lewtun HF Staff commited on
Commit
659bf1f
·
verified ·
1 Parent(s): 7b8278d

Upload eval_results/lewtun/qwen2-0.5B-lr-3e-6/72e44bab27d4dc1a6573f534de36fa4bb914ba00/ifeval/results_2024-08-24T20-28-36.811969.json with huggingface_hub

Browse files
eval_results/lewtun/qwen2-0.5B-lr-3e-6/72e44bab27d4dc1a6573f534de36fa4bb914ba00/ifeval/results_2024-08-24T20-28-36.811969.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 108438.693492102,
9
+ "end_time": 108987.1098869,
10
+ "total_evaluation_time_secondes": "548.4163947979978",
11
+ "model_name": "lewtun/qwen2-0.5B-lr-3e-6",
12
+ "model_sha": "72e44bab27d4dc1a6573f534de36fa4bb914ba00",
13
+ "model_dtype": "torch.bfloat16",
14
+ "model_size": "1.11 GB",
15
+ "config": null
16
+ },
17
+ "results": {
18
+ "extended|ifeval|0": {
19
+ "prompt_level_strict_acc": 0.11829944547134935,
20
+ "prompt_level_strict_acc_stderr": 0.013898087176706578,
21
+ "inst_level_strict_acc": 0.2158273381294964,
22
+ "inst_level_strict_acc_stderr": 0.00044423365880965,
23
+ "prompt_level_loose_acc": 0.12199630314232902,
24
+ "prompt_level_loose_acc_stderr": 0.014083954960767033,
25
+ "inst_level_loose_acc": 0.22302158273381295,
26
+ "inst_level_loose_acc_stderr": 0.0004467402849055767
27
+ },
28
+ "all": {
29
+ "prompt_level_strict_acc": 0.11829944547134935,
30
+ "prompt_level_strict_acc_stderr": 0.013898087176706578,
31
+ "inst_level_strict_acc": 0.2158273381294964,
32
+ "inst_level_strict_acc_stderr": 0.00044423365880965,
33
+ "prompt_level_loose_acc": 0.12199630314232902,
34
+ "prompt_level_loose_acc_stderr": 0.014083954960767033,
35
+ "inst_level_loose_acc": 0.22302158273381295,
36
+ "inst_level_loose_acc_stderr": 0.0004467402849055767
37
+ }
38
+ },
39
+ "versions": {
40
+ "extended|ifeval|0": 0
41
+ },
42
+ "config_tasks": {
43
+ "extended|ifeval": {
44
+ "name": "ifeval",
45
+ "prompt_function": "ifeval_prompt",
46
+ "hf_repo": "wis-k/instruction-following-eval",
47
+ "hf_subset": "default",
48
+ "metric": [
49
+ "ifeval_metric"
50
+ ],
51
+ "hf_avail_splits": [
52
+ "train"
53
+ ],
54
+ "evaluation_splits": [
55
+ "train"
56
+ ],
57
+ "few_shots_split": "train",
58
+ "few_shots_select": "random_sampling",
59
+ "generation_size": 1280,
60
+ "stop_sequence": [],
61
+ "output_regex": null,
62
+ "num_samples": null,
63
+ "frozen": false,
64
+ "suite": [
65
+ "extended"
66
+ ],
67
+ "original_num_docs": 541,
68
+ "effective_num_docs": 541,
69
+ "trust_dataset": null,
70
+ "must_remove_duplicate_docs": null,
71
+ "version": 0
72
+ }
73
+ },
74
+ "summary_tasks": {
75
+ "extended|ifeval|0": {
76
+ "hashes": {
77
+ "hash_examples": "e99cbf567588d7c6",
78
+ "hash_full_prompts": "59b28e3481c07ebd",
79
+ "hash_input_tokens": "2ed110864a8215dc",
80
+ "hash_cont_tokens": "837c1d8e59049c31"
81
+ },
82
+ "truncated": 541,
83
+ "non_truncated": 0,
84
+ "padded": 111,
85
+ "non_padded": 430,
86
+ "effective_few_shots": 0.0,
87
+ "num_truncated_few_shots": 0
88
+ }
89
+ },
90
+ "summary_general": {
91
+ "hashes": {
92
+ "hash_examples": "ea046ab2c6fc5928",
93
+ "hash_full_prompts": "80d0963a452d7fca",
94
+ "hash_input_tokens": "bfb412c1e9921b7e",
95
+ "hash_cont_tokens": "b294e17c5c100d53"
96
+ },
97
+ "truncated": 541,
98
+ "non_truncated": 0,
99
+ "padded": 111,
100
+ "non_padded": 430,
101
+ "num_truncated_few_shots": 0
102
+ }
103
+ }