YYYYYYibo
/

nash_dpo_iter_3

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

nash_dpo_iter_3 / all_results.json

YYYYYYibo's picture

Model save

7915532 verified 6 months ago

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.6320372126319191,
	"train_runtime": 7509.7506,
	"train_samples": 21135,
	"train_samples_per_second": 2.814,
	"train_steps_per_second": 0.022
	}