Hugging Face's logo

seyviour
/
paligemma_vqav2_2

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
paligemma_vqav2_2 / README.md
seyviour's picture
seyviour
seyviour/paligemma_VQAv2_enel645_2
b8d840d verified
preview code
|
raw
history blame contribute delete
1.44 kB
metadata
library_name: peft
license: gemma
base_model: google/paligemma-3b-pt-224
tags:
  - generated_from_trainer
model-index:
  - name: paligemma_vqav2_2
    results: []

paligemma_vqav2_2

This model is a fine-tuned version of google/paligemma-3b-pt-224 on an unknown dataset.

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: 4e-05
  • train_batch_size: 3
  • eval_batch_size: 3
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 12
  • optimizer: Use OptimizerNames.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: 2
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
No log 0.9888 66 1.0517

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.1
  • Pytorch 2.4.0.post301
  • Datasets 2.14.4
  • Tokenizers 0.20.1