---
license: llama3
base_model: Minbyul/llama3-8b-instruct-wo-kqa_golden-iter-sft-step1
tags:
- alignment-handbook
- trl
- dpo
- generated_from_trainer
- trl
- dpo
- alignment-handbook
- generated_from_trainer
datasets:
- HuggingFaceH4/ultrafeedback_binarized
model-index:
- name: llama3-8b-instruct-wo-kqa_golden-iter-dpo-step1
  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. -->

# llama3-8b-instruct-wo-kqa_golden-iter-dpo-step1

This model is a fine-tuned version of [Minbyul/llama3-8b-instruct-wo-kqa_golden-iter-sft-step1](https://huggingface.co/Minbyul/llama3-8b-instruct-wo-kqa_golden-iter-sft-step1) on the HuggingFaceH4/ultrafeedback_binarized dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6931
- Rewards/chosen: 0.0
- Rewards/rejected: 0.0
- Rewards/accuracies: 0.0
- Rewards/margins: 0.0
- Logps/rejected: -369.7173
- Logps/chosen: -476.8867
- Logits/rejected: -0.5081
- Logits/chosen: -0.6523

## 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-07
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- total_eval_batch_size: 16
- 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 4.38.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2