PSO/benchmark_results/pso_v6_heavy_tasks.csv at master

mirror of https://github.com/jung-geun/PSO.git synced 2026-09-20 14:11:48 +09:00

Files

T

jung-geun 813433000a feat: modernize PSO and add convergence research

Migrate the package and examples to the tensor-native PyTorch implementation, add benchmark evidence, and add the guarded post-training convergence protocol with TensorBoard progress monitoring and hash-verified recovery.

Constraint: Preserve one-shot official-test sealing and auditable research artifacts

Rejected: Commit local .omc runs and downloaded datasets | multi-gigabyte runtime state is machine-local

Confidence: high

Scope-risk: broad

Not-tested: Production CUDA run on pieroot-server

2026-09-07 22:03:25 +09:00

7.5 KiB

Raw Permalink Blame History

1	section	workload	method	metric	value
2	protocol	global	all	version	HEAVY-TASK-PSO-V6 1.0.0
3	protocol	global	all	official_test_data_loaded	False
4	protocol	global	all	official_test_evaluations	0
5	baseline	mnist_compact	untrained	val_nll	2.325095
6	baseline	mnist_compact	untrained	val_accuracy	6.65
7	baseline	mnist_wide	untrained	val_nll	2.32458
8	baseline	mnist_wide	untrained	val_accuracy	9.31
9	baseline	fashion_compact	untrained	val_nll	2.320302
10	baseline	fashion_compact	untrained	val_accuracy	8.08
11	baseline	fashion_wide	untrained	val_nll	2.311222
12	baseline	fashion_wide	untrained	val_accuracy	8.77
13	screen	mnist_compact	G0	val_nll	2.019988
14	screen	mnist_compact	G0	val_acc	33.32
15	screen	mnist_compact	G0	gbest_loss	2.014459
16	screen	mnist_compact	G0	gbest_acc	34.4
17	screen	mnist_compact	G0	throughput_sps	1106883.43
18	screen	mnist_compact	G5	val_nll	1.959743
19	screen	mnist_compact	G5	val_acc	33.95
20	screen	mnist_compact	G5	gbest_loss	1.971574
21	screen	mnist_compact	G5	gbest_acc	32.35
22	screen	mnist_compact	G5	throughput_sps	1139465.88
23	screen	mnist_compact	G6	val_nll	1.957307
24	screen	mnist_compact	G6	val_acc	35.11
25	screen	mnist_compact	G6	gbest_loss	1.941859
26	screen	mnist_compact	G6	gbest_acc	35.35
27	screen	mnist_compact	G6	throughput_sps	1340969.41
28	screen	mnist_compact	G8	val_nll	1.690442
29	screen	mnist_compact	G8	val_acc	43.88
30	screen	mnist_compact	G8	gbest_loss	1.675063
31	screen	mnist_compact	G8	gbest_acc	43.6
32	screen	mnist_compact	G8	throughput_sps	984615.38
33	screen	mnist_wide	G0	val_nll	2.088156
34	screen	mnist_wide	G0	val_acc	33.19
35	screen	mnist_wide	G0	gbest_loss	2.087951
36	screen	mnist_wide	G0	gbest_acc	32.45
37	screen	mnist_wide	G0	throughput_sps	595459.62
38	screen	mnist_wide	G5	val_nll	1.913566
39	screen	mnist_wide	G5	val_acc	39.87
40	screen	mnist_wide	G5	gbest_loss	1.924357
41	screen	mnist_wide	G5	gbest_acc	39.5
42	screen	mnist_wide	G5	throughput_sps	772511.47
43	screen	mnist_wide	G6	val_nll	2.017511
44	screen	mnist_wide	G6	val_acc	29.46
45	screen	mnist_wide	G6	gbest_loss	2.014518
46	screen	mnist_wide	G6	gbest_acc	27.8
47	screen	mnist_wide	G6	throughput_sps	777013.35
48	screen	mnist_wide	G8	val_nll	2.056341
49	screen	mnist_wide	G8	val_acc	20.43
50	screen	mnist_wide	G8	gbest_loss	2.062368
51	screen	mnist_wide	G8	gbest_acc	20.3
52	screen	mnist_wide	G8	throughput_sps	855005.34
53	screen	fashion_compact	G0	val_nll	1.969548
54	screen	fashion_compact	G0	val_acc	28.25
55	screen	fashion_compact	G0	gbest_loss	1.96974
56	screen	fashion_compact	G0	gbest_acc	28.15
57	screen	fashion_compact	G0	throughput_sps	1219977.13
58	screen	fashion_compact	G5	val_nll	1.892402
59	screen	fashion_compact	G5	val_acc	34.31
60	screen	fashion_compact	G5	gbest_loss	1.874629
61	screen	fashion_compact	G5	gbest_acc	36.6
62	screen	fashion_compact	G5	throughput_sps	1122281.97
63	screen	fashion_compact	G6	val_nll	1.824273
64	screen	fashion_compact	G6	val_acc	35.2
65	screen	fashion_compact	G6	gbest_loss	1.844914
66	screen	fashion_compact	G6	gbest_acc	33.5
67	screen	fashion_compact	G6	throughput_sps	1152322.65
68	screen	fashion_compact	G8	val_nll	1.88018
69	screen	fashion_compact	G8	val_acc	30.85
70	screen	fashion_compact	G8	gbest_loss	1.895269
71	screen	fashion_compact	G8	gbest_acc	28.85
72	screen	fashion_compact	G8	throughput_sps	1193139.45
73	screen	fashion_wide	G0	val_nll	1.981316
74	screen	fashion_wide	G0	val_acc	36.39
75	screen	fashion_wide	G0	gbest_loss	1.98436
76	screen	fashion_wide	G0	gbest_acc	36.05
77	screen	fashion_wide	G0	throughput_sps	540327.57
78	screen	fashion_wide	G5	val_nll	1.945862
79	screen	fashion_wide	G5	val_acc	31.97
80	screen	fashion_wide	G5	gbest_loss	1.938569
81	screen	fashion_wide	G5	gbest_acc	33.3
82	screen	fashion_wide	G5	throughput_sps	807401.18
83	screen	fashion_wide	G6	val_nll	1.975825
84	screen	fashion_wide	G6	val_acc	28.64
85	screen	fashion_wide	G6	gbest_loss	1.960139
86	screen	fashion_wide	G6	gbest_acc	28.1
87	screen	fashion_wide	G6	throughput_sps	735350.44
88	screen	fashion_wide	G8	val_nll	1.987923
89	screen	fashion_wide	G8	val_acc	28.69
90	screen	fashion_wide	G8	gbest_loss	1.976977
91	screen	fashion_wide	G8	gbest_acc	28.45
92	screen	fashion_wide	G8	throughput_sps	865800.87
93	confirm	mnist_compact	G8	val_acc_mean	49.153333
94	confirm	mnist_compact	G8	val_acc_std	1.320656
95	confirm	mnist_compact	G8	val_nll_mean	1.518089
96	confirm	mnist_compact	G8	val_nll_std	0.061523
97	confirm	mnist_compact	G8	wall_time_sec_mean	4.530167
98	confirm	mnist_compact	G6	val_acc_mean	45.966667
99	confirm	mnist_compact	G6	val_acc_std	3.545438
100	confirm	mnist_compact	G6	val_nll_mean	1.642081
101	confirm	mnist_compact	G6	val_nll_std	0.091398
102	confirm	mnist_compact	G6	wall_time_sec_mean	5.2706
103	confirm	mnist_wide	G8	val_acc_mean	41.03
104	confirm	mnist_wide	G8	val_acc_std	4.055083
105	confirm	mnist_wide	G8	val_nll_mean	1.733351
106	confirm	mnist_wide	G8	val_nll_std	0.084331
107	confirm	mnist_wide	G8	wall_time_sec_mean	9.4569
108	confirm	mnist_wide	G5	val_acc_mean	43.86
109	confirm	mnist_wide	G5	val_acc_std	3.512222
110	confirm	mnist_wide	G5	val_nll_mean	1.721259
111	confirm	mnist_wide	G5	val_nll_std	0.098656
112	confirm	mnist_wide	G5	wall_time_sec_mean	9.868467
113	confirm	fashion_compact	G8	val_acc_mean	47.003333
114	confirm	fashion_compact	G8	val_acc_std	5.2259
115	confirm	fashion_compact	G8	val_nll_mean	1.511217
116	confirm	fashion_compact	G8	val_nll_std	0.168628
117	confirm	fashion_compact	G8	wall_time_sec_mean	5.0146
118	confirm	fashion_compact	G6	val_acc_mean	45.616667
119	confirm	fashion_compact	G6	val_acc_std	3.585392
120	confirm	fashion_compact	G6	val_nll_mean	1.584443
121	confirm	fashion_compact	G6	val_nll_std	0.053077
122	confirm	fashion_compact	G6	wall_time_sec_mean	4.839267
123	confirm	fashion_wide	G8	val_acc_mean	41.666667
124	confirm	fashion_wide	G8	val_acc_std	2.269016
125	confirm	fashion_wide	G8	val_nll_mean	1.615937
126	confirm	fashion_wide	G8	val_nll_std	0.036692
127	confirm	fashion_wide	G8	wall_time_sec_mean	9.499333
128	confirm	fashion_wide	G5	val_acc_mean	46.31
129	confirm	fashion_wide	G5	val_acc_std	7.568494
130	confirm	fashion_wide	G5	val_nll_mean	1.525747
131	confirm	fashion_wide	G5	val_nll_std	0.149706
132	confirm	fashion_wide	G5	wall_time_sec_mean	10.038833
133	feasibility	mnist_compact	G8	execution_feasible	True
134	feasibility	mnist_compact	G8	optimization_feasible	True
135	feasibility	mnist_compact	G8	mean_val_nll	1.518089
136	feasibility	mnist_compact	G8	mean_val_acc	49.1533
137	feasibility	mnist_compact	G6	execution_feasible	True
138	feasibility	mnist_compact	G6	optimization_feasible	True
139	feasibility	mnist_compact	G6	mean_val_nll	1.642081
140	feasibility	mnist_compact	G6	mean_val_acc	45.9667
141	feasibility	mnist_wide	G8	execution_feasible	True
142	feasibility	mnist_wide	G8	optimization_feasible	True
143	feasibility	mnist_wide	G8	mean_val_nll	1.733351
144	feasibility	mnist_wide	G8	mean_val_acc	41.03
145	feasibility	mnist_wide	G5	execution_feasible	True
146	feasibility	mnist_wide	G5	optimization_feasible	True
147	feasibility	mnist_wide	G5	mean_val_nll	1.721259
148	feasibility	mnist_wide	G5	mean_val_acc	43.86
149	feasibility	fashion_compact	G8	execution_feasible	True
150	feasibility	fashion_compact	G8	optimization_feasible	True
151	feasibility	fashion_compact	G8	mean_val_nll	1.511217
152	feasibility	fashion_compact	G8	mean_val_acc	47.0033
153	feasibility	fashion_compact	G6	execution_feasible	True
154	feasibility	fashion_compact	G6	optimization_feasible	True
155	feasibility	fashion_compact	G6	mean_val_nll	1.584443
156	feasibility	fashion_compact	G6	mean_val_acc	45.6167
157	feasibility	fashion_wide	G8	execution_feasible	True
158	feasibility	fashion_wide	G8	optimization_feasible	True
159	feasibility	fashion_wide	G8	mean_val_nll	1.615937
160	feasibility	fashion_wide	G8	mean_val_acc	41.6667
161	feasibility	fashion_wide	G5	execution_feasible	True
162	feasibility	fashion_wide	G5	optimization_feasible	True
163	feasibility	fashion_wide	G5	mean_val_nll	1.525747
164	feasibility	fashion_wide	G5	mean_val_acc	46.31

7.5 KiB Raw Permalink Blame History

7.5 KiB

Raw Permalink Blame History