| --- |
| library_name: transformers |
| base_model: allenai/scibert_scivocab_uncased |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: sciBERT-RA-Context-Cross-Encoder |
| 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. --> |
|
|
| # sciBERT-RA-Context-Cross-Encoder |
|
|
| This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.8088 |
| - Accuracy: 0.8608 |
| - Macro F1: 0.8608 |
| - Genuine F1: 0.8595 |
| - Implausible F1: 0.862 |
|
|
| ## 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 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: 10 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 | Genuine F1 | Implausible F1 | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:----------:|:--------------:| |
| | 0.4080 | 1.0 | 669 | 0.3342 | 0.8698 | 0.8696 | 0.8649 | 0.8743 | |
| | 0.3192 | 2.0 | 1338 | 0.3226 | 0.8653 | 0.8653 | 0.8653 | 0.8653 | |
| | 0.2567 | 3.0 | 2007 | 0.3989 | 0.8608 | 0.8608 | 0.8614 | 0.8602 | |
| | 0.2252 | 4.0 | 2676 | 0.4264 | 0.8735 | 0.8735 | 0.874 | 0.873 | |
| | 0.1172 | 5.0 | 3345 | 0.6592 | 0.8548 | 0.8547 | 0.8588 | 0.8505 | |
| | 0.0879 | 6.0 | 4014 | 0.7473 | 0.8638 | 0.8637 | 0.8598 | 0.8675 | |
| | 0.1181 | 7.0 | 4683 | 0.8088 | 0.8608 | 0.8608 | 0.8595 | 0.862 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 5.17.0 |
| - Pytorch 2.11.0+cu130 |
| - Datasets 4.8.5 |
| - Tokenizers 0.23.2 |
| |
