Hugging Face's logo

rjuez00
/
meddocan-flair-spanish-fast-bilstm-crf

PyTorch
Model card Files Community
rjuez00 commited on
Commit
7bb8e24
•
1 Parent(s): 0cbcc2d

Upload training.log

Browse files
Files changed (1) hide show
  1. training.log +911 -0
training.log ADDED
@@ -0,0 +1,911 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2022-05-01 23:23:01,886 ----------------------------------------------------------------------------------------------------
2
+ 2022-05-01 23:23:01,888 Model: "SequenceTagger(
3
+ (embeddings): StackedEmbeddings(
4
+ (list_embedding_0): WordEmbeddings(
5
+ 'es'
6
+ (embedding): Embedding(985667, 300)
7
+ )
8
+ (list_embedding_1): FlairEmbeddings(
9
+ (lm): LanguageModel(
10
+ (drop): Dropout(p=0.5, inplace=False)
11
+ (encoder): Embedding(275, 100)
12
+ (rnn): LSTM(100, 1024)
13
+ (decoder): Linear(in_features=1024, out_features=275, bias=True)
14
+ )
15
+ )
16
+ (list_embedding_2): FlairEmbeddings(
17
+ (lm): LanguageModel(
18
+ (drop): Dropout(p=0.5, inplace=False)
19
+ (encoder): Embedding(275, 100)
20
+ (rnn): LSTM(100, 1024)
21
+ (decoder): Linear(in_features=1024, out_features=275, bias=True)
22
+ )
23
+ )
24
+ )
25
+ (word_dropout): WordDropout(p=0.05)
26
+ (locked_dropout): LockedDropout(p=0.5)
27
+ (embedding2nn): Linear(in_features=2348, out_features=2348, bias=True)
28
+ (rnn): LSTM(2348, 256, batch_first=True, bidirectional=True)
29
+ (linear): Linear(in_features=512, out_features=91, bias=True)
30
+ (loss_function): ViterbiLoss()
31
+ (crf): CRF()
32
+ )"
33
+ 2022-05-01 23:23:01,902 ----------------------------------------------------------------------------------------------------
34
+ 2022-05-01 23:23:01,903 Corpus: "Corpus: 500 train + 250 dev + 250 test sentences"
35
+ 2022-05-01 23:23:01,905 ----------------------------------------------------------------------------------------------------
36
+ 2022-05-01 23:23:01,905 Parameters:
37
+ 2022-05-01 23:23:01,906 - learning_rate: "0.200000"
38
+ 2022-05-01 23:23:01,907 - mini_batch_size: "10"
39
+ 2022-05-01 23:23:01,908 - patience: "10"
40
+ 2022-05-01 23:23:01,909 - anneal_factor: "0.5"
41
+ 2022-05-01 23:23:01,911 - max_epochs: "50"
42
+ 2022-05-01 23:23:01,912 - shuffle: "True"
43
+ 2022-05-01 23:23:01,913 - train_with_dev: "False"
44
+ 2022-05-01 23:23:01,914 - batch_growth_annealing: "False"
45
+ 2022-05-01 23:23:01,915 ----------------------------------------------------------------------------------------------------
46
+ 2022-05-01 23:23:01,917 Model training base path: "models\MEDDOCAN_0.2_256_1_50"
47
+ 2022-05-01 23:23:01,917 ----------------------------------------------------------------------------------------------------
48
+ 2022-05-01 23:23:01,919 Device: cuda:0
49
+ 2022-05-01 23:23:01,919 ----------------------------------------------------------------------------------------------------
50
+ 2022-05-01 23:23:01,920 Embeddings storage mode: cpu
51
+ 2022-05-01 23:23:01,921 ----------------------------------------------------------------------------------------------------
52
+ 2022-05-01 23:23:35,311 epoch 1 - iter 5/50 - loss 1.59770210 - samples/sec: 1.50 - lr: 0.200000
53
+ 2022-05-01 23:24:19,565 epoch 1 - iter 10/50 - loss 1.22090360 - samples/sec: 1.13 - lr: 0.200000
54
+ 2022-05-01 23:25:15,944 epoch 1 - iter 15/50 - loss 1.02848553 - samples/sec: 0.89 - lr: 0.200000
55
+ 2022-05-01 23:25:52,969 epoch 1 - iter 20/50 - loss 0.95874139 - samples/sec: 1.35 - lr: 0.200000
56
+ 2022-05-01 23:26:28,930 epoch 1 - iter 25/50 - loss 0.89945026 - samples/sec: 1.39 - lr: 0.200000
57
+ 2022-05-01 23:27:26,783 epoch 1 - iter 30/50 - loss 0.84958336 - samples/sec: 0.86 - lr: 0.200000
58
+ 2022-05-01 23:28:02,524 epoch 1 - iter 35/50 - loss 0.80448277 - samples/sec: 1.40 - lr: 0.200000
59
+ 2022-05-01 23:28:42,398 epoch 1 - iter 40/50 - loss 0.75353698 - samples/sec: 1.25 - lr: 0.200000
60
+ 2022-05-01 23:29:24,488 epoch 1 - iter 45/50 - loss 0.70636858 - samples/sec: 1.19 - lr: 0.200000
61
+ 2022-05-01 23:29:57,479 epoch 1 - iter 50/50 - loss 0.67653360 - samples/sec: 1.52 - lr: 0.200000
62
+ 2022-05-01 23:29:57,479 ----------------------------------------------------------------------------------------------------
63
+ 2022-05-01 23:29:57,480 EPOCH 1 done: loss 0.6765 - lr 0.200000
64
+ 2022-05-01 23:31:31,830 Evaluating as a multi-label problem: False
65
+ 2022-05-01 23:31:31,896 DEV : loss 0.2667730748653412 - f1-score (micro avg) 0.3403
66
+ 2022-05-01 23:31:32,269 BAD EPOCHS (no improvement): 0
67
+ 2022-05-01 23:31:32,270 saving best model
68
+ 2022-05-01 23:31:41,163 ----------------------------------------------------------------------------------------------------
69
+ 2022-05-01 23:32:10,079 epoch 2 - iter 5/50 - loss 0.26837264 - samples/sec: 1.73 - lr: 0.200000
70
+ 2022-05-01 23:32:38,348 epoch 2 - iter 10/50 - loss 0.25512219 - samples/sec: 1.77 - lr: 0.200000
71
+ 2022-05-01 23:33:25,959 epoch 2 - iter 15/50 - loss 0.24141508 - samples/sec: 1.05 - lr: 0.200000
72
+ 2022-05-01 23:33:58,103 epoch 2 - iter 20/50 - loss 0.24137457 - samples/sec: 1.56 - lr: 0.200000
73
+ 2022-05-01 23:34:27,942 epoch 2 - iter 25/50 - loss 0.22911312 - samples/sec: 1.68 - lr: 0.200000
74
+ 2022-05-01 23:35:07,567 epoch 2 - iter 30/50 - loss 0.21942959 - samples/sec: 1.26 - lr: 0.200000
75
+ 2022-05-01 23:35:44,133 epoch 2 - iter 35/50 - loss 0.21099236 - samples/sec: 1.37 - lr: 0.200000
76
+ 2022-05-01 23:36:12,702 epoch 2 - iter 40/50 - loss 0.20117677 - samples/sec: 1.75 - lr: 0.200000
77
+ 2022-05-01 23:36:40,151 epoch 2 - iter 45/50 - loss 0.19527944 - samples/sec: 1.82 - lr: 0.200000
78
+ 2022-05-01 23:37:14,987 epoch 2 - iter 50/50 - loss 0.18599383 - samples/sec: 1.44 - lr: 0.200000
79
+ 2022-05-01 23:37:14,988 ----------------------------------------------------------------------------------------------------
80
+ 2022-05-01 23:37:14,989 EPOCH 2 done: loss 0.1860 - lr 0.200000
81
+ 2022-05-01 23:37:54,099 Evaluating as a multi-label problem: False
82
+ 2022-05-01 23:37:54,149 DEV : loss 0.10558532178401947 - f1-score (micro avg) 0.7993
83
+ 2022-05-01 23:37:54,515 BAD EPOCHS (no improvement): 0
84
+ 2022-05-01 23:37:54,516 saving best model
85
+ 2022-05-01 23:38:04,167 ----------------------------------------------------------------------------------------------------
86
+ 2022-05-01 23:38:23,278 epoch 3 - iter 5/50 - loss 0.12075763 - samples/sec: 2.62 - lr: 0.200000
87
+ 2022-05-01 23:38:54,354 epoch 3 - iter 10/50 - loss 0.11133641 - samples/sec: 1.61 - lr: 0.200000
88
+ 2022-05-01 23:39:36,208 epoch 3 - iter 15/50 - loss 0.10202662 - samples/sec: 1.19 - lr: 0.200000
89
+ 2022-05-01 23:40:09,117 epoch 3 - iter 20/50 - loss 0.10255281 - samples/sec: 1.52 - lr: 0.200000
90
+ 2022-05-01 23:40:49,810 epoch 3 - iter 25/50 - loss 0.10239848 - samples/sec: 1.23 - lr: 0.200000
91
+ 2022-05-01 23:41:24,375 epoch 3 - iter 30/50 - loss 0.10247606 - samples/sec: 1.45 - lr: 0.200000
92
+ 2022-05-01 23:42:06,554 epoch 3 - iter 35/50 - loss 0.10204595 - samples/sec: 1.19 - lr: 0.200000
93
+ 2022-05-01 23:42:26,443 epoch 3 - iter 40/50 - loss 0.09969777 - samples/sec: 2.51 - lr: 0.200000
94
+ 2022-05-01 23:42:54,644 epoch 3 - iter 45/50 - loss 0.09706174 - samples/sec: 1.77 - lr: 0.200000
95
+ 2022-05-01 23:43:39,435 epoch 3 - iter 50/50 - loss 0.09644519 - samples/sec: 1.12 - lr: 0.200000
96
+ 2022-05-01 23:43:39,436 ----------------------------------------------------------------------------------------------------
97
+ 2022-05-01 23:43:39,436 EPOCH 3 done: loss 0.0964 - lr 0.200000
98
+ 2022-05-01 23:44:19,655 Evaluating as a multi-label problem: False
99
+ 2022-05-01 23:44:19,706 DEV : loss 0.06000390276312828 - f1-score (micro avg) 0.8631
100
+ 2022-05-01 23:44:20,071 BAD EPOCHS (no improvement): 0
101
+ 2022-05-01 23:44:20,072 saving best model
102
+ 2022-05-01 23:44:28,984 ----------------------------------------------------------------------------------------------------
103
+ 2022-05-01 23:45:01,528 epoch 4 - iter 5/50 - loss 0.05997595 - samples/sec: 1.54 - lr: 0.200000
104
+ 2022-05-01 23:45:36,630 epoch 4 - iter 10/50 - loss 0.06104511 - samples/sec: 1.42 - lr: 0.200000
105
+ 2022-05-01 23:46:14,658 epoch 4 - iter 15/50 - loss 0.06759936 - samples/sec: 1.31 - lr: 0.200000
106
+ 2022-05-01 23:46:59,249 epoch 4 - iter 20/50 - loss 0.06746941 - samples/sec: 1.12 - lr: 0.200000
107
+ 2022-05-01 23:47:29,662 epoch 4 - iter 25/50 - loss 0.06798332 - samples/sec: 1.64 - lr: 0.200000
108
+ 2022-05-01 23:47:50,681 epoch 4 - iter 30/50 - loss 0.06628922 - samples/sec: 2.38 - lr: 0.200000
109
+ 2022-05-01 23:48:21,281 epoch 4 - iter 35/50 - loss 0.06766836 - samples/sec: 1.63 - lr: 0.200000
110
+ 2022-05-01 23:48:59,019 epoch 4 - iter 40/50 - loss 0.06650118 - samples/sec: 1.32 - lr: 0.200000
111
+ 2022-05-01 23:49:28,564 epoch 4 - iter 45/50 - loss 0.06828091 - samples/sec: 1.69 - lr: 0.200000
112
+ 2022-05-01 23:50:02,085 epoch 4 - iter 50/50 - loss 0.06737072 - samples/sec: 1.49 - lr: 0.200000
113
+ 2022-05-01 23:50:02,086 ----------------------------------------------------------------------------------------------------
114
+ 2022-05-01 23:50:02,086 EPOCH 4 done: loss 0.0674 - lr 0.200000
115
+ 2022-05-01 23:50:41,517 Evaluating as a multi-label problem: False
116
+ 2022-05-01 23:50:41,563 DEV : loss 0.045093271881341934 - f1-score (micro avg) 0.8808
117
+ 2022-05-01 23:50:41,928 BAD EPOCHS (no improvement): 0
118
+ 2022-05-01 23:50:41,929 saving best model
119
+ 2022-05-01 23:50:51,213 ----------------------------------------------------------------------------------------------------
120
+ 2022-05-01 23:51:18,866 epoch 5 - iter 5/50 - loss 0.05137303 - samples/sec: 1.81 - lr: 0.200000
121
+ 2022-05-01 23:52:10,306 epoch 5 - iter 10/50 - loss 0.05808767 - samples/sec: 0.97 - lr: 0.200000
122
+ 2022-05-01 23:52:41,605 epoch 5 - iter 15/50 - loss 0.05403072 - samples/sec: 1.60 - lr: 0.200000
123
+ 2022-05-01 23:53:18,265 epoch 5 - iter 20/50 - loss 0.05575972 - samples/sec: 1.36 - lr: 0.200000
124
+ 2022-05-01 23:53:45,984 epoch 5 - iter 25/50 - loss 0.05667813 - samples/sec: 1.80 - lr: 0.200000
125
+ 2022-05-01 23:54:12,408 epoch 5 - iter 30/50 - loss 0.05813678 - samples/sec: 1.89 - lr: 0.200000
126
+ 2022-05-01 23:54:48,879 epoch 5 - iter 35/50 - loss 0.05635215 - samples/sec: 1.37 - lr: 0.200000
127
+ 2022-05-01 23:55:20,294 epoch 5 - iter 40/50 - loss 0.05496344 - samples/sec: 1.59 - lr: 0.200000
128
+ 2022-05-01 23:55:57,264 epoch 5 - iter 45/50 - loss 0.05412934 - samples/sec: 1.35 - lr: 0.200000
129
+ 2022-05-01 23:56:29,456 epoch 5 - iter 50/50 - loss 0.05322523 - samples/sec: 1.55 - lr: 0.200000
130
+ 2022-05-01 23:56:29,457 ----------------------------------------------------------------------------------------------------
131
+ 2022-05-01 23:56:29,457 EPOCH 5 done: loss 0.0532 - lr 0.200000
132
+ 2022-05-01 23:57:08,478 Evaluating as a multi-label problem: False
133
+ 2022-05-01 23:57:08,524 DEV : loss 0.03656361997127533 - f1-score (micro avg) 0.9084
134
+ 2022-05-01 23:57:08,897 BAD EPOCHS (no improvement): 0
135
+ 2022-05-01 23:57:08,898 saving best model
136
+ 2022-05-01 23:57:17,797 ----------------------------------------------------------------------------------------------------
137
+ 2022-05-01 23:57:43,187 epoch 6 - iter 5/50 - loss 0.04689242 - samples/sec: 1.97 - lr: 0.200000
138
+ 2022-05-01 23:58:18,364 epoch 6 - iter 10/50 - loss 0.04299304 - samples/sec: 1.42 - lr: 0.200000
139
+ 2022-05-01 23:58:50,071 epoch 6 - iter 15/50 - loss 0.04159477 - samples/sec: 1.58 - lr: 0.200000
140
+ 2022-05-01 23:59:26,356 epoch 6 - iter 20/50 - loss 0.04343081 - samples/sec: 1.38 - lr: 0.200000
141
+ 2022-05-02 00:00:06,529 epoch 6 - iter 25/50 - loss 0.04264925 - samples/sec: 1.24 - lr: 0.200000
142
+ 2022-05-02 00:00:42,433 epoch 6 - iter 30/50 - loss 0.04251982 - samples/sec: 1.39 - lr: 0.200000
143
+ 2022-05-02 00:01:06,840 epoch 6 - iter 35/50 - loss 0.04183623 - samples/sec: 2.05 - lr: 0.200000
144
+ 2022-05-02 00:01:40,303 epoch 6 - iter 40/50 - loss 0.04246998 - samples/sec: 1.49 - lr: 0.200000
145
+ 2022-05-02 00:02:19,403 epoch 6 - iter 45/50 - loss 0.04248011 - samples/sec: 1.28 - lr: 0.200000
146
+ 2022-05-02 00:02:57,541 epoch 6 - iter 50/50 - loss 0.04399777 - samples/sec: 1.31 - lr: 0.200000
147
+ 2022-05-02 00:02:57,541 ----------------------------------------------------------------------------------------------------
148
+ 2022-05-02 00:02:57,542 EPOCH 6 done: loss 0.0440 - lr 0.200000
149
+ 2022-05-02 00:03:36,993 Evaluating as a multi-label problem: False
150
+ 2022-05-02 00:03:37,038 DEV : loss 0.037273112684488297 - f1-score (micro avg) 0.9195
151
+ 2022-05-02 00:03:37,403 BAD EPOCHS (no improvement): 0
152
+ 2022-05-02 00:03:37,404 saving best model
153
+ 2022-05-02 00:03:46,904 ----------------------------------------------------------------------------------------------------
154
+ 2022-05-02 00:04:22,613 epoch 7 - iter 5/50 - loss 0.03349910 - samples/sec: 1.40 - lr: 0.200000
155
+ 2022-05-02 00:04:58,995 epoch 7 - iter 10/50 - loss 0.03472188 - samples/sec: 1.37 - lr: 0.200000
156
+ 2022-05-02 00:05:25,831 epoch 7 - iter 15/50 - loss 0.03835497 - samples/sec: 1.86 - lr: 0.200000
157
+ 2022-05-02 00:06:00,400 epoch 7 - iter 20/50 - loss 0.03844130 - samples/sec: 1.45 - lr: 0.200000
158
+ 2022-05-02 00:06:36,603 epoch 7 - iter 25/50 - loss 0.03732885 - samples/sec: 1.38 - lr: 0.200000
159
+ 2022-05-02 00:07:08,107 epoch 7 - iter 30/50 - loss 0.03826566 - samples/sec: 1.59 - lr: 0.200000
160
+ 2022-05-02 00:07:42,622 epoch 7 - iter 35/50 - loss 0.03954662 - samples/sec: 1.45 - lr: 0.200000
161
+ 2022-05-02 00:08:14,606 epoch 7 - iter 40/50 - loss 0.03913941 - samples/sec: 1.56 - lr: 0.200000
162
+ 2022-05-02 00:08:52,908 epoch 7 - iter 45/50 - loss 0.03871489 - samples/sec: 1.31 - lr: 0.200000
163
+ 2022-05-02 00:09:20,721 epoch 7 - iter 50/50 - loss 0.03832722 - samples/sec: 1.80 - lr: 0.200000
164
+ 2022-05-02 00:09:20,722 ----------------------------------------------------------------------------------------------------
165
+ 2022-05-02 00:09:20,722 EPOCH 7 done: loss 0.0383 - lr 0.200000
166
+ 2022-05-02 00:09:59,642 Evaluating as a multi-label problem: False
167
+ 2022-05-02 00:09:59,688 DEV : loss 0.029755419120192528 - f1-score (micro avg) 0.9317
168
+ 2022-05-02 00:10:00,059 BAD EPOCHS (no improvement): 0
169
+ 2022-05-02 00:10:00,060 saving best model
170
+ 2022-05-02 00:10:08,363 ----------------------------------------------------------------------------------------------------
171
+ 2022-05-02 00:10:55,833 epoch 8 - iter 5/50 - loss 0.03673092 - samples/sec: 1.05 - lr: 0.200000
172
+ 2022-05-02 00:11:25,240 epoch 8 - iter 10/50 - loss 0.04053941 - samples/sec: 1.70 - lr: 0.200000
173
+ 2022-05-02 00:11:46,498 epoch 8 - iter 15/50 - loss 0.04106418 - samples/sec: 2.35 - lr: 0.200000
174
+ 2022-05-02 00:12:20,799 epoch 8 - iter 20/50 - loss 0.03779785 - samples/sec: 1.46 - lr: 0.200000
175
+ 2022-05-02 00:12:48,963 epoch 8 - iter 25/50 - loss 0.03618513 - samples/sec: 1.78 - lr: 0.200000
176
+ 2022-05-02 00:13:27,747 epoch 8 - iter 30/50 - loss 0.03501196 - samples/sec: 1.29 - lr: 0.200000
177
+ 2022-05-02 00:14:03,023 epoch 8 - iter 35/50 - loss 0.03475598 - samples/sec: 1.42 - lr: 0.200000
178
+ 2022-05-02 00:14:34,716 epoch 8 - iter 40/50 - loss 0.03522584 - samples/sec: 1.58 - lr: 0.200000
179
+ 2022-05-02 00:15:05,598 epoch 8 - iter 45/50 - loss 0.03505073 - samples/sec: 1.62 - lr: 0.200000
180
+ 2022-05-02 00:15:40,732 epoch 8 - iter 50/50 - loss 0.03479370 - samples/sec: 1.42 - lr: 0.200000
181
+ 2022-05-02 00:15:40,732 ----------------------------------------------------------------------------------------------------
182
+ 2022-05-02 00:15:40,733 EPOCH 8 done: loss 0.0348 - lr 0.200000
183
+ 2022-05-02 00:16:19,766 Evaluating as a multi-label problem: False
184
+ 2022-05-02 00:16:19,811 DEV : loss 0.028399672359228134 - f1-score (micro avg) 0.932
185
+ 2022-05-02 00:16:20,176 BAD EPOCHS (no improvement): 0
186
+ 2022-05-02 00:16:20,178 saving best model
187
+ 2022-05-02 00:16:29,609 ----------------------------------------------------------------------------------------------------
188
+ 2022-05-02 00:17:06,426 epoch 9 - iter 5/50 - loss 0.03593539 - samples/sec: 1.36 - lr: 0.200000
189
+ 2022-05-02 00:17:44,011 epoch 9 - iter 10/50 - loss 0.03445235 - samples/sec: 1.33 - lr: 0.200000
190
+ 2022-05-02 00:18:15,693 epoch 9 - iter 15/50 - loss 0.03372001 - samples/sec: 1.58 - lr: 0.200000
191
+ 2022-05-02 00:18:44,953 epoch 9 - iter 20/50 - loss 0.03244884 - samples/sec: 1.71 - lr: 0.200000
192
+ 2022-05-02 00:19:16,259 epoch 9 - iter 25/50 - loss 0.03058462 - samples/sec: 1.60 - lr: 0.200000
193
+ 2022-05-02 00:19:46,052 epoch 9 - iter 30/50 - loss 0.03377173 - samples/sec: 1.68 - lr: 0.200000
194
+ 2022-05-02 00:20:25,262 epoch 9 - iter 35/50 - loss 0.03337994 - samples/sec: 1.28 - lr: 0.200000
195
+ 2022-05-02 00:21:05,799 epoch 9 - iter 40/50 - loss 0.03208589 - samples/sec: 1.23 - lr: 0.200000
196
+ 2022-05-02 00:21:40,955 epoch 9 - iter 45/50 - loss 0.03154899 - samples/sec: 1.42 - lr: 0.200000
197
+ 2022-05-02 00:22:13,426 epoch 9 - iter 50/50 - loss 0.03037378 - samples/sec: 1.54 - lr: 0.200000
198
+ 2022-05-02 00:22:13,426 ----------------------------------------------------------------------------------------------------
199
+ 2022-05-02 00:22:13,427 EPOCH 9 done: loss 0.0304 - lr 0.200000
200
+ 2022-05-02 00:22:53,652 Evaluating as a multi-label problem: False
201
+ 2022-05-02 00:22:53,696 DEV : loss 0.028395378962159157 - f1-score (micro avg) 0.9339
202
+ 2022-05-02 00:22:54,070 BAD EPOCHS (no improvement): 0
203
+ 2022-05-02 00:22:54,071 saving best model
204
+ 2022-05-02 00:23:02,524 ----------------------------------------------------------------------------------------------------
205
+ 2022-05-02 00:23:45,470 epoch 10 - iter 5/50 - loss 0.03084326 - samples/sec: 1.16 - lr: 0.200000
206
+ 2022-05-02 00:24:19,819 epoch 10 - iter 10/50 - loss 0.03219383 - samples/sec: 1.46 - lr: 0.200000
207
+ 2022-05-02 00:24:50,366 epoch 10 - iter 15/50 - loss 0.02999675 - samples/sec: 1.64 - lr: 0.200000
208
+ 2022-05-02 00:25:17,886 epoch 10 - iter 20/50 - loss 0.02958139 - samples/sec: 1.82 - lr: 0.200000
209
+ 2022-05-02 00:25:41,637 epoch 10 - iter 25/50 - loss 0.02933146 - samples/sec: 2.11 - lr: 0.200000
210
+ 2022-05-02 00:26:15,166 epoch 10 - iter 30/50 - loss 0.02880682 - samples/sec: 1.49 - lr: 0.200000
211
+ 2022-05-02 00:26:52,817 epoch 10 - iter 35/50 - loss 0.02927866 - samples/sec: 1.33 - lr: 0.200000
212
+ 2022-05-02 00:27:38,134 epoch 10 - iter 40/50 - loss 0.02862815 - samples/sec: 1.10 - lr: 0.200000
213
+ 2022-05-02 00:28:14,650 epoch 10 - iter 45/50 - loss 0.02787564 - samples/sec: 1.37 - lr: 0.200000
214
+ 2022-05-02 00:28:43,914 epoch 10 - iter 50/50 - loss 0.02729656 - samples/sec: 1.71 - lr: 0.200000
215
+ 2022-05-02 00:28:43,915 ----------------------------------------------------------------------------------------------------
216
+ 2022-05-02 00:28:43,915 EPOCH 10 done: loss 0.0273 - lr 0.200000
217
+ 2022-05-02 00:29:23,261 Evaluating as a multi-label problem: False
218
+ 2022-05-02 00:29:23,304 DEV : loss 0.025133976712822914 - f1-score (micro avg) 0.944
219
+ 2022-05-02 00:29:23,669 BAD EPOCHS (no improvement): 0
220
+ 2022-05-02 00:29:23,670 saving best model
221
+ 2022-05-02 00:29:32,910 ----------------------------------------------------------------------------------------------------
222
+ 2022-05-02 00:30:15,108 epoch 11 - iter 5/50 - loss 0.02523557 - samples/sec: 1.18 - lr: 0.200000
223
+ 2022-05-02 00:30:45,040 epoch 11 - iter 10/50 - loss 0.02381533 - samples/sec: 1.67 - lr: 0.200000
224
+ 2022-05-02 00:31:17,310 epoch 11 - iter 15/50 - loss 0.02341191 - samples/sec: 1.55 - lr: 0.200000
225
+ 2022-05-02 00:31:52,233 epoch 11 - iter 20/50 - loss 0.02200684 - samples/sec: 1.43 - lr: 0.200000
226
+ 2022-05-02 00:32:41,368 epoch 11 - iter 25/50 - loss 0.02186411 - samples/sec: 1.02 - lr: 0.200000
227
+ 2022-05-02 00:33:13,139 epoch 11 - iter 30/50 - loss 0.02192222 - samples/sec: 1.57 - lr: 0.200000
228
+ 2022-05-02 00:33:43,923 epoch 11 - iter 35/50 - loss 0.02305194 - samples/sec: 1.62 - lr: 0.200000
229
+ 2022-05-02 00:34:09,379 epoch 11 - iter 40/50 - loss 0.02347979 - samples/sec: 1.96 - lr: 0.200000
230
+ 2022-05-02 00:34:37,983 epoch 11 - iter 45/50 - loss 0.02361421 - samples/sec: 1.75 - lr: 0.200000
231
+ 2022-05-02 00:35:03,872 epoch 11 - iter 50/50 - loss 0.02428412 - samples/sec: 1.93 - lr: 0.200000
232
+ 2022-05-02 00:35:03,872 ----------------------------------------------------------------------------------------------------
233
+ 2022-05-02 00:35:03,873 EPOCH 11 done: loss 0.0243 - lr 0.200000
234
+ 2022-05-02 00:35:44,968 Evaluating as a multi-label problem: False
235
+ 2022-05-02 00:35:45,015 DEV : loss 0.026334436610341072 - f1-score (micro avg) 0.9396
236
+ 2022-05-02 00:35:45,381 BAD EPOCHS (no improvement): 1
237
+ 2022-05-02 00:35:45,382 ----------------------------------------------------------------------------------------------------
238
+ 2022-05-02 00:36:22,815 epoch 12 - iter 5/50 - loss 0.02158002 - samples/sec: 1.34 - lr: 0.200000
239
+ 2022-05-02 00:36:50,791 epoch 12 - iter 10/50 - loss 0.02242517 - samples/sec: 1.79 - lr: 0.200000
240
+ 2022-05-02 00:37:31,278 epoch 12 - iter 15/50 - loss 0.02516461 - samples/sec: 1.24 - lr: 0.200000
241
+ 2022-05-02 00:37:55,878 epoch 12 - iter 20/50 - loss 0.02368683 - samples/sec: 2.03 - lr: 0.200000
242
+ 2022-05-02 00:38:32,457 epoch 12 - iter 25/50 - loss 0.02282569 - samples/sec: 1.37 - lr: 0.200000
243
+ 2022-05-02 00:38:57,152 epoch 12 - iter 30/50 - loss 0.02390196 - samples/sec: 2.02 - lr: 0.200000
244
+ 2022-05-02 00:39:29,525 epoch 12 - iter 35/50 - loss 0.02389076 - samples/sec: 1.54 - lr: 0.200000
245
+ 2022-05-02 00:39:58,203 epoch 12 - iter 40/50 - loss 0.02421242 - samples/sec: 1.74 - lr: 0.200000
246
+ 2022-05-02 00:40:33,677 epoch 12 - iter 45/50 - loss 0.02379508 - samples/sec: 1.41 - lr: 0.200000
247
+ 2022-05-02 00:41:14,763 epoch 12 - iter 50/50 - loss 0.02382885 - samples/sec: 1.22 - lr: 0.200000
248
+ 2022-05-02 00:41:14,764 ----------------------------------------------------------------------------------------------------
249
+ 2022-05-02 00:41:14,764 EPOCH 12 done: loss 0.0238 - lr 0.200000
250
+ 2022-05-02 00:41:53,918 Evaluating as a multi-label problem: False
251
+ 2022-05-02 00:41:53,967 DEV : loss 0.02187209390103817 - f1-score (micro avg) 0.9478
252
+ 2022-05-02 00:41:54,335 BAD EPOCHS (no improvement): 0
253
+ 2022-05-02 00:41:54,336 saving best model
254
+ 2022-05-02 00:42:03,138 ----------------------------------------------------------------------------------------------------
255
+ 2022-05-02 00:42:37,483 epoch 13 - iter 5/50 - loss 0.01595983 - samples/sec: 1.46 - lr: 0.200000
256
+ 2022-05-02 00:43:11,211 epoch 13 - iter 10/50 - loss 0.01940878 - samples/sec: 1.48 - lr: 0.200000
257
+ 2022-05-02 00:43:44,288 epoch 13 - iter 15/50 - loss 0.01918797 - samples/sec: 1.51 - lr: 0.200000
258
+ 2022-05-02 00:44:17,614 epoch 13 - iter 20/50 - loss 0.02097053 - samples/sec: 1.50 - lr: 0.200000
259
+ 2022-05-02 00:44:52,637 epoch 13 - iter 25/50 - loss 0.02118569 - samples/sec: 1.43 - lr: 0.200000
260
+ 2022-05-02 00:45:23,793 epoch 13 - iter 30/50 - loss 0.02108534 - samples/sec: 1.60 - lr: 0.200000
261
+ 2022-05-02 00:45:58,611 epoch 13 - iter 35/50 - loss 0.02156080 - samples/sec: 1.44 - lr: 0.200000
262
+ 2022-05-02 00:46:32,161 epoch 13 - iter 40/50 - loss 0.02155976 - samples/sec: 1.49 - lr: 0.200000
263
+ 2022-05-02 00:47:12,349 epoch 13 - iter 45/50 - loss 0.02131631 - samples/sec: 1.24 - lr: 0.200000
264
+ 2022-05-02 00:47:42,825 epoch 13 - iter 50/50 - loss 0.02173357 - samples/sec: 1.64 - lr: 0.200000
265
+ 2022-05-02 00:47:42,826 ----------------------------------------------------------------------------------------------------
266
+ 2022-05-02 00:47:42,826 EPOCH 13 done: loss 0.0217 - lr 0.200000
267
+ 2022-05-02 00:48:21,860 Evaluating as a multi-label problem: False
268
+ 2022-05-02 00:48:21,905 DEV : loss 0.021116062998771667 - f1-score (micro avg) 0.9509
269
+ 2022-05-02 00:48:22,269 BAD EPOCHS (no improvement): 0
270
+ 2022-05-02 00:48:22,270 saving best model
271
+ 2022-05-02 00:48:31,210 ----------------------------------------------------------------------------------------------------
272
+ 2022-05-02 00:49:10,797 epoch 14 - iter 5/50 - loss 0.02427360 - samples/sec: 1.26 - lr: 0.200000
273
+ 2022-05-02 00:49:36,539 epoch 14 - iter 10/50 - loss 0.02328227 - samples/sec: 1.94 - lr: 0.200000
274
+ 2022-05-02 00:50:16,285 epoch 14 - iter 15/50 - loss 0.01982494 - samples/sec: 1.26 - lr: 0.200000
275
+ 2022-05-02 00:50:51,647 epoch 14 - iter 20/50 - loss 0.02059868 - samples/sec: 1.41 - lr: 0.200000
276
+ 2022-05-02 00:51:25,391 epoch 14 - iter 25/50 - loss 0.02076474 - samples/sec: 1.48 - lr: 0.200000
277
+ 2022-05-02 00:51:55,696 epoch 14 - iter 30/50 - loss 0.02144539 - samples/sec: 1.65 - lr: 0.200000
278
+ 2022-05-02 00:52:26,919 epoch 14 - iter 35/50 - loss 0.02110313 - samples/sec: 1.60 - lr: 0.200000
279
+ 2022-05-02 00:52:58,105 epoch 14 - iter 40/50 - loss 0.02127847 - samples/sec: 1.60 - lr: 0.200000
280
+ 2022-05-02 00:53:47,068 epoch 14 - iter 45/50 - loss 0.02099371 - samples/sec: 1.02 - lr: 0.200000
281
+ 2022-05-02 00:54:15,855 epoch 14 - iter 50/50 - loss 0.02046734 - samples/sec: 1.74 - lr: 0.200000
282
+ 2022-05-02 00:54:15,856 ----------------------------------------------------------------------------------------------------
283
+ 2022-05-02 00:54:15,857 EPOCH 14 done: loss 0.0205 - lr 0.200000
284
+ 2022-05-02 00:54:55,254 Evaluating as a multi-label problem: False
285
+ 2022-05-02 00:54:55,298 DEV : loss 0.02108933962881565 - f1-score (micro avg) 0.9537
286
+ 2022-05-02 00:54:55,680 BAD EPOCHS (no improvement): 0
287
+ 2022-05-02 00:54:55,681 saving best model
288
+ 2022-05-02 00:55:04,301 ----------------------------------------------------------------------------------------------------
289
+ 2022-05-02 00:55:34,155 epoch 15 - iter 5/50 - loss 0.01950543 - samples/sec: 1.67 - lr: 0.200000
290
+ 2022-05-02 00:56:03,084 epoch 15 - iter 10/50 - loss 0.02058720 - samples/sec: 1.73 - lr: 0.200000
291
+ 2022-05-02 00:56:31,187 epoch 15 - iter 15/50 - loss 0.02046045 - samples/sec: 1.78 - lr: 0.200000
292
+ 2022-05-02 00:57:04,609 epoch 15 - iter 20/50 - loss 0.01964520 - samples/sec: 1.50 - lr: 0.200000
293
+ 2022-05-02 00:57:47,134 epoch 15 - iter 25/50 - loss 0.01987998 - samples/sec: 1.18 - lr: 0.200000
294
+ 2022-05-02 00:58:25,045 epoch 15 - iter 30/50 - loss 0.01935321 - samples/sec: 1.32 - lr: 0.200000
295
+ 2022-05-02 00:59:01,058 epoch 15 - iter 35/50 - loss 0.01904119 - samples/sec: 1.39 - lr: 0.200000
296
+ 2022-05-02 00:59:41,437 epoch 15 - iter 40/50 - loss 0.01936876 - samples/sec: 1.24 - lr: 0.200000
297
+ 2022-05-02 01:00:10,781 epoch 15 - iter 45/50 - loss 0.01951098 - samples/sec: 1.70 - lr: 0.200000
298
+ 2022-05-02 01:00:45,634 epoch 15 - iter 50/50 - loss 0.01972059 - samples/sec: 1.43 - lr: 0.200000
299
+ 2022-05-02 01:00:45,636 ----------------------------------------------------------------------------------------------------
300
+ 2022-05-02 01:00:45,636 EPOCH 15 done: loss 0.0197 - lr 0.200000
301
+ 2022-05-02 01:01:24,510 Evaluating as a multi-label problem: False
302
+ 2022-05-02 01:01:24,558 DEV : loss 0.020560553297400475 - f1-score (micro avg) 0.9518
303
+ 2022-05-02 01:01:24,931 BAD EPOCHS (no improvement): 1
304
+ 2022-05-02 01:01:24,932 ----------------------------------------------------------------------------------------------------
305
+ 2022-05-02 01:01:53,067 epoch 16 - iter 5/50 - loss 0.01790667 - samples/sec: 1.78 - lr: 0.200000
306
+ 2022-05-02 01:02:21,670 epoch 16 - iter 10/50 - loss 0.02379275 - samples/sec: 1.75 - lr: 0.200000
307
+ 2022-05-02 01:02:44,064 epoch 16 - iter 15/50 - loss 0.02357462 - samples/sec: 2.23 - lr: 0.200000
308
+ 2022-05-02 01:03:20,210 epoch 16 - iter 20/50 - loss 0.02218496 - samples/sec: 1.38 - lr: 0.200000
309
+ 2022-05-02 01:03:48,753 epoch 16 - iter 25/50 - loss 0.02170782 - samples/sec: 1.75 - lr: 0.200000
310
+ 2022-05-02 01:04:22,565 epoch 16 - iter 30/50 - loss 0.02075927 - samples/sec: 1.48 - lr: 0.200000
311
+ 2022-05-02 01:05:02,214 epoch 16 - iter 35/50 - loss 0.02010830 - samples/sec: 1.26 - lr: 0.200000
312
+ 2022-05-02 01:05:34,092 epoch 16 - iter 40/50 - loss 0.01945366 - samples/sec: 1.57 - lr: 0.200000
313
+ 2022-05-02 01:06:17,686 epoch 16 - iter 45/50 - loss 0.01910837 - samples/sec: 1.15 - lr: 0.200000
314
+ 2022-05-02 01:06:57,074 epoch 16 - iter 50/50 - loss 0.01894594 - samples/sec: 1.27 - lr: 0.200000
315
+ 2022-05-02 01:06:57,075 ----------------------------------------------------------------------------------------------------
316
+ 2022-05-02 01:06:57,075 EPOCH 16 done: loss 0.0189 - lr 0.200000
317
+ 2022-05-02 01:07:37,431 Evaluating as a multi-label problem: False
318
+ 2022-05-02 01:07:37,476 DEV : loss 0.020650509744882584 - f1-score (micro avg) 0.9516
319
+ 2022-05-02 01:07:37,839 BAD EPOCHS (no improvement): 2
320
+ 2022-05-02 01:07:37,840 ----------------------------------------------------------------------------------------------------
321
+ 2022-05-02 01:08:12,820 epoch 17 - iter 5/50 - loss 0.01775903 - samples/sec: 1.43 - lr: 0.200000
322
+ 2022-05-02 01:08:49,642 epoch 17 - iter 10/50 - loss 0.01847558 - samples/sec: 1.36 - lr: 0.200000
323
+ 2022-05-02 01:09:22,478 epoch 17 - iter 15/50 - loss 0.01929665 - samples/sec: 1.52 - lr: 0.200000
324
+ 2022-05-02 01:09:48,281 epoch 17 - iter 20/50 - loss 0.01883245 - samples/sec: 1.94 - lr: 0.200000
325
+ 2022-05-02 01:10:22,521 epoch 17 - iter 25/50 - loss 0.01824307 - samples/sec: 1.46 - lr: 0.200000
326
+ 2022-05-02 01:11:04,633 epoch 17 - iter 30/50 - loss 0.01856908 - samples/sec: 1.19 - lr: 0.200000
327
+ 2022-05-02 01:11:39,303 epoch 17 - iter 35/50 - loss 0.01790228 - samples/sec: 1.44 - lr: 0.200000
328
+ 2022-05-02 01:12:13,630 epoch 17 - iter 40/50 - loss 0.01752612 - samples/sec: 1.46 - lr: 0.200000
329
+ 2022-05-02 01:12:45,060 epoch 17 - iter 45/50 - loss 0.01804019 - samples/sec: 1.59 - lr: 0.200000
330
+ 2022-05-02 01:13:18,752 epoch 17 - iter 50/50 - loss 0.01787853 - samples/sec: 1.48 - lr: 0.200000
331
+ 2022-05-02 01:13:18,753 ----------------------------------------------------------------------------------------------------
332
+ 2022-05-02 01:13:18,753 EPOCH 17 done: loss 0.0179 - lr 0.200000
333
+ 2022-05-02 01:13:59,143 Evaluating as a multi-label problem: False
334
+ 2022-05-02 01:13:59,188 DEV : loss 0.02100243978202343 - f1-score (micro avg) 0.9506
335
+ 2022-05-02 01:13:59,553 BAD EPOCHS (no improvement): 3
336
+ 2022-05-02 01:13:59,554 ----------------------------------------------------------------------------------------------------
337
+ 2022-05-02 01:14:27,572 epoch 18 - iter 5/50 - loss 0.01636678 - samples/sec: 1.78 - lr: 0.200000
338
+ 2022-05-02 01:15:03,029 epoch 18 - iter 10/50 - loss 0.01629214 - samples/sec: 1.41 - lr: 0.200000
339
+ 2022-05-02 01:15:28,881 epoch 18 - iter 15/50 - loss 0.01487124 - samples/sec: 1.93 - lr: 0.200000
340
+ 2022-05-02 01:16:04,971 epoch 18 - iter 20/50 - loss 0.01425007 - samples/sec: 1.39 - lr: 0.200000
341
+ 2022-05-02 01:16:41,273 epoch 18 - iter 25/50 - loss 0.01569630 - samples/sec: 1.38 - lr: 0.200000
342
+ 2022-05-02 01:17:13,885 epoch 18 - iter 30/50 - loss 0.01615162 - samples/sec: 1.53 - lr: 0.200000
343
+ 2022-05-02 01:17:45,417 epoch 18 - iter 35/50 - loss 0.01645502 - samples/sec: 1.59 - lr: 0.200000
344
+ 2022-05-02 01:18:21,429 epoch 18 - iter 40/50 - loss 0.01665576 - samples/sec: 1.39 - lr: 0.200000
345
+ 2022-05-02 01:18:57,110 epoch 18 - iter 45/50 - loss 0.01607554 - samples/sec: 1.40 - lr: 0.200000
346
+ 2022-05-02 01:19:34,403 epoch 18 - iter 50/50 - loss 0.01598979 - samples/sec: 1.34 - lr: 0.200000
347
+ 2022-05-02 01:19:34,404 ----------------------------------------------------------------------------------------------------
348
+ 2022-05-02 01:19:34,405 EPOCH 18 done: loss 0.0160 - lr 0.200000
349
+ 2022-05-02 01:20:13,523 Evaluating as a multi-label problem: False
350
+ 2022-05-02 01:20:13,574 DEV : loss 0.018712053075432777 - f1-score (micro avg) 0.9583
351
+ 2022-05-02 01:20:13,937 BAD EPOCHS (no improvement): 0
352
+ 2022-05-02 01:20:13,938 saving best model
353
+ 2022-05-02 01:20:23,339 ----------------------------------------------------------------------------------------------------
354
+ 2022-05-02 01:20:58,270 epoch 19 - iter 5/50 - loss 0.01076146 - samples/sec: 1.43 - lr: 0.200000
355
+ 2022-05-02 01:21:45,833 epoch 19 - iter 10/50 - loss 0.01678426 - samples/sec: 1.05 - lr: 0.200000
356
+ 2022-05-02 01:22:18,791 epoch 19 - iter 15/50 - loss 0.01447219 - samples/sec: 1.52 - lr: 0.200000
357
+ 2022-05-02 01:22:51,320 epoch 19 - iter 20/50 - loss 0.01453955 - samples/sec: 1.54 - lr: 0.200000
358
+ 2022-05-02 01:23:23,166 epoch 19 - iter 25/50 - loss 0.01504475 - samples/sec: 1.57 - lr: 0.200000
359
+ 2022-05-02 01:23:55,865 epoch 19 - iter 30/50 - loss 0.01543580 - samples/sec: 1.53 - lr: 0.200000
360
+ 2022-05-02 01:24:25,803 epoch 19 - iter 35/50 - loss 0.01585270 - samples/sec: 1.67 - lr: 0.200000
361
+ 2022-05-02 01:25:00,789 epoch 19 - iter 40/50 - loss 0.01576396 - samples/sec: 1.43 - lr: 0.200000
362
+ 2022-05-02 01:25:38,197 epoch 19 - iter 45/50 - loss 0.01585149 - samples/sec: 1.34 - lr: 0.200000
363
+ 2022-05-02 01:26:15,183 epoch 19 - iter 50/50 - loss 0.01546972 - samples/sec: 1.35 - lr: 0.200000
364
+ 2022-05-02 01:26:15,183 ----------------------------------------------------------------------------------------------------
365
+ 2022-05-02 01:26:15,184 EPOCH 19 done: loss 0.0155 - lr 0.200000
366
+ 2022-05-02 01:26:53,858 Evaluating as a multi-label problem: False
367
+ 2022-05-02 01:26:53,902 DEV : loss 0.017985524609684944 - f1-score (micro avg) 0.9561
368
+ 2022-05-02 01:26:54,267 BAD EPOCHS (no improvement): 1
369
+ 2022-05-02 01:26:54,268 ----------------------------------------------------------------------------------------------------
370
+ 2022-05-02 01:27:33,418 epoch 20 - iter 5/50 - loss 0.01535513 - samples/sec: 1.28 - lr: 0.200000
371
+ 2022-05-02 01:28:04,020 epoch 20 - iter 10/50 - loss 0.01551717 - samples/sec: 1.63 - lr: 0.200000
372
+ 2022-05-02 01:28:34,059 epoch 20 - iter 15/50 - loss 0.01660312 - samples/sec: 1.66 - lr: 0.200000
373
+ 2022-05-02 01:29:23,815 epoch 20 - iter 20/50 - loss 0.01587475 - samples/sec: 1.00 - lr: 0.200000
374
+ 2022-05-02 01:30:05,532 epoch 20 - iter 25/50 - loss 0.01458499 - samples/sec: 1.20 - lr: 0.200000
375
+ 2022-05-02 01:30:33,536 epoch 20 - iter 30/50 - loss 0.01440965 - samples/sec: 1.79 - lr: 0.200000
376
+ 2022-05-02 01:31:00,194 epoch 20 - iter 35/50 - loss 0.01434420 - samples/sec: 1.88 - lr: 0.200000
377
+ 2022-05-02 01:31:31,884 epoch 20 - iter 40/50 - loss 0.01437732 - samples/sec: 1.58 - lr: 0.200000
378
+ 2022-05-02 01:31:56,030 epoch 20 - iter 45/50 - loss 0.01440543 - samples/sec: 2.07 - lr: 0.200000
379
+ 2022-05-02 01:32:27,251 epoch 20 - iter 50/50 - loss 0.01453023 - samples/sec: 1.60 - lr: 0.200000
380
+ 2022-05-02 01:32:27,252 ----------------------------------------------------------------------------------------------------
381
+ 2022-05-02 01:32:27,253 EPOCH 20 done: loss 0.0145 - lr 0.200000
382
+ 2022-05-02 01:33:06,063 Evaluating as a multi-label problem: False
383
+ 2022-05-02 01:33:06,108 DEV : loss 0.018309906125068665 - f1-score (micro avg) 0.9562
384
+ 2022-05-02 01:33:06,474 BAD EPOCHS (no improvement): 2
385
+ 2022-05-02 01:33:06,475 ----------------------------------------------------------------------------------------------------
386
+ 2022-05-02 01:33:45,644 epoch 21 - iter 5/50 - loss 0.01345298 - samples/sec: 1.28 - lr: 0.200000
387
+ 2022-05-02 01:34:26,293 epoch 21 - iter 10/50 - loss 0.01108962 - samples/sec: 1.23 - lr: 0.200000
388
+ 2022-05-02 01:34:55,482 epoch 21 - iter 15/50 - loss 0.01187357 - samples/sec: 1.71 - lr: 0.200000
389
+ 2022-05-02 01:35:28,688 epoch 21 - iter 20/50 - loss 0.01313972 - samples/sec: 1.51 - lr: 0.200000
390
+ 2022-05-02 01:36:09,049 epoch 21 - iter 25/50 - loss 0.01240205 - samples/sec: 1.24 - lr: 0.200000
391
+ 2022-05-02 01:36:39,683 epoch 21 - iter 30/50 - loss 0.01321939 - samples/sec: 1.63 - lr: 0.200000
392
+ 2022-05-02 01:37:12,914 epoch 21 - iter 35/50 - loss 0.01343786 - samples/sec: 1.50 - lr: 0.200000
393
+ 2022-05-02 01:37:44,070 epoch 21 - iter 40/50 - loss 0.01324334 - samples/sec: 1.60 - lr: 0.200000
394
+ 2022-05-02 01:38:16,115 epoch 21 - iter 45/50 - loss 0.01348715 - samples/sec: 1.56 - lr: 0.200000
395
+ 2022-05-02 01:38:46,778 epoch 21 - iter 50/50 - loss 0.01385155 - samples/sec: 1.63 - lr: 0.200000
396
+ 2022-05-02 01:38:46,779 ----------------------------------------------------------------------------------------------------
397
+ 2022-05-02 01:38:46,779 EPOCH 21 done: loss 0.0139 - lr 0.200000
398
+ 2022-05-02 01:39:25,947 Evaluating as a multi-label problem: False
399
+ 2022-05-02 01:39:25,992 DEV : loss 0.018414735794067383 - f1-score (micro avg) 0.9577
400
+ 2022-05-02 01:39:26,373 BAD EPOCHS (no improvement): 3
401
+ 2022-05-02 01:39:26,374 ----------------------------------------------------------------------------------------------------
402
+ 2022-05-02 01:39:53,285 epoch 22 - iter 5/50 - loss 0.01103225 - samples/sec: 1.86 - lr: 0.200000
403
+ 2022-05-02 01:40:25,757 epoch 22 - iter 10/50 - loss 0.01337513 - samples/sec: 1.54 - lr: 0.200000
404
+ 2022-05-02 01:40:57,872 epoch 22 - iter 15/50 - loss 0.01214435 - samples/sec: 1.56 - lr: 0.200000
405
+ 2022-05-02 01:41:26,185 epoch 22 - iter 20/50 - loss 0.01222157 - samples/sec: 1.77 - lr: 0.200000
406
+ 2022-05-02 01:41:57,662 epoch 22 - iter 25/50 - loss 0.01256829 - samples/sec: 1.59 - lr: 0.200000
407
+ 2022-05-02 01:42:34,091 epoch 22 - iter 30/50 - loss 0.01301611 - samples/sec: 1.37 - lr: 0.200000
408
+ 2022-05-02 01:43:00,864 epoch 22 - iter 35/50 - loss 0.01281379 - samples/sec: 1.87 - lr: 0.200000
409
+ 2022-05-02 01:43:39,312 epoch 22 - iter 40/50 - loss 0.01315224 - samples/sec: 1.30 - lr: 0.200000
410
+ 2022-05-02 01:44:15,640 epoch 22 - iter 45/50 - loss 0.01337695 - samples/sec: 1.38 - lr: 0.200000
411
+ 2022-05-02 01:44:59,195 epoch 22 - iter 50/50 - loss 0.01316689 - samples/sec: 1.15 - lr: 0.200000
412
+ 2022-05-02 01:44:59,196 ----------------------------------------------------------------------------------------------------
413
+ 2022-05-02 01:44:59,197 EPOCH 22 done: loss 0.0132 - lr 0.200000
414
+ 2022-05-02 01:45:38,278 Evaluating as a multi-label problem: False
415
+ 2022-05-02 01:45:38,322 DEV : loss 0.018778858706355095 - f1-score (micro avg) 0.9612
416
+ 2022-05-02 01:45:38,692 BAD EPOCHS (no improvement): 0
417
+ 2022-05-02 01:45:38,693 saving best model
418
+ 2022-05-02 01:45:47,564 ----------------------------------------------------------------------------------------------------
419
+ 2022-05-02 01:46:17,827 epoch 23 - iter 5/50 - loss 0.01019548 - samples/sec: 1.65 - lr: 0.200000
420
+ 2022-05-02 01:46:46,764 epoch 23 - iter 10/50 - loss 0.01091285 - samples/sec: 1.73 - lr: 0.200000
421
+ 2022-05-02 01:47:21,766 epoch 23 - iter 15/50 - loss 0.01073102 - samples/sec: 1.43 - lr: 0.200000
422
+ 2022-05-02 01:48:07,800 epoch 23 - iter 20/50 - loss 0.01171196 - samples/sec: 1.09 - lr: 0.200000
423
+ 2022-05-02 01:48:38,601 epoch 23 - iter 25/50 - loss 0.01172103 - samples/sec: 1.62 - lr: 0.200000
424
+ 2022-05-02 01:49:09,042 epoch 23 - iter 30/50 - loss 0.01160284 - samples/sec: 1.64 - lr: 0.200000
425
+ 2022-05-02 01:49:48,139 epoch 23 - iter 35/50 - loss 0.01137587 - samples/sec: 1.28 - lr: 0.200000
426
+ 2022-05-02 01:50:19,671 epoch 23 - iter 40/50 - loss 0.01143246 - samples/sec: 1.59 - lr: 0.200000
427
+ 2022-05-02 01:50:51,284 epoch 23 - iter 45/50 - loss 0.01146448 - samples/sec: 1.58 - lr: 0.200000
428
+ 2022-05-02 01:51:23,749 epoch 23 - iter 50/50 - loss 0.01230814 - samples/sec: 1.54 - lr: 0.200000
429
+ 2022-05-02 01:51:23,750 ----------------------------------------------------------------------------------------------------
430
+ 2022-05-02 01:51:23,750 EPOCH 23 done: loss 0.0123 - lr 0.200000
431
+ 2022-05-02 01:52:04,699 Evaluating as a multi-label problem: False
432
+ 2022-05-02 01:52:04,744 DEV : loss 0.017714107409119606 - f1-score (micro avg) 0.9588
433
+ 2022-05-02 01:52:05,113 BAD EPOCHS (no improvement): 1
434
+ 2022-05-02 01:52:05,114 ----------------------------------------------------------------------------------------------------
435
+ 2022-05-02 01:52:38,189 epoch 24 - iter 5/50 - loss 0.01070257 - samples/sec: 1.51 - lr: 0.200000
436
+ 2022-05-02 01:53:08,291 epoch 24 - iter 10/50 - loss 0.01020088 - samples/sec: 1.66 - lr: 0.200000
437
+ 2022-05-02 01:53:33,455 epoch 24 - iter 15/50 - loss 0.00992330 - samples/sec: 1.99 - lr: 0.200000
438
+ 2022-05-02 01:54:09,840 epoch 24 - iter 20/50 - loss 0.01034393 - samples/sec: 1.37 - lr: 0.200000
439
+ 2022-05-02 01:54:52,220 epoch 24 - iter 25/50 - loss 0.01178760 - samples/sec: 1.18 - lr: 0.200000
440
+ 2022-05-02 01:55:36,887 epoch 24 - iter 30/50 - loss 0.01193657 - samples/sec: 1.12 - lr: 0.200000
441
+ 2022-05-02 01:56:07,695 epoch 24 - iter 35/50 - loss 0.01230857 - samples/sec: 1.62 - lr: 0.200000
442
+ 2022-05-02 01:56:40,715 epoch 24 - iter 40/50 - loss 0.01227429 - samples/sec: 1.51 - lr: 0.200000
443
+ 2022-05-02 01:57:15,524 epoch 24 - iter 45/50 - loss 0.01214672 - samples/sec: 1.44 - lr: 0.200000
444
+ 2022-05-02 01:57:45,095 epoch 24 - iter 50/50 - loss 0.01231205 - samples/sec: 1.69 - lr: 0.200000
445
+ 2022-05-02 01:57:45,096 ----------------------------------------------------------------------------------------------------
446
+ 2022-05-02 01:57:45,097 EPOCH 24 done: loss 0.0123 - lr 0.200000
447
+ 2022-05-02 01:58:25,136 Evaluating as a multi-label problem: False
448
+ 2022-05-02 01:58:25,186 DEV : loss 0.017465807497501373 - f1-score (micro avg) 0.9626
449
+ 2022-05-02 01:58:25,551 BAD EPOCHS (no improvement): 0
450
+ 2022-05-02 01:58:25,552 saving best model
451
+ 2022-05-02 01:58:34,906 ----------------------------------------------------------------------------------------------------
452
+ 2022-05-02 01:59:11,121 epoch 25 - iter 5/50 - loss 0.00835182 - samples/sec: 1.38 - lr: 0.200000
453
+ 2022-05-02 01:59:44,515 epoch 25 - iter 10/50 - loss 0.00841875 - samples/sec: 1.50 - lr: 0.200000
454
+ 2022-05-02 02:00:13,509 epoch 25 - iter 15/50 - loss 0.00920303 - samples/sec: 1.72 - lr: 0.200000
455
+ 2022-05-02 02:00:48,331 epoch 25 - iter 20/50 - loss 0.00963892 - samples/sec: 1.44 - lr: 0.200000
456
+ 2022-05-02 02:01:18,476 epoch 25 - iter 25/50 - loss 0.01193988 - samples/sec: 1.66 - lr: 0.200000
457
+ 2022-05-02 02:01:48,637 epoch 25 - iter 30/50 - loss 0.01230734 - samples/sec: 1.66 - lr: 0.200000
458
+ 2022-05-02 02:02:23,092 epoch 25 - iter 35/50 - loss 0.01185128 - samples/sec: 1.45 - lr: 0.200000
459
+ 2022-05-02 02:03:13,132 epoch 25 - iter 40/50 - loss 0.01183207 - samples/sec: 1.00 - lr: 0.200000
460
+ 2022-05-02 02:03:46,504 epoch 25 - iter 45/50 - loss 0.01221390 - samples/sec: 1.50 - lr: 0.200000
461
+ 2022-05-02 02:04:16,675 epoch 25 - iter 50/50 - loss 0.01210439 - samples/sec: 1.66 - lr: 0.200000
462
+ 2022-05-02 02:04:16,676 ----------------------------------------------------------------------------------------------------
463
+ 2022-05-02 02:04:16,676 EPOCH 25 done: loss 0.0121 - lr 0.200000
464
+ 2022-05-02 02:04:57,080 Evaluating as a multi-label problem: False
465
+ 2022-05-02 02:04:57,124 DEV : loss 0.018742656335234642 - f1-score (micro avg) 0.9609
466
+ 2022-05-02 02:04:57,494 BAD EPOCHS (no improvement): 1
467
+ 2022-05-02 02:04:57,495 ----------------------------------------------------------------------------------------------------
468
+ 2022-05-02 02:05:40,113 epoch 26 - iter 5/50 - loss 0.01515581 - samples/sec: 1.17 - lr: 0.200000
469
+ 2022-05-02 02:06:19,456 epoch 26 - iter 10/50 - loss 0.01236536 - samples/sec: 1.27 - lr: 0.200000
470
+ 2022-05-02 02:06:50,164 epoch 26 - iter 15/50 - loss 0.01183759 - samples/sec: 1.63 - lr: 0.200000
471
+ 2022-05-02 02:07:26,562 epoch 26 - iter 20/50 - loss 0.01143644 - samples/sec: 1.37 - lr: 0.200000
472
+ 2022-05-02 02:08:14,090 epoch 26 - iter 25/50 - loss 0.01049456 - samples/sec: 1.05 - lr: 0.200000
473
+ 2022-05-02 02:08:42,526 epoch 26 - iter 30/50 - loss 0.01066549 - samples/sec: 1.76 - lr: 0.200000
474
+ 2022-05-02 02:09:09,369 epoch 26 - iter 35/50 - loss 0.01084137 - samples/sec: 1.86 - lr: 0.200000
475
+ 2022-05-02 02:09:42,534 epoch 26 - iter 40/50 - loss 0.01059200 - samples/sec: 1.51 - lr: 0.200000
476
+ 2022-05-02 02:10:12,322 epoch 26 - iter 45/50 - loss 0.01109223 - samples/sec: 1.68 - lr: 0.200000
477
+ 2022-05-02 02:10:43,603 epoch 26 - iter 50/50 - loss 0.01107015 - samples/sec: 1.60 - lr: 0.200000
478
+ 2022-05-02 02:10:43,604 ----------------------------------------------------------------------------------------------------
479
+ 2022-05-02 02:10:43,605 EPOCH 26 done: loss 0.0111 - lr 0.200000
480
+ 2022-05-02 02:11:22,640 Evaluating as a multi-label problem: False
481
+ 2022-05-02 02:11:22,683 DEV : loss 0.01924612745642662 - f1-score (micro avg) 0.96
482
+ 2022-05-02 02:11:23,056 BAD EPOCHS (no improvement): 2
483
+ 2022-05-02 02:11:23,057 ----------------------------------------------------------------------------------------------------
484
+ 2022-05-02 02:11:43,600 epoch 27 - iter 5/50 - loss 0.01222196 - samples/sec: 2.43 - lr: 0.200000
485
+ 2022-05-02 02:12:15,657 epoch 27 - iter 10/50 - loss 0.01096847 - samples/sec: 1.56 - lr: 0.200000
486
+ 2022-05-02 02:12:47,655 epoch 27 - iter 15/50 - loss 0.01201508 - samples/sec: 1.56 - lr: 0.200000
487
+ 2022-05-02 02:13:19,201 epoch 27 - iter 20/50 - loss 0.01161129 - samples/sec: 1.59 - lr: 0.200000
488
+ 2022-05-02 02:14:07,805 epoch 27 - iter 25/50 - loss 0.01143997 - samples/sec: 1.03 - lr: 0.200000
489
+ 2022-05-02 02:14:49,203 epoch 27 - iter 30/50 - loss 0.01160461 - samples/sec: 1.21 - lr: 0.200000
490
+ 2022-05-02 02:15:20,163 epoch 27 - iter 35/50 - loss 0.01096207 - samples/sec: 1.62 - lr: 0.200000
491
+ 2022-05-02 02:15:54,248 epoch 27 - iter 40/50 - loss 0.01156551 - samples/sec: 1.47 - lr: 0.200000
492
+ 2022-05-02 02:16:32,198 epoch 27 - iter 45/50 - loss 0.01141787 - samples/sec: 1.32 - lr: 0.200000
493
+ 2022-05-02 02:17:08,506 epoch 27 - iter 50/50 - loss 0.01140012 - samples/sec: 1.38 - lr: 0.200000
494
+ 2022-05-02 02:17:08,507 ----------------------------------------------------------------------------------------------------
495
+ 2022-05-02 02:17:08,507 EPOCH 27 done: loss 0.0114 - lr 0.200000
496
+ 2022-05-02 02:17:48,158 Evaluating as a multi-label problem: False
497
+ 2022-05-02 02:17:48,203 DEV : loss 0.01935002952814102 - f1-score (micro avg) 0.9593
498
+ 2022-05-02 02:17:48,571 BAD EPOCHS (no improvement): 3
499
+ 2022-05-02 02:17:48,571 ----------------------------------------------------------------------------------------------------
500
+ 2022-05-02 02:18:18,076 epoch 28 - iter 5/50 - loss 0.00714381 - samples/sec: 1.69 - lr: 0.200000
501
+ 2022-05-02 02:18:56,536 epoch 28 - iter 10/50 - loss 0.00726069 - samples/sec: 1.30 - lr: 0.200000
502
+ 2022-05-02 02:19:37,502 epoch 28 - iter 15/50 - loss 0.00840913 - samples/sec: 1.22 - lr: 0.200000
503
+ 2022-05-02 02:20:11,621 epoch 28 - iter 20/50 - loss 0.01007193 - samples/sec: 1.47 - lr: 0.200000
504
+ 2022-05-02 02:20:46,800 epoch 28 - iter 25/50 - loss 0.00936459 - samples/sec: 1.42 - lr: 0.200000
505
+ 2022-05-02 02:21:18,299 epoch 28 - iter 30/50 - loss 0.00938612 - samples/sec: 1.59 - lr: 0.200000
506
+ 2022-05-02 02:21:58,955 epoch 28 - iter 35/50 - loss 0.00933655 - samples/sec: 1.23 - lr: 0.200000
507
+ 2022-05-02 02:22:38,343 epoch 28 - iter 40/50 - loss 0.00978371 - samples/sec: 1.27 - lr: 0.200000
508
+ 2022-05-02 02:23:08,433 epoch 28 - iter 45/50 - loss 0.00974709 - samples/sec: 1.66 - lr: 0.200000
509
+ 2022-05-02 02:23:39,063 epoch 28 - iter 50/50 - loss 0.00984920 - samples/sec: 1.63 - lr: 0.200000
510
+ 2022-05-02 02:23:39,064 ----------------------------------------------------------------------------------------------------
511
+ 2022-05-02 02:23:39,064 EPOCH 28 done: loss 0.0098 - lr 0.200000
512
+ 2022-05-02 02:24:19,633 Evaluating as a multi-label problem: False
513
+ 2022-05-02 02:24:19,682 DEV : loss 0.018351776525378227 - f1-score (micro avg) 0.96
514
+ 2022-05-02 02:24:20,051 BAD EPOCHS (no improvement): 4
515
+ 2022-05-02 02:24:20,052 ----------------------------------------------------------------------------------------------------
516
+ 2022-05-02 02:24:57,108 epoch 29 - iter 5/50 - loss 0.01188691 - samples/sec: 1.35 - lr: 0.200000
517
+ 2022-05-02 02:25:34,742 epoch 29 - iter 10/50 - loss 0.01063387 - samples/sec: 1.33 - lr: 0.200000
518
+ 2022-05-02 02:26:04,950 epoch 29 - iter 15/50 - loss 0.00998180 - samples/sec: 1.66 - lr: 0.200000
519
+ 2022-05-02 02:26:30,786 epoch 29 - iter 20/50 - loss 0.01001974 - samples/sec: 1.94 - lr: 0.200000
520
+ 2022-05-02 02:26:55,423 epoch 29 - iter 25/50 - loss 0.00960256 - samples/sec: 2.03 - lr: 0.200000
521
+ 2022-05-02 02:27:30,608 epoch 29 - iter 30/50 - loss 0.00967787 - samples/sec: 1.42 - lr: 0.200000
522
+ 2022-05-02 02:28:10,517 epoch 29 - iter 35/50 - loss 0.00961606 - samples/sec: 1.25 - lr: 0.200000
523
+ 2022-05-02 02:28:41,426 epoch 29 - iter 40/50 - loss 0.00957507 - samples/sec: 1.62 - lr: 0.200000
524
+ 2022-05-02 02:29:18,841 epoch 29 - iter 45/50 - loss 0.00927588 - samples/sec: 1.34 - lr: 0.200000
525
+ 2022-05-02 02:29:58,327 epoch 29 - iter 50/50 - loss 0.00950956 - samples/sec: 1.27 - lr: 0.200000
526
+ 2022-05-02 02:29:58,328 ----------------------------------------------------------------------------------------------------
527
+ 2022-05-02 02:29:58,329 EPOCH 29 done: loss 0.0095 - lr 0.200000
528
+ 2022-05-02 02:30:37,470 Evaluating as a multi-label problem: False
529
+ 2022-05-02 02:30:37,516 DEV : loss 0.01798679679632187 - f1-score (micro avg) 0.9595
530
+ 2022-05-02 02:30:37,883 BAD EPOCHS (no improvement): 5
531
+ 2022-05-02 02:30:37,884 ----------------------------------------------------------------------------------------------------
532
+ 2022-05-02 02:31:12,192 epoch 30 - iter 5/50 - loss 0.00737040 - samples/sec: 1.46 - lr: 0.200000
533
+ 2022-05-02 02:31:45,250 epoch 30 - iter 10/50 - loss 0.00827101 - samples/sec: 1.51 - lr: 0.200000
534
+ 2022-05-02 02:32:17,645 epoch 30 - iter 15/50 - loss 0.00917759 - samples/sec: 1.54 - lr: 0.200000
535
+ 2022-05-02 02:33:00,407 epoch 30 - iter 20/50 - loss 0.00855301 - samples/sec: 1.17 - lr: 0.200000
536
+ 2022-05-02 02:33:30,651 epoch 30 - iter 25/50 - loss 0.00852118 - samples/sec: 1.65 - lr: 0.200000
537
+ 2022-05-02 02:34:00,536 epoch 30 - iter 30/50 - loss 0.00899308 - samples/sec: 1.67 - lr: 0.200000
538
+ 2022-05-02 02:34:32,171 epoch 30 - iter 35/50 - loss 0.00916576 - samples/sec: 1.58 - lr: 0.200000
539
+ 2022-05-02 02:34:56,863 epoch 30 - iter 40/50 - loss 0.00927975 - samples/sec: 2.02 - lr: 0.200000
540
+ 2022-05-02 02:35:37,355 epoch 30 - iter 45/50 - loss 0.00930276 - samples/sec: 1.23 - lr: 0.200000
541
+ 2022-05-02 02:36:17,993 epoch 30 - iter 50/50 - loss 0.00947876 - samples/sec: 1.23 - lr: 0.200000
542
+ 2022-05-02 02:36:17,994 ----------------------------------------------------------------------------------------------------
543
+ 2022-05-02 02:36:17,994 EPOCH 30 done: loss 0.0095 - lr 0.200000
544
+ 2022-05-02 02:36:57,575 Evaluating as a multi-label problem: False
545
+ 2022-05-02 02:36:57,623 DEV : loss 0.01766378805041313 - f1-score (micro avg) 0.9596
546
+ 2022-05-02 02:36:57,995 BAD EPOCHS (no improvement): 6
547
+ 2022-05-02 02:36:57,996 ----------------------------------------------------------------------------------------------------
548
+ 2022-05-02 02:37:35,964 epoch 31 - iter 5/50 - loss 0.00540228 - samples/sec: 1.32 - lr: 0.200000
549
+ 2022-05-02 02:38:13,609 epoch 31 - iter 10/50 - loss 0.00796408 - samples/sec: 1.33 - lr: 0.200000
550
+ 2022-05-02 02:38:40,907 epoch 31 - iter 15/50 - loss 0.00790600 - samples/sec: 1.83 - lr: 0.200000
551
+ 2022-05-02 02:39:10,971 epoch 31 - iter 20/50 - loss 0.00841028 - samples/sec: 1.66 - lr: 0.200000
552
+ 2022-05-02 02:39:48,555 epoch 31 - iter 25/50 - loss 0.00897818 - samples/sec: 1.33 - lr: 0.200000
553
+ 2022-05-02 02:40:20,816 epoch 31 - iter 30/50 - loss 0.00844028 - samples/sec: 1.55 - lr: 0.200000
554
+ 2022-05-02 02:40:51,705 epoch 31 - iter 35/50 - loss 0.00912694 - samples/sec: 1.62 - lr: 0.200000
555
+ 2022-05-02 02:41:22,319 epoch 31 - iter 40/50 - loss 0.00887215 - samples/sec: 1.63 - lr: 0.200000
556
+ 2022-05-02 02:41:55,419 epoch 31 - iter 45/50 - loss 0.00843974 - samples/sec: 1.51 - lr: 0.200000
557
+ 2022-05-02 02:42:33,483 epoch 31 - iter 50/50 - loss 0.00863241 - samples/sec: 1.31 - lr: 0.200000
558
+ 2022-05-02 02:42:33,484 ----------------------------------------------------------------------------------------------------
559
+ 2022-05-02 02:42:33,485 EPOCH 31 done: loss 0.0086 - lr 0.200000
560
+ 2022-05-02 02:43:13,323 Evaluating as a multi-label problem: False
561
+ 2022-05-02 02:43:13,368 DEV : loss 0.017775144428014755 - f1-score (micro avg) 0.9612
562
+ 2022-05-02 02:43:13,738 BAD EPOCHS (no improvement): 7
563
+ 2022-05-02 02:43:13,739 ----------------------------------------------------------------------------------------------------
564
+ 2022-05-02 02:43:40,413 epoch 32 - iter 5/50 - loss 0.00900492 - samples/sec: 1.87 - lr: 0.200000
565
+ 2022-05-02 02:44:14,751 epoch 32 - iter 10/50 - loss 0.00783097 - samples/sec: 1.46 - lr: 0.200000
566
+ 2022-05-02 02:44:40,602 epoch 32 - iter 15/50 - loss 0.00789850 - samples/sec: 1.93 - lr: 0.200000
567
+ 2022-05-02 02:45:13,097 epoch 32 - iter 20/50 - loss 0.00810840 - samples/sec: 1.54 - lr: 0.200000
568
+ 2022-05-02 02:45:49,181 epoch 32 - iter 25/50 - loss 0.00788602 - samples/sec: 1.39 - lr: 0.200000
569
+ 2022-05-02 02:46:20,816 epoch 32 - iter 30/50 - loss 0.00780582 - samples/sec: 1.58 - lr: 0.200000
570
+ 2022-05-02 02:46:57,467 epoch 32 - iter 35/50 - loss 0.00822874 - samples/sec: 1.36 - lr: 0.200000
571
+ 2022-05-02 02:47:22,986 epoch 32 - iter 40/50 - loss 0.00859442 - samples/sec: 1.96 - lr: 0.200000
572
+ 2022-05-02 02:47:59,988 epoch 32 - iter 45/50 - loss 0.00865436 - samples/sec: 1.35 - lr: 0.200000
573
+ 2022-05-02 02:48:42,533 epoch 32 - iter 50/50 - loss 0.00860554 - samples/sec: 1.18 - lr: 0.200000
574
+ 2022-05-02 02:48:42,534 ----------------------------------------------------------------------------------------------------
575
+ 2022-05-02 02:48:42,534 EPOCH 32 done: loss 0.0086 - lr 0.200000
576
+ 2022-05-02 02:49:21,924 Evaluating as a multi-label problem: False
577
+ 2022-05-02 02:49:21,970 DEV : loss 0.019158849492669106 - f1-score (micro avg) 0.9604
578
+ 2022-05-02 02:49:22,345 BAD EPOCHS (no improvement): 8
579
+ 2022-05-02 02:49:22,346 ----------------------------------------------------------------------------------------------------
580
+ 2022-05-02 02:49:49,386 epoch 33 - iter 5/50 - loss 0.00888103 - samples/sec: 1.85 - lr: 0.200000
581
+ 2022-05-02 02:50:24,726 epoch 33 - iter 10/50 - loss 0.00883522 - samples/sec: 1.41 - lr: 0.200000
582
+ 2022-05-02 02:50:54,622 epoch 33 - iter 15/50 - loss 0.00844782 - samples/sec: 1.67 - lr: 0.200000
583
+ 2022-05-02 02:51:28,896 epoch 33 - iter 20/50 - loss 0.00893736 - samples/sec: 1.46 - lr: 0.200000
584
+ 2022-05-02 02:51:59,487 epoch 33 - iter 25/50 - loss 0.00896741 - samples/sec: 1.63 - lr: 0.200000
585
+ 2022-05-02 02:52:37,803 epoch 33 - iter 30/50 - loss 0.00906042 - samples/sec: 1.30 - lr: 0.200000
586
+ 2022-05-02 02:53:08,668 epoch 33 - iter 35/50 - loss 0.00929703 - samples/sec: 1.62 - lr: 0.200000
587
+ 2022-05-02 02:53:44,806 epoch 33 - iter 40/50 - loss 0.00960662 - samples/sec: 1.38 - lr: 0.200000
588
+ 2022-05-02 02:54:16,998 epoch 33 - iter 45/50 - loss 0.00940144 - samples/sec: 1.55 - lr: 0.200000
589
+ 2022-05-02 02:54:59,497 epoch 33 - iter 50/50 - loss 0.00937120 - samples/sec: 1.18 - lr: 0.200000
590
+ 2022-05-02 02:54:59,498 ----------------------------------------------------------------------------------------------------
591
+ 2022-05-02 02:54:59,499 EPOCH 33 done: loss 0.0094 - lr 0.200000
592
+ 2022-05-02 02:55:38,290 Evaluating as a multi-label problem: False
593
+ 2022-05-02 02:55:38,334 DEV : loss 0.018400516360998154 - f1-score (micro avg) 0.9612
594
+ 2022-05-02 02:55:38,700 BAD EPOCHS (no improvement): 9
595
+ 2022-05-02 02:55:38,701 ----------------------------------------------------------------------------------------------------
596
+ 2022-05-02 02:56:19,536 epoch 34 - iter 5/50 - loss 0.00930039 - samples/sec: 1.22 - lr: 0.200000
597
+ 2022-05-02 02:56:48,489 epoch 34 - iter 10/50 - loss 0.00801897 - samples/sec: 1.73 - lr: 0.200000
598
+ 2022-05-02 02:57:27,994 epoch 34 - iter 15/50 - loss 0.00840370 - samples/sec: 1.27 - lr: 0.200000
599
+ 2022-05-02 02:58:03,940 epoch 34 - iter 20/50 - loss 0.00762042 - samples/sec: 1.39 - lr: 0.200000
600
+ 2022-05-02 02:58:39,076 epoch 34 - iter 25/50 - loss 0.00737031 - samples/sec: 1.42 - lr: 0.200000
601
+ 2022-05-02 02:59:01,972 epoch 34 - iter 30/50 - loss 0.00704501 - samples/sec: 2.18 - lr: 0.200000
602
+ 2022-05-02 02:59:32,954 epoch 34 - iter 35/50 - loss 0.00732848 - samples/sec: 1.61 - lr: 0.200000
603
+ 2022-05-02 03:00:16,722 epoch 34 - iter 40/50 - loss 0.00780114 - samples/sec: 1.14 - lr: 0.200000
604
+ 2022-05-02 03:00:45,766 epoch 34 - iter 45/50 - loss 0.00797383 - samples/sec: 1.72 - lr: 0.200000
605
+ 2022-05-02 03:01:15,266 epoch 34 - iter 50/50 - loss 0.00824764 - samples/sec: 1.70 - lr: 0.200000
606
+ 2022-05-02 03:01:15,267 ----------------------------------------------------------------------------------------------------
607
+ 2022-05-02 03:01:15,267 EPOCH 34 done: loss 0.0082 - lr 0.200000
608
+ 2022-05-02 03:01:54,223 Evaluating as a multi-label problem: False
609
+ 2022-05-02 03:01:54,269 DEV : loss 0.018301010131835938 - f1-score (micro avg) 0.9617
610
+ 2022-05-02 03:01:54,649 BAD EPOCHS (no improvement): 10
611
+ 2022-05-02 03:01:54,650 ----------------------------------------------------------------------------------------------------
612
+ 2022-05-02 03:02:33,599 epoch 35 - iter 5/50 - loss 0.00672813 - samples/sec: 1.28 - lr: 0.200000
613
+ 2022-05-02 03:02:55,671 epoch 35 - iter 10/50 - loss 0.00684949 - samples/sec: 2.27 - lr: 0.200000
614
+ 2022-05-02 03:03:23,572 epoch 35 - iter 15/50 - loss 0.00667993 - samples/sec: 1.79 - lr: 0.200000
615
+ 2022-05-02 03:04:09,116 epoch 35 - iter 20/50 - loss 0.00670091 - samples/sec: 1.10 - lr: 0.200000
616
+ 2022-05-02 03:04:38,504 epoch 35 - iter 25/50 - loss 0.00725066 - samples/sec: 1.70 - lr: 0.200000
617
+ 2022-05-02 03:05:10,247 epoch 35 - iter 30/50 - loss 0.00737094 - samples/sec: 1.58 - lr: 0.200000
618
+ 2022-05-02 03:05:35,176 epoch 35 - iter 35/50 - loss 0.00738323 - samples/sec: 2.01 - lr: 0.200000
619
+ 2022-05-02 03:06:15,171 epoch 35 - iter 40/50 - loss 0.00753408 - samples/sec: 1.25 - lr: 0.200000
620
+ 2022-05-02 03:06:52,576 epoch 35 - iter 45/50 - loss 0.00780416 - samples/sec: 1.34 - lr: 0.200000
621
+ 2022-05-02 03:07:24,629 epoch 35 - iter 50/50 - loss 0.00799998 - samples/sec: 1.56 - lr: 0.200000
622
+ 2022-05-02 03:07:24,630 ----------------------------------------------------------------------------------------------------
623
+ 2022-05-02 03:07:24,631 EPOCH 35 done: loss 0.0080 - lr 0.200000
624
+ 2022-05-02 03:08:05,047 Evaluating as a multi-label problem: False
625
+ 2022-05-02 03:08:05,090 DEV : loss 0.018051404505968094 - f1-score (micro avg) 0.963
626
+ 2022-05-02 03:08:05,454 BAD EPOCHS (no improvement): 0
627
+ 2022-05-02 03:08:05,455 saving best model
628
+ 2022-05-02 03:08:14,444 ----------------------------------------------------------------------------------------------------
629
+ 2022-05-02 03:09:03,265 epoch 36 - iter 5/50 - loss 0.00774939 - samples/sec: 1.02 - lr: 0.200000
630
+ 2022-05-02 03:09:36,191 epoch 36 - iter 10/50 - loss 0.00701369 - samples/sec: 1.52 - lr: 0.200000
631
+ 2022-05-02 03:10:09,038 epoch 36 - iter 15/50 - loss 0.00697280 - samples/sec: 1.52 - lr: 0.200000
632
+ 2022-05-02 03:10:40,425 epoch 36 - iter 20/50 - loss 0.00749198 - samples/sec: 1.59 - lr: 0.200000
633
+ 2022-05-02 03:11:16,958 epoch 36 - iter 25/50 - loss 0.00806585 - samples/sec: 1.37 - lr: 0.200000
634
+ 2022-05-02 03:11:45,131 epoch 36 - iter 30/50 - loss 0.00864917 - samples/sec: 1.77 - lr: 0.200000
635
+ 2022-05-02 03:12:13,728 epoch 36 - iter 35/50 - loss 0.00846672 - samples/sec: 1.75 - lr: 0.200000
636
+ 2022-05-02 03:12:39,751 epoch 36 - iter 40/50 - loss 0.00842475 - samples/sec: 1.92 - lr: 0.200000
637
+ 2022-05-02 03:13:07,675 epoch 36 - iter 45/50 - loss 0.00844087 - samples/sec: 1.79 - lr: 0.200000
638
+ 2022-05-02 03:13:49,112 epoch 36 - iter 50/50 - loss 0.00817720 - samples/sec: 1.21 - lr: 0.200000
639
+ 2022-05-02 03:13:49,113 ----------------------------------------------------------------------------------------------------
640
+ 2022-05-02 03:13:49,114 EPOCH 36 done: loss 0.0082 - lr 0.200000
641
+ 2022-05-02 03:14:29,703 Evaluating as a multi-label problem: False
642
+ 2022-05-02 03:14:29,754 DEV : loss 0.01777895726263523 - f1-score (micro avg) 0.9628
643
+ 2022-05-02 03:14:30,121 BAD EPOCHS (no improvement): 1
644
+ 2022-05-02 03:14:30,122 ----------------------------------------------------------------------------------------------------
645
+ 2022-05-02 03:15:02,202 epoch 37 - iter 5/50 - loss 0.00678465 - samples/sec: 1.56 - lr: 0.200000
646
+ 2022-05-02 03:15:31,626 epoch 37 - iter 10/50 - loss 0.00711282 - samples/sec: 1.70 - lr: 0.200000
647
+ 2022-05-02 03:16:05,651 epoch 37 - iter 15/50 - loss 0.00692723 - samples/sec: 1.47 - lr: 0.200000
648
+ 2022-05-02 03:16:32,979 epoch 37 - iter 20/50 - loss 0.00728154 - samples/sec: 1.83 - lr: 0.200000
649
+ 2022-05-02 03:17:19,997 epoch 37 - iter 25/50 - loss 0.00692815 - samples/sec: 1.06 - lr: 0.200000
650
+ 2022-05-02 03:17:50,851 epoch 37 - iter 30/50 - loss 0.00723098 - samples/sec: 1.62 - lr: 0.200000
651
+ 2022-05-02 03:18:20,670 epoch 37 - iter 35/50 - loss 0.00738427 - samples/sec: 1.68 - lr: 0.200000
652
+ 2022-05-02 03:18:52,690 epoch 37 - iter 40/50 - loss 0.00743336 - samples/sec: 1.56 - lr: 0.200000
653
+ 2022-05-02 03:19:22,905 epoch 37 - iter 45/50 - loss 0.00776175 - samples/sec: 1.65 - lr: 0.200000
654
+ 2022-05-02 03:19:57,500 epoch 37 - iter 50/50 - loss 0.00759396 - samples/sec: 1.45 - lr: 0.200000
655
+ 2022-05-02 03:19:57,501 ----------------------------------------------------------------------------------------------------
656
+ 2022-05-02 03:19:57,502 EPOCH 37 done: loss 0.0076 - lr 0.200000
657
+ 2022-05-02 03:20:36,804 Evaluating as a multi-label problem: False
658
+ 2022-05-02 03:20:36,854 DEV : loss 0.018867511302232742 - f1-score (micro avg) 0.9629
659
+ 2022-05-02 03:20:37,220 BAD EPOCHS (no improvement): 2
660
+ 2022-05-02 03:20:37,222 ----------------------------------------------------------------------------------------------------
661
+ 2022-05-02 03:21:14,005 epoch 38 - iter 5/50 - loss 0.00502706 - samples/sec: 1.36 - lr: 0.200000
662
+ 2022-05-02 03:21:45,072 epoch 38 - iter 10/50 - loss 0.00603790 - samples/sec: 1.61 - lr: 0.200000
663
+ 2022-05-02 03:22:23,347 epoch 38 - iter 15/50 - loss 0.00607479 - samples/sec: 1.31 - lr: 0.200000
664
+ 2022-05-02 03:22:54,297 epoch 38 - iter 20/50 - loss 0.00607842 - samples/sec: 1.62 - lr: 0.200000
665
+ 2022-05-02 03:23:33,868 epoch 38 - iter 25/50 - loss 0.00653946 - samples/sec: 1.26 - lr: 0.200000
666
+ 2022-05-02 03:24:08,970 epoch 38 - iter 30/50 - loss 0.00666707 - samples/sec: 1.42 - lr: 0.200000
667
+ 2022-05-02 03:24:31,165 epoch 38 - iter 35/50 - loss 0.00657104 - samples/sec: 2.25 - lr: 0.200000
668
+ 2022-05-02 03:25:06,361 epoch 38 - iter 40/50 - loss 0.00663129 - samples/sec: 1.42 - lr: 0.200000
669
+ 2022-05-02 03:25:44,941 epoch 38 - iter 45/50 - loss 0.00653636 - samples/sec: 1.30 - lr: 0.200000
670
+ 2022-05-02 03:26:13,438 epoch 38 - iter 50/50 - loss 0.00651986 - samples/sec: 1.75 - lr: 0.200000
671
+ 2022-05-02 03:26:13,439 ----------------------------------------------------------------------------------------------------
672
+ 2022-05-02 03:26:13,439 EPOCH 38 done: loss 0.0065 - lr 0.200000
673
+ 2022-05-02 03:26:53,621 Evaluating as a multi-label problem: False
674
+ 2022-05-02 03:26:53,666 DEV : loss 0.018436787649989128 - f1-score (micro avg) 0.9632
675
+ 2022-05-02 03:26:54,055 BAD EPOCHS (no improvement): 0
676
+ 2022-05-02 03:26:54,056 saving best model
677
+ 2022-05-02 03:27:03,732 ----------------------------------------------------------------------------------------------------
678
+ 2022-05-02 03:27:35,897 epoch 39 - iter 5/50 - loss 0.00704727 - samples/sec: 1.55 - lr: 0.200000
679
+ 2022-05-02 03:28:11,391 epoch 39 - iter 10/50 - loss 0.00789169 - samples/sec: 1.41 - lr: 0.200000
680
+ 2022-05-02 03:28:38,682 epoch 39 - iter 15/50 - loss 0.00737736 - samples/sec: 1.83 - lr: 0.200000
681
+ 2022-05-02 03:29:23,031 epoch 39 - iter 20/50 - loss 0.00751732 - samples/sec: 1.13 - lr: 0.200000
682
+ 2022-05-02 03:29:52,736 epoch 39 - iter 25/50 - loss 0.00812244 - samples/sec: 1.68 - lr: 0.200000
683
+ 2022-05-02 03:30:23,314 epoch 39 - iter 30/50 - loss 0.00787767 - samples/sec: 1.64 - lr: 0.200000
684
+ 2022-05-02 03:30:53,193 epoch 39 - iter 35/50 - loss 0.00775394 - samples/sec: 1.67 - lr: 0.200000
685
+ 2022-05-02 03:31:27,445 epoch 39 - iter 40/50 - loss 0.00734473 - samples/sec: 1.46 - lr: 0.200000
686
+ 2022-05-02 03:31:56,948 epoch 39 - iter 45/50 - loss 0.00731734 - samples/sec: 1.69 - lr: 0.200000
687
+ 2022-05-02 03:32:37,328 epoch 39 - iter 50/50 - loss 0.00763368 - samples/sec: 1.24 - lr: 0.200000
688
+ 2022-05-02 03:32:37,329 ----------------------------------------------------------------------------------------------------
689
+ 2022-05-02 03:32:37,329 EPOCH 39 done: loss 0.0076 - lr 0.200000
690
+ 2022-05-02 03:33:16,692 Evaluating as a multi-label problem: False
691
+ 2022-05-02 03:33:16,737 DEV : loss 0.01816430687904358 - f1-score (micro avg) 0.9645
692
+ 2022-05-02 03:33:17,106 BAD EPOCHS (no improvement): 0
693
+ 2022-05-02 03:33:17,107 saving best model
694
+ 2022-05-02 03:33:25,502 ----------------------------------------------------------------------------------------------------
695
+ 2022-05-02 03:34:03,393 epoch 40 - iter 5/50 - loss 0.00493482 - samples/sec: 1.32 - lr: 0.200000
696
+ 2022-05-02 03:34:34,081 epoch 40 - iter 10/50 - loss 0.00511723 - samples/sec: 1.63 - lr: 0.200000
697
+ 2022-05-02 03:35:09,070 epoch 40 - iter 15/50 - loss 0.00534785 - samples/sec: 1.43 - lr: 0.200000
698
+ 2022-05-02 03:35:37,343 epoch 40 - iter 20/50 - loss 0.00606398 - samples/sec: 1.77 - lr: 0.200000
699
+ 2022-05-02 03:36:10,001 epoch 40 - iter 25/50 - loss 0.00644121 - samples/sec: 1.53 - lr: 0.200000
700
+ 2022-05-02 03:36:41,834 epoch 40 - iter 30/50 - loss 0.00676844 - samples/sec: 1.57 - lr: 0.200000
701
+ 2022-05-02 03:37:27,568 epoch 40 - iter 35/50 - loss 0.00697915 - samples/sec: 1.09 - lr: 0.200000
702
+ 2022-05-02 03:38:00,985 epoch 40 - iter 40/50 - loss 0.00690226 - samples/sec: 1.50 - lr: 0.200000
703
+ 2022-05-02 03:38:28,211 epoch 40 - iter 45/50 - loss 0.00681445 - samples/sec: 1.84 - lr: 0.200000
704
+ 2022-05-02 03:38:58,591 epoch 40 - iter 50/50 - loss 0.00696226 - samples/sec: 1.65 - lr: 0.200000
705
+ 2022-05-02 03:38:58,592 ----------------------------------------------------------------------------------------------------
706
+ 2022-05-02 03:38:58,592 EPOCH 40 done: loss 0.0070 - lr 0.200000
707
+ 2022-05-02 03:39:38,059 Evaluating as a multi-label problem: False
708
+ 2022-05-02 03:39:38,103 DEV : loss 0.01855480670928955 - f1-score (micro avg) 0.962
709
+ 2022-05-02 03:39:38,470 BAD EPOCHS (no improvement): 1
710
+ 2022-05-02 03:39:38,471 ----------------------------------------------------------------------------------------------------
711
+ 2022-05-02 03:40:15,930 epoch 41 - iter 5/50 - loss 0.00739891 - samples/sec: 1.33 - lr: 0.200000
712
+ 2022-05-02 03:40:44,171 epoch 41 - iter 10/50 - loss 0.00607033 - samples/sec: 1.77 - lr: 0.200000
713
+ 2022-05-02 03:41:13,145 epoch 41 - iter 15/50 - loss 0.00602773 - samples/sec: 1.73 - lr: 0.200000
714
+ 2022-05-02 03:41:43,923 epoch 41 - iter 20/50 - loss 0.00613717 - samples/sec: 1.62 - lr: 0.200000
715
+ 2022-05-02 03:42:20,324 epoch 41 - iter 25/50 - loss 0.00585712 - samples/sec: 1.37 - lr: 0.200000
716
+ 2022-05-02 03:42:54,389 epoch 41 - iter 30/50 - loss 0.00639456 - samples/sec: 1.47 - lr: 0.200000
717
+ 2022-05-02 03:43:27,458 epoch 41 - iter 35/50 - loss 0.00614994 - samples/sec: 1.51 - lr: 0.200000
718
+ 2022-05-02 03:44:05,801 epoch 41 - iter 40/50 - loss 0.00638997 - samples/sec: 1.30 - lr: 0.200000
719
+ 2022-05-02 03:44:50,784 epoch 41 - iter 45/50 - loss 0.00678687 - samples/sec: 1.11 - lr: 0.200000
720
+ 2022-05-02 03:45:14,289 epoch 41 - iter 50/50 - loss 0.00694265 - samples/sec: 2.13 - lr: 0.200000
721
+ 2022-05-02 03:45:14,290 ----------------------------------------------------------------------------------------------------
722
+ 2022-05-02 03:45:14,291 EPOCH 41 done: loss 0.0069 - lr 0.200000
723
+ 2022-05-02 03:45:52,990 Evaluating as a multi-label problem: False
724
+ 2022-05-02 03:45:53,034 DEV : loss 0.01870078593492508 - f1-score (micro avg) 0.9626
725
+ 2022-05-02 03:45:53,405 BAD EPOCHS (no improvement): 2
726
+ 2022-05-02 03:45:53,406 ----------------------------------------------------------------------------------------------------
727
+ 2022-05-02 03:46:25,691 epoch 42 - iter 5/50 - loss 0.00699241 - samples/sec: 1.55 - lr: 0.200000
728
+ 2022-05-02 03:47:08,400 epoch 42 - iter 10/50 - loss 0.00596010 - samples/sec: 1.17 - lr: 0.200000
729
+ 2022-05-02 03:47:30,866 epoch 42 - iter 15/50 - loss 0.00588924 - samples/sec: 2.23 - lr: 0.200000
730
+ 2022-05-02 03:48:13,951 epoch 42 - iter 20/50 - loss 0.00624356 - samples/sec: 1.16 - lr: 0.200000
731
+ 2022-05-02 03:48:44,149 epoch 42 - iter 25/50 - loss 0.00631574 - samples/sec: 1.66 - lr: 0.200000
732
+ 2022-05-02 03:49:20,505 epoch 42 - iter 30/50 - loss 0.00643996 - samples/sec: 1.38 - lr: 0.200000
733
+ 2022-05-02 03:49:45,133 epoch 42 - iter 35/50 - loss 0.00667616 - samples/sec: 2.03 - lr: 0.200000
734
+ 2022-05-02 03:50:18,165 epoch 42 - iter 40/50 - loss 0.00700492 - samples/sec: 1.51 - lr: 0.200000
735
+ 2022-05-02 03:50:53,156 epoch 42 - iter 45/50 - loss 0.00678408 - samples/sec: 1.43 - lr: 0.200000
736
+ 2022-05-02 03:51:25,544 epoch 42 - iter 50/50 - loss 0.00678955 - samples/sec: 1.54 - lr: 0.200000
737
+ 2022-05-02 03:51:25,545 ----------------------------------------------------------------------------------------------------
738
+ 2022-05-02 03:51:25,545 EPOCH 42 done: loss 0.0068 - lr 0.200000
739
+ 2022-05-02 03:52:05,756 Evaluating as a multi-label problem: False
740
+ 2022-05-02 03:52:05,800 DEV : loss 0.01834353432059288 - f1-score (micro avg) 0.9616
741
+ 2022-05-02 03:52:06,164 BAD EPOCHS (no improvement): 3
742
+ 2022-05-02 03:52:06,165 ----------------------------------------------------------------------------------------------------
743
+ 2022-05-02 03:52:49,229 epoch 43 - iter 5/50 - loss 0.00382102 - samples/sec: 1.16 - lr: 0.200000
744
+ 2022-05-02 03:53:14,391 epoch 43 - iter 10/50 - loss 0.00441287 - samples/sec: 1.99 - lr: 0.200000
745
+ 2022-05-02 03:53:50,878 epoch 43 - iter 15/50 - loss 0.00610719 - samples/sec: 1.37 - lr: 0.200000
746
+ 2022-05-02 03:54:15,096 epoch 43 - iter 20/50 - loss 0.00708661 - samples/sec: 2.06 - lr: 0.200000
747
+ 2022-05-02 03:54:53,324 epoch 43 - iter 25/50 - loss 0.00687901 - samples/sec: 1.31 - lr: 0.200000
748
+ 2022-05-02 03:55:30,974 epoch 43 - iter 30/50 - loss 0.00650433 - samples/sec: 1.33 - lr: 0.200000
749
+ 2022-05-02 03:56:01,765 epoch 43 - iter 35/50 - loss 0.00649756 - samples/sec: 1.62 - lr: 0.200000
750
+ 2022-05-02 03:56:40,798 epoch 43 - iter 40/50 - loss 0.00632866 - samples/sec: 1.28 - lr: 0.200000
751
+ 2022-05-02 03:57:09,767 epoch 43 - iter 45/50 - loss 0.00641276 - samples/sec: 1.73 - lr: 0.200000
752
+ 2022-05-02 03:57:43,805 epoch 43 - iter 50/50 - loss 0.00674023 - samples/sec: 1.47 - lr: 0.200000
753
+ 2022-05-02 03:57:43,806 ----------------------------------------------------------------------------------------------------
754
+ 2022-05-02 03:57:43,806 EPOCH 43 done: loss 0.0067 - lr 0.200000
755
+ 2022-05-02 03:58:22,878 Evaluating as a multi-label problem: False
756
+ 2022-05-02 03:58:22,920 DEV : loss 0.01952836476266384 - f1-score (micro avg) 0.9592
757
+ 2022-05-02 03:58:23,284 BAD EPOCHS (no improvement): 4
758
+ 2022-05-02 03:58:23,285 ----------------------------------------------------------------------------------------------------
759
+ 2022-05-02 03:58:55,110 epoch 44 - iter 5/50 - loss 0.00617694 - samples/sec: 1.57 - lr: 0.200000
760
+ 2022-05-02 03:59:23,093 epoch 44 - iter 10/50 - loss 0.00782368 - samples/sec: 1.79 - lr: 0.200000
761
+ 2022-05-02 04:00:05,690 epoch 44 - iter 15/50 - loss 0.00699202 - samples/sec: 1.17 - lr: 0.200000
762
+ 2022-05-02 04:00:38,236 epoch 44 - iter 20/50 - loss 0.00723170 - samples/sec: 1.54 - lr: 0.200000
763
+ 2022-05-02 04:01:10,804 epoch 44 - iter 25/50 - loss 0.00684588 - samples/sec: 1.54 - lr: 0.200000
764
+ 2022-05-02 04:01:48,432 epoch 44 - iter 30/50 - loss 0.00641966 - samples/sec: 1.33 - lr: 0.200000
765
+ 2022-05-02 04:02:17,203 epoch 44 - iter 35/50 - loss 0.00669356 - samples/sec: 1.74 - lr: 0.200000
766
+ 2022-05-02 04:02:54,650 epoch 44 - iter 40/50 - loss 0.00668287 - samples/sec: 1.34 - lr: 0.200000
767
+ 2022-05-02 04:03:22,198 epoch 44 - iter 45/50 - loss 0.00660592 - samples/sec: 1.82 - lr: 0.200000
768
+ 2022-05-02 04:03:58,934 epoch 44 - iter 50/50 - loss 0.00681308 - samples/sec: 1.36 - lr: 0.200000
769
+ 2022-05-02 04:03:58,935 ----------------------------------------------------------------------------------------------------
770
+ 2022-05-02 04:03:58,935 EPOCH 44 done: loss 0.0068 - lr 0.200000
771
+ 2022-05-02 04:04:37,750 Evaluating as a multi-label problem: False
772
+ 2022-05-02 04:04:37,795 DEV : loss 0.018793215975165367 - f1-score (micro avg) 0.9625
773
+ 2022-05-02 04:04:38,161 BAD EPOCHS (no improvement): 5
774
+ 2022-05-02 04:04:38,162 ----------------------------------------------------------------------------------------------------
775
+ 2022-05-02 04:05:14,305 epoch 45 - iter 5/50 - loss 0.00664220 - samples/sec: 1.38 - lr: 0.200000
776
+ 2022-05-02 04:06:06,827 epoch 45 - iter 10/50 - loss 0.00594277 - samples/sec: 0.95 - lr: 0.200000
777
+ 2022-05-02 04:06:38,541 epoch 45 - iter 15/50 - loss 0.00605866 - samples/sec: 1.58 - lr: 0.200000
778
+ 2022-05-02 04:07:11,610 epoch 45 - iter 20/50 - loss 0.00606972 - samples/sec: 1.51 - lr: 0.200000
779
+ 2022-05-02 04:07:39,389 epoch 45 - iter 25/50 - loss 0.00596314 - samples/sec: 1.80 - lr: 0.200000
780
+ 2022-05-02 04:08:06,185 epoch 45 - iter 30/50 - loss 0.00619607 - samples/sec: 1.87 - lr: 0.200000
781
+ 2022-05-02 04:08:33,048 epoch 45 - iter 35/50 - loss 0.00650871 - samples/sec: 1.86 - lr: 0.200000
782
+ 2022-05-02 04:09:01,263 epoch 45 - iter 40/50 - loss 0.00649112 - samples/sec: 1.77 - lr: 0.200000
783
+ 2022-05-02 04:09:32,657 epoch 45 - iter 45/50 - loss 0.00625125 - samples/sec: 1.59 - lr: 0.200000
784
+ 2022-05-02 04:10:13,334 epoch 45 - iter 50/50 - loss 0.00621363 - samples/sec: 1.23 - lr: 0.200000
785
+ 2022-05-02 04:10:13,334 ----------------------------------------------------------------------------------------------------
786
+ 2022-05-02 04:10:13,335 EPOCH 45 done: loss 0.0062 - lr 0.200000
787
+ 2022-05-02 04:10:54,629 Evaluating as a multi-label problem: False
788
+ 2022-05-02 04:10:54,675 DEV : loss 0.01875368133187294 - f1-score (micro avg) 0.9659
789
+ 2022-05-02 04:10:55,039 BAD EPOCHS (no improvement): 0
790
+ 2022-05-02 04:10:55,040 saving best model
791
+ 2022-05-02 04:11:04,631 ----------------------------------------------------------------------------------------------------
792
+ 2022-05-02 04:11:42,244 epoch 46 - iter 5/50 - loss 0.00622060 - samples/sec: 1.33 - lr: 0.200000
793
+ 2022-05-02 04:12:23,485 epoch 46 - iter 10/50 - loss 0.00544820 - samples/sec: 1.21 - lr: 0.200000
794
+ 2022-05-02 04:12:47,831 epoch 46 - iter 15/50 - loss 0.00567605 - samples/sec: 2.05 - lr: 0.200000
795
+ 2022-05-02 04:13:29,683 epoch 46 - iter 20/50 - loss 0.00636548 - samples/sec: 1.19 - lr: 0.200000
796
+ 2022-05-02 04:14:08,975 epoch 46 - iter 25/50 - loss 0.00624251 - samples/sec: 1.27 - lr: 0.200000
797
+ 2022-05-02 04:14:38,253 epoch 46 - iter 30/50 - loss 0.00601930 - samples/sec: 1.71 - lr: 0.200000
798
+ 2022-05-02 04:15:08,597 epoch 46 - iter 35/50 - loss 0.00623052 - samples/sec: 1.65 - lr: 0.200000
799
+ 2022-05-02 04:15:30,549 epoch 46 - iter 40/50 - loss 0.00605721 - samples/sec: 2.28 - lr: 0.200000
800
+ 2022-05-02 04:16:04,471 epoch 46 - iter 45/50 - loss 0.00587524 - samples/sec: 1.47 - lr: 0.200000
801
+ 2022-05-02 04:16:35,080 epoch 46 - iter 50/50 - loss 0.00596984 - samples/sec: 1.63 - lr: 0.200000
802
+ 2022-05-02 04:16:35,080 ----------------------------------------------------------------------------------------------------
803
+ 2022-05-02 04:16:35,081 EPOCH 46 done: loss 0.0060 - lr 0.200000
804
+ 2022-05-02 04:17:15,891 Evaluating as a multi-label problem: False
805
+ 2022-05-02 04:17:15,948 DEV : loss 0.019861916080117226 - f1-score (micro avg) 0.9631
806
+ 2022-05-02 04:17:16,374 BAD EPOCHS (no improvement): 1
807
+ 2022-05-02 04:17:16,375 ----------------------------------------------------------------------------------------------------
808
+ 2022-05-02 04:17:53,868 epoch 47 - iter 5/50 - loss 0.00329793 - samples/sec: 1.33 - lr: 0.200000
809
+ 2022-05-02 04:18:25,464 epoch 47 - iter 10/50 - loss 0.00456497 - samples/sec: 1.58 - lr: 0.200000
810
+ 2022-05-02 04:18:57,331 epoch 47 - iter 15/50 - loss 0.00512056 - samples/sec: 1.57 - lr: 0.200000
811
+ 2022-05-02 04:19:21,148 epoch 47 - iter 20/50 - loss 0.00517656 - samples/sec: 2.10 - lr: 0.200000
812
+ 2022-05-02 04:19:53,614 epoch 47 - iter 25/50 - loss 0.00511799 - samples/sec: 1.54 - lr: 0.200000
813
+ 2022-05-02 04:20:25,387 epoch 47 - iter 30/50 - loss 0.00550104 - samples/sec: 1.57 - lr: 0.200000
814
+ 2022-05-02 04:20:57,416 epoch 47 - iter 35/50 - loss 0.00566895 - samples/sec: 1.56 - lr: 0.200000
815
+ 2022-05-02 04:21:31,894 epoch 47 - iter 40/50 - loss 0.00574943 - samples/sec: 1.45 - lr: 0.200000
816
+ 2022-05-02 04:22:05,905 epoch 47 - iter 45/50 - loss 0.00593496 - samples/sec: 1.47 - lr: 0.200000
817
+ 2022-05-02 04:22:39,481 epoch 47 - iter 50/50 - loss 0.00584942 - samples/sec: 1.49 - lr: 0.200000
818
+ 2022-05-02 04:22:39,482 ----------------------------------------------------------------------------------------------------
819
+ 2022-05-02 04:22:39,482 EPOCH 47 done: loss 0.0058 - lr 0.200000
820
+ 2022-05-02 04:23:18,905 Evaluating as a multi-label problem: False
821
+ 2022-05-02 04:23:18,950 DEV : loss 0.018801940605044365 - f1-score (micro avg) 0.96
822
+ 2022-05-02 04:23:19,314 BAD EPOCHS (no improvement): 2
823
+ 2022-05-02 04:23:19,315 ----------------------------------------------------------------------------------------------------
824
+ 2022-05-02 04:23:50,290 epoch 48 - iter 5/50 - loss 0.00435976 - samples/sec: 1.61 - lr: 0.200000
825
+ 2022-05-02 04:24:25,890 epoch 48 - iter 10/50 - loss 0.00498775 - samples/sec: 1.40 - lr: 0.200000
826
+ 2022-05-02 04:24:51,199 epoch 48 - iter 15/50 - loss 0.00497191 - samples/sec: 1.98 - lr: 0.200000
827
+ 2022-05-02 04:25:22,764 epoch 48 - iter 20/50 - loss 0.00501331 - samples/sec: 1.58 - lr: 0.200000
828
+ 2022-05-02 04:25:59,864 epoch 48 - iter 25/50 - loss 0.00489165 - samples/sec: 1.35 - lr: 0.200000
829
+ 2022-05-02 04:26:32,572 epoch 48 - iter 30/50 - loss 0.00520801 - samples/sec: 1.53 - lr: 0.200000
830
+ 2022-05-02 04:27:05,100 epoch 48 - iter 35/50 - loss 0.00572989 - samples/sec: 1.54 - lr: 0.200000
831
+ 2022-05-02 04:27:45,148 epoch 48 - iter 40/50 - loss 0.00558734 - samples/sec: 1.25 - lr: 0.200000
832
+ 2022-05-02 04:28:25,956 epoch 48 - iter 45/50 - loss 0.00531911 - samples/sec: 1.23 - lr: 0.200000
833
+ 2022-05-02 04:29:01,263 epoch 48 - iter 50/50 - loss 0.00539028 - samples/sec: 1.42 - lr: 0.200000
834
+ 2022-05-02 04:29:01,264 ----------------------------------------------------------------------------------------------------
835
+ 2022-05-02 04:29:01,264 EPOCH 48 done: loss 0.0054 - lr 0.200000
836
+ 2022-05-02 04:29:40,429 Evaluating as a multi-label problem: False
837
+ 2022-05-02 04:29:40,475 DEV : loss 0.019677503034472466 - f1-score (micro avg) 0.9629
838
+ 2022-05-02 04:29:40,841 BAD EPOCHS (no improvement): 3
839
+ 2022-05-02 04:29:40,842 ----------------------------------------------------------------------------------------------------
840
+ 2022-05-02 04:30:21,222 epoch 49 - iter 5/50 - loss 0.00625104 - samples/sec: 1.24 - lr: 0.200000
841
+ 2022-05-02 04:30:54,452 epoch 49 - iter 10/50 - loss 0.00485302 - samples/sec: 1.50 - lr: 0.200000
842
+ 2022-05-02 04:31:22,014 epoch 49 - iter 15/50 - loss 0.00488327 - samples/sec: 1.81 - lr: 0.200000
843
+ 2022-05-02 04:31:51,442 epoch 49 - iter 20/50 - loss 0.00581335 - samples/sec: 1.70 - lr: 0.200000
844
+ 2022-05-02 04:32:21,382 epoch 49 - iter 25/50 - loss 0.00557588 - samples/sec: 1.67 - lr: 0.200000
845
+ 2022-05-02 04:32:55,714 epoch 49 - iter 30/50 - loss 0.00564434 - samples/sec: 1.46 - lr: 0.200000
846
+ 2022-05-02 04:33:36,460 epoch 49 - iter 35/50 - loss 0.00576337 - samples/sec: 1.23 - lr: 0.200000
847
+ 2022-05-02 04:34:16,985 epoch 49 - iter 40/50 - loss 0.00592190 - samples/sec: 1.23 - lr: 0.200000
848
+ 2022-05-02 04:34:56,867 epoch 49 - iter 45/50 - loss 0.00603678 - samples/sec: 1.25 - lr: 0.200000
849
+ 2022-05-02 04:35:26,786 epoch 49 - iter 50/50 - loss 0.00588768 - samples/sec: 1.67 - lr: 0.200000
850
+ 2022-05-02 04:35:26,787 ----------------------------------------------------------------------------------------------------
851
+ 2022-05-02 04:35:26,787 EPOCH 49 done: loss 0.0059 - lr 0.200000
852
+ 2022-05-02 04:36:05,770 Evaluating as a multi-label problem: False
853
+ 2022-05-02 04:36:05,814 DEV : loss 0.019637076184153557 - f1-score (micro avg) 0.9654
854
+ 2022-05-02 04:36:06,179 BAD EPOCHS (no improvement): 4
855
+ 2022-05-02 04:36:06,180 ----------------------------------------------------------------------------------------------------
856
+ 2022-05-02 04:36:50,406 epoch 50 - iter 5/50 - loss 0.00780800 - samples/sec: 1.13 - lr: 0.200000
857
+ 2022-05-02 04:37:18,463 epoch 50 - iter 10/50 - loss 0.00764671 - samples/sec: 1.78 - lr: 0.200000
858
+ 2022-05-02 04:37:46,752 epoch 50 - iter 15/50 - loss 0.00627114 - samples/sec: 1.77 - lr: 0.200000
859
+ 2022-05-02 04:38:17,544 epoch 50 - iter 20/50 - loss 0.00548444 - samples/sec: 1.62 - lr: 0.200000
860
+ 2022-05-02 04:38:52,761 epoch 50 - iter 25/50 - loss 0.00588776 - samples/sec: 1.42 - lr: 0.200000
861
+ 2022-05-02 04:39:27,812 epoch 50 - iter 30/50 - loss 0.00611878 - samples/sec: 1.43 - lr: 0.200000
862
+ 2022-05-02 04:39:58,107 epoch 50 - iter 35/50 - loss 0.00582060 - samples/sec: 1.65 - lr: 0.200000
863
+ 2022-05-02 04:40:27,614 epoch 50 - iter 40/50 - loss 0.00572197 - samples/sec: 1.69 - lr: 0.200000
864
+ 2022-05-02 04:41:09,757 epoch 50 - iter 45/50 - loss 0.00549231 - samples/sec: 1.19 - lr: 0.200000
865
+ 2022-05-02 04:41:43,995 epoch 50 - iter 50/50 - loss 0.00543316 - samples/sec: 1.46 - lr: 0.200000
866
+ 2022-05-02 04:41:43,996 ----------------------------------------------------------------------------------------------------
867
+ 2022-05-02 04:41:43,996 EPOCH 50 done: loss 0.0054 - lr 0.200000
868
+ 2022-05-02 04:42:23,054 Evaluating as a multi-label problem: False
869
+ 2022-05-02 04:42:23,100 DEV : loss 0.019652361050248146 - f1-score (micro avg) 0.9649
870
+ 2022-05-02 04:42:23,469 BAD EPOCHS (no improvement): 5
871
+ 2022-05-02 04:42:31,812 ----------------------------------------------------------------------------------------------------
872
+ 2022-05-02 04:42:31,813 loading file models\MEDDOCAN_0.2_256_1_50\best-model.pt
873
+ 2022-05-02 04:42:36,016 SequenceTagger predicts: Dictionary with 91 tags: O, S-TERRITORIO, B-TERRITORIO, E-TERRITORIO, I-TERRITORIO, S-FECHAS, B-FECHAS, E-FECHAS, I-FECHAS, S-EDAD_SUJETO_ASISTENCIA, B-EDAD_SUJETO_ASISTENCIA, E-EDAD_SUJETO_ASISTENCIA, I-EDAD_SUJETO_ASISTENCIA, S-NOMBRE_SUJETO_ASISTENCIA, B-NOMBRE_SUJETO_ASISTENCIA, E-NOMBRE_SUJETO_ASISTENCIA, I-NOMBRE_SUJETO_ASISTENCIA, S-NOMBRE_PERSONAL_SANITARIO, B-NOMBRE_PERSONAL_SANITARIO, E-NOMBRE_PERSONAL_SANITARIO, I-NOMBRE_PERSONAL_SANITARIO, S-SEXO_SUJETO_ASISTENCIA, B-SEXO_SUJETO_ASISTENCIA, E-SEXO_SUJETO_ASISTENCIA, I-SEXO_SUJETO_ASISTENCIA, S-CALLE, B-CALLE, E-CALLE, I-CALLE, S-PAIS, B-PAIS, E-PAIS, I-PAIS, S-ID_SUJETO_ASISTENCIA, B-ID_SUJETO_ASISTENCIA, E-ID_SUJETO_ASISTENCIA, I-ID_SUJETO_ASISTENCIA, S-CORREO_ELECTRONICO, B-CORREO_ELECTRONICO, E-CORREO_ELECTRONICO, I-CORREO_ELECTRONICO, S-ID_TITULACION_PERSONAL_SANITARIO, B-ID_TITULACION_PERSONAL_SANITARIO, E-ID_TITULACION_PERSONAL_SANITARIO, I-ID_TITULACION_PERSONAL_SANITARIO, S-ID_ASEGURAMIENTO, B-ID_ASEGURAMIENTO, E-ID_ASEGURAMIENTO, I-ID_ASEGURAMIENTO, S-HOSPITAL
874
+ 2022-05-02 04:43:57,625 Evaluating as a multi-label problem: False
875
+ 2022-05-02 04:43:57,669 0.9709 0.9611 0.966 0.9397
876
+ 2022-05-02 04:43:57,669
877
+ Results:
878
+ - F-score (micro) 0.966
879
+ - F-score (macro) 0.8574
880
+ - Accuracy 0.9397
881
+
882
+ By class:
883
+ precision recall f1-score support
884
+
885
+ TERRITORIO 0.9727 0.9676 0.9701 956
886
+ FECHAS 0.9803 0.9787 0.9795 611
887
+ EDAD_SUJETO_ASISTENCIA 0.9902 0.9788 0.9845 518
888
+ NOMBRE_SUJETO_ASISTENCIA 0.9980 0.9980 0.9980 502
889
+ NOMBRE_PERSONAL_SANITARIO 0.9900 0.9900 0.9900 501
890
+ SEXO_SUJETO_ASISTENCIA 0.9869 0.9805 0.9837 461
891
+ CALLE 0.9611 0.9564 0.9587 413
892
+ PAIS 0.9587 0.9587 0.9587 363
893
+ ID_SUJETO_ASISTENCIA 0.9823 0.9788 0.9805 283
894
+ CORREO_ELECTRONICO 0.9880 0.9880 0.9880 249
895
+ ID_TITULACION_PERSONAL_SANITARIO 0.9957 1.0000 0.9979 234
896
+ ID_ASEGURAMIENTO 0.9800 0.9899 0.9849 198
897
+ HOSPITAL 0.8889 0.8615 0.8750 130
898
+ FAMILIARES_SUJETO_ASISTENCIA 0.7500 0.6667 0.7059 81
899
+ INSTITUCION 0.4773 0.3134 0.3784 67
900
+ ID_CONTACTO_ASISTENCIAL 0.9500 0.9744 0.9620 39
901
+ NUMERO_TELEFONO 0.8929 0.9615 0.9259 26
902
+ PROFESION 0.7500 0.6667 0.7059 9
903
+ NUMERO_FAX 0.8333 0.7143 0.7692 7
904
+ CENTRO_SALUD 1.0000 0.8333 0.9091 6
905
+ OTROS_SUJETO_ASISTENCIA 0.0000 0.0000 0.0000 7
906
+
907
+ micro avg 0.9709 0.9611 0.9660 5661
908
+ macro avg 0.8727 0.8456 0.8574 5661
909
+ weighted avg 0.9675 0.9611 0.9640 5661
910
+
911
+ 2022-05-02 04:43:57,674 ----------------------------------------------------------------------------------------------------