YYYYYYibo
/

two_agent_1_epoch_2_dpo_iter_6

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

two_agent_1_epoch_2_dpo_iter_6 / train_results.json

YYYYYYibo's picture

Model save

f8e7726 verified 6 months ago

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.6908076347726764,
	"train_runtime": 32496.9517,
	"train_samples": 21135,
	"train_samples_per_second": 0.65,
	"train_steps_per_second": 0.005
	}