Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
version1_2-5epochs-ft – AI Model by 3sara | AlphaNeural AI
You can deploy this model and start earning money today!
3sara
/
version1_2-5epochs-ft
like
0
peft
safetensors
colpali-finetuned
generated_from_trainer
vidore/colpaligemma-3b-pt-448-base
adapter
gemma
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
version1_2-5epochs-from_base
This model is a fine-tuned version of
vidore/colpaligemma-3b-pt-448-base
on the 3sara/validated_colpali_italian_documents_with_images dataset.
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: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use adamw_torch 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: 100
num_epochs: 5
Training results
Training Loss
Epoch
Step
Validation Loss
No log
0.0103
1
0.3841
Framework versions
PEFT 0.15.2
Transformers 4.51.3
Pytorch 2.7.1+cu126
Datasets 3.6.0
Tokenizers 0.21.1
