Files
Qwen3-8B-Chemistry-SDPO-TR/results/training_scores.csv

92 lines
1.2 KiB
CSV
Raw Normal View History

step,critic_score_mean
1,0.5234375
2,0.40234375
3,0.3828125
4,0.44921875
5,0.4609375
6,0.43359375
7,0.31640625
8,0.51953125
9,0.359375
11,0.58984375
12,0.58203125
13,0.578125
14,0.59765625
15,0.56640625
16,0.55859375
17,0.48828125
18,0.625
19,0.65625
21,0.515625
22,0.5
23,0.75
24,0.7109375
25,0.671875
26,0.71484375
27,0.65234375
28,0.703125
29,0.578125
31,0.68359375
32,0.67578125
33,0.66796875
34,0.7109375
35,0.59765625
36,0.734375
37,0.57421875
38,0.6796875
39,0.625
41,0.6484375
42,0.7265625
43,0.703125
44,0.6640625
45,0.62109375
46,0.53125
47,0.71484375
48,0.6875
49,0.78515625
51,0.61328125
52,0.64453125
53,0.7109375
54,0.609375
55,0.71875
56,0.640625
57,0.69140625
58,0.828125
59,0.66015625
61,0.68359375
62,0.671875
63,0.57421875
64,0.8359375
65,0.8125
66,0.6640625
67,0.71875
68,0.515625
69,0.70703125
71,0.73046875
72,0.796875
73,0.7109375
74,0.734375
75,0.78125
76,0.65625
77,0.7421875
78,0.76953125
79,0.67578125
81,0.671875
82,0.6875
83,0.57421875
84,0.73828125
85,0.76171875
86,0.66015625
87,0.78125
88,0.75
89,0.671875
91,0.7265625
92,0.62890625
93,0.89453125
94,0.81640625
95,0.71875
96,0.734375
97,0.6953125
98,0.69921875
99,0.625