DUAL-GPO-2
/

phi-2-ipo-test-iter-0

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

phi-2-ipo-test-iter-0 / train_results.json

BraylonDash's picture

Model save

415f17b verified 3 months ago

raw history blame contribute delete

No virus

196 Bytes

	{
	"epoch": 3.99,
	"train_loss": 1918.4646684695513,
	"train_runtime": 14252.7073,
	"train_samples": 30567,
	"train_samples_per_second": 1.403,
	"train_steps_per_second": 0.088
	}