YYYYYYibo
/

nash_dpo_doff_no_golden_iter_1

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

nash_dpo_doff_no_golden_iter_1 / train_results.json

YYYYYYibo's picture

Model save

f9aa23f verified 6 months ago

185 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.0,
	"train_runtime": 0.012,
	"train_samples": 19600,
	"train_samples_per_second": 1639445.565,
	"train_steps_per_second": 12797.713
	}