| --- |
| base_model: klue/roberta-large |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: reward-bert-duplicate-answer |
| 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. --> |
|
|
| # reward-bert-duplicate-answer |
|
|
| This model is a fine-tuned version of [klue/roberta-large](https://huggingface.co/klue/roberta-large) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.0604 |
| - Accuracy: 0.0 |
|
|
| ## 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: 9e-06 |
| - train_batch_size: 4 |
| - eval_batch_size: 4 |
| - seed: 2023 |
| - gradient_accumulation_steps: 8 |
| - total_train_batch_size: 32 |
| - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08 |
| - lr_scheduler_type: cosine |
| - num_epochs: 1 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:| |
| | 0.2202 | 0.13 | 100 | 0.0750 | 0.0 | |
| | 0.1527 | 0.25 | 200 | 0.0377 | 0.0 | |
| | 0.1483 | 0.38 | 300 | 0.0729 | 0.0 | |
| | 0.1896 | 0.5 | 400 | 0.1465 | 0.0 | |
| | 0.1341 | 0.63 | 500 | 0.0729 | 0.0 | |
| | 0.0876 | 0.75 | 600 | 0.0351 | 0.0 | |
| | 0.1345 | 0.88 | 700 | 0.0604 | 0.0 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.35.0 |
| - Pytorch 2.1.0+cu118 |
| - Datasets 2.14.6 |
| - Tokenizers 0.14.1 |
| |
