DUAL-GPO
/

phi-2-gpo-test-iter-1

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

phi-2-gpo-test-iter-1 / train_results.json

BraylonDash's picture

Model save

c00337c verified 3 months ago

raw history blame contribute delete

No virus

195 Bytes

	{
	"epoch": 1.33,
	"train_loss": 0.0015329468587879092,
	"train_runtime": 7.3105,
	"train_samples": 30567,
	"train_samples_per_second": 2.736,
	"train_steps_per_second": 0.274
	}