1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
|
{
"config": {
"hidden_size": 80,
"train_epochs": 1000,
"inter_period": 100,
"inter_epochs": 100,
"pre_epochs": 100,
"max_inter_episodes": 0,
"batch_size": 16,
"input_dim": 1,
"train_steps": 300,
"lyap_steps": 55,
"floss_input_steps": 300,
"seed_ic": 1,
"seed_input": 1,
"seed_net": 1,
"seed_ons": 1,
"lr": 0.001,
"beta1": 0.9,
"beta2": 0.999,
"init_type": 1,
"recurrent_gain": 1.0,
"recurrent_mean_gain": 0.0,
"input_scale": 1.0,
"delay": 10,
"ws_std": 1.0,
"ws_mean": 0.0,
"wr_std": 1.0,
"wr_mean": 0.0,
"b_std": 0.1,
"b_mean": 0.0,
"n_lyap": 40,
"task": -1,
"lyap_target": 0.0,
"eval_every": 100,
"eval_batches": 4,
"log_every_floss": 25,
"device": "cuda",
"out": "/home/yurenh2/rrm/research/flossing/flossing_suite/results/toy_rnn/toy_prefloss_N80_k40_E1000.json"
},
"evals": [
{
"epoch": 1,
"train_loss": 1.8594624996185303,
"train_accuracy": 0.49777580071174377,
"eval_loss": 1.6856758892536163,
"eval_accuracy": 0.5019461743772242,
"elapsed": 6.14853048324585
},
{
"epoch": 100,
"train_loss": 0.11722302436828613,
"train_accuracy": 0.964635231316726,
"eval_loss": 0.11776464246213436,
"eval_accuracy": 0.9623554270462634,
"elapsed": 20.684497117996216
},
{
"epoch": 200,
"train_loss": 0.028137803077697754,
"train_accuracy": 0.9931049822064056,
"eval_loss": 0.027145093772560358,
"eval_accuracy": 0.9935498220640568,
"elapsed": 37.35478901863098
},
{
"epoch": 300,
"train_loss": 0.012114334851503372,
"train_accuracy": 0.9975533807829181,
"eval_loss": 0.014187443535774946,
"eval_accuracy": 0.9963300711743772,
"elapsed": 55.917400598526
},
{
"epoch": 400,
"train_loss": 0.008550425991415977,
"train_accuracy": 0.9986654804270463,
"eval_loss": 0.009522247593849897,
"eval_accuracy": 0.9975533807829181,
"elapsed": 70.93301439285278
},
{
"epoch": 500,
"train_loss": 0.006629249546676874,
"train_accuracy": 0.998220640569395,
"eval_loss": 0.009814425837248564,
"eval_accuracy": 0.9973865658362989,
"elapsed": 85.52227640151978
},
{
"epoch": 600,
"train_loss": 0.007227692287415266,
"train_accuracy": 0.998220640569395,
"eval_loss": 0.006339075975120068,
"eval_accuracy": 0.9983874555160143,
"elapsed": 100.7544515132904
},
{
"epoch": 700,
"train_loss": 0.00907257292419672,
"train_accuracy": 0.9979982206405694,
"eval_loss": 0.008150239707902074,
"eval_accuracy": 0.9981094306049823,
"elapsed": 117.6931049823761
},
{
"epoch": 800,
"train_loss": 0.005422760266810656,
"train_accuracy": 0.998220640569395,
"eval_loss": 0.006329314899630845,
"eval_accuracy": 0.9981650355871887,
"elapsed": 135.87456274032593
},
{
"epoch": 900,
"train_loss": 0.0072866384871304035,
"train_accuracy": 0.998220640569395,
"eval_loss": 0.0068275314988568425,
"eval_accuracy": 0.9981650355871886,
"elapsed": 154.51783514022827
},
{
"epoch": 1000,
"train_loss": 0.010031766258180141,
"train_accuracy": 0.9973309608540926,
"eval_loss": 0.01047352165915072,
"eval_accuracy": 0.9972753558718862,
"elapsed": 172.1986005306244
}
],
"floss": [
{
"epoch": 1,
"kind": "pre",
"floss_step": 1,
"loss": 0.2797410190105438,
"lambda_mean": -0.507389485836029,
"lambda_1": -0.2639281749725342,
"elapsed": 0.7015585899353027
},
{
"epoch": 1,
"kind": "pre",
"floss_step": 25,
"loss": 0.09786238521337509,
"lambda_mean": -0.29911166429519653,
"lambda_1": -0.1687435507774353,
"elapsed": 1.9113752841949463
},
{
"epoch": 1,
"kind": "pre",
"floss_step": 50,
"loss": 0.04969814047217369,
"lambda_mean": -0.21222734451293945,
"lambda_1": -0.13751955330371857,
"elapsed": 3.170351028442383
},
{
"epoch": 1,
"kind": "pre",
"floss_step": 75,
"loss": 0.02838609553873539,
"lambda_mean": -0.1609755903482437,
"lambda_1": -0.10771095007658005,
"elapsed": 4.427560806274414
},
{
"epoch": 1,
"kind": "pre",
"floss_step": 100,
"loss": 0.00937537383288145,
"lambda_mean": -0.09084373712539673,
"lambda_1": -0.053737666457891464,
"elapsed": 5.687152147293091
}
],
"task": []
}
|
