| --- |
| library_name: transformers |
| license: agpl-3.0 |
| base_model: RonTon05/model_content_V2_test |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: New_MTL_Full_Finetuning_OverSampling |
| 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. --> |
|
|
| # New_MTL_Full_Finetuning_OverSampling |
|
|
| 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: 0.4517 |
| - F1 Task1: 0.9727 |
| - F1 Task2: 0.7492 |
| - Acc Task1: 0.9789 |
| - Acc Task2: 0.9160 |
| - F1 Macro: 0.8609 |
|
|
| ## 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: 128 |
| - eval_batch_size: 128 |
| - seed: 42 |
| - gradient_accumulation_steps: 2 |
| - total_train_batch_size: 256 |
| - 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 |
| - lr_scheduler_warmup_steps: 261 |
| - num_epochs: 10 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | F1 Task1 | F1 Task2 | Acc Task1 | Acc Task2 | F1 Macro | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:---------:|:--------:| |
| | 0.9477 | 1.0 | 261 | 0.6483 | 0.9686 | 0.3580 | 0.9757 | 0.8208 | 0.6633 | |
| | 0.5012 | 2.0 | 522 | 0.4314 | 0.9709 | 0.7120 | 0.9774 | 0.8852 | 0.8414 | |
| | 0.3632 | 3.0 | 783 | 0.3812 | 0.9722 | 0.7348 | 0.9786 | 0.9047 | 0.8535 | |
| | 0.2974 | 4.0 | 1044 | 0.3800 | 0.9742 | 0.7434 | 0.9800 | 0.9074 | 0.8588 | |
| | 0.2496 | 5.0 | 1305 | 0.3895 | 0.9728 | 0.7440 | 0.9790 | 0.9115 | 0.8584 | |
| | 0.2106 | 6.0 | 1566 | 0.4031 | 0.9731 | 0.7459 | 0.9791 | 0.9108 | 0.8595 | |
| | 0.1790 | 7.0 | 1827 | 0.4297 | 0.9734 | 0.7460 | 0.9794 | 0.9157 | 0.8597 | |
| | 0.1574 | 8.0 | 2088 | 0.4305 | 0.9731 | 0.7487 | 0.9792 | 0.9180 | 0.8609 | |
| | 0.1412 | 9.0 | 2349 | 0.4515 | 0.9743 | 0.7511 | 0.9801 | 0.9172 | 0.8627 | |
| | 0.1321 | 10.0 | 2610 | 0.4517 | 0.9727 | 0.7492 | 0.9789 | 0.9160 | 0.8609 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 5.17.0 |
| - Pytorch 2.10.0+cu128 |
| - Datasets 5.0.1 |
| - Tokenizers 0.23.2 |
| |
