lewtun HF Staff commited on
Commit
eae0b10
·
verified ·
1 Parent(s): b200bc5

Upload eval_results/deepseek-ai/deepseek-math-7b-rl/main/aimo_kaggle_medium_pot/results_2024-05-27T12-35-59.406866.json with huggingface_hub

Browse files
eval_results/deepseek-ai/deepseek-math-7b-rl/main/aimo_kaggle_medium_pot/results_2024-05-27T12-35-59.406866.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config_general": {
3
+ "lighteval_sha": "?",
4
+ "num_fewshot_seeds": 1,
5
+ "override_batch_size": 4,
6
+ "max_samples": null,
7
+ "job_id": "",
8
+ "start_time": 4051098.729740778,
9
+ "end_time": 4051401.342947718,
10
+ "total_evaluation_time_secondes": "302.61320694023743",
11
+ "model_name": "deepseek-ai/deepseek-math-7b-rl",
12
+ "model_sha": "f3cd419a172ff5a100e9a563ebfe7900d78e9740",
13
+ "model_dtype": "torch.bfloat16",
14
+ "model_size": "12.93 GB",
15
+ "config": null
16
+ },
17
+ "results": {
18
+ "custom|aimo_kaggle_medium_pot:v0|0": {
19
+ "qem": 0.025,
20
+ "qem_stderr": 0.024999999999999998
21
+ },
22
+ "all": {
23
+ "qem": 0.025,
24
+ "qem_stderr": 0.024999999999999998
25
+ }
26
+ },
27
+ "versions": {
28
+ "custom|aimo_kaggle_medium_pot:v0|0": 0
29
+ },
30
+ "config_tasks": {
31
+ "custom|aimo_kaggle_medium_pot:v0": {
32
+ "name": "aimo_kaggle_medium_pot:v0",
33
+ "prompt_function": "kaggle_medium_pot_prompt_fn_v0",
34
+ "hf_repo": "AI-MO/kaggle-validation-set-medium",
35
+ "hf_subset": "v0",
36
+ "metric": [
37
+ "quasi_exact_match_code_and_math"
38
+ ],
39
+ "hf_avail_splits": [
40
+ "train"
41
+ ],
42
+ "evaluation_splits": [
43
+ "train"
44
+ ],
45
+ "few_shots_split": null,
46
+ "few_shots_select": null,
47
+ "generation_size": 2048,
48
+ "stop_sequence": null,
49
+ "output_regex": null,
50
+ "num_samples": null,
51
+ "frozen": false,
52
+ "suite": [
53
+ "custom"
54
+ ],
55
+ "original_num_docs": 40,
56
+ "effective_num_docs": 40,
57
+ "trust_dataset": null,
58
+ "must_remove_duplicate_docs": null,
59
+ "version": 0
60
+ }
61
+ },
62
+ "summary_tasks": {
63
+ "custom|aimo_kaggle_medium_pot:v0|0": {
64
+ "hashes": {
65
+ "hash_examples": "2799c24461029dc3",
66
+ "hash_full_prompts": "de6572b914d5bba6",
67
+ "hash_input_tokens": "bb5427e5227cc6b4",
68
+ "hash_cont_tokens": "38c9a1261865d264"
69
+ },
70
+ "truncated": 40,
71
+ "non_truncated": 0,
72
+ "padded": 31,
73
+ "non_padded": 9,
74
+ "effective_few_shots": 0.0,
75
+ "num_truncated_few_shots": 0
76
+ }
77
+ },
78
+ "summary_general": {
79
+ "hashes": {
80
+ "hash_examples": "c72202b0a18ef5f9",
81
+ "hash_full_prompts": "a0429b0dea3e33db",
82
+ "hash_input_tokens": "8e6ef9684e80b71f",
83
+ "hash_cont_tokens": "b1bd4ed4824c97cb"
84
+ },
85
+ "truncated": 40,
86
+ "non_truncated": 0,
87
+ "padded": 31,
88
+ "non_padded": 9,
89
+ "num_truncated_few_shots": 0
90
+ }
91
+ }