---
library_name: transformers
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 was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4935
- Rewards/chosen: -1.4744
- Rewards/rejected: -2.5261
- Rewards/accuracies: 0.7852
- Rewards/margins: 1.0517
- Logps/rejected: -508.4335
- Logps/chosen: -401.7670
- Logits/rejected: -0.6948
- Logits/chosen: -0.8246

## 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: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- 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 |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.4747        | 0.9984 | 477  | 0.4935          | -1.4744        | -2.5261          | 0.7852             | 1.0517          | -508.4335      | -401.7670    | -0.6948         | -0.8246       |


### Framework versions

- Transformers 4.45.2
- Pytorch 2.5.1+rocm6.2
- Datasets 3.5.0
- Tokenizers 0.20.3