zhangsj0722
/

E-GRPO

Model card Files Files and versions

xet

Community

zhangsj0722 commited on Nov 13, 2025

Commit

40bb282

verified ·

1 Parent(s): ee42f9a

Upload first_half_step_hps_reward.txt with huggingface_hub

Browse files

Files changed (1) hide show

first_half_step_hps_reward.txt +301 -0

first_half_step_hps_reward.txt ADDED Viewed

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

+0.29024505615234375
+0.30950927734375
+0.3063812255859375
+0.298675537109375
+0.304168701171875
+0.30133056640625
+0.3088226318359375
+0.3030853271484375
+0.30484771728515625
+0.30533599853515625
+0.30896759033203125
+0.3061676025390625
+0.32244873046875
+0.316314697265625
+0.3185577392578125
+0.31928253173828125
+0.3109283447265625
+0.3131561279296875
+0.33001708984375
+0.3160552978515625
+0.31844329833984375
+0.32216644287109375
+0.327362060546875
+0.3195648193359375
+0.3247222900390625
+0.33331298828125
+0.339111328125
+0.3380279541015625
+0.318572998046875
+0.336151123046875
+0.3344268798828125
+0.34130859375
+0.3331146240234375
+0.346710205078125
+0.3404388427734375
+0.3390045166015625
+0.33238983154296875
+0.3272857666015625
+0.3361968994140625
+0.3323822021484375
+0.3320770263671875
+0.3280029296875
+0.3439788818359375
+0.3343048095703125
+0.33734130859375
+0.34417724609375
+0.34185791015625
+0.3326873779296875
+0.34514617919921875
+0.35394287109375
+0.3542327880859375
+0.3455352783203125
+0.34490966796875
+0.34747314453125
+0.345306396484375
+0.335784912109375
+0.33965301513671875
+0.3451690673828125
+0.339263916015625
+0.3590850830078125
+0.33576202392578125
+0.33941650390625
+0.3457489013671875
+0.3572998046875
+0.32452392578125
+0.33782958984375
+0.3343353271484375
+0.34906005859375
+0.3419952392578125
+0.351959228515625
+0.3518829345703125
+0.34453582763671875
+0.359466552734375
+0.3438262939453125
+0.3670501708984375
+0.346160888671875
+0.350799560546875
+0.336822509765625
+0.3511199951171875
+0.3379058837890625
+0.3524322509765625
+0.3470001220703125
+0.341888427734375
+0.3504791259765625
+0.355804443359375
+0.3410491943359375
+0.362213134765625
+0.3455352783203125
+0.3426055908203125
+0.3501739501953125
+0.3638458251953125
+0.354095458984375
+0.3419189453125
+0.3489837646484375
+0.3653106689453125
+0.3584442138671875
+0.3451080322265625
+0.353485107421875
+0.364105224609375
+0.3568878173828125
+0.354248046875
+0.3574676513671875
+0.35866546630859375
+0.3670196533203125
+0.3628082275390625
+0.3614044189453125
+0.3359527587890625
+0.369903564453125
+0.3542327880859375
+0.3677215576171875
+0.3679962158203125
+0.36151123046875
+0.3747711181640625
+0.3534393310546875
+0.3679046630859375
+0.35137939453125
+0.345306396484375
+0.3698577880859375
+0.3567352294921875
+0.36749267578125
+0.3553924560546875
+0.36053466796875
+0.361236572265625
+0.3644866943359375
+0.353973388671875
+0.3558197021484375
+0.3748016357421875
+0.3663177490234375
+0.364044189453125
+0.34814453125
+0.34649658203125
+0.3628997802734375
+0.3687744140625
+0.3812103271484375
+0.366729736328125
+0.359771728515625
+0.372589111328125
+0.355224609375
+0.357940673828125
+0.36669921875
+0.372467041015625
+0.35784912109375
+0.3607635498046875
+0.3700408935546875
+0.352630615234375
+0.3704833984375
+0.3604888916015625
+0.376495361328125
+0.377227783203125
+0.3718109130859375
+0.3663787841796875
+0.3494873046875
+0.3687744140625
+0.3623809814453125
+0.3662872314453125
+0.3517608642578125
+0.365875244140625
+0.372894287109375
+0.3605804443359375
+0.3780670166015625
+0.3689117431640625
+0.384521484375
+0.3739471435546875
+0.378692626953125
+0.3827362060546875
+0.3543243408203125
+0.3778839111328125
+0.3835601806640625
+0.3852386474609375
+0.3654327392578125
+0.3620452880859375
+0.37286376953125
+0.3570404052734375
+0.376983642578125
+0.3626861572265625
+0.3782196044921875
+0.391693115234375
+0.371063232421875
+0.3735504150390625
+0.3720703125
+0.3545989990234375
+0.3660736083984375
+0.373870849609375
+0.399749755859375
+0.3576812744140625
+0.373809814453125
+0.3666534423828125
+0.3933258056640625
+0.380401611328125
+0.367095947265625
+0.375518798828125
+0.3797760009765625
+0.37445068359375
+0.389434814453125
+0.37896728515625
+0.376739501953125
+0.365447998046875
+0.38543701171875
+0.38287353515625
+0.36480712890625
+0.3736572265625
+0.3734893798828125
+0.3716278076171875
+0.3787384033203125
+0.38897705078125
+0.352630615234375
+0.3583526611328125
+0.385833740234375
+0.387481689453125
+0.388641357421875
+0.3771820068359375
+0.363922119140625
+0.396392822265625
+0.385009765625
+0.3739166259765625
+0.3798980712890625
+0.3865814208984375
+0.3791046142578125
+0.389678955078125
+0.3865814208984375
+0.3959503173828125
+0.3803863525390625
+0.38641357421875
+0.3731231689453125
+0.3852081298828125
+0.3741455078125
+0.3762969970703125
+0.3704071044921875
+0.3805389404296875
+0.365020751953125
+0.3909149169921875
+0.387664794921875
+0.3863677978515625
+0.3704681396484375
+0.3721160888671875
+0.380584716796875
+0.3882293701171875
+0.368804931640625
+0.3785858154296875
+0.3932647705078125
+0.3826141357421875
+0.365997314453125
+0.37353515625
+0.3926849365234375
+0.3762969970703125
+0.3726654052734375
+0.3666839599609375
+0.393096923828125
+0.3879547119140625
+0.3816986083984375
+0.3942108154296875
+0.378509521484375
+0.37164306640625
+0.3744354248046875
+0.376861572265625
+0.3887176513671875
+0.3804168701171875
+0.3783416748046875
+0.3607940673828125
+0.383697509765625
+0.39373779296875
+0.379669189453125
+0.3933563232421875
+0.3850555419921875
+0.389892578125
+0.3875885009765625
+0.382476806640625
+0.3769073486328125
+0.3704071044921875
+0.37451171875
+0.3746185302734375
+0.3947296142578125
+0.38092041015625
+0.3759918212890625
+0.3885650634765625
+0.369598388671875
+0.3823089599609375
+0.377685546875
+0.375335693359375
+0.379638671875
+0.3846435546875
+0.3831024169921875
+0.3849334716796875
+0.4084930419921875
+0.373291015625
+0.3846893310546875
+0.3778076171875
+0.391510009765625
+0.400634765625
+0.3840484619140625
+0.398284912109375
+0.3907470703125
+0.4174957275390625
+0.385101318359375
+0.3972320556640625
+0.3962554931640625
+0.39837646484375
+0.3730010986328125
+0.386077880859375
+0.3885345458984375
+0.3670196533203125