---
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: RewardModel_RobertaBase
  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. -->

# RewardModel_RobertaBase

This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4742
- F1: 0.7921
- Roc Auc: 0.7917
- Accuracy: 0.7897

## 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: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
| No log        | 1.0   | 93   | 0.6779          | 0.6257 | 0.625   | 0.6230   |
| 0.6429        | 2.0   | 186  | 0.4775          | 0.7833 | 0.7837  | 0.7817   |
| 0.5357        | 3.0   | 279  | 0.4742          | 0.7921 | 0.7917  | 0.7897   |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1