lewtun HF Staff commited on
Commit
09c76a4
·
verified ·
1 Parent(s): ff4eaeb

Upload eval_results/Qwen/Qwen1.5-0.5B-Chat/main/aimo_kaggle/results_2024-04-22T15-27-33.072805.json with huggingface_hub

Browse files
eval_results/Qwen/Qwen1.5-0.5B-Chat/main/aimo_kaggle/results_2024-04-22T15-27-33.072805.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": 977156.574444742,
9
+ "end_time": 977305.86296132,
10
+ "total_evaluation_time_secondes": "149.2885165780317",
11
+ "model_name": "Qwen/Qwen1.5-0.5B-Chat",
12
+ "model_sha": "f82bd3692de0283f4a4b31e06d164dd8467fb52e",
13
+ "model_dtype": "torch.bfloat16",
14
+ "model_size": "1.05 GB",
15
+ "config": null
16
+ },
17
+ "results": {
18
+ "custom|aimo_kaggle|0": {
19
+ "qem": 0.16666666666666666,
20
+ "qem_stderr": 0.04247059928646881
21
+ },
22
+ "all": {
23
+ "qem": 0.16666666666666666,
24
+ "qem_stderr": 0.04247059928646881
25
+ }
26
+ },
27
+ "versions": {
28
+ "custom|aimo_kaggle|0": 0
29
+ },
30
+ "config_tasks": {
31
+ "custom|aimo_kaggle": {
32
+ "name": "aimo_kaggle",
33
+ "prompt_function": "kaggle_prompt_fn",
34
+ "hf_repo": "AI-MO/kaggle-validation-set-v1",
35
+ "hf_subset": "default",
36
+ "metric": [
37
+ "quasi_exact_match_math"
38
+ ],
39
+ "hf_avail_splits": [
40
+ "train"
41
+ ],
42
+ "evaluation_splits": [
43
+ "train"
44
+ ],
45
+ "few_shots_split": null,
46
+ "few_shots_select": null,
47
+ "generation_size": 2048,
48
+ "stop_sequence": null,
49
+ "output_regex": null,
50
+ "frozen": false,
51
+ "suite": [
52
+ "custom"
53
+ ],
54
+ "original_num_docs": 78,
55
+ "effective_num_docs": 78,
56
+ "trust_dataset": null,
57
+ "must_remove_duplicate_docs": null
58
+ }
59
+ },
60
+ "summary_tasks": {
61
+ "custom|aimo_kaggle|0": {
62
+ "hashes": {
63
+ "hash_examples": "df0b9e4031e0ac93",
64
+ "hash_full_prompts": "149fbbece304ca8c",
65
+ "hash_input_tokens": "87638e69ae967323",
66
+ "hash_cont_tokens": "4fd6feaaaa3f87ca"
67
+ },
68
+ "truncated": 78,
69
+ "non_truncated": 0,
70
+ "padded": 45,
71
+ "non_padded": 33,
72
+ "effective_few_shots": 0.0,
73
+ "num_truncated_few_shots": 0
74
+ }
75
+ },
76
+ "summary_general": {
77
+ "hashes": {
78
+ "hash_examples": "f5b0a912024169d0",
79
+ "hash_full_prompts": "69ac57f47ce9940f",
80
+ "hash_input_tokens": "3260a6fe0e574b57",
81
+ "hash_cont_tokens": "918d06800f3b0c0a"
82
+ },
83
+ "truncated": 78,
84
+ "non_truncated": 0,
85
+ "padded": 45,
86
+ "non_padded": 33,
87
+ "num_truncated_few_shots": 0
88
+ }
89
+ }