Hugging Face's logo

stefan-it
/
flair-co-funer-german_bert_base-bs16-e10-lr3e-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
829a558
•
1 Parent(s): e7ef55b

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 11:45:43,177 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 11:45:43,177 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 11:45:43,178 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 11:45:43,178 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 11:45:43,178 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 11:45:43,178 Train: 758 sentences
54
+ 2024-03-26 11:45:43,178 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 11:45:43,178 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 11:45:43,178 Training Params:
57
+ 2024-03-26 11:45:43,178 - learning_rate: "3e-05"
58
+ 2024-03-26 11:45:43,178 - mini_batch_size: "16"
59
+ 2024-03-26 11:45:43,178 - max_epochs: "10"
60
+ 2024-03-26 11:45:43,178 - shuffle: "True"
61
+ 2024-03-26 11:45:43,178 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 11:45:43,178 Plugins:
63
+ 2024-03-26 11:45:43,178 - TensorboardLogger
64
+ 2024-03-26 11:45:43,178 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 11:45:43,178 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 11:45:43,178 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 11:45:43,178 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 11:45:43,178 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 11:45:43,178 Computation:
70
+ 2024-03-26 11:45:43,178 - compute on device: cuda:0
71
+ 2024-03-26 11:45:43,178 - embedding storage: none
72
+ 2024-03-26 11:45:43,178 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 11:45:43,178 Model training base path: "flair-co-funer-german_bert_base-bs16-e10-lr3e-05-4"
74
+ 2024-03-26 11:45:43,178 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 11:45:43,178 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 11:45:43,178 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 11:45:44,651 epoch 1 - iter 4/48 - loss 3.09549930 - time (sec): 1.47 - samples/sec: 1771.64 - lr: 0.000002 - momentum: 0.000000
78
+ 2024-03-26 11:45:46,599 epoch 1 - iter 8/48 - loss 3.05860497 - time (sec): 3.42 - samples/sec: 1497.54 - lr: 0.000004 - momentum: 0.000000
79
+ 2024-03-26 11:45:47,991 epoch 1 - iter 12/48 - loss 2.97301780 - time (sec): 4.81 - samples/sec: 1517.11 - lr: 0.000007 - momentum: 0.000000
80
+ 2024-03-26 11:45:50,619 epoch 1 - iter 16/48 - loss 2.81904351 - time (sec): 7.44 - samples/sec: 1437.84 - lr: 0.000009 - momentum: 0.000000
81
+ 2024-03-26 11:45:52,789 epoch 1 - iter 20/48 - loss 2.69072216 - time (sec): 9.61 - samples/sec: 1425.29 - lr: 0.000012 - momentum: 0.000000
82
+ 2024-03-26 11:45:55,470 epoch 1 - iter 24/48 - loss 2.55781908 - time (sec): 12.29 - samples/sec: 1376.96 - lr: 0.000014 - momentum: 0.000000
83
+ 2024-03-26 11:45:58,068 epoch 1 - iter 28/48 - loss 2.43219709 - time (sec): 14.89 - samples/sec: 1362.47 - lr: 0.000017 - momentum: 0.000000
84
+ 2024-03-26 11:45:59,951 epoch 1 - iter 32/48 - loss 2.34102141 - time (sec): 16.77 - samples/sec: 1363.77 - lr: 0.000019 - momentum: 0.000000
85
+ 2024-03-26 11:46:00,897 epoch 1 - iter 36/48 - loss 2.26816176 - time (sec): 17.72 - samples/sec: 1409.81 - lr: 0.000022 - momentum: 0.000000
86
+ 2024-03-26 11:46:02,804 epoch 1 - iter 40/48 - loss 2.17382454 - time (sec): 19.63 - samples/sec: 1419.19 - lr: 0.000024 - momentum: 0.000000
87
+ 2024-03-26 11:46:04,923 epoch 1 - iter 44/48 - loss 2.06590701 - time (sec): 21.74 - samples/sec: 1436.16 - lr: 0.000027 - momentum: 0.000000
88
+ 2024-03-26 11:46:06,685 epoch 1 - iter 48/48 - loss 1.97932119 - time (sec): 23.51 - samples/sec: 1466.46 - lr: 0.000029 - momentum: 0.000000
89
+ 2024-03-26 11:46:06,686 ----------------------------------------------------------------------------------------------------
90
+ 2024-03-26 11:46:06,686 EPOCH 1 done: loss 1.9793 - lr: 0.000029
91
+ 2024-03-26 11:46:07,557 DEV : loss 0.7610657215118408 - f1-score (micro avg) 0.523
92
+ 2024-03-26 11:46:07,559 saving best model
93
+ 2024-03-26 11:46:07,873 ----------------------------------------------------------------------------------------------------
94
+ 2024-03-26 11:46:09,182 epoch 2 - iter 4/48 - loss 1.00588389 - time (sec): 1.31 - samples/sec: 1809.27 - lr: 0.000030 - momentum: 0.000000
95
+ 2024-03-26 11:46:11,520 epoch 2 - iter 8/48 - loss 0.79773619 - time (sec): 3.65 - samples/sec: 1496.17 - lr: 0.000030 - momentum: 0.000000
96
+ 2024-03-26 11:46:13,365 epoch 2 - iter 12/48 - loss 0.75438594 - time (sec): 5.49 - samples/sec: 1551.86 - lr: 0.000029 - momentum: 0.000000
97
+ 2024-03-26 11:46:15,862 epoch 2 - iter 16/48 - loss 0.69088754 - time (sec): 7.99 - samples/sec: 1412.25 - lr: 0.000029 - momentum: 0.000000
98
+ 2024-03-26 11:46:19,281 epoch 2 - iter 20/48 - loss 0.63021194 - time (sec): 11.41 - samples/sec: 1293.37 - lr: 0.000029 - momentum: 0.000000
99
+ 2024-03-26 11:46:20,807 epoch 2 - iter 24/48 - loss 0.62522090 - time (sec): 12.93 - samples/sec: 1348.63 - lr: 0.000028 - momentum: 0.000000
100
+ 2024-03-26 11:46:23,493 epoch 2 - iter 28/48 - loss 0.60290004 - time (sec): 15.62 - samples/sec: 1325.52 - lr: 0.000028 - momentum: 0.000000
101
+ 2024-03-26 11:46:26,244 epoch 2 - iter 32/48 - loss 0.57675820 - time (sec): 18.37 - samples/sec: 1328.72 - lr: 0.000028 - momentum: 0.000000
102
+ 2024-03-26 11:46:28,390 epoch 2 - iter 36/48 - loss 0.56861350 - time (sec): 20.52 - samples/sec: 1318.12 - lr: 0.000028 - momentum: 0.000000
103
+ 2024-03-26 11:46:30,965 epoch 2 - iter 40/48 - loss 0.54982812 - time (sec): 23.09 - samples/sec: 1307.11 - lr: 0.000027 - momentum: 0.000000
104
+ 2024-03-26 11:46:32,094 epoch 2 - iter 44/48 - loss 0.53992976 - time (sec): 24.22 - samples/sec: 1338.69 - lr: 0.000027 - momentum: 0.000000
105
+ 2024-03-26 11:46:33,278 epoch 2 - iter 48/48 - loss 0.52605631 - time (sec): 25.40 - samples/sec: 1356.93 - lr: 0.000027 - momentum: 0.000000
106
+ 2024-03-26 11:46:33,278 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 11:46:33,278 EPOCH 2 done: loss 0.5261 - lr: 0.000027
108
+ 2024-03-26 11:46:34,230 DEV : loss 0.3057578504085541 - f1-score (micro avg) 0.8021
109
+ 2024-03-26 11:46:34,232 saving best model
110
+ 2024-03-26 11:46:34,699 ----------------------------------------------------------------------------------------------------
111
+ 2024-03-26 11:46:36,914 epoch 3 - iter 4/48 - loss 0.30145275 - time (sec): 2.21 - samples/sec: 1108.67 - lr: 0.000026 - momentum: 0.000000
112
+ 2024-03-26 11:46:38,470 epoch 3 - iter 8/48 - loss 0.25277524 - time (sec): 3.77 - samples/sec: 1270.27 - lr: 0.000026 - momentum: 0.000000
113
+ 2024-03-26 11:46:41,075 epoch 3 - iter 12/48 - loss 0.26402459 - time (sec): 6.38 - samples/sec: 1220.17 - lr: 0.000026 - momentum: 0.000000
114
+ 2024-03-26 11:46:43,227 epoch 3 - iter 16/48 - loss 0.26444662 - time (sec): 8.53 - samples/sec: 1250.49 - lr: 0.000026 - momentum: 0.000000
115
+ 2024-03-26 11:46:45,257 epoch 3 - iter 20/48 - loss 0.26227190 - time (sec): 10.56 - samples/sec: 1311.31 - lr: 0.000025 - momentum: 0.000000
116
+ 2024-03-26 11:46:47,499 epoch 3 - iter 24/48 - loss 0.25621355 - time (sec): 12.80 - samples/sec: 1335.61 - lr: 0.000025 - momentum: 0.000000
117
+ 2024-03-26 11:46:50,084 epoch 3 - iter 28/48 - loss 0.24877474 - time (sec): 15.38 - samples/sec: 1296.51 - lr: 0.000025 - momentum: 0.000000
118
+ 2024-03-26 11:46:52,756 epoch 3 - iter 32/48 - loss 0.24041754 - time (sec): 18.06 - samples/sec: 1273.36 - lr: 0.000025 - momentum: 0.000000
119
+ 2024-03-26 11:46:54,934 epoch 3 - iter 36/48 - loss 0.23832241 - time (sec): 20.23 - samples/sec: 1279.35 - lr: 0.000024 - momentum: 0.000000
120
+ 2024-03-26 11:46:57,306 epoch 3 - iter 40/48 - loss 0.24630100 - time (sec): 22.61 - samples/sec: 1296.33 - lr: 0.000024 - momentum: 0.000000
121
+ 2024-03-26 11:46:59,921 epoch 3 - iter 44/48 - loss 0.24001606 - time (sec): 25.22 - samples/sec: 1280.99 - lr: 0.000024 - momentum: 0.000000
122
+ 2024-03-26 11:47:01,444 epoch 3 - iter 48/48 - loss 0.24260838 - time (sec): 26.74 - samples/sec: 1288.93 - lr: 0.000023 - momentum: 0.000000
123
+ 2024-03-26 11:47:01,444 ----------------------------------------------------------------------------------------------------
124
+ 2024-03-26 11:47:01,444 EPOCH 3 done: loss 0.2426 - lr: 0.000023
125
+ 2024-03-26 11:47:02,396 DEV : loss 0.24360495805740356 - f1-score (micro avg) 0.8595
126
+ 2024-03-26 11:47:02,398 saving best model
127
+ 2024-03-26 11:47:02,856 ----------------------------------------------------------------------------------------------------
128
+ 2024-03-26 11:47:05,914 epoch 4 - iter 4/48 - loss 0.12795448 - time (sec): 3.06 - samples/sec: 1192.54 - lr: 0.000023 - momentum: 0.000000
129
+ 2024-03-26 11:47:07,229 epoch 4 - iter 8/48 - loss 0.14859439 - time (sec): 4.37 - samples/sec: 1345.42 - lr: 0.000023 - momentum: 0.000000
130
+ 2024-03-26 11:47:09,386 epoch 4 - iter 12/48 - loss 0.16381198 - time (sec): 6.53 - samples/sec: 1412.84 - lr: 0.000023 - momentum: 0.000000
131
+ 2024-03-26 11:47:12,101 epoch 4 - iter 16/48 - loss 0.16311786 - time (sec): 9.24 - samples/sec: 1317.99 - lr: 0.000022 - momentum: 0.000000
132
+ 2024-03-26 11:47:13,115 epoch 4 - iter 20/48 - loss 0.16463006 - time (sec): 10.26 - samples/sec: 1400.38 - lr: 0.000022 - momentum: 0.000000
133
+ 2024-03-26 11:47:14,580 epoch 4 - iter 24/48 - loss 0.16449895 - time (sec): 11.72 - samples/sec: 1441.92 - lr: 0.000022 - momentum: 0.000000
134
+ 2024-03-26 11:47:17,752 epoch 4 - iter 28/48 - loss 0.15737998 - time (sec): 14.89 - samples/sec: 1355.04 - lr: 0.000022 - momentum: 0.000000
135
+ 2024-03-26 11:47:20,326 epoch 4 - iter 32/48 - loss 0.16722060 - time (sec): 17.47 - samples/sec: 1346.27 - lr: 0.000021 - momentum: 0.000000
136
+ 2024-03-26 11:47:21,933 epoch 4 - iter 36/48 - loss 0.16726320 - time (sec): 19.08 - samples/sec: 1377.55 - lr: 0.000021 - momentum: 0.000000
137
+ 2024-03-26 11:47:23,982 epoch 4 - iter 40/48 - loss 0.16404076 - time (sec): 21.12 - samples/sec: 1391.74 - lr: 0.000021 - momentum: 0.000000
138
+ 2024-03-26 11:47:25,933 epoch 4 - iter 44/48 - loss 0.16294098 - time (sec): 23.08 - samples/sec: 1405.54 - lr: 0.000020 - momentum: 0.000000
139
+ 2024-03-26 11:47:27,014 epoch 4 - iter 48/48 - loss 0.16439185 - time (sec): 24.16 - samples/sec: 1427.00 - lr: 0.000020 - momentum: 0.000000
140
+ 2024-03-26 11:47:27,015 ----------------------------------------------------------------------------------------------------
141
+ 2024-03-26 11:47:27,015 EPOCH 4 done: loss 0.1644 - lr: 0.000020
142
+ 2024-03-26 11:47:27,966 DEV : loss 0.23152601718902588 - f1-score (micro avg) 0.8802
143
+ 2024-03-26 11:47:27,968 saving best model
144
+ 2024-03-26 11:47:28,459 ----------------------------------------------------------------------------------------------------
145
+ 2024-03-26 11:47:29,577 epoch 5 - iter 4/48 - loss 0.19052126 - time (sec): 1.11 - samples/sec: 2287.23 - lr: 0.000020 - momentum: 0.000000
146
+ 2024-03-26 11:47:31,576 epoch 5 - iter 8/48 - loss 0.17349732 - time (sec): 3.11 - samples/sec: 1665.56 - lr: 0.000020 - momentum: 0.000000
147
+ 2024-03-26 11:47:33,746 epoch 5 - iter 12/48 - loss 0.15486907 - time (sec): 5.28 - samples/sec: 1515.53 - lr: 0.000019 - momentum: 0.000000
148
+ 2024-03-26 11:47:36,149 epoch 5 - iter 16/48 - loss 0.14690282 - time (sec): 7.68 - samples/sec: 1443.38 - lr: 0.000019 - momentum: 0.000000
149
+ 2024-03-26 11:47:38,420 epoch 5 - iter 20/48 - loss 0.14271247 - time (sec): 9.95 - samples/sec: 1374.60 - lr: 0.000019 - momentum: 0.000000
150
+ 2024-03-26 11:47:40,647 epoch 5 - iter 24/48 - loss 0.13760899 - time (sec): 12.18 - samples/sec: 1394.70 - lr: 0.000018 - momentum: 0.000000
151
+ 2024-03-26 11:47:42,374 epoch 5 - iter 28/48 - loss 0.13435191 - time (sec): 13.91 - samples/sec: 1415.02 - lr: 0.000018 - momentum: 0.000000
152
+ 2024-03-26 11:47:44,537 epoch 5 - iter 32/48 - loss 0.12594520 - time (sec): 16.07 - samples/sec: 1437.44 - lr: 0.000018 - momentum: 0.000000
153
+ 2024-03-26 11:47:46,006 epoch 5 - iter 36/48 - loss 0.12460472 - time (sec): 17.54 - samples/sec: 1459.35 - lr: 0.000018 - momentum: 0.000000
154
+ 2024-03-26 11:47:48,705 epoch 5 - iter 40/48 - loss 0.11980810 - time (sec): 20.24 - samples/sec: 1424.31 - lr: 0.000017 - momentum: 0.000000
155
+ 2024-03-26 11:47:51,717 epoch 5 - iter 44/48 - loss 0.11945876 - time (sec): 23.25 - samples/sec: 1377.39 - lr: 0.000017 - momentum: 0.000000
156
+ 2024-03-26 11:47:53,286 epoch 5 - iter 48/48 - loss 0.12163729 - time (sec): 24.82 - samples/sec: 1388.84 - lr: 0.000017 - momentum: 0.000000
157
+ 2024-03-26 11:47:53,286 ----------------------------------------------------------------------------------------------------
158
+ 2024-03-26 11:47:53,286 EPOCH 5 done: loss 0.1216 - lr: 0.000017
159
+ 2024-03-26 11:47:54,267 DEV : loss 0.18433180451393127 - f1-score (micro avg) 0.8884
160
+ 2024-03-26 11:47:54,269 saving best model
161
+ 2024-03-26 11:47:54,756 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 11:47:56,703 epoch 6 - iter 4/48 - loss 0.13051442 - time (sec): 1.95 - samples/sec: 1509.64 - lr: 0.000017 - momentum: 0.000000
163
+ 2024-03-26 11:47:58,475 epoch 6 - iter 8/48 - loss 0.10157641 - time (sec): 3.72 - samples/sec: 1558.95 - lr: 0.000016 - momentum: 0.000000
164
+ 2024-03-26 11:48:00,861 epoch 6 - iter 12/48 - loss 0.10287141 - time (sec): 6.10 - samples/sec: 1444.47 - lr: 0.000016 - momentum: 0.000000
165
+ 2024-03-26 11:48:02,495 epoch 6 - iter 16/48 - loss 0.09403836 - time (sec): 7.74 - samples/sec: 1464.25 - lr: 0.000016 - momentum: 0.000000
166
+ 2024-03-26 11:48:05,189 epoch 6 - iter 20/48 - loss 0.08683212 - time (sec): 10.43 - samples/sec: 1377.07 - lr: 0.000015 - momentum: 0.000000
167
+ 2024-03-26 11:48:07,268 epoch 6 - iter 24/48 - loss 0.08891366 - time (sec): 12.51 - samples/sec: 1397.92 - lr: 0.000015 - momentum: 0.000000
168
+ 2024-03-26 11:48:10,008 epoch 6 - iter 28/48 - loss 0.08855013 - time (sec): 15.25 - samples/sec: 1372.63 - lr: 0.000015 - momentum: 0.000000
169
+ 2024-03-26 11:48:12,127 epoch 6 - iter 32/48 - loss 0.08678004 - time (sec): 17.37 - samples/sec: 1352.96 - lr: 0.000015 - momentum: 0.000000
170
+ 2024-03-26 11:48:13,293 epoch 6 - iter 36/48 - loss 0.08791381 - time (sec): 18.54 - samples/sec: 1399.47 - lr: 0.000014 - momentum: 0.000000
171
+ 2024-03-26 11:48:15,565 epoch 6 - iter 40/48 - loss 0.08879619 - time (sec): 20.81 - samples/sec: 1389.61 - lr: 0.000014 - momentum: 0.000000
172
+ 2024-03-26 11:48:17,262 epoch 6 - iter 44/48 - loss 0.09174772 - time (sec): 22.50 - samples/sec: 1410.84 - lr: 0.000014 - momentum: 0.000000
173
+ 2024-03-26 11:48:19,176 epoch 6 - iter 48/48 - loss 0.08921771 - time (sec): 24.42 - samples/sec: 1411.69 - lr: 0.000014 - momentum: 0.000000
174
+ 2024-03-26 11:48:19,176 ----------------------------------------------------------------------------------------------------
175
+ 2024-03-26 11:48:19,176 EPOCH 6 done: loss 0.0892 - lr: 0.000014
176
+ 2024-03-26 11:48:20,141 DEV : loss 0.1853693574666977 - f1-score (micro avg) 0.9087
177
+ 2024-03-26 11:48:20,143 saving best model
178
+ 2024-03-26 11:48:20,630 ----------------------------------------------------------------------------------------------------
179
+ 2024-03-26 11:48:22,266 epoch 7 - iter 4/48 - loss 0.06603823 - time (sec): 1.64 - samples/sec: 1709.98 - lr: 0.000013 - momentum: 0.000000
180
+ 2024-03-26 11:48:24,417 epoch 7 - iter 8/48 - loss 0.05619435 - time (sec): 3.79 - samples/sec: 1616.26 - lr: 0.000013 - momentum: 0.000000
181
+ 2024-03-26 11:48:26,762 epoch 7 - iter 12/48 - loss 0.05569263 - time (sec): 6.13 - samples/sec: 1436.63 - lr: 0.000013 - momentum: 0.000000
182
+ 2024-03-26 11:48:28,025 epoch 7 - iter 16/48 - loss 0.06293055 - time (sec): 7.39 - samples/sec: 1522.02 - lr: 0.000012 - momentum: 0.000000
183
+ 2024-03-26 11:48:30,201 epoch 7 - iter 20/48 - loss 0.06307589 - time (sec): 9.57 - samples/sec: 1498.89 - lr: 0.000012 - momentum: 0.000000
184
+ 2024-03-26 11:48:31,777 epoch 7 - iter 24/48 - loss 0.06017691 - time (sec): 11.15 - samples/sec: 1544.12 - lr: 0.000012 - momentum: 0.000000
185
+ 2024-03-26 11:48:33,986 epoch 7 - iter 28/48 - loss 0.06081892 - time (sec): 13.36 - samples/sec: 1503.01 - lr: 0.000012 - momentum: 0.000000
186
+ 2024-03-26 11:48:36,785 epoch 7 - iter 32/48 - loss 0.06314787 - time (sec): 16.16 - samples/sec: 1441.57 - lr: 0.000011 - momentum: 0.000000
187
+ 2024-03-26 11:48:38,902 epoch 7 - iter 36/48 - loss 0.06250353 - time (sec): 18.27 - samples/sec: 1436.17 - lr: 0.000011 - momentum: 0.000000
188
+ 2024-03-26 11:48:40,055 epoch 7 - iter 40/48 - loss 0.06618433 - time (sec): 19.43 - samples/sec: 1467.11 - lr: 0.000011 - momentum: 0.000000
189
+ 2024-03-26 11:48:42,708 epoch 7 - iter 44/48 - loss 0.06737787 - time (sec): 22.08 - samples/sec: 1452.17 - lr: 0.000010 - momentum: 0.000000
190
+ 2024-03-26 11:48:43,879 epoch 7 - iter 48/48 - loss 0.06792919 - time (sec): 23.25 - samples/sec: 1482.72 - lr: 0.000010 - momentum: 0.000000
191
+ 2024-03-26 11:48:43,880 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 11:48:43,880 EPOCH 7 done: loss 0.0679 - lr: 0.000010
193
+ 2024-03-26 11:48:44,827 DEV : loss 0.18232010304927826 - f1-score (micro avg) 0.91
194
+ 2024-03-26 11:48:44,829 saving best model
195
+ 2024-03-26 11:48:45,300 ----------------------------------------------------------------------------------------------------
196
+ 2024-03-26 11:48:47,467 epoch 8 - iter 4/48 - loss 0.03714663 - time (sec): 2.16 - samples/sec: 1280.39 - lr: 0.000010 - momentum: 0.000000
197
+ 2024-03-26 11:48:50,167 epoch 8 - iter 8/48 - loss 0.03361336 - time (sec): 4.87 - samples/sec: 1241.21 - lr: 0.000010 - momentum: 0.000000
198
+ 2024-03-26 11:48:51,850 epoch 8 - iter 12/48 - loss 0.03532371 - time (sec): 6.55 - samples/sec: 1295.03 - lr: 0.000009 - momentum: 0.000000
199
+ 2024-03-26 11:48:54,494 epoch 8 - iter 16/48 - loss 0.04333594 - time (sec): 9.19 - samples/sec: 1252.38 - lr: 0.000009 - momentum: 0.000000
200
+ 2024-03-26 11:48:56,236 epoch 8 - iter 20/48 - loss 0.04632785 - time (sec): 10.93 - samples/sec: 1299.41 - lr: 0.000009 - momentum: 0.000000
201
+ 2024-03-26 11:48:57,768 epoch 8 - iter 24/48 - loss 0.05319808 - time (sec): 12.47 - samples/sec: 1363.58 - lr: 0.000009 - momentum: 0.000000
202
+ 2024-03-26 11:48:59,674 epoch 8 - iter 28/48 - loss 0.05657064 - time (sec): 14.37 - samples/sec: 1387.59 - lr: 0.000008 - momentum: 0.000000
203
+ 2024-03-26 11:49:02,385 epoch 8 - iter 32/48 - loss 0.05777782 - time (sec): 17.08 - samples/sec: 1375.19 - lr: 0.000008 - momentum: 0.000000
204
+ 2024-03-26 11:49:04,885 epoch 8 - iter 36/48 - loss 0.05931562 - time (sec): 19.58 - samples/sec: 1365.05 - lr: 0.000008 - momentum: 0.000000
205
+ 2024-03-26 11:49:07,154 epoch 8 - iter 40/48 - loss 0.05882360 - time (sec): 21.85 - samples/sec: 1346.48 - lr: 0.000007 - momentum: 0.000000
206
+ 2024-03-26 11:49:09,580 epoch 8 - iter 44/48 - loss 0.05703173 - time (sec): 24.28 - samples/sec: 1330.58 - lr: 0.000007 - momentum: 0.000000
207
+ 2024-03-26 11:49:11,182 epoch 8 - iter 48/48 - loss 0.05700452 - time (sec): 25.88 - samples/sec: 1331.98 - lr: 0.000007 - momentum: 0.000000
208
+ 2024-03-26 11:49:11,182 ----------------------------------------------------------------------------------------------------
209
+ 2024-03-26 11:49:11,182 EPOCH 8 done: loss 0.0570 - lr: 0.000007
210
+ 2024-03-26 11:49:12,150 DEV : loss 0.1904592365026474 - f1-score (micro avg) 0.9126
211
+ 2024-03-26 11:49:12,153 saving best model
212
+ 2024-03-26 11:49:12,624 ----------------------------------------------------------------------------------------------------
213
+ 2024-03-26 11:49:14,556 epoch 9 - iter 4/48 - loss 0.05954110 - time (sec): 1.93 - samples/sec: 1495.61 - lr: 0.000007 - momentum: 0.000000
214
+ 2024-03-26 11:49:17,841 epoch 9 - iter 8/48 - loss 0.05659017 - time (sec): 5.22 - samples/sec: 1206.66 - lr: 0.000006 - momentum: 0.000000
215
+ 2024-03-26 11:49:19,553 epoch 9 - iter 12/48 - loss 0.04714393 - time (sec): 6.93 - samples/sec: 1248.33 - lr: 0.000006 - momentum: 0.000000
216
+ 2024-03-26 11:49:21,495 epoch 9 - iter 16/48 - loss 0.05412922 - time (sec): 8.87 - samples/sec: 1288.76 - lr: 0.000006 - momentum: 0.000000
217
+ 2024-03-26 11:49:24,385 epoch 9 - iter 20/48 - loss 0.04842308 - time (sec): 11.76 - samples/sec: 1262.88 - lr: 0.000006 - momentum: 0.000000
218
+ 2024-03-26 11:49:25,948 epoch 9 - iter 24/48 - loss 0.04794347 - time (sec): 13.32 - samples/sec: 1309.55 - lr: 0.000005 - momentum: 0.000000
219
+ 2024-03-26 11:49:27,975 epoch 9 - iter 28/48 - loss 0.05034416 - time (sec): 15.35 - samples/sec: 1330.81 - lr: 0.000005 - momentum: 0.000000
220
+ 2024-03-26 11:49:30,408 epoch 9 - iter 32/48 - loss 0.04906075 - time (sec): 17.78 - samples/sec: 1306.28 - lr: 0.000005 - momentum: 0.000000
221
+ 2024-03-26 11:49:31,739 epoch 9 - iter 36/48 - loss 0.05395636 - time (sec): 19.11 - samples/sec: 1337.37 - lr: 0.000004 - momentum: 0.000000
222
+ 2024-03-26 11:49:35,032 epoch 9 - iter 40/48 - loss 0.05096711 - time (sec): 22.41 - samples/sec: 1291.46 - lr: 0.000004 - momentum: 0.000000
223
+ 2024-03-26 11:49:37,174 epoch 9 - iter 44/48 - loss 0.04799635 - time (sec): 24.55 - samples/sec: 1315.65 - lr: 0.000004 - momentum: 0.000000
224
+ 2024-03-26 11:49:38,168 epoch 9 - iter 48/48 - loss 0.04898665 - time (sec): 25.54 - samples/sec: 1349.54 - lr: 0.000004 - momentum: 0.000000
225
+ 2024-03-26 11:49:38,168 ----------------------------------------------------------------------------------------------------
226
+ 2024-03-26 11:49:38,168 EPOCH 9 done: loss 0.0490 - lr: 0.000004
227
+ 2024-03-26 11:49:39,113 DEV : loss 0.18231666088104248 - f1-score (micro avg) 0.9251
228
+ 2024-03-26 11:49:39,114 saving best model
229
+ 2024-03-26 11:49:39,563 ----------------------------------------------------------------------------------------------------
230
+ 2024-03-26 11:49:41,526 epoch 10 - iter 4/48 - loss 0.05551802 - time (sec): 1.96 - samples/sec: 1317.05 - lr: 0.000003 - momentum: 0.000000
231
+ 2024-03-26 11:49:44,390 epoch 10 - iter 8/48 - loss 0.03666070 - time (sec): 4.83 - samples/sec: 1198.44 - lr: 0.000003 - momentum: 0.000000
232
+ 2024-03-26 11:49:46,447 epoch 10 - iter 12/48 - loss 0.04190061 - time (sec): 6.88 - samples/sec: 1265.75 - lr: 0.000003 - momentum: 0.000000
233
+ 2024-03-26 11:49:48,559 epoch 10 - iter 16/48 - loss 0.04315321 - time (sec): 9.00 - samples/sec: 1352.32 - lr: 0.000002 - momentum: 0.000000
234
+ 2024-03-26 11:49:49,427 epoch 10 - iter 20/48 - loss 0.04114819 - time (sec): 9.86 - samples/sec: 1431.18 - lr: 0.000002 - momentum: 0.000000
235
+ 2024-03-26 11:49:51,170 epoch 10 - iter 24/48 - loss 0.04045979 - time (sec): 11.61 - samples/sec: 1457.39 - lr: 0.000002 - momentum: 0.000000
236
+ 2024-03-26 11:49:52,116 epoch 10 - iter 28/48 - loss 0.03995345 - time (sec): 12.55 - samples/sec: 1522.22 - lr: 0.000002 - momentum: 0.000000
237
+ 2024-03-26 11:49:54,497 epoch 10 - iter 32/48 - loss 0.03875589 - time (sec): 14.93 - samples/sec: 1489.79 - lr: 0.000001 - momentum: 0.000000
238
+ 2024-03-26 11:49:57,098 epoch 10 - iter 36/48 - loss 0.04305678 - time (sec): 17.53 - samples/sec: 1453.98 - lr: 0.000001 - momentum: 0.000000
239
+ 2024-03-26 11:49:59,095 epoch 10 - iter 40/48 - loss 0.04511330 - time (sec): 19.53 - samples/sec: 1444.56 - lr: 0.000001 - momentum: 0.000000
240
+ 2024-03-26 11:50:01,791 epoch 10 - iter 44/48 - loss 0.04429458 - time (sec): 22.23 - samples/sec: 1430.59 - lr: 0.000001 - momentum: 0.000000
241
+ 2024-03-26 11:50:03,422 epoch 10 - iter 48/48 - loss 0.04405461 - time (sec): 23.86 - samples/sec: 1444.82 - lr: 0.000000 - momentum: 0.000000
242
+ 2024-03-26 11:50:03,423 ----------------------------------------------------------------------------------------------------
243
+ 2024-03-26 11:50:03,423 EPOCH 10 done: loss 0.0441 - lr: 0.000000
244
+ 2024-03-26 11:50:04,381 DEV : loss 0.18572011590003967 - f1-score (micro avg) 0.9186
245
+ 2024-03-26 11:50:04,707 ----------------------------------------------------------------------------------------------------
246
+ 2024-03-26 11:50:04,708 Loading model from best epoch ...
247
+ 2024-03-26 11:50:05,626 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 11:50:06,416
249
+ Results:
250
+ - F-score (micro) 0.9084
251
+ - F-score (macro) 0.6914
252
+ - Accuracy 0.8345
253
+
254
+ By class:
255
+ precision recall f1-score support
256
+
257
+ Unternehmen 0.9144 0.8835 0.8987 266
258
+ Auslagerung 0.8534 0.9116 0.8816 249
259
+ Ort 0.9779 0.9925 0.9852 134
260
+ Software 0.0000 0.0000 0.0000 0
261
+
262
+ micro avg 0.9002 0.9168 0.9084 649
263
+ macro avg 0.6864 0.6969 0.6914 649
264
+ weighted avg 0.9041 0.9168 0.9100 649
265
+
266
+ 2024-03-26 11:50:06,416 ----------------------------------------------------------------------------------------------------