yhyu13
commited on
Commit
•
43b1a6a
1
Parent(s):
505dc7d
Add chatgpt alpaca eval
Browse files- alpaca_eval/chatgpt_fn_--phi-2-alpaca-gpt4-dpo/alpaca_eval_log.txt +632 -0
- alpaca_eval/chatgpt_fn_--phi-2-alpaca-gpt4-dpo/annotation_chatgpt_fn.json +0 -0
- alpaca_eval/chatgpt_fn_--phi-2-alpaca-gpt4-dpo/leaderboard.csv +14 -0
- alpaca_eval/chatgpt_fn_--phi-2-alpaca-gpt4-dpo/model_outputs.json +0 -0
- alpaca_eval/chatgpt_fn_--phi-2-alpaca-gpt4-dpo/reference_outputs.json +0 -0
alpaca_eval/chatgpt_fn_--phi-2-alpaca-gpt4-dpo/alpaca_eval_log.txt
ADDED
@@ -0,0 +1,632 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
INFO:root:Evaluating the phi-2-alpaca-gpt4-dpo outputs.
|
2 |
+
INFO:root:Creating the annotator from `chatgpt_fn`.
|
3 |
+
INFO:root:Saving annotations to `/home/hangyu5/Documents/Git-repoMy/AIResearchVault/repo/LLM-infrastructure/alpaca_eval/src/alpaca_eval/evaluators_configs/chatgpt_fn/annotations_seed0_configs.json`.
|
4 |
+
INFO:root:Loading all annotations from /home/hangyu5/Documents/Git-repoMy/AIResearchVault/repo/LLM-infrastructure/alpaca_eval/src/alpaca_eval/evaluators_configs/chatgpt_fn/annotations_seed0_configs.json.
|
5 |
+
https://api.openai-proxy.org/v1
|
6 |
+
|
7 |
+
INFO:root:Saving all annotations to /home/hangyu5/Documents/Git-repoMy/AIResearchVault/repo/LLM-infrastructure/alpaca_eval/src/alpaca_eval/evaluators_configs/chatgpt_fn/annotations_seed0_configs.json.
|
8 |
+
INFO:root:Loading all annotations from /home/hangyu5/Documents/Git-repoMy/AIResearchVault/repo/LLM-infrastructure/alpaca_eval/src/alpaca_eval/evaluators_configs/chatgpt_fn/annotations_seed0_configs.json.
|
9 |
+
|
10 |
+
INFO:root:Saving all annotations to /home/hangyu5/Documents/Git-repoMy/AIResearchVault/repo/LLM-infrastructure/alpaca_eval/src/alpaca_eval/evaluators_configs/chatgpt_fn/annotations_seed0_configs.json.
|
11 |
+
INFO:root:Loading all annotations from /home/hangyu5/Documents/Git-repoMy/AIResearchVault/repo/LLM-infrastructure/alpaca_eval/src/alpaca_eval/evaluators_configs/chatgpt_fn/annotations_seed0_configs.json.
|
12 |
+
|
13 |
+
INFO:root:Saving all annotations to /home/hangyu5/Documents/Git-repoMy/AIResearchVault/repo/LLM-infrastructure/alpaca_eval/src/alpaca_eval/evaluators_configs/chatgpt_fn/annotations_seed0_configs.json.
|
14 |
+
INFO:root:Loading all annotations from /home/hangyu5/Documents/Git-repoMy/AIResearchVault/repo/LLM-infrastructure/alpaca_eval/src/alpaca_eval/evaluators_configs/chatgpt_fn/annotations_seed0_configs.json.
|
15 |
+
|
16 |
+
INFO:root:Using `openai_completions` on 64 prompts using gpt-3.5-turbo-16k-0613.
|
17 |
+
INFO:root:Kwargs to completion: {'n': 1, 'model': 'gpt-3.5-turbo-16k-0613', 'is_chat': True, 'temperature': 0, 'function_call': {'name': 'print_best_model'}, 'functions': [{'name': 'print_best_model', 'description': 'Print the best model given the preferred output.', 'parameters': {'type': 'object', 'properties': {'best_output': {'type': 'string', 'description': "Name of the best output, should be 'Output (a)' or 'Output (b)'"}}}, 'required': ['best_output']}]}. num_procs=5
|
18 |
+
|
19 |
+
|
20 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
21 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
22 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
23 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
24 |
+
|
25 |
+
|
26 |
+
|
27 |
+
|
28 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
29 |
+
|
30 |
+
|
31 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
32 |
+
|
33 |
+
|
34 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
35 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
36 |
+
|
37 |
+
|
38 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
39 |
+
|
40 |
+
|
41 |
+
|
42 |
+
|
43 |
+
|
44 |
+
|
45 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
46 |
+
|
47 |
+
|
48 |
+
|
49 |
+
|
50 |
+
|
51 |
+
|
52 |
+
|
53 |
+
|
54 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
55 |
+
|
56 |
+
|
57 |
+
|
58 |
+
|
59 |
+
|
60 |
+
|
61 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
62 |
+
|
63 |
+
|
64 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
65 |
+
|
66 |
+
|
67 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
68 |
+
|
69 |
+
|
70 |
+
|
71 |
+
|
72 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
73 |
+
|
74 |
+
|
75 |
+
|
76 |
+
|
77 |
+
|
78 |
+
|
79 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
80 |
+
|
81 |
+
|
82 |
+
|
83 |
+
|
84 |
+
|
85 |
+
|
86 |
+
|
87 |
+
|
88 |
+
|
89 |
+
|
90 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
91 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
92 |
+
|
93 |
+
|
94 |
+
|
95 |
+
|
96 |
+
|
97 |
+
|
98 |
+
|
99 |
+
|
100 |
+
|
101 |
+
|
102 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
103 |
+
|
104 |
+
|
105 |
+
|
106 |
+
|
107 |
+
|
108 |
+
|
109 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
110 |
+
|
111 |
+
|
112 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
113 |
+
|
114 |
+
|
115 |
+
|
116 |
+
|
117 |
+
|
118 |
+
|
119 |
+
|
120 |
+
|
121 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
122 |
+
|
123 |
+
|
124 |
+
|
125 |
+
|
126 |
+
INFO:root:Completed 64 examples in 17.3 seconds.
|
127 |
+
INFO:root:Saving all annotations to /home/hangyu5/Documents/Git-repoMy/AIResearchVault/repo/LLM-infrastructure/alpaca_eval/src/alpaca_eval/evaluators_configs/chatgpt_fn/annotations_seed0_configs.json.
|
128 |
+
INFO:root:Loading all annotations from /home/hangyu5/Documents/Git-repoMy/AIResearchVault/repo/LLM-infrastructure/alpaca_eval/src/alpaca_eval/evaluators_configs/chatgpt_fn/annotations_seed0_configs.json.
|
129 |
+
|
130 |
+
INFO:root:Using `openai_completions` on 128 prompts using gpt-3.5-turbo-16k-0613.
|
131 |
+
INFO:root:Kwargs to completion: {'n': 1, 'model': 'gpt-3.5-turbo-16k-0613', 'is_chat': True, 'temperature': 0, 'function_call': {'name': 'print_best_model'}, 'functions': [{'name': 'print_best_model', 'description': 'Print the best model given the preferred output.', 'parameters': {'type': 'object', 'properties': {'best_output': {'type': 'string', 'description': "Name of the best output, should be 'Output (a)' or 'Output (b)'"}}}, 'required': ['best_output']}]}. num_procs=5
|
132 |
+
|
133 |
+
|
134 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
135 |
+
|
136 |
+
|
137 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
138 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
139 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
140 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
141 |
+
|
142 |
+
|
143 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
144 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
145 |
+
|
146 |
+
|
147 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
148 |
+
|
149 |
+
|
150 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
151 |
+
|
152 |
+
|
153 |
+
|
154 |
+
|
155 |
+
|
156 |
+
|
157 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
158 |
+
|
159 |
+
|
160 |
+
|
161 |
+
|
162 |
+
|
163 |
+
|
164 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
165 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
166 |
+
|
167 |
+
|
168 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
169 |
+
|
170 |
+
|
171 |
+
|
172 |
+
|
173 |
+
|
174 |
+
|
175 |
+
|
176 |
+
|
177 |
+
|
178 |
+
|
179 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
180 |
+
|
181 |
+
|
182 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
183 |
+
|
184 |
+
|
185 |
+
|
186 |
+
|
187 |
+
|
188 |
+
|
189 |
+
|
190 |
+
|
191 |
+
|
192 |
+
|
193 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
194 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
195 |
+
|
196 |
+
|
197 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
198 |
+
|
199 |
+
|
200 |
+
|
201 |
+
|
202 |
+
|
203 |
+
|
204 |
+
|
205 |
+
|
206 |
+
|
207 |
+
|
208 |
+
|
209 |
+
|
210 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
211 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
212 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
213 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
214 |
+
|
215 |
+
|
216 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
217 |
+
|
218 |
+
|
219 |
+
|
220 |
+
|
221 |
+
|
222 |
+
|
223 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
224 |
+
|
225 |
+
|
226 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
227 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
228 |
+
|
229 |
+
|
230 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
231 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
232 |
+
|
233 |
+
|
234 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
235 |
+
|
236 |
+
|
237 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
238 |
+
|
239 |
+
|
240 |
+
|
241 |
+
|
242 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
243 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
244 |
+
|
245 |
+
|
246 |
+
|
247 |
+
|
248 |
+
|
249 |
+
|
250 |
+
|
251 |
+
|
252 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
253 |
+
|
254 |
+
|
255 |
+
|
256 |
+
|
257 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
258 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
259 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
260 |
+
|
261 |
+
|
262 |
+
|
263 |
+
|
264 |
+
|
265 |
+
|
266 |
+
|
267 |
+
|
268 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
269 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
270 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
271 |
+
|
272 |
+
|
273 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
274 |
+
|
275 |
+
|
276 |
+
|
277 |
+
|
278 |
+
|
279 |
+
|
280 |
+
|
281 |
+
|
282 |
+
|
283 |
+
|
284 |
+
|
285 |
+
|
286 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
287 |
+
|
288 |
+
|
289 |
+
|
290 |
+
|
291 |
+
|
292 |
+
|
293 |
+
|
294 |
+
|
295 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
296 |
+
|
297 |
+
|
298 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
299 |
+
|
300 |
+
|
301 |
+
|
302 |
+
|
303 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
304 |
+
|
305 |
+
|
306 |
+
|
307 |
+
|
308 |
+
|
309 |
+
|
310 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
311 |
+
|
312 |
+
|
313 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
314 |
+
|
315 |
+
|
316 |
+
|
317 |
+
|
318 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
319 |
+
|
320 |
+
|
321 |
+
|
322 |
+
|
323 |
+
|
324 |
+
|
325 |
+
|
326 |
+
|
327 |
+
|
328 |
+
|
329 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
330 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
331 |
+
|
332 |
+
|
333 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
334 |
+
|
335 |
+
|
336 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
337 |
+
|
338 |
+
|
339 |
+
INFO:root:Completed 128 examples in 34.5 seconds.
|
340 |
+
INFO:root:Saving all annotations to /home/hangyu5/Documents/Git-repoMy/AIResearchVault/repo/LLM-infrastructure/alpaca_eval/src/alpaca_eval/evaluators_configs/chatgpt_fn/annotations_seed0_configs.json.
|
341 |
+
INFO:root:Loading all annotations from /home/hangyu5/Documents/Git-repoMy/AIResearchVault/repo/LLM-infrastructure/alpaca_eval/src/alpaca_eval/evaluators_configs/chatgpt_fn/annotations_seed0_configs.json.
|
342 |
+
|
343 |
+
INFO:root:Using `openai_completions` on 127 prompts using gpt-3.5-turbo-16k-0613.
|
344 |
+
INFO:root:Kwargs to completion: {'n': 1, 'model': 'gpt-3.5-turbo-16k-0613', 'is_chat': True, 'temperature': 0, 'function_call': {'name': 'print_best_model'}, 'functions': [{'name': 'print_best_model', 'description': 'Print the best model given the preferred output.', 'parameters': {'type': 'object', 'properties': {'best_output': {'type': 'string', 'description': "Name of the best output, should be 'Output (a)' or 'Output (b)'"}}}, 'required': ['best_output']}]}. num_procs=5
|
345 |
+
|
346 |
+
|
347 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
348 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
349 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
350 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
351 |
+
|
352 |
+
|
353 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
354 |
+
|
355 |
+
|
356 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
357 |
+
|
358 |
+
|
359 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
360 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
361 |
+
|
362 |
+
|
363 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
364 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
365 |
+
|
366 |
+
|
367 |
+
|
368 |
+
|
369 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
370 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
371 |
+
|
372 |
+
|
373 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
374 |
+
|
375 |
+
|
376 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
377 |
+
|
378 |
+
|
379 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
380 |
+
|
381 |
+
|
382 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
383 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
384 |
+
|
385 |
+
|
386 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
387 |
+
|
388 |
+
|
389 |
+
|
390 |
+
|
391 |
+
|
392 |
+
|
393 |
+
|
394 |
+
|
395 |
+
|
396 |
+
|
397 |
+
|
398 |
+
|
399 |
+
|
400 |
+
|
401 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
402 |
+
|
403 |
+
|
404 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
405 |
+
|
406 |
+
|
407 |
+
|
408 |
+
|
409 |
+
|
410 |
+
|
411 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
412 |
+
|
413 |
+
|
414 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
415 |
+
|
416 |
+
|
417 |
+
|
418 |
+
|
419 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
420 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
421 |
+
|
422 |
+
|
423 |
+
|
424 |
+
|
425 |
+
|
426 |
+
|
427 |
+
|
428 |
+
|
429 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
430 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
431 |
+
|
432 |
+
|
433 |
+
|
434 |
+
|
435 |
+
|
436 |
+
|
437 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
438 |
+
|
439 |
+
|
440 |
+
|
441 |
+
|
442 |
+
|
443 |
+
|
444 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
445 |
+
|
446 |
+
|
447 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
448 |
+
|
449 |
+
|
450 |
+
|
451 |
+
|
452 |
+
|
453 |
+
|
454 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
455 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
456 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
457 |
+
|
458 |
+
|
459 |
+
|
460 |
+
|
461 |
+
|
462 |
+
|
463 |
+
|
464 |
+
|
465 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
466 |
+
|
467 |
+
|
468 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
469 |
+
|
470 |
+
|
471 |
+
|
472 |
+
|
473 |
+
|
474 |
+
|
475 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
476 |
+
|
477 |
+
|
478 |
+
|
479 |
+
|
480 |
+
|
481 |
+
|
482 |
+
|
483 |
+
|
484 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
485 |
+
|
486 |
+
|
487 |
+
|
488 |
+
|
489 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
490 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
491 |
+
|
492 |
+
|
493 |
+
|
494 |
+
|
495 |
+
|
496 |
+
|
497 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
498 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
499 |
+
|
500 |
+
|
501 |
+
|
502 |
+
|
503 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
504 |
+
|
505 |
+
|
506 |
+
|
507 |
+
|
508 |
+
|
509 |
+
|
510 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
511 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
512 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
513 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
514 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
515 |
+
|
516 |
+
|
517 |
+
|
518 |
+
|
519 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
520 |
+
|
521 |
+
|
522 |
+
|
523 |
+
|
524 |
+
|
525 |
+
|
526 |
+
|
527 |
+
|
528 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
529 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
530 |
+
|
531 |
+
|
532 |
+
|
533 |
+
|
534 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
535 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
536 |
+
|
537 |
+
|
538 |
+
|
539 |
+
|
540 |
+
|
541 |
+
|
542 |
+
|
543 |
+
|
544 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
545 |
+
|
546 |
+
|
547 |
+
|
548 |
+
|
549 |
+
INFO:root:Completed 127 examples in 33.9 seconds.
|
550 |
+
INFO:root:Saving all annotations to /home/hangyu5/Documents/Git-repoMy/AIResearchVault/repo/LLM-infrastructure/alpaca_eval/src/alpaca_eval/evaluators_configs/chatgpt_fn/annotations_seed0_configs.json.
|
551 |
+
INFO:root:Loading all annotations from /home/hangyu5/Documents/Git-repoMy/AIResearchVault/repo/LLM-infrastructure/alpaca_eval/src/alpaca_eval/evaluators_configs/chatgpt_fn/annotations_seed0_configs.json.
|
552 |
+
|
553 |
+
INFO:root:Using `openai_completions` on 37 prompts using gpt-3.5-turbo-16k-0613.
|
554 |
+
INFO:root:Kwargs to completion: {'n': 1, 'model': 'gpt-3.5-turbo-16k-0613', 'is_chat': True, 'temperature': 0, 'function_call': {'name': 'print_best_model'}, 'functions': [{'name': 'print_best_model', 'description': 'Print the best model given the preferred output.', 'parameters': {'type': 'object', 'properties': {'best_output': {'type': 'string', 'description': "Name of the best output, should be 'Output (a)' or 'Output (b)'"}}}, 'required': ['best_output']}]}. num_procs=5
|
555 |
+
|
556 |
+
|
557 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
558 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
559 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
560 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
561 |
+
|
562 |
+
|
563 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
564 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
565 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
566 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
567 |
+
|
568 |
+
|
569 |
+
|
570 |
+
|
571 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
572 |
+
|
573 |
+
|
574 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
575 |
+
|
576 |
+
|
577 |
+
|
578 |
+
|
579 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
580 |
+
|
581 |
+
|
582 |
+
|
583 |
+
|
584 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
585 |
+
|
586 |
+
|
587 |
+
|
588 |
+
|
589 |
+
|
590 |
+
|
591 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
592 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
593 |
+
|
594 |
+
|
595 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
596 |
+
|
597 |
+
|
598 |
+
|
599 |
+
|
600 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
601 |
+
|
602 |
+
|
603 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
604 |
+
|
605 |
+
|
606 |
+
|
607 |
+
|
608 |
+
INFO:httpx:HTTP Request: POST https://api.openai-proxy.org/v1/chat/completions "HTTP/1.1 200 OK"
|
609 |
+
|
610 |
+
|
611 |
+
|
612 |
+
INFO:root:Completed 37 examples in 10.7 seconds.
|
613 |
+
INFO:root:Saving all annotations to /home/hangyu5/Documents/Git-repoMy/AIResearchVault/repo/LLM-infrastructure/alpaca_eval/src/alpaca_eval/evaluators_configs/chatgpt_fn/annotations_seed0_configs.json.
|
614 |
+
INFO:root:Loading all annotations from /home/hangyu5/Documents/Git-repoMy/AIResearchVault/repo/LLM-infrastructure/alpaca_eval/src/alpaca_eval/evaluators_configs/chatgpt_fn/annotations_seed0_configs.json.
|
615 |
+
|
616 |
+
INFO:root:drop 1 outputs that are not[0, 1, 2]
|
617 |
+
INFO:root:Saving all results to output/chatgpt_fn_--phi-2-alpaca-gpt4-dpo-eval
|
618 |
+
INFO:root:Saving result to the precomputed leaderboard at /home/hangyu5/Documents/Git-repoMy/AIResearchVault/repo/LLM-infrastructure/alpaca_eval/src/alpaca_eval/leaderboards/data_AlpacaEval/chatgpt_fn_leaderboard.csv
|
619 |
+
win_rate standard_error n_total avg_length
|
620 |
+
gpt4 73.79 1.54 805 1365
|
621 |
+
claude 70.37 1.60 805 1082
|
622 |
+
chatgpt 66.09 1.66 805 811
|
623 |
+
wizardlm-13b 65.16 1.67 805 985
|
624 |
+
vicuna-13b 64.10 1.69 805 1037
|
625 |
+
guanaco-65b 62.36 1.71 805 1249
|
626 |
+
oasst-rlhf-llama-33b 62.05 1.71 805 1079
|
627 |
+
alpaca-farm-ppo-human 60.25 1.72 805 803
|
628 |
+
falcon-40b-instruct 56.52 1.74 805 662
|
629 |
+
phi-2-alpaca-gpt4-dpo 55.60 1.75 804 4532
|
630 |
+
text_davinci_003 50.00 0.00 805 307
|
631 |
+
alpaca-7b 45.22 1.74 805 396
|
632 |
+
text_davinci_001 28.07 1.56 805 296
|
alpaca_eval/chatgpt_fn_--phi-2-alpaca-gpt4-dpo/annotation_chatgpt_fn.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
alpaca_eval/chatgpt_fn_--phi-2-alpaca-gpt4-dpo/leaderboard.csv
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
,win_rate,standard_error,n_wins,n_wins_base,n_draws,n_total,mode,avg_length
|
2 |
+
gpt4,73.7888198757764,1.5359801545073597,588,205,12,805,minimal,1365
|
3 |
+
claude,70.37267080745342,1.599519507147828,562,234,9,805,minimal,1082
|
4 |
+
chatgpt,66.08695652173913,1.6626479994330317,529,270,6,805,minimal,811
|
5 |
+
wizardlm-13b,65.15527950310559,1.670034107787565,520,276,9,805,minimal,985
|
6 |
+
vicuna-13b,64.09937888198758,1.6895185863153146,515,288,2,805,minimal,1037
|
7 |
+
guanaco-65b,62.36024844720497,1.7086348811605765,502,303,0,805,minimal,1249
|
8 |
+
oasst-rlhf-llama-33b,62.0496894409938,1.7080028976103514,498,304,3,805,minimal,1079
|
9 |
+
alpaca-farm-ppo-human,60.24844720496895,1.7169496733548772,481,316,8,805,minimal,803
|
10 |
+
falcon-40b-instruct,56.52173913043478,1.7438750520312944,453,348,4,805,minimal,662
|
11 |
+
phi-2-alpaca-gpt4-dpo,55.59701492537313,1.7533719245384987,447,357,0,804,community,4532
|
12 |
+
text_davinci_003,50.0,0.0,0,0,805,805,minimal,307
|
13 |
+
alpaca-7b,45.21739130434783,1.7375846781579476,356,433,16,805,minimal,396
|
14 |
+
text_davinci_001,28.07453416149068,1.5602183426587484,216,569,20,805,minimal,296
|
alpaca_eval/chatgpt_fn_--phi-2-alpaca-gpt4-dpo/model_outputs.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
alpaca_eval/chatgpt_fn_--phi-2-alpaca-gpt4-dpo/reference_outputs.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|