lewtun HF staff commited on
Commit
8962620
·
verified ·
1 Parent(s): ddaafa7

Upload eval_results/orpo-explorers/mistral-7b-orpo-v3.0/main/ifeval/results_2024-04-14T20-36-55.973171.json with huggingface_hub

Browse files
eval_results/orpo-explorers/mistral-7b-orpo-v3.0/main/ifeval/results_2024-04-14T20-36-55.973171.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": 1316407.052685539,
9
+ "end_time": 1317160.853959446,
10
+ "total_evaluation_time_secondes": "753.8012739070691",
11
+ "model_name": "orpo-explorers/mistral-7b-orpo-v3.0",
12
+ "model_sha": "3ff5cd5a7ccd4876dcf4cf2214c332a125d51d42",
13
+ "model_dtype": "torch.bfloat16",
14
+ "model_size": "13.99 GB",
15
+ "config": null
16
+ },
17
+ "results": {
18
+ "extended|ifeval|0": {
19
+ "prompt_level_strict_acc": 0.4399260628465804,
20
+ "prompt_level_strict_acc_stderr": 0.021360708220801976,
21
+ "inst_level_strict_acc": 0.5563549160671463,
22
+ "inst_level_strict_acc_stderr": 0.0005270091163326927,
23
+ "prompt_level_loose_acc": 0.4731977818853974,
24
+ "prompt_level_loose_acc_stderr": 0.021485638661937957,
25
+ "inst_level_loose_acc": 0.5887290167865707,
26
+ "inst_level_loose_acc_stderr": 0.0005318762884551026
27
+ },
28
+ "all": {
29
+ "prompt_level_strict_acc": 0.4399260628465804,
30
+ "prompt_level_strict_acc_stderr": 0.021360708220801976,
31
+ "inst_level_strict_acc": 0.5563549160671463,
32
+ "inst_level_strict_acc_stderr": 0.0005270091163326927,
33
+ "prompt_level_loose_acc": 0.4731977818853974,
34
+ "prompt_level_loose_acc_stderr": 0.021485638661937957,
35
+ "inst_level_loose_acc": 0.5887290167865707,
36
+ "inst_level_loose_acc_stderr": 0.0005318762884551026
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": "46932ca113ba6b0c",
77
+ "hash_input_tokens": "8b2e0300fbfb70bc",
78
+ "hash_cont_tokens": "ec8390443b15c18f"
79
+ },
80
+ "truncated": 541,
81
+ "non_truncated": 0,
82
+ "padded": 123,
83
+ "non_padded": 418,
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": "8ed52f7b74eb0590",
92
+ "hash_input_tokens": "9f4b7e9e7ff95d4a",
93
+ "hash_cont_tokens": "bac5fff0a9396db3"
94
+ },
95
+ "truncated": 541,
96
+ "non_truncated": 0,
97
+ "padded": 123,
98
+ "non_padded": 418,
99
+ "num_truncated_few_shots": 0
100
+ }
101
+ }