Hugging Face's logo

stefan-it
/
flair-co-funer-german_dbmdz_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
3e0f742
•
1 Parent(s): c388944

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 15:43:55,078 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 15:43:55,078 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 15:43:55,078 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 15:43:55,079 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 15:43:55,079 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 15:43:55,079 Train: 758 sentences
54
+ 2024-03-26 15:43:55,079 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 15:43:55,079 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 15:43:55,079 Training Params:
57
+ 2024-03-26 15:43:55,079 - learning_rate: "5e-05"
58
+ 2024-03-26 15:43:55,079 - mini_batch_size: "8"
59
+ 2024-03-26 15:43:55,079 - max_epochs: "10"
60
+ 2024-03-26 15:43:55,079 - shuffle: "True"
61
+ 2024-03-26 15:43:55,079 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 15:43:55,079 Plugins:
63
+ 2024-03-26 15:43:55,079 - TensorboardLogger
64
+ 2024-03-26 15:43:55,079 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 15:43:55,079 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 15:43:55,079 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 15:43:55,079 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 15:43:55,079 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 15:43:55,079 Computation:
70
+ 2024-03-26 15:43:55,079 - compute on device: cuda:0
71
+ 2024-03-26 15:43:55,079 - embedding storage: none
72
+ 2024-03-26 15:43:55,079 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 15:43:55,079 Model training base path: "flair-co-funer-german_dbmdz_bert_base-bs8-e10-lr5e-05-2"
74
+ 2024-03-26 15:43:55,079 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 15:43:55,079 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 15:43:55,079 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 15:43:56,891 epoch 1 - iter 9/95 - loss 3.04906218 - time (sec): 1.81 - samples/sec: 1945.01 - lr: 0.000004 - momentum: 0.000000
78
+ 2024-03-26 15:43:58,966 epoch 1 - iter 18/95 - loss 2.90354229 - time (sec): 3.89 - samples/sec: 1854.23 - lr: 0.000009 - momentum: 0.000000
79
+ 2024-03-26 15:44:00,517 epoch 1 - iter 27/95 - loss 2.67761977 - time (sec): 5.44 - samples/sec: 1854.06 - lr: 0.000014 - momentum: 0.000000
80
+ 2024-03-26 15:44:02,437 epoch 1 - iter 36/95 - loss 2.47492641 - time (sec): 7.36 - samples/sec: 1875.88 - lr: 0.000018 - momentum: 0.000000
81
+ 2024-03-26 15:44:04,489 epoch 1 - iter 45/95 - loss 2.30291695 - time (sec): 9.41 - samples/sec: 1811.90 - lr: 0.000023 - momentum: 0.000000
82
+ 2024-03-26 15:44:06,443 epoch 1 - iter 54/95 - loss 2.13831895 - time (sec): 11.36 - samples/sec: 1786.97 - lr: 0.000028 - momentum: 0.000000
83
+ 2024-03-26 15:44:07,963 epoch 1 - iter 63/95 - loss 2.00131862 - time (sec): 12.88 - samples/sec: 1795.65 - lr: 0.000033 - momentum: 0.000000
84
+ 2024-03-26 15:44:09,208 epoch 1 - iter 72/95 - loss 1.87302257 - time (sec): 14.13 - samples/sec: 1850.86 - lr: 0.000037 - momentum: 0.000000
85
+ 2024-03-26 15:44:10,744 epoch 1 - iter 81/95 - loss 1.75332523 - time (sec): 15.67 - samples/sec: 1877.79 - lr: 0.000042 - momentum: 0.000000
86
+ 2024-03-26 15:44:12,668 epoch 1 - iter 90/95 - loss 1.64074065 - time (sec): 17.59 - samples/sec: 1853.99 - lr: 0.000047 - momentum: 0.000000
87
+ 2024-03-26 15:44:13,717 ----------------------------------------------------------------------------------------------------
88
+ 2024-03-26 15:44:13,717 EPOCH 1 done: loss 1.5782 - lr: 0.000047
89
+ 2024-03-26 15:44:14,599 DEV : loss 0.429016649723053 - f1-score (micro avg) 0.6995
90
+ 2024-03-26 15:44:14,600 saving best model
91
+ 2024-03-26 15:44:14,862 ----------------------------------------------------------------------------------------------------
92
+ 2024-03-26 15:44:16,175 epoch 2 - iter 9/95 - loss 0.55171150 - time (sec): 1.31 - samples/sec: 2472.16 - lr: 0.000050 - momentum: 0.000000
93
+ 2024-03-26 15:44:18,041 epoch 2 - iter 18/95 - loss 0.44710038 - time (sec): 3.18 - samples/sec: 2161.54 - lr: 0.000049 - momentum: 0.000000
94
+ 2024-03-26 15:44:20,841 epoch 2 - iter 27/95 - loss 0.37050551 - time (sec): 5.98 - samples/sec: 1933.54 - lr: 0.000048 - momentum: 0.000000
95
+ 2024-03-26 15:44:22,897 epoch 2 - iter 36/95 - loss 0.35311636 - time (sec): 8.03 - samples/sec: 1850.45 - lr: 0.000048 - momentum: 0.000000
96
+ 2024-03-26 15:44:24,654 epoch 2 - iter 45/95 - loss 0.33135861 - time (sec): 9.79 - samples/sec: 1835.82 - lr: 0.000047 - momentum: 0.000000
97
+ 2024-03-26 15:44:26,731 epoch 2 - iter 54/95 - loss 0.32511028 - time (sec): 11.87 - samples/sec: 1792.70 - lr: 0.000047 - momentum: 0.000000
98
+ 2024-03-26 15:44:28,256 epoch 2 - iter 63/95 - loss 0.33001788 - time (sec): 13.39 - samples/sec: 1817.17 - lr: 0.000046 - momentum: 0.000000
99
+ 2024-03-26 15:44:29,742 epoch 2 - iter 72/95 - loss 0.32705052 - time (sec): 14.88 - samples/sec: 1843.65 - lr: 0.000046 - momentum: 0.000000
100
+ 2024-03-26 15:44:30,906 epoch 2 - iter 81/95 - loss 0.32519771 - time (sec): 16.04 - samples/sec: 1877.87 - lr: 0.000045 - momentum: 0.000000
101
+ 2024-03-26 15:44:32,175 epoch 2 - iter 90/95 - loss 0.31988236 - time (sec): 17.31 - samples/sec: 1900.31 - lr: 0.000045 - momentum: 0.000000
102
+ 2024-03-26 15:44:33,124 ----------------------------------------------------------------------------------------------------
103
+ 2024-03-26 15:44:33,124 EPOCH 2 done: loss 0.3123 - lr: 0.000045
104
+ 2024-03-26 15:44:34,014 DEV : loss 0.25234273076057434 - f1-score (micro avg) 0.8359
105
+ 2024-03-26 15:44:34,015 saving best model
106
+ 2024-03-26 15:44:34,442 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 15:44:36,441 epoch 3 - iter 9/95 - loss 0.15396058 - time (sec): 2.00 - samples/sec: 1667.13 - lr: 0.000044 - momentum: 0.000000
108
+ 2024-03-26 15:44:38,484 epoch 3 - iter 18/95 - loss 0.18281328 - time (sec): 4.04 - samples/sec: 1798.03 - lr: 0.000043 - momentum: 0.000000
109
+ 2024-03-26 15:44:39,437 epoch 3 - iter 27/95 - loss 0.20249771 - time (sec): 4.99 - samples/sec: 1927.75 - lr: 0.000043 - momentum: 0.000000
110
+ 2024-03-26 15:44:41,157 epoch 3 - iter 36/95 - loss 0.20428948 - time (sec): 6.71 - samples/sec: 1890.40 - lr: 0.000042 - momentum: 0.000000
111
+ 2024-03-26 15:44:42,399 epoch 3 - iter 45/95 - loss 0.21368920 - time (sec): 7.95 - samples/sec: 1936.39 - lr: 0.000042 - momentum: 0.000000
112
+ 2024-03-26 15:44:44,409 epoch 3 - iter 54/95 - loss 0.20866549 - time (sec): 9.96 - samples/sec: 1876.21 - lr: 0.000041 - momentum: 0.000000
113
+ 2024-03-26 15:44:46,019 epoch 3 - iter 63/95 - loss 0.20420607 - time (sec): 11.57 - samples/sec: 1885.92 - lr: 0.000041 - momentum: 0.000000
114
+ 2024-03-26 15:44:47,516 epoch 3 - iter 72/95 - loss 0.19797482 - time (sec): 13.07 - samples/sec: 1895.69 - lr: 0.000040 - momentum: 0.000000
115
+ 2024-03-26 15:44:49,294 epoch 3 - iter 81/95 - loss 0.19325066 - time (sec): 14.85 - samples/sec: 1882.62 - lr: 0.000040 - momentum: 0.000000
116
+ 2024-03-26 15:44:51,874 epoch 3 - iter 90/95 - loss 0.17774909 - time (sec): 17.43 - samples/sec: 1876.25 - lr: 0.000039 - momentum: 0.000000
117
+ 2024-03-26 15:44:52,958 ----------------------------------------------------------------------------------------------------
118
+ 2024-03-26 15:44:52,959 EPOCH 3 done: loss 0.1745 - lr: 0.000039
119
+ 2024-03-26 15:44:53,855 DEV : loss 0.2372324913740158 - f1-score (micro avg) 0.8683
120
+ 2024-03-26 15:44:53,858 saving best model
121
+ 2024-03-26 15:44:54,299 ----------------------------------------------------------------------------------------------------
122
+ 2024-03-26 15:44:55,969 epoch 4 - iter 9/95 - loss 0.14538574 - time (sec): 1.67 - samples/sec: 1926.45 - lr: 0.000039 - momentum: 0.000000
123
+ 2024-03-26 15:44:57,933 epoch 4 - iter 18/95 - loss 0.12829142 - time (sec): 3.63 - samples/sec: 1854.32 - lr: 0.000038 - momentum: 0.000000
124
+ 2024-03-26 15:44:59,144 epoch 4 - iter 27/95 - loss 0.13259479 - time (sec): 4.84 - samples/sec: 1943.48 - lr: 0.000037 - momentum: 0.000000
125
+ 2024-03-26 15:45:00,782 epoch 4 - iter 36/95 - loss 0.13132510 - time (sec): 6.48 - samples/sec: 1915.32 - lr: 0.000037 - momentum: 0.000000
126
+ 2024-03-26 15:45:02,907 epoch 4 - iter 45/95 - loss 0.12758950 - time (sec): 8.61 - samples/sec: 1855.40 - lr: 0.000036 - momentum: 0.000000
127
+ 2024-03-26 15:45:04,418 epoch 4 - iter 54/95 - loss 0.13166202 - time (sec): 10.12 - samples/sec: 1865.49 - lr: 0.000036 - momentum: 0.000000
128
+ 2024-03-26 15:45:06,845 epoch 4 - iter 63/95 - loss 0.12800293 - time (sec): 12.54 - samples/sec: 1817.50 - lr: 0.000035 - momentum: 0.000000
129
+ 2024-03-26 15:45:09,327 epoch 4 - iter 72/95 - loss 0.11981137 - time (sec): 15.03 - samples/sec: 1780.27 - lr: 0.000035 - momentum: 0.000000
130
+ 2024-03-26 15:45:10,754 epoch 4 - iter 81/95 - loss 0.11873174 - time (sec): 16.45 - samples/sec: 1786.17 - lr: 0.000034 - momentum: 0.000000
131
+ 2024-03-26 15:45:12,517 epoch 4 - iter 90/95 - loss 0.11781756 - time (sec): 18.22 - samples/sec: 1785.85 - lr: 0.000034 - momentum: 0.000000
132
+ 2024-03-26 15:45:13,628 ----------------------------------------------------------------------------------------------------
133
+ 2024-03-26 15:45:13,628 EPOCH 4 done: loss 0.1153 - lr: 0.000034
134
+ 2024-03-26 15:45:14,535 DEV : loss 0.2066950798034668 - f1-score (micro avg) 0.8863
135
+ 2024-03-26 15:45:14,536 saving best model
136
+ 2024-03-26 15:45:14,976 ----------------------------------------------------------------------------------------------------
137
+ 2024-03-26 15:45:15,943 epoch 5 - iter 9/95 - loss 0.06807319 - time (sec): 0.97 - samples/sec: 2132.15 - lr: 0.000033 - momentum: 0.000000
138
+ 2024-03-26 15:45:17,532 epoch 5 - iter 18/95 - loss 0.08290938 - time (sec): 2.55 - samples/sec: 2083.78 - lr: 0.000032 - momentum: 0.000000
139
+ 2024-03-26 15:45:19,983 epoch 5 - iter 27/95 - loss 0.08255992 - time (sec): 5.01 - samples/sec: 1821.36 - lr: 0.000032 - momentum: 0.000000
140
+ 2024-03-26 15:45:21,822 epoch 5 - iter 36/95 - loss 0.08473432 - time (sec): 6.84 - samples/sec: 1812.71 - lr: 0.000031 - momentum: 0.000000
141
+ 2024-03-26 15:45:23,776 epoch 5 - iter 45/95 - loss 0.08269002 - time (sec): 8.80 - samples/sec: 1776.58 - lr: 0.000031 - momentum: 0.000000
142
+ 2024-03-26 15:45:25,367 epoch 5 - iter 54/95 - loss 0.08277269 - time (sec): 10.39 - samples/sec: 1813.62 - lr: 0.000030 - momentum: 0.000000
143
+ 2024-03-26 15:45:27,697 epoch 5 - iter 63/95 - loss 0.08331892 - time (sec): 12.72 - samples/sec: 1800.68 - lr: 0.000030 - momentum: 0.000000
144
+ 2024-03-26 15:45:29,103 epoch 5 - iter 72/95 - loss 0.08802009 - time (sec): 14.13 - samples/sec: 1818.52 - lr: 0.000029 - momentum: 0.000000
145
+ 2024-03-26 15:45:30,994 epoch 5 - iter 81/95 - loss 0.08437929 - time (sec): 16.02 - samples/sec: 1792.95 - lr: 0.000029 - momentum: 0.000000
146
+ 2024-03-26 15:45:32,837 epoch 5 - iter 90/95 - loss 0.08550405 - time (sec): 17.86 - samples/sec: 1794.86 - lr: 0.000028 - momentum: 0.000000
147
+ 2024-03-26 15:45:34,185 ----------------------------------------------------------------------------------------------------
148
+ 2024-03-26 15:45:34,185 EPOCH 5 done: loss 0.0855 - lr: 0.000028
149
+ 2024-03-26 15:45:35,085 DEV : loss 0.19790305197238922 - f1-score (micro avg) 0.8901
150
+ 2024-03-26 15:45:35,087 saving best model
151
+ 2024-03-26 15:45:35,506 ----------------------------------------------------------------------------------------------------
152
+ 2024-03-26 15:45:36,879 epoch 6 - iter 9/95 - loss 0.05356144 - time (sec): 1.37 - samples/sec: 2100.97 - lr: 0.000027 - momentum: 0.000000
153
+ 2024-03-26 15:45:39,111 epoch 6 - iter 18/95 - loss 0.06201362 - time (sec): 3.60 - samples/sec: 1990.64 - lr: 0.000027 - momentum: 0.000000
154
+ 2024-03-26 15:45:40,667 epoch 6 - iter 27/95 - loss 0.06021193 - time (sec): 5.16 - samples/sec: 1946.92 - lr: 0.000026 - momentum: 0.000000
155
+ 2024-03-26 15:45:42,632 epoch 6 - iter 36/95 - loss 0.06452764 - time (sec): 7.12 - samples/sec: 1895.25 - lr: 0.000026 - momentum: 0.000000
156
+ 2024-03-26 15:45:44,758 epoch 6 - iter 45/95 - loss 0.07905695 - time (sec): 9.25 - samples/sec: 1920.75 - lr: 0.000025 - momentum: 0.000000
157
+ 2024-03-26 15:45:45,947 epoch 6 - iter 54/95 - loss 0.07603800 - time (sec): 10.44 - samples/sec: 1936.71 - lr: 0.000025 - momentum: 0.000000
158
+ 2024-03-26 15:45:47,009 epoch 6 - iter 63/95 - loss 0.07510932 - time (sec): 11.50 - samples/sec: 1957.68 - lr: 0.000024 - momentum: 0.000000
159
+ 2024-03-26 15:45:48,541 epoch 6 - iter 72/95 - loss 0.06975631 - time (sec): 13.03 - samples/sec: 1959.14 - lr: 0.000024 - momentum: 0.000000
160
+ 2024-03-26 15:45:50,541 epoch 6 - iter 81/95 - loss 0.06716849 - time (sec): 15.03 - samples/sec: 1944.87 - lr: 0.000023 - momentum: 0.000000
161
+ 2024-03-26 15:45:52,516 epoch 6 - iter 90/95 - loss 0.06603697 - time (sec): 17.01 - samples/sec: 1933.77 - lr: 0.000023 - momentum: 0.000000
162
+ 2024-03-26 15:45:53,440 ----------------------------------------------------------------------------------------------------
163
+ 2024-03-26 15:45:53,440 EPOCH 6 done: loss 0.0653 - lr: 0.000023
164
+ 2024-03-26 15:45:54,335 DEV : loss 0.19000057876110077 - f1-score (micro avg) 0.9076
165
+ 2024-03-26 15:45:54,336 saving best model
166
+ 2024-03-26 15:45:54,769 ----------------------------------------------------------------------------------------------------
167
+ 2024-03-26 15:45:56,183 epoch 7 - iter 9/95 - loss 0.04441026 - time (sec): 1.41 - samples/sec: 1881.32 - lr: 0.000022 - momentum: 0.000000
168
+ 2024-03-26 15:45:57,977 epoch 7 - iter 18/95 - loss 0.04434418 - time (sec): 3.21 - samples/sec: 1807.29 - lr: 0.000021 - momentum: 0.000000
169
+ 2024-03-26 15:45:59,583 epoch 7 - iter 27/95 - loss 0.04390939 - time (sec): 4.81 - samples/sec: 1895.17 - lr: 0.000021 - momentum: 0.000000
170
+ 2024-03-26 15:46:01,296 epoch 7 - iter 36/95 - loss 0.04576864 - time (sec): 6.53 - samples/sec: 1842.86 - lr: 0.000020 - momentum: 0.000000
171
+ 2024-03-26 15:46:02,652 epoch 7 - iter 45/95 - loss 0.04494806 - time (sec): 7.88 - samples/sec: 1860.17 - lr: 0.000020 - momentum: 0.000000
172
+ 2024-03-26 15:46:04,712 epoch 7 - iter 54/95 - loss 0.04435586 - time (sec): 9.94 - samples/sec: 1802.99 - lr: 0.000019 - momentum: 0.000000
173
+ 2024-03-26 15:46:06,946 epoch 7 - iter 63/95 - loss 0.04482951 - time (sec): 12.18 - samples/sec: 1753.31 - lr: 0.000019 - momentum: 0.000000
174
+ 2024-03-26 15:46:09,500 epoch 7 - iter 72/95 - loss 0.05400091 - time (sec): 14.73 - samples/sec: 1750.13 - lr: 0.000018 - momentum: 0.000000
175
+ 2024-03-26 15:46:11,443 epoch 7 - iter 81/95 - loss 0.05662332 - time (sec): 16.67 - samples/sec: 1757.87 - lr: 0.000018 - momentum: 0.000000
176
+ 2024-03-26 15:46:13,410 epoch 7 - iter 90/95 - loss 0.05734886 - time (sec): 18.64 - samples/sec: 1758.49 - lr: 0.000017 - momentum: 0.000000
177
+ 2024-03-26 15:46:14,303 ----------------------------------------------------------------------------------------------------
178
+ 2024-03-26 15:46:14,304 EPOCH 7 done: loss 0.0558 - lr: 0.000017
179
+ 2024-03-26 15:46:15,199 DEV : loss 0.1933394968509674 - f1-score (micro avg) 0.92
180
+ 2024-03-26 15:46:15,200 saving best model
181
+ 2024-03-26 15:46:15,649 ----------------------------------------------------------------------------------------------------
182
+ 2024-03-26 15:46:17,905 epoch 8 - iter 9/95 - loss 0.03916721 - time (sec): 2.25 - samples/sec: 1681.22 - lr: 0.000016 - momentum: 0.000000
183
+ 2024-03-26 15:46:19,452 epoch 8 - iter 18/95 - loss 0.03789649 - time (sec): 3.80 - samples/sec: 1813.49 - lr: 0.000016 - momentum: 0.000000
184
+ 2024-03-26 15:46:21,612 epoch 8 - iter 27/95 - loss 0.05354041 - time (sec): 5.96 - samples/sec: 1774.02 - lr: 0.000015 - momentum: 0.000000
185
+ 2024-03-26 15:46:23,155 epoch 8 - iter 36/95 - loss 0.04724161 - time (sec): 7.50 - samples/sec: 1798.27 - lr: 0.000015 - momentum: 0.000000
186
+ 2024-03-26 15:46:25,015 epoch 8 - iter 45/95 - loss 0.04108329 - time (sec): 9.36 - samples/sec: 1778.12 - lr: 0.000014 - momentum: 0.000000
187
+ 2024-03-26 15:46:26,701 epoch 8 - iter 54/95 - loss 0.04522755 - time (sec): 11.05 - samples/sec: 1787.98 - lr: 0.000014 - momentum: 0.000000
188
+ 2024-03-26 15:46:28,507 epoch 8 - iter 63/95 - loss 0.04539544 - time (sec): 12.86 - samples/sec: 1786.30 - lr: 0.000013 - momentum: 0.000000
189
+ 2024-03-26 15:46:29,812 epoch 8 - iter 72/95 - loss 0.04420003 - time (sec): 14.16 - samples/sec: 1806.70 - lr: 0.000013 - momentum: 0.000000
190
+ 2024-03-26 15:46:31,633 epoch 8 - iter 81/95 - loss 0.04348041 - time (sec): 15.98 - samples/sec: 1832.19 - lr: 0.000012 - momentum: 0.000000
191
+ 2024-03-26 15:46:34,035 epoch 8 - iter 90/95 - loss 0.04015730 - time (sec): 18.38 - samples/sec: 1794.31 - lr: 0.000012 - momentum: 0.000000
192
+ 2024-03-26 15:46:34,842 ----------------------------------------------------------------------------------------------------
193
+ 2024-03-26 15:46:34,842 EPOCH 8 done: loss 0.0410 - lr: 0.000012
194
+ 2024-03-26 15:46:35,746 DEV : loss 0.22626325488090515 - f1-score (micro avg) 0.9277
195
+ 2024-03-26 15:46:35,747 saving best model
196
+ 2024-03-26 15:46:36,180 ----------------------------------------------------------------------------------------------------
197
+ 2024-03-26 15:46:37,921 epoch 9 - iter 9/95 - loss 0.06402781 - time (sec): 1.74 - samples/sec: 1953.34 - lr: 0.000011 - momentum: 0.000000
198
+ 2024-03-26 15:46:40,109 epoch 9 - iter 18/95 - loss 0.04075891 - time (sec): 3.93 - samples/sec: 1766.04 - lr: 0.000010 - momentum: 0.000000
199
+ 2024-03-26 15:46:41,981 epoch 9 - iter 27/95 - loss 0.04754879 - time (sec): 5.80 - samples/sec: 1799.43 - lr: 0.000010 - momentum: 0.000000
200
+ 2024-03-26 15:46:43,517 epoch 9 - iter 36/95 - loss 0.04592789 - time (sec): 7.33 - samples/sec: 1809.98 - lr: 0.000009 - momentum: 0.000000
201
+ 2024-03-26 15:46:44,918 epoch 9 - iter 45/95 - loss 0.03894026 - time (sec): 8.74 - samples/sec: 1846.68 - lr: 0.000009 - momentum: 0.000000
202
+ 2024-03-26 15:46:46,322 epoch 9 - iter 54/95 - loss 0.03544114 - time (sec): 10.14 - samples/sec: 1896.79 - lr: 0.000008 - momentum: 0.000000
203
+ 2024-03-26 15:46:48,132 epoch 9 - iter 63/95 - loss 0.04097507 - time (sec): 11.95 - samples/sec: 1902.10 - lr: 0.000008 - momentum: 0.000000
204
+ 2024-03-26 15:46:50,128 epoch 9 - iter 72/95 - loss 0.04044040 - time (sec): 13.95 - samples/sec: 1873.16 - lr: 0.000007 - momentum: 0.000000
205
+ 2024-03-26 15:46:52,395 epoch 9 - iter 81/95 - loss 0.04054164 - time (sec): 16.21 - samples/sec: 1830.64 - lr: 0.000007 - momentum: 0.000000
206
+ 2024-03-26 15:46:54,122 epoch 9 - iter 90/95 - loss 0.03879098 - time (sec): 17.94 - samples/sec: 1845.06 - lr: 0.000006 - momentum: 0.000000
207
+ 2024-03-26 15:46:54,706 ----------------------------------------------------------------------------------------------------
208
+ 2024-03-26 15:46:54,706 EPOCH 9 done: loss 0.0376 - lr: 0.000006
209
+ 2024-03-26 15:46:55,606 DEV : loss 0.2059858739376068 - f1-score (micro avg) 0.9262
210
+ 2024-03-26 15:46:55,607 ----------------------------------------------------------------------------------------------------
211
+ 2024-03-26 15:46:57,654 epoch 10 - iter 9/95 - loss 0.00549981 - time (sec): 2.05 - samples/sec: 1887.20 - lr: 0.000005 - momentum: 0.000000
212
+ 2024-03-26 15:46:59,396 epoch 10 - iter 18/95 - loss 0.01199100 - time (sec): 3.79 - samples/sec: 1875.24 - lr: 0.000005 - momentum: 0.000000
213
+ 2024-03-26 15:47:00,503 epoch 10 - iter 27/95 - loss 0.01029262 - time (sec): 4.90 - samples/sec: 1945.52 - lr: 0.000004 - momentum: 0.000000
214
+ 2024-03-26 15:47:02,011 epoch 10 - iter 36/95 - loss 0.01999514 - time (sec): 6.40 - samples/sec: 1955.23 - lr: 0.000004 - momentum: 0.000000
215
+ 2024-03-26 15:47:03,952 epoch 10 - iter 45/95 - loss 0.02876719 - time (sec): 8.34 - samples/sec: 1891.83 - lr: 0.000003 - momentum: 0.000000
216
+ 2024-03-26 15:47:05,038 epoch 10 - iter 54/95 - loss 0.03284923 - time (sec): 9.43 - samples/sec: 1941.08 - lr: 0.000003 - momentum: 0.000000
217
+ 2024-03-26 15:47:06,261 epoch 10 - iter 63/95 - loss 0.02918205 - time (sec): 10.65 - samples/sec: 1969.63 - lr: 0.000002 - momentum: 0.000000
218
+ 2024-03-26 15:47:08,166 epoch 10 - iter 72/95 - loss 0.02945329 - time (sec): 12.56 - samples/sec: 1966.32 - lr: 0.000002 - momentum: 0.000000
219
+ 2024-03-26 15:47:10,805 epoch 10 - iter 81/95 - loss 0.02814755 - time (sec): 15.20 - samples/sec: 1927.41 - lr: 0.000001 - momentum: 0.000000
220
+ 2024-03-26 15:47:12,807 epoch 10 - iter 90/95 - loss 0.02870849 - time (sec): 17.20 - samples/sec: 1907.74 - lr: 0.000001 - momentum: 0.000000
221
+ 2024-03-26 15:47:13,723 ----------------------------------------------------------------------------------------------------
222
+ 2024-03-26 15:47:13,723 EPOCH 10 done: loss 0.0284 - lr: 0.000001
223
+ 2024-03-26 15:47:14,622 DEV : loss 0.22495582699775696 - f1-score (micro avg) 0.928
224
+ 2024-03-26 15:47:14,623 saving best model
225
+ 2024-03-26 15:47:15,360 ----------------------------------------------------------------------------------------------------
226
+ 2024-03-26 15:47:15,360 Loading model from best epoch ...
227
+ 2024-03-26 15:47:16,209 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 15:47:16,955
229
+ Results:
230
+ - F-score (micro) 0.9076
231
+ - F-score (macro) 0.6885
232
+ - Accuracy 0.8331
233
+
234
+ By class:
235
+ precision recall f1-score support
236
+
237
+ Unternehmen 0.9046 0.8910 0.8977 266
238
+ Auslagerung 0.8755 0.9036 0.8893 249
239
+ Ort 0.9496 0.9851 0.9670 134
240
+ Software 0.0000 0.0000 0.0000 0
241
+
242
+ micro avg 0.9000 0.9153 0.9076 649
243
+ macro avg 0.6824 0.6949 0.6885 649
244
+ weighted avg 0.9027 0.9153 0.9088 649
245
+
246
+ 2024-03-26 15:47:16,955 ----------------------------------------------------------------------------------------------------