初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-4B-Material-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
|
||||
1,0.55078125
|
||||
2,0.5078125
|
||||
3,0.6171875
|
||||
4,0.62109375
|
||||
5,0.55078125
|
||||
6,0.625
|
||||
7,0.66796875
|
||||
8,0.62109375
|
||||
9,0.62109375
|
||||
11,0.48046875
|
||||
12,0.61328125
|
||||
13,0.51953125
|
||||
14,0.7890625
|
||||
15,0.671875
|
||||
16,0.70703125
|
||||
17,0.578125
|
||||
18,0.609375
|
||||
19,0.65625
|
||||
21,0.59375
|
||||
22,0.7109375
|
||||
23,0.78125
|
||||
24,0.875
|
||||
25,0.64453125
|
||||
26,0.66796875
|
||||
27,0.7890625
|
||||
28,0.63671875
|
||||
29,0.6640625
|
||||
31,0.6328125
|
||||
32,0.6875
|
||||
33,0.74609375
|
||||
34,0.8125
|
||||
35,0.765625
|
||||
36,0.66796875
|
||||
37,0.8359375
|
||||
38,0.5859375
|
||||
39,0.75390625
|
||||
41,0.5859375
|
||||
42,0.69140625
|
||||
43,0.546875
|
||||
44,0.734375
|
||||
45,0.8125
|
||||
46,0.765625
|
||||
47,0.6953125
|
||||
48,0.8203125
|
||||
49,0.6171875
|
||||
51,0.671875
|
||||
52,0.7421875
|
||||
53,0.65234375
|
||||
54,0.5703125
|
||||
55,0.73828125
|
||||
56,0.7890625
|
||||
57,0.7578125
|
||||
58,0.8359375
|
||||
59,0.70703125
|
||||
61,0.83984375
|
||||
62,0.82421875
|
||||
63,0.68359375
|
||||
64,0.7890625
|
||||
65,0.62890625
|
||||
66,0.72265625
|
||||
67,0.80078125
|
||||
68,0.8203125
|
||||
69,0.828125
|
||||
71,0.78515625
|
||||
72,0.7890625
|
||||
73,0.6875
|
||||
74,0.84375
|
||||
75,0.66015625
|
||||
76,0.69140625
|
||||
77,0.5
|
||||
78,0.6328125
|
||||
79,0.80078125
|
||||
81,0.69921875
|
||||
82,0.7109375
|
||||
83,0.6953125
|
||||
84,0.84375
|
||||
85,0.71875
|
||||
86,0.81640625
|
||||
87,0.62109375
|
||||
88,0.6640625
|
||||
89,0.73828125
|
||||
91,0.75
|
||||
92,0.69140625
|
||||
93,0.7734375
|
||||
94,0.75
|
||||
95,0.71875
|
||||
96,0.6484375
|
||||
97,0.87890625
|
||||
98,0.921875
|
||||
99,0.7578125
|
||||
|
Reference in New Issue
Block a user