---
license: gemma
library_name: peft
tags:
- generated_from_trainer
base_model: google/paligemma-3b-pt-224
model-index:
- name: gemma_hg
  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_hg

This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 5.1803

## 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: 0.0001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 50

### Training results

| Training Loss | Epoch   | Step | Validation Loss |
|:-------------:|:-------:|:----:|:---------------:|
| 3.2946        | 7.6923  | 25   | 2.8461          |
| 2.4688        | 15.3846 | 50   | 3.0570          |
| 1.7313        | 23.0769 | 75   | 4.2260          |
| 1.1646        | 30.7692 | 100  | 4.8145          |
| 0.8469        | 38.4615 | 125  | 5.0539          |
| 0.7022        | 46.1538 | 150  | 5.1803          |


### Framework versions

- PEFT 0.9.0
- Transformers 4.41.2
- Pytorch 2.1.2.post300
- Datasets 2.18.0
- Tokenizers 0.19.1