Files
Qwen3-4B-Physics-GRPO-TR/results/training_scores.csv

92 lines
1.2 KiB
CSV
Raw Normal View History

step,critic_score_mean
1,0.6640625
2,0.578125
3,0.5546875
4,0.625
5,0.7578125
6,0.55859375
7,0.703125
8,0.671875
9,0.64453125
11,0.609375
12,0.59375
13,0.515625
14,0.640625
15,0.6796875
16,0.6953125
17,0.65234375
18,0.40234375
19,0.6875
21,0.671875
22,0.625
23,0.46484375
24,0.7265625
25,0.6640625
26,0.7578125
27,0.71875
28,0.65234375
29,0.6875
31,0.65625
32,0.68359375
33,0.6953125
34,0.65625
35,0.6640625
36,0.56640625
37,0.671875
38,0.61328125
39,0.79296875
41,0.75390625
42,0.5703125
43,0.69140625
44,0.61328125
45,0.625
46,0.7578125
47,0.78125
48,0.69921875
49,0.77734375
51,0.66796875
52,0.65625
53,0.71484375
54,0.73828125
55,0.75390625
56,0.68359375
57,0.59765625
58,0.5859375
59,0.62109375
61,0.68359375
62,0.6328125
63,0.6640625
64,0.66796875
65,0.890625
66,0.7265625
67,0.734375
68,0.7265625
69,0.7265625
71,0.75
72,0.7421875
73,0.61328125
74,0.75390625
75,0.859375
76,0.6875
77,0.703125
78,0.78125
79,0.8046875
81,0.7109375
82,0.63671875
83,0.66796875
84,0.671875
85,0.671875
86,0.6328125
87,0.6875
88,0.66015625
89,0.79296875
91,0.81640625
92,0.69921875
93,0.734375
94,0.7265625
95,0.625
96,0.67578125
97,0.6796875
98,0.70703125
99,0.86328125