Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
pavement
/
clip-roberta-finetuned
like
0
Feature Extraction
Transformers
TensorBoard
Safetensors
ydshieh/coco_dataset_script
vision-text-dual-encoder
Generated from Trainer
Inference Endpoints
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
c9a8289
clip-roberta-finetuned
/
train_results.json
pavement
End of training
c9a8289
verified
7 months ago
raw
Copy download link
history
blame
Safe
185 Bytes
{
"epoch"
:
3.0
,
"total_flos"
:
40055184000000.0
,
"train_loss"
:
0.0
,
"train_runtime"
:
99.4754
,
"train_samples_per_second"
:
3.016
,
"train_steps_per_second"
:
3.016
}