---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: alignment-handbook/zephyr-7b-sft-full
model-index:
- name: zephyr-dpo-timedial-selfgen-mix2
  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. -->

# zephyr-dpo-timedial-selfgen-mix2

This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2588
- Rewards/chosen: 0.2087
- Rewards/rejected: -1.0200
- Rewards/accuracies: 1.0
- Rewards/margins: 1.2287
- Logps/rejected: -132.2824
- Logps/chosen: -6.8403
- Logits/rejected: -2.8679
- Logits/chosen: -2.8807

## 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: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- 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

| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.4825        | 0.35  | 100  | 0.4632          | 0.2303         | -0.3022          | 1.0                | 0.5325          | -60.5070       | -4.6766      | -2.9751         | -2.9715       |
| 0.2786        | 0.69  | 200  | 0.2588          | 0.2087         | -1.0200          | 1.0                | 1.2287          | -132.2824      | -6.8403      | -2.8679         | -2.8807       |


### Framework versions

- PEFT 0.7.1
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2