Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
finetuned_paligemma_riscm_full – AI Model by caglarmert | AlphaNeural AI
You can deploy this model and start earning money today!
caglarmert
/
finetuned_paligemma_riscm_full
like
0
peft
tensorboard
safetensors
generated_from_trainer
en
caglarmert/full_riscm
google/paligemma-3b-pt-224
adapter
gemma
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
finetuned_paligemma_riscm_full
This model is a fine-tuned version of
google/paligemma-3b-pt-224
on
caglarmert/full_risc
.
Model description
Fine tuned Paligemma with 10% of the data.
Intended uses & limitations
Trained for only 2 epoch.
Training and evaluation data
10% of the data, no evaluation
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 2e-05
train_batch_size: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_8BIT 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: 2
Training results
Framework versions
PEFT 0.15.2
Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1
