---
library_name: transformers
license: mit
base_model: gpt2
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: results_orca_dpo_wandb
  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. -->

# results_orca_dpo_wandb

This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6150
- Rewards/chosen: -0.2701
- Rewards/rejected: -2.5585
- Rewards/accuracies: 0.7940
- Rewards/margins: 2.2885
- Logps/rejected: -425.4867
- Logps/chosen: -344.9728
- Logits/rejected: -76.3682
- Logits/chosen: -76.4329

## 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: 0.0001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 200

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.9158        | 0.0346 | 50   | 0.7779          | -1.2673        | -3.1650          | 0.7319             | 1.8977          | -431.5514      | -354.9452    | -99.3161        | -98.3339      |
| 1.2481        | 0.0691 | 100  | 0.9942          | -3.1400        | -6.5742          | 0.7368             | 3.4342          | -465.6436      | -373.6723    | -86.8154        | -86.6002      |
| 0.6814        | 0.1037 | 150  | 0.7237          | -0.3674        | -2.6648          | 0.7635             | 2.2974          | -426.5488      | -345.9457    | -75.5469        | -75.8445      |
| 0.6615        | 0.1382 | 200  | 0.6150          | -0.2701        | -2.5585          | 0.7940             | 2.2885          | -425.4867      | -344.9728    | -76.3682        | -76.4329      |


### Framework versions

- Transformers 4.45.0
- Pytorch 2.4.0+cu124
- Datasets 3.2.0
- Tokenizers 0.20.3