Hugging Face's logo

stefan-it
/
flair-co-funer-gbert_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
3
stefan-it commited on
Commit
5d2c939
•
1 Parent(s): 9a3fc7e

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +242 -0
training.log ADDED
@@ -0,0 +1,242 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-03-26 09:55:54,516 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 09:55:54,517 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 09:55:54,517 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 09:55:54,517 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 09:55:54,517 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 09:55:54,517 Train: 758 sentences
54
+ 2024-03-26 09:55:54,517 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 09:55:54,517 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 09:55:54,517 Training Params:
57
+ 2024-03-26 09:55:54,517 - learning_rate: "5e-05"
58
+ 2024-03-26 09:55:54,517 - mini_batch_size: "8"
59
+ 2024-03-26 09:55:54,517 - max_epochs: "10"
60
+ 2024-03-26 09:55:54,517 - shuffle: "True"
61
+ 2024-03-26 09:55:54,517 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 09:55:54,517 Plugins:
63
+ 2024-03-26 09:55:54,517 - TensorboardLogger
64
+ 2024-03-26 09:55:54,517 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 09:55:54,517 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 09:55:54,517 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 09:55:54,517 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 09:55:54,517 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 09:55:54,517 Computation:
70
+ 2024-03-26 09:55:54,517 - compute on device: cuda:0
71
+ 2024-03-26 09:55:54,517 - embedding storage: none
72
+ 2024-03-26 09:55:54,517 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 09:55:54,517 Model training base path: "flair-co-funer-gbert_base-bs8-e10-lr5e-05-2"
74
+ 2024-03-26 09:55:54,517 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 09:55:54,517 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 09:55:54,517 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 09:55:56,359 epoch 1 - iter 9/95 - loss 3.51295648 - time (sec): 1.84 - samples/sec: 1913.27 - lr: 0.000004 - momentum: 0.000000
78
+ 2024-03-26 09:55:58,471 epoch 1 - iter 18/95 - loss 3.24148185 - time (sec): 3.95 - samples/sec: 1822.75 - lr: 0.000009 - momentum: 0.000000
79
+ 2024-03-26 09:56:00,044 epoch 1 - iter 27/95 - loss 2.94359502 - time (sec): 5.53 - samples/sec: 1824.22 - lr: 0.000014 - momentum: 0.000000
80
+ 2024-03-26 09:56:01,995 epoch 1 - iter 36/95 - loss 2.72268801 - time (sec): 7.48 - samples/sec: 1845.85 - lr: 0.000018 - momentum: 0.000000
81
+ 2024-03-26 09:56:04,076 epoch 1 - iter 45/95 - loss 2.52912232 - time (sec): 9.56 - samples/sec: 1783.63 - lr: 0.000023 - momentum: 0.000000
82
+ 2024-03-26 09:56:06,050 epoch 1 - iter 54/95 - loss 2.35533618 - time (sec): 11.53 - samples/sec: 1760.66 - lr: 0.000028 - momentum: 0.000000
83
+ 2024-03-26 09:56:07,584 epoch 1 - iter 63/95 - loss 2.22092888 - time (sec): 13.07 - samples/sec: 1770.48 - lr: 0.000033 - momentum: 0.000000
84
+ 2024-03-26 09:56:08,848 epoch 1 - iter 72/95 - loss 2.07343945 - time (sec): 14.33 - samples/sec: 1824.85 - lr: 0.000037 - momentum: 0.000000
85
+ 2024-03-26 09:56:10,406 epoch 1 - iter 81/95 - loss 1.94077724 - time (sec): 15.89 - samples/sec: 1851.36 - lr: 0.000042 - momentum: 0.000000
86
+ 2024-03-26 09:56:12,341 epoch 1 - iter 90/95 - loss 1.81672289 - time (sec): 17.82 - samples/sec: 1829.55 - lr: 0.000047 - momentum: 0.000000
87
+ 2024-03-26 09:56:13,406 ----------------------------------------------------------------------------------------------------
88
+ 2024-03-26 09:56:13,406 EPOCH 1 done: loss 1.7469 - lr: 0.000047
89
+ 2024-03-26 09:56:14,309 DEV : loss 0.4293653666973114 - f1-score (micro avg) 0.7027
90
+ 2024-03-26 09:56:14,310 saving best model
91
+ 2024-03-26 09:56:14,570 ----------------------------------------------------------------------------------------------------
92
+ 2024-03-26 09:56:15,883 epoch 2 - iter 9/95 - loss 0.60874536 - time (sec): 1.31 - samples/sec: 2473.32 - lr: 0.000050 - momentum: 0.000000
93
+ 2024-03-26 09:56:17,748 epoch 2 - iter 18/95 - loss 0.49896854 - time (sec): 3.18 - samples/sec: 2162.35 - lr: 0.000049 - momentum: 0.000000
94
+ 2024-03-26 09:56:20,547 epoch 2 - iter 27/95 - loss 0.41484753 - time (sec): 5.98 - samples/sec: 1934.16 - lr: 0.000048 - momentum: 0.000000
95
+ 2024-03-26 09:56:22,603 epoch 2 - iter 36/95 - loss 0.39641865 - time (sec): 8.03 - samples/sec: 1850.91 - lr: 0.000048 - momentum: 0.000000
96
+ 2024-03-26 09:56:24,354 epoch 2 - iter 45/95 - loss 0.37116751 - time (sec): 9.78 - samples/sec: 1837.44 - lr: 0.000047 - momentum: 0.000000
97
+ 2024-03-26 09:56:26,443 epoch 2 - iter 54/95 - loss 0.35768210 - time (sec): 11.87 - samples/sec: 1792.21 - lr: 0.000047 - momentum: 0.000000
98
+ 2024-03-26 09:56:27,969 epoch 2 - iter 63/95 - loss 0.36146991 - time (sec): 13.40 - samples/sec: 1816.49 - lr: 0.000046 - momentum: 0.000000
99
+ 2024-03-26 09:56:29,446 epoch 2 - iter 72/95 - loss 0.35422116 - time (sec): 14.87 - samples/sec: 1844.21 - lr: 0.000046 - momentum: 0.000000
100
+ 2024-03-26 09:56:30,605 epoch 2 - iter 81/95 - loss 0.34979111 - time (sec): 16.03 - samples/sec: 1878.96 - lr: 0.000045 - momentum: 0.000000
101
+ 2024-03-26 09:56:31,880 epoch 2 - iter 90/95 - loss 0.34698102 - time (sec): 17.31 - samples/sec: 1900.71 - lr: 0.000045 - momentum: 0.000000
102
+ 2024-03-26 09:56:32,837 ----------------------------------------------------------------------------------------------------
103
+ 2024-03-26 09:56:32,837 EPOCH 2 done: loss 0.3378 - lr: 0.000045
104
+ 2024-03-26 09:56:33,723 DEV : loss 0.25087055563926697 - f1-score (micro avg) 0.8296
105
+ 2024-03-26 09:56:33,724 saving best model
106
+ 2024-03-26 09:56:34,168 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 09:56:36,165 epoch 3 - iter 9/95 - loss 0.18016583 - time (sec): 2.00 - samples/sec: 1668.07 - lr: 0.000044 - momentum: 0.000000
108
+ 2024-03-26 09:56:38,211 epoch 3 - iter 18/95 - loss 0.20468785 - time (sec): 4.04 - samples/sec: 1796.92 - lr: 0.000043 - momentum: 0.000000
109
+ 2024-03-26 09:56:39,167 epoch 3 - iter 27/95 - loss 0.22616043 - time (sec): 5.00 - samples/sec: 1925.55 - lr: 0.000043 - momentum: 0.000000
110
+ 2024-03-26 09:56:40,892 epoch 3 - iter 36/95 - loss 0.22034828 - time (sec): 6.72 - samples/sec: 1887.55 - lr: 0.000042 - momentum: 0.000000
111
+ 2024-03-26 09:56:42,136 epoch 3 - iter 45/95 - loss 0.22037517 - time (sec): 7.97 - samples/sec: 1933.42 - lr: 0.000042 - momentum: 0.000000
112
+ 2024-03-26 09:56:44,155 epoch 3 - iter 54/95 - loss 0.21422754 - time (sec): 9.99 - samples/sec: 1872.38 - lr: 0.000041 - momentum: 0.000000
113
+ 2024-03-26 09:56:45,763 epoch 3 - iter 63/95 - loss 0.20959317 - time (sec): 11.59 - samples/sec: 1882.81 - lr: 0.000041 - momentum: 0.000000
114
+ 2024-03-26 09:56:47,260 epoch 3 - iter 72/95 - loss 0.20513440 - time (sec): 13.09 - samples/sec: 1892.83 - lr: 0.000040 - momentum: 0.000000
115
+ 2024-03-26 09:56:49,036 epoch 3 - iter 81/95 - loss 0.19871669 - time (sec): 14.87 - samples/sec: 1880.58 - lr: 0.000040 - momentum: 0.000000
116
+ 2024-03-26 09:56:51,620 epoch 3 - iter 90/95 - loss 0.18183164 - time (sec): 17.45 - samples/sec: 1874.07 - lr: 0.000039 - momentum: 0.000000
117
+ 2024-03-26 09:56:52,702 ----------------------------------------------------------------------------------------------------
118
+ 2024-03-26 09:56:52,702 EPOCH 3 done: loss 0.1792 - lr: 0.000039
119
+ 2024-03-26 09:56:53,591 DEV : loss 0.22550131380558014 - f1-score (micro avg) 0.8869
120
+ 2024-03-26 09:56:53,591 saving best model
121
+ 2024-03-26 09:56:54,016 ----------------------------------------------------------------------------------------------------
122
+ 2024-03-26 09:56:55,692 epoch 4 - iter 9/95 - loss 0.16564534 - time (sec): 1.67 - samples/sec: 1918.92 - lr: 0.000039 - momentum: 0.000000
123
+ 2024-03-26 09:56:57,658 epoch 4 - iter 18/95 - loss 0.14460325 - time (sec): 3.64 - samples/sec: 1850.14 - lr: 0.000038 - momentum: 0.000000
124
+ 2024-03-26 09:56:58,873 epoch 4 - iter 27/95 - loss 0.13705328 - time (sec): 4.86 - samples/sec: 1938.49 - lr: 0.000037 - momentum: 0.000000
125
+ 2024-03-26 09:57:00,516 epoch 4 - iter 36/95 - loss 0.13381213 - time (sec): 6.50 - samples/sec: 1910.14 - lr: 0.000037 - momentum: 0.000000
126
+ 2024-03-26 09:57:02,650 epoch 4 - iter 45/95 - loss 0.13001690 - time (sec): 8.63 - samples/sec: 1849.74 - lr: 0.000036 - momentum: 0.000000
127
+ 2024-03-26 09:57:04,167 epoch 4 - iter 54/95 - loss 0.13595740 - time (sec): 10.15 - samples/sec: 1859.49 - lr: 0.000036 - momentum: 0.000000
128
+ 2024-03-26 09:57:06,602 epoch 4 - iter 63/95 - loss 0.13274558 - time (sec): 12.58 - samples/sec: 1811.67 - lr: 0.000035 - momentum: 0.000000
129
+ 2024-03-26 09:57:09,090 epoch 4 - iter 72/95 - loss 0.12565390 - time (sec): 15.07 - samples/sec: 1774.73 - lr: 0.000035 - momentum: 0.000000
130
+ 2024-03-26 09:57:10,512 epoch 4 - iter 81/95 - loss 0.12269682 - time (sec): 16.49 - samples/sec: 1781.62 - lr: 0.000034 - momentum: 0.000000
131
+ 2024-03-26 09:57:12,279 epoch 4 - iter 90/95 - loss 0.12294753 - time (sec): 18.26 - samples/sec: 1781.38 - lr: 0.000034 - momentum: 0.000000
132
+ 2024-03-26 09:57:13,394 ----------------------------------------------------------------------------------------------------
133
+ 2024-03-26 09:57:13,394 EPOCH 4 done: loss 0.1198 - lr: 0.000034
134
+ 2024-03-26 09:57:14,288 DEV : loss 0.19063404202461243 - f1-score (micro avg) 0.877
135
+ 2024-03-26 09:57:14,289 ----------------------------------------------------------------------------------------------------
136
+ 2024-03-26 09:57:15,247 epoch 5 - iter 9/95 - loss 0.07671720 - time (sec): 0.96 - samples/sec: 2150.56 - lr: 0.000033 - momentum: 0.000000
137
+ 2024-03-26 09:57:16,837 epoch 5 - iter 18/95 - loss 0.08732704 - time (sec): 2.55 - samples/sec: 2089.09 - lr: 0.000032 - momentum: 0.000000
138
+ 2024-03-26 09:57:19,294 epoch 5 - iter 27/95 - loss 0.08678902 - time (sec): 5.00 - samples/sec: 1821.53 - lr: 0.000032 - momentum: 0.000000
139
+ 2024-03-26 09:57:21,118 epoch 5 - iter 36/95 - loss 0.08229238 - time (sec): 6.83 - samples/sec: 1816.91 - lr: 0.000031 - momentum: 0.000000
140
+ 2024-03-26 09:57:23,067 epoch 5 - iter 45/95 - loss 0.08039814 - time (sec): 8.78 - samples/sec: 1780.80 - lr: 0.000031 - momentum: 0.000000
141
+ 2024-03-26 09:57:24,661 epoch 5 - iter 54/95 - loss 0.08120875 - time (sec): 10.37 - samples/sec: 1816.90 - lr: 0.000030 - momentum: 0.000000
142
+ 2024-03-26 09:57:26,989 epoch 5 - iter 63/95 - loss 0.07961933 - time (sec): 12.70 - samples/sec: 1803.60 - lr: 0.000030 - momentum: 0.000000
143
+ 2024-03-26 09:57:28,389 epoch 5 - iter 72/95 - loss 0.08356768 - time (sec): 14.10 - samples/sec: 1821.80 - lr: 0.000029 - momentum: 0.000000
144
+ 2024-03-26 09:57:30,275 epoch 5 - iter 81/95 - loss 0.08023690 - time (sec): 15.99 - samples/sec: 1796.39 - lr: 0.000029 - momentum: 0.000000
145
+ 2024-03-26 09:57:32,125 epoch 5 - iter 90/95 - loss 0.08106053 - time (sec): 17.84 - samples/sec: 1797.19 - lr: 0.000028 - momentum: 0.000000
146
+ 2024-03-26 09:57:33,476 ----------------------------------------------------------------------------------------------------
147
+ 2024-03-26 09:57:33,476 EPOCH 5 done: loss 0.0808 - lr: 0.000028
148
+ 2024-03-26 09:57:34,464 DEV : loss 0.16919878125190735 - f1-score (micro avg) 0.9171
149
+ 2024-03-26 09:57:34,465 saving best model
150
+ 2024-03-26 09:57:34,895 ----------------------------------------------------------------------------------------------------
151
+ 2024-03-26 09:57:36,259 epoch 6 - iter 9/95 - loss 0.05513905 - time (sec): 1.36 - samples/sec: 2113.60 - lr: 0.000027 - momentum: 0.000000
152
+ 2024-03-26 09:57:38,408 epoch 6 - iter 18/95 - loss 0.05798422 - time (sec): 3.51 - samples/sec: 2042.14 - lr: 0.000027 - momentum: 0.000000
153
+ 2024-03-26 09:57:39,966 epoch 6 - iter 27/95 - loss 0.05351134 - time (sec): 5.07 - samples/sec: 1980.67 - lr: 0.000026 - momentum: 0.000000
154
+ 2024-03-26 09:57:41,933 epoch 6 - iter 36/95 - loss 0.05595926 - time (sec): 7.04 - samples/sec: 1918.68 - lr: 0.000026 - momentum: 0.000000
155
+ 2024-03-26 09:57:44,066 epoch 6 - iter 45/95 - loss 0.06826327 - time (sec): 9.17 - samples/sec: 1937.30 - lr: 0.000025 - momentum: 0.000000
156
+ 2024-03-26 09:57:45,252 epoch 6 - iter 54/95 - loss 0.06442393 - time (sec): 10.36 - samples/sec: 1952.25 - lr: 0.000025 - momentum: 0.000000
157
+ 2024-03-26 09:57:46,310 epoch 6 - iter 63/95 - loss 0.06557445 - time (sec): 11.41 - samples/sec: 1972.50 - lr: 0.000024 - momentum: 0.000000
158
+ 2024-03-26 09:57:47,834 epoch 6 - iter 72/95 - loss 0.06074062 - time (sec): 12.94 - samples/sec: 1973.50 - lr: 0.000024 - momentum: 0.000000
159
+ 2024-03-26 09:57:49,828 epoch 6 - iter 81/95 - loss 0.05887365 - time (sec): 14.93 - samples/sec: 1957.97 - lr: 0.000023 - momentum: 0.000000
160
+ 2024-03-26 09:57:51,808 epoch 6 - iter 90/95 - loss 0.05836864 - time (sec): 16.91 - samples/sec: 1944.79 - lr: 0.000023 - momentum: 0.000000
161
+ 2024-03-26 09:57:52,732 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 09:57:52,732 EPOCH 6 done: loss 0.0565 - lr: 0.000023
163
+ 2024-03-26 09:57:53,630 DEV : loss 0.1597478985786438 - f1-score (micro avg) 0.935
164
+ 2024-03-26 09:57:53,631 saving best model
165
+ 2024-03-26 09:57:54,057 ----------------------------------------------------------------------------------------------------
166
+ 2024-03-26 09:57:55,485 epoch 7 - iter 9/95 - loss 0.03244858 - time (sec): 1.43 - samples/sec: 1864.42 - lr: 0.000022 - momentum: 0.000000
167
+ 2024-03-26 09:57:57,279 epoch 7 - iter 18/95 - loss 0.03958068 - time (sec): 3.22 - samples/sec: 1800.01 - lr: 0.000021 - momentum: 0.000000
168
+ 2024-03-26 09:57:58,885 epoch 7 - iter 27/95 - loss 0.03643340 - time (sec): 4.82 - samples/sec: 1890.63 - lr: 0.000021 - momentum: 0.000000
169
+ 2024-03-26 09:58:00,601 epoch 7 - iter 36/95 - loss 0.03750744 - time (sec): 6.54 - samples/sec: 1838.53 - lr: 0.000020 - momentum: 0.000000
170
+ 2024-03-26 09:58:01,955 epoch 7 - iter 45/95 - loss 0.03833106 - time (sec): 7.90 - samples/sec: 1856.99 - lr: 0.000020 - momentum: 0.000000
171
+ 2024-03-26 09:58:04,002 epoch 7 - iter 54/95 - loss 0.03880059 - time (sec): 9.94 - samples/sec: 1803.00 - lr: 0.000019 - momentum: 0.000000
172
+ 2024-03-26 09:58:06,229 epoch 7 - iter 63/95 - loss 0.03928334 - time (sec): 12.17 - samples/sec: 1754.30 - lr: 0.000019 - momentum: 0.000000
173
+ 2024-03-26 09:58:08,782 epoch 7 - iter 72/95 - loss 0.04446132 - time (sec): 14.72 - samples/sec: 1751.07 - lr: 0.000018 - momentum: 0.000000
174
+ 2024-03-26 09:58:10,730 epoch 7 - iter 81/95 - loss 0.04659624 - time (sec): 16.67 - samples/sec: 1758.17 - lr: 0.000018 - momentum: 0.000000
175
+ 2024-03-26 09:58:12,692 epoch 7 - iter 90/95 - loss 0.04764396 - time (sec): 18.63 - samples/sec: 1759.23 - lr: 0.000017 - momentum: 0.000000
176
+ 2024-03-26 09:58:13,582 ----------------------------------------------------------------------------------------------------
177
+ 2024-03-26 09:58:13,582 EPOCH 7 done: loss 0.0462 - lr: 0.000017
178
+ 2024-03-26 09:58:14,481 DEV : loss 0.1805838942527771 - f1-score (micro avg) 0.9222
179
+ 2024-03-26 09:58:14,482 ----------------------------------------------------------------------------------------------------
180
+ 2024-03-26 09:58:16,739 epoch 8 - iter 9/95 - loss 0.03112277 - time (sec): 2.26 - samples/sec: 1678.52 - lr: 0.000016 - momentum: 0.000000
181
+ 2024-03-26 09:58:18,290 epoch 8 - iter 18/95 - loss 0.03749051 - time (sec): 3.81 - samples/sec: 1809.73 - lr: 0.000016 - momentum: 0.000000
182
+ 2024-03-26 09:58:20,455 epoch 8 - iter 27/95 - loss 0.04423972 - time (sec): 5.97 - samples/sec: 1770.15 - lr: 0.000015 - momentum: 0.000000
183
+ 2024-03-26 09:58:21,995 epoch 8 - iter 36/95 - loss 0.03953226 - time (sec): 7.51 - samples/sec: 1795.95 - lr: 0.000015 - momentum: 0.000000
184
+ 2024-03-26 09:58:23,855 epoch 8 - iter 45/95 - loss 0.03510558 - time (sec): 9.37 - samples/sec: 1776.30 - lr: 0.000014 - momentum: 0.000000
185
+ 2024-03-26 09:58:25,542 epoch 8 - iter 54/95 - loss 0.04168451 - time (sec): 11.06 - samples/sec: 1786.17 - lr: 0.000014 - momentum: 0.000000
186
+ 2024-03-26 09:58:27,341 epoch 8 - iter 63/95 - loss 0.04091545 - time (sec): 12.86 - samples/sec: 1785.80 - lr: 0.000013 - momentum: 0.000000
187
+ 2024-03-26 09:58:28,638 epoch 8 - iter 72/95 - loss 0.03864673 - time (sec): 14.16 - samples/sec: 1807.18 - lr: 0.000013 - momentum: 0.000000
188
+ 2024-03-26 09:58:30,461 epoch 8 - iter 81/95 - loss 0.03694964 - time (sec): 15.98 - samples/sec: 1832.46 - lr: 0.000012 - momentum: 0.000000
189
+ 2024-03-26 09:58:32,860 epoch 8 - iter 90/95 - loss 0.03440669 - time (sec): 18.38 - samples/sec: 1794.90 - lr: 0.000012 - momentum: 0.000000
190
+ 2024-03-26 09:58:33,664 ----------------------------------------------------------------------------------------------------
191
+ 2024-03-26 09:58:33,664 EPOCH 8 done: loss 0.0361 - lr: 0.000012
192
+ 2024-03-26 09:58:34,570 DEV : loss 0.20250095427036285 - f1-score (micro avg) 0.9227
193
+ 2024-03-26 09:58:34,571 ----------------------------------------------------------------------------------------------------
194
+ 2024-03-26 09:58:36,320 epoch 9 - iter 9/95 - loss 0.04686787 - time (sec): 1.75 - samples/sec: 1942.96 - lr: 0.000011 - momentum: 0.000000
195
+ 2024-03-26 09:58:38,509 epoch 9 - iter 18/95 - loss 0.02950774 - time (sec): 3.94 - samples/sec: 1761.42 - lr: 0.000010 - momentum: 0.000000
196
+ 2024-03-26 09:58:40,380 epoch 9 - iter 27/95 - loss 0.03881406 - time (sec): 5.81 - samples/sec: 1796.36 - lr: 0.000010 - momentum: 0.000000
197
+ 2024-03-26 09:58:41,918 epoch 9 - iter 36/95 - loss 0.03710701 - time (sec): 7.35 - samples/sec: 1807.00 - lr: 0.000009 - momentum: 0.000000
198
+ 2024-03-26 09:58:43,318 epoch 9 - iter 45/95 - loss 0.03227612 - time (sec): 8.75 - samples/sec: 1844.24 - lr: 0.000009 - momentum: 0.000000
199
+ 2024-03-26 09:58:44,720 epoch 9 - iter 54/95 - loss 0.02974616 - time (sec): 10.15 - samples/sec: 1895.14 - lr: 0.000008 - momentum: 0.000000
200
+ 2024-03-26 09:58:46,529 epoch 9 - iter 63/95 - loss 0.03186545 - time (sec): 11.96 - samples/sec: 1900.89 - lr: 0.000008 - momentum: 0.000000
201
+ 2024-03-26 09:58:48,529 epoch 9 - iter 72/95 - loss 0.03279052 - time (sec): 13.96 - samples/sec: 1871.55 - lr: 0.000007 - momentum: 0.000000
202
+ 2024-03-26 09:58:50,796 epoch 9 - iter 81/95 - loss 0.03338961 - time (sec): 16.22 - samples/sec: 1829.34 - lr: 0.000007 - momentum: 0.000000
203
+ 2024-03-26 09:58:52,521 epoch 9 - iter 90/95 - loss 0.03218886 - time (sec): 17.95 - samples/sec: 1844.02 - lr: 0.000006 - momentum: 0.000000
204
+ 2024-03-26 09:58:53,105 ----------------------------------------------------------------------------------------------------
205
+ 2024-03-26 09:58:53,105 EPOCH 9 done: loss 0.0313 - lr: 0.000006
206
+ 2024-03-26 09:58:54,013 DEV : loss 0.194478839635849 - f1-score (micro avg) 0.9333
207
+ 2024-03-26 09:58:54,016 ----------------------------------------------------------------------------------------------------
208
+ 2024-03-26 09:58:56,147 epoch 10 - iter 9/95 - loss 0.00307710 - time (sec): 2.13 - samples/sec: 1812.59 - lr: 0.000005 - momentum: 0.000000
209
+ 2024-03-26 09:58:57,890 epoch 10 - iter 18/95 - loss 0.01367119 - time (sec): 3.87 - samples/sec: 1833.86 - lr: 0.000005 - momentum: 0.000000
210
+ 2024-03-26 09:58:58,993 epoch 10 - iter 27/95 - loss 0.01197108 - time (sec): 4.98 - samples/sec: 1913.69 - lr: 0.000004 - momentum: 0.000000
211
+ 2024-03-26 09:59:00,434 epoch 10 - iter 36/95 - loss 0.01892848 - time (sec): 6.42 - samples/sec: 1950.84 - lr: 0.000004 - momentum: 0.000000
212
+ 2024-03-26 09:59:02,371 epoch 10 - iter 45/95 - loss 0.02347308 - time (sec): 8.35 - samples/sec: 1889.33 - lr: 0.000003 - momentum: 0.000000
213
+ 2024-03-26 09:59:03,458 epoch 10 - iter 54/95 - loss 0.02477599 - time (sec): 9.44 - samples/sec: 1938.85 - lr: 0.000003 - momentum: 0.000000
214
+ 2024-03-26 09:59:04,679 epoch 10 - iter 63/95 - loss 0.02232245 - time (sec): 10.66 - samples/sec: 1967.89 - lr: 0.000002 - momentum: 0.000000
215
+ 2024-03-26 09:59:06,585 epoch 10 - iter 72/95 - loss 0.02358988 - time (sec): 12.57 - samples/sec: 1964.69 - lr: 0.000002 - momentum: 0.000000
216
+ 2024-03-26 09:59:09,224 epoch 10 - iter 81/95 - loss 0.02309473 - time (sec): 15.21 - samples/sec: 1926.11 - lr: 0.000001 - momentum: 0.000000
217
+ 2024-03-26 09:59:11,224 epoch 10 - iter 90/95 - loss 0.02402159 - time (sec): 17.21 - samples/sec: 1906.77 - lr: 0.000001 - momentum: 0.000000
218
+ 2024-03-26 09:59:12,141 ----------------------------------------------------------------------------------------------------
219
+ 2024-03-26 09:59:12,141 EPOCH 10 done: loss 0.0238 - lr: 0.000001
220
+ 2024-03-26 09:59:13,096 DEV : loss 0.20281948149204254 - f1-score (micro avg) 0.9285
221
+ 2024-03-26 09:59:13,379 ----------------------------------------------------------------------------------------------------
222
+ 2024-03-26 09:59:13,380 Loading model from best epoch ...
223
+ 2024-03-26 09:59:14,264 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
224
+ 2024-03-26 09:59:15,009
225
+ Results:
226
+ - F-score (micro) 0.9117
227
+ - F-score (macro) 0.692
228
+ - Accuracy 0.8402
229
+
230
+ By class:
231
+ precision recall f1-score support
232
+
233
+ Unternehmen 0.9328 0.8872 0.9094 266
234
+ Auslagerung 0.8626 0.9076 0.8845 249
235
+ Ort 0.9635 0.9851 0.9742 134
236
+ Software 0.0000 0.0000 0.0000 0
237
+
238
+ micro avg 0.9083 0.9153 0.9117 649
239
+ macro avg 0.6897 0.6950 0.6920 649
240
+ weighted avg 0.9122 0.9153 0.9133 649
241
+
242
+ 2024-03-26 09:59:15,009 ----------------------------------------------------------------------------------------------------