Hugging Face's logo

stefan-it
/
flair-co-funer-gbert_base-bs8-e10-lr5e-05-4

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
hetzner
hetzner-gex44
hetzner-gpu
Model card Files Metrics Community
3
stefan-it commited on
Commit
83cadb9
•
1 Parent(s): 48dd929

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +245 -0
training.log ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-03-26 10:28:35,728 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 10:28:35,729 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(31103, 768)
7
+ (position_embeddings): Embedding(512, 768)
8
+ (token_type_embeddings): Embedding(2, 768)
9
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=768, out_features=768, bias=True)
18
+ (key): Linear(in_features=768, out_features=768, bias=True)
19
+ (value): Linear(in_features=768, out_features=768, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=768, out_features=768, bias=True)
24
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
34
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
35
+ (dropout): Dropout(p=0.1, inplace=False)
36
+ )
37
+ )
38
+ )
39
+ )
40
+ (pooler): BertPooler(
41
+ (dense): Linear(in_features=768, out_features=768, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=768, out_features=17, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2024-03-26 10:28:35,729 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 10:28:35,729 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 10:28:35,729 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 10:28:35,729 Train: 758 sentences
54
+ 2024-03-26 10:28:35,729 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 10:28:35,729 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 10:28:35,729 Training Params:
57
+ 2024-03-26 10:28:35,729 - learning_rate: "5e-05"
58
+ 2024-03-26 10:28:35,729 - mini_batch_size: "8"
59
+ 2024-03-26 10:28:35,729 - max_epochs: "10"
60
+ 2024-03-26 10:28:35,729 - shuffle: "True"
61
+ 2024-03-26 10:28:35,729 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 10:28:35,729 Plugins:
63
+ 2024-03-26 10:28:35,729 - TensorboardLogger
64
+ 2024-03-26 10:28:35,729 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 10:28:35,729 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 10:28:35,729 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 10:28:35,729 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 10:28:35,729 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 10:28:35,729 Computation:
70
+ 2024-03-26 10:28:35,729 - compute on device: cuda:0
71
+ 2024-03-26 10:28:35,729 - embedding storage: none
72
+ 2024-03-26 10:28:35,729 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 10:28:35,729 Model training base path: "flair-co-funer-gbert_base-bs8-e10-lr5e-05-4"
74
+ 2024-03-26 10:28:35,729 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 10:28:35,729 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 10:28:35,729 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 10:28:37,074 epoch 1 - iter 9/95 - loss 3.29095728 - time (sec): 1.34 - samples/sec: 2157.52 - lr: 0.000004 - momentum: 0.000000
78
+ 2024-03-26 10:28:38,456 epoch 1 - iter 18/95 - loss 3.08915397 - time (sec): 2.73 - samples/sec: 2022.41 - lr: 0.000009 - momentum: 0.000000
79
+ 2024-03-26 10:28:40,075 epoch 1 - iter 27/95 - loss 2.78831297 - time (sec): 4.35 - samples/sec: 1973.60 - lr: 0.000014 - momentum: 0.000000
80
+ 2024-03-26 10:28:42,038 epoch 1 - iter 36/95 - loss 2.55176526 - time (sec): 6.31 - samples/sec: 1892.23 - lr: 0.000018 - momentum: 0.000000
81
+ 2024-03-26 10:28:43,886 epoch 1 - iter 45/95 - loss 2.34472767 - time (sec): 8.16 - samples/sec: 1911.70 - lr: 0.000023 - momentum: 0.000000
82
+ 2024-03-26 10:28:46,102 epoch 1 - iter 54/95 - loss 2.18435379 - time (sec): 10.37 - samples/sec: 1845.74 - lr: 0.000028 - momentum: 0.000000
83
+ 2024-03-26 10:28:48,110 epoch 1 - iter 63/95 - loss 2.02400115 - time (sec): 12.38 - samples/sec: 1825.52 - lr: 0.000033 - momentum: 0.000000
84
+ 2024-03-26 10:28:49,077 epoch 1 - iter 72/95 - loss 1.92796284 - time (sec): 13.35 - samples/sec: 1871.48 - lr: 0.000037 - momentum: 0.000000
85
+ 2024-03-26 10:28:51,349 epoch 1 - iter 81/95 - loss 1.78146040 - time (sec): 15.62 - samples/sec: 1818.51 - lr: 0.000042 - momentum: 0.000000
86
+ 2024-03-26 10:28:52,676 epoch 1 - iter 90/95 - loss 1.64759700 - time (sec): 16.95 - samples/sec: 1885.89 - lr: 0.000047 - momentum: 0.000000
87
+ 2024-03-26 10:28:53,938 ----------------------------------------------------------------------------------------------------
88
+ 2024-03-26 10:28:53,938 EPOCH 1 done: loss 1.5782 - lr: 0.000047
89
+ 2024-03-26 10:28:54,771 DEV : loss 0.4267578125 - f1-score (micro avg) 0.6895
90
+ 2024-03-26 10:28:54,773 saving best model
91
+ 2024-03-26 10:28:55,033 ----------------------------------------------------------------------------------------------------
92
+ 2024-03-26 10:28:56,620 epoch 2 - iter 9/95 - loss 0.54697289 - time (sec): 1.59 - samples/sec: 1816.17 - lr: 0.000050 - momentum: 0.000000
93
+ 2024-03-26 10:28:58,258 epoch 2 - iter 18/95 - loss 0.45713150 - time (sec): 3.22 - samples/sec: 1916.68 - lr: 0.000049 - momentum: 0.000000
94
+ 2024-03-26 10:29:00,032 epoch 2 - iter 27/95 - loss 0.41563849 - time (sec): 5.00 - samples/sec: 1891.77 - lr: 0.000048 - momentum: 0.000000
95
+ 2024-03-26 10:29:02,403 epoch 2 - iter 36/95 - loss 0.36132141 - time (sec): 7.37 - samples/sec: 1770.32 - lr: 0.000048 - momentum: 0.000000
96
+ 2024-03-26 10:29:04,360 epoch 2 - iter 45/95 - loss 0.34829906 - time (sec): 9.33 - samples/sec: 1769.00 - lr: 0.000047 - momentum: 0.000000
97
+ 2024-03-26 10:29:06,122 epoch 2 - iter 54/95 - loss 0.35634407 - time (sec): 11.09 - samples/sec: 1788.56 - lr: 0.000047 - momentum: 0.000000
98
+ 2024-03-26 10:29:08,529 epoch 2 - iter 63/95 - loss 0.33840681 - time (sec): 13.50 - samples/sec: 1771.74 - lr: 0.000046 - momentum: 0.000000
99
+ 2024-03-26 10:29:10,339 epoch 2 - iter 72/95 - loss 0.33790562 - time (sec): 15.31 - samples/sec: 1766.89 - lr: 0.000046 - momentum: 0.000000
100
+ 2024-03-26 10:29:12,498 epoch 2 - iter 81/95 - loss 0.33273931 - time (sec): 17.46 - samples/sec: 1751.70 - lr: 0.000045 - momentum: 0.000000
101
+ 2024-03-26 10:29:13,779 epoch 2 - iter 90/95 - loss 0.32834277 - time (sec): 18.74 - samples/sec: 1777.33 - lr: 0.000045 - momentum: 0.000000
102
+ 2024-03-26 10:29:14,221 ----------------------------------------------------------------------------------------------------
103
+ 2024-03-26 10:29:14,221 EPOCH 2 done: loss 0.3237 - lr: 0.000045
104
+ 2024-03-26 10:29:15,109 DEV : loss 0.2464773952960968 - f1-score (micro avg) 0.8605
105
+ 2024-03-26 10:29:15,110 saving best model
106
+ 2024-03-26 10:29:15,549 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 10:29:17,114 epoch 3 - iter 9/95 - loss 0.20825595 - time (sec): 1.56 - samples/sec: 1694.91 - lr: 0.000044 - momentum: 0.000000
108
+ 2024-03-26 10:29:18,827 epoch 3 - iter 18/95 - loss 0.17689281 - time (sec): 3.28 - samples/sec: 1705.87 - lr: 0.000043 - momentum: 0.000000
109
+ 2024-03-26 10:29:20,654 epoch 3 - iter 27/95 - loss 0.17979153 - time (sec): 5.10 - samples/sec: 1745.24 - lr: 0.000043 - momentum: 0.000000
110
+ 2024-03-26 10:29:22,428 epoch 3 - iter 36/95 - loss 0.18580580 - time (sec): 6.88 - samples/sec: 1755.08 - lr: 0.000042 - momentum: 0.000000
111
+ 2024-03-26 10:29:24,423 epoch 3 - iter 45/95 - loss 0.17998091 - time (sec): 8.87 - samples/sec: 1779.47 - lr: 0.000042 - momentum: 0.000000
112
+ 2024-03-26 10:29:26,639 epoch 3 - iter 54/95 - loss 0.17698755 - time (sec): 11.09 - samples/sec: 1746.72 - lr: 0.000041 - momentum: 0.000000
113
+ 2024-03-26 10:29:28,331 epoch 3 - iter 63/95 - loss 0.17392405 - time (sec): 12.78 - samples/sec: 1750.43 - lr: 0.000041 - momentum: 0.000000
114
+ 2024-03-26 10:29:30,291 epoch 3 - iter 72/95 - loss 0.17133371 - time (sec): 14.74 - samples/sec: 1756.22 - lr: 0.000040 - momentum: 0.000000
115
+ 2024-03-26 10:29:32,243 epoch 3 - iter 81/95 - loss 0.17832679 - time (sec): 16.69 - samples/sec: 1774.24 - lr: 0.000040 - momentum: 0.000000
116
+ 2024-03-26 10:29:34,459 epoch 3 - iter 90/95 - loss 0.17162912 - time (sec): 18.91 - samples/sec: 1753.84 - lr: 0.000039 - momentum: 0.000000
117
+ 2024-03-26 10:29:35,067 ----------------------------------------------------------------------------------------------------
118
+ 2024-03-26 10:29:35,067 EPOCH 3 done: loss 0.1731 - lr: 0.000039
119
+ 2024-03-26 10:29:35,977 DEV : loss 0.1760903000831604 - f1-score (micro avg) 0.8827
120
+ 2024-03-26 10:29:35,978 saving best model
121
+ 2024-03-26 10:29:36,404 ----------------------------------------------------------------------------------------------------
122
+ 2024-03-26 10:29:38,783 epoch 4 - iter 9/95 - loss 0.06788233 - time (sec): 2.38 - samples/sec: 1662.93 - lr: 0.000039 - momentum: 0.000000
123
+ 2024-03-26 10:29:39,946 epoch 4 - iter 18/95 - loss 0.08548344 - time (sec): 3.54 - samples/sec: 1807.39 - lr: 0.000038 - momentum: 0.000000
124
+ 2024-03-26 10:29:42,047 epoch 4 - iter 27/95 - loss 0.09484554 - time (sec): 5.64 - samples/sec: 1843.15 - lr: 0.000037 - momentum: 0.000000
125
+ 2024-03-26 10:29:43,510 epoch 4 - iter 36/95 - loss 0.10345344 - time (sec): 7.11 - samples/sec: 1877.49 - lr: 0.000037 - momentum: 0.000000
126
+ 2024-03-26 10:29:44,804 epoch 4 - iter 45/95 - loss 0.10546483 - time (sec): 8.40 - samples/sec: 1910.57 - lr: 0.000036 - momentum: 0.000000
127
+ 2024-03-26 10:29:46,854 epoch 4 - iter 54/95 - loss 0.10315337 - time (sec): 10.45 - samples/sec: 1852.22 - lr: 0.000036 - momentum: 0.000000
128
+ 2024-03-26 10:29:49,095 epoch 4 - iter 63/95 - loss 0.11633996 - time (sec): 12.69 - samples/sec: 1824.42 - lr: 0.000035 - momentum: 0.000000
129
+ 2024-03-26 10:29:50,531 epoch 4 - iter 72/95 - loss 0.11408630 - time (sec): 14.13 - samples/sec: 1860.23 - lr: 0.000035 - momentum: 0.000000
130
+ 2024-03-26 10:29:52,116 epoch 4 - iter 81/95 - loss 0.11337976 - time (sec): 15.71 - samples/sec: 1890.41 - lr: 0.000034 - momentum: 0.000000
131
+ 2024-03-26 10:29:53,706 epoch 4 - iter 90/95 - loss 0.11156393 - time (sec): 17.30 - samples/sec: 1919.30 - lr: 0.000034 - momentum: 0.000000
132
+ 2024-03-26 10:29:54,325 ----------------------------------------------------------------------------------------------------
133
+ 2024-03-26 10:29:54,325 EPOCH 4 done: loss 0.1120 - lr: 0.000034
134
+ 2024-03-26 10:29:55,226 DEV : loss 0.17519471049308777 - f1-score (micro avg) 0.909
135
+ 2024-03-26 10:29:55,227 saving best model
136
+ 2024-03-26 10:29:55,670 ----------------------------------------------------------------------------------------------------
137
+ 2024-03-26 10:29:56,867 epoch 5 - iter 9/95 - loss 0.12043110 - time (sec): 1.20 - samples/sec: 2473.59 - lr: 0.000033 - momentum: 0.000000
138
+ 2024-03-26 10:29:58,296 epoch 5 - iter 18/95 - loss 0.10960541 - time (sec): 2.63 - samples/sec: 2220.06 - lr: 0.000032 - momentum: 0.000000
139
+ 2024-03-26 10:30:00,275 epoch 5 - iter 27/95 - loss 0.09760046 - time (sec): 4.60 - samples/sec: 1997.58 - lr: 0.000032 - momentum: 0.000000
140
+ 2024-03-26 10:30:02,673 epoch 5 - iter 36/95 - loss 0.09358827 - time (sec): 7.00 - samples/sec: 1813.85 - lr: 0.000031 - momentum: 0.000000
141
+ 2024-03-26 10:30:03,889 epoch 5 - iter 45/95 - loss 0.09683649 - time (sec): 8.22 - samples/sec: 1858.53 - lr: 0.000031 - momentum: 0.000000
142
+ 2024-03-26 10:30:05,744 epoch 5 - iter 54/95 - loss 0.09239902 - time (sec): 10.07 - samples/sec: 1900.20 - lr: 0.000030 - momentum: 0.000000
143
+ 2024-03-26 10:30:07,795 epoch 5 - iter 63/95 - loss 0.08595866 - time (sec): 12.12 - samples/sec: 1884.90 - lr: 0.000030 - momentum: 0.000000
144
+ 2024-03-26 10:30:09,052 epoch 5 - iter 72/95 - loss 0.08467307 - time (sec): 13.38 - samples/sec: 1913.09 - lr: 0.000029 - momentum: 0.000000
145
+ 2024-03-26 10:30:11,594 epoch 5 - iter 81/95 - loss 0.07917529 - time (sec): 15.92 - samples/sec: 1844.62 - lr: 0.000029 - momentum: 0.000000
146
+ 2024-03-26 10:30:13,611 epoch 5 - iter 90/95 - loss 0.07825247 - time (sec): 17.94 - samples/sec: 1825.05 - lr: 0.000028 - momentum: 0.000000
147
+ 2024-03-26 10:30:14,473 ----------------------------------------------------------------------------------------------------
148
+ 2024-03-26 10:30:14,473 EPOCH 5 done: loss 0.0797 - lr: 0.000028
149
+ 2024-03-26 10:30:15,378 DEV : loss 0.14438194036483765 - f1-score (micro avg) 0.9224
150
+ 2024-03-26 10:30:15,379 saving best model
151
+ 2024-03-26 10:30:15,816 ----------------------------------------------------------------------------------------------------
152
+ 2024-03-26 10:30:17,459 epoch 6 - iter 9/95 - loss 0.09244981 - time (sec): 1.64 - samples/sec: 2018.64 - lr: 0.000027 - momentum: 0.000000
153
+ 2024-03-26 10:30:19,514 epoch 6 - iter 18/95 - loss 0.06354727 - time (sec): 3.70 - samples/sec: 1832.96 - lr: 0.000027 - momentum: 0.000000
154
+ 2024-03-26 10:30:20,945 epoch 6 - iter 27/95 - loss 0.06574351 - time (sec): 5.13 - samples/sec: 1863.31 - lr: 0.000026 - momentum: 0.000000
155
+ 2024-03-26 10:30:23,266 epoch 6 - iter 36/95 - loss 0.05330838 - time (sec): 7.45 - samples/sec: 1723.80 - lr: 0.000026 - momentum: 0.000000
156
+ 2024-03-26 10:30:25,027 epoch 6 - iter 45/95 - loss 0.05097494 - time (sec): 9.21 - samples/sec: 1746.61 - lr: 0.000025 - momentum: 0.000000
157
+ 2024-03-26 10:30:27,502 epoch 6 - iter 54/95 - loss 0.05867496 - time (sec): 11.69 - samples/sec: 1722.90 - lr: 0.000025 - momentum: 0.000000
158
+ 2024-03-26 10:30:29,011 epoch 6 - iter 63/95 - loss 0.06045661 - time (sec): 13.19 - samples/sec: 1739.77 - lr: 0.000024 - momentum: 0.000000
159
+ 2024-03-26 10:30:30,546 epoch 6 - iter 72/95 - loss 0.06179262 - time (sec): 14.73 - samples/sec: 1761.21 - lr: 0.000024 - momentum: 0.000000
160
+ 2024-03-26 10:30:32,622 epoch 6 - iter 81/95 - loss 0.06226128 - time (sec): 16.81 - samples/sec: 1754.24 - lr: 0.000023 - momentum: 0.000000
161
+ 2024-03-26 10:30:33,799 epoch 6 - iter 90/95 - loss 0.06477171 - time (sec): 17.98 - samples/sec: 1798.68 - lr: 0.000023 - momentum: 0.000000
162
+ 2024-03-26 10:30:35,131 ----------------------------------------------------------------------------------------------------
163
+ 2024-03-26 10:30:35,131 EPOCH 6 done: loss 0.0628 - lr: 0.000023
164
+ 2024-03-26 10:30:36,044 DEV : loss 0.16837507486343384 - f1-score (micro avg) 0.912
165
+ 2024-03-26 10:30:36,047 ----------------------------------------------------------------------------------------------------
166
+ 2024-03-26 10:30:37,419 epoch 7 - iter 9/95 - loss 0.04042555 - time (sec): 1.37 - samples/sec: 2313.60 - lr: 0.000022 - momentum: 0.000000
167
+ 2024-03-26 10:30:39,544 epoch 7 - iter 18/95 - loss 0.04069942 - time (sec): 3.50 - samples/sec: 1928.39 - lr: 0.000021 - momentum: 0.000000
168
+ 2024-03-26 10:30:41,509 epoch 7 - iter 27/95 - loss 0.04506976 - time (sec): 5.46 - samples/sec: 1789.58 - lr: 0.000021 - momentum: 0.000000
169
+ 2024-03-26 10:30:42,799 epoch 7 - iter 36/95 - loss 0.04308197 - time (sec): 6.75 - samples/sec: 1852.73 - lr: 0.000020 - momentum: 0.000000
170
+ 2024-03-26 10:30:44,491 epoch 7 - iter 45/95 - loss 0.04045458 - time (sec): 8.44 - samples/sec: 1863.40 - lr: 0.000020 - momentum: 0.000000
171
+ 2024-03-26 10:30:46,696 epoch 7 - iter 54/95 - loss 0.03804365 - time (sec): 10.65 - samples/sec: 1839.96 - lr: 0.000019 - momentum: 0.000000
172
+ 2024-03-26 10:30:48,735 epoch 7 - iter 63/95 - loss 0.04117399 - time (sec): 12.69 - samples/sec: 1794.55 - lr: 0.000019 - momentum: 0.000000
173
+ 2024-03-26 10:30:50,858 epoch 7 - iter 72/95 - loss 0.03975813 - time (sec): 14.81 - samples/sec: 1771.80 - lr: 0.000018 - momentum: 0.000000
174
+ 2024-03-26 10:30:52,373 epoch 7 - iter 81/95 - loss 0.04421200 - time (sec): 16.32 - samples/sec: 1778.87 - lr: 0.000018 - momentum: 0.000000
175
+ 2024-03-26 10:30:54,245 epoch 7 - iter 90/95 - loss 0.05043406 - time (sec): 18.20 - samples/sec: 1807.50 - lr: 0.000017 - momentum: 0.000000
176
+ 2024-03-26 10:30:54,925 ----------------------------------------------------------------------------------------------------
177
+ 2024-03-26 10:30:54,925 EPOCH 7 done: loss 0.0503 - lr: 0.000017
178
+ 2024-03-26 10:30:55,831 DEV : loss 0.16629257798194885 - f1-score (micro avg) 0.9369
179
+ 2024-03-26 10:30:55,833 saving best model
180
+ 2024-03-26 10:30:56,261 ----------------------------------------------------------------------------------------------------
181
+ 2024-03-26 10:30:57,904 epoch 8 - iter 9/95 - loss 0.01558551 - time (sec): 1.64 - samples/sec: 1791.91 - lr: 0.000016 - momentum: 0.000000
182
+ 2024-03-26 10:31:00,035 epoch 8 - iter 18/95 - loss 0.02309291 - time (sec): 3.77 - samples/sec: 1757.14 - lr: 0.000016 - momentum: 0.000000
183
+ 2024-03-26 10:31:01,878 epoch 8 - iter 27/95 - loss 0.03236659 - time (sec): 5.62 - samples/sec: 1728.05 - lr: 0.000015 - momentum: 0.000000
184
+ 2024-03-26 10:31:03,856 epoch 8 - iter 36/95 - loss 0.03080217 - time (sec): 7.59 - samples/sec: 1734.43 - lr: 0.000015 - momentum: 0.000000
185
+ 2024-03-26 10:31:04,880 epoch 8 - iter 45/95 - loss 0.03971592 - time (sec): 8.62 - samples/sec: 1820.33 - lr: 0.000014 - momentum: 0.000000
186
+ 2024-03-26 10:31:06,819 epoch 8 - iter 54/95 - loss 0.04108818 - time (sec): 10.56 - samples/sec: 1809.42 - lr: 0.000014 - momentum: 0.000000
187
+ 2024-03-26 10:31:09,038 epoch 8 - iter 63/95 - loss 0.04377676 - time (sec): 12.78 - samples/sec: 1793.88 - lr: 0.000013 - momentum: 0.000000
188
+ 2024-03-26 10:31:11,243 epoch 8 - iter 72/95 - loss 0.04319877 - time (sec): 14.98 - samples/sec: 1784.40 - lr: 0.000013 - momentum: 0.000000
189
+ 2024-03-26 10:31:12,951 epoch 8 - iter 81/95 - loss 0.04251063 - time (sec): 16.69 - samples/sec: 1788.33 - lr: 0.000012 - momentum: 0.000000
190
+ 2024-03-26 10:31:14,865 epoch 8 - iter 90/95 - loss 0.03992474 - time (sec): 18.60 - samples/sec: 1784.67 - lr: 0.000012 - momentum: 0.000000
191
+ 2024-03-26 10:31:15,459 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 10:31:15,459 EPOCH 8 done: loss 0.0404 - lr: 0.000012
193
+ 2024-03-26 10:31:16,369 DEV : loss 0.15785594284534454 - f1-score (micro avg) 0.9382
194
+ 2024-03-26 10:31:16,370 saving best model
195
+ 2024-03-26 10:31:16,801 ----------------------------------------------------------------------------------------------------
196
+ 2024-03-26 10:31:18,339 epoch 9 - iter 9/95 - loss 0.02870197 - time (sec): 1.54 - samples/sec: 2070.29 - lr: 0.000011 - momentum: 0.000000
197
+ 2024-03-26 10:31:20,627 epoch 9 - iter 18/95 - loss 0.02268037 - time (sec): 3.82 - samples/sec: 1781.03 - lr: 0.000010 - momentum: 0.000000
198
+ 2024-03-26 10:31:22,218 epoch 9 - iter 27/95 - loss 0.01915786 - time (sec): 5.41 - samples/sec: 1799.85 - lr: 0.000010 - momentum: 0.000000
199
+ 2024-03-26 10:31:24,521 epoch 9 - iter 36/95 - loss 0.02449214 - time (sec): 7.72 - samples/sec: 1757.80 - lr: 0.000009 - momentum: 0.000000
200
+ 2024-03-26 10:31:26,418 epoch 9 - iter 45/95 - loss 0.02330329 - time (sec): 9.62 - samples/sec: 1730.41 - lr: 0.000009 - momentum: 0.000000
201
+ 2024-03-26 10:31:27,794 epoch 9 - iter 54/95 - loss 0.02848105 - time (sec): 10.99 - samples/sec: 1775.35 - lr: 0.000008 - momentum: 0.000000
202
+ 2024-03-26 10:31:29,866 epoch 9 - iter 63/95 - loss 0.02663824 - time (sec): 13.06 - samples/sec: 1755.13 - lr: 0.000008 - momentum: 0.000000
203
+ 2024-03-26 10:31:31,084 epoch 9 - iter 72/95 - loss 0.03016438 - time (sec): 14.28 - samples/sec: 1790.00 - lr: 0.000007 - momentum: 0.000000
204
+ 2024-03-26 10:31:33,856 epoch 9 - iter 81/95 - loss 0.03043791 - time (sec): 17.05 - samples/sec: 1741.38 - lr: 0.000007 - momentum: 0.000000
205
+ 2024-03-26 10:31:35,497 epoch 9 - iter 90/95 - loss 0.02846557 - time (sec): 18.69 - samples/sec: 1762.25 - lr: 0.000006 - momentum: 0.000000
206
+ 2024-03-26 10:31:36,157 ----------------------------------------------------------------------------------------------------
207
+ 2024-03-26 10:31:36,158 EPOCH 9 done: loss 0.0293 - lr: 0.000006
208
+ 2024-03-26 10:31:37,075 DEV : loss 0.17136143147945404 - f1-score (micro avg) 0.9443
209
+ 2024-03-26 10:31:37,076 saving best model
210
+ 2024-03-26 10:31:37,540 ----------------------------------------------------------------------------------------------------
211
+ 2024-03-26 10:31:39,384 epoch 10 - iter 9/95 - loss 0.03543689 - time (sec): 1.84 - samples/sec: 1682.13 - lr: 0.000005 - momentum: 0.000000
212
+ 2024-03-26 10:31:41,567 epoch 10 - iter 18/95 - loss 0.03398521 - time (sec): 4.03 - samples/sec: 1655.13 - lr: 0.000005 - momentum: 0.000000
213
+ 2024-03-26 10:31:42,989 epoch 10 - iter 27/95 - loss 0.02864523 - time (sec): 5.45 - samples/sec: 1800.34 - lr: 0.000004 - momentum: 0.000000
214
+ 2024-03-26 10:31:44,708 epoch 10 - iter 36/95 - loss 0.02526881 - time (sec): 7.17 - samples/sec: 1841.01 - lr: 0.000004 - momentum: 0.000000
215
+ 2024-03-26 10:31:46,128 epoch 10 - iter 45/95 - loss 0.02433110 - time (sec): 8.59 - samples/sec: 1870.07 - lr: 0.000003 - momentum: 0.000000
216
+ 2024-03-26 10:31:47,144 epoch 10 - iter 54/95 - loss 0.02218444 - time (sec): 9.60 - samples/sec: 1943.11 - lr: 0.000003 - momentum: 0.000000
217
+ 2024-03-26 10:31:48,949 epoch 10 - iter 63/95 - loss 0.02021689 - time (sec): 11.41 - samples/sec: 1915.96 - lr: 0.000002 - momentum: 0.000000
218
+ 2024-03-26 10:31:51,203 epoch 10 - iter 72/95 - loss 0.02517433 - time (sec): 13.66 - samples/sec: 1866.01 - lr: 0.000002 - momentum: 0.000000
219
+ 2024-03-26 10:31:52,834 epoch 10 - iter 81/95 - loss 0.02584878 - time (sec): 15.29 - samples/sec: 1857.82 - lr: 0.000001 - momentum: 0.000000
220
+ 2024-03-26 10:31:55,141 epoch 10 - iter 90/95 - loss 0.02442898 - time (sec): 17.60 - samples/sec: 1846.49 - lr: 0.000001 - momentum: 0.000000
221
+ 2024-03-26 10:31:56,381 ----------------------------------------------------------------------------------------------------
222
+ 2024-03-26 10:31:56,381 EPOCH 10 done: loss 0.0242 - lr: 0.000001
223
+ 2024-03-26 10:31:57,328 DEV : loss 0.18190717697143555 - f1-score (micro avg) 0.9364
224
+ 2024-03-26 10:31:57,605 ----------------------------------------------------------------------------------------------------
225
+ 2024-03-26 10:31:57,605 Loading model from best epoch ...
226
+ 2024-03-26 10:31:58,541 SequenceTagger predicts: Dictionary with 17 tags: O, S-Unternehmen, B-Unternehmen, E-Unternehmen, I-Unternehmen, S-Auslagerung, B-Auslagerung, E-Auslagerung, I-Auslagerung, S-Ort, B-Ort, E-Ort, I-Ort, S-Software, B-Software, E-Software, I-Software
227
+ 2024-03-26 10:31:59,301
228
+ Results:
229
+ - F-score (micro) 0.9155
230
+ - F-score (macro) 0.6953
231
+ - Accuracy 0.8466
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ Unternehmen 0.9325 0.8835 0.9073 266
237
+ Auslagerung 0.8702 0.9157 0.8924 249
238
+ Ort 0.9708 0.9925 0.9815 134
239
+ Software 0.0000 0.0000 0.0000 0
240
+
241
+ micro avg 0.9127 0.9183 0.9155 649
242
+ macro avg 0.6934 0.6979 0.6953 649
243
+ weighted avg 0.9165 0.9183 0.9169 649
244
+
245
+ 2024-03-26 10:31:59,302 ----------------------------------------------------------------------------------------------------