Downloads · 30 days
2
7% of all-time downloads
paligemma1000try2000
mahmoudkamal105/paligemma1000try2000
paligemma1000try2000 is a machine learning model from mahmoudkamal105. 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 other.
should probably proofread and complete it, then remove this comment. --
All-time downloads
27
Public
Repo size
275 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt157 MB · 40%
At a glance
- Library
- peft
- License
- other
- Access
- Public
- Created
- Oct 15, 2024
- Updated
- Oct 15, 2024
- SHA
- 8800b5f9
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. -->
train_2024-10-15-07-48-53
This model is a fine-tuned version of google/paligemma-3b-pt-448 on the my_chartQA dataset. It achieves the following results on the evaluation set:
- Loss: 0.0001
- Num Input Tokens Seen: 6043392
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
|---|---|---|---|---|
| 0.0006 | 1.6162 | 100 | 0.0002 | 3302400 |
Framework versions
- PEFT 0.12.0
- Transformers 4.45.2
- Pytorch 2.4.1+cu121
- Datasets 2.21.0
- Tokenizers 0.20.1
- Library
- peft
- License
- other
- Created
- Oct 15, 2024
- Updated
- Oct 15, 2024