---
license: gemma
library_name: peft
tags:
- trl
- reward-trainer
- generated_from_trainer
base_model: google/gemma-2b
metrics:
- accuracy
model-index:
- name: RM-harmless_harmless_contrast_loraR64_20000_gemma2b_lr1e-06_bs2_g4
  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. -->

# RM-harmless_harmless_contrast_loraR64_20000_gemma2b_lr1e-06_bs2_g4

This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6606
- Accuracy: 0.6115

## 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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2.0

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.693         | 1.0   | 2250 | 0.7084          | 0.5645   |
| 0.6394        | 2.0   | 4500 | 0.6606          | 0.6115   |


### Framework versions

- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1