DUAL-GPO
/

zephyr-7b-gpo-v1-i2

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

zephyr-7b-gpo-v1-i2 / all_results.json

lole25's picture

Model save

d3dbf8e verified 6 months ago

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.08193727386991183,
	"train_runtime": 13050.0697,
	"train_samples": 12000,
	"train_samples_per_second": 0.92,
	"train_steps_per_second": 0.23
	}