---
library_name: peft
tags:
- llama-factory
- lora
- generated_from_trainer
base_model: google/gemma-7b
model-index:
- name: Gemma_AAID_mixed_train
  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_AAID_mixed_train

This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the AAID_mixed dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6853

## 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: 0.0003
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.589         | 0.2188 | 200  | 0.6853          |
| 0.3117        | 0.4375 | 400  | 0.8606          |
| 0.1797        | 0.6563 | 600  | 0.9867          |
| 0.0901        | 0.8750 | 800  | 1.2095          |


### Framework versions

- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1