bert-large-uncased_cls_sst2
This model is a fine-tuned version of bert-large-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3787
- Accuracy: 0.9255
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 433 | 0.4188 | 0.8578 |
| 0.3762 | 2.0 | 866 | 0.4894 | 0.8968 |
| 0.3253 | 3.0 | 1299 | 0.3313 | 0.9094 |
| 0.1601 | 4.0 | 1732 | 0.3399 | 0.9232 |
| 0.0744 | 5.0 | 2165 | 0.3787 | 0.9255 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1