| --- |
| library_name: transformers |
| license: mit |
| base_model: jhu-clsp/mmBERT-base |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: trainer_output |
| 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. --> |
|
|
| # trainer_output |
| |
| This model is a fine-tuned version of [jhu-clsp/mmBERT-base](https://huggingface.co/jhu-clsp/mmBERT-base) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.8549 |
| - Accuracy: 92.5064 |
| - Sentence accuracy: 47.9134 |
| |
| ## 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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: linear |
| - num_epochs: 25 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | Sentence accuracy | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------------:| |
| | 0.9817 | 1.0 | 596 | 0.6246 | 89.2170 | 35.2396 | |
| | 0.3128 | 2.0 | 1192 | 0.5229 | 90.7575 | 40.1855 | |
| | 0.1836 | 3.0 | 1788 | 0.5851 | 91.7304 | 42.9675 | |
| | 0.1099 | 4.0 | 2384 | 0.6264 | 91.4177 | 41.7311 | |
| | 0.0744 | 5.0 | 2980 | 0.6672 | 92.2400 | 46.2133 | |
| | 0.0333 | 6.0 | 3576 | 0.6985 | 91.7535 | 43.8949 | |
| | 0.0234 | 7.0 | 4172 | 0.7473 | 92.2863 | 45.9042 | |
| | 0.0165 | 8.0 | 4768 | 0.7186 | 92.1589 | 45.2859 | |
| | 0.0167 | 9.0 | 5364 | 0.8132 | 92.4832 | 47.4498 | |
| | 0.0118 | 10.0 | 5960 | 0.8421 | 92.4253 | 46.3679 | |
| | 0.0058 | 11.0 | 6556 | 0.7998 | 92.4716 | 44.8223 | |
| | 0.0057 | 12.0 | 7152 | 0.7845 | 92.7843 | 47.2952 | |
| | 0.0039 | 13.0 | 7748 | 0.8570 | 92.6569 | 47.2952 | |
| | 0.0042 | 14.0 | 8344 | 0.8719 | 92.7496 | 48.2226 | |
| | 0.004 | 15.0 | 8940 | 0.8683 | 92.5990 | 47.9134 | |
| | 0.0038 | 16.0 | 9536 | 0.8549 | 92.5064 | 47.9134 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.57.3 |
| - Pytorch 2.11.0+cu128 |
| - Datasets 4.0.0 |
| - Tokenizers 0.22.2 |
|
|
