lewtun HF staff commited on
Commit
4fbc93a
·
verified ·
1 Parent(s): 257abc2

Upload eval_results/alpindale/WizardLM-2-8x22B/main/ifeval/results_2024-04-16T11-06-30.245588.json with huggingface_hub

Browse files
eval_results/alpindale/WizardLM-2-8x22B/main/ifeval/results_2024-04-16T11-06-30.245588.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 468806.504287818,
9
+ "end_time": 484689.513194686,
10
+ "total_evaluation_time_secondes": "15883.008906867995",
11
+ "model_name": "alpindale/WizardLM-2-8x22B",
12
+ "model_sha": "dd9964910e87b3876a2959911a29cbdb1d518180",
13
+ "model_dtype": "torch.bfloat16",
14
+ "model_size": "263.68 GB",
15
+ "config": null
16
+ },
17
+ "results": {
18
+ "extended|ifeval|0": {
19
+ "prompt_level_strict_acc": 0.5619223659889094,
20
+ "prompt_level_strict_acc_stderr": 0.02135093113549094,
21
+ "inst_level_strict_acc": 0.670263788968825,
22
+ "inst_level_strict_acc_stderr": 0.000496105791739948,
23
+ "prompt_level_loose_acc": 0.6247689463955638,
24
+ "prompt_level_loose_acc_stderr": 0.020835898065035694,
25
+ "inst_level_loose_acc": 0.7206235011990407,
26
+ "inst_level_loose_acc_stderr": 0.0004853658799765977
27
+ },
28
+ "all": {
29
+ "prompt_level_strict_acc": 0.5619223659889094,
30
+ "prompt_level_strict_acc_stderr": 0.02135093113549094,
31
+ "inst_level_strict_acc": 0.670263788968825,
32
+ "inst_level_strict_acc_stderr": 0.000496105791739948,
33
+ "prompt_level_loose_acc": 0.6247689463955638,
34
+ "prompt_level_loose_acc_stderr": 0.020835898065035694,
35
+ "inst_level_loose_acc": 0.7206235011990407,
36
+ "inst_level_loose_acc_stderr": 0.0004853658799765977
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
+ "frozen": false,
63
+ "suite": [
64
+ "extended"
65
+ ],
66
+ "original_num_docs": 541,
67
+ "effective_num_docs": 541,
68
+ "trust_dataset": null,
69
+ "must_remove_duplicate_docs": null
70
+ }
71
+ },
72
+ "summary_tasks": {
73
+ "extended|ifeval|0": {
74
+ "hashes": {
75
+ "hash_examples": "e99cbf567588d7c6",
76
+ "hash_full_prompts": "65ce6f78dff49b9b",
77
+ "hash_input_tokens": "2210f07150c9e23a",
78
+ "hash_cont_tokens": "52c4f16e94e6f5b4"
79
+ },
80
+ "truncated": 541,
81
+ "non_truncated": 0,
82
+ "padded": 118,
83
+ "non_padded": 423,
84
+ "effective_few_shots": 0.0,
85
+ "num_truncated_few_shots": 0
86
+ }
87
+ },
88
+ "summary_general": {
89
+ "hashes": {
90
+ "hash_examples": "ea046ab2c6fc5928",
91
+ "hash_full_prompts": "d0f34a7fe2118466",
92
+ "hash_input_tokens": "e13bde2327c2d4fe",
93
+ "hash_cont_tokens": "c956d685a038b1bc"
94
+ },
95
+ "truncated": 541,
96
+ "non_truncated": 0,
97
+ "padded": 118,
98
+ "non_padded": 423,
99
+ "num_truncated_few_shots": 0
100
+ }
101
+ }