Hugging Face's logo

stefan-it
/
flair-co-funer-german_bert_base-bs8-e10-lr5e-05-5

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
f5b5899
•
1 Parent(s): 0be9f14

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 12:16:08,752 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 12:16:08,752 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(30001, 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 12:16:08,752 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 12:16:08,752 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 12:16:08,752 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 12:16:08,752 Train: 758 sentences
54
+ 2024-03-26 12:16:08,752 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 12:16:08,752 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 12:16:08,752 Training Params:
57
+ 2024-03-26 12:16:08,752 - learning_rate: "5e-05"
58
+ 2024-03-26 12:16:08,752 - mini_batch_size: "8"
59
+ 2024-03-26 12:16:08,752 - max_epochs: "10"
60
+ 2024-03-26 12:16:08,752 - shuffle: "True"
61
+ 2024-03-26 12:16:08,752 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 12:16:08,752 Plugins:
63
+ 2024-03-26 12:16:08,752 - TensorboardLogger
64
+ 2024-03-26 12:16:08,752 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 12:16:08,752 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 12:16:08,752 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 12:16:08,752 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 12:16:08,752 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 12:16:08,752 Computation:
70
+ 2024-03-26 12:16:08,752 - compute on device: cuda:0
71
+ 2024-03-26 12:16:08,752 - embedding storage: none
72
+ 2024-03-26 12:16:08,752 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 12:16:08,752 Model training base path: "flair-co-funer-german_bert_base-bs8-e10-lr5e-05-5"
74
+ 2024-03-26 12:16:08,752 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 12:16:08,752 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 12:16:08,753 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 12:16:10,658 epoch 1 - iter 9/95 - loss 3.11198415 - time (sec): 1.91 - samples/sec: 1645.31 - lr: 0.000004 - momentum: 0.000000
78
+ 2024-03-26 12:16:12,565 epoch 1 - iter 18/95 - loss 2.93717664 - time (sec): 3.81 - samples/sec: 1739.78 - lr: 0.000009 - momentum: 0.000000
79
+ 2024-03-26 12:16:14,989 epoch 1 - iter 27/95 - loss 2.69525162 - time (sec): 6.24 - samples/sec: 1663.01 - lr: 0.000014 - momentum: 0.000000
80
+ 2024-03-26 12:16:16,504 epoch 1 - iter 36/95 - loss 2.50040802 - time (sec): 7.75 - samples/sec: 1742.82 - lr: 0.000018 - momentum: 0.000000
81
+ 2024-03-26 12:16:18,693 epoch 1 - iter 45/95 - loss 2.31776846 - time (sec): 9.94 - samples/sec: 1728.92 - lr: 0.000023 - momentum: 0.000000
82
+ 2024-03-26 12:16:20,306 epoch 1 - iter 54/95 - loss 2.14521065 - time (sec): 11.55 - samples/sec: 1751.33 - lr: 0.000028 - momentum: 0.000000
83
+ 2024-03-26 12:16:21,980 epoch 1 - iter 63/95 - loss 1.99301232 - time (sec): 13.23 - samples/sec: 1769.35 - lr: 0.000033 - momentum: 0.000000
84
+ 2024-03-26 12:16:23,916 epoch 1 - iter 72/95 - loss 1.84828066 - time (sec): 15.16 - samples/sec: 1760.81 - lr: 0.000037 - momentum: 0.000000
85
+ 2024-03-26 12:16:26,005 epoch 1 - iter 81/95 - loss 1.70543233 - time (sec): 17.25 - samples/sec: 1747.54 - lr: 0.000042 - momentum: 0.000000
86
+ 2024-03-26 12:16:27,656 epoch 1 - iter 90/95 - loss 1.60560457 - time (sec): 18.90 - samples/sec: 1741.84 - lr: 0.000047 - momentum: 0.000000
87
+ 2024-03-26 12:16:28,437 ----------------------------------------------------------------------------------------------------
88
+ 2024-03-26 12:16:28,437 EPOCH 1 done: loss 1.5561 - lr: 0.000047
89
+ 2024-03-26 12:16:29,291 DEV : loss 0.3953661024570465 - f1-score (micro avg) 0.7299
90
+ 2024-03-26 12:16:29,292 saving best model
91
+ 2024-03-26 12:16:29,557 ----------------------------------------------------------------------------------------------------
92
+ 2024-03-26 12:16:31,857 epoch 2 - iter 9/95 - loss 0.42411772 - time (sec): 2.30 - samples/sec: 1659.61 - lr: 0.000050 - momentum: 0.000000
93
+ 2024-03-26 12:16:33,790 epoch 2 - iter 18/95 - loss 0.40210576 - time (sec): 4.23 - samples/sec: 1652.57 - lr: 0.000049 - momentum: 0.000000
94
+ 2024-03-26 12:16:36,173 epoch 2 - iter 27/95 - loss 0.37000509 - time (sec): 6.62 - samples/sec: 1616.94 - lr: 0.000048 - momentum: 0.000000
95
+ 2024-03-26 12:16:37,537 epoch 2 - iter 36/95 - loss 0.36304993 - time (sec): 7.98 - samples/sec: 1731.82 - lr: 0.000048 - momentum: 0.000000
96
+ 2024-03-26 12:16:39,517 epoch 2 - iter 45/95 - loss 0.34645812 - time (sec): 9.96 - samples/sec: 1694.75 - lr: 0.000047 - momentum: 0.000000
97
+ 2024-03-26 12:16:40,851 epoch 2 - iter 54/95 - loss 0.34203299 - time (sec): 11.29 - samples/sec: 1740.46 - lr: 0.000047 - momentum: 0.000000
98
+ 2024-03-26 12:16:42,447 epoch 2 - iter 63/95 - loss 0.33030418 - time (sec): 12.89 - samples/sec: 1755.81 - lr: 0.000046 - momentum: 0.000000
99
+ 2024-03-26 12:16:44,546 epoch 2 - iter 72/95 - loss 0.32731874 - time (sec): 14.99 - samples/sec: 1748.69 - lr: 0.000046 - momentum: 0.000000
100
+ 2024-03-26 12:16:46,462 epoch 2 - iter 81/95 - loss 0.33534075 - time (sec): 16.90 - samples/sec: 1750.65 - lr: 0.000045 - momentum: 0.000000
101
+ 2024-03-26 12:16:48,417 epoch 2 - iter 90/95 - loss 0.32353294 - time (sec): 18.86 - samples/sec: 1753.84 - lr: 0.000045 - momentum: 0.000000
102
+ 2024-03-26 12:16:48,995 ----------------------------------------------------------------------------------------------------
103
+ 2024-03-26 12:16:48,995 EPOCH 2 done: loss 0.3240 - lr: 0.000045
104
+ 2024-03-26 12:16:49,916 DEV : loss 0.2869855463504791 - f1-score (micro avg) 0.8389
105
+ 2024-03-26 12:16:49,917 saving best model
106
+ 2024-03-26 12:16:50,346 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 12:16:51,570 epoch 3 - iter 9/95 - loss 0.27417263 - time (sec): 1.22 - samples/sec: 2120.71 - lr: 0.000044 - momentum: 0.000000
108
+ 2024-03-26 12:16:53,842 epoch 3 - iter 18/95 - loss 0.21977563 - time (sec): 3.49 - samples/sec: 1837.05 - lr: 0.000043 - momentum: 0.000000
109
+ 2024-03-26 12:16:55,561 epoch 3 - iter 27/95 - loss 0.22232998 - time (sec): 5.21 - samples/sec: 1871.79 - lr: 0.000043 - momentum: 0.000000
110
+ 2024-03-26 12:16:57,399 epoch 3 - iter 36/95 - loss 0.21205041 - time (sec): 7.05 - samples/sec: 1867.67 - lr: 0.000042 - momentum: 0.000000
111
+ 2024-03-26 12:16:58,861 epoch 3 - iter 45/95 - loss 0.19668558 - time (sec): 8.51 - samples/sec: 1865.50 - lr: 0.000042 - momentum: 0.000000
112
+ 2024-03-26 12:17:01,066 epoch 3 - iter 54/95 - loss 0.19132023 - time (sec): 10.72 - samples/sec: 1802.40 - lr: 0.000041 - momentum: 0.000000
113
+ 2024-03-26 12:17:02,798 epoch 3 - iter 63/95 - loss 0.19343591 - time (sec): 12.45 - samples/sec: 1787.69 - lr: 0.000041 - momentum: 0.000000
114
+ 2024-03-26 12:17:05,134 epoch 3 - iter 72/95 - loss 0.18645392 - time (sec): 14.79 - samples/sec: 1754.33 - lr: 0.000040 - momentum: 0.000000
115
+ 2024-03-26 12:17:07,392 epoch 3 - iter 81/95 - loss 0.18633466 - time (sec): 17.04 - samples/sec: 1746.40 - lr: 0.000040 - momentum: 0.000000
116
+ 2024-03-26 12:17:09,149 epoch 3 - iter 90/95 - loss 0.18210534 - time (sec): 18.80 - samples/sec: 1740.35 - lr: 0.000039 - momentum: 0.000000
117
+ 2024-03-26 12:17:10,046 ----------------------------------------------------------------------------------------------------
118
+ 2024-03-26 12:17:10,046 EPOCH 3 done: loss 0.1812 - lr: 0.000039
119
+ 2024-03-26 12:17:10,972 DEV : loss 0.23773233592510223 - f1-score (micro avg) 0.874
120
+ 2024-03-26 12:17:10,973 saving best model
121
+ 2024-03-26 12:17:11,406 ----------------------------------------------------------------------------------------------------
122
+ 2024-03-26 12:17:14,332 epoch 4 - iter 9/95 - loss 0.09110161 - time (sec): 2.92 - samples/sec: 1458.90 - lr: 0.000039 - momentum: 0.000000
123
+ 2024-03-26 12:17:15,394 epoch 4 - iter 18/95 - loss 0.11946256 - time (sec): 3.99 - samples/sec: 1669.22 - lr: 0.000038 - momentum: 0.000000
124
+ 2024-03-26 12:17:18,006 epoch 4 - iter 27/95 - loss 0.11225660 - time (sec): 6.60 - samples/sec: 1612.05 - lr: 0.000037 - momentum: 0.000000
125
+ 2024-03-26 12:17:20,657 epoch 4 - iter 36/95 - loss 0.10969523 - time (sec): 9.25 - samples/sec: 1568.83 - lr: 0.000037 - momentum: 0.000000
126
+ 2024-03-26 12:17:22,378 epoch 4 - iter 45/95 - loss 0.10414682 - time (sec): 10.97 - samples/sec: 1605.33 - lr: 0.000036 - momentum: 0.000000
127
+ 2024-03-26 12:17:24,113 epoch 4 - iter 54/95 - loss 0.10683855 - time (sec): 12.71 - samples/sec: 1621.28 - lr: 0.000036 - momentum: 0.000000
128
+ 2024-03-26 12:17:26,080 epoch 4 - iter 63/95 - loss 0.10871462 - time (sec): 14.67 - samples/sec: 1646.34 - lr: 0.000035 - momentum: 0.000000
129
+ 2024-03-26 12:17:27,836 epoch 4 - iter 72/95 - loss 0.11330020 - time (sec): 16.43 - samples/sec: 1689.44 - lr: 0.000035 - momentum: 0.000000
130
+ 2024-03-26 12:17:28,871 epoch 4 - iter 81/95 - loss 0.11517013 - time (sec): 17.46 - samples/sec: 1730.13 - lr: 0.000034 - momentum: 0.000000
131
+ 2024-03-26 12:17:30,331 epoch 4 - iter 90/95 - loss 0.11512696 - time (sec): 18.92 - samples/sec: 1753.74 - lr: 0.000034 - momentum: 0.000000
132
+ 2024-03-26 12:17:30,885 ----------------------------------------------------------------------------------------------------
133
+ 2024-03-26 12:17:30,885 EPOCH 4 done: loss 0.1159 - lr: 0.000034
134
+ 2024-03-26 12:17:31,816 DEV : loss 0.1792612224817276 - f1-score (micro avg) 0.8988
135
+ 2024-03-26 12:17:31,817 saving best model
136
+ 2024-03-26 12:17:32,249 ----------------------------------------------------------------------------------------------------
137
+ 2024-03-26 12:17:33,905 epoch 5 - iter 9/95 - loss 0.10687482 - time (sec): 1.65 - samples/sec: 1979.76 - lr: 0.000033 - momentum: 0.000000
138
+ 2024-03-26 12:17:35,911 epoch 5 - iter 18/95 - loss 0.08268843 - time (sec): 3.66 - samples/sec: 1945.00 - lr: 0.000032 - momentum: 0.000000
139
+ 2024-03-26 12:17:38,085 epoch 5 - iter 27/95 - loss 0.07045579 - time (sec): 5.83 - samples/sec: 1814.52 - lr: 0.000032 - momentum: 0.000000
140
+ 2024-03-26 12:17:39,453 epoch 5 - iter 36/95 - loss 0.08169072 - time (sec): 7.20 - samples/sec: 1866.69 - lr: 0.000031 - momentum: 0.000000
141
+ 2024-03-26 12:17:41,576 epoch 5 - iter 45/95 - loss 0.07912089 - time (sec): 9.33 - samples/sec: 1827.05 - lr: 0.000031 - momentum: 0.000000
142
+ 2024-03-26 12:17:42,773 epoch 5 - iter 54/95 - loss 0.08168215 - time (sec): 10.52 - samples/sec: 1860.75 - lr: 0.000030 - momentum: 0.000000
143
+ 2024-03-26 12:17:44,288 epoch 5 - iter 63/95 - loss 0.08776931 - time (sec): 12.04 - samples/sec: 1872.91 - lr: 0.000030 - momentum: 0.000000
144
+ 2024-03-26 12:17:46,330 epoch 5 - iter 72/95 - loss 0.08910227 - time (sec): 14.08 - samples/sec: 1834.21 - lr: 0.000029 - momentum: 0.000000
145
+ 2024-03-26 12:17:48,138 epoch 5 - iter 81/95 - loss 0.08562803 - time (sec): 15.89 - samples/sec: 1823.20 - lr: 0.000029 - momentum: 0.000000
146
+ 2024-03-26 12:17:50,604 epoch 5 - iter 90/95 - loss 0.08505748 - time (sec): 18.35 - samples/sec: 1791.38 - lr: 0.000028 - momentum: 0.000000
147
+ 2024-03-26 12:17:51,604 ----------------------------------------------------------------------------------------------------
148
+ 2024-03-26 12:17:51,604 EPOCH 5 done: loss 0.0832 - lr: 0.000028
149
+ 2024-03-26 12:17:52,535 DEV : loss 0.19528663158416748 - f1-score (micro avg) 0.902
150
+ 2024-03-26 12:17:52,536 saving best model
151
+ 2024-03-26 12:17:52,967 ----------------------------------------------------------------------------------------------------
152
+ 2024-03-26 12:17:54,978 epoch 6 - iter 9/95 - loss 0.07127974 - time (sec): 2.01 - samples/sec: 1623.06 - lr: 0.000027 - momentum: 0.000000
153
+ 2024-03-26 12:17:57,485 epoch 6 - iter 18/95 - loss 0.07270535 - time (sec): 4.52 - samples/sec: 1641.86 - lr: 0.000027 - momentum: 0.000000
154
+ 2024-03-26 12:17:58,659 epoch 6 - iter 27/95 - loss 0.08746512 - time (sec): 5.69 - samples/sec: 1737.38 - lr: 0.000026 - momentum: 0.000000
155
+ 2024-03-26 12:18:00,368 epoch 6 - iter 36/95 - loss 0.07826196 - time (sec): 7.40 - samples/sec: 1743.94 - lr: 0.000026 - momentum: 0.000000
156
+ 2024-03-26 12:18:02,358 epoch 6 - iter 45/95 - loss 0.07323678 - time (sec): 9.39 - samples/sec: 1740.04 - lr: 0.000025 - momentum: 0.000000
157
+ 2024-03-26 12:18:04,568 epoch 6 - iter 54/95 - loss 0.06698128 - time (sec): 11.60 - samples/sec: 1706.05 - lr: 0.000025 - momentum: 0.000000
158
+ 2024-03-26 12:18:06,266 epoch 6 - iter 63/95 - loss 0.06973624 - time (sec): 13.30 - samples/sec: 1727.33 - lr: 0.000024 - momentum: 0.000000
159
+ 2024-03-26 12:18:07,867 epoch 6 - iter 72/95 - loss 0.07049901 - time (sec): 14.90 - samples/sec: 1748.07 - lr: 0.000024 - momentum: 0.000000
160
+ 2024-03-26 12:18:09,132 epoch 6 - iter 81/95 - loss 0.06883005 - time (sec): 16.16 - samples/sec: 1778.42 - lr: 0.000023 - momentum: 0.000000
161
+ 2024-03-26 12:18:11,040 epoch 6 - iter 90/95 - loss 0.06491973 - time (sec): 18.07 - samples/sec: 1778.06 - lr: 0.000023 - momentum: 0.000000
162
+ 2024-03-26 12:18:12,595 ----------------------------------------------------------------------------------------------------
163
+ 2024-03-26 12:18:12,595 EPOCH 6 done: loss 0.0621 - lr: 0.000023
164
+ 2024-03-26 12:18:13,530 DEV : loss 0.21062487363815308 - f1-score (micro avg) 0.9138
165
+ 2024-03-26 12:18:13,531 saving best model
166
+ 2024-03-26 12:18:13,967 ----------------------------------------------------------------------------------------------------
167
+ 2024-03-26 12:18:15,657 epoch 7 - iter 9/95 - loss 0.03135025 - time (sec): 1.69 - samples/sec: 1864.58 - lr: 0.000022 - momentum: 0.000000
168
+ 2024-03-26 12:18:17,178 epoch 7 - iter 18/95 - loss 0.04612086 - time (sec): 3.21 - samples/sec: 1832.91 - lr: 0.000021 - momentum: 0.000000
169
+ 2024-03-26 12:18:18,494 epoch 7 - iter 27/95 - loss 0.06246375 - time (sec): 4.53 - samples/sec: 1871.28 - lr: 0.000021 - momentum: 0.000000
170
+ 2024-03-26 12:18:20,844 epoch 7 - iter 36/95 - loss 0.05586240 - time (sec): 6.87 - samples/sec: 1848.73 - lr: 0.000020 - momentum: 0.000000
171
+ 2024-03-26 12:18:22,814 epoch 7 - iter 45/95 - loss 0.05942577 - time (sec): 8.85 - samples/sec: 1840.86 - lr: 0.000020 - momentum: 0.000000
172
+ 2024-03-26 12:18:24,526 epoch 7 - iter 54/95 - loss 0.05670271 - time (sec): 10.56 - samples/sec: 1836.88 - lr: 0.000019 - momentum: 0.000000
173
+ 2024-03-26 12:18:26,122 epoch 7 - iter 63/95 - loss 0.05494130 - time (sec): 12.15 - samples/sec: 1854.57 - lr: 0.000019 - momentum: 0.000000
174
+ 2024-03-26 12:18:27,660 epoch 7 - iter 72/95 - loss 0.05485412 - time (sec): 13.69 - samples/sec: 1846.14 - lr: 0.000018 - momentum: 0.000000
175
+ 2024-03-26 12:18:30,467 epoch 7 - iter 81/95 - loss 0.05275127 - time (sec): 16.50 - samples/sec: 1780.62 - lr: 0.000018 - momentum: 0.000000
176
+ 2024-03-26 12:18:32,128 epoch 7 - iter 90/95 - loss 0.05187601 - time (sec): 18.16 - samples/sec: 1788.35 - lr: 0.000017 - momentum: 0.000000
177
+ 2024-03-26 12:18:33,304 ----------------------------------------------------------------------------------------------------
178
+ 2024-03-26 12:18:33,304 EPOCH 7 done: loss 0.0513 - lr: 0.000017
179
+ 2024-03-26 12:18:34,241 DEV : loss 0.20660282671451569 - f1-score (micro avg) 0.9272
180
+ 2024-03-26 12:18:34,242 saving best model
181
+ 2024-03-26 12:18:34,679 ----------------------------------------------------------------------------------------------------
182
+ 2024-03-26 12:18:36,879 epoch 8 - iter 9/95 - loss 0.03834922 - time (sec): 2.20 - samples/sec: 1537.49 - lr: 0.000016 - momentum: 0.000000
183
+ 2024-03-26 12:18:38,447 epoch 8 - iter 18/95 - loss 0.02899613 - time (sec): 3.77 - samples/sec: 1620.37 - lr: 0.000016 - momentum: 0.000000
184
+ 2024-03-26 12:18:40,508 epoch 8 - iter 27/95 - loss 0.03237573 - time (sec): 5.83 - samples/sec: 1683.99 - lr: 0.000015 - momentum: 0.000000
185
+ 2024-03-26 12:18:42,512 epoch 8 - iter 36/95 - loss 0.02944665 - time (sec): 7.83 - samples/sec: 1719.11 - lr: 0.000015 - momentum: 0.000000
186
+ 2024-03-26 12:18:43,936 epoch 8 - iter 45/95 - loss 0.02812948 - time (sec): 9.26 - samples/sec: 1778.26 - lr: 0.000014 - momentum: 0.000000
187
+ 2024-03-26 12:18:45,426 epoch 8 - iter 54/95 - loss 0.02849860 - time (sec): 10.74 - samples/sec: 1849.54 - lr: 0.000014 - momentum: 0.000000
188
+ 2024-03-26 12:18:47,076 epoch 8 - iter 63/95 - loss 0.03008751 - time (sec): 12.39 - samples/sec: 1834.71 - lr: 0.000013 - momentum: 0.000000
189
+ 2024-03-26 12:18:49,219 epoch 8 - iter 72/95 - loss 0.02843088 - time (sec): 14.54 - samples/sec: 1800.89 - lr: 0.000013 - momentum: 0.000000
190
+ 2024-03-26 12:18:50,819 epoch 8 - iter 81/95 - loss 0.03172865 - time (sec): 16.14 - samples/sec: 1824.66 - lr: 0.000012 - momentum: 0.000000
191
+ 2024-03-26 12:18:52,888 epoch 8 - iter 90/95 - loss 0.03341049 - time (sec): 18.21 - samples/sec: 1805.85 - lr: 0.000012 - momentum: 0.000000
192
+ 2024-03-26 12:18:53,534 ----------------------------------------------------------------------------------------------------
193
+ 2024-03-26 12:18:53,534 EPOCH 8 done: loss 0.0346 - lr: 0.000012
194
+ 2024-03-26 12:18:54,465 DEV : loss 0.20071536302566528 - f1-score (micro avg) 0.9346
195
+ 2024-03-26 12:18:54,466 saving best model
196
+ 2024-03-26 12:18:54,944 ----------------------------------------------------------------------------------------------------
197
+ 2024-03-26 12:18:57,548 epoch 9 - iter 9/95 - loss 0.01191280 - time (sec): 2.60 - samples/sec: 1656.95 - lr: 0.000011 - momentum: 0.000000
198
+ 2024-03-26 12:18:59,147 epoch 9 - iter 18/95 - loss 0.01847100 - time (sec): 4.20 - samples/sec: 1721.14 - lr: 0.000010 - momentum: 0.000000
199
+ 2024-03-26 12:19:01,758 epoch 9 - iter 27/95 - loss 0.02360116 - time (sec): 6.81 - samples/sec: 1659.11 - lr: 0.000010 - momentum: 0.000000
200
+ 2024-03-26 12:19:03,626 epoch 9 - iter 36/95 - loss 0.02717013 - time (sec): 8.68 - samples/sec: 1669.48 - lr: 0.000009 - momentum: 0.000000
201
+ 2024-03-26 12:19:04,806 epoch 9 - iter 45/95 - loss 0.02510231 - time (sec): 9.86 - samples/sec: 1729.78 - lr: 0.000009 - momentum: 0.000000
202
+ 2024-03-26 12:19:06,575 epoch 9 - iter 54/95 - loss 0.02242460 - time (sec): 11.63 - samples/sec: 1725.14 - lr: 0.000008 - momentum: 0.000000
203
+ 2024-03-26 12:19:07,996 epoch 9 - iter 63/95 - loss 0.02704971 - time (sec): 13.05 - samples/sec: 1769.91 - lr: 0.000008 - momentum: 0.000000
204
+ 2024-03-26 12:19:09,192 epoch 9 - iter 72/95 - loss 0.02678838 - time (sec): 14.25 - samples/sec: 1818.51 - lr: 0.000007 - momentum: 0.000000
205
+ 2024-03-26 12:19:10,741 epoch 9 - iter 81/95 - loss 0.02504760 - time (sec): 15.80 - samples/sec: 1818.68 - lr: 0.000007 - momentum: 0.000000
206
+ 2024-03-26 12:19:13,539 epoch 9 - iter 90/95 - loss 0.02802835 - time (sec): 18.59 - samples/sec: 1773.37 - lr: 0.000006 - momentum: 0.000000
207
+ 2024-03-26 12:19:14,336 ----------------------------------------------------------------------------------------------------
208
+ 2024-03-26 12:19:14,336 EPOCH 9 done: loss 0.0276 - lr: 0.000006
209
+ 2024-03-26 12:19:15,294 DEV : loss 0.2257862389087677 - f1-score (micro avg) 0.9343
210
+ 2024-03-26 12:19:15,295 ----------------------------------------------------------------------------------------------------
211
+ 2024-03-26 12:19:17,811 epoch 10 - iter 9/95 - loss 0.02415602 - time (sec): 2.52 - samples/sec: 1604.40 - lr: 0.000005 - momentum: 0.000000
212
+ 2024-03-26 12:19:19,392 epoch 10 - iter 18/95 - loss 0.02153363 - time (sec): 4.10 - samples/sec: 1702.07 - lr: 0.000005 - momentum: 0.000000
213
+ 2024-03-26 12:19:21,402 epoch 10 - iter 27/95 - loss 0.01906523 - time (sec): 6.11 - samples/sec: 1650.45 - lr: 0.000004 - momentum: 0.000000
214
+ 2024-03-26 12:19:23,503 epoch 10 - iter 36/95 - loss 0.01928902 - time (sec): 8.21 - samples/sec: 1662.79 - lr: 0.000004 - momentum: 0.000000
215
+ 2024-03-26 12:19:25,399 epoch 10 - iter 45/95 - loss 0.01845826 - time (sec): 10.10 - samples/sec: 1678.97 - lr: 0.000003 - momentum: 0.000000
216
+ 2024-03-26 12:19:26,550 epoch 10 - iter 54/95 - loss 0.01897577 - time (sec): 11.25 - samples/sec: 1740.80 - lr: 0.000003 - momentum: 0.000000
217
+ 2024-03-26 12:19:28,216 epoch 10 - iter 63/95 - loss 0.02489403 - time (sec): 12.92 - samples/sec: 1761.30 - lr: 0.000002 - momentum: 0.000000
218
+ 2024-03-26 12:19:30,071 epoch 10 - iter 72/95 - loss 0.02391188 - time (sec): 14.78 - samples/sec: 1750.83 - lr: 0.000002 - momentum: 0.000000
219
+ 2024-03-26 12:19:31,803 epoch 10 - iter 81/95 - loss 0.02463096 - time (sec): 16.51 - samples/sec: 1758.98 - lr: 0.000001 - momentum: 0.000000
220
+ 2024-03-26 12:19:34,650 epoch 10 - iter 90/95 - loss 0.02255689 - time (sec): 19.35 - samples/sec: 1722.51 - lr: 0.000001 - momentum: 0.000000
221
+ 2024-03-26 12:19:35,202 ----------------------------------------------------------------------------------------------------
222
+ 2024-03-26 12:19:35,202 EPOCH 10 done: loss 0.0221 - lr: 0.000001
223
+ 2024-03-26 12:19:36,133 DEV : loss 0.22455048561096191 - f1-score (micro avg) 0.9336
224
+ 2024-03-26 12:19:36,401 ----------------------------------------------------------------------------------------------------
225
+ 2024-03-26 12:19:36,402 Loading model from best epoch ...
226
+ 2024-03-26 12:19:37,342 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 12:19:38,103
228
+ Results:
229
+ - F-score (micro) 0.9105
230
+ - F-score (macro) 0.6913
231
+ - Accuracy 0.8368
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ Unternehmen 0.9151 0.8910 0.9029 266
237
+ Auslagerung 0.8692 0.9076 0.8880 249
238
+ Ort 0.9635 0.9851 0.9742 134
239
+ Software 0.0000 0.0000 0.0000 0
240
+
241
+ micro avg 0.9043 0.9168 0.9105 649
242
+ macro avg 0.6869 0.6959 0.6913 649
243
+ weighted avg 0.9075 0.9168 0.9119 649
244
+
245
+ 2024-03-26 12:19:38,103 ----------------------------------------------------------------------------------------------------