Downloads · 30 days
4
15% of all-time downloads
paligemma_vqav2_warnup
RoyRoyRpy/paligemma_vqav2_warnup
paligemma_vqav2_warnup is a machine learning model from RoyRoyRpy. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as gemma.
should probably proofread and complete it, then remove this comment. --
All-time downloads
27
Public
Repo size
5.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.4 GB · 98%
At a glance
- Library
- peft
- License
- gemma
- Access
- Public
- Created
- Oct 21, 2024
- Updated
- Oct 21, 2024
- SHA
- e45b81a5
Base models
Model card
From the Hugging Face model README
<!-- 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. -->
paligemma_vqav2_warnup
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: 0.8534
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: 10
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 40
- 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: 1000
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.0325 | 0.3125 | 100 | 7.1622 |
| 6.5146 | 0.625 | 200 | 5.6221 |
| 4.4912 | 0.9375 | 300 | 3.4696 |
| 3.2824 | 1.25 | 400 | 2.6386 |
| 2.6828 | 1.5625 | 500 | 2.1185 |
| 2.2276 | 1.875 | 600 | 1.7020 |
| 1.9293 | 2.1875 | 700 | 1.4613 |
| 1.7957 | 2.5 | 800 | 1.3059 |
| 1.6281 | 2.8125 | 900 | 1.1815 |
| 1.4253 | 3.125 | 1000 | 1.1008 |
| 1.4404 | 3.4375 | 1100 | 1.0513 |
| 1.4239 | 3.75 | 1200 | 1.0156 |
| 1.2985 | 4.0625 | 1300 | 0.9709 |
| 1.243 | 4.375 | 1400 | 0.9393 |
| 1.2105 | 4.6875 | 1500 | 0.9237 |
| 1.2035 | 5.0 | 1600 | 0.9088 |
| 1.0704 | 5.3125 | 1700 | 0.8927 |
| 1.0891 | 5.625 | 1800 | 0.8735 |
| 1.0861 | 5.9375 | 1900 | 0.8598 |
| 0.9853 | 6.25 | 2000 | 0.8530 |
| 0.9866 | 6.5625 | 2100 | 0.8392 |
| 1.0206 | 6.875 | 2200 | 0.8399 |
| 0.8914 | 7.1875 | 2300 | 0.8293 |
| 0.9062 | 7.5 | 2400 | 0.8325 |
| 0.8579 | 7.8125 | 2500 | 0.8147 |
| 0.828 | 8.125 | 2600 | 0.8267 |
| 0.7969 | 8.4375 | 2700 | 0.8321 |
| 0.8175 | 8.75 | 2800 | 0.8179 |
| 0.7948 | 9.0625 | 2900 | 0.8356 |
| 0.7221 | 9.375 | 3000 | 0.8104 |
| 0.7124 | 9.6875 | 3100 | 0.8266 |
| 0.7199 | 10.0 | 3200 | 0.8143 |
| 0.6601 | 10.3125 | 3300 | 0.8399 |
| 0.6517 | 10.625 | 3400 | 0.8415 |
| 0.6509 | 10.9375 | 3500 | 0.8221 |
| 0.5981 | 11.25 | 3600 | 0.8582 |
| 0.6011 | 11.5625 | 3700 | 0.8481 |
| 0.5756 | 11.875 | 3800 | 0.8534 |
Framework versions
- PEFT 0.13.0
- Transformers 4.46.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0
- Library
- peft
- License
- gemma
- Created
- Oct 21, 2024
- Updated
- Oct 21, 2024