Hugging Face's logo

stefan-it
/
flair-co-funer-gbert_base-bs16-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
3f0e079
·
verified ·
1 Parent(s): 7729642

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +266 -0
training.log ADDED
@@ -0,0 +1,266 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-03-26 10:32:23,127 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 10:32:23,128 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 10:32:23,128 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 10:32:23,128 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 10:32:23,128 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 10:32:23,128 Train: 758 sentences
54
+ 2024-03-26 10:32:23,128 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 10:32:23,128 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 10:32:23,128 Training Params:
57
+ 2024-03-26 10:32:23,128 - learning_rate: "3e-05"
58
+ 2024-03-26 10:32:23,128 - mini_batch_size: "16"
59
+ 2024-03-26 10:32:23,128 - max_epochs: "10"
60
+ 2024-03-26 10:32:23,128 - shuffle: "True"
61
+ 2024-03-26 10:32:23,128 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 10:32:23,128 Plugins:
63
+ 2024-03-26 10:32:23,128 - TensorboardLogger
64
+ 2024-03-26 10:32:23,128 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 10:32:23,128 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 10:32:23,128 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 10:32:23,128 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 10:32:23,128 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 10:32:23,128 Computation:
70
+ 2024-03-26 10:32:23,128 - compute on device: cuda:0
71
+ 2024-03-26 10:32:23,128 - embedding storage: none
72
+ 2024-03-26 10:32:23,128 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 10:32:23,128 Model training base path: "flair-co-funer-gbert_base-bs16-e10-lr3e-05-5"
74
+ 2024-03-26 10:32:23,128 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 10:32:23,128 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 10:32:23,128 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 10:32:24,598 epoch 1 - iter 4/48 - loss 3.42174338 - time (sec): 1.47 - samples/sec: 1783.63 - lr: 0.000002 - momentum: 0.000000
78
+ 2024-03-26 10:32:27,269 epoch 1 - iter 8/48 - loss 3.34969237 - time (sec): 4.14 - samples/sec: 1469.88 - lr: 0.000004 - momentum: 0.000000
79
+ 2024-03-26 10:32:29,096 epoch 1 - iter 12/48 - loss 3.21022744 - time (sec): 5.97 - samples/sec: 1492.57 - lr: 0.000007 - momentum: 0.000000
80
+ 2024-03-26 10:32:30,643 epoch 1 - iter 16/48 - loss 3.08575155 - time (sec): 7.52 - samples/sec: 1600.92 - lr: 0.000009 - momentum: 0.000000
81
+ 2024-03-26 10:32:32,765 epoch 1 - iter 20/48 - loss 2.96305669 - time (sec): 9.64 - samples/sec: 1564.66 - lr: 0.000012 - momentum: 0.000000
82
+ 2024-03-26 10:32:35,464 epoch 1 - iter 24/48 - loss 2.80357407 - time (sec): 12.34 - samples/sec: 1495.63 - lr: 0.000014 - momentum: 0.000000
83
+ 2024-03-26 10:32:37,074 epoch 1 - iter 28/48 - loss 2.70398010 - time (sec): 13.95 - samples/sec: 1504.87 - lr: 0.000017 - momentum: 0.000000
84
+ 2024-03-26 10:32:39,150 epoch 1 - iter 32/48 - loss 2.59920726 - time (sec): 16.02 - samples/sec: 1500.36 - lr: 0.000019 - momentum: 0.000000
85
+ 2024-03-26 10:32:40,684 epoch 1 - iter 36/48 - loss 2.51975944 - time (sec): 17.56 - samples/sec: 1520.78 - lr: 0.000022 - momentum: 0.000000
86
+ 2024-03-26 10:32:43,449 epoch 1 - iter 40/48 - loss 2.42029873 - time (sec): 20.32 - samples/sec: 1471.62 - lr: 0.000024 - momentum: 0.000000
87
+ 2024-03-26 10:32:44,635 epoch 1 - iter 44/48 - loss 2.34834067 - time (sec): 21.51 - samples/sec: 1494.53 - lr: 0.000027 - momentum: 0.000000
88
+ 2024-03-26 10:32:46,460 epoch 1 - iter 48/48 - loss 2.28449819 - time (sec): 23.33 - samples/sec: 1477.49 - lr: 0.000029 - momentum: 0.000000
89
+ 2024-03-26 10:32:46,460 ----------------------------------------------------------------------------------------------------
90
+ 2024-03-26 10:32:46,460 EPOCH 1 done: loss 2.2845 - lr: 0.000029
91
+ 2024-03-26 10:32:47,268 DEV : loss 0.9604241847991943 - f1-score (micro avg) 0.3618
92
+ 2024-03-26 10:32:47,270 saving best model
93
+ 2024-03-26 10:32:47,541 ----------------------------------------------------------------------------------------------------
94
+ 2024-03-26 10:32:50,227 epoch 2 - iter 4/48 - loss 1.28816124 - time (sec): 2.69 - samples/sec: 1285.61 - lr: 0.000030 - momentum: 0.000000
95
+ 2024-03-26 10:32:52,063 epoch 2 - iter 8/48 - loss 1.17022404 - time (sec): 4.52 - samples/sec: 1355.15 - lr: 0.000030 - momentum: 0.000000
96
+ 2024-03-26 10:32:53,954 epoch 2 - iter 12/48 - loss 1.08807460 - time (sec): 6.41 - samples/sec: 1391.37 - lr: 0.000029 - momentum: 0.000000
97
+ 2024-03-26 10:32:56,597 epoch 2 - iter 16/48 - loss 1.00135461 - time (sec): 9.06 - samples/sec: 1397.48 - lr: 0.000029 - momentum: 0.000000
98
+ 2024-03-26 10:32:57,967 epoch 2 - iter 20/48 - loss 0.95421133 - time (sec): 10.43 - samples/sec: 1436.97 - lr: 0.000029 - momentum: 0.000000
99
+ 2024-03-26 10:33:00,756 epoch 2 - iter 24/48 - loss 0.89570225 - time (sec): 13.22 - samples/sec: 1354.36 - lr: 0.000028 - momentum: 0.000000
100
+ 2024-03-26 10:33:02,346 epoch 2 - iter 28/48 - loss 0.87277024 - time (sec): 14.80 - samples/sec: 1388.82 - lr: 0.000028 - momentum: 0.000000
101
+ 2024-03-26 10:33:04,346 epoch 2 - iter 32/48 - loss 0.83120939 - time (sec): 16.80 - samples/sec: 1381.65 - lr: 0.000028 - momentum: 0.000000
102
+ 2024-03-26 10:33:06,098 epoch 2 - iter 36/48 - loss 0.80333747 - time (sec): 18.56 - samples/sec: 1412.40 - lr: 0.000028 - momentum: 0.000000
103
+ 2024-03-26 10:33:08,454 epoch 2 - iter 40/48 - loss 0.78653155 - time (sec): 20.91 - samples/sec: 1399.75 - lr: 0.000027 - momentum: 0.000000
104
+ 2024-03-26 10:33:10,633 epoch 2 - iter 44/48 - loss 0.75591748 - time (sec): 23.09 - samples/sec: 1404.58 - lr: 0.000027 - momentum: 0.000000
105
+ 2024-03-26 10:33:11,882 epoch 2 - iter 48/48 - loss 0.74272218 - time (sec): 24.34 - samples/sec: 1416.25 - lr: 0.000027 - momentum: 0.000000
106
+ 2024-03-26 10:33:11,882 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 10:33:11,882 EPOCH 2 done: loss 0.7427 - lr: 0.000027
108
+ 2024-03-26 10:33:12,826 DEV : loss 0.40468811988830566 - f1-score (micro avg) 0.7292
109
+ 2024-03-26 10:33:12,829 saving best model
110
+ 2024-03-26 10:33:13,266 ----------------------------------------------------------------------------------------------------
111
+ 2024-03-26 10:33:14,352 epoch 3 - iter 4/48 - loss 0.49596632 - time (sec): 1.08 - samples/sec: 2058.76 - lr: 0.000026 - momentum: 0.000000
112
+ 2024-03-26 10:33:16,238 epoch 3 - iter 8/48 - loss 0.46225213 - time (sec): 2.97 - samples/sec: 1659.01 - lr: 0.000026 - momentum: 0.000000
113
+ 2024-03-26 10:33:18,449 epoch 3 - iter 12/48 - loss 0.42796127 - time (sec): 5.18 - samples/sec: 1655.05 - lr: 0.000026 - momentum: 0.000000
114
+ 2024-03-26 10:33:20,399 epoch 3 - iter 16/48 - loss 0.42776954 - time (sec): 7.13 - samples/sec: 1595.06 - lr: 0.000026 - momentum: 0.000000
115
+ 2024-03-26 10:33:22,249 epoch 3 - iter 20/48 - loss 0.41446283 - time (sec): 8.98 - samples/sec: 1578.55 - lr: 0.000025 - momentum: 0.000000
116
+ 2024-03-26 10:33:24,188 epoch 3 - iter 24/48 - loss 0.39349862 - time (sec): 10.92 - samples/sec: 1535.14 - lr: 0.000025 - momentum: 0.000000
117
+ 2024-03-26 10:33:27,365 epoch 3 - iter 28/48 - loss 0.38449578 - time (sec): 14.10 - samples/sec: 1420.00 - lr: 0.000025 - momentum: 0.000000
118
+ 2024-03-26 10:33:28,862 epoch 3 - iter 32/48 - loss 0.38744582 - time (sec): 15.59 - samples/sec: 1444.44 - lr: 0.000025 - momentum: 0.000000
119
+ 2024-03-26 10:33:32,145 epoch 3 - iter 36/48 - loss 0.37499873 - time (sec): 18.88 - samples/sec: 1374.10 - lr: 0.000024 - momentum: 0.000000
120
+ 2024-03-26 10:33:34,511 epoch 3 - iter 40/48 - loss 0.37551102 - time (sec): 21.24 - samples/sec: 1377.47 - lr: 0.000024 - momentum: 0.000000
121
+ 2024-03-26 10:33:36,637 epoch 3 - iter 44/48 - loss 0.36375984 - time (sec): 23.37 - samples/sec: 1373.08 - lr: 0.000024 - momentum: 0.000000
122
+ 2024-03-26 10:33:38,217 epoch 3 - iter 48/48 - loss 0.35890800 - time (sec): 24.95 - samples/sec: 1381.71 - lr: 0.000023 - momentum: 0.000000
123
+ 2024-03-26 10:33:38,217 ----------------------------------------------------------------------------------------------------
124
+ 2024-03-26 10:33:38,217 EPOCH 3 done: loss 0.3589 - lr: 0.000023
125
+ 2024-03-26 10:33:39,112 DEV : loss 0.27302658557891846 - f1-score (micro avg) 0.8268
126
+ 2024-03-26 10:33:39,113 saving best model
127
+ 2024-03-26 10:33:39,570 ----------------------------------------------------------------------------------------------------
128
+ 2024-03-26 10:33:42,514 epoch 4 - iter 4/48 - loss 0.19657748 - time (sec): 2.94 - samples/sec: 1268.10 - lr: 0.000023 - momentum: 0.000000
129
+ 2024-03-26 10:33:44,032 epoch 4 - iter 8/48 - loss 0.26531707 - time (sec): 4.46 - samples/sec: 1394.75 - lr: 0.000023 - momentum: 0.000000
130
+ 2024-03-26 10:33:46,535 epoch 4 - iter 12/48 - loss 0.23600165 - time (sec): 6.96 - samples/sec: 1335.78 - lr: 0.000023 - momentum: 0.000000
131
+ 2024-03-26 10:33:49,184 epoch 4 - iter 16/48 - loss 0.22424944 - time (sec): 9.61 - samples/sec: 1320.94 - lr: 0.000022 - momentum: 0.000000
132
+ 2024-03-26 10:33:51,440 epoch 4 - iter 20/48 - loss 0.22450465 - time (sec): 11.87 - samples/sec: 1329.79 - lr: 0.000022 - momentum: 0.000000
133
+ 2024-03-26 10:33:52,949 epoch 4 - iter 24/48 - loss 0.21775032 - time (sec): 13.38 - samples/sec: 1362.99 - lr: 0.000022 - momentum: 0.000000
134
+ 2024-03-26 10:33:55,323 epoch 4 - iter 28/48 - loss 0.21925009 - time (sec): 15.75 - samples/sec: 1348.67 - lr: 0.000022 - momentum: 0.000000
135
+ 2024-03-26 10:33:58,301 epoch 4 - iter 32/48 - loss 0.21788102 - time (sec): 18.73 - samples/sec: 1338.14 - lr: 0.000021 - momentum: 0.000000
136
+ 2024-03-26 10:33:59,940 epoch 4 - iter 36/48 - loss 0.22148320 - time (sec): 20.37 - samples/sec: 1362.82 - lr: 0.000021 - momentum: 0.000000
137
+ 2024-03-26 10:34:00,924 epoch 4 - iter 40/48 - loss 0.22402948 - time (sec): 21.35 - samples/sec: 1406.42 - lr: 0.000021 - momentum: 0.000000
138
+ 2024-03-26 10:34:02,373 epoch 4 - iter 44/48 - loss 0.22269543 - time (sec): 22.80 - samples/sec: 1426.91 - lr: 0.000020 - momentum: 0.000000
139
+ 2024-03-26 10:34:03,248 epoch 4 - iter 48/48 - loss 0.22546892 - time (sec): 23.68 - samples/sec: 1456.04 - lr: 0.000020 - momentum: 0.000000
140
+ 2024-03-26 10:34:03,249 ----------------------------------------------------------------------------------------------------
141
+ 2024-03-26 10:34:03,249 EPOCH 4 done: loss 0.2255 - lr: 0.000020
142
+ 2024-03-26 10:34:04,178 DEV : loss 0.21694348752498627 - f1-score (micro avg) 0.8668
143
+ 2024-03-26 10:34:04,179 saving best model
144
+ 2024-03-26 10:34:04,626 ----------------------------------------------------------------------------------------------------
145
+ 2024-03-26 10:34:06,458 epoch 5 - iter 4/48 - loss 0.19428206 - time (sec): 1.83 - samples/sec: 1568.42 - lr: 0.000020 - momentum: 0.000000
146
+ 2024-03-26 10:34:08,320 epoch 5 - iter 8/48 - loss 0.17767071 - time (sec): 3.69 - samples/sec: 1680.03 - lr: 0.000020 - momentum: 0.000000
147
+ 2024-03-26 10:34:11,423 epoch 5 - iter 12/48 - loss 0.16683946 - time (sec): 6.80 - samples/sec: 1415.75 - lr: 0.000019 - momentum: 0.000000
148
+ 2024-03-26 10:34:12,740 epoch 5 - iter 16/48 - loss 0.16232137 - time (sec): 8.11 - samples/sec: 1465.64 - lr: 0.000019 - momentum: 0.000000
149
+ 2024-03-26 10:34:15,012 epoch 5 - iter 20/48 - loss 0.17440101 - time (sec): 10.39 - samples/sec: 1450.97 - lr: 0.000019 - momentum: 0.000000
150
+ 2024-03-26 10:34:17,156 epoch 5 - iter 24/48 - loss 0.17192285 - time (sec): 12.53 - samples/sec: 1418.79 - lr: 0.000018 - momentum: 0.000000
151
+ 2024-03-26 10:34:18,518 epoch 5 - iter 28/48 - loss 0.17925284 - time (sec): 13.89 - samples/sec: 1460.83 - lr: 0.000018 - momentum: 0.000000
152
+ 2024-03-26 10:34:19,893 epoch 5 - iter 32/48 - loss 0.17792134 - time (sec): 15.27 - samples/sec: 1493.34 - lr: 0.000018 - momentum: 0.000000
153
+ 2024-03-26 10:34:22,020 epoch 5 - iter 36/48 - loss 0.17567673 - time (sec): 17.39 - samples/sec: 1484.72 - lr: 0.000018 - momentum: 0.000000
154
+ 2024-03-26 10:34:23,851 epoch 5 - iter 40/48 - loss 0.17203264 - time (sec): 19.22 - samples/sec: 1482.94 - lr: 0.000017 - momentum: 0.000000
155
+ 2024-03-26 10:34:25,850 epoch 5 - iter 44/48 - loss 0.16894302 - time (sec): 21.22 - samples/sec: 1495.78 - lr: 0.000017 - momentum: 0.000000
156
+ 2024-03-26 10:34:27,967 epoch 5 - iter 48/48 - loss 0.16401284 - time (sec): 23.34 - samples/sec: 1476.91 - lr: 0.000017 - momentum: 0.000000
157
+ 2024-03-26 10:34:27,968 ----------------------------------------------------------------------------------------------------
158
+ 2024-03-26 10:34:27,968 EPOCH 5 done: loss 0.1640 - lr: 0.000017
159
+ 2024-03-26 10:34:28,903 DEV : loss 0.18316593766212463 - f1-score (micro avg) 0.8989
160
+ 2024-03-26 10:34:28,904 saving best model
161
+ 2024-03-26 10:34:29,357 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 10:34:31,248 epoch 6 - iter 4/48 - loss 0.11402572 - time (sec): 1.89 - samples/sec: 1452.03 - lr: 0.000017 - momentum: 0.000000
163
+ 2024-03-26 10:34:33,993 epoch 6 - iter 8/48 - loss 0.13108460 - time (sec): 4.64 - samples/sec: 1371.26 - lr: 0.000016 - momentum: 0.000000
164
+ 2024-03-26 10:34:35,896 epoch 6 - iter 12/48 - loss 0.13466569 - time (sec): 6.54 - samples/sec: 1381.02 - lr: 0.000016 - momentum: 0.000000
165
+ 2024-03-26 10:34:37,391 epoch 6 - iter 16/48 - loss 0.14181831 - time (sec): 8.03 - samples/sec: 1440.26 - lr: 0.000016 - momentum: 0.000000
166
+ 2024-03-26 10:34:40,086 epoch 6 - iter 20/48 - loss 0.13391803 - time (sec): 10.73 - samples/sec: 1359.11 - lr: 0.000015 - momentum: 0.000000
167
+ 2024-03-26 10:34:42,753 epoch 6 - iter 24/48 - loss 0.12515977 - time (sec): 13.40 - samples/sec: 1333.77 - lr: 0.000015 - momentum: 0.000000
168
+ 2024-03-26 10:34:45,203 epoch 6 - iter 28/48 - loss 0.12156669 - time (sec): 15.84 - samples/sec: 1309.57 - lr: 0.000015 - momentum: 0.000000
169
+ 2024-03-26 10:34:46,575 epoch 6 - iter 32/48 - loss 0.12956941 - time (sec): 17.22 - samples/sec: 1354.12 - lr: 0.000015 - momentum: 0.000000
170
+ 2024-03-26 10:34:48,427 epoch 6 - iter 36/48 - loss 0.12512582 - time (sec): 19.07 - samples/sec: 1365.67 - lr: 0.000014 - momentum: 0.000000
171
+ 2024-03-26 10:34:49,401 epoch 6 - iter 40/48 - loss 0.12510773 - time (sec): 20.04 - samples/sec: 1407.42 - lr: 0.000014 - momentum: 0.000000
172
+ 2024-03-26 10:34:51,921 epoch 6 - iter 44/48 - loss 0.12302160 - time (sec): 22.56 - samples/sec: 1378.98 - lr: 0.000014 - momentum: 0.000000
173
+ 2024-03-26 10:34:54,677 epoch 6 - iter 48/48 - loss 0.11948777 - time (sec): 25.32 - samples/sec: 1361.49 - lr: 0.000014 - momentum: 0.000000
174
+ 2024-03-26 10:34:54,677 ----------------------------------------------------------------------------------------------------
175
+ 2024-03-26 10:34:54,677 EPOCH 6 done: loss 0.1195 - lr: 0.000014
176
+ 2024-03-26 10:34:55,602 DEV : loss 0.17593741416931152 - f1-score (micro avg) 0.9047
177
+ 2024-03-26 10:34:55,603 saving best model
178
+ 2024-03-26 10:34:56,043 ----------------------------------------------------------------------------------------------------
179
+ 2024-03-26 10:34:58,190 epoch 7 - iter 4/48 - loss 0.07193929 - time (sec): 2.15 - samples/sec: 1355.94 - lr: 0.000013 - momentum: 0.000000
180
+ 2024-03-26 10:34:59,884 epoch 7 - iter 8/48 - loss 0.07829483 - time (sec): 3.84 - samples/sec: 1388.19 - lr: 0.000013 - momentum: 0.000000
181
+ 2024-03-26 10:35:01,302 epoch 7 - iter 12/48 - loss 0.09926755 - time (sec): 5.26 - samples/sec: 1443.79 - lr: 0.000013 - momentum: 0.000000
182
+ 2024-03-26 10:35:03,166 epoch 7 - iter 16/48 - loss 0.09217692 - time (sec): 7.12 - samples/sec: 1490.81 - lr: 0.000012 - momentum: 0.000000
183
+ 2024-03-26 10:35:05,426 epoch 7 - iter 20/48 - loss 0.10826327 - time (sec): 9.38 - samples/sec: 1544.71 - lr: 0.000012 - momentum: 0.000000
184
+ 2024-03-26 10:35:06,765 epoch 7 - iter 24/48 - loss 0.10534646 - time (sec): 10.72 - samples/sec: 1589.25 - lr: 0.000012 - momentum: 0.000000
185
+ 2024-03-26 10:35:08,993 epoch 7 - iter 28/48 - loss 0.10590492 - time (sec): 12.95 - samples/sec: 1540.41 - lr: 0.000012 - momentum: 0.000000
186
+ 2024-03-26 10:35:10,852 epoch 7 - iter 32/48 - loss 0.10727827 - time (sec): 14.81 - samples/sec: 1537.67 - lr: 0.000011 - momentum: 0.000000
187
+ 2024-03-26 10:35:12,826 epoch 7 - iter 36/48 - loss 0.10332516 - time (sec): 16.78 - samples/sec: 1506.23 - lr: 0.000011 - momentum: 0.000000
188
+ 2024-03-26 10:35:15,604 epoch 7 - iter 40/48 - loss 0.09911907 - time (sec): 19.56 - samples/sec: 1489.04 - lr: 0.000011 - momentum: 0.000000
189
+ 2024-03-26 10:35:17,089 epoch 7 - iter 44/48 - loss 0.10167987 - time (sec): 21.04 - samples/sec: 1504.90 - lr: 0.000010 - momentum: 0.000000
190
+ 2024-03-26 10:35:19,230 epoch 7 - iter 48/48 - loss 0.09882403 - time (sec): 23.19 - samples/sec: 1486.78 - lr: 0.000010 - momentum: 0.000000
191
+ 2024-03-26 10:35:19,231 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 10:35:19,231 EPOCH 7 done: loss 0.0988 - lr: 0.000010
193
+ 2024-03-26 10:35:20,253 DEV : loss 0.1646314412355423 - f1-score (micro avg) 0.9061
194
+ 2024-03-26 10:35:20,255 saving best model
195
+ 2024-03-26 10:35:20,700 ----------------------------------------------------------------------------------------------------
196
+ 2024-03-26 10:35:22,898 epoch 8 - iter 4/48 - loss 0.11098392 - time (sec): 2.20 - samples/sec: 1268.70 - lr: 0.000010 - momentum: 0.000000
197
+ 2024-03-26 10:35:24,438 epoch 8 - iter 8/48 - loss 0.07876314 - time (sec): 3.74 - samples/sec: 1454.16 - lr: 0.000010 - momentum: 0.000000
198
+ 2024-03-26 10:35:27,315 epoch 8 - iter 12/48 - loss 0.07330689 - time (sec): 6.61 - samples/sec: 1360.55 - lr: 0.000009 - momentum: 0.000000
199
+ 2024-03-26 10:35:29,741 epoch 8 - iter 16/48 - loss 0.07476028 - time (sec): 9.04 - samples/sec: 1358.86 - lr: 0.000009 - momentum: 0.000000
200
+ 2024-03-26 10:35:31,169 epoch 8 - iter 20/48 - loss 0.07344860 - time (sec): 10.47 - samples/sec: 1418.97 - lr: 0.000009 - momentum: 0.000000
201
+ 2024-03-26 10:35:32,574 epoch 8 - iter 24/48 - loss 0.07668558 - time (sec): 11.87 - samples/sec: 1490.26 - lr: 0.000009 - momentum: 0.000000
202
+ 2024-03-26 10:35:33,889 epoch 8 - iter 28/48 - loss 0.07782502 - time (sec): 13.19 - samples/sec: 1550.34 - lr: 0.000008 - momentum: 0.000000
203
+ 2024-03-26 10:35:36,042 epoch 8 - iter 32/48 - loss 0.07998551 - time (sec): 15.34 - samples/sec: 1510.12 - lr: 0.000008 - momentum: 0.000000
204
+ 2024-03-26 10:35:38,563 epoch 8 - iter 36/48 - loss 0.07829167 - time (sec): 17.86 - samples/sec: 1465.75 - lr: 0.000008 - momentum: 0.000000
205
+ 2024-03-26 10:35:40,493 epoch 8 - iter 40/48 - loss 0.07846917 - time (sec): 19.79 - samples/sec: 1474.58 - lr: 0.000007 - momentum: 0.000000
206
+ 2024-03-26 10:35:42,623 epoch 8 - iter 44/48 - loss 0.07975602 - time (sec): 21.92 - samples/sec: 1457.06 - lr: 0.000007 - momentum: 0.000000
207
+ 2024-03-26 10:35:44,229 epoch 8 - iter 48/48 - loss 0.07998176 - time (sec): 23.53 - samples/sec: 1465.11 - lr: 0.000007 - momentum: 0.000000
208
+ 2024-03-26 10:35:44,229 ----------------------------------------------------------------------------------------------------
209
+ 2024-03-26 10:35:44,229 EPOCH 8 done: loss 0.0800 - lr: 0.000007
210
+ 2024-03-26 10:35:45,173 DEV : loss 0.15970855951309204 - f1-score (micro avg) 0.9157
211
+ 2024-03-26 10:35:45,174 saving best model
212
+ 2024-03-26 10:35:45,649 ----------------------------------------------------------------------------------------------------
213
+ 2024-03-26 10:35:48,341 epoch 9 - iter 4/48 - loss 0.08143347 - time (sec): 2.69 - samples/sec: 1300.71 - lr: 0.000007 - momentum: 0.000000
214
+ 2024-03-26 10:35:50,382 epoch 9 - iter 8/48 - loss 0.06854402 - time (sec): 4.73 - samples/sec: 1349.75 - lr: 0.000006 - momentum: 0.000000
215
+ 2024-03-26 10:35:53,210 epoch 9 - iter 12/48 - loss 0.06763631 - time (sec): 7.56 - samples/sec: 1286.71 - lr: 0.000006 - momentum: 0.000000
216
+ 2024-03-26 10:35:56,316 epoch 9 - iter 16/48 - loss 0.07652995 - time (sec): 10.67 - samples/sec: 1260.55 - lr: 0.000006 - momentum: 0.000000
217
+ 2024-03-26 10:35:57,193 epoch 9 - iter 20/48 - loss 0.07456477 - time (sec): 11.54 - samples/sec: 1349.45 - lr: 0.000006 - momentum: 0.000000
218
+ 2024-03-26 10:35:59,066 epoch 9 - iter 24/48 - loss 0.07180523 - time (sec): 13.42 - samples/sec: 1343.61 - lr: 0.000005 - momentum: 0.000000
219
+ 2024-03-26 10:36:01,066 epoch 9 - iter 28/48 - loss 0.07078084 - time (sec): 15.42 - samples/sec: 1358.35 - lr: 0.000005 - momentum: 0.000000
220
+ 2024-03-26 10:36:02,055 epoch 9 - iter 32/48 - loss 0.07277106 - time (sec): 16.41 - samples/sec: 1424.08 - lr: 0.000005 - momentum: 0.000000
221
+ 2024-03-26 10:36:03,174 epoch 9 - iter 36/48 - loss 0.07325922 - time (sec): 17.52 - samples/sec: 1478.45 - lr: 0.000004 - momentum: 0.000000
222
+ 2024-03-26 10:36:04,484 epoch 9 - iter 40/48 - loss 0.07069114 - time (sec): 18.83 - samples/sec: 1505.97 - lr: 0.000004 - momentum: 0.000000
223
+ 2024-03-26 10:36:07,539 epoch 9 - iter 44/48 - loss 0.07071166 - time (sec): 21.89 - samples/sec: 1473.69 - lr: 0.000004 - momentum: 0.000000
224
+ 2024-03-26 10:36:09,018 epoch 9 - iter 48/48 - loss 0.06860300 - time (sec): 23.37 - samples/sec: 1475.18 - lr: 0.000004 - momentum: 0.000000
225
+ 2024-03-26 10:36:09,018 ----------------------------------------------------------------------------------------------------
226
+ 2024-03-26 10:36:09,018 EPOCH 9 done: loss 0.0686 - lr: 0.000004
227
+ 2024-03-26 10:36:09,944 DEV : loss 0.15753228962421417 - f1-score (micro avg) 0.9145
228
+ 2024-03-26 10:36:09,946 ----------------------------------------------------------------------------------------------------
229
+ 2024-03-26 10:36:12,787 epoch 10 - iter 4/48 - loss 0.07280782 - time (sec): 2.84 - samples/sec: 1307.60 - lr: 0.000003 - momentum: 0.000000
230
+ 2024-03-26 10:36:14,756 epoch 10 - iter 8/48 - loss 0.06728858 - time (sec): 4.81 - samples/sec: 1343.72 - lr: 0.000003 - momentum: 0.000000
231
+ 2024-03-26 10:36:16,943 epoch 10 - iter 12/48 - loss 0.06391531 - time (sec): 7.00 - samples/sec: 1299.82 - lr: 0.000003 - momentum: 0.000000
232
+ 2024-03-26 10:36:19,395 epoch 10 - iter 16/48 - loss 0.06018551 - time (sec): 9.45 - samples/sec: 1263.95 - lr: 0.000002 - momentum: 0.000000
233
+ 2024-03-26 10:36:21,959 epoch 10 - iter 20/48 - loss 0.05973564 - time (sec): 12.01 - samples/sec: 1267.40 - lr: 0.000002 - momentum: 0.000000
234
+ 2024-03-26 10:36:23,375 epoch 10 - iter 24/48 - loss 0.05860970 - time (sec): 13.43 - samples/sec: 1328.32 - lr: 0.000002 - momentum: 0.000000
235
+ 2024-03-26 10:36:24,259 epoch 10 - iter 28/48 - loss 0.05937806 - time (sec): 14.31 - samples/sec: 1399.56 - lr: 0.000002 - momentum: 0.000000
236
+ 2024-03-26 10:36:26,197 epoch 10 - iter 32/48 - loss 0.06338573 - time (sec): 16.25 - samples/sec: 1419.38 - lr: 0.000001 - momentum: 0.000000
237
+ 2024-03-26 10:36:28,468 epoch 10 - iter 36/48 - loss 0.06419294 - time (sec): 18.52 - samples/sec: 1396.82 - lr: 0.000001 - momentum: 0.000000
238
+ 2024-03-26 10:36:30,126 epoch 10 - iter 40/48 - loss 0.06609780 - time (sec): 20.18 - samples/sec: 1423.24 - lr: 0.000001 - momentum: 0.000000
239
+ 2024-03-26 10:36:33,296 epoch 10 - iter 44/48 - loss 0.06545318 - time (sec): 23.35 - samples/sec: 1403.65 - lr: 0.000001 - momentum: 0.000000
240
+ 2024-03-26 10:36:34,015 epoch 10 - iter 48/48 - loss 0.06560482 - time (sec): 24.07 - samples/sec: 1432.26 - lr: 0.000000 - momentum: 0.000000
241
+ 2024-03-26 10:36:34,015 ----------------------------------------------------------------------------------------------------
242
+ 2024-03-26 10:36:34,016 EPOCH 10 done: loss 0.0656 - lr: 0.000000
243
+ 2024-03-26 10:36:34,922 DEV : loss 0.15896496176719666 - f1-score (micro avg) 0.9196
244
+ 2024-03-26 10:36:34,924 saving best model
245
+ 2024-03-26 10:36:35,661 ----------------------------------------------------------------------------------------------------
246
+ 2024-03-26 10:36:35,661 Loading model from best epoch ...
247
+ 2024-03-26 10:36:36,521 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
248
+ 2024-03-26 10:36:37,385
249
+ Results:
250
+ - F-score (micro) 0.8921
251
+ - F-score (macro) 0.6787
252
+ - Accuracy 0.8086
253
+
254
+ By class:
255
+ precision recall f1-score support
256
+
257
+ Unternehmen 0.8996 0.8759 0.8876 266
258
+ Auslagerung 0.8385 0.8755 0.8566 249
259
+ Ort 0.9565 0.9851 0.9706 134
260
+ Software 0.0000 0.0000 0.0000 0
261
+
262
+ micro avg 0.8860 0.8983 0.8921 649
263
+ macro avg 0.6736 0.6841 0.6787 649
264
+ weighted avg 0.8879 0.8983 0.8928 649
265
+
266
+ 2024-03-26 10:36:37,385 ----------------------------------------------------------------------------------------------------