---
library_name: peft
tags:
- trl
- dpo
- alignment-handbook
- generated_from_trainer
base_model: NbAiLab/nb-gpt-j-6B-v2
model-index:
- name: aftonposten-6b-align-scan
  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. -->

# aftonposten-6b-align-scan

This model is a fine-tuned version of [NbAiLab/nb-gpt-j-6B-v2](https://huggingface.co./NbAiLab/nb-gpt-j-6B-v2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Logits/chosen: -2.2444
- Logits/rejected: -2.2395
- Logps/chosen: -34.0121
- Logps/rejected: -37.4951
- Loss: 0.5001
- Rewards/accuracies: 0.5046
- Rewards/chosen: 0.0180
- Rewards/margins: 0.0007
- Rewards/rejected: 0.0172

## 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: 5e-06
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1

### Training results

| Training Loss | Epoch | Step | Logits/chosen | Logits/rejected | Logps/chosen | Logps/rejected | Validation Loss | Rewards/accuracies | Rewards/chosen | Rewards/margins | Rewards/rejected |
|:-------------:|:-----:|:----:|:-------------:|:---------------:|:------------:|:--------------:|:---------------:|:------------------:|:--------------:|:---------------:|:----------------:|
| 0.4981        | 0.26  | 100  | -2.2441       | -2.2392         | -34.0229     | -37.5093       | 0.4997          | 0.5079             | 0.0093         | 0.0034          | 0.0059           |
| 0.4987        | 0.52  | 200  | -2.2435       | -2.2386         | -34.0140     | -37.4995       | 0.4999          | 0.5075             | 0.0165         | 0.0027          | 0.0137           |
| 0.4901        | 0.78  | 300  | -2.2444       | -2.2395         | -34.0121     | -37.4951       | 0.5001          | 0.5046             | 0.0180         | 0.0007          | 0.0172           |


### Framework versions

- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.1.2+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1