| --- |
| license: mit |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| - precision |
| - recall |
| - f1 |
| model-index: |
| - name: paper_feedback_intent |
| 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. --> |
|
|
| # paper_feedback_intent |
|
|
| 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: 0.3621 |
| - Accuracy: 0.9302 |
| - Precision: 0.9307 |
| - Recall: 0.9302 |
| - F1: 0.9297 |
|
|
| ## 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: 16 |
| - eval_batch_size: 16 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - num_epochs: 10 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
| | 0.9174 | 1.0 | 11 | 0.7054 | 0.7907 | 0.7903 | 0.7907 | 0.7861 | |
| | 0.6917 | 2.0 | 22 | 0.4665 | 0.8140 | 0.8134 | 0.8140 | 0.8118 | |
| | 0.4276 | 3.0 | 33 | 0.3326 | 0.9070 | 0.9065 | 0.9070 | 0.9041 | |
| | 0.2656 | 4.0 | 44 | 0.3286 | 0.9070 | 0.9065 | 0.9070 | 0.9041 | |
| | 0.1611 | 5.0 | 55 | 0.3044 | 0.9302 | 0.9307 | 0.9302 | 0.9297 | |
| | 0.1025 | 6.0 | 66 | 0.3227 | 0.9302 | 0.9307 | 0.9302 | 0.9297 | |
| | 0.0799 | 7.0 | 77 | 0.3216 | 0.9302 | 0.9307 | 0.9302 | 0.9297 | |
| | 0.0761 | 8.0 | 88 | 0.3529 | 0.9302 | 0.9307 | 0.9302 | 0.9297 | |
| | 0.0479 | 9.0 | 99 | 0.3605 | 0.9302 | 0.9307 | 0.9302 | 0.9297 | |
| | 0.0358 | 10.0 | 110 | 0.3621 | 0.9302 | 0.9307 | 0.9302 | 0.9297 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.17.0 |
| - Pytorch 1.10.0+cu111 |
| - Datasets 2.0.0 |
| - Tokenizers 0.11.6 |
|
|
