metadata
library_name: transformers
license: gemma
base_model: google/paligemma-3b-pt-224
tags:
- generated_from_trainer
model-index:
- name: results_solo_good_fold_5_pt
results: []
results_solo_good_fold_5_pt
This model is a fine-tuned version of google/paligemma-3b-pt-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1692
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- 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
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2009 | 1.0 | 2091 | 0.1753 |
| 0.1969 | 2.0 | 4182 | 0.1692 |
| 0.1833 | 3.0 | 6273 | 0.1785 |
| 0.1923 | 4.0 | 8364 | 0.1724 |
| 0.1814 | 5.0 | 10455 | 0.1761 |
| 0.185 | 6.0 | 12546 | 0.1716 |
| 0.1839 | 7.0 | 14637 | 0.1729 |
| 0.191 | 8.0 | 16728 | 0.1720 |
| 0.1881 | 9.0 | 18819 | 0.1714 |
| 0.187 | 10.0 | 20910 | 0.1719 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.1.2+cu121
- Tokenizers 0.21.0