Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
finetuned_paligemma_health – AI Model by Leodid | AlphaNeural AI
You can deploy this model and start earning money today!
Leodid
/
finetuned_paligemma_health
like
0
peft
tensorboard
safetensors
adapter
lora
transformers
text-generation
google/paligemma-3b-pt-224
gemma
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
finetuned_paligemma_health
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: 2.6929
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: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3
Training results
Training Loss
Epoch
Step
Validation Loss
2.8558
0.4171
200
2.8332
2.8183
0.8342
400
2.7632
2.7436
1.2503
600
2.7337
2.7613
1.6674
800
2.7132
2.6521
2.0834
1000
2.7031
2.6197
2.5005
1200
2.6969
2.6083
2.9176
1400
2.6929
Framework versions
PEFT 0.17.1
Transformers 4.57.0
Pytorch 2.8.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1
