| --- |
| library_name: transformers |
| license: agpl-3.0 |
| base_model: RonTon05/model_content_V2_test |
| tags: |
| - generated_from_trainer |
| metrics: |
| - f1 |
| model-index: |
| - name: MTL_Frozen_Binary_Head |
| 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. --> |
|
|
| # MTL_Frozen_Binary_Head |
| |
| This model is a fine-tuned version of [RonTon05/model_content_V2_test](https://huggingface.co/RonTon05/model_content_V2_test) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.9871 |
| - F1 Task1: 0.9903 |
| - F1 Task2: 0.7752 |
| - Acc Task1: 0.9945 |
| - Acc Task2: 0.7587 |
| - F1: 0.8828 |
| - F1 Macro: 0.8828 |
| |
| ## 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: 64 |
| - eval_batch_size: 64 |
| - 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 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | F1 Task1 | F1 Task2 | Acc Task1 | Acc Task2 | F1 | F1 Macro | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:---------:|:------:|:--------:| |
| | 1.6496 | 1.0 | 275 | 1.3011 | 0.9763 | 0.3112 | 0.9864 | 0.5693 | 0.6438 | 0.6438 | |
| | 1.0802 | 2.0 | 550 | 1.0318 | 0.9895 | 0.5528 | 0.9941 | 0.6586 | 0.7711 | 0.7711 | |
| | 0.8327 | 3.0 | 825 | 0.9183 | 0.9880 | 0.6750 | 0.9932 | 0.7200 | 0.8315 | 0.8315 | |
| | 0.6482 | 4.0 | 1100 | 0.8339 | 0.9895 | 0.7142 | 0.9941 | 0.7444 | 0.8519 | 0.8519 | |
| | 0.5080 | 5.0 | 1375 | 0.8138 | 0.9899 | 0.7506 | 0.9943 | 0.7521 | 0.8703 | 0.8703 | |
| | 0.3938 | 6.0 | 1650 | 0.8271 | 0.9899 | 0.7537 | 0.9943 | 0.7526 | 0.8718 | 0.8718 | |
| | 0.3061 | 7.0 | 1925 | 0.9401 | 0.9895 | 0.7559 | 0.9941 | 0.7439 | 0.8727 | 0.8727 | |
| | 0.2469 | 8.0 | 2200 | 0.9307 | 0.9899 | 0.7725 | 0.9943 | 0.7585 | 0.8812 | 0.8812 | |
| | 0.2041 | 9.0 | 2475 | 0.9748 | 0.9899 | 0.7718 | 0.9943 | 0.7578 | 0.8808 | 0.8808 | |
| | 0.1769 | 10.0 | 2750 | 0.9871 | 0.9903 | 0.7752 | 0.9945 | 0.7587 | 0.8828 | 0.8828 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 5.9.0 |
| - Pytorch 2.7.1+cu118 |
| - Datasets 4.8.5 |
| - Tokenizers 0.22.2 |
| |
