DUAL-GPO
/

zephyr-7b-gpo-u3-i1

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

zephyr-7b-gpo-u3-i1 / train_results.json

lole25's picture

Model save

a7d8dc6 verified 3 months ago

raw history blame contribute delete

No virus

195 Bytes

	{
	"epoch": 5.0,
	"train_loss": 0.3515237546205521,
	"train_runtime": 12848.6235,
	"train_samples": 61135,
	"train_samples_per_second": 0.389,
	"train_steps_per_second": 0.097
	}