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

92 lines
1.3 KiB
CSV
Raw Normal View History

step,critic_score_mean
1,0.453125
2,0.34765625
3,0.4453125
4,0.41015625
5,0.4375
6,0.4375
7,0.34375
8,0.42578125
9,0.39453125
11,0.5703125
12,0.57421875
13,0.51171875
14,0.5234375
15,0.56640625
16,0.51953125
17,0.46484375
18,0.62109375
19,0.62109375
21,0.49609375
22,0.5078125
23,0.73828125
24,0.6796875
25,0.60546875
26,0.68359375
27,0.58203125
28,0.60546875
29,0.5625
31,0.6640625
32,0.60546875
33,0.671875
34,0.63671875
35,0.59765625
36,0.6484375
37,0.515625
38,0.66796875
39,0.64453125
41,0.625
42,0.64453125
43,0.6484375
44,0.69921875
45,0.6171875
46,0.54296875
47,0.65234375
48,0.71484375
49,0.7578125
51,0.63671875
52,0.6171875
53,0.6328125
54,0.61328125
55,0.6953125
56,0.6171875
57,0.6875
58,0.75390625
59,0.6953125
61,0.67578125
62,0.6796875
63,0.625
64,0.765625
65,0.7421875
66,0.61328125
67,0.66015625
68,0.56640625
69,0.66796875
71,0.6796875
72,0.73828125
73,0.68359375
74,0.7109375
75,0.76953125
76,0.609375
77,0.7109375
78,0.72265625
79,0.6015625
81,0.5859375
82,0.68359375
83,0.6328125
84,0.71875
85,0.80078125
86,0.69140625
87,0.69921875
88,0.70703125
89,0.625
91,0.703125
92,0.67578125
93,0.8125
94,0.79296875
95,0.66796875
96,0.72265625
97,0.6796875
98,0.7421875
99,0.6484375