lewtun HF staff commited on
Commit
d9fd1e9
·
verified ·
1 Parent(s): 64ca8c1

Upload eval_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/main/aime24/results_2025-02-06T15-18-58.986325.json with huggingface_hub

Browse files
eval_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/main/aime24/results_2025-02-06T15-18-58.986325.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config_general": {
3
+ "lighteval_sha": "?",
4
+ "num_fewshot_seeds": 1,
5
+ "override_batch_size": -1,
6
+ "max_samples": null,
7
+ "job_id": 0,
8
+ "start_time": 83434.21699032,
9
+ "end_time": 83991.449675551,
10
+ "total_evaluation_time_secondes": "557.232685231007",
11
+ "model_name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
12
+ "model_sha": "",
13
+ "model_dtype": null,
14
+ "model_size": null
15
+ },
16
+ "results": {
17
+ "custom|aime24|0": {
18
+ "extractive_match": 0.3,
19
+ "extractive_match_stderr": 0.0850962943396763
20
+ },
21
+ "all": {
22
+ "extractive_match": 0.3,
23
+ "extractive_match_stderr": 0.0850962943396763
24
+ }
25
+ },
26
+ "versions": {
27
+ "custom|aime24|0": 1
28
+ },
29
+ "config_tasks": {
30
+ "custom|aime24": {
31
+ "name": "aime24",
32
+ "prompt_function": "aime_prompt_fn",
33
+ "hf_repo": "HuggingFaceH4/aime_2024",
34
+ "hf_subset": "default",
35
+ "metric": [
36
+ {
37
+ "metric_name": "extractive_match",
38
+ "higher_is_better": true,
39
+ "category": "3",
40
+ "use_case": "1",
41
+ "sample_level_fn": "sample_level_fn",
42
+ "corpus_level_fn": "mean"
43
+ }
44
+ ],
45
+ "hf_revision": null,
46
+ "hf_filter": null,
47
+ "hf_avail_splits": [
48
+ "train"
49
+ ],
50
+ "trust_dataset": false,
51
+ "evaluation_splits": [
52
+ "train"
53
+ ],
54
+ "few_shots_split": null,
55
+ "few_shots_select": null,
56
+ "generation_size": 32768,
57
+ "generation_grammar": null,
58
+ "stop_sequence": [],
59
+ "num_samples": null,
60
+ "suite": [
61
+ "custom"
62
+ ],
63
+ "original_num_docs": 30,
64
+ "effective_num_docs": 30,
65
+ "must_remove_duplicate_docs": false,
66
+ "version": 1
67
+ }
68
+ },
69
+ "summary_tasks": {
70
+ "custom|aime24|0": {
71
+ "hashes": {
72
+ "hash_examples": "18ca0099f8d8f826",
73
+ "hash_full_prompts": "d34905fb622c50aa",
74
+ "hash_input_tokens": "6d1b89ed573bfa89",
75
+ "hash_cont_tokens": "892270bbdf1ba4ca"
76
+ },
77
+ "truncated": 0,
78
+ "non_truncated": 30,
79
+ "padded": 0,
80
+ "non_padded": 30,
81
+ "effective_few_shots": 0.0,
82
+ "num_truncated_few_shots": 0
83
+ }
84
+ },
85
+ "summary_general": {
86
+ "hashes": {
87
+ "hash_examples": "c4769936f28d3d77",
88
+ "hash_full_prompts": "da635cdfbf36e078",
89
+ "hash_input_tokens": "a41b3c52a63d1650",
90
+ "hash_cont_tokens": "566402dfda2de898"
91
+ },
92
+ "truncated": 0,
93
+ "non_truncated": 30,
94
+ "padded": 0,
95
+ "non_padded": 30,
96
+ "num_truncated_few_shots": 0
97
+ }
98
+ }