E-Rong
/

til-26-ae-agent

Model card Files Files and versions

til-26-ae-agent / phase3_eval_1100000.txt

E-Rong's picture

push phase 3 training

6dc6669 verified 3 months ago

History Blame Contribute Delete

60 Bytes

	Stage: random
	Step: 1100000
	WinRate: 95.0%
	AvgReward: 205.0