metadata
library_name: peft
license: gemma
base_model: google/paligemma-3b-mix-224
tags:
- generated_from_trainer
model-index:
- name: paligemma_Mix_Med_VQA_Overall
results: []
paligemma_Mix_Med_VQA_Overall
This model is a fine-tuned version of google/paligemma-3b-mix-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4923
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: 6
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6312 | 0.9079 | 217 | 0.5481 |
| 0.3645 | 1.8159 | 434 | 0.4459 |
| 0.2202 | 2.7238 | 651 | 0.4304 |
| 0.1215 | 3.6318 | 868 | 0.4490 |
| 0.0843 | 4.5397 | 1085 | 0.4923 |
Framework versions
- PEFT 0.15.2
- Transformers 4.45.1
- Pytorch 2.6.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.3