Hugging Face's logo

stefan-it
/
flair-co-funer-gbert_base-bs8-e10-lr3e-05-3

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
hetzner
hetzner-gex44
hetzner-gpu
Model card Files Metrics Community
3
stefan-it commited on
Commit
1dfd1f1
•
1 Parent(s): 4f90250

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +245 -0
training.log ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-03-26 10:08:27,529 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 10:08:27,530 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=17, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2024-03-26 10:08:27,530 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 10:08:27,530 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 10:08:27,530 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 10:08:27,530 Train: 758 sentences
54
+ 2024-03-26 10:08:27,530 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 10:08:27,530 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 10:08:27,530 Training Params:
57
+ 2024-03-26 10:08:27,530 - learning_rate: "3e-05"
58
+ 2024-03-26 10:08:27,530 - mini_batch_size: "8"
59
+ 2024-03-26 10:08:27,530 - max_epochs: "10"
60
+ 2024-03-26 10:08:27,530 - shuffle: "True"
61
+ 2024-03-26 10:08:27,530 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 10:08:27,530 Plugins:
63
+ 2024-03-26 10:08:27,530 - TensorboardLogger
64
+ 2024-03-26 10:08:27,530 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 10:08:27,530 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 10:08:27,530 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 10:08:27,530 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 10:08:27,530 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 10:08:27,530 Computation:
70
+ 2024-03-26 10:08:27,530 - compute on device: cuda:0
71
+ 2024-03-26 10:08:27,530 - embedding storage: none
72
+ 2024-03-26 10:08:27,530 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 10:08:27,530 Model training base path: "flair-co-funer-gbert_base-bs8-e10-lr3e-05-3"
74
+ 2024-03-26 10:08:27,530 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 10:08:27,530 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 10:08:27,530 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 10:08:28,894 epoch 1 - iter 9/95 - loss 3.33554699 - time (sec): 1.36 - samples/sec: 2339.39 - lr: 0.000003 - momentum: 0.000000
78
+ 2024-03-26 10:08:30,720 epoch 1 - iter 18/95 - loss 3.19797484 - time (sec): 3.19 - samples/sec: 1979.89 - lr: 0.000005 - momentum: 0.000000
79
+ 2024-03-26 10:08:32,649 epoch 1 - iter 27/95 - loss 2.97461067 - time (sec): 5.12 - samples/sec: 1930.07 - lr: 0.000008 - momentum: 0.000000
80
+ 2024-03-26 10:08:34,027 epoch 1 - iter 36/95 - loss 2.75332136 - time (sec): 6.50 - samples/sec: 1947.46 - lr: 0.000011 - momentum: 0.000000
81
+ 2024-03-26 10:08:35,938 epoch 1 - iter 45/95 - loss 2.59851272 - time (sec): 8.41 - samples/sec: 1929.36 - lr: 0.000014 - momentum: 0.000000
82
+ 2024-03-26 10:08:37,303 epoch 1 - iter 54/95 - loss 2.45841522 - time (sec): 9.77 - samples/sec: 1953.13 - lr: 0.000017 - momentum: 0.000000
83
+ 2024-03-26 10:08:38,555 epoch 1 - iter 63/95 - loss 2.33834595 - time (sec): 11.02 - samples/sec: 1980.60 - lr: 0.000020 - momentum: 0.000000
84
+ 2024-03-26 10:08:40,505 epoch 1 - iter 72/95 - loss 2.19376938 - time (sec): 12.97 - samples/sec: 1966.88 - lr: 0.000022 - momentum: 0.000000
85
+ 2024-03-26 10:08:42,493 epoch 1 - iter 81/95 - loss 2.04587440 - time (sec): 14.96 - samples/sec: 1951.25 - lr: 0.000025 - momentum: 0.000000
86
+ 2024-03-26 10:08:44,026 epoch 1 - iter 90/95 - loss 1.92876562 - time (sec): 16.50 - samples/sec: 1969.18 - lr: 0.000028 - momentum: 0.000000
87
+ 2024-03-26 10:08:45,081 ----------------------------------------------------------------------------------------------------
88
+ 2024-03-26 10:08:45,081 EPOCH 1 done: loss 1.8562 - lr: 0.000028
89
+ 2024-03-26 10:08:46,033 DEV : loss 0.5581119656562805 - f1-score (micro avg) 0.6418
90
+ 2024-03-26 10:08:46,034 saving best model
91
+ 2024-03-26 10:08:46,319 ----------------------------------------------------------------------------------------------------
92
+ 2024-03-26 10:08:47,674 epoch 2 - iter 9/95 - loss 0.66546774 - time (sec): 1.35 - samples/sec: 2022.54 - lr: 0.000030 - momentum: 0.000000
93
+ 2024-03-26 10:08:49,508 epoch 2 - iter 18/95 - loss 0.54284628 - time (sec): 3.19 - samples/sec: 1915.63 - lr: 0.000029 - momentum: 0.000000
94
+ 2024-03-26 10:08:50,678 epoch 2 - iter 27/95 - loss 0.51960536 - time (sec): 4.36 - samples/sec: 1968.72 - lr: 0.000029 - momentum: 0.000000
95
+ 2024-03-26 10:08:52,927 epoch 2 - iter 36/95 - loss 0.49655748 - time (sec): 6.61 - samples/sec: 1918.83 - lr: 0.000029 - momentum: 0.000000
96
+ 2024-03-26 10:08:54,866 epoch 2 - iter 45/95 - loss 0.47810842 - time (sec): 8.55 - samples/sec: 1924.12 - lr: 0.000028 - momentum: 0.000000
97
+ 2024-03-26 10:08:57,021 epoch 2 - iter 54/95 - loss 0.46197107 - time (sec): 10.70 - samples/sec: 1895.84 - lr: 0.000028 - momentum: 0.000000
98
+ 2024-03-26 10:08:59,025 epoch 2 - iter 63/95 - loss 0.44425485 - time (sec): 12.71 - samples/sec: 1850.15 - lr: 0.000028 - momentum: 0.000000
99
+ 2024-03-26 10:09:00,540 epoch 2 - iter 72/95 - loss 0.44340772 - time (sec): 14.22 - samples/sec: 1857.68 - lr: 0.000028 - momentum: 0.000000
100
+ 2024-03-26 10:09:01,979 epoch 2 - iter 81/95 - loss 0.44607382 - time (sec): 15.66 - samples/sec: 1881.11 - lr: 0.000027 - momentum: 0.000000
101
+ 2024-03-26 10:09:04,191 epoch 2 - iter 90/95 - loss 0.43041023 - time (sec): 17.87 - samples/sec: 1856.06 - lr: 0.000027 - momentum: 0.000000
102
+ 2024-03-26 10:09:04,830 ----------------------------------------------------------------------------------------------------
103
+ 2024-03-26 10:09:04,830 EPOCH 2 done: loss 0.4258 - lr: 0.000027
104
+ 2024-03-26 10:09:05,720 DEV : loss 0.2841838002204895 - f1-score (micro avg) 0.8242
105
+ 2024-03-26 10:09:05,721 saving best model
106
+ 2024-03-26 10:09:06,177 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 10:09:07,810 epoch 3 - iter 9/95 - loss 0.24170767 - time (sec): 1.63 - samples/sec: 1830.36 - lr: 0.000026 - momentum: 0.000000
108
+ 2024-03-26 10:09:09,596 epoch 3 - iter 18/95 - loss 0.23005411 - time (sec): 3.42 - samples/sec: 1852.45 - lr: 0.000026 - momentum: 0.000000
109
+ 2024-03-26 10:09:10,786 epoch 3 - iter 27/95 - loss 0.24030877 - time (sec): 4.61 - samples/sec: 2027.95 - lr: 0.000026 - momentum: 0.000000
110
+ 2024-03-26 10:09:12,339 epoch 3 - iter 36/95 - loss 0.22730704 - time (sec): 6.16 - samples/sec: 2016.47 - lr: 0.000025 - momentum: 0.000000
111
+ 2024-03-26 10:09:13,752 epoch 3 - iter 45/95 - loss 0.23076599 - time (sec): 7.57 - samples/sec: 2023.93 - lr: 0.000025 - momentum: 0.000000
112
+ 2024-03-26 10:09:15,747 epoch 3 - iter 54/95 - loss 0.22498599 - time (sec): 9.57 - samples/sec: 1975.21 - lr: 0.000025 - momentum: 0.000000
113
+ 2024-03-26 10:09:17,740 epoch 3 - iter 63/95 - loss 0.22620463 - time (sec): 11.56 - samples/sec: 1925.53 - lr: 0.000025 - momentum: 0.000000
114
+ 2024-03-26 10:09:19,577 epoch 3 - iter 72/95 - loss 0.22489015 - time (sec): 13.40 - samples/sec: 1909.05 - lr: 0.000024 - momentum: 0.000000
115
+ 2024-03-26 10:09:21,583 epoch 3 - iter 81/95 - loss 0.21879733 - time (sec): 15.41 - samples/sec: 1881.98 - lr: 0.000024 - momentum: 0.000000
116
+ 2024-03-26 10:09:23,545 epoch 3 - iter 90/95 - loss 0.22689307 - time (sec): 17.37 - samples/sec: 1882.69 - lr: 0.000024 - momentum: 0.000000
117
+ 2024-03-26 10:09:24,635 ----------------------------------------------------------------------------------------------------
118
+ 2024-03-26 10:09:24,635 EPOCH 3 done: loss 0.2202 - lr: 0.000024
119
+ 2024-03-26 10:09:25,529 DEV : loss 0.22958670556545258 - f1-score (micro avg) 0.8489
120
+ 2024-03-26 10:09:25,530 saving best model
121
+ 2024-03-26 10:09:26,003 ----------------------------------------------------------------------------------------------------
122
+ 2024-03-26 10:09:27,292 epoch 4 - iter 9/95 - loss 0.16111365 - time (sec): 1.29 - samples/sec: 2155.79 - lr: 0.000023 - momentum: 0.000000
123
+ 2024-03-26 10:09:29,139 epoch 4 - iter 18/95 - loss 0.14919663 - time (sec): 3.13 - samples/sec: 1960.47 - lr: 0.000023 - momentum: 0.000000
124
+ 2024-03-26 10:09:31,065 epoch 4 - iter 27/95 - loss 0.14644479 - time (sec): 5.06 - samples/sec: 1908.24 - lr: 0.000022 - momentum: 0.000000
125
+ 2024-03-26 10:09:32,548 epoch 4 - iter 36/95 - loss 0.14385233 - time (sec): 6.54 - samples/sec: 1916.88 - lr: 0.000022 - momentum: 0.000000
126
+ 2024-03-26 10:09:34,984 epoch 4 - iter 45/95 - loss 0.14276960 - time (sec): 8.98 - samples/sec: 1840.15 - lr: 0.000022 - momentum: 0.000000
127
+ 2024-03-26 10:09:36,848 epoch 4 - iter 54/95 - loss 0.13773929 - time (sec): 10.84 - samples/sec: 1819.90 - lr: 0.000022 - momentum: 0.000000
128
+ 2024-03-26 10:09:38,790 epoch 4 - iter 63/95 - loss 0.13313938 - time (sec): 12.79 - samples/sec: 1798.79 - lr: 0.000021 - momentum: 0.000000
129
+ 2024-03-26 10:09:40,670 epoch 4 - iter 72/95 - loss 0.14004047 - time (sec): 14.67 - samples/sec: 1814.15 - lr: 0.000021 - momentum: 0.000000
130
+ 2024-03-26 10:09:42,693 epoch 4 - iter 81/95 - loss 0.14802288 - time (sec): 16.69 - samples/sec: 1811.70 - lr: 0.000021 - momentum: 0.000000
131
+ 2024-03-26 10:09:43,671 epoch 4 - iter 90/95 - loss 0.14738465 - time (sec): 17.67 - samples/sec: 1851.18 - lr: 0.000020 - momentum: 0.000000
132
+ 2024-03-26 10:09:44,699 ----------------------------------------------------------------------------------------------------
133
+ 2024-03-26 10:09:44,699 EPOCH 4 done: loss 0.1476 - lr: 0.000020
134
+ 2024-03-26 10:09:45,593 DEV : loss 0.18175187706947327 - f1-score (micro avg) 0.8926
135
+ 2024-03-26 10:09:45,594 saving best model
136
+ 2024-03-26 10:09:46,046 ----------------------------------------------------------------------------------------------------
137
+ 2024-03-26 10:09:47,930 epoch 5 - iter 9/95 - loss 0.09143063 - time (sec): 1.88 - samples/sec: 1826.09 - lr: 0.000020 - momentum: 0.000000
138
+ 2024-03-26 10:09:49,363 epoch 5 - iter 18/95 - loss 0.09824734 - time (sec): 3.31 - samples/sec: 1888.04 - lr: 0.000019 - momentum: 0.000000
139
+ 2024-03-26 10:09:50,724 epoch 5 - iter 27/95 - loss 0.10332613 - time (sec): 4.68 - samples/sec: 1931.27 - lr: 0.000019 - momentum: 0.000000
140
+ 2024-03-26 10:09:52,603 epoch 5 - iter 36/95 - loss 0.10675406 - time (sec): 6.55 - samples/sec: 1872.34 - lr: 0.000019 - momentum: 0.000000
141
+ 2024-03-26 10:09:54,890 epoch 5 - iter 45/95 - loss 0.10676981 - time (sec): 8.84 - samples/sec: 1841.19 - lr: 0.000019 - momentum: 0.000000
142
+ 2024-03-26 10:09:57,324 epoch 5 - iter 54/95 - loss 0.10270566 - time (sec): 11.28 - samples/sec: 1801.32 - lr: 0.000018 - momentum: 0.000000
143
+ 2024-03-26 10:09:58,986 epoch 5 - iter 63/95 - loss 0.10148077 - time (sec): 12.94 - samples/sec: 1795.70 - lr: 0.000018 - momentum: 0.000000
144
+ 2024-03-26 10:10:00,751 epoch 5 - iter 72/95 - loss 0.10182338 - time (sec): 14.70 - samples/sec: 1798.64 - lr: 0.000018 - momentum: 0.000000
145
+ 2024-03-26 10:10:02,950 epoch 5 - iter 81/95 - loss 0.10627975 - time (sec): 16.90 - samples/sec: 1785.23 - lr: 0.000017 - momentum: 0.000000
146
+ 2024-03-26 10:10:04,337 epoch 5 - iter 90/95 - loss 0.10709497 - time (sec): 18.29 - samples/sec: 1802.11 - lr: 0.000017 - momentum: 0.000000
147
+ 2024-03-26 10:10:05,102 ----------------------------------------------------------------------------------------------------
148
+ 2024-03-26 10:10:05,102 EPOCH 5 done: loss 0.1049 - lr: 0.000017
149
+ 2024-03-26 10:10:06,013 DEV : loss 0.15699249505996704 - f1-score (micro avg) 0.9156
150
+ 2024-03-26 10:10:06,014 saving best model
151
+ 2024-03-26 10:10:06,467 ----------------------------------------------------------------------------------------------------
152
+ 2024-03-26 10:10:08,404 epoch 6 - iter 9/95 - loss 0.07898146 - time (sec): 1.94 - samples/sec: 1802.35 - lr: 0.000016 - momentum: 0.000000
153
+ 2024-03-26 10:10:09,954 epoch 6 - iter 18/95 - loss 0.08189262 - time (sec): 3.49 - samples/sec: 1824.53 - lr: 0.000016 - momentum: 0.000000
154
+ 2024-03-26 10:10:11,860 epoch 6 - iter 27/95 - loss 0.07955601 - time (sec): 5.39 - samples/sec: 1834.02 - lr: 0.000016 - momentum: 0.000000
155
+ 2024-03-26 10:10:13,430 epoch 6 - iter 36/95 - loss 0.08207944 - time (sec): 6.96 - samples/sec: 1831.73 - lr: 0.000016 - momentum: 0.000000
156
+ 2024-03-26 10:10:14,880 epoch 6 - iter 45/95 - loss 0.07878711 - time (sec): 8.41 - samples/sec: 1869.51 - lr: 0.000015 - momentum: 0.000000
157
+ 2024-03-26 10:10:16,329 epoch 6 - iter 54/95 - loss 0.07682753 - time (sec): 9.86 - samples/sec: 1867.79 - lr: 0.000015 - momentum: 0.000000
158
+ 2024-03-26 10:10:17,606 epoch 6 - iter 63/95 - loss 0.07419095 - time (sec): 11.14 - samples/sec: 1930.45 - lr: 0.000015 - momentum: 0.000000
159
+ 2024-03-26 10:10:19,852 epoch 6 - iter 72/95 - loss 0.08078885 - time (sec): 13.38 - samples/sec: 1897.36 - lr: 0.000014 - momentum: 0.000000
160
+ 2024-03-26 10:10:21,433 epoch 6 - iter 81/95 - loss 0.07732747 - time (sec): 14.96 - samples/sec: 1914.85 - lr: 0.000014 - momentum: 0.000000
161
+ 2024-03-26 10:10:23,139 epoch 6 - iter 90/95 - loss 0.07983208 - time (sec): 16.67 - samples/sec: 1933.33 - lr: 0.000014 - momentum: 0.000000
162
+ 2024-03-26 10:10:24,405 ----------------------------------------------------------------------------------------------------
163
+ 2024-03-26 10:10:24,405 EPOCH 6 done: loss 0.0808 - lr: 0.000014
164
+ 2024-03-26 10:10:25,320 DEV : loss 0.16210442781448364 - f1-score (micro avg) 0.9114
165
+ 2024-03-26 10:10:25,321 ----------------------------------------------------------------------------------------------------
166
+ 2024-03-26 10:10:27,208 epoch 7 - iter 9/95 - loss 0.07576515 - time (sec): 1.89 - samples/sec: 1684.03 - lr: 0.000013 - momentum: 0.000000
167
+ 2024-03-26 10:10:29,242 epoch 7 - iter 18/95 - loss 0.06224530 - time (sec): 3.92 - samples/sec: 1672.44 - lr: 0.000013 - momentum: 0.000000
168
+ 2024-03-26 10:10:30,776 epoch 7 - iter 27/95 - loss 0.05614093 - time (sec): 5.45 - samples/sec: 1793.70 - lr: 0.000013 - momentum: 0.000000
169
+ 2024-03-26 10:10:32,724 epoch 7 - iter 36/95 - loss 0.05508867 - time (sec): 7.40 - samples/sec: 1780.19 - lr: 0.000012 - momentum: 0.000000
170
+ 2024-03-26 10:10:35,103 epoch 7 - iter 45/95 - loss 0.06099413 - time (sec): 9.78 - samples/sec: 1772.80 - lr: 0.000012 - momentum: 0.000000
171
+ 2024-03-26 10:10:36,627 epoch 7 - iter 54/95 - loss 0.06007902 - time (sec): 11.30 - samples/sec: 1779.41 - lr: 0.000012 - momentum: 0.000000
172
+ 2024-03-26 10:10:38,814 epoch 7 - iter 63/95 - loss 0.05988849 - time (sec): 13.49 - samples/sec: 1784.97 - lr: 0.000011 - momentum: 0.000000
173
+ 2024-03-26 10:10:40,594 epoch 7 - iter 72/95 - loss 0.06350792 - time (sec): 15.27 - samples/sec: 1792.44 - lr: 0.000011 - momentum: 0.000000
174
+ 2024-03-26 10:10:42,014 epoch 7 - iter 81/95 - loss 0.05993214 - time (sec): 16.69 - samples/sec: 1804.64 - lr: 0.000011 - momentum: 0.000000
175
+ 2024-03-26 10:10:43,984 epoch 7 - iter 90/95 - loss 0.06299791 - time (sec): 18.66 - samples/sec: 1784.97 - lr: 0.000010 - momentum: 0.000000
176
+ 2024-03-26 10:10:44,467 ----------------------------------------------------------------------------------------------------
177
+ 2024-03-26 10:10:44,467 EPOCH 7 done: loss 0.0641 - lr: 0.000010
178
+ 2024-03-26 10:10:45,364 DEV : loss 0.15182051062583923 - f1-score (micro avg) 0.9275
179
+ 2024-03-26 10:10:45,365 saving best model
180
+ 2024-03-26 10:10:45,816 ----------------------------------------------------------------------------------------------------
181
+ 2024-03-26 10:10:47,691 epoch 8 - iter 9/95 - loss 0.04093905 - time (sec): 1.87 - samples/sec: 1710.97 - lr: 0.000010 - momentum: 0.000000
182
+ 2024-03-26 10:10:50,179 epoch 8 - iter 18/95 - loss 0.03651141 - time (sec): 4.36 - samples/sec: 1698.06 - lr: 0.000010 - momentum: 0.000000
183
+ 2024-03-26 10:10:51,943 epoch 8 - iter 27/95 - loss 0.03614220 - time (sec): 6.13 - samples/sec: 1736.98 - lr: 0.000009 - momentum: 0.000000
184
+ 2024-03-26 10:10:53,486 epoch 8 - iter 36/95 - loss 0.03690008 - time (sec): 7.67 - samples/sec: 1728.69 - lr: 0.000009 - momentum: 0.000000
185
+ 2024-03-26 10:10:54,998 epoch 8 - iter 45/95 - loss 0.03446730 - time (sec): 9.18 - samples/sec: 1759.04 - lr: 0.000009 - momentum: 0.000000
186
+ 2024-03-26 10:10:56,657 epoch 8 - iter 54/95 - loss 0.03525247 - time (sec): 10.84 - samples/sec: 1779.42 - lr: 0.000008 - momentum: 0.000000
187
+ 2024-03-26 10:10:58,853 epoch 8 - iter 63/95 - loss 0.04458381 - time (sec): 13.04 - samples/sec: 1775.29 - lr: 0.000008 - momentum: 0.000000
188
+ 2024-03-26 10:11:01,101 epoch 8 - iter 72/95 - loss 0.04856792 - time (sec): 15.28 - samples/sec: 1755.92 - lr: 0.000008 - momentum: 0.000000
189
+ 2024-03-26 10:11:02,760 epoch 8 - iter 81/95 - loss 0.05222485 - time (sec): 16.94 - samples/sec: 1758.08 - lr: 0.000007 - momentum: 0.000000
190
+ 2024-03-26 10:11:04,053 epoch 8 - iter 90/95 - loss 0.05236197 - time (sec): 18.24 - samples/sec: 1800.43 - lr: 0.000007 - momentum: 0.000000
191
+ 2024-03-26 10:11:04,949 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 10:11:04,949 EPOCH 8 done: loss 0.0509 - lr: 0.000007
193
+ 2024-03-26 10:11:05,851 DEV : loss 0.14655029773712158 - f1-score (micro avg) 0.9337
194
+ 2024-03-26 10:11:05,852 saving best model
195
+ 2024-03-26 10:11:06,294 ----------------------------------------------------------------------------------------------------
196
+ 2024-03-26 10:11:08,265 epoch 9 - iter 9/95 - loss 0.02126199 - time (sec): 1.97 - samples/sec: 1789.49 - lr: 0.000007 - momentum: 0.000000
197
+ 2024-03-26 10:11:10,061 epoch 9 - iter 18/95 - loss 0.03879203 - time (sec): 3.77 - samples/sec: 1777.15 - lr: 0.000006 - momentum: 0.000000
198
+ 2024-03-26 10:11:11,930 epoch 9 - iter 27/95 - loss 0.04085316 - time (sec): 5.64 - samples/sec: 1812.78 - lr: 0.000006 - momentum: 0.000000
199
+ 2024-03-26 10:11:13,786 epoch 9 - iter 36/95 - loss 0.03895674 - time (sec): 7.49 - samples/sec: 1812.92 - lr: 0.000006 - momentum: 0.000000
200
+ 2024-03-26 10:11:16,045 epoch 9 - iter 45/95 - loss 0.03523787 - time (sec): 9.75 - samples/sec: 1738.45 - lr: 0.000005 - momentum: 0.000000
201
+ 2024-03-26 10:11:17,969 epoch 9 - iter 54/95 - loss 0.04020057 - time (sec): 11.67 - samples/sec: 1729.24 - lr: 0.000005 - momentum: 0.000000
202
+ 2024-03-26 10:11:19,855 epoch 9 - iter 63/95 - loss 0.03879557 - time (sec): 13.56 - samples/sec: 1741.15 - lr: 0.000005 - momentum: 0.000000
203
+ 2024-03-26 10:11:21,740 epoch 9 - iter 72/95 - loss 0.04013875 - time (sec): 15.45 - samples/sec: 1744.73 - lr: 0.000004 - momentum: 0.000000
204
+ 2024-03-26 10:11:22,989 epoch 9 - iter 81/95 - loss 0.04101646 - time (sec): 16.69 - samples/sec: 1768.48 - lr: 0.000004 - momentum: 0.000000
205
+ 2024-03-26 10:11:24,390 epoch 9 - iter 90/95 - loss 0.04377843 - time (sec): 18.10 - samples/sec: 1791.00 - lr: 0.000004 - momentum: 0.000000
206
+ 2024-03-26 10:11:25,341 ----------------------------------------------------------------------------------------------------
207
+ 2024-03-26 10:11:25,341 EPOCH 9 done: loss 0.0436 - lr: 0.000004
208
+ 2024-03-26 10:11:26,244 DEV : loss 0.15030568838119507 - f1-score (micro avg) 0.9421
209
+ 2024-03-26 10:11:26,245 saving best model
210
+ 2024-03-26 10:11:26,697 ----------------------------------------------------------------------------------------------------
211
+ 2024-03-26 10:11:28,828 epoch 10 - iter 9/95 - loss 0.02320407 - time (sec): 2.13 - samples/sec: 1789.47 - lr: 0.000003 - momentum: 0.000000
212
+ 2024-03-26 10:11:30,093 epoch 10 - iter 18/95 - loss 0.02217229 - time (sec): 3.39 - samples/sec: 1907.07 - lr: 0.000003 - momentum: 0.000000
213
+ 2024-03-26 10:11:31,401 epoch 10 - iter 27/95 - loss 0.04519325 - time (sec): 4.70 - samples/sec: 2016.50 - lr: 0.000003 - momentum: 0.000000
214
+ 2024-03-26 10:11:32,755 epoch 10 - iter 36/95 - loss 0.04245546 - time (sec): 6.06 - samples/sec: 2036.53 - lr: 0.000002 - momentum: 0.000000
215
+ 2024-03-26 10:11:34,631 epoch 10 - iter 45/95 - loss 0.03751937 - time (sec): 7.93 - samples/sec: 2007.47 - lr: 0.000002 - momentum: 0.000000
216
+ 2024-03-26 10:11:36,210 epoch 10 - iter 54/95 - loss 0.03686825 - time (sec): 9.51 - samples/sec: 1993.00 - lr: 0.000002 - momentum: 0.000000
217
+ 2024-03-26 10:11:38,733 epoch 10 - iter 63/95 - loss 0.03767893 - time (sec): 12.03 - samples/sec: 1910.37 - lr: 0.000001 - momentum: 0.000000
218
+ 2024-03-26 10:11:40,022 epoch 10 - iter 72/95 - loss 0.03674440 - time (sec): 13.32 - samples/sec: 1913.90 - lr: 0.000001 - momentum: 0.000000
219
+ 2024-03-26 10:11:42,365 epoch 10 - iter 81/95 - loss 0.03457245 - time (sec): 15.67 - samples/sec: 1859.29 - lr: 0.000001 - momentum: 0.000000
220
+ 2024-03-26 10:11:44,581 epoch 10 - iter 90/95 - loss 0.03657945 - time (sec): 17.88 - samples/sec: 1839.05 - lr: 0.000000 - momentum: 0.000000
221
+ 2024-03-26 10:11:45,635 ----------------------------------------------------------------------------------------------------
222
+ 2024-03-26 10:11:45,635 EPOCH 10 done: loss 0.0367 - lr: 0.000000
223
+ 2024-03-26 10:11:46,537 DEV : loss 0.14958544075489044 - f1-score (micro avg) 0.9397
224
+ 2024-03-26 10:11:46,820 ----------------------------------------------------------------------------------------------------
225
+ 2024-03-26 10:11:46,820 Loading model from best epoch ...
226
+ 2024-03-26 10:11:47,739 SequenceTagger predicts: Dictionary with 17 tags: O, S-Unternehmen, B-Unternehmen, E-Unternehmen, I-Unternehmen, S-Auslagerung, B-Auslagerung, E-Auslagerung, I-Auslagerung, S-Ort, B-Ort, E-Ort, I-Ort, S-Software, B-Software, E-Software, I-Software
227
+ 2024-03-26 10:11:48,486
228
+ Results:
229
+ - F-score (micro) 0.9056
230
+ - F-score (macro) 0.6892
231
+ - Accuracy 0.8333
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ Unternehmen 0.9216 0.8835 0.9021 266
237
+ Auslagerung 0.8376 0.9116 0.8731 249
238
+ Ort 0.9708 0.9925 0.9815 134
239
+ Software 0.0000 0.0000 0.0000 0
240
+
241
+ micro avg 0.8947 0.9168 0.9056 649
242
+ macro avg 0.6825 0.6969 0.6892 649
243
+ weighted avg 0.8995 0.9168 0.9074 649
244
+
245
+ 2024-03-26 10:11:48,486 ----------------------------------------------------------------------------------------------------