YYYYYYibo
/

vanilla_dpo_iter_6

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

vanilla_dpo_iter_6 / train_results.json

YYYYYYibo's picture

Model save

e3b5ca8 verified 8 months ago

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.5778744011214285,
	"train_runtime": 7573.0657,
	"train_samples": 21135,
	"train_samples_per_second": 2.791,
	"train_steps_per_second": 0.022
	}