edbeeching HF Staff commited on
Commit
bf55f3b
·
verified ·
1 Parent(s): eb6ec4c

Upload eval_results/edbeeching/mixtral-8x7b-instruct-v0.1_merged/v0.2/winogrande/results_2024-04-14T13-06-04.592120.json with huggingface_hub

Browse files
eval_results/edbeeching/mixtral-8x7b-instruct-v0.1_merged/v0.2/winogrande/results_2024-04-14T13-06-04.592120.json ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config_general": {
3
+ "lighteval_sha": "?",
4
+ "num_fewshot_seeds": 1,
5
+ "override_batch_size": 1,
6
+ "max_samples": null,
7
+ "job_id": "",
8
+ "start_time": 150031.573520117,
9
+ "end_time": 152648.212435551,
10
+ "total_evaluation_time_secondes": "2616.638915433985",
11
+ "model_name": "edbeeching/mixtral-8x7b-instruct-v0.1_merged",
12
+ "model_sha": "02e5e37da870d6382b35fd16e9545bbab51dd218",
13
+ "model_dtype": "torch.bfloat16",
14
+ "model_size": "87.49 GB",
15
+ "config": null
16
+ },
17
+ "results": {
18
+ "leaderboard|winogrande|5": {
19
+ "acc": 0.6724546172059984,
20
+ "acc_stderr": 0.013190169546797017
21
+ },
22
+ "all": {
23
+ "acc": 0.6724546172059984,
24
+ "acc_stderr": 0.013190169546797017
25
+ }
26
+ },
27
+ "versions": {
28
+ "leaderboard|winogrande|5": 0
29
+ },
30
+ "config_tasks": {
31
+ "leaderboard|winogrande": {
32
+ "name": "winogrande",
33
+ "prompt_function": "winogrande",
34
+ "hf_repo": "winogrande",
35
+ "hf_subset": "winogrande_xl",
36
+ "metric": [
37
+ "loglikelihood_acc"
38
+ ],
39
+ "hf_avail_splits": [
40
+ "train",
41
+ "test",
42
+ "validation"
43
+ ],
44
+ "evaluation_splits": [
45
+ "validation"
46
+ ],
47
+ "few_shots_split": null,
48
+ "few_shots_select": "random_sampling",
49
+ "generation_size": -1,
50
+ "stop_sequence": [
51
+ "\n"
52
+ ],
53
+ "output_regex": null,
54
+ "frozen": false,
55
+ "suite": [
56
+ "leaderboard"
57
+ ],
58
+ "original_num_docs": 1267,
59
+ "effective_num_docs": 1267,
60
+ "trust_dataset": true,
61
+ "must_remove_duplicate_docs": null
62
+ }
63
+ },
64
+ "summary_tasks": {
65
+ "leaderboard|winogrande|5": {
66
+ "hashes": {
67
+ "hash_examples": "087d5d1a1afd4c7b",
68
+ "hash_full_prompts": "21d1cf75825bfc31",
69
+ "hash_input_tokens": "74087c8eca355022",
70
+ "hash_cont_tokens": "0dbce81de89a82c0"
71
+ },
72
+ "truncated": 0,
73
+ "non_truncated": 1267,
74
+ "padded": 2391,
75
+ "non_padded": 143,
76
+ "effective_few_shots": 5.0,
77
+ "num_truncated_few_shots": 0
78
+ }
79
+ },
80
+ "summary_general": {
81
+ "hashes": {
82
+ "hash_examples": "b9a49975cc41fab7",
83
+ "hash_full_prompts": "9056d6e5dbbb5d94",
84
+ "hash_input_tokens": "87041500b927b70d",
85
+ "hash_cont_tokens": "366469c3d3fbabf2"
86
+ },
87
+ "truncated": 0,
88
+ "non_truncated": 1267,
89
+ "padded": 2391,
90
+ "non_padded": 143,
91
+ "num_truncated_few_shots": 0
92
+ }
93
+ }