paligemma_vqav2_5
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: 1.3111
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: 0.01
- 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 | 1.3603 |
| 3.8993 | 1.9984 | 637 | 1.4898 |
| 3.8993 | 2.9992 | 956 | 1.4614 |
| 1.4292 | 4.0 | 1275 | 1.3704 |
| 1.3891 | 4.9976 | 1593 | 1.4197 |
| 1.3891 | 5.9984 | 1912 | 1.3354 |
| 1.3778 | 6.9992 | 2231 | 1.3378 |
| 1.352 | 8.0 | 2550 | 1.3342 |
| 1.352 | 8.9976 | 2868 | 1.3289 |
| 1.3392 | 9.9984 | 3187 | 1.3175 |
| 1.3266 | 10.9992 | 3506 | 1.3176 |
| 1.3266 | 11.9718 | 3816 | 1.3111 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.2
- Pytorch 2.1.2.post304
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 0
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.
Model tree for palicoqiqi/paligemma_vqav2_5
Base model
google/paligemma-3b-pt-224