---
license: gemma
library_name: peft
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
base_model: google/gemma-7b
datasets:
- chansung/no_robots_only_coding
model-index:
- name: gemma-7b-sft-qlora-no-robots15
  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. -->

# gemma-7b-sft-qlora-no-robots15

This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the chansung/no_robots_only_coding dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2830

## 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: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 21.906        | 0.91  | 5    | 7.6533          |
| 13.5603       | 2.0   | 11   | 6.6442          |
| 10.2605       | 2.91  | 16   | 6.0815          |
| 9.9129        | 4.0   | 22   | 3.1148          |
| 4.5895        | 4.91  | 27   | 1.6583          |
| 1.6316        | 6.0   | 33   | 1.4155          |
| 1.4115        | 6.91  | 38   | 1.3543          |
| 1.2971        | 8.0   | 44   | 1.3133          |
| 1.1321        | 8.91  | 49   | 1.2903          |
| 0.9739        | 10.0  | 55   | 1.2820          |
| 0.917         | 10.91 | 60   | 1.2888          |
| 0.8541        | 12.0  | 66   | 1.2781          |
| 0.8659        | 12.91 | 71   | 1.2892          |
| 0.8354        | 13.64 | 75   | 1.2830          |


### Framework versions

- PEFT 0.7.1
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2