lewtun HF staff commited on
Commit
3bd1d33
·
verified ·
1 Parent(s): d7d46b5

Upload eval_results/deepseek-ai/deepseek-llm-67b-chat/main/ifeval/results_2024-03-05T03-30-18.059805.json with huggingface_hub

Browse files
eval_results/deepseek-ai/deepseek-llm-67b-chat/main/ifeval/results_2024-03-05T03-30-18.059805.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 3048910.253903816,
9
+ "end_time": 3067826.362818127,
10
+ "total_evaluation_time_secondes": "18916.108914311044",
11
+ "model_name": "deepseek-ai/deepseek-llm-67b-chat",
12
+ "model_sha": "79648bef7658bb824e4630740f6e1484c1b0620b",
13
+ "model_dtype": "torch.bfloat16",
14
+ "model_size": "125.78 GB",
15
+ "config": null
16
+ },
17
+ "results": {
18
+ "custom|ifeval|0": {
19
+ "prompt_level_strict_acc": 0.5046210720887245,
20
+ "prompt_level_strict_acc_stderr": 0.021515655182902067,
21
+ "inst_level_strict_acc": 0.6187050359712231,
22
+ "inst_level_strict_acc_stderr": 0.0004886473327186499,
23
+ "prompt_level_loose_acc": 0.5526802218114603,
24
+ "prompt_level_loose_acc_stderr": 0.02139681502042596,
25
+ "inst_level_loose_acc": 0.6546762589928058,
26
+ "inst_level_loose_acc_stderr": 0.00047924837463123813
27
+ }
28
+ },
29
+ "versions": {
30
+ "custom|ifeval|0": 0
31
+ },
32
+ "config_tasks": {
33
+ "custom|ifeval": {
34
+ "name": "ifeval",
35
+ "prompt_function": "ifeval_prompt",
36
+ "hf_repo": "wis-k/instruction-following-eval",
37
+ "hf_subset": "default",
38
+ "metric": [
39
+ "ifeval_metric"
40
+ ],
41
+ "hf_avail_splits": [
42
+ "train"
43
+ ],
44
+ "evaluation_splits": [
45
+ "train"
46
+ ],
47
+ "few_shots_split": "train",
48
+ "few_shots_select": "random_sampling",
49
+ "generation_size": 1280,
50
+ "stop_sequence": [],
51
+ "output_regex": null,
52
+ "frozen": false,
53
+ "suite": [
54
+ "custom"
55
+ ],
56
+ "original_num_docs": 541,
57
+ "effective_num_docs": 541
58
+ }
59
+ },
60
+ "summary_tasks": {
61
+ "custom|ifeval|0": {
62
+ "hashes": {
63
+ "hash_examples": "e99cbf567588d7c6",
64
+ "hash_full_prompts": "9e50b497b0bfea1b",
65
+ "hash_input_tokens": "410760e9186aa2a8",
66
+ "hash_cont_tokens": "4cfe6ce2c00e8570"
67
+ },
68
+ "truncated": 0,
69
+ "non_truncated": 541,
70
+ "padded": 0,
71
+ "non_padded": 541,
72
+ "effective_few_shots": 0.0,
73
+ "num_truncated_few_shots": 0
74
+ }
75
+ },
76
+ "summary_general": {
77
+ "hashes": {
78
+ "hash_examples": "ea046ab2c6fc5928",
79
+ "hash_full_prompts": "1907749e7908081b",
80
+ "hash_input_tokens": "66ea2dc43333b4f6",
81
+ "hash_cont_tokens": "028fee03012cef08"
82
+ },
83
+ "truncated": 0,
84
+ "non_truncated": 541,
85
+ "padded": 0,
86
+ "non_padded": 541,
87
+ "num_truncated_few_shots": 0
88
+ }
89
+ }