---
base_model: checkpoints/Llama-3-8B-Instruct-DPO-Iter1
tags:
- alignment-handbook
- generated_from_trainer
- trl
- sppo
datasets:
- synthetic_data_llama-3-8b-instruct-dpo-iter2_score
model-index:
- name: mistral-7b-instruct-sppo-iter1
  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. -->

# mistral-7b-instruct-sppo-iter1

This model is a fine-tuned version of [checkpoints/Llama-3-8B-Instruct-DPO-Iter1](https://huggingface.co/checkpoints/Llama-3-8B-Instruct-DPO-Iter1) on the synthetic_data_llama-3-8b-instruct-dpo-iter2_score dataset.

## 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: 1
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1.0

### Training results



### Framework versions

- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.14.6
- Tokenizers 0.19.1