Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
christti
/
clip-vit-bert-coco
like
0
Feature Extraction
Transformers
Safetensors
ydshieh/coco_dataset_script
vision-text-dual-encoder
Generated from Trainer
Inference Endpoints
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
e81f6c4
clip-vit-bert-coco
/
all_results.json
christti
End of training
fec648c
verified
11 months ago
raw
Copy download link
history
blame
Safe
144 Bytes
{
"eval_loss"
:
2.8376755714416504
,
"eval_runtime"
:
404.3846
,
"eval_samples_per_second"
:
61.857
,
"eval_steps_per_second"
:
1.934
}