EllieS
/

Temp-L1-SFT-L2-DPO

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

Temp-L1-SFT-L2-DPO / train_results.json

EllieS's picture

Model save

5bbba36 verified 8 months ago

195 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.04242442899794605,
	"train_runtime": 8772.4234,
	"train_samples": 16017,
	"train_samples_per_second": 1.826,
	"train_steps_per_second": 0.456
	}