lewtun HF Staff commited on
Commit
8c3b166
·
verified ·
1 Parent(s): 069c829

Upload eval_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B/main/aime24/results_2025-05-05T15-39-35.769139.json with huggingface_hub

Browse files
eval_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B/main/aime24/results_2025-05-05T15-39-35.769139.json ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config_general": {
3
+ "lighteval_sha": "?",
4
+ "num_fewshot_seeds": 1,
5
+ "max_samples": null,
6
+ "job_id": 0,
7
+ "start_time": 3879609.024844506,
8
+ "end_time": 3881207.742854839,
9
+ "total_evaluation_time_secondes": "1598.7180103333667",
10
+ "model_name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
11
+ "model_sha": "",
12
+ "model_dtype": null,
13
+ "model_size": null,
14
+ "generation_parameters": {
15
+ "early_stopping": null,
16
+ "repetition_penalty": null,
17
+ "frequency_penalty": null,
18
+ "length_penalty": null,
19
+ "presence_penalty": null,
20
+ "max_new_tokens": 32768,
21
+ "min_new_tokens": null,
22
+ "seed": null,
23
+ "stop_tokens": null,
24
+ "temperature": 0.6,
25
+ "top_k": null,
26
+ "min_p": null,
27
+ "top_p": 0.95,
28
+ "truncate_prompt": null,
29
+ "response_format": null
30
+ }
31
+ },
32
+ "results": {
33
+ "lighteval|aime24|0": {
34
+ "math_pass@1:1_samples": 0.4,
35
+ "math_pass@1:1_samples_stderr": 0.09097176522946843,
36
+ "math_pass@1:4_samples": 0.44166666666666665,
37
+ "math_pass@1:4_samples_stderr": 0.0705920501748796,
38
+ "math_pass@1:8_samples": 0.4625,
39
+ "math_pass@1:8_samples_stderr": 0.06967442760488933,
40
+ "math_pass@1:16_samples": 0.48125,
41
+ "math_pass@1:16_samples_stderr": 0.06827816142505748,
42
+ "math_pass@1:32_samples": 0.5010416666666667,
43
+ "math_pass@1:32_samples_stderr": 0.0683583957579014,
44
+ "math_pass@1:64_samples": 0.5083333333333333,
45
+ "math_pass@1:64_samples_stderr": 0.06756062580027589
46
+ },
47
+ "all": {
48
+ "math_pass@1:1_samples": 0.4,
49
+ "math_pass@1:1_samples_stderr": 0.09097176522946843,
50
+ "math_pass@1:4_samples": 0.44166666666666665,
51
+ "math_pass@1:4_samples_stderr": 0.0705920501748796,
52
+ "math_pass@1:8_samples": 0.4625,
53
+ "math_pass@1:8_samples_stderr": 0.06967442760488933,
54
+ "math_pass@1:16_samples": 0.48125,
55
+ "math_pass@1:16_samples_stderr": 0.06827816142505748,
56
+ "math_pass@1:32_samples": 0.5010416666666667,
57
+ "math_pass@1:32_samples_stderr": 0.0683583957579014,
58
+ "math_pass@1:64_samples": 0.5083333333333333,
59
+ "math_pass@1:64_samples_stderr": 0.06756062580027589
60
+ }
61
+ },
62
+ "versions": {
63
+ "lighteval|aime24|0": 2
64
+ },
65
+ "config_tasks": {
66
+ "lighteval|aime24": {
67
+ "name": "aime24",
68
+ "prompt_function": "aime_prompt_fn",
69
+ "hf_repo": "HuggingFaceH4/aime_2024",
70
+ "hf_subset": "default",
71
+ "metric": [
72
+ {
73
+ "metric_name": "math_pass@1:1_samples",
74
+ "higher_is_better": true,
75
+ "category": "5",
76
+ "use_case": "6",
77
+ "sample_level_fn": "compute",
78
+ "corpus_level_fn": "mean"
79
+ },
80
+ {
81
+ "metric_name": "math_pass@1:4_samples",
82
+ "higher_is_better": true,
83
+ "category": "5",
84
+ "use_case": "6",
85
+ "sample_level_fn": "compute",
86
+ "corpus_level_fn": "mean"
87
+ },
88
+ {
89
+ "metric_name": "math_pass@1:8_samples",
90
+ "higher_is_better": true,
91
+ "category": "5",
92
+ "use_case": "6",
93
+ "sample_level_fn": "compute",
94
+ "corpus_level_fn": "mean"
95
+ },
96
+ {
97
+ "metric_name": "math_pass@1:16_samples",
98
+ "higher_is_better": true,
99
+ "category": "5",
100
+ "use_case": "6",
101
+ "sample_level_fn": "compute",
102
+ "corpus_level_fn": "mean"
103
+ },
104
+ {
105
+ "metric_name": "math_pass@1:32_samples",
106
+ "higher_is_better": true,
107
+ "category": "5",
108
+ "use_case": "6",
109
+ "sample_level_fn": "compute",
110
+ "corpus_level_fn": "mean"
111
+ },
112
+ {
113
+ "metric_name": "math_pass@1:64_samples",
114
+ "higher_is_better": true,
115
+ "category": "5",
116
+ "use_case": "6",
117
+ "sample_level_fn": "compute",
118
+ "corpus_level_fn": "mean"
119
+ }
120
+ ],
121
+ "hf_revision": null,
122
+ "hf_filter": null,
123
+ "hf_avail_splits": [
124
+ "train"
125
+ ],
126
+ "trust_dataset": false,
127
+ "evaluation_splits": [
128
+ "train"
129
+ ],
130
+ "few_shots_split": null,
131
+ "few_shots_select": null,
132
+ "generation_size": 32768,
133
+ "generation_grammar": null,
134
+ "stop_sequence": [],
135
+ "num_samples": null,
136
+ "suite": [
137
+ "lighteval"
138
+ ],
139
+ "original_num_docs": 30,
140
+ "effective_num_docs": 30,
141
+ "must_remove_duplicate_docs": false,
142
+ "version": 2
143
+ }
144
+ },
145
+ "summary_tasks": {
146
+ "lighteval|aime24|0": {
147
+ "hashes": {
148
+ "hash_examples": "ddec8fc79d0a014b",
149
+ "hash_full_prompts": "253167becf0dfed7",
150
+ "hash_input_tokens": "bf1cc75b5f12dfb8",
151
+ "hash_cont_tokens": "f114a3f99a00cd7c"
152
+ },
153
+ "truncated": 0,
154
+ "non_truncated": 30,
155
+ "padded": 0,
156
+ "non_padded": 30,
157
+ "effective_few_shots": 0.0,
158
+ "num_truncated_few_shots": 0
159
+ }
160
+ },
161
+ "summary_general": {
162
+ "hashes": {
163
+ "hash_examples": "c903e836a519cf98",
164
+ "hash_full_prompts": "84ff409b6bbf7cc0",
165
+ "hash_input_tokens": "9a8c7e54ce09af84",
166
+ "hash_cont_tokens": "1eddddd5795e4ba3"
167
+ },
168
+ "truncated": 0,
169
+ "non_truncated": 30,
170
+ "padded": 0,
171
+ "non_padded": 30,
172
+ "num_truncated_few_shots": 0
173
+ }
174
+ }