| --- |
| library_name: transformers |
| language: |
| - en |
| license: mit |
| base_model: microsoft/deberta-v3-small |
| tags: |
| - generated_from_trainer |
| metrics: |
| - precision |
| - recall |
| - f1 |
| - accuracy |
| - matthews_correlation |
| model-index: |
| - name: wordnet-network-predictor |
| 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. --> |
|
|
| # wordnet-network-predictor |
|
|
| This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.0483 |
| - Precision: 0.9808 |
| - Recall: 0.9944 |
| - F1: 0.9875 |
| - Accuracy: 0.9874 |
| - Matthews Correlation: 0.9749 |
|
|
| ## 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: 1e-05 |
| - train_batch_size: 64 |
| - eval_batch_size: 64 |
| - seed: 42 |
| - gradient_accumulation_steps: 5 |
| - total_train_batch_size: 320 |
| - 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: cosine |
| - num_epochs: 10 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | Matthews Correlation | |
| |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|:--------------------:| |
| | No log | 0 | 0 | 0.7276 | 0.4368 | 0.7188 | 0.5434 | 0.3935 | -0.2846 | |
| | 0.3924 | 1.0 | 2144 | 0.0697 | 0.9622 | 0.9893 | 0.9756 | 0.9751 | 0.9506 | |
| | 0.2978 | 2.0 | 4288 | 0.0522 | 0.9770 | 0.9883 | 0.9826 | 0.9825 | 0.9650 | |
| | 0.2273 | 3.0 | 6432 | 0.0534 | 0.9739 | 0.9932 | 0.9834 | 0.9832 | 0.9666 | |
| | 0.1735 | 4.0 | 8576 | 0.0483 | 0.9786 | 0.9925 | 0.9855 | 0.9853 | 0.9707 | |
| | 0.1457 | 5.0 | 10720 | 0.0463 | 0.9790 | 0.9935 | 0.9862 | 0.9860 | 0.9722 | |
| | 0.1212 | 6.0 | 12864 | 0.0456 | 0.9798 | 0.9940 | 0.9869 | 0.9867 | 0.9735 | |
| | 0.0956 | 7.0 | 15008 | 0.0483 | 0.9800 | 0.9945 | 0.9872 | 0.9870 | 0.9742 | |
| | 0.1035 | 8.0 | 17152 | 0.0462 | 0.9820 | 0.9937 | 0.9878 | 0.9877 | 0.9755 | |
| | 0.0810 | 9.0 | 19296 | 0.0482 | 0.9807 | 0.9942 | 0.9874 | 0.9873 | 0.9746 | |
| | 0.0831 | 10.0 | 21440 | 0.0483 | 0.9808 | 0.9944 | 0.9875 | 0.9874 | 0.9749 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 5.3.0 |
| - Pytorch 2.10.0+cu128 |
| - Datasets 4.5.0 |
| - Tokenizers 0.22.2 |
|
|
