Table 4. Iterative Fitting Process for Hyperparameters.

iteration	active workers	eval result	objective: log(1 + loss)	objective runtime	bestsofar (observed)	bestsofar (estim.)	sigma
1	8	best	2.8198	1499.2	2.8198	2.8198	23.245
2	8	best	1.6928	1930.3	1.6928	1.7527	0.00011607
3	8	best	1.6916	2003.1	1.6916	1.7458	0.10798
4	8	accept	1.8157	2040.9	1.6916	1.6916	0.25442
5	8	accept	1.7151	2042.7	1.6916	1.692	0.031193
6	8	accept	1.7796	2043.9	1.6916	1.6983	0.88557
7	8	accept	1.819	1979.5	1.6916	1.6918	0.00021741
8	8	accept	1.7869	1916.2	1.6916	1.7242	0.0005629
9	8	accept	1.7659	2042.8	1.6916	1.735	0.074124
10	8	accept	1.7739	2045.1	1.6916	1.7339	0.0022856
11	8	accept	1.7694	2050.4	1.6916	1.7339	0.00010002
12	8	accept	6.0762	5409.5	1.6916	1.737	819.24
13	8	accept	5.7821	6033.3	1.6916	1.7361	708.63
14	8	accept	1.7222	2189.1	1.6916	1.7262	0.011508
15	8	accept	4.8688	4670.2	1.6916	1.7226	372.45
16	8	accept	1.7966	2220.4	1.6916	1.7452	0.039516
17	8	accept	1.7491	2127.8	1.6916	1.7457	0.016879
18	8	best	1.6747	2207.9	1.6747	1.7161	0.00010001
19	8	accept	1.7589	2202.8	1.6747	1.7154	0.024322
20	8	accept	1.9357	1973.7	1.6747	1.7148	3.3463
21	8	accept	1.69	2189.4	1.6747	1.7141	0.005429
22	8	accept	1.72	2133.9	1.6747	1.7151	0.0011314
23	8	accept	1.705	2133.6	1.6747	1.7148	1.5404
24	8	accept	1.7	2211.5	1.6747	1.7165	0.0099237
25	8	accept	1.7516	2173.2	1.6747	1.7164	0.00010032
26	8	accept	1.7519	2248.1	1.6747	1.7161	0.00010015
27	8	accept	1.7126	2172.2	1.6747	1.7159	0.13824
28	8	accept	2.3887	1972.9	1.6747	1.7138	8.3652
29	8	accept	3.6048	1881.1	1.6747	1.7184	74.358
30	8	accept	1.7374	2040.4	1.6747	1.7182	0.47048