初始化项目,由ModelHub XC社区提供模型

Model: SeongryongJung/Qwen3-8B-Chemistry-SRPO-TR
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-03 21:23:23 +08:00
commit 2d74f845e2
23 changed files with 153336 additions and 0 deletions

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0c17c1f54149b9b11c90aa0c150f1b2383ba4653c792d4f0701ce5d1581e42ba
size 113462

View File

@@ -0,0 +1,91 @@
step,critic_score_mean
1,0.453125
2,0.34765625
3,0.4453125
4,0.41015625
5,0.4375
6,0.4375
7,0.34375
8,0.42578125
9,0.39453125
11,0.5703125
12,0.57421875
13,0.51171875
14,0.5234375
15,0.56640625
16,0.51953125
17,0.46484375
18,0.62109375
19,0.62109375
21,0.49609375
22,0.5078125
23,0.73828125
24,0.6796875
25,0.60546875
26,0.68359375
27,0.58203125
28,0.60546875
29,0.5625
31,0.6640625
32,0.60546875
33,0.671875
34,0.63671875
35,0.59765625
36,0.6484375
37,0.515625
38,0.66796875
39,0.64453125
41,0.625
42,0.64453125
43,0.6484375
44,0.69921875
45,0.6171875
46,0.54296875
47,0.65234375
48,0.71484375
49,0.7578125
51,0.63671875
52,0.6171875
53,0.6328125
54,0.61328125
55,0.6953125
56,0.6171875
57,0.6875
58,0.75390625
59,0.6953125
61,0.67578125
62,0.6796875
63,0.625
64,0.765625
65,0.7421875
66,0.61328125
67,0.66015625
68,0.56640625
69,0.66796875
71,0.6796875
72,0.73828125
73,0.68359375
74,0.7109375
75,0.76953125
76,0.609375
77,0.7109375
78,0.72265625
79,0.6015625
81,0.5859375
82,0.68359375
83,0.6328125
84,0.71875
85,0.80078125
86,0.69140625
87,0.69921875
88,0.70703125
89,0.625
91,0.703125
92,0.67578125
93,0.8125
94,0.79296875
95,0.66796875
96,0.72265625
97,0.6796875
98,0.7421875
99,0.6484375
1 step critic_score_mean
2 1 0.453125
3 2 0.34765625
4 3 0.4453125
5 4 0.41015625
6 5 0.4375
7 6 0.4375
8 7 0.34375
9 8 0.42578125
10 9 0.39453125
11 11 0.5703125
12 12 0.57421875
13 13 0.51171875
14 14 0.5234375
15 15 0.56640625
16 16 0.51953125
17 17 0.46484375
18 18 0.62109375
19 19 0.62109375
20 21 0.49609375
21 22 0.5078125
22 23 0.73828125
23 24 0.6796875
24 25 0.60546875
25 26 0.68359375
26 27 0.58203125
27 28 0.60546875
28 29 0.5625
29 31 0.6640625
30 32 0.60546875
31 33 0.671875
32 34 0.63671875
33 35 0.59765625
34 36 0.6484375
35 37 0.515625
36 38 0.66796875
37 39 0.64453125
38 41 0.625
39 42 0.64453125
40 43 0.6484375
41 44 0.69921875
42 45 0.6171875
43 46 0.54296875
44 47 0.65234375
45 48 0.71484375
46 49 0.7578125
47 51 0.63671875
48 52 0.6171875
49 53 0.6328125
50 54 0.61328125
51 55 0.6953125
52 56 0.6171875
53 57 0.6875
54 58 0.75390625
55 59 0.6953125
56 61 0.67578125
57 62 0.6796875
58 63 0.625
59 64 0.765625
60 65 0.7421875
61 66 0.61328125
62 67 0.66015625
63 68 0.56640625
64 69 0.66796875
65 71 0.6796875
66 72 0.73828125
67 73 0.68359375
68 74 0.7109375
69 75 0.76953125
70 76 0.609375
71 77 0.7109375
72 78 0.72265625
73 79 0.6015625
74 81 0.5859375
75 82 0.68359375
76 83 0.6328125
77 84 0.71875
78 85 0.80078125
79 86 0.69140625
80 87 0.69921875
81 88 0.70703125
82 89 0.625
83 91 0.703125
84 92 0.67578125
85 93 0.8125
86 94 0.79296875
87 95 0.66796875
88 96 0.72265625
89 97 0.6796875
90 98 0.7421875
91 99 0.6484375

View File

@@ -0,0 +1,11 @@
step,val_mean16
10,0.503571428571
20,0.626785714286
30,0.657142857143
40,0.687202380952
50,0.708035714286
60,0.708035714286
70,0.716964285714
80,0.714583333333
90,0.722321428571
100,0.73630952381
1 step val_mean16
2 10 0.503571428571
3 20 0.626785714286
4 30 0.657142857143
5 40 0.687202380952
6 50 0.708035714286
7 60 0.708035714286
8 70 0.716964285714
9 80 0.714583333333
10 90 0.722321428571
11 100 0.73630952381