ddanshin
/

clip-roberta-finetuned

Feature Extraction

vision-text-dual-encoder

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

clip-roberta-finetuned / all_results.json

ddanshin's picture

End of training

043a8b5 11 months ago

raw history blame contribute delete

No virus

312 Bytes

	{
	"epoch": 3.0,
	"eval_loss": 1.5849734544754028,
	"eval_runtime": 152.5492,
	"eval_samples_per_second": 163.973,
	"eval_steps_per_second": 0.642,
	"train_loss": 0.3111796811702326,
	"train_runtime": 14391.5786,
	"train_samples_per_second": 123.354,
	"train_steps_per_second": 0.482
	}