Hugging Face's logo

stefan-it
/
flair-co-funer-german_dbmdz_bert_base-bs16-e10-lr3e-05-4

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
62b627a
•
1 Parent(s): 54e5fa9

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 16:03:49,239 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 16:03:49,239 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 16:03:49,239 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 16:03:49,240 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 16:03:49,240 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 16:03:49,240 Train: 758 sentences
54
+ 2024-03-26 16:03:49,240 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 16:03:49,240 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 16:03:49,240 Training Params:
57
+ 2024-03-26 16:03:49,240 - learning_rate: "3e-05"
58
+ 2024-03-26 16:03:49,240 - mini_batch_size: "16"
59
+ 2024-03-26 16:03:49,240 - max_epochs: "10"
60
+ 2024-03-26 16:03:49,240 - shuffle: "True"
61
+ 2024-03-26 16:03:49,240 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 16:03:49,240 Plugins:
63
+ 2024-03-26 16:03:49,240 - TensorboardLogger
64
+ 2024-03-26 16:03:49,240 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 16:03:49,240 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 16:03:49,240 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 16:03:49,240 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 16:03:49,240 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 16:03:49,240 Computation:
70
+ 2024-03-26 16:03:49,240 - compute on device: cuda:0
71
+ 2024-03-26 16:03:49,240 - embedding storage: none
72
+ 2024-03-26 16:03:49,240 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 16:03:49,240 Model training base path: "flair-co-funer-german_dbmdz_bert_base-bs16-e10-lr3e-05-4"
74
+ 2024-03-26 16:03:49,240 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 16:03:49,240 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 16:03:49,240 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 16:03:50,727 epoch 1 - iter 4/48 - loss 3.01640190 - time (sec): 1.49 - samples/sec: 1755.99 - lr: 0.000002 - momentum: 0.000000
78
+ 2024-03-26 16:03:52,541 epoch 1 - iter 8/48 - loss 2.96742700 - time (sec): 3.30 - samples/sec: 1551.95 - lr: 0.000004 - momentum: 0.000000
79
+ 2024-03-26 16:03:53,871 epoch 1 - iter 12/48 - loss 2.91390131 - time (sec): 4.63 - samples/sec: 1576.94 - lr: 0.000007 - momentum: 0.000000
80
+ 2024-03-26 16:03:56,400 epoch 1 - iter 16/48 - loss 2.81253980 - time (sec): 7.16 - samples/sec: 1494.26 - lr: 0.000009 - momentum: 0.000000
81
+ 2024-03-26 16:03:58,500 epoch 1 - iter 20/48 - loss 2.69076344 - time (sec): 9.26 - samples/sec: 1479.37 - lr: 0.000012 - momentum: 0.000000
82
+ 2024-03-26 16:04:01,168 epoch 1 - iter 24/48 - loss 2.55974652 - time (sec): 11.93 - samples/sec: 1418.90 - lr: 0.000014 - momentum: 0.000000
83
+ 2024-03-26 16:04:03,662 epoch 1 - iter 28/48 - loss 2.44809026 - time (sec): 14.42 - samples/sec: 1406.64 - lr: 0.000017 - momentum: 0.000000
84
+ 2024-03-26 16:04:05,541 epoch 1 - iter 32/48 - loss 2.35897900 - time (sec): 16.30 - samples/sec: 1403.25 - lr: 0.000019 - momentum: 0.000000
85
+ 2024-03-26 16:04:06,433 epoch 1 - iter 36/48 - loss 2.29176753 - time (sec): 17.19 - samples/sec: 1452.95 - lr: 0.000022 - momentum: 0.000000
86
+ 2024-03-26 16:04:08,293 epoch 1 - iter 40/48 - loss 2.19360469 - time (sec): 19.05 - samples/sec: 1461.82 - lr: 0.000024 - momentum: 0.000000
87
+ 2024-03-26 16:04:10,330 epoch 1 - iter 44/48 - loss 2.08193654 - time (sec): 21.09 - samples/sec: 1480.73 - lr: 0.000027 - momentum: 0.000000
88
+ 2024-03-26 16:04:12,058 epoch 1 - iter 48/48 - loss 1.99530450 - time (sec): 22.82 - samples/sec: 1510.76 - lr: 0.000029 - momentum: 0.000000
89
+ 2024-03-26 16:04:12,058 ----------------------------------------------------------------------------------------------------
90
+ 2024-03-26 16:04:12,058 EPOCH 1 done: loss 1.9953 - lr: 0.000029
91
+ 2024-03-26 16:04:13,044 DEV : loss 0.7687539458274841 - f1-score (micro avg) 0.4963
92
+ 2024-03-26 16:04:13,045 saving best model
93
+ 2024-03-26 16:04:13,325 ----------------------------------------------------------------------------------------------------
94
+ 2024-03-26 16:04:14,566 epoch 2 - iter 4/48 - loss 1.05234656 - time (sec): 1.24 - samples/sec: 1908.57 - lr: 0.000030 - momentum: 0.000000
95
+ 2024-03-26 16:04:16,802 epoch 2 - iter 8/48 - loss 0.86861665 - time (sec): 3.48 - samples/sec: 1569.41 - lr: 0.000030 - momentum: 0.000000
96
+ 2024-03-26 16:04:18,575 epoch 2 - iter 12/48 - loss 0.81234012 - time (sec): 5.25 - samples/sec: 1623.16 - lr: 0.000029 - momentum: 0.000000
97
+ 2024-03-26 16:04:20,952 epoch 2 - iter 16/48 - loss 0.72967794 - time (sec): 7.63 - samples/sec: 1479.30 - lr: 0.000029 - momentum: 0.000000
98
+ 2024-03-26 16:04:24,328 epoch 2 - iter 20/48 - loss 0.66501742 - time (sec): 11.00 - samples/sec: 1341.02 - lr: 0.000029 - momentum: 0.000000
99
+ 2024-03-26 16:04:25,802 epoch 2 - iter 24/48 - loss 0.65016550 - time (sec): 12.48 - samples/sec: 1398.00 - lr: 0.000028 - momentum: 0.000000
100
+ 2024-03-26 16:04:28,439 epoch 2 - iter 28/48 - loss 0.62771530 - time (sec): 15.11 - samples/sec: 1369.96 - lr: 0.000028 - momentum: 0.000000
101
+ 2024-03-26 16:04:31,123 epoch 2 - iter 32/48 - loss 0.59657920 - time (sec): 17.80 - samples/sec: 1371.43 - lr: 0.000028 - momentum: 0.000000
102
+ 2024-03-26 16:04:33,192 epoch 2 - iter 36/48 - loss 0.58504856 - time (sec): 19.87 - samples/sec: 1361.19 - lr: 0.000028 - momentum: 0.000000
103
+ 2024-03-26 16:04:35,662 epoch 2 - iter 40/48 - loss 0.56665662 - time (sec): 22.34 - samples/sec: 1351.30 - lr: 0.000027 - momentum: 0.000000
104
+ 2024-03-26 16:04:36,711 epoch 2 - iter 44/48 - loss 0.55732793 - time (sec): 23.39 - samples/sec: 1386.51 - lr: 0.000027 - momentum: 0.000000
105
+ 2024-03-26 16:04:37,875 epoch 2 - iter 48/48 - loss 0.54730932 - time (sec): 24.55 - samples/sec: 1404.15 - lr: 0.000027 - momentum: 0.000000
106
+ 2024-03-26 16:04:37,876 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 16:04:37,876 EPOCH 2 done: loss 0.5473 - lr: 0.000027
108
+ 2024-03-26 16:04:38,788 DEV : loss 0.3269508481025696 - f1-score (micro avg) 0.7953
109
+ 2024-03-26 16:04:38,790 saving best model
110
+ 2024-03-26 16:04:39,251 ----------------------------------------------------------------------------------------------------
111
+ 2024-03-26 16:04:41,238 epoch 3 - iter 4/48 - loss 0.32273077 - time (sec): 1.99 - samples/sec: 1236.41 - lr: 0.000026 - momentum: 0.000000
112
+ 2024-03-26 16:04:42,789 epoch 3 - iter 8/48 - loss 0.27329305 - time (sec): 3.54 - samples/sec: 1354.27 - lr: 0.000026 - momentum: 0.000000
113
+ 2024-03-26 16:04:45,347 epoch 3 - iter 12/48 - loss 0.28542240 - time (sec): 6.09 - samples/sec: 1276.47 - lr: 0.000026 - momentum: 0.000000
114
+ 2024-03-26 16:04:47,350 epoch 3 - iter 16/48 - loss 0.29088610 - time (sec): 8.10 - samples/sec: 1316.91 - lr: 0.000026 - momentum: 0.000000
115
+ 2024-03-26 16:04:49,228 epoch 3 - iter 20/48 - loss 0.28489785 - time (sec): 9.98 - samples/sec: 1387.86 - lr: 0.000025 - momentum: 0.000000
116
+ 2024-03-26 16:04:51,441 epoch 3 - iter 24/48 - loss 0.27481321 - time (sec): 12.19 - samples/sec: 1402.53 - lr: 0.000025 - momentum: 0.000000
117
+ 2024-03-26 16:04:53,895 epoch 3 - iter 28/48 - loss 0.26488170 - time (sec): 14.64 - samples/sec: 1362.11 - lr: 0.000025 - momentum: 0.000000
118
+ 2024-03-26 16:04:56,442 epoch 3 - iter 32/48 - loss 0.26071963 - time (sec): 17.19 - samples/sec: 1337.56 - lr: 0.000025 - momentum: 0.000000
119
+ 2024-03-26 16:04:58,546 epoch 3 - iter 36/48 - loss 0.25954332 - time (sec): 19.29 - samples/sec: 1341.72 - lr: 0.000024 - momentum: 0.000000
120
+ 2024-03-26 16:05:00,842 epoch 3 - iter 40/48 - loss 0.26609240 - time (sec): 21.59 - samples/sec: 1357.38 - lr: 0.000024 - momentum: 0.000000
121
+ 2024-03-26 16:05:03,359 epoch 3 - iter 44/48 - loss 0.25854646 - time (sec): 24.11 - samples/sec: 1340.25 - lr: 0.000024 - momentum: 0.000000
122
+ 2024-03-26 16:05:04,864 epoch 3 - iter 48/48 - loss 0.25895918 - time (sec): 25.61 - samples/sec: 1345.95 - lr: 0.000023 - momentum: 0.000000
123
+ 2024-03-26 16:05:04,864 ----------------------------------------------------------------------------------------------------
124
+ 2024-03-26 16:05:04,864 EPOCH 3 done: loss 0.2590 - lr: 0.000023
125
+ 2024-03-26 16:05:05,788 DEV : loss 0.2578723728656769 - f1-score (micro avg) 0.8517
126
+ 2024-03-26 16:05:05,789 saving best model
127
+ 2024-03-26 16:05:06,243 ----------------------------------------------------------------------------------------------------
128
+ 2024-03-26 16:05:09,220 epoch 4 - iter 4/48 - loss 0.12629222 - time (sec): 2.98 - samples/sec: 1224.51 - lr: 0.000023 - momentum: 0.000000
129
+ 2024-03-26 16:05:10,525 epoch 4 - iter 8/48 - loss 0.15790626 - time (sec): 4.28 - samples/sec: 1373.73 - lr: 0.000023 - momentum: 0.000000
130
+ 2024-03-26 16:05:12,600 epoch 4 - iter 12/48 - loss 0.16547955 - time (sec): 6.36 - samples/sec: 1451.18 - lr: 0.000023 - momentum: 0.000000
131
+ 2024-03-26 16:05:15,136 epoch 4 - iter 16/48 - loss 0.16938562 - time (sec): 8.89 - samples/sec: 1370.07 - lr: 0.000022 - momentum: 0.000000
132
+ 2024-03-26 16:05:16,123 epoch 4 - iter 20/48 - loss 0.17108509 - time (sec): 9.88 - samples/sec: 1454.01 - lr: 0.000022 - momentum: 0.000000
133
+ 2024-03-26 16:05:17,519 epoch 4 - iter 24/48 - loss 0.17307095 - time (sec): 11.27 - samples/sec: 1499.18 - lr: 0.000022 - momentum: 0.000000
134
+ 2024-03-26 16:05:20,617 epoch 4 - iter 28/48 - loss 0.16591345 - time (sec): 14.37 - samples/sec: 1404.16 - lr: 0.000022 - momentum: 0.000000
135
+ 2024-03-26 16:05:23,088 epoch 4 - iter 32/48 - loss 0.17880494 - time (sec): 16.84 - samples/sec: 1396.18 - lr: 0.000021 - momentum: 0.000000
136
+ 2024-03-26 16:05:24,598 epoch 4 - iter 36/48 - loss 0.17838065 - time (sec): 18.35 - samples/sec: 1431.70 - lr: 0.000021 - momentum: 0.000000
137
+ 2024-03-26 16:05:26,578 epoch 4 - iter 40/48 - loss 0.17479243 - time (sec): 20.33 - samples/sec: 1445.81 - lr: 0.000021 - momentum: 0.000000
138
+ 2024-03-26 16:05:28,479 epoch 4 - iter 44/48 - loss 0.17457045 - time (sec): 22.24 - samples/sec: 1458.66 - lr: 0.000020 - momentum: 0.000000
139
+ 2024-03-26 16:05:29,532 epoch 4 - iter 48/48 - loss 0.17660779 - time (sec): 23.29 - samples/sec: 1480.25 - lr: 0.000020 - momentum: 0.000000
140
+ 2024-03-26 16:05:29,532 ----------------------------------------------------------------------------------------------------
141
+ 2024-03-26 16:05:29,532 EPOCH 4 done: loss 0.1766 - lr: 0.000020
142
+ 2024-03-26 16:05:30,444 DEV : loss 0.24019527435302734 - f1-score (micro avg) 0.8821
143
+ 2024-03-26 16:05:30,445 saving best model
144
+ 2024-03-26 16:05:30,882 ----------------------------------------------------------------------------------------------------
145
+ 2024-03-26 16:05:31,935 epoch 5 - iter 4/48 - loss 0.21813518 - time (sec): 1.05 - samples/sec: 2416.12 - lr: 0.000020 - momentum: 0.000000
146
+ 2024-03-26 16:05:33,823 epoch 5 - iter 8/48 - loss 0.18958705 - time (sec): 2.94 - samples/sec: 1762.05 - lr: 0.000020 - momentum: 0.000000
147
+ 2024-03-26 16:05:36,015 epoch 5 - iter 12/48 - loss 0.17988105 - time (sec): 5.13 - samples/sec: 1559.36 - lr: 0.000019 - momentum: 0.000000
148
+ 2024-03-26 16:05:38,273 epoch 5 - iter 16/48 - loss 0.16768415 - time (sec): 7.39 - samples/sec: 1500.73 - lr: 0.000019 - momentum: 0.000000
149
+ 2024-03-26 16:05:40,512 epoch 5 - iter 20/48 - loss 0.16354606 - time (sec): 9.63 - samples/sec: 1421.07 - lr: 0.000019 - momentum: 0.000000
150
+ 2024-03-26 16:05:42,669 epoch 5 - iter 24/48 - loss 0.15615852 - time (sec): 11.79 - samples/sec: 1441.51 - lr: 0.000018 - momentum: 0.000000
151
+ 2024-03-26 16:05:44,264 epoch 5 - iter 28/48 - loss 0.15294373 - time (sec): 13.38 - samples/sec: 1470.82 - lr: 0.000018 - momentum: 0.000000
152
+ 2024-03-26 16:05:46,350 epoch 5 - iter 32/48 - loss 0.14264617 - time (sec): 15.47 - samples/sec: 1493.61 - lr: 0.000018 - momentum: 0.000000
153
+ 2024-03-26 16:05:47,737 epoch 5 - iter 36/48 - loss 0.14222184 - time (sec): 16.85 - samples/sec: 1518.84 - lr: 0.000018 - momentum: 0.000000
154
+ 2024-03-26 16:05:50,265 epoch 5 - iter 40/48 - loss 0.13629646 - time (sec): 19.38 - samples/sec: 1487.30 - lr: 0.000017 - momentum: 0.000000
155
+ 2024-03-26 16:05:53,174 epoch 5 - iter 44/48 - loss 0.13484468 - time (sec): 22.29 - samples/sec: 1436.75 - lr: 0.000017 - momentum: 0.000000
156
+ 2024-03-26 16:05:54,669 epoch 5 - iter 48/48 - loss 0.13720050 - time (sec): 23.79 - samples/sec: 1449.24 - lr: 0.000017 - momentum: 0.000000
157
+ 2024-03-26 16:05:54,669 ----------------------------------------------------------------------------------------------------
158
+ 2024-03-26 16:05:54,669 EPOCH 5 done: loss 0.1372 - lr: 0.000017
159
+ 2024-03-26 16:05:55,584 DEV : loss 0.17373321950435638 - f1-score (micro avg) 0.8822
160
+ 2024-03-26 16:05:55,585 saving best model
161
+ 2024-03-26 16:05:56,014 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 16:05:57,875 epoch 6 - iter 4/48 - loss 0.16156735 - time (sec): 1.86 - samples/sec: 1579.94 - lr: 0.000017 - momentum: 0.000000
163
+ 2024-03-26 16:05:59,593 epoch 6 - iter 8/48 - loss 0.13747974 - time (sec): 3.58 - samples/sec: 1620.28 - lr: 0.000016 - momentum: 0.000000
164
+ 2024-03-26 16:06:01,888 epoch 6 - iter 12/48 - loss 0.12654976 - time (sec): 5.87 - samples/sec: 1501.35 - lr: 0.000016 - momentum: 0.000000
165
+ 2024-03-26 16:06:03,449 epoch 6 - iter 16/48 - loss 0.11499352 - time (sec): 7.43 - samples/sec: 1524.11 - lr: 0.000016 - momentum: 0.000000
166
+ 2024-03-26 16:06:05,998 epoch 6 - iter 20/48 - loss 0.10474209 - time (sec): 9.98 - samples/sec: 1438.97 - lr: 0.000015 - momentum: 0.000000
167
+ 2024-03-26 16:06:08,037 epoch 6 - iter 24/48 - loss 0.10414922 - time (sec): 12.02 - samples/sec: 1454.86 - lr: 0.000015 - momentum: 0.000000
168
+ 2024-03-26 16:06:10,651 epoch 6 - iter 28/48 - loss 0.10373188 - time (sec): 14.64 - samples/sec: 1430.32 - lr: 0.000015 - momentum: 0.000000
169
+ 2024-03-26 16:06:12,691 epoch 6 - iter 32/48 - loss 0.10040075 - time (sec): 16.68 - samples/sec: 1409.28 - lr: 0.000015 - momentum: 0.000000
170
+ 2024-03-26 16:06:13,800 epoch 6 - iter 36/48 - loss 0.10266182 - time (sec): 17.79 - samples/sec: 1458.55 - lr: 0.000014 - momentum: 0.000000
171
+ 2024-03-26 16:06:15,989 epoch 6 - iter 40/48 - loss 0.10436027 - time (sec): 19.97 - samples/sec: 1447.66 - lr: 0.000014 - momentum: 0.000000
172
+ 2024-03-26 16:06:17,590 epoch 6 - iter 44/48 - loss 0.10624856 - time (sec): 21.58 - samples/sec: 1471.64 - lr: 0.000014 - momentum: 0.000000
173
+ 2024-03-26 16:06:19,359 epoch 6 - iter 48/48 - loss 0.10324865 - time (sec): 23.34 - samples/sec: 1476.67 - lr: 0.000014 - momentum: 0.000000
174
+ 2024-03-26 16:06:19,360 ----------------------------------------------------------------------------------------------------
175
+ 2024-03-26 16:06:19,360 EPOCH 6 done: loss 0.1032 - lr: 0.000014
176
+ 2024-03-26 16:06:20,259 DEV : loss 0.17608517408370972 - f1-score (micro avg) 0.9107
177
+ 2024-03-26 16:06:20,260 saving best model
178
+ 2024-03-26 16:06:20,713 ----------------------------------------------------------------------------------------------------
179
+ 2024-03-26 16:06:22,243 epoch 7 - iter 4/48 - loss 0.10018007 - time (sec): 1.53 - samples/sec: 1831.90 - lr: 0.000013 - momentum: 0.000000
180
+ 2024-03-26 16:06:24,347 epoch 7 - iter 8/48 - loss 0.07755405 - time (sec): 3.63 - samples/sec: 1685.16 - lr: 0.000013 - momentum: 0.000000
181
+ 2024-03-26 16:06:26,578 epoch 7 - iter 12/48 - loss 0.07358055 - time (sec): 5.86 - samples/sec: 1502.66 - lr: 0.000013 - momentum: 0.000000
182
+ 2024-03-26 16:06:27,747 epoch 7 - iter 16/48 - loss 0.08302123 - time (sec): 7.03 - samples/sec: 1600.65 - lr: 0.000012 - momentum: 0.000000
183
+ 2024-03-26 16:06:29,853 epoch 7 - iter 20/48 - loss 0.08162502 - time (sec): 9.14 - samples/sec: 1569.94 - lr: 0.000012 - momentum: 0.000000
184
+ 2024-03-26 16:06:31,362 epoch 7 - iter 24/48 - loss 0.07788313 - time (sec): 10.65 - samples/sec: 1616.72 - lr: 0.000012 - momentum: 0.000000
185
+ 2024-03-26 16:06:33,464 epoch 7 - iter 28/48 - loss 0.07674570 - time (sec): 12.75 - samples/sec: 1574.63 - lr: 0.000012 - momentum: 0.000000
186
+ 2024-03-26 16:06:36,225 epoch 7 - iter 32/48 - loss 0.07632740 - time (sec): 15.51 - samples/sec: 1501.58 - lr: 0.000011 - momentum: 0.000000
187
+ 2024-03-26 16:06:38,184 epoch 7 - iter 36/48 - loss 0.07494768 - time (sec): 17.47 - samples/sec: 1502.13 - lr: 0.000011 - momentum: 0.000000
188
+ 2024-03-26 16:06:39,300 epoch 7 - iter 40/48 - loss 0.07830908 - time (sec): 18.58 - samples/sec: 1533.48 - lr: 0.000011 - momentum: 0.000000
189
+ 2024-03-26 16:06:41,890 epoch 7 - iter 44/48 - loss 0.07784393 - time (sec): 21.17 - samples/sec: 1514.14 - lr: 0.000010 - momentum: 0.000000
190
+ 2024-03-26 16:06:42,990 epoch 7 - iter 48/48 - loss 0.07956492 - time (sec): 22.27 - samples/sec: 1547.57 - lr: 0.000010 - momentum: 0.000000
191
+ 2024-03-26 16:06:42,990 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 16:06:42,991 EPOCH 7 done: loss 0.0796 - lr: 0.000010
193
+ 2024-03-26 16:06:43,904 DEV : loss 0.1826418936252594 - f1-score (micro avg) 0.9269
194
+ 2024-03-26 16:06:43,905 saving best model
195
+ 2024-03-26 16:06:44,375 ----------------------------------------------------------------------------------------------------
196
+ 2024-03-26 16:06:46,485 epoch 8 - iter 4/48 - loss 0.04736933 - time (sec): 2.11 - samples/sec: 1314.62 - lr: 0.000010 - momentum: 0.000000
197
+ 2024-03-26 16:06:49,093 epoch 8 - iter 8/48 - loss 0.04070346 - time (sec): 4.72 - samples/sec: 1280.39 - lr: 0.000010 - momentum: 0.000000
198
+ 2024-03-26 16:06:50,759 epoch 8 - iter 12/48 - loss 0.04177010 - time (sec): 6.38 - samples/sec: 1328.63 - lr: 0.000009 - momentum: 0.000000
199
+ 2024-03-26 16:06:53,368 epoch 8 - iter 16/48 - loss 0.05117556 - time (sec): 8.99 - samples/sec: 1280.28 - lr: 0.000009 - momentum: 0.000000
200
+ 2024-03-26 16:06:55,023 epoch 8 - iter 20/48 - loss 0.05209403 - time (sec): 10.65 - samples/sec: 1334.52 - lr: 0.000009 - momentum: 0.000000
201
+ 2024-03-26 16:06:56,484 epoch 8 - iter 24/48 - loss 0.05785789 - time (sec): 12.11 - samples/sec: 1403.84 - lr: 0.000009 - momentum: 0.000000
202
+ 2024-03-26 16:06:58,353 epoch 8 - iter 28/48 - loss 0.06393769 - time (sec): 13.98 - samples/sec: 1426.81 - lr: 0.000008 - momentum: 0.000000
203
+ 2024-03-26 16:07:01,005 epoch 8 - iter 32/48 - loss 0.06493712 - time (sec): 16.63 - samples/sec: 1412.73 - lr: 0.000008 - momentum: 0.000000
204
+ 2024-03-26 16:07:03,412 epoch 8 - iter 36/48 - loss 0.06609066 - time (sec): 19.04 - samples/sec: 1404.31 - lr: 0.000008 - momentum: 0.000000
205
+ 2024-03-26 16:07:05,614 epoch 8 - iter 40/48 - loss 0.06561863 - time (sec): 21.24 - samples/sec: 1385.41 - lr: 0.000007 - momentum: 0.000000
206
+ 2024-03-26 16:07:07,862 epoch 8 - iter 44/48 - loss 0.06415178 - time (sec): 23.49 - samples/sec: 1375.45 - lr: 0.000007 - momentum: 0.000000
207
+ 2024-03-26 16:07:09,423 epoch 8 - iter 48/48 - loss 0.06483716 - time (sec): 25.05 - samples/sec: 1376.28 - lr: 0.000007 - momentum: 0.000000
208
+ 2024-03-26 16:07:09,423 ----------------------------------------------------------------------------------------------------
209
+ 2024-03-26 16:07:09,424 EPOCH 8 done: loss 0.0648 - lr: 0.000007
210
+ 2024-03-26 16:07:10,376 DEV : loss 0.1771041601896286 - f1-score (micro avg) 0.9315
211
+ 2024-03-26 16:07:10,378 saving best model
212
+ 2024-03-26 16:07:10,843 ----------------------------------------------------------------------------------------------------
213
+ 2024-03-26 16:07:12,700 epoch 9 - iter 4/48 - loss 0.07065489 - time (sec): 1.86 - samples/sec: 1556.01 - lr: 0.000007 - momentum: 0.000000
214
+ 2024-03-26 16:07:15,940 epoch 9 - iter 8/48 - loss 0.06582465 - time (sec): 5.10 - samples/sec: 1235.16 - lr: 0.000006 - momentum: 0.000000
215
+ 2024-03-26 16:07:17,586 epoch 9 - iter 12/48 - loss 0.05729645 - time (sec): 6.74 - samples/sec: 1282.83 - lr: 0.000006 - momentum: 0.000000
216
+ 2024-03-26 16:07:19,465 epoch 9 - iter 16/48 - loss 0.06242567 - time (sec): 8.62 - samples/sec: 1326.10 - lr: 0.000006 - momentum: 0.000000
217
+ 2024-03-26 16:07:22,345 epoch 9 - iter 20/48 - loss 0.05752235 - time (sec): 11.50 - samples/sec: 1291.33 - lr: 0.000006 - momentum: 0.000000
218
+ 2024-03-26 16:07:23,878 epoch 9 - iter 24/48 - loss 0.05575202 - time (sec): 13.03 - samples/sec: 1338.69 - lr: 0.000005 - momentum: 0.000000
219
+ 2024-03-26 16:07:25,822 epoch 9 - iter 28/48 - loss 0.05750958 - time (sec): 14.98 - samples/sec: 1363.86 - lr: 0.000005 - momentum: 0.000000
220
+ 2024-03-26 16:07:28,150 epoch 9 - iter 32/48 - loss 0.05658503 - time (sec): 17.31 - samples/sec: 1342.34 - lr: 0.000005 - momentum: 0.000000
221
+ 2024-03-26 16:07:29,453 epoch 9 - iter 36/48 - loss 0.06099649 - time (sec): 18.61 - samples/sec: 1373.69 - lr: 0.000004 - momentum: 0.000000
222
+ 2024-03-26 16:07:32,663 epoch 9 - iter 40/48 - loss 0.05936938 - time (sec): 21.82 - samples/sec: 1326.27 - lr: 0.000004 - momentum: 0.000000
223
+ 2024-03-26 16:07:34,786 epoch 9 - iter 44/48 - loss 0.05578945 - time (sec): 23.94 - samples/sec: 1349.03 - lr: 0.000004 - momentum: 0.000000
224
+ 2024-03-26 16:07:35,785 epoch 9 - iter 48/48 - loss 0.05796324 - time (sec): 24.94 - samples/sec: 1382.14 - lr: 0.000004 - momentum: 0.000000
225
+ 2024-03-26 16:07:35,785 ----------------------------------------------------------------------------------------------------
226
+ 2024-03-26 16:07:35,785 EPOCH 9 done: loss 0.0580 - lr: 0.000004
227
+ 2024-03-26 16:07:36,709 DEV : loss 0.175104558467865 - f1-score (micro avg) 0.9315
228
+ 2024-03-26 16:07:36,710 ----------------------------------------------------------------------------------------------------
229
+ 2024-03-26 16:07:38,586 epoch 10 - iter 4/48 - loss 0.06033202 - time (sec): 1.88 - samples/sec: 1378.38 - lr: 0.000003 - momentum: 0.000000
230
+ 2024-03-26 16:07:41,367 epoch 10 - iter 8/48 - loss 0.04830006 - time (sec): 4.66 - samples/sec: 1242.55 - lr: 0.000003 - momentum: 0.000000
231
+ 2024-03-26 16:07:43,394 epoch 10 - iter 12/48 - loss 0.05421156 - time (sec): 6.68 - samples/sec: 1303.69 - lr: 0.000003 - momentum: 0.000000
232
+ 2024-03-26 16:07:45,419 epoch 10 - iter 16/48 - loss 0.04947033 - time (sec): 8.71 - samples/sec: 1397.01 - lr: 0.000002 - momentum: 0.000000
233
+ 2024-03-26 16:07:46,290 epoch 10 - iter 20/48 - loss 0.04811459 - time (sec): 9.58 - samples/sec: 1473.72 - lr: 0.000002 - momentum: 0.000000
234
+ 2024-03-26 16:07:47,976 epoch 10 - iter 24/48 - loss 0.04694625 - time (sec): 11.26 - samples/sec: 1501.57 - lr: 0.000002 - momentum: 0.000000
235
+ 2024-03-26 16:07:48,915 epoch 10 - iter 28/48 - loss 0.04653300 - time (sec): 12.20 - samples/sec: 1565.69 - lr: 0.000002 - momentum: 0.000000
236
+ 2024-03-26 16:07:51,240 epoch 10 - iter 32/48 - loss 0.04512651 - time (sec): 14.53 - samples/sec: 1531.23 - lr: 0.000001 - momentum: 0.000000
237
+ 2024-03-26 16:07:53,733 epoch 10 - iter 36/48 - loss 0.04887373 - time (sec): 17.02 - samples/sec: 1497.74 - lr: 0.000001 - momentum: 0.000000
238
+ 2024-03-26 16:07:55,630 epoch 10 - iter 40/48 - loss 0.05137305 - time (sec): 18.92 - samples/sec: 1491.37 - lr: 0.000001 - momentum: 0.000000
239
+ 2024-03-26 16:07:58,196 epoch 10 - iter 44/48 - loss 0.04997394 - time (sec): 21.48 - samples/sec: 1480.08 - lr: 0.000001 - momentum: 0.000000
240
+ 2024-03-26 16:07:59,793 epoch 10 - iter 48/48 - loss 0.05010805 - time (sec): 23.08 - samples/sec: 1493.44 - lr: 0.000000 - momentum: 0.000000
241
+ 2024-03-26 16:07:59,794 ----------------------------------------------------------------------------------------------------
242
+ 2024-03-26 16:07:59,794 EPOCH 10 done: loss 0.0501 - lr: 0.000000
243
+ 2024-03-26 16:08:00,709 DEV : loss 0.17769017815589905 - f1-score (micro avg) 0.9391
244
+ 2024-03-26 16:08:00,711 saving best model
245
+ 2024-03-26 16:08:01,442 ----------------------------------------------------------------------------------------------------
246
+ 2024-03-26 16:08:01,443 Loading model from best epoch ...
247
+ 2024-03-26 16:08:02,222 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 16:08:02,995
249
+ Results:
250
+ - F-score (micro) 0.8991
251
+ - F-score (macro) 0.6833
252
+ - Accuracy 0.8201
253
+
254
+ By class:
255
+ precision recall f1-score support
256
+
257
+ Unternehmen 0.8783 0.8684 0.8733 266
258
+ Auslagerung 0.8824 0.9036 0.8929 249
259
+ Ort 0.9496 0.9851 0.9670 134
260
+ Software 0.0000 0.0000 0.0000 0
261
+
262
+ micro avg 0.8923 0.9060 0.8991 649
263
+ macro avg 0.6776 0.6893 0.6833 649
264
+ weighted avg 0.8946 0.9060 0.9002 649
265
+
266
+ 2024-03-26 16:08:02,995 ----------------------------------------------------------------------------------------------------