---
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- generated_from_trainer
model-index:
- name: zephyr-7b-dpo-lora
  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-7b-dpo-lora

This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5657
- Rewards/chosen: -0.0834
- Rewards/rejected: -0.5329
- Rewards/accuracies: 0.7020
- Rewards/margins: 0.4496
- Logps/rejected: -224.6124
- Logps/chosen: -265.4659
- Logits/rejected: -2.0001
- Logits/chosen: -2.1212

## 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-07
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 32
- total_train_batch_size: 256
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.6123        | 1.0   | 242  | 0.6065          | 0.0003         | -0.2418          | 0.6660             | 0.2421          | -221.7009      | -264.6292    | -2.0235         | -2.1436       |
| 0.5841        | 2.0   | 484  | 0.5733          | -0.0606        | -0.4698          | 0.7040             | 0.4092          | -223.9813      | -265.2384    | -2.0064         | -2.1272       |
| 0.567         | 3.0   | 726  | 0.5657          | -0.0834        | -0.5329          | 0.7020             | 0.4496          | -224.6124      | -265.4659    | -2.0001         | -2.1212       |


### Framework versions

- Transformers 4.35.0
- Pytorch 2.0.1
- Datasets 2.14.6
- Tokenizers 0.14.1