Files
Qwen3-4B-Chemistry-RLRT-TR/results/training_scores.csv

92 lines
1.2 KiB
CSV
Raw Normal View History

step,critic_score_mean
1,0.58203125
2,0.36328125
3,0.4765625
4,0.32421875
5,0.4765625
6,0.46484375
7,0.37109375
8,0.53125
9,0.3671875
11,0.44921875
12,0.5390625
13,0.421875
14,0.41796875
15,0.484375
16,0.45703125
17,0.35546875
18,0.40234375
19,0.5390625
21,0.375
22,0.32421875
23,0.55078125
24,0.56640625
25,0.43359375
26,0.5546875
27,0.44921875
28,0.53515625
29,0.36328125
31,0.5625
32,0.5078125
33,0.47265625
34,0.48828125
35,0.4453125
36,0.51953125
37,0.41015625
38,0.4765625
39,0.48046875
41,0.35546875
42,0.40625
43,0.484375
44,0.61328125
45,0.578125
46,0.40234375
47,0.484375
48,0.41015625
49,0.5546875
51,0.640625
52,0.4375
53,0.59375
54,0.34765625
55,0.55859375
56,0.45703125
57,0.46875
58,0.50390625
59,0.4375
61,0.51953125
62,0.5078125
63,0.53515625
64,0.6328125
65,0.5859375
66,0.5390625
67,0.5703125
68,0.3359375
69,0.5859375
71,0.54296875
72,0.56640625
73,0.5703125
74,0.52734375
75,0.6875
76,0.55859375
77,0.59765625
78,0.578125
79,0.47265625
81,0.453125
82,0.61328125
83,0.48828125
84,0.58203125
85,0.6484375
86,0.4375
87,0.3984375
88,0.53515625
89,0.5625
91,0.45703125
92,0.546875
93,0.6875
94,0.64453125
95,0.59375
96,0.5078125
97,0.48046875
98,0.4609375
99,0.4921875