| --- |
| 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_ESC |
| 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_ESC |
|
|
| 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: 0.9798 |
| - F1 Task1: 0.9891 |
| - F1 Task2: 0.7678 |
| - Acc Task1: 0.9939 |
| - Acc Task2: 0.7626 |
| - F1: 0.8784 |
| - F1 Macro: 0.8784 |
|
|
| ## 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 | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:---------:|:------:|:--------:| |
| | 1.6569 | 1.0 | 275 | 1.2547 | 0.9879 | 0.2903 | 0.9932 | 0.5718 | 0.6391 | 0.6391 | |
| | 1.0892 | 2.0 | 550 | 1.0031 | 0.9879 | 0.5537 | 0.9932 | 0.6748 | 0.7708 | 0.7708 | |
| | 0.8380 | 3.0 | 825 | 0.9031 | 0.9863 | 0.6681 | 0.9923 | 0.7150 | 0.8272 | 0.8272 | |
| | 0.6510 | 4.0 | 1100 | 0.8875 | 0.9879 | 0.7025 | 0.9932 | 0.7262 | 0.8452 | 0.8452 | |
| | 0.5109 | 5.0 | 1375 | 0.8376 | 0.9883 | 0.7234 | 0.9934 | 0.7521 | 0.8559 | 0.8559 | |
| | 0.3947 | 6.0 | 1650 | 0.8322 | 0.9891 | 0.7526 | 0.9939 | 0.7610 | 0.8708 | 0.8708 | |
| | 0.3137 | 7.0 | 1925 | 0.9283 | 0.9886 | 0.7496 | 0.9936 | 0.7516 | 0.8691 | 0.8691 | |
| | 0.2608 | 8.0 | 2200 | 0.9745 | 0.9899 | 0.7599 | 0.9943 | 0.7562 | 0.8749 | 0.8749 | |
| | 0.2211 | 9.0 | 2475 | 0.9593 | 0.9875 | 0.7710 | 0.9929 | 0.7646 | 0.8793 | 0.8793 | |
| | 0.1950 | 10.0 | 2750 | 0.9798 | 0.9891 | 0.7678 | 0.9939 | 0.7626 | 0.8784 | 0.8784 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 5.10.2 |
| - Pytorch 2.7.1+cu118 |
| - Datasets 4.8.5 |
| - Tokenizers 0.22.2 |
|
|
