| --- |
| license: apache-2.0 |
| base_model: bert-base-uncased |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: 2d_oomv2_800 |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # 2d_oomv2_800 |
|
|
| This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the [ComNum](https://huggingface.co/datasets/abbassix/ComNum) dataset. |
| This model used 800 samples as training, 200 as validation, and 1200 as test on three epochs. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.3666 |
| - Accuracy: 0.835 |
|
|
| This model achieves the following results on the test set: |
| - Loss: 0.3656 |
| - Accuracy: 0.7487 |
| <!-- |
| {'eval_loss': 0.36558857560157776, 'eval_accuracy': 0.7487, 'eval_runtime': 725.6959, 'eval_samples_per_second': 13.78, 'eval_steps_per_second': 1.722} |
| --> |
| ## 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: 8 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - num_epochs: 3.0 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:| |
| | No log | 1.0 | 100 | 0.3891 | 0.765 | |
| | No log | 2.0 | 200 | 0.3528 | 0.765 | |
| | No log | 3.0 | 300 | 0.3666 | 0.835 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.36.2 |
| - Pytorch 2.1.0+cu121 |
| - Datasets 2.16.1 |
| - Tokenizers 0.15.0 |
| |
