---
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: allenai/tulu-2-13b
model-index:
- name: tulu2-13b-cost-UI-UF-HHRLHF-5e-7
  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. -->

# tulu2-13b-cost-UI-UF-HHRLHF-5e-7

This model is a fine-tuned version of [allenai/tulu-2-13b](https://huggingface.co/allenai/tulu-2-13b) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6892
- Rewards/chosen: 0.0042
- Rewards/rejected: -0.0043
- Rewards/accuracies: 0.5820
- Rewards/margins: 0.0085
- Rewards/margins Max: 0.0641
- Rewards/margins Min: -0.0449
- Rewards/margins Std: 0.0365
- Logps/rejected: -315.0963
- Logps/chosen: -326.8977
- Logits/rejected: -0.8867
- Logits/chosen: -1.0136

## 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: 2
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- total_eval_batch_size: 16
- 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 | Rewards/margins Max | Rewards/margins Min | Rewards/margins Std | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:-------------------:|:-------------------:|:-------------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.6522        | 1.0   | 2632 | 0.6892          | 0.0042         | -0.0043          | 0.5820             | 0.0085          | 0.0641              | -0.0449             | 0.0365              | -315.0963      | -326.8977    | -0.8867         | -1.0136       |


### Framework versions

- PEFT 0.7.1
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2