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 / eval_results.json

jiequan's picture

End of training

9d425d2 verified 7 months ago

162 Bytes

	{
	"epoch": 3.0,
	"eval_loss": 1.6024179458618164,
	"eval_runtime": 220.1844,
	"eval_samples_per_second": 96.905,
	"eval_steps_per_second": 0.191
	}