Hugging Face's logo

stefan-it
/
flair-co-funer-german_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
95c5527
•
1 Parent(s): c319b57

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 10:59:50,722 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 10:59:50,722 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 10:59:50,722 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 10:59:50,722 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 10:59:50,722 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 10:59:50,722 Train: 758 sentences
54
+ 2024-03-26 10:59:50,722 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 10:59:50,722 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 10:59:50,722 Training Params:
57
+ 2024-03-26 10:59:50,722 - learning_rate: "5e-05"
58
+ 2024-03-26 10:59:50,722 - mini_batch_size: "16"
59
+ 2024-03-26 10:59:50,722 - max_epochs: "10"
60
+ 2024-03-26 10:59:50,722 - shuffle: "True"
61
+ 2024-03-26 10:59:50,722 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 10:59:50,722 Plugins:
63
+ 2024-03-26 10:59:50,722 - TensorboardLogger
64
+ 2024-03-26 10:59:50,722 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 10:59:50,723 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 10:59:50,723 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 10:59:50,723 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 10:59:50,723 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 10:59:50,723 Computation:
70
+ 2024-03-26 10:59:50,723 - compute on device: cuda:0
71
+ 2024-03-26 10:59:50,723 - embedding storage: none
72
+ 2024-03-26 10:59:50,723 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 10:59:50,723 Model training base path: "flair-co-funer-german_bert_base-bs16-e10-lr5e-05-1"
74
+ 2024-03-26 10:59:50,723 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 10:59:50,723 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 10:59:50,723 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 10:59:52,827 epoch 1 - iter 4/48 - loss 3.17719565 - time (sec): 2.10 - samples/sec: 1290.23 - lr: 0.000003 - momentum: 0.000000
78
+ 2024-03-26 10:59:54,174 epoch 1 - iter 8/48 - loss 3.22940502 - time (sec): 3.45 - samples/sec: 1561.49 - lr: 0.000007 - momentum: 0.000000
79
+ 2024-03-26 10:59:57,198 epoch 1 - iter 12/48 - loss 3.11554189 - time (sec): 6.48 - samples/sec: 1343.86 - lr: 0.000011 - momentum: 0.000000
80
+ 2024-03-26 11:00:00,546 epoch 1 - iter 16/48 - loss 2.96962598 - time (sec): 9.82 - samples/sec: 1241.33 - lr: 0.000016 - momentum: 0.000000
81
+ 2024-03-26 11:00:03,131 epoch 1 - iter 20/48 - loss 2.80109533 - time (sec): 12.41 - samples/sec: 1239.73 - lr: 0.000020 - momentum: 0.000000
82
+ 2024-03-26 11:00:04,908 epoch 1 - iter 24/48 - loss 2.64646526 - time (sec): 14.18 - samples/sec: 1285.69 - lr: 0.000024 - momentum: 0.000000
83
+ 2024-03-26 11:00:06,561 epoch 1 - iter 28/48 - loss 2.52516425 - time (sec): 15.84 - samples/sec: 1307.09 - lr: 0.000028 - momentum: 0.000000
84
+ 2024-03-26 11:00:08,744 epoch 1 - iter 32/48 - loss 2.41186996 - time (sec): 18.02 - samples/sec: 1311.61 - lr: 0.000032 - momentum: 0.000000
85
+ 2024-03-26 11:00:09,739 epoch 1 - iter 36/48 - loss 2.32081588 - time (sec): 19.02 - samples/sec: 1369.83 - lr: 0.000036 - momentum: 0.000000
86
+ 2024-03-26 11:00:11,786 epoch 1 - iter 40/48 - loss 2.21383836 - time (sec): 21.06 - samples/sec: 1382.32 - lr: 0.000041 - momentum: 0.000000
87
+ 2024-03-26 11:00:13,867 epoch 1 - iter 44/48 - loss 2.11699490 - time (sec): 23.14 - samples/sec: 1368.86 - lr: 0.000045 - momentum: 0.000000
88
+ 2024-03-26 11:00:15,419 epoch 1 - iter 48/48 - loss 2.01053611 - time (sec): 24.70 - samples/sec: 1395.88 - lr: 0.000049 - momentum: 0.000000
89
+ 2024-03-26 11:00:15,419 ----------------------------------------------------------------------------------------------------
90
+ 2024-03-26 11:00:15,419 EPOCH 1 done: loss 2.0105 - lr: 0.000049
91
+ 2024-03-26 11:00:16,279 DEV : loss 0.6016283631324768 - f1-score (micro avg) 0.5787
92
+ 2024-03-26 11:00:16,281 saving best model
93
+ 2024-03-26 11:00:16,555 ----------------------------------------------------------------------------------------------------
94
+ 2024-03-26 11:00:19,245 epoch 2 - iter 4/48 - loss 0.70959951 - time (sec): 2.69 - samples/sec: 1153.63 - lr: 0.000050 - momentum: 0.000000
95
+ 2024-03-26 11:00:21,418 epoch 2 - iter 8/48 - loss 0.70407287 - time (sec): 4.86 - samples/sec: 1360.00 - lr: 0.000049 - momentum: 0.000000
96
+ 2024-03-26 11:00:23,773 epoch 2 - iter 12/48 - loss 0.65597292 - time (sec): 7.22 - samples/sec: 1282.88 - lr: 0.000049 - momentum: 0.000000
97
+ 2024-03-26 11:00:25,873 epoch 2 - iter 16/48 - loss 0.61448768 - time (sec): 9.32 - samples/sec: 1278.96 - lr: 0.000048 - momentum: 0.000000
98
+ 2024-03-26 11:00:28,044 epoch 2 - iter 20/48 - loss 0.57629162 - time (sec): 11.49 - samples/sec: 1305.28 - lr: 0.000048 - momentum: 0.000000
99
+ 2024-03-26 11:00:31,219 epoch 2 - iter 24/48 - loss 0.52019540 - time (sec): 14.66 - samples/sec: 1261.90 - lr: 0.000047 - momentum: 0.000000
100
+ 2024-03-26 11:00:33,666 epoch 2 - iter 28/48 - loss 0.50568930 - time (sec): 17.11 - samples/sec: 1258.99 - lr: 0.000047 - momentum: 0.000000
101
+ 2024-03-26 11:00:35,456 epoch 2 - iter 32/48 - loss 0.48837358 - time (sec): 18.90 - samples/sec: 1276.55 - lr: 0.000046 - momentum: 0.000000
102
+ 2024-03-26 11:00:36,527 epoch 2 - iter 36/48 - loss 0.47541041 - time (sec): 19.97 - samples/sec: 1324.58 - lr: 0.000046 - momentum: 0.000000
103
+ 2024-03-26 11:00:38,421 epoch 2 - iter 40/48 - loss 0.46034741 - time (sec): 21.87 - samples/sec: 1344.51 - lr: 0.000046 - momentum: 0.000000
104
+ 2024-03-26 11:00:40,494 epoch 2 - iter 44/48 - loss 0.45159252 - time (sec): 23.94 - samples/sec: 1341.26 - lr: 0.000045 - momentum: 0.000000
105
+ 2024-03-26 11:00:41,950 epoch 2 - iter 48/48 - loss 0.44143919 - time (sec): 25.39 - samples/sec: 1357.48 - lr: 0.000045 - momentum: 0.000000
106
+ 2024-03-26 11:00:41,950 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 11:00:41,950 EPOCH 2 done: loss 0.4414 - lr: 0.000045
108
+ 2024-03-26 11:00:42,973 DEV : loss 0.3147665560245514 - f1-score (micro avg) 0.8072
109
+ 2024-03-26 11:00:42,974 saving best model
110
+ 2024-03-26 11:00:43,402 ----------------------------------------------------------------------------------------------------
111
+ 2024-03-26 11:00:45,991 epoch 3 - iter 4/48 - loss 0.28698034 - time (sec): 2.59 - samples/sec: 1179.06 - lr: 0.000044 - momentum: 0.000000
112
+ 2024-03-26 11:00:47,895 epoch 3 - iter 8/48 - loss 0.25658164 - time (sec): 4.49 - samples/sec: 1305.97 - lr: 0.000044 - momentum: 0.000000
113
+ 2024-03-26 11:00:49,761 epoch 3 - iter 12/48 - loss 0.26858709 - time (sec): 6.36 - samples/sec: 1381.81 - lr: 0.000043 - momentum: 0.000000
114
+ 2024-03-26 11:00:52,180 epoch 3 - iter 16/48 - loss 0.24605106 - time (sec): 8.78 - samples/sec: 1391.39 - lr: 0.000043 - momentum: 0.000000
115
+ 2024-03-26 11:00:53,687 epoch 3 - iter 20/48 - loss 0.25301403 - time (sec): 10.29 - samples/sec: 1438.66 - lr: 0.000042 - momentum: 0.000000
116
+ 2024-03-26 11:00:56,688 epoch 3 - iter 24/48 - loss 0.24057070 - time (sec): 13.29 - samples/sec: 1423.43 - lr: 0.000042 - momentum: 0.000000
117
+ 2024-03-26 11:00:57,456 epoch 3 - iter 28/48 - loss 0.22678079 - time (sec): 14.05 - samples/sec: 1497.16 - lr: 0.000041 - momentum: 0.000000
118
+ 2024-03-26 11:01:00,172 epoch 3 - iter 32/48 - loss 0.22006429 - time (sec): 16.77 - samples/sec: 1432.64 - lr: 0.000041 - momentum: 0.000000
119
+ 2024-03-26 11:01:02,238 epoch 3 - iter 36/48 - loss 0.20958441 - time (sec): 18.84 - samples/sec: 1425.88 - lr: 0.000040 - momentum: 0.000000
120
+ 2024-03-26 11:01:04,210 epoch 3 - iter 40/48 - loss 0.20985973 - time (sec): 20.81 - samples/sec: 1414.06 - lr: 0.000040 - momentum: 0.000000
121
+ 2024-03-26 11:01:06,442 epoch 3 - iter 44/48 - loss 0.20453707 - time (sec): 23.04 - samples/sec: 1415.64 - lr: 0.000040 - momentum: 0.000000
122
+ 2024-03-26 11:01:07,725 epoch 3 - iter 48/48 - loss 0.20307138 - time (sec): 24.32 - samples/sec: 1417.29 - lr: 0.000039 - momentum: 0.000000
123
+ 2024-03-26 11:01:07,725 ----------------------------------------------------------------------------------------------------
124
+ 2024-03-26 11:01:07,725 EPOCH 3 done: loss 0.2031 - lr: 0.000039
125
+ 2024-03-26 11:01:08,671 DEV : loss 0.25678685307502747 - f1-score (micro avg) 0.8519
126
+ 2024-03-26 11:01:08,672 saving best model
127
+ 2024-03-26 11:01:09,109 ----------------------------------------------------------------------------------------------------
128
+ 2024-03-26 11:01:10,611 epoch 4 - iter 4/48 - loss 0.12080968 - time (sec): 1.50 - samples/sec: 1816.16 - lr: 0.000039 - momentum: 0.000000
129
+ 2024-03-26 11:01:13,125 epoch 4 - iter 8/48 - loss 0.15034122 - time (sec): 4.01 - samples/sec: 1429.16 - lr: 0.000038 - momentum: 0.000000
130
+ 2024-03-26 11:01:15,244 epoch 4 - iter 12/48 - loss 0.16078746 - time (sec): 6.13 - samples/sec: 1424.34 - lr: 0.000038 - momentum: 0.000000
131
+ 2024-03-26 11:01:17,467 epoch 4 - iter 16/48 - loss 0.14298013 - time (sec): 8.36 - samples/sec: 1432.75 - lr: 0.000037 - momentum: 0.000000
132
+ 2024-03-26 11:01:20,491 epoch 4 - iter 20/48 - loss 0.13519036 - time (sec): 11.38 - samples/sec: 1360.97 - lr: 0.000037 - momentum: 0.000000
133
+ 2024-03-26 11:01:21,975 epoch 4 - iter 24/48 - loss 0.13663630 - time (sec): 12.87 - samples/sec: 1400.91 - lr: 0.000036 - momentum: 0.000000
134
+ 2024-03-26 11:01:23,514 epoch 4 - iter 28/48 - loss 0.13658070 - time (sec): 14.40 - samples/sec: 1439.83 - lr: 0.000036 - momentum: 0.000000
135
+ 2024-03-26 11:01:26,144 epoch 4 - iter 32/48 - loss 0.13666749 - time (sec): 17.03 - samples/sec: 1422.91 - lr: 0.000035 - momentum: 0.000000
136
+ 2024-03-26 11:01:27,183 epoch 4 - iter 36/48 - loss 0.13693895 - time (sec): 18.07 - samples/sec: 1470.16 - lr: 0.000035 - momentum: 0.000000
137
+ 2024-03-26 11:01:29,617 epoch 4 - iter 40/48 - loss 0.13278247 - time (sec): 20.51 - samples/sec: 1424.10 - lr: 0.000034 - momentum: 0.000000
138
+ 2024-03-26 11:01:31,480 epoch 4 - iter 44/48 - loss 0.13260496 - time (sec): 22.37 - samples/sec: 1442.33 - lr: 0.000034 - momentum: 0.000000
139
+ 2024-03-26 11:01:32,883 epoch 4 - iter 48/48 - loss 0.13127512 - time (sec): 23.77 - samples/sec: 1450.02 - lr: 0.000034 - momentum: 0.000000
140
+ 2024-03-26 11:01:32,884 ----------------------------------------------------------------------------------------------------
141
+ 2024-03-26 11:01:32,884 EPOCH 4 done: loss 0.1313 - lr: 0.000034
142
+ 2024-03-26 11:01:33,832 DEV : loss 0.21583451330661774 - f1-score (micro avg) 0.8756
143
+ 2024-03-26 11:01:33,833 saving best model
144
+ 2024-03-26 11:01:34,279 ----------------------------------------------------------------------------------------------------
145
+ 2024-03-26 11:01:36,221 epoch 5 - iter 4/48 - loss 0.10870825 - time (sec): 1.94 - samples/sec: 1437.93 - lr: 0.000033 - momentum: 0.000000
146
+ 2024-03-26 11:01:38,764 epoch 5 - iter 8/48 - loss 0.09524973 - time (sec): 4.48 - samples/sec: 1324.28 - lr: 0.000033 - momentum: 0.000000
147
+ 2024-03-26 11:01:40,833 epoch 5 - iter 12/48 - loss 0.09712497 - time (sec): 6.55 - samples/sec: 1307.49 - lr: 0.000032 - momentum: 0.000000
148
+ 2024-03-26 11:01:42,897 epoch 5 - iter 16/48 - loss 0.09416056 - time (sec): 8.62 - samples/sec: 1340.70 - lr: 0.000032 - momentum: 0.000000
149
+ 2024-03-26 11:01:44,870 epoch 5 - iter 20/48 - loss 0.09859046 - time (sec): 10.59 - samples/sec: 1351.47 - lr: 0.000031 - momentum: 0.000000
150
+ 2024-03-26 11:01:46,427 epoch 5 - iter 24/48 - loss 0.10256071 - time (sec): 12.15 - samples/sec: 1400.37 - lr: 0.000031 - momentum: 0.000000
151
+ 2024-03-26 11:01:48,743 epoch 5 - iter 28/48 - loss 0.10312729 - time (sec): 14.46 - samples/sec: 1392.86 - lr: 0.000030 - momentum: 0.000000
152
+ 2024-03-26 11:01:51,403 epoch 5 - iter 32/48 - loss 0.10114194 - time (sec): 17.12 - samples/sec: 1382.56 - lr: 0.000030 - momentum: 0.000000
153
+ 2024-03-26 11:01:53,777 epoch 5 - iter 36/48 - loss 0.09523322 - time (sec): 19.50 - samples/sec: 1391.93 - lr: 0.000029 - momentum: 0.000000
154
+ 2024-03-26 11:01:54,702 epoch 5 - iter 40/48 - loss 0.09494868 - time (sec): 20.42 - samples/sec: 1432.80 - lr: 0.000029 - momentum: 0.000000
155
+ 2024-03-26 11:01:57,363 epoch 5 - iter 44/48 - loss 0.09114674 - time (sec): 23.08 - samples/sec: 1402.97 - lr: 0.000029 - momentum: 0.000000
156
+ 2024-03-26 11:01:58,852 epoch 5 - iter 48/48 - loss 0.09130317 - time (sec): 24.57 - samples/sec: 1402.93 - lr: 0.000028 - momentum: 0.000000
157
+ 2024-03-26 11:01:58,853 ----------------------------------------------------------------------------------------------------
158
+ 2024-03-26 11:01:58,853 EPOCH 5 done: loss 0.0913 - lr: 0.000028
159
+ 2024-03-26 11:01:59,809 DEV : loss 0.19779938459396362 - f1-score (micro avg) 0.8914
160
+ 2024-03-26 11:01:59,812 saving best model
161
+ 2024-03-26 11:02:00,262 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 11:02:02,268 epoch 6 - iter 4/48 - loss 0.05285658 - time (sec): 2.01 - samples/sec: 1318.38 - lr: 0.000028 - momentum: 0.000000
163
+ 2024-03-26 11:02:04,480 epoch 6 - iter 8/48 - loss 0.07094565 - time (sec): 4.22 - samples/sec: 1311.76 - lr: 0.000027 - momentum: 0.000000
164
+ 2024-03-26 11:02:06,334 epoch 6 - iter 12/48 - loss 0.07133832 - time (sec): 6.07 - samples/sec: 1423.40 - lr: 0.000027 - momentum: 0.000000
165
+ 2024-03-26 11:02:08,617 epoch 6 - iter 16/48 - loss 0.07133402 - time (sec): 8.35 - samples/sec: 1375.26 - lr: 0.000026 - momentum: 0.000000
166
+ 2024-03-26 11:02:10,436 epoch 6 - iter 20/48 - loss 0.07725707 - time (sec): 10.17 - samples/sec: 1379.46 - lr: 0.000026 - momentum: 0.000000
167
+ 2024-03-26 11:02:12,944 epoch 6 - iter 24/48 - loss 0.07565556 - time (sec): 12.68 - samples/sec: 1357.85 - lr: 0.000025 - momentum: 0.000000
168
+ 2024-03-26 11:02:14,899 epoch 6 - iter 28/48 - loss 0.07510084 - time (sec): 14.64 - samples/sec: 1351.33 - lr: 0.000025 - momentum: 0.000000
169
+ 2024-03-26 11:02:17,426 epoch 6 - iter 32/48 - loss 0.07424382 - time (sec): 17.16 - samples/sec: 1331.71 - lr: 0.000024 - momentum: 0.000000
170
+ 2024-03-26 11:02:20,980 epoch 6 - iter 36/48 - loss 0.06879978 - time (sec): 20.72 - samples/sec: 1287.17 - lr: 0.000024 - momentum: 0.000000
171
+ 2024-03-26 11:02:22,685 epoch 6 - iter 40/48 - loss 0.06691408 - time (sec): 22.42 - samples/sec: 1317.93 - lr: 0.000023 - momentum: 0.000000
172
+ 2024-03-26 11:02:24,577 epoch 6 - iter 44/48 - loss 0.06499311 - time (sec): 24.31 - samples/sec: 1320.84 - lr: 0.000023 - momentum: 0.000000
173
+ 2024-03-26 11:02:25,873 epoch 6 - iter 48/48 - loss 0.06648827 - time (sec): 25.61 - samples/sec: 1346.03 - lr: 0.000023 - momentum: 0.000000
174
+ 2024-03-26 11:02:25,873 ----------------------------------------------------------------------------------------------------
175
+ 2024-03-26 11:02:25,873 EPOCH 6 done: loss 0.0665 - lr: 0.000023
176
+ 2024-03-26 11:02:26,828 DEV : loss 0.1999371349811554 - f1-score (micro avg) 0.9161
177
+ 2024-03-26 11:02:26,830 saving best model
178
+ 2024-03-26 11:02:27,281 ----------------------------------------------------------------------------------------------------
179
+ 2024-03-26 11:02:28,971 epoch 7 - iter 4/48 - loss 0.06036740 - time (sec): 1.69 - samples/sec: 1629.41 - lr: 0.000022 - momentum: 0.000000
180
+ 2024-03-26 11:02:31,071 epoch 7 - iter 8/48 - loss 0.06185033 - time (sec): 3.79 - samples/sec: 1420.34 - lr: 0.000022 - momentum: 0.000000
181
+ 2024-03-26 11:02:33,357 epoch 7 - iter 12/48 - loss 0.06731893 - time (sec): 6.07 - samples/sec: 1367.20 - lr: 0.000021 - momentum: 0.000000
182
+ 2024-03-26 11:02:35,999 epoch 7 - iter 16/48 - loss 0.05862319 - time (sec): 8.71 - samples/sec: 1324.52 - lr: 0.000021 - momentum: 0.000000
183
+ 2024-03-26 11:02:38,385 epoch 7 - iter 20/48 - loss 0.05493743 - time (sec): 11.10 - samples/sec: 1316.65 - lr: 0.000020 - momentum: 0.000000
184
+ 2024-03-26 11:02:39,763 epoch 7 - iter 24/48 - loss 0.05293912 - time (sec): 12.48 - samples/sec: 1370.98 - lr: 0.000020 - momentum: 0.000000
185
+ 2024-03-26 11:02:41,198 epoch 7 - iter 28/48 - loss 0.05212759 - time (sec): 13.91 - samples/sec: 1433.60 - lr: 0.000019 - momentum: 0.000000
186
+ 2024-03-26 11:02:43,213 epoch 7 - iter 32/48 - loss 0.05081756 - time (sec): 15.93 - samples/sec: 1423.96 - lr: 0.000019 - momentum: 0.000000
187
+ 2024-03-26 11:02:45,413 epoch 7 - iter 36/48 - loss 0.04903245 - time (sec): 18.13 - samples/sec: 1412.86 - lr: 0.000018 - momentum: 0.000000
188
+ 2024-03-26 11:02:47,992 epoch 7 - iter 40/48 - loss 0.05091923 - time (sec): 20.71 - samples/sec: 1388.02 - lr: 0.000018 - momentum: 0.000000
189
+ 2024-03-26 11:02:49,872 epoch 7 - iter 44/48 - loss 0.05031687 - time (sec): 22.59 - samples/sec: 1403.46 - lr: 0.000017 - momentum: 0.000000
190
+ 2024-03-26 11:02:51,872 epoch 7 - iter 48/48 - loss 0.04903771 - time (sec): 24.59 - samples/sec: 1402.03 - lr: 0.000017 - momentum: 0.000000
191
+ 2024-03-26 11:02:51,872 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 11:02:51,872 EPOCH 7 done: loss 0.0490 - lr: 0.000017
193
+ 2024-03-26 11:02:52,826 DEV : loss 0.19628769159317017 - f1-score (micro avg) 0.91
194
+ 2024-03-26 11:02:52,829 ----------------------------------------------------------------------------------------------------
195
+ 2024-03-26 11:02:54,902 epoch 8 - iter 4/48 - loss 0.03574904 - time (sec): 2.07 - samples/sec: 1304.28 - lr: 0.000017 - momentum: 0.000000
196
+ 2024-03-26 11:02:57,726 epoch 8 - iter 8/48 - loss 0.03594155 - time (sec): 4.90 - samples/sec: 1134.80 - lr: 0.000016 - momentum: 0.000000
197
+ 2024-03-26 11:02:59,057 epoch 8 - iter 12/48 - loss 0.03729970 - time (sec): 6.23 - samples/sec: 1281.91 - lr: 0.000016 - momentum: 0.000000
198
+ 2024-03-26 11:03:01,523 epoch 8 - iter 16/48 - loss 0.04291151 - time (sec): 8.69 - samples/sec: 1294.85 - lr: 0.000015 - momentum: 0.000000
199
+ 2024-03-26 11:03:04,125 epoch 8 - iter 20/48 - loss 0.03659224 - time (sec): 11.30 - samples/sec: 1333.96 - lr: 0.000015 - momentum: 0.000000
200
+ 2024-03-26 11:03:05,469 epoch 8 - iter 24/48 - loss 0.03664124 - time (sec): 12.64 - samples/sec: 1408.00 - lr: 0.000014 - momentum: 0.000000
201
+ 2024-03-26 11:03:08,835 epoch 8 - iter 28/48 - loss 0.03886089 - time (sec): 16.01 - samples/sec: 1363.36 - lr: 0.000014 - momentum: 0.000000
202
+ 2024-03-26 11:03:10,860 epoch 8 - iter 32/48 - loss 0.03830054 - time (sec): 18.03 - samples/sec: 1367.36 - lr: 0.000013 - momentum: 0.000000
203
+ 2024-03-26 11:03:11,922 epoch 8 - iter 36/48 - loss 0.03798648 - time (sec): 19.09 - samples/sec: 1406.43 - lr: 0.000013 - momentum: 0.000000
204
+ 2024-03-26 11:03:13,634 epoch 8 - iter 40/48 - loss 0.03809773 - time (sec): 20.80 - samples/sec: 1404.82 - lr: 0.000012 - momentum: 0.000000
205
+ 2024-03-26 11:03:15,288 epoch 8 - iter 44/48 - loss 0.03863525 - time (sec): 22.46 - samples/sec: 1422.70 - lr: 0.000012 - momentum: 0.000000
206
+ 2024-03-26 11:03:17,312 epoch 8 - iter 48/48 - loss 0.03975429 - time (sec): 24.48 - samples/sec: 1408.02 - lr: 0.000011 - momentum: 0.000000
207
+ 2024-03-26 11:03:17,312 ----------------------------------------------------------------------------------------------------
208
+ 2024-03-26 11:03:17,312 EPOCH 8 done: loss 0.0398 - lr: 0.000011
209
+ 2024-03-26 11:03:18,283 DEV : loss 0.19287405908107758 - f1-score (micro avg) 0.9269
210
+ 2024-03-26 11:03:18,284 saving best model
211
+ 2024-03-26 11:03:18,696 ----------------------------------------------------------------------------------------------------
212
+ 2024-03-26 11:03:20,629 epoch 9 - iter 4/48 - loss 0.01911719 - time (sec): 1.93 - samples/sec: 1386.69 - lr: 0.000011 - momentum: 0.000000
213
+ 2024-03-26 11:03:23,880 epoch 9 - iter 8/48 - loss 0.01246336 - time (sec): 5.18 - samples/sec: 1204.95 - lr: 0.000011 - momentum: 0.000000
214
+ 2024-03-26 11:03:25,618 epoch 9 - iter 12/48 - loss 0.01953089 - time (sec): 6.92 - samples/sec: 1255.75 - lr: 0.000010 - momentum: 0.000000
215
+ 2024-03-26 11:03:27,891 epoch 9 - iter 16/48 - loss 0.02215764 - time (sec): 9.19 - samples/sec: 1253.18 - lr: 0.000010 - momentum: 0.000000
216
+ 2024-03-26 11:03:30,272 epoch 9 - iter 20/48 - loss 0.02954547 - time (sec): 11.57 - samples/sec: 1278.31 - lr: 0.000009 - momentum: 0.000000
217
+ 2024-03-26 11:03:32,531 epoch 9 - iter 24/48 - loss 0.03008158 - time (sec): 13.83 - samples/sec: 1292.82 - lr: 0.000009 - momentum: 0.000000
218
+ 2024-03-26 11:03:34,919 epoch 9 - iter 28/48 - loss 0.02806782 - time (sec): 16.22 - samples/sec: 1292.06 - lr: 0.000008 - momentum: 0.000000
219
+ 2024-03-26 11:03:37,371 epoch 9 - iter 32/48 - loss 0.02822729 - time (sec): 18.67 - samples/sec: 1285.90 - lr: 0.000008 - momentum: 0.000000
220
+ 2024-03-26 11:03:39,285 epoch 9 - iter 36/48 - loss 0.03078142 - time (sec): 20.59 - samples/sec: 1300.40 - lr: 0.000007 - momentum: 0.000000
221
+ 2024-03-26 11:03:41,552 epoch 9 - iter 40/48 - loss 0.03147072 - time (sec): 22.86 - samples/sec: 1290.12 - lr: 0.000007 - momentum: 0.000000
222
+ 2024-03-26 11:03:43,705 epoch 9 - iter 44/48 - loss 0.03087065 - time (sec): 25.01 - samples/sec: 1303.67 - lr: 0.000006 - momentum: 0.000000
223
+ 2024-03-26 11:03:44,519 epoch 9 - iter 48/48 - loss 0.03185010 - time (sec): 25.82 - samples/sec: 1335.01 - lr: 0.000006 - momentum: 0.000000
224
+ 2024-03-26 11:03:44,519 ----------------------------------------------------------------------------------------------------
225
+ 2024-03-26 11:03:44,519 EPOCH 9 done: loss 0.0319 - lr: 0.000006
226
+ 2024-03-26 11:03:45,484 DEV : loss 0.19984783232212067 - f1-score (micro avg) 0.9272
227
+ 2024-03-26 11:03:45,485 saving best model
228
+ 2024-03-26 11:03:46,030 ----------------------------------------------------------------------------------------------------
229
+ 2024-03-26 11:03:47,843 epoch 10 - iter 4/48 - loss 0.01174329 - time (sec): 1.81 - samples/sec: 1450.44 - lr: 0.000006 - momentum: 0.000000
230
+ 2024-03-26 11:03:49,911 epoch 10 - iter 8/48 - loss 0.02116348 - time (sec): 3.88 - samples/sec: 1427.87 - lr: 0.000005 - momentum: 0.000000
231
+ 2024-03-26 11:03:52,585 epoch 10 - iter 12/48 - loss 0.02314468 - time (sec): 6.55 - samples/sec: 1331.47 - lr: 0.000005 - momentum: 0.000000
232
+ 2024-03-26 11:03:54,534 epoch 10 - iter 16/48 - loss 0.02792261 - time (sec): 8.50 - samples/sec: 1349.10 - lr: 0.000004 - momentum: 0.000000
233
+ 2024-03-26 11:03:56,483 epoch 10 - iter 20/48 - loss 0.02603172 - time (sec): 10.45 - samples/sec: 1384.04 - lr: 0.000004 - momentum: 0.000000
234
+ 2024-03-26 11:03:58,175 epoch 10 - iter 24/48 - loss 0.03120182 - time (sec): 12.14 - samples/sec: 1396.51 - lr: 0.000003 - momentum: 0.000000
235
+ 2024-03-26 11:04:00,003 epoch 10 - iter 28/48 - loss 0.02955069 - time (sec): 13.97 - samples/sec: 1416.07 - lr: 0.000003 - momentum: 0.000000
236
+ 2024-03-26 11:04:01,231 epoch 10 - iter 32/48 - loss 0.02961233 - time (sec): 15.20 - samples/sec: 1448.94 - lr: 0.000002 - momentum: 0.000000
237
+ 2024-03-26 11:04:04,310 epoch 10 - iter 36/48 - loss 0.02651203 - time (sec): 18.28 - samples/sec: 1401.24 - lr: 0.000002 - momentum: 0.000000
238
+ 2024-03-26 11:04:07,199 epoch 10 - iter 40/48 - loss 0.02941146 - time (sec): 21.17 - samples/sec: 1373.80 - lr: 0.000001 - momentum: 0.000000
239
+ 2024-03-26 11:04:10,009 epoch 10 - iter 44/48 - loss 0.02745505 - time (sec): 23.98 - samples/sec: 1346.36 - lr: 0.000001 - momentum: 0.000000
240
+ 2024-03-26 11:04:11,645 epoch 10 - iter 48/48 - loss 0.02670516 - time (sec): 25.61 - samples/sec: 1345.79 - lr: 0.000000 - momentum: 0.000000
241
+ 2024-03-26 11:04:11,646 ----------------------------------------------------------------------------------------------------
242
+ 2024-03-26 11:04:11,646 EPOCH 10 done: loss 0.0267 - lr: 0.000000
243
+ 2024-03-26 11:04:12,623 DEV : loss 0.19916442036628723 - f1-score (micro avg) 0.9316
244
+ 2024-03-26 11:04:12,624 saving best model
245
+ 2024-03-26 11:04:13,361 ----------------------------------------------------------------------------------------------------
246
+ 2024-03-26 11:04:13,362 Loading model from best epoch ...
247
+ 2024-03-26 11:04:14,266 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 11:04:15,056
249
+ Results:
250
+ - F-score (micro) 0.9173
251
+ - F-score (macro) 0.697
252
+ - Accuracy 0.8496
253
+
254
+ By class:
255
+ precision recall f1-score support
256
+
257
+ Unternehmen 0.9115 0.8910 0.9011 266
258
+ Auslagerung 0.8842 0.9197 0.9016 249
259
+ Ort 0.9779 0.9925 0.9852 134
260
+ Software 0.0000 0.0000 0.0000 0
261
+
262
+ micro avg 0.9117 0.9230 0.9173 649
263
+ macro avg 0.6934 0.7008 0.6970 649
264
+ weighted avg 0.9147 0.9230 0.9187 649
265
+
266
+ 2024-03-26 11:04:15,056 ----------------------------------------------------------------------------------------------------