初始化项目,由ModelHub XC社区提供模型

Model: SeongryongJung/qwen3-4b-tooluse-srpo-ema005
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-20 16:14:29 +08:00
commit 9aabae373d
19 changed files with 153324 additions and 0 deletions

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d56b97d485bd24953861da024015c467e9b6b7db7262dc91ccabdded453db12b
size 114330

View File

@@ -0,0 +1,91 @@
step,critic_score_mean
1,0.259765625
2,0.328125
3,0.421875
4,0.326171875
5,0.31640625
6,0.37109375
7,0.318359375
8,0.4453125
9,0.4140625
11,0.353515625
12,0.357421875
13,0.330078125
14,0.3828125
15,0.296875
16,0.279296875
17,0.384765625
18,0.4140625
19,0.2578125
21,0.353515625
22,0.314453125
23,0.380859375
24,0.359375
25,0.265625
26,0.41015625
27,0.400390625
28,0.34765625
29,0.369140625
31,0.400390625
32,0.302734375
33,0.203125
34,0.318359375
35,0.384765625
36,0.359375
37,0.271484375
38,0.337890625
39,0.38671875
41,0.40625
42,0.23828125
43,0.31640625
44,0.263671875
45,0.390625
46,0.392578125
47,0.435546875
48,0.326171875
49,0.30078125
51,0.5859375
52,0.337890625
53,0.384765625
54,0.30859375
55,0.474609375
56,0.318359375
57,0.361328125
58,0.33984375
59,0.27734375
61,0.384765625
62,0.33203125
63,0.373046875
64,0.416015625
65,0.474609375
66,0.47265625
67,0.373046875
68,0.228515625
69,0.501953125
71,0.328125
72,0.3828125
73,0.30859375
74,0.310546875
75,0.353515625
76,0.416015625
77,0.470703125
78,0.3984375
79,0.3828125
81,0.31640625
82,0.341796875
83,0.419921875
84,0.369140625
85,0.3046875
86,0.3046875
87,0.375
88,0.455078125
89,0.318359375
91,0.361328125
92,0.330078125
93,0.4375
94,0.34765625
95,0.314453125
96,0.328125
97,0.298828125
98,0.421875
99,0.431640625
1 step critic_score_mean
2 1 0.259765625
3 2 0.328125
4 3 0.421875
5 4 0.326171875
6 5 0.31640625
7 6 0.37109375
8 7 0.318359375
9 8 0.4453125
10 9 0.4140625
11 11 0.353515625
12 12 0.357421875
13 13 0.330078125
14 14 0.3828125
15 15 0.296875
16 16 0.279296875
17 17 0.384765625
18 18 0.4140625
19 19 0.2578125
20 21 0.353515625
21 22 0.314453125
22 23 0.380859375
23 24 0.359375
24 25 0.265625
25 26 0.41015625
26 27 0.400390625
27 28 0.34765625
28 29 0.369140625
29 31 0.400390625
30 32 0.302734375
31 33 0.203125
32 34 0.318359375
33 35 0.384765625
34 36 0.359375
35 37 0.271484375
36 38 0.337890625
37 39 0.38671875
38 41 0.40625
39 42 0.23828125
40 43 0.31640625
41 44 0.263671875
42 45 0.390625
43 46 0.392578125
44 47 0.435546875
45 48 0.326171875
46 49 0.30078125
47 51 0.5859375
48 52 0.337890625
49 53 0.384765625
50 54 0.30859375
51 55 0.474609375
52 56 0.318359375
53 57 0.361328125
54 58 0.33984375
55 59 0.27734375
56 61 0.384765625
57 62 0.33203125
58 63 0.373046875
59 64 0.416015625
60 65 0.474609375
61 66 0.47265625
62 67 0.373046875
63 68 0.228515625
64 69 0.501953125
65 71 0.328125
66 72 0.3828125
67 73 0.30859375
68 74 0.310546875
69 75 0.353515625
70 76 0.416015625
71 77 0.470703125
72 78 0.3984375
73 79 0.3828125
74 81 0.31640625
75 82 0.341796875
76 83 0.419921875
77 84 0.369140625
78 85 0.3046875
79 86 0.3046875
80 87 0.375
81 88 0.455078125
82 89 0.318359375
83 91 0.361328125
84 92 0.330078125
85 93 0.4375
86 94 0.34765625
87 95 0.314453125
88 96 0.328125
89 97 0.298828125
90 98 0.421875
91 99 0.431640625

View File

@@ -0,0 +1,11 @@
step,val_mean16
10,0.597426470588
20,0.567095588235
30,0.566176470588
40,0.625919117647
50,0.611213235294
60,0.606617647059
70,0.605698529412
80,0.577205882353
90,0.576286764706
100,0.572610294118
1 step val_mean16
2 10 0.597426470588
3 20 0.567095588235
4 30 0.566176470588
5 40 0.625919117647
6 50 0.611213235294
7 60 0.606617647059
8 70 0.605698529412
9 80 0.577205882353
10 90 0.576286764706
11 100 0.572610294118