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for gokulsrinivasagan/bert_tiny_lda_100_v1_book_cola
Base model
gokulsrinivasagan/bert_tiny_lda_100_v1_bookDataset used to train gokulsrinivasagan/bert_tiny_lda_100_v1_book_cola
Evaluation results
- Matthews Correlation on GLUE COLAself-reported0.200
- Accuracy on GLUE COLAself-reported0.693