DUAL-GPO
/

phi-2-gpo-test-iter-0

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

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

BraylonDash's picture

Model save

0e6ceac verified 3 months ago

raw history blame contribute delete

No virus

195 Bytes

	{
	"epoch": 2.0,
	"train_loss": 0.00012263256940059364,
	"train_runtime": 3.7437,
	"train_samples": 30567,
	"train_samples_per_second": 2.137,
	"train_steps_per_second": 0.534
	}