Weili
/

image-captioning-output

Image-Text-to-Text

vision-encoder-decoder

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

image-captioning-output / train_results.json

Weili's picture

End of training

53c9b1d about 2 years ago

history blame contribute delete

208 Bytes

	{
	"epoch": 3.0,
	"total_flos": 3.2211655354615726e+18,
	"train_loss": 0.2087684871917057,
	"train_runtime": 2567.1485,
	"train_samples_per_second": 6.916,
	"train_steps_per_second": 0.864
	}