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

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: 0.6593

## 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: 32
- 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 |
|:-------------:|:------:|:----:|:---------------:|
| 3.1586        | 0.0109 | 10   | 0.7969          |
| 0.6717        | 0.0219 | 20   | 0.7616          |
| 0.5741        | 0.0328 | 30   | 0.7398          |
| 0.5809        | 0.0438 | 40   | 0.7745          |
| 0.5313        | 0.0547 | 50   | 0.7014          |
| 0.4879        | 0.0656 | 60   | 0.7165          |
| 0.4665        | 0.0766 | 70   | 0.7070          |
| 0.4509        | 0.0875 | 80   | 0.7005          |
| 0.4542        | 0.0984 | 90   | 0.6933          |
| 0.4188        | 0.1094 | 100  | 0.6599          |
| 0.4131        | 0.1203 | 110  | 0.6593          |
| 0.4137        | 0.1313 | 120  | 0.6896          |
| 0.4087        | 0.1422 | 130  | 0.6930          |
| 0.3968        | 0.1531 | 140  | 0.6692          |
| 0.4048        | 0.1641 | 150  | 0.6872          |
| 0.3953        | 0.1750 | 160  | 0.6939          |


### Framework versions

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