Upload eval_results/mistralai/Mixtral-8x7B-Instruct-v0.1/main/ifeval/results_2024-03-02T19-39-49.974051.json with huggingface_hub
Browse files
eval_results/mistralai/Mixtral-8x7B-Instruct-v0.1/main/ifeval/results_2024-03-02T19-39-49.974051.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": 1718023.074120519,
|
9 |
+
"end_time": 1722400.171275446,
|
10 |
+
"total_evaluation_time_secondes": "4377.097154926974",
|
11 |
+
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
12 |
+
"model_sha": "1e637f2d7cb0a9d6fb1922f305cb784995190a83",
|
13 |
+
"model_dtype": "torch.bfloat16",
|
14 |
+
"model_size": "87.49 GB",
|
15 |
+
"config": null
|
16 |
+
},
|
17 |
+
"results": {
|
18 |
+
"custom|ifeval|0": {
|
19 |
+
"prompt_level_strict_acc": 0.49722735674676527,
|
20 |
+
"prompt_level_strict_acc_stderr": 0.021516243323548123,
|
21 |
+
"inst_level_strict_acc": 0.605515587529976,
|
22 |
+
"inst_level_strict_acc_stderr": 0.0004956773219686272,
|
23 |
+
"prompt_level_loose_acc": 0.5508317929759704,
|
24 |
+
"prompt_level_loose_acc_stderr": 0.0214050932335883,
|
25 |
+
"inst_level_loose_acc": 0.6510791366906474,
|
26 |
+
"inst_level_loose_acc_stderr": 0.0004942945051618118
|
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": "50f8a8f5a08077cd",
|
65 |
+
"hash_input_tokens": "fb1ed90207cf652b",
|
66 |
+
"hash_cont_tokens": "4eed2bab8b8ba6c7"
|
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": "9c04db679f2c9132",
|
80 |
+
"hash_input_tokens": "af9a63ef7d2de8ba",
|
81 |
+
"hash_cont_tokens": "8bfcf41538522c12"
|
82 |
+
},
|
83 |
+
"truncated": 0,
|
84 |
+
"non_truncated": 541,
|
85 |
+
"padded": 0,
|
86 |
+
"non_padded": 541,
|
87 |
+
"num_truncated_few_shots": 0
|
88 |
+
}
|
89 |
+
}
|