DUAL-GPO
/

phi-2-gpo-renew2-b0.01-log-i0

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

phi-2-gpo-renew2-b0.01-log-i0 / train_results.json

BraylonDash's picture

Model save

dca0b81 verified about 2 months ago

raw history blame contribute delete

No virus

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.691200782103989,
	"train_runtime": 55857.7878,
	"train_samples": 61135,
	"train_samples_per_second": 1.094,
	"train_steps_per_second": 0.068
	}