Hugging Face's logo

stefan-it
/
flair-co-funer-german_dbmdz_bert_base-bs8-e10-lr5e-05-1

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
0440ad7
•
1 Parent(s): 4ae14da

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +243 -0
training.log ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-03-26 15:27:27,825 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 15:27:27,825 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 15:27:27,826 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 15:27:27,826 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 15:27:27,826 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 15:27:27,826 Train: 758 sentences
54
+ 2024-03-26 15:27:27,826 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 15:27:27,826 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 15:27:27,826 Training Params:
57
+ 2024-03-26 15:27:27,826 - learning_rate: "5e-05"
58
+ 2024-03-26 15:27:27,826 - mini_batch_size: "8"
59
+ 2024-03-26 15:27:27,826 - max_epochs: "10"
60
+ 2024-03-26 15:27:27,826 - shuffle: "True"
61
+ 2024-03-26 15:27:27,826 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 15:27:27,826 Plugins:
63
+ 2024-03-26 15:27:27,826 - TensorboardLogger
64
+ 2024-03-26 15:27:27,826 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 15:27:27,826 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 15:27:27,826 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 15:27:27,826 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 15:27:27,826 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 15:27:27,826 Computation:
70
+ 2024-03-26 15:27:27,826 - compute on device: cuda:0
71
+ 2024-03-26 15:27:27,826 - embedding storage: none
72
+ 2024-03-26 15:27:27,826 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 15:27:27,826 Model training base path: "flair-co-funer-german_dbmdz_bert_base-bs8-e10-lr5e-05-1"
74
+ 2024-03-26 15:27:27,826 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 15:27:27,826 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 15:27:27,826 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 15:27:29,419 epoch 1 - iter 9/95 - loss 3.13070860 - time (sec): 1.59 - samples/sec: 1932.69 - lr: 0.000004 - momentum: 0.000000
78
+ 2024-03-26 15:27:30,954 epoch 1 - iter 18/95 - loss 2.95822820 - time (sec): 3.13 - samples/sec: 1998.62 - lr: 0.000009 - momentum: 0.000000
79
+ 2024-03-26 15:27:33,348 epoch 1 - iter 27/95 - loss 2.68831949 - time (sec): 5.52 - samples/sec: 1854.35 - lr: 0.000014 - momentum: 0.000000
80
+ 2024-03-26 15:27:35,580 epoch 1 - iter 36/95 - loss 2.46404671 - time (sec): 7.75 - samples/sec: 1803.09 - lr: 0.000018 - momentum: 0.000000
81
+ 2024-03-26 15:27:37,482 epoch 1 - iter 45/95 - loss 2.27412112 - time (sec): 9.66 - samples/sec: 1808.63 - lr: 0.000023 - momentum: 0.000000
82
+ 2024-03-26 15:27:38,713 epoch 1 - iter 54/95 - loss 2.12463673 - time (sec): 10.89 - samples/sec: 1849.95 - lr: 0.000028 - momentum: 0.000000
83
+ 2024-03-26 15:27:40,436 epoch 1 - iter 63/95 - loss 1.97163936 - time (sec): 12.61 - samples/sec: 1844.97 - lr: 0.000033 - momentum: 0.000000
84
+ 2024-03-26 15:27:41,737 epoch 1 - iter 72/95 - loss 1.85271444 - time (sec): 13.91 - samples/sec: 1872.62 - lr: 0.000037 - momentum: 0.000000
85
+ 2024-03-26 15:27:43,740 epoch 1 - iter 81/95 - loss 1.71149458 - time (sec): 15.91 - samples/sec: 1861.16 - lr: 0.000042 - momentum: 0.000000
86
+ 2024-03-26 15:27:45,067 epoch 1 - iter 90/95 - loss 1.61167649 - time (sec): 17.24 - samples/sec: 1881.62 - lr: 0.000047 - momentum: 0.000000
87
+ 2024-03-26 15:27:46,289 ----------------------------------------------------------------------------------------------------
88
+ 2024-03-26 15:27:46,289 EPOCH 1 done: loss 1.5372 - lr: 0.000047
89
+ 2024-03-26 15:27:47,216 DEV : loss 0.4110299050807953 - f1-score (micro avg) 0.7131
90
+ 2024-03-26 15:27:47,217 saving best model
91
+ 2024-03-26 15:27:47,503 ----------------------------------------------------------------------------------------------------
92
+ 2024-03-26 15:27:49,568 epoch 2 - iter 9/95 - loss 0.36243150 - time (sec): 2.06 - samples/sec: 1788.95 - lr: 0.000050 - momentum: 0.000000
93
+ 2024-03-26 15:27:51,260 epoch 2 - iter 18/95 - loss 0.39160173 - time (sec): 3.76 - samples/sec: 1931.52 - lr: 0.000049 - momentum: 0.000000
94
+ 2024-03-26 15:27:53,081 epoch 2 - iter 27/95 - loss 0.37985520 - time (sec): 5.58 - samples/sec: 1848.37 - lr: 0.000048 - momentum: 0.000000
95
+ 2024-03-26 15:27:54,860 epoch 2 - iter 36/95 - loss 0.36638865 - time (sec): 7.36 - samples/sec: 1817.59 - lr: 0.000048 - momentum: 0.000000
96
+ 2024-03-26 15:27:56,767 epoch 2 - iter 45/95 - loss 0.34692669 - time (sec): 9.26 - samples/sec: 1828.18 - lr: 0.000047 - momentum: 0.000000
97
+ 2024-03-26 15:27:58,974 epoch 2 - iter 54/95 - loss 0.32389617 - time (sec): 11.47 - samples/sec: 1800.04 - lr: 0.000047 - momentum: 0.000000
98
+ 2024-03-26 15:28:00,320 epoch 2 - iter 63/95 - loss 0.32907154 - time (sec): 12.82 - samples/sec: 1838.02 - lr: 0.000046 - momentum: 0.000000
99
+ 2024-03-26 15:28:01,653 epoch 2 - iter 72/95 - loss 0.32309260 - time (sec): 14.15 - samples/sec: 1869.63 - lr: 0.000046 - momentum: 0.000000
100
+ 2024-03-26 15:28:03,468 epoch 2 - iter 81/95 - loss 0.31443661 - time (sec): 15.96 - samples/sec: 1854.18 - lr: 0.000045 - momentum: 0.000000
101
+ 2024-03-26 15:28:05,122 epoch 2 - iter 90/95 - loss 0.30978395 - time (sec): 17.62 - samples/sec: 1852.35 - lr: 0.000045 - momentum: 0.000000
102
+ 2024-03-26 15:28:06,072 ----------------------------------------------------------------------------------------------------
103
+ 2024-03-26 15:28:06,072 EPOCH 2 done: loss 0.3041 - lr: 0.000045
104
+ 2024-03-26 15:28:06,980 DEV : loss 0.2726188600063324 - f1-score (micro avg) 0.8589
105
+ 2024-03-26 15:28:06,983 saving best model
106
+ 2024-03-26 15:28:07,435 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 15:28:09,388 epoch 3 - iter 9/95 - loss 0.27963646 - time (sec): 1.95 - samples/sec: 1719.52 - lr: 0.000044 - momentum: 0.000000
108
+ 2024-03-26 15:28:11,340 epoch 3 - iter 18/95 - loss 0.23117903 - time (sec): 3.90 - samples/sec: 1723.69 - lr: 0.000043 - momentum: 0.000000
109
+ 2024-03-26 15:28:12,698 epoch 3 - iter 27/95 - loss 0.21432801 - time (sec): 5.26 - samples/sec: 1817.80 - lr: 0.000043 - momentum: 0.000000
110
+ 2024-03-26 15:28:15,180 epoch 3 - iter 36/95 - loss 0.20348653 - time (sec): 7.74 - samples/sec: 1745.83 - lr: 0.000042 - momentum: 0.000000
111
+ 2024-03-26 15:28:17,410 epoch 3 - iter 45/95 - loss 0.19347259 - time (sec): 9.97 - samples/sec: 1779.90 - lr: 0.000042 - momentum: 0.000000
112
+ 2024-03-26 15:28:18,594 epoch 3 - iter 54/95 - loss 0.19292353 - time (sec): 11.16 - samples/sec: 1836.39 - lr: 0.000041 - momentum: 0.000000
113
+ 2024-03-26 15:28:20,520 epoch 3 - iter 63/95 - loss 0.18736924 - time (sec): 13.08 - samples/sec: 1820.60 - lr: 0.000041 - momentum: 0.000000
114
+ 2024-03-26 15:28:22,146 epoch 3 - iter 72/95 - loss 0.17704759 - time (sec): 14.71 - samples/sec: 1825.80 - lr: 0.000040 - momentum: 0.000000
115
+ 2024-03-26 15:28:23,897 epoch 3 - iter 81/95 - loss 0.18033371 - time (sec): 16.46 - samples/sec: 1817.25 - lr: 0.000040 - momentum: 0.000000
116
+ 2024-03-26 15:28:26,084 epoch 3 - iter 90/95 - loss 0.17298046 - time (sec): 18.65 - samples/sec: 1786.35 - lr: 0.000039 - momentum: 0.000000
117
+ 2024-03-26 15:28:26,562 ----------------------------------------------------------------------------------------------------
118
+ 2024-03-26 15:28:26,562 EPOCH 3 done: loss 0.1725 - lr: 0.000039
119
+ 2024-03-26 15:28:27,491 DEV : loss 0.22025352716445923 - f1-score (micro avg) 0.8935
120
+ 2024-03-26 15:28:27,493 saving best model
121
+ 2024-03-26 15:28:27,948 ----------------------------------------------------------------------------------------------------
122
+ 2024-03-26 15:28:29,557 epoch 4 - iter 9/95 - loss 0.14092195 - time (sec): 1.61 - samples/sec: 2004.45 - lr: 0.000039 - momentum: 0.000000
123
+ 2024-03-26 15:28:31,585 epoch 4 - iter 18/95 - loss 0.12653179 - time (sec): 3.63 - samples/sec: 1774.44 - lr: 0.000038 - momentum: 0.000000
124
+ 2024-03-26 15:28:33,358 epoch 4 - iter 27/95 - loss 0.12699223 - time (sec): 5.41 - samples/sec: 1801.77 - lr: 0.000037 - momentum: 0.000000
125
+ 2024-03-26 15:28:35,913 epoch 4 - iter 36/95 - loss 0.10548739 - time (sec): 7.96 - samples/sec: 1730.39 - lr: 0.000037 - momentum: 0.000000
126
+ 2024-03-26 15:28:37,595 epoch 4 - iter 45/95 - loss 0.11251881 - time (sec): 9.64 - samples/sec: 1750.56 - lr: 0.000036 - momentum: 0.000000
127
+ 2024-03-26 15:28:39,146 epoch 4 - iter 54/95 - loss 0.11452554 - time (sec): 11.20 - samples/sec: 1801.59 - lr: 0.000036 - momentum: 0.000000
128
+ 2024-03-26 15:28:41,003 epoch 4 - iter 63/95 - loss 0.11777649 - time (sec): 13.05 - samples/sec: 1823.81 - lr: 0.000035 - momentum: 0.000000
129
+ 2024-03-26 15:28:42,290 epoch 4 - iter 72/95 - loss 0.11862434 - time (sec): 14.34 - samples/sec: 1852.95 - lr: 0.000035 - momentum: 0.000000
130
+ 2024-03-26 15:28:44,007 epoch 4 - iter 81/95 - loss 0.11757033 - time (sec): 16.06 - samples/sec: 1843.02 - lr: 0.000034 - momentum: 0.000000
131
+ 2024-03-26 15:28:45,515 epoch 4 - iter 90/95 - loss 0.11485727 - time (sec): 17.56 - samples/sec: 1862.55 - lr: 0.000034 - momentum: 0.000000
132
+ 2024-03-26 15:28:46,418 ----------------------------------------------------------------------------------------------------
133
+ 2024-03-26 15:28:46,418 EPOCH 4 done: loss 0.1144 - lr: 0.000034
134
+ 2024-03-26 15:28:47,349 DEV : loss 0.2242664098739624 - f1-score (micro avg) 0.8907
135
+ 2024-03-26 15:28:47,350 ----------------------------------------------------------------------------------------------------
136
+ 2024-03-26 15:28:49,014 epoch 5 - iter 9/95 - loss 0.07661688 - time (sec): 1.66 - samples/sec: 1902.20 - lr: 0.000033 - momentum: 0.000000
137
+ 2024-03-26 15:28:51,153 epoch 5 - iter 18/95 - loss 0.07915592 - time (sec): 3.80 - samples/sec: 1762.83 - lr: 0.000032 - momentum: 0.000000
138
+ 2024-03-26 15:28:52,711 epoch 5 - iter 27/95 - loss 0.07883660 - time (sec): 5.36 - samples/sec: 1809.37 - lr: 0.000032 - momentum: 0.000000
139
+ 2024-03-26 15:28:54,374 epoch 5 - iter 36/95 - loss 0.08005146 - time (sec): 7.02 - samples/sec: 1796.08 - lr: 0.000031 - momentum: 0.000000
140
+ 2024-03-26 15:28:56,044 epoch 5 - iter 45/95 - loss 0.09108018 - time (sec): 8.69 - samples/sec: 1845.23 - lr: 0.000031 - momentum: 0.000000
141
+ 2024-03-26 15:28:57,640 epoch 5 - iter 54/95 - loss 0.09556091 - time (sec): 10.29 - samples/sec: 1890.07 - lr: 0.000030 - momentum: 0.000000
142
+ 2024-03-26 15:28:59,478 epoch 5 - iter 63/95 - loss 0.09055561 - time (sec): 12.13 - samples/sec: 1868.04 - lr: 0.000030 - momentum: 0.000000
143
+ 2024-03-26 15:29:01,689 epoch 5 - iter 72/95 - loss 0.08392596 - time (sec): 14.34 - samples/sec: 1892.53 - lr: 0.000029 - momentum: 0.000000
144
+ 2024-03-26 15:29:02,930 epoch 5 - iter 81/95 - loss 0.08323894 - time (sec): 15.58 - samples/sec: 1911.38 - lr: 0.000029 - momentum: 0.000000
145
+ 2024-03-26 15:29:05,058 epoch 5 - iter 90/95 - loss 0.07969065 - time (sec): 17.71 - samples/sec: 1870.08 - lr: 0.000028 - momentum: 0.000000
146
+ 2024-03-26 15:29:05,679 ----------------------------------------------------------------------------------------------------
147
+ 2024-03-26 15:29:05,679 EPOCH 5 done: loss 0.0803 - lr: 0.000028
148
+ 2024-03-26 15:29:06,577 DEV : loss 0.21445128321647644 - f1-score (micro avg) 0.9126
149
+ 2024-03-26 15:29:06,578 saving best model
150
+ 2024-03-26 15:29:07,116 ----------------------------------------------------------------------------------------------------
151
+ 2024-03-26 15:29:08,678 epoch 6 - iter 9/95 - loss 0.03632379 - time (sec): 1.56 - samples/sec: 1852.05 - lr: 0.000027 - momentum: 0.000000
152
+ 2024-03-26 15:29:10,675 epoch 6 - iter 18/95 - loss 0.05141724 - time (sec): 3.56 - samples/sec: 1843.60 - lr: 0.000027 - momentum: 0.000000
153
+ 2024-03-26 15:29:12,349 epoch 6 - iter 27/95 - loss 0.05798526 - time (sec): 5.23 - samples/sec: 1878.69 - lr: 0.000026 - momentum: 0.000000
154
+ 2024-03-26 15:29:13,998 epoch 6 - iter 36/95 - loss 0.05669773 - time (sec): 6.88 - samples/sec: 1841.59 - lr: 0.000026 - momentum: 0.000000
155
+ 2024-03-26 15:29:15,588 epoch 6 - iter 45/95 - loss 0.06106147 - time (sec): 8.47 - samples/sec: 1856.42 - lr: 0.000025 - momentum: 0.000000
156
+ 2024-03-26 15:29:17,582 epoch 6 - iter 54/95 - loss 0.06318994 - time (sec): 10.46 - samples/sec: 1837.19 - lr: 0.000025 - momentum: 0.000000
157
+ 2024-03-26 15:29:19,166 epoch 6 - iter 63/95 - loss 0.06556589 - time (sec): 12.05 - samples/sec: 1834.67 - lr: 0.000024 - momentum: 0.000000
158
+ 2024-03-26 15:29:21,972 epoch 6 - iter 72/95 - loss 0.05957997 - time (sec): 14.85 - samples/sec: 1795.19 - lr: 0.000024 - momentum: 0.000000
159
+ 2024-03-26 15:29:23,818 epoch 6 - iter 81/95 - loss 0.05895095 - time (sec): 16.70 - samples/sec: 1803.15 - lr: 0.000023 - momentum: 0.000000
160
+ 2024-03-26 15:29:25,492 epoch 6 - iter 90/95 - loss 0.05937033 - time (sec): 18.38 - samples/sec: 1796.56 - lr: 0.000023 - momentum: 0.000000
161
+ 2024-03-26 15:29:26,111 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 15:29:26,111 EPOCH 6 done: loss 0.0591 - lr: 0.000023
163
+ 2024-03-26 15:29:27,033 DEV : loss 0.19351260364055634 - f1-score (micro avg) 0.9177
164
+ 2024-03-26 15:29:27,036 saving best model
165
+ 2024-03-26 15:29:27,497 ----------------------------------------------------------------------------------------------------
166
+ 2024-03-26 15:29:28,830 epoch 7 - iter 9/95 - loss 0.06471264 - time (sec): 1.33 - samples/sec: 2218.53 - lr: 0.000022 - momentum: 0.000000
167
+ 2024-03-26 15:29:30,458 epoch 7 - iter 18/95 - loss 0.05493774 - time (sec): 2.96 - samples/sec: 1983.66 - lr: 0.000021 - momentum: 0.000000
168
+ 2024-03-26 15:29:32,243 epoch 7 - iter 27/95 - loss 0.05992386 - time (sec): 4.75 - samples/sec: 1926.33 - lr: 0.000021 - momentum: 0.000000
169
+ 2024-03-26 15:29:34,101 epoch 7 - iter 36/95 - loss 0.05179589 - time (sec): 6.60 - samples/sec: 1894.42 - lr: 0.000020 - momentum: 0.000000
170
+ 2024-03-26 15:29:36,393 epoch 7 - iter 45/95 - loss 0.04631679 - time (sec): 8.90 - samples/sec: 1842.34 - lr: 0.000020 - momentum: 0.000000
171
+ 2024-03-26 15:29:37,374 epoch 7 - iter 54/95 - loss 0.04784598 - time (sec): 9.88 - samples/sec: 1918.22 - lr: 0.000019 - momentum: 0.000000
172
+ 2024-03-26 15:29:39,224 epoch 7 - iter 63/95 - loss 0.04478083 - time (sec): 11.73 - samples/sec: 1918.30 - lr: 0.000019 - momentum: 0.000000
173
+ 2024-03-26 15:29:41,135 epoch 7 - iter 72/95 - loss 0.04368843 - time (sec): 13.64 - samples/sec: 1878.20 - lr: 0.000018 - momentum: 0.000000
174
+ 2024-03-26 15:29:43,059 epoch 7 - iter 81/95 - loss 0.04493601 - time (sec): 15.56 - samples/sec: 1876.21 - lr: 0.000018 - momentum: 0.000000
175
+ 2024-03-26 15:29:44,991 epoch 7 - iter 90/95 - loss 0.04441015 - time (sec): 17.49 - samples/sec: 1879.45 - lr: 0.000017 - momentum: 0.000000
176
+ 2024-03-26 15:29:45,824 ----------------------------------------------------------------------------------------------------
177
+ 2024-03-26 15:29:45,824 EPOCH 7 done: loss 0.0443 - lr: 0.000017
178
+ 2024-03-26 15:29:46,750 DEV : loss 0.22614780068397522 - f1-score (micro avg) 0.9114
179
+ 2024-03-26 15:29:46,751 ----------------------------------------------------------------------------------------------------
180
+ 2024-03-26 15:29:48,375 epoch 8 - iter 9/95 - loss 0.03781758 - time (sec): 1.62 - samples/sec: 1842.63 - lr: 0.000016 - momentum: 0.000000
181
+ 2024-03-26 15:29:50,386 epoch 8 - iter 18/95 - loss 0.04003328 - time (sec): 3.63 - samples/sec: 1673.11 - lr: 0.000016 - momentum: 0.000000
182
+ 2024-03-26 15:29:51,952 epoch 8 - iter 27/95 - loss 0.04016870 - time (sec): 5.20 - samples/sec: 1770.10 - lr: 0.000015 - momentum: 0.000000
183
+ 2024-03-26 15:29:53,681 epoch 8 - iter 36/95 - loss 0.04087006 - time (sec): 6.93 - samples/sec: 1816.97 - lr: 0.000015 - momentum: 0.000000
184
+ 2024-03-26 15:29:55,990 epoch 8 - iter 45/95 - loss 0.03527162 - time (sec): 9.24 - samples/sec: 1799.65 - lr: 0.000014 - momentum: 0.000000
185
+ 2024-03-26 15:29:58,298 epoch 8 - iter 54/95 - loss 0.03591706 - time (sec): 11.55 - samples/sec: 1803.48 - lr: 0.000014 - momentum: 0.000000
186
+ 2024-03-26 15:30:00,264 epoch 8 - iter 63/95 - loss 0.03768535 - time (sec): 13.51 - samples/sec: 1806.93 - lr: 0.000013 - momentum: 0.000000
187
+ 2024-03-26 15:30:01,348 epoch 8 - iter 72/95 - loss 0.03700051 - time (sec): 14.60 - samples/sec: 1839.60 - lr: 0.000013 - momentum: 0.000000
188
+ 2024-03-26 15:30:03,012 epoch 8 - iter 81/95 - loss 0.03620747 - time (sec): 16.26 - samples/sec: 1825.32 - lr: 0.000012 - momentum: 0.000000
189
+ 2024-03-26 15:30:04,386 epoch 8 - iter 90/95 - loss 0.03547569 - time (sec): 17.63 - samples/sec: 1840.72 - lr: 0.000012 - momentum: 0.000000
190
+ 2024-03-26 15:30:05,601 ----------------------------------------------------------------------------------------------------
191
+ 2024-03-26 15:30:05,601 EPOCH 8 done: loss 0.0381 - lr: 0.000012
192
+ 2024-03-26 15:30:06,534 DEV : loss 0.22081464529037476 - f1-score (micro avg) 0.9378
193
+ 2024-03-26 15:30:06,537 saving best model
194
+ 2024-03-26 15:30:06,991 ----------------------------------------------------------------------------------------------------
195
+ 2024-03-26 15:30:08,755 epoch 9 - iter 9/95 - loss 0.01270656 - time (sec): 1.76 - samples/sec: 1969.81 - lr: 0.000011 - momentum: 0.000000
196
+ 2024-03-26 15:30:10,678 epoch 9 - iter 18/95 - loss 0.01559003 - time (sec): 3.69 - samples/sec: 1832.92 - lr: 0.000010 - momentum: 0.000000
197
+ 2024-03-26 15:30:12,513 epoch 9 - iter 27/95 - loss 0.01660339 - time (sec): 5.52 - samples/sec: 1779.55 - lr: 0.000010 - momentum: 0.000000
198
+ 2024-03-26 15:30:14,390 epoch 9 - iter 36/95 - loss 0.02526995 - time (sec): 7.40 - samples/sec: 1819.75 - lr: 0.000009 - momentum: 0.000000
199
+ 2024-03-26 15:30:16,281 epoch 9 - iter 45/95 - loss 0.02355525 - time (sec): 9.29 - samples/sec: 1795.02 - lr: 0.000009 - momentum: 0.000000
200
+ 2024-03-26 15:30:18,139 epoch 9 - iter 54/95 - loss 0.02327141 - time (sec): 11.15 - samples/sec: 1824.84 - lr: 0.000008 - momentum: 0.000000
201
+ 2024-03-26 15:30:20,018 epoch 9 - iter 63/95 - loss 0.02441589 - time (sec): 13.03 - samples/sec: 1823.01 - lr: 0.000008 - momentum: 0.000000
202
+ 2024-03-26 15:30:21,603 epoch 9 - iter 72/95 - loss 0.02670088 - time (sec): 14.61 - samples/sec: 1832.26 - lr: 0.000007 - momentum: 0.000000
203
+ 2024-03-26 15:30:23,305 epoch 9 - iter 81/95 - loss 0.02941488 - time (sec): 16.31 - samples/sec: 1822.84 - lr: 0.000007 - momentum: 0.000000
204
+ 2024-03-26 15:30:25,059 epoch 9 - iter 90/95 - loss 0.02761290 - time (sec): 18.07 - samples/sec: 1839.87 - lr: 0.000006 - momentum: 0.000000
205
+ 2024-03-26 15:30:25,559 ----------------------------------------------------------------------------------------------------
206
+ 2024-03-26 15:30:25,559 EPOCH 9 done: loss 0.0284 - lr: 0.000006
207
+ 2024-03-26 15:30:26,474 DEV : loss 0.22866545617580414 - f1-score (micro avg) 0.9306
208
+ 2024-03-26 15:30:26,476 ----------------------------------------------------------------------------------------------------
209
+ 2024-03-26 15:30:27,944 epoch 10 - iter 9/95 - loss 0.01343831 - time (sec): 1.47 - samples/sec: 1892.16 - lr: 0.000005 - momentum: 0.000000
210
+ 2024-03-26 15:30:29,758 epoch 10 - iter 18/95 - loss 0.01508347 - time (sec): 3.28 - samples/sec: 1842.05 - lr: 0.000005 - momentum: 0.000000
211
+ 2024-03-26 15:30:31,987 epoch 10 - iter 27/95 - loss 0.02303455 - time (sec): 5.51 - samples/sec: 1754.41 - lr: 0.000004 - momentum: 0.000000
212
+ 2024-03-26 15:30:33,838 epoch 10 - iter 36/95 - loss 0.02337816 - time (sec): 7.36 - samples/sec: 1781.61 - lr: 0.000004 - momentum: 0.000000
213
+ 2024-03-26 15:30:35,008 epoch 10 - iter 45/95 - loss 0.02283129 - time (sec): 8.53 - samples/sec: 1837.13 - lr: 0.000003 - momentum: 0.000000
214
+ 2024-03-26 15:30:36,914 epoch 10 - iter 54/95 - loss 0.02373572 - time (sec): 10.44 - samples/sec: 1824.11 - lr: 0.000003 - momentum: 0.000000
215
+ 2024-03-26 15:30:38,312 epoch 10 - iter 63/95 - loss 0.02527243 - time (sec): 11.84 - samples/sec: 1835.91 - lr: 0.000002 - momentum: 0.000000
216
+ 2024-03-26 15:30:40,557 epoch 10 - iter 72/95 - loss 0.02191466 - time (sec): 14.08 - samples/sec: 1819.01 - lr: 0.000002 - momentum: 0.000000
217
+ 2024-03-26 15:30:42,859 epoch 10 - iter 81/95 - loss 0.02551541 - time (sec): 16.38 - samples/sec: 1802.31 - lr: 0.000001 - momentum: 0.000000
218
+ 2024-03-26 15:30:44,694 epoch 10 - iter 90/95 - loss 0.02328698 - time (sec): 18.22 - samples/sec: 1796.83 - lr: 0.000001 - momentum: 0.000000
219
+ 2024-03-26 15:30:45,706 ----------------------------------------------------------------------------------------------------
220
+ 2024-03-26 15:30:45,706 EPOCH 10 done: loss 0.0223 - lr: 0.000001
221
+ 2024-03-26 15:30:46,628 DEV : loss 0.2289051115512848 - f1-score (micro avg) 0.9364
222
+ 2024-03-26 15:30:46,938 ----------------------------------------------------------------------------------------------------
223
+ 2024-03-26 15:30:46,939 Loading model from best epoch ...
224
+ 2024-03-26 15:30:47,812 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
225
+ 2024-03-26 15:30:48,571
226
+ Results:
227
+ - F-score (micro) 0.9134
228
+ - F-score (macro) 0.6937
229
+ - Accuracy 0.843
230
+
231
+ By class:
232
+ precision recall f1-score support
233
+
234
+ Unternehmen 0.9004 0.8835 0.8918 266
235
+ Auslagerung 0.8911 0.9197 0.9051 249
236
+ Ort 0.9706 0.9851 0.9778 134
237
+ Software 0.0000 0.0000 0.0000 0
238
+
239
+ micro avg 0.9085 0.9183 0.9134 649
240
+ macro avg 0.6905 0.6971 0.6937 649
241
+ weighted avg 0.9113 0.9183 0.9147 649
242
+
243
+ 2024-03-26 15:30:48,571 ----------------------------------------------------------------------------------------------------