---
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-gemini1_5flash-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. -->

# gemma7b-summarize-gemini1_5flash-1k

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: 8.7240

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 51.5906       | 1.0   | 2    | 16.5290         |
| 51.5906       | 2.0   | 4    | 14.1666         |
| 38.4458       | 3.0   | 6    | 13.0907         |
| 38.4458       | 4.0   | 8    | 11.6308         |
| 23.9261       | 5.0   | 10   | 10.3576         |
| 23.9261       | 6.0   | 12   | 9.4846          |
| 23.9261       | 7.0   | 14   | 9.0308          |
| 20.7948       | 8.0   | 16   | 8.8035          |
| 20.7948       | 9.0   | 18   | 8.7407          |
| 20.2787       | 10.0  | 20   | 8.7240          |


### Framework versions

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