BertClassificationTest
This model is a fine-tuned version of google-bert/bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5371
- Accuracy: 0.8558
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 65 | 0.4451 | 0.8462 |
No log | 2.0 | 130 | 0.4713 | 0.8462 |
No log | 3.0 | 195 | 0.4581 | 0.8558 |
No log | 4.0 | 260 | 0.5371 | 0.8558 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0
- Downloads last month
- 46
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for poooj/BertClassificationTest
Base model
google-bert/bert-base-uncased