初始化项目,由ModelHub XC社区提供模型

Model: SeongryongJung/Qwen3-4B-Chemistry-SDPO-TR
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-03 22:43:24 +08:00
commit f0b01151ab
21 changed files with 153276 additions and 0 deletions

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3a4beb246368afcd1aa10e432ce44c95b7574ff32bd6b464700496ffc0c424ad
size 115748

View File

@@ -0,0 +1,91 @@
step,critic_score_mean
1,0.59765625
2,0.3828125
3,0.4296875
4,0.33203125
5,0.4609375
6,0.50390625
7,0.4453125
8,0.57421875
9,0.3515625
11,0.45703125
12,0.62109375
13,0.6171875
14,0.53125
15,0.65625
16,0.4765625
17,0.41796875
18,0.515625
19,0.54296875
21,0.5703125
22,0.6015625
23,0.70703125
24,0.67578125
25,0.5703125
26,0.67578125
27,0.62109375
28,0.63671875
29,0.44921875
31,0.62109375
32,0.6015625
33,0.67578125
34,0.6640625
35,0.6015625
36,0.73046875
37,0.609375
38,0.6484375
39,0.61328125
41,0.5625
42,0.6875
43,0.71484375
44,0.6171875
45,0.5234375
46,0.67578125
47,0.5859375
48,0.66796875
49,0.73828125
51,0.625
52,0.5078125
53,0.6640625
54,0.51171875
55,0.7421875
56,0.58984375
57,0.671875
58,0.76171875
59,0.63671875
61,0.69140625
62,0.7109375
63,0.58984375
64,0.84375
65,0.7578125
66,0.59375
67,0.59765625
68,0.609375
69,0.60546875
71,0.59375
72,0.70703125
73,0.61328125
74,0.73046875
75,0.71484375
76,0.5625
77,0.63671875
78,0.69140625
79,0.63671875
81,0.609375
82,0.67578125
83,0.640625
84,0.7578125
85,0.7578125
86,0.5546875
87,0.734375
88,0.6640625
89,0.640625
91,0.671875
92,0.7265625
93,0.7890625
94,0.828125
95,0.7578125
96,0.671875
97,0.6640625
98,0.70703125
99,0.68359375
1 step critic_score_mean
2 1 0.59765625
3 2 0.3828125
4 3 0.4296875
5 4 0.33203125
6 5 0.4609375
7 6 0.50390625
8 7 0.4453125
9 8 0.57421875
10 9 0.3515625
11 11 0.45703125
12 12 0.62109375
13 13 0.6171875
14 14 0.53125
15 15 0.65625
16 16 0.4765625
17 17 0.41796875
18 18 0.515625
19 19 0.54296875
20 21 0.5703125
21 22 0.6015625
22 23 0.70703125
23 24 0.67578125
24 25 0.5703125
25 26 0.67578125
26 27 0.62109375
27 28 0.63671875
28 29 0.44921875
29 31 0.62109375
30 32 0.6015625
31 33 0.67578125
32 34 0.6640625
33 35 0.6015625
34 36 0.73046875
35 37 0.609375
36 38 0.6484375
37 39 0.61328125
38 41 0.5625
39 42 0.6875
40 43 0.71484375
41 44 0.6171875
42 45 0.5234375
43 46 0.67578125
44 47 0.5859375
45 48 0.66796875
46 49 0.73828125
47 51 0.625
48 52 0.5078125
49 53 0.6640625
50 54 0.51171875
51 55 0.7421875
52 56 0.58984375
53 57 0.671875
54 58 0.76171875
55 59 0.63671875
56 61 0.69140625
57 62 0.7109375
58 63 0.58984375
59 64 0.84375
60 65 0.7578125
61 66 0.59375
62 67 0.59765625
63 68 0.609375
64 69 0.60546875
65 71 0.59375
66 72 0.70703125
67 73 0.61328125
68 74 0.73046875
69 75 0.71484375
70 76 0.5625
71 77 0.63671875
72 78 0.69140625
73 79 0.63671875
74 81 0.609375
75 82 0.67578125
76 83 0.640625
77 84 0.7578125
78 85 0.7578125
79 86 0.5546875
80 87 0.734375
81 88 0.6640625
82 89 0.640625
83 91 0.671875
84 92 0.7265625
85 93 0.7890625
86 94 0.828125
87 95 0.7578125
88 96 0.671875
89 97 0.6640625
90 98 0.70703125
91 99 0.68359375

View File

@@ -0,0 +1,11 @@
step,val_mean16
10,0.558928571429
20,0.669345238095
30,0.689880952381
40,0.677976190476
50,0.677976190476
60,0.680952380952
70,0.682738095238
80,0.702380952381
90,0.743452380952
100,0.749107142857
1 step val_mean16
2 10 0.558928571429
3 20 0.669345238095
4 30 0.689880952381
5 40 0.677976190476
6 50 0.677976190476
7 60 0.680952380952
8 70 0.682738095238
9 80 0.702380952381
10 90 0.743452380952
11 100 0.749107142857