---
base_model: google/paligemma-3b-mix-448
datasets:
- khatt-paragraphs
library_name: peft
license: gemma
tags:
- generated_from_trainer
model-index:
- name: paligemma_khatt_paragraph_mix_448_ep1_r128
  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. -->

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/ahmed-heakl/huggingface/runs/x0hpb71u)
# paligemma_khatt_paragraph_mix_448_ep1_r128

This model is a fine-tuned version of [google/paligemma-3b-mix-448](https://huggingface.co/google/paligemma-3b-mix-448) on the khatt-paragraphs dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6759

## 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: 1e-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 2
- num_epochs: 1

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 2.5113        | 0.1014 | 100  | 2.4764          |
| 2.1232        | 0.2027 | 200  | 2.1948          |
| 1.8843        | 0.3041 | 300  | 2.0064          |
| 1.815         | 0.4055 | 400  | 1.8942          |
| 1.8574        | 0.5068 | 500  | 1.8223          |
| 1.6986        | 0.6082 | 600  | 1.7674          |
| 1.749         | 0.7096 | 700  | 1.7335          |
| 1.7122        | 0.8109 | 800  | 1.7025          |
| 1.61          | 0.9123 | 900  | 1.6759          |


### Framework versions

- PEFT 0.11.1
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1