nkandpa2 commited on
Commit
3f68199
·
verified ·
1 Parent(s): 81c0e48

Delete folder evals/ifeval with huggingface_hub

Browse files
evals/ifeval/results_2025-01-19T18-33-05.553250.json DELETED
@@ -1,138 +0,0 @@
1
- {
2
- "results": {
3
- "ifeval": {
4
- "alias": "ifeval",
5
- "prompt_level_strict_acc,none": 0.10720887245841035,
6
- "prompt_level_strict_acc_stderr,none": 0.013313536005565717,
7
- "inst_level_strict_acc,none": 0.17865707434052758,
8
- "inst_level_strict_acc_stderr,none": "N/A",
9
- "prompt_level_loose_acc,none": 0.11275415896487985,
10
- "prompt_level_loose_acc_stderr,none": 0.013611042535042884,
11
- "inst_level_loose_acc,none": 0.18465227817745802,
12
- "inst_level_loose_acc_stderr,none": "N/A"
13
- }
14
- },
15
- "group_subtasks": {
16
- "ifeval": []
17
- },
18
- "configs": {
19
- "ifeval": {
20
- "task": "ifeval",
21
- "dataset_path": "google/IFEval",
22
- "test_split": "train",
23
- "doc_to_text": "prompt",
24
- "doc_to_target": 0,
25
- "process_results": "def process_results(doc, results):\n inp = InputExample(\n key=doc[\"key\"],\n instruction_id_list=doc[\"instruction_id_list\"],\n prompt=doc[\"prompt\"],\n kwargs=doc[\"kwargs\"],\n )\n response = results[0]\n\n out_strict = test_instruction_following_strict(inp, response)\n out_loose = test_instruction_following_loose(inp, response)\n\n return {\n \"prompt_level_strict_acc\": out_strict.follow_all_instructions,\n \"inst_level_strict_acc\": out_strict.follow_instruction_list,\n \"prompt_level_loose_acc\": out_loose.follow_all_instructions,\n \"inst_level_loose_acc\": out_loose.follow_instruction_list,\n }\n",
26
- "description": "",
27
- "target_delimiter": " ",
28
- "fewshot_delimiter": "\n\n",
29
- "num_fewshot": 0,
30
- "metric_list": [
31
- {
32
- "metric": "prompt_level_strict_acc",
33
- "aggregation": "mean",
34
- "higher_is_better": true
35
- },
36
- {
37
- "metric": "inst_level_strict_acc",
38
- "aggregation": "def agg_inst_level_acc(items):\n flat_items = [item for sublist in items for item in sublist]\n inst_level_acc = sum(flat_items) / len(flat_items)\n return inst_level_acc\n",
39
- "higher_is_better": true
40
- },
41
- {
42
- "metric": "prompt_level_loose_acc",
43
- "aggregation": "mean",
44
- "higher_is_better": true
45
- },
46
- {
47
- "metric": "inst_level_loose_acc",
48
- "aggregation": "def agg_inst_level_acc(items):\n flat_items = [item for sublist in items for item in sublist]\n inst_level_acc = sum(flat_items) / len(flat_items)\n return inst_level_acc\n",
49
- "higher_is_better": true
50
- }
51
- ],
52
- "output_type": "generate_until",
53
- "generation_kwargs": {
54
- "until": [],
55
- "do_sample": false,
56
- "temperature": 0.0,
57
- "max_gen_toks": 1280
58
- },
59
- "repeats": 1,
60
- "should_decontaminate": false,
61
- "metadata": {
62
- "version": 4.0
63
- }
64
- }
65
- },
66
- "versions": {
67
- "ifeval": 4.0
68
- },
69
- "n-shot": {
70
- "ifeval": 0
71
- },
72
- "higher_is_better": {
73
- "ifeval": {
74
- "prompt_level_strict_acc": true,
75
- "inst_level_strict_acc": true,
76
- "prompt_level_loose_acc": true,
77
- "inst_level_loose_acc": true
78
- }
79
- },
80
- "n-samples": {
81
- "ifeval": {
82
- "original": 541,
83
- "effective": 541
84
- }
85
- },
86
- "config": {
87
- "model": "hf",
88
- "model_args": "pretrained=meta-llama/Llama-3.2-1B",
89
- "model_num_parameters": 1235814400,
90
- "model_dtype": "torch.bfloat16",
91
- "model_revision": "main",
92
- "model_sha": "4e20de362430cd3b72f300e6b0f18e50e7166e08",
93
- "batch_size": "8",
94
- "batch_sizes": [],
95
- "device": "cuda:0",
96
- "use_cache": null,
97
- "limit": null,
98
- "bootstrap_iters": 100000,
99
- "gen_kwargs": null,
100
- "random_seed": 0,
101
- "numpy_seed": 1234,
102
- "torch_seed": 1234,
103
- "fewshot_seed": 1234
104
- },
105
- "git_hash": null,
106
- "date": 1737327375.7943065,
107
- "pretty_env_info": "'NoneType' object has no attribute 'splitlines'",
108
- "transformers_version": "4.46.3",
109
- "upper_git_hash": null,
110
- "tokenizer_pad_token": [
111
- "<|end_of_text|>",
112
- "128001"
113
- ],
114
- "tokenizer_eos_token": [
115
- "<|end_of_text|>",
116
- "128001"
117
- ],
118
- "tokenizer_bos_token": [
119
- "<|begin_of_text|>",
120
- "128000"
121
- ],
122
- "eot_token_id": 128001,
123
- "max_length": 131072,
124
- "task_hashes": {
125
- "ifeval": "a9cc24d7d92904c9f59225bb28b88b892d9ab82be222808ea7fa345ffd4500ae"
126
- },
127
- "model_source": "hf",
128
- "model_name": "meta-llama/Llama-3.2-1B",
129
- "model_name_sanitized": "meta-llama__Llama-3.2-1B",
130
- "system_instruction": null,
131
- "system_instruction_sha": null,
132
- "fewshot_as_multiturn": false,
133
- "chat_template": null,
134
- "chat_template_sha": null,
135
- "start_time": 893539.652412064,
136
- "end_time": 895764.932439824,
137
- "total_evaluation_time_seconds": "2225.28002775996"
138
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
evals/ifeval/samples_ifeval_2025-01-19T18-33-05.553250.jsonl DELETED
The diff for this file is too large to render. See raw diff