lewtun HF Staff commited on
Commit
889a70f
·
verified ·
1 Parent(s): 2b614fa

Upload eval_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B/main/lcb/results_2025-04-30T10-44-48.599957.json with huggingface_hub

Browse files
eval_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B/main/lcb/results_2025-04-30T10-44-48.599957.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config_general": {
3
+ "lighteval_sha": "?",
4
+ "num_fewshot_seeds": 1,
5
+ "max_samples": null,
6
+ "job_id": 0,
7
+ "start_time": 2879386.759314188,
8
+ "end_time": 2893360.613595474,
9
+ "total_evaluation_time_secondes": "13973.854281286243",
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
+ "extended|lcb:codegeneration|0": {
34
+ "codegen_pass@1:16": 0.37406716417910446,
35
+ "codegen_pass@1:16_stderr": 0.0252054846316825
36
+ },
37
+ "all": {
38
+ "codegen_pass@1:16": 0.37406716417910446,
39
+ "codegen_pass@1:16_stderr": 0.0252054846316825
40
+ }
41
+ },
42
+ "versions": {
43
+ "extended|lcb:codegeneration|0": 0
44
+ },
45
+ "config_tasks": {
46
+ "extended|lcb:codegeneration": {
47
+ "name": "lcb:codegeneration",
48
+ "prompt_function": "lcb_codegeneration_prompt_fn",
49
+ "hf_repo": "livecodebench/code_generation_lite",
50
+ "hf_subset": "v4_v5",
51
+ "metric": [
52
+ {
53
+ "metric_name": "codegen_pass@1:16",
54
+ "higher_is_better": true,
55
+ "category": "5",
56
+ "use_case": "6",
57
+ "sample_level_fn": "codegen_metric",
58
+ "corpus_level_fn": "mean"
59
+ }
60
+ ],
61
+ "hf_revision": null,
62
+ "hf_filter": null,
63
+ "hf_avail_splits": [
64
+ "test"
65
+ ],
66
+ "trust_dataset": true,
67
+ "evaluation_splits": [
68
+ "test"
69
+ ],
70
+ "few_shots_split": null,
71
+ "few_shots_select": null,
72
+ "generation_size": 32768,
73
+ "generation_grammar": null,
74
+ "stop_sequence": [],
75
+ "num_samples": null,
76
+ "suite": [
77
+ "extended"
78
+ ],
79
+ "original_num_docs": 268,
80
+ "effective_num_docs": 268,
81
+ "must_remove_duplicate_docs": false,
82
+ "version": 0
83
+ }
84
+ },
85
+ "summary_tasks": {
86
+ "extended|lcb:codegeneration|0": {
87
+ "hashes": {
88
+ "hash_examples": "8db44696993f602e",
89
+ "hash_full_prompts": "16619eb15cd731c4",
90
+ "hash_input_tokens": "f2009e7e4ab48758",
91
+ "hash_cont_tokens": "8eee1ffc9b8d3819"
92
+ },
93
+ "truncated": 0,
94
+ "non_truncated": 268,
95
+ "padded": 0,
96
+ "non_padded": 268,
97
+ "effective_few_shots": 0.0,
98
+ "num_truncated_few_shots": 0
99
+ }
100
+ },
101
+ "summary_general": {
102
+ "hashes": {
103
+ "hash_examples": "cc556c609442b994",
104
+ "hash_full_prompts": "1da488ee9ead0424",
105
+ "hash_input_tokens": "cdf841c20171e0de",
106
+ "hash_cont_tokens": "7822510d029a789d"
107
+ },
108
+ "truncated": 0,
109
+ "non_truncated": 268,
110
+ "padded": 0,
111
+ "non_padded": 268,
112
+ "num_truncated_few_shots": 0
113
+ }
114
+ }