lewtun HF staff commited on
Commit
f3ba112
·
verified ·
1 Parent(s): 16d2863

Upload eval_results/orpo-explorers/Mixtral-8x7B-capybara-dpo-7k-v0.1/main/ifeval/results_2024-03-30T22-38-36.845776.json with huggingface_hub

Browse files
eval_results/orpo-explorers/Mixtral-8x7B-capybara-dpo-7k-v0.1/main/ifeval/results_2024-03-30T22-38-36.845776.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": 1980757.365437526,
9
+ "end_time": 1988146.128475196,
10
+ "total_evaluation_time_secondes": "7388.763037669938",
11
+ "model_name": "orpo-explorers/Mixtral-8x7B-capybara-dpo-7k-v0.1",
12
+ "model_sha": "eb40523fd37aa4e3bdce346c46e69eb781fea2a7",
13
+ "model_dtype": "torch.bfloat16",
14
+ "model_size": "87.49 GB",
15
+ "config": null
16
+ },
17
+ "results": {
18
+ "extended|ifeval|0": {
19
+ "prompt_level_strict_acc": 0.5378927911275416,
20
+ "prompt_level_strict_acc_stderr": 0.021454695436204704,
21
+ "inst_level_strict_acc": 0.645083932853717,
22
+ "inst_level_strict_acc_stderr": 0.0005251386045421347,
23
+ "prompt_level_loose_acc": 0.5711645101663586,
24
+ "prompt_level_loose_acc_stderr": 0.02129752256905075,
25
+ "inst_level_loose_acc": 0.670263788968825,
26
+ "inst_level_loose_acc_stderr": 0.0005093480960900186
27
+ },
28
+ "all": {
29
+ "prompt_level_strict_acc": 0.5378927911275416,
30
+ "prompt_level_strict_acc_stderr": 0.021454695436204704,
31
+ "inst_level_strict_acc": 0.645083932853717,
32
+ "inst_level_strict_acc_stderr": 0.0005251386045421347,
33
+ "prompt_level_loose_acc": 0.5711645101663586,
34
+ "prompt_level_loose_acc_stderr": 0.02129752256905075,
35
+ "inst_level_loose_acc": 0.670263788968825,
36
+ "inst_level_loose_acc_stderr": 0.0005093480960900186
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": "23ccf06a3acb20fa"
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": "56d7e32c6c19f829"
94
+ },
95
+ "truncated": 541,
96
+ "non_truncated": 0,
97
+ "padded": 123,
98
+ "non_padded": 418,
99
+ "num_truncated_few_shots": 0
100
+ }
101
+ }