Hugging Face's logo

stefan-it
/
flair-co-funer-german_bert_base-bs8-e10-lr5e-05-2

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
bfc0b70
•
1 Parent(s): 2905001

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +244 -0
training.log ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-03-26 11:25:08,484 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 11:25:08,484 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(30001, 768)
7
+ (position_embeddings): Embedding(512, 768)
8
+ (token_type_embeddings): Embedding(2, 768)
9
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=768, out_features=768, bias=True)
18
+ (key): Linear(in_features=768, out_features=768, bias=True)
19
+ (value): Linear(in_features=768, out_features=768, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=768, out_features=768, bias=True)
24
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
34
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
35
+ (dropout): Dropout(p=0.1, inplace=False)
36
+ )
37
+ )
38
+ )
39
+ )
40
+ (pooler): BertPooler(
41
+ (dense): Linear(in_features=768, out_features=768, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=768, out_features=17, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2024-03-26 11:25:08,484 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 11:25:08,484 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 11:25:08,484 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 11:25:08,484 Train: 758 sentences
54
+ 2024-03-26 11:25:08,484 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 11:25:08,484 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 11:25:08,484 Training Params:
57
+ 2024-03-26 11:25:08,484 - learning_rate: "5e-05"
58
+ 2024-03-26 11:25:08,484 - mini_batch_size: "8"
59
+ 2024-03-26 11:25:08,484 - max_epochs: "10"
60
+ 2024-03-26 11:25:08,484 - shuffle: "True"
61
+ 2024-03-26 11:25:08,484 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 11:25:08,484 Plugins:
63
+ 2024-03-26 11:25:08,484 - TensorboardLogger
64
+ 2024-03-26 11:25:08,485 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 11:25:08,485 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 11:25:08,485 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 11:25:08,485 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 11:25:08,485 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 11:25:08,485 Computation:
70
+ 2024-03-26 11:25:08,485 - compute on device: cuda:0
71
+ 2024-03-26 11:25:08,485 - embedding storage: none
72
+ 2024-03-26 11:25:08,485 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 11:25:08,485 Model training base path: "flair-co-funer-german_bert_base-bs8-e10-lr5e-05-2"
74
+ 2024-03-26 11:25:08,485 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 11:25:08,485 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 11:25:08,485 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 11:25:10,385 epoch 1 - iter 9/95 - loss 3.09716797 - time (sec): 1.90 - samples/sec: 1854.36 - lr: 0.000004 - momentum: 0.000000
78
+ 2024-03-26 11:25:12,609 epoch 1 - iter 18/95 - loss 2.98425342 - time (sec): 4.12 - samples/sec: 1747.66 - lr: 0.000009 - momentum: 0.000000
79
+ 2024-03-26 11:25:14,206 epoch 1 - iter 27/95 - loss 2.75626977 - time (sec): 5.72 - samples/sec: 1762.22 - lr: 0.000014 - momentum: 0.000000
80
+ 2024-03-26 11:25:16,182 epoch 1 - iter 36/95 - loss 2.52340752 - time (sec): 7.70 - samples/sec: 1793.07 - lr: 0.000018 - momentum: 0.000000
81
+ 2024-03-26 11:25:18,306 epoch 1 - iter 45/95 - loss 2.33537982 - time (sec): 9.82 - samples/sec: 1736.01 - lr: 0.000023 - momentum: 0.000000
82
+ 2024-03-26 11:25:20,363 epoch 1 - iter 54/95 - loss 2.14784687 - time (sec): 11.88 - samples/sec: 1709.56 - lr: 0.000028 - momentum: 0.000000
83
+ 2024-03-26 11:25:21,947 epoch 1 - iter 63/95 - loss 1.99895001 - time (sec): 13.46 - samples/sec: 1718.46 - lr: 0.000033 - momentum: 0.000000
84
+ 2024-03-26 11:25:23,260 epoch 1 - iter 72/95 - loss 1.86613909 - time (sec): 14.77 - samples/sec: 1769.97 - lr: 0.000037 - momentum: 0.000000
85
+ 2024-03-26 11:25:24,845 epoch 1 - iter 81/95 - loss 1.73720955 - time (sec): 16.36 - samples/sec: 1798.08 - lr: 0.000042 - momentum: 0.000000
86
+ 2024-03-26 11:25:26,876 epoch 1 - iter 90/95 - loss 1.62324711 - time (sec): 18.39 - samples/sec: 1773.05 - lr: 0.000047 - momentum: 0.000000
87
+ 2024-03-26 11:25:27,991 ----------------------------------------------------------------------------------------------------
88
+ 2024-03-26 11:25:27,991 EPOCH 1 done: loss 1.5628 - lr: 0.000047
89
+ 2024-03-26 11:25:28,925 DEV : loss 0.42946571111679077 - f1-score (micro avg) 0.6734
90
+ 2024-03-26 11:25:28,926 saving best model
91
+ 2024-03-26 11:25:29,186 ----------------------------------------------------------------------------------------------------
92
+ 2024-03-26 11:25:30,531 epoch 2 - iter 9/95 - loss 0.52425744 - time (sec): 1.34 - samples/sec: 2412.74 - lr: 0.000050 - momentum: 0.000000
93
+ 2024-03-26 11:25:32,418 epoch 2 - iter 18/95 - loss 0.42454204 - time (sec): 3.23 - samples/sec: 2125.97 - lr: 0.000049 - momentum: 0.000000
94
+ 2024-03-26 11:25:35,299 epoch 2 - iter 27/95 - loss 0.35787075 - time (sec): 6.11 - samples/sec: 1890.91 - lr: 0.000048 - momentum: 0.000000
95
+ 2024-03-26 11:25:37,460 epoch 2 - iter 36/95 - loss 0.33935478 - time (sec): 8.27 - samples/sec: 1796.90 - lr: 0.000048 - momentum: 0.000000
96
+ 2024-03-26 11:25:39,264 epoch 2 - iter 45/95 - loss 0.32453877 - time (sec): 10.08 - samples/sec: 1783.53 - lr: 0.000047 - momentum: 0.000000
97
+ 2024-03-26 11:25:41,421 epoch 2 - iter 54/95 - loss 0.31681048 - time (sec): 12.23 - samples/sec: 1739.10 - lr: 0.000047 - momentum: 0.000000
98
+ 2024-03-26 11:25:43,050 epoch 2 - iter 63/95 - loss 0.32280342 - time (sec): 13.86 - samples/sec: 1755.49 - lr: 0.000046 - momentum: 0.000000
99
+ 2024-03-26 11:25:44,582 epoch 2 - iter 72/95 - loss 0.31919664 - time (sec): 15.40 - samples/sec: 1781.82 - lr: 0.000046 - momentum: 0.000000
100
+ 2024-03-26 11:25:45,762 epoch 2 - iter 81/95 - loss 0.31666683 - time (sec): 16.58 - samples/sec: 1817.58 - lr: 0.000045 - momentum: 0.000000
101
+ 2024-03-26 11:25:47,062 epoch 2 - iter 90/95 - loss 0.31133068 - time (sec): 17.88 - samples/sec: 1840.38 - lr: 0.000045 - momentum: 0.000000
102
+ 2024-03-26 11:25:48,058 ----------------------------------------------------------------------------------------------------
103
+ 2024-03-26 11:25:48,058 EPOCH 2 done: loss 0.3026 - lr: 0.000045
104
+ 2024-03-26 11:25:48,986 DEV : loss 0.2420356720685959 - f1-score (micro avg) 0.8595
105
+ 2024-03-26 11:25:48,987 saving best model
106
+ 2024-03-26 11:25:49,407 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 11:25:51,437 epoch 3 - iter 9/95 - loss 0.16715958 - time (sec): 2.03 - samples/sec: 1641.60 - lr: 0.000044 - momentum: 0.000000
108
+ 2024-03-26 11:25:53,556 epoch 3 - iter 18/95 - loss 0.17381845 - time (sec): 4.15 - samples/sec: 1751.20 - lr: 0.000043 - momentum: 0.000000
109
+ 2024-03-26 11:25:54,531 epoch 3 - iter 27/95 - loss 0.17679162 - time (sec): 5.12 - samples/sec: 1878.86 - lr: 0.000043 - momentum: 0.000000
110
+ 2024-03-26 11:25:56,295 epoch 3 - iter 36/95 - loss 0.18025597 - time (sec): 6.89 - samples/sec: 1842.80 - lr: 0.000042 - momentum: 0.000000
111
+ 2024-03-26 11:25:57,578 epoch 3 - iter 45/95 - loss 0.19307875 - time (sec): 8.17 - samples/sec: 1885.50 - lr: 0.000042 - momentum: 0.000000
112
+ 2024-03-26 11:25:59,636 epoch 3 - iter 54/95 - loss 0.19055428 - time (sec): 10.23 - samples/sec: 1828.08 - lr: 0.000041 - momentum: 0.000000
113
+ 2024-03-26 11:26:01,285 epoch 3 - iter 63/95 - loss 0.18895940 - time (sec): 11.88 - samples/sec: 1837.87 - lr: 0.000041 - momentum: 0.000000
114
+ 2024-03-26 11:26:02,859 epoch 3 - iter 72/95 - loss 0.18580014 - time (sec): 13.45 - samples/sec: 1842.25 - lr: 0.000040 - momentum: 0.000000
115
+ 2024-03-26 11:26:04,674 epoch 3 - iter 81/95 - loss 0.17923377 - time (sec): 15.27 - samples/sec: 1831.34 - lr: 0.000040 - momentum: 0.000000
116
+ 2024-03-26 11:26:07,356 epoch 3 - iter 90/95 - loss 0.16261609 - time (sec): 17.95 - samples/sec: 1822.14 - lr: 0.000039 - momentum: 0.000000
117
+ 2024-03-26 11:26:08,536 ----------------------------------------------------------------------------------------------------
118
+ 2024-03-26 11:26:08,536 EPOCH 3 done: loss 0.1590 - lr: 0.000039
119
+ 2024-03-26 11:26:09,461 DEV : loss 0.2054598480463028 - f1-score (micro avg) 0.8766
120
+ 2024-03-26 11:26:09,462 saving best model
121
+ 2024-03-26 11:26:09,906 ----------------------------------------------------------------------------------------------------
122
+ 2024-03-26 11:26:11,637 epoch 4 - iter 9/95 - loss 0.14638681 - time (sec): 1.73 - samples/sec: 1859.05 - lr: 0.000039 - momentum: 0.000000
123
+ 2024-03-26 11:26:13,727 epoch 4 - iter 18/95 - loss 0.12145680 - time (sec): 3.82 - samples/sec: 1763.69 - lr: 0.000038 - momentum: 0.000000
124
+ 2024-03-26 11:26:14,982 epoch 4 - iter 27/95 - loss 0.11451776 - time (sec): 5.07 - samples/sec: 1854.74 - lr: 0.000037 - momentum: 0.000000
125
+ 2024-03-26 11:26:16,682 epoch 4 - iter 36/95 - loss 0.11076776 - time (sec): 6.77 - samples/sec: 1832.49 - lr: 0.000037 - momentum: 0.000000
126
+ 2024-03-26 11:26:18,901 epoch 4 - iter 45/95 - loss 0.11578584 - time (sec): 8.99 - samples/sec: 1775.37 - lr: 0.000036 - momentum: 0.000000
127
+ 2024-03-26 11:26:20,465 epoch 4 - iter 54/95 - loss 0.12488811 - time (sec): 10.56 - samples/sec: 1787.73 - lr: 0.000036 - momentum: 0.000000
128
+ 2024-03-26 11:26:22,981 epoch 4 - iter 63/95 - loss 0.12320034 - time (sec): 13.07 - samples/sec: 1743.98 - lr: 0.000035 - momentum: 0.000000
129
+ 2024-03-26 11:26:25,529 epoch 4 - iter 72/95 - loss 0.11446488 - time (sec): 15.62 - samples/sec: 1712.38 - lr: 0.000035 - momentum: 0.000000
130
+ 2024-03-26 11:26:26,993 epoch 4 - iter 81/95 - loss 0.11224908 - time (sec): 17.09 - samples/sec: 1720.04 - lr: 0.000034 - momentum: 0.000000
131
+ 2024-03-26 11:26:28,824 epoch 4 - iter 90/95 - loss 0.11286006 - time (sec): 18.92 - samples/sec: 1719.75 - lr: 0.000034 - momentum: 0.000000
132
+ 2024-03-26 11:26:29,991 ----------------------------------------------------------------------------------------------------
133
+ 2024-03-26 11:26:29,991 EPOCH 4 done: loss 0.1095 - lr: 0.000034
134
+ 2024-03-26 11:26:30,941 DEV : loss 0.17261318862438202 - f1-score (micro avg) 0.9079
135
+ 2024-03-26 11:26:30,942 saving best model
136
+ 2024-03-26 11:26:31,383 ----------------------------------------------------------------------------------------------------
137
+ 2024-03-26 11:26:32,354 epoch 5 - iter 9/95 - loss 0.06453080 - time (sec): 0.97 - samples/sec: 2125.49 - lr: 0.000033 - momentum: 0.000000
138
+ 2024-03-26 11:26:33,984 epoch 5 - iter 18/95 - loss 0.08104053 - time (sec): 2.60 - samples/sec: 2047.72 - lr: 0.000032 - momentum: 0.000000
139
+ 2024-03-26 11:26:36,556 epoch 5 - iter 27/95 - loss 0.08099319 - time (sec): 5.17 - samples/sec: 1762.87 - lr: 0.000032 - momentum: 0.000000
140
+ 2024-03-26 11:26:38,458 epoch 5 - iter 36/95 - loss 0.07354078 - time (sec): 7.07 - samples/sec: 1753.97 - lr: 0.000031 - momentum: 0.000000
141
+ 2024-03-26 11:26:40,466 epoch 5 - iter 45/95 - loss 0.07068799 - time (sec): 9.08 - samples/sec: 1721.12 - lr: 0.000031 - momentum: 0.000000
142
+ 2024-03-26 11:26:42,119 epoch 5 - iter 54/95 - loss 0.07369301 - time (sec): 10.73 - samples/sec: 1755.40 - lr: 0.000030 - momentum: 0.000000
143
+ 2024-03-26 11:26:44,549 epoch 5 - iter 63/95 - loss 0.07522678 - time (sec): 13.16 - samples/sec: 1739.81 - lr: 0.000030 - momentum: 0.000000
144
+ 2024-03-26 11:26:45,980 epoch 5 - iter 72/95 - loss 0.08100158 - time (sec): 14.60 - samples/sec: 1759.93 - lr: 0.000029 - momentum: 0.000000
145
+ 2024-03-26 11:26:47,908 epoch 5 - iter 81/95 - loss 0.07798969 - time (sec): 16.52 - samples/sec: 1737.95 - lr: 0.000029 - momentum: 0.000000
146
+ 2024-03-26 11:26:49,814 epoch 5 - iter 90/95 - loss 0.07834740 - time (sec): 18.43 - samples/sec: 1739.35 - lr: 0.000028 - momentum: 0.000000
147
+ 2024-03-26 11:26:51,195 ----------------------------------------------------------------------------------------------------
148
+ 2024-03-26 11:26:51,195 EPOCH 5 done: loss 0.0785 - lr: 0.000028
149
+ 2024-03-26 11:26:52,138 DEV : loss 0.18624915182590485 - f1-score (micro avg) 0.9194
150
+ 2024-03-26 11:26:52,141 saving best model
151
+ 2024-03-26 11:26:52,566 ----------------------------------------------------------------------------------------------------
152
+ 2024-03-26 11:26:54,098 epoch 6 - iter 9/95 - loss 0.05414098 - time (sec): 1.53 - samples/sec: 1882.26 - lr: 0.000027 - momentum: 0.000000
153
+ 2024-03-26 11:26:56,308 epoch 6 - iter 18/95 - loss 0.05167176 - time (sec): 3.74 - samples/sec: 1917.26 - lr: 0.000027 - momentum: 0.000000
154
+ 2024-03-26 11:26:57,907 epoch 6 - iter 27/95 - loss 0.05120337 - time (sec): 5.34 - samples/sec: 1881.23 - lr: 0.000026 - momentum: 0.000000
155
+ 2024-03-26 11:26:59,948 epoch 6 - iter 36/95 - loss 0.05928124 - time (sec): 7.38 - samples/sec: 1829.62 - lr: 0.000026 - momentum: 0.000000
156
+ 2024-03-26 11:27:02,159 epoch 6 - iter 45/95 - loss 0.06953449 - time (sec): 9.59 - samples/sec: 1852.31 - lr: 0.000025 - momentum: 0.000000
157
+ 2024-03-26 11:27:03,364 epoch 6 - iter 54/95 - loss 0.06636505 - time (sec): 10.79 - samples/sec: 1872.73 - lr: 0.000025 - momentum: 0.000000
158
+ 2024-03-26 11:27:04,452 epoch 6 - iter 63/95 - loss 0.06537325 - time (sec): 11.88 - samples/sec: 1894.58 - lr: 0.000024 - momentum: 0.000000
159
+ 2024-03-26 11:27:06,016 epoch 6 - iter 72/95 - loss 0.06000050 - time (sec): 13.45 - samples/sec: 1898.69 - lr: 0.000024 - momentum: 0.000000
160
+ 2024-03-26 11:27:08,069 epoch 6 - iter 81/95 - loss 0.05966242 - time (sec): 15.50 - samples/sec: 1886.10 - lr: 0.000023 - momentum: 0.000000
161
+ 2024-03-26 11:27:10,124 epoch 6 - iter 90/95 - loss 0.05915014 - time (sec): 17.56 - samples/sec: 1873.42 - lr: 0.000023 - momentum: 0.000000
162
+ 2024-03-26 11:27:11,088 ----------------------------------------------------------------------------------------------------
163
+ 2024-03-26 11:27:11,088 EPOCH 6 done: loss 0.0573 - lr: 0.000023
164
+ 2024-03-26 11:27:12,028 DEV : loss 0.19410739839076996 - f1-score (micro avg) 0.9256
165
+ 2024-03-26 11:27:12,031 saving best model
166
+ 2024-03-26 11:27:12,463 ----------------------------------------------------------------------------------------------------
167
+ 2024-03-26 11:27:13,906 epoch 7 - iter 9/95 - loss 0.01965996 - time (sec): 1.44 - samples/sec: 1844.63 - lr: 0.000022 - momentum: 0.000000
168
+ 2024-03-26 11:27:15,772 epoch 7 - iter 18/95 - loss 0.03318242 - time (sec): 3.31 - samples/sec: 1752.16 - lr: 0.000021 - momentum: 0.000000
169
+ 2024-03-26 11:27:17,412 epoch 7 - iter 27/95 - loss 0.03102681 - time (sec): 4.95 - samples/sec: 1843.86 - lr: 0.000021 - momentum: 0.000000
170
+ 2024-03-26 11:27:19,183 epoch 7 - iter 36/95 - loss 0.03313823 - time (sec): 6.72 - samples/sec: 1789.96 - lr: 0.000020 - momentum: 0.000000
171
+ 2024-03-26 11:27:20,563 epoch 7 - iter 45/95 - loss 0.03466366 - time (sec): 8.10 - samples/sec: 1810.58 - lr: 0.000020 - momentum: 0.000000
172
+ 2024-03-26 11:27:22,675 epoch 7 - iter 54/95 - loss 0.03377152 - time (sec): 10.21 - samples/sec: 1755.65 - lr: 0.000019 - momentum: 0.000000
173
+ 2024-03-26 11:27:24,978 epoch 7 - iter 63/95 - loss 0.03490540 - time (sec): 12.51 - samples/sec: 1706.02 - lr: 0.000019 - momentum: 0.000000
174
+ 2024-03-26 11:27:27,678 epoch 7 - iter 72/95 - loss 0.04113555 - time (sec): 15.21 - samples/sec: 1694.55 - lr: 0.000018 - momentum: 0.000000
175
+ 2024-03-26 11:27:29,683 epoch 7 - iter 81/95 - loss 0.04662207 - time (sec): 17.22 - samples/sec: 1702.18 - lr: 0.000018 - momentum: 0.000000
176
+ 2024-03-26 11:27:31,707 epoch 7 - iter 90/95 - loss 0.04632564 - time (sec): 19.24 - samples/sec: 1703.41 - lr: 0.000017 - momentum: 0.000000
177
+ 2024-03-26 11:27:32,660 ----------------------------------------------------------------------------------------------------
178
+ 2024-03-26 11:27:32,660 EPOCH 7 done: loss 0.0458 - lr: 0.000017
179
+ 2024-03-26 11:27:33,604 DEV : loss 0.19183886051177979 - f1-score (micro avg) 0.9122
180
+ 2024-03-26 11:27:33,607 ----------------------------------------------------------------------------------------------------
181
+ 2024-03-26 11:27:35,920 epoch 8 - iter 9/95 - loss 0.03236922 - time (sec): 2.31 - samples/sec: 1638.73 - lr: 0.000016 - momentum: 0.000000
182
+ 2024-03-26 11:27:37,498 epoch 8 - iter 18/95 - loss 0.03529936 - time (sec): 3.89 - samples/sec: 1771.62 - lr: 0.000016 - momentum: 0.000000
183
+ 2024-03-26 11:27:39,688 epoch 8 - iter 27/95 - loss 0.04103026 - time (sec): 6.08 - samples/sec: 1738.97 - lr: 0.000015 - momentum: 0.000000
184
+ 2024-03-26 11:27:41,266 epoch 8 - iter 36/95 - loss 0.03739362 - time (sec): 7.66 - samples/sec: 1761.75 - lr: 0.000015 - momentum: 0.000000
185
+ 2024-03-26 11:27:43,191 epoch 8 - iter 45/95 - loss 0.03747045 - time (sec): 9.58 - samples/sec: 1737.32 - lr: 0.000014 - momentum: 0.000000
186
+ 2024-03-26 11:27:44,956 epoch 8 - iter 54/95 - loss 0.03977666 - time (sec): 11.35 - samples/sec: 1740.83 - lr: 0.000014 - momentum: 0.000000
187
+ 2024-03-26 11:27:46,766 epoch 8 - iter 63/95 - loss 0.03873128 - time (sec): 13.16 - samples/sec: 1745.22 - lr: 0.000013 - momentum: 0.000000
188
+ 2024-03-26 11:27:48,092 epoch 8 - iter 72/95 - loss 0.03720393 - time (sec): 14.48 - samples/sec: 1766.25 - lr: 0.000013 - momentum: 0.000000
189
+ 2024-03-26 11:27:49,977 epoch 8 - iter 81/95 - loss 0.03735308 - time (sec): 16.37 - samples/sec: 1788.75 - lr: 0.000012 - momentum: 0.000000
190
+ 2024-03-26 11:27:52,509 epoch 8 - iter 90/95 - loss 0.03457049 - time (sec): 18.90 - samples/sec: 1745.14 - lr: 0.000012 - momentum: 0.000000
191
+ 2024-03-26 11:27:53,363 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 11:27:53,363 EPOCH 8 done: loss 0.0350 - lr: 0.000012
193
+ 2024-03-26 11:27:54,304 DEV : loss 0.19405929744243622 - f1-score (micro avg) 0.9388
194
+ 2024-03-26 11:27:54,305 saving best model
195
+ 2024-03-26 11:27:54,714 ----------------------------------------------------------------------------------------------------
196
+ 2024-03-26 11:27:56,495 epoch 9 - iter 9/95 - loss 0.03300844 - time (sec): 1.78 - samples/sec: 1907.81 - lr: 0.000011 - momentum: 0.000000
197
+ 2024-03-26 11:27:58,733 epoch 9 - iter 18/95 - loss 0.02341987 - time (sec): 4.02 - samples/sec: 1725.89 - lr: 0.000010 - momentum: 0.000000
198
+ 2024-03-26 11:28:00,673 epoch 9 - iter 27/95 - loss 0.03209448 - time (sec): 5.96 - samples/sec: 1751.40 - lr: 0.000010 - momentum: 0.000000
199
+ 2024-03-26 11:28:02,260 epoch 9 - iter 36/95 - loss 0.03363631 - time (sec): 7.55 - samples/sec: 1759.39 - lr: 0.000009 - momentum: 0.000000
200
+ 2024-03-26 11:28:03,712 epoch 9 - iter 45/95 - loss 0.02843998 - time (sec): 9.00 - samples/sec: 1792.89 - lr: 0.000009 - momentum: 0.000000
201
+ 2024-03-26 11:28:05,141 epoch 9 - iter 54/95 - loss 0.02593440 - time (sec): 10.43 - samples/sec: 1844.58 - lr: 0.000008 - momentum: 0.000000
202
+ 2024-03-26 11:28:07,051 epoch 9 - iter 63/95 - loss 0.03115415 - time (sec): 12.34 - samples/sec: 1842.43 - lr: 0.000008 - momentum: 0.000000
203
+ 2024-03-26 11:28:09,104 epoch 9 - iter 72/95 - loss 0.03264374 - time (sec): 14.39 - samples/sec: 1815.38 - lr: 0.000007 - momentum: 0.000000
204
+ 2024-03-26 11:28:11,445 epoch 9 - iter 81/95 - loss 0.03396355 - time (sec): 16.73 - samples/sec: 1774.04 - lr: 0.000007 - momentum: 0.000000
205
+ 2024-03-26 11:28:13,232 epoch 9 - iter 90/95 - loss 0.03292421 - time (sec): 18.52 - samples/sec: 1787.49 - lr: 0.000006 - momentum: 0.000000
206
+ 2024-03-26 11:28:13,832 ----------------------------------------------------------------------------------------------------
207
+ 2024-03-26 11:28:13,832 EPOCH 9 done: loss 0.0325 - lr: 0.000006
208
+ 2024-03-26 11:28:14,774 DEV : loss 0.18781226873397827 - f1-score (micro avg) 0.9312
209
+ 2024-03-26 11:28:14,776 ----------------------------------------------------------------------------------------------------
210
+ 2024-03-26 11:28:16,894 epoch 10 - iter 9/95 - loss 0.00384695 - time (sec): 2.12 - samples/sec: 1823.81 - lr: 0.000005 - momentum: 0.000000
211
+ 2024-03-26 11:28:18,697 epoch 10 - iter 18/95 - loss 0.01394885 - time (sec): 3.92 - samples/sec: 1812.19 - lr: 0.000005 - momentum: 0.000000
212
+ 2024-03-26 11:28:19,808 epoch 10 - iter 27/95 - loss 0.01175287 - time (sec): 5.03 - samples/sec: 1893.10 - lr: 0.000004 - momentum: 0.000000
213
+ 2024-03-26 11:28:21,357 epoch 10 - iter 36/95 - loss 0.01921167 - time (sec): 6.58 - samples/sec: 1902.68 - lr: 0.000004 - momentum: 0.000000
214
+ 2024-03-26 11:28:23,413 epoch 10 - iter 45/95 - loss 0.02733494 - time (sec): 8.64 - samples/sec: 1827.85 - lr: 0.000003 - momentum: 0.000000
215
+ 2024-03-26 11:28:24,524 epoch 10 - iter 54/95 - loss 0.03012670 - time (sec): 9.75 - samples/sec: 1878.06 - lr: 0.000003 - momentum: 0.000000
216
+ 2024-03-26 11:28:25,797 epoch 10 - iter 63/95 - loss 0.02746056 - time (sec): 11.02 - samples/sec: 1904.01 - lr: 0.000002 - momentum: 0.000000
217
+ 2024-03-26 11:28:27,748 epoch 10 - iter 72/95 - loss 0.02769668 - time (sec): 12.97 - samples/sec: 1903.69 - lr: 0.000002 - momentum: 0.000000
218
+ 2024-03-26 11:28:30,400 epoch 10 - iter 81/95 - loss 0.02547260 - time (sec): 15.62 - samples/sec: 1874.86 - lr: 0.000001 - momentum: 0.000000
219
+ 2024-03-26 11:28:32,496 epoch 10 - iter 90/95 - loss 0.02619711 - time (sec): 17.72 - samples/sec: 1851.69 - lr: 0.000001 - momentum: 0.000000
220
+ 2024-03-26 11:28:33,443 ----------------------------------------------------------------------------------------------------
221
+ 2024-03-26 11:28:33,443 EPOCH 10 done: loss 0.0255 - lr: 0.000001
222
+ 2024-03-26 11:28:34,380 DEV : loss 0.2008616179227829 - f1-score (micro avg) 0.9344
223
+ 2024-03-26 11:28:34,663 ----------------------------------------------------------------------------------------------------
224
+ 2024-03-26 11:28:34,663 Loading model from best epoch ...
225
+ 2024-03-26 11:28:35,501 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
226
+ 2024-03-26 11:28:36,262
227
+ Results:
228
+ - F-score (micro) 0.9159
229
+ - F-score (macro) 0.6952
230
+ - Accuracy 0.846
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ Unternehmen 0.9157 0.8985 0.9070 266
236
+ Auslagerung 0.8769 0.9157 0.8959 249
237
+ Ort 0.9706 0.9851 0.9778 134
238
+ Software 0.0000 0.0000 0.0000 0
239
+
240
+ micro avg 0.9090 0.9230 0.9159 649
241
+ macro avg 0.6908 0.6998 0.6952 649
242
+ weighted avg 0.9122 0.9230 0.9174 649
243
+
244
+ 2024-03-26 11:28:36,263 ----------------------------------------------------------------------------------------------------