Hugging Face's logo

stefan-it
/
flair-co-funer-gbert_base-bs8-e10-lr3e-05-5

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
e6aea09
•
1 Parent(s): de11571

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +246 -0
training.log ADDED
@@ -0,0 +1,246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-03-26 10:41:29,094 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 10:41:29,095 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 10:41:29,095 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 10:41:29,095 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 10:41:29,095 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 10:41:29,095 Train: 758 sentences
54
+ 2024-03-26 10:41:29,095 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 10:41:29,095 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 10:41:29,095 Training Params:
57
+ 2024-03-26 10:41:29,095 - learning_rate: "3e-05"
58
+ 2024-03-26 10:41:29,095 - mini_batch_size: "8"
59
+ 2024-03-26 10:41:29,095 - max_epochs: "10"
60
+ 2024-03-26 10:41:29,095 - shuffle: "True"
61
+ 2024-03-26 10:41:29,095 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 10:41:29,095 Plugins:
63
+ 2024-03-26 10:41:29,095 - TensorboardLogger
64
+ 2024-03-26 10:41:29,095 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 10:41:29,095 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 10:41:29,095 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 10:41:29,095 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 10:41:29,095 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 10:41:29,095 Computation:
70
+ 2024-03-26 10:41:29,095 - compute on device: cuda:0
71
+ 2024-03-26 10:41:29,095 - embedding storage: none
72
+ 2024-03-26 10:41:29,095 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 10:41:29,095 Model training base path: "flair-co-funer-gbert_base-bs8-e10-lr3e-05-5"
74
+ 2024-03-26 10:41:29,095 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 10:41:29,095 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 10:41:29,095 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 10:41:30,964 epoch 1 - iter 9/95 - loss 3.42654605 - time (sec): 1.87 - samples/sec: 1678.28 - lr: 0.000003 - momentum: 0.000000
78
+ 2024-03-26 10:41:32,825 epoch 1 - iter 18/95 - loss 3.24644063 - time (sec): 3.73 - samples/sec: 1778.68 - lr: 0.000005 - momentum: 0.000000
79
+ 2024-03-26 10:41:35,107 epoch 1 - iter 27/95 - loss 3.02768317 - time (sec): 6.01 - samples/sec: 1725.38 - lr: 0.000008 - momentum: 0.000000
80
+ 2024-03-26 10:41:36,586 epoch 1 - iter 36/95 - loss 2.85323508 - time (sec): 7.49 - samples/sec: 1803.47 - lr: 0.000011 - momentum: 0.000000
81
+ 2024-03-26 10:41:38,735 epoch 1 - iter 45/95 - loss 2.68498607 - time (sec): 9.64 - samples/sec: 1782.83 - lr: 0.000014 - momentum: 0.000000
82
+ 2024-03-26 10:41:40,309 epoch 1 - iter 54/95 - loss 2.53008030 - time (sec): 11.21 - samples/sec: 1804.43 - lr: 0.000017 - momentum: 0.000000
83
+ 2024-03-26 10:41:41,933 epoch 1 - iter 63/95 - loss 2.40929636 - time (sec): 12.84 - samples/sec: 1823.01 - lr: 0.000020 - momentum: 0.000000
84
+ 2024-03-26 10:41:43,810 epoch 1 - iter 72/95 - loss 2.29079356 - time (sec): 14.71 - samples/sec: 1814.54 - lr: 0.000022 - momentum: 0.000000
85
+ 2024-03-26 10:41:45,869 epoch 1 - iter 81/95 - loss 2.15393416 - time (sec): 16.77 - samples/sec: 1797.45 - lr: 0.000025 - momentum: 0.000000
86
+ 2024-03-26 10:41:47,485 epoch 1 - iter 90/95 - loss 2.04297528 - time (sec): 18.39 - samples/sec: 1790.48 - lr: 0.000028 - momentum: 0.000000
87
+ 2024-03-26 10:41:48,235 ----------------------------------------------------------------------------------------------------
88
+ 2024-03-26 10:41:48,235 EPOCH 1 done: loss 1.9877 - lr: 0.000028
89
+ 2024-03-26 10:41:49,212 DEV : loss 0.5643121004104614 - f1-score (micro avg) 0.5905
90
+ 2024-03-26 10:41:49,213 saving best model
91
+ 2024-03-26 10:41:49,488 ----------------------------------------------------------------------------------------------------
92
+ 2024-03-26 10:41:51,746 epoch 2 - iter 9/95 - loss 0.75423522 - time (sec): 2.26 - samples/sec: 1690.40 - lr: 0.000030 - momentum: 0.000000
93
+ 2024-03-26 10:41:53,648 epoch 2 - iter 18/95 - loss 0.67076063 - time (sec): 4.16 - samples/sec: 1681.81 - lr: 0.000029 - momentum: 0.000000
94
+ 2024-03-26 10:41:55,955 epoch 2 - iter 27/95 - loss 0.59698468 - time (sec): 6.47 - samples/sec: 1654.32 - lr: 0.000029 - momentum: 0.000000
95
+ 2024-03-26 10:41:57,307 epoch 2 - iter 36/95 - loss 0.56867706 - time (sec): 7.82 - samples/sec: 1767.41 - lr: 0.000029 - momentum: 0.000000
96
+ 2024-03-26 10:41:59,255 epoch 2 - iter 45/95 - loss 0.52773200 - time (sec): 9.77 - samples/sec: 1728.14 - lr: 0.000028 - momentum: 0.000000
97
+ 2024-03-26 10:42:00,571 epoch 2 - iter 54/95 - loss 0.51655232 - time (sec): 11.08 - samples/sec: 1773.56 - lr: 0.000028 - momentum: 0.000000
98
+ 2024-03-26 10:42:02,135 epoch 2 - iter 63/95 - loss 0.49530789 - time (sec): 12.65 - samples/sec: 1789.56 - lr: 0.000028 - momentum: 0.000000
99
+ 2024-03-26 10:42:04,204 epoch 2 - iter 72/95 - loss 0.48119961 - time (sec): 14.72 - samples/sec: 1781.11 - lr: 0.000028 - momentum: 0.000000
100
+ 2024-03-26 10:42:06,106 epoch 2 - iter 81/95 - loss 0.48406945 - time (sec): 16.62 - samples/sec: 1780.83 - lr: 0.000027 - momentum: 0.000000
101
+ 2024-03-26 10:42:08,031 epoch 2 - iter 90/95 - loss 0.46381765 - time (sec): 18.54 - samples/sec: 1783.79 - lr: 0.000027 - momentum: 0.000000
102
+ 2024-03-26 10:42:08,613 ----------------------------------------------------------------------------------------------------
103
+ 2024-03-26 10:42:08,613 EPOCH 2 done: loss 0.4626 - lr: 0.000027
104
+ 2024-03-26 10:42:09,533 DEV : loss 0.2954573631286621 - f1-score (micro avg) 0.8136
105
+ 2024-03-26 10:42:09,534 saving best model
106
+ 2024-03-26 10:42:09,992 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 10:42:11,211 epoch 3 - iter 9/95 - loss 0.34685241 - time (sec): 1.22 - samples/sec: 2129.79 - lr: 0.000026 - momentum: 0.000000
108
+ 2024-03-26 10:42:13,447 epoch 3 - iter 18/95 - loss 0.29465517 - time (sec): 3.45 - samples/sec: 1858.92 - lr: 0.000026 - momentum: 0.000000
109
+ 2024-03-26 10:42:15,149 epoch 3 - iter 27/95 - loss 0.29721879 - time (sec): 5.16 - samples/sec: 1892.76 - lr: 0.000026 - momentum: 0.000000
110
+ 2024-03-26 10:42:16,842 epoch 3 - iter 36/95 - loss 0.27964027 - time (sec): 6.85 - samples/sec: 1923.01 - lr: 0.000025 - momentum: 0.000000
111
+ 2024-03-26 10:42:18,293 epoch 3 - iter 45/95 - loss 0.26416821 - time (sec): 8.30 - samples/sec: 1913.63 - lr: 0.000025 - momentum: 0.000000
112
+ 2024-03-26 10:42:20,409 epoch 3 - iter 54/95 - loss 0.25431604 - time (sec): 10.42 - samples/sec: 1854.76 - lr: 0.000025 - momentum: 0.000000
113
+ 2024-03-26 10:42:22,078 epoch 3 - iter 63/95 - loss 0.25168090 - time (sec): 12.08 - samples/sec: 1841.80 - lr: 0.000025 - momentum: 0.000000
114
+ 2024-03-26 10:42:24,353 epoch 3 - iter 72/95 - loss 0.24092237 - time (sec): 14.36 - samples/sec: 1806.47 - lr: 0.000024 - momentum: 0.000000
115
+ 2024-03-26 10:42:26,535 epoch 3 - iter 81/95 - loss 0.24173243 - time (sec): 16.54 - samples/sec: 1799.51 - lr: 0.000024 - momentum: 0.000000
116
+ 2024-03-26 10:42:28,291 epoch 3 - iter 90/95 - loss 0.23675211 - time (sec): 18.30 - samples/sec: 1788.31 - lr: 0.000024 - momentum: 0.000000
117
+ 2024-03-26 10:42:29,170 ----------------------------------------------------------------------------------------------------
118
+ 2024-03-26 10:42:29,170 EPOCH 3 done: loss 0.2346 - lr: 0.000024
119
+ 2024-03-26 10:42:30,083 DEV : loss 0.25258246064186096 - f1-score (micro avg) 0.8418
120
+ 2024-03-26 10:42:30,086 saving best model
121
+ 2024-03-26 10:42:30,548 ----------------------------------------------------------------------------------------------------
122
+ 2024-03-26 10:42:33,320 epoch 4 - iter 9/95 - loss 0.13973827 - time (sec): 2.77 - samples/sec: 1539.99 - lr: 0.000023 - momentum: 0.000000
123
+ 2024-03-26 10:42:34,368 epoch 4 - iter 18/95 - loss 0.17102613 - time (sec): 3.82 - samples/sec: 1742.16 - lr: 0.000023 - momentum: 0.000000
124
+ 2024-03-26 10:42:36,871 epoch 4 - iter 27/95 - loss 0.15553756 - time (sec): 6.32 - samples/sec: 1682.43 - lr: 0.000022 - momentum: 0.000000
125
+ 2024-03-26 10:42:39,490 epoch 4 - iter 36/95 - loss 0.15521838 - time (sec): 8.94 - samples/sec: 1623.06 - lr: 0.000022 - momentum: 0.000000
126
+ 2024-03-26 10:42:41,198 epoch 4 - iter 45/95 - loss 0.14604913 - time (sec): 10.65 - samples/sec: 1653.87 - lr: 0.000022 - momentum: 0.000000
127
+ 2024-03-26 10:42:42,912 epoch 4 - iter 54/95 - loss 0.14691915 - time (sec): 12.36 - samples/sec: 1666.30 - lr: 0.000022 - momentum: 0.000000
128
+ 2024-03-26 10:42:44,820 epoch 4 - iter 63/95 - loss 0.14863785 - time (sec): 14.27 - samples/sec: 1692.65 - lr: 0.000021 - momentum: 0.000000
129
+ 2024-03-26 10:42:46,497 epoch 4 - iter 72/95 - loss 0.15029495 - time (sec): 15.95 - samples/sec: 1740.39 - lr: 0.000021 - momentum: 0.000000
130
+ 2024-03-26 10:42:47,539 epoch 4 - iter 81/95 - loss 0.15078477 - time (sec): 16.99 - samples/sec: 1778.33 - lr: 0.000021 - momentum: 0.000000
131
+ 2024-03-26 10:42:48,951 epoch 4 - iter 90/95 - loss 0.15106787 - time (sec): 18.40 - samples/sec: 1803.55 - lr: 0.000020 - momentum: 0.000000
132
+ 2024-03-26 10:42:49,495 ----------------------------------------------------------------------------------------------------
133
+ 2024-03-26 10:42:49,495 EPOCH 4 done: loss 0.1534 - lr: 0.000020
134
+ 2024-03-26 10:42:50,400 DEV : loss 0.19777600467205048 - f1-score (micro avg) 0.8718
135
+ 2024-03-26 10:42:50,403 saving best model
136
+ 2024-03-26 10:42:50,855 ----------------------------------------------------------------------------------------------------
137
+ 2024-03-26 10:42:52,508 epoch 5 - iter 9/95 - loss 0.15220596 - time (sec): 1.65 - samples/sec: 1983.92 - lr: 0.000020 - momentum: 0.000000
138
+ 2024-03-26 10:42:54,479 epoch 5 - iter 18/95 - loss 0.13098915 - time (sec): 3.62 - samples/sec: 1965.88 - lr: 0.000019 - momentum: 0.000000
139
+ 2024-03-26 10:42:56,595 epoch 5 - iter 27/95 - loss 0.11083492 - time (sec): 5.74 - samples/sec: 1845.02 - lr: 0.000019 - momentum: 0.000000
140
+ 2024-03-26 10:42:57,933 epoch 5 - iter 36/95 - loss 0.11927393 - time (sec): 7.08 - samples/sec: 1899.89 - lr: 0.000019 - momentum: 0.000000
141
+ 2024-03-26 10:43:00,030 epoch 5 - iter 45/95 - loss 0.11574143 - time (sec): 9.17 - samples/sec: 1857.47 - lr: 0.000019 - momentum: 0.000000
142
+ 2024-03-26 10:43:01,203 epoch 5 - iter 54/95 - loss 0.11686041 - time (sec): 10.35 - samples/sec: 1892.44 - lr: 0.000018 - momentum: 0.000000
143
+ 2024-03-26 10:43:02,679 epoch 5 - iter 63/95 - loss 0.11820642 - time (sec): 11.82 - samples/sec: 1906.99 - lr: 0.000018 - momentum: 0.000000
144
+ 2024-03-26 10:43:04,594 epoch 5 - iter 72/95 - loss 0.11682067 - time (sec): 13.74 - samples/sec: 1879.84 - lr: 0.000018 - momentum: 0.000000
145
+ 2024-03-26 10:43:06,357 epoch 5 - iter 81/95 - loss 0.11463584 - time (sec): 15.50 - samples/sec: 1868.66 - lr: 0.000017 - momentum: 0.000000
146
+ 2024-03-26 10:43:08,774 epoch 5 - iter 90/95 - loss 0.11201321 - time (sec): 17.92 - samples/sec: 1835.01 - lr: 0.000017 - momentum: 0.000000
147
+ 2024-03-26 10:43:09,747 ----------------------------------------------------------------------------------------------------
148
+ 2024-03-26 10:43:09,747 EPOCH 5 done: loss 0.1090 - lr: 0.000017
149
+ 2024-03-26 10:43:10,665 DEV : loss 0.19377665221691132 - f1-score (micro avg) 0.9065
150
+ 2024-03-26 10:43:10,666 saving best model
151
+ 2024-03-26 10:43:11,119 ----------------------------------------------------------------------------------------------------
152
+ 2024-03-26 10:43:13,150 epoch 6 - iter 9/95 - loss 0.10470235 - time (sec): 2.03 - samples/sec: 1606.17 - lr: 0.000016 - momentum: 0.000000
153
+ 2024-03-26 10:43:15,582 epoch 6 - iter 18/95 - loss 0.10237268 - time (sec): 4.46 - samples/sec: 1661.59 - lr: 0.000016 - momentum: 0.000000
154
+ 2024-03-26 10:43:16,733 epoch 6 - iter 27/95 - loss 0.11282455 - time (sec): 5.61 - samples/sec: 1761.06 - lr: 0.000016 - momentum: 0.000000
155
+ 2024-03-26 10:43:18,338 epoch 6 - iter 36/95 - loss 0.10383378 - time (sec): 7.22 - samples/sec: 1787.46 - lr: 0.000016 - momentum: 0.000000
156
+ 2024-03-26 10:43:20,287 epoch 6 - iter 45/95 - loss 0.09688053 - time (sec): 9.17 - samples/sec: 1782.16 - lr: 0.000015 - momentum: 0.000000
157
+ 2024-03-26 10:43:22,434 epoch 6 - iter 54/95 - loss 0.09239524 - time (sec): 11.31 - samples/sec: 1748.98 - lr: 0.000015 - momentum: 0.000000
158
+ 2024-03-26 10:43:24,130 epoch 6 - iter 63/95 - loss 0.09428611 - time (sec): 13.01 - samples/sec: 1765.33 - lr: 0.000015 - momentum: 0.000000
159
+ 2024-03-26 10:43:25,692 epoch 6 - iter 72/95 - loss 0.09316211 - time (sec): 14.57 - samples/sec: 1787.10 - lr: 0.000014 - momentum: 0.000000
160
+ 2024-03-26 10:43:26,931 epoch 6 - iter 81/95 - loss 0.09128789 - time (sec): 15.81 - samples/sec: 1817.96 - lr: 0.000014 - momentum: 0.000000
161
+ 2024-03-26 10:43:28,803 epoch 6 - iter 90/95 - loss 0.08841068 - time (sec): 17.68 - samples/sec: 1817.00 - lr: 0.000014 - momentum: 0.000000
162
+ 2024-03-26 10:43:30,318 ----------------------------------------------------------------------------------------------------
163
+ 2024-03-26 10:43:30,318 EPOCH 6 done: loss 0.0851 - lr: 0.000014
164
+ 2024-03-26 10:43:31,226 DEV : loss 0.17975111305713654 - f1-score (micro avg) 0.9083
165
+ 2024-03-26 10:43:31,227 saving best model
166
+ 2024-03-26 10:43:31,659 ----------------------------------------------------------------------------------------------------
167
+ 2024-03-26 10:43:33,339 epoch 7 - iter 9/95 - loss 0.04434295 - time (sec): 1.68 - samples/sec: 1875.20 - lr: 0.000013 - momentum: 0.000000
168
+ 2024-03-26 10:43:34,833 epoch 7 - iter 18/95 - loss 0.05737186 - time (sec): 3.17 - samples/sec: 1854.04 - lr: 0.000013 - momentum: 0.000000
169
+ 2024-03-26 10:43:36,131 epoch 7 - iter 27/95 - loss 0.07086475 - time (sec): 4.47 - samples/sec: 1894.14 - lr: 0.000013 - momentum: 0.000000
170
+ 2024-03-26 10:43:38,374 epoch 7 - iter 36/95 - loss 0.06375980 - time (sec): 6.71 - samples/sec: 1893.08 - lr: 0.000012 - momentum: 0.000000
171
+ 2024-03-26 10:43:40,286 epoch 7 - iter 45/95 - loss 0.07056595 - time (sec): 8.63 - samples/sec: 1887.67 - lr: 0.000012 - momentum: 0.000000
172
+ 2024-03-26 10:43:41,972 epoch 7 - iter 54/95 - loss 0.06904809 - time (sec): 10.31 - samples/sec: 1880.46 - lr: 0.000012 - momentum: 0.000000
173
+ 2024-03-26 10:43:43,526 epoch 7 - iter 63/95 - loss 0.06977752 - time (sec): 11.87 - samples/sec: 1899.40 - lr: 0.000011 - momentum: 0.000000
174
+ 2024-03-26 10:43:45,039 epoch 7 - iter 72/95 - loss 0.06918325 - time (sec): 13.38 - samples/sec: 1889.29 - lr: 0.000011 - momentum: 0.000000
175
+ 2024-03-26 10:43:47,746 epoch 7 - iter 81/95 - loss 0.06689062 - time (sec): 16.09 - samples/sec: 1826.35 - lr: 0.000011 - momentum: 0.000000
176
+ 2024-03-26 10:43:49,350 epoch 7 - iter 90/95 - loss 0.06702086 - time (sec): 17.69 - samples/sec: 1835.80 - lr: 0.000010 - momentum: 0.000000
177
+ 2024-03-26 10:43:50,524 ----------------------------------------------------------------------------------------------------
178
+ 2024-03-26 10:43:50,524 EPOCH 7 done: loss 0.0651 - lr: 0.000010
179
+ 2024-03-26 10:43:51,429 DEV : loss 0.1919691115617752 - f1-score (micro avg) 0.919
180
+ 2024-03-26 10:43:51,431 saving best model
181
+ 2024-03-26 10:43:51,886 ----------------------------------------------------------------------------------------------------
182
+ 2024-03-26 10:43:54,039 epoch 8 - iter 9/95 - loss 0.06610781 - time (sec): 2.15 - samples/sec: 1570.14 - lr: 0.000010 - momentum: 0.000000
183
+ 2024-03-26 10:43:55,548 epoch 8 - iter 18/95 - loss 0.04891073 - time (sec): 3.66 - samples/sec: 1666.75 - lr: 0.000010 - momentum: 0.000000
184
+ 2024-03-26 10:43:57,528 epoch 8 - iter 27/95 - loss 0.04824918 - time (sec): 5.64 - samples/sec: 1739.20 - lr: 0.000009 - momentum: 0.000000
185
+ 2024-03-26 10:43:59,502 epoch 8 - iter 36/95 - loss 0.04612903 - time (sec): 7.62 - samples/sec: 1767.94 - lr: 0.000009 - momentum: 0.000000
186
+ 2024-03-26 10:44:00,922 epoch 8 - iter 45/95 - loss 0.04536822 - time (sec): 9.04 - samples/sec: 1821.45 - lr: 0.000009 - momentum: 0.000000
187
+ 2024-03-26 10:44:02,407 epoch 8 - iter 54/95 - loss 0.04799100 - time (sec): 10.52 - samples/sec: 1888.93 - lr: 0.000008 - momentum: 0.000000
188
+ 2024-03-26 10:44:03,975 epoch 8 - iter 63/95 - loss 0.05032246 - time (sec): 12.09 - samples/sec: 1881.30 - lr: 0.000008 - momentum: 0.000000
189
+ 2024-03-26 10:44:06,059 epoch 8 - iter 72/95 - loss 0.04831321 - time (sec): 14.17 - samples/sec: 1847.42 - lr: 0.000008 - momentum: 0.000000
190
+ 2024-03-26 10:44:07,625 epoch 8 - iter 81/95 - loss 0.04954977 - time (sec): 15.74 - samples/sec: 1870.96 - lr: 0.000007 - momentum: 0.000000
191
+ 2024-03-26 10:44:09,704 epoch 8 - iter 90/95 - loss 0.05038584 - time (sec): 17.82 - samples/sec: 1845.36 - lr: 0.000007 - momentum: 0.000000
192
+ 2024-03-26 10:44:10,340 ----------------------------------------------------------------------------------------------------
193
+ 2024-03-26 10:44:10,340 EPOCH 8 done: loss 0.0513 - lr: 0.000007
194
+ 2024-03-26 10:44:11,259 DEV : loss 0.18480534851551056 - f1-score (micro avg) 0.9234
195
+ 2024-03-26 10:44:11,260 saving best model
196
+ 2024-03-26 10:44:11,747 ----------------------------------------------------------------------------------------------------
197
+ 2024-03-26 10:44:14,274 epoch 9 - iter 9/95 - loss 0.04107350 - time (sec): 2.52 - samples/sec: 1708.97 - lr: 0.000007 - momentum: 0.000000
198
+ 2024-03-26 10:44:15,817 epoch 9 - iter 18/95 - loss 0.04278555 - time (sec): 4.07 - samples/sec: 1777.85 - lr: 0.000006 - momentum: 0.000000
199
+ 2024-03-26 10:44:18,277 epoch 9 - iter 27/95 - loss 0.04284774 - time (sec): 6.53 - samples/sec: 1731.78 - lr: 0.000006 - momentum: 0.000000
200
+ 2024-03-26 10:44:20,086 epoch 9 - iter 36/95 - loss 0.04627102 - time (sec): 8.34 - samples/sec: 1738.43 - lr: 0.000006 - momentum: 0.000000
201
+ 2024-03-26 10:44:21,245 epoch 9 - iter 45/95 - loss 0.04508424 - time (sec): 9.50 - samples/sec: 1796.22 - lr: 0.000005 - momentum: 0.000000
202
+ 2024-03-26 10:44:22,992 epoch 9 - iter 54/95 - loss 0.04164060 - time (sec): 11.24 - samples/sec: 1784.65 - lr: 0.000005 - momentum: 0.000000
203
+ 2024-03-26 10:44:24,382 epoch 9 - iter 63/95 - loss 0.04372655 - time (sec): 12.63 - samples/sec: 1828.58 - lr: 0.000005 - momentum: 0.000000
204
+ 2024-03-26 10:44:25,554 epoch 9 - iter 72/95 - loss 0.04325581 - time (sec): 13.80 - samples/sec: 1876.77 - lr: 0.000004 - momentum: 0.000000
205
+ 2024-03-26 10:44:27,084 epoch 9 - iter 81/95 - loss 0.04077638 - time (sec): 15.33 - samples/sec: 1873.36 - lr: 0.000004 - momentum: 0.000000
206
+ 2024-03-26 10:44:29,824 epoch 9 - iter 90/95 - loss 0.04197464 - time (sec): 18.07 - samples/sec: 1824.41 - lr: 0.000004 - momentum: 0.000000
207
+ 2024-03-26 10:44:30,596 ----------------------------------------------------------------------------------------------------
208
+ 2024-03-26 10:44:30,596 EPOCH 9 done: loss 0.0407 - lr: 0.000004
209
+ 2024-03-26 10:44:31,501 DEV : loss 0.18239974975585938 - f1-score (micro avg) 0.9226
210
+ 2024-03-26 10:44:31,502 ----------------------------------------------------------------------------------------------------
211
+ 2024-03-26 10:44:33,951 epoch 10 - iter 9/95 - loss 0.04098225 - time (sec): 2.45 - samples/sec: 1648.42 - lr: 0.000003 - momentum: 0.000000
212
+ 2024-03-26 10:44:35,523 epoch 10 - iter 18/95 - loss 0.03496454 - time (sec): 4.02 - samples/sec: 1734.57 - lr: 0.000003 - momentum: 0.000000
213
+ 2024-03-26 10:44:37,487 epoch 10 - iter 27/95 - loss 0.03208139 - time (sec): 5.98 - samples/sec: 1684.20 - lr: 0.000003 - momentum: 0.000000
214
+ 2024-03-26 10:44:39,570 epoch 10 - iter 36/95 - loss 0.03470194 - time (sec): 8.07 - samples/sec: 1691.68 - lr: 0.000002 - momentum: 0.000000
215
+ 2024-03-26 10:44:41,433 epoch 10 - iter 45/95 - loss 0.03231506 - time (sec): 9.93 - samples/sec: 1708.14 - lr: 0.000002 - momentum: 0.000000
216
+ 2024-03-26 10:44:42,579 epoch 10 - iter 54/95 - loss 0.03455335 - time (sec): 11.08 - samples/sec: 1768.88 - lr: 0.000002 - momentum: 0.000000
217
+ 2024-03-26 10:44:44,201 epoch 10 - iter 63/95 - loss 0.03741024 - time (sec): 12.70 - samples/sec: 1792.16 - lr: 0.000001 - momentum: 0.000000
218
+ 2024-03-26 10:44:46,014 epoch 10 - iter 72/95 - loss 0.03685135 - time (sec): 14.51 - samples/sec: 1782.77 - lr: 0.000001 - momentum: 0.000000
219
+ 2024-03-26 10:44:47,684 epoch 10 - iter 81/95 - loss 0.03873599 - time (sec): 16.18 - samples/sec: 1794.43 - lr: 0.000001 - momentum: 0.000000
220
+ 2024-03-26 10:44:50,462 epoch 10 - iter 90/95 - loss 0.03651296 - time (sec): 18.96 - samples/sec: 1758.44 - lr: 0.000000 - momentum: 0.000000
221
+ 2024-03-26 10:44:51,025 ----------------------------------------------------------------------------------------------------
222
+ 2024-03-26 10:44:51,026 EPOCH 10 done: loss 0.0368 - lr: 0.000000
223
+ 2024-03-26 10:44:51,950 DEV : loss 0.18397146463394165 - f1-score (micro avg) 0.9263
224
+ 2024-03-26 10:44:51,952 saving best model
225
+ 2024-03-26 10:44:52,689 ----------------------------------------------------------------------------------------------------
226
+ 2024-03-26 10:44:52,689 Loading model from best epoch ...
227
+ 2024-03-26 10:44:53,611 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
228
+ 2024-03-26 10:44:54,368
229
+ Results:
230
+ - F-score (micro) 0.9063
231
+ - F-score (macro) 0.6881
232
+ - Accuracy 0.8322
233
+
234
+ By class:
235
+ precision recall f1-score support
236
+
237
+ Unternehmen 0.9219 0.8872 0.9042 266
238
+ Auslagerung 0.8638 0.8916 0.8775 249
239
+ Ort 0.9565 0.9851 0.9706 134
240
+ Software 0.0000 0.0000 0.0000 0
241
+
242
+ micro avg 0.9035 0.9091 0.9063 649
243
+ macro avg 0.6856 0.6910 0.6881 649
244
+ weighted avg 0.9068 0.9091 0.9077 649
245
+
246
+ 2024-03-26 10:44:54,369 ----------------------------------------------------------------------------------------------------