---
base_model: HuggingFaceTB/cosmo2-135M-webinst-sc2
tags:
- alignment-handbook
- trl
- dpo
- generated_from_trainer
- trl
- dpo
- generated_from_trainer
datasets:
- HuggingFaceTB/Helpsteer
model-index:
- name: cosmo2-135M-webinst-sc2-dpo-helpsteer-ep1
  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. -->

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/loubnabnl/huggingface/runs/bh5ijwbx)
# cosmo2-135M-webinst-sc2-dpo-helpsteer-ep1

This model is a fine-tuned version of [HuggingFaceTB/cosmo2-135M-webinst-sc2](https://huggingface.co/HuggingFaceTB/cosmo2-135M-webinst-sc2) on the HuggingFaceTB/Helpsteer dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6824
- Rewards/chosen: -0.0115
- Rewards/rejected: -0.0340
- Rewards/accuracies: 0.5833
- Rewards/margins: 0.0225
- Logps/rejected: -190.0087
- Logps/chosen: -147.2760
- Logits/rejected: 0.1785
- Logits/chosen: -0.0247
- IFEval loose prompt 14.79
- IFEval strict prompt 12.2
  
## 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: 2
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 32
- 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



### Framework versions

- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1