Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
paligemma-3b-224-vizwiz – AI Model by nanom | AlphaNeural AI
You can deploy this model and start earning money today!
nanom
/
paligemma-3b-224-vizwiz
like
0
transformers
tensorboard
safetensors
paligemma
image-to-text
generated_from_trainer
google/paligemma-3b-pt-224
finetune
gemma
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
ckpts_store
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: 0.9315
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: 4
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 2
num_epochs: 3
Training results
Training Loss
Epoch
Step
Validation Loss
0.7087
0.9972
267
0.8475
0.3908
1.9981
535
0.8885
0.1561
2.9916
801
0.9315
Framework versions
Transformers 4.41.1
Pytorch 2.2.2+cu121
Datasets 2.19.1
Tokenizers 0.19.1
