---
library_name: transformers
license: gemma
base_model: google/gemma-2-9b-it
tags:
- alignment-handbook
- trl
- simpo
- generated_from_trainer
- trl
- simpo
- generated_from_trainer
datasets:
- jz666/gemma2-ultrafeedback-ppl-split
model-index:
- name: simpo-train-small-correct
  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. -->

# simpo-train-small-correct

This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) on the jz666/gemma2-ultrafeedback-ppl-split dataset.
It achieves the following results on the evaluation set:
- Loss: 4.1299
- Rewards/chosen: -14.3711
- Rewards/rejected: -17.0128
- Rewards/accuracies: 0.6721
- Rewards/margins: 2.6416
- Logps/rejected: -1.7013
- Logps/chosen: -1.4371
- Logits/rejected: -13.7500
- Logits/chosen: -13.7681

## 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: 8e-07
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- 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



### Framework versions

- Transformers 4.44.2
- Pytorch 2.7.0+cu128
- Datasets 2.18.0
- Tokenizers 0.19.1