metadata
library_name: transformers
license: gemma
base_model: google/paligemma-3b-pt-224
tags:
- generated_from_trainer
model-index:
- name: results_solo_good_fold_4_pt
results: []
results_solo_good_fold_4_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: 0.1700
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 |
|---|---|---|---|
| 0.2176 | 1.0 | 2091 | 0.1707 |
| 0.1996 | 2.0 | 4182 | 0.1760 |
| 0.2025 | 3.0 | 6273 | 0.1760 |
| 0.1979 | 4.0 | 8364 | 0.1781 |
| 0.198 | 5.0 | 10455 | 0.1706 |
| 0.1942 | 6.0 | 12546 | 0.1710 |
| 0.1968 | 7.0 | 14637 | 0.1703 |
| 0.1949 | 8.0 | 16728 | 0.1700 |
| 0.1937 | 9.0 | 18819 | 0.1702 |
| 0.1939 | 10.0 | 20910 | 0.1704 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.1.2+cu121
- Tokenizers 0.21.0