初始化项目,由ModelHub XC社区提供模型

Model: SeongryongJung/Qwen3-4B-Chemistry-RLRT-TR
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-03 20:29:22 +08:00
commit 22e0cd8b2b
21 changed files with 153725 additions and 0 deletions

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:71ccc08d4675905705e178b45e3b5b05ffd6e77b35e5efc39d6bb287bb19a9ca
size 138388

View File

@@ -0,0 +1,91 @@
step,critic_score_mean
1,0.58203125
2,0.36328125
3,0.4765625
4,0.32421875
5,0.4765625
6,0.46484375
7,0.37109375
8,0.53125
9,0.3671875
11,0.44921875
12,0.5390625
13,0.421875
14,0.41796875
15,0.484375
16,0.45703125
17,0.35546875
18,0.40234375
19,0.5390625
21,0.375
22,0.32421875
23,0.55078125
24,0.56640625
25,0.43359375
26,0.5546875
27,0.44921875
28,0.53515625
29,0.36328125
31,0.5625
32,0.5078125
33,0.47265625
34,0.48828125
35,0.4453125
36,0.51953125
37,0.41015625
38,0.4765625
39,0.48046875
41,0.35546875
42,0.40625
43,0.484375
44,0.61328125
45,0.578125
46,0.40234375
47,0.484375
48,0.41015625
49,0.5546875
51,0.640625
52,0.4375
53,0.59375
54,0.34765625
55,0.55859375
56,0.45703125
57,0.46875
58,0.50390625
59,0.4375
61,0.51953125
62,0.5078125
63,0.53515625
64,0.6328125
65,0.5859375
66,0.5390625
67,0.5703125
68,0.3359375
69,0.5859375
71,0.54296875
72,0.56640625
73,0.5703125
74,0.52734375
75,0.6875
76,0.55859375
77,0.59765625
78,0.578125
79,0.47265625
81,0.453125
82,0.61328125
83,0.48828125
84,0.58203125
85,0.6484375
86,0.4375
87,0.3984375
88,0.53515625
89,0.5625
91,0.45703125
92,0.546875
93,0.6875
94,0.64453125
95,0.59375
96,0.5078125
97,0.48046875
98,0.4609375
99,0.4921875
1 step critic_score_mean
2 1 0.58203125
3 2 0.36328125
4 3 0.4765625
5 4 0.32421875
6 5 0.4765625
7 6 0.46484375
8 7 0.37109375
9 8 0.53125
10 9 0.3671875
11 11 0.44921875
12 12 0.5390625
13 13 0.421875
14 14 0.41796875
15 15 0.484375
16 16 0.45703125
17 17 0.35546875
18 18 0.40234375
19 19 0.5390625
20 21 0.375
21 22 0.32421875
22 23 0.55078125
23 24 0.56640625
24 25 0.43359375
25 26 0.5546875
26 27 0.44921875
27 28 0.53515625
28 29 0.36328125
29 31 0.5625
30 32 0.5078125
31 33 0.47265625
32 34 0.48828125
33 35 0.4453125
34 36 0.51953125
35 37 0.41015625
36 38 0.4765625
37 39 0.48046875
38 41 0.35546875
39 42 0.40625
40 43 0.484375
41 44 0.61328125
42 45 0.578125
43 46 0.40234375
44 47 0.484375
45 48 0.41015625
46 49 0.5546875
47 51 0.640625
48 52 0.4375
49 53 0.59375
50 54 0.34765625
51 55 0.55859375
52 56 0.45703125
53 57 0.46875
54 58 0.50390625
55 59 0.4375
56 61 0.51953125
57 62 0.5078125
58 63 0.53515625
59 64 0.6328125
60 65 0.5859375
61 66 0.5390625
62 67 0.5703125
63 68 0.3359375
64 69 0.5859375
65 71 0.54296875
66 72 0.56640625
67 73 0.5703125
68 74 0.52734375
69 75 0.6875
70 76 0.55859375
71 77 0.59765625
72 78 0.578125
73 79 0.47265625
74 81 0.453125
75 82 0.61328125
76 83 0.48828125
77 84 0.58203125
78 85 0.6484375
79 86 0.4375
80 87 0.3984375
81 88 0.53515625
82 89 0.5625
83 91 0.45703125
84 92 0.546875
85 93 0.6875
86 94 0.64453125
87 95 0.59375
88 96 0.5078125
89 97 0.48046875
90 98 0.4609375
91 99 0.4921875

View File

@@ -0,0 +1,11 @@
step,val_mean16
10,0.442261904762
20,0.490773809524
30,0.488392857143
40,0.514880952381
50,0.530654761905
60,0.527678571429
70,0.555654761905
80,0.560416666667
90,0.576488095238
100,0.591666666667
1 step val_mean16
2 10 0.442261904762
3 20 0.490773809524
4 30 0.488392857143
5 40 0.514880952381
6 50 0.530654761905
7 60 0.527678571429
8 70 0.555654761905
9 80 0.560416666667
10 90 0.576488095238
11 100 0.591666666667