Hugging Face's logo

stefan-it
/
flair-co-funer-german_bert_base-bs8-e10-lr3e-05-4

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
hetzner
hetzner-gex44
hetzner-gpu
Model card Files Metrics Community
2
stefan-it commited on
Commit
0a057b2
•
1 Parent(s): 3002000

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 11:55:14,243 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 11:55:14,244 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(30001, 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 11:55:14,244 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 11:55:14,244 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 11:55:14,244 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 11:55:14,244 Train: 758 sentences
54
+ 2024-03-26 11:55:14,244 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 11:55:14,244 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 11:55:14,244 Training Params:
57
+ 2024-03-26 11:55:14,244 - learning_rate: "3e-05"
58
+ 2024-03-26 11:55:14,244 - mini_batch_size: "8"
59
+ 2024-03-26 11:55:14,244 - max_epochs: "10"
60
+ 2024-03-26 11:55:14,244 - shuffle: "True"
61
+ 2024-03-26 11:55:14,244 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 11:55:14,244 Plugins:
63
+ 2024-03-26 11:55:14,244 - TensorboardLogger
64
+ 2024-03-26 11:55:14,244 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 11:55:14,244 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 11:55:14,244 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 11:55:14,244 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 11:55:14,244 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 11:55:14,244 Computation:
70
+ 2024-03-26 11:55:14,244 - compute on device: cuda:0
71
+ 2024-03-26 11:55:14,244 - embedding storage: none
72
+ 2024-03-26 11:55:14,244 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 11:55:14,244 Model training base path: "flair-co-funer-german_bert_base-bs8-e10-lr3e-05-4"
74
+ 2024-03-26 11:55:14,244 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 11:55:14,244 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 11:55:14,244 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 11:55:15,614 epoch 1 - iter 9/95 - loss 3.13058506 - time (sec): 1.37 - samples/sec: 2118.05 - lr: 0.000003 - momentum: 0.000000
78
+ 2024-03-26 11:55:17,057 epoch 1 - iter 18/95 - loss 2.99271397 - time (sec): 2.81 - samples/sec: 1960.78 - lr: 0.000005 - momentum: 0.000000
79
+ 2024-03-26 11:55:18,741 epoch 1 - iter 27/95 - loss 2.79183140 - time (sec): 4.50 - samples/sec: 1907.45 - lr: 0.000008 - momentum: 0.000000
80
+ 2024-03-26 11:55:20,758 epoch 1 - iter 36/95 - loss 2.57558044 - time (sec): 6.51 - samples/sec: 1832.93 - lr: 0.000011 - momentum: 0.000000
81
+ 2024-03-26 11:55:22,679 epoch 1 - iter 45/95 - loss 2.38059933 - time (sec): 8.43 - samples/sec: 1848.95 - lr: 0.000014 - momentum: 0.000000
82
+ 2024-03-26 11:55:24,946 epoch 1 - iter 54/95 - loss 2.23386946 - time (sec): 10.70 - samples/sec: 1789.14 - lr: 0.000017 - momentum: 0.000000
83
+ 2024-03-26 11:55:26,992 epoch 1 - iter 63/95 - loss 2.09375127 - time (sec): 12.75 - samples/sec: 1773.07 - lr: 0.000020 - momentum: 0.000000
84
+ 2024-03-26 11:55:28,001 epoch 1 - iter 72/95 - loss 2.00600562 - time (sec): 13.76 - samples/sec: 1815.85 - lr: 0.000022 - momentum: 0.000000
85
+ 2024-03-26 11:55:30,327 epoch 1 - iter 81/95 - loss 1.86859507 - time (sec): 16.08 - samples/sec: 1766.20 - lr: 0.000025 - momentum: 0.000000
86
+ 2024-03-26 11:55:31,746 epoch 1 - iter 90/95 - loss 1.73894185 - time (sec): 17.50 - samples/sec: 1826.13 - lr: 0.000028 - momentum: 0.000000
87
+ 2024-03-26 11:55:33,044 ----------------------------------------------------------------------------------------------------
88
+ 2024-03-26 11:55:33,044 EPOCH 1 done: loss 1.6731 - lr: 0.000028
89
+ 2024-03-26 11:55:34,148 DEV : loss 0.5027876496315002 - f1-score (micro avg) 0.6381
90
+ 2024-03-26 11:55:34,149 saving best model
91
+ 2024-03-26 11:55:34,458 ----------------------------------------------------------------------------------------------------
92
+ 2024-03-26 11:55:36,068 epoch 2 - iter 9/95 - loss 0.64246937 - time (sec): 1.61 - samples/sec: 1790.78 - lr: 0.000030 - momentum: 0.000000
93
+ 2024-03-26 11:55:37,805 epoch 2 - iter 18/95 - loss 0.54570834 - time (sec): 3.35 - samples/sec: 1846.87 - lr: 0.000029 - momentum: 0.000000
94
+ 2024-03-26 11:55:39,662 epoch 2 - iter 27/95 - loss 0.49748009 - time (sec): 5.20 - samples/sec: 1817.26 - lr: 0.000029 - momentum: 0.000000
95
+ 2024-03-26 11:55:42,119 epoch 2 - iter 36/95 - loss 0.44071019 - time (sec): 7.66 - samples/sec: 1703.13 - lr: 0.000029 - momentum: 0.000000
96
+ 2024-03-26 11:55:44,129 epoch 2 - iter 45/95 - loss 0.42197375 - time (sec): 9.67 - samples/sec: 1706.10 - lr: 0.000028 - momentum: 0.000000
97
+ 2024-03-26 11:55:45,906 epoch 2 - iter 54/95 - loss 0.43662546 - time (sec): 11.45 - samples/sec: 1732.55 - lr: 0.000028 - momentum: 0.000000
98
+ 2024-03-26 11:55:48,355 epoch 2 - iter 63/95 - loss 0.41482903 - time (sec): 13.90 - samples/sec: 1720.57 - lr: 0.000028 - momentum: 0.000000
99
+ 2024-03-26 11:55:50,232 epoch 2 - iter 72/95 - loss 0.41137379 - time (sec): 15.77 - samples/sec: 1714.43 - lr: 0.000028 - momentum: 0.000000
100
+ 2024-03-26 11:55:52,509 epoch 2 - iter 81/95 - loss 0.39878521 - time (sec): 18.05 - samples/sec: 1694.82 - lr: 0.000027 - momentum: 0.000000
101
+ 2024-03-26 11:55:53,829 epoch 2 - iter 90/95 - loss 0.39323040 - time (sec): 19.37 - samples/sec: 1719.95 - lr: 0.000027 - momentum: 0.000000
102
+ 2024-03-26 11:55:54,274 ----------------------------------------------------------------------------------------------------
103
+ 2024-03-26 11:55:54,274 EPOCH 2 done: loss 0.3875 - lr: 0.000027
104
+ 2024-03-26 11:55:55,230 DEV : loss 0.26269641518592834 - f1-score (micro avg) 0.8432
105
+ 2024-03-26 11:55:55,231 saving best model
106
+ 2024-03-26 11:55:55,712 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 11:55:57,291 epoch 3 - iter 9/95 - loss 0.23539211 - time (sec): 1.58 - samples/sec: 1678.72 - lr: 0.000026 - momentum: 0.000000
108
+ 2024-03-26 11:55:59,018 epoch 3 - iter 18/95 - loss 0.19969135 - time (sec): 3.31 - samples/sec: 1690.47 - lr: 0.000026 - momentum: 0.000000
109
+ 2024-03-26 11:56:00,928 epoch 3 - iter 27/95 - loss 0.20929956 - time (sec): 5.22 - samples/sec: 1707.64 - lr: 0.000026 - momentum: 0.000000
110
+ 2024-03-26 11:56:02,804 epoch 3 - iter 36/95 - loss 0.21437445 - time (sec): 7.09 - samples/sec: 1702.20 - lr: 0.000025 - momentum: 0.000000
111
+ 2024-03-26 11:56:04,876 epoch 3 - iter 45/95 - loss 0.21033512 - time (sec): 9.16 - samples/sec: 1723.01 - lr: 0.000025 - momentum: 0.000000
112
+ 2024-03-26 11:56:07,231 epoch 3 - iter 54/95 - loss 0.20765555 - time (sec): 11.52 - samples/sec: 1681.50 - lr: 0.000025 - momentum: 0.000000
113
+ 2024-03-26 11:56:09,032 epoch 3 - iter 63/95 - loss 0.20000055 - time (sec): 13.32 - samples/sec: 1679.54 - lr: 0.000025 - momentum: 0.000000
114
+ 2024-03-26 11:56:11,057 epoch 3 - iter 72/95 - loss 0.19513201 - time (sec): 15.34 - samples/sec: 1687.04 - lr: 0.000024 - momentum: 0.000000
115
+ 2024-03-26 11:56:13,099 epoch 3 - iter 81/95 - loss 0.20246445 - time (sec): 17.39 - samples/sec: 1703.42 - lr: 0.000024 - momentum: 0.000000
116
+ 2024-03-26 11:56:15,408 epoch 3 - iter 90/95 - loss 0.19703968 - time (sec): 19.70 - samples/sec: 1683.77 - lr: 0.000024 - momentum: 0.000000
117
+ 2024-03-26 11:56:16,030 ----------------------------------------------------------------------------------------------------
118
+ 2024-03-26 11:56:16,030 EPOCH 3 done: loss 0.2000 - lr: 0.000024
119
+ 2024-03-26 11:56:16,982 DEV : loss 0.22551582753658295 - f1-score (micro avg) 0.8695
120
+ 2024-03-26 11:56:16,984 saving best model
121
+ 2024-03-26 11:56:17,467 ----------------------------------------------------------------------------------------------------
122
+ 2024-03-26 11:56:19,917 epoch 4 - iter 9/95 - loss 0.07948519 - time (sec): 2.45 - samples/sec: 1614.35 - lr: 0.000023 - momentum: 0.000000
123
+ 2024-03-26 11:56:21,099 epoch 4 - iter 18/95 - loss 0.09981629 - time (sec): 3.63 - samples/sec: 1762.46 - lr: 0.000023 - momentum: 0.000000
124
+ 2024-03-26 11:56:23,337 epoch 4 - iter 27/95 - loss 0.11508058 - time (sec): 5.87 - samples/sec: 1771.76 - lr: 0.000022 - momentum: 0.000000
125
+ 2024-03-26 11:56:24,863 epoch 4 - iter 36/95 - loss 0.11806040 - time (sec): 7.40 - samples/sec: 1803.94 - lr: 0.000022 - momentum: 0.000000
126
+ 2024-03-26 11:56:26,211 epoch 4 - iter 45/95 - loss 0.12282635 - time (sec): 8.74 - samples/sec: 1835.27 - lr: 0.000022 - momentum: 0.000000
127
+ 2024-03-26 11:56:28,318 epoch 4 - iter 54/95 - loss 0.12105965 - time (sec): 10.85 - samples/sec: 1783.81 - lr: 0.000022 - momentum: 0.000000
128
+ 2024-03-26 11:56:30,676 epoch 4 - iter 63/95 - loss 0.13073889 - time (sec): 13.21 - samples/sec: 1752.76 - lr: 0.000021 - momentum: 0.000000
129
+ 2024-03-26 11:56:32,200 epoch 4 - iter 72/95 - loss 0.12964938 - time (sec): 14.73 - samples/sec: 1783.61 - lr: 0.000021 - momentum: 0.000000
130
+ 2024-03-26 11:56:33,848 epoch 4 - iter 81/95 - loss 0.12734713 - time (sec): 16.38 - samples/sec: 1813.11 - lr: 0.000021 - momentum: 0.000000
131
+ 2024-03-26 11:56:35,509 epoch 4 - iter 90/95 - loss 0.12668397 - time (sec): 18.04 - samples/sec: 1840.50 - lr: 0.000020 - momentum: 0.000000
132
+ 2024-03-26 11:56:36,136 ----------------------------------------------------------------------------------------------------
133
+ 2024-03-26 11:56:36,136 EPOCH 4 done: loss 0.1279 - lr: 0.000020
134
+ 2024-03-26 11:56:37,104 DEV : loss 0.21427477896213531 - f1-score (micro avg) 0.8761
135
+ 2024-03-26 11:56:37,105 saving best model
136
+ 2024-03-26 11:56:37,573 ----------------------------------------------------------------------------------------------------
137
+ 2024-03-26 11:56:38,812 epoch 5 - iter 9/95 - loss 0.15616297 - time (sec): 1.24 - samples/sec: 2388.07 - lr: 0.000020 - momentum: 0.000000
138
+ 2024-03-26 11:56:40,316 epoch 5 - iter 18/95 - loss 0.12941988 - time (sec): 2.74 - samples/sec: 2124.88 - lr: 0.000019 - momentum: 0.000000
139
+ 2024-03-26 11:56:42,400 epoch 5 - iter 27/95 - loss 0.10965291 - time (sec): 4.83 - samples/sec: 1905.49 - lr: 0.000019 - momentum: 0.000000
140
+ 2024-03-26 11:56:44,860 epoch 5 - iter 36/95 - loss 0.10946624 - time (sec): 7.29 - samples/sec: 1743.07 - lr: 0.000019 - momentum: 0.000000
141
+ 2024-03-26 11:56:46,119 epoch 5 - iter 45/95 - loss 0.11654181 - time (sec): 8.54 - samples/sec: 1787.38 - lr: 0.000019 - momentum: 0.000000
142
+ 2024-03-26 11:56:48,086 epoch 5 - iter 54/95 - loss 0.11010807 - time (sec): 10.51 - samples/sec: 1820.74 - lr: 0.000018 - momentum: 0.000000
143
+ 2024-03-26 11:56:50,215 epoch 5 - iter 63/95 - loss 0.10411708 - time (sec): 12.64 - samples/sec: 1807.78 - lr: 0.000018 - momentum: 0.000000
144
+ 2024-03-26 11:56:51,505 epoch 5 - iter 72/95 - loss 0.10148918 - time (sec): 13.93 - samples/sec: 1837.51 - lr: 0.000018 - momentum: 0.000000
145
+ 2024-03-26 11:56:54,129 epoch 5 - iter 81/95 - loss 0.09457679 - time (sec): 16.55 - samples/sec: 1774.16 - lr: 0.000017 - momentum: 0.000000
146
+ 2024-03-26 11:56:56,202 epoch 5 - iter 90/95 - loss 0.09353758 - time (sec): 18.63 - samples/sec: 1757.55 - lr: 0.000017 - momentum: 0.000000
147
+ 2024-03-26 11:56:57,088 ----------------------------------------------------------------------------------------------------
148
+ 2024-03-26 11:56:57,088 EPOCH 5 done: loss 0.0960 - lr: 0.000017
149
+ 2024-03-26 11:56:58,118 DEV : loss 0.1832679659128189 - f1-score (micro avg) 0.9051
150
+ 2024-03-26 11:56:58,119 saving best model
151
+ 2024-03-26 11:56:58,578 ----------------------------------------------------------------------------------------------------
152
+ 2024-03-26 11:57:00,298 epoch 6 - iter 9/95 - loss 0.10379749 - time (sec): 1.72 - samples/sec: 1930.27 - lr: 0.000016 - momentum: 0.000000
153
+ 2024-03-26 11:57:02,406 epoch 6 - iter 18/95 - loss 0.07357947 - time (sec): 3.83 - samples/sec: 1771.45 - lr: 0.000016 - momentum: 0.000000
154
+ 2024-03-26 11:57:03,879 epoch 6 - iter 27/95 - loss 0.07333469 - time (sec): 5.30 - samples/sec: 1803.32 - lr: 0.000016 - momentum: 0.000000
155
+ 2024-03-26 11:57:06,336 epoch 6 - iter 36/95 - loss 0.06078613 - time (sec): 7.76 - samples/sec: 1655.85 - lr: 0.000016 - momentum: 0.000000
156
+ 2024-03-26 11:57:08,153 epoch 6 - iter 45/95 - loss 0.05928533 - time (sec): 9.57 - samples/sec: 1680.63 - lr: 0.000015 - momentum: 0.000000
157
+ 2024-03-26 11:57:10,706 epoch 6 - iter 54/95 - loss 0.06721573 - time (sec): 12.13 - samples/sec: 1660.36 - lr: 0.000015 - momentum: 0.000000
158
+ 2024-03-26 11:57:12,299 epoch 6 - iter 63/95 - loss 0.06698720 - time (sec): 13.72 - samples/sec: 1673.28 - lr: 0.000015 - momentum: 0.000000
159
+ 2024-03-26 11:57:13,866 epoch 6 - iter 72/95 - loss 0.06755913 - time (sec): 15.29 - samples/sec: 1697.04 - lr: 0.000014 - momentum: 0.000000
160
+ 2024-03-26 11:57:16,008 epoch 6 - iter 81/95 - loss 0.06727789 - time (sec): 17.43 - samples/sec: 1691.62 - lr: 0.000014 - momentum: 0.000000
161
+ 2024-03-26 11:57:17,236 epoch 6 - iter 90/95 - loss 0.07050407 - time (sec): 18.66 - samples/sec: 1733.78 - lr: 0.000014 - momentum: 0.000000
162
+ 2024-03-26 11:57:18,646 ----------------------------------------------------------------------------------------------------
163
+ 2024-03-26 11:57:18,647 EPOCH 6 done: loss 0.0694 - lr: 0.000014
164
+ 2024-03-26 11:57:19,600 DEV : loss 0.1858818531036377 - f1-score (micro avg) 0.9155
165
+ 2024-03-26 11:57:19,601 saving best model
166
+ 2024-03-26 11:57:20,100 ----------------------------------------------------------------------------------------------------
167
+ 2024-03-26 11:57:21,480 epoch 7 - iter 9/95 - loss 0.05033159 - time (sec): 1.38 - samples/sec: 2298.68 - lr: 0.000013 - momentum: 0.000000
168
+ 2024-03-26 11:57:23,669 epoch 7 - iter 18/95 - loss 0.04331294 - time (sec): 3.57 - samples/sec: 1889.59 - lr: 0.000013 - momentum: 0.000000
169
+ 2024-03-26 11:57:25,670 epoch 7 - iter 27/95 - loss 0.05181771 - time (sec): 5.57 - samples/sec: 1754.90 - lr: 0.000013 - momentum: 0.000000
170
+ 2024-03-26 11:57:27,029 epoch 7 - iter 36/95 - loss 0.04939961 - time (sec): 6.93 - samples/sec: 1805.36 - lr: 0.000012 - momentum: 0.000000
171
+ 2024-03-26 11:57:28,743 epoch 7 - iter 45/95 - loss 0.05029394 - time (sec): 8.64 - samples/sec: 1820.56 - lr: 0.000012 - momentum: 0.000000
172
+ 2024-03-26 11:57:31,048 epoch 7 - iter 54/95 - loss 0.04643465 - time (sec): 10.95 - samples/sec: 1789.80 - lr: 0.000012 - momentum: 0.000000
173
+ 2024-03-26 11:57:33,130 epoch 7 - iter 63/95 - loss 0.04969253 - time (sec): 13.03 - samples/sec: 1747.42 - lr: 0.000011 - momentum: 0.000000
174
+ 2024-03-26 11:57:35,410 epoch 7 - iter 72/95 - loss 0.04844695 - time (sec): 15.31 - samples/sec: 1714.08 - lr: 0.000011 - momentum: 0.000000
175
+ 2024-03-26 11:57:36,957 epoch 7 - iter 81/95 - loss 0.05295729 - time (sec): 16.86 - samples/sec: 1722.76 - lr: 0.000011 - momentum: 0.000000
176
+ 2024-03-26 11:57:38,930 epoch 7 - iter 90/95 - loss 0.05654994 - time (sec): 18.83 - samples/sec: 1746.79 - lr: 0.000010 - momentum: 0.000000
177
+ 2024-03-26 11:57:39,636 ----------------------------------------------------------------------------------------------------
178
+ 2024-03-26 11:57:39,636 EPOCH 7 done: loss 0.0559 - lr: 0.000010
179
+ 2024-03-26 11:57:40,619 DEV : loss 0.181927889585495 - f1-score (micro avg) 0.9094
180
+ 2024-03-26 11:57:40,620 ----------------------------------------------------------------------------------------------------
181
+ 2024-03-26 11:57:42,328 epoch 8 - iter 9/95 - loss 0.01844897 - time (sec): 1.71 - samples/sec: 1723.93 - lr: 0.000010 - momentum: 0.000000
182
+ 2024-03-26 11:57:44,526 epoch 8 - iter 18/95 - loss 0.02171896 - time (sec): 3.91 - samples/sec: 1697.56 - lr: 0.000010 - momentum: 0.000000
183
+ 2024-03-26 11:57:46,418 epoch 8 - iter 27/95 - loss 0.02913290 - time (sec): 5.80 - samples/sec: 1674.25 - lr: 0.000009 - momentum: 0.000000
184
+ 2024-03-26 11:57:48,479 epoch 8 - iter 36/95 - loss 0.02986360 - time (sec): 7.86 - samples/sec: 1676.01 - lr: 0.000009 - momentum: 0.000000
185
+ 2024-03-26 11:57:49,539 epoch 8 - iter 45/95 - loss 0.03933294 - time (sec): 8.92 - samples/sec: 1759.00 - lr: 0.000009 - momentum: 0.000000
186
+ 2024-03-26 11:57:51,533 epoch 8 - iter 54/95 - loss 0.04288869 - time (sec): 10.91 - samples/sec: 1750.58 - lr: 0.000008 - momentum: 0.000000
187
+ 2024-03-26 11:57:53,850 epoch 8 - iter 63/95 - loss 0.04528908 - time (sec): 13.23 - samples/sec: 1732.41 - lr: 0.000008 - momentum: 0.000000
188
+ 2024-03-26 11:57:56,133 epoch 8 - iter 72/95 - loss 0.04533457 - time (sec): 15.51 - samples/sec: 1723.35 - lr: 0.000008 - momentum: 0.000000
189
+ 2024-03-26 11:57:57,900 epoch 8 - iter 81/95 - loss 0.04477217 - time (sec): 17.28 - samples/sec: 1727.25 - lr: 0.000007 - momentum: 0.000000
190
+ 2024-03-26 11:57:59,976 epoch 8 - iter 90/95 - loss 0.04204724 - time (sec): 19.36 - samples/sec: 1715.31 - lr: 0.000007 - momentum: 0.000000
191
+ 2024-03-26 11:58:00,588 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 11:58:00,588 EPOCH 8 done: loss 0.0426 - lr: 0.000007
193
+ 2024-03-26 11:58:01,571 DEV : loss 0.20383676886558533 - f1-score (micro avg) 0.9172
194
+ 2024-03-26 11:58:01,572 saving best model
195
+ 2024-03-26 11:58:02,023 ----------------------------------------------------------------------------------------------------
196
+ 2024-03-26 11:58:03,617 epoch 9 - iter 9/95 - loss 0.02505376 - time (sec): 1.59 - samples/sec: 1995.95 - lr: 0.000007 - momentum: 0.000000
197
+ 2024-03-26 11:58:06,031 epoch 9 - iter 18/95 - loss 0.02969341 - time (sec): 4.01 - samples/sec: 1699.30 - lr: 0.000006 - momentum: 0.000000
198
+ 2024-03-26 11:58:07,698 epoch 9 - iter 27/95 - loss 0.02626858 - time (sec): 5.67 - samples/sec: 1717.55 - lr: 0.000006 - momentum: 0.000000
199
+ 2024-03-26 11:58:10,071 epoch 9 - iter 36/95 - loss 0.02897411 - time (sec): 8.05 - samples/sec: 1685.99 - lr: 0.000006 - momentum: 0.000000
200
+ 2024-03-26 11:58:12,008 epoch 9 - iter 45/95 - loss 0.03122157 - time (sec): 9.98 - samples/sec: 1666.39 - lr: 0.000005 - momentum: 0.000000
201
+ 2024-03-26 11:58:13,454 epoch 9 - iter 54/95 - loss 0.03516292 - time (sec): 11.43 - samples/sec: 1707.17 - lr: 0.000005 - momentum: 0.000000
202
+ 2024-03-26 11:58:15,631 epoch 9 - iter 63/95 - loss 0.03376295 - time (sec): 13.61 - samples/sec: 1684.97 - lr: 0.000005 - momentum: 0.000000
203
+ 2024-03-26 11:58:16,873 epoch 9 - iter 72/95 - loss 0.03901638 - time (sec): 14.85 - samples/sec: 1721.52 - lr: 0.000004 - momentum: 0.000000
204
+ 2024-03-26 11:58:19,716 epoch 9 - iter 81/95 - loss 0.03682128 - time (sec): 17.69 - samples/sec: 1678.48 - lr: 0.000004 - momentum: 0.000000
205
+ 2024-03-26 11:58:21,389 epoch 9 - iter 90/95 - loss 0.03456541 - time (sec): 19.37 - samples/sec: 1701.21 - lr: 0.000004 - momentum: 0.000000
206
+ 2024-03-26 11:58:22,071 ----------------------------------------------------------------------------------------------------
207
+ 2024-03-26 11:58:22,072 EPOCH 9 done: loss 0.0375 - lr: 0.000004
208
+ 2024-03-26 11:58:23,034 DEV : loss 0.20626600086688995 - f1-score (micro avg) 0.9191
209
+ 2024-03-26 11:58:23,036 saving best model
210
+ 2024-03-26 11:58:23,539 ----------------------------------------------------------------------------------------------------
211
+ 2024-03-26 11:58:25,474 epoch 10 - iter 9/95 - loss 0.02794878 - time (sec): 1.93 - samples/sec: 1603.68 - lr: 0.000003 - momentum: 0.000000
212
+ 2024-03-26 11:58:27,841 epoch 10 - iter 18/95 - loss 0.02797907 - time (sec): 4.30 - samples/sec: 1549.55 - lr: 0.000003 - momentum: 0.000000
213
+ 2024-03-26 11:58:29,273 epoch 10 - iter 27/95 - loss 0.02998392 - time (sec): 5.73 - samples/sec: 1711.03 - lr: 0.000003 - momentum: 0.000000
214
+ 2024-03-26 11:58:31,038 epoch 10 - iter 36/95 - loss 0.02767804 - time (sec): 7.50 - samples/sec: 1760.03 - lr: 0.000002 - momentum: 0.000000
215
+ 2024-03-26 11:58:32,481 epoch 10 - iter 45/95 - loss 0.02603534 - time (sec): 8.94 - samples/sec: 1796.13 - lr: 0.000002 - momentum: 0.000000
216
+ 2024-03-26 11:58:33,534 epoch 10 - iter 54/95 - loss 0.02457130 - time (sec): 9.99 - samples/sec: 1867.33 - lr: 0.000002 - momentum: 0.000000
217
+ 2024-03-26 11:58:35,396 epoch 10 - iter 63/95 - loss 0.02346308 - time (sec): 11.86 - samples/sec: 1843.70 - lr: 0.000001 - momentum: 0.000000
218
+ 2024-03-26 11:58:37,726 epoch 10 - iter 72/95 - loss 0.02934107 - time (sec): 14.19 - samples/sec: 1797.18 - lr: 0.000001 - momentum: 0.000000
219
+ 2024-03-26 11:58:39,435 epoch 10 - iter 81/95 - loss 0.03184212 - time (sec): 15.90 - samples/sec: 1787.51 - lr: 0.000001 - momentum: 0.000000
220
+ 2024-03-26 11:58:41,916 epoch 10 - iter 90/95 - loss 0.03020914 - time (sec): 18.38 - samples/sec: 1768.61 - lr: 0.000000 - momentum: 0.000000
221
+ 2024-03-26 11:58:43,184 ----------------------------------------------------------------------------------------------------
222
+ 2024-03-26 11:58:43,184 EPOCH 10 done: loss 0.0306 - lr: 0.000000
223
+ 2024-03-26 11:58:44,147 DEV : loss 0.21392525732517242 - f1-score (micro avg) 0.9134
224
+ 2024-03-26 11:58:44,460 ----------------------------------------------------------------------------------------------------
225
+ 2024-03-26 11:58:44,460 Loading model from best epoch ...
226
+ 2024-03-26 11:58:45,371 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 11:58:46,180
228
+ Results:
229
+ - F-score (micro) 0.9024
230
+ - F-score (macro) 0.6877
231
+ - Accuracy 0.8245
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ Unternehmen 0.8826 0.8759 0.8792 266
237
+ Auslagerung 0.8659 0.9076 0.8863 249
238
+ Ort 0.9779 0.9925 0.9852 134
239
+ Software 0.0000 0.0000 0.0000 0
240
+
241
+ micro avg 0.8929 0.9122 0.9024 649
242
+ macro avg 0.6816 0.6940 0.6877 649
243
+ weighted avg 0.8959 0.9122 0.9038 649
244
+
245
+ 2024-03-26 11:58:46,180 ----------------------------------------------------------------------------------------------------