| --- |
| license: mit |
| base_model: roberta-base |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: tapt_seq_bn_amazon_helpfulness_classification_model_v2 |
| 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. --> |
|
|
| # tapt_seq_bn_amazon_helpfulness_classification_model_v2 |
| |
| This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.3540 |
| - Accuracy: 0.864 |
| - F1 Macro: 0.6950 |
| |
| ## 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: 0.0001 |
| - train_batch_size: 16 |
| - eval_batch_size: 16 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06 |
| - lr_scheduler_type: linear |
| - lr_scheduler_warmup_ratio: 0.06 |
| - num_epochs: 10 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | |
| |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| |
| | 0.3384 | 1.0 | 1563 | 0.3308 | 0.8586 | 0.6739 | |
| | 0.3245 | 2.0 | 3126 | 0.3256 | 0.8652 | 0.6719 | |
| | 0.3258 | 3.0 | 4689 | 0.3408 | 0.8674 | 0.6464 | |
| | 0.3309 | 4.0 | 6252 | 0.3150 | 0.8678 | 0.6527 | |
| | 0.292 | 5.0 | 7815 | 0.3226 | 0.8692 | 0.6787 | |
| | 0.2756 | 6.0 | 9378 | 0.3384 | 0.8688 | 0.6498 | |
| | 0.2584 | 7.0 | 10941 | 0.3489 | 0.8654 | 0.6946 | |
| | 0.2758 | 8.0 | 12504 | 0.3540 | 0.864 | 0.6950 | |
| | 0.2476 | 9.0 | 14067 | 0.3540 | 0.8668 | 0.6688 | |
| | 0.2303 | 10.0 | 15630 | 0.3686 | 0.8662 | 0.6542 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.36.2 |
| - Pytorch 2.2.1+cu121 |
| - Datasets 2.18.0 |
| - Tokenizers 0.15.2 |
|
|
