| --- |
| license: mit |
| tags: |
| - generated_from_trainer |
| metrics: |
| - f1 |
| - accuracy |
| - recall |
| base_model: ibm/ColD-Fusion |
| model-index: |
| - name: roberta_comp |
| 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. --> |
|
|
| # roberta_comp |
| |
| This model is a fine-tuned version of [ibm/ColD-Fusion](https://huggingface.co/ibm/ColD-Fusion) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.3066 |
| - F1: 0.8077 |
| - Roc Auc: 0.8650 |
| - Accuracy: 0.5765 |
| - Recall: 0.8105 |
| |
| ## 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: 8 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - num_epochs: 5 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy | Recall | |
| |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|:------:| |
| | No log | 1.0 | 231 | 0.3455 | 0.7594 | 0.8284 | 0.5306 | 0.7474 | |
| | No log | 2.0 | 462 | 0.2986 | 0.7986 | 0.8569 | 0.5714 | 0.7930 | |
| | 0.3143 | 3.0 | 693 | 0.3006 | 0.8056 | 0.8632 | 0.5867 | 0.8070 | |
| | 0.3143 | 4.0 | 924 | 0.3066 | 0.8077 | 0.8650 | 0.5765 | 0.8105 | |
| | 0.1365 | 5.0 | 1155 | 0.3117 | 0.8028 | 0.8618 | 0.5663 | 0.8070 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.25.1 |
| - Pytorch 1.13.1+rocm5.2 |
| - Datasets 2.8.0 |
| - Tokenizers 0.13.2 |
| |
