jiequan
/

clip-roberta-finetuned

Feature Extraction

vision-text-dual-encoder

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

clip-roberta-finetuned / train_results.json

jiequan's picture

End of training

9d425d2 verified 7 months ago

208 Bytes

	{
	"epoch": 3.0,
	"total_flos": 2.368703361024e+17,
	"train_loss": 0.30996957313790807,
	"train_runtime": 15330.9154,
	"train_samples_per_second": 115.796,
	"train_steps_per_second": 0.226
	}