gagan3012
/

ViTGPT2_VW

Image-Text-to-Text

vision-encoder-decoder

Generated from Trainer

Model card Files Files and versions

ViTGPT2_VW / train_results.json

gagan3012's picture

End of training

6ab563d about 4 years ago

172 Bytes

	{
	"epoch": 0.04,
	"train_loss": 0.0033295607640092873,
	"train_runtime": 303.4327,
	"train_samples_per_second": 386.099,
	"train_steps_per_second": 48.264
	}