Hugging Face's logo

stefan-it
/
flair-co-funer-german_dbmdz_bert_base-bs16-e10-lr3e-05-5

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
9d92914
•
1 Parent(s): e81c96d

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 16:20:27,818 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 16:20:27,818 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 16:20:27,818 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 16:20:27,819 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 16:20:27,819 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 16:20:27,819 Train: 758 sentences
54
+ 2024-03-26 16:20:27,819 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 16:20:27,819 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 16:20:27,819 Training Params:
57
+ 2024-03-26 16:20:27,819 - learning_rate: "3e-05"
58
+ 2024-03-26 16:20:27,819 - mini_batch_size: "16"
59
+ 2024-03-26 16:20:27,819 - max_epochs: "10"
60
+ 2024-03-26 16:20:27,819 - shuffle: "True"
61
+ 2024-03-26 16:20:27,819 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 16:20:27,819 Plugins:
63
+ 2024-03-26 16:20:27,819 - TensorboardLogger
64
+ 2024-03-26 16:20:27,819 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 16:20:27,819 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 16:20:27,819 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 16:20:27,819 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 16:20:27,819 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 16:20:27,819 Computation:
70
+ 2024-03-26 16:20:27,819 - compute on device: cuda:0
71
+ 2024-03-26 16:20:27,819 - embedding storage: none
72
+ 2024-03-26 16:20:27,819 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 16:20:27,819 Model training base path: "flair-co-funer-german_dbmdz_bert_base-bs16-e10-lr3e-05-5"
74
+ 2024-03-26 16:20:27,819 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 16:20:27,819 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 16:20:27,819 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 16:20:29,303 epoch 1 - iter 4/48 - loss 3.33243891 - time (sec): 1.48 - samples/sec: 1765.97 - lr: 0.000002 - momentum: 0.000000
78
+ 2024-03-26 16:20:31,987 epoch 1 - iter 8/48 - loss 3.27444886 - time (sec): 4.17 - samples/sec: 1460.39 - lr: 0.000004 - momentum: 0.000000
79
+ 2024-03-26 16:20:33,821 epoch 1 - iter 12/48 - loss 3.19284867 - time (sec): 6.00 - samples/sec: 1483.98 - lr: 0.000007 - momentum: 0.000000
80
+ 2024-03-26 16:20:35,385 epoch 1 - iter 16/48 - loss 3.06760041 - time (sec): 7.57 - samples/sec: 1590.22 - lr: 0.000009 - momentum: 0.000000
81
+ 2024-03-26 16:20:37,530 epoch 1 - iter 20/48 - loss 2.93913875 - time (sec): 9.71 - samples/sec: 1552.75 - lr: 0.000012 - momentum: 0.000000
82
+ 2024-03-26 16:20:40,287 epoch 1 - iter 24/48 - loss 2.77773408 - time (sec): 12.47 - samples/sec: 1479.70 - lr: 0.000014 - momentum: 0.000000
83
+ 2024-03-26 16:20:41,904 epoch 1 - iter 28/48 - loss 2.66904977 - time (sec): 14.08 - samples/sec: 1490.07 - lr: 0.000017 - momentum: 0.000000
84
+ 2024-03-26 16:20:43,986 epoch 1 - iter 32/48 - loss 2.55099320 - time (sec): 16.17 - samples/sec: 1486.98 - lr: 0.000019 - momentum: 0.000000
85
+ 2024-03-26 16:20:45,522 epoch 1 - iter 36/48 - loss 2.46407907 - time (sec): 17.70 - samples/sec: 1508.20 - lr: 0.000022 - momentum: 0.000000
86
+ 2024-03-26 16:20:48,292 epoch 1 - iter 40/48 - loss 2.35518313 - time (sec): 20.47 - samples/sec: 1460.67 - lr: 0.000024 - momentum: 0.000000
87
+ 2024-03-26 16:20:49,477 epoch 1 - iter 44/48 - loss 2.27229820 - time (sec): 21.66 - samples/sec: 1484.13 - lr: 0.000027 - momentum: 0.000000
88
+ 2024-03-26 16:20:51,300 epoch 1 - iter 48/48 - loss 2.20094714 - time (sec): 23.48 - samples/sec: 1468.08 - lr: 0.000029 - momentum: 0.000000
89
+ 2024-03-26 16:20:51,300 ----------------------------------------------------------------------------------------------------
90
+ 2024-03-26 16:20:51,301 EPOCH 1 done: loss 2.2009 - lr: 0.000029
91
+ 2024-03-26 16:20:52,115 DEV : loss 0.8398668169975281 - f1-score (micro avg) 0.4601
92
+ 2024-03-26 16:20:52,116 saving best model
93
+ 2024-03-26 16:20:52,380 ----------------------------------------------------------------------------------------------------
94
+ 2024-03-26 16:20:55,073 epoch 2 - iter 4/48 - loss 0.97764540 - time (sec): 2.69 - samples/sec: 1282.27 - lr: 0.000030 - momentum: 0.000000
95
+ 2024-03-26 16:20:56,909 epoch 2 - iter 8/48 - loss 0.92169240 - time (sec): 4.53 - samples/sec: 1353.08 - lr: 0.000030 - momentum: 0.000000
96
+ 2024-03-26 16:20:58,797 epoch 2 - iter 12/48 - loss 0.87356675 - time (sec): 6.42 - samples/sec: 1390.54 - lr: 0.000029 - momentum: 0.000000
97
+ 2024-03-26 16:21:01,443 epoch 2 - iter 16/48 - loss 0.79202489 - time (sec): 9.06 - samples/sec: 1396.31 - lr: 0.000029 - momentum: 0.000000
98
+ 2024-03-26 16:21:02,817 epoch 2 - iter 20/48 - loss 0.76156184 - time (sec): 10.44 - samples/sec: 1435.48 - lr: 0.000029 - momentum: 0.000000
99
+ 2024-03-26 16:21:05,616 epoch 2 - iter 24/48 - loss 0.71680551 - time (sec): 13.24 - samples/sec: 1352.27 - lr: 0.000028 - momentum: 0.000000
100
+ 2024-03-26 16:21:07,217 epoch 2 - iter 28/48 - loss 0.70169294 - time (sec): 14.84 - samples/sec: 1385.86 - lr: 0.000028 - momentum: 0.000000
101
+ 2024-03-26 16:21:09,224 epoch 2 - iter 32/48 - loss 0.66814375 - time (sec): 16.84 - samples/sec: 1378.44 - lr: 0.000028 - momentum: 0.000000
102
+ 2024-03-26 16:21:10,971 epoch 2 - iter 36/48 - loss 0.64979725 - time (sec): 18.59 - samples/sec: 1409.85 - lr: 0.000028 - momentum: 0.000000
103
+ 2024-03-26 16:21:13,315 epoch 2 - iter 40/48 - loss 0.63823796 - time (sec): 20.94 - samples/sec: 1398.22 - lr: 0.000027 - momentum: 0.000000
104
+ 2024-03-26 16:21:15,494 epoch 2 - iter 44/48 - loss 0.61211544 - time (sec): 23.11 - samples/sec: 1403.26 - lr: 0.000027 - momentum: 0.000000
105
+ 2024-03-26 16:21:16,745 epoch 2 - iter 48/48 - loss 0.60381110 - time (sec): 24.37 - samples/sec: 1414.81 - lr: 0.000027 - momentum: 0.000000
106
+ 2024-03-26 16:21:16,746 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 16:21:16,746 EPOCH 2 done: loss 0.6038 - lr: 0.000027
108
+ 2024-03-26 16:21:17,672 DEV : loss 0.35631129145622253 - f1-score (micro avg) 0.7369
109
+ 2024-03-26 16:21:17,673 saving best model
110
+ 2024-03-26 16:21:18,130 ----------------------------------------------------------------------------------------------------
111
+ 2024-03-26 16:21:19,212 epoch 3 - iter 4/48 - loss 0.42050435 - time (sec): 1.08 - samples/sec: 2063.24 - lr: 0.000026 - momentum: 0.000000
112
+ 2024-03-26 16:21:21,086 epoch 3 - iter 8/48 - loss 0.36994000 - time (sec): 2.96 - samples/sec: 1667.12 - lr: 0.000026 - momentum: 0.000000
113
+ 2024-03-26 16:21:23,303 epoch 3 - iter 12/48 - loss 0.33936035 - time (sec): 5.17 - samples/sec: 1657.72 - lr: 0.000026 - momentum: 0.000000
114
+ 2024-03-26 16:21:25,257 epoch 3 - iter 16/48 - loss 0.33771789 - time (sec): 7.13 - samples/sec: 1596.10 - lr: 0.000026 - momentum: 0.000000
115
+ 2024-03-26 16:21:27,102 epoch 3 - iter 20/48 - loss 0.33282889 - time (sec): 8.97 - samples/sec: 1580.23 - lr: 0.000025 - momentum: 0.000000
116
+ 2024-03-26 16:21:29,041 epoch 3 - iter 24/48 - loss 0.31782340 - time (sec): 10.91 - samples/sec: 1536.45 - lr: 0.000025 - momentum: 0.000000
117
+ 2024-03-26 16:21:32,217 epoch 3 - iter 28/48 - loss 0.30362057 - time (sec): 14.09 - samples/sec: 1420.98 - lr: 0.000025 - momentum: 0.000000
118
+ 2024-03-26 16:21:33,721 epoch 3 - iter 32/48 - loss 0.30431378 - time (sec): 15.59 - samples/sec: 1444.75 - lr: 0.000025 - momentum: 0.000000
119
+ 2024-03-26 16:21:37,002 epoch 3 - iter 36/48 - loss 0.29035892 - time (sec): 18.87 - samples/sec: 1374.51 - lr: 0.000024 - momentum: 0.000000
120
+ 2024-03-26 16:21:39,388 epoch 3 - iter 40/48 - loss 0.28751496 - time (sec): 21.26 - samples/sec: 1376.57 - lr: 0.000024 - momentum: 0.000000
121
+ 2024-03-26 16:21:41,517 epoch 3 - iter 44/48 - loss 0.28096716 - time (sec): 23.39 - samples/sec: 1372.11 - lr: 0.000024 - momentum: 0.000000
122
+ 2024-03-26 16:21:43,103 epoch 3 - iter 48/48 - loss 0.27892438 - time (sec): 24.97 - samples/sec: 1380.42 - lr: 0.000023 - momentum: 0.000000
123
+ 2024-03-26 16:21:43,103 ----------------------------------------------------------------------------------------------------
124
+ 2024-03-26 16:21:43,103 EPOCH 3 done: loss 0.2789 - lr: 0.000023
125
+ 2024-03-26 16:21:44,031 DEV : loss 0.23076379299163818 - f1-score (micro avg) 0.8511
126
+ 2024-03-26 16:21:44,033 saving best model
127
+ 2024-03-26 16:21:44,473 ----------------------------------------------------------------------------------------------------
128
+ 2024-03-26 16:21:47,385 epoch 4 - iter 4/48 - loss 0.14723859 - time (sec): 2.91 - samples/sec: 1280.87 - lr: 0.000023 - momentum: 0.000000
129
+ 2024-03-26 16:21:48,880 epoch 4 - iter 8/48 - loss 0.19096714 - time (sec): 4.41 - samples/sec: 1411.21 - lr: 0.000023 - momentum: 0.000000
130
+ 2024-03-26 16:21:51,392 epoch 4 - iter 12/48 - loss 0.17787461 - time (sec): 6.92 - samples/sec: 1344.27 - lr: 0.000023 - momentum: 0.000000
131
+ 2024-03-26 16:21:54,042 epoch 4 - iter 16/48 - loss 0.17213388 - time (sec): 9.57 - samples/sec: 1326.82 - lr: 0.000022 - momentum: 0.000000
132
+ 2024-03-26 16:21:56,290 epoch 4 - iter 20/48 - loss 0.16683254 - time (sec): 11.82 - samples/sec: 1335.55 - lr: 0.000022 - momentum: 0.000000
133
+ 2024-03-26 16:21:57,785 epoch 4 - iter 24/48 - loss 0.16783017 - time (sec): 13.31 - samples/sec: 1369.58 - lr: 0.000022 - momentum: 0.000000
134
+ 2024-03-26 16:22:00,142 epoch 4 - iter 28/48 - loss 0.17152331 - time (sec): 15.67 - samples/sec: 1355.74 - lr: 0.000022 - momentum: 0.000000
135
+ 2024-03-26 16:22:03,081 epoch 4 - iter 32/48 - loss 0.17071354 - time (sec): 18.61 - samples/sec: 1346.75 - lr: 0.000021 - momentum: 0.000000
136
+ 2024-03-26 16:22:04,712 epoch 4 - iter 36/48 - loss 0.17256077 - time (sec): 20.24 - samples/sec: 1371.45 - lr: 0.000021 - momentum: 0.000000
137
+ 2024-03-26 16:22:05,702 epoch 4 - iter 40/48 - loss 0.17602230 - time (sec): 21.23 - samples/sec: 1414.58 - lr: 0.000021 - momentum: 0.000000
138
+ 2024-03-26 16:22:07,134 epoch 4 - iter 44/48 - loss 0.17600155 - time (sec): 22.66 - samples/sec: 1435.65 - lr: 0.000020 - momentum: 0.000000
139
+ 2024-03-26 16:22:08,005 epoch 4 - iter 48/48 - loss 0.17965021 - time (sec): 23.53 - samples/sec: 1464.92 - lr: 0.000020 - momentum: 0.000000
140
+ 2024-03-26 16:22:08,006 ----------------------------------------------------------------------------------------------------
141
+ 2024-03-26 16:22:08,006 EPOCH 4 done: loss 0.1797 - lr: 0.000020
142
+ 2024-03-26 16:22:08,929 DEV : loss 0.19128400087356567 - f1-score (micro avg) 0.8865
143
+ 2024-03-26 16:22:08,930 saving best model
144
+ 2024-03-26 16:22:09,357 ----------------------------------------------------------------------------------------------------
145
+ 2024-03-26 16:22:11,177 epoch 5 - iter 4/48 - loss 0.14799718 - time (sec): 1.82 - samples/sec: 1578.71 - lr: 0.000020 - momentum: 0.000000
146
+ 2024-03-26 16:22:13,039 epoch 5 - iter 8/48 - loss 0.13649489 - time (sec): 3.68 - samples/sec: 1685.38 - lr: 0.000020 - momentum: 0.000000
147
+ 2024-03-26 16:22:16,132 epoch 5 - iter 12/48 - loss 0.12703718 - time (sec): 6.77 - samples/sec: 1420.24 - lr: 0.000019 - momentum: 0.000000
148
+ 2024-03-26 16:22:17,451 epoch 5 - iter 16/48 - loss 0.12204170 - time (sec): 8.09 - samples/sec: 1469.19 - lr: 0.000019 - momentum: 0.000000
149
+ 2024-03-26 16:22:19,722 epoch 5 - iter 20/48 - loss 0.13938063 - time (sec): 10.37 - samples/sec: 1453.83 - lr: 0.000019 - momentum: 0.000000
150
+ 2024-03-26 16:22:21,860 epoch 5 - iter 24/48 - loss 0.13765159 - time (sec): 12.50 - samples/sec: 1421.75 - lr: 0.000018 - momentum: 0.000000
151
+ 2024-03-26 16:22:23,223 epoch 5 - iter 28/48 - loss 0.14191204 - time (sec): 13.87 - samples/sec: 1463.46 - lr: 0.000018 - momentum: 0.000000
152
+ 2024-03-26 16:22:24,594 epoch 5 - iter 32/48 - loss 0.14166725 - time (sec): 15.24 - samples/sec: 1496.23 - lr: 0.000018 - momentum: 0.000000
153
+ 2024-03-26 16:22:26,716 epoch 5 - iter 36/48 - loss 0.14084111 - time (sec): 17.36 - samples/sec: 1487.67 - lr: 0.000018 - momentum: 0.000000
154
+ 2024-03-26 16:22:28,542 epoch 5 - iter 40/48 - loss 0.13988440 - time (sec): 19.18 - samples/sec: 1486.03 - lr: 0.000017 - momentum: 0.000000
155
+ 2024-03-26 16:22:30,541 epoch 5 - iter 44/48 - loss 0.13722618 - time (sec): 21.18 - samples/sec: 1498.59 - lr: 0.000017 - momentum: 0.000000
156
+ 2024-03-26 16:22:32,649 epoch 5 - iter 48/48 - loss 0.13324400 - time (sec): 23.29 - samples/sec: 1480.01 - lr: 0.000017 - momentum: 0.000000
157
+ 2024-03-26 16:22:32,649 ----------------------------------------------------------------------------------------------------
158
+ 2024-03-26 16:22:32,650 EPOCH 5 done: loss 0.1332 - lr: 0.000017
159
+ 2024-03-26 16:22:33,569 DEV : loss 0.18336626887321472 - f1-score (micro avg) 0.8929
160
+ 2024-03-26 16:22:33,571 saving best model
161
+ 2024-03-26 16:22:34,022 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 16:22:35,910 epoch 6 - iter 4/48 - loss 0.10824307 - time (sec): 1.89 - samples/sec: 1454.79 - lr: 0.000017 - momentum: 0.000000
163
+ 2024-03-26 16:22:38,630 epoch 6 - iter 8/48 - loss 0.11635535 - time (sec): 4.61 - samples/sec: 1379.60 - lr: 0.000016 - momentum: 0.000000
164
+ 2024-03-26 16:22:40,511 epoch 6 - iter 12/48 - loss 0.11860529 - time (sec): 6.49 - samples/sec: 1391.86 - lr: 0.000016 - momentum: 0.000000
165
+ 2024-03-26 16:22:41,984 epoch 6 - iter 16/48 - loss 0.12373574 - time (sec): 7.96 - samples/sec: 1453.46 - lr: 0.000016 - momentum: 0.000000
166
+ 2024-03-26 16:22:44,659 epoch 6 - iter 20/48 - loss 0.11554259 - time (sec): 10.64 - samples/sec: 1370.95 - lr: 0.000015 - momentum: 0.000000
167
+ 2024-03-26 16:22:47,307 epoch 6 - iter 24/48 - loss 0.10657385 - time (sec): 13.28 - samples/sec: 1344.95 - lr: 0.000015 - momentum: 0.000000
168
+ 2024-03-26 16:22:49,757 epoch 6 - iter 28/48 - loss 0.10502829 - time (sec): 15.73 - samples/sec: 1318.85 - lr: 0.000015 - momentum: 0.000000
169
+ 2024-03-26 16:22:51,129 epoch 6 - iter 32/48 - loss 0.11414547 - time (sec): 17.11 - samples/sec: 1362.93 - lr: 0.000015 - momentum: 0.000000
170
+ 2024-03-26 16:22:52,981 epoch 6 - iter 36/48 - loss 0.10975802 - time (sec): 18.96 - samples/sec: 1373.68 - lr: 0.000014 - momentum: 0.000000
171
+ 2024-03-26 16:22:53,959 epoch 6 - iter 40/48 - loss 0.11001287 - time (sec): 19.94 - samples/sec: 1415.04 - lr: 0.000014 - momentum: 0.000000
172
+ 2024-03-26 16:22:56,456 epoch 6 - iter 44/48 - loss 0.10762077 - time (sec): 22.43 - samples/sec: 1387.00 - lr: 0.000014 - momentum: 0.000000
173
+ 2024-03-26 16:22:59,205 epoch 6 - iter 48/48 - loss 0.10325396 - time (sec): 25.18 - samples/sec: 1368.93 - lr: 0.000014 - momentum: 0.000000
174
+ 2024-03-26 16:22:59,205 ----------------------------------------------------------------------------------------------------
175
+ 2024-03-26 16:22:59,205 EPOCH 6 done: loss 0.1033 - lr: 0.000014
176
+ 2024-03-26 16:23:00,104 DEV : loss 0.186451718211174 - f1-score (micro avg) 0.8952
177
+ 2024-03-26 16:23:00,105 saving best model
178
+ 2024-03-26 16:23:00,568 ----------------------------------------------------------------------------------------------------
179
+ 2024-03-26 16:23:02,694 epoch 7 - iter 4/48 - loss 0.05956705 - time (sec): 2.12 - samples/sec: 1369.90 - lr: 0.000013 - momentum: 0.000000
180
+ 2024-03-26 16:23:04,375 epoch 7 - iter 8/48 - loss 0.06304602 - time (sec): 3.80 - samples/sec: 1400.81 - lr: 0.000013 - momentum: 0.000000
181
+ 2024-03-26 16:23:05,781 epoch 7 - iter 12/48 - loss 0.09022166 - time (sec): 5.21 - samples/sec: 1456.53 - lr: 0.000013 - momentum: 0.000000
182
+ 2024-03-26 16:23:07,632 epoch 7 - iter 16/48 - loss 0.08283968 - time (sec): 7.06 - samples/sec: 1503.32 - lr: 0.000012 - momentum: 0.000000
183
+ 2024-03-26 16:23:09,888 epoch 7 - iter 20/48 - loss 0.09229244 - time (sec): 9.32 - samples/sec: 1555.37 - lr: 0.000012 - momentum: 0.000000
184
+ 2024-03-26 16:23:11,222 epoch 7 - iter 24/48 - loss 0.08973072 - time (sec): 10.65 - samples/sec: 1599.53 - lr: 0.000012 - momentum: 0.000000
185
+ 2024-03-26 16:23:13,436 epoch 7 - iter 28/48 - loss 0.08953758 - time (sec): 12.87 - samples/sec: 1550.28 - lr: 0.000012 - momentum: 0.000000
186
+ 2024-03-26 16:23:15,290 epoch 7 - iter 32/48 - loss 0.09068748 - time (sec): 14.72 - samples/sec: 1546.78 - lr: 0.000011 - momentum: 0.000000
187
+ 2024-03-26 16:23:17,277 epoch 7 - iter 36/48 - loss 0.08845022 - time (sec): 16.71 - samples/sec: 1512.95 - lr: 0.000011 - momentum: 0.000000
188
+ 2024-03-26 16:23:20,044 epoch 7 - iter 40/48 - loss 0.08448801 - time (sec): 19.47 - samples/sec: 1495.60 - lr: 0.000011 - momentum: 0.000000
189
+ 2024-03-26 16:23:21,520 epoch 7 - iter 44/48 - loss 0.08574476 - time (sec): 20.95 - samples/sec: 1511.66 - lr: 0.000010 - momentum: 0.000000
190
+ 2024-03-26 16:23:23,638 epoch 7 - iter 48/48 - loss 0.08296352 - time (sec): 23.07 - samples/sec: 1494.36 - lr: 0.000010 - momentum: 0.000000
191
+ 2024-03-26 16:23:23,639 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 16:23:23,639 EPOCH 7 done: loss 0.0830 - lr: 0.000010
193
+ 2024-03-26 16:23:24,535 DEV : loss 0.17565500736236572 - f1-score (micro avg) 0.8989
194
+ 2024-03-26 16:23:24,536 saving best model
195
+ 2024-03-26 16:23:24,982 ----------------------------------------------------------------------------------------------------
196
+ 2024-03-26 16:23:27,264 epoch 8 - iter 4/48 - loss 0.09509616 - time (sec): 2.28 - samples/sec: 1223.00 - lr: 0.000010 - momentum: 0.000000
197
+ 2024-03-26 16:23:28,791 epoch 8 - iter 8/48 - loss 0.06551246 - time (sec): 3.81 - samples/sec: 1427.41 - lr: 0.000010 - momentum: 0.000000
198
+ 2024-03-26 16:23:31,677 epoch 8 - iter 12/48 - loss 0.05936792 - time (sec): 6.69 - samples/sec: 1344.49 - lr: 0.000009 - momentum: 0.000000
199
+ 2024-03-26 16:23:34,104 epoch 8 - iter 16/48 - loss 0.06172484 - time (sec): 9.12 - samples/sec: 1347.09 - lr: 0.000009 - momentum: 0.000000
200
+ 2024-03-26 16:23:35,538 epoch 8 - iter 20/48 - loss 0.05961344 - time (sec): 10.55 - samples/sec: 1407.47 - lr: 0.000009 - momentum: 0.000000
201
+ 2024-03-26 16:23:36,941 epoch 8 - iter 24/48 - loss 0.06299755 - time (sec): 11.96 - samples/sec: 1479.82 - lr: 0.000009 - momentum: 0.000000
202
+ 2024-03-26 16:23:38,250 epoch 8 - iter 28/48 - loss 0.06330688 - time (sec): 13.27 - samples/sec: 1541.24 - lr: 0.000008 - momentum: 0.000000
203
+ 2024-03-26 16:23:40,419 epoch 8 - iter 32/48 - loss 0.06427299 - time (sec): 15.44 - samples/sec: 1500.93 - lr: 0.000008 - momentum: 0.000000
204
+ 2024-03-26 16:23:42,951 epoch 8 - iter 36/48 - loss 0.06243502 - time (sec): 17.97 - samples/sec: 1457.19 - lr: 0.000008 - momentum: 0.000000
205
+ 2024-03-26 16:23:44,885 epoch 8 - iter 40/48 - loss 0.06427326 - time (sec): 19.90 - samples/sec: 1466.47 - lr: 0.000007 - momentum: 0.000000
206
+ 2024-03-26 16:23:47,020 epoch 8 - iter 44/48 - loss 0.06609326 - time (sec): 22.04 - samples/sec: 1449.54 - lr: 0.000007 - momentum: 0.000000
207
+ 2024-03-26 16:23:48,631 epoch 8 - iter 48/48 - loss 0.06732946 - time (sec): 23.65 - samples/sec: 1457.77 - lr: 0.000007 - momentum: 0.000000
208
+ 2024-03-26 16:23:48,631 ----------------------------------------------------------------------------------------------------
209
+ 2024-03-26 16:23:48,631 EPOCH 8 done: loss 0.0673 - lr: 0.000007
210
+ 2024-03-26 16:23:49,563 DEV : loss 0.17866738140583038 - f1-score (micro avg) 0.9161
211
+ 2024-03-26 16:23:49,566 saving best model
212
+ 2024-03-26 16:23:50,022 ----------------------------------------------------------------------------------------------------
213
+ 2024-03-26 16:23:52,687 epoch 9 - iter 4/48 - loss 0.05635972 - time (sec): 2.66 - samples/sec: 1313.34 - lr: 0.000007 - momentum: 0.000000
214
+ 2024-03-26 16:23:54,721 epoch 9 - iter 8/48 - loss 0.04969652 - time (sec): 4.70 - samples/sec: 1359.34 - lr: 0.000006 - momentum: 0.000000
215
+ 2024-03-26 16:23:57,544 epoch 9 - iter 12/48 - loss 0.04878836 - time (sec): 7.52 - samples/sec: 1293.36 - lr: 0.000006 - momentum: 0.000000
216
+ 2024-03-26 16:24:00,636 epoch 9 - iter 16/48 - loss 0.06176998 - time (sec): 10.61 - samples/sec: 1266.76 - lr: 0.000006 - momentum: 0.000000
217
+ 2024-03-26 16:24:01,512 epoch 9 - iter 20/48 - loss 0.06154541 - time (sec): 11.49 - samples/sec: 1355.71 - lr: 0.000006 - momentum: 0.000000
218
+ 2024-03-26 16:24:03,379 epoch 9 - iter 24/48 - loss 0.05983481 - time (sec): 13.36 - samples/sec: 1349.60 - lr: 0.000005 - momentum: 0.000000
219
+ 2024-03-26 16:24:05,388 epoch 9 - iter 28/48 - loss 0.05892038 - time (sec): 15.37 - samples/sec: 1362.76 - lr: 0.000005 - momentum: 0.000000
220
+ 2024-03-26 16:24:06,393 epoch 9 - iter 32/48 - loss 0.06007050 - time (sec): 16.37 - samples/sec: 1427.10 - lr: 0.000005 - momentum: 0.000000
221
+ 2024-03-26 16:24:07,517 epoch 9 - iter 36/48 - loss 0.05951861 - time (sec): 17.49 - samples/sec: 1480.94 - lr: 0.000004 - momentum: 0.000000
222
+ 2024-03-26 16:24:08,827 epoch 9 - iter 40/48 - loss 0.05760006 - time (sec): 18.80 - samples/sec: 1508.29 - lr: 0.000004 - momentum: 0.000000
223
+ 2024-03-26 16:24:11,938 epoch 9 - iter 44/48 - loss 0.06032529 - time (sec): 21.92 - samples/sec: 1471.87 - lr: 0.000004 - momentum: 0.000000
224
+ 2024-03-26 16:24:13,417 epoch 9 - iter 48/48 - loss 0.05798854 - time (sec): 23.39 - samples/sec: 1473.49 - lr: 0.000004 - momentum: 0.000000
225
+ 2024-03-26 16:24:13,418 ----------------------------------------------------------------------------------------------------
226
+ 2024-03-26 16:24:13,418 EPOCH 9 done: loss 0.0580 - lr: 0.000004
227
+ 2024-03-26 16:24:14,343 DEV : loss 0.1765606552362442 - f1-score (micro avg) 0.9177
228
+ 2024-03-26 16:24:14,344 saving best model
229
+ 2024-03-26 16:24:14,792 ----------------------------------------------------------------------------------------------------
230
+ 2024-03-26 16:24:17,626 epoch 10 - iter 4/48 - loss 0.05458151 - time (sec): 2.83 - samples/sec: 1310.58 - lr: 0.000003 - momentum: 0.000000
231
+ 2024-03-26 16:24:19,584 epoch 10 - iter 8/48 - loss 0.04944972 - time (sec): 4.79 - samples/sec: 1348.75 - lr: 0.000003 - momentum: 0.000000
232
+ 2024-03-26 16:24:21,756 epoch 10 - iter 12/48 - loss 0.04715640 - time (sec): 6.96 - samples/sec: 1306.11 - lr: 0.000003 - momentum: 0.000000
233
+ 2024-03-26 16:24:24,192 epoch 10 - iter 16/48 - loss 0.04421213 - time (sec): 9.40 - samples/sec: 1270.61 - lr: 0.000002 - momentum: 0.000000
234
+ 2024-03-26 16:24:26,739 epoch 10 - iter 20/48 - loss 0.04651412 - time (sec): 11.95 - samples/sec: 1274.41 - lr: 0.000002 - momentum: 0.000000
235
+ 2024-03-26 16:24:28,153 epoch 10 - iter 24/48 - loss 0.04510724 - time (sec): 13.36 - samples/sec: 1335.07 - lr: 0.000002 - momentum: 0.000000
236
+ 2024-03-26 16:24:29,025 epoch 10 - iter 28/48 - loss 0.04686140 - time (sec): 14.23 - samples/sec: 1407.49 - lr: 0.000002 - momentum: 0.000000
237
+ 2024-03-26 16:24:30,944 epoch 10 - iter 32/48 - loss 0.05020359 - time (sec): 16.15 - samples/sec: 1428.10 - lr: 0.000001 - momentum: 0.000000
238
+ 2024-03-26 16:24:33,193 epoch 10 - iter 36/48 - loss 0.05011506 - time (sec): 18.40 - samples/sec: 1406.00 - lr: 0.000001 - momentum: 0.000000
239
+ 2024-03-26 16:24:34,840 epoch 10 - iter 40/48 - loss 0.05124147 - time (sec): 20.05 - samples/sec: 1432.59 - lr: 0.000001 - momentum: 0.000000
240
+ 2024-03-26 16:24:37,982 epoch 10 - iter 44/48 - loss 0.05009590 - time (sec): 23.19 - samples/sec: 1413.36 - lr: 0.000001 - momentum: 0.000000
241
+ 2024-03-26 16:24:38,698 epoch 10 - iter 48/48 - loss 0.05065391 - time (sec): 23.91 - samples/sec: 1442.04 - lr: 0.000000 - momentum: 0.000000
242
+ 2024-03-26 16:24:38,698 ----------------------------------------------------------------------------------------------------
243
+ 2024-03-26 16:24:38,699 EPOCH 10 done: loss 0.0507 - lr: 0.000000
244
+ 2024-03-26 16:24:39,612 DEV : loss 0.17731061577796936 - f1-score (micro avg) 0.9171
245
+ 2024-03-26 16:24:39,882 ----------------------------------------------------------------------------------------------------
246
+ 2024-03-26 16:24:39,883 Loading model from best epoch ...
247
+ 2024-03-26 16:24:40,622 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 16:24:41,491
249
+ Results:
250
+ - F-score (micro) 0.8926
251
+ - F-score (macro) 0.68
252
+ - Accuracy 0.8095
253
+
254
+ By class:
255
+ precision recall f1-score support
256
+
257
+ Unternehmen 0.8876 0.8609 0.8740 266
258
+ Auslagerung 0.8566 0.8876 0.8718 249
259
+ Ort 0.9635 0.9851 0.9742 134
260
+ Software 0.0000 0.0000 0.0000 0
261
+
262
+ micro avg 0.8885 0.8968 0.8926 649
263
+ macro avg 0.6769 0.6834 0.6800 649
264
+ weighted avg 0.8914 0.8968 0.8939 649
265
+
266
+ 2024-03-26 16:24:41,491 ----------------------------------------------------------------------------------------------------