---
license: gemma
library_name: peft
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
base_model: google/gemma-2b
datasets:
- llama-duo/synth_summarize_dataset_dedup
model-index:
- name: gemma2b-summarize-gpt4o-1k
  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. -->

# gemma2b-summarize-gpt4o-1k

This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the llama-duo/synth_summarize_dataset_dedup dataset.
It achieves the following results on the evaluation set:
- Loss: 2.7415

## 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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 3
- gradient_accumulation_steps: 2
- total_train_batch_size: 48
- total_eval_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.9975        | 0.8   | 2    | 3.1990          |
| 2.8744        | 2.0   | 5    | 3.0048          |
| 2.8744        | 2.8   | 7    | 2.8992          |
| 2.3833        | 4.0   | 10   | 2.8237          |
| 2.3833        | 4.8   | 12   | 2.7889          |
| 2.1436        | 6.0   | 15   | 2.7588          |
| 2.1436        | 6.8   | 17   | 2.7501          |
| 2.0522        | 8.0   | 20   | 2.7415          |


### Framework versions

- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1