summaryrefslogtreecommitdiff
path: root/configs/eval_tasks_config.json
blob: e0dda43bf2fd75a9c5fe556c367e9c9ee7501afd (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
[
  {
    "name": "dm_val",
    "task_type": "math",
    "dataset_path": "./data/dm_val.json",
    "is_verifiable": true,
    "metric_type": "accuracy",
    "num_samples": -1,
    "max_gen_len": 2048,
    "temperature": 0.7,
    "top_p": 0.8,
    "num_samples_per_prompt": 1
  },
  {
    "name": "aime24",
    "task_type": "math",
    "dataset_path": "./data/aime24.json",
    "is_verifiable": true,
    "metric_type": "accuracy",
    "num_samples": -1,
    "max_gen_len": 4096,
    "temperature": 0.7,
    "top_p": 0.8,
    "num_samples_per_prompt": 1
  },
  {
    "name": "aime25",
    "task_type": "math",
    "dataset_path": "./data/aime25.json",
    "is_verifiable": true,
    "metric_type": "accuracy",
    "num_samples": -1,
    "max_gen_len": 4096,
    "temperature": 0.7,
    "top_p": 0.8,
    "num_samples_per_prompt": 1
  },
  {
    "name": "amc23",
    "task_type": "math",
    "dataset_path": "./data/amc23.json",
    "is_verifiable": true,
    "metric_type": "accuracy",
    "num_samples": -1,
    "max_gen_len": 2048,
    "temperature": 0.7,
    "top_p": 0.8,
    "num_samples_per_prompt": 1
  },
  {
    "name": "math500",
    "task_type": "math",
    "dataset_path": "./data/math500.json",
    "is_verifiable": true,
    "metric_type": "accuracy",
    "num_samples": 500,
    "max_gen_len": 2048,
    "temperature": 0.7,
    "top_p": 0.8,
    "num_samples_per_prompt": 1
  },
  {
    "name": "gsm8k",
    "task_type": "math",
    "dataset_path": "./data/gsm8k.json",
    "is_verifiable": true,
    "metric_type": "accuracy",
    "num_samples": 500,
    "max_gen_len": 1024,
    "temperature": 0.7,
    "top_p": 0.8,
    "num_samples_per_prompt": 1
  },
  {
    "name": "mmlu_stem",
    "task_type": "qa",
    "dataset_path": "./data/mmlu_stem.json",
    "is_verifiable": true,
    "metric_type": "accuracy",
    "num_samples": 500,
    "max_gen_len": 512,
    "temperature": 0.3,
    "top_p": 0.9,
    "num_samples_per_prompt": 1
  },
  {
    "name": "humaneval",
    "task_type": "code",
    "dataset_path": "./data/humaneval.json",
    "is_verifiable": true,
    "metric_type": "accuracy",
    "num_samples": 164,
    "max_gen_len": 1024,
    "temperature": 0.2,
    "top_p": 0.95,
    "num_samples_per_prompt": 1
  }
]