hBERTv2_data_aug_cola
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2 on the GLUE COLA dataset. It achieves the following results on the evaluation set:
- Loss: 0.6181
- Matthews Correlation: 0.0
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
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.6082 | 1.0 | 835 | 0.6237 | 0.0 |
| 0.6068 | 2.0 | 1670 | 0.6186 | 0.0 |
| 0.6064 | 3.0 | 2505 | 0.6181 | 0.0 |
| 0.6062 | 4.0 | 3340 | 0.6218 | 0.0 |
| 0.6061 | 5.0 | 4175 | 0.6212 | 0.0 |
| 0.6062 | 6.0 | 5010 | 0.6186 | 0.0 |
| 0.606 | 7.0 | 5845 | 0.6189 | 0.0 |
| 0.6062 | 8.0 | 6680 | 0.6203 | 0.0 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.14.0a0+410ce96
- Datasets 2.10.1
- Tokenizers 0.13.2
- 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.