Hugging Face's logo

stefan-it
/
flair-co-funer-german_dbmdz_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
1cd0638
•
1 Parent(s): 8492b8a

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +246 -0
training.log ADDED
@@ -0,0 +1,246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-03-26 16:13:04,091 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 16:13:04,092 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 16:13:04,092 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 16:13:04,092 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 16:13:04,092 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 16:13:04,092 Train: 758 sentences
54
+ 2024-03-26 16:13:04,092 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 16:13:04,092 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 16:13:04,092 Training Params:
57
+ 2024-03-26 16:13:04,092 - learning_rate: "3e-05"
58
+ 2024-03-26 16:13:04,092 - mini_batch_size: "8"
59
+ 2024-03-26 16:13:04,092 - max_epochs: "10"
60
+ 2024-03-26 16:13:04,092 - shuffle: "True"
61
+ 2024-03-26 16:13:04,092 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 16:13:04,092 Plugins:
63
+ 2024-03-26 16:13:04,092 - TensorboardLogger
64
+ 2024-03-26 16:13:04,092 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 16:13:04,092 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 16:13:04,092 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 16:13:04,092 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 16:13:04,092 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 16:13:04,092 Computation:
70
+ 2024-03-26 16:13:04,092 - compute on device: cuda:0
71
+ 2024-03-26 16:13:04,092 - embedding storage: none
72
+ 2024-03-26 16:13:04,092 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 16:13:04,092 Model training base path: "flair-co-funer-german_dbmdz_bert_base-bs8-e10-lr3e-05-4"
74
+ 2024-03-26 16:13:04,092 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 16:13:04,092 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 16:13:04,092 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 16:13:05,441 epoch 1 - iter 9/95 - loss 3.01892317 - time (sec): 1.35 - samples/sec: 2152.42 - lr: 0.000003 - momentum: 0.000000
78
+ 2024-03-26 16:13:06,820 epoch 1 - iter 18/95 - loss 2.94981305 - time (sec): 2.73 - samples/sec: 2022.04 - lr: 0.000005 - momentum: 0.000000
79
+ 2024-03-26 16:13:08,432 epoch 1 - iter 27/95 - loss 2.78986887 - time (sec): 4.34 - samples/sec: 1976.26 - lr: 0.000008 - momentum: 0.000000
80
+ 2024-03-26 16:13:10,392 epoch 1 - iter 36/95 - loss 2.58386486 - time (sec): 6.30 - samples/sec: 1895.02 - lr: 0.000011 - momentum: 0.000000
81
+ 2024-03-26 16:13:12,239 epoch 1 - iter 45/95 - loss 2.39924465 - time (sec): 8.15 - samples/sec: 1914.24 - lr: 0.000014 - momentum: 0.000000
82
+ 2024-03-26 16:13:14,452 epoch 1 - iter 54/95 - loss 2.24473941 - time (sec): 10.36 - samples/sec: 1848.24 - lr: 0.000017 - momentum: 0.000000
83
+ 2024-03-26 16:13:16,455 epoch 1 - iter 63/95 - loss 2.10652823 - time (sec): 12.36 - samples/sec: 1828.33 - lr: 0.000020 - momentum: 0.000000
84
+ 2024-03-26 16:13:17,425 epoch 1 - iter 72/95 - loss 2.02587073 - time (sec): 13.33 - samples/sec: 1873.71 - lr: 0.000022 - momentum: 0.000000
85
+ 2024-03-26 16:13:19,697 epoch 1 - iter 81/95 - loss 1.88802215 - time (sec): 15.60 - samples/sec: 1820.33 - lr: 0.000025 - momentum: 0.000000
86
+ 2024-03-26 16:13:21,027 epoch 1 - iter 90/95 - loss 1.75243499 - time (sec): 16.93 - samples/sec: 1887.35 - lr: 0.000028 - momentum: 0.000000
87
+ 2024-03-26 16:13:22,289 ----------------------------------------------------------------------------------------------------
88
+ 2024-03-26 16:13:22,290 EPOCH 1 done: loss 1.6837 - lr: 0.000028
89
+ 2024-03-26 16:13:23,178 DEV : loss 0.5122107267379761 - f1-score (micro avg) 0.6199
90
+ 2024-03-26 16:13:23,180 saving best model
91
+ 2024-03-26 16:13:23,441 ----------------------------------------------------------------------------------------------------
92
+ 2024-03-26 16:13:25,018 epoch 2 - iter 9/95 - loss 0.64396303 - time (sec): 1.58 - samples/sec: 1827.81 - lr: 0.000030 - momentum: 0.000000
93
+ 2024-03-26 16:13:26,643 epoch 2 - iter 18/95 - loss 0.55024335 - time (sec): 3.20 - samples/sec: 1930.56 - lr: 0.000029 - momentum: 0.000000
94
+ 2024-03-26 16:13:28,415 epoch 2 - iter 27/95 - loss 0.49926632 - time (sec): 4.97 - samples/sec: 1901.22 - lr: 0.000029 - momentum: 0.000000
95
+ 2024-03-26 16:13:30,773 epoch 2 - iter 36/95 - loss 0.43995028 - time (sec): 7.33 - samples/sec: 1779.64 - lr: 0.000029 - momentum: 0.000000
96
+ 2024-03-26 16:13:32,718 epoch 2 - iter 45/95 - loss 0.42382182 - time (sec): 9.28 - samples/sec: 1778.63 - lr: 0.000028 - momentum: 0.000000
97
+ 2024-03-26 16:13:34,462 epoch 2 - iter 54/95 - loss 0.43455854 - time (sec): 11.02 - samples/sec: 1799.70 - lr: 0.000028 - momentum: 0.000000
98
+ 2024-03-26 16:13:36,855 epoch 2 - iter 63/95 - loss 0.41135255 - time (sec): 13.41 - samples/sec: 1782.58 - lr: 0.000028 - momentum: 0.000000
99
+ 2024-03-26 16:13:38,662 epoch 2 - iter 72/95 - loss 0.41076175 - time (sec): 15.22 - samples/sec: 1776.73 - lr: 0.000028 - momentum: 0.000000
100
+ 2024-03-26 16:13:40,826 epoch 2 - iter 81/95 - loss 0.40019733 - time (sec): 17.38 - samples/sec: 1759.78 - lr: 0.000027 - momentum: 0.000000
101
+ 2024-03-26 16:13:42,109 epoch 2 - iter 90/95 - loss 0.39608461 - time (sec): 18.67 - samples/sec: 1784.75 - lr: 0.000027 - momentum: 0.000000
102
+ 2024-03-26 16:13:42,557 ----------------------------------------------------------------------------------------------------
103
+ 2024-03-26 16:13:42,557 EPOCH 2 done: loss 0.3914 - lr: 0.000027
104
+ 2024-03-26 16:13:43,466 DEV : loss 0.3047449290752411 - f1-score (micro avg) 0.8109
105
+ 2024-03-26 16:13:43,467 saving best model
106
+ 2024-03-26 16:13:43,903 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 16:13:45,404 epoch 3 - iter 9/95 - loss 0.23934414 - time (sec): 1.50 - samples/sec: 1767.18 - lr: 0.000026 - momentum: 0.000000
108
+ 2024-03-26 16:13:47,113 epoch 3 - iter 18/95 - loss 0.21659015 - time (sec): 3.21 - samples/sec: 1742.16 - lr: 0.000026 - momentum: 0.000000
109
+ 2024-03-26 16:13:48,946 epoch 3 - iter 27/95 - loss 0.21961110 - time (sec): 5.04 - samples/sec: 1766.65 - lr: 0.000026 - momentum: 0.000000
110
+ 2024-03-26 16:13:50,724 epoch 3 - iter 36/95 - loss 0.22376893 - time (sec): 6.82 - samples/sec: 1770.25 - lr: 0.000025 - momentum: 0.000000
111
+ 2024-03-26 16:13:52,726 epoch 3 - iter 45/95 - loss 0.22130363 - time (sec): 8.82 - samples/sec: 1789.86 - lr: 0.000025 - momentum: 0.000000
112
+ 2024-03-26 16:13:54,955 epoch 3 - iter 54/95 - loss 0.21592911 - time (sec): 11.05 - samples/sec: 1752.80 - lr: 0.000025 - momentum: 0.000000
113
+ 2024-03-26 16:13:56,657 epoch 3 - iter 63/95 - loss 0.20957384 - time (sec): 12.75 - samples/sec: 1754.24 - lr: 0.000025 - momentum: 0.000000
114
+ 2024-03-26 16:13:58,612 epoch 3 - iter 72/95 - loss 0.20499047 - time (sec): 14.71 - samples/sec: 1760.18 - lr: 0.000024 - momentum: 0.000000
115
+ 2024-03-26 16:14:00,581 epoch 3 - iter 81/95 - loss 0.21084290 - time (sec): 16.68 - samples/sec: 1775.97 - lr: 0.000024 - momentum: 0.000000
116
+ 2024-03-26 16:14:02,808 epoch 3 - iter 90/95 - loss 0.20345167 - time (sec): 18.90 - samples/sec: 1754.34 - lr: 0.000024 - momentum: 0.000000
117
+ 2024-03-26 16:14:03,421 ----------------------------------------------------------------------------------------------------
118
+ 2024-03-26 16:14:03,421 EPOCH 3 done: loss 0.2055 - lr: 0.000024
119
+ 2024-03-26 16:14:04,337 DEV : loss 0.21783055365085602 - f1-score (micro avg) 0.8673
120
+ 2024-03-26 16:14:04,339 saving best model
121
+ 2024-03-26 16:14:04,801 ----------------------------------------------------------------------------------------------------
122
+ 2024-03-26 16:14:07,176 epoch 4 - iter 9/95 - loss 0.07517827 - time (sec): 2.38 - samples/sec: 1665.20 - lr: 0.000023 - momentum: 0.000000
123
+ 2024-03-26 16:14:08,341 epoch 4 - iter 18/95 - loss 0.10000483 - time (sec): 3.54 - samples/sec: 1807.80 - lr: 0.000023 - momentum: 0.000000
124
+ 2024-03-26 16:14:10,456 epoch 4 - iter 27/95 - loss 0.12477688 - time (sec): 5.66 - samples/sec: 1838.82 - lr: 0.000022 - momentum: 0.000000
125
+ 2024-03-26 16:14:11,938 epoch 4 - iter 36/95 - loss 0.12845343 - time (sec): 7.14 - samples/sec: 1869.30 - lr: 0.000022 - momentum: 0.000000
126
+ 2024-03-26 16:14:13,235 epoch 4 - iter 45/95 - loss 0.12810894 - time (sec): 8.43 - samples/sec: 1902.63 - lr: 0.000022 - momentum: 0.000000
127
+ 2024-03-26 16:14:15,282 epoch 4 - iter 54/95 - loss 0.12646511 - time (sec): 10.48 - samples/sec: 1846.77 - lr: 0.000022 - momentum: 0.000000
128
+ 2024-03-26 16:14:17,528 epoch 4 - iter 63/95 - loss 0.13973987 - time (sec): 12.73 - samples/sec: 1819.20 - lr: 0.000021 - momentum: 0.000000
129
+ 2024-03-26 16:14:18,968 epoch 4 - iter 72/95 - loss 0.13882561 - time (sec): 14.17 - samples/sec: 1854.83 - lr: 0.000021 - momentum: 0.000000
130
+ 2024-03-26 16:14:20,553 epoch 4 - iter 81/95 - loss 0.13686782 - time (sec): 15.75 - samples/sec: 1885.58 - lr: 0.000021 - momentum: 0.000000
131
+ 2024-03-26 16:14:22,160 epoch 4 - iter 90/95 - loss 0.13516261 - time (sec): 17.36 - samples/sec: 1912.90 - lr: 0.000020 - momentum: 0.000000
132
+ 2024-03-26 16:14:22,783 ----------------------------------------------------------------------------------------------------
133
+ 2024-03-26 16:14:22,783 EPOCH 4 done: loss 0.1357 - lr: 0.000020
134
+ 2024-03-26 16:14:23,693 DEV : loss 0.19859355688095093 - f1-score (micro avg) 0.9001
135
+ 2024-03-26 16:14:23,694 saving best model
136
+ 2024-03-26 16:14:24,137 ----------------------------------------------------------------------------------------------------
137
+ 2024-03-26 16:14:25,337 epoch 5 - iter 9/95 - loss 0.15499173 - time (sec): 1.20 - samples/sec: 2465.78 - lr: 0.000020 - momentum: 0.000000
138
+ 2024-03-26 16:14:26,763 epoch 5 - iter 18/95 - loss 0.12626124 - time (sec): 2.63 - samples/sec: 2220.05 - lr: 0.000019 - momentum: 0.000000
139
+ 2024-03-26 16:14:28,731 epoch 5 - iter 27/95 - loss 0.11156913 - time (sec): 4.59 - samples/sec: 2001.98 - lr: 0.000019 - momentum: 0.000000
140
+ 2024-03-26 16:14:31,129 epoch 5 - iter 36/95 - loss 0.10681209 - time (sec): 6.99 - samples/sec: 1816.67 - lr: 0.000019 - momentum: 0.000000
141
+ 2024-03-26 16:14:32,338 epoch 5 - iter 45/95 - loss 0.11337595 - time (sec): 8.20 - samples/sec: 1862.46 - lr: 0.000019 - momentum: 0.000000
142
+ 2024-03-26 16:14:34,180 epoch 5 - iter 54/95 - loss 0.10710186 - time (sec): 10.04 - samples/sec: 1906.04 - lr: 0.000018 - momentum: 0.000000
143
+ 2024-03-26 16:14:36,215 epoch 5 - iter 63/95 - loss 0.10095178 - time (sec): 12.08 - samples/sec: 1892.23 - lr: 0.000018 - momentum: 0.000000
144
+ 2024-03-26 16:14:37,462 epoch 5 - iter 72/95 - loss 0.09984606 - time (sec): 13.32 - samples/sec: 1921.32 - lr: 0.000018 - momentum: 0.000000
145
+ 2024-03-26 16:14:39,985 epoch 5 - iter 81/95 - loss 0.09463996 - time (sec): 15.85 - samples/sec: 1853.36 - lr: 0.000017 - momentum: 0.000000
146
+ 2024-03-26 16:14:42,006 epoch 5 - iter 90/95 - loss 0.09475277 - time (sec): 17.87 - samples/sec: 1832.33 - lr: 0.000017 - momentum: 0.000000
147
+ 2024-03-26 16:14:42,871 ----------------------------------------------------------------------------------------------------
148
+ 2024-03-26 16:14:42,871 EPOCH 5 done: loss 0.0957 - lr: 0.000017
149
+ 2024-03-26 16:14:43,890 DEV : loss 0.17372848093509674 - f1-score (micro avg) 0.8924
150
+ 2024-03-26 16:14:43,891 ----------------------------------------------------------------------------------------------------
151
+ 2024-03-26 16:14:45,553 epoch 6 - iter 9/95 - loss 0.11813969 - time (sec): 1.66 - samples/sec: 1996.15 - lr: 0.000016 - momentum: 0.000000
152
+ 2024-03-26 16:14:47,611 epoch 6 - iter 18/95 - loss 0.08450061 - time (sec): 3.72 - samples/sec: 1821.92 - lr: 0.000016 - momentum: 0.000000
153
+ 2024-03-26 16:14:49,052 epoch 6 - iter 27/95 - loss 0.08305533 - time (sec): 5.16 - samples/sec: 1851.53 - lr: 0.000016 - momentum: 0.000000
154
+ 2024-03-26 16:14:51,388 epoch 6 - iter 36/95 - loss 0.06803915 - time (sec): 7.50 - samples/sec: 1713.00 - lr: 0.000016 - momentum: 0.000000
155
+ 2024-03-26 16:14:53,168 epoch 6 - iter 45/95 - loss 0.06604557 - time (sec): 9.28 - samples/sec: 1734.19 - lr: 0.000015 - momentum: 0.000000
156
+ 2024-03-26 16:14:55,645 epoch 6 - iter 54/95 - loss 0.07294541 - time (sec): 11.75 - samples/sec: 1712.88 - lr: 0.000015 - momentum: 0.000000
157
+ 2024-03-26 16:14:57,157 epoch 6 - iter 63/95 - loss 0.07352466 - time (sec): 13.27 - samples/sec: 1730.50 - lr: 0.000015 - momentum: 0.000000
158
+ 2024-03-26 16:14:58,699 epoch 6 - iter 72/95 - loss 0.07270595 - time (sec): 14.81 - samples/sec: 1751.86 - lr: 0.000014 - momentum: 0.000000
159
+ 2024-03-26 16:15:00,785 epoch 6 - iter 81/95 - loss 0.07352203 - time (sec): 16.89 - samples/sec: 1745.08 - lr: 0.000014 - momentum: 0.000000
160
+ 2024-03-26 16:15:01,968 epoch 6 - iter 90/95 - loss 0.07693810 - time (sec): 18.08 - samples/sec: 1789.28 - lr: 0.000014 - momentum: 0.000000
161
+ 2024-03-26 16:15:03,303 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 16:15:03,303 EPOCH 6 done: loss 0.0749 - lr: 0.000014
163
+ 2024-03-26 16:15:04,234 DEV : loss 0.17936821281909943 - f1-score (micro avg) 0.9228
164
+ 2024-03-26 16:15:04,236 saving best model
165
+ 2024-03-26 16:15:04,682 ----------------------------------------------------------------------------------------------------
166
+ 2024-03-26 16:15:06,057 epoch 7 - iter 9/95 - loss 0.06958458 - time (sec): 1.37 - samples/sec: 2311.25 - lr: 0.000013 - momentum: 0.000000
167
+ 2024-03-26 16:15:08,176 epoch 7 - iter 18/95 - loss 0.05784086 - time (sec): 3.49 - samples/sec: 1931.12 - lr: 0.000013 - momentum: 0.000000
168
+ 2024-03-26 16:15:10,073 epoch 7 - iter 27/95 - loss 0.06236455 - time (sec): 5.39 - samples/sec: 1813.90 - lr: 0.000013 - momentum: 0.000000
169
+ 2024-03-26 16:15:11,375 epoch 7 - iter 36/95 - loss 0.06012303 - time (sec): 6.69 - samples/sec: 1869.77 - lr: 0.000012 - momentum: 0.000000
170
+ 2024-03-26 16:15:13,075 epoch 7 - iter 45/95 - loss 0.05742602 - time (sec): 8.39 - samples/sec: 1875.36 - lr: 0.000012 - momentum: 0.000000
171
+ 2024-03-26 16:15:15,276 epoch 7 - iter 54/95 - loss 0.05375127 - time (sec): 10.59 - samples/sec: 1849.97 - lr: 0.000012 - momentum: 0.000000
172
+ 2024-03-26 16:15:17,316 epoch 7 - iter 63/95 - loss 0.05596495 - time (sec): 12.63 - samples/sec: 1802.49 - lr: 0.000011 - momentum: 0.000000
173
+ 2024-03-26 16:15:19,447 epoch 7 - iter 72/95 - loss 0.05433191 - time (sec): 14.76 - samples/sec: 1777.64 - lr: 0.000011 - momentum: 0.000000
174
+ 2024-03-26 16:15:20,963 epoch 7 - iter 81/95 - loss 0.05821444 - time (sec): 16.28 - samples/sec: 1784.00 - lr: 0.000011 - momentum: 0.000000
175
+ 2024-03-26 16:15:22,840 epoch 7 - iter 90/95 - loss 0.06164903 - time (sec): 18.15 - samples/sec: 1811.68 - lr: 0.000010 - momentum: 0.000000
176
+ 2024-03-26 16:15:23,531 ----------------------------------------------------------------------------------------------------
177
+ 2024-03-26 16:15:23,531 EPOCH 7 done: loss 0.0607 - lr: 0.000010
178
+ 2024-03-26 16:15:24,452 DEV : loss 0.17456422746181488 - f1-score (micro avg) 0.931
179
+ 2024-03-26 16:15:24,455 saving best model
180
+ 2024-03-26 16:15:24,925 ----------------------------------------------------------------------------------------------------
181
+ 2024-03-26 16:15:26,576 epoch 8 - iter 9/95 - loss 0.03164527 - time (sec): 1.65 - samples/sec: 1783.01 - lr: 0.000010 - momentum: 0.000000
182
+ 2024-03-26 16:15:28,709 epoch 8 - iter 18/95 - loss 0.03273288 - time (sec): 3.78 - samples/sec: 1752.09 - lr: 0.000010 - momentum: 0.000000
183
+ 2024-03-26 16:15:30,558 epoch 8 - iter 27/95 - loss 0.04257132 - time (sec): 5.63 - samples/sec: 1723.16 - lr: 0.000009 - momentum: 0.000000
184
+ 2024-03-26 16:15:32,534 epoch 8 - iter 36/95 - loss 0.04208931 - time (sec): 7.61 - samples/sec: 1731.08 - lr: 0.000009 - momentum: 0.000000
185
+ 2024-03-26 16:15:33,565 epoch 8 - iter 45/95 - loss 0.05163225 - time (sec): 8.64 - samples/sec: 1815.79 - lr: 0.000009 - momentum: 0.000000
186
+ 2024-03-26 16:15:35,509 epoch 8 - iter 54/95 - loss 0.05431701 - time (sec): 10.58 - samples/sec: 1804.85 - lr: 0.000008 - momentum: 0.000000
187
+ 2024-03-26 16:15:37,748 epoch 8 - iter 63/95 - loss 0.05448027 - time (sec): 12.82 - samples/sec: 1787.38 - lr: 0.000008 - momentum: 0.000000
188
+ 2024-03-26 16:15:39,958 epoch 8 - iter 72/95 - loss 0.05350915 - time (sec): 15.03 - samples/sec: 1778.34 - lr: 0.000008 - momentum: 0.000000
189
+ 2024-03-26 16:15:41,669 epoch 8 - iter 81/95 - loss 0.05217506 - time (sec): 16.74 - samples/sec: 1782.50 - lr: 0.000007 - momentum: 0.000000
190
+ 2024-03-26 16:15:43,594 epoch 8 - iter 90/95 - loss 0.04976103 - time (sec): 18.67 - samples/sec: 1778.45 - lr: 0.000007 - momentum: 0.000000
191
+ 2024-03-26 16:15:44,189 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 16:15:44,190 EPOCH 8 done: loss 0.0505 - lr: 0.000007
193
+ 2024-03-26 16:15:45,127 DEV : loss 0.18435950577259064 - f1-score (micro avg) 0.9326
194
+ 2024-03-26 16:15:45,128 saving best model
195
+ 2024-03-26 16:15:45,601 ----------------------------------------------------------------------------------------------------
196
+ 2024-03-26 16:15:47,129 epoch 9 - iter 9/95 - loss 0.04389027 - time (sec): 1.53 - samples/sec: 2082.70 - lr: 0.000007 - momentum: 0.000000
197
+ 2024-03-26 16:15:49,410 epoch 9 - iter 18/95 - loss 0.03620731 - time (sec): 3.81 - samples/sec: 1788.41 - lr: 0.000006 - momentum: 0.000000
198
+ 2024-03-26 16:15:50,997 epoch 9 - iter 27/95 - loss 0.02956550 - time (sec): 5.40 - samples/sec: 1806.40 - lr: 0.000006 - momentum: 0.000000
199
+ 2024-03-26 16:15:53,280 epoch 9 - iter 36/95 - loss 0.03571516 - time (sec): 7.68 - samples/sec: 1766.87 - lr: 0.000006 - momentum: 0.000000
200
+ 2024-03-26 16:15:55,165 epoch 9 - iter 45/95 - loss 0.03668108 - time (sec): 9.56 - samples/sec: 1739.74 - lr: 0.000005 - momentum: 0.000000
201
+ 2024-03-26 16:15:56,535 epoch 9 - iter 54/95 - loss 0.03858777 - time (sec): 10.93 - samples/sec: 1784.77 - lr: 0.000005 - momentum: 0.000000
202
+ 2024-03-26 16:15:58,590 epoch 9 - iter 63/95 - loss 0.03601310 - time (sec): 12.99 - samples/sec: 1765.15 - lr: 0.000005 - momentum: 0.000000
203
+ 2024-03-26 16:15:59,803 epoch 9 - iter 72/95 - loss 0.04076328 - time (sec): 14.20 - samples/sec: 1800.00 - lr: 0.000004 - momentum: 0.000000
204
+ 2024-03-26 16:16:02,536 epoch 9 - iter 81/95 - loss 0.03883671 - time (sec): 16.93 - samples/sec: 1753.65 - lr: 0.000004 - momentum: 0.000000
205
+ 2024-03-26 16:16:04,161 epoch 9 - iter 90/95 - loss 0.03642009 - time (sec): 18.56 - samples/sec: 1775.06 - lr: 0.000004 - momentum: 0.000000
206
+ 2024-03-26 16:16:04,819 ----------------------------------------------------------------------------------------------------
207
+ 2024-03-26 16:16:04,820 EPOCH 9 done: loss 0.0392 - lr: 0.000004
208
+ 2024-03-26 16:16:05,747 DEV : loss 0.18579983711242676 - f1-score (micro avg) 0.9379
209
+ 2024-03-26 16:16:05,749 saving best model
210
+ 2024-03-26 16:16:06,220 ----------------------------------------------------------------------------------------------------
211
+ 2024-03-26 16:16:08,063 epoch 10 - iter 9/95 - loss 0.03895271 - time (sec): 1.84 - samples/sec: 1684.25 - lr: 0.000003 - momentum: 0.000000
212
+ 2024-03-26 16:16:10,318 epoch 10 - iter 18/95 - loss 0.03731677 - time (sec): 4.10 - samples/sec: 1627.21 - lr: 0.000003 - momentum: 0.000000
213
+ 2024-03-26 16:16:11,737 epoch 10 - iter 27/95 - loss 0.03325541 - time (sec): 5.51 - samples/sec: 1778.77 - lr: 0.000003 - momentum: 0.000000
214
+ 2024-03-26 16:16:13,455 epoch 10 - iter 36/95 - loss 0.03072498 - time (sec): 7.23 - samples/sec: 1824.40 - lr: 0.000002 - momentum: 0.000000
215
+ 2024-03-26 16:16:14,871 epoch 10 - iter 45/95 - loss 0.03067039 - time (sec): 8.65 - samples/sec: 1856.85 - lr: 0.000002 - momentum: 0.000000
216
+ 2024-03-26 16:16:15,893 epoch 10 - iter 54/95 - loss 0.02972160 - time (sec): 9.67 - samples/sec: 1929.57 - lr: 0.000002 - momentum: 0.000000
217
+ 2024-03-26 16:16:17,698 epoch 10 - iter 63/95 - loss 0.02849617 - time (sec): 11.48 - samples/sec: 1904.78 - lr: 0.000001 - momentum: 0.000000
218
+ 2024-03-26 16:16:19,950 epoch 10 - iter 72/95 - loss 0.03464330 - time (sec): 13.73 - samples/sec: 1857.14 - lr: 0.000001 - momentum: 0.000000
219
+ 2024-03-26 16:16:21,578 epoch 10 - iter 81/95 - loss 0.03819664 - time (sec): 15.36 - samples/sec: 1850.26 - lr: 0.000001 - momentum: 0.000000
220
+ 2024-03-26 16:16:23,897 epoch 10 - iter 90/95 - loss 0.03582206 - time (sec): 17.68 - samples/sec: 1838.69 - lr: 0.000000 - momentum: 0.000000
221
+ 2024-03-26 16:16:25,150 ----------------------------------------------------------------------------------------------------
222
+ 2024-03-26 16:16:25,150 EPOCH 10 done: loss 0.0380 - lr: 0.000000
223
+ 2024-03-26 16:16:26,095 DEV : loss 0.19086487591266632 - f1-score (micro avg) 0.9417
224
+ 2024-03-26 16:16:26,097 saving best model
225
+ 2024-03-26 16:16:26,869 ----------------------------------------------------------------------------------------------------
226
+ 2024-03-26 16:16:26,869 Loading model from best epoch ...
227
+ 2024-03-26 16:16:27,761 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
228
+ 2024-03-26 16:16:28,529
229
+ Results:
230
+ - F-score (micro) 0.9067
231
+ - F-score (macro) 0.6885
232
+ - Accuracy 0.8329
233
+
234
+ By class:
235
+ precision recall f1-score support
236
+
237
+ Unternehmen 0.8931 0.8797 0.8864 266
238
+ Auslagerung 0.8833 0.9116 0.8972 249
239
+ Ort 0.9565 0.9851 0.9706 134
240
+ Software 0.0000 0.0000 0.0000 0
241
+
242
+ micro avg 0.8998 0.9137 0.9067 649
243
+ macro avg 0.6832 0.6941 0.6885 649
244
+ weighted avg 0.9024 0.9137 0.9079 649
245
+
246
+ 2024-03-26 16:16:28,529 ----------------------------------------------------------------------------------------------------