Phantom-Optimum Audit and Optimizer Drift Monitor / results.json
Failed on benchmark
1{
2 "seed": 7,
3 "count_sweep": [
4 {
5 "a": 0.0,
6 "N_observed": 2,
7 "N_predicted": 2
8 },
9 {
10 "a": 0.25,
11 "N_observed": 2,
12 "N_predicted": 2
13 },
14 {
15 "a": 0.5,
16 "N_observed": 2,
17 "N_predicted": 2
18 },
19 {
20 "a": 0.75,
21 "N_observed": 2,
22 "N_predicted": 2
23 },
24 {
25 "a": 1.0,
26 "N_observed": 2,
27 "N_predicted": 2
28 },
29 {
30 "a": 1.25,
31 "N_observed": 2,
32 "N_predicted": 2
33 },
34 {
35 "a": 1.5,
36 "N_observed": 2,
37 "N_predicted": 2
38 },
39 {
40 "a": 1.75,
41 "N_observed": 2,
42 "N_predicted": 2
43 },
44 {
45 "a": 2.0,
46 "N_observed": 1,
47 "N_predicted": 1
48 },
49 {
50 "a": 2.25,
51 "N_observed": 1,
52 "N_predicted": 1
53 },
54 {
55 "a": 2.5,
56 "N_observed": 1,
57 "N_predicted": 1
58 },
59 {
60 "a": 2.75,
61 "N_observed": 1,
62 "N_predicted": 1
63 },
64 {
65 "a": 3.0,
66 "N_observed": 1,
67 "N_predicted": 1
68 }
69 ],
70 "drift_sweep": [
71 {
72 "b": 0.0,
73 "e_observed": 0.0,
74 "e_predicted_linear": 0.0
75 },
76 {
77 "b": 0.02,
78 "e_observed": 0.004947944371993862,
79 "e_predicted_linear": 0.005
80 },
81 {
82 "b": 0.04,
83 "e_observed": 0.009795514873250477,
84 "e_predicted_linear": 0.01
85 },
86 {
87 "b": 0.06,
88 "e_observed": 0.014547958214748524,
89 "e_predicted_linear": 0.015
90 },
91 {
92 "b": 0.08,
93 "e_observed": 0.0192100856122841,
94 "e_predicted_linear": 0.02
95 },
96 {
97 "b": 0.1,
98 "e_observed": 0.023786322106388647,
99 "e_predicted_linear": 0.025
100 },
101 {
102 "b": 0.12,
103 "e_observed": 0.028280747617421942,
104 "e_predicted_linear": 0.03
105 },
106 {
107 "b": 0.14,
108 "e_observed": 0.03269713434115673,
109 "e_predicted_linear": 0.035
110 },
111 {
112 "b": 0.16,
113 "e_observed": 0.03703897738555095,
114 "e_predicted_linear": 0.04
115 }
116 ],
117 "curvature_sweep": [
118 {
119 "a": 0.5,
120 "slope_observed": 0.16425908040932277,
121 "slope_predicted": 0.16666666666666666
122 },
123 {
124 "a": 1.0,
125 "slope_observed": 0.24351017415264425,
126 "slope_predicted": 0.25
127 },
128 {
129 "a": 1.5,
130 "slope_observed": 0.4661712618582142,
131 "slope_predicted": 0.5
132 }
133 ],
134 "trajectory": [
135 {
136 "t": 0,
137 "b": 0.0,
138 "validation_loss": 0.0001,
139 "e": 0.0,
140 "N": 2,
141 "J": 0.75
142 },
143 {
144 "t": 1,
145 "b": 0.01,
146 "validation_loss": 9.444444444444444e-05,
147 "e": 0.0024868652080565212,
148 "N": 2,
149 "J": 0.7429164760726776
150 },
151 {
152 "t": 2,
153 "b": 0.02,
154 "validation_loss": 8.888888888888889e-05,
155 "e": 0.004947944371993862,
156 "N": 2,
157 "J": 0.7358082130205136
158 },
159 {
160 "t": 3,
161 "b": 0.03,
162 "validation_loss": 8.333333333333334e-05,
163 "e": 0.007383937646366356,
164 "N": 2,
165 "J": 0.7286754651773547
166 },
167 {
168 "t": 4,
169 "b": 0.04,
170 "validation_loss": 7.777777777777778e-05,
171 "e": 0.009795514873250477,
172 "N": 2,
173 "J": 0.7215184800272865
174 },
175 {
176 "t": 5,
177 "b": 0.05,
178 "validation_loss": 7.222222222222222e-05,
179 "e": 0.012183317161763574,
180 "N": 2,
181 "J": 0.71433749850209
182 },
183 {
184 "t": 6,
185 "b": 0.06,
186 "validation_loss": 6.666666666666668e-05,
187 "e": 0.014547958214748524,
188 "N": 2,
189 "J": 0.7071327552610067
190 },
191 {
192 "t": 7,
193 "b": 0.07,
194 "validation_loss": 6.111111111111111e-05,
195 "e": 0.016890026337057717,
196 "N": 2,
197 "J": 0.6999044789541379
198 },
199 {
200 "t": 8,
201 "b": 0.08,
202 "validation_loss": 5.555555555555556e-05,
203 "e": 0.0192100856122841,
204 "N": 2,
205 "J": 0.6926528924706876
206 },
207 {
208 "t": 9,
209 "b": 0.09,
210 "validation_loss": 5e-05,
211 "e": 0.02150867756494368,
212 "N": 2,
213 "J": 0.6853782131731491
214 },
215 {
216 "t": 10,
217 "b": 0.1,
218 "validation_loss": 4.4444444444444447e-05,
219 "e": 0.023786322106388647,
220 "N": 2,
221 "J": 0.6780806531184411
222 },
223 {
224 "t": 11,
225 "b": 0.11,
226 "validation_loss": 3.8888888888888884e-05,
227 "e": 0.026043518553710787,
228 "N": 2,
229 "J": 0.670760419266911
230 },
231 {
232 "t": 12,
233 "b": 0.12,
234 "validation_loss": 3.333333333333334e-05,
235 "e": 0.028280747617421942,
236 "N": 2,
237 "J": 0.6634177136800471
238 },
239 {
240 "t": 13,
241 "b": 0.13,
242 "validation_loss": 2.777777777777777e-05,
243 "e": 0.030498471182231035,
244 "N": 2,
245 "J": 0.6560527337076693
246 },
247 {
248 "t": 14,
249 "b": 0.14,
250 "validation_loss": 2.222222222222221e-05,
251 "e": 0.03269713434115673,
252 "N": 2,
253 "J": 0.6486656721653072
254 },
255 {
256 "t": 15,
257 "b": 0.15,
258 "validation_loss": 1.6666666666666664e-05,
259 "e": 0.034877165395384435,
260 "N": 2,
261 "J": 0.6412567175024155
262 },
263 {
264 "t": 16,
265 "b": 0.16,
266 "validation_loss": 1.1111111111111105e-05,
267 "e": 0.03703897738555095,
268 "N": 2,
269 "J": 0.633826053962023
270 },
271 {
272 "t": 17,
273 "b": 0.17,
274 "validation_loss": 5.555555555555547e-06,
275 "e": 0.0391829684262861,
276 "N": 2,
277 "J": 0.6263738617323705
278 },
279 {
280 "t": 18,
281 "b": 0.18,
282 "validation_loss": 0.0,
283 "e": 0.04130952259865128,
284 "N": 2,
285 "J": 0.6189003170910433
286 }
287 ],
288 "selection": {
289 "baseline_validation_only": {
290 "t": 18,
291 "b": 0.18,
292 "validation_loss": 0.0,
293 "e": 0.04130952259865128,
294 "N": 2,
295 "J": 0.6189003170910433
296 },
297 "audit_selected": {
298 "t": 4,
299 "b": 0.04,
300 "validation_loss": 7.777777777777778e-05,
301 "e": 0.009795514873250477,
302 "N": 2,
303 "J": 0.7215184800272865
304 },
305 "tau_u": 0.02,
306 "tau_J": 0.03,
307 "N_max": 2
308 },
309 "summary": {
310 "count_all_correct": true,
311 "max_drift_linear_abs_error": 0.002961022614449048,
312 "slope_relative_errors": [
313 0.014445517544063313,
314 0.025959303389422983,
315 0.06765747628357155
316 ]
317 }
318}