---
license: mit
base_model: HuggingFaceH4/mistral-7b-sft-beta
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: zephyr-7b-dpo-full
  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-full

This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5034
- Rewards/chosen: -1.3101
- Rewards/rejected: -2.2670
- Rewards/accuracies: 0.7695
- Rewards/margins: 0.9569
- Logps/rejected: -484.0533
- Logps/chosen: -388.0500
- Logits/rejected: -1.9827
- Logits/chosen: -2.0268

## 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: 8
- eval_batch_size: 8
- seed: 1
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.5691        | 0.21  | 100  | 0.5829          | -0.6557        | -1.1886          | 0.7422             | 0.5328          | -376.2088      | -322.6110    | -2.7021         | -2.7191       |
| 0.5446        | 0.42  | 200  | 0.5301          | -0.8102        | -1.6275          | 0.7812             | 0.8173          | -420.1078      | -338.0599    | -2.2434         | -2.2738       |
| 0.5094        | 0.63  | 300  | 0.5146          | -1.3749        | -2.3136          | 0.7656             | 0.9387          | -488.7169      | -394.5290    | -1.9920         | -2.0372       |
| 0.5086        | 0.84  | 400  | 0.5034          | -1.3101        | -2.2670          | 0.7695             | 0.9569          | -484.0533      | -388.0500    | -1.9827         | -2.0268       |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1