---
library_name: peft
tags:
- alignment-handbook
- trl
- dpo
- generated_from_trainer
base_model: norallm/normistral-7b-warm
datasets:
- hugodk-sch/aftonposten_title_prefs
model-index:
- name: ap-normistral-7b-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. -->

# ap-normistral-7b-align-scan

This model is a fine-tuned version of [data/ap-normistral-7b-sft-qlora](https://huggingface.co./data/ap-normistral-7b-sft-qlora) on the hugodk-sch/aftonposten_title_prefs dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9944
- Rewards/chosen: -0.0085
- Rewards/rejected: -0.0141
- Rewards/accuracies: 0.6005
- Rewards/margins: 0.0056
- Logps/rejected: -37.3726
- Logps/chosen: -33.2900
- Logits/rejected: 97.6266
- Logits/chosen: 97.6599

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.9955        | 0.26  | 100  | 0.9999          | 0.0005         | 0.0004           | 0.5187             | 0.0001          | -35.9246       | -32.3899     | 98.7274         | 98.7339       |
| 0.9858        | 0.52  | 200  | 0.9965          | -0.0053        | -0.0088          | 0.5274             | 0.0035          | -36.8453       | -32.9718     | 98.0264         | 98.0513       |
| 0.9814        | 0.78  | 300  | 0.9947          | -0.0086        | -0.0139          | 0.5889             | 0.0053          | -37.3559       | -33.3009     | 97.6402         | 97.6739       |


### Framework versions

- PEFT 0.10.0
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.1