DUAL-GPO
/

phi-2-gpo-iter-0

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

phi-2-gpo-iter-0 / train_results.json

lole25's picture

Model save

503f00f verified 3 months ago

raw history blame contribute delete

No virus

196 Bytes

	{
	"epoch": 1.99,
	"train_loss": 0.001956978782771095,
	"train_runtime": 290.9594,
	"train_samples": 61135,
	"train_samples_per_second": 6.874,
	"train_steps_per_second": 0.426
	}