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 / eval_results.json

wooseoko's picture

End of training

9610f9f almost 2 years ago

162 Bytes

	{
	"epoch": 3.0,
	"eval_loss": 2.353191375732422,
	"eval_runtime": 253.6601,
	"eval_samples_per_second": 195.541,
	"eval_steps_per_second": 6.114
	}