Upload eval_results/Qwen/Qwen1.5-7B-Chat/main/ifeval/results_2024-03-28T13-55-10.959962.json with huggingface_hub
Browse files
eval_results/Qwen/Qwen1.5-7B-Chat/main/ifeval/results_2024-03-28T13-55-10.959962.json
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": 668121.272123906,
|
9 |
+
"end_time": 668717.330829345,
|
10 |
+
"total_evaluation_time_secondes": "596.0587054390926",
|
11 |
+
"model_name": "Qwen/Qwen1.5-7B-Chat",
|
12 |
+
"model_sha": "a2662f4bc1afe913a91cd49f794d229a8c28f97e",
|
13 |
+
"model_dtype": "torch.bfloat16",
|
14 |
+
"model_size": "14.88 GB",
|
15 |
+
"config": null
|
16 |
+
},
|
17 |
+
"results": {
|
18 |
+
"extended|ifeval|0": {
|
19 |
+
"prompt_level_strict_acc": 0.36414048059149723,
|
20 |
+
"prompt_level_strict_acc_stderr": 0.020707047958591986,
|
21 |
+
"inst_level_strict_acc": 0.48081534772182255,
|
22 |
+
"inst_level_strict_acc_stderr": 0.0005389541620950422,
|
23 |
+
"prompt_level_loose_acc": 0.40850277264325324,
|
24 |
+
"prompt_level_loose_acc_stderr": 0.02115324409872036,
|
25 |
+
"inst_level_loose_acc": 0.5239808153477218,
|
26 |
+
"inst_level_loose_acc_stderr": 0.0005337352169361823
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"versions": {
|
30 |
+
"extended|ifeval|0": 0
|
31 |
+
},
|
32 |
+
"config_tasks": {
|
33 |
+
"extended|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 |
+
"extended"
|
55 |
+
],
|
56 |
+
"original_num_docs": 541,
|
57 |
+
"effective_num_docs": 541,
|
58 |
+
"trust_dataset": null,
|
59 |
+
"must_remove_duplicate_docs": null
|
60 |
+
}
|
61 |
+
},
|
62 |
+
"summary_tasks": {
|
63 |
+
"extended|ifeval|0": {
|
64 |
+
"hashes": {
|
65 |
+
"hash_examples": "e99cbf567588d7c6",
|
66 |
+
"hash_full_prompts": "1d8bccd45ca3707b",
|
67 |
+
"hash_input_tokens": "4aede348bfb0e38d",
|
68 |
+
"hash_cont_tokens": "2fb0d0953a819f20"
|
69 |
+
},
|
70 |
+
"truncated": 541,
|
71 |
+
"non_truncated": 0,
|
72 |
+
"padded": 111,
|
73 |
+
"non_padded": 430,
|
74 |
+
"effective_few_shots": 0.0,
|
75 |
+
"num_truncated_few_shots": 0
|
76 |
+
}
|
77 |
+
},
|
78 |
+
"summary_general": {
|
79 |
+
"hashes": {
|
80 |
+
"hash_examples": "ea046ab2c6fc5928",
|
81 |
+
"hash_full_prompts": "41a5572cc1263dc7",
|
82 |
+
"hash_input_tokens": "dc284e5de619e6a7",
|
83 |
+
"hash_cont_tokens": "d0e068c70912d569"
|
84 |
+
},
|
85 |
+
"truncated": 541,
|
86 |
+
"non_truncated": 0,
|
87 |
+
"padded": 111,
|
88 |
+
"non_padded": 430,
|
89 |
+
"num_truncated_few_shots": 0
|
90 |
+
}
|
91 |
+
}
|