DUAL-GPO
/

phi-2-dpo-test-iter-0

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

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

BraylonDash's picture

Model save

9237faa verified 3 months ago

raw history blame contribute delete

No virus

198 Bytes

	{
	"epoch": 3.99,
	"train_loss": 9.35627439654733e-05,
	"train_runtime": 14053.8323,
	"train_samples": 61135,
	"train_samples_per_second": 1.423,
	"train_steps_per_second": 0.089
	}