Hugging Face's logo

stefan-it
/
flair-co-funer-german_dbmdz_bert_base-bs16-e10-lr5e-05-1

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
ef98539
•
1 Parent(s): f389b68

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 15:19:10,879 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 15:19:10,880 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 15:19:10,880 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 15:19:10,880 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 15:19:10,880 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 15:19:10,880 Train: 758 sentences
54
+ 2024-03-26 15:19:10,880 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 15:19:10,880 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 15:19:10,880 Training Params:
57
+ 2024-03-26 15:19:10,880 - learning_rate: "5e-05"
58
+ 2024-03-26 15:19:10,880 - mini_batch_size: "16"
59
+ 2024-03-26 15:19:10,880 - max_epochs: "10"
60
+ 2024-03-26 15:19:10,880 - shuffle: "True"
61
+ 2024-03-26 15:19:10,880 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 15:19:10,880 Plugins:
63
+ 2024-03-26 15:19:10,880 - TensorboardLogger
64
+ 2024-03-26 15:19:10,880 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 15:19:10,880 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 15:19:10,880 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 15:19:10,880 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 15:19:10,880 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 15:19:10,880 Computation:
70
+ 2024-03-26 15:19:10,880 - compute on device: cuda:0
71
+ 2024-03-26 15:19:10,880 - embedding storage: none
72
+ 2024-03-26 15:19:10,880 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 15:19:10,880 Model training base path: "flair-co-funer-german_dbmdz_bert_base-bs16-e10-lr5e-05-1"
74
+ 2024-03-26 15:19:10,880 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 15:19:10,880 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 15:19:10,880 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 15:19:12,847 epoch 1 - iter 4/48 - loss 3.18710618 - time (sec): 1.97 - samples/sec: 1380.24 - lr: 0.000003 - momentum: 0.000000
78
+ 2024-03-26 15:19:14,124 epoch 1 - iter 8/48 - loss 3.09303232 - time (sec): 3.24 - samples/sec: 1661.43 - lr: 0.000007 - momentum: 0.000000
79
+ 2024-03-26 15:19:17,035 epoch 1 - iter 12/48 - loss 2.92685396 - time (sec): 6.15 - samples/sec: 1413.88 - lr: 0.000011 - momentum: 0.000000
80
+ 2024-03-26 15:19:20,178 epoch 1 - iter 16/48 - loss 2.77394981 - time (sec): 9.30 - samples/sec: 1311.46 - lr: 0.000016 - momentum: 0.000000
81
+ 2024-03-26 15:19:22,625 epoch 1 - iter 20/48 - loss 2.60483538 - time (sec): 11.74 - samples/sec: 1309.74 - lr: 0.000020 - momentum: 0.000000
82
+ 2024-03-26 15:19:24,324 epoch 1 - iter 24/48 - loss 2.45562033 - time (sec): 13.44 - samples/sec: 1356.58 - lr: 0.000024 - momentum: 0.000000
83
+ 2024-03-26 15:19:25,898 epoch 1 - iter 28/48 - loss 2.33984829 - time (sec): 15.02 - samples/sec: 1378.49 - lr: 0.000028 - momentum: 0.000000
84
+ 2024-03-26 15:19:27,958 epoch 1 - iter 32/48 - loss 2.22907451 - time (sec): 17.08 - samples/sec: 1384.04 - lr: 0.000032 - momentum: 0.000000
85
+ 2024-03-26 15:19:28,922 epoch 1 - iter 36/48 - loss 2.13980267 - time (sec): 18.04 - samples/sec: 1443.80 - lr: 0.000036 - momentum: 0.000000
86
+ 2024-03-26 15:19:30,847 epoch 1 - iter 40/48 - loss 2.03505922 - time (sec): 19.97 - samples/sec: 1458.26 - lr: 0.000041 - momentum: 0.000000
87
+ 2024-03-26 15:19:32,831 epoch 1 - iter 44/48 - loss 1.93976338 - time (sec): 21.95 - samples/sec: 1443.26 - lr: 0.000045 - momentum: 0.000000
88
+ 2024-03-26 15:19:34,302 epoch 1 - iter 48/48 - loss 1.83562410 - time (sec): 23.42 - samples/sec: 1471.82 - lr: 0.000049 - momentum: 0.000000
89
+ 2024-03-26 15:19:34,302 ----------------------------------------------------------------------------------------------------
90
+ 2024-03-26 15:19:34,302 EPOCH 1 done: loss 1.8356 - lr: 0.000049
91
+ 2024-03-26 15:19:35,110 DEV : loss 0.5811887979507446 - f1-score (micro avg) 0.5756
92
+ 2024-03-26 15:19:35,111 saving best model
93
+ 2024-03-26 15:19:35,406 ----------------------------------------------------------------------------------------------------
94
+ 2024-03-26 15:19:37,866 epoch 2 - iter 4/48 - loss 0.58486496 - time (sec): 2.46 - samples/sec: 1261.37 - lr: 0.000050 - momentum: 0.000000
95
+ 2024-03-26 15:19:39,917 epoch 2 - iter 8/48 - loss 0.58476379 - time (sec): 4.51 - samples/sec: 1466.21 - lr: 0.000049 - momentum: 0.000000
96
+ 2024-03-26 15:19:42,156 epoch 2 - iter 12/48 - loss 0.55560922 - time (sec): 6.75 - samples/sec: 1371.90 - lr: 0.000049 - momentum: 0.000000
97
+ 2024-03-26 15:19:44,192 epoch 2 - iter 16/48 - loss 0.52680501 - time (sec): 8.78 - samples/sec: 1356.44 - lr: 0.000048 - momentum: 0.000000
98
+ 2024-03-26 15:19:46,297 epoch 2 - iter 20/48 - loss 0.50334021 - time (sec): 10.89 - samples/sec: 1377.00 - lr: 0.000048 - momentum: 0.000000
99
+ 2024-03-26 15:19:49,439 epoch 2 - iter 24/48 - loss 0.46270809 - time (sec): 14.03 - samples/sec: 1318.68 - lr: 0.000047 - momentum: 0.000000
100
+ 2024-03-26 15:19:51,796 epoch 2 - iter 28/48 - loss 0.45349179 - time (sec): 16.39 - samples/sec: 1314.34 - lr: 0.000047 - momentum: 0.000000
101
+ 2024-03-26 15:19:53,512 epoch 2 - iter 32/48 - loss 0.44049362 - time (sec): 18.11 - samples/sec: 1332.61 - lr: 0.000046 - momentum: 0.000000
102
+ 2024-03-26 15:19:54,537 epoch 2 - iter 36/48 - loss 0.43314393 - time (sec): 19.13 - samples/sec: 1382.81 - lr: 0.000046 - momentum: 0.000000
103
+ 2024-03-26 15:19:56,393 epoch 2 - iter 40/48 - loss 0.42530707 - time (sec): 20.99 - samples/sec: 1400.87 - lr: 0.000046 - momentum: 0.000000
104
+ 2024-03-26 15:19:58,389 epoch 2 - iter 44/48 - loss 0.41740411 - time (sec): 22.98 - samples/sec: 1397.08 - lr: 0.000045 - momentum: 0.000000
105
+ 2024-03-26 15:19:59,838 epoch 2 - iter 48/48 - loss 0.40956046 - time (sec): 24.43 - samples/sec: 1410.97 - lr: 0.000045 - momentum: 0.000000
106
+ 2024-03-26 15:19:59,839 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 15:19:59,839 EPOCH 2 done: loss 0.4096 - lr: 0.000045
108
+ 2024-03-26 15:20:00,755 DEV : loss 0.272553026676178 - f1-score (micro avg) 0.8298
109
+ 2024-03-26 15:20:00,756 saving best model
110
+ 2024-03-26 15:20:01,196 ----------------------------------------------------------------------------------------------------
111
+ 2024-03-26 15:20:03,756 epoch 3 - iter 4/48 - loss 0.31989894 - time (sec): 2.56 - samples/sec: 1192.67 - lr: 0.000044 - momentum: 0.000000
112
+ 2024-03-26 15:20:05,595 epoch 3 - iter 8/48 - loss 0.27331228 - time (sec): 4.40 - samples/sec: 1333.91 - lr: 0.000044 - momentum: 0.000000
113
+ 2024-03-26 15:20:07,412 epoch 3 - iter 12/48 - loss 0.27445132 - time (sec): 6.22 - samples/sec: 1413.77 - lr: 0.000043 - momentum: 0.000000
114
+ 2024-03-26 15:20:09,808 epoch 3 - iter 16/48 - loss 0.24654164 - time (sec): 8.61 - samples/sec: 1418.25 - lr: 0.000043 - momentum: 0.000000
115
+ 2024-03-26 15:20:11,265 epoch 3 - iter 20/48 - loss 0.25313421 - time (sec): 10.07 - samples/sec: 1469.72 - lr: 0.000042 - momentum: 0.000000
116
+ 2024-03-26 15:20:14,197 epoch 3 - iter 24/48 - loss 0.23543316 - time (sec): 13.00 - samples/sec: 1454.62 - lr: 0.000042 - momentum: 0.000000
117
+ 2024-03-26 15:20:14,966 epoch 3 - iter 28/48 - loss 0.22728542 - time (sec): 13.77 - samples/sec: 1528.13 - lr: 0.000041 - momentum: 0.000000
118
+ 2024-03-26 15:20:17,516 epoch 3 - iter 32/48 - loss 0.21669512 - time (sec): 16.32 - samples/sec: 1472.22 - lr: 0.000041 - momentum: 0.000000
119
+ 2024-03-26 15:20:19,519 epoch 3 - iter 36/48 - loss 0.20670519 - time (sec): 18.32 - samples/sec: 1465.84 - lr: 0.000040 - momentum: 0.000000
120
+ 2024-03-26 15:20:21,407 epoch 3 - iter 40/48 - loss 0.20928493 - time (sec): 20.21 - samples/sec: 1455.87 - lr: 0.000040 - momentum: 0.000000
121
+ 2024-03-26 15:20:23,547 epoch 3 - iter 44/48 - loss 0.20368097 - time (sec): 22.35 - samples/sec: 1459.35 - lr: 0.000040 - momentum: 0.000000
122
+ 2024-03-26 15:20:24,773 epoch 3 - iter 48/48 - loss 0.20349750 - time (sec): 23.58 - samples/sec: 1462.14 - lr: 0.000039 - momentum: 0.000000
123
+ 2024-03-26 15:20:24,773 ----------------------------------------------------------------------------------------------------
124
+ 2024-03-26 15:20:24,774 EPOCH 3 done: loss 0.2035 - lr: 0.000039
125
+ 2024-03-26 15:20:25,672 DEV : loss 0.23047742247581482 - f1-score (micro avg) 0.8644
126
+ 2024-03-26 15:20:25,673 saving best model
127
+ 2024-03-26 15:20:26,144 ----------------------------------------------------------------------------------------------------
128
+ 2024-03-26 15:20:27,630 epoch 4 - iter 4/48 - loss 0.14469592 - time (sec): 1.49 - samples/sec: 1836.29 - lr: 0.000039 - momentum: 0.000000
129
+ 2024-03-26 15:20:30,029 epoch 4 - iter 8/48 - loss 0.14637825 - time (sec): 3.88 - samples/sec: 1477.43 - lr: 0.000038 - momentum: 0.000000
130
+ 2024-03-26 15:20:32,121 epoch 4 - iter 12/48 - loss 0.15299926 - time (sec): 5.98 - samples/sec: 1462.06 - lr: 0.000038 - momentum: 0.000000
131
+ 2024-03-26 15:20:34,281 epoch 4 - iter 16/48 - loss 0.13823076 - time (sec): 8.14 - samples/sec: 1471.76 - lr: 0.000037 - momentum: 0.000000
132
+ 2024-03-26 15:20:37,290 epoch 4 - iter 20/48 - loss 0.13133648 - time (sec): 11.14 - samples/sec: 1389.87 - lr: 0.000037 - momentum: 0.000000
133
+ 2024-03-26 15:20:38,715 epoch 4 - iter 24/48 - loss 0.13273192 - time (sec): 12.57 - samples/sec: 1433.84 - lr: 0.000036 - momentum: 0.000000
134
+ 2024-03-26 15:20:40,234 epoch 4 - iter 28/48 - loss 0.13029406 - time (sec): 14.09 - samples/sec: 1472.01 - lr: 0.000036 - momentum: 0.000000
135
+ 2024-03-26 15:20:42,695 epoch 4 - iter 32/48 - loss 0.13574662 - time (sec): 16.55 - samples/sec: 1464.53 - lr: 0.000035 - momentum: 0.000000
136
+ 2024-03-26 15:20:43,678 epoch 4 - iter 36/48 - loss 0.13547460 - time (sec): 17.53 - samples/sec: 1515.41 - lr: 0.000035 - momentum: 0.000000
137
+ 2024-03-26 15:20:46,040 epoch 4 - iter 40/48 - loss 0.13133812 - time (sec): 19.90 - samples/sec: 1467.93 - lr: 0.000034 - momentum: 0.000000
138
+ 2024-03-26 15:20:47,826 epoch 4 - iter 44/48 - loss 0.13151623 - time (sec): 21.68 - samples/sec: 1488.17 - lr: 0.000034 - momentum: 0.000000
139
+ 2024-03-26 15:20:49,177 epoch 4 - iter 48/48 - loss 0.13003788 - time (sec): 23.03 - samples/sec: 1496.71 - lr: 0.000034 - momentum: 0.000000
140
+ 2024-03-26 15:20:49,177 ----------------------------------------------------------------------------------------------------
141
+ 2024-03-26 15:20:49,177 EPOCH 4 done: loss 0.1300 - lr: 0.000034
142
+ 2024-03-26 15:20:50,080 DEV : loss 0.19684486091136932 - f1-score (micro avg) 0.8822
143
+ 2024-03-26 15:20:50,081 saving best model
144
+ 2024-03-26 15:20:50,536 ----------------------------------------------------------------------------------------------------
145
+ 2024-03-26 15:20:52,431 epoch 5 - iter 4/48 - loss 0.11101026 - time (sec): 1.89 - samples/sec: 1472.44 - lr: 0.000033 - momentum: 0.000000
146
+ 2024-03-26 15:20:54,844 epoch 5 - iter 8/48 - loss 0.09405511 - time (sec): 4.31 - samples/sec: 1378.35 - lr: 0.000033 - momentum: 0.000000
147
+ 2024-03-26 15:20:56,780 epoch 5 - iter 12/48 - loss 0.09868726 - time (sec): 6.24 - samples/sec: 1372.16 - lr: 0.000032 - momentum: 0.000000
148
+ 2024-03-26 15:20:58,770 epoch 5 - iter 16/48 - loss 0.09987471 - time (sec): 8.23 - samples/sec: 1403.14 - lr: 0.000032 - momentum: 0.000000
149
+ 2024-03-26 15:21:00,667 epoch 5 - iter 20/48 - loss 0.10225445 - time (sec): 10.13 - samples/sec: 1412.64 - lr: 0.000031 - momentum: 0.000000
150
+ 2024-03-26 15:21:02,174 epoch 5 - iter 24/48 - loss 0.10614739 - time (sec): 11.64 - samples/sec: 1461.65 - lr: 0.000031 - momentum: 0.000000
151
+ 2024-03-26 15:21:04,347 epoch 5 - iter 28/48 - loss 0.10649413 - time (sec): 13.81 - samples/sec: 1458.67 - lr: 0.000030 - momentum: 0.000000
152
+ 2024-03-26 15:21:06,936 epoch 5 - iter 32/48 - loss 0.10514418 - time (sec): 16.40 - samples/sec: 1443.49 - lr: 0.000030 - momentum: 0.000000
153
+ 2024-03-26 15:21:09,285 epoch 5 - iter 36/48 - loss 0.09964481 - time (sec): 18.75 - samples/sec: 1447.45 - lr: 0.000029 - momentum: 0.000000
154
+ 2024-03-26 15:21:10,168 epoch 5 - iter 40/48 - loss 0.10020545 - time (sec): 19.63 - samples/sec: 1490.45 - lr: 0.000029 - momentum: 0.000000
155
+ 2024-03-26 15:21:12,771 epoch 5 - iter 44/48 - loss 0.09600844 - time (sec): 22.23 - samples/sec: 1456.49 - lr: 0.000029 - momentum: 0.000000
156
+ 2024-03-26 15:21:14,236 epoch 5 - iter 48/48 - loss 0.09625165 - time (sec): 23.70 - samples/sec: 1454.55 - lr: 0.000028 - momentum: 0.000000
157
+ 2024-03-26 15:21:14,236 ----------------------------------------------------------------------------------------------------
158
+ 2024-03-26 15:21:14,237 EPOCH 5 done: loss 0.0963 - lr: 0.000028
159
+ 2024-03-26 15:21:15,149 DEV : loss 0.18545496463775635 - f1-score (micro avg) 0.9018
160
+ 2024-03-26 15:21:15,151 saving best model
161
+ 2024-03-26 15:21:15,614 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 15:21:17,602 epoch 6 - iter 4/48 - loss 0.06257767 - time (sec): 1.99 - samples/sec: 1330.90 - lr: 0.000028 - momentum: 0.000000
163
+ 2024-03-26 15:21:19,694 epoch 6 - iter 8/48 - loss 0.08686096 - time (sec): 4.08 - samples/sec: 1356.29 - lr: 0.000027 - momentum: 0.000000
164
+ 2024-03-26 15:21:21,500 epoch 6 - iter 12/48 - loss 0.08442024 - time (sec): 5.88 - samples/sec: 1468.53 - lr: 0.000027 - momentum: 0.000000
165
+ 2024-03-26 15:21:23,710 epoch 6 - iter 16/48 - loss 0.08112975 - time (sec): 8.09 - samples/sec: 1419.29 - lr: 0.000026 - momentum: 0.000000
166
+ 2024-03-26 15:21:25,455 epoch 6 - iter 20/48 - loss 0.08423255 - time (sec): 9.84 - samples/sec: 1426.20 - lr: 0.000026 - momentum: 0.000000
167
+ 2024-03-26 15:21:27,886 epoch 6 - iter 24/48 - loss 0.07972403 - time (sec): 12.27 - samples/sec: 1403.28 - lr: 0.000025 - momentum: 0.000000
168
+ 2024-03-26 15:21:29,707 epoch 6 - iter 28/48 - loss 0.08176774 - time (sec): 14.09 - samples/sec: 1403.53 - lr: 0.000025 - momentum: 0.000000
169
+ 2024-03-26 15:21:32,151 epoch 6 - iter 32/48 - loss 0.08182395 - time (sec): 16.54 - samples/sec: 1382.24 - lr: 0.000024 - momentum: 0.000000
170
+ 2024-03-26 15:21:35,535 epoch 6 - iter 36/48 - loss 0.07761302 - time (sec): 19.92 - samples/sec: 1338.70 - lr: 0.000024 - momentum: 0.000000
171
+ 2024-03-26 15:21:37,124 epoch 6 - iter 40/48 - loss 0.07583205 - time (sec): 21.51 - samples/sec: 1373.90 - lr: 0.000023 - momentum: 0.000000
172
+ 2024-03-26 15:21:38,926 epoch 6 - iter 44/48 - loss 0.07472669 - time (sec): 23.31 - samples/sec: 1377.69 - lr: 0.000023 - momentum: 0.000000
173
+ 2024-03-26 15:21:40,201 epoch 6 - iter 48/48 - loss 0.07681090 - time (sec): 24.59 - samples/sec: 1402.13 - lr: 0.000023 - momentum: 0.000000
174
+ 2024-03-26 15:21:40,201 ----------------------------------------------------------------------------------------------------
175
+ 2024-03-26 15:21:40,201 EPOCH 6 done: loss 0.0768 - lr: 0.000023
176
+ 2024-03-26 15:21:41,112 DEV : loss 0.18713432550430298 - f1-score (micro avg) 0.9134
177
+ 2024-03-26 15:21:41,114 saving best model
178
+ 2024-03-26 15:21:41,539 ----------------------------------------------------------------------------------------------------
179
+ 2024-03-26 15:21:43,160 epoch 7 - iter 4/48 - loss 0.09293975 - time (sec): 1.62 - samples/sec: 1696.85 - lr: 0.000022 - momentum: 0.000000
180
+ 2024-03-26 15:21:45,287 epoch 7 - iter 8/48 - loss 0.07180060 - time (sec): 3.75 - samples/sec: 1435.30 - lr: 0.000022 - momentum: 0.000000
181
+ 2024-03-26 15:21:47,573 epoch 7 - iter 12/48 - loss 0.07251455 - time (sec): 6.03 - samples/sec: 1376.28 - lr: 0.000021 - momentum: 0.000000
182
+ 2024-03-26 15:21:50,141 epoch 7 - iter 16/48 - loss 0.06294037 - time (sec): 8.60 - samples/sec: 1342.06 - lr: 0.000021 - momentum: 0.000000
183
+ 2024-03-26 15:21:52,401 epoch 7 - iter 20/48 - loss 0.06103248 - time (sec): 10.86 - samples/sec: 1345.79 - lr: 0.000020 - momentum: 0.000000
184
+ 2024-03-26 15:21:53,748 epoch 7 - iter 24/48 - loss 0.05931107 - time (sec): 12.21 - samples/sec: 1401.44 - lr: 0.000020 - momentum: 0.000000
185
+ 2024-03-26 15:21:55,138 epoch 7 - iter 28/48 - loss 0.05692812 - time (sec): 13.60 - samples/sec: 1466.97 - lr: 0.000019 - momentum: 0.000000
186
+ 2024-03-26 15:21:57,107 epoch 7 - iter 32/48 - loss 0.05413519 - time (sec): 15.57 - samples/sec: 1457.06 - lr: 0.000019 - momentum: 0.000000
187
+ 2024-03-26 15:21:59,243 epoch 7 - iter 36/48 - loss 0.05205198 - time (sec): 17.70 - samples/sec: 1446.84 - lr: 0.000018 - momentum: 0.000000
188
+ 2024-03-26 15:22:01,686 epoch 7 - iter 40/48 - loss 0.05290442 - time (sec): 20.15 - samples/sec: 1426.73 - lr: 0.000018 - momentum: 0.000000
189
+ 2024-03-26 15:22:03,506 epoch 7 - iter 44/48 - loss 0.05308150 - time (sec): 21.97 - samples/sec: 1443.20 - lr: 0.000017 - momentum: 0.000000
190
+ 2024-03-26 15:22:05,405 epoch 7 - iter 48/48 - loss 0.05261033 - time (sec): 23.86 - samples/sec: 1444.48 - lr: 0.000017 - momentum: 0.000000
191
+ 2024-03-26 15:22:05,405 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 15:22:05,405 EPOCH 7 done: loss 0.0526 - lr: 0.000017
193
+ 2024-03-26 15:22:06,353 DEV : loss 0.1793615221977234 - f1-score (micro avg) 0.911
194
+ 2024-03-26 15:22:06,355 ----------------------------------------------------------------------------------------------------
195
+ 2024-03-26 15:22:08,300 epoch 8 - iter 4/48 - loss 0.04398425 - time (sec): 1.94 - samples/sec: 1390.21 - lr: 0.000017 - momentum: 0.000000
196
+ 2024-03-26 15:22:11,067 epoch 8 - iter 8/48 - loss 0.04003061 - time (sec): 4.71 - samples/sec: 1179.46 - lr: 0.000016 - momentum: 0.000000
197
+ 2024-03-26 15:22:12,332 epoch 8 - iter 12/48 - loss 0.04018561 - time (sec): 5.98 - samples/sec: 1335.91 - lr: 0.000016 - momentum: 0.000000
198
+ 2024-03-26 15:22:14,718 epoch 8 - iter 16/48 - loss 0.04398152 - time (sec): 8.36 - samples/sec: 1346.18 - lr: 0.000015 - momentum: 0.000000
199
+ 2024-03-26 15:22:17,196 epoch 8 - iter 20/48 - loss 0.03752477 - time (sec): 10.84 - samples/sec: 1390.07 - lr: 0.000015 - momentum: 0.000000
200
+ 2024-03-26 15:22:18,470 epoch 8 - iter 24/48 - loss 0.03831492 - time (sec): 12.11 - samples/sec: 1469.13 - lr: 0.000014 - momentum: 0.000000
201
+ 2024-03-26 15:22:21,703 epoch 8 - iter 28/48 - loss 0.03971932 - time (sec): 15.35 - samples/sec: 1421.87 - lr: 0.000014 - momentum: 0.000000
202
+ 2024-03-26 15:22:23,681 epoch 8 - iter 32/48 - loss 0.04079558 - time (sec): 17.32 - samples/sec: 1423.06 - lr: 0.000013 - momentum: 0.000000
203
+ 2024-03-26 15:22:24,735 epoch 8 - iter 36/48 - loss 0.04136868 - time (sec): 18.38 - samples/sec: 1460.99 - lr: 0.000013 - momentum: 0.000000
204
+ 2024-03-26 15:22:26,389 epoch 8 - iter 40/48 - loss 0.04156890 - time (sec): 20.03 - samples/sec: 1458.98 - lr: 0.000012 - momentum: 0.000000
205
+ 2024-03-26 15:22:27,955 epoch 8 - iter 44/48 - loss 0.04044990 - time (sec): 21.60 - samples/sec: 1479.33 - lr: 0.000012 - momentum: 0.000000
206
+ 2024-03-26 15:22:29,881 epoch 8 - iter 48/48 - loss 0.04185402 - time (sec): 23.53 - samples/sec: 1465.33 - lr: 0.000011 - momentum: 0.000000
207
+ 2024-03-26 15:22:29,881 ----------------------------------------------------------------------------------------------------
208
+ 2024-03-26 15:22:29,881 EPOCH 8 done: loss 0.0419 - lr: 0.000011
209
+ 2024-03-26 15:22:30,781 DEV : loss 0.1833573579788208 - f1-score (micro avg) 0.9202
210
+ 2024-03-26 15:22:30,782 saving best model
211
+ 2024-03-26 15:22:31,220 ----------------------------------------------------------------------------------------------------
212
+ 2024-03-26 15:22:33,067 epoch 9 - iter 4/48 - loss 0.01983911 - time (sec): 1.84 - samples/sec: 1452.18 - lr: 0.000011 - momentum: 0.000000
213
+ 2024-03-26 15:22:36,225 epoch 9 - iter 8/48 - loss 0.01479519 - time (sec): 5.00 - samples/sec: 1248.34 - lr: 0.000011 - momentum: 0.000000
214
+ 2024-03-26 15:22:37,878 epoch 9 - iter 12/48 - loss 0.02269400 - time (sec): 6.66 - samples/sec: 1305.81 - lr: 0.000010 - momentum: 0.000000
215
+ 2024-03-26 15:22:40,119 epoch 9 - iter 16/48 - loss 0.02357261 - time (sec): 8.90 - samples/sec: 1295.05 - lr: 0.000010 - momentum: 0.000000
216
+ 2024-03-26 15:22:42,385 epoch 9 - iter 20/48 - loss 0.02814877 - time (sec): 11.16 - samples/sec: 1325.41 - lr: 0.000009 - momentum: 0.000000
217
+ 2024-03-26 15:22:44,548 epoch 9 - iter 24/48 - loss 0.02932997 - time (sec): 13.33 - samples/sec: 1342.11 - lr: 0.000009 - momentum: 0.000000
218
+ 2024-03-26 15:22:46,915 epoch 9 - iter 28/48 - loss 0.02799787 - time (sec): 15.69 - samples/sec: 1335.53 - lr: 0.000008 - momentum: 0.000000
219
+ 2024-03-26 15:22:49,248 epoch 9 - iter 32/48 - loss 0.02763381 - time (sec): 18.03 - samples/sec: 1332.11 - lr: 0.000008 - momentum: 0.000000
220
+ 2024-03-26 15:22:51,038 epoch 9 - iter 36/48 - loss 0.03042036 - time (sec): 19.82 - samples/sec: 1351.06 - lr: 0.000007 - momentum: 0.000000
221
+ 2024-03-26 15:22:53,218 epoch 9 - iter 40/48 - loss 0.03212191 - time (sec): 22.00 - samples/sec: 1340.54 - lr: 0.000007 - momentum: 0.000000
222
+ 2024-03-26 15:22:55,349 epoch 9 - iter 44/48 - loss 0.03178939 - time (sec): 24.13 - samples/sec: 1351.29 - lr: 0.000006 - momentum: 0.000000
223
+ 2024-03-26 15:22:56,102 epoch 9 - iter 48/48 - loss 0.03247208 - time (sec): 24.88 - samples/sec: 1385.53 - lr: 0.000006 - momentum: 0.000000
224
+ 2024-03-26 15:22:56,102 ----------------------------------------------------------------------------------------------------
225
+ 2024-03-26 15:22:56,103 EPOCH 9 done: loss 0.0325 - lr: 0.000006
226
+ 2024-03-26 15:22:57,024 DEV : loss 0.18409405648708344 - f1-score (micro avg) 0.922
227
+ 2024-03-26 15:22:57,025 saving best model
228
+ 2024-03-26 15:22:57,468 ----------------------------------------------------------------------------------------------------
229
+ 2024-03-26 15:22:59,218 epoch 10 - iter 4/48 - loss 0.02465374 - time (sec): 1.75 - samples/sec: 1502.78 - lr: 0.000006 - momentum: 0.000000
230
+ 2024-03-26 15:23:01,162 epoch 10 - iter 8/48 - loss 0.02043026 - time (sec): 3.69 - samples/sec: 1500.48 - lr: 0.000005 - momentum: 0.000000
231
+ 2024-03-26 15:23:03,770 epoch 10 - iter 12/48 - loss 0.02341113 - time (sec): 6.30 - samples/sec: 1385.00 - lr: 0.000005 - momentum: 0.000000
232
+ 2024-03-26 15:23:05,677 epoch 10 - iter 16/48 - loss 0.02494848 - time (sec): 8.21 - samples/sec: 1397.68 - lr: 0.000004 - momentum: 0.000000
233
+ 2024-03-26 15:23:07,497 epoch 10 - iter 20/48 - loss 0.02414231 - time (sec): 10.03 - samples/sec: 1442.51 - lr: 0.000004 - momentum: 0.000000
234
+ 2024-03-26 15:23:09,127 epoch 10 - iter 24/48 - loss 0.02884870 - time (sec): 11.66 - samples/sec: 1454.73 - lr: 0.000003 - momentum: 0.000000
235
+ 2024-03-26 15:23:10,862 epoch 10 - iter 28/48 - loss 0.02687785 - time (sec): 13.39 - samples/sec: 1477.39 - lr: 0.000003 - momentum: 0.000000
236
+ 2024-03-26 15:23:12,055 epoch 10 - iter 32/48 - loss 0.02669034 - time (sec): 14.59 - samples/sec: 1509.99 - lr: 0.000002 - momentum: 0.000000
237
+ 2024-03-26 15:23:15,009 epoch 10 - iter 36/48 - loss 0.02386780 - time (sec): 17.54 - samples/sec: 1460.35 - lr: 0.000002 - momentum: 0.000000
238
+ 2024-03-26 15:23:17,775 epoch 10 - iter 40/48 - loss 0.02684189 - time (sec): 20.31 - samples/sec: 1432.15 - lr: 0.000001 - momentum: 0.000000
239
+ 2024-03-26 15:23:20,553 epoch 10 - iter 44/48 - loss 0.02557963 - time (sec): 23.08 - samples/sec: 1398.52 - lr: 0.000001 - momentum: 0.000000
240
+ 2024-03-26 15:23:22,144 epoch 10 - iter 48/48 - loss 0.02482446 - time (sec): 24.67 - samples/sec: 1397.05 - lr: 0.000000 - momentum: 0.000000
241
+ 2024-03-26 15:23:22,144 ----------------------------------------------------------------------------------------------------
242
+ 2024-03-26 15:23:22,144 EPOCH 10 done: loss 0.0248 - lr: 0.000000
243
+ 2024-03-26 15:23:23,081 DEV : loss 0.183772012591362 - f1-score (micro avg) 0.927
244
+ 2024-03-26 15:23:23,083 saving best model
245
+ 2024-03-26 15:23:23,957 ----------------------------------------------------------------------------------------------------
246
+ 2024-03-26 15:23:23,957 Loading model from best epoch ...
247
+ 2024-03-26 15:23:24,860 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 15:23:25,631
249
+ Results:
250
+ - F-score (micro) 0.9052
251
+ - F-score (macro) 0.689
252
+ - Accuracy 0.8303
253
+
254
+ By class:
255
+ precision recall f1-score support
256
+
257
+ Unternehmen 0.8902 0.8835 0.8868 266
258
+ Auslagerung 0.8577 0.9197 0.8876 249
259
+ Ort 0.9708 0.9925 0.9815 134
260
+ Software 0.0000 0.0000 0.0000 0
261
+
262
+ micro avg 0.8910 0.9199 0.9052 649
263
+ macro avg 0.6797 0.6989 0.6890 649
264
+ weighted avg 0.8943 0.9199 0.9067 649
265
+
266
+ 2024-03-26 15:23:25,631 ----------------------------------------------------------------------------------------------------