---
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 the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1420
- Rewards/chosen: 5.3389
- Rewards/rejected: -11.5415
- Rewards/accuracies: 0.9258
- Rewards/margins: 16.8803
- Logps/rejected: -131.7123
- Logps/chosen: -119.9761
- Logits/rejected: -1.8130
- Logits/chosen: -1.8134

## 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: 42
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.1496        | 0.21  | 100  | 0.1356          | 4.1320         | -11.2810         | 0.9414             | 15.4129         | -130.8439      | -123.9990    | -1.7910         | -1.8010       |
| 0.1795        | 0.42  | 200  | 0.1364          | 5.2675         | -11.0420         | 0.9336             | 16.3095         | -130.0476      | -120.2140    | -1.8607         | -1.8614       |
| 0.1585        | 0.63  | 300  | 0.1425          | 5.1387         | -11.7029         | 0.9258             | 16.8416         | -132.2504      | -120.6432    | -1.7960         | -1.7980       |
| 0.2005        | 0.84  | 400  | 0.1420          | 5.3389         | -11.5415         | 0.9258             | 16.8803         | -131.7123      | -119.9761    | -1.8130         | -1.8134       |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.2