edbeeching HF staff commited on
Commit
02ef020
·
verified ·
1 Parent(s): e416725

Upload eval_results/AI-MO/deepseek-coder-33b-sft/aimo_v01.27/aimo_kaggle_pot/results_2024-05-06T21-04-41.600997.json with huggingface_hub

Browse files
eval_results/AI-MO/deepseek-coder-33b-sft/aimo_v01.27/aimo_kaggle_pot/results_2024-05-06T21-04-41.600997.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 599201.067565778,
9
+ "end_time": 599821.81939217,
10
+ "total_evaluation_time_secondes": "620.7518263919046",
11
+ "model_name": "AI-MO/deepseek-coder-33b-sft",
12
+ "model_sha": "9e88a64f3fe2d5fe0622d0adb6e30af60f53f065",
13
+ "model_dtype": "torch.bfloat16",
14
+ "model_size": "62.59 GB",
15
+ "config": null
16
+ },
17
+ "results": {
18
+ "custom|aimo_kaggle_pot:v0|0": {
19
+ "qem": 0.0,
20
+ "qem_stderr": 0.0
21
+ },
22
+ "all": {
23
+ "qem": 0.0,
24
+ "qem_stderr": 0.0
25
+ }
26
+ },
27
+ "versions": {
28
+ "custom|aimo_kaggle_pot:v0|0": 0
29
+ },
30
+ "config_tasks": {
31
+ "custom|aimo_kaggle_pot:v0": {
32
+ "name": "aimo_kaggle_pot:v0",
33
+ "prompt_function": "kaggle_pot_prompt_fn",
34
+ "hf_repo": "AI-MO/kaggle-validation-set",
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
+ "frozen": false,
51
+ "suite": [
52
+ "custom"
53
+ ],
54
+ "original_num_docs": 50,
55
+ "effective_num_docs": 50,
56
+ "trust_dataset": null,
57
+ "must_remove_duplicate_docs": null
58
+ }
59
+ },
60
+ "summary_tasks": {
61
+ "custom|aimo_kaggle_pot:v0|0": {
62
+ "hashes": {
63
+ "hash_examples": "631fc2e76ca58b0a",
64
+ "hash_full_prompts": "b1f5e7e9d5861f25",
65
+ "hash_input_tokens": "733e9d834e9a6357",
66
+ "hash_cont_tokens": "ca141ee9dfdf5e0d"
67
+ },
68
+ "truncated": 48,
69
+ "non_truncated": 2,
70
+ "padded": 35,
71
+ "non_padded": 15,
72
+ "effective_few_shots": 0.0,
73
+ "num_truncated_few_shots": 0
74
+ }
75
+ },
76
+ "summary_general": {
77
+ "hashes": {
78
+ "hash_examples": "58058a251072a7cd",
79
+ "hash_full_prompts": "2471c91834f9103b",
80
+ "hash_input_tokens": "b5469fa2ae4e0166",
81
+ "hash_cont_tokens": "f2145e9bc8c53819"
82
+ },
83
+ "truncated": 48,
84
+ "non_truncated": 2,
85
+ "padded": 35,
86
+ "non_padded": 15,
87
+ "num_truncated_few_shots": 0
88
+ }
89
+ }