Hugging Face's logo

stefan-it
/
flair-co-funer-german_dbmdz_bert_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
2
stefan-it commited on
Commit
4b4d2c4
•
1 Parent(s): 6fe76c0

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +244 -0
training.log ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-03-26 15:56:28,731 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 15:56:28,732 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 15:56:28,732 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 15:56:28,732 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 15:56:28,732 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 15:56:28,732 Train: 758 sentences
54
+ 2024-03-26 15:56:28,732 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 15:56:28,732 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 15:56:28,732 Training Params:
57
+ 2024-03-26 15:56:28,732 - learning_rate: "3e-05"
58
+ 2024-03-26 15:56:28,732 - mini_batch_size: "8"
59
+ 2024-03-26 15:56:28,732 - max_epochs: "10"
60
+ 2024-03-26 15:56:28,732 - shuffle: "True"
61
+ 2024-03-26 15:56:28,732 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 15:56:28,732 Plugins:
63
+ 2024-03-26 15:56:28,732 - TensorboardLogger
64
+ 2024-03-26 15:56:28,732 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 15:56:28,732 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 15:56:28,732 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 15:56:28,732 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 15:56:28,732 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 15:56:28,732 Computation:
70
+ 2024-03-26 15:56:28,732 - compute on device: cuda:0
71
+ 2024-03-26 15:56:28,732 - embedding storage: none
72
+ 2024-03-26 15:56:28,732 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 15:56:28,732 Model training base path: "flair-co-funer-german_dbmdz_bert_base-bs8-e10-lr3e-05-3"
74
+ 2024-03-26 15:56:28,732 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 15:56:28,732 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 15:56:28,732 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 15:56:30,097 epoch 1 - iter 9/95 - loss 3.40897965 - time (sec): 1.36 - samples/sec: 2337.45 - lr: 0.000003 - momentum: 0.000000
78
+ 2024-03-26 15:56:31,929 epoch 1 - iter 18/95 - loss 3.31388316 - time (sec): 3.20 - samples/sec: 1975.60 - lr: 0.000005 - momentum: 0.000000
79
+ 2024-03-26 15:56:33,863 epoch 1 - iter 27/95 - loss 3.13512952 - time (sec): 5.13 - samples/sec: 1925.69 - lr: 0.000008 - momentum: 0.000000
80
+ 2024-03-26 15:56:35,243 epoch 1 - iter 36/95 - loss 2.90060599 - time (sec): 6.51 - samples/sec: 1943.33 - lr: 0.000011 - momentum: 0.000000
81
+ 2024-03-26 15:56:37,153 epoch 1 - iter 45/95 - loss 2.72060347 - time (sec): 8.42 - samples/sec: 1926.55 - lr: 0.000014 - momentum: 0.000000
82
+ 2024-03-26 15:56:38,514 epoch 1 - iter 54/95 - loss 2.57144999 - time (sec): 9.78 - samples/sec: 1951.41 - lr: 0.000017 - momentum: 0.000000
83
+ 2024-03-26 15:56:39,775 epoch 1 - iter 63/95 - loss 2.43257036 - time (sec): 11.04 - samples/sec: 1977.54 - lr: 0.000020 - momentum: 0.000000
84
+ 2024-03-26 15:56:41,727 epoch 1 - iter 72/95 - loss 2.26703987 - time (sec): 12.99 - samples/sec: 1963.85 - lr: 0.000022 - momentum: 0.000000
85
+ 2024-03-26 15:56:43,715 epoch 1 - iter 81/95 - loss 2.11127819 - time (sec): 14.98 - samples/sec: 1948.56 - lr: 0.000025 - momentum: 0.000000
86
+ 2024-03-26 15:56:45,258 epoch 1 - iter 90/95 - loss 1.98170918 - time (sec): 16.53 - samples/sec: 1965.61 - lr: 0.000028 - momentum: 0.000000
87
+ 2024-03-26 15:56:46,305 ----------------------------------------------------------------------------------------------------
88
+ 2024-03-26 15:56:46,305 EPOCH 1 done: loss 1.9038 - lr: 0.000028
89
+ 2024-03-26 15:56:47,108 DEV : loss 0.5299527049064636 - f1-score (micro avg) 0.6036
90
+ 2024-03-26 15:56:47,110 saving best model
91
+ 2024-03-26 15:56:47,370 ----------------------------------------------------------------------------------------------------
92
+ 2024-03-26 15:56:48,729 epoch 2 - iter 9/95 - loss 0.66224744 - time (sec): 1.36 - samples/sec: 2017.66 - lr: 0.000030 - momentum: 0.000000
93
+ 2024-03-26 15:56:50,558 epoch 2 - iter 18/95 - loss 0.53988141 - time (sec): 3.19 - samples/sec: 1916.77 - lr: 0.000029 - momentum: 0.000000
94
+ 2024-03-26 15:56:51,733 epoch 2 - iter 27/95 - loss 0.51256267 - time (sec): 4.36 - samples/sec: 1966.97 - lr: 0.000029 - momentum: 0.000000
95
+ 2024-03-26 15:56:53,980 epoch 2 - iter 36/95 - loss 0.48754644 - time (sec): 6.61 - samples/sec: 1918.41 - lr: 0.000029 - momentum: 0.000000
96
+ 2024-03-26 15:56:55,914 epoch 2 - iter 45/95 - loss 0.47258088 - time (sec): 8.54 - samples/sec: 1924.86 - lr: 0.000028 - momentum: 0.000000
97
+ 2024-03-26 15:56:58,060 epoch 2 - iter 54/95 - loss 0.45416617 - time (sec): 10.69 - samples/sec: 1897.89 - lr: 0.000028 - momentum: 0.000000
98
+ 2024-03-26 15:57:00,064 epoch 2 - iter 63/95 - loss 0.43873715 - time (sec): 12.69 - samples/sec: 1851.93 - lr: 0.000028 - momentum: 0.000000
99
+ 2024-03-26 15:57:01,581 epoch 2 - iter 72/95 - loss 0.44036924 - time (sec): 14.21 - samples/sec: 1858.93 - lr: 0.000028 - momentum: 0.000000
100
+ 2024-03-26 15:57:03,021 epoch 2 - iter 81/95 - loss 0.44477795 - time (sec): 15.65 - samples/sec: 1882.26 - lr: 0.000027 - momentum: 0.000000
101
+ 2024-03-26 15:57:05,231 epoch 2 - iter 90/95 - loss 0.43018505 - time (sec): 17.86 - samples/sec: 1857.15 - lr: 0.000027 - momentum: 0.000000
102
+ 2024-03-26 15:57:05,871 ----------------------------------------------------------------------------------------------------
103
+ 2024-03-26 15:57:05,871 EPOCH 2 done: loss 0.4259 - lr: 0.000027
104
+ 2024-03-26 15:57:06,762 DEV : loss 0.26071757078170776 - f1-score (micro avg) 0.8174
105
+ 2024-03-26 15:57:06,763 saving best model
106
+ 2024-03-26 15:57:07,209 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 15:57:08,832 epoch 3 - iter 9/95 - loss 0.22653679 - time (sec): 1.62 - samples/sec: 1843.04 - lr: 0.000026 - momentum: 0.000000
108
+ 2024-03-26 15:57:10,615 epoch 3 - iter 18/95 - loss 0.22165536 - time (sec): 3.40 - samples/sec: 1860.04 - lr: 0.000026 - momentum: 0.000000
109
+ 2024-03-26 15:57:11,803 epoch 3 - iter 27/95 - loss 0.24382814 - time (sec): 4.59 - samples/sec: 2034.94 - lr: 0.000026 - momentum: 0.000000
110
+ 2024-03-26 15:57:13,353 epoch 3 - iter 36/95 - loss 0.23044148 - time (sec): 6.14 - samples/sec: 2022.92 - lr: 0.000025 - momentum: 0.000000
111
+ 2024-03-26 15:57:14,754 epoch 3 - iter 45/95 - loss 0.23407852 - time (sec): 7.54 - samples/sec: 2032.17 - lr: 0.000025 - momentum: 0.000000
112
+ 2024-03-26 15:57:16,740 epoch 3 - iter 54/95 - loss 0.22455760 - time (sec): 9.53 - samples/sec: 1983.54 - lr: 0.000025 - momentum: 0.000000
113
+ 2024-03-26 15:57:18,733 epoch 3 - iter 63/95 - loss 0.22224367 - time (sec): 11.52 - samples/sec: 1932.29 - lr: 0.000025 - momentum: 0.000000
114
+ 2024-03-26 15:57:20,573 epoch 3 - iter 72/95 - loss 0.22558822 - time (sec): 13.36 - samples/sec: 1914.35 - lr: 0.000024 - momentum: 0.000000
115
+ 2024-03-26 15:57:22,569 epoch 3 - iter 81/95 - loss 0.21667138 - time (sec): 15.36 - samples/sec: 1887.88 - lr: 0.000024 - momentum: 0.000000
116
+ 2024-03-26 15:57:24,529 epoch 3 - iter 90/95 - loss 0.22596741 - time (sec): 17.32 - samples/sec: 1888.10 - lr: 0.000024 - momentum: 0.000000
117
+ 2024-03-26 15:57:25,615 ----------------------------------------------------------------------------------------------------
118
+ 2024-03-26 15:57:25,615 EPOCH 3 done: loss 0.2201 - lr: 0.000024
119
+ 2024-03-26 15:57:26,503 DEV : loss 0.1964208483695984 - f1-score (micro avg) 0.8634
120
+ 2024-03-26 15:57:26,504 saving best model
121
+ 2024-03-26 15:57:26,934 ----------------------------------------------------------------------------------------------------
122
+ 2024-03-26 15:57:28,224 epoch 4 - iter 9/95 - loss 0.16679719 - time (sec): 1.29 - samples/sec: 2154.19 - lr: 0.000023 - momentum: 0.000000
123
+ 2024-03-26 15:57:30,061 epoch 4 - iter 18/95 - loss 0.14830405 - time (sec): 3.12 - samples/sec: 1966.91 - lr: 0.000023 - momentum: 0.000000
124
+ 2024-03-26 15:57:31,987 epoch 4 - iter 27/95 - loss 0.14763405 - time (sec): 5.05 - samples/sec: 1911.65 - lr: 0.000022 - momentum: 0.000000
125
+ 2024-03-26 15:57:33,468 epoch 4 - iter 36/95 - loss 0.15489395 - time (sec): 6.53 - samples/sec: 1920.27 - lr: 0.000022 - momentum: 0.000000
126
+ 2024-03-26 15:57:35,904 epoch 4 - iter 45/95 - loss 0.14705872 - time (sec): 8.97 - samples/sec: 1842.61 - lr: 0.000022 - momentum: 0.000000
127
+ 2024-03-26 15:57:37,763 epoch 4 - iter 54/95 - loss 0.14253798 - time (sec): 10.83 - samples/sec: 1822.80 - lr: 0.000022 - momentum: 0.000000
128
+ 2024-03-26 15:57:39,702 epoch 4 - iter 63/95 - loss 0.13908137 - time (sec): 12.77 - samples/sec: 1801.41 - lr: 0.000021 - momentum: 0.000000
129
+ 2024-03-26 15:57:41,583 epoch 4 - iter 72/95 - loss 0.14419298 - time (sec): 14.65 - samples/sec: 1816.43 - lr: 0.000021 - momentum: 0.000000
130
+ 2024-03-26 15:57:43,605 epoch 4 - iter 81/95 - loss 0.15288539 - time (sec): 16.67 - samples/sec: 1813.74 - lr: 0.000021 - momentum: 0.000000
131
+ 2024-03-26 15:57:44,587 epoch 4 - iter 90/95 - loss 0.15087821 - time (sec): 17.65 - samples/sec: 1852.76 - lr: 0.000020 - momentum: 0.000000
132
+ 2024-03-26 15:57:45,693 ----------------------------------------------------------------------------------------------------
133
+ 2024-03-26 15:57:45,693 EPOCH 4 done: loss 0.1500 - lr: 0.000020
134
+ 2024-03-26 15:57:46,582 DEV : loss 0.17337767779827118 - f1-score (micro avg) 0.9175
135
+ 2024-03-26 15:57:46,583 saving best model
136
+ 2024-03-26 15:57:47,000 ----------------------------------------------------------------------------------------------------
137
+ 2024-03-26 15:57:48,882 epoch 5 - iter 9/95 - loss 0.10880030 - time (sec): 1.88 - samples/sec: 1826.69 - lr: 0.000020 - momentum: 0.000000
138
+ 2024-03-26 15:57:50,305 epoch 5 - iter 18/95 - loss 0.10527757 - time (sec): 3.30 - samples/sec: 1894.02 - lr: 0.000019 - momentum: 0.000000
139
+ 2024-03-26 15:57:51,662 epoch 5 - iter 27/95 - loss 0.11148545 - time (sec): 4.66 - samples/sec: 1937.47 - lr: 0.000019 - momentum: 0.000000
140
+ 2024-03-26 15:57:53,538 epoch 5 - iter 36/95 - loss 0.11019626 - time (sec): 6.54 - samples/sec: 1877.44 - lr: 0.000019 - momentum: 0.000000
141
+ 2024-03-26 15:57:55,752 epoch 5 - iter 45/95 - loss 0.11013483 - time (sec): 8.75 - samples/sec: 1860.38 - lr: 0.000019 - momentum: 0.000000
142
+ 2024-03-26 15:57:58,184 epoch 5 - iter 54/95 - loss 0.10479061 - time (sec): 11.18 - samples/sec: 1816.22 - lr: 0.000018 - momentum: 0.000000
143
+ 2024-03-26 15:57:59,845 epoch 5 - iter 63/95 - loss 0.10233405 - time (sec): 12.84 - samples/sec: 1808.75 - lr: 0.000018 - momentum: 0.000000
144
+ 2024-03-26 15:58:01,611 epoch 5 - iter 72/95 - loss 0.10005286 - time (sec): 14.61 - samples/sec: 1810.08 - lr: 0.000018 - momentum: 0.000000
145
+ 2024-03-26 15:58:03,809 epoch 5 - iter 81/95 - loss 0.10086012 - time (sec): 16.81 - samples/sec: 1795.16 - lr: 0.000017 - momentum: 0.000000
146
+ 2024-03-26 15:58:05,197 epoch 5 - iter 90/95 - loss 0.10258345 - time (sec): 18.20 - samples/sec: 1811.34 - lr: 0.000017 - momentum: 0.000000
147
+ 2024-03-26 15:58:05,963 ----------------------------------------------------------------------------------------------------
148
+ 2024-03-26 15:58:05,963 EPOCH 5 done: loss 0.1007 - lr: 0.000017
149
+ 2024-03-26 15:58:06,877 DEV : loss 0.18982082605361938 - f1-score (micro avg) 0.9014
150
+ 2024-03-26 15:58:06,879 ----------------------------------------------------------------------------------------------------
151
+ 2024-03-26 15:58:08,817 epoch 6 - iter 9/95 - loss 0.08028524 - time (sec): 1.94 - samples/sec: 1800.97 - lr: 0.000016 - momentum: 0.000000
152
+ 2024-03-26 15:58:10,371 epoch 6 - iter 18/95 - loss 0.07532962 - time (sec): 3.49 - samples/sec: 1821.86 - lr: 0.000016 - momentum: 0.000000
153
+ 2024-03-26 15:58:12,275 epoch 6 - iter 27/95 - loss 0.07164228 - time (sec): 5.39 - samples/sec: 1832.84 - lr: 0.000016 - momentum: 0.000000
154
+ 2024-03-26 15:58:13,840 epoch 6 - iter 36/95 - loss 0.07300866 - time (sec): 6.96 - samples/sec: 1832.15 - lr: 0.000016 - momentum: 0.000000
155
+ 2024-03-26 15:58:15,292 epoch 6 - iter 45/95 - loss 0.07241842 - time (sec): 8.41 - samples/sec: 1869.29 - lr: 0.000015 - momentum: 0.000000
156
+ 2024-03-26 15:58:16,740 epoch 6 - iter 54/95 - loss 0.06820202 - time (sec): 9.86 - samples/sec: 1867.89 - lr: 0.000015 - momentum: 0.000000
157
+ 2024-03-26 15:58:18,021 epoch 6 - iter 63/95 - loss 0.06931340 - time (sec): 11.14 - samples/sec: 1929.82 - lr: 0.000015 - momentum: 0.000000
158
+ 2024-03-26 15:58:20,266 epoch 6 - iter 72/95 - loss 0.07841376 - time (sec): 13.39 - samples/sec: 1897.00 - lr: 0.000014 - momentum: 0.000000
159
+ 2024-03-26 15:58:21,841 epoch 6 - iter 81/95 - loss 0.07719176 - time (sec): 14.96 - samples/sec: 1915.32 - lr: 0.000014 - momentum: 0.000000
160
+ 2024-03-26 15:58:23,542 epoch 6 - iter 90/95 - loss 0.07990913 - time (sec): 16.66 - samples/sec: 1934.39 - lr: 0.000014 - momentum: 0.000000
161
+ 2024-03-26 15:58:24,803 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 15:58:24,803 EPOCH 6 done: loss 0.0806 - lr: 0.000014
163
+ 2024-03-26 15:58:25,702 DEV : loss 0.1600886434316635 - f1-score (micro avg) 0.924
164
+ 2024-03-26 15:58:25,703 saving best model
165
+ 2024-03-26 15:58:26,144 ----------------------------------------------------------------------------------------------------
166
+ 2024-03-26 15:58:28,029 epoch 7 - iter 9/95 - loss 0.06613833 - time (sec): 1.88 - samples/sec: 1686.24 - lr: 0.000013 - momentum: 0.000000
167
+ 2024-03-26 15:58:30,062 epoch 7 - iter 18/95 - loss 0.04739985 - time (sec): 3.92 - samples/sec: 1674.05 - lr: 0.000013 - momentum: 0.000000
168
+ 2024-03-26 15:58:31,594 epoch 7 - iter 27/95 - loss 0.04411594 - time (sec): 5.45 - samples/sec: 1795.59 - lr: 0.000013 - momentum: 0.000000
169
+ 2024-03-26 15:58:33,544 epoch 7 - iter 36/95 - loss 0.04328564 - time (sec): 7.40 - samples/sec: 1781.17 - lr: 0.000012 - momentum: 0.000000
170
+ 2024-03-26 15:58:35,924 epoch 7 - iter 45/95 - loss 0.04655521 - time (sec): 9.78 - samples/sec: 1773.48 - lr: 0.000012 - momentum: 0.000000
171
+ 2024-03-26 15:58:37,435 epoch 7 - iter 54/95 - loss 0.04811539 - time (sec): 11.29 - samples/sec: 1781.91 - lr: 0.000012 - momentum: 0.000000
172
+ 2024-03-26 15:58:39,611 epoch 7 - iter 63/95 - loss 0.05314137 - time (sec): 13.47 - samples/sec: 1788.51 - lr: 0.000011 - momentum: 0.000000
173
+ 2024-03-26 15:58:41,395 epoch 7 - iter 72/95 - loss 0.05860180 - time (sec): 15.25 - samples/sec: 1795.17 - lr: 0.000011 - momentum: 0.000000
174
+ 2024-03-26 15:58:42,812 epoch 7 - iter 81/95 - loss 0.05550674 - time (sec): 16.67 - samples/sec: 1807.44 - lr: 0.000011 - momentum: 0.000000
175
+ 2024-03-26 15:58:44,785 epoch 7 - iter 90/95 - loss 0.05925639 - time (sec): 18.64 - samples/sec: 1787.13 - lr: 0.000010 - momentum: 0.000000
176
+ 2024-03-26 15:58:45,269 ----------------------------------------------------------------------------------------------------
177
+ 2024-03-26 15:58:45,269 EPOCH 7 done: loss 0.0597 - lr: 0.000010
178
+ 2024-03-26 15:58:46,162 DEV : loss 0.17188522219657898 - f1-score (micro avg) 0.9241
179
+ 2024-03-26 15:58:46,163 saving best model
180
+ 2024-03-26 15:58:46,602 ----------------------------------------------------------------------------------------------------
181
+ 2024-03-26 15:58:48,476 epoch 8 - iter 9/95 - loss 0.03912649 - time (sec): 1.87 - samples/sec: 1712.62 - lr: 0.000010 - momentum: 0.000000
182
+ 2024-03-26 15:58:50,957 epoch 8 - iter 18/95 - loss 0.03142629 - time (sec): 4.35 - samples/sec: 1701.28 - lr: 0.000010 - momentum: 0.000000
183
+ 2024-03-26 15:58:52,712 epoch 8 - iter 27/95 - loss 0.02965443 - time (sec): 6.11 - samples/sec: 1741.95 - lr: 0.000009 - momentum: 0.000000
184
+ 2024-03-26 15:58:54,254 epoch 8 - iter 36/95 - loss 0.03024610 - time (sec): 7.65 - samples/sec: 1732.94 - lr: 0.000009 - momentum: 0.000000
185
+ 2024-03-26 15:58:55,761 epoch 8 - iter 45/95 - loss 0.02925025 - time (sec): 9.16 - samples/sec: 1763.56 - lr: 0.000009 - momentum: 0.000000
186
+ 2024-03-26 15:58:57,421 epoch 8 - iter 54/95 - loss 0.03157322 - time (sec): 10.82 - samples/sec: 1783.17 - lr: 0.000008 - momentum: 0.000000
187
+ 2024-03-26 15:58:59,609 epoch 8 - iter 63/95 - loss 0.03982388 - time (sec): 13.01 - samples/sec: 1779.39 - lr: 0.000008 - momentum: 0.000000
188
+ 2024-03-26 15:59:01,852 epoch 8 - iter 72/95 - loss 0.04270864 - time (sec): 15.25 - samples/sec: 1760.01 - lr: 0.000008 - momentum: 0.000000
189
+ 2024-03-26 15:59:03,581 epoch 8 - iter 81/95 - loss 0.04809513 - time (sec): 16.98 - samples/sec: 1754.53 - lr: 0.000007 - momentum: 0.000000
190
+ 2024-03-26 15:59:04,872 epoch 8 - iter 90/95 - loss 0.04825491 - time (sec): 18.27 - samples/sec: 1797.23 - lr: 0.000007 - momentum: 0.000000
191
+ 2024-03-26 15:59:05,769 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 15:59:05,769 EPOCH 8 done: loss 0.0470 - lr: 0.000007
193
+ 2024-03-26 15:59:06,667 DEV : loss 0.18762652575969696 - f1-score (micro avg) 0.9151
194
+ 2024-03-26 15:59:06,668 ----------------------------------------------------------------------------------------------------
195
+ 2024-03-26 15:59:08,646 epoch 9 - iter 9/95 - loss 0.02786068 - time (sec): 1.98 - samples/sec: 1782.79 - lr: 0.000007 - momentum: 0.000000
196
+ 2024-03-26 15:59:10,364 epoch 9 - iter 18/95 - loss 0.03817157 - time (sec): 3.70 - samples/sec: 1810.99 - lr: 0.000006 - momentum: 0.000000
197
+ 2024-03-26 15:59:12,234 epoch 9 - iter 27/95 - loss 0.03881680 - time (sec): 5.57 - samples/sec: 1835.48 - lr: 0.000006 - momentum: 0.000000
198
+ 2024-03-26 15:59:14,086 epoch 9 - iter 36/95 - loss 0.03703367 - time (sec): 7.42 - samples/sec: 1830.87 - lr: 0.000006 - momentum: 0.000000
199
+ 2024-03-26 15:59:16,342 epoch 9 - iter 45/95 - loss 0.03362287 - time (sec): 9.67 - samples/sec: 1752.19 - lr: 0.000005 - momentum: 0.000000
200
+ 2024-03-26 15:59:18,263 epoch 9 - iter 54/95 - loss 0.03626384 - time (sec): 11.59 - samples/sec: 1741.11 - lr: 0.000005 - momentum: 0.000000
201
+ 2024-03-26 15:59:20,138 epoch 9 - iter 63/95 - loss 0.03563241 - time (sec): 13.47 - samples/sec: 1752.97 - lr: 0.000005 - momentum: 0.000000
202
+ 2024-03-26 15:59:22,027 epoch 9 - iter 72/95 - loss 0.03537384 - time (sec): 15.36 - samples/sec: 1754.66 - lr: 0.000004 - momentum: 0.000000
203
+ 2024-03-26 15:59:23,268 epoch 9 - iter 81/95 - loss 0.03717623 - time (sec): 16.60 - samples/sec: 1778.52 - lr: 0.000004 - momentum: 0.000000
204
+ 2024-03-26 15:59:24,671 epoch 9 - iter 90/95 - loss 0.04047492 - time (sec): 18.00 - samples/sec: 1800.27 - lr: 0.000004 - momentum: 0.000000
205
+ 2024-03-26 15:59:25,618 ----------------------------------------------------------------------------------------------------
206
+ 2024-03-26 15:59:25,618 EPOCH 9 done: loss 0.0402 - lr: 0.000004
207
+ 2024-03-26 15:59:26,519 DEV : loss 0.1871178150177002 - f1-score (micro avg) 0.9299
208
+ 2024-03-26 15:59:26,520 saving best model
209
+ 2024-03-26 15:59:27,006 ----------------------------------------------------------------------------------------------------
210
+ 2024-03-26 15:59:29,148 epoch 10 - iter 9/95 - loss 0.01758337 - time (sec): 2.14 - samples/sec: 1781.63 - lr: 0.000003 - momentum: 0.000000
211
+ 2024-03-26 15:59:30,409 epoch 10 - iter 18/95 - loss 0.01823423 - time (sec): 3.40 - samples/sec: 1903.69 - lr: 0.000003 - momentum: 0.000000
212
+ 2024-03-26 15:59:31,722 epoch 10 - iter 27/95 - loss 0.04357034 - time (sec): 4.71 - samples/sec: 2011.87 - lr: 0.000003 - momentum: 0.000000
213
+ 2024-03-26 15:59:33,077 epoch 10 - iter 36/95 - loss 0.03985547 - time (sec): 6.07 - samples/sec: 2032.60 - lr: 0.000002 - momentum: 0.000000
214
+ 2024-03-26 15:59:34,946 epoch 10 - iter 45/95 - loss 0.03388188 - time (sec): 7.94 - samples/sec: 2006.10 - lr: 0.000002 - momentum: 0.000000
215
+ 2024-03-26 15:59:36,525 epoch 10 - iter 54/95 - loss 0.03360974 - time (sec): 9.52 - samples/sec: 1991.96 - lr: 0.000002 - momentum: 0.000000
216
+ 2024-03-26 15:59:39,048 epoch 10 - iter 63/95 - loss 0.03430991 - time (sec): 12.04 - samples/sec: 1909.64 - lr: 0.000001 - momentum: 0.000000
217
+ 2024-03-26 15:59:40,337 epoch 10 - iter 72/95 - loss 0.03306366 - time (sec): 13.33 - samples/sec: 1913.17 - lr: 0.000001 - momentum: 0.000000
218
+ 2024-03-26 15:59:42,678 epoch 10 - iter 81/95 - loss 0.03085863 - time (sec): 15.67 - samples/sec: 1858.94 - lr: 0.000001 - momentum: 0.000000
219
+ 2024-03-26 15:59:44,897 epoch 10 - iter 90/95 - loss 0.03301571 - time (sec): 17.89 - samples/sec: 1838.40 - lr: 0.000000 - momentum: 0.000000
220
+ 2024-03-26 15:59:45,957 ----------------------------------------------------------------------------------------------------
221
+ 2024-03-26 15:59:45,957 EPOCH 10 done: loss 0.0338 - lr: 0.000000
222
+ 2024-03-26 15:59:46,860 DEV : loss 0.18731436133384705 - f1-score (micro avg) 0.9295
223
+ 2024-03-26 15:59:47,124 ----------------------------------------------------------------------------------------------------
224
+ 2024-03-26 15:59:47,125 Loading model from best epoch ...
225
+ 2024-03-26 15:59:47,973 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
226
+ 2024-03-26 15:59:48,738
227
+ Results:
228
+ - F-score (micro) 0.9152
229
+ - F-score (macro) 0.6943
230
+ - Accuracy 0.846
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ Unternehmen 0.9151 0.8910 0.9029 266
236
+ Auslagerung 0.8779 0.9237 0.9002 249
237
+ Ort 0.9635 0.9851 0.9742 134
238
+ Software 0.0000 0.0000 0.0000 0
239
+
240
+ micro avg 0.9076 0.9230 0.9152 649
241
+ macro avg 0.6891 0.6999 0.6943 649
242
+ weighted avg 0.9108 0.9230 0.9166 649
243
+
244
+ 2024-03-26 15:59:48,738 ----------------------------------------------------------------------------------------------------