---
library_name: peft
tags:
- trl
- kto
- generated_from_trainer
base_model: HuggingFaceH4/zephyr-7b-beta
model-index:
- name: WeniGPT-Agents-Zephyr-1.0.23-KTO
  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-Agents-Zephyr-1.0.23-KTO

This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5
- Rewards/chosen: -253.6596
- Rewards/rejected: -211.2579
- Rewards/margins: -42.4016
- Kl: 0.0
- Logps/chosen: -2820.3469
- Logps/rejected: -2352.2148

## 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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 147
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/margins | Kl  | Logps/chosen | Logps/rejected |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:---------------:|:---:|:------------:|:--------------:|
| 0.6222        | 0.32  | 50   | 0.5             | -253.6881      | -211.3268        | -42.3612        | 0.0 | -2820.6318   | -2352.9041     |
| 0.6529        | 0.65  | 100  | 0.5             | -253.6596      | -211.2579        | -42.4016        | 0.0 | -2820.3469   | -2352.2148     |


### Framework versions

- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2