Hugging Face's logo

stefan-it
/
flair-co-funer-german_dbmdz_bert_base-bs16-e10-lr5e-05-2

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
4216430
•
1 Parent(s): 67e3d82

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 15:35:37,399 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 15:35:37,399 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 15:35:37,399 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 15:35:37,399 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 15:35:37,399 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 15:35:37,399 Train: 758 sentences
54
+ 2024-03-26 15:35:37,399 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 15:35:37,399 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 15:35:37,400 Training Params:
57
+ 2024-03-26 15:35:37,400 - learning_rate: "5e-05"
58
+ 2024-03-26 15:35:37,400 - mini_batch_size: "16"
59
+ 2024-03-26 15:35:37,400 - max_epochs: "10"
60
+ 2024-03-26 15:35:37,400 - shuffle: "True"
61
+ 2024-03-26 15:35:37,400 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 15:35:37,400 Plugins:
63
+ 2024-03-26 15:35:37,400 - TensorboardLogger
64
+ 2024-03-26 15:35:37,400 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 15:35:37,400 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 15:35:37,400 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 15:35:37,400 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 15:35:37,400 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 15:35:37,400 Computation:
70
+ 2024-03-26 15:35:37,400 - compute on device: cuda:0
71
+ 2024-03-26 15:35:37,400 - embedding storage: none
72
+ 2024-03-26 15:35:37,400 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 15:35:37,400 Model training base path: "flair-co-funer-german_dbmdz_bert_base-bs16-e10-lr5e-05-2"
74
+ 2024-03-26 15:35:37,400 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 15:35:37,400 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 15:35:37,400 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 15:35:39,129 epoch 1 - iter 4/48 - loss 3.07312460 - time (sec): 1.73 - samples/sec: 1747.50 - lr: 0.000003 - momentum: 0.000000
78
+ 2024-03-26 15:35:41,228 epoch 1 - iter 8/48 - loss 3.02312743 - time (sec): 3.83 - samples/sec: 1621.91 - lr: 0.000007 - momentum: 0.000000
79
+ 2024-03-26 15:35:43,070 epoch 1 - iter 12/48 - loss 2.90188608 - time (sec): 5.67 - samples/sec: 1572.17 - lr: 0.000011 - momentum: 0.000000
80
+ 2024-03-26 15:35:45,086 epoch 1 - iter 16/48 - loss 2.72233276 - time (sec): 7.69 - samples/sec: 1578.74 - lr: 0.000016 - momentum: 0.000000
81
+ 2024-03-26 15:35:47,278 epoch 1 - iter 20/48 - loss 2.59399868 - time (sec): 9.88 - samples/sec: 1546.98 - lr: 0.000020 - momentum: 0.000000
82
+ 2024-03-26 15:35:50,308 epoch 1 - iter 24/48 - loss 2.48249883 - time (sec): 12.91 - samples/sec: 1408.32 - lr: 0.000024 - momentum: 0.000000
83
+ 2024-03-26 15:35:52,713 epoch 1 - iter 28/48 - loss 2.35935279 - time (sec): 15.31 - samples/sec: 1391.83 - lr: 0.000028 - momentum: 0.000000
84
+ 2024-03-26 15:35:53,539 epoch 1 - iter 32/48 - loss 2.28426536 - time (sec): 16.14 - samples/sec: 1446.85 - lr: 0.000032 - momentum: 0.000000
85
+ 2024-03-26 15:35:54,806 epoch 1 - iter 36/48 - loss 2.18399143 - time (sec): 17.41 - samples/sec: 1502.43 - lr: 0.000036 - momentum: 0.000000
86
+ 2024-03-26 15:35:56,683 epoch 1 - iter 40/48 - loss 2.08833547 - time (sec): 19.28 - samples/sec: 1508.62 - lr: 0.000041 - momentum: 0.000000
87
+ 2024-03-26 15:35:58,574 epoch 1 - iter 44/48 - loss 1.98854010 - time (sec): 21.17 - samples/sec: 1509.00 - lr: 0.000045 - momentum: 0.000000
88
+ 2024-03-26 15:35:59,934 epoch 1 - iter 48/48 - loss 1.90654993 - time (sec): 22.53 - samples/sec: 1529.80 - lr: 0.000049 - momentum: 0.000000
89
+ 2024-03-26 15:35:59,934 ----------------------------------------------------------------------------------------------------
90
+ 2024-03-26 15:35:59,934 EPOCH 1 done: loss 1.9065 - lr: 0.000049
91
+ 2024-03-26 15:36:00,761 DEV : loss 0.6141952276229858 - f1-score (micro avg) 0.6085
92
+ 2024-03-26 15:36:00,762 saving best model
93
+ 2024-03-26 15:36:01,041 ----------------------------------------------------------------------------------------------------
94
+ 2024-03-26 15:36:02,355 epoch 2 - iter 4/48 - loss 0.87011800 - time (sec): 1.31 - samples/sec: 2207.91 - lr: 0.000050 - momentum: 0.000000
95
+ 2024-03-26 15:36:04,190 epoch 2 - iter 8/48 - loss 0.71306806 - time (sec): 3.15 - samples/sec: 1936.50 - lr: 0.000049 - momentum: 0.000000
96
+ 2024-03-26 15:36:07,606 epoch 2 - iter 12/48 - loss 0.60363924 - time (sec): 6.56 - samples/sec: 1550.38 - lr: 0.000049 - momentum: 0.000000
97
+ 2024-03-26 15:36:10,070 epoch 2 - iter 16/48 - loss 0.55894177 - time (sec): 9.03 - samples/sec: 1475.29 - lr: 0.000048 - momentum: 0.000000
98
+ 2024-03-26 15:36:12,701 epoch 2 - iter 20/48 - loss 0.52394312 - time (sec): 11.66 - samples/sec: 1424.73 - lr: 0.000048 - momentum: 0.000000
99
+ 2024-03-26 15:36:14,572 epoch 2 - iter 24/48 - loss 0.49100232 - time (sec): 13.53 - samples/sec: 1424.89 - lr: 0.000047 - momentum: 0.000000
100
+ 2024-03-26 15:36:16,335 epoch 2 - iter 28/48 - loss 0.48803275 - time (sec): 15.29 - samples/sec: 1434.06 - lr: 0.000047 - momentum: 0.000000
101
+ 2024-03-26 15:36:18,033 epoch 2 - iter 32/48 - loss 0.47732716 - time (sec): 16.99 - samples/sec: 1448.04 - lr: 0.000046 - momentum: 0.000000
102
+ 2024-03-26 15:36:19,866 epoch 2 - iter 36/48 - loss 0.46725186 - time (sec): 18.82 - samples/sec: 1457.25 - lr: 0.000046 - momentum: 0.000000
103
+ 2024-03-26 15:36:20,877 epoch 2 - iter 40/48 - loss 0.45840695 - time (sec): 19.84 - samples/sec: 1504.95 - lr: 0.000046 - momentum: 0.000000
104
+ 2024-03-26 15:36:22,299 epoch 2 - iter 44/48 - loss 0.45495518 - time (sec): 21.26 - samples/sec: 1524.90 - lr: 0.000045 - momentum: 0.000000
105
+ 2024-03-26 15:36:23,817 epoch 2 - iter 48/48 - loss 0.44213553 - time (sec): 22.78 - samples/sec: 1513.57 - lr: 0.000045 - momentum: 0.000000
106
+ 2024-03-26 15:36:23,817 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 15:36:23,817 EPOCH 2 done: loss 0.4421 - lr: 0.000045
108
+ 2024-03-26 15:36:24,712 DEV : loss 0.27931642532348633 - f1-score (micro avg) 0.8352
109
+ 2024-03-26 15:36:24,713 saving best model
110
+ 2024-03-26 15:36:25,138 ----------------------------------------------------------------------------------------------------
111
+ 2024-03-26 15:36:27,686 epoch 3 - iter 4/48 - loss 0.23770738 - time (sec): 2.55 - samples/sec: 1181.16 - lr: 0.000044 - momentum: 0.000000
112
+ 2024-03-26 15:36:29,820 epoch 3 - iter 8/48 - loss 0.24600668 - time (sec): 4.68 - samples/sec: 1356.26 - lr: 0.000044 - momentum: 0.000000
113
+ 2024-03-26 15:36:31,393 epoch 3 - iter 12/48 - loss 0.26325747 - time (sec): 6.25 - samples/sec: 1418.43 - lr: 0.000043 - momentum: 0.000000
114
+ 2024-03-26 15:36:33,129 epoch 3 - iter 16/48 - loss 0.25250839 - time (sec): 7.99 - samples/sec: 1422.30 - lr: 0.000043 - momentum: 0.000000
115
+ 2024-03-26 15:36:34,277 epoch 3 - iter 20/48 - loss 0.25207231 - time (sec): 9.14 - samples/sec: 1497.09 - lr: 0.000042 - momentum: 0.000000
116
+ 2024-03-26 15:36:36,117 epoch 3 - iter 24/48 - loss 0.25814835 - time (sec): 10.98 - samples/sec: 1498.80 - lr: 0.000042 - momentum: 0.000000
117
+ 2024-03-26 15:36:38,561 epoch 3 - iter 28/48 - loss 0.25191411 - time (sec): 13.42 - samples/sec: 1441.34 - lr: 0.000041 - momentum: 0.000000
118
+ 2024-03-26 15:36:40,411 epoch 3 - iter 32/48 - loss 0.25103396 - time (sec): 15.27 - samples/sec: 1449.61 - lr: 0.000041 - momentum: 0.000000
119
+ 2024-03-26 15:36:41,841 epoch 3 - iter 36/48 - loss 0.24492805 - time (sec): 16.70 - samples/sec: 1483.48 - lr: 0.000040 - momentum: 0.000000
120
+ 2024-03-26 15:36:44,097 epoch 3 - iter 40/48 - loss 0.23624108 - time (sec): 18.96 - samples/sec: 1456.23 - lr: 0.000040 - momentum: 0.000000
121
+ 2024-03-26 15:36:47,342 epoch 3 - iter 44/48 - loss 0.21763247 - time (sec): 22.20 - samples/sec: 1451.22 - lr: 0.000040 - momentum: 0.000000
122
+ 2024-03-26 15:36:48,594 epoch 3 - iter 48/48 - loss 0.21155181 - time (sec): 23.46 - samples/sec: 1469.64 - lr: 0.000039 - momentum: 0.000000
123
+ 2024-03-26 15:36:48,594 ----------------------------------------------------------------------------------------------------
124
+ 2024-03-26 15:36:48,595 EPOCH 3 done: loss 0.2116 - lr: 0.000039
125
+ 2024-03-26 15:36:49,505 DEV : loss 0.2284693866968155 - f1-score (micro avg) 0.8693
126
+ 2024-03-26 15:36:49,507 saving best model
127
+ 2024-03-26 15:36:49,846 ----------------------------------------------------------------------------------------------------
128
+ 2024-03-26 15:36:51,395 epoch 4 - iter 4/48 - loss 0.21854109 - time (sec): 1.55 - samples/sec: 1646.04 - lr: 0.000039 - momentum: 0.000000
129
+ 2024-03-26 15:36:53,687 epoch 4 - iter 8/48 - loss 0.17963265 - time (sec): 3.84 - samples/sec: 1560.36 - lr: 0.000038 - momentum: 0.000000
130
+ 2024-03-26 15:36:54,940 epoch 4 - iter 12/48 - loss 0.16487773 - time (sec): 5.09 - samples/sec: 1641.00 - lr: 0.000038 - momentum: 0.000000
131
+ 2024-03-26 15:36:57,158 epoch 4 - iter 16/48 - loss 0.16632533 - time (sec): 7.31 - samples/sec: 1541.83 - lr: 0.000037 - momentum: 0.000000
132
+ 2024-03-26 15:36:59,682 epoch 4 - iter 20/48 - loss 0.15573120 - time (sec): 9.84 - samples/sec: 1421.53 - lr: 0.000037 - momentum: 0.000000
133
+ 2024-03-26 15:37:01,688 epoch 4 - iter 24/48 - loss 0.16003533 - time (sec): 11.84 - samples/sec: 1421.61 - lr: 0.000036 - momentum: 0.000000
134
+ 2024-03-26 15:37:03,790 epoch 4 - iter 28/48 - loss 0.15561340 - time (sec): 13.94 - samples/sec: 1426.73 - lr: 0.000036 - momentum: 0.000000
135
+ 2024-03-26 15:37:06,333 epoch 4 - iter 32/48 - loss 0.15475400 - time (sec): 16.49 - samples/sec: 1398.72 - lr: 0.000035 - momentum: 0.000000
136
+ 2024-03-26 15:37:09,125 epoch 4 - iter 36/48 - loss 0.14633806 - time (sec): 19.28 - samples/sec: 1387.54 - lr: 0.000035 - momentum: 0.000000
137
+ 2024-03-26 15:37:10,806 epoch 4 - iter 40/48 - loss 0.14249669 - time (sec): 20.96 - samples/sec: 1388.09 - lr: 0.000034 - momentum: 0.000000
138
+ 2024-03-26 15:37:12,785 epoch 4 - iter 44/48 - loss 0.14215231 - time (sec): 22.94 - samples/sec: 1391.66 - lr: 0.000034 - momentum: 0.000000
139
+ 2024-03-26 15:37:14,435 epoch 4 - iter 48/48 - loss 0.14147744 - time (sec): 24.59 - samples/sec: 1401.96 - lr: 0.000034 - momentum: 0.000000
140
+ 2024-03-26 15:37:14,435 ----------------------------------------------------------------------------------------------------
141
+ 2024-03-26 15:37:14,435 EPOCH 4 done: loss 0.1415 - lr: 0.000034
142
+ 2024-03-26 15:37:15,389 DEV : loss 0.19012174010276794 - f1-score (micro avg) 0.8841
143
+ 2024-03-26 15:37:15,390 saving best model
144
+ 2024-03-26 15:37:15,849 ----------------------------------------------------------------------------------------------------
145
+ 2024-03-26 15:37:16,676 epoch 5 - iter 4/48 - loss 0.08789891 - time (sec): 0.83 - samples/sec: 2218.69 - lr: 0.000033 - momentum: 0.000000
146
+ 2024-03-26 15:37:18,049 epoch 5 - iter 8/48 - loss 0.10372291 - time (sec): 2.20 - samples/sec: 2022.02 - lr: 0.000033 - momentum: 0.000000
147
+ 2024-03-26 15:37:20,792 epoch 5 - iter 12/48 - loss 0.10462130 - time (sec): 4.94 - samples/sec: 1614.72 - lr: 0.000032 - momentum: 0.000000
148
+ 2024-03-26 15:37:23,739 epoch 5 - iter 16/48 - loss 0.10346493 - time (sec): 7.89 - samples/sec: 1430.45 - lr: 0.000032 - momentum: 0.000000
149
+ 2024-03-26 15:37:25,113 epoch 5 - iter 20/48 - loss 0.10655057 - time (sec): 9.26 - samples/sec: 1481.95 - lr: 0.000031 - momentum: 0.000000
150
+ 2024-03-26 15:37:27,556 epoch 5 - iter 24/48 - loss 0.10142190 - time (sec): 11.71 - samples/sec: 1431.31 - lr: 0.000031 - momentum: 0.000000
151
+ 2024-03-26 15:37:29,621 epoch 5 - iter 28/48 - loss 0.09756151 - time (sec): 13.77 - samples/sec: 1418.78 - lr: 0.000030 - momentum: 0.000000
152
+ 2024-03-26 15:37:31,861 epoch 5 - iter 32/48 - loss 0.10117255 - time (sec): 16.01 - samples/sec: 1446.65 - lr: 0.000030 - momentum: 0.000000
153
+ 2024-03-26 15:37:33,318 epoch 5 - iter 36/48 - loss 0.10485977 - time (sec): 17.47 - samples/sec: 1470.52 - lr: 0.000029 - momentum: 0.000000
154
+ 2024-03-26 15:37:35,840 epoch 5 - iter 40/48 - loss 0.10064567 - time (sec): 19.99 - samples/sec: 1421.19 - lr: 0.000029 - momentum: 0.000000
155
+ 2024-03-26 15:37:37,913 epoch 5 - iter 44/48 - loss 0.10009326 - time (sec): 22.06 - samples/sec: 1433.90 - lr: 0.000029 - momentum: 0.000000
156
+ 2024-03-26 15:37:39,864 epoch 5 - iter 48/48 - loss 0.09969822 - time (sec): 24.01 - samples/sec: 1435.48 - lr: 0.000028 - momentum: 0.000000
157
+ 2024-03-26 15:37:39,864 ----------------------------------------------------------------------------------------------------
158
+ 2024-03-26 15:37:39,864 EPOCH 5 done: loss 0.0997 - lr: 0.000028
159
+ 2024-03-26 15:37:40,791 DEV : loss 0.18266673386096954 - f1-score (micro avg) 0.9049
160
+ 2024-03-26 15:37:40,792 saving best model
161
+ 2024-03-26 15:37:41,245 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 15:37:42,823 epoch 6 - iter 4/48 - loss 0.07595299 - time (sec): 1.58 - samples/sec: 1577.51 - lr: 0.000028 - momentum: 0.000000
163
+ 2024-03-26 15:37:45,221 epoch 6 - iter 8/48 - loss 0.06704105 - time (sec): 3.98 - samples/sec: 1609.57 - lr: 0.000027 - momentum: 0.000000
164
+ 2024-03-26 15:37:47,160 epoch 6 - iter 12/48 - loss 0.07042495 - time (sec): 5.91 - samples/sec: 1531.43 - lr: 0.000027 - momentum: 0.000000
165
+ 2024-03-26 15:37:49,173 epoch 6 - iter 16/48 - loss 0.06567751 - time (sec): 7.93 - samples/sec: 1529.66 - lr: 0.000026 - momentum: 0.000000
166
+ 2024-03-26 15:37:51,930 epoch 6 - iter 20/48 - loss 0.06815485 - time (sec): 10.68 - samples/sec: 1495.20 - lr: 0.000026 - momentum: 0.000000
167
+ 2024-03-26 15:37:53,436 epoch 6 - iter 24/48 - loss 0.08123693 - time (sec): 12.19 - samples/sec: 1518.39 - lr: 0.000025 - momentum: 0.000000
168
+ 2024-03-26 15:37:54,805 epoch 6 - iter 28/48 - loss 0.08036052 - time (sec): 13.56 - samples/sec: 1524.21 - lr: 0.000025 - momentum: 0.000000
169
+ 2024-03-26 15:37:55,977 epoch 6 - iter 32/48 - loss 0.07729706 - time (sec): 14.73 - samples/sec: 1544.29 - lr: 0.000024 - momentum: 0.000000
170
+ 2024-03-26 15:37:57,449 epoch 6 - iter 36/48 - loss 0.07336392 - time (sec): 16.20 - samples/sec: 1575.73 - lr: 0.000024 - momentum: 0.000000
171
+ 2024-03-26 15:37:59,355 epoch 6 - iter 40/48 - loss 0.07524986 - time (sec): 18.11 - samples/sec: 1564.82 - lr: 0.000023 - momentum: 0.000000
172
+ 2024-03-26 15:38:01,541 epoch 6 - iter 44/48 - loss 0.07188943 - time (sec): 20.30 - samples/sec: 1584.31 - lr: 0.000023 - momentum: 0.000000
173
+ 2024-03-26 15:38:03,193 epoch 6 - iter 48/48 - loss 0.07191073 - time (sec): 21.95 - samples/sec: 1570.65 - lr: 0.000023 - momentum: 0.000000
174
+ 2024-03-26 15:38:03,193 ----------------------------------------------------------------------------------------------------
175
+ 2024-03-26 15:38:03,193 EPOCH 6 done: loss 0.0719 - lr: 0.000023
176
+ 2024-03-26 15:38:04,109 DEV : loss 0.1665915995836258 - f1-score (micro avg) 0.9167
177
+ 2024-03-26 15:38:04,112 saving best model
178
+ 2024-03-26 15:38:04,559 ----------------------------------------------------------------------------------------------------
179
+ 2024-03-26 15:38:06,165 epoch 7 - iter 4/48 - loss 0.04465727 - time (sec): 1.61 - samples/sec: 1516.59 - lr: 0.000022 - momentum: 0.000000
180
+ 2024-03-26 15:38:07,765 epoch 7 - iter 8/48 - loss 0.04957911 - time (sec): 3.21 - samples/sec: 1545.12 - lr: 0.000022 - momentum: 0.000000
181
+ 2024-03-26 15:38:09,870 epoch 7 - iter 12/48 - loss 0.05129160 - time (sec): 5.31 - samples/sec: 1482.12 - lr: 0.000021 - momentum: 0.000000
182
+ 2024-03-26 15:38:11,884 epoch 7 - iter 16/48 - loss 0.05015252 - time (sec): 7.32 - samples/sec: 1521.02 - lr: 0.000021 - momentum: 0.000000
183
+ 2024-03-26 15:38:12,528 epoch 7 - iter 20/48 - loss 0.04819502 - time (sec): 7.97 - samples/sec: 1626.30 - lr: 0.000020 - momentum: 0.000000
184
+ 2024-03-26 15:38:14,111 epoch 7 - iter 24/48 - loss 0.04851626 - time (sec): 9.55 - samples/sec: 1604.11 - lr: 0.000020 - momentum: 0.000000
185
+ 2024-03-26 15:38:16,961 epoch 7 - iter 28/48 - loss 0.04755189 - time (sec): 12.40 - samples/sec: 1501.74 - lr: 0.000019 - momentum: 0.000000
186
+ 2024-03-26 15:38:19,717 epoch 7 - iter 32/48 - loss 0.04786266 - time (sec): 15.16 - samples/sec: 1429.36 - lr: 0.000019 - momentum: 0.000000
187
+ 2024-03-26 15:38:22,448 epoch 7 - iter 36/48 - loss 0.05400353 - time (sec): 17.89 - samples/sec: 1441.13 - lr: 0.000018 - momentum: 0.000000
188
+ 2024-03-26 15:38:24,410 epoch 7 - iter 40/48 - loss 0.05744225 - time (sec): 19.85 - samples/sec: 1448.16 - lr: 0.000018 - momentum: 0.000000
189
+ 2024-03-26 15:38:26,939 epoch 7 - iter 44/48 - loss 0.05714303 - time (sec): 22.38 - samples/sec: 1423.34 - lr: 0.000017 - momentum: 0.000000
190
+ 2024-03-26 15:38:28,677 epoch 7 - iter 48/48 - loss 0.05577251 - time (sec): 24.12 - samples/sec: 1429.34 - lr: 0.000017 - momentum: 0.000000
191
+ 2024-03-26 15:38:28,677 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 15:38:28,677 EPOCH 7 done: loss 0.0558 - lr: 0.000017
193
+ 2024-03-26 15:38:29,574 DEV : loss 0.17425081133842468 - f1-score (micro avg) 0.9086
194
+ 2024-03-26 15:38:29,575 ----------------------------------------------------------------------------------------------------
195
+ 2024-03-26 15:38:32,285 epoch 8 - iter 4/48 - loss 0.04358600 - time (sec): 2.71 - samples/sec: 1218.69 - lr: 0.000017 - momentum: 0.000000
196
+ 2024-03-26 15:38:34,337 epoch 8 - iter 8/48 - loss 0.03704583 - time (sec): 4.76 - samples/sec: 1232.18 - lr: 0.000016 - momentum: 0.000000
197
+ 2024-03-26 15:38:37,518 epoch 8 - iter 12/48 - loss 0.04307949 - time (sec): 7.94 - samples/sec: 1220.10 - lr: 0.000016 - momentum: 0.000000
198
+ 2024-03-26 15:38:39,444 epoch 8 - iter 16/48 - loss 0.04750863 - time (sec): 9.87 - samples/sec: 1250.67 - lr: 0.000015 - momentum: 0.000000
199
+ 2024-03-26 15:38:40,896 epoch 8 - iter 20/48 - loss 0.04531580 - time (sec): 11.32 - samples/sec: 1297.20 - lr: 0.000015 - momentum: 0.000000
200
+ 2024-03-26 15:38:43,316 epoch 8 - iter 24/48 - loss 0.04591327 - time (sec): 13.74 - samples/sec: 1298.64 - lr: 0.000014 - momentum: 0.000000
201
+ 2024-03-26 15:38:45,068 epoch 8 - iter 28/48 - loss 0.04770562 - time (sec): 15.49 - samples/sec: 1334.70 - lr: 0.000014 - momentum: 0.000000
202
+ 2024-03-26 15:38:46,725 epoch 8 - iter 32/48 - loss 0.04682980 - time (sec): 17.15 - samples/sec: 1356.50 - lr: 0.000013 - momentum: 0.000000
203
+ 2024-03-26 15:38:48,007 epoch 8 - iter 36/48 - loss 0.04495140 - time (sec): 18.43 - samples/sec: 1387.94 - lr: 0.000013 - momentum: 0.000000
204
+ 2024-03-26 15:38:50,333 epoch 8 - iter 40/48 - loss 0.04489026 - time (sec): 20.76 - samples/sec: 1396.76 - lr: 0.000012 - momentum: 0.000000
205
+ 2024-03-26 15:38:53,143 epoch 8 - iter 44/48 - loss 0.04213215 - time (sec): 23.57 - samples/sec: 1367.02 - lr: 0.000012 - momentum: 0.000000
206
+ 2024-03-26 15:38:55,050 epoch 8 - iter 48/48 - loss 0.04244810 - time (sec): 25.47 - samples/sec: 1353.19 - lr: 0.000011 - momentum: 0.000000
207
+ 2024-03-26 15:38:55,050 ----------------------------------------------------------------------------------------------------
208
+ 2024-03-26 15:38:55,050 EPOCH 8 done: loss 0.0424 - lr: 0.000011
209
+ 2024-03-26 15:38:55,965 DEV : loss 0.17965388298034668 - f1-score (micro avg) 0.9341
210
+ 2024-03-26 15:38:55,968 saving best model
211
+ 2024-03-26 15:38:56,413 ----------------------------------------------------------------------------------------------------
212
+ 2024-03-26 15:38:58,223 epoch 9 - iter 4/48 - loss 0.04139139 - time (sec): 1.81 - samples/sec: 1571.99 - lr: 0.000011 - momentum: 0.000000
213
+ 2024-03-26 15:39:00,617 epoch 9 - iter 8/48 - loss 0.03244052 - time (sec): 4.20 - samples/sec: 1458.80 - lr: 0.000011 - momentum: 0.000000
214
+ 2024-03-26 15:39:02,946 epoch 9 - iter 12/48 - loss 0.04079715 - time (sec): 6.53 - samples/sec: 1413.06 - lr: 0.000010 - momentum: 0.000000
215
+ 2024-03-26 15:39:04,985 epoch 9 - iter 16/48 - loss 0.04285224 - time (sec): 8.57 - samples/sec: 1411.16 - lr: 0.000010 - momentum: 0.000000
216
+ 2024-03-26 15:39:06,428 epoch 9 - iter 20/48 - loss 0.03763700 - time (sec): 10.01 - samples/sec: 1471.63 - lr: 0.000009 - momentum: 0.000000
217
+ 2024-03-26 15:39:07,623 epoch 9 - iter 24/48 - loss 0.03541261 - time (sec): 11.21 - samples/sec: 1519.85 - lr: 0.000009 - momentum: 0.000000
218
+ 2024-03-26 15:39:09,311 epoch 9 - iter 28/48 - loss 0.03426824 - time (sec): 12.90 - samples/sec: 1533.40 - lr: 0.000008 - momentum: 0.000000
219
+ 2024-03-26 15:39:11,547 epoch 9 - iter 32/48 - loss 0.03918176 - time (sec): 15.13 - samples/sec: 1519.44 - lr: 0.000008 - momentum: 0.000000
220
+ 2024-03-26 15:39:14,194 epoch 9 - iter 36/48 - loss 0.03880368 - time (sec): 17.78 - samples/sec: 1469.17 - lr: 0.000007 - momentum: 0.000000
221
+ 2024-03-26 15:39:17,077 epoch 9 - iter 40/48 - loss 0.03934873 - time (sec): 20.66 - samples/sec: 1426.36 - lr: 0.000007 - momentum: 0.000000
222
+ 2024-03-26 15:39:18,869 epoch 9 - iter 44/48 - loss 0.03857612 - time (sec): 22.46 - samples/sec: 1441.98 - lr: 0.000006 - momentum: 0.000000
223
+ 2024-03-26 15:39:19,899 epoch 9 - iter 48/48 - loss 0.03835348 - time (sec): 23.49 - samples/sec: 1467.80 - lr: 0.000006 - momentum: 0.000000
224
+ 2024-03-26 15:39:19,899 ----------------------------------------------------------------------------------------------------
225
+ 2024-03-26 15:39:19,899 EPOCH 9 done: loss 0.0384 - lr: 0.000006
226
+ 2024-03-26 15:39:20,824 DEV : loss 0.17883603274822235 - f1-score (micro avg) 0.9302
227
+ 2024-03-26 15:39:20,825 ----------------------------------------------------------------------------------------------------
228
+ 2024-03-26 15:39:23,112 epoch 10 - iter 4/48 - loss 0.01116868 - time (sec): 2.29 - samples/sec: 1443.97 - lr: 0.000006 - momentum: 0.000000
229
+ 2024-03-26 15:39:25,167 epoch 10 - iter 8/48 - loss 0.01523454 - time (sec): 4.34 - samples/sec: 1422.79 - lr: 0.000005 - momentum: 0.000000
230
+ 2024-03-26 15:39:27,080 epoch 10 - iter 12/48 - loss 0.01753598 - time (sec): 6.25 - samples/sec: 1410.73 - lr: 0.000005 - momentum: 0.000000
231
+ 2024-03-26 15:39:28,312 epoch 10 - iter 16/48 - loss 0.01945254 - time (sec): 7.49 - samples/sec: 1471.98 - lr: 0.000004 - momentum: 0.000000
232
+ 2024-03-26 15:39:30,220 epoch 10 - iter 20/48 - loss 0.02580218 - time (sec): 9.39 - samples/sec: 1459.18 - lr: 0.000004 - momentum: 0.000000
233
+ 2024-03-26 15:39:32,429 epoch 10 - iter 24/48 - loss 0.03253601 - time (sec): 11.60 - samples/sec: 1431.13 - lr: 0.000003 - momentum: 0.000000
234
+ 2024-03-26 15:39:33,332 epoch 10 - iter 28/48 - loss 0.03209414 - time (sec): 12.51 - samples/sec: 1502.27 - lr: 0.000003 - momentum: 0.000000
235
+ 2024-03-26 15:39:34,592 epoch 10 - iter 32/48 - loss 0.03112196 - time (sec): 13.77 - samples/sec: 1542.81 - lr: 0.000002 - momentum: 0.000000
236
+ 2024-03-26 15:39:37,345 epoch 10 - iter 36/48 - loss 0.03026376 - time (sec): 16.52 - samples/sec: 1494.77 - lr: 0.000002 - momentum: 0.000000
237
+ 2024-03-26 15:39:39,747 epoch 10 - iter 40/48 - loss 0.03004181 - time (sec): 18.92 - samples/sec: 1519.61 - lr: 0.000001 - momentum: 0.000000
238
+ 2024-03-26 15:39:42,280 epoch 10 - iter 44/48 - loss 0.03015505 - time (sec): 21.46 - samples/sec: 1494.94 - lr: 0.000001 - momentum: 0.000000
239
+ 2024-03-26 15:39:44,182 epoch 10 - iter 48/48 - loss 0.02958669 - time (sec): 23.36 - samples/sec: 1475.89 - lr: 0.000000 - momentum: 0.000000
240
+ 2024-03-26 15:39:44,182 ----------------------------------------------------------------------------------------------------
241
+ 2024-03-26 15:39:44,182 EPOCH 10 done: loss 0.0296 - lr: 0.000000
242
+ 2024-03-26 15:39:45,108 DEV : loss 0.1830984354019165 - f1-score (micro avg) 0.9301
243
+ 2024-03-26 15:39:45,404 ----------------------------------------------------------------------------------------------------
244
+ 2024-03-26 15:39:45,405 Loading model from best epoch ...
245
+ 2024-03-26 15:39:46,288 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 15:39:47,144
247
+ Results:
248
+ - F-score (micro) 0.9002
249
+ - F-score (macro) 0.6845
250
+ - Accuracy 0.8208
251
+
252
+ By class:
253
+ precision recall f1-score support
254
+
255
+ Unternehmen 0.8817 0.8684 0.8750 266
256
+ Auslagerung 0.8702 0.9157 0.8924 249
257
+ Ort 0.9565 0.9851 0.9706 134
258
+ Software 0.0000 0.0000 0.0000 0
259
+
260
+ micro avg 0.8901 0.9106 0.9002 649
261
+ macro avg 0.6771 0.6923 0.6845 649
262
+ weighted avg 0.8927 0.9106 0.9014 649
263
+
264
+ 2024-03-26 15:39:47,144 ----------------------------------------------------------------------------------------------------