sa_BERT_48_sst2
This model is a fine-tuned version of gokuls/bert_base_48 on the GLUE SST2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4556
- Accuracy: 0.8028
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: 4e-05
- train_batch_size: 96
- eval_batch_size: 96
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.36 | 1.0 | 702 | 0.4556 | 0.8028 |
| 0.2158 | 2.0 | 1404 | 0.5677 | 0.8039 |
| 0.1674 | 3.0 | 2106 | 0.5359 | 0.8119 |
| 0.1358 | 4.0 | 2808 | 0.6864 | 0.7878 |
| 0.11 | 5.0 | 3510 | 0.4984 | 0.8085 |
| 0.0927 | 6.0 | 4212 | 0.6800 | 0.7856 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3