---
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-16k
  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-16k

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: 2.6632

## 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 |
|:-------------:|:------:|:----:|:---------------:|
| 20.3933       | 0.9811 | 26   | 7.9476          |
| 5.2781        | 2.0    | 53   | 4.2830          |
| 1.5712        | 2.9811 | 79   | 2.9235          |
| 1.2696        | 4.0    | 106  | 2.7524          |
| 1.1842        | 4.9811 | 132  | 2.7035          |
| 1.1359        | 6.0    | 159  | 2.6779          |
| 1.1053        | 6.9811 | 185  | 2.6764          |
| 1.0828        | 8.0    | 212  | 2.6683          |
| 1.0853        | 8.9811 | 238  | 2.6656          |
| 1.0794        | 9.8113 | 260  | 2.6632          |


### Framework versions

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