abhishek commited on
Commit
46ed9bc
·
verified ·
1 Parent(s): 3432998

Upload eval_results/abhishek/autotrain-mixtral-8x7b-orpo-v1/main/hellaswag/results_2024-05-01T18-10-18.674527.json with huggingface_hub

Browse files
eval_results/abhishek/autotrain-mixtral-8x7b-orpo-v1/main/hellaswag/results_2024-05-01T18-10-18.674527.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1117.895192294,
9
+ "end_time": 5167.91069733,
10
+ "total_evaluation_time_secondes": "4050.0155050360004",
11
+ "model_name": "abhishek/autotrain-mixtral-8x7b-orpo-v1",
12
+ "model_sha": "a8be37cf01ad767a0c71e0ba3af29c0b3ebcb559",
13
+ "model_dtype": "torch.bfloat16",
14
+ "model_size": "87.49 GB",
15
+ "config": null
16
+ },
17
+ "results": {
18
+ "leaderboard|hellaswag|10": {
19
+ "acc": 0.6608245369448317,
20
+ "acc_stderr": 0.004724619193427587,
21
+ "acc_norm": 0.8556064528978291,
22
+ "acc_norm_stderr": 0.003507699935074236
23
+ },
24
+ "all": {
25
+ "acc": 0.6608245369448317,
26
+ "acc_stderr": 0.004724619193427587,
27
+ "acc_norm": 0.8556064528978291,
28
+ "acc_norm_stderr": 0.003507699935074236
29
+ }
30
+ },
31
+ "versions": {
32
+ "leaderboard|hellaswag|10": 0
33
+ },
34
+ "config_tasks": {
35
+ "leaderboard|hellaswag": {
36
+ "name": "hellaswag",
37
+ "prompt_function": "hellaswag_harness",
38
+ "hf_repo": "hellaswag",
39
+ "hf_subset": "default",
40
+ "metric": [
41
+ "loglikelihood_acc",
42
+ "loglikelihood_acc_norm"
43
+ ],
44
+ "hf_avail_splits": [
45
+ "train",
46
+ "test",
47
+ "validation"
48
+ ],
49
+ "evaluation_splits": [
50
+ "validation"
51
+ ],
52
+ "few_shots_split": null,
53
+ "few_shots_select": "random_sampling_from_train",
54
+ "generation_size": -1,
55
+ "stop_sequence": [
56
+ "\n"
57
+ ],
58
+ "output_regex": null,
59
+ "frozen": false,
60
+ "suite": [
61
+ "leaderboard"
62
+ ],
63
+ "original_num_docs": 10042,
64
+ "effective_num_docs": 10042,
65
+ "trust_dataset": true,
66
+ "must_remove_duplicate_docs": null
67
+ }
68
+ },
69
+ "summary_tasks": {
70
+ "leaderboard|hellaswag|10": {
71
+ "hashes": {
72
+ "hash_examples": "31985c805c3a737e",
73
+ "hash_full_prompts": "451e22e8c3aaeeb6",
74
+ "hash_input_tokens": "211987b65c444c03",
75
+ "hash_cont_tokens": "01fbe12ab59c35bc"
76
+ },
77
+ "truncated": 0,
78
+ "non_truncated": 10042,
79
+ "padded": 40095,
80
+ "non_padded": 73,
81
+ "effective_few_shots": 10.0,
82
+ "num_truncated_few_shots": 0
83
+ }
84
+ },
85
+ "summary_general": {
86
+ "hashes": {
87
+ "hash_examples": "63bc2cf8bae03fbc",
88
+ "hash_full_prompts": "b2452b7405d0326a",
89
+ "hash_input_tokens": "c32a410c27b9a570",
90
+ "hash_cont_tokens": "ff85c47746c926c3"
91
+ },
92
+ "truncated": 0,
93
+ "non_truncated": 10042,
94
+ "padded": 40095,
95
+ "non_padded": 73,
96
+ "num_truncated_few_shots": 0
97
+ }
98
+ }