zhangsj0722
/

E-GRPO

Model card Files Files and versions

xet

Community

zhangsj0722 commited on Nov 13, 2025

Commit

9510732

verified ·

1 Parent(s): 40bb282

Upload first_4_step_hps_reward.txt with huggingface_hub

Browse files

Files changed (1) hide show

first_4_step_hps_reward.txt +304 -0

first_4_step_hps_reward.txt ADDED Viewed

	@@ -0,0 +1,304 @@

+0.295440673828125
+0.295440673828125
+0.26861572265625
+0.2981758117675781
+0.2970771789550781
+0.2967567443847656
+0.30367279052734375
+0.2960090637207031
+0.29532623291015625
+0.3072547912597656
+0.30632781982421875
+0.3070831298828125
+0.3064765930175781
+0.3050270080566406
+0.3067665100097656
+0.308013916015625
+0.3174781799316406
+0.31272125244140625
+0.3077430725097656
+0.321380615234375
+0.3144111633300781
+0.312835693359375
+0.3090629577636719
+0.3079795837402344
+0.3195533752441406
+0.31896209716796875
+0.3082389831542969
+0.3218231201171875
+0.32581329345703125
+0.3259735107421875
+0.3134613037109375
+0.3098411560058594
+0.32938385009765625
+0.3107032775878906
+0.33098602294921875
+0.310516357421875
+0.3190765380859375
+0.32004547119140625
+0.3234672546386719
+0.3268280029296875
+0.3316688537597656
+0.3175201416015625
+0.3214569091796875
+0.32611083984375
+0.31966400146484375
+0.32807159423828125
+0.32651519775390625
+0.3176918029785156
+0.3373870849609375
+0.3192634582519531
+0.3441314697265625
+0.3244590759277344
+0.32989501953125
+0.32451629638671875
+0.3368988037109375
+0.3337211608886719
+0.3284263610839844
+0.33992767333984375
+0.34723663330078125
+0.3366546630859375
+0.3322257995605469
+0.33774566650390625
+0.33489227294921875
+0.33254241943359375
+0.33575439453125
+0.33107757568359375
+0.34405517578125
+0.33463287353515625
+0.3231697082519531
+0.34774017333984375
+0.33966064453125
+0.3411216735839844
+0.33953094482421875
+0.34067535400390625
+0.33902740478515625
+0.33809661865234375
+0.34041595458984375
+0.349639892578125
+0.3338203430175781
+0.342681884765625
+0.3357391357421875
+0.3415679931640625
+0.34828948974609375
+0.34635162353515625
+0.34454345703125
+0.34494781494140625
+0.34958648681640625
+0.346099853515625
+0.3408317565917969
+0.349395751953125
+0.3497772216796875
+0.3567047119140625
+0.348419189453125
+0.3372802734375
+0.35219573974609375
+0.34393310546875
+0.35323333740234375
+0.3513031005859375
+0.34980010986328125
+0.3513641357421875
+0.34941864013671875
+0.344757080078125
+0.35382843017578125
+0.348968505859375
+0.35366058349609375
+0.3462982177734375
+0.3499908447265625
+0.357818603515625
+0.3522796630859375
+0.36529541015625
+0.3456878662109375
+0.3528289794921875
+0.36222076416015625
+0.3612518310546875
+0.35004425048828125
+0.35205078125
+0.3574371337890625
+0.35012054443359375
+0.36109161376953125
+0.35620880126953125
+0.3551483154296875
+0.3553047180175781
+0.3611106872558594
+0.34571075439453125
+0.35626983642578125
+0.35295867919921875
+0.36067962646484375
+0.35892486572265625
+0.36312103271484375
+0.3546600341796875
+0.358642578125
+0.3537445068359375
+0.34883880615234375
+0.3633880615234375
+0.36563873291015625
+0.35894012451171875
+0.35337066650390625
+0.34784698486328125
+0.355682373046875
+0.34955596923828125
+0.349822998046875
+0.35589599609375
+0.35584259033203125
+0.3572273254394531
+0.36414337158203125
+0.35028076171875
+0.36144256591796875
+0.3659210205078125
+0.36859130859375
+0.3707427978515625
+0.3687744140625
+0.35467529296875
+0.3657073974609375
+0.35693359375
+0.36295318603515625
+0.3542976379394531
+0.3443603515625
+0.3673858642578125
+0.3533782958984375
+0.35517120361328125
+0.35831451416015625
+0.35455322265625
+0.36553955078125
+0.36977386474609375
+0.3651123046875
+0.36591339111328125
+0.3739471435546875
+0.36463165283203125
+0.36267852783203125
+0.35863494873046875
+0.3687286376953125
+0.3679962158203125
+0.367095947265625
+0.3668365478515625
+0.383544921875
+0.360626220703125
+0.3569984436035156
+0.3648834228515625
+0.37885284423828125
+0.36974334716796875
+0.3653411865234375
+0.364898681640625
+0.35491180419921875
+0.3631591796875
+0.3721771240234375
+0.36554718017578125
+0.36666107177734375
+0.373077392578125
+0.36664581298828125
+0.36548614501953125
+0.36631011962890625
+0.36809539794921875
+0.3772430419921875
+0.36452484130859375
+0.3717193603515625
+0.36934661865234375
+0.370452880859375
+0.36956787109375
+0.3602142333984375
+0.368865966796875
+0.372283935546875
+0.3693695068359375
+0.3623046875
+0.3682098388671875
+0.3656158447265625
+0.3691864013671875
+0.37798309326171875
+0.36455535888671875
+0.37741851806640625
+0.3779296875
+0.3729400634765625
+0.36072540283203125
+0.3682098388671875
+0.37557220458984375
+0.3739776611328125
+0.36435699462890625
+0.37041473388671875
+0.3682403564453125
+0.3660125732421875
+0.35602569580078125
+0.38251495361328125
+0.37110137939453125
+0.3636322021484375
+0.3679656982421875
+0.36474609375
+0.36743927001953125
+0.3743438720703125
+0.36177825927734375
+0.37529754638671875
+0.38401031494140625
+0.381072998046875
+0.3689117431640625
+0.36994171142578125
+0.36365509033203125
+0.3684234619140625
+0.37664794921875
+0.37192535400390625
+0.37445831298828125
+0.38455963134765625
+0.36367034912109375
+0.3696098327636719
+0.37244415283203125
+0.3745574951171875
+0.37067413330078125
+0.36008453369140625
+0.3655853271484375
+0.3704833984375
+0.3646659851074219
+0.365814208984375
+0.370880126953125
+0.37796783447265625
+0.3792877197265625
+0.3719024658203125
+0.37286376953125
+0.37134552001953125
+0.36989593505859375
+0.37999725341796875
+0.3795623779296875
+0.36771392822265625
+0.370697021484375
+0.3692169189453125
+0.3730316162109375
+0.37087249755859375
+0.36328887939453125
+0.37419891357421875
+0.36891937255859375
+0.37450408935546875
+0.37224578857421875
+0.370147705078125
+0.37357330322265625
+0.3778228759765625
+0.37863922119140625
+0.380340576171875
+0.377288818359375
+0.36902618408203125
+0.367706298828125
+0.38042449951171875
+0.37567138671875
+0.36417388916015625
+0.361846923828125
+0.3763427734375
+0.37975311279296875
+0.3698272705078125
+0.3805084228515625
+0.38370513916015625
+0.37488555908203125
+0.3761138916015625
+0.379913330078125
+0.37053680419921875
+0.3692779541015625
+0.3818359375
+0.382110595703125
+0.36019134521484375
+0.3718414306640625
+0.37381744384765625
+0.37738037109375
+0.37111663818359375
+0.39101409912109375
+0.38714599609375
+0.36930084228515625
+0.3765716552734375
+0.373992919921875
+0.37505340576171875
+0.3773651123046875