Hugging Face's logo

stefan-it
/
flair-co-funer-german_dbmdz_bert_base-bs8-e10-lr3e-05-2

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
hetzner
hetzner-gex44
hetzner-gpu
Model card Files
xet
Metrics Community
2
stefan-it commited on
Commit
5bf8763
·
verified ·
1 Parent(s): 4c4a5bb

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 15:40:12,486 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 15:40:12,486 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 15:40:12,486 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 15:40:12,487 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 15:40:12,487 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 15:40:12,487 Train: 758 sentences
54
+ 2024-03-26 15:40:12,487 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 15:40:12,487 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 15:40:12,487 Training Params:
57
+ 2024-03-26 15:40:12,487 - learning_rate: "3e-05"
58
+ 2024-03-26 15:40:12,487 - mini_batch_size: "8"
59
+ 2024-03-26 15:40:12,487 - max_epochs: "10"
60
+ 2024-03-26 15:40:12,487 - shuffle: "True"
61
+ 2024-03-26 15:40:12,487 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 15:40:12,487 Plugins:
63
+ 2024-03-26 15:40:12,487 - TensorboardLogger
64
+ 2024-03-26 15:40:12,487 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 15:40:12,487 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 15:40:12,487 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 15:40:12,487 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 15:40:12,487 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 15:40:12,487 Computation:
70
+ 2024-03-26 15:40:12,487 - compute on device: cuda:0
71
+ 2024-03-26 15:40:12,487 - embedding storage: none
72
+ 2024-03-26 15:40:12,487 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 15:40:12,487 Model training base path: "flair-co-funer-german_dbmdz_bert_base-bs8-e10-lr3e-05-2"
74
+ 2024-03-26 15:40:12,487 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 15:40:12,487 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 15:40:12,487 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 15:40:14,307 epoch 1 - iter 9/95 - loss 3.06540800 - time (sec): 1.82 - samples/sec: 1935.79 - lr: 0.000003 - momentum: 0.000000
78
+ 2024-03-26 15:40:16,395 epoch 1 - iter 18/95 - loss 2.98543676 - time (sec): 3.91 - samples/sec: 1844.22 - lr: 0.000005 - momentum: 0.000000
79
+ 2024-03-26 15:40:17,950 epoch 1 - iter 27/95 - loss 2.82818511 - time (sec): 5.46 - samples/sec: 1845.71 - lr: 0.000008 - momentum: 0.000000
80
+ 2024-03-26 15:40:19,874 epoch 1 - iter 36/95 - loss 2.64677852 - time (sec): 7.39 - samples/sec: 1868.41 - lr: 0.000011 - momentum: 0.000000
81
+ 2024-03-26 15:40:21,944 epoch 1 - iter 45/95 - loss 2.48493169 - time (sec): 9.46 - samples/sec: 1802.88 - lr: 0.000014 - momentum: 0.000000
82
+ 2024-03-26 15:40:23,899 epoch 1 - iter 54/95 - loss 2.34259258 - time (sec): 11.41 - samples/sec: 1779.43 - lr: 0.000017 - momentum: 0.000000
83
+ 2024-03-26 15:40:25,435 epoch 1 - iter 63/95 - loss 2.22525861 - time (sec): 12.95 - samples/sec: 1786.68 - lr: 0.000020 - momentum: 0.000000
84
+ 2024-03-26 15:40:26,692 epoch 1 - iter 72/95 - loss 2.10777242 - time (sec): 14.21 - samples/sec: 1840.95 - lr: 0.000022 - momentum: 0.000000
85
+ 2024-03-26 15:40:28,235 epoch 1 - iter 81/95 - loss 1.99428411 - time (sec): 15.75 - samples/sec: 1867.99 - lr: 0.000025 - momentum: 0.000000
86
+ 2024-03-26 15:40:30,167 epoch 1 - iter 90/95 - loss 1.88297203 - time (sec): 17.68 - samples/sec: 1844.46 - lr: 0.000028 - momentum: 0.000000
87
+ 2024-03-26 15:40:31,213 ----------------------------------------------------------------------------------------------------
88
+ 2024-03-26 15:40:31,213 EPOCH 1 done: loss 1.8180 - lr: 0.000028
89
+ 2024-03-26 15:40:32,187 DEV : loss 0.5155203342437744 - f1-score (micro avg) 0.6383
90
+ 2024-03-26 15:40:32,188 saving best model
91
+ 2024-03-26 15:40:32,460 ----------------------------------------------------------------------------------------------------
92
+ 2024-03-26 15:40:33,765 epoch 2 - iter 9/95 - loss 0.73800033 - time (sec): 1.30 - samples/sec: 2486.66 - lr: 0.000030 - momentum: 0.000000
93
+ 2024-03-26 15:40:35,631 epoch 2 - iter 18/95 - loss 0.59456126 - time (sec): 3.17 - samples/sec: 2166.51 - lr: 0.000029 - momentum: 0.000000
94
+ 2024-03-26 15:40:38,431 epoch 2 - iter 27/95 - loss 0.49498182 - time (sec): 5.97 - samples/sec: 1935.89 - lr: 0.000029 - momentum: 0.000000
95
+ 2024-03-26 15:40:40,488 epoch 2 - iter 36/95 - loss 0.46708892 - time (sec): 8.03 - samples/sec: 1851.97 - lr: 0.000029 - momentum: 0.000000
96
+ 2024-03-26 15:40:42,235 epoch 2 - iter 45/95 - loss 0.43499089 - time (sec): 9.77 - samples/sec: 1838.88 - lr: 0.000028 - momentum: 0.000000
97
+ 2024-03-26 15:40:44,315 epoch 2 - iter 54/95 - loss 0.42013650 - time (sec): 11.85 - samples/sec: 1794.88 - lr: 0.000028 - momentum: 0.000000
98
+ 2024-03-26 15:40:45,836 epoch 2 - iter 63/95 - loss 0.42234655 - time (sec): 13.38 - samples/sec: 1819.56 - lr: 0.000028 - momentum: 0.000000
99
+ 2024-03-26 15:40:47,314 epoch 2 - iter 72/95 - loss 0.41658737 - time (sec): 14.85 - samples/sec: 1846.84 - lr: 0.000028 - momentum: 0.000000
100
+ 2024-03-26 15:40:48,477 epoch 2 - iter 81/95 - loss 0.41208706 - time (sec): 16.02 - samples/sec: 1881.01 - lr: 0.000027 - momentum: 0.000000
101
+ 2024-03-26 15:40:49,745 epoch 2 - iter 90/95 - loss 0.40602769 - time (sec): 17.28 - samples/sec: 1903.37 - lr: 0.000027 - momentum: 0.000000
102
+ 2024-03-26 15:40:50,697 ----------------------------------------------------------------------------------------------------
103
+ 2024-03-26 15:40:50,697 EPOCH 2 done: loss 0.3967 - lr: 0.000027
104
+ 2024-03-26 15:40:51,586 DEV : loss 0.26970556378364563 - f1-score (micro avg) 0.8238
105
+ 2024-03-26 15:40:51,587 saving best model
106
+ 2024-03-26 15:40:52,052 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 15:40:54,053 epoch 3 - iter 9/95 - loss 0.20835677 - time (sec): 2.00 - samples/sec: 1665.21 - lr: 0.000026 - momentum: 0.000000
108
+ 2024-03-26 15:40:56,093 epoch 3 - iter 18/95 - loss 0.23115316 - time (sec): 4.04 - samples/sec: 1797.95 - lr: 0.000026 - momentum: 0.000000
109
+ 2024-03-26 15:40:57,044 epoch 3 - iter 27/95 - loss 0.25465988 - time (sec): 4.99 - samples/sec: 1928.66 - lr: 0.000026 - momentum: 0.000000
110
+ 2024-03-26 15:40:58,765 epoch 3 - iter 36/95 - loss 0.25192352 - time (sec): 6.71 - samples/sec: 1890.69 - lr: 0.000025 - momentum: 0.000000
111
+ 2024-03-26 15:41:00,010 epoch 3 - iter 45/95 - loss 0.25628493 - time (sec): 7.96 - samples/sec: 1935.91 - lr: 0.000025 - momentum: 0.000000
112
+ 2024-03-26 15:41:02,022 epoch 3 - iter 54/95 - loss 0.24802067 - time (sec): 9.97 - samples/sec: 1875.48 - lr: 0.000025 - momentum: 0.000000
113
+ 2024-03-26 15:41:03,625 epoch 3 - iter 63/95 - loss 0.24391783 - time (sec): 11.57 - samples/sec: 1886.39 - lr: 0.000025 - momentum: 0.000000
114
+ 2024-03-26 15:41:05,125 epoch 3 - iter 72/95 - loss 0.23907559 - time (sec): 13.07 - samples/sec: 1895.63 - lr: 0.000024 - momentum: 0.000000
115
+ 2024-03-26 15:41:06,904 epoch 3 - iter 81/95 - loss 0.23408928 - time (sec): 14.85 - samples/sec: 1882.53 - lr: 0.000024 - momentum: 0.000000
116
+ 2024-03-26 15:41:09,491 epoch 3 - iter 90/95 - loss 0.21349430 - time (sec): 17.44 - samples/sec: 1875.49 - lr: 0.000024 - momentum: 0.000000
117
+ 2024-03-26 15:41:10,573 ----------------------------------------------------------------------------------------------------
118
+ 2024-03-26 15:41:10,573 EPOCH 3 done: loss 0.2095 - lr: 0.000024
119
+ 2024-03-26 15:41:11,463 DEV : loss 0.23282712697982788 - f1-score (micro avg) 0.8548
120
+ 2024-03-26 15:41:11,464 saving best model
121
+ 2024-03-26 15:41:11,911 ----------------------------------------------------------------------------------------------------
122
+ 2024-03-26 15:41:13,575 epoch 4 - iter 9/95 - loss 0.18254107 - time (sec): 1.66 - samples/sec: 1934.22 - lr: 0.000023 - momentum: 0.000000
123
+ 2024-03-26 15:41:15,532 epoch 4 - iter 18/95 - loss 0.15909112 - time (sec): 3.62 - samples/sec: 1861.36 - lr: 0.000023 - momentum: 0.000000
124
+ 2024-03-26 15:41:16,741 epoch 4 - iter 27/95 - loss 0.15496899 - time (sec): 4.83 - samples/sec: 1949.69 - lr: 0.000022 - momentum: 0.000000
125
+ 2024-03-26 15:41:18,372 epoch 4 - iter 36/95 - loss 0.15784319 - time (sec): 6.46 - samples/sec: 1922.03 - lr: 0.000022 - momentum: 0.000000
126
+ 2024-03-26 15:41:20,490 epoch 4 - iter 45/95 - loss 0.15558124 - time (sec): 8.58 - samples/sec: 1861.76 - lr: 0.000022 - momentum: 0.000000
127
+ 2024-03-26 15:41:22,003 epoch 4 - iter 54/95 - loss 0.15932292 - time (sec): 10.09 - samples/sec: 1870.48 - lr: 0.000022 - momentum: 0.000000
128
+ 2024-03-26 15:41:24,413 epoch 4 - iter 63/95 - loss 0.15131129 - time (sec): 12.50 - samples/sec: 1823.95 - lr: 0.000021 - momentum: 0.000000
129
+ 2024-03-26 15:41:26,887 epoch 4 - iter 72/95 - loss 0.14104034 - time (sec): 14.97 - samples/sec: 1786.51 - lr: 0.000021 - momentum: 0.000000
130
+ 2024-03-26 15:41:28,301 epoch 4 - iter 81/95 - loss 0.14018074 - time (sec): 16.39 - samples/sec: 1793.26 - lr: 0.000021 - momentum: 0.000000
131
+ 2024-03-26 15:41:30,052 epoch 4 - iter 90/95 - loss 0.13938696 - time (sec): 18.14 - samples/sec: 1793.47 - lr: 0.000020 - momentum: 0.000000
132
+ 2024-03-26 15:41:31,154 ----------------------------------------------------------------------------------------------------
133
+ 2024-03-26 15:41:31,154 EPOCH 4 done: loss 0.1367 - lr: 0.000020
134
+ 2024-03-26 15:41:32,048 DEV : loss 0.20248137414455414 - f1-score (micro avg) 0.897
135
+ 2024-03-26 15:41:32,049 saving best model
136
+ 2024-03-26 15:41:32,514 ----------------------------------------------------------------------------------------------------
137
+ 2024-03-26 15:41:33,481 epoch 5 - iter 9/95 - loss 0.08003747 - time (sec): 0.96 - samples/sec: 2134.72 - lr: 0.000020 - momentum: 0.000000
138
+ 2024-03-26 15:41:35,145 epoch 5 - iter 18/95 - loss 0.10141185 - time (sec): 2.63 - samples/sec: 2024.88 - lr: 0.000019 - momentum: 0.000000
139
+ 2024-03-26 15:41:37,601 epoch 5 - iter 27/95 - loss 0.10479908 - time (sec): 5.08 - samples/sec: 1792.94 - lr: 0.000019 - momentum: 0.000000
140
+ 2024-03-26 15:41:39,428 epoch 5 - iter 36/95 - loss 0.09976634 - time (sec): 6.91 - samples/sec: 1795.08 - lr: 0.000019 - momentum: 0.000000
141
+ 2024-03-26 15:41:41,371 epoch 5 - iter 45/95 - loss 0.09450519 - time (sec): 8.85 - samples/sec: 1765.26 - lr: 0.000019 - momentum: 0.000000
142
+ 2024-03-26 15:41:42,973 epoch 5 - iter 54/95 - loss 0.09640069 - time (sec): 10.46 - samples/sec: 1801.98 - lr: 0.000018 - momentum: 0.000000
143
+ 2024-03-26 15:41:45,300 epoch 5 - iter 63/95 - loss 0.09570810 - time (sec): 12.78 - samples/sec: 1791.60 - lr: 0.000018 - momentum: 0.000000
144
+ 2024-03-26 15:41:46,701 epoch 5 - iter 72/95 - loss 0.10087366 - time (sec): 14.18 - samples/sec: 1810.86 - lr: 0.000018 - momentum: 0.000000
145
+ 2024-03-26 15:41:48,581 epoch 5 - iter 81/95 - loss 0.09656308 - time (sec): 16.06 - samples/sec: 1787.55 - lr: 0.000017 - momentum: 0.000000
146
+ 2024-03-26 15:41:50,426 epoch 5 - iter 90/95 - loss 0.09544348 - time (sec): 17.91 - samples/sec: 1789.75 - lr: 0.000017 - momentum: 0.000000
147
+ 2024-03-26 15:41:51,773 ----------------------------------------------------------------------------------------------------
148
+ 2024-03-26 15:41:51,773 EPOCH 5 done: loss 0.0957 - lr: 0.000017
149
+ 2024-03-26 15:41:52,658 DEV : loss 0.18282510340213776 - f1-score (micro avg) 0.9018
150
+ 2024-03-26 15:41:52,659 saving best model
151
+ 2024-03-26 15:41:53,118 ----------------------------------------------------------------------------------------------------
152
+ 2024-03-26 15:41:54,488 epoch 6 - iter 9/95 - loss 0.05876429 - time (sec): 1.37 - samples/sec: 2104.44 - lr: 0.000016 - momentum: 0.000000
153
+ 2024-03-26 15:41:56,637 epoch 6 - iter 18/95 - loss 0.06157639 - time (sec): 3.52 - samples/sec: 2038.65 - lr: 0.000016 - momentum: 0.000000
154
+ 2024-03-26 15:41:58,197 epoch 6 - iter 27/95 - loss 0.05890095 - time (sec): 5.08 - samples/sec: 1977.70 - lr: 0.000016 - momentum: 0.000000
155
+ 2024-03-26 15:42:00,164 epoch 6 - iter 36/95 - loss 0.06546844 - time (sec): 7.04 - samples/sec: 1916.54 - lr: 0.000016 - momentum: 0.000000
156
+ 2024-03-26 15:42:02,301 epoch 6 - iter 45/95 - loss 0.07740664 - time (sec): 9.18 - samples/sec: 1934.90 - lr: 0.000015 - momentum: 0.000000
157
+ 2024-03-26 15:42:03,487 epoch 6 - iter 54/95 - loss 0.07626467 - time (sec): 10.37 - samples/sec: 1950.01 - lr: 0.000015 - momentum: 0.000000
158
+ 2024-03-26 15:42:04,553 epoch 6 - iter 63/95 - loss 0.07604980 - time (sec): 11.43 - samples/sec: 1969.14 - lr: 0.000015 - momentum: 0.000000
159
+ 2024-03-26 15:42:06,088 epoch 6 - iter 72/95 - loss 0.07068612 - time (sec): 12.97 - samples/sec: 1968.89 - lr: 0.000014 - momentum: 0.000000
160
+ 2024-03-26 15:42:08,085 epoch 6 - iter 81/95 - loss 0.06914491 - time (sec): 14.97 - samples/sec: 1953.49 - lr: 0.000014 - momentum: 0.000000
161
+ 2024-03-26 15:42:10,065 epoch 6 - iter 90/95 - loss 0.06921921 - time (sec): 16.95 - samples/sec: 1940.92 - lr: 0.000014 - momentum: 0.000000
162
+ 2024-03-26 15:42:10,988 ----------------------------------------------------------------------------------------------------
163
+ 2024-03-26 15:42:10,988 EPOCH 6 done: loss 0.0677 - lr: 0.000014
164
+ 2024-03-26 15:42:11,881 DEV : loss 0.18957725167274475 - f1-score (micro avg) 0.9152
165
+ 2024-03-26 15:42:11,882 saving best model
166
+ 2024-03-26 15:42:12,331 ----------------------------------------------------------------------------------------------------
167
+ 2024-03-26 15:42:13,762 epoch 7 - iter 9/95 - loss 0.04478296 - time (sec): 1.43 - samples/sec: 1859.67 - lr: 0.000013 - momentum: 0.000000
168
+ 2024-03-26 15:42:15,536 epoch 7 - iter 18/95 - loss 0.05377288 - time (sec): 3.20 - samples/sec: 1809.15 - lr: 0.000013 - momentum: 0.000000
169
+ 2024-03-26 15:42:17,129 epoch 7 - iter 27/95 - loss 0.05538811 - time (sec): 4.80 - samples/sec: 1901.87 - lr: 0.000013 - momentum: 0.000000
170
+ 2024-03-26 15:42:18,829 epoch 7 - iter 36/95 - loss 0.05372464 - time (sec): 6.50 - samples/sec: 1851.31 - lr: 0.000012 - momentum: 0.000000
171
+ 2024-03-26 15:42:20,180 epoch 7 - iter 45/95 - loss 0.05305431 - time (sec): 7.85 - samples/sec: 1868.49 - lr: 0.000012 - momentum: 0.000000
172
+ 2024-03-26 15:42:22,222 epoch 7 - iter 54/95 - loss 0.05387578 - time (sec): 9.89 - samples/sec: 1812.68 - lr: 0.000012 - momentum: 0.000000
173
+ 2024-03-26 15:42:24,451 epoch 7 - iter 63/95 - loss 0.05309062 - time (sec): 12.12 - samples/sec: 1761.72 - lr: 0.000011 - momentum: 0.000000
174
+ 2024-03-26 15:42:26,980 epoch 7 - iter 72/95 - loss 0.06066650 - time (sec): 14.65 - samples/sec: 1760.08 - lr: 0.000011 - momentum: 0.000000
175
+ 2024-03-26 15:42:28,904 epoch 7 - iter 81/95 - loss 0.06401076 - time (sec): 16.57 - samples/sec: 1768.68 - lr: 0.000011 - momentum: 0.000000
176
+ 2024-03-26 15:42:30,861 epoch 7 - iter 90/95 - loss 0.06500645 - time (sec): 18.53 - samples/sec: 1769.11 - lr: 0.000010 - momentum: 0.000000
177
+ 2024-03-26 15:42:31,750 ----------------------------------------------------------------------------------------------------
178
+ 2024-03-26 15:42:31,750 EPOCH 7 done: loss 0.0635 - lr: 0.000010
179
+ 2024-03-26 15:42:32,643 DEV : loss 0.1907779574394226 - f1-score (micro avg) 0.9114
180
+ 2024-03-26 15:42:32,644 ----------------------------------------------------------------------------------------------------
181
+ 2024-03-26 15:42:34,896 epoch 8 - iter 9/95 - loss 0.04036110 - time (sec): 2.25 - samples/sec: 1682.42 - lr: 0.000010 - momentum: 0.000000
182
+ 2024-03-26 15:42:36,441 epoch 8 - iter 18/95 - loss 0.04551092 - time (sec): 3.80 - samples/sec: 1814.98 - lr: 0.000010 - momentum: 0.000000
183
+ 2024-03-26 15:42:38,602 epoch 8 - iter 27/95 - loss 0.06111466 - time (sec): 5.96 - samples/sec: 1774.69 - lr: 0.000009 - momentum: 0.000000
184
+ 2024-03-26 15:42:40,144 epoch 8 - iter 36/95 - loss 0.05495416 - time (sec): 7.50 - samples/sec: 1799.10 - lr: 0.000009 - momentum: 0.000000
185
+ 2024-03-26 15:42:42,001 epoch 8 - iter 45/95 - loss 0.04865017 - time (sec): 9.36 - samples/sec: 1779.30 - lr: 0.000009 - momentum: 0.000000
186
+ 2024-03-26 15:42:43,679 epoch 8 - iter 54/95 - loss 0.05233134 - time (sec): 11.03 - samples/sec: 1790.25 - lr: 0.000008 - momentum: 0.000000
187
+ 2024-03-26 15:42:45,475 epoch 8 - iter 63/95 - loss 0.05181467 - time (sec): 12.83 - samples/sec: 1789.75 - lr: 0.000008 - momentum: 0.000000
188
+ 2024-03-26 15:42:46,781 epoch 8 - iter 72/95 - loss 0.05009695 - time (sec): 14.14 - samples/sec: 1809.59 - lr: 0.000008 - momentum: 0.000000
189
+ 2024-03-26 15:42:48,603 epoch 8 - iter 81/95 - loss 0.04968315 - time (sec): 15.96 - samples/sec: 1834.68 - lr: 0.000007 - momentum: 0.000000
190
+ 2024-03-26 15:42:51,006 epoch 8 - iter 90/95 - loss 0.04619173 - time (sec): 18.36 - samples/sec: 1796.39 - lr: 0.000007 - momentum: 0.000000
191
+ 2024-03-26 15:42:51,812 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 15:42:51,812 EPOCH 8 done: loss 0.0468 - lr: 0.000007
193
+ 2024-03-26 15:42:52,710 DEV : loss 0.2047257125377655 - f1-score (micro avg) 0.9243
194
+ 2024-03-26 15:42:52,712 saving best model
195
+ 2024-03-26 15:42:53,147 ----------------------------------------------------------------------------------------------------
196
+ 2024-03-26 15:42:54,962 epoch 9 - iter 9/95 - loss 0.06070442 - time (sec): 1.81 - samples/sec: 1872.51 - lr: 0.000007 - momentum: 0.000000
197
+ 2024-03-26 15:42:57,140 epoch 9 - iter 18/95 - loss 0.04271149 - time (sec): 3.99 - samples/sec: 1737.27 - lr: 0.000006 - momentum: 0.000000
198
+ 2024-03-26 15:42:59,012 epoch 9 - iter 27/95 - loss 0.04904370 - time (sec): 5.86 - samples/sec: 1779.69 - lr: 0.000006 - momentum: 0.000000
199
+ 2024-03-26 15:43:00,548 epoch 9 - iter 36/95 - loss 0.04849692 - time (sec): 7.40 - samples/sec: 1794.15 - lr: 0.000006 - momentum: 0.000000
200
+ 2024-03-26 15:43:01,950 epoch 9 - iter 45/95 - loss 0.04227572 - time (sec): 8.80 - samples/sec: 1832.77 - lr: 0.000005 - momentum: 0.000000
201
+ 2024-03-26 15:43:03,351 epoch 9 - iter 54/95 - loss 0.03939595 - time (sec): 10.20 - samples/sec: 1885.07 - lr: 0.000005 - momentum: 0.000000
202
+ 2024-03-26 15:43:05,159 epoch 9 - iter 63/95 - loss 0.04440370 - time (sec): 12.01 - samples/sec: 1892.31 - lr: 0.000005 - momentum: 0.000000
203
+ 2024-03-26 15:43:07,159 epoch 9 - iter 72/95 - loss 0.04368057 - time (sec): 14.01 - samples/sec: 1864.39 - lr: 0.000004 - momentum: 0.000000
204
+ 2024-03-26 15:43:09,427 epoch 9 - iter 81/95 - loss 0.04508413 - time (sec): 16.28 - samples/sec: 1823.20 - lr: 0.000004 - momentum: 0.000000
205
+ 2024-03-26 15:43:11,154 epoch 9 - iter 90/95 - loss 0.04367290 - time (sec): 18.01 - samples/sec: 1838.28 - lr: 0.000004 - momentum: 0.000000
206
+ 2024-03-26 15:43:11,741 ----------------------------------------------------------------------------------------------------
207
+ 2024-03-26 15:43:11,741 EPOCH 9 done: loss 0.0428 - lr: 0.000004
208
+ 2024-03-26 15:43:12,644 DEV : loss 0.2012164443731308 - f1-score (micro avg) 0.9366
209
+ 2024-03-26 15:43:12,645 saving best model
210
+ 2024-03-26 15:43:13,084 ----------------------------------------------------------------------------------------------------
211
+ 2024-03-26 15:43:15,135 epoch 10 - iter 9/95 - loss 0.01028236 - time (sec): 2.05 - samples/sec: 1883.95 - lr: 0.000003 - momentum: 0.000000
212
+ 2024-03-26 15:43:16,888 epoch 10 - iter 18/95 - loss 0.02145361 - time (sec): 3.80 - samples/sec: 1868.01 - lr: 0.000003 - momentum: 0.000000
213
+ 2024-03-26 15:43:17,991 epoch 10 - iter 27/95 - loss 0.01929684 - time (sec): 4.91 - samples/sec: 1941.57 - lr: 0.000003 - momentum: 0.000000
214
+ 2024-03-26 15:43:19,424 epoch 10 - iter 36/95 - loss 0.02733041 - time (sec): 6.34 - samples/sec: 1975.04 - lr: 0.000002 - momentum: 0.000000
215
+ 2024-03-26 15:43:21,362 epoch 10 - iter 45/95 - loss 0.03522743 - time (sec): 8.28 - samples/sec: 1907.13 - lr: 0.000002 - momentum: 0.000000
216
+ 2024-03-26 15:43:22,448 epoch 10 - iter 54/95 - loss 0.03959733 - time (sec): 9.36 - samples/sec: 1955.17 - lr: 0.000002 - momentum: 0.000000
217
+ 2024-03-26 15:43:23,670 epoch 10 - iter 63/95 - loss 0.03591018 - time (sec): 10.58 - samples/sec: 1982.36 - lr: 0.000001 - momentum: 0.000000
218
+ 2024-03-26 15:43:25,572 epoch 10 - iter 72/95 - loss 0.03543953 - time (sec): 12.49 - samples/sec: 1977.49 - lr: 0.000001 - momentum: 0.000000
219
+ 2024-03-26 15:43:28,209 epoch 10 - iter 81/95 - loss 0.03611102 - time (sec): 15.12 - samples/sec: 1936.80 - lr: 0.000001 - momentum: 0.000000
220
+ 2024-03-26 15:43:30,214 epoch 10 - iter 90/95 - loss 0.03608582 - time (sec): 17.13 - samples/sec: 1915.57 - lr: 0.000000 - momentum: 0.000000
221
+ 2024-03-26 15:43:31,130 ----------------------------------------------------------------------------------------------------
222
+ 2024-03-26 15:43:31,130 EPOCH 10 done: loss 0.0358 - lr: 0.000000
223
+ 2024-03-26 15:43:32,026 DEV : loss 0.20790590345859528 - f1-score (micro avg) 0.9267
224
+ 2024-03-26 15:43:32,318 ----------------------------------------------------------------------------------------------------
225
+ 2024-03-26 15:43:32,319 Loading model from best epoch ...
226
+ 2024-03-26 15:43:33,177 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 15:43:33,917
228
+ Results:
229
+ - F-score (micro) 0.9072
230
+ - F-score (macro) 0.6888
231
+ - Accuracy 0.8336
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ Unternehmen 0.8969 0.8835 0.8902 266
237
+ Auslagerung 0.8707 0.9197 0.8945 249
238
+ Ort 0.9565 0.9851 0.9706 134
239
+ Software 0.0000 0.0000 0.0000 0
240
+
241
+ micro avg 0.8962 0.9183 0.9072 649
242
+ macro avg 0.6810 0.6971 0.6888 649
243
+ weighted avg 0.8992 0.9183 0.9084 649
244
+
245
+ 2024-03-26 15:43:33,917 ----------------------------------------------------------------------------------------------------