SeongryongJung/Qwen-4b-base-RLSD
08
1step,critic_score_mean,val_math_dapo_acc_mean_at_1
21,0.1162109375,
32,0.1142578125,
43,0.12109375,
54,0.11328125,
65,0.1298828125,
76,0.13525390625,
87,0.11376953125,
98,0.13720703125,
109,0.138671875,
1110,0.14013671875,0.13333333333333333
1211,0.125,
1312,0.15576171875,
1413,0.1279296875,
1514,0.15185546875,
1615,0.1591796875,
1716,0.16796875,
1817,0.1416015625,
1918,0.16552734375,
2019,0.1708984375,
2120,0.1767578125,0.1
2221,0.1787109375,
2322,0.1826171875,
2423,0.22265625,
2524,0.1875,
2625,0.17236328125,
2726,0.23388671875,
2827,0.22216796875,
2928,0.20166015625,
3029,0.26416015625,
3130,0.2275390625,0.13333333333333333
3231,0.25537109375,
3332,0.22705078125,
3433,0.23095703125,
3534,0.24267578125,
3635,0.232421875,
3736,0.24365234375,
3837,0.2421875,
3938,0.21728515625,
4039,0.2431640625,
4140,0.2626953125,0.1
4241,0.2666015625,
4342,0.25634765625,
4443,0.26904296875,
4544,0.2685546875,
4645,0.25341796875,
4746,0.275390625,
4847,0.291015625,
4948,0.26416015625,
5049,0.29345703125,
5150,0.25,0.13333333333333333
5251,0.28515625,
5352,0.2470703125,
5453,0.25390625,
5554,0.31689453125,
5655,0.25048828125,
5756,0.3115234375,
5857,0.25927734375,
5958,0.29345703125,
6059,0.271484375,
6160,0.25732421875,0.16666666666666666
6261,0.30224609375,
6362,0.2783203125,
6463,0.32177734375,
6564,0.2568359375,
6665,0.2900390625,
6766,0.26904296875,
6867,0.265625,
6968,0.2998046875,
7069,0.236328125,
7170,0.27978515625,0.13333333333333333
7271,0.30419921875,
7372,0.27294921875,
7473,0.302734375,
7574,0.27880859375,
7675,0.28466796875,
7776,0.3046875,
7877,0.306640625,
7978,0.31689453125,
8079,0.30029296875,
8180,0.3173828125,0.1
8281,0.29638671875,
8382,0.3330078125,
8483,0.33837890625,
8584,0.287109375,
8685,0.28955078125,
8786,0.30810546875,
8887,0.326171875,
8988,0.3515625,
9089,0.3203125,
9190,0.3046875,0.16666666666666666
9291,0.322265625,
9392,0.33056640625,
9493,0.30224609375,
9594,0.34521484375,
9695,0.33984375,
9796,0.30322265625,
9897,0.31640625,
9998,0.32373046875,
10099,0.3447265625,
101100,0.30419921875,0.1
102 