---
license: mit
library_name: peft
tags:
- trl
- kto
- KTO
- WeniGPT
- generated_from_trainer
base_model: HuggingFaceH4/zephyr-7b-beta
model-index:
- name: WeniGPT-Agents-Zephyr-1.0.1-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-1.0.1-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: 0.4733
- Rewards/chosen: -140.3215
- Logps/chosen: -1703.4486
- Rewards/rejected: -136.0403
- Logps/rejected: -1636.1003
- Kl: 0.0
- Rewards/margins: -6.8907

## 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: 145
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Logps/chosen | Rewards/rejected | Logps/rejected | Kl  | Rewards/margins |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:------------:|:----------------:|:--------------:|:---:|:---------------:|
| 0.4204        | 0.34  | 50   | 0.4736          | -17.1046       | -471.2798    | -19.5147         | -470.8448      | 0.0 | 1.9299          |
| 0.4813        | 0.68  | 100  | 0.4733          | -140.3215      | -1703.4486   | -136.0403        | -1636.1003     | 0.0 | -6.8907         |


### Framework versions

- PEFT 0.10.0
- Transformers 4.39.1
- Pytorch 2.1.0+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2