hBERTv1_data_aug_sst2
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1 on the GLUE SST2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6087
- Accuracy: 0.7856
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 | Accuracy |
|---|---|---|---|---|
| 0.2892 | 1.0 | 4374 | 0.6087 | 0.7856 |
| 0.1628 | 2.0 | 8748 | 0.7398 | 0.7810 |
| 0.1151 | 3.0 | 13122 | 0.8492 | 0.8016 |
| 0.0917 | 4.0 | 17496 | 1.0381 | 0.7867 |
| 0.0862 | 5.0 | 21870 | 0.9657 | 0.7867 |
| 0.0762 | 6.0 | 26244 | 1.0815 | 0.7821 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.14.0a0+410ce96
- Datasets 2.10.1
- Tokenizers 0.13.2
- Downloads last month
- 1
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.