DUAL-GPO
/

zephyr-7b-dpo-qlora-v1

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

zephyr-7b-dpo-qlora-v1 / train_results.json

lole25's picture

Model save

94ec2f2 verified 7 months ago

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.5233479982519362,
	"train_runtime": 176392.38,
	"train_samples": 61135,
	"train_samples_per_second": 0.347,
	"train_steps_per_second": 0.087
	}