Upload results for model meta-llama/Meta-Llama-3.1-70B-Instruct
#693
by
ggbetz
- opened
data/meta-llama/Meta-Llama-3.1-70B-Instruct/cot/24-09-09-19:06:49_idx25/meta-llama__Meta-Llama-3.1-70B-Instruct/results_2024-09-09T22-07-35.408180.json
ADDED
@@ -0,0 +1,292 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"results": {
|
3 |
+
"repudiandae-autem-9860_lsat-rc_cot": {
|
4 |
+
"acc,none": 0.8475836431226765,
|
5 |
+
"acc_stderr,none": 0.021955315121071482,
|
6 |
+
"alias": "repudiandae-autem-9860_lsat-rc_cot"
|
7 |
+
},
|
8 |
+
"repudiandae-autem-9860_lsat-lr_cot": {
|
9 |
+
"acc,none": 0.711764705882353,
|
10 |
+
"acc_stderr,none": 0.020076264678059532,
|
11 |
+
"alias": "repudiandae-autem-9860_lsat-lr_cot"
|
12 |
+
},
|
13 |
+
"repudiandae-autem-9860_lsat-ar_cot": {
|
14 |
+
"acc,none": 0.26956521739130435,
|
15 |
+
"acc_stderr,none": 0.02932276422894953,
|
16 |
+
"alias": "repudiandae-autem-9860_lsat-ar_cot"
|
17 |
+
},
|
18 |
+
"repudiandae-autem-9860_logiqa_cot": {
|
19 |
+
"acc,none": 0.41214057507987223,
|
20 |
+
"acc_stderr,none": 0.01968880784416188,
|
21 |
+
"alias": "repudiandae-autem-9860_logiqa_cot"
|
22 |
+
},
|
23 |
+
"repudiandae-autem-9860_logiqa2_cot": {
|
24 |
+
"acc,none": 0.6005089058524173,
|
25 |
+
"acc_stderr,none": 0.012357345371236998,
|
26 |
+
"alias": "repudiandae-autem-9860_logiqa2_cot"
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"group_subtasks": {
|
30 |
+
"repudiandae-autem-9860_logiqa2_cot": [],
|
31 |
+
"repudiandae-autem-9860_logiqa_cot": [],
|
32 |
+
"repudiandae-autem-9860_lsat-ar_cot": [],
|
33 |
+
"repudiandae-autem-9860_lsat-lr_cot": [],
|
34 |
+
"repudiandae-autem-9860_lsat-rc_cot": []
|
35 |
+
},
|
36 |
+
"configs": {
|
37 |
+
"repudiandae-autem-9860_logiqa2_cot": {
|
38 |
+
"task": "repudiandae-autem-9860_logiqa2_cot",
|
39 |
+
"group": "logikon-bench",
|
40 |
+
"dataset_path": "cot-leaderboard/cot-eval-traces-2.0",
|
41 |
+
"dataset_kwargs": {
|
42 |
+
"data_files": {
|
43 |
+
"test": "data/meta-llama/Meta-Llama-3.1-70B-Instruct/repudiandae-autem-9860-logiqa2.parquet"
|
44 |
+
}
|
45 |
+
},
|
46 |
+
"test_split": "test",
|
47 |
+
"doc_to_text": "def doc_to_text_cot(doc) -> str:\n \"\"\"\n Answer the following question about the given passage. [Base your answer on the reasoning below.]\n \n Passage: <passage>\n \n Question: <question>\n A. <choice1>\n B. <choice2>\n C. <choice3>\n D. <choice4>\n [E. <choice5>]\n \n [Reasoning: <reasoning>]\n \n Answer:\n \"\"\"\n k = len(doc[\"options\"])\n choices = [\"a\", \"b\", \"c\", \"d\", \"e\"][:k]\n prompt = \"Answer the following question about the given passage. Base your answer on the reasoning below.\\n\\n\"\n prompt = \"Passage: \" + doc[\"passage\"] + \"\\n\\n\"\n prompt += \"Question: \" + doc[\"question\"] + \"\\n\"\n for choice, option in zip(choices, doc[\"options\"]):\n prompt += f\"{choice.upper()}. {option}\\n\"\n prompt += \"\\n\"\n prompt += \"Reasoning: \" + doc[\"reasoning_trace\"] + \"\\n\\n\" \n prompt += \"Answer:\"\n return prompt\n",
|
48 |
+
"doc_to_target": "{{answer}}",
|
49 |
+
"doc_to_choice": "{{options}}",
|
50 |
+
"description": "",
|
51 |
+
"target_delimiter": " ",
|
52 |
+
"fewshot_delimiter": "\n\n",
|
53 |
+
"num_fewshot": 0,
|
54 |
+
"metric_list": [
|
55 |
+
{
|
56 |
+
"metric": "acc",
|
57 |
+
"aggregation": "mean",
|
58 |
+
"higher_is_better": true
|
59 |
+
}
|
60 |
+
],
|
61 |
+
"output_type": "multiple_choice",
|
62 |
+
"repeats": 1,
|
63 |
+
"should_decontaminate": false,
|
64 |
+
"metadata": {
|
65 |
+
"version": 0.0
|
66 |
+
}
|
67 |
+
},
|
68 |
+
"repudiandae-autem-9860_logiqa_cot": {
|
69 |
+
"task": "repudiandae-autem-9860_logiqa_cot",
|
70 |
+
"group": "logikon-bench",
|
71 |
+
"dataset_path": "cot-leaderboard/cot-eval-traces-2.0",
|
72 |
+
"dataset_kwargs": {
|
73 |
+
"data_files": {
|
74 |
+
"test": "data/meta-llama/Meta-Llama-3.1-70B-Instruct/repudiandae-autem-9860-logiqa.parquet"
|
75 |
+
}
|
76 |
+
},
|
77 |
+
"test_split": "test",
|
78 |
+
"doc_to_text": "def doc_to_text_cot(doc) -> str:\n \"\"\"\n Answer the following question about the given passage. [Base your answer on the reasoning below.]\n \n Passage: <passage>\n \n Question: <question>\n A. <choice1>\n B. <choice2>\n C. <choice3>\n D. <choice4>\n [E. <choice5>]\n \n [Reasoning: <reasoning>]\n \n Answer:\n \"\"\"\n k = len(doc[\"options\"])\n choices = [\"a\", \"b\", \"c\", \"d\", \"e\"][:k]\n prompt = \"Answer the following question about the given passage. Base your answer on the reasoning below.\\n\\n\"\n prompt = \"Passage: \" + doc[\"passage\"] + \"\\n\\n\"\n prompt += \"Question: \" + doc[\"question\"] + \"\\n\"\n for choice, option in zip(choices, doc[\"options\"]):\n prompt += f\"{choice.upper()}. {option}\\n\"\n prompt += \"\\n\"\n prompt += \"Reasoning: \" + doc[\"reasoning_trace\"] + \"\\n\\n\" \n prompt += \"Answer:\"\n return prompt\n",
|
79 |
+
"doc_to_target": "{{answer}}",
|
80 |
+
"doc_to_choice": "{{options}}",
|
81 |
+
"description": "",
|
82 |
+
"target_delimiter": " ",
|
83 |
+
"fewshot_delimiter": "\n\n",
|
84 |
+
"num_fewshot": 0,
|
85 |
+
"metric_list": [
|
86 |
+
{
|
87 |
+
"metric": "acc",
|
88 |
+
"aggregation": "mean",
|
89 |
+
"higher_is_better": true
|
90 |
+
}
|
91 |
+
],
|
92 |
+
"output_type": "multiple_choice",
|
93 |
+
"repeats": 1,
|
94 |
+
"should_decontaminate": false,
|
95 |
+
"metadata": {
|
96 |
+
"version": 0.0
|
97 |
+
}
|
98 |
+
},
|
99 |
+
"repudiandae-autem-9860_lsat-ar_cot": {
|
100 |
+
"task": "repudiandae-autem-9860_lsat-ar_cot",
|
101 |
+
"group": "logikon-bench",
|
102 |
+
"dataset_path": "cot-leaderboard/cot-eval-traces-2.0",
|
103 |
+
"dataset_kwargs": {
|
104 |
+
"data_files": {
|
105 |
+
"test": "data/meta-llama/Meta-Llama-3.1-70B-Instruct/repudiandae-autem-9860-lsat-ar.parquet"
|
106 |
+
}
|
107 |
+
},
|
108 |
+
"test_split": "test",
|
109 |
+
"doc_to_text": "def doc_to_text_cot(doc) -> str:\n \"\"\"\n Answer the following question about the given passage. [Base your answer on the reasoning below.]\n \n Passage: <passage>\n \n Question: <question>\n A. <choice1>\n B. <choice2>\n C. <choice3>\n D. <choice4>\n [E. <choice5>]\n \n [Reasoning: <reasoning>]\n \n Answer:\n \"\"\"\n k = len(doc[\"options\"])\n choices = [\"a\", \"b\", \"c\", \"d\", \"e\"][:k]\n prompt = \"Answer the following question about the given passage. Base your answer on the reasoning below.\\n\\n\"\n prompt = \"Passage: \" + doc[\"passage\"] + \"\\n\\n\"\n prompt += \"Question: \" + doc[\"question\"] + \"\\n\"\n for choice, option in zip(choices, doc[\"options\"]):\n prompt += f\"{choice.upper()}. {option}\\n\"\n prompt += \"\\n\"\n prompt += \"Reasoning: \" + doc[\"reasoning_trace\"] + \"\\n\\n\" \n prompt += \"Answer:\"\n return prompt\n",
|
110 |
+
"doc_to_target": "{{answer}}",
|
111 |
+
"doc_to_choice": "{{options}}",
|
112 |
+
"description": "",
|
113 |
+
"target_delimiter": " ",
|
114 |
+
"fewshot_delimiter": "\n\n",
|
115 |
+
"num_fewshot": 0,
|
116 |
+
"metric_list": [
|
117 |
+
{
|
118 |
+
"metric": "acc",
|
119 |
+
"aggregation": "mean",
|
120 |
+
"higher_is_better": true
|
121 |
+
}
|
122 |
+
],
|
123 |
+
"output_type": "multiple_choice",
|
124 |
+
"repeats": 1,
|
125 |
+
"should_decontaminate": false,
|
126 |
+
"metadata": {
|
127 |
+
"version": 0.0
|
128 |
+
}
|
129 |
+
},
|
130 |
+
"repudiandae-autem-9860_lsat-lr_cot": {
|
131 |
+
"task": "repudiandae-autem-9860_lsat-lr_cot",
|
132 |
+
"group": "logikon-bench",
|
133 |
+
"dataset_path": "cot-leaderboard/cot-eval-traces-2.0",
|
134 |
+
"dataset_kwargs": {
|
135 |
+
"data_files": {
|
136 |
+
"test": "data/meta-llama/Meta-Llama-3.1-70B-Instruct/repudiandae-autem-9860-lsat-lr.parquet"
|
137 |
+
}
|
138 |
+
},
|
139 |
+
"test_split": "test",
|
140 |
+
"doc_to_text": "def doc_to_text_cot(doc) -> str:\n \"\"\"\n Answer the following question about the given passage. [Base your answer on the reasoning below.]\n \n Passage: <passage>\n \n Question: <question>\n A. <choice1>\n B. <choice2>\n C. <choice3>\n D. <choice4>\n [E. <choice5>]\n \n [Reasoning: <reasoning>]\n \n Answer:\n \"\"\"\n k = len(doc[\"options\"])\n choices = [\"a\", \"b\", \"c\", \"d\", \"e\"][:k]\n prompt = \"Answer the following question about the given passage. Base your answer on the reasoning below.\\n\\n\"\n prompt = \"Passage: \" + doc[\"passage\"] + \"\\n\\n\"\n prompt += \"Question: \" + doc[\"question\"] + \"\\n\"\n for choice, option in zip(choices, doc[\"options\"]):\n prompt += f\"{choice.upper()}. {option}\\n\"\n prompt += \"\\n\"\n prompt += \"Reasoning: \" + doc[\"reasoning_trace\"] + \"\\n\\n\" \n prompt += \"Answer:\"\n return prompt\n",
|
141 |
+
"doc_to_target": "{{answer}}",
|
142 |
+
"doc_to_choice": "{{options}}",
|
143 |
+
"description": "",
|
144 |
+
"target_delimiter": " ",
|
145 |
+
"fewshot_delimiter": "\n\n",
|
146 |
+
"num_fewshot": 0,
|
147 |
+
"metric_list": [
|
148 |
+
{
|
149 |
+
"metric": "acc",
|
150 |
+
"aggregation": "mean",
|
151 |
+
"higher_is_better": true
|
152 |
+
}
|
153 |
+
],
|
154 |
+
"output_type": "multiple_choice",
|
155 |
+
"repeats": 1,
|
156 |
+
"should_decontaminate": false,
|
157 |
+
"metadata": {
|
158 |
+
"version": 0.0
|
159 |
+
}
|
160 |
+
},
|
161 |
+
"repudiandae-autem-9860_lsat-rc_cot": {
|
162 |
+
"task": "repudiandae-autem-9860_lsat-rc_cot",
|
163 |
+
"group": "logikon-bench",
|
164 |
+
"dataset_path": "cot-leaderboard/cot-eval-traces-2.0",
|
165 |
+
"dataset_kwargs": {
|
166 |
+
"data_files": {
|
167 |
+
"test": "data/meta-llama/Meta-Llama-3.1-70B-Instruct/repudiandae-autem-9860-lsat-rc.parquet"
|
168 |
+
}
|
169 |
+
},
|
170 |
+
"test_split": "test",
|
171 |
+
"doc_to_text": "def doc_to_text_cot(doc) -> str:\n \"\"\"\n Answer the following question about the given passage. [Base your answer on the reasoning below.]\n \n Passage: <passage>\n \n Question: <question>\n A. <choice1>\n B. <choice2>\n C. <choice3>\n D. <choice4>\n [E. <choice5>]\n \n [Reasoning: <reasoning>]\n \n Answer:\n \"\"\"\n k = len(doc[\"options\"])\n choices = [\"a\", \"b\", \"c\", \"d\", \"e\"][:k]\n prompt = \"Answer the following question about the given passage. Base your answer on the reasoning below.\\n\\n\"\n prompt = \"Passage: \" + doc[\"passage\"] + \"\\n\\n\"\n prompt += \"Question: \" + doc[\"question\"] + \"\\n\"\n for choice, option in zip(choices, doc[\"options\"]):\n prompt += f\"{choice.upper()}. {option}\\n\"\n prompt += \"\\n\"\n prompt += \"Reasoning: \" + doc[\"reasoning_trace\"] + \"\\n\\n\" \n prompt += \"Answer:\"\n return prompt\n",
|
172 |
+
"doc_to_target": "{{answer}}",
|
173 |
+
"doc_to_choice": "{{options}}",
|
174 |
+
"description": "",
|
175 |
+
"target_delimiter": " ",
|
176 |
+
"fewshot_delimiter": "\n\n",
|
177 |
+
"num_fewshot": 0,
|
178 |
+
"metric_list": [
|
179 |
+
{
|
180 |
+
"metric": "acc",
|
181 |
+
"aggregation": "mean",
|
182 |
+
"higher_is_better": true
|
183 |
+
}
|
184 |
+
],
|
185 |
+
"output_type": "multiple_choice",
|
186 |
+
"repeats": 1,
|
187 |
+
"should_decontaminate": false,
|
188 |
+
"metadata": {
|
189 |
+
"version": 0.0
|
190 |
+
}
|
191 |
+
}
|
192 |
+
},
|
193 |
+
"versions": {
|
194 |
+
"repudiandae-autem-9860_logiqa2_cot": 0.0,
|
195 |
+
"repudiandae-autem-9860_logiqa_cot": 0.0,
|
196 |
+
"repudiandae-autem-9860_lsat-ar_cot": 0.0,
|
197 |
+
"repudiandae-autem-9860_lsat-lr_cot": 0.0,
|
198 |
+
"repudiandae-autem-9860_lsat-rc_cot": 0.0
|
199 |
+
},
|
200 |
+
"n-shot": {
|
201 |
+
"repudiandae-autem-9860_logiqa2_cot": 0,
|
202 |
+
"repudiandae-autem-9860_logiqa_cot": 0,
|
203 |
+
"repudiandae-autem-9860_lsat-ar_cot": 0,
|
204 |
+
"repudiandae-autem-9860_lsat-lr_cot": 0,
|
205 |
+
"repudiandae-autem-9860_lsat-rc_cot": 0
|
206 |
+
},
|
207 |
+
"higher_is_better": {
|
208 |
+
"repudiandae-autem-9860_logiqa2_cot": {
|
209 |
+
"acc": true
|
210 |
+
},
|
211 |
+
"repudiandae-autem-9860_logiqa_cot": {
|
212 |
+
"acc": true
|
213 |
+
},
|
214 |
+
"repudiandae-autem-9860_lsat-ar_cot": {
|
215 |
+
"acc": true
|
216 |
+
},
|
217 |
+
"repudiandae-autem-9860_lsat-lr_cot": {
|
218 |
+
"acc": true
|
219 |
+
},
|
220 |
+
"repudiandae-autem-9860_lsat-rc_cot": {
|
221 |
+
"acc": true
|
222 |
+
}
|
223 |
+
},
|
224 |
+
"n-samples": {
|
225 |
+
"repudiandae-autem-9860_lsat-rc_cot": {
|
226 |
+
"original": 269,
|
227 |
+
"effective": 269
|
228 |
+
},
|
229 |
+
"repudiandae-autem-9860_lsat-lr_cot": {
|
230 |
+
"original": 510,
|
231 |
+
"effective": 510
|
232 |
+
},
|
233 |
+
"repudiandae-autem-9860_lsat-ar_cot": {
|
234 |
+
"original": 230,
|
235 |
+
"effective": 230
|
236 |
+
},
|
237 |
+
"repudiandae-autem-9860_logiqa_cot": {
|
238 |
+
"original": 626,
|
239 |
+
"effective": 626
|
240 |
+
},
|
241 |
+
"repudiandae-autem-9860_logiqa2_cot": {
|
242 |
+
"original": 1572,
|
243 |
+
"effective": 1572
|
244 |
+
}
|
245 |
+
},
|
246 |
+
"config": {
|
247 |
+
"model": "vllm",
|
248 |
+
"model_args": "pretrained=meta-llama/Meta-Llama-3.1-70B-Instruct,revision=main,dtype=bfloat16,tensor_parallel_size=8,gpu_memory_utilization=0.7,trust_remote_code=true,max_length=2048",
|
249 |
+
"batch_size": "auto",
|
250 |
+
"batch_sizes": [],
|
251 |
+
"device": null,
|
252 |
+
"use_cache": null,
|
253 |
+
"limit": null,
|
254 |
+
"bootstrap_iters": 100000,
|
255 |
+
"gen_kwargs": null,
|
256 |
+
"random_seed": 0,
|
257 |
+
"numpy_seed": 1234,
|
258 |
+
"torch_seed": 1234,
|
259 |
+
"fewshot_seed": 1234
|
260 |
+
},
|
261 |
+
"git_hash": "4d6d2d8",
|
262 |
+
"date": 1725911244.8980067,
|
263 |
+
"pretty_env_info": "PyTorch version: 2.3.1+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.4 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.29.2\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-4.18.0-477.51.1.el8_8.x86_64-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.4.131\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-40GB\nGPU 1: NVIDIA A100-SXM4-40GB\nGPU 2: NVIDIA A100-SXM4-40GB\nGPU 3: NVIDIA A100-SXM4-40GB\nGPU 4: NVIDIA A100-SXM4-40GB\nGPU 5: NVIDIA A100-SXM4-40GB\nGPU 6: NVIDIA A100-SXM4-40GB\nGPU 7: NVIDIA A100-SXM4-40GB\n\nNvidia driver version: 550.54.15\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.1.0\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 43 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 256\nOn-line CPU(s) list: 0-255\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7742 64-Core Processor\nCPU family: 23\nModel: 49\nThread(s) per core: 2\nCore(s) per socket: 64\nSocket(s): 2\nStepping: 0\nFrequency boost: enabled\nCPU max MHz: 2250.0000\nCPU min MHz: 1500.0000\nBogoMIPS: 4491.74\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr wbnoinvd arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl umip rdpid overflow_recov succor smca sme sev sev_es\nVirtualization: AMD-V\nL1d cache: 4 MiB (128 instances)\nL1i cache: 4 MiB (128 instances)\nL2 cache: 64 MiB (128 instances)\nL3 cache: 512 MiB (32 instances)\nNUMA node(s): 8\nNUMA node0 CPU(s): 0-15,128-143\nNUMA node1 CPU(s): 16-31,144-159\nNUMA node2 CPU(s): 32-47,160-175\nNUMA node3 CPU(s): 48-63,176-191\nNUMA node4 CPU(s): 64-79,192-207\nNUMA node5 CPU(s): 80-95,208-223\nNUMA node6 CPU(s): 96-111,224-239\nNUMA node7 CPU(s): 112-127,240-255\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Retbleed: Mitigation; untrained return thunk; SMT enabled with STIBP protection\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Retpolines, IBPB conditional, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Not affected\n\nVersions of relevant libraries:\n[pip3] flashinfer==0.1.3+cu121torch2.3\n[pip3] mypy-extensions==1.0.0\n[pip3] numpy==1.24.4\n[pip3] onnx==1.16.0\n[pip3] optree==0.11.0\n[pip3] pytorch-quantization==2.1.2\n[pip3] pytorch-triton==3.0.0+989adb9a2\n[pip3] torch==2.3.1\n[pip3] torch-tensorrt==2.4.0a0\n[pip3] torchvision==0.18.1\n[pip3] triton==2.3.1\n[conda] Could not collect",
|
264 |
+
"transformers_version": "4.43.3",
|
265 |
+
"upper_git_hash": null,
|
266 |
+
"tokenizer_pad_token": [
|
267 |
+
"<|eot_id|>",
|
268 |
+
128009
|
269 |
+
],
|
270 |
+
"tokenizer_eos_token": [
|
271 |
+
"<|eot_id|>",
|
272 |
+
128009
|
273 |
+
],
|
274 |
+
"tokenizer_bos_token": [
|
275 |
+
"<|begin_of_text|>",
|
276 |
+
128000
|
277 |
+
],
|
278 |
+
"eot_token_id": 128009,
|
279 |
+
"max_length": 2048,
|
280 |
+
"task_hashes": {},
|
281 |
+
"model_source": "vllm",
|
282 |
+
"model_name": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
283 |
+
"model_name_sanitized": "meta-llama__Meta-Llama-3.1-70B-Instruct",
|
284 |
+
"system_instruction": null,
|
285 |
+
"system_instruction_sha": null,
|
286 |
+
"fewshot_as_multiturn": false,
|
287 |
+
"chat_template": null,
|
288 |
+
"chat_template_sha": null,
|
289 |
+
"start_time": 7718560.780495724,
|
290 |
+
"end_time": 7719776.927820672,
|
291 |
+
"total_evaluation_time_seconds": "1216.1473249485716"
|
292 |
+
}
|