Hugging Face's logo

stefan-it
/
flair-co-funer-german_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
d360f74
•
1 Parent(s): 7a30a06

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +263 -0
training.log ADDED
@@ -0,0 +1,263 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-03-26 11:33:29,248 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 11:33:29,248 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(30001, 768)
7
+ (position_embeddings): Embedding(512, 768)
8
+ (token_type_embeddings): Embedding(2, 768)
9
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=768, out_features=768, bias=True)
18
+ (key): Linear(in_features=768, out_features=768, bias=True)
19
+ (value): Linear(in_features=768, out_features=768, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=768, out_features=768, bias=True)
24
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
34
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
35
+ (dropout): Dropout(p=0.1, inplace=False)
36
+ )
37
+ )
38
+ )
39
+ )
40
+ (pooler): BertPooler(
41
+ (dense): Linear(in_features=768, out_features=768, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=768, out_features=17, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2024-03-26 11:33:29,248 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 11:33:29,248 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 11:33:29,248 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 11:33:29,248 Train: 758 sentences
54
+ 2024-03-26 11:33:29,248 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 11:33:29,248 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 11:33:29,248 Training Params:
57
+ 2024-03-26 11:33:29,248 - learning_rate: "5e-05"
58
+ 2024-03-26 11:33:29,248 - mini_batch_size: "16"
59
+ 2024-03-26 11:33:29,248 - max_epochs: "10"
60
+ 2024-03-26 11:33:29,248 - shuffle: "True"
61
+ 2024-03-26 11:33:29,248 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 11:33:29,248 Plugins:
63
+ 2024-03-26 11:33:29,248 - TensorboardLogger
64
+ 2024-03-26 11:33:29,248 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 11:33:29,248 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 11:33:29,248 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 11:33:29,248 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 11:33:29,248 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 11:33:29,248 Computation:
70
+ 2024-03-26 11:33:29,248 - compute on device: cuda:0
71
+ 2024-03-26 11:33:29,248 - embedding storage: none
72
+ 2024-03-26 11:33:29,248 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 11:33:29,248 Model training base path: "flair-co-funer-german_bert_base-bs16-e10-lr5e-05-3"
74
+ 2024-03-26 11:33:29,248 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 11:33:29,249 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 11:33:29,249 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 11:33:30,579 epoch 1 - iter 4/48 - loss 3.07489042 - time (sec): 1.33 - samples/sec: 2069.01 - lr: 0.000003 - momentum: 0.000000
78
+ 2024-03-26 11:33:32,704 epoch 1 - iter 8/48 - loss 3.08771911 - time (sec): 3.46 - samples/sec: 1685.38 - lr: 0.000007 - momentum: 0.000000
79
+ 2024-03-26 11:33:34,228 epoch 1 - iter 12/48 - loss 2.94390144 - time (sec): 4.98 - samples/sec: 1681.86 - lr: 0.000011 - momentum: 0.000000
80
+ 2024-03-26 11:33:37,270 epoch 1 - iter 16/48 - loss 2.77162015 - time (sec): 8.02 - samples/sec: 1445.94 - lr: 0.000016 - momentum: 0.000000
81
+ 2024-03-26 11:33:39,010 epoch 1 - iter 20/48 - loss 2.60962695 - time (sec): 9.76 - samples/sec: 1475.60 - lr: 0.000020 - momentum: 0.000000
82
+ 2024-03-26 11:33:40,472 epoch 1 - iter 24/48 - loss 2.51067364 - time (sec): 11.22 - samples/sec: 1529.72 - lr: 0.000024 - momentum: 0.000000
83
+ 2024-03-26 11:33:41,866 epoch 1 - iter 28/48 - loss 2.39999582 - time (sec): 12.62 - samples/sec: 1547.60 - lr: 0.000028 - momentum: 0.000000
84
+ 2024-03-26 11:33:44,008 epoch 1 - iter 32/48 - loss 2.27938260 - time (sec): 14.76 - samples/sec: 1539.92 - lr: 0.000032 - momentum: 0.000000
85
+ 2024-03-26 11:33:45,593 epoch 1 - iter 36/48 - loss 2.16989687 - time (sec): 16.34 - samples/sec: 1561.40 - lr: 0.000036 - momentum: 0.000000
86
+ 2024-03-26 11:33:47,867 epoch 1 - iter 40/48 - loss 2.03915890 - time (sec): 18.62 - samples/sec: 1556.37 - lr: 0.000041 - momentum: 0.000000
87
+ 2024-03-26 11:33:49,800 epoch 1 - iter 44/48 - loss 1.93179330 - time (sec): 20.55 - samples/sec: 1560.33 - lr: 0.000045 - momentum: 0.000000
88
+ 2024-03-26 11:33:51,477 epoch 1 - iter 48/48 - loss 1.84076884 - time (sec): 22.23 - samples/sec: 1550.84 - lr: 0.000049 - momentum: 0.000000
89
+ 2024-03-26 11:33:51,477 ----------------------------------------------------------------------------------------------------
90
+ 2024-03-26 11:33:51,477 EPOCH 1 done: loss 1.8408 - lr: 0.000049
91
+ 2024-03-26 11:33:52,341 DEV : loss 0.5940399169921875 - f1-score (micro avg) 0.635
92
+ 2024-03-26 11:33:52,342 saving best model
93
+ 2024-03-26 11:33:52,617 ----------------------------------------------------------------------------------------------------
94
+ 2024-03-26 11:33:54,062 epoch 2 - iter 4/48 - loss 0.72316569 - time (sec): 1.44 - samples/sec: 1727.06 - lr: 0.000050 - momentum: 0.000000
95
+ 2024-03-26 11:33:55,558 epoch 2 - iter 8/48 - loss 0.57588712 - time (sec): 2.94 - samples/sec: 1659.65 - lr: 0.000049 - momentum: 0.000000
96
+ 2024-03-26 11:33:57,043 epoch 2 - iter 12/48 - loss 0.56563452 - time (sec): 4.43 - samples/sec: 1737.03 - lr: 0.000049 - momentum: 0.000000
97
+ 2024-03-26 11:33:59,008 epoch 2 - iter 16/48 - loss 0.52469522 - time (sec): 6.39 - samples/sec: 1683.10 - lr: 0.000048 - momentum: 0.000000
98
+ 2024-03-26 11:34:01,353 epoch 2 - iter 20/48 - loss 0.50473970 - time (sec): 8.74 - samples/sec: 1623.17 - lr: 0.000048 - momentum: 0.000000
99
+ 2024-03-26 11:34:03,440 epoch 2 - iter 24/48 - loss 0.47203328 - time (sec): 10.82 - samples/sec: 1602.62 - lr: 0.000047 - momentum: 0.000000
100
+ 2024-03-26 11:34:06,292 epoch 2 - iter 28/48 - loss 0.46192324 - time (sec): 13.68 - samples/sec: 1530.16 - lr: 0.000047 - momentum: 0.000000
101
+ 2024-03-26 11:34:08,529 epoch 2 - iter 32/48 - loss 0.44576921 - time (sec): 15.91 - samples/sec: 1500.06 - lr: 0.000046 - momentum: 0.000000
102
+ 2024-03-26 11:34:10,295 epoch 2 - iter 36/48 - loss 0.43726579 - time (sec): 17.68 - samples/sec: 1494.39 - lr: 0.000046 - momentum: 0.000000
103
+ 2024-03-26 11:34:12,061 epoch 2 - iter 40/48 - loss 0.43733009 - time (sec): 19.44 - samples/sec: 1500.28 - lr: 0.000046 - momentum: 0.000000
104
+ 2024-03-26 11:34:14,381 epoch 2 - iter 44/48 - loss 0.42304062 - time (sec): 21.76 - samples/sec: 1488.86 - lr: 0.000045 - momentum: 0.000000
105
+ 2024-03-26 11:34:15,946 epoch 2 - iter 48/48 - loss 0.41515240 - time (sec): 23.33 - samples/sec: 1477.66 - lr: 0.000045 - momentum: 0.000000
106
+ 2024-03-26 11:34:15,946 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 11:34:15,946 EPOCH 2 done: loss 0.4152 - lr: 0.000045
108
+ 2024-03-26 11:34:16,914 DEV : loss 0.26913678646087646 - f1-score (micro avg) 0.8164
109
+ 2024-03-26 11:34:16,917 saving best model
110
+ 2024-03-26 11:34:17,390 ----------------------------------------------------------------------------------------------------
111
+ 2024-03-26 11:34:18,964 epoch 3 - iter 4/48 - loss 0.27840730 - time (sec): 1.57 - samples/sec: 1558.05 - lr: 0.000044 - momentum: 0.000000
112
+ 2024-03-26 11:34:21,788 epoch 3 - iter 8/48 - loss 0.22660795 - time (sec): 4.40 - samples/sec: 1303.04 - lr: 0.000044 - momentum: 0.000000
113
+ 2024-03-26 11:34:23,083 epoch 3 - iter 12/48 - loss 0.22777721 - time (sec): 5.69 - samples/sec: 1431.27 - lr: 0.000043 - momentum: 0.000000
114
+ 2024-03-26 11:34:24,492 epoch 3 - iter 16/48 - loss 0.20623331 - time (sec): 7.10 - samples/sec: 1554.57 - lr: 0.000043 - momentum: 0.000000
115
+ 2024-03-26 11:34:26,009 epoch 3 - iter 20/48 - loss 0.20655534 - time (sec): 8.62 - samples/sec: 1567.86 - lr: 0.000042 - momentum: 0.000000
116
+ 2024-03-26 11:34:28,814 epoch 3 - iter 24/48 - loss 0.20077536 - time (sec): 11.42 - samples/sec: 1462.28 - lr: 0.000042 - momentum: 0.000000
117
+ 2024-03-26 11:34:30,804 epoch 3 - iter 28/48 - loss 0.20515197 - time (sec): 13.41 - samples/sec: 1477.75 - lr: 0.000041 - momentum: 0.000000
118
+ 2024-03-26 11:34:33,323 epoch 3 - iter 32/48 - loss 0.19788947 - time (sec): 15.93 - samples/sec: 1431.16 - lr: 0.000041 - momentum: 0.000000
119
+ 2024-03-26 11:34:35,287 epoch 3 - iter 36/48 - loss 0.20165014 - time (sec): 17.90 - samples/sec: 1429.28 - lr: 0.000040 - momentum: 0.000000
120
+ 2024-03-26 11:34:37,666 epoch 3 - iter 40/48 - loss 0.19334685 - time (sec): 20.27 - samples/sec: 1408.84 - lr: 0.000040 - momentum: 0.000000
121
+ 2024-03-26 11:34:40,145 epoch 3 - iter 44/48 - loss 0.20288087 - time (sec): 22.75 - samples/sec: 1398.52 - lr: 0.000040 - momentum: 0.000000
122
+ 2024-03-26 11:34:42,579 epoch 3 - iter 48/48 - loss 0.19661772 - time (sec): 25.19 - samples/sec: 1368.61 - lr: 0.000039 - momentum: 0.000000
123
+ 2024-03-26 11:34:42,579 ----------------------------------------------------------------------------------------------------
124
+ 2024-03-26 11:34:42,579 EPOCH 3 done: loss 0.1966 - lr: 0.000039
125
+ 2024-03-26 11:34:43,613 DEV : loss 0.21700386703014374 - f1-score (micro avg) 0.8608
126
+ 2024-03-26 11:34:43,614 saving best model
127
+ 2024-03-26 11:34:44,036 ----------------------------------------------------------------------------------------------------
128
+ 2024-03-26 11:34:45,449 epoch 4 - iter 4/48 - loss 0.14641328 - time (sec): 1.41 - samples/sec: 1773.85 - lr: 0.000039 - momentum: 0.000000
129
+ 2024-03-26 11:34:47,395 epoch 4 - iter 8/48 - loss 0.13808574 - time (sec): 3.36 - samples/sec: 1595.81 - lr: 0.000038 - momentum: 0.000000
130
+ 2024-03-26 11:34:50,115 epoch 4 - iter 12/48 - loss 0.12876595 - time (sec): 6.08 - samples/sec: 1388.37 - lr: 0.000038 - momentum: 0.000000
131
+ 2024-03-26 11:34:52,081 epoch 4 - iter 16/48 - loss 0.13156323 - time (sec): 8.04 - samples/sec: 1407.85 - lr: 0.000037 - momentum: 0.000000
132
+ 2024-03-26 11:34:54,572 epoch 4 - iter 20/48 - loss 0.12428123 - time (sec): 10.53 - samples/sec: 1394.75 - lr: 0.000037 - momentum: 0.000000
133
+ 2024-03-26 11:34:57,507 epoch 4 - iter 24/48 - loss 0.11793333 - time (sec): 13.47 - samples/sec: 1353.70 - lr: 0.000036 - momentum: 0.000000
134
+ 2024-03-26 11:34:58,691 epoch 4 - iter 28/48 - loss 0.11608881 - time (sec): 14.65 - samples/sec: 1386.24 - lr: 0.000036 - momentum: 0.000000
135
+ 2024-03-26 11:35:01,804 epoch 4 - iter 32/48 - loss 0.11458934 - time (sec): 17.77 - samples/sec: 1329.30 - lr: 0.000035 - momentum: 0.000000
136
+ 2024-03-26 11:35:03,594 epoch 4 - iter 36/48 - loss 0.11846800 - time (sec): 19.56 - samples/sec: 1360.43 - lr: 0.000035 - momentum: 0.000000
137
+ 2024-03-26 11:35:06,500 epoch 4 - iter 40/48 - loss 0.12511856 - time (sec): 22.46 - samples/sec: 1330.40 - lr: 0.000034 - momentum: 0.000000
138
+ 2024-03-26 11:35:07,417 epoch 4 - iter 44/48 - loss 0.12629946 - time (sec): 23.38 - samples/sec: 1376.32 - lr: 0.000034 - momentum: 0.000000
139
+ 2024-03-26 11:35:08,913 epoch 4 - iter 48/48 - loss 0.12787118 - time (sec): 24.88 - samples/sec: 1385.74 - lr: 0.000034 - momentum: 0.000000
140
+ 2024-03-26 11:35:08,914 ----------------------------------------------------------------------------------------------------
141
+ 2024-03-26 11:35:08,914 EPOCH 4 done: loss 0.1279 - lr: 0.000034
142
+ 2024-03-26 11:35:09,895 DEV : loss 0.18662486970424652 - f1-score (micro avg) 0.8817
143
+ 2024-03-26 11:35:09,897 saving best model
144
+ 2024-03-26 11:35:10,332 ----------------------------------------------------------------------------------------------------
145
+ 2024-03-26 11:35:12,809 epoch 5 - iter 4/48 - loss 0.06830634 - time (sec): 2.48 - samples/sec: 1283.35 - lr: 0.000033 - momentum: 0.000000
146
+ 2024-03-26 11:35:14,268 epoch 5 - iter 8/48 - loss 0.08573760 - time (sec): 3.94 - samples/sec: 1446.25 - lr: 0.000033 - momentum: 0.000000
147
+ 2024-03-26 11:35:15,788 epoch 5 - iter 12/48 - loss 0.08684380 - time (sec): 5.46 - samples/sec: 1510.47 - lr: 0.000032 - momentum: 0.000000
148
+ 2024-03-26 11:35:18,018 epoch 5 - iter 16/48 - loss 0.08965837 - time (sec): 7.69 - samples/sec: 1431.53 - lr: 0.000032 - momentum: 0.000000
149
+ 2024-03-26 11:35:20,150 epoch 5 - iter 20/48 - loss 0.10094467 - time (sec): 9.82 - samples/sec: 1434.23 - lr: 0.000031 - momentum: 0.000000
150
+ 2024-03-26 11:35:22,751 epoch 5 - iter 24/48 - loss 0.09379417 - time (sec): 12.42 - samples/sec: 1417.55 - lr: 0.000031 - momentum: 0.000000
151
+ 2024-03-26 11:35:25,342 epoch 5 - iter 28/48 - loss 0.08737934 - time (sec): 15.01 - samples/sec: 1402.35 - lr: 0.000030 - momentum: 0.000000
152
+ 2024-03-26 11:35:27,327 epoch 5 - iter 32/48 - loss 0.08652809 - time (sec): 16.99 - samples/sec: 1401.19 - lr: 0.000030 - momentum: 0.000000
153
+ 2024-03-26 11:35:29,218 epoch 5 - iter 36/48 - loss 0.08405259 - time (sec): 18.89 - samples/sec: 1400.33 - lr: 0.000029 - momentum: 0.000000
154
+ 2024-03-26 11:35:31,655 epoch 5 - iter 40/48 - loss 0.08424074 - time (sec): 21.32 - samples/sec: 1385.12 - lr: 0.000029 - momentum: 0.000000
155
+ 2024-03-26 11:35:33,674 epoch 5 - iter 44/48 - loss 0.08675698 - time (sec): 23.34 - samples/sec: 1383.79 - lr: 0.000029 - momentum: 0.000000
156
+ 2024-03-26 11:35:34,768 epoch 5 - iter 48/48 - loss 0.08578516 - time (sec): 24.44 - samples/sec: 1410.70 - lr: 0.000028 - momentum: 0.000000
157
+ 2024-03-26 11:35:34,769 ----------------------------------------------------------------------------------------------------
158
+ 2024-03-26 11:35:34,769 EPOCH 5 done: loss 0.0858 - lr: 0.000028
159
+ 2024-03-26 11:35:35,716 DEV : loss 0.17283330857753754 - f1-score (micro avg) 0.8942
160
+ 2024-03-26 11:35:35,717 saving best model
161
+ 2024-03-26 11:35:36,174 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 11:35:38,850 epoch 6 - iter 4/48 - loss 0.05365840 - time (sec): 2.68 - samples/sec: 1188.40 - lr: 0.000028 - momentum: 0.000000
163
+ 2024-03-26 11:35:40,878 epoch 6 - iter 8/48 - loss 0.05720723 - time (sec): 4.70 - samples/sec: 1248.47 - lr: 0.000027 - momentum: 0.000000
164
+ 2024-03-26 11:35:42,486 epoch 6 - iter 12/48 - loss 0.06649040 - time (sec): 6.31 - samples/sec: 1397.93 - lr: 0.000027 - momentum: 0.000000
165
+ 2024-03-26 11:35:44,519 epoch 6 - iter 16/48 - loss 0.06053967 - time (sec): 8.34 - samples/sec: 1393.76 - lr: 0.000026 - momentum: 0.000000
166
+ 2024-03-26 11:35:45,652 epoch 6 - iter 20/48 - loss 0.05981345 - time (sec): 9.48 - samples/sec: 1474.40 - lr: 0.000026 - momentum: 0.000000
167
+ 2024-03-26 11:35:47,585 epoch 6 - iter 24/48 - loss 0.05907532 - time (sec): 11.41 - samples/sec: 1464.86 - lr: 0.000025 - momentum: 0.000000
168
+ 2024-03-26 11:35:48,768 epoch 6 - iter 28/48 - loss 0.06005105 - time (sec): 12.59 - samples/sec: 1510.48 - lr: 0.000025 - momentum: 0.000000
169
+ 2024-03-26 11:35:50,567 epoch 6 - iter 32/48 - loss 0.05586702 - time (sec): 14.39 - samples/sec: 1530.72 - lr: 0.000024 - momentum: 0.000000
170
+ 2024-03-26 11:35:53,101 epoch 6 - iter 36/48 - loss 0.06595337 - time (sec): 16.93 - samples/sec: 1500.21 - lr: 0.000024 - momentum: 0.000000
171
+ 2024-03-26 11:35:55,243 epoch 6 - iter 40/48 - loss 0.06371281 - time (sec): 19.07 - samples/sec: 1490.16 - lr: 0.000023 - momentum: 0.000000
172
+ 2024-03-26 11:35:57,163 epoch 6 - iter 44/48 - loss 0.06590059 - time (sec): 20.99 - samples/sec: 1498.80 - lr: 0.000023 - momentum: 0.000000
173
+ 2024-03-26 11:35:58,837 epoch 6 - iter 48/48 - loss 0.06662131 - time (sec): 22.66 - samples/sec: 1521.17 - lr: 0.000023 - momentum: 0.000000
174
+ 2024-03-26 11:35:58,837 ----------------------------------------------------------------------------------------------------
175
+ 2024-03-26 11:35:58,837 EPOCH 6 done: loss 0.0666 - lr: 0.000023
176
+ 2024-03-26 11:35:59,808 DEV : loss 0.15879587829113007 - f1-score (micro avg) 0.9341
177
+ 2024-03-26 11:35:59,809 saving best model
178
+ 2024-03-26 11:36:00,267 ----------------------------------------------------------------------------------------------------
179
+ 2024-03-26 11:36:02,501 epoch 7 - iter 4/48 - loss 0.07284967 - time (sec): 2.23 - samples/sec: 1237.82 - lr: 0.000022 - momentum: 0.000000
180
+ 2024-03-26 11:36:04,244 epoch 7 - iter 8/48 - loss 0.05810049 - time (sec): 3.98 - samples/sec: 1445.13 - lr: 0.000022 - momentum: 0.000000
181
+ 2024-03-26 11:36:06,352 epoch 7 - iter 12/48 - loss 0.04687988 - time (sec): 6.08 - samples/sec: 1408.13 - lr: 0.000021 - momentum: 0.000000
182
+ 2024-03-26 11:36:09,051 epoch 7 - iter 16/48 - loss 0.04388564 - time (sec): 8.78 - samples/sec: 1345.71 - lr: 0.000021 - momentum: 0.000000
183
+ 2024-03-26 11:36:11,822 epoch 7 - iter 20/48 - loss 0.04451078 - time (sec): 11.55 - samples/sec: 1352.70 - lr: 0.000020 - momentum: 0.000000
184
+ 2024-03-26 11:36:13,366 epoch 7 - iter 24/48 - loss 0.04438006 - time (sec): 13.10 - samples/sec: 1376.06 - lr: 0.000020 - momentum: 0.000000
185
+ 2024-03-26 11:36:15,571 epoch 7 - iter 28/48 - loss 0.04184705 - time (sec): 15.30 - samples/sec: 1390.16 - lr: 0.000019 - momentum: 0.000000
186
+ 2024-03-26 11:36:17,773 epoch 7 - iter 32/48 - loss 0.04525184 - time (sec): 17.51 - samples/sec: 1396.63 - lr: 0.000019 - momentum: 0.000000
187
+ 2024-03-26 11:36:20,032 epoch 7 - iter 36/48 - loss 0.04947562 - time (sec): 19.76 - samples/sec: 1385.10 - lr: 0.000018 - momentum: 0.000000
188
+ 2024-03-26 11:36:21,659 epoch 7 - iter 40/48 - loss 0.04694456 - time (sec): 21.39 - samples/sec: 1393.87 - lr: 0.000018 - momentum: 0.000000
189
+ 2024-03-26 11:36:23,419 epoch 7 - iter 44/48 - loss 0.05016226 - time (sec): 23.15 - samples/sec: 1408.92 - lr: 0.000017 - momentum: 0.000000
190
+ 2024-03-26 11:36:24,776 epoch 7 - iter 48/48 - loss 0.04985462 - time (sec): 24.51 - samples/sec: 1406.54 - lr: 0.000017 - momentum: 0.000000
191
+ 2024-03-26 11:36:24,777 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 11:36:24,777 EPOCH 7 done: loss 0.0499 - lr: 0.000017
193
+ 2024-03-26 11:36:25,828 DEV : loss 0.16802552342414856 - f1-score (micro avg) 0.9333
194
+ 2024-03-26 11:36:25,830 ----------------------------------------------------------------------------------------------------
195
+ 2024-03-26 11:36:28,176 epoch 8 - iter 4/48 - loss 0.02523109 - time (sec): 2.35 - samples/sec: 1253.12 - lr: 0.000017 - momentum: 0.000000
196
+ 2024-03-26 11:36:30,775 epoch 8 - iter 8/48 - loss 0.02208519 - time (sec): 4.94 - samples/sec: 1337.73 - lr: 0.000016 - momentum: 0.000000
197
+ 2024-03-26 11:36:32,833 epoch 8 - iter 12/48 - loss 0.02316165 - time (sec): 7.00 - samples/sec: 1314.10 - lr: 0.000016 - momentum: 0.000000
198
+ 2024-03-26 11:36:34,948 epoch 8 - iter 16/48 - loss 0.02270118 - time (sec): 9.12 - samples/sec: 1315.04 - lr: 0.000015 - momentum: 0.000000
199
+ 2024-03-26 11:36:36,478 epoch 8 - iter 20/48 - loss 0.02510760 - time (sec): 10.65 - samples/sec: 1342.76 - lr: 0.000015 - momentum: 0.000000
200
+ 2024-03-26 11:36:38,968 epoch 8 - iter 24/48 - loss 0.02440371 - time (sec): 13.14 - samples/sec: 1319.99 - lr: 0.000014 - momentum: 0.000000
201
+ 2024-03-26 11:36:41,209 epoch 8 - iter 28/48 - loss 0.02404743 - time (sec): 15.38 - samples/sec: 1310.63 - lr: 0.000014 - momentum: 0.000000
202
+ 2024-03-26 11:36:43,580 epoch 8 - iter 32/48 - loss 0.03201898 - time (sec): 17.75 - samples/sec: 1322.64 - lr: 0.000013 - momentum: 0.000000
203
+ 2024-03-26 11:36:46,883 epoch 8 - iter 36/48 - loss 0.03651999 - time (sec): 21.05 - samples/sec: 1274.74 - lr: 0.000013 - momentum: 0.000000
204
+ 2024-03-26 11:36:48,978 epoch 8 - iter 40/48 - loss 0.04125936 - time (sec): 23.15 - samples/sec: 1278.60 - lr: 0.000012 - momentum: 0.000000
205
+ 2024-03-26 11:36:49,806 epoch 8 - iter 44/48 - loss 0.04000375 - time (sec): 23.98 - samples/sec: 1325.12 - lr: 0.000012 - momentum: 0.000000
206
+ 2024-03-26 11:36:51,680 epoch 8 - iter 48/48 - loss 0.03939075 - time (sec): 25.85 - samples/sec: 1333.53 - lr: 0.000011 - momentum: 0.000000
207
+ 2024-03-26 11:36:51,681 ----------------------------------------------------------------------------------------------------
208
+ 2024-03-26 11:36:51,681 EPOCH 8 done: loss 0.0394 - lr: 0.000011
209
+ 2024-03-26 11:36:52,644 DEV : loss 0.18046870827674866 - f1-score (micro avg) 0.9294
210
+ 2024-03-26 11:36:52,647 ----------------------------------------------------------------------------------------------------
211
+ 2024-03-26 11:36:55,407 epoch 9 - iter 4/48 - loss 0.01368922 - time (sec): 2.76 - samples/sec: 1195.26 - lr: 0.000011 - momentum: 0.000000
212
+ 2024-03-26 11:36:57,113 epoch 9 - iter 8/48 - loss 0.02194754 - time (sec): 4.47 - samples/sec: 1284.97 - lr: 0.000011 - momentum: 0.000000
213
+ 2024-03-26 11:36:59,325 epoch 9 - iter 12/48 - loss 0.02259365 - time (sec): 6.68 - samples/sec: 1344.23 - lr: 0.000010 - momentum: 0.000000
214
+ 2024-03-26 11:37:01,488 epoch 9 - iter 16/48 - loss 0.02747245 - time (sec): 8.84 - samples/sec: 1369.80 - lr: 0.000010 - momentum: 0.000000
215
+ 2024-03-26 11:37:03,868 epoch 9 - iter 20/48 - loss 0.02337877 - time (sec): 11.22 - samples/sec: 1348.38 - lr: 0.000009 - momentum: 0.000000
216
+ 2024-03-26 11:37:05,818 epoch 9 - iter 24/48 - loss 0.02369286 - time (sec): 13.17 - samples/sec: 1344.53 - lr: 0.000009 - momentum: 0.000000
217
+ 2024-03-26 11:37:09,104 epoch 9 - iter 28/48 - loss 0.02677139 - time (sec): 16.46 - samples/sec: 1298.13 - lr: 0.000008 - momentum: 0.000000
218
+ 2024-03-26 11:37:10,540 epoch 9 - iter 32/48 - loss 0.02760924 - time (sec): 17.89 - samples/sec: 1335.17 - lr: 0.000008 - momentum: 0.000000
219
+ 2024-03-26 11:37:13,071 epoch 9 - iter 36/48 - loss 0.02778603 - time (sec): 20.42 - samples/sec: 1319.50 - lr: 0.000007 - momentum: 0.000000
220
+ 2024-03-26 11:37:14,592 epoch 9 - iter 40/48 - loss 0.02879429 - time (sec): 21.94 - samples/sec: 1336.09 - lr: 0.000007 - momentum: 0.000000
221
+ 2024-03-26 11:37:16,189 epoch 9 - iter 44/48 - loss 0.03224152 - time (sec): 23.54 - samples/sec: 1351.25 - lr: 0.000006 - momentum: 0.000000
222
+ 2024-03-26 11:37:17,651 epoch 9 - iter 48/48 - loss 0.03182031 - time (sec): 25.00 - samples/sec: 1378.69 - lr: 0.000006 - momentum: 0.000000
223
+ 2024-03-26 11:37:17,651 ----------------------------------------------------------------------------------------------------
224
+ 2024-03-26 11:37:17,651 EPOCH 9 done: loss 0.0318 - lr: 0.000006
225
+ 2024-03-26 11:37:18,590 DEV : loss 0.18695427477359772 - f1-score (micro avg) 0.9263
226
+ 2024-03-26 11:37:18,591 ----------------------------------------------------------------------------------------------------
227
+ 2024-03-26 11:37:21,015 epoch 10 - iter 4/48 - loss 0.02264444 - time (sec): 2.42 - samples/sec: 1358.51 - lr: 0.000006 - momentum: 0.000000
228
+ 2024-03-26 11:37:22,976 epoch 10 - iter 8/48 - loss 0.01694052 - time (sec): 4.38 - samples/sec: 1333.02 - lr: 0.000005 - momentum: 0.000000
229
+ 2024-03-26 11:37:24,212 epoch 10 - iter 12/48 - loss 0.02510073 - time (sec): 5.62 - samples/sec: 1484.16 - lr: 0.000005 - momentum: 0.000000
230
+ 2024-03-26 11:37:25,824 epoch 10 - iter 16/48 - loss 0.02807504 - time (sec): 7.23 - samples/sec: 1551.36 - lr: 0.000004 - momentum: 0.000000
231
+ 2024-03-26 11:37:27,540 epoch 10 - iter 20/48 - loss 0.02802998 - time (sec): 8.95 - samples/sec: 1595.24 - lr: 0.000004 - momentum: 0.000000
232
+ 2024-03-26 11:37:29,677 epoch 10 - iter 24/48 - loss 0.02579472 - time (sec): 11.09 - samples/sec: 1537.39 - lr: 0.000003 - momentum: 0.000000
233
+ 2024-03-26 11:37:31,826 epoch 10 - iter 28/48 - loss 0.02330368 - time (sec): 13.23 - samples/sec: 1507.27 - lr: 0.000003 - momentum: 0.000000
234
+ 2024-03-26 11:37:34,002 epoch 10 - iter 32/48 - loss 0.02482044 - time (sec): 15.41 - samples/sec: 1513.99 - lr: 0.000002 - momentum: 0.000000
235
+ 2024-03-26 11:37:35,409 epoch 10 - iter 36/48 - loss 0.02437032 - time (sec): 16.82 - samples/sec: 1516.24 - lr: 0.000002 - momentum: 0.000000
236
+ 2024-03-26 11:37:38,098 epoch 10 - iter 40/48 - loss 0.02266370 - time (sec): 19.51 - samples/sec: 1479.35 - lr: 0.000001 - momentum: 0.000000
237
+ 2024-03-26 11:37:40,623 epoch 10 - iter 44/48 - loss 0.02605707 - time (sec): 22.03 - samples/sec: 1459.52 - lr: 0.000001 - momentum: 0.000000
238
+ 2024-03-26 11:37:42,293 epoch 10 - iter 48/48 - loss 0.02700708 - time (sec): 23.70 - samples/sec: 1454.42 - lr: 0.000000 - momentum: 0.000000
239
+ 2024-03-26 11:37:42,293 ----------------------------------------------------------------------------------------------------
240
+ 2024-03-26 11:37:42,293 EPOCH 10 done: loss 0.0270 - lr: 0.000000
241
+ 2024-03-26 11:37:43,246 DEV : loss 0.17998817563056946 - f1-score (micro avg) 0.9326
242
+ 2024-03-26 11:37:43,555 ----------------------------------------------------------------------------------------------------
243
+ 2024-03-26 11:37:43,555 Loading model from best epoch ...
244
+ 2024-03-26 11:37:44,460 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
245
+ 2024-03-26 11:37:45,303
246
+ Results:
247
+ - F-score (micro) 0.9052
248
+ - F-score (macro) 0.6892
249
+ - Accuracy 0.8279
250
+
251
+ By class:
252
+ precision recall f1-score support
253
+
254
+ Unternehmen 0.9027 0.8722 0.8872 266
255
+ Auslagerung 0.8775 0.8916 0.8845 249
256
+ Ort 0.9779 0.9925 0.9852 134
257
+ Software 0.0000 0.0000 0.0000 0
258
+
259
+ micro avg 0.9059 0.9045 0.9052 649
260
+ macro avg 0.6895 0.6891 0.6892 649
261
+ weighted avg 0.9086 0.9045 0.9064 649
262
+
263
+ 2024-03-26 11:37:45,304 ----------------------------------------------------------------------------------------------------