Hugging Face's logo

stefan-it
/
autotrain-flair-mobie-gbert_base-bs16-e10-lr5e-05-2

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
2
stefan-it commited on
Commit
2e9eea2
•
1 Parent(s): b926ae2

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +261 -0
training.log ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-19 00:44:31,863 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-19 00:44:31,864 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(31103, 768)
7
+ (position_embeddings): Embedding(512, 768)
8
+ (token_type_embeddings): Embedding(2, 768)
9
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=768, out_features=768, bias=True)
18
+ (key): Linear(in_features=768, out_features=768, bias=True)
19
+ (value): Linear(in_features=768, out_features=768, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=768, out_features=768, bias=True)
24
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
34
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
35
+ (dropout): Dropout(p=0.1, inplace=False)
36
+ )
37
+ )
38
+ )
39
+ )
40
+ (pooler): BertPooler(
41
+ (dense): Linear(in_features=768, out_features=768, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=768, out_features=81, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-19 00:44:31,864 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-19 00:44:31,864 Corpus: 6900 train + 1576 dev + 1833 test sentences
52
+ 2023-10-19 00:44:31,864 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-19 00:44:31,864 Train: 6900 sentences
54
+ 2023-10-19 00:44:31,864 (train_with_dev=False, train_with_test=False)
55
+ 2023-10-19 00:44:31,864 ----------------------------------------------------------------------------------------------------
56
+ 2023-10-19 00:44:31,864 Training Params:
57
+ 2023-10-19 00:44:31,864 - learning_rate: "5e-05"
58
+ 2023-10-19 00:44:31,864 - mini_batch_size: "16"
59
+ 2023-10-19 00:44:31,864 - max_epochs: "10"
60
+ 2023-10-19 00:44:31,864 - shuffle: "True"
61
+ 2023-10-19 00:44:31,864 ----------------------------------------------------------------------------------------------------
62
+ 2023-10-19 00:44:31,864 Plugins:
63
+ 2023-10-19 00:44:31,865 - TensorboardLogger
64
+ 2023-10-19 00:44:31,865 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-19 00:44:31,865 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-19 00:44:31,865 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-19 00:44:31,865 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-19 00:44:31,865 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-19 00:44:31,865 Computation:
70
+ 2023-10-19 00:44:31,865 - compute on device: cuda:0
71
+ 2023-10-19 00:44:31,865 - embedding storage: none
72
+ 2023-10-19 00:44:31,865 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-19 00:44:31,865 Model training base path: "autotrain-flair-mobie-gbert_base-bs16-e10-lr5e-05-2"
74
+ 2023-10-19 00:44:31,865 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-19 00:44:31,865 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-19 00:44:31,865 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2023-10-19 00:44:47,212 epoch 1 - iter 43/432 - loss 4.53411937 - time (sec): 15.35 - samples/sec: 393.73 - lr: 0.000005 - momentum: 0.000000
78
+ 2023-10-19 00:45:01,344 epoch 1 - iter 86/432 - loss 3.33775768 - time (sec): 29.48 - samples/sec: 416.66 - lr: 0.000010 - momentum: 0.000000
79
+ 2023-10-19 00:45:16,011 epoch 1 - iter 129/432 - loss 2.84542967 - time (sec): 44.15 - samples/sec: 413.11 - lr: 0.000015 - momentum: 0.000000
80
+ 2023-10-19 00:45:30,003 epoch 1 - iter 172/432 - loss 2.52975191 - time (sec): 58.14 - samples/sec: 418.24 - lr: 0.000020 - momentum: 0.000000
81
+ 2023-10-19 00:45:45,094 epoch 1 - iter 215/432 - loss 2.29564387 - time (sec): 73.23 - samples/sec: 411.52 - lr: 0.000025 - momentum: 0.000000
82
+ 2023-10-19 00:46:00,541 epoch 1 - iter 258/432 - loss 2.05922596 - time (sec): 88.68 - samples/sec: 413.66 - lr: 0.000030 - momentum: 0.000000
83
+ 2023-10-19 00:46:15,508 epoch 1 - iter 301/432 - loss 1.88915277 - time (sec): 103.64 - samples/sec: 413.75 - lr: 0.000035 - momentum: 0.000000
84
+ 2023-10-19 00:46:30,838 epoch 1 - iter 344/432 - loss 1.74992637 - time (sec): 118.97 - samples/sec: 412.05 - lr: 0.000040 - momentum: 0.000000
85
+ 2023-10-19 00:46:45,525 epoch 1 - iter 387/432 - loss 1.63015802 - time (sec): 133.66 - samples/sec: 411.49 - lr: 0.000045 - momentum: 0.000000
86
+ 2023-10-19 00:47:01,349 epoch 1 - iter 430/432 - loss 1.51696167 - time (sec): 149.48 - samples/sec: 411.83 - lr: 0.000050 - momentum: 0.000000
87
+ 2023-10-19 00:47:01,949 ----------------------------------------------------------------------------------------------------
88
+ 2023-10-19 00:47:01,950 EPOCH 1 done: loss 1.5134 - lr: 0.000050
89
+ 2023-10-19 00:47:15,678 DEV : loss 0.4629705548286438 - f1-score (micro avg) 0.7131
90
+ 2023-10-19 00:47:15,701 saving best model
91
+ 2023-10-19 00:47:16,128 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-19 00:47:30,352 epoch 2 - iter 43/432 - loss 0.50778740 - time (sec): 14.22 - samples/sec: 457.10 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-19 00:47:44,769 epoch 2 - iter 86/432 - loss 0.47541374 - time (sec): 28.64 - samples/sec: 445.06 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-19 00:48:00,063 epoch 2 - iter 129/432 - loss 0.46875804 - time (sec): 43.93 - samples/sec: 425.92 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-19 00:48:15,298 epoch 2 - iter 172/432 - loss 0.45799863 - time (sec): 59.17 - samples/sec: 423.05 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-19 00:48:30,441 epoch 2 - iter 215/432 - loss 0.44907689 - time (sec): 74.31 - samples/sec: 416.91 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-19 00:48:44,633 epoch 2 - iter 258/432 - loss 0.43929109 - time (sec): 88.50 - samples/sec: 419.49 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-19 00:48:58,777 epoch 2 - iter 301/432 - loss 0.43307480 - time (sec): 102.65 - samples/sec: 418.41 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-19 00:49:12,715 epoch 2 - iter 344/432 - loss 0.42908565 - time (sec): 116.58 - samples/sec: 421.01 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-19 00:49:26,745 epoch 2 - iter 387/432 - loss 0.42075222 - time (sec): 130.62 - samples/sec: 423.33 - lr: 0.000045 - momentum: 0.000000
101
+ 2023-10-19 00:49:40,040 epoch 2 - iter 430/432 - loss 0.41576500 - time (sec): 143.91 - samples/sec: 427.96 - lr: 0.000044 - momentum: 0.000000
102
+ 2023-10-19 00:49:40,571 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-19 00:49:40,571 EPOCH 2 done: loss 0.4159 - lr: 0.000044
104
+ 2023-10-19 00:49:52,635 DEV : loss 0.3158990442752838 - f1-score (micro avg) 0.7988
105
+ 2023-10-19 00:49:52,658 saving best model
106
+ 2023-10-19 00:49:53,913 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-19 00:50:07,149 epoch 3 - iter 43/432 - loss 0.28934365 - time (sec): 13.23 - samples/sec: 444.45 - lr: 0.000044 - momentum: 0.000000
108
+ 2023-10-19 00:50:20,635 epoch 3 - iter 86/432 - loss 0.27279891 - time (sec): 26.72 - samples/sec: 440.82 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-19 00:50:34,946 epoch 3 - iter 129/432 - loss 0.25809605 - time (sec): 41.03 - samples/sec: 434.32 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-19 00:50:49,105 epoch 3 - iter 172/432 - loss 0.25877208 - time (sec): 55.19 - samples/sec: 432.01 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-19 00:51:02,303 epoch 3 - iter 215/432 - loss 0.25490899 - time (sec): 68.39 - samples/sec: 439.98 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-19 00:51:15,378 epoch 3 - iter 258/432 - loss 0.25311964 - time (sec): 81.46 - samples/sec: 447.45 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-19 00:51:28,206 epoch 3 - iter 301/432 - loss 0.24979741 - time (sec): 94.29 - samples/sec: 452.91 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-19 00:51:42,585 epoch 3 - iter 344/432 - loss 0.24676564 - time (sec): 108.67 - samples/sec: 451.89 - lr: 0.000040 - momentum: 0.000000
115
+ 2023-10-19 00:51:55,659 epoch 3 - iter 387/432 - loss 0.24375527 - time (sec): 121.74 - samples/sec: 452.41 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-19 00:52:09,164 epoch 3 - iter 430/432 - loss 0.24783731 - time (sec): 135.25 - samples/sec: 456.10 - lr: 0.000039 - momentum: 0.000000
117
+ 2023-10-19 00:52:09,637 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-19 00:52:09,637 EPOCH 3 done: loss 0.2479 - lr: 0.000039
119
+ 2023-10-19 00:52:22,049 DEV : loss 0.31579792499542236 - f1-score (micro avg) 0.808
120
+ 2023-10-19 00:52:22,074 saving best model
121
+ 2023-10-19 00:52:23,320 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-19 00:52:37,087 epoch 4 - iter 43/432 - loss 0.16644201 - time (sec): 13.77 - samples/sec: 457.00 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-19 00:52:50,583 epoch 4 - iter 86/432 - loss 0.18332177 - time (sec): 27.26 - samples/sec: 456.18 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-19 00:53:04,413 epoch 4 - iter 129/432 - loss 0.18640017 - time (sec): 41.09 - samples/sec: 458.34 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-19 00:53:17,780 epoch 4 - iter 172/432 - loss 0.18492662 - time (sec): 54.46 - samples/sec: 454.60 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-19 00:53:31,940 epoch 4 - iter 215/432 - loss 0.18135848 - time (sec): 68.62 - samples/sec: 451.54 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-19 00:53:46,014 epoch 4 - iter 258/432 - loss 0.18461289 - time (sec): 82.69 - samples/sec: 451.15 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-19 00:53:59,805 epoch 4 - iter 301/432 - loss 0.18702010 - time (sec): 96.48 - samples/sec: 451.95 - lr: 0.000035 - momentum: 0.000000
129
+ 2023-10-19 00:54:13,646 epoch 4 - iter 344/432 - loss 0.18583796 - time (sec): 110.32 - samples/sec: 450.40 - lr: 0.000034 - momentum: 0.000000
130
+ 2023-10-19 00:54:26,549 epoch 4 - iter 387/432 - loss 0.18370163 - time (sec): 123.23 - samples/sec: 452.55 - lr: 0.000034 - momentum: 0.000000
131
+ 2023-10-19 00:54:40,668 epoch 4 - iter 430/432 - loss 0.18206557 - time (sec): 137.35 - samples/sec: 449.35 - lr: 0.000033 - momentum: 0.000000
132
+ 2023-10-19 00:54:41,284 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-19 00:54:41,284 EPOCH 4 done: loss 0.1820 - lr: 0.000033
134
+ 2023-10-19 00:54:53,592 DEV : loss 0.30372321605682373 - f1-score (micro avg) 0.828
135
+ 2023-10-19 00:54:53,617 saving best model
136
+ 2023-10-19 00:54:54,870 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-19 00:55:08,008 epoch 5 - iter 43/432 - loss 0.13612790 - time (sec): 13.14 - samples/sec: 465.32 - lr: 0.000033 - momentum: 0.000000
138
+ 2023-10-19 00:55:22,047 epoch 5 - iter 86/432 - loss 0.14054460 - time (sec): 27.18 - samples/sec: 447.47 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-19 00:55:37,157 epoch 5 - iter 129/432 - loss 0.13394142 - time (sec): 42.29 - samples/sec: 432.53 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-19 00:55:51,326 epoch 5 - iter 172/432 - loss 0.13270704 - time (sec): 56.45 - samples/sec: 435.38 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-19 00:56:05,579 epoch 5 - iter 215/432 - loss 0.13290468 - time (sec): 70.71 - samples/sec: 432.49 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-19 00:56:19,533 epoch 5 - iter 258/432 - loss 0.13547413 - time (sec): 84.66 - samples/sec: 438.78 - lr: 0.000030 - momentum: 0.000000
143
+ 2023-10-19 00:56:33,952 epoch 5 - iter 301/432 - loss 0.13486846 - time (sec): 99.08 - samples/sec: 436.52 - lr: 0.000029 - momentum: 0.000000
144
+ 2023-10-19 00:56:48,205 epoch 5 - iter 344/432 - loss 0.13344437 - time (sec): 113.33 - samples/sec: 436.88 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-19 00:57:02,971 epoch 5 - iter 387/432 - loss 0.13475190 - time (sec): 128.10 - samples/sec: 434.34 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-19 00:57:17,198 epoch 5 - iter 430/432 - loss 0.13409932 - time (sec): 142.33 - samples/sec: 432.98 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-19 00:57:17,739 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-19 00:57:17,740 EPOCH 5 done: loss 0.1340 - lr: 0.000028
149
+ 2023-10-19 00:57:30,751 DEV : loss 0.32670849561691284 - f1-score (micro avg) 0.8352
150
+ 2023-10-19 00:57:30,783 saving best model
151
+ 2023-10-19 00:57:32,032 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-19 00:57:47,516 epoch 6 - iter 43/432 - loss 0.08687325 - time (sec): 15.48 - samples/sec: 398.91 - lr: 0.000027 - momentum: 0.000000
153
+ 2023-10-19 00:58:02,149 epoch 6 - iter 86/432 - loss 0.09122781 - time (sec): 30.12 - samples/sec: 403.22 - lr: 0.000027 - momentum: 0.000000
154
+ 2023-10-19 00:58:16,671 epoch 6 - iter 129/432 - loss 0.09486365 - time (sec): 44.64 - samples/sec: 404.97 - lr: 0.000026 - momentum: 0.000000
155
+ 2023-10-19 00:58:30,400 epoch 6 - iter 172/432 - loss 0.09596723 - time (sec): 58.37 - samples/sec: 418.15 - lr: 0.000026 - momentum: 0.000000
156
+ 2023-10-19 00:58:44,957 epoch 6 - iter 215/432 - loss 0.09805027 - time (sec): 72.92 - samples/sec: 419.17 - lr: 0.000025 - momentum: 0.000000
157
+ 2023-10-19 00:58:59,364 epoch 6 - iter 258/432 - loss 0.09925226 - time (sec): 87.33 - samples/sec: 422.65 - lr: 0.000024 - momentum: 0.000000
158
+ 2023-10-19 00:59:15,357 epoch 6 - iter 301/432 - loss 0.09985027 - time (sec): 103.32 - samples/sec: 418.87 - lr: 0.000024 - momentum: 0.000000
159
+ 2023-10-19 00:59:30,282 epoch 6 - iter 344/432 - loss 0.09891744 - time (sec): 118.25 - samples/sec: 417.55 - lr: 0.000023 - momentum: 0.000000
160
+ 2023-10-19 00:59:45,039 epoch 6 - iter 387/432 - loss 0.09861899 - time (sec): 133.01 - samples/sec: 415.82 - lr: 0.000023 - momentum: 0.000000
161
+ 2023-10-19 01:00:00,507 epoch 6 - iter 430/432 - loss 0.09818502 - time (sec): 148.47 - samples/sec: 415.48 - lr: 0.000022 - momentum: 0.000000
162
+ 2023-10-19 01:00:01,244 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-19 01:00:01,245 EPOCH 6 done: loss 0.0982 - lr: 0.000022
164
+ 2023-10-19 01:00:14,505 DEV : loss 0.3421052396297455 - f1-score (micro avg) 0.8432
165
+ 2023-10-19 01:00:14,529 saving best model
166
+ 2023-10-19 01:00:15,772 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-19 01:00:29,443 epoch 7 - iter 43/432 - loss 0.06939444 - time (sec): 13.67 - samples/sec: 466.85 - lr: 0.000022 - momentum: 0.000000
168
+ 2023-10-19 01:00:43,853 epoch 7 - iter 86/432 - loss 0.06747434 - time (sec): 28.08 - samples/sec: 444.91 - lr: 0.000021 - momentum: 0.000000
169
+ 2023-10-19 01:00:59,051 epoch 7 - iter 129/432 - loss 0.06960008 - time (sec): 43.28 - samples/sec: 422.62 - lr: 0.000021 - momentum: 0.000000
170
+ 2023-10-19 01:01:14,327 epoch 7 - iter 172/432 - loss 0.06786994 - time (sec): 58.55 - samples/sec: 419.32 - lr: 0.000020 - momentum: 0.000000
171
+ 2023-10-19 01:01:28,754 epoch 7 - iter 215/432 - loss 0.07131507 - time (sec): 72.98 - samples/sec: 422.99 - lr: 0.000019 - momentum: 0.000000
172
+ 2023-10-19 01:01:43,871 epoch 7 - iter 258/432 - loss 0.07531973 - time (sec): 88.10 - samples/sec: 420.42 - lr: 0.000019 - momentum: 0.000000
173
+ 2023-10-19 01:01:59,085 epoch 7 - iter 301/432 - loss 0.07563695 - time (sec): 103.31 - samples/sec: 417.98 - lr: 0.000018 - momentum: 0.000000
174
+ 2023-10-19 01:02:14,048 epoch 7 - iter 344/432 - loss 0.07673450 - time (sec): 118.28 - samples/sec: 416.50 - lr: 0.000018 - momentum: 0.000000
175
+ 2023-10-19 01:02:29,624 epoch 7 - iter 387/432 - loss 0.07707972 - time (sec): 133.85 - samples/sec: 414.18 - lr: 0.000017 - momentum: 0.000000
176
+ 2023-10-19 01:02:44,948 epoch 7 - iter 430/432 - loss 0.07751613 - time (sec): 149.17 - samples/sec: 413.46 - lr: 0.000017 - momentum: 0.000000
177
+ 2023-10-19 01:02:45,737 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-19 01:02:45,737 EPOCH 7 done: loss 0.0774 - lr: 0.000017
179
+ 2023-10-19 01:02:59,356 DEV : loss 0.352491557598114 - f1-score (micro avg) 0.8393
180
+ 2023-10-19 01:02:59,383 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-19 01:03:13,741 epoch 8 - iter 43/432 - loss 0.05261681 - time (sec): 14.36 - samples/sec: 416.10 - lr: 0.000016 - momentum: 0.000000
182
+ 2023-10-19 01:03:28,728 epoch 8 - iter 86/432 - loss 0.05721217 - time (sec): 29.34 - samples/sec: 428.52 - lr: 0.000016 - momentum: 0.000000
183
+ 2023-10-19 01:03:42,822 epoch 8 - iter 129/432 - loss 0.05369074 - time (sec): 43.44 - samples/sec: 419.25 - lr: 0.000015 - momentum: 0.000000
184
+ 2023-10-19 01:03:56,732 epoch 8 - iter 172/432 - loss 0.05678762 - time (sec): 57.35 - samples/sec: 436.78 - lr: 0.000014 - momentum: 0.000000
185
+ 2023-10-19 01:04:11,247 epoch 8 - iter 215/432 - loss 0.05652943 - time (sec): 71.86 - samples/sec: 437.82 - lr: 0.000014 - momentum: 0.000000
186
+ 2023-10-19 01:04:26,331 epoch 8 - iter 258/432 - loss 0.05696515 - time (sec): 86.95 - samples/sec: 430.93 - lr: 0.000013 - momentum: 0.000000
187
+ 2023-10-19 01:04:41,478 epoch 8 - iter 301/432 - loss 0.05623302 - time (sec): 102.09 - samples/sec: 428.45 - lr: 0.000013 - momentum: 0.000000
188
+ 2023-10-19 01:04:55,979 epoch 8 - iter 344/432 - loss 0.05774074 - time (sec): 116.59 - samples/sec: 429.21 - lr: 0.000012 - momentum: 0.000000
189
+ 2023-10-19 01:05:10,754 epoch 8 - iter 387/432 - loss 0.05776864 - time (sec): 131.37 - samples/sec: 424.98 - lr: 0.000012 - momentum: 0.000000
190
+ 2023-10-19 01:05:26,178 epoch 8 - iter 430/432 - loss 0.05789217 - time (sec): 146.79 - samples/sec: 419.88 - lr: 0.000011 - momentum: 0.000000
191
+ 2023-10-19 01:05:27,034 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-19 01:05:27,034 EPOCH 8 done: loss 0.0581 - lr: 0.000011
193
+ 2023-10-19 01:05:40,257 DEV : loss 0.38706132769584656 - f1-score (micro avg) 0.8476
194
+ 2023-10-19 01:05:40,282 saving best model
195
+ 2023-10-19 01:05:41,538 ----------------------------------------------------------------------------------------------------
196
+ 2023-10-19 01:05:56,043 epoch 9 - iter 43/432 - loss 0.05079748 - time (sec): 14.50 - samples/sec: 412.31 - lr: 0.000011 - momentum: 0.000000
197
+ 2023-10-19 01:06:10,747 epoch 9 - iter 86/432 - loss 0.04252692 - time (sec): 29.21 - samples/sec: 426.59 - lr: 0.000010 - momentum: 0.000000
198
+ 2023-10-19 01:06:26,222 epoch 9 - iter 129/432 - loss 0.03956511 - time (sec): 44.68 - samples/sec: 415.35 - lr: 0.000009 - momentum: 0.000000
199
+ 2023-10-19 01:06:42,255 epoch 9 - iter 172/432 - loss 0.03891272 - time (sec): 60.72 - samples/sec: 400.27 - lr: 0.000009 - momentum: 0.000000
200
+ 2023-10-19 01:06:56,986 epoch 9 - iter 215/432 - loss 0.03816925 - time (sec): 75.45 - samples/sec: 409.16 - lr: 0.000008 - momentum: 0.000000
201
+ 2023-10-19 01:07:12,082 epoch 9 - iter 258/432 - loss 0.03904535 - time (sec): 90.54 - samples/sec: 408.11 - lr: 0.000008 - momentum: 0.000000
202
+ 2023-10-19 01:07:27,198 epoch 9 - iter 301/432 - loss 0.03968716 - time (sec): 105.66 - samples/sec: 410.39 - lr: 0.000007 - momentum: 0.000000
203
+ 2023-10-19 01:07:42,126 epoch 9 - iter 344/432 - loss 0.04100224 - time (sec): 120.59 - samples/sec: 409.28 - lr: 0.000007 - momentum: 0.000000
204
+ 2023-10-19 01:07:57,146 epoch 9 - iter 387/432 - loss 0.04208186 - time (sec): 135.61 - samples/sec: 408.46 - lr: 0.000006 - momentum: 0.000000
205
+ 2023-10-19 01:08:12,686 epoch 9 - iter 430/432 - loss 0.04243790 - time (sec): 151.15 - samples/sec: 408.30 - lr: 0.000006 - momentum: 0.000000
206
+ 2023-10-19 01:08:13,050 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-19 01:08:13,050 EPOCH 9 done: loss 0.0424 - lr: 0.000006
208
+ 2023-10-19 01:08:26,197 DEV : loss 0.410501629114151 - f1-score (micro avg) 0.8488
209
+ 2023-10-19 01:08:26,221 saving best model
210
+ 2023-10-19 01:08:27,465 ----------------------------------------------------------------------------------------------------
211
+ 2023-10-19 01:08:41,343 epoch 10 - iter 43/432 - loss 0.04022390 - time (sec): 13.88 - samples/sec: 427.28 - lr: 0.000005 - momentum: 0.000000
212
+ 2023-10-19 01:08:56,759 epoch 10 - iter 86/432 - loss 0.03411555 - time (sec): 29.29 - samples/sec: 404.61 - lr: 0.000004 - momentum: 0.000000
213
+ 2023-10-19 01:09:11,614 epoch 10 - iter 129/432 - loss 0.03451278 - time (sec): 44.15 - samples/sec: 409.44 - lr: 0.000004 - momentum: 0.000000
214
+ 2023-10-19 01:09:26,919 epoch 10 - iter 172/432 - loss 0.03635957 - time (sec): 59.45 - samples/sec: 414.23 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-19 01:09:42,287 epoch 10 - iter 215/432 - loss 0.03736899 - time (sec): 74.82 - samples/sec: 417.49 - lr: 0.000003 - momentum: 0.000000
216
+ 2023-10-19 01:09:57,205 epoch 10 - iter 258/432 - loss 0.03656773 - time (sec): 89.74 - samples/sec: 417.19 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-19 01:10:11,814 epoch 10 - iter 301/432 - loss 0.03588521 - time (sec): 104.35 - samples/sec: 418.34 - lr: 0.000002 - momentum: 0.000000
218
+ 2023-10-19 01:10:26,748 epoch 10 - iter 344/432 - loss 0.03577744 - time (sec): 119.28 - samples/sec: 417.64 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-19 01:10:40,324 epoch 10 - iter 387/432 - loss 0.03395260 - time (sec): 132.86 - samples/sec: 418.94 - lr: 0.000001 - momentum: 0.000000
220
+ 2023-10-19 01:10:56,124 epoch 10 - iter 430/432 - loss 0.03336868 - time (sec): 148.66 - samples/sec: 414.75 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-19 01:10:56,799 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-19 01:10:56,799 EPOCH 10 done: loss 0.0333 - lr: 0.000000
223
+ 2023-10-19 01:11:10,126 DEV : loss 0.4209924340248108 - f1-score (micro avg) 0.8495
224
+ 2023-10-19 01:11:10,151 saving best model
225
+ 2023-10-19 01:11:11,931 ----------------------------------------------------------------------------------------------------
226
+ 2023-10-19 01:11:11,932 Loading model from best epoch ...
227
+ 2023-10-19 01:11:14,091 SequenceTagger predicts: Dictionary with 81 tags: O, S-location-route, B-location-route, E-location-route, I-location-route, S-location-stop, B-location-stop, E-location-stop, I-location-stop, S-trigger, B-trigger, E-trigger, I-trigger, S-organization-company, B-organization-company, E-organization-company, I-organization-company, S-location-city, B-location-city, E-location-city, I-location-city, S-location, B-location, E-location, I-location, S-event-cause, B-event-cause, E-event-cause, I-event-cause, S-location-street, B-location-street, E-location-street, I-location-street, S-time, B-time, E-time, I-time, S-date, B-date, E-date, I-date, S-number, B-number, E-number, I-number, S-duration, B-duration, E-duration, I-duration, S-organization
228
+ 2023-10-19 01:11:32,197
229
+ Results:
230
+ - F-score (micro) 0.7756
231
+ - F-score (macro) 0.5886
232
+ - Accuracy 0.678
233
+
234
+ By class:
235
+ precision recall f1-score support
236
+
237
+ location-stop 0.8753 0.8444 0.8596 765
238
+ trigger 0.7333 0.5810 0.6484 833
239
+ location 0.7902 0.8496 0.8188 665
240
+ location-city 0.8322 0.8852 0.8579 566
241
+ date 0.8912 0.8528 0.8716 394
242
+ location-street 0.9449 0.8886 0.9159 386
243
+ time 0.7889 0.8906 0.8367 256
244
+ location-route 0.9065 0.7852 0.8415 284
245
+ organization-company 0.8038 0.6667 0.7289 252
246
+ distance 0.9766 1.0000 0.9882 167
247
+ number 0.6742 0.8054 0.7339 149
248
+ duration 0.3397 0.3252 0.3323 163
249
+ event-cause 0.0000 0.0000 0.0000 0
250
+ disaster-type 0.9189 0.4928 0.6415 69
251
+ organization 0.5600 0.5000 0.5283 28
252
+ person 0.4286 0.9000 0.5806 10
253
+ set 0.0000 0.0000 0.0000 0
254
+ org-position 0.0000 0.0000 0.0000 1
255
+ money 0.0000 0.0000 0.0000 0
256
+
257
+ micro avg 0.7713 0.7801 0.7756 4988
258
+ macro avg 0.6034 0.5930 0.5886 4988
259
+ weighted avg 0.8134 0.7801 0.7929 4988
260
+
261
+ 2023-10-19 01:11:32,197 ----------------------------------------------------------------------------------------------------