metadata
library_name: peft
license: mit
base_model: google/paligemma-3b-pt-224
tags:
- generated_from_trainer
- vlm
- PaliGemma
- LoRA
- PEFT
model-index:
- name: paligemma_intersections
results: []
datasets:
- ariG23498/intersection-dataset
language:
- en
Model description
This model is a fine-tuned version of google/paligemma-3b-pt-224 on ariG23498/intersection-dataset.
Training procedure
Finetuning done using (LoRA) PEFT method. Rank = 8 choosen.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_BNB 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: 2
- num_epochs: 2
Framework versions
- PEFT 0.14.0
- Transformers 4.50.2
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1