---
library_name: transformers
license: bsd-3-clause
base_model: Salesforce/blip-vqa-base
tags:
- generated_from_trainer
model-index:
- name: blip2-finetuned-ai2d
  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. -->

# blip2-finetuned-ai2d

This model is a fine-tuned version of [Salesforce/blip-vqa-base](https://huggingface.co/Salesforce/blip-vqa-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3500

## 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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 8
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.3867        | 1.4380 | 50   | 0.3808          |
| 0.3498        | 2.8759 | 100  | 0.3536          |
| 0.3525        | 4.2920 | 150  | 0.3529          |
| 0.3497        | 5.7299 | 200  | 0.3553          |
| 0.321         | 7.1460 | 250  | 0.3500          |


### Framework versions

- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0