---
library_name: peft
tags:
- alignment-handbook
- generated_from_trainer
- trl
- dpo
base_model: DUAL-GPO/phi-2-dpo-chatml-lora-40k-60k-i1-merged
datasets:
- HuggingFaceH4/ultrafeedback_binarized
model-index:
- name: phi-2-dpo-chatml-lora-40k-60k-v2-i2
  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. -->

# phi-2-dpo-chatml-lora-40k-60k-v2-i2

This model is a fine-tuned version of [DUAL-GPO/phi-2-dpo-chatml-lora-40k-60k-i1-merged](https://huggingface.co/DUAL-GPO/phi-2-dpo-chatml-lora-40k-60k-i1-merged) on the HuggingFaceH4/ultrafeedback_binarized 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-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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

- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.14.6
- Tokenizers 0.15.2