---
library_name: transformers
license: gemma
base_model: vidore/colpaligemma-3b-pt-448-base
tags:
- colpali
- generated_from_trainer
model-index:
- name: finetune_colpali_v1_2-german_ver2-4bit
  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. -->

# finetune_colpali_v1_2-german_ver2-4bit

This model is a fine-tuned version of [vidore/colpaligemma-3b-pt-448-base](https://huggingface.co/vidore/colpaligemma-3b-pt-448-base) on the German_docx dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0498
- Model Preparation Time: 0.0105

## 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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Model Preparation Time |
|:-------------:|:------:|:----:|:---------------:|:----------------------:|
| No log        | 0.0816 | 1    | 0.4190          | 0.0105                 |
| 1.6183        | 0.8163 | 10   | 0.3540          | 0.0105                 |
| 1.4293        | 1.6327 | 20   | 0.2496          | 0.0105                 |
| 0.9161        | 2.4490 | 30   | 0.1681          | 0.0105                 |
| 0.6           | 3.2653 | 40   | 0.1203          | 0.0105                 |
| 0.5019        | 4.0816 | 50   | 0.0785          | 0.0105                 |
| 0.3168        | 4.8980 | 60   | 0.0498          | 0.0105                 |


### Framework versions

- Transformers 4.46.1
- Pytorch 2.3.1
- Datasets 3.1.0
- Tokenizers 0.20.1