metadata
library_name: peft
license: gemma
base_model: google/paligemma-3b-pt-224
tags:
- generated_from_trainer
model-index:
- name: paligemma_vqav2_1
results: []
paligemma_vqav2_1
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: 0.4158
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_HF 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 |
|---|---|---|---|
| No log | 0.9976 | 318 | 0.3705 |
| 1.1065 | 1.9984 | 637 | 0.2753 |
| 1.1065 | 2.9992 | 956 | 0.2679 |
| 0.2268 | 4.0 | 1275 | 0.2718 |
| 0.1558 | 4.9976 | 1593 | 0.2638 |
| 0.1558 | 5.9984 | 1912 | 0.2820 |
| 0.1057 | 6.9992 | 2231 | 0.3018 |
| 0.0623 | 8.0 | 2550 | 0.3286 |
| 0.0623 | 8.9976 | 2868 | 0.3621 |
| 0.0325 | 9.9984 | 3187 | 0.3919 |
| 0.0191 | 10.9992 | 3506 | 0.4125 |
| 0.0191 | 11.9718 | 3816 | 0.4158 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.2
- Pytorch 2.1.2.post304
- Datasets 3.1.0
- Tokenizers 0.20.3