bert_uncased_L-2_H-128_A-2_sst2
This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the GLUE SST2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4250
- Accuracy: 0.8096
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 |
|---|---|---|---|---|
| 0.5112 | 1.0 | 264 | 0.4485 | 0.7947 |
| 0.3556 | 2.0 | 528 | 0.4250 | 0.8096 |
| 0.2973 | 3.0 | 792 | 0.4395 | 0.8142 |
| 0.2606 | 4.0 | 1056 | 0.4392 | 0.8234 |
| 0.2359 | 5.0 | 1320 | 0.4604 | 0.8268 |
| 0.2163 | 6.0 | 1584 | 0.4542 | 0.8257 |
| 0.2006 | 7.0 | 1848 | 0.4868 | 0.8291 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3