---
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: -2.2435
- Logits/rejected: -2.2386
- Logps/chosen: -34.0177
- Logps/rejected: -37.5002
- Loss: 0.9998
- Rewards/accuracies: 0.4904
- Rewards/chosen: 0.0135
- Rewards/margins: 0.0004
- Rewards/rejected: 0.0132

## 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 |
|:-------------:|:-----:|:----:|:-------------:|:---------------:|:------------:|:--------------:|:---------------:|:------------------:|:--------------:|:---------------:|:----------------:|
| 1.0026        | 0.26  | 100  | -2.2433       | -2.2384         | -34.0232     | -37.4972       | 1.0066          | 0.4983             | 0.0091         | -0.0064         | 0.0155           |
| 0.9923        | 0.52  | 200  | -2.2438       | -2.2389         | -34.0187     | -37.5175       | 0.9864          | 0.5328             | 0.0127         | 0.0134          | -0.0007          |
| 0.9775        | 0.78  | 300  | -2.2435       | -2.2386         | -34.0177     | -37.5002       | 0.9998          | 0.4904             | 0.0135         | 0.0004          | 0.0132           |


### Framework versions

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