Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
medsiglip-448-ft-crc100k – AI Model by anirudhsrivastava | AlphaNeural AI
You can deploy this model and start earning money today!
anirudhsrivastava
/
medsiglip-448-ft-crc100k
like
0
transformers
tensorboard
safetensors
siglip
zero-shot-image-classification
generated_from_trainer
imagefolder
google/medsiglip-448
finetune
other
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
medsiglip-448-ft-crc100k
This model is a fine-tuned version of
google/medsiglip-448
on the imagefolder dataset. It achieves the following results on the evaluation set:
Loss: 1.2713
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: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 64
optimizer: Use adamw_torch 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: 5
num_epochs: 2
Training results
Training Loss
Epoch
Step
Validation Loss
1.3465
0.3556
50
1.3722
1.3101
0.7111
100
1.3356
1.3028
1.064
150
1.2855
1.2389
1.4196
200
1.3003
1.2522
1.7751
250
1.2713
Framework versions
Transformers 4.55.4
Pytorch 2.5.1+cu121
Datasets 4.0.0
Tokenizers 0.21.0
