DUAL-GPO
/

zephyr-7b-ipo-qlora-v0

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

zephyr-7b-ipo-qlora-v0 / train_results.json

lole25's picture

Model save

4269203 verified 9 months ago

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 1830.215161976219,
	"train_runtime": 182270.758,
	"train_samples": 61135,
	"train_samples_per_second": 0.335,
	"train_steps_per_second": 0.084
	}