edbeeching HF staff commited on
Commit
b980c45
·
verified ·
1 Parent(s): 7d8dca8

Delete eval_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/main/aime24

Browse files
eval_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/main/aime24/results_2025-01-29T15-31-36.985431.json DELETED
@@ -1,98 +0,0 @@
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": 586568.507312398,
9
- "end_time": 586891.821811319,
10
- "total_evaluation_time_secondes": "323.31449892092496",
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": 0.13333333333333333,
19
- "extractive_match_stderr": 0.06312427686319991
20
- },
21
- "all": {
22
- "extractive_match": 0.13333333333333333,
23
- "extractive_match_stderr": 0.06312427686319991
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": "c8d272b0e0f1e46d"
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": "50cff5d6e1d17695"
91
- },
92
- "truncated": 0,
93
- "non_truncated": 30,
94
- "padded": 0,
95
- "non_padded": 30,
96
- "num_truncated_few_shots": 0
97
- }
98
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eval_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/main/aime24/results_2025-01-29T15-41-23.502842.json DELETED
@@ -1,98 +0,0 @@
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": 587163.524823451,
9
- "end_time": 587478.339194759,
10
- "total_evaluation_time_secondes": "314.814371308079",
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": 0.13333333333333333,
19
- "extractive_match_stderr": 0.06312427686319991
20
- },
21
- "all": {
22
- "extractive_match": 0.13333333333333333,
23
- "extractive_match_stderr": 0.06312427686319991
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": "c8d272b0e0f1e46d"
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": "50cff5d6e1d17695"
91
- },
92
- "truncated": 0,
93
- "non_truncated": 30,
94
- "padded": 0,
95
- "non_padded": 30,
96
- "num_truncated_few_shots": 0
97
- }
98
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eval_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/main/aime24/results_2025-01-29T15-50-22.917041.json DELETED
@@ -1,98 +0,0 @@
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": 587693.785933964,
9
- "end_time": 588017.753334951,
10
- "total_evaluation_time_secondes": "323.9674009870505",
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": 0.13333333333333333,
19
- "extractive_match_stderr": 0.06312427686319991
20
- },
21
- "all": {
22
- "extractive_match": 0.13333333333333333,
23
- "extractive_match_stderr": 0.06312427686319991
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": "c8d272b0e0f1e46d"
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": "50cff5d6e1d17695"
91
- },
92
- "truncated": 0,
93
- "non_truncated": 30,
94
- "padded": 0,
95
- "non_padded": 30,
96
- "num_truncated_few_shots": 0
97
- }
98
- }