paligemmafinetune1
This model is a fine-tuned version of google/paligemma-3b-pt-224 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4436
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT 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: 12
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 24.2038 | 1.0 | 37 | 4.3750 |
| 12.9412 | 2.0 | 74 | 2.6652 |
| 9.258 | 3.0 | 111 | 2.1382 |
| 7.6493 | 4.0 | 148 | 1.8650 |
| 6.6366 | 5.0 | 185 | 1.6935 |
| 5.8271 | 6.0 | 222 | 1.5854 |
| 5.2018 | 7.0 | 259 | 1.5177 |
| 4.6514 | 8.0 | 296 | 1.4738 |
| 4.1935 | 9.0 | 333 | 1.4556 |
| 3.8422 | 10.0 | 370 | 1.4444 |
| 3.6184 | 11.0 | 407 | 1.4451 |
| 3.7232 | 11.6849 | 432 | 1.4436 |
Framework versions
- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.5.1+cu121
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- 29
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for RodrigoR07/paligemmafinetune1
Base model
google/paligemma-3b-pt-224