Hugging Face's logo

stefan-it
/
flair-co-funer-german_dbmdz_bert_base-bs16-e10-lr5e-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
ddfd409
•
1 Parent(s): 4dd048d

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 15:52:02,958 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 15:52:02,959 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 15:52:02,959 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 15:52:02,959 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 15:52:02,959 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 15:52:02,959 Train: 758 sentences
54
+ 2024-03-26 15:52:02,959 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 15:52:02,959 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 15:52:02,959 Training Params:
57
+ 2024-03-26 15:52:02,959 - learning_rate: "5e-05"
58
+ 2024-03-26 15:52:02,959 - mini_batch_size: "16"
59
+ 2024-03-26 15:52:02,959 - max_epochs: "10"
60
+ 2024-03-26 15:52:02,959 - shuffle: "True"
61
+ 2024-03-26 15:52:02,959 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 15:52:02,959 Plugins:
63
+ 2024-03-26 15:52:02,959 - TensorboardLogger
64
+ 2024-03-26 15:52:02,959 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 15:52:02,959 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 15:52:02,959 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 15:52:02,959 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 15:52:02,959 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 15:52:02,959 Computation:
70
+ 2024-03-26 15:52:02,959 - compute on device: cuda:0
71
+ 2024-03-26 15:52:02,959 - embedding storage: none
72
+ 2024-03-26 15:52:02,959 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 15:52:02,959 Model training base path: "flair-co-funer-german_dbmdz_bert_base-bs16-e10-lr5e-05-3"
74
+ 2024-03-26 15:52:02,959 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 15:52:02,959 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 15:52:02,959 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 15:52:04,198 epoch 1 - iter 4/48 - loss 3.36871580 - time (sec): 1.24 - samples/sec: 2223.21 - lr: 0.000003 - momentum: 0.000000
78
+ 2024-03-26 15:52:06,153 epoch 1 - iter 8/48 - loss 3.35491608 - time (sec): 3.19 - samples/sec: 1823.73 - lr: 0.000007 - momentum: 0.000000
79
+ 2024-03-26 15:52:07,676 epoch 1 - iter 12/48 - loss 3.27876324 - time (sec): 4.72 - samples/sec: 1775.38 - lr: 0.000011 - momentum: 0.000000
80
+ 2024-03-26 15:52:10,553 epoch 1 - iter 16/48 - loss 3.11865705 - time (sec): 7.59 - samples/sec: 1527.33 - lr: 0.000016 - momentum: 0.000000
81
+ 2024-03-26 15:52:12,193 epoch 1 - iter 20/48 - loss 2.92420891 - time (sec): 9.23 - samples/sec: 1559.91 - lr: 0.000020 - momentum: 0.000000
82
+ 2024-03-26 15:52:13,621 epoch 1 - iter 24/48 - loss 2.79486934 - time (sec): 10.66 - samples/sec: 1610.32 - lr: 0.000024 - momentum: 0.000000
83
+ 2024-03-26 15:52:14,931 epoch 1 - iter 28/48 - loss 2.64942505 - time (sec): 11.97 - samples/sec: 1631.10 - lr: 0.000028 - momentum: 0.000000
84
+ 2024-03-26 15:52:17,003 epoch 1 - iter 32/48 - loss 2.49591100 - time (sec): 14.04 - samples/sec: 1618.44 - lr: 0.000032 - momentum: 0.000000
85
+ 2024-03-26 15:52:18,551 epoch 1 - iter 36/48 - loss 2.36472815 - time (sec): 15.59 - samples/sec: 1636.77 - lr: 0.000036 - momentum: 0.000000
86
+ 2024-03-26 15:52:20,770 epoch 1 - iter 40/48 - loss 2.21807707 - time (sec): 17.81 - samples/sec: 1626.92 - lr: 0.000041 - momentum: 0.000000
87
+ 2024-03-26 15:52:22,666 epoch 1 - iter 44/48 - loss 2.09300028 - time (sec): 19.71 - samples/sec: 1627.18 - lr: 0.000045 - momentum: 0.000000
88
+ 2024-03-26 15:52:24,279 epoch 1 - iter 48/48 - loss 1.99414814 - time (sec): 21.32 - samples/sec: 1616.93 - lr: 0.000049 - momentum: 0.000000
89
+ 2024-03-26 15:52:24,279 ----------------------------------------------------------------------------------------------------
90
+ 2024-03-26 15:52:24,279 EPOCH 1 done: loss 1.9941 - lr: 0.000049
91
+ 2024-03-26 15:52:25,089 DEV : loss 0.534384548664093 - f1-score (micro avg) 0.6359
92
+ 2024-03-26 15:52:25,090 saving best model
93
+ 2024-03-26 15:52:25,350 ----------------------------------------------------------------------------------------------------
94
+ 2024-03-26 15:52:26,756 epoch 2 - iter 4/48 - loss 0.67744424 - time (sec): 1.41 - samples/sec: 1775.23 - lr: 0.000050 - momentum: 0.000000
95
+ 2024-03-26 15:52:28,206 epoch 2 - iter 8/48 - loss 0.55139495 - time (sec): 2.85 - samples/sec: 1709.87 - lr: 0.000049 - momentum: 0.000000
96
+ 2024-03-26 15:52:29,612 epoch 2 - iter 12/48 - loss 0.54765888 - time (sec): 4.26 - samples/sec: 1803.91 - lr: 0.000049 - momentum: 0.000000
97
+ 2024-03-26 15:52:31,456 epoch 2 - iter 16/48 - loss 0.50626208 - time (sec): 6.11 - samples/sec: 1761.98 - lr: 0.000048 - momentum: 0.000000
98
+ 2024-03-26 15:52:33,777 epoch 2 - iter 20/48 - loss 0.49532790 - time (sec): 8.43 - samples/sec: 1682.91 - lr: 0.000048 - momentum: 0.000000
99
+ 2024-03-26 15:52:35,771 epoch 2 - iter 24/48 - loss 0.46590322 - time (sec): 10.42 - samples/sec: 1664.63 - lr: 0.000047 - momentum: 0.000000
100
+ 2024-03-26 15:52:38,456 epoch 2 - iter 28/48 - loss 0.45169069 - time (sec): 13.10 - samples/sec: 1596.77 - lr: 0.000047 - momentum: 0.000000
101
+ 2024-03-26 15:52:40,618 epoch 2 - iter 32/48 - loss 0.43566903 - time (sec): 15.27 - samples/sec: 1563.38 - lr: 0.000046 - momentum: 0.000000
102
+ 2024-03-26 15:52:42,312 epoch 2 - iter 36/48 - loss 0.43297444 - time (sec): 16.96 - samples/sec: 1557.48 - lr: 0.000046 - momentum: 0.000000
103
+ 2024-03-26 15:52:43,999 epoch 2 - iter 40/48 - loss 0.43365283 - time (sec): 18.65 - samples/sec: 1564.35 - lr: 0.000046 - momentum: 0.000000
104
+ 2024-03-26 15:52:46,130 epoch 2 - iter 44/48 - loss 0.42306738 - time (sec): 20.78 - samples/sec: 1559.38 - lr: 0.000045 - momentum: 0.000000
105
+ 2024-03-26 15:52:47,625 epoch 2 - iter 48/48 - loss 0.41433491 - time (sec): 22.27 - samples/sec: 1547.60 - lr: 0.000045 - momentum: 0.000000
106
+ 2024-03-26 15:52:47,626 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 15:52:47,626 EPOCH 2 done: loss 0.4143 - lr: 0.000045
108
+ 2024-03-26 15:52:48,507 DEV : loss 0.27958521246910095 - f1-score (micro avg) 0.8259
109
+ 2024-03-26 15:52:48,508 saving best model
110
+ 2024-03-26 15:52:48,954 ----------------------------------------------------------------------------------------------------
111
+ 2024-03-26 15:52:50,440 epoch 3 - iter 4/48 - loss 0.27629199 - time (sec): 1.48 - samples/sec: 1650.03 - lr: 0.000044 - momentum: 0.000000
112
+ 2024-03-26 15:52:53,216 epoch 3 - iter 8/48 - loss 0.21900262 - time (sec): 4.26 - samples/sec: 1344.64 - lr: 0.000044 - momentum: 0.000000
113
+ 2024-03-26 15:52:54,448 epoch 3 - iter 12/48 - loss 0.23721159 - time (sec): 5.49 - samples/sec: 1483.07 - lr: 0.000043 - momentum: 0.000000
114
+ 2024-03-26 15:52:55,799 epoch 3 - iter 16/48 - loss 0.22015402 - time (sec): 6.84 - samples/sec: 1612.92 - lr: 0.000043 - momentum: 0.000000
115
+ 2024-03-26 15:52:57,237 epoch 3 - iter 20/48 - loss 0.22188495 - time (sec): 8.28 - samples/sec: 1631.55 - lr: 0.000042 - momentum: 0.000000
116
+ 2024-03-26 15:52:59,912 epoch 3 - iter 24/48 - loss 0.21454789 - time (sec): 10.96 - samples/sec: 1524.48 - lr: 0.000042 - momentum: 0.000000
117
+ 2024-03-26 15:53:01,801 epoch 3 - iter 28/48 - loss 0.21846474 - time (sec): 12.85 - samples/sec: 1542.93 - lr: 0.000041 - momentum: 0.000000
118
+ 2024-03-26 15:53:04,292 epoch 3 - iter 32/48 - loss 0.20921952 - time (sec): 15.34 - samples/sec: 1486.76 - lr: 0.000041 - momentum: 0.000000
119
+ 2024-03-26 15:53:06,201 epoch 3 - iter 36/48 - loss 0.21499627 - time (sec): 17.25 - samples/sec: 1483.18 - lr: 0.000040 - momentum: 0.000000
120
+ 2024-03-26 15:53:08,534 epoch 3 - iter 40/48 - loss 0.20811360 - time (sec): 19.58 - samples/sec: 1458.97 - lr: 0.000040 - momentum: 0.000000
121
+ 2024-03-26 15:53:10,945 epoch 3 - iter 44/48 - loss 0.21735434 - time (sec): 21.99 - samples/sec: 1447.14 - lr: 0.000040 - momentum: 0.000000
122
+ 2024-03-26 15:53:13,249 epoch 3 - iter 48/48 - loss 0.20978841 - time (sec): 24.29 - samples/sec: 1418.97 - lr: 0.000039 - momentum: 0.000000
123
+ 2024-03-26 15:53:13,249 ----------------------------------------------------------------------------------------------------
124
+ 2024-03-26 15:53:13,249 EPOCH 3 done: loss 0.2098 - lr: 0.000039
125
+ 2024-03-26 15:53:14,147 DEV : loss 0.1994694024324417 - f1-score (micro avg) 0.8687
126
+ 2024-03-26 15:53:14,149 saving best model
127
+ 2024-03-26 15:53:14,593 ----------------------------------------------------------------------------------------------------
128
+ 2024-03-26 15:53:15,971 epoch 4 - iter 4/48 - loss 0.15914292 - time (sec): 1.38 - samples/sec: 1820.14 - lr: 0.000039 - momentum: 0.000000
129
+ 2024-03-26 15:53:17,861 epoch 4 - iter 8/48 - loss 0.14834117 - time (sec): 3.27 - samples/sec: 1640.83 - lr: 0.000038 - momentum: 0.000000
130
+ 2024-03-26 15:53:20,373 epoch 4 - iter 12/48 - loss 0.13533886 - time (sec): 5.78 - samples/sec: 1460.32 - lr: 0.000038 - momentum: 0.000000
131
+ 2024-03-26 15:53:22,252 epoch 4 - iter 16/48 - loss 0.14253572 - time (sec): 7.66 - samples/sec: 1478.91 - lr: 0.000037 - momentum: 0.000000
132
+ 2024-03-26 15:53:24,628 epoch 4 - iter 20/48 - loss 0.13383594 - time (sec): 10.03 - samples/sec: 1464.44 - lr: 0.000037 - momentum: 0.000000
133
+ 2024-03-26 15:53:27,500 epoch 4 - iter 24/48 - loss 0.12723340 - time (sec): 12.91 - samples/sec: 1412.93 - lr: 0.000036 - momentum: 0.000000
134
+ 2024-03-26 15:53:28,611 epoch 4 - iter 28/48 - loss 0.12587698 - time (sec): 14.02 - samples/sec: 1449.28 - lr: 0.000036 - momentum: 0.000000
135
+ 2024-03-26 15:53:31,598 epoch 4 - iter 32/48 - loss 0.12620216 - time (sec): 17.00 - samples/sec: 1389.04 - lr: 0.000035 - momentum: 0.000000
136
+ 2024-03-26 15:53:33,309 epoch 4 - iter 36/48 - loss 0.12972818 - time (sec): 18.71 - samples/sec: 1421.66 - lr: 0.000035 - momentum: 0.000000
137
+ 2024-03-26 15:53:36,115 epoch 4 - iter 40/48 - loss 0.13833744 - time (sec): 21.52 - samples/sec: 1388.68 - lr: 0.000034 - momentum: 0.000000
138
+ 2024-03-26 15:53:37,019 epoch 4 - iter 44/48 - loss 0.14040303 - time (sec): 22.42 - samples/sec: 1434.97 - lr: 0.000034 - momentum: 0.000000
139
+ 2024-03-26 15:53:38,491 epoch 4 - iter 48/48 - loss 0.14126333 - time (sec): 23.90 - samples/sec: 1442.56 - lr: 0.000034 - momentum: 0.000000
140
+ 2024-03-26 15:53:38,491 ----------------------------------------------------------------------------------------------------
141
+ 2024-03-26 15:53:38,491 EPOCH 4 done: loss 0.1413 - lr: 0.000034
142
+ 2024-03-26 15:53:39,390 DEV : loss 0.18417491018772125 - f1-score (micro avg) 0.9023
143
+ 2024-03-26 15:53:39,391 saving best model
144
+ 2024-03-26 15:53:39,808 ----------------------------------------------------------------------------------------------------
145
+ 2024-03-26 15:53:42,254 epoch 5 - iter 4/48 - loss 0.08062461 - time (sec): 2.44 - samples/sec: 1300.88 - lr: 0.000033 - momentum: 0.000000
146
+ 2024-03-26 15:53:43,670 epoch 5 - iter 8/48 - loss 0.10869288 - time (sec): 3.86 - samples/sec: 1475.04 - lr: 0.000033 - momentum: 0.000000
147
+ 2024-03-26 15:53:45,120 epoch 5 - iter 12/48 - loss 0.10565853 - time (sec): 5.31 - samples/sec: 1552.27 - lr: 0.000032 - momentum: 0.000000
148
+ 2024-03-26 15:53:47,297 epoch 5 - iter 16/48 - loss 0.10167389 - time (sec): 7.49 - samples/sec: 1469.81 - lr: 0.000032 - momentum: 0.000000
149
+ 2024-03-26 15:53:49,350 epoch 5 - iter 20/48 - loss 0.10838379 - time (sec): 9.54 - samples/sec: 1476.06 - lr: 0.000031 - momentum: 0.000000
150
+ 2024-03-26 15:53:51,814 epoch 5 - iter 24/48 - loss 0.10181658 - time (sec): 12.00 - samples/sec: 1466.58 - lr: 0.000031 - momentum: 0.000000
151
+ 2024-03-26 15:53:54,360 epoch 5 - iter 28/48 - loss 0.09694413 - time (sec): 14.55 - samples/sec: 1446.70 - lr: 0.000030 - momentum: 0.000000
152
+ 2024-03-26 15:53:56,226 epoch 5 - iter 32/48 - loss 0.09530949 - time (sec): 16.42 - samples/sec: 1450.67 - lr: 0.000030 - momentum: 0.000000
153
+ 2024-03-26 15:53:58,030 epoch 5 - iter 36/48 - loss 0.09236130 - time (sec): 18.22 - samples/sec: 1451.54 - lr: 0.000029 - momentum: 0.000000
154
+ 2024-03-26 15:54:00,314 epoch 5 - iter 40/48 - loss 0.09219478 - time (sec): 20.50 - samples/sec: 1440.45 - lr: 0.000029 - momentum: 0.000000
155
+ 2024-03-26 15:54:02,252 epoch 5 - iter 44/48 - loss 0.09581412 - time (sec): 22.44 - samples/sec: 1439.37 - lr: 0.000029 - momentum: 0.000000
156
+ 2024-03-26 15:54:03,297 epoch 5 - iter 48/48 - loss 0.09520551 - time (sec): 23.49 - samples/sec: 1467.77 - lr: 0.000028 - momentum: 0.000000
157
+ 2024-03-26 15:54:03,297 ----------------------------------------------------------------------------------------------------
158
+ 2024-03-26 15:54:03,297 EPOCH 5 done: loss 0.0952 - lr: 0.000028
159
+ 2024-03-26 15:54:04,196 DEV : loss 0.1844843178987503 - f1-score (micro avg) 0.9094
160
+ 2024-03-26 15:54:04,198 saving best model
161
+ 2024-03-26 15:54:04,638 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 15:54:07,219 epoch 6 - iter 4/48 - loss 0.06778703 - time (sec): 2.58 - samples/sec: 1232.60 - lr: 0.000028 - momentum: 0.000000
163
+ 2024-03-26 15:54:09,206 epoch 6 - iter 8/48 - loss 0.06680921 - time (sec): 4.57 - samples/sec: 1285.84 - lr: 0.000027 - momentum: 0.000000
164
+ 2024-03-26 15:54:10,772 epoch 6 - iter 12/48 - loss 0.06684490 - time (sec): 6.13 - samples/sec: 1438.61 - lr: 0.000027 - momentum: 0.000000
165
+ 2024-03-26 15:54:12,722 epoch 6 - iter 16/48 - loss 0.06208855 - time (sec): 8.08 - samples/sec: 1438.89 - lr: 0.000026 - momentum: 0.000000
166
+ 2024-03-26 15:54:13,791 epoch 6 - iter 20/48 - loss 0.06558676 - time (sec): 9.15 - samples/sec: 1526.83 - lr: 0.000026 - momentum: 0.000000
167
+ 2024-03-26 15:54:15,711 epoch 6 - iter 24/48 - loss 0.06594786 - time (sec): 11.07 - samples/sec: 1509.68 - lr: 0.000025 - momentum: 0.000000
168
+ 2024-03-26 15:54:16,852 epoch 6 - iter 28/48 - loss 0.06539093 - time (sec): 12.21 - samples/sec: 1557.62 - lr: 0.000025 - momentum: 0.000000
169
+ 2024-03-26 15:54:18,609 epoch 6 - iter 32/48 - loss 0.06402909 - time (sec): 13.97 - samples/sec: 1577.02 - lr: 0.000024 - momentum: 0.000000
170
+ 2024-03-26 15:54:20,995 epoch 6 - iter 36/48 - loss 0.07604529 - time (sec): 16.36 - samples/sec: 1552.56 - lr: 0.000024 - momentum: 0.000000
171
+ 2024-03-26 15:54:23,030 epoch 6 - iter 40/48 - loss 0.07312409 - time (sec): 18.39 - samples/sec: 1545.07 - lr: 0.000023 - momentum: 0.000000
172
+ 2024-03-26 15:54:24,891 epoch 6 - iter 44/48 - loss 0.07627946 - time (sec): 20.25 - samples/sec: 1553.26 - lr: 0.000023 - momentum: 0.000000
173
+ 2024-03-26 15:54:26,419 epoch 6 - iter 48/48 - loss 0.07671114 - time (sec): 21.78 - samples/sec: 1582.82 - lr: 0.000023 - momentum: 0.000000
174
+ 2024-03-26 15:54:26,419 ----------------------------------------------------------------------------------------------------
175
+ 2024-03-26 15:54:26,419 EPOCH 6 done: loss 0.0767 - lr: 0.000023
176
+ 2024-03-26 15:54:27,324 DEV : loss 0.17374055087566376 - f1-score (micro avg) 0.9099
177
+ 2024-03-26 15:54:27,326 saving best model
178
+ 2024-03-26 15:54:27,747 ----------------------------------------------------------------------------------------------------
179
+ 2024-03-26 15:54:29,906 epoch 7 - iter 4/48 - loss 0.07425281 - time (sec): 2.16 - samples/sec: 1281.28 - lr: 0.000022 - momentum: 0.000000
180
+ 2024-03-26 15:54:31,595 epoch 7 - iter 8/48 - loss 0.05887528 - time (sec): 3.85 - samples/sec: 1493.64 - lr: 0.000022 - momentum: 0.000000
181
+ 2024-03-26 15:54:33,643 epoch 7 - iter 12/48 - loss 0.04957316 - time (sec): 5.89 - samples/sec: 1453.44 - lr: 0.000021 - momentum: 0.000000
182
+ 2024-03-26 15:54:36,191 epoch 7 - iter 16/48 - loss 0.04756465 - time (sec): 8.44 - samples/sec: 1399.92 - lr: 0.000021 - momentum: 0.000000
183
+ 2024-03-26 15:54:38,842 epoch 7 - iter 20/48 - loss 0.05175879 - time (sec): 11.09 - samples/sec: 1408.93 - lr: 0.000020 - momentum: 0.000000
184
+ 2024-03-26 15:54:40,355 epoch 7 - iter 24/48 - loss 0.05180407 - time (sec): 12.61 - samples/sec: 1429.71 - lr: 0.000020 - momentum: 0.000000
185
+ 2024-03-26 15:54:42,438 epoch 7 - iter 28/48 - loss 0.04908208 - time (sec): 14.69 - samples/sec: 1448.25 - lr: 0.000019 - momentum: 0.000000
186
+ 2024-03-26 15:54:44,585 epoch 7 - iter 32/48 - loss 0.05229406 - time (sec): 16.84 - samples/sec: 1452.08 - lr: 0.000019 - momentum: 0.000000
187
+ 2024-03-26 15:54:46,786 epoch 7 - iter 36/48 - loss 0.05610937 - time (sec): 19.04 - samples/sec: 1437.97 - lr: 0.000018 - momentum: 0.000000
188
+ 2024-03-26 15:54:48,353 epoch 7 - iter 40/48 - loss 0.05349840 - time (sec): 20.60 - samples/sec: 1447.06 - lr: 0.000018 - momentum: 0.000000
189
+ 2024-03-26 15:54:49,993 epoch 7 - iter 44/48 - loss 0.05687802 - time (sec): 22.24 - samples/sec: 1466.35 - lr: 0.000017 - momentum: 0.000000
190
+ 2024-03-26 15:54:51,315 epoch 7 - iter 48/48 - loss 0.05675112 - time (sec): 23.57 - samples/sec: 1462.78 - lr: 0.000017 - momentum: 0.000000
191
+ 2024-03-26 15:54:51,315 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 15:54:51,315 EPOCH 7 done: loss 0.0568 - lr: 0.000017
193
+ 2024-03-26 15:54:52,224 DEV : loss 0.1754644811153412 - f1-score (micro avg) 0.9258
194
+ 2024-03-26 15:54:52,225 saving best model
195
+ 2024-03-26 15:54:52,663 ----------------------------------------------------------------------------------------------------
196
+ 2024-03-26 15:54:55,003 epoch 8 - iter 4/48 - loss 0.02736370 - time (sec): 2.34 - samples/sec: 1256.96 - lr: 0.000017 - momentum: 0.000000
197
+ 2024-03-26 15:54:57,540 epoch 8 - iter 8/48 - loss 0.02700390 - time (sec): 4.87 - samples/sec: 1356.81 - lr: 0.000016 - momentum: 0.000000
198
+ 2024-03-26 15:54:59,525 epoch 8 - iter 12/48 - loss 0.02802816 - time (sec): 6.86 - samples/sec: 1341.50 - lr: 0.000016 - momentum: 0.000000
199
+ 2024-03-26 15:55:01,510 epoch 8 - iter 16/48 - loss 0.02894184 - time (sec): 8.84 - samples/sec: 1355.67 - lr: 0.000015 - momentum: 0.000000
200
+ 2024-03-26 15:55:03,025 epoch 8 - iter 20/48 - loss 0.03150964 - time (sec): 10.36 - samples/sec: 1380.11 - lr: 0.000015 - momentum: 0.000000
201
+ 2024-03-26 15:55:05,354 epoch 8 - iter 24/48 - loss 0.02969630 - time (sec): 12.69 - samples/sec: 1366.69 - lr: 0.000014 - momentum: 0.000000
202
+ 2024-03-26 15:55:07,489 epoch 8 - iter 28/48 - loss 0.02992001 - time (sec): 14.82 - samples/sec: 1359.70 - lr: 0.000014 - momentum: 0.000000
203
+ 2024-03-26 15:55:09,783 epoch 8 - iter 32/48 - loss 0.03878451 - time (sec): 17.12 - samples/sec: 1371.42 - lr: 0.000013 - momentum: 0.000000
204
+ 2024-03-26 15:55:12,948 epoch 8 - iter 36/48 - loss 0.04273473 - time (sec): 20.28 - samples/sec: 1323.14 - lr: 0.000013 - momentum: 0.000000
205
+ 2024-03-26 15:55:14,918 epoch 8 - iter 40/48 - loss 0.04616562 - time (sec): 22.25 - samples/sec: 1329.97 - lr: 0.000012 - momentum: 0.000000
206
+ 2024-03-26 15:55:15,712 epoch 8 - iter 44/48 - loss 0.04479597 - time (sec): 23.05 - samples/sec: 1378.50 - lr: 0.000012 - momentum: 0.000000
207
+ 2024-03-26 15:55:17,517 epoch 8 - iter 48/48 - loss 0.04471448 - time (sec): 24.85 - samples/sec: 1387.13 - lr: 0.000011 - momentum: 0.000000
208
+ 2024-03-26 15:55:17,517 ----------------------------------------------------------------------------------------------------
209
+ 2024-03-26 15:55:17,517 EPOCH 8 done: loss 0.0447 - lr: 0.000011
210
+ 2024-03-26 15:55:18,427 DEV : loss 0.1700660139322281 - f1-score (micro avg) 0.9317
211
+ 2024-03-26 15:55:18,428 saving best model
212
+ 2024-03-26 15:55:18,873 ----------------------------------------------------------------------------------------------------
213
+ 2024-03-26 15:55:21,552 epoch 9 - iter 4/48 - loss 0.02576288 - time (sec): 2.68 - samples/sec: 1231.65 - lr: 0.000011 - momentum: 0.000000
214
+ 2024-03-26 15:55:23,217 epoch 9 - iter 8/48 - loss 0.02794343 - time (sec): 4.34 - samples/sec: 1321.42 - lr: 0.000011 - momentum: 0.000000
215
+ 2024-03-26 15:55:25,320 epoch 9 - iter 12/48 - loss 0.03166695 - time (sec): 6.45 - samples/sec: 1392.61 - lr: 0.000010 - momentum: 0.000000
216
+ 2024-03-26 15:55:27,386 epoch 9 - iter 16/48 - loss 0.03166024 - time (sec): 8.51 - samples/sec: 1422.73 - lr: 0.000010 - momentum: 0.000000
217
+ 2024-03-26 15:55:29,689 epoch 9 - iter 20/48 - loss 0.02724723 - time (sec): 10.82 - samples/sec: 1398.87 - lr: 0.000009 - momentum: 0.000000
218
+ 2024-03-26 15:55:31,590 epoch 9 - iter 24/48 - loss 0.03010259 - time (sec): 12.72 - samples/sec: 1392.59 - lr: 0.000009 - momentum: 0.000000
219
+ 2024-03-26 15:55:34,763 epoch 9 - iter 28/48 - loss 0.03210630 - time (sec): 15.89 - samples/sec: 1344.54 - lr: 0.000008 - momentum: 0.000000
220
+ 2024-03-26 15:55:36,120 epoch 9 - iter 32/48 - loss 0.03325750 - time (sec): 17.25 - samples/sec: 1385.30 - lr: 0.000008 - momentum: 0.000000
221
+ 2024-03-26 15:55:38,466 epoch 9 - iter 36/48 - loss 0.03263536 - time (sec): 19.59 - samples/sec: 1375.54 - lr: 0.000007 - momentum: 0.000000
222
+ 2024-03-26 15:55:39,916 epoch 9 - iter 40/48 - loss 0.03437591 - time (sec): 21.04 - samples/sec: 1393.42 - lr: 0.000007 - momentum: 0.000000
223
+ 2024-03-26 15:55:41,411 epoch 9 - iter 44/48 - loss 0.03798605 - time (sec): 22.54 - samples/sec: 1411.50 - lr: 0.000006 - momentum: 0.000000
224
+ 2024-03-26 15:55:42,804 epoch 9 - iter 48/48 - loss 0.03764149 - time (sec): 23.93 - samples/sec: 1440.58 - lr: 0.000006 - momentum: 0.000000
225
+ 2024-03-26 15:55:42,804 ----------------------------------------------------------------------------------------------------
226
+ 2024-03-26 15:55:42,804 EPOCH 9 done: loss 0.0376 - lr: 0.000006
227
+ 2024-03-26 15:55:43,716 DEV : loss 0.19358719885349274 - f1-score (micro avg) 0.9372
228
+ 2024-03-26 15:55:43,717 saving best model
229
+ 2024-03-26 15:55:44,161 ----------------------------------------------------------------------------------------------------
230
+ 2024-03-26 15:55:46,521 epoch 10 - iter 4/48 - loss 0.01698527 - time (sec): 2.36 - samples/sec: 1395.97 - lr: 0.000006 - momentum: 0.000000
231
+ 2024-03-26 15:55:48,421 epoch 10 - iter 8/48 - loss 0.01570125 - time (sec): 4.26 - samples/sec: 1372.71 - lr: 0.000005 - momentum: 0.000000
232
+ 2024-03-26 15:55:49,592 epoch 10 - iter 12/48 - loss 0.03071953 - time (sec): 5.43 - samples/sec: 1536.69 - lr: 0.000005 - momentum: 0.000000
233
+ 2024-03-26 15:55:51,101 epoch 10 - iter 16/48 - loss 0.03178666 - time (sec): 6.94 - samples/sec: 1617.13 - lr: 0.000004 - momentum: 0.000000
234
+ 2024-03-26 15:55:52,789 epoch 10 - iter 20/48 - loss 0.03140645 - time (sec): 8.63 - samples/sec: 1654.91 - lr: 0.000004 - momentum: 0.000000
235
+ 2024-03-26 15:55:54,792 epoch 10 - iter 24/48 - loss 0.02924738 - time (sec): 10.63 - samples/sec: 1603.43 - lr: 0.000003 - momentum: 0.000000
236
+ 2024-03-26 15:55:56,896 epoch 10 - iter 28/48 - loss 0.02706663 - time (sec): 12.73 - samples/sec: 1566.63 - lr: 0.000003 - momentum: 0.000000
237
+ 2024-03-26 15:55:58,995 epoch 10 - iter 32/48 - loss 0.02812544 - time (sec): 14.83 - samples/sec: 1573.00 - lr: 0.000002 - momentum: 0.000000
238
+ 2024-03-26 15:56:00,384 epoch 10 - iter 36/48 - loss 0.02759213 - time (sec): 16.22 - samples/sec: 1572.08 - lr: 0.000002 - momentum: 0.000000
239
+ 2024-03-26 15:56:03,004 epoch 10 - iter 40/48 - loss 0.02639293 - time (sec): 18.84 - samples/sec: 1531.69 - lr: 0.000001 - momentum: 0.000000
240
+ 2024-03-26 15:56:05,520 epoch 10 - iter 44/48 - loss 0.02901644 - time (sec): 21.36 - samples/sec: 1505.63 - lr: 0.000001 - momentum: 0.000000
241
+ 2024-03-26 15:56:07,109 epoch 10 - iter 48/48 - loss 0.02914343 - time (sec): 22.95 - samples/sec: 1502.34 - lr: 0.000000 - momentum: 0.000000
242
+ 2024-03-26 15:56:07,109 ----------------------------------------------------------------------------------------------------
243
+ 2024-03-26 15:56:07,109 EPOCH 10 done: loss 0.0291 - lr: 0.000000
244
+ 2024-03-26 15:56:08,014 DEV : loss 0.18885844945907593 - f1-score (micro avg) 0.9335
245
+ 2024-03-26 15:56:08,280 ----------------------------------------------------------------------------------------------------
246
+ 2024-03-26 15:56:08,280 Loading model from best epoch ...
247
+ 2024-03-26 15:56:09,218 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 15:56:09,964
249
+ Results:
250
+ - F-score (micro) 0.9065
251
+ - F-score (macro) 0.6888
252
+ - Accuracy 0.8312
253
+
254
+ By class:
255
+ precision recall f1-score support
256
+
257
+ Unternehmen 0.9004 0.8835 0.8918 266
258
+ Auslagerung 0.8609 0.9197 0.8893 249
259
+ Ort 0.9635 0.9851 0.9742 134
260
+ Software 0.0000 0.0000 0.0000 0
261
+
262
+ micro avg 0.8949 0.9183 0.9065 649
263
+ macro avg 0.6812 0.6971 0.6888 649
264
+ weighted avg 0.8983 0.9183 0.9079 649
265
+
266
+ 2024-03-26 15:56:09,964 ----------------------------------------------------------------------------------------------------