dball
/

zephyr-7b-dpo-qlora

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

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

dball's picture

Model save

30e4e51 verified 11 months ago

192 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.539378755131,
	"train_runtime": 172496.8646,
	"train_samples": 61135,
	"train_samples_per_second": 0.354,
	"train_steps_per_second": 0.044
	}