Downloads · 30 days
2
1% of all-time downloads
paligemma_racer_with_callback
mateoguaman/paligemma_racer_with_callback
paligemma_racer_with_callback is a image-text-to-text model from mateoguaman. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as gemma.
should probably proofread and complete it, then remove this comment. --
All-time downloads
139
Public
Parameters
2.9B
140 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.8 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- gemma
- Model type
- paligemma
- Access
- Public
- Created
- Dec 2, 2024
- Updated
- Dec 2, 2024
- SHA
- b3a71f06
Try a prompt
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_racer_with_callback
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: 2.7534
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: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use 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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 14.3458 | 0.0837 | 100 | 11.3555 |
| 5.8308 | 0.1674 | 200 | 5.3573 |
| 4.7279 | 0.2512 | 300 | 4.4599 |
| 4.2547 | 0.3349 | 400 | 4.0549 |
| 3.8251 | 0.4186 | 500 | 3.7226 |
| 3.5905 | 0.5023 | 600 | 3.4916 |
| 3.4127 | 0.5860 | 700 | 3.3164 |
| 3.2567 | 0.6697 | 800 | 3.2098 |
| 3.1429 | 0.7535 | 900 | 3.0517 |
| 3.0571 | 0.8372 | 1000 | 3.0442 |
| 2.9557 | 0.9209 | 1100 | 2.9618 |
| 2.8957 | 1.0046 | 1200 | 2.9191 |
| 2.8354 | 1.0883 | 1300 | 2.8804 |
| 2.7862 | 1.1720 | 1400 | 2.8233 |
| 2.7565 | 1.2558 | 1500 | 2.8176 |
| 2.7191 | 1.3395 | 1600 | 2.7984 |
| 2.7381 | 1.4232 | 1700 | 2.7764 |
| 2.7112 | 1.5069 | 1800 | 2.7780 |
| 2.6708 | 1.5906 | 1900 | 2.7629 |
| 2.6919 | 1.6743 | 2000 | 2.7580 |
| 2.6809 | 1.7581 | 2100 | 2.7595 |
| 2.6524 | 1.8418 | 2200 | 2.7533 |
| 2.6527 | 1.9255 | 2300 | 2.7534 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1
- Datasets 3.1.0
- Tokenizers 0.20.3
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- paligemma
- License
- gemma
- Created
- Dec 2, 2024
- Updated
- Dec 2, 2024