Hugging Face's logo

stefan-it
/
flair-co-funer-gbert_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
3
stefan-it commited on
Commit
25d16ec
•
1 Parent(s): 9d600a6

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +247 -0
training.log ADDED
@@ -0,0 +1,247 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-03-26 09:39:45,010 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 09:39:45,010 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 09:39:45,010 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 09:39:45,011 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 09:39:45,011 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 09:39:45,011 Train: 758 sentences
54
+ 2024-03-26 09:39:45,011 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 09:39:45,011 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 09:39:45,011 Training Params:
57
+ 2024-03-26 09:39:45,011 - learning_rate: "5e-05"
58
+ 2024-03-26 09:39:45,011 - mini_batch_size: "8"
59
+ 2024-03-26 09:39:45,011 - max_epochs: "10"
60
+ 2024-03-26 09:39:45,011 - shuffle: "True"
61
+ 2024-03-26 09:39:45,011 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 09:39:45,011 Plugins:
63
+ 2024-03-26 09:39:45,011 - TensorboardLogger
64
+ 2024-03-26 09:39:45,011 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 09:39:45,011 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 09:39:45,011 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 09:39:45,011 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 09:39:45,011 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 09:39:45,011 Computation:
70
+ 2024-03-26 09:39:45,011 - compute on device: cuda:0
71
+ 2024-03-26 09:39:45,011 - embedding storage: none
72
+ 2024-03-26 09:39:45,011 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 09:39:45,011 Model training base path: "flair-co-funer-gbert_base-bs8-e10-lr5e-05-1"
74
+ 2024-03-26 09:39:45,011 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 09:39:45,011 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 09:39:45,011 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 09:39:46,596 epoch 1 - iter 9/95 - loss 3.05326256 - time (sec): 1.59 - samples/sec: 1942.31 - lr: 0.000004 - momentum: 0.000000
78
+ 2024-03-26 09:39:48,126 epoch 1 - iter 18/95 - loss 2.83895391 - time (sec): 3.12 - samples/sec: 2006.72 - lr: 0.000009 - momentum: 0.000000
79
+ 2024-03-26 09:39:50,518 epoch 1 - iter 27/95 - loss 2.59331548 - time (sec): 5.51 - samples/sec: 1859.51 - lr: 0.000014 - momentum: 0.000000
80
+ 2024-03-26 09:39:52,748 epoch 1 - iter 36/95 - loss 2.43003112 - time (sec): 7.74 - samples/sec: 1806.93 - lr: 0.000018 - momentum: 0.000000
81
+ 2024-03-26 09:39:54,635 epoch 1 - iter 45/95 - loss 2.28997757 - time (sec): 9.62 - samples/sec: 1814.48 - lr: 0.000023 - momentum: 0.000000
82
+ 2024-03-26 09:39:55,860 epoch 1 - iter 54/95 - loss 2.17102423 - time (sec): 10.85 - samples/sec: 1856.38 - lr: 0.000028 - momentum: 0.000000
83
+ 2024-03-26 09:39:57,564 epoch 1 - iter 63/95 - loss 2.05061689 - time (sec): 12.55 - samples/sec: 1853.40 - lr: 0.000033 - momentum: 0.000000
84
+ 2024-03-26 09:39:58,845 epoch 1 - iter 72/95 - loss 1.94125898 - time (sec): 13.83 - samples/sec: 1883.06 - lr: 0.000037 - momentum: 0.000000
85
+ 2024-03-26 09:40:00,817 epoch 1 - iter 81/95 - loss 1.81009489 - time (sec): 15.81 - samples/sec: 1873.87 - lr: 0.000042 - momentum: 0.000000
86
+ 2024-03-26 09:40:02,140 epoch 1 - iter 90/95 - loss 1.71143912 - time (sec): 17.13 - samples/sec: 1893.86 - lr: 0.000047 - momentum: 0.000000
87
+ 2024-03-26 09:40:03,361 ----------------------------------------------------------------------------------------------------
88
+ 2024-03-26 09:40:03,361 EPOCH 1 done: loss 1.6404 - lr: 0.000047
89
+ 2024-03-26 09:40:04,256 DEV : loss 0.47643521428108215 - f1-score (micro avg) 0.6785
90
+ 2024-03-26 09:40:04,257 saving best model
91
+ 2024-03-26 09:40:04,516 ----------------------------------------------------------------------------------------------------
92
+ 2024-03-26 09:40:06,572 epoch 2 - iter 9/95 - loss 0.50078791 - time (sec): 2.06 - samples/sec: 1796.30 - lr: 0.000050 - momentum: 0.000000
93
+ 2024-03-26 09:40:08,253 epoch 2 - iter 18/95 - loss 0.51331330 - time (sec): 3.74 - samples/sec: 1941.68 - lr: 0.000049 - momentum: 0.000000
94
+ 2024-03-26 09:40:10,067 epoch 2 - iter 27/95 - loss 0.48020903 - time (sec): 5.55 - samples/sec: 1857.13 - lr: 0.000048 - momentum: 0.000000
95
+ 2024-03-26 09:40:11,830 epoch 2 - iter 36/95 - loss 0.45498260 - time (sec): 7.31 - samples/sec: 1828.20 - lr: 0.000048 - momentum: 0.000000
96
+ 2024-03-26 09:40:13,733 epoch 2 - iter 45/95 - loss 0.42599735 - time (sec): 9.22 - samples/sec: 1837.36 - lr: 0.000047 - momentum: 0.000000
97
+ 2024-03-26 09:40:15,932 epoch 2 - iter 54/95 - loss 0.39935025 - time (sec): 11.42 - samples/sec: 1808.62 - lr: 0.000047 - momentum: 0.000000
98
+ 2024-03-26 09:40:17,254 epoch 2 - iter 63/95 - loss 0.39798422 - time (sec): 12.74 - samples/sec: 1849.41 - lr: 0.000046 - momentum: 0.000000
99
+ 2024-03-26 09:40:18,582 epoch 2 - iter 72/95 - loss 0.38729757 - time (sec): 14.07 - samples/sec: 1880.73 - lr: 0.000046 - momentum: 0.000000
100
+ 2024-03-26 09:40:20,377 epoch 2 - iter 81/95 - loss 0.37731322 - time (sec): 15.86 - samples/sec: 1866.35 - lr: 0.000045 - momentum: 0.000000
101
+ 2024-03-26 09:40:22,028 epoch 2 - iter 90/95 - loss 0.36835332 - time (sec): 17.51 - samples/sec: 1863.65 - lr: 0.000045 - momentum: 0.000000
102
+ 2024-03-26 09:40:22,959 ----------------------------------------------------------------------------------------------------
103
+ 2024-03-26 09:40:22,959 EPOCH 2 done: loss 0.3625 - lr: 0.000045
104
+ 2024-03-26 09:40:23,850 DEV : loss 0.2613222301006317 - f1-score (micro avg) 0.8448
105
+ 2024-03-26 09:40:23,851 saving best model
106
+ 2024-03-26 09:40:24,277 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 09:40:26,224 epoch 3 - iter 9/95 - loss 0.29508313 - time (sec): 1.95 - samples/sec: 1724.83 - lr: 0.000044 - momentum: 0.000000
108
+ 2024-03-26 09:40:28,144 epoch 3 - iter 18/95 - loss 0.25482220 - time (sec): 3.87 - samples/sec: 1740.63 - lr: 0.000043 - momentum: 0.000000
109
+ 2024-03-26 09:40:29,490 epoch 3 - iter 27/95 - loss 0.23523110 - time (sec): 5.21 - samples/sec: 1835.40 - lr: 0.000043 - momentum: 0.000000
110
+ 2024-03-26 09:40:31,951 epoch 3 - iter 36/95 - loss 0.22688565 - time (sec): 7.67 - samples/sec: 1762.04 - lr: 0.000042 - momentum: 0.000000
111
+ 2024-03-26 09:40:34,173 epoch 3 - iter 45/95 - loss 0.21492865 - time (sec): 9.89 - samples/sec: 1794.15 - lr: 0.000042 - momentum: 0.000000
112
+ 2024-03-26 09:40:35,332 epoch 3 - iter 54/95 - loss 0.21043158 - time (sec): 11.05 - samples/sec: 1853.67 - lr: 0.000041 - momentum: 0.000000
113
+ 2024-03-26 09:40:37,247 epoch 3 - iter 63/95 - loss 0.20029173 - time (sec): 12.97 - samples/sec: 1836.73 - lr: 0.000041 - momentum: 0.000000
114
+ 2024-03-26 09:40:38,856 epoch 3 - iter 72/95 - loss 0.19106908 - time (sec): 14.58 - samples/sec: 1842.42 - lr: 0.000040 - momentum: 0.000000
115
+ 2024-03-26 09:40:40,595 epoch 3 - iter 81/95 - loss 0.19348835 - time (sec): 16.32 - samples/sec: 1833.29 - lr: 0.000040 - momentum: 0.000000
116
+ 2024-03-26 09:40:42,760 epoch 3 - iter 90/95 - loss 0.18565234 - time (sec): 18.48 - samples/sec: 1802.35 - lr: 0.000039 - momentum: 0.000000
117
+ 2024-03-26 09:40:43,234 ----------------------------------------------------------------------------------------------------
118
+ 2024-03-26 09:40:43,234 EPOCH 3 done: loss 0.1856 - lr: 0.000039
119
+ 2024-03-26 09:40:44,130 DEV : loss 0.23596186935901642 - f1-score (micro avg) 0.8698
120
+ 2024-03-26 09:40:44,131 saving best model
121
+ 2024-03-26 09:40:44,555 ----------------------------------------------------------------------------------------------------
122
+ 2024-03-26 09:40:46,145 epoch 4 - iter 9/95 - loss 0.14874311 - time (sec): 1.59 - samples/sec: 2028.73 - lr: 0.000039 - momentum: 0.000000
123
+ 2024-03-26 09:40:48,154 epoch 4 - iter 18/95 - loss 0.12660212 - time (sec): 3.60 - samples/sec: 1792.97 - lr: 0.000038 - momentum: 0.000000
124
+ 2024-03-26 09:40:49,928 epoch 4 - iter 27/95 - loss 0.13552995 - time (sec): 5.37 - samples/sec: 1813.99 - lr: 0.000037 - momentum: 0.000000
125
+ 2024-03-26 09:40:52,465 epoch 4 - iter 36/95 - loss 0.11480824 - time (sec): 7.91 - samples/sec: 1742.21 - lr: 0.000037 - momentum: 0.000000
126
+ 2024-03-26 09:40:54,141 epoch 4 - iter 45/95 - loss 0.12251085 - time (sec): 9.58 - samples/sec: 1761.77 - lr: 0.000036 - momentum: 0.000000
127
+ 2024-03-26 09:40:55,663 epoch 4 - iter 54/95 - loss 0.12355944 - time (sec): 11.11 - samples/sec: 1816.10 - lr: 0.000036 - momentum: 0.000000
128
+ 2024-03-26 09:40:57,506 epoch 4 - iter 63/95 - loss 0.12445641 - time (sec): 12.95 - samples/sec: 1838.45 - lr: 0.000035 - momentum: 0.000000
129
+ 2024-03-26 09:40:58,769 epoch 4 - iter 72/95 - loss 0.12555656 - time (sec): 14.21 - samples/sec: 1869.52 - lr: 0.000035 - momentum: 0.000000
130
+ 2024-03-26 09:41:00,477 epoch 4 - iter 81/95 - loss 0.12386474 - time (sec): 15.92 - samples/sec: 1858.83 - lr: 0.000034 - momentum: 0.000000
131
+ 2024-03-26 09:41:01,961 epoch 4 - iter 90/95 - loss 0.12057520 - time (sec): 17.40 - samples/sec: 1879.79 - lr: 0.000034 - momentum: 0.000000
132
+ 2024-03-26 09:41:02,859 ----------------------------------------------------------------------------------------------------
133
+ 2024-03-26 09:41:02,859 EPOCH 4 done: loss 0.1194 - lr: 0.000034
134
+ 2024-03-26 09:41:03,820 DEV : loss 0.19999347627162933 - f1-score (micro avg) 0.901
135
+ 2024-03-26 09:41:03,822 saving best model
136
+ 2024-03-26 09:41:04,250 ----------------------------------------------------------------------------------------------------
137
+ 2024-03-26 09:41:05,898 epoch 5 - iter 9/95 - loss 0.07573403 - time (sec): 1.65 - samples/sec: 1922.66 - lr: 0.000033 - momentum: 0.000000
138
+ 2024-03-26 09:41:08,022 epoch 5 - iter 18/95 - loss 0.07869165 - time (sec): 3.77 - samples/sec: 1777.86 - lr: 0.000032 - momentum: 0.000000
139
+ 2024-03-26 09:41:09,581 epoch 5 - iter 27/95 - loss 0.07792090 - time (sec): 5.33 - samples/sec: 1820.04 - lr: 0.000032 - momentum: 0.000000
140
+ 2024-03-26 09:41:11,245 epoch 5 - iter 36/95 - loss 0.08045788 - time (sec): 6.99 - samples/sec: 1803.86 - lr: 0.000031 - momentum: 0.000000
141
+ 2024-03-26 09:41:12,916 epoch 5 - iter 45/95 - loss 0.08891161 - time (sec): 8.66 - samples/sec: 1851.54 - lr: 0.000031 - momentum: 0.000000
142
+ 2024-03-26 09:41:14,512 epoch 5 - iter 54/95 - loss 0.09411735 - time (sec): 10.26 - samples/sec: 1895.46 - lr: 0.000030 - momentum: 0.000000
143
+ 2024-03-26 09:41:16,339 epoch 5 - iter 63/95 - loss 0.09161241 - time (sec): 12.09 - samples/sec: 1874.42 - lr: 0.000030 - momentum: 0.000000
144
+ 2024-03-26 09:41:18,555 epoch 5 - iter 72/95 - loss 0.08398116 - time (sec): 14.30 - samples/sec: 1897.22 - lr: 0.000029 - momentum: 0.000000
145
+ 2024-03-26 09:41:19,793 epoch 5 - iter 81/95 - loss 0.08584221 - time (sec): 15.54 - samples/sec: 1916.06 - lr: 0.000029 - momentum: 0.000000
146
+ 2024-03-26 09:41:21,926 epoch 5 - iter 90/95 - loss 0.08331687 - time (sec): 17.67 - samples/sec: 1873.64 - lr: 0.000028 - momentum: 0.000000
147
+ 2024-03-26 09:41:22,547 ----------------------------------------------------------------------------------------------------
148
+ 2024-03-26 09:41:22,547 EPOCH 5 done: loss 0.0837 - lr: 0.000028
149
+ 2024-03-26 09:41:23,531 DEV : loss 0.18806229531764984 - f1-score (micro avg) 0.911
150
+ 2024-03-26 09:41:23,532 saving best model
151
+ 2024-03-26 09:41:23,936 ----------------------------------------------------------------------------------------------------
152
+ 2024-03-26 09:41:25,491 epoch 6 - iter 9/95 - loss 0.04652808 - time (sec): 1.55 - samples/sec: 1859.82 - lr: 0.000027 - momentum: 0.000000
153
+ 2024-03-26 09:41:27,487 epoch 6 - iter 18/95 - loss 0.06784961 - time (sec): 3.55 - samples/sec: 1847.95 - lr: 0.000027 - momentum: 0.000000
154
+ 2024-03-26 09:41:29,145 epoch 6 - iter 27/95 - loss 0.07010724 - time (sec): 5.21 - samples/sec: 1887.21 - lr: 0.000026 - momentum: 0.000000
155
+ 2024-03-26 09:41:30,788 epoch 6 - iter 36/95 - loss 0.06725345 - time (sec): 6.85 - samples/sec: 1849.66 - lr: 0.000026 - momentum: 0.000000
156
+ 2024-03-26 09:41:32,367 epoch 6 - iter 45/95 - loss 0.06885703 - time (sec): 8.43 - samples/sec: 1865.39 - lr: 0.000025 - momentum: 0.000000
157
+ 2024-03-26 09:41:34,350 epoch 6 - iter 54/95 - loss 0.06740445 - time (sec): 10.41 - samples/sec: 1846.29 - lr: 0.000025 - momentum: 0.000000
158
+ 2024-03-26 09:41:35,908 epoch 6 - iter 63/95 - loss 0.07108303 - time (sec): 11.97 - samples/sec: 1846.54 - lr: 0.000024 - momentum: 0.000000
159
+ 2024-03-26 09:41:38,697 epoch 6 - iter 72/95 - loss 0.06547846 - time (sec): 14.76 - samples/sec: 1806.63 - lr: 0.000024 - momentum: 0.000000
160
+ 2024-03-26 09:41:40,524 epoch 6 - iter 81/95 - loss 0.06482397 - time (sec): 16.59 - samples/sec: 1815.43 - lr: 0.000023 - momentum: 0.000000
161
+ 2024-03-26 09:41:42,179 epoch 6 - iter 90/95 - loss 0.06574631 - time (sec): 18.24 - samples/sec: 1809.61 - lr: 0.000023 - momentum: 0.000000
162
+ 2024-03-26 09:41:42,794 ----------------------------------------------------------------------------------------------------
163
+ 2024-03-26 09:41:42,795 EPOCH 6 done: loss 0.0667 - lr: 0.000023
164
+ 2024-03-26 09:41:43,692 DEV : loss 0.174924835562706 - f1-score (micro avg) 0.9185
165
+ 2024-03-26 09:41:43,693 saving best model
166
+ 2024-03-26 09:41:44,116 ----------------------------------------------------------------------------------------------------
167
+ 2024-03-26 09:41:45,420 epoch 7 - iter 9/95 - loss 0.06767963 - time (sec): 1.30 - samples/sec: 2270.48 - lr: 0.000022 - momentum: 0.000000
168
+ 2024-03-26 09:41:47,027 epoch 7 - iter 18/95 - loss 0.06888470 - time (sec): 2.91 - samples/sec: 2018.29 - lr: 0.000021 - momentum: 0.000000
169
+ 2024-03-26 09:41:48,805 epoch 7 - iter 27/95 - loss 0.06592699 - time (sec): 4.69 - samples/sec: 1949.91 - lr: 0.000021 - momentum: 0.000000
170
+ 2024-03-26 09:41:50,655 epoch 7 - iter 36/95 - loss 0.05818934 - time (sec): 6.54 - samples/sec: 1913.50 - lr: 0.000020 - momentum: 0.000000
171
+ 2024-03-26 09:41:52,926 epoch 7 - iter 45/95 - loss 0.05334698 - time (sec): 8.81 - samples/sec: 1860.40 - lr: 0.000020 - momentum: 0.000000
172
+ 2024-03-26 09:41:53,898 epoch 7 - iter 54/95 - loss 0.05494572 - time (sec): 9.78 - samples/sec: 1936.94 - lr: 0.000019 - momentum: 0.000000
173
+ 2024-03-26 09:41:55,732 epoch 7 - iter 63/95 - loss 0.05116780 - time (sec): 11.61 - samples/sec: 1936.77 - lr: 0.000019 - momentum: 0.000000
174
+ 2024-03-26 09:41:57,627 epoch 7 - iter 72/95 - loss 0.04795444 - time (sec): 13.51 - samples/sec: 1895.98 - lr: 0.000018 - momentum: 0.000000
175
+ 2024-03-26 09:41:59,541 epoch 7 - iter 81/95 - loss 0.04872493 - time (sec): 15.42 - samples/sec: 1893.01 - lr: 0.000018 - momentum: 0.000000
176
+ 2024-03-26 09:42:01,463 epoch 7 - iter 90/95 - loss 0.04880589 - time (sec): 17.35 - samples/sec: 1895.49 - lr: 0.000017 - momentum: 0.000000
177
+ 2024-03-26 09:42:02,287 ----------------------------------------------------------------------------------------------------
178
+ 2024-03-26 09:42:02,287 EPOCH 7 done: loss 0.0481 - lr: 0.000017
179
+ 2024-03-26 09:42:03,187 DEV : loss 0.1872955858707428 - f1-score (micro avg) 0.92
180
+ 2024-03-26 09:42:03,188 saving best model
181
+ 2024-03-26 09:42:03,612 ----------------------------------------------------------------------------------------------------
182
+ 2024-03-26 09:42:05,211 epoch 8 - iter 9/95 - loss 0.04073955 - time (sec): 1.60 - samples/sec: 1872.84 - lr: 0.000016 - momentum: 0.000000
183
+ 2024-03-26 09:42:07,208 epoch 8 - iter 18/95 - loss 0.03528090 - time (sec): 3.59 - samples/sec: 1692.16 - lr: 0.000016 - momentum: 0.000000
184
+ 2024-03-26 09:42:08,761 epoch 8 - iter 27/95 - loss 0.04052889 - time (sec): 5.15 - samples/sec: 1788.69 - lr: 0.000015 - momentum: 0.000000
185
+ 2024-03-26 09:42:10,474 epoch 8 - iter 36/95 - loss 0.04517583 - time (sec): 6.86 - samples/sec: 1835.26 - lr: 0.000015 - momentum: 0.000000
186
+ 2024-03-26 09:42:12,770 epoch 8 - iter 45/95 - loss 0.03767857 - time (sec): 9.16 - samples/sec: 1815.74 - lr: 0.000014 - momentum: 0.000000
187
+ 2024-03-26 09:42:15,060 epoch 8 - iter 54/95 - loss 0.03986219 - time (sec): 11.45 - samples/sec: 1819.38 - lr: 0.000014 - momentum: 0.000000
188
+ 2024-03-26 09:42:17,011 epoch 8 - iter 63/95 - loss 0.04051201 - time (sec): 13.40 - samples/sec: 1822.54 - lr: 0.000013 - momentum: 0.000000
189
+ 2024-03-26 09:42:18,089 epoch 8 - iter 72/95 - loss 0.03988279 - time (sec): 14.47 - samples/sec: 1855.07 - lr: 0.000013 - momentum: 0.000000
190
+ 2024-03-26 09:42:19,748 epoch 8 - iter 81/95 - loss 0.03860408 - time (sec): 16.13 - samples/sec: 1839.72 - lr: 0.000012 - momentum: 0.000000
191
+ 2024-03-26 09:42:21,104 epoch 8 - iter 90/95 - loss 0.03816824 - time (sec): 17.49 - samples/sec: 1855.88 - lr: 0.000012 - momentum: 0.000000
192
+ 2024-03-26 09:42:22,312 ----------------------------------------------------------------------------------------------------
193
+ 2024-03-26 09:42:22,312 EPOCH 8 done: loss 0.0396 - lr: 0.000012
194
+ 2024-03-26 09:42:23,209 DEV : loss 0.18396545946598053 - f1-score (micro avg) 0.9319
195
+ 2024-03-26 09:42:23,210 saving best model
196
+ 2024-03-26 09:42:23,634 ----------------------------------------------------------------------------------------------------
197
+ 2024-03-26 09:42:25,375 epoch 9 - iter 9/95 - loss 0.01845985 - time (sec): 1.74 - samples/sec: 1997.59 - lr: 0.000011 - momentum: 0.000000
198
+ 2024-03-26 09:42:27,288 epoch 9 - iter 18/95 - loss 0.01833515 - time (sec): 3.65 - samples/sec: 1849.94 - lr: 0.000010 - momentum: 0.000000
199
+ 2024-03-26 09:42:29,101 epoch 9 - iter 27/95 - loss 0.02202731 - time (sec): 5.47 - samples/sec: 1797.96 - lr: 0.000010 - momentum: 0.000000
200
+ 2024-03-26 09:42:30,945 epoch 9 - iter 36/95 - loss 0.03266732 - time (sec): 7.31 - samples/sec: 1842.06 - lr: 0.000009 - momentum: 0.000000
201
+ 2024-03-26 09:42:32,805 epoch 9 - iter 45/95 - loss 0.02971071 - time (sec): 9.17 - samples/sec: 1818.40 - lr: 0.000009 - momentum: 0.000000
202
+ 2024-03-26 09:42:34,629 epoch 9 - iter 54/95 - loss 0.02917467 - time (sec): 10.99 - samples/sec: 1850.50 - lr: 0.000008 - momentum: 0.000000
203
+ 2024-03-26 09:42:36,484 epoch 9 - iter 63/95 - loss 0.02881615 - time (sec): 12.85 - samples/sec: 1848.20 - lr: 0.000008 - momentum: 0.000000
204
+ 2024-03-26 09:42:38,047 epoch 9 - iter 72/95 - loss 0.03226438 - time (sec): 14.41 - samples/sec: 1857.67 - lr: 0.000007 - momentum: 0.000000
205
+ 2024-03-26 09:42:39,732 epoch 9 - iter 81/95 - loss 0.03501505 - time (sec): 16.10 - samples/sec: 1847.40 - lr: 0.000007 - momentum: 0.000000
206
+ 2024-03-26 09:42:41,468 epoch 9 - iter 90/95 - loss 0.03249197 - time (sec): 17.83 - samples/sec: 1864.18 - lr: 0.000006 - momentum: 0.000000
207
+ 2024-03-26 09:42:41,959 ----------------------------------------------------------------------------------------------------
208
+ 2024-03-26 09:42:41,959 EPOCH 9 done: loss 0.0336 - lr: 0.000006
209
+ 2024-03-26 09:42:42,855 DEV : loss 0.17702238261699677 - f1-score (micro avg) 0.9415
210
+ 2024-03-26 09:42:42,856 saving best model
211
+ 2024-03-26 09:42:43,284 ----------------------------------------------------------------------------------------------------
212
+ 2024-03-26 09:42:44,746 epoch 10 - iter 9/95 - loss 0.00570096 - time (sec): 1.46 - samples/sec: 1901.64 - lr: 0.000005 - momentum: 0.000000
213
+ 2024-03-26 09:42:46,561 epoch 10 - iter 18/95 - loss 0.01306014 - time (sec): 3.28 - samples/sec: 1845.46 - lr: 0.000005 - momentum: 0.000000
214
+ 2024-03-26 09:42:48,768 epoch 10 - iter 27/95 - loss 0.02043505 - time (sec): 5.48 - samples/sec: 1763.51 - lr: 0.000004 - momentum: 0.000000
215
+ 2024-03-26 09:42:50,611 epoch 10 - iter 36/95 - loss 0.02853352 - time (sec): 7.33 - samples/sec: 1790.46 - lr: 0.000004 - momentum: 0.000000
216
+ 2024-03-26 09:42:51,766 epoch 10 - iter 45/95 - loss 0.02757904 - time (sec): 8.48 - samples/sec: 1848.38 - lr: 0.000003 - momentum: 0.000000
217
+ 2024-03-26 09:42:53,667 epoch 10 - iter 54/95 - loss 0.03013318 - time (sec): 10.38 - samples/sec: 1834.01 - lr: 0.000003 - momentum: 0.000000
218
+ 2024-03-26 09:42:55,048 epoch 10 - iter 63/95 - loss 0.03142502 - time (sec): 11.76 - samples/sec: 1847.45 - lr: 0.000002 - momentum: 0.000000
219
+ 2024-03-26 09:42:57,280 epoch 10 - iter 72/95 - loss 0.02735320 - time (sec): 13.99 - samples/sec: 1830.31 - lr: 0.000002 - momentum: 0.000000
220
+ 2024-03-26 09:42:59,572 epoch 10 - iter 81/95 - loss 0.03121748 - time (sec): 16.29 - samples/sec: 1813.03 - lr: 0.000001 - momentum: 0.000000
221
+ 2024-03-26 09:43:01,405 epoch 10 - iter 90/95 - loss 0.02889432 - time (sec): 18.12 - samples/sec: 1806.66 - lr: 0.000001 - momentum: 0.000000
222
+ 2024-03-26 09:43:02,414 ----------------------------------------------------------------------------------------------------
223
+ 2024-03-26 09:43:02,414 EPOCH 10 done: loss 0.0278 - lr: 0.000001
224
+ 2024-03-26 09:43:03,313 DEV : loss 0.18273191154003143 - f1-score (micro avg) 0.9477
225
+ 2024-03-26 09:43:03,314 saving best model
226
+ 2024-03-26 09:43:04,053 ----------------------------------------------------------------------------------------------------
227
+ 2024-03-26 09:43:04,053 Loading model from best epoch ...
228
+ 2024-03-26 09:43:04,938 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
229
+ 2024-03-26 09:43:05,688
230
+ Results:
231
+ - F-score (micro) 0.918
232
+ - F-score (macro) 0.696
233
+ - Accuracy 0.8509
234
+
235
+ By class:
236
+ precision recall f1-score support
237
+
238
+ Unternehmen 0.9294 0.8910 0.9098 266
239
+ Auslagerung 0.8779 0.9237 0.9002 249
240
+ Ort 0.9635 0.9851 0.9742 134
241
+ Software 0.0000 0.0000 0.0000 0
242
+
243
+ micro avg 0.9131 0.9230 0.9180 649
244
+ macro avg 0.6927 0.6999 0.6960 649
245
+ weighted avg 0.9167 0.9230 0.9194 649
246
+
247
+ 2024-03-26 09:43:05,688 ----------------------------------------------------------------------------------------------------