Hugging Face's logo

stefan-it
/
flair-co-funer-german_dbmdz_bert_base-bs16-e10-lr3e-05-3

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
ec1db72
•
1 Parent(s): 269c05c

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +266 -0
training.log ADDED
@@ -0,0 +1,266 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-03-26 15:47:36,999 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 15:47:36,999 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 15:47:36,999 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 15:47:36,999 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 15:47:36,999 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 15:47:36,999 Train: 758 sentences
54
+ 2024-03-26 15:47:36,999 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 15:47:36,999 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 15:47:36,999 Training Params:
57
+ 2024-03-26 15:47:36,999 - learning_rate: "3e-05"
58
+ 2024-03-26 15:47:36,999 - mini_batch_size: "16"
59
+ 2024-03-26 15:47:36,999 - max_epochs: "10"
60
+ 2024-03-26 15:47:36,999 - shuffle: "True"
61
+ 2024-03-26 15:47:36,999 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 15:47:36,999 Plugins:
63
+ 2024-03-26 15:47:36,999 - TensorboardLogger
64
+ 2024-03-26 15:47:36,999 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 15:47:36,999 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 15:47:36,999 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 15:47:36,999 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 15:47:36,999 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 15:47:36,999 Computation:
70
+ 2024-03-26 15:47:36,999 - compute on device: cuda:0
71
+ 2024-03-26 15:47:36,999 - embedding storage: none
72
+ 2024-03-26 15:47:36,999 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 15:47:36,999 Model training base path: "flair-co-funer-german_dbmdz_bert_base-bs16-e10-lr3e-05-3"
74
+ 2024-03-26 15:47:36,999 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 15:47:36,999 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 15:47:37,000 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 15:47:38,243 epoch 1 - iter 4/48 - loss 3.37379841 - time (sec): 1.24 - samples/sec: 2215.07 - lr: 0.000002 - momentum: 0.000000
78
+ 2024-03-26 15:47:40,206 epoch 1 - iter 8/48 - loss 3.38378942 - time (sec): 3.21 - samples/sec: 1816.61 - lr: 0.000004 - momentum: 0.000000
79
+ 2024-03-26 15:47:41,730 epoch 1 - iter 12/48 - loss 3.35565868 - time (sec): 4.73 - samples/sec: 1770.37 - lr: 0.000007 - momentum: 0.000000
80
+ 2024-03-26 15:47:44,610 epoch 1 - iter 16/48 - loss 3.28068558 - time (sec): 7.61 - samples/sec: 1524.04 - lr: 0.000009 - momentum: 0.000000
81
+ 2024-03-26 15:47:46,256 epoch 1 - iter 20/48 - loss 3.13339846 - time (sec): 9.26 - samples/sec: 1556.12 - lr: 0.000012 - momentum: 0.000000
82
+ 2024-03-26 15:47:47,687 epoch 1 - iter 24/48 - loss 2.99408989 - time (sec): 10.69 - samples/sec: 1606.41 - lr: 0.000014 - momentum: 0.000000
83
+ 2024-03-26 15:47:49,001 epoch 1 - iter 28/48 - loss 2.84824149 - time (sec): 12.00 - samples/sec: 1627.05 - lr: 0.000017 - momentum: 0.000000
84
+ 2024-03-26 15:47:51,083 epoch 1 - iter 32/48 - loss 2.70044326 - time (sec): 14.08 - samples/sec: 1613.86 - lr: 0.000019 - momentum: 0.000000
85
+ 2024-03-26 15:47:52,621 epoch 1 - iter 36/48 - loss 2.57582595 - time (sec): 15.62 - samples/sec: 1633.62 - lr: 0.000022 - momentum: 0.000000
86
+ 2024-03-26 15:47:54,837 epoch 1 - iter 40/48 - loss 2.44489920 - time (sec): 17.84 - samples/sec: 1624.49 - lr: 0.000024 - momentum: 0.000000
87
+ 2024-03-26 15:47:56,731 epoch 1 - iter 44/48 - loss 2.33561949 - time (sec): 19.73 - samples/sec: 1625.16 - lr: 0.000027 - momentum: 0.000000
88
+ 2024-03-26 15:47:58,339 epoch 1 - iter 48/48 - loss 2.24504382 - time (sec): 21.34 - samples/sec: 1615.44 - lr: 0.000029 - momentum: 0.000000
89
+ 2024-03-26 15:47:58,339 ----------------------------------------------------------------------------------------------------
90
+ 2024-03-26 15:47:58,339 EPOCH 1 done: loss 2.2450 - lr: 0.000029
91
+ 2024-03-26 15:47:59,148 DEV : loss 0.8031646609306335 - f1-score (micro avg) 0.4656
92
+ 2024-03-26 15:47:59,149 saving best model
93
+ 2024-03-26 15:47:59,410 ----------------------------------------------------------------------------------------------------
94
+ 2024-03-26 15:48:00,812 epoch 2 - iter 4/48 - loss 1.04326321 - time (sec): 1.40 - samples/sec: 1780.71 - lr: 0.000030 - momentum: 0.000000
95
+ 2024-03-26 15:48:02,265 epoch 2 - iter 8/48 - loss 0.87730803 - time (sec): 2.85 - samples/sec: 1710.29 - lr: 0.000030 - momentum: 0.000000
96
+ 2024-03-26 15:48:03,681 epoch 2 - iter 12/48 - loss 0.83901534 - time (sec): 4.27 - samples/sec: 1800.20 - lr: 0.000029 - momentum: 0.000000
97
+ 2024-03-26 15:48:05,535 epoch 2 - iter 16/48 - loss 0.77100321 - time (sec): 6.12 - samples/sec: 1756.57 - lr: 0.000029 - momentum: 0.000000
98
+ 2024-03-26 15:48:07,867 epoch 2 - iter 20/48 - loss 0.73954646 - time (sec): 8.46 - samples/sec: 1676.84 - lr: 0.000029 - momentum: 0.000000
99
+ 2024-03-26 15:48:09,869 epoch 2 - iter 24/48 - loss 0.69136182 - time (sec): 10.46 - samples/sec: 1658.52 - lr: 0.000028 - momentum: 0.000000
100
+ 2024-03-26 15:48:12,567 epoch 2 - iter 28/48 - loss 0.66596220 - time (sec): 13.16 - samples/sec: 1590.53 - lr: 0.000028 - momentum: 0.000000
101
+ 2024-03-26 15:48:14,742 epoch 2 - iter 32/48 - loss 0.64037489 - time (sec): 15.33 - samples/sec: 1556.83 - lr: 0.000028 - momentum: 0.000000
102
+ 2024-03-26 15:48:16,449 epoch 2 - iter 36/48 - loss 0.62884232 - time (sec): 17.04 - samples/sec: 1550.49 - lr: 0.000028 - momentum: 0.000000
103
+ 2024-03-26 15:48:18,141 epoch 2 - iter 40/48 - loss 0.62020735 - time (sec): 18.73 - samples/sec: 1557.51 - lr: 0.000027 - momentum: 0.000000
104
+ 2024-03-26 15:48:20,284 epoch 2 - iter 44/48 - loss 0.60189604 - time (sec): 20.87 - samples/sec: 1552.36 - lr: 0.000027 - momentum: 0.000000
105
+ 2024-03-26 15:48:21,787 epoch 2 - iter 48/48 - loss 0.58624485 - time (sec): 22.38 - samples/sec: 1540.59 - lr: 0.000027 - momentum: 0.000000
106
+ 2024-03-26 15:48:21,787 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 15:48:21,787 EPOCH 2 done: loss 0.5862 - lr: 0.000027
108
+ 2024-03-26 15:48:22,767 DEV : loss 0.32458996772766113 - f1-score (micro avg) 0.7892
109
+ 2024-03-26 15:48:22,768 saving best model
110
+ 2024-03-26 15:48:23,190 ----------------------------------------------------------------------------------------------------
111
+ 2024-03-26 15:48:24,682 epoch 3 - iter 4/48 - loss 0.35901192 - time (sec): 1.49 - samples/sec: 1643.98 - lr: 0.000026 - momentum: 0.000000
112
+ 2024-03-26 15:48:27,381 epoch 3 - iter 8/48 - loss 0.31347438 - time (sec): 4.19 - samples/sec: 1367.54 - lr: 0.000026 - momentum: 0.000000
113
+ 2024-03-26 15:48:28,614 epoch 3 - iter 12/48 - loss 0.32826115 - time (sec): 5.42 - samples/sec: 1502.29 - lr: 0.000026 - momentum: 0.000000
114
+ 2024-03-26 15:48:29,957 epoch 3 - iter 16/48 - loss 0.30830080 - time (sec): 6.77 - samples/sec: 1631.60 - lr: 0.000026 - momentum: 0.000000
115
+ 2024-03-26 15:48:31,394 epoch 3 - iter 20/48 - loss 0.31154007 - time (sec): 8.20 - samples/sec: 1647.17 - lr: 0.000025 - momentum: 0.000000
116
+ 2024-03-26 15:48:34,065 epoch 3 - iter 24/48 - loss 0.30431891 - time (sec): 10.87 - samples/sec: 1536.24 - lr: 0.000025 - momentum: 0.000000
117
+ 2024-03-26 15:48:35,947 epoch 3 - iter 28/48 - loss 0.30275570 - time (sec): 12.76 - samples/sec: 1553.88 - lr: 0.000025 - momentum: 0.000000
118
+ 2024-03-26 15:48:38,432 epoch 3 - iter 32/48 - loss 0.29026230 - time (sec): 15.24 - samples/sec: 1496.08 - lr: 0.000025 - momentum: 0.000000
119
+ 2024-03-26 15:48:40,337 epoch 3 - iter 36/48 - loss 0.29110826 - time (sec): 17.14 - samples/sec: 1491.88 - lr: 0.000024 - momentum: 0.000000
120
+ 2024-03-26 15:48:42,660 epoch 3 - iter 40/48 - loss 0.28131814 - time (sec): 19.47 - samples/sec: 1467.23 - lr: 0.000024 - momentum: 0.000000
121
+ 2024-03-26 15:48:45,068 epoch 3 - iter 44/48 - loss 0.28892993 - time (sec): 21.88 - samples/sec: 1454.64 - lr: 0.000024 - momentum: 0.000000
122
+ 2024-03-26 15:48:47,362 epoch 3 - iter 48/48 - loss 0.28042318 - time (sec): 24.17 - samples/sec: 1426.23 - lr: 0.000023 - momentum: 0.000000
123
+ 2024-03-26 15:48:47,362 ----------------------------------------------------------------------------------------------------
124
+ 2024-03-26 15:48:47,362 EPOCH 3 done: loss 0.2804 - lr: 0.000023
125
+ 2024-03-26 15:48:48,272 DEV : loss 0.23968861997127533 - f1-score (micro avg) 0.8524
126
+ 2024-03-26 15:48:48,275 saving best model
127
+ 2024-03-26 15:48:48,727 ----------------------------------------------------------------------------------------------------
128
+ 2024-03-26 15:48:50,103 epoch 4 - iter 4/48 - loss 0.21412296 - time (sec): 1.37 - samples/sec: 1824.20 - lr: 0.000023 - momentum: 0.000000
129
+ 2024-03-26 15:48:51,996 epoch 4 - iter 8/48 - loss 0.20087814 - time (sec): 3.27 - samples/sec: 1640.43 - lr: 0.000023 - momentum: 0.000000
130
+ 2024-03-26 15:48:54,504 epoch 4 - iter 12/48 - loss 0.18530637 - time (sec): 5.77 - samples/sec: 1461.50 - lr: 0.000023 - momentum: 0.000000
131
+ 2024-03-26 15:48:56,381 epoch 4 - iter 16/48 - loss 0.19056545 - time (sec): 7.65 - samples/sec: 1479.99 - lr: 0.000022 - momentum: 0.000000
132
+ 2024-03-26 15:48:58,737 epoch 4 - iter 20/48 - loss 0.18109565 - time (sec): 10.01 - samples/sec: 1468.23 - lr: 0.000022 - momentum: 0.000000
133
+ 2024-03-26 15:49:01,604 epoch 4 - iter 24/48 - loss 0.17043274 - time (sec): 12.87 - samples/sec: 1416.31 - lr: 0.000022 - momentum: 0.000000
134
+ 2024-03-26 15:49:02,712 epoch 4 - iter 28/48 - loss 0.17008703 - time (sec): 13.98 - samples/sec: 1452.82 - lr: 0.000022 - momentum: 0.000000
135
+ 2024-03-26 15:49:05,694 epoch 4 - iter 32/48 - loss 0.16578596 - time (sec): 16.96 - samples/sec: 1392.19 - lr: 0.000021 - momentum: 0.000000
136
+ 2024-03-26 15:49:07,403 epoch 4 - iter 36/48 - loss 0.17310898 - time (sec): 18.67 - samples/sec: 1424.82 - lr: 0.000021 - momentum: 0.000000
137
+ 2024-03-26 15:49:10,200 epoch 4 - iter 40/48 - loss 0.17983930 - time (sec): 21.47 - samples/sec: 1391.90 - lr: 0.000021 - momentum: 0.000000
138
+ 2024-03-26 15:49:11,102 epoch 4 - iter 44/48 - loss 0.18378026 - time (sec): 22.37 - samples/sec: 1438.31 - lr: 0.000020 - momentum: 0.000000
139
+ 2024-03-26 15:49:12,572 epoch 4 - iter 48/48 - loss 0.18337316 - time (sec): 23.84 - samples/sec: 1445.82 - lr: 0.000020 - momentum: 0.000000
140
+ 2024-03-26 15:49:12,572 ----------------------------------------------------------------------------------------------------
141
+ 2024-03-26 15:49:12,572 EPOCH 4 done: loss 0.1834 - lr: 0.000020
142
+ 2024-03-26 15:49:13,476 DEV : loss 0.20375721156597137 - f1-score (micro avg) 0.8751
143
+ 2024-03-26 15:49:13,477 saving best model
144
+ 2024-03-26 15:49:13,891 ----------------------------------------------------------------------------------------------------
145
+ 2024-03-26 15:49:16,313 epoch 5 - iter 4/48 - loss 0.11807576 - time (sec): 2.42 - samples/sec: 1313.26 - lr: 0.000020 - momentum: 0.000000
146
+ 2024-03-26 15:49:17,731 epoch 5 - iter 8/48 - loss 0.14793918 - time (sec): 3.84 - samples/sec: 1483.23 - lr: 0.000020 - momentum: 0.000000
147
+ 2024-03-26 15:49:19,178 epoch 5 - iter 12/48 - loss 0.14657960 - time (sec): 5.29 - samples/sec: 1559.11 - lr: 0.000019 - momentum: 0.000000
148
+ 2024-03-26 15:49:21,349 epoch 5 - iter 16/48 - loss 0.14409177 - time (sec): 7.46 - samples/sec: 1475.54 - lr: 0.000019 - momentum: 0.000000
149
+ 2024-03-26 15:49:23,405 epoch 5 - iter 20/48 - loss 0.15265255 - time (sec): 9.51 - samples/sec: 1480.21 - lr: 0.000019 - momentum: 0.000000
150
+ 2024-03-26 15:49:25,879 epoch 5 - iter 24/48 - loss 0.14616029 - time (sec): 11.99 - samples/sec: 1468.65 - lr: 0.000018 - momentum: 0.000000
151
+ 2024-03-26 15:49:28,433 epoch 5 - iter 28/48 - loss 0.13912038 - time (sec): 14.54 - samples/sec: 1447.64 - lr: 0.000018 - momentum: 0.000000
152
+ 2024-03-26 15:49:30,299 epoch 5 - iter 32/48 - loss 0.13859993 - time (sec): 16.41 - samples/sec: 1451.45 - lr: 0.000018 - momentum: 0.000000
153
+ 2024-03-26 15:49:32,115 epoch 5 - iter 36/48 - loss 0.13486299 - time (sec): 18.22 - samples/sec: 1451.25 - lr: 0.000018 - momentum: 0.000000
154
+ 2024-03-26 15:49:34,416 epoch 5 - iter 40/48 - loss 0.13391851 - time (sec): 20.52 - samples/sec: 1439.04 - lr: 0.000017 - momentum: 0.000000
155
+ 2024-03-26 15:49:36,365 epoch 5 - iter 44/48 - loss 0.13625635 - time (sec): 22.47 - samples/sec: 1437.33 - lr: 0.000017 - momentum: 0.000000
156
+ 2024-03-26 15:49:37,417 epoch 5 - iter 48/48 - loss 0.13539195 - time (sec): 23.52 - samples/sec: 1465.38 - lr: 0.000017 - momentum: 0.000000
157
+ 2024-03-26 15:49:37,417 ----------------------------------------------------------------------------------------------------
158
+ 2024-03-26 15:49:37,417 EPOCH 5 done: loss 0.1354 - lr: 0.000017
159
+ 2024-03-26 15:49:38,319 DEV : loss 0.19656339287757874 - f1-score (micro avg) 0.8769
160
+ 2024-03-26 15:49:38,319 saving best model
161
+ 2024-03-26 15:49:38,757 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 15:49:41,340 epoch 6 - iter 4/48 - loss 0.09964959 - time (sec): 2.58 - samples/sec: 1231.29 - lr: 0.000017 - momentum: 0.000000
163
+ 2024-03-26 15:49:43,319 epoch 6 - iter 8/48 - loss 0.10546942 - time (sec): 4.56 - samples/sec: 1287.23 - lr: 0.000016 - momentum: 0.000000
164
+ 2024-03-26 15:49:44,879 epoch 6 - iter 12/48 - loss 0.10479654 - time (sec): 6.12 - samples/sec: 1441.45 - lr: 0.000016 - momentum: 0.000000
165
+ 2024-03-26 15:49:46,811 epoch 6 - iter 16/48 - loss 0.09781057 - time (sec): 8.05 - samples/sec: 1444.08 - lr: 0.000016 - momentum: 0.000000
166
+ 2024-03-26 15:49:47,869 epoch 6 - iter 20/48 - loss 0.10170422 - time (sec): 9.11 - samples/sec: 1533.69 - lr: 0.000015 - momentum: 0.000000
167
+ 2024-03-26 15:49:49,769 epoch 6 - iter 24/48 - loss 0.10095479 - time (sec): 11.01 - samples/sec: 1517.96 - lr: 0.000015 - momentum: 0.000000
168
+ 2024-03-26 15:49:50,901 epoch 6 - iter 28/48 - loss 0.10031886 - time (sec): 12.14 - samples/sec: 1566.60 - lr: 0.000015 - momentum: 0.000000
169
+ 2024-03-26 15:49:52,650 epoch 6 - iter 32/48 - loss 0.09608854 - time (sec): 13.89 - samples/sec: 1585.85 - lr: 0.000015 - momentum: 0.000000
170
+ 2024-03-26 15:49:55,118 epoch 6 - iter 36/48 - loss 0.10539029 - time (sec): 16.36 - samples/sec: 1552.15 - lr: 0.000014 - momentum: 0.000000
171
+ 2024-03-26 15:49:57,149 epoch 6 - iter 40/48 - loss 0.10342541 - time (sec): 18.39 - samples/sec: 1545.02 - lr: 0.000014 - momentum: 0.000000
172
+ 2024-03-26 15:49:59,006 epoch 6 - iter 44/48 - loss 0.10552790 - time (sec): 20.25 - samples/sec: 1553.60 - lr: 0.000014 - momentum: 0.000000
173
+ 2024-03-26 15:50:00,528 epoch 6 - iter 48/48 - loss 0.10513778 - time (sec): 21.77 - samples/sec: 1583.52 - lr: 0.000014 - momentum: 0.000000
174
+ 2024-03-26 15:50:00,528 ----------------------------------------------------------------------------------------------------
175
+ 2024-03-26 15:50:00,528 EPOCH 6 done: loss 0.1051 - lr: 0.000014
176
+ 2024-03-26 15:50:01,423 DEV : loss 0.17874132096767426 - f1-score (micro avg) 0.8906
177
+ 2024-03-26 15:50:01,424 saving best model
178
+ 2024-03-26 15:50:01,864 ----------------------------------------------------------------------------------------------------
179
+ 2024-03-26 15:50:03,950 epoch 7 - iter 4/48 - loss 0.10289225 - time (sec): 2.08 - samples/sec: 1326.42 - lr: 0.000013 - momentum: 0.000000
180
+ 2024-03-26 15:50:05,640 epoch 7 - iter 8/48 - loss 0.09604354 - time (sec): 3.77 - samples/sec: 1522.30 - lr: 0.000013 - momentum: 0.000000
181
+ 2024-03-26 15:50:07,700 epoch 7 - iter 12/48 - loss 0.08236734 - time (sec): 5.83 - samples/sec: 1468.53 - lr: 0.000013 - momentum: 0.000000
182
+ 2024-03-26 15:50:10,260 epoch 7 - iter 16/48 - loss 0.07567250 - time (sec): 8.39 - samples/sec: 1407.95 - lr: 0.000012 - momentum: 0.000000
183
+ 2024-03-26 15:50:12,931 epoch 7 - iter 20/48 - loss 0.07694176 - time (sec): 11.07 - samples/sec: 1412.55 - lr: 0.000012 - momentum: 0.000000
184
+ 2024-03-26 15:50:14,448 epoch 7 - iter 24/48 - loss 0.07791950 - time (sec): 12.58 - samples/sec: 1432.47 - lr: 0.000012 - momentum: 0.000000
185
+ 2024-03-26 15:50:16,533 epoch 7 - iter 28/48 - loss 0.07423173 - time (sec): 14.67 - samples/sec: 1450.44 - lr: 0.000012 - momentum: 0.000000
186
+ 2024-03-26 15:50:18,667 epoch 7 - iter 32/48 - loss 0.07743964 - time (sec): 16.80 - samples/sec: 1455.12 - lr: 0.000011 - momentum: 0.000000
187
+ 2024-03-26 15:50:20,872 epoch 7 - iter 36/48 - loss 0.08204888 - time (sec): 19.01 - samples/sec: 1440.31 - lr: 0.000011 - momentum: 0.000000
188
+ 2024-03-26 15:50:22,443 epoch 7 - iter 40/48 - loss 0.07843893 - time (sec): 20.58 - samples/sec: 1448.97 - lr: 0.000011 - momentum: 0.000000
189
+ 2024-03-26 15:50:24,087 epoch 7 - iter 44/48 - loss 0.08223725 - time (sec): 22.22 - samples/sec: 1467.91 - lr: 0.000010 - momentum: 0.000000
190
+ 2024-03-26 15:50:25,403 epoch 7 - iter 48/48 - loss 0.08252587 - time (sec): 23.54 - samples/sec: 1464.57 - lr: 0.000010 - momentum: 0.000000
191
+ 2024-03-26 15:50:25,403 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 15:50:25,403 EPOCH 7 done: loss 0.0825 - lr: 0.000010
193
+ 2024-03-26 15:50:26,297 DEV : loss 0.17732246220111847 - f1-score (micro avg) 0.9049
194
+ 2024-03-26 15:50:26,298 saving best model
195
+ 2024-03-26 15:50:26,725 ----------------------------------------------------------------------------------------------------
196
+ 2024-03-26 15:50:29,038 epoch 8 - iter 4/48 - loss 0.06075169 - time (sec): 2.31 - samples/sec: 1271.50 - lr: 0.000010 - momentum: 0.000000
197
+ 2024-03-26 15:50:31,556 epoch 8 - iter 8/48 - loss 0.05551287 - time (sec): 4.83 - samples/sec: 1369.60 - lr: 0.000010 - momentum: 0.000000
198
+ 2024-03-26 15:50:33,525 epoch 8 - iter 12/48 - loss 0.05367756 - time (sec): 6.80 - samples/sec: 1353.52 - lr: 0.000009 - momentum: 0.000000
199
+ 2024-03-26 15:50:35,496 epoch 8 - iter 16/48 - loss 0.05290307 - time (sec): 8.77 - samples/sec: 1367.30 - lr: 0.000009 - momentum: 0.000000
200
+ 2024-03-26 15:50:37,000 epoch 8 - iter 20/48 - loss 0.05432871 - time (sec): 10.27 - samples/sec: 1391.60 - lr: 0.000009 - momentum: 0.000000
201
+ 2024-03-26 15:50:39,319 epoch 8 - iter 24/48 - loss 0.05341962 - time (sec): 12.59 - samples/sec: 1377.15 - lr: 0.000009 - momentum: 0.000000
202
+ 2024-03-26 15:50:41,440 epoch 8 - iter 28/48 - loss 0.05337120 - time (sec): 14.71 - samples/sec: 1369.90 - lr: 0.000008 - momentum: 0.000000
203
+ 2024-03-26 15:50:43,722 epoch 8 - iter 32/48 - loss 0.06255002 - time (sec): 17.00 - samples/sec: 1381.28 - lr: 0.000008 - momentum: 0.000000
204
+ 2024-03-26 15:50:46,862 epoch 8 - iter 36/48 - loss 0.06460117 - time (sec): 20.14 - samples/sec: 1332.82 - lr: 0.000008 - momentum: 0.000000
205
+ 2024-03-26 15:50:48,818 epoch 8 - iter 40/48 - loss 0.06712721 - time (sec): 22.09 - samples/sec: 1339.68 - lr: 0.000007 - momentum: 0.000000
206
+ 2024-03-26 15:50:49,609 epoch 8 - iter 44/48 - loss 0.06594343 - time (sec): 22.88 - samples/sec: 1388.37 - lr: 0.000007 - momentum: 0.000000
207
+ 2024-03-26 15:50:51,407 epoch 8 - iter 48/48 - loss 0.06743138 - time (sec): 24.68 - samples/sec: 1396.74 - lr: 0.000007 - momentum: 0.000000
208
+ 2024-03-26 15:50:51,407 ----------------------------------------------------------------------------------------------------
209
+ 2024-03-26 15:50:51,407 EPOCH 8 done: loss 0.0674 - lr: 0.000007
210
+ 2024-03-26 15:50:52,311 DEV : loss 0.17159819602966309 - f1-score (micro avg) 0.9157
211
+ 2024-03-26 15:50:52,312 saving best model
212
+ 2024-03-26 15:50:52,740 ----------------------------------------------------------------------------------------------------
213
+ 2024-03-26 15:50:55,418 epoch 9 - iter 4/48 - loss 0.03996473 - time (sec): 2.68 - samples/sec: 1232.16 - lr: 0.000007 - momentum: 0.000000
214
+ 2024-03-26 15:50:57,081 epoch 9 - iter 8/48 - loss 0.04324845 - time (sec): 4.34 - samples/sec: 1322.13 - lr: 0.000006 - momentum: 0.000000
215
+ 2024-03-26 15:50:59,184 epoch 9 - iter 12/48 - loss 0.05334992 - time (sec): 6.44 - samples/sec: 1393.21 - lr: 0.000006 - momentum: 0.000000
216
+ 2024-03-26 15:51:01,255 epoch 9 - iter 16/48 - loss 0.05554006 - time (sec): 8.51 - samples/sec: 1422.38 - lr: 0.000006 - momentum: 0.000000
217
+ 2024-03-26 15:51:03,568 epoch 9 - iter 20/48 - loss 0.04996482 - time (sec): 10.83 - samples/sec: 1397.40 - lr: 0.000006 - momentum: 0.000000
218
+ 2024-03-26 15:51:05,474 epoch 9 - iter 24/48 - loss 0.05118172 - time (sec): 12.73 - samples/sec: 1390.82 - lr: 0.000005 - momentum: 0.000000
219
+ 2024-03-26 15:51:08,665 epoch 9 - iter 28/48 - loss 0.05247513 - time (sec): 15.92 - samples/sec: 1341.59 - lr: 0.000005 - momentum: 0.000000
220
+ 2024-03-26 15:51:10,022 epoch 9 - iter 32/48 - loss 0.05419220 - time (sec): 17.28 - samples/sec: 1382.48 - lr: 0.000005 - momentum: 0.000000
221
+ 2024-03-26 15:51:12,370 epoch 9 - iter 36/48 - loss 0.05323258 - time (sec): 19.63 - samples/sec: 1372.98 - lr: 0.000004 - momentum: 0.000000
222
+ 2024-03-26 15:51:13,823 epoch 9 - iter 40/48 - loss 0.05598120 - time (sec): 21.08 - samples/sec: 1390.82 - lr: 0.000004 - momentum: 0.000000
223
+ 2024-03-26 15:51:15,323 epoch 9 - iter 44/48 - loss 0.06011503 - time (sec): 22.58 - samples/sec: 1408.71 - lr: 0.000004 - momentum: 0.000000
224
+ 2024-03-26 15:51:16,718 epoch 9 - iter 48/48 - loss 0.05993914 - time (sec): 23.98 - samples/sec: 1437.74 - lr: 0.000004 - momentum: 0.000000
225
+ 2024-03-26 15:51:16,718 ----------------------------------------------------------------------------------------------------
226
+ 2024-03-26 15:51:16,718 EPOCH 9 done: loss 0.0599 - lr: 0.000004
227
+ 2024-03-26 15:51:17,641 DEV : loss 0.17445135116577148 - f1-score (micro avg) 0.9153
228
+ 2024-03-26 15:51:17,642 ----------------------------------------------------------------------------------------------------
229
+ 2024-03-26 15:51:20,004 epoch 10 - iter 4/48 - loss 0.03793612 - time (sec): 2.36 - samples/sec: 1393.76 - lr: 0.000003 - momentum: 0.000000
230
+ 2024-03-26 15:51:21,979 epoch 10 - iter 8/48 - loss 0.03970409 - time (sec): 4.34 - samples/sec: 1347.83 - lr: 0.000003 - momentum: 0.000000
231
+ 2024-03-26 15:51:23,153 epoch 10 - iter 12/48 - loss 0.05682156 - time (sec): 5.51 - samples/sec: 1513.67 - lr: 0.000003 - momentum: 0.000000
232
+ 2024-03-26 15:51:24,664 epoch 10 - iter 16/48 - loss 0.06071482 - time (sec): 7.02 - samples/sec: 1597.92 - lr: 0.000002 - momentum: 0.000000
233
+ 2024-03-26 15:51:26,354 epoch 10 - iter 20/48 - loss 0.06010429 - time (sec): 8.71 - samples/sec: 1638.72 - lr: 0.000002 - momentum: 0.000000
234
+ 2024-03-26 15:51:28,361 epoch 10 - iter 24/48 - loss 0.05659568 - time (sec): 10.72 - samples/sec: 1590.02 - lr: 0.000002 - momentum: 0.000000
235
+ 2024-03-26 15:51:30,466 epoch 10 - iter 28/48 - loss 0.05309482 - time (sec): 12.82 - samples/sec: 1555.51 - lr: 0.000002 - momentum: 0.000000
236
+ 2024-03-26 15:51:32,568 epoch 10 - iter 32/48 - loss 0.05297842 - time (sec): 14.93 - samples/sec: 1563.19 - lr: 0.000001 - momentum: 0.000000
237
+ 2024-03-26 15:51:33,959 epoch 10 - iter 36/48 - loss 0.05326019 - time (sec): 16.32 - samples/sec: 1562.80 - lr: 0.000001 - momentum: 0.000000
238
+ 2024-03-26 15:51:36,578 epoch 10 - iter 40/48 - loss 0.05017067 - time (sec): 18.94 - samples/sec: 1524.02 - lr: 0.000001 - momentum: 0.000000
239
+ 2024-03-26 15:51:39,089 epoch 10 - iter 44/48 - loss 0.05227028 - time (sec): 21.45 - samples/sec: 1499.29 - lr: 0.000001 - momentum: 0.000000
240
+ 2024-03-26 15:51:40,674 epoch 10 - iter 48/48 - loss 0.05245429 - time (sec): 23.03 - samples/sec: 1496.71 - lr: 0.000000 - momentum: 0.000000
241
+ 2024-03-26 15:51:40,674 ----------------------------------------------------------------------------------------------------
242
+ 2024-03-26 15:51:40,674 EPOCH 10 done: loss 0.0525 - lr: 0.000000
243
+ 2024-03-26 15:51:41,572 DEV : loss 0.17229919135570526 - f1-score (micro avg) 0.9175
244
+ 2024-03-26 15:51:41,573 saving best model
245
+ 2024-03-26 15:51:42,279 ----------------------------------------------------------------------------------------------------
246
+ 2024-03-26 15:51:42,280 Loading model from best epoch ...
247
+ 2024-03-26 15:51:42,995 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
248
+ 2024-03-26 15:51:43,741
249
+ Results:
250
+ - F-score (micro) 0.9033
251
+ - F-score (macro) 0.6868
252
+ - Accuracy 0.8259
253
+
254
+ By class:
255
+ precision recall f1-score support
256
+
257
+ Unternehmen 0.8864 0.8797 0.8830 266
258
+ Auslagerung 0.8697 0.9116 0.8902 249
259
+ Ort 0.9635 0.9851 0.9742 134
260
+ Software 0.0000 0.0000 0.0000 0
261
+
262
+ micro avg 0.8931 0.9137 0.9033 649
263
+ macro avg 0.6799 0.6941 0.6868 649
264
+ weighted avg 0.8959 0.9137 0.9046 649
265
+
266
+ 2024-03-26 15:51:43,741 ----------------------------------------------------------------------------------------------------