---
license: mit
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: HuggingFaceH4/zephyr-7b-beta
model-index:
- name: WeniGPT-2.4.1-Zephyr-7B-3-epochs-LLM_Base_2.0.3_DPO
  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. -->

# WeniGPT-2.4.1-Zephyr-7B-3-epochs-LLM_Base_2.0.3_DPO

This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6603
- Rewards/chosen: -0.0862
- Rewards/rejected: -0.8016
- Rewards/accuracies: 0.0500
- Rewards/margins: 0.7154
- Logps/rejected: -15.9648
- Logps/chosen: -5.8822
- Logits/rejected: -2.0424
- Logits/chosen: -2.0422

## 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-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 267
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.645         | 1.12  | 100  | 0.6629          | -0.0384        | -0.7857          | 0.0469             | 0.7473          | -15.8056       | -5.4039      | -2.0586         | -2.0584       |
| 0.6487        | 2.23  | 200  | 0.6603          | -0.0862        | -0.8016          | 0.0500             | 0.7154          | -15.9648       | -5.8822      | -2.0424         | -2.0422       |


### Framework versions

- PEFT 0.8.2
- Transformers 4.38.2
- Pytorch 2.1.0+cu118
- Datasets 2.17.1
- Tokenizers 0.15.2