bilbo991
/

clip-homer

Feature Extraction

vision-text-dual-encoder

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

clip-homer / train_results.json

bilbo991's picture

End of training

574f885 over 1 year ago

167 Bytes

	{
	"epoch": 3.0,
	"train_loss": 1.4532607096354166,
	"train_runtime": 6576.4517,
	"train_samples_per_second": 45.617,
	"train_steps_per_second": 1.426
	}