zhangsj0722
/

E-GRPO

Model card Files Files and versions

xet

Community

zhangsj0722 commited on Nov 13, 2025

Commit

ee42f9a

verified ·

1 Parent(s): 6b8904d

Upload second_half_step_hps_reward.txt with huggingface_hub

Browse files

Files changed (1) hide show

second_half_step_hps_reward.txt +301 -0

second_half_step_hps_reward.txt ADDED Viewed

	@@ -0,0 +1,301 @@

+0.29024505615234375
+0.3083343505859375
+0.30265045166015625
+0.29034423828125
+0.3047637939453125
+0.28522491455078125
+0.30803680419921875
+0.29839324951171875
+0.308197021484375
+0.291015625
+0.3046875
+0.29615020751953125
+0.30438232421875
+0.298919677734375
+0.316375732421875
+0.3007965087890625
+0.30007171630859375
+0.304107666015625
+0.30324554443359375
+0.305328369140625
+0.30010986328125
+0.30644989013671875
+0.30854034423828125
+0.30355072021484375
+0.29741668701171875
+0.317108154296875
+0.309661865234375
+0.3107757568359375
+0.2958984375
+0.32318115234375
+0.3095550537109375
+0.3078460693359375
+0.31697845458984375
+0.3214874267578125
+0.309173583984375
+0.30426025390625
+0.295745849609375
+0.3087310791015625
+0.3076019287109375
+0.29882049560546875
+0.305267333984375
+0.2960968017578125
+0.32219696044921875
+0.29714202880859375
+0.30504608154296875
+0.3225250244140625
+0.304351806640625
+0.30364990234375
+0.3229827880859375
+0.31604766845703125
+0.31737518310546875
+0.3224639892578125
+0.31549072265625
+0.31562042236328125
+0.3121185302734375
+0.2939300537109375
+0.30937957763671875
+0.2911529541015625
+0.3163909912109375
+0.33990478515625
+0.29837799072265625
+0.30664825439453125
+0.31903076171875
+0.3292083740234375
+0.29669189453125
+0.3023223876953125
+0.295623779296875
+0.318389892578125
+0.307342529296875
+0.30419158935546875
+0.31552886962890625
+0.3011016845703125
+0.3311004638671875
+0.3085174560546875
+0.3422698974609375
+0.30585479736328125
+0.309539794921875
+0.30361175537109375
+0.304840087890625
+0.31134033203125
+0.32167816162109375
+0.30646514892578125
+0.2993621826171875
+0.31439208984375
+0.3266754150390625
+0.3139801025390625
+0.3302154541015625
+0.3068695068359375
+0.3012847900390625
+0.31061553955078125
+0.329376220703125
+0.3133544921875
+0.3058624267578125
+0.3143768310546875
+0.3391265869140625
+0.32568359375
+0.32041168212890625
+0.3142242431640625
+0.316741943359375
+0.323486328125
+0.31363677978515625
+0.31926727294921875
+0.3259429931640625
+0.32436370849609375
+0.3216552734375
+0.3348541259765625
+0.30222320556640625
+0.3341217041015625
+0.31595611572265625
+0.34423828125
+0.338043212890625
+0.3298492431640625
+0.3401336669921875
+0.3205108642578125
+0.32283782958984375
+0.31085968017578125
+0.3186187744140625
+0.3358001708984375
+0.32035064697265625
+0.325958251953125
+0.31952667236328125
+0.32720947265625
+0.3175048828125
+0.3289031982421875
+0.3249664306640625
+0.321502685546875
+0.331878662109375
+0.338226318359375
+0.33233642578125
+0.3235931396484375
+0.312225341796875
+0.320404052734375
+0.33685302734375
+0.33502197265625
+0.3295135498046875
+0.3224945068359375
+0.3403472900390625
+0.331298828125
+0.321075439453125
+0.3358306884765625
+0.3306884765625
+0.32244873046875
+0.3397064208984375
+0.332733154296875
+0.31763458251953125
+0.3422088623046875
+0.3178558349609375
+0.33602142333984375
+0.349334716796875
+0.34326171875
+0.3278656005859375
+0.314117431640625
+0.327484130859375
+0.3400115966796875
+0.3393707275390625
+0.3101043701171875
+0.33392333984375
+0.3402252197265625
+0.32286834716796875
+0.3447265625
+0.33123779296875
+0.3371124267578125
+0.3368988037109375
+0.334075927734375
+0.35302734375
+0.325592041015625
+0.32947540283203125
+0.34654998779296875
+0.345977783203125
+0.3298187255859375
+0.3321380615234375
+0.328094482421875
+0.31995391845703125
+0.337127685546875
+0.332672119140625
+0.346435546875
+0.340850830078125
+0.3383636474609375
+0.338287353515625
+0.340362548828125
+0.324554443359375
+0.341033935546875
+0.328399658203125
+0.360687255859375
+0.3332366943359375
+0.338134765625
+0.3365936279296875
+0.34820556640625
+0.33843994140625
+0.3254547119140625
+0.3435516357421875
+0.339874267578125
+0.3367919921875
+0.3381805419921875
+0.336090087890625
+0.3354949951171875
+0.329315185546875
+0.344207763671875
+0.342010498046875
+0.3294525146484375
+0.3473358154296875
+0.3399658203125
+0.3375701904296875
+0.343902587890625
+0.3498992919921875
+0.3091888427734375
+0.334442138671875
+0.3637237548828125
+0.34674072265625
+0.3499908447265625
+0.347503662109375
+0.335235595703125
+0.3554229736328125
+0.353515625
+0.33587646484375
+0.3454742431640625
+0.33908843994140625
+0.3378448486328125
+0.3392333984375
+0.3545074462890625
+0.3518218994140625
+0.34722900390625
+0.3450927734375
+0.3378448486328125
+0.3454132080078125
+0.3445892333984375
+0.351104736328125
+0.3298797607421875
+0.350311279296875
+0.3359222412109375
+0.3577728271484375
+0.3446197509765625
+0.355438232421875
+0.3446197509765625
+0.3460845947265625
+0.3364105224609375
+0.33612823486328125
+0.3380889892578125
+0.345977783203125
+0.35125732421875
+0.3446197509765625
+0.3403472900390625
+0.3384857177734375
+0.35254669189453125
+0.33483123779296875
+0.344757080078125
+0.33329010009765625
+0.3623809814453125
+0.349609375
+0.344482421875
+0.3447265625
+0.3444976806640625
+0.334503173828125
+0.345123291015625
+0.345123291015625
+0.35107421875
+0.3488922119140625
+0.34161376953125
+0.3331756591796875
+0.34405517578125
+0.36199951171875
+0.343109130859375
+0.355926513671875
+0.352142333984375
+0.3451690673828125
+0.35001373291015625
+0.35528564453125
+0.351715087890625
+0.326568603515625
+0.33489990234375
+0.33010101318359375
+0.3617706298828125
+0.3389739990234375
+0.346466064453125
+0.3453521728515625
+0.3364410400390625
+0.3564910888671875
+0.331329345703125
+0.3497467041015625
+0.3443603515625
+0.347808837890625
+0.349334716796875
+0.3463592529296875
+0.3671875
+0.3425140380859375
+0.3540496826171875
+0.35107421875
+0.359771728515625
+0.363983154296875
+0.35601806640625
+0.3617095947265625
+0.35272979736328125
+0.3751983642578125
+0.350189208984375
+0.36077880859375
+0.360382080078125
+0.358856201171875
+0.3356475830078125
+0.3455657958984375
+0.35638427734375
+0.3380889892578125