Hugging Face's logo

stefan-it
/
flair-co-funer-german_bert_base-bs16-e10-lr5e-05-4

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
f8c18d8
•
1 Parent(s): 0f798aa

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +264 -0
training.log ADDED
@@ -0,0 +1,264 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-03-26 11:50:32,184 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 11:50:32,184 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 11:50:32,185 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 11:50:32,185 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 11:50:32,185 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 11:50:32,185 Train: 758 sentences
54
+ 2024-03-26 11:50:32,185 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 11:50:32,185 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 11:50:32,185 Training Params:
57
+ 2024-03-26 11:50:32,185 - learning_rate: "5e-05"
58
+ 2024-03-26 11:50:32,185 - mini_batch_size: "16"
59
+ 2024-03-26 11:50:32,185 - max_epochs: "10"
60
+ 2024-03-26 11:50:32,185 - shuffle: "True"
61
+ 2024-03-26 11:50:32,185 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 11:50:32,185 Plugins:
63
+ 2024-03-26 11:50:32,185 - TensorboardLogger
64
+ 2024-03-26 11:50:32,185 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 11:50:32,185 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 11:50:32,185 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 11:50:32,185 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 11:50:32,185 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 11:50:32,185 Computation:
70
+ 2024-03-26 11:50:32,185 - compute on device: cuda:0
71
+ 2024-03-26 11:50:32,185 - embedding storage: none
72
+ 2024-03-26 11:50:32,185 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 11:50:32,185 Model training base path: "flair-co-funer-german_bert_base-bs16-e10-lr5e-05-4"
74
+ 2024-03-26 11:50:32,185 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 11:50:32,185 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 11:50:32,185 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 11:50:33,652 epoch 1 - iter 4/48 - loss 3.09191904 - time (sec): 1.47 - samples/sec: 1778.87 - lr: 0.000003 - momentum: 0.000000
78
+ 2024-03-26 11:50:35,595 epoch 1 - iter 8/48 - loss 3.02643970 - time (sec): 3.41 - samples/sec: 1502.31 - lr: 0.000007 - momentum: 0.000000
79
+ 2024-03-26 11:50:36,980 epoch 1 - iter 12/48 - loss 2.89705049 - time (sec): 4.79 - samples/sec: 1522.91 - lr: 0.000011 - momentum: 0.000000
80
+ 2024-03-26 11:50:39,603 epoch 1 - iter 16/48 - loss 2.67413210 - time (sec): 7.42 - samples/sec: 1442.39 - lr: 0.000016 - momentum: 0.000000
81
+ 2024-03-26 11:50:41,764 epoch 1 - iter 20/48 - loss 2.51616525 - time (sec): 9.58 - samples/sec: 1430.08 - lr: 0.000020 - momentum: 0.000000
82
+ 2024-03-26 11:50:44,429 epoch 1 - iter 24/48 - loss 2.37789495 - time (sec): 12.24 - samples/sec: 1382.39 - lr: 0.000024 - momentum: 0.000000
83
+ 2024-03-26 11:50:47,019 epoch 1 - iter 28/48 - loss 2.24810861 - time (sec): 14.83 - samples/sec: 1367.59 - lr: 0.000028 - momentum: 0.000000
84
+ 2024-03-26 11:50:48,900 epoch 1 - iter 32/48 - loss 2.14871723 - time (sec): 16.71 - samples/sec: 1368.52 - lr: 0.000032 - momentum: 0.000000
85
+ 2024-03-26 11:50:49,846 epoch 1 - iter 36/48 - loss 2.07405562 - time (sec): 17.66 - samples/sec: 1414.47 - lr: 0.000036 - momentum: 0.000000
86
+ 2024-03-26 11:50:51,759 epoch 1 - iter 40/48 - loss 1.96081698 - time (sec): 19.57 - samples/sec: 1422.95 - lr: 0.000041 - momentum: 0.000000
87
+ 2024-03-26 11:50:53,872 epoch 1 - iter 44/48 - loss 1.83563996 - time (sec): 21.69 - samples/sec: 1440.03 - lr: 0.000045 - momentum: 0.000000
88
+ 2024-03-26 11:50:55,635 epoch 1 - iter 48/48 - loss 1.74075518 - time (sec): 23.45 - samples/sec: 1470.02 - lr: 0.000049 - momentum: 0.000000
89
+ 2024-03-26 11:50:55,636 ----------------------------------------------------------------------------------------------------
90
+ 2024-03-26 11:50:55,636 EPOCH 1 done: loss 1.7408 - lr: 0.000049
91
+ 2024-03-26 11:50:56,486 DEV : loss 0.5590143203735352 - f1-score (micro avg) 0.6215
92
+ 2024-03-26 11:50:56,487 saving best model
93
+ 2024-03-26 11:50:56,761 ----------------------------------------------------------------------------------------------------
94
+ 2024-03-26 11:50:58,068 epoch 2 - iter 4/48 - loss 0.74927750 - time (sec): 1.31 - samples/sec: 1813.34 - lr: 0.000050 - momentum: 0.000000
95
+ 2024-03-26 11:51:00,399 epoch 2 - iter 8/48 - loss 0.55633973 - time (sec): 3.64 - samples/sec: 1500.40 - lr: 0.000049 - momentum: 0.000000
96
+ 2024-03-26 11:51:02,248 epoch 2 - iter 12/48 - loss 0.53592159 - time (sec): 5.49 - samples/sec: 1553.43 - lr: 0.000049 - momentum: 0.000000
97
+ 2024-03-26 11:51:04,751 epoch 2 - iter 16/48 - loss 0.48174577 - time (sec): 7.99 - samples/sec: 1412.27 - lr: 0.000048 - momentum: 0.000000
98
+ 2024-03-26 11:51:08,163 epoch 2 - iter 20/48 - loss 0.43660137 - time (sec): 11.40 - samples/sec: 1294.14 - lr: 0.000048 - momentum: 0.000000
99
+ 2024-03-26 11:51:09,690 epoch 2 - iter 24/48 - loss 0.44556220 - time (sec): 12.93 - samples/sec: 1349.19 - lr: 0.000047 - momentum: 0.000000
100
+ 2024-03-26 11:51:12,390 epoch 2 - iter 28/48 - loss 0.43334658 - time (sec): 15.63 - samples/sec: 1324.84 - lr: 0.000047 - momentum: 0.000000
101
+ 2024-03-26 11:51:15,161 epoch 2 - iter 32/48 - loss 0.41770016 - time (sec): 18.40 - samples/sec: 1326.68 - lr: 0.000046 - momentum: 0.000000
102
+ 2024-03-26 11:51:17,310 epoch 2 - iter 36/48 - loss 0.41558433 - time (sec): 20.55 - samples/sec: 1316.12 - lr: 0.000046 - momentum: 0.000000
103
+ 2024-03-26 11:51:19,903 epoch 2 - iter 40/48 - loss 0.40243733 - time (sec): 23.14 - samples/sec: 1304.33 - lr: 0.000046 - momentum: 0.000000
104
+ 2024-03-26 11:51:21,028 epoch 2 - iter 44/48 - loss 0.39684789 - time (sec): 24.27 - samples/sec: 1336.21 - lr: 0.000045 - momentum: 0.000000
105
+ 2024-03-26 11:51:22,215 epoch 2 - iter 48/48 - loss 0.38872982 - time (sec): 25.45 - samples/sec: 1354.35 - lr: 0.000045 - momentum: 0.000000
106
+ 2024-03-26 11:51:22,215 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 11:51:22,215 EPOCH 2 done: loss 0.3887 - lr: 0.000045
108
+ 2024-03-26 11:51:23,158 DEV : loss 0.2667681574821472 - f1-score (micro avg) 0.8317
109
+ 2024-03-26 11:51:23,159 saving best model
110
+ 2024-03-26 11:51:23,612 ----------------------------------------------------------------------------------------------------
111
+ 2024-03-26 11:51:25,734 epoch 3 - iter 4/48 - loss 0.22802041 - time (sec): 2.12 - samples/sec: 1157.60 - lr: 0.000044 - momentum: 0.000000
112
+ 2024-03-26 11:51:27,299 epoch 3 - iter 8/48 - loss 0.17935289 - time (sec): 3.69 - samples/sec: 1299.68 - lr: 0.000044 - momentum: 0.000000
113
+ 2024-03-26 11:51:29,925 epoch 3 - iter 12/48 - loss 0.20412596 - time (sec): 6.31 - samples/sec: 1232.54 - lr: 0.000043 - momentum: 0.000000
114
+ 2024-03-26 11:51:32,088 epoch 3 - iter 16/48 - loss 0.20474341 - time (sec): 8.48 - samples/sec: 1258.27 - lr: 0.000043 - momentum: 0.000000
115
+ 2024-03-26 11:51:34,119 epoch 3 - iter 20/48 - loss 0.20097314 - time (sec): 10.51 - samples/sec: 1317.88 - lr: 0.000042 - momentum: 0.000000
116
+ 2024-03-26 11:51:36,366 epoch 3 - iter 24/48 - loss 0.19596982 - time (sec): 12.75 - samples/sec: 1340.53 - lr: 0.000042 - momentum: 0.000000
117
+ 2024-03-26 11:51:38,961 epoch 3 - iter 28/48 - loss 0.19183246 - time (sec): 15.35 - samples/sec: 1299.58 - lr: 0.000041 - momentum: 0.000000
118
+ 2024-03-26 11:51:41,654 epoch 3 - iter 32/48 - loss 0.18547973 - time (sec): 18.04 - samples/sec: 1274.49 - lr: 0.000041 - momentum: 0.000000
119
+ 2024-03-26 11:51:43,846 epoch 3 - iter 36/48 - loss 0.18265888 - time (sec): 20.23 - samples/sec: 1279.47 - lr: 0.000040 - momentum: 0.000000
120
+ 2024-03-26 11:51:46,235 epoch 3 - iter 40/48 - loss 0.19056221 - time (sec): 22.62 - samples/sec: 1295.44 - lr: 0.000040 - momentum: 0.000000
121
+ 2024-03-26 11:51:48,874 epoch 3 - iter 44/48 - loss 0.18669032 - time (sec): 25.26 - samples/sec: 1279.02 - lr: 0.000040 - momentum: 0.000000
122
+ 2024-03-26 11:51:50,421 epoch 3 - iter 48/48 - loss 0.18771402 - time (sec): 26.81 - samples/sec: 1285.87 - lr: 0.000039 - momentum: 0.000000
123
+ 2024-03-26 11:51:50,422 ----------------------------------------------------------------------------------------------------
124
+ 2024-03-26 11:51:50,422 EPOCH 3 done: loss 0.1877 - lr: 0.000039
125
+ 2024-03-26 11:51:51,355 DEV : loss 0.21384288370609283 - f1-score (micro avg) 0.8696
126
+ 2024-03-26 11:51:51,356 saving best model
127
+ 2024-03-26 11:51:51,792 ----------------------------------------------------------------------------------------------------
128
+ 2024-03-26 11:51:54,910 epoch 4 - iter 4/48 - loss 0.08055261 - time (sec): 3.12 - samples/sec: 1169.44 - lr: 0.000039 - momentum: 0.000000
129
+ 2024-03-26 11:51:56,214 epoch 4 - iter 8/48 - loss 0.09810133 - time (sec): 4.42 - samples/sec: 1330.29 - lr: 0.000038 - momentum: 0.000000
130
+ 2024-03-26 11:51:58,359 epoch 4 - iter 12/48 - loss 0.11670141 - time (sec): 6.57 - samples/sec: 1404.78 - lr: 0.000038 - momentum: 0.000000
131
+ 2024-03-26 11:52:01,056 epoch 4 - iter 16/48 - loss 0.11824326 - time (sec): 9.26 - samples/sec: 1315.21 - lr: 0.000037 - momentum: 0.000000
132
+ 2024-03-26 11:52:02,065 epoch 4 - iter 20/48 - loss 0.11907194 - time (sec): 10.27 - samples/sec: 1398.47 - lr: 0.000037 - momentum: 0.000000
133
+ 2024-03-26 11:52:03,528 epoch 4 - iter 24/48 - loss 0.11905123 - time (sec): 11.74 - samples/sec: 1440.38 - lr: 0.000036 - momentum: 0.000000
134
+ 2024-03-26 11:52:06,697 epoch 4 - iter 28/48 - loss 0.11424266 - time (sec): 14.90 - samples/sec: 1354.19 - lr: 0.000036 - momentum: 0.000000
135
+ 2024-03-26 11:52:09,263 epoch 4 - iter 32/48 - loss 0.12479927 - time (sec): 17.47 - samples/sec: 1346.09 - lr: 0.000035 - momentum: 0.000000
136
+ 2024-03-26 11:52:10,874 epoch 4 - iter 36/48 - loss 0.12327164 - time (sec): 19.08 - samples/sec: 1377.21 - lr: 0.000035 - momentum: 0.000000
137
+ 2024-03-26 11:52:12,915 epoch 4 - iter 40/48 - loss 0.12170118 - time (sec): 21.12 - samples/sec: 1391.90 - lr: 0.000034 - momentum: 0.000000
138
+ 2024-03-26 11:52:14,876 epoch 4 - iter 44/48 - loss 0.12158731 - time (sec): 23.08 - samples/sec: 1405.09 - lr: 0.000034 - momentum: 0.000000
139
+ 2024-03-26 11:52:15,962 epoch 4 - iter 48/48 - loss 0.12234921 - time (sec): 24.17 - samples/sec: 1426.28 - lr: 0.000034 - momentum: 0.000000
140
+ 2024-03-26 11:52:15,962 ----------------------------------------------------------------------------------------------------
141
+ 2024-03-26 11:52:15,962 EPOCH 4 done: loss 0.1223 - lr: 0.000034
142
+ 2024-03-26 11:52:16,902 DEV : loss 0.2320009469985962 - f1-score (micro avg) 0.8838
143
+ 2024-03-26 11:52:16,903 saving best model
144
+ 2024-03-26 11:52:17,342 ----------------------------------------------------------------------------------------------------
145
+ 2024-03-26 11:52:18,454 epoch 5 - iter 4/48 - loss 0.14241480 - time (sec): 1.11 - samples/sec: 2291.05 - lr: 0.000033 - momentum: 0.000000
146
+ 2024-03-26 11:52:20,452 epoch 5 - iter 8/48 - loss 0.12170118 - time (sec): 3.11 - samples/sec: 1666.99 - lr: 0.000033 - momentum: 0.000000
147
+ 2024-03-26 11:52:22,622 epoch 5 - iter 12/48 - loss 0.10872669 - time (sec): 5.28 - samples/sec: 1516.14 - lr: 0.000032 - momentum: 0.000000
148
+ 2024-03-26 11:52:25,017 epoch 5 - iter 16/48 - loss 0.10192099 - time (sec): 7.67 - samples/sec: 1445.48 - lr: 0.000032 - momentum: 0.000000
149
+ 2024-03-26 11:52:27,291 epoch 5 - iter 20/48 - loss 0.10039604 - time (sec): 9.95 - samples/sec: 1375.72 - lr: 0.000031 - momentum: 0.000000
150
+ 2024-03-26 11:52:29,517 epoch 5 - iter 24/48 - loss 0.09677573 - time (sec): 12.17 - samples/sec: 1395.72 - lr: 0.000031 - momentum: 0.000000
151
+ 2024-03-26 11:52:31,245 epoch 5 - iter 28/48 - loss 0.09570667 - time (sec): 13.90 - samples/sec: 1415.80 - lr: 0.000030 - momentum: 0.000000
152
+ 2024-03-26 11:52:33,409 epoch 5 - iter 32/48 - loss 0.08837081 - time (sec): 16.06 - samples/sec: 1438.06 - lr: 0.000030 - momentum: 0.000000
153
+ 2024-03-26 11:52:34,876 epoch 5 - iter 36/48 - loss 0.08830167 - time (sec): 17.53 - samples/sec: 1460.14 - lr: 0.000029 - momentum: 0.000000
154
+ 2024-03-26 11:52:37,584 epoch 5 - iter 40/48 - loss 0.08443272 - time (sec): 20.24 - samples/sec: 1424.26 - lr: 0.000029 - momentum: 0.000000
155
+ 2024-03-26 11:52:40,594 epoch 5 - iter 44/48 - loss 0.08378061 - time (sec): 23.25 - samples/sec: 1377.49 - lr: 0.000029 - momentum: 0.000000
156
+ 2024-03-26 11:52:42,160 epoch 5 - iter 48/48 - loss 0.08478604 - time (sec): 24.82 - samples/sec: 1389.10 - lr: 0.000028 - momentum: 0.000000
157
+ 2024-03-26 11:52:42,160 ----------------------------------------------------------------------------------------------------
158
+ 2024-03-26 11:52:42,160 EPOCH 5 done: loss 0.0848 - lr: 0.000028
159
+ 2024-03-26 11:52:43,122 DEV : loss 0.17314665019512177 - f1-score (micro avg) 0.9055
160
+ 2024-03-26 11:52:43,124 saving best model
161
+ 2024-03-26 11:52:43,574 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 11:52:45,519 epoch 6 - iter 4/48 - loss 0.09272200 - time (sec): 1.94 - samples/sec: 1511.87 - lr: 0.000028 - momentum: 0.000000
163
+ 2024-03-26 11:52:47,296 epoch 6 - iter 8/48 - loss 0.07485378 - time (sec): 3.72 - samples/sec: 1557.93 - lr: 0.000027 - momentum: 0.000000
164
+ 2024-03-26 11:52:49,682 epoch 6 - iter 12/48 - loss 0.07041558 - time (sec): 6.11 - samples/sec: 1443.76 - lr: 0.000027 - momentum: 0.000000
165
+ 2024-03-26 11:52:51,317 epoch 6 - iter 16/48 - loss 0.06510204 - time (sec): 7.74 - samples/sec: 1463.60 - lr: 0.000026 - momentum: 0.000000
166
+ 2024-03-26 11:52:54,012 epoch 6 - iter 20/48 - loss 0.05955492 - time (sec): 10.44 - samples/sec: 1376.47 - lr: 0.000026 - momentum: 0.000000
167
+ 2024-03-26 11:52:56,075 epoch 6 - iter 24/48 - loss 0.06109297 - time (sec): 12.50 - samples/sec: 1399.15 - lr: 0.000025 - momentum: 0.000000
168
+ 2024-03-26 11:52:58,815 epoch 6 - iter 28/48 - loss 0.06141292 - time (sec): 15.24 - samples/sec: 1373.57 - lr: 0.000025 - momentum: 0.000000
169
+ 2024-03-26 11:53:00,923 epoch 6 - iter 32/48 - loss 0.06055801 - time (sec): 17.35 - samples/sec: 1354.68 - lr: 0.000024 - momentum: 0.000000
170
+ 2024-03-26 11:53:02,092 epoch 6 - iter 36/48 - loss 0.06095859 - time (sec): 18.52 - samples/sec: 1400.89 - lr: 0.000024 - momentum: 0.000000
171
+ 2024-03-26 11:53:04,358 epoch 6 - iter 40/48 - loss 0.06004242 - time (sec): 20.78 - samples/sec: 1391.32 - lr: 0.000023 - momentum: 0.000000
172
+ 2024-03-26 11:53:06,050 epoch 6 - iter 44/48 - loss 0.06403233 - time (sec): 22.48 - samples/sec: 1412.70 - lr: 0.000023 - momentum: 0.000000
173
+ 2024-03-26 11:53:07,960 epoch 6 - iter 48/48 - loss 0.06292329 - time (sec): 24.39 - samples/sec: 1413.64 - lr: 0.000023 - momentum: 0.000000
174
+ 2024-03-26 11:53:07,960 ----------------------------------------------------------------------------------------------------
175
+ 2024-03-26 11:53:07,960 EPOCH 6 done: loss 0.0629 - lr: 0.000023
176
+ 2024-03-26 11:53:08,931 DEV : loss 0.189381942152977 - f1-score (micro avg) 0.8991
177
+ 2024-03-26 11:53:08,932 ----------------------------------------------------------------------------------------------------
178
+ 2024-03-26 11:53:10,489 epoch 7 - iter 4/48 - loss 0.04704627 - time (sec): 1.56 - samples/sec: 1797.92 - lr: 0.000022 - momentum: 0.000000
179
+ 2024-03-26 11:53:12,647 epoch 7 - iter 8/48 - loss 0.04048940 - time (sec): 3.71 - samples/sec: 1647.48 - lr: 0.000022 - momentum: 0.000000
180
+ 2024-03-26 11:53:15,007 epoch 7 - iter 12/48 - loss 0.03980474 - time (sec): 6.07 - samples/sec: 1450.14 - lr: 0.000021 - momentum: 0.000000
181
+ 2024-03-26 11:53:16,272 epoch 7 - iter 16/48 - loss 0.04476687 - time (sec): 7.34 - samples/sec: 1533.43 - lr: 0.000021 - momentum: 0.000000
182
+ 2024-03-26 11:53:18,458 epoch 7 - iter 20/48 - loss 0.04349881 - time (sec): 9.52 - samples/sec: 1506.04 - lr: 0.000020 - momentum: 0.000000
183
+ 2024-03-26 11:53:20,044 epoch 7 - iter 24/48 - loss 0.04224759 - time (sec): 11.11 - samples/sec: 1549.09 - lr: 0.000020 - momentum: 0.000000
184
+ 2024-03-26 11:53:22,279 epoch 7 - iter 28/48 - loss 0.04243268 - time (sec): 13.35 - samples/sec: 1504.12 - lr: 0.000019 - momentum: 0.000000
185
+ 2024-03-26 11:53:25,084 epoch 7 - iter 32/48 - loss 0.04481656 - time (sec): 16.15 - samples/sec: 1441.94 - lr: 0.000019 - momentum: 0.000000
186
+ 2024-03-26 11:53:27,217 epoch 7 - iter 36/48 - loss 0.04402562 - time (sec): 18.28 - samples/sec: 1435.12 - lr: 0.000018 - momentum: 0.000000
187
+ 2024-03-26 11:53:28,363 epoch 7 - iter 40/48 - loss 0.04695744 - time (sec): 19.43 - samples/sec: 1466.74 - lr: 0.000018 - momentum: 0.000000
188
+ 2024-03-26 11:53:31,040 epoch 7 - iter 44/48 - loss 0.04939896 - time (sec): 22.11 - samples/sec: 1450.26 - lr: 0.000017 - momentum: 0.000000
189
+ 2024-03-26 11:53:32,211 epoch 7 - iter 48/48 - loss 0.04967125 - time (sec): 23.28 - samples/sec: 1480.83 - lr: 0.000017 - momentum: 0.000000
190
+ 2024-03-26 11:53:32,212 ----------------------------------------------------------------------------------------------------
191
+ 2024-03-26 11:53:32,212 EPOCH 7 done: loss 0.0497 - lr: 0.000017
192
+ 2024-03-26 11:53:33,165 DEV : loss 0.1776585429906845 - f1-score (micro avg) 0.918
193
+ 2024-03-26 11:53:33,166 saving best model
194
+ 2024-03-26 11:53:33,650 ----------------------------------------------------------------------------------------------------
195
+ 2024-03-26 11:53:35,899 epoch 8 - iter 4/48 - loss 0.01606641 - time (sec): 2.25 - samples/sec: 1232.77 - lr: 0.000017 - momentum: 0.000000
196
+ 2024-03-26 11:53:38,601 epoch 8 - iter 8/48 - loss 0.02001419 - time (sec): 4.95 - samples/sec: 1219.97 - lr: 0.000016 - momentum: 0.000000
197
+ 2024-03-26 11:53:40,284 epoch 8 - iter 12/48 - loss 0.01944511 - time (sec): 6.63 - samples/sec: 1278.40 - lr: 0.000016 - momentum: 0.000000
198
+ 2024-03-26 11:53:42,946 epoch 8 - iter 16/48 - loss 0.02496767 - time (sec): 9.30 - samples/sec: 1238.39 - lr: 0.000015 - momentum: 0.000000
199
+ 2024-03-26 11:53:44,682 epoch 8 - iter 20/48 - loss 0.03010170 - time (sec): 11.03 - samples/sec: 1287.97 - lr: 0.000015 - momentum: 0.000000
200
+ 2024-03-26 11:53:46,227 epoch 8 - iter 24/48 - loss 0.03609072 - time (sec): 12.58 - samples/sec: 1351.61 - lr: 0.000014 - momentum: 0.000000
201
+ 2024-03-26 11:53:48,151 epoch 8 - iter 28/48 - loss 0.03779326 - time (sec): 14.50 - samples/sec: 1375.28 - lr: 0.000014 - momentum: 0.000000
202
+ 2024-03-26 11:53:50,870 epoch 8 - iter 32/48 - loss 0.03941547 - time (sec): 17.22 - samples/sec: 1364.27 - lr: 0.000013 - momentum: 0.000000
203
+ 2024-03-26 11:53:53,365 epoch 8 - iter 36/48 - loss 0.03979896 - time (sec): 19.71 - samples/sec: 1355.95 - lr: 0.000013 - momentum: 0.000000
204
+ 2024-03-26 11:53:55,625 epoch 8 - iter 40/48 - loss 0.03932473 - time (sec): 21.97 - samples/sec: 1338.97 - lr: 0.000012 - momentum: 0.000000
205
+ 2024-03-26 11:53:58,043 epoch 8 - iter 44/48 - loss 0.03756691 - time (sec): 24.39 - samples/sec: 1324.33 - lr: 0.000012 - momentum: 0.000000
206
+ 2024-03-26 11:53:59,648 epoch 8 - iter 48/48 - loss 0.03706335 - time (sec): 26.00 - samples/sec: 1325.99 - lr: 0.000011 - momentum: 0.000000
207
+ 2024-03-26 11:53:59,648 ----------------------------------------------------------------------------------------------------
208
+ 2024-03-26 11:53:59,648 EPOCH 8 done: loss 0.0371 - lr: 0.000011
209
+ 2024-03-26 11:54:00,585 DEV : loss 0.17568133771419525 - f1-score (micro avg) 0.9315
210
+ 2024-03-26 11:54:00,586 saving best model
211
+ 2024-03-26 11:54:01,026 ----------------------------------------------------------------------------------------------------
212
+ 2024-03-26 11:54:02,945 epoch 9 - iter 4/48 - loss 0.03057517 - time (sec): 1.92 - samples/sec: 1504.93 - lr: 0.000011 - momentum: 0.000000
213
+ 2024-03-26 11:54:06,225 epoch 9 - iter 8/48 - loss 0.02777670 - time (sec): 5.20 - samples/sec: 1210.84 - lr: 0.000011 - momentum: 0.000000
214
+ 2024-03-26 11:54:07,959 epoch 9 - iter 12/48 - loss 0.02319110 - time (sec): 6.93 - samples/sec: 1247.46 - lr: 0.000010 - momentum: 0.000000
215
+ 2024-03-26 11:54:09,943 epoch 9 - iter 16/48 - loss 0.02857044 - time (sec): 8.92 - samples/sec: 1282.11 - lr: 0.000010 - momentum: 0.000000
216
+ 2024-03-26 11:54:12,838 epoch 9 - iter 20/48 - loss 0.02512622 - time (sec): 11.81 - samples/sec: 1257.43 - lr: 0.000009 - momentum: 0.000000
217
+ 2024-03-26 11:54:14,417 epoch 9 - iter 24/48 - loss 0.02482773 - time (sec): 13.39 - samples/sec: 1303.02 - lr: 0.000009 - momentum: 0.000000
218
+ 2024-03-26 11:54:16,447 epoch 9 - iter 28/48 - loss 0.02786716 - time (sec): 15.42 - samples/sec: 1324.71 - lr: 0.000008 - momentum: 0.000000
219
+ 2024-03-26 11:54:18,876 epoch 9 - iter 32/48 - loss 0.02711697 - time (sec): 17.85 - samples/sec: 1301.45 - lr: 0.000008 - momentum: 0.000000
220
+ 2024-03-26 11:54:20,202 epoch 9 - iter 36/48 - loss 0.03102021 - time (sec): 19.18 - samples/sec: 1333.10 - lr: 0.000007 - momentum: 0.000000
221
+ 2024-03-26 11:54:23,481 epoch 9 - iter 40/48 - loss 0.03040776 - time (sec): 22.46 - samples/sec: 1288.71 - lr: 0.000007 - momentum: 0.000000
222
+ 2024-03-26 11:54:25,619 epoch 9 - iter 44/48 - loss 0.02844050 - time (sec): 24.59 - samples/sec: 1313.34 - lr: 0.000006 - momentum: 0.000000
223
+ 2024-03-26 11:54:26,608 epoch 9 - iter 48/48 - loss 0.02882616 - time (sec): 25.58 - samples/sec: 1347.54 - lr: 0.000006 - momentum: 0.000000
224
+ 2024-03-26 11:54:26,608 ----------------------------------------------------------------------------------------------------
225
+ 2024-03-26 11:54:26,608 EPOCH 9 done: loss 0.0288 - lr: 0.000006
226
+ 2024-03-26 11:54:27,540 DEV : loss 0.1826149970293045 - f1-score (micro avg) 0.9308
227
+ 2024-03-26 11:54:27,541 ----------------------------------------------------------------------------------------------------
228
+ 2024-03-26 11:54:29,493 epoch 10 - iter 4/48 - loss 0.02449608 - time (sec): 1.95 - samples/sec: 1324.59 - lr: 0.000006 - momentum: 0.000000
229
+ 2024-03-26 11:54:32,350 epoch 10 - iter 8/48 - loss 0.01705663 - time (sec): 4.81 - samples/sec: 1203.11 - lr: 0.000005 - momentum: 0.000000
230
+ 2024-03-26 11:54:34,380 epoch 10 - iter 12/48 - loss 0.02218434 - time (sec): 6.84 - samples/sec: 1274.17 - lr: 0.000005 - momentum: 0.000000
231
+ 2024-03-26 11:54:36,467 epoch 10 - iter 16/48 - loss 0.02207035 - time (sec): 8.93 - samples/sec: 1362.88 - lr: 0.000004 - momentum: 0.000000
232
+ 2024-03-26 11:54:37,324 epoch 10 - iter 20/48 - loss 0.02077247 - time (sec): 9.78 - samples/sec: 1443.11 - lr: 0.000004 - momentum: 0.000000
233
+ 2024-03-26 11:54:39,048 epoch 10 - iter 24/48 - loss 0.02024295 - time (sec): 11.51 - samples/sec: 1469.98 - lr: 0.000003 - momentum: 0.000000
234
+ 2024-03-26 11:54:39,981 epoch 10 - iter 28/48 - loss 0.01939105 - time (sec): 12.44 - samples/sec: 1536.11 - lr: 0.000003 - momentum: 0.000000
235
+ 2024-03-26 11:54:42,327 epoch 10 - iter 32/48 - loss 0.01801898 - time (sec): 14.79 - samples/sec: 1504.67 - lr: 0.000002 - momentum: 0.000000
236
+ 2024-03-26 11:54:44,924 epoch 10 - iter 36/48 - loss 0.02222425 - time (sec): 17.38 - samples/sec: 1466.68 - lr: 0.000002 - momentum: 0.000000
237
+ 2024-03-26 11:54:46,906 epoch 10 - iter 40/48 - loss 0.02282312 - time (sec): 19.36 - samples/sec: 1457.07 - lr: 0.000001 - momentum: 0.000000
238
+ 2024-03-26 11:54:49,574 epoch 10 - iter 44/48 - loss 0.02314136 - time (sec): 22.03 - samples/sec: 1443.26 - lr: 0.000001 - momentum: 0.000000
239
+ 2024-03-26 11:54:51,197 epoch 10 - iter 48/48 - loss 0.02323381 - time (sec): 23.66 - samples/sec: 1457.27 - lr: 0.000000 - momentum: 0.000000
240
+ 2024-03-26 11:54:51,197 ----------------------------------------------------------------------------------------------------
241
+ 2024-03-26 11:54:51,197 EPOCH 10 done: loss 0.0232 - lr: 0.000000
242
+ 2024-03-26 11:54:52,159 DEV : loss 0.1922144740819931 - f1-score (micro avg) 0.9281
243
+ 2024-03-26 11:54:52,449 ----------------------------------------------------------------------------------------------------
244
+ 2024-03-26 11:54:52,450 Loading model from best epoch ...
245
+ 2024-03-26 11:54:53,340 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
246
+ 2024-03-26 11:54:54,197
247
+ Results:
248
+ - F-score (micro) 0.9009
249
+ - F-score (macro) 0.6853
250
+ - Accuracy 0.822
251
+
252
+ By class:
253
+ precision recall f1-score support
254
+
255
+ Unternehmen 0.9000 0.8797 0.8897 266
256
+ Auslagerung 0.8523 0.9036 0.8772 249
257
+ Ort 0.9635 0.9851 0.9742 134
258
+ Software 0.0000 0.0000 0.0000 0
259
+
260
+ micro avg 0.8914 0.9106 0.9009 649
261
+ macro avg 0.6789 0.6921 0.6853 649
262
+ weighted avg 0.8948 0.9106 0.9024 649
263
+
264
+ 2024-03-26 11:54:54,197 ----------------------------------------------------------------------------------------------------