Hugging Face's logo

stefan-it
/
flair-co-funer-german_dbmdz_bert_base-bs16-e10-lr3e-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
4ad1f30
•
1 Parent(s): e95ac95

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +264 -0
training.log ADDED
@@ -0,0 +1,264 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-03-26 15:14:34,038 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 15:14:34,038 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 15:14:34,038 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 15:14:34,038 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 15:14:34,038 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 15:14:34,038 Train: 758 sentences
54
+ 2024-03-26 15:14:34,038 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 15:14:34,038 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 15:14:34,038 Training Params:
57
+ 2024-03-26 15:14:34,038 - learning_rate: "3e-05"
58
+ 2024-03-26 15:14:34,038 - mini_batch_size: "16"
59
+ 2024-03-26 15:14:34,038 - max_epochs: "10"
60
+ 2024-03-26 15:14:34,038 - shuffle: "True"
61
+ 2024-03-26 15:14:34,038 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 15:14:34,039 Plugins:
63
+ 2024-03-26 15:14:34,039 - TensorboardLogger
64
+ 2024-03-26 15:14:34,039 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 15:14:34,039 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 15:14:34,039 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 15:14:34,039 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 15:14:34,039 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 15:14:34,039 Computation:
70
+ 2024-03-26 15:14:34,039 - compute on device: cuda:0
71
+ 2024-03-26 15:14:34,039 - embedding storage: none
72
+ 2024-03-26 15:14:34,039 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 15:14:34,039 Model training base path: "flair-co-funer-german_dbmdz_bert_base-bs16-e10-lr3e-05-1"
74
+ 2024-03-26 15:14:34,039 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 15:14:34,039 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 15:14:34,039 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 15:14:36,089 epoch 1 - iter 4/48 - loss 3.19165048 - time (sec): 2.05 - samples/sec: 1324.66 - lr: 0.000002 - momentum: 0.000000
78
+ 2024-03-26 15:14:37,340 epoch 1 - iter 8/48 - loss 3.12589882 - time (sec): 3.30 - samples/sec: 1632.73 - lr: 0.000004 - momentum: 0.000000
79
+ 2024-03-26 15:14:40,335 epoch 1 - iter 12/48 - loss 3.01481360 - time (sec): 6.30 - samples/sec: 1382.17 - lr: 0.000007 - momentum: 0.000000
80
+ 2024-03-26 15:14:43,425 epoch 1 - iter 16/48 - loss 2.91594700 - time (sec): 9.39 - samples/sec: 1299.12 - lr: 0.000009 - momentum: 0.000000
81
+ 2024-03-26 15:14:45,824 epoch 1 - iter 20/48 - loss 2.78008767 - time (sec): 11.79 - samples/sec: 1305.20 - lr: 0.000012 - momentum: 0.000000
82
+ 2024-03-26 15:14:47,491 epoch 1 - iter 24/48 - loss 2.64309938 - time (sec): 13.45 - samples/sec: 1355.67 - lr: 0.000014 - momentum: 0.000000
83
+ 2024-03-26 15:14:49,028 epoch 1 - iter 28/48 - loss 2.53140637 - time (sec): 14.99 - samples/sec: 1381.13 - lr: 0.000017 - momentum: 0.000000
84
+ 2024-03-26 15:14:51,057 epoch 1 - iter 32/48 - loss 2.43079271 - time (sec): 17.02 - samples/sec: 1388.85 - lr: 0.000019 - momentum: 0.000000
85
+ 2024-03-26 15:14:52,008 epoch 1 - iter 36/48 - loss 2.34988494 - time (sec): 17.97 - samples/sec: 1449.66 - lr: 0.000022 - momentum: 0.000000
86
+ 2024-03-26 15:14:53,905 epoch 1 - iter 40/48 - loss 2.25808154 - time (sec): 19.87 - samples/sec: 1465.66 - lr: 0.000024 - momentum: 0.000000
87
+ 2024-03-26 15:14:55,848 epoch 1 - iter 44/48 - loss 2.17449596 - time (sec): 21.81 - samples/sec: 1452.64 - lr: 0.000027 - momentum: 0.000000
88
+ 2024-03-26 15:14:57,292 epoch 1 - iter 48/48 - loss 2.07749518 - time (sec): 23.25 - samples/sec: 1482.45 - lr: 0.000029 - momentum: 0.000000
89
+ 2024-03-26 15:14:57,293 ----------------------------------------------------------------------------------------------------
90
+ 2024-03-26 15:14:57,293 EPOCH 1 done: loss 2.0775 - lr: 0.000029
91
+ 2024-03-26 15:14:58,074 DEV : loss 0.7547357678413391 - f1-score (micro avg) 0.4587
92
+ 2024-03-26 15:14:58,075 saving best model
93
+ 2024-03-26 15:14:58,382 ----------------------------------------------------------------------------------------------------
94
+ 2024-03-26 15:15:00,772 epoch 2 - iter 4/48 - loss 0.87835898 - time (sec): 2.39 - samples/sec: 1297.92 - lr: 0.000030 - momentum: 0.000000
95
+ 2024-03-26 15:15:02,774 epoch 2 - iter 8/48 - loss 0.82924125 - time (sec): 4.39 - samples/sec: 1505.55 - lr: 0.000030 - momentum: 0.000000
96
+ 2024-03-26 15:15:04,961 epoch 2 - iter 12/48 - loss 0.78307482 - time (sec): 6.58 - samples/sec: 1407.36 - lr: 0.000029 - momentum: 0.000000
97
+ 2024-03-26 15:15:06,957 epoch 2 - iter 16/48 - loss 0.73793447 - time (sec): 8.57 - samples/sec: 1389.69 - lr: 0.000029 - momentum: 0.000000
98
+ 2024-03-26 15:15:09,016 epoch 2 - iter 20/48 - loss 0.69795767 - time (sec): 10.63 - samples/sec: 1410.28 - lr: 0.000029 - momentum: 0.000000
99
+ 2024-03-26 15:15:12,087 epoch 2 - iter 24/48 - loss 0.64550357 - time (sec): 13.70 - samples/sec: 1350.10 - lr: 0.000028 - momentum: 0.000000
100
+ 2024-03-26 15:15:14,380 epoch 2 - iter 28/48 - loss 0.62937634 - time (sec): 16.00 - samples/sec: 1346.53 - lr: 0.000028 - momentum: 0.000000
101
+ 2024-03-26 15:15:16,052 epoch 2 - iter 32/48 - loss 0.60969033 - time (sec): 17.67 - samples/sec: 1365.46 - lr: 0.000028 - momentum: 0.000000
102
+ 2024-03-26 15:15:17,057 epoch 2 - iter 36/48 - loss 0.59690634 - time (sec): 18.67 - samples/sec: 1416.53 - lr: 0.000028 - momentum: 0.000000
103
+ 2024-03-26 15:15:18,872 epoch 2 - iter 40/48 - loss 0.58182916 - time (sec): 20.49 - samples/sec: 1434.76 - lr: 0.000027 - momentum: 0.000000
104
+ 2024-03-26 15:15:20,859 epoch 2 - iter 44/48 - loss 0.56921362 - time (sec): 22.48 - samples/sec: 1428.49 - lr: 0.000027 - momentum: 0.000000
105
+ 2024-03-26 15:15:22,282 epoch 2 - iter 48/48 - loss 0.55879090 - time (sec): 23.90 - samples/sec: 1442.35 - lr: 0.000027 - momentum: 0.000000
106
+ 2024-03-26 15:15:22,283 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 15:15:22,283 EPOCH 2 done: loss 0.5588 - lr: 0.000027
108
+ 2024-03-26 15:15:23,170 DEV : loss 0.3483647108078003 - f1-score (micro avg) 0.7525
109
+ 2024-03-26 15:15:23,171 saving best model
110
+ 2024-03-26 15:15:23,642 ----------------------------------------------------------------------------------------------------
111
+ 2024-03-26 15:15:26,131 epoch 3 - iter 4/48 - loss 0.42554044 - time (sec): 2.49 - samples/sec: 1226.51 - lr: 0.000026 - momentum: 0.000000
112
+ 2024-03-26 15:15:27,917 epoch 3 - iter 8/48 - loss 0.36736974 - time (sec): 4.27 - samples/sec: 1372.57 - lr: 0.000026 - momentum: 0.000000
113
+ 2024-03-26 15:15:29,681 epoch 3 - iter 12/48 - loss 0.37982842 - time (sec): 6.04 - samples/sec: 1455.20 - lr: 0.000026 - momentum: 0.000000
114
+ 2024-03-26 15:15:32,017 epoch 3 - iter 16/48 - loss 0.34862313 - time (sec): 8.37 - samples/sec: 1458.32 - lr: 0.000026 - momentum: 0.000000
115
+ 2024-03-26 15:15:33,439 epoch 3 - iter 20/48 - loss 0.35600240 - time (sec): 9.80 - samples/sec: 1510.45 - lr: 0.000025 - momentum: 0.000000
116
+ 2024-03-26 15:15:36,314 epoch 3 - iter 24/48 - loss 0.33051180 - time (sec): 12.67 - samples/sec: 1492.46 - lr: 0.000025 - momentum: 0.000000
117
+ 2024-03-26 15:15:37,063 epoch 3 - iter 28/48 - loss 0.31909097 - time (sec): 13.42 - samples/sec: 1567.77 - lr: 0.000025 - momentum: 0.000000
118
+ 2024-03-26 15:15:39,561 epoch 3 - iter 32/48 - loss 0.30474272 - time (sec): 15.92 - samples/sec: 1509.24 - lr: 0.000025 - momentum: 0.000000
119
+ 2024-03-26 15:15:41,525 epoch 3 - iter 36/48 - loss 0.29293187 - time (sec): 17.88 - samples/sec: 1501.91 - lr: 0.000024 - momentum: 0.000000
120
+ 2024-03-26 15:15:43,381 epoch 3 - iter 40/48 - loss 0.29426814 - time (sec): 19.74 - samples/sec: 1490.71 - lr: 0.000024 - momentum: 0.000000
121
+ 2024-03-26 15:15:45,460 epoch 3 - iter 44/48 - loss 0.28452650 - time (sec): 21.82 - samples/sec: 1494.96 - lr: 0.000024 - momentum: 0.000000
122
+ 2024-03-26 15:15:46,655 epoch 3 - iter 48/48 - loss 0.28252752 - time (sec): 23.01 - samples/sec: 1497.98 - lr: 0.000023 - momentum: 0.000000
123
+ 2024-03-26 15:15:46,655 ----------------------------------------------------------------------------------------------------
124
+ 2024-03-26 15:15:46,655 EPOCH 3 done: loss 0.2825 - lr: 0.000023
125
+ 2024-03-26 15:15:47,539 DEV : loss 0.2684253454208374 - f1-score (micro avg) 0.8406
126
+ 2024-03-26 15:15:47,540 saving best model
127
+ 2024-03-26 15:15:48,027 ----------------------------------------------------------------------------------------------------
128
+ 2024-03-26 15:15:49,485 epoch 4 - iter 4/48 - loss 0.21880852 - time (sec): 1.46 - samples/sec: 1871.45 - lr: 0.000023 - momentum: 0.000000
129
+ 2024-03-26 15:15:51,835 epoch 4 - iter 8/48 - loss 0.19646105 - time (sec): 3.81 - samples/sec: 1506.99 - lr: 0.000023 - momentum: 0.000000
130
+ 2024-03-26 15:15:53,880 epoch 4 - iter 12/48 - loss 0.20673784 - time (sec): 5.85 - samples/sec: 1493.01 - lr: 0.000023 - momentum: 0.000000
131
+ 2024-03-26 15:15:55,985 epoch 4 - iter 16/48 - loss 0.18724788 - time (sec): 7.96 - samples/sec: 1504.85 - lr: 0.000022 - momentum: 0.000000
132
+ 2024-03-26 15:15:58,933 epoch 4 - iter 20/48 - loss 0.17809836 - time (sec): 10.91 - samples/sec: 1420.35 - lr: 0.000022 - momentum: 0.000000
133
+ 2024-03-26 15:16:00,315 epoch 4 - iter 24/48 - loss 0.18212376 - time (sec): 12.29 - samples/sec: 1466.78 - lr: 0.000022 - momentum: 0.000000
134
+ 2024-03-26 15:16:01,789 epoch 4 - iter 28/48 - loss 0.17976411 - time (sec): 13.76 - samples/sec: 1507.07 - lr: 0.000022 - momentum: 0.000000
135
+ 2024-03-26 15:16:04,194 epoch 4 - iter 32/48 - loss 0.18600193 - time (sec): 16.17 - samples/sec: 1499.26 - lr: 0.000021 - momentum: 0.000000
136
+ 2024-03-26 15:16:05,152 epoch 4 - iter 36/48 - loss 0.18393574 - time (sec): 17.12 - samples/sec: 1551.60 - lr: 0.000021 - momentum: 0.000000
137
+ 2024-03-26 15:16:07,462 epoch 4 - iter 40/48 - loss 0.17961505 - time (sec): 19.43 - samples/sec: 1502.79 - lr: 0.000021 - momentum: 0.000000
138
+ 2024-03-26 15:16:09,207 epoch 4 - iter 44/48 - loss 0.17919507 - time (sec): 21.18 - samples/sec: 1523.47 - lr: 0.000020 - momentum: 0.000000
139
+ 2024-03-26 15:16:10,522 epoch 4 - iter 48/48 - loss 0.17788382 - time (sec): 22.49 - samples/sec: 1532.47 - lr: 0.000020 - momentum: 0.000000
140
+ 2024-03-26 15:16:10,522 ----------------------------------------------------------------------------------------------------
141
+ 2024-03-26 15:16:10,522 EPOCH 4 done: loss 0.1779 - lr: 0.000020
142
+ 2024-03-26 15:16:11,426 DEV : loss 0.22643746435642242 - f1-score (micro avg) 0.8702
143
+ 2024-03-26 15:16:11,427 saving best model
144
+ 2024-03-26 15:16:11,888 ----------------------------------------------------------------------------------------------------
145
+ 2024-03-26 15:16:13,757 epoch 5 - iter 4/48 - loss 0.19167230 - time (sec): 1.87 - samples/sec: 1493.04 - lr: 0.000020 - momentum: 0.000000
146
+ 2024-03-26 15:16:16,134 epoch 5 - iter 8/48 - loss 0.14926396 - time (sec): 4.25 - samples/sec: 1398.45 - lr: 0.000020 - momentum: 0.000000
147
+ 2024-03-26 15:16:18,047 epoch 5 - iter 12/48 - loss 0.14941697 - time (sec): 6.16 - samples/sec: 1391.13 - lr: 0.000019 - momentum: 0.000000
148
+ 2024-03-26 15:16:20,001 epoch 5 - iter 16/48 - loss 0.14589982 - time (sec): 8.11 - samples/sec: 1423.97 - lr: 0.000019 - momentum: 0.000000
149
+ 2024-03-26 15:16:21,862 epoch 5 - iter 20/48 - loss 0.14536738 - time (sec): 9.97 - samples/sec: 1434.95 - lr: 0.000019 - momentum: 0.000000
150
+ 2024-03-26 15:16:23,326 epoch 5 - iter 24/48 - loss 0.14909722 - time (sec): 11.44 - samples/sec: 1487.13 - lr: 0.000018 - momentum: 0.000000
151
+ 2024-03-26 15:16:25,465 epoch 5 - iter 28/48 - loss 0.14748304 - time (sec): 13.58 - samples/sec: 1483.73 - lr: 0.000018 - momentum: 0.000000
152
+ 2024-03-26 15:16:28,010 epoch 5 - iter 32/48 - loss 0.14274256 - time (sec): 16.12 - samples/sec: 1468.41 - lr: 0.000018 - momentum: 0.000000
153
+ 2024-03-26 15:16:30,322 epoch 5 - iter 36/48 - loss 0.13498729 - time (sec): 18.43 - samples/sec: 1472.21 - lr: 0.000018 - momentum: 0.000000
154
+ 2024-03-26 15:16:31,191 epoch 5 - iter 40/48 - loss 0.13651791 - time (sec): 19.30 - samples/sec: 1515.82 - lr: 0.000017 - momentum: 0.000000
155
+ 2024-03-26 15:16:33,755 epoch 5 - iter 44/48 - loss 0.13118301 - time (sec): 21.87 - samples/sec: 1481.02 - lr: 0.000017 - momentum: 0.000000
156
+ 2024-03-26 15:16:35,195 epoch 5 - iter 48/48 - loss 0.13075996 - time (sec): 23.31 - samples/sec: 1479.07 - lr: 0.000017 - momentum: 0.000000
157
+ 2024-03-26 15:16:35,195 ----------------------------------------------------------------------------------------------------
158
+ 2024-03-26 15:16:35,195 EPOCH 5 done: loss 0.1308 - lr: 0.000017
159
+ 2024-03-26 15:16:36,078 DEV : loss 0.21334028244018555 - f1-score (micro avg) 0.8849
160
+ 2024-03-26 15:16:36,079 saving best model
161
+ 2024-03-26 15:16:36,554 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 15:16:38,518 epoch 6 - iter 4/48 - loss 0.07229173 - time (sec): 1.96 - samples/sec: 1347.77 - lr: 0.000017 - momentum: 0.000000
163
+ 2024-03-26 15:16:40,587 epoch 6 - iter 8/48 - loss 0.10943851 - time (sec): 4.03 - samples/sec: 1372.46 - lr: 0.000016 - momentum: 0.000000
164
+ 2024-03-26 15:16:42,367 epoch 6 - iter 12/48 - loss 0.11635493 - time (sec): 5.81 - samples/sec: 1487.23 - lr: 0.000016 - momentum: 0.000000
165
+ 2024-03-26 15:16:44,543 epoch 6 - iter 16/48 - loss 0.11534795 - time (sec): 7.99 - samples/sec: 1438.54 - lr: 0.000016 - momentum: 0.000000
166
+ 2024-03-26 15:16:46,251 epoch 6 - iter 20/48 - loss 0.11677616 - time (sec): 9.70 - samples/sec: 1447.40 - lr: 0.000015 - momentum: 0.000000
167
+ 2024-03-26 15:16:48,639 epoch 6 - iter 24/48 - loss 0.11214852 - time (sec): 12.08 - samples/sec: 1425.04 - lr: 0.000015 - momentum: 0.000000
168
+ 2024-03-26 15:16:50,419 epoch 6 - iter 28/48 - loss 0.11277352 - time (sec): 13.86 - samples/sec: 1426.79 - lr: 0.000015 - momentum: 0.000000
169
+ 2024-03-26 15:16:52,810 epoch 6 - iter 32/48 - loss 0.10938620 - time (sec): 16.25 - samples/sec: 1406.26 - lr: 0.000015 - momentum: 0.000000
170
+ 2024-03-26 15:16:56,144 epoch 6 - iter 36/48 - loss 0.10537937 - time (sec): 19.59 - samples/sec: 1361.38 - lr: 0.000014 - momentum: 0.000000
171
+ 2024-03-26 15:16:57,717 epoch 6 - iter 40/48 - loss 0.10289584 - time (sec): 21.16 - samples/sec: 1396.47 - lr: 0.000014 - momentum: 0.000000
172
+ 2024-03-26 15:16:59,502 epoch 6 - iter 44/48 - loss 0.10130647 - time (sec): 22.95 - samples/sec: 1399.57 - lr: 0.000014 - momentum: 0.000000
173
+ 2024-03-26 15:17:00,765 epoch 6 - iter 48/48 - loss 0.10418891 - time (sec): 24.21 - samples/sec: 1423.93 - lr: 0.000014 - momentum: 0.000000
174
+ 2024-03-26 15:17:00,765 ----------------------------------------------------------------------------------------------------
175
+ 2024-03-26 15:17:00,765 EPOCH 6 done: loss 0.1042 - lr: 0.000014
176
+ 2024-03-26 15:17:01,740 DEV : loss 0.20428664982318878 - f1-score (micro avg) 0.8842
177
+ 2024-03-26 15:17:01,741 ----------------------------------------------------------------------------------------------------
178
+ 2024-03-26 15:17:03,355 epoch 7 - iter 4/48 - loss 0.13032170 - time (sec): 1.61 - samples/sec: 1703.68 - lr: 0.000013 - momentum: 0.000000
179
+ 2024-03-26 15:17:05,389 epoch 7 - iter 8/48 - loss 0.10742934 - time (sec): 3.65 - samples/sec: 1474.44 - lr: 0.000013 - momentum: 0.000000
180
+ 2024-03-26 15:17:07,638 epoch 7 - iter 12/48 - loss 0.10136169 - time (sec): 5.90 - samples/sec: 1408.08 - lr: 0.000013 - momentum: 0.000000
181
+ 2024-03-26 15:17:10,171 epoch 7 - iter 16/48 - loss 0.09085061 - time (sec): 8.43 - samples/sec: 1369.30 - lr: 0.000012 - momentum: 0.000000
182
+ 2024-03-26 15:17:12,395 epoch 7 - iter 20/48 - loss 0.08766466 - time (sec): 10.65 - samples/sec: 1372.00 - lr: 0.000012 - momentum: 0.000000
183
+ 2024-03-26 15:17:13,725 epoch 7 - iter 24/48 - loss 0.08553855 - time (sec): 11.98 - samples/sec: 1427.68 - lr: 0.000012 - momentum: 0.000000
184
+ 2024-03-26 15:17:15,105 epoch 7 - iter 28/48 - loss 0.08419102 - time (sec): 13.36 - samples/sec: 1492.63 - lr: 0.000012 - momentum: 0.000000
185
+ 2024-03-26 15:17:17,046 epoch 7 - iter 32/48 - loss 0.08080807 - time (sec): 15.30 - samples/sec: 1481.99 - lr: 0.000011 - momentum: 0.000000
186
+ 2024-03-26 15:17:19,160 epoch 7 - iter 36/48 - loss 0.07770884 - time (sec): 17.42 - samples/sec: 1470.49 - lr: 0.000011 - momentum: 0.000000
187
+ 2024-03-26 15:17:21,575 epoch 7 - iter 40/48 - loss 0.07757463 - time (sec): 19.83 - samples/sec: 1449.17 - lr: 0.000011 - momentum: 0.000000
188
+ 2024-03-26 15:17:23,374 epoch 7 - iter 44/48 - loss 0.07880122 - time (sec): 21.63 - samples/sec: 1465.43 - lr: 0.000010 - momentum: 0.000000
189
+ 2024-03-26 15:17:25,249 epoch 7 - iter 48/48 - loss 0.07866429 - time (sec): 23.51 - samples/sec: 1466.43 - lr: 0.000010 - momentum: 0.000000
190
+ 2024-03-26 15:17:25,249 ----------------------------------------------------------------------------------------------------
191
+ 2024-03-26 15:17:25,249 EPOCH 7 done: loss 0.0787 - lr: 0.000010
192
+ 2024-03-26 15:17:26,149 DEV : loss 0.17981727421283722 - f1-score (micro avg) 0.908
193
+ 2024-03-26 15:17:26,150 saving best model
194
+ 2024-03-26 15:17:26,652 ----------------------------------------------------------------------------------------------------
195
+ 2024-03-26 15:17:28,588 epoch 8 - iter 4/48 - loss 0.07650047 - time (sec): 1.93 - samples/sec: 1396.98 - lr: 0.000010 - momentum: 0.000000
196
+ 2024-03-26 15:17:31,347 epoch 8 - iter 8/48 - loss 0.06695826 - time (sec): 4.69 - samples/sec: 1183.67 - lr: 0.000010 - momentum: 0.000000
197
+ 2024-03-26 15:17:32,602 epoch 8 - iter 12/48 - loss 0.07061215 - time (sec): 5.95 - samples/sec: 1341.86 - lr: 0.000009 - momentum: 0.000000
198
+ 2024-03-26 15:17:34,976 epoch 8 - iter 16/48 - loss 0.07549260 - time (sec): 8.32 - samples/sec: 1352.47 - lr: 0.000009 - momentum: 0.000000
199
+ 2024-03-26 15:17:37,453 epoch 8 - iter 20/48 - loss 0.06463020 - time (sec): 10.80 - samples/sec: 1395.20 - lr: 0.000009 - momentum: 0.000000
200
+ 2024-03-26 15:17:38,724 epoch 8 - iter 24/48 - loss 0.06822777 - time (sec): 12.07 - samples/sec: 1474.30 - lr: 0.000009 - momentum: 0.000000
201
+ 2024-03-26 15:17:41,931 epoch 8 - iter 28/48 - loss 0.06654063 - time (sec): 15.28 - samples/sec: 1428.25 - lr: 0.000008 - momentum: 0.000000
202
+ 2024-03-26 15:17:43,898 epoch 8 - iter 32/48 - loss 0.06923248 - time (sec): 17.25 - samples/sec: 1429.61 - lr: 0.000008 - momentum: 0.000000
203
+ 2024-03-26 15:17:44,942 epoch 8 - iter 36/48 - loss 0.06831414 - time (sec): 18.29 - samples/sec: 1468.17 - lr: 0.000008 - momentum: 0.000000
204
+ 2024-03-26 15:17:46,603 epoch 8 - iter 40/48 - loss 0.06747054 - time (sec): 19.95 - samples/sec: 1464.99 - lr: 0.000007 - momentum: 0.000000
205
+ 2024-03-26 15:17:48,156 epoch 8 - iter 44/48 - loss 0.06619118 - time (sec): 21.50 - samples/sec: 1485.92 - lr: 0.000007 - momentum: 0.000000
206
+ 2024-03-26 15:17:50,074 epoch 8 - iter 48/48 - loss 0.06702109 - time (sec): 23.42 - samples/sec: 1471.81 - lr: 0.000007 - momentum: 0.000000
207
+ 2024-03-26 15:17:50,074 ----------------------------------------------------------------------------------------------------
208
+ 2024-03-26 15:17:50,075 EPOCH 8 done: loss 0.0670 - lr: 0.000007
209
+ 2024-03-26 15:17:50,978 DEV : loss 0.1929100602865219 - f1-score (micro avg) 0.9141
210
+ 2024-03-26 15:17:50,980 saving best model
211
+ 2024-03-26 15:17:51,467 ----------------------------------------------------------------------------------------------------
212
+ 2024-03-26 15:17:53,278 epoch 9 - iter 4/48 - loss 0.04211889 - time (sec): 1.81 - samples/sec: 1481.20 - lr: 0.000007 - momentum: 0.000000
213
+ 2024-03-26 15:17:56,401 epoch 9 - iter 8/48 - loss 0.03309625 - time (sec): 4.93 - samples/sec: 1266.23 - lr: 0.000006 - momentum: 0.000000
214
+ 2024-03-26 15:17:58,037 epoch 9 - iter 12/48 - loss 0.04604848 - time (sec): 6.57 - samples/sec: 1323.25 - lr: 0.000006 - momentum: 0.000000
215
+ 2024-03-26 15:18:00,252 epoch 9 - iter 16/48 - loss 0.04819190 - time (sec): 8.78 - samples/sec: 1311.92 - lr: 0.000006 - momentum: 0.000000
216
+ 2024-03-26 15:18:02,497 epoch 9 - iter 20/48 - loss 0.05279948 - time (sec): 11.03 - samples/sec: 1341.70 - lr: 0.000006 - momentum: 0.000000
217
+ 2024-03-26 15:18:04,641 epoch 9 - iter 24/48 - loss 0.05550487 - time (sec): 13.17 - samples/sec: 1357.77 - lr: 0.000005 - momentum: 0.000000
218
+ 2024-03-26 15:18:06,976 epoch 9 - iter 28/48 - loss 0.05363801 - time (sec): 15.51 - samples/sec: 1351.59 - lr: 0.000005 - momentum: 0.000000
219
+ 2024-03-26 15:18:09,275 epoch 9 - iter 32/48 - loss 0.05283883 - time (sec): 17.81 - samples/sec: 1348.56 - lr: 0.000005 - momentum: 0.000000
220
+ 2024-03-26 15:18:11,047 epoch 9 - iter 36/48 - loss 0.05589561 - time (sec): 19.58 - samples/sec: 1367.45 - lr: 0.000004 - momentum: 0.000000
221
+ 2024-03-26 15:18:13,200 epoch 9 - iter 40/48 - loss 0.05713220 - time (sec): 21.73 - samples/sec: 1356.87 - lr: 0.000004 - momentum: 0.000000
222
+ 2024-03-26 15:18:15,303 epoch 9 - iter 44/48 - loss 0.05677953 - time (sec): 23.83 - samples/sec: 1367.89 - lr: 0.000004 - momentum: 0.000000
223
+ 2024-03-26 15:18:16,060 epoch 9 - iter 48/48 - loss 0.05723015 - time (sec): 24.59 - samples/sec: 1401.79 - lr: 0.000004 - momentum: 0.000000
224
+ 2024-03-26 15:18:16,061 ----------------------------------------------------------------------------------------------------
225
+ 2024-03-26 15:18:16,061 EPOCH 9 done: loss 0.0572 - lr: 0.000004
226
+ 2024-03-26 15:18:16,980 DEV : loss 0.18385276198387146 - f1-score (micro avg) 0.9123
227
+ 2024-03-26 15:18:16,982 ----------------------------------------------------------------------------------------------------
228
+ 2024-03-26 15:18:18,703 epoch 10 - iter 4/48 - loss 0.04058926 - time (sec): 1.72 - samples/sec: 1528.48 - lr: 0.000003 - momentum: 0.000000
229
+ 2024-03-26 15:18:20,627 epoch 10 - iter 8/48 - loss 0.04133721 - time (sec): 3.64 - samples/sec: 1520.71 - lr: 0.000003 - momentum: 0.000000
230
+ 2024-03-26 15:18:23,218 epoch 10 - iter 12/48 - loss 0.04345885 - time (sec): 6.24 - samples/sec: 1399.60 - lr: 0.000003 - momentum: 0.000000
231
+ 2024-03-26 15:18:25,117 epoch 10 - iter 16/48 - loss 0.05006167 - time (sec): 8.13 - samples/sec: 1410.32 - lr: 0.000002 - momentum: 0.000000
232
+ 2024-03-26 15:18:26,939 epoch 10 - iter 20/48 - loss 0.05224594 - time (sec): 9.96 - samples/sec: 1452.96 - lr: 0.000002 - momentum: 0.000000
233
+ 2024-03-26 15:18:28,569 epoch 10 - iter 24/48 - loss 0.06212561 - time (sec): 11.59 - samples/sec: 1463.73 - lr: 0.000002 - momentum: 0.000000
234
+ 2024-03-26 15:18:30,293 epoch 10 - iter 28/48 - loss 0.05844941 - time (sec): 13.31 - samples/sec: 1486.59 - lr: 0.000002 - momentum: 0.000000
235
+ 2024-03-26 15:18:31,476 epoch 10 - iter 32/48 - loss 0.05652740 - time (sec): 14.49 - samples/sec: 1519.58 - lr: 0.000001 - momentum: 0.000000
236
+ 2024-03-26 15:18:34,414 epoch 10 - iter 36/48 - loss 0.05129798 - time (sec): 17.43 - samples/sec: 1469.42 - lr: 0.000001 - momentum: 0.000000
237
+ 2024-03-26 15:18:37,169 epoch 10 - iter 40/48 - loss 0.05311061 - time (sec): 20.19 - samples/sec: 1440.66 - lr: 0.000001 - momentum: 0.000000
238
+ 2024-03-26 15:18:39,929 epoch 10 - iter 44/48 - loss 0.05134307 - time (sec): 22.95 - samples/sec: 1406.91 - lr: 0.000001 - momentum: 0.000000
239
+ 2024-03-26 15:18:41,511 epoch 10 - iter 48/48 - loss 0.05016706 - time (sec): 24.53 - samples/sec: 1405.42 - lr: 0.000000 - momentum: 0.000000
240
+ 2024-03-26 15:18:41,511 ----------------------------------------------------------------------------------------------------
241
+ 2024-03-26 15:18:41,511 EPOCH 10 done: loss 0.0502 - lr: 0.000000
242
+ 2024-03-26 15:18:42,489 DEV : loss 0.1834828406572342 - f1-score (micro avg) 0.9119
243
+ 2024-03-26 15:18:42,787 ----------------------------------------------------------------------------------------------------
244
+ 2024-03-26 15:18:42,787 Loading model from best epoch ...
245
+ 2024-03-26 15:18:43,740 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
246
+ 2024-03-26 15:18:44,526
247
+ Results:
248
+ - F-score (micro) 0.904
249
+ - F-score (macro) 0.6873
250
+ - Accuracy 0.8282
251
+
252
+ By class:
253
+ precision recall f1-score support
254
+
255
+ Unternehmen 0.8830 0.8797 0.8814 266
256
+ Auslagerung 0.8764 0.9116 0.8937 249
257
+ Ort 0.9635 0.9851 0.9742 134
258
+ Software 0.0000 0.0000 0.0000 0
259
+
260
+ micro avg 0.8944 0.9137 0.9040 649
261
+ macro avg 0.6807 0.6941 0.6873 649
262
+ weighted avg 0.8971 0.9137 0.9053 649
263
+
264
+ 2024-03-26 15:18:44,526 ----------------------------------------------------------------------------------------------------