edbeeching HF Staff commited on
Commit
db9974d
·
verified ·
1 Parent(s): 3b77d3e

Upload eval_results/open-r1/Qwen2.5-7B-Instruct-GRPO/v05.02-step-000000096/lcb_v4/results_2025-03-26T11-53-23.126487.json with huggingface_hub

Browse files
eval_results/open-r1/Qwen2.5-7B-Instruct-GRPO/v05.02-step-000000096/lcb_v4/results_2025-03-26T11-53-23.126487.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": 148438.750138811,
9
+ "end_time": 150622.350814095,
10
+ "total_evaluation_time_secondes": "2183.6006752839894",
11
+ "model_name": "open-r1/Qwen2.5-7B-Instruct-GRPO",
12
+ "model_sha": "",
13
+ "model_dtype": null,
14
+ "model_size": null
15
+ },
16
+ "results": {
17
+ "extended|lcb:codegeneration_v4|0": {
18
+ "codegen_pass@1:16": 0.13923267326732675,
19
+ "codegen_pass@1:16_stderr": 0.03156256051017152
20
+ },
21
+ "all": {
22
+ "codegen_pass@1:16": 0.13923267326732675,
23
+ "codegen_pass@1:16_stderr": 0.03156256051017152
24
+ }
25
+ },
26
+ "versions": {
27
+ "extended|lcb:codegeneration_v4|0": 0
28
+ },
29
+ "config_tasks": {
30
+ "extended|lcb:codegeneration_v4": {
31
+ "name": "lcb:codegeneration_v4",
32
+ "prompt_function": "lcb_codegeneration_prompt_fn",
33
+ "hf_repo": "livecodebench/code_generation_lite",
34
+ "hf_subset": "v4",
35
+ "metric": [
36
+ {
37
+ "metric_name": "codegen_pass@1:16",
38
+ "higher_is_better": true,
39
+ "category": "5",
40
+ "use_case": "6",
41
+ "sample_level_fn": "codegen_metric",
42
+ "corpus_level_fn": "mean"
43
+ }
44
+ ],
45
+ "hf_revision": null,
46
+ "hf_filter": null,
47
+ "hf_avail_splits": [
48
+ "test"
49
+ ],
50
+ "trust_dataset": true,
51
+ "evaluation_splits": [
52
+ "test"
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
+ "extended"
62
+ ],
63
+ "original_num_docs": 101,
64
+ "effective_num_docs": 101,
65
+ "must_remove_duplicate_docs": false,
66
+ "version": 0
67
+ }
68
+ },
69
+ "summary_tasks": {
70
+ "extended|lcb:codegeneration_v4|0": {
71
+ "hashes": {
72
+ "hash_examples": "ee74af48a322e28a",
73
+ "hash_full_prompts": "3d27e1a95d6fdb09",
74
+ "hash_input_tokens": "6b5b21f1aa61e997",
75
+ "hash_cont_tokens": "f2e30d29c6075533"
76
+ },
77
+ "truncated": 0,
78
+ "non_truncated": 101,
79
+ "padded": 0,
80
+ "non_padded": 101,
81
+ "effective_few_shots": 0.0,
82
+ "num_truncated_few_shots": 0
83
+ }
84
+ },
85
+ "summary_general": {
86
+ "hashes": {
87
+ "hash_examples": "3c08862e3cfc7d00",
88
+ "hash_full_prompts": "4b3dffc6825d9e7d",
89
+ "hash_input_tokens": "9b4b1e63c7467ea5",
90
+ "hash_cont_tokens": "03c449b4a3b66e64"
91
+ },
92
+ "truncated": 0,
93
+ "non_truncated": 101,
94
+ "padded": 0,
95
+ "non_padded": 101,
96
+ "num_truncated_few_shots": 0
97
+ }
98
+ }