wooseoko
/

clip-roberta-finetuned_GQA

Feature Extraction

vision-text-dual-encoder

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

clip-roberta-finetuned_GQA / train_results.json

wooseoko's picture

End of training

9610f9f almost 2 years ago

167 Bytes

	{
	"epoch": 3.0,
	"train_loss": 1.4714843301307519,
	"train_runtime": 14279.912,
	"train_samples_per_second": 73.765,
	"train_steps_per_second": 2.305
	}