---
base_model: ChaiML/reward_models_100_170000000_cp_498032
tags:
- generated_from_trainer
model-index:
- name: reward-model
  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-model

This model is a fine-tuned version of [ChaiML/reward_models_100_170000000_cp_498032](https://huggingface.co/ChaiML/reward_models_100_170000000_cp_498032) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6275

## 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: 1e-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 7
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 200
- num_epochs: 1

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.6911        | 0.04  | 200  | 0.6674          |
| 0.654         | 0.09  | 400  | 0.6472          |
| 0.6654        | 0.13  | 600  | 0.6429          |
| 0.6381        | 0.17  | 800  | 0.6391          |
| 0.6546        | 0.21  | 1000 | 0.6381          |
| 0.6575        | 0.26  | 1200 | 0.6352          |
| 0.6458        | 0.3   | 1400 | 0.6344          |
| 0.6574        | 0.34  | 1600 | 0.6335          |
| 0.6409        | 0.39  | 1800 | 0.6314          |
| 0.6255        | 0.43  | 2000 | 0.6306          |
| 0.6342        | 0.47  | 2200 | 0.6300          |
| 0.6117        | 0.51  | 2400 | 0.6298          |
| 0.6651        | 0.56  | 2600 | 0.6307          |
| 0.6624        | 0.6   | 2800 | 0.6294          |
| 0.6213        | 0.64  | 3000 | 0.6286          |
| 0.6486        | 0.68  | 3200 | 0.6278          |
| 0.6258        | 0.73  | 3400 | 0.6277          |
| 0.6336        | 0.77  | 3600 | 0.6278          |
| 0.5842        | 0.81  | 3800 | 0.6277          |
| 0.6748        | 0.86  | 4000 | 0.6275          |
| 0.5985        | 0.9   | 4200 | 0.6275          |
| 0.6207        | 0.94  | 4400 | 0.6275          |
| 0.5901        | 0.98  | 4600 | 0.6275          |


### Framework versions

- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.6
- Tokenizers 0.14.1