| --- |
| library_name: transformers |
| license: mit |
| base_model: microsoft/deberta-v3-large |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: deberta-category |
| 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. --> |
|
|
| # deberta-category |
|
|
| This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.3595 |
| - Macro F1: 0.7766 |
| - Weighted F1: 0.8732 |
| - Accuracy: 0.8728 |
|
|
| ## 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: 32 |
| - eval_batch_size: 32 |
| - seed: 42 |
| - optimizer: Use OptimizerNames.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 |
| - mixed_precision_training: Native AMP |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Macro F1 | Weighted F1 | Accuracy | |
| |:-------------:|:------:|:----:|:---------------:|:--------:|:-----------:|:--------:| |
| | 0.4592 | 0.4840 | 500 | 0.4634 | 0.5938 | 0.7383 | 0.7330 | |
| | 0.2541 | 0.9681 | 1000 | 0.3037 | 0.6894 | 0.8289 | 0.8264 | |
| | 0.1975 | 1.4521 | 1500 | 0.3295 | 0.7422 | 0.8453 | 0.8458 | |
| | 0.1439 | 1.9361 | 2000 | 0.2862 | 0.7455 | 0.8511 | 0.8488 | |
| | 0.1674 | 2.4201 | 2500 | 0.2982 | 0.7427 | 0.8633 | 0.8629 | |
| | 0.1932 | 2.9042 | 3000 | 0.2622 | 0.7373 | 0.8593 | 0.8589 | |
| | 0.1468 | 3.3882 | 3500 | 0.3017 | 0.7825 | 0.8622 | 0.8627 | |
| | 0.0525 | 3.8722 | 4000 | 0.3540 | 0.7629 | 0.8622 | 0.8602 | |
| | 0.0977 | 4.3562 | 4500 | 0.3557 | 0.7677 | 0.8598 | 0.8572 | |
| | 0.0696 | 4.8403 | 5000 | 0.3595 | 0.7766 | 0.8732 | 0.8728 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.53.3 |
| - Pytorch 2.6.0+cu124 |
| - Datasets 4.0.0 |
| - Tokenizers 0.21.2 |
|
|
