gagan3012
/

ViTGPT2_VW

Image-Text-to-Text

vision-encoder-decoder

Generated from Trainer

Model card Files Files and versions

ViTGPT2_VW / eval_results.json

gagan3012's picture

End of training

6ab563d about 4 years ago

164 Bytes

	{
	"epoch": 0.04,
	"eval_loss": 0.07713703066110611,
	"eval_runtime": 761.1334,
	"eval_samples_per_second": 50.911,
	"eval_steps_per_second": 6.364
	}