Hugging Face's logo

stefan-it
/
flair-co-funer-gbert_base-bs16-e10-lr3e-05-2

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
hetzner
hetzner-gex44
hetzner-gpu
Model card Files Metrics Community
3
stefan-it commited on
Commit
ffe4aa6
·
verified ·
1 Parent(s): aae8ee6

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +265 -0
training.log ADDED
@@ -0,0 +1,265 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-03-26 09:43:20,711 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 09:43:20,711 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 09:43:20,712 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 09:43:20,712 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 09:43:20,712 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 09:43:20,712 Train: 758 sentences
54
+ 2024-03-26 09:43:20,712 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 09:43:20,712 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 09:43:20,712 Training Params:
57
+ 2024-03-26 09:43:20,712 - learning_rate: "3e-05"
58
+ 2024-03-26 09:43:20,712 - mini_batch_size: "16"
59
+ 2024-03-26 09:43:20,712 - max_epochs: "10"
60
+ 2024-03-26 09:43:20,712 - shuffle: "True"
61
+ 2024-03-26 09:43:20,712 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 09:43:20,712 Plugins:
63
+ 2024-03-26 09:43:20,712 - TensorboardLogger
64
+ 2024-03-26 09:43:20,712 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 09:43:20,712 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 09:43:20,712 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 09:43:20,712 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 09:43:20,712 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 09:43:20,712 Computation:
70
+ 2024-03-26 09:43:20,712 - compute on device: cuda:0
71
+ 2024-03-26 09:43:20,712 - embedding storage: none
72
+ 2024-03-26 09:43:20,712 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 09:43:20,712 Model training base path: "flair-co-funer-gbert_base-bs16-e10-lr3e-05-2"
74
+ 2024-03-26 09:43:20,712 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 09:43:20,712 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 09:43:20,712 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 09:43:22,441 epoch 1 - iter 4/48 - loss 3.54097837 - time (sec): 1.73 - samples/sec: 1747.68 - lr: 0.000002 - momentum: 0.000000
78
+ 2024-03-26 09:43:24,541 epoch 1 - iter 8/48 - loss 3.46732419 - time (sec): 3.83 - samples/sec: 1621.38 - lr: 0.000004 - momentum: 0.000000
79
+ 2024-03-26 09:43:26,386 epoch 1 - iter 12/48 - loss 3.37699881 - time (sec): 5.67 - samples/sec: 1571.13 - lr: 0.000007 - momentum: 0.000000
80
+ 2024-03-26 09:43:28,400 epoch 1 - iter 16/48 - loss 3.22918949 - time (sec): 7.69 - samples/sec: 1578.39 - lr: 0.000009 - momentum: 0.000000
81
+ 2024-03-26 09:43:30,598 epoch 1 - iter 20/48 - loss 3.05714722 - time (sec): 9.89 - samples/sec: 1545.81 - lr: 0.000012 - momentum: 0.000000
82
+ 2024-03-26 09:43:33,642 epoch 1 - iter 24/48 - loss 2.91610601 - time (sec): 12.93 - samples/sec: 1405.97 - lr: 0.000014 - momentum: 0.000000
83
+ 2024-03-26 09:43:36,053 epoch 1 - iter 28/48 - loss 2.77155856 - time (sec): 15.34 - samples/sec: 1389.33 - lr: 0.000017 - momentum: 0.000000
84
+ 2024-03-26 09:43:36,876 epoch 1 - iter 32/48 - loss 2.67641615 - time (sec): 16.16 - samples/sec: 1444.62 - lr: 0.000019 - momentum: 0.000000
85
+ 2024-03-26 09:43:38,140 epoch 1 - iter 36/48 - loss 2.56751661 - time (sec): 17.43 - samples/sec: 1500.56 - lr: 0.000022 - momentum: 0.000000
86
+ 2024-03-26 09:43:40,010 epoch 1 - iter 40/48 - loss 2.47153744 - time (sec): 19.30 - samples/sec: 1507.46 - lr: 0.000024 - momentum: 0.000000
87
+ 2024-03-26 09:43:41,898 epoch 1 - iter 44/48 - loss 2.37591552 - time (sec): 21.19 - samples/sec: 1508.12 - lr: 0.000027 - momentum: 0.000000
88
+ 2024-03-26 09:43:43,251 epoch 1 - iter 48/48 - loss 2.29457447 - time (sec): 22.54 - samples/sec: 1529.47 - lr: 0.000029 - momentum: 0.000000
89
+ 2024-03-26 09:43:43,251 ----------------------------------------------------------------------------------------------------
90
+ 2024-03-26 09:43:43,251 EPOCH 1 done: loss 2.2946 - lr: 0.000029
91
+ 2024-03-26 09:43:44,060 DEV : loss 0.868198812007904 - f1-score (micro avg) 0.3671
92
+ 2024-03-26 09:43:44,061 saving best model
93
+ 2024-03-26 09:43:44,339 ----------------------------------------------------------------------------------------------------
94
+ 2024-03-26 09:43:45,643 epoch 2 - iter 4/48 - loss 1.21391336 - time (sec): 1.30 - samples/sec: 2226.04 - lr: 0.000030 - momentum: 0.000000
95
+ 2024-03-26 09:43:47,473 epoch 2 - iter 8/48 - loss 1.01735114 - time (sec): 3.13 - samples/sec: 1946.30 - lr: 0.000030 - momentum: 0.000000
96
+ 2024-03-26 09:43:50,883 epoch 2 - iter 12/48 - loss 0.91073315 - time (sec): 6.54 - samples/sec: 1555.26 - lr: 0.000029 - momentum: 0.000000
97
+ 2024-03-26 09:43:53,349 epoch 2 - iter 16/48 - loss 0.84066048 - time (sec): 9.01 - samples/sec: 1478.39 - lr: 0.000029 - momentum: 0.000000
98
+ 2024-03-26 09:43:55,980 epoch 2 - iter 20/48 - loss 0.78893352 - time (sec): 11.64 - samples/sec: 1427.19 - lr: 0.000029 - momentum: 0.000000
99
+ 2024-03-26 09:43:57,851 epoch 2 - iter 24/48 - loss 0.74386229 - time (sec): 13.51 - samples/sec: 1426.93 - lr: 0.000028 - momentum: 0.000000
100
+ 2024-03-26 09:43:59,611 epoch 2 - iter 28/48 - loss 0.72707811 - time (sec): 15.27 - samples/sec: 1436.22 - lr: 0.000028 - momentum: 0.000000
101
+ 2024-03-26 09:44:01,311 epoch 2 - iter 32/48 - loss 0.70317913 - time (sec): 16.97 - samples/sec: 1449.78 - lr: 0.000028 - momentum: 0.000000
102
+ 2024-03-26 09:44:03,143 epoch 2 - iter 36/48 - loss 0.68201229 - time (sec): 18.80 - samples/sec: 1458.93 - lr: 0.000028 - momentum: 0.000000
103
+ 2024-03-26 09:44:04,149 epoch 2 - iter 40/48 - loss 0.66472757 - time (sec): 19.81 - samples/sec: 1506.96 - lr: 0.000027 - momentum: 0.000000
104
+ 2024-03-26 09:44:05,571 epoch 2 - iter 44/48 - loss 0.65567832 - time (sec): 21.23 - samples/sec: 1526.81 - lr: 0.000027 - momentum: 0.000000
105
+ 2024-03-26 09:44:07,083 epoch 2 - iter 48/48 - loss 0.63834426 - time (sec): 22.74 - samples/sec: 1515.70 - lr: 0.000027 - momentum: 0.000000
106
+ 2024-03-26 09:44:07,083 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 09:44:07,083 EPOCH 2 done: loss 0.6383 - lr: 0.000027
108
+ 2024-03-26 09:44:07,970 DEV : loss 0.3501518666744232 - f1-score (micro avg) 0.7641
109
+ 2024-03-26 09:44:07,971 saving best model
110
+ 2024-03-26 09:44:08,428 ----------------------------------------------------------------------------------------------------
111
+ 2024-03-26 09:44:11,061 epoch 3 - iter 4/48 - loss 0.38909483 - time (sec): 2.63 - samples/sec: 1143.78 - lr: 0.000026 - momentum: 0.000000
112
+ 2024-03-26 09:44:13,193 epoch 3 - iter 8/48 - loss 0.38382097 - time (sec): 4.76 - samples/sec: 1333.23 - lr: 0.000026 - momentum: 0.000000
113
+ 2024-03-26 09:44:14,762 epoch 3 - iter 12/48 - loss 0.39785448 - time (sec): 6.33 - samples/sec: 1401.18 - lr: 0.000026 - momentum: 0.000000
114
+ 2024-03-26 09:44:16,497 epoch 3 - iter 16/48 - loss 0.36688780 - time (sec): 8.07 - samples/sec: 1408.90 - lr: 0.000026 - momentum: 0.000000
115
+ 2024-03-26 09:44:17,643 epoch 3 - iter 20/48 - loss 0.36697264 - time (sec): 9.21 - samples/sec: 1485.03 - lr: 0.000025 - momentum: 0.000000
116
+ 2024-03-26 09:44:19,479 epoch 3 - iter 24/48 - loss 0.37183904 - time (sec): 11.05 - samples/sec: 1489.25 - lr: 0.000025 - momentum: 0.000000
117
+ 2024-03-26 09:44:21,917 epoch 3 - iter 28/48 - loss 0.36591246 - time (sec): 13.49 - samples/sec: 1434.46 - lr: 0.000025 - momentum: 0.000000
118
+ 2024-03-26 09:44:23,760 epoch 3 - iter 32/48 - loss 0.35952677 - time (sec): 15.33 - samples/sec: 1444.19 - lr: 0.000025 - momentum: 0.000000
119
+ 2024-03-26 09:44:25,187 epoch 3 - iter 36/48 - loss 0.35091038 - time (sec): 16.76 - samples/sec: 1478.74 - lr: 0.000024 - momentum: 0.000000
120
+ 2024-03-26 09:44:27,447 epoch 3 - iter 40/48 - loss 0.33792769 - time (sec): 19.02 - samples/sec: 1451.82 - lr: 0.000024 - momentum: 0.000000
121
+ 2024-03-26 09:44:30,704 epoch 3 - iter 44/48 - loss 0.31414364 - time (sec): 22.27 - samples/sec: 1446.67 - lr: 0.000024 - momentum: 0.000000
122
+ 2024-03-26 09:44:31,961 epoch 3 - iter 48/48 - loss 0.30774544 - time (sec): 23.53 - samples/sec: 1464.97 - lr: 0.000023 - momentum: 0.000000
123
+ 2024-03-26 09:44:31,961 ----------------------------------------------------------------------------------------------------
124
+ 2024-03-26 09:44:31,961 EPOCH 3 done: loss 0.3077 - lr: 0.000023
125
+ 2024-03-26 09:44:32,882 DEV : loss 0.26573842763900757 - f1-score (micro avg) 0.8386
126
+ 2024-03-26 09:44:32,883 saving best model
127
+ 2024-03-26 09:44:33,332 ----------------------------------------------------------------------------------------------------
128
+ 2024-03-26 09:44:34,890 epoch 4 - iter 4/48 - loss 0.27499759 - time (sec): 1.56 - samples/sec: 1638.26 - lr: 0.000023 - momentum: 0.000000
129
+ 2024-03-26 09:44:37,093 epoch 4 - iter 8/48 - loss 0.24221231 - time (sec): 3.76 - samples/sec: 1594.15 - lr: 0.000023 - momentum: 0.000000
130
+ 2024-03-26 09:44:38,337 epoch 4 - iter 12/48 - loss 0.23930651 - time (sec): 5.00 - samples/sec: 1670.67 - lr: 0.000023 - momentum: 0.000000
131
+ 2024-03-26 09:44:40,546 epoch 4 - iter 16/48 - loss 0.23924867 - time (sec): 7.21 - samples/sec: 1563.30 - lr: 0.000022 - momentum: 0.000000
132
+ 2024-03-26 09:44:43,067 epoch 4 - iter 20/48 - loss 0.22689797 - time (sec): 9.73 - samples/sec: 1436.47 - lr: 0.000022 - momentum: 0.000000
133
+ 2024-03-26 09:44:45,085 epoch 4 - iter 24/48 - loss 0.23176516 - time (sec): 11.75 - samples/sec: 1432.56 - lr: 0.000022 - momentum: 0.000000
134
+ 2024-03-26 09:44:47,195 epoch 4 - iter 28/48 - loss 0.22426201 - time (sec): 13.86 - samples/sec: 1435.28 - lr: 0.000022 - momentum: 0.000000
135
+ 2024-03-26 09:44:49,751 epoch 4 - iter 32/48 - loss 0.22093128 - time (sec): 16.42 - samples/sec: 1404.63 - lr: 0.000021 - momentum: 0.000000
136
+ 2024-03-26 09:44:52,547 epoch 4 - iter 36/48 - loss 0.21058242 - time (sec): 19.21 - samples/sec: 1392.25 - lr: 0.000021 - momentum: 0.000000
137
+ 2024-03-26 09:44:54,235 epoch 4 - iter 40/48 - loss 0.20472930 - time (sec): 20.90 - samples/sec: 1391.98 - lr: 0.000021 - momentum: 0.000000
138
+ 2024-03-26 09:44:56,221 epoch 4 - iter 44/48 - loss 0.20327120 - time (sec): 22.89 - samples/sec: 1394.79 - lr: 0.000020 - momentum: 0.000000
139
+ 2024-03-26 09:44:57,880 epoch 4 - iter 48/48 - loss 0.20204122 - time (sec): 24.55 - samples/sec: 1404.36 - lr: 0.000020 - momentum: 0.000000
140
+ 2024-03-26 09:44:57,880 ----------------------------------------------------------------------------------------------------
141
+ 2024-03-26 09:44:57,881 EPOCH 4 done: loss 0.2020 - lr: 0.000020
142
+ 2024-03-26 09:44:58,784 DEV : loss 0.2160491645336151 - f1-score (micro avg) 0.8654
143
+ 2024-03-26 09:44:58,785 saving best model
144
+ 2024-03-26 09:44:59,236 ----------------------------------------------------------------------------------------------------
145
+ 2024-03-26 09:45:00,059 epoch 5 - iter 4/48 - loss 0.11408889 - time (sec): 0.82 - samples/sec: 2231.23 - lr: 0.000020 - momentum: 0.000000
146
+ 2024-03-26 09:45:01,428 epoch 5 - iter 8/48 - loss 0.15205366 - time (sec): 2.19 - samples/sec: 2030.58 - lr: 0.000020 - momentum: 0.000000
147
+ 2024-03-26 09:45:04,164 epoch 5 - iter 12/48 - loss 0.14478600 - time (sec): 4.93 - samples/sec: 1619.74 - lr: 0.000019 - momentum: 0.000000
148
+ 2024-03-26 09:45:07,113 epoch 5 - iter 16/48 - loss 0.14042386 - time (sec): 7.88 - samples/sec: 1432.90 - lr: 0.000019 - momentum: 0.000000
149
+ 2024-03-26 09:45:08,490 epoch 5 - iter 20/48 - loss 0.14804854 - time (sec): 9.25 - samples/sec: 1483.74 - lr: 0.000019 - momentum: 0.000000
150
+ 2024-03-26 09:45:10,941 epoch 5 - iter 24/48 - loss 0.14514482 - time (sec): 11.70 - samples/sec: 1431.68 - lr: 0.000018 - momentum: 0.000000
151
+ 2024-03-26 09:45:13,001 epoch 5 - iter 28/48 - loss 0.14291018 - time (sec): 13.76 - samples/sec: 1419.68 - lr: 0.000018 - momentum: 0.000000
152
+ 2024-03-26 09:45:15,244 epoch 5 - iter 32/48 - loss 0.14292917 - time (sec): 16.01 - samples/sec: 1447.11 - lr: 0.000018 - momentum: 0.000000
153
+ 2024-03-26 09:45:16,701 epoch 5 - iter 36/48 - loss 0.14908240 - time (sec): 17.46 - samples/sec: 1470.91 - lr: 0.000018 - momentum: 0.000000
154
+ 2024-03-26 09:45:19,231 epoch 5 - iter 40/48 - loss 0.14377708 - time (sec): 19.99 - samples/sec: 1420.95 - lr: 0.000017 - momentum: 0.000000
155
+ 2024-03-26 09:45:21,304 epoch 5 - iter 44/48 - loss 0.14312629 - time (sec): 22.07 - samples/sec: 1433.66 - lr: 0.000017 - momentum: 0.000000
156
+ 2024-03-26 09:45:23,247 epoch 5 - iter 48/48 - loss 0.14304449 - time (sec): 24.01 - samples/sec: 1435.77 - lr: 0.000017 - momentum: 0.000000
157
+ 2024-03-26 09:45:23,247 ----------------------------------------------------------------------------------------------------
158
+ 2024-03-26 09:45:23,247 EPOCH 5 done: loss 0.1430 - lr: 0.000017
159
+ 2024-03-26 09:45:24,148 DEV : loss 0.19238987565040588 - f1-score (micro avg) 0.8786
160
+ 2024-03-26 09:45:24,150 saving best model
161
+ 2024-03-26 09:45:24,606 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 09:45:26,184 epoch 6 - iter 4/48 - loss 0.11206717 - time (sec): 1.58 - samples/sec: 1579.51 - lr: 0.000017 - momentum: 0.000000
163
+ 2024-03-26 09:45:28,582 epoch 6 - iter 8/48 - loss 0.12248471 - time (sec): 3.97 - samples/sec: 1610.52 - lr: 0.000016 - momentum: 0.000000
164
+ 2024-03-26 09:45:30,514 epoch 6 - iter 12/48 - loss 0.12381849 - time (sec): 5.91 - samples/sec: 1533.89 - lr: 0.000016 - momentum: 0.000000
165
+ 2024-03-26 09:45:32,523 epoch 6 - iter 16/48 - loss 0.11636626 - time (sec): 7.91 - samples/sec: 1532.16 - lr: 0.000016 - momentum: 0.000000
166
+ 2024-03-26 09:45:35,264 epoch 6 - iter 20/48 - loss 0.11487295 - time (sec): 10.66 - samples/sec: 1499.36 - lr: 0.000015 - momentum: 0.000000
167
+ 2024-03-26 09:45:36,772 epoch 6 - iter 24/48 - loss 0.12472605 - time (sec): 12.16 - samples/sec: 1521.80 - lr: 0.000015 - momentum: 0.000000
168
+ 2024-03-26 09:45:38,138 epoch 6 - iter 28/48 - loss 0.12552974 - time (sec): 13.53 - samples/sec: 1527.57 - lr: 0.000015 - momentum: 0.000000
169
+ 2024-03-26 09:45:39,301 epoch 6 - iter 32/48 - loss 0.12340584 - time (sec): 14.69 - samples/sec: 1548.39 - lr: 0.000015 - momentum: 0.000000
170
+ 2024-03-26 09:45:40,766 epoch 6 - iter 36/48 - loss 0.11845859 - time (sec): 16.16 - samples/sec: 1580.23 - lr: 0.000014 - momentum: 0.000000
171
+ 2024-03-26 09:45:42,672 epoch 6 - iter 40/48 - loss 0.11916775 - time (sec): 18.06 - samples/sec: 1568.82 - lr: 0.000014 - momentum: 0.000000
172
+ 2024-03-26 09:45:44,858 epoch 6 - iter 44/48 - loss 0.11527571 - time (sec): 20.25 - samples/sec: 1587.88 - lr: 0.000014 - momentum: 0.000000
173
+ 2024-03-26 09:45:46,508 epoch 6 - iter 48/48 - loss 0.11522214 - time (sec): 21.90 - samples/sec: 1574.13 - lr: 0.000014 - momentum: 0.000000
174
+ 2024-03-26 09:45:46,508 ----------------------------------------------------------------------------------------------------
175
+ 2024-03-26 09:45:46,508 EPOCH 6 done: loss 0.1152 - lr: 0.000014
176
+ 2024-03-26 09:45:47,403 DEV : loss 0.17289206385612488 - f1-score (micro avg) 0.8941
177
+ 2024-03-26 09:45:47,404 saving best model
178
+ 2024-03-26 09:45:47,857 ----------------------------------------------------------------------------------------------------
179
+ 2024-03-26 09:45:49,548 epoch 7 - iter 4/48 - loss 0.07200689 - time (sec): 1.69 - samples/sec: 1441.68 - lr: 0.000013 - momentum: 0.000000
180
+ 2024-03-26 09:45:51,129 epoch 7 - iter 8/48 - loss 0.09330083 - time (sec): 3.27 - samples/sec: 1514.70 - lr: 0.000013 - momentum: 0.000000
181
+ 2024-03-26 09:45:53,214 epoch 7 - iter 12/48 - loss 0.09038192 - time (sec): 5.36 - samples/sec: 1469.64 - lr: 0.000013 - momentum: 0.000000
182
+ 2024-03-26 09:45:55,204 epoch 7 - iter 16/48 - loss 0.09096213 - time (sec): 7.35 - samples/sec: 1516.73 - lr: 0.000012 - momentum: 0.000000
183
+ 2024-03-26 09:45:55,835 epoch 7 - iter 20/48 - loss 0.08593354 - time (sec): 7.98 - samples/sec: 1624.73 - lr: 0.000012 - momentum: 0.000000
184
+ 2024-03-26 09:45:57,400 epoch 7 - iter 24/48 - loss 0.08538935 - time (sec): 9.54 - samples/sec: 1605.80 - lr: 0.000012 - momentum: 0.000000
185
+ 2024-03-26 09:46:00,234 epoch 7 - iter 28/48 - loss 0.08421075 - time (sec): 12.38 - samples/sec: 1504.87 - lr: 0.000012 - momentum: 0.000000
186
+ 2024-03-26 09:46:02,989 epoch 7 - iter 32/48 - loss 0.08232354 - time (sec): 15.13 - samples/sec: 1431.85 - lr: 0.000011 - momentum: 0.000000
187
+ 2024-03-26 09:46:05,703 epoch 7 - iter 36/48 - loss 0.08605663 - time (sec): 17.84 - samples/sec: 1444.74 - lr: 0.000011 - momentum: 0.000000
188
+ 2024-03-26 09:46:07,663 epoch 7 - iter 40/48 - loss 0.08909139 - time (sec): 19.80 - samples/sec: 1451.56 - lr: 0.000011 - momentum: 0.000000
189
+ 2024-03-26 09:46:10,190 epoch 7 - iter 44/48 - loss 0.09175837 - time (sec): 22.33 - samples/sec: 1426.44 - lr: 0.000010 - momentum: 0.000000
190
+ 2024-03-26 09:46:11,923 epoch 7 - iter 48/48 - loss 0.09047578 - time (sec): 24.06 - samples/sec: 1432.51 - lr: 0.000010 - momentum: 0.000000
191
+ 2024-03-26 09:46:11,923 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 09:46:11,923 EPOCH 7 done: loss 0.0905 - lr: 0.000010
193
+ 2024-03-26 09:46:12,819 DEV : loss 0.17756354808807373 - f1-score (micro avg) 0.8921
194
+ 2024-03-26 09:46:12,820 ----------------------------------------------------------------------------------------------------
195
+ 2024-03-26 09:46:15,432 epoch 8 - iter 4/48 - loss 0.09145265 - time (sec): 2.61 - samples/sec: 1264.58 - lr: 0.000010 - momentum: 0.000000
196
+ 2024-03-26 09:46:17,478 epoch 8 - iter 8/48 - loss 0.06932129 - time (sec): 4.66 - samples/sec: 1259.86 - lr: 0.000010 - momentum: 0.000000
197
+ 2024-03-26 09:46:20,637 epoch 8 - iter 12/48 - loss 0.06960067 - time (sec): 7.82 - samples/sec: 1239.81 - lr: 0.000009 - momentum: 0.000000
198
+ 2024-03-26 09:46:22,554 epoch 8 - iter 16/48 - loss 0.08062008 - time (sec): 9.73 - samples/sec: 1268.10 - lr: 0.000009 - momentum: 0.000000
199
+ 2024-03-26 09:46:23,990 epoch 8 - iter 20/48 - loss 0.08058957 - time (sec): 11.17 - samples/sec: 1314.68 - lr: 0.000009 - momentum: 0.000000
200
+ 2024-03-26 09:46:26,394 epoch 8 - iter 24/48 - loss 0.07978568 - time (sec): 13.57 - samples/sec: 1314.65 - lr: 0.000009 - momentum: 0.000000
201
+ 2024-03-26 09:46:28,134 epoch 8 - iter 28/48 - loss 0.08353391 - time (sec): 15.31 - samples/sec: 1350.27 - lr: 0.000008 - momentum: 0.000000
202
+ 2024-03-26 09:46:29,789 epoch 8 - iter 32/48 - loss 0.08022088 - time (sec): 16.97 - samples/sec: 1371.01 - lr: 0.000008 - momentum: 0.000000
203
+ 2024-03-26 09:46:31,061 epoch 8 - iter 36/48 - loss 0.07954960 - time (sec): 18.24 - samples/sec: 1402.54 - lr: 0.000008 - momentum: 0.000000
204
+ 2024-03-26 09:46:33,360 epoch 8 - iter 40/48 - loss 0.07805199 - time (sec): 20.54 - samples/sec: 1411.53 - lr: 0.000007 - momentum: 0.000000
205
+ 2024-03-26 09:46:36,162 epoch 8 - iter 44/48 - loss 0.07479444 - time (sec): 23.34 - samples/sec: 1380.24 - lr: 0.000007 - momentum: 0.000000
206
+ 2024-03-26 09:46:38,065 epoch 8 - iter 48/48 - loss 0.07452892 - time (sec): 25.24 - samples/sec: 1365.52 - lr: 0.000007 - momentum: 0.000000
207
+ 2024-03-26 09:46:38,065 ----------------------------------------------------------------------------------------------------
208
+ 2024-03-26 09:46:38,065 EPOCH 8 done: loss 0.0745 - lr: 0.000007
209
+ 2024-03-26 09:46:38,956 DEV : loss 0.1639167219400406 - f1-score (micro avg) 0.9223
210
+ 2024-03-26 09:46:38,957 saving best model
211
+ 2024-03-26 09:46:39,402 ----------------------------------------------------------------------------------------------------
212
+ 2024-03-26 09:46:41,189 epoch 9 - iter 4/48 - loss 0.08119094 - time (sec): 1.78 - samples/sec: 1593.39 - lr: 0.000007 - momentum: 0.000000
213
+ 2024-03-26 09:46:43,560 epoch 9 - iter 8/48 - loss 0.06826402 - time (sec): 4.16 - samples/sec: 1475.47 - lr: 0.000006 - momentum: 0.000000
214
+ 2024-03-26 09:46:45,875 epoch 9 - iter 12/48 - loss 0.08047549 - time (sec): 6.47 - samples/sec: 1426.58 - lr: 0.000006 - momentum: 0.000000
215
+ 2024-03-26 09:46:47,883 epoch 9 - iter 16/48 - loss 0.07774196 - time (sec): 8.48 - samples/sec: 1426.44 - lr: 0.000006 - momentum: 0.000000
216
+ 2024-03-26 09:46:49,315 epoch 9 - iter 20/48 - loss 0.06981163 - time (sec): 9.91 - samples/sec: 1487.02 - lr: 0.000006 - momentum: 0.000000
217
+ 2024-03-26 09:46:50,501 epoch 9 - iter 24/48 - loss 0.06576084 - time (sec): 11.10 - samples/sec: 1535.18 - lr: 0.000005 - momentum: 0.000000
218
+ 2024-03-26 09:46:52,176 epoch 9 - iter 28/48 - loss 0.06423120 - time (sec): 12.77 - samples/sec: 1548.47 - lr: 0.000005 - momentum: 0.000000
219
+ 2024-03-26 09:46:54,403 epoch 9 - iter 32/48 - loss 0.06847394 - time (sec): 15.00 - samples/sec: 1533.11 - lr: 0.000005 - momentum: 0.000000
220
+ 2024-03-26 09:46:57,049 epoch 9 - iter 36/48 - loss 0.06724059 - time (sec): 17.64 - samples/sec: 1480.42 - lr: 0.000004 - momentum: 0.000000
221
+ 2024-03-26 09:46:59,934 epoch 9 - iter 40/48 - loss 0.06646050 - time (sec): 20.53 - samples/sec: 1435.67 - lr: 0.000004 - momentum: 0.000000
222
+ 2024-03-26 09:47:01,715 epoch 9 - iter 44/48 - loss 0.06605033 - time (sec): 22.31 - samples/sec: 1451.29 - lr: 0.000004 - momentum: 0.000000
223
+ 2024-03-26 09:47:02,735 epoch 9 - iter 48/48 - loss 0.06612071 - time (sec): 23.33 - samples/sec: 1477.52 - lr: 0.000004 - momentum: 0.000000
224
+ 2024-03-26 09:47:02,735 ----------------------------------------------------------------------------------------------------
225
+ 2024-03-26 09:47:02,735 EPOCH 9 done: loss 0.0661 - lr: 0.000004
226
+ 2024-03-26 09:47:03,634 DEV : loss 0.15946133434772491 - f1-score (micro avg) 0.9256
227
+ 2024-03-26 09:47:03,635 saving best model
228
+ 2024-03-26 09:47:04,087 ----------------------------------------------------------------------------------------------------
229
+ 2024-03-26 09:47:06,375 epoch 10 - iter 4/48 - loss 0.03203042 - time (sec): 2.29 - samples/sec: 1444.51 - lr: 0.000003 - momentum: 0.000000
230
+ 2024-03-26 09:47:08,406 epoch 10 - iter 8/48 - loss 0.04820710 - time (sec): 4.32 - samples/sec: 1430.94 - lr: 0.000003 - momentum: 0.000000
231
+ 2024-03-26 09:47:10,303 epoch 10 - iter 12/48 - loss 0.04809610 - time (sec): 6.21 - samples/sec: 1420.07 - lr: 0.000003 - momentum: 0.000000
232
+ 2024-03-26 09:47:11,525 epoch 10 - iter 16/48 - loss 0.05153512 - time (sec): 7.44 - samples/sec: 1481.96 - lr: 0.000002 - momentum: 0.000000
233
+ 2024-03-26 09:47:13,416 epoch 10 - iter 20/48 - loss 0.05993410 - time (sec): 9.33 - samples/sec: 1469.67 - lr: 0.000002 - momentum: 0.000000
234
+ 2024-03-26 09:47:15,606 epoch 10 - iter 24/48 - loss 0.06493684 - time (sec): 11.52 - samples/sec: 1441.99 - lr: 0.000002 - momentum: 0.000000
235
+ 2024-03-26 09:47:16,480 epoch 10 - iter 28/48 - loss 0.06441247 - time (sec): 12.39 - samples/sec: 1516.33 - lr: 0.000002 - momentum: 0.000000
236
+ 2024-03-26 09:47:17,728 epoch 10 - iter 32/48 - loss 0.06219799 - time (sec): 13.64 - samples/sec: 1557.26 - lr: 0.000001 - momentum: 0.000000
237
+ 2024-03-26 09:47:20,461 epoch 10 - iter 36/48 - loss 0.05975149 - time (sec): 16.37 - samples/sec: 1508.27 - lr: 0.000001 - momentum: 0.000000
238
+ 2024-03-26 09:47:22,867 epoch 10 - iter 40/48 - loss 0.06004247 - time (sec): 18.78 - samples/sec: 1531.22 - lr: 0.000001 - momentum: 0.000000
239
+ 2024-03-26 09:47:25,399 epoch 10 - iter 44/48 - loss 0.05988235 - time (sec): 21.31 - samples/sec: 1505.10 - lr: 0.000001 - momentum: 0.000000
240
+ 2024-03-26 09:47:27,307 epoch 10 - iter 48/48 - loss 0.05921491 - time (sec): 23.22 - samples/sec: 1484.68 - lr: 0.000000 - momentum: 0.000000
241
+ 2024-03-26 09:47:27,308 ----------------------------------------------------------------------------------------------------
242
+ 2024-03-26 09:47:27,308 EPOCH 10 done: loss 0.0592 - lr: 0.000000
243
+ 2024-03-26 09:47:28,208 DEV : loss 0.1646251529455185 - f1-score (micro avg) 0.9228
244
+ 2024-03-26 09:47:28,489 ----------------------------------------------------------------------------------------------------
245
+ 2024-03-26 09:47:28,490 Loading model from best epoch ...
246
+ 2024-03-26 09:47:29,430 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
247
+ 2024-03-26 09:47:30,175
248
+ Results:
249
+ - F-score (micro) 0.8969
250
+ - F-score (macro) 0.6818
251
+ - Accuracy 0.8175
252
+
253
+ By class:
254
+ precision recall f1-score support
255
+
256
+ Unternehmen 0.9105 0.8797 0.8948 266
257
+ Auslagerung 0.8371 0.8876 0.8616 249
258
+ Ort 0.9565 0.9851 0.9706 134
259
+ Software 0.0000 0.0000 0.0000 0
260
+
261
+ micro avg 0.8894 0.9045 0.8969 649
262
+ macro avg 0.6760 0.6881 0.6818 649
263
+ weighted avg 0.8919 0.9045 0.8977 649
264
+
265
+ 2024-03-26 09:47:30,176 ----------------------------------------------------------------------------------------------------