---
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: mistral-7b-dpo-full-wo-kqa_golden-ep3
  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. -->

# mistral-7b-dpo-full-wo-kqa_golden-ep3

This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2889
- Rewards/chosen: -0.9091
- Rewards/rejected: -3.8737
- Rewards/accuracies: 0.8250
- Rewards/margins: 2.9646
- Logps/rejected: -1290.0824
- Logps/chosen: -656.5975
- Logits/rejected: -2.9198
- Logits/chosen: -3.1186

## 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: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 32
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.1851        | 0.53  | 100  | 0.2889          | -0.9091        | -3.8737          | 0.8250             | 2.9646          | -1290.0824     | -656.5975    | -2.9198         | -3.1186       |


### Framework versions

- Transformers 4.39.0.dev0
- Pytorch 2.1.2
- Datasets 2.14.6
- Tokenizers 0.15.2