---
library_name: peft
tags:
- trl
- dpo
- 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:
- Loss: 0.4464
- Rewards/chosen: 0.0179
- Rewards/rejected: -0.0124
- Rewards/accuracies: 0.5428
- Rewards/margins: 0.0304
- Logps/rejected: -37.5321
- Logps/chosen: -34.0121
- Logits/rejected: -2.2303
- Logits/chosen: -2.2352

## 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 | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.3817        | 0.26  | 100  | 0.4287          | 0.0507         | 0.0294           | 0.5577             | 0.0213          | -37.4799       | -33.9712     | -2.2329         | -2.2378       |
| 0.3991        | 0.52  | 200  | 0.4536          | -0.0010        | -0.0197          | 0.5374             | 0.0187          | -37.5412       | -34.0358     | -2.2300         | -2.2349       |
| 0.2816        | 0.78  | 300  | 0.4464          | 0.0179         | -0.0124          | 0.5428             | 0.0304          | -37.5321       | -34.0121     | -2.2303         | -2.2352       |


### Framework versions

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