DUAL-GPO
/

phi-2-gpo-renew2-b0.001-log-i0

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

phi-2-gpo-renew2-b0.001-log-i0 / train_results.json

BraylonDash's picture

Model save

d49272b verified about 2 months ago

raw history blame contribute delete

No virus

196 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.04185271042490998,
	"train_runtime": 56342.1754,
	"train_samples": 61135,
	"train_samples_per_second": 1.085,
	"train_steps_per_second": 0.068
	}