Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
medgemma-4b-v6 – AI Model by santoshtec146 | AlphaNeural AI
You can deploy this model and start earning money today!
santoshtec146
/
medgemma-4b-v6
like
0
peft
safetensors
adapter
lora
transformers
unsloth
text-generation
conversational
unsloth/medgemma-4b-it
other
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
medgemma-4b-v6
This model is a fine-tuned version of
unsloth/medgemma-4b-it
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 1.1172
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: 0.0002
train_batch_size: 64
eval_batch_size: 4
seed: 42
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 2
Training results
Training Loss
Epoch
Step
Validation Loss
0.7526
0.2703
500
1.0008
0.6905
0.5405
1000
1.0087
0.642
0.8108
1500
1.1368
0.5022
1.0811
2000
1.1172
Framework versions
PEFT 0.18.0
Transformers 4.57.3
Pytorch 2.9.1+cu128
Datasets 4.3.0
Tokenizers 0.22.1
