---
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-filtered-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. -->

# simpo-train-filtered-full

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: 2.7573
- Rewards/chosen: -19.6452
- Rewards/rejected: -24.9351
- Rewards/accuracies: 0.7807
- Rewards/margins: 5.2899
- Logps/rejected: -2.4935
- Logps/chosen: -1.9645
- Logits/rejected: -13.6533
- Logits/chosen: -13.5874

## 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

| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 2.7931        | 0.8724 | 400  | 2.7628          | -19.4831       | -24.7305         | 0.7807             | 5.2474          | -2.4731        | -1.9483      | -13.6040        | -13.5429      |


### Framework versions

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