edbeeching HF Staff commited on
Commit
12b3ccc
·
verified ·
1 Parent(s): c365a0d

Upload eval_results/Qwen/Qwen1.5-0.5B-Chat/main/ifeval/results_2024-09-19T15-02-33.736822.json with huggingface_hub

Browse files
eval_results/Qwen/Qwen1.5-0.5B-Chat/main/ifeval/results_2024-09-19T15-02-33.736822.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1318523.106995843,
9
+ "end_time": 1318572.923984487,
10
+ "total_evaluation_time_secondes": "49.81698864419013",
11
+ "model_name": "Qwen/Qwen1.5-0.5B-Chat",
12
+ "model_sha": "",
13
+ "model_dtype": null,
14
+ "model_size": null
15
+ },
16
+ "results": {
17
+ "extended|ifeval|0": {
18
+ "prompt_level_strict_acc": 0.12014787430683918,
19
+ "prompt_level_strict_acc_stderr": 0.013991555826864807,
20
+ "inst_level_strict_acc": 0.21223021582733814,
21
+ "inst_level_strict_acc_stderr": 0.000451535488220651,
22
+ "prompt_level_loose_acc": 0.133086876155268,
23
+ "prompt_level_loose_acc_stderr": 0.01461700934290452,
24
+ "inst_level_loose_acc": 0.2314148681055156,
25
+ "inst_level_loose_acc_stderr": 0.00047257010339242197
26
+ },
27
+ "all": {
28
+ "prompt_level_strict_acc": 0.12014787430683918,
29
+ "prompt_level_strict_acc_stderr": 0.013991555826864807,
30
+ "inst_level_strict_acc": 0.21223021582733814,
31
+ "inst_level_strict_acc_stderr": 0.000451535488220651,
32
+ "prompt_level_loose_acc": 0.133086876155268,
33
+ "prompt_level_loose_acc_stderr": 0.01461700934290452,
34
+ "inst_level_loose_acc": 0.2314148681055156,
35
+ "inst_level_loose_acc_stderr": 0.00047257010339242197
36
+ }
37
+ },
38
+ "versions": {
39
+ "extended|ifeval|0": "0.1"
40
+ },
41
+ "config_tasks": {
42
+ "extended|ifeval": {
43
+ "name": "ifeval",
44
+ "prompt_function": "ifeval_prompt",
45
+ "hf_repo": "google/IFEval",
46
+ "hf_subset": "default",
47
+ "metric": [
48
+ {
49
+ "metric_name": [
50
+ "prompt_level_strict_acc",
51
+ "inst_level_strict_acc",
52
+ "prompt_level_loose_acc",
53
+ "inst_level_loose_acc"
54
+ ],
55
+ "higher_is_better": {
56
+ "prompt_level_strict_acc": true,
57
+ "inst_level_strict_acc": true,
58
+ "prompt_level_loose_acc": true,
59
+ "inst_level_loose_acc": true
60
+ },
61
+ "category": "3",
62
+ "use_case": "1",
63
+ "sample_level_fn": "ifeval_metric",
64
+ "corpus_level_fn": {
65
+ "prompt_level_strict_acc": "mean",
66
+ "inst_level_strict_acc": "agg_inst_level_acc",
67
+ "prompt_level_loose_acc": "mean",
68
+ "inst_level_loose_acc": "agg_inst_level_acc"
69
+ }
70
+ }
71
+ ],
72
+ "hf_revision": null,
73
+ "hf_filter": null,
74
+ "hf_avail_splits": [
75
+ "train"
76
+ ],
77
+ "trust_dataset": false,
78
+ "evaluation_splits": [
79
+ "train"
80
+ ],
81
+ "few_shots_split": "train",
82
+ "few_shots_select": "random_sampling",
83
+ "generation_size": 1280,
84
+ "generation_grammar": null,
85
+ "stop_sequence": [],
86
+ "output_regex": null,
87
+ "num_samples": null,
88
+ "suite": [
89
+ "extended"
90
+ ],
91
+ "original_num_docs": 541,
92
+ "effective_num_docs": 541,
93
+ "must_remove_duplicate_docs": false,
94
+ "version": "0.1",
95
+ "frozen": false
96
+ }
97
+ },
98
+ "summary_tasks": {
99
+ "extended|ifeval|0": {
100
+ "hashes": {
101
+ "hash_examples": "e99cbf567588d7c6",
102
+ "hash_full_prompts": "59b28e3481c07ebd",
103
+ "hash_input_tokens": "6a954e01c279bd0c",
104
+ "hash_cont_tokens": "bdb38b50ae298c9e"
105
+ },
106
+ "truncated": 0,
107
+ "non_truncated": 541,
108
+ "padded": 0,
109
+ "non_padded": 541,
110
+ "effective_few_shots": 0.0,
111
+ "num_truncated_few_shots": 0
112
+ }
113
+ },
114
+ "summary_general": {
115
+ "hashes": {
116
+ "hash_examples": "ea046ab2c6fc5928",
117
+ "hash_full_prompts": "80d0963a452d7fca",
118
+ "hash_input_tokens": "6ac119dc036808b9",
119
+ "hash_cont_tokens": "0de021f6a57008fc"
120
+ },
121
+ "truncated": 0,
122
+ "non_truncated": 541,
123
+ "padded": 0,
124
+ "non_padded": 541,
125
+ "num_truncated_few_shots": 0
126
+ }
127
+ }