初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-8B-Biology-RLSD-TR Source: Original Platform
This commit is contained in:
91
results/training_scores.csv
Normal file
91
results/training_scores.csv
Normal file
@@ -0,0 +1,91 @@
|
||||
step,critic_score_mean
|
||||
1,0.33984375
|
||||
2,0.3828125
|
||||
3,0.44921875
|
||||
4,0.37890625
|
||||
5,0.44921875
|
||||
6,0.34375
|
||||
7,0.2890625
|
||||
8,0.2421875
|
||||
9,0.34765625
|
||||
11,0.42578125
|
||||
12,0.421875
|
||||
13,0.3203125
|
||||
14,0.29296875
|
||||
15,0.3671875
|
||||
16,0.40234375
|
||||
17,0.30078125
|
||||
18,0.4296875
|
||||
19,0.3828125
|
||||
21,0.4140625
|
||||
22,0.4296875
|
||||
23,0.33984375
|
||||
24,0.453125
|
||||
25,0.4296875
|
||||
26,0.38671875
|
||||
27,0.359375
|
||||
28,0.375
|
||||
29,0.4375
|
||||
31,0.31640625
|
||||
32,0.5
|
||||
33,0.41015625
|
||||
34,0.390625
|
||||
35,0.4765625
|
||||
36,0.390625
|
||||
37,0.4140625
|
||||
38,0.44140625
|
||||
39,0.4765625
|
||||
41,0.45703125
|
||||
42,0.3515625
|
||||
43,0.56640625
|
||||
44,0.4921875
|
||||
45,0.40234375
|
||||
46,0.4140625
|
||||
47,0.40625
|
||||
48,0.48046875
|
||||
49,0.43359375
|
||||
51,0.4375
|
||||
52,0.53515625
|
||||
53,0.48828125
|
||||
54,0.5
|
||||
55,0.609375
|
||||
56,0.53515625
|
||||
57,0.53515625
|
||||
58,0.4921875
|
||||
59,0.4921875
|
||||
61,0.46875
|
||||
62,0.5078125
|
||||
63,0.5546875
|
||||
64,0.65625
|
||||
65,0.57421875
|
||||
66,0.45703125
|
||||
67,0.515625
|
||||
68,0.5859375
|
||||
69,0.49609375
|
||||
71,0.50390625
|
||||
72,0.5546875
|
||||
73,0.59765625
|
||||
74,0.45703125
|
||||
75,0.55859375
|
||||
76,0.4765625
|
||||
77,0.6640625
|
||||
78,0.640625
|
||||
79,0.47265625
|
||||
81,0.59375
|
||||
82,0.58203125
|
||||
83,0.5390625
|
||||
84,0.50390625
|
||||
85,0.5
|
||||
86,0.56640625
|
||||
87,0.578125
|
||||
88,0.44140625
|
||||
89,0.6328125
|
||||
91,0.4921875
|
||||
92,0.6328125
|
||||
93,0.6015625
|
||||
94,0.609375
|
||||
95,0.6640625
|
||||
96,0.6484375
|
||||
97,0.65625
|
||||
98,0.4609375
|
||||
99,0.54296875
|
||||
|
Reference in New Issue
Block a user