zhangsj0722
/

E-GRPO

Model card Files Files and versions

xet

Community

zhangsj0722 commited on Nov 13, 2025

Commit

6b8904d

verified ·

1 Parent(s): fa36342

Upload allstep_hps_reward.txt with huggingface_hub

Browse files

Files changed (1) hide show

allstep_hps_reward.txt +287 -0

allstep_hps_reward.txt ADDED Viewed

	@@ -0,0 +1,287 @@

+0.29024505615234375
+0.31035614013671875
+0.30260467529296875
+0.295257568359375
+0.31035614013671875
+0.29074859619140625
+0.30974578857421875
+0.3040313720703125
+0.31451416015625
+0.29689788818359375
+0.30657958984375
+0.304107666015625
+0.31475830078125
+0.3076629638671875
+0.3118743896484375
+0.314788818359375
+0.305755615234375
+0.3140411376953125
+0.31983184814453125
+0.302886962890625
+0.30861663818359375
+0.3182525634765625
+0.31224822998046875
+0.3073272705078125
+0.309356689453125
+0.324432373046875
+0.32806396484375
+0.328460693359375
+0.3112640380859375
+0.3250274658203125
+0.327667236328125
+0.3203582763671875
+0.3302764892578125
+0.3345489501953125
+0.3179168701171875
+0.3258819580078125
+0.32049560546875
+0.3231353759765625
+0.3221282958984375
+0.31212615966796875
+0.31829833984375
+0.31444549560546875
+0.338226318359375
+0.3131866455078125
+0.31711578369140625
+0.330322265625
+0.3142547607421875
+0.31957244873046875
+0.3380889892578125
+0.33135986328125
+0.3397064208984375
+0.326507568359375
+0.3359222412109375
+0.3341827392578125
+0.3295135498046875
+0.3284149169921875
+0.32765960693359375
+0.319366455078125
+0.3087120056152344
+0.3507080078125
+0.31842041015625
+0.3263702392578125
+0.3317108154296875
+0.3450164794921875
+0.32067108154296875
+0.322113037109375
+0.322509765625
+0.34234619140625
+0.322723388671875
+0.32834625244140625
+0.333648681640625
+0.32614898681640625
+0.3507232666015625
+0.32708740234375
+0.356658935546875
+0.32439422607421875
+0.3292999267578125
+0.3313751220703125
+0.331634521484375
+0.3281707763671875
+0.3465576171875
+0.325897216796875
+0.32177734375
+0.33380126953125
+0.3447723388671875
+0.3212890625
+0.3517913818359375
+0.3278045654296875
+0.323577880859375
+0.3359222412109375
+0.3493804931640625
+0.3450775146484375
+0.328125
+0.33392333984375
+0.365814208984375
+0.34600830078125
+0.3427886962890625
+0.3453521728515625
+0.3419342041015625
+0.35064697265625
+0.33972930908203125
+0.347686767578125
+0.3508148193359375
+0.3571319580078125
+0.350250244140625
+0.355865478515625
+0.3333282470703125
+0.3570709228515625
+0.349212646484375
+0.362762451171875
+0.3553619384765625
+0.3541107177734375
+0.36395263671875
+0.3411102294921875
+0.353851318359375
+0.3333282470703125
+0.331695556640625
+0.3570556640625
+0.3437652587890625
+0.35491943359375
+0.3447113037109375
+0.3557891845703125
+0.33612060546875
+0.353057861328125
+0.3459320068359375
+0.351318359375
+0.365753173828125
+0.3592681884765625
+0.353851318359375
+0.3462677001953125
+0.3391571044921875
+0.350067138671875
+0.3566131591796875
+0.3647613525390625
+0.357635498046875
+0.3394927978515625
+0.362548828125
+0.346893310546875
+0.3467254638671875
+0.357391357421875
+0.3572845458984375
+0.3468170166015625
+0.3583984375
+0.3495635986328125
+0.3398895263671875
+0.3620758056640625
+0.3436737060546875
+0.3658294677734375
+0.3696746826171875
+0.363433837890625
+0.349700927734375
+0.34075927734375
+0.35308837890625
+0.3619232177734375
+0.358184814453125
+0.336669921875
+0.3583526611328125
+0.3554534912109375
+0.34332275390625
+0.3705291748046875
+0.3642425537109375
+0.3626556396484375
+0.3618621826171875
+0.37091064453125
+0.3772735595703125
+0.339111328125
+0.3716888427734375
+0.3685150146484375
+0.3658599853515625
+0.354644775390625
+0.352264404296875
+0.3607940673828125
+0.350738525390625
+0.35784912109375
+0.348297119140625
+0.3655853271484375
+0.36690521240234375
+0.3651275634765625
+0.36004638671875
+0.3629913330078125
+0.3441009521484375
+0.364013671875
+0.3559722900390625
+0.3897705078125
+0.3580169677734375
+0.3651580810546875
+0.3556060791015625
+0.379486083984375
+0.36655426025390625
+0.3540191650390625
+0.3636932373046875
+0.3766021728515625
+0.359649658203125
+0.3726043701171875
+0.373992919921875
+0.3694000244140625
+0.358917236328125
+0.36865234375
+0.377044677734375
+0.3600311279296875
+0.366241455078125
+0.3564453125
+0.36297607421875
+0.373260498046875
+0.3801727294921875
+0.34295654296875
+0.3532257080078125
+0.3811492919921875
+0.374786376953125
+0.3818359375
+0.3707122802734375
+0.358917236328125
+0.3844451904296875
+0.3736724853515625
+0.359283447265625
+0.371673583984375
+0.375335693359375
+0.3662567138671875
+0.38824462890625
+0.379669189453125
+0.387786865234375
+0.379302978515625
+0.3759307861328125
+0.3624725341796875
+0.370880126953125
+0.37103271484375
+0.371307373046875
+0.363189697265625
+0.3720550537109375
+0.36273193359375
+0.384735107421875
+0.3798828125
+0.382171630859375
+0.3591156005859375
+0.36907958984375
+0.3668975830078125
+0.38067626953125
+0.36004638671875
+0.37542724609375
+0.3874359130859375
+0.36920166015625
+0.3557586669921875
+0.3635101318359375
+0.3779449462890625
+0.3658905029296875
+0.360992431640625
+0.3618316650390625
+0.3864898681640625
+0.3709869384765625
+0.37127685546875
+0.3894500732421875
+0.3738555908203125
+0.367889404296875
+0.3612823486328125
+0.36602783203125
+0.376861572265625
+0.3683319091796875
+0.3683929443359375
+0.3529052734375
+0.3675079345703125
+0.388763427734375
+0.375732421875
+0.3828582763671875
+0.37738037109375
+0.3782806396484375
+0.3789215087890625
+0.3732452392578125
+0.3744354248046875
+0.3596954345703125
+0.363861083984375
+0.3609619140625
+0.385223388671875
+0.3695831298828125
+0.3633575439453125
+0.3798980712890625
+0.3574371337890625
+0.38043212890625
+0.370330810546875
+0.3741607666015625
+0.377197265625
+0.371917724609375
+0.37445068359375
+0.3754425048828125
+0.390228271484375
+0.363067626953125
+0.3730926513671875
+0.3759765625