|
|
--- |
|
|
library_name: transformers |
|
|
license: gemma |
|
|
base_model: google/paligemma-3b-pt-224 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: results_solo_good_fold_3_pt |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# results_solo_good_fold_3_pt |
|
|
|
|
|
This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.1706 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
|
| 0.2222 | 1.0 | 2091 | 0.1874 | |
|
|
| 0.2177 | 2.0 | 4182 | 0.1752 | |
|
|
| 0.1985 | 3.0 | 6273 | 0.1770 | |
|
|
| 0.2127 | 4.0 | 8364 | 0.1783 | |
|
|
| 0.2038 | 5.0 | 10455 | 0.1725 | |
|
|
| 0.1984 | 6.0 | 12546 | 0.1706 | |
|
|
| 0.1982 | 7.0 | 14637 | 0.1723 | |
|
|
| 0.203 | 8.0 | 16728 | 0.1725 | |
|
|
| 0.1915 | 9.0 | 18819 | 0.1724 | |
|
|
| 0.1967 | 10.0 | 20910 | 0.1715 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.48.3 |
|
|
- Pytorch 2.1.2+cu121 |
|
|
- Tokenizers 0.21.0 |
|
|
|
