---
library_name: peft
tags:
- alignment-handbook
- generated_from_trainer
datasets:
- llama-duo/synth_summarize_dataset_dedup
base_model: google/gemma-7b
model-index:
- name: gemma7b-summarize-gpt4o-32k
  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. -->

# gemma7b-summarize-gpt4o-32k

This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the llama-duo/synth_summarize_dataset_dedup dataset.
It achieves the following results on the evaluation set:
- Loss: 2.5602

## 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: 4
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- 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: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.5798        | 1.0   | 55   | 4.0590          |
| 1.346         | 2.0   | 110  | 2.6944          |
| 1.1944        | 3.0   | 165  | 2.6027          |
| 1.1119        | 4.0   | 220  | 2.5779          |
| 1.0741        | 5.0   | 275  | 2.5495          |
| 1.0435        | 6.0   | 330  | 2.5501          |
| 1.0191        | 7.0   | 385  | 2.5536          |
| 0.9965        | 8.0   | 440  | 2.5604          |
| 0.9986        | 9.0   | 495  | 2.5597          |
| 0.9948        | 10.0  | 550  | 2.5602          |


### Framework versions

- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1