DUAL-GPO
/

zephyr-7b-gpo-v8-i1

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

zephyr-7b-gpo-v8-i1 / all_results.json

lole25's picture

Model save

f90326a verified 6 months ago

196 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.14340321629899808,
	"train_runtime": 34860.3009,
	"train_samples": 33340,
	"train_samples_per_second": 0.956,
	"train_steps_per_second": 0.239
	}