DUAL-GPO
/

phi-2-gpo-renew2-b0.001-extra-i1

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

phi-2-gpo-renew2-b0.001-extra-i1 / train_results.json

BraylonDash's picture

Model save

b611c76 verified about 2 months ago

raw history blame contribute delete

No virus

196 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.07849642387894454,
	"train_runtime": 13138.6455,
	"train_samples": 61135,
	"train_samples_per_second": 1.142,
	"train_steps_per_second": 0.071
	}