Hugging Face's logo

stefan-it
/
flair-co-funer-gbert_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
3
stefan-it commited on
Commit
8eeb39c
•
1 Parent(s): ff423ed

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +267 -0
training.log ADDED
@@ -0,0 +1,267 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-03-26 10:15:43,560 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 10:15:43,560 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 10:15:43,560 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 10:15:43,560 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 10:15:43,560 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 10:15:43,560 Train: 758 sentences
54
+ 2024-03-26 10:15:43,560 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 10:15:43,560 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 10:15:43,560 Training Params:
57
+ 2024-03-26 10:15:43,560 - learning_rate: "3e-05"
58
+ 2024-03-26 10:15:43,560 - mini_batch_size: "16"
59
+ 2024-03-26 10:15:43,560 - max_epochs: "10"
60
+ 2024-03-26 10:15:43,560 - shuffle: "True"
61
+ 2024-03-26 10:15:43,560 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 10:15:43,560 Plugins:
63
+ 2024-03-26 10:15:43,561 - TensorboardLogger
64
+ 2024-03-26 10:15:43,561 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 10:15:43,561 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 10:15:43,561 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 10:15:43,561 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 10:15:43,561 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 10:15:43,561 Computation:
70
+ 2024-03-26 10:15:43,561 - compute on device: cuda:0
71
+ 2024-03-26 10:15:43,561 - embedding storage: none
72
+ 2024-03-26 10:15:43,561 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 10:15:43,561 Model training base path: "flair-co-funer-gbert_base-bs16-e10-lr3e-05-4"
74
+ 2024-03-26 10:15:43,561 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 10:15:43,561 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 10:15:43,561 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 10:15:45,022 epoch 1 - iter 4/48 - loss 3.33606037 - time (sec): 1.46 - samples/sec: 1786.73 - lr: 0.000002 - momentum: 0.000000
78
+ 2024-03-26 10:15:46,837 epoch 1 - iter 8/48 - loss 3.28043995 - time (sec): 3.28 - samples/sec: 1563.83 - lr: 0.000004 - momentum: 0.000000
79
+ 2024-03-26 10:15:48,161 epoch 1 - iter 12/48 - loss 3.18154181 - time (sec): 4.60 - samples/sec: 1587.29 - lr: 0.000007 - momentum: 0.000000
80
+ 2024-03-26 10:15:50,702 epoch 1 - iter 16/48 - loss 2.99682926 - time (sec): 7.14 - samples/sec: 1498.23 - lr: 0.000009 - momentum: 0.000000
81
+ 2024-03-26 10:15:52,809 epoch 1 - iter 20/48 - loss 2.86564017 - time (sec): 9.25 - samples/sec: 1481.19 - lr: 0.000012 - momentum: 0.000000
82
+ 2024-03-26 10:15:55,477 epoch 1 - iter 24/48 - loss 2.71552302 - time (sec): 11.92 - samples/sec: 1420.36 - lr: 0.000014 - momentum: 0.000000
83
+ 2024-03-26 10:15:57,959 epoch 1 - iter 28/48 - loss 2.59674920 - time (sec): 14.40 - samples/sec: 1408.98 - lr: 0.000017 - momentum: 0.000000
84
+ 2024-03-26 10:15:59,832 epoch 1 - iter 32/48 - loss 2.50531239 - time (sec): 16.27 - samples/sec: 1405.82 - lr: 0.000019 - momentum: 0.000000
85
+ 2024-03-26 10:16:00,713 epoch 1 - iter 36/48 - loss 2.43592440 - time (sec): 17.15 - samples/sec: 1456.40 - lr: 0.000022 - momentum: 0.000000
86
+ 2024-03-26 10:16:02,569 epoch 1 - iter 40/48 - loss 2.34208452 - time (sec): 19.01 - samples/sec: 1465.32 - lr: 0.000024 - momentum: 0.000000
87
+ 2024-03-26 10:16:04,586 epoch 1 - iter 44/48 - loss 2.23846575 - time (sec): 21.02 - samples/sec: 1485.36 - lr: 0.000027 - momentum: 0.000000
88
+ 2024-03-26 10:16:06,292 epoch 1 - iter 48/48 - loss 2.15856647 - time (sec): 22.73 - samples/sec: 1516.53 - lr: 0.000029 - momentum: 0.000000
89
+ 2024-03-26 10:16:06,292 ----------------------------------------------------------------------------------------------------
90
+ 2024-03-26 10:16:06,292 EPOCH 1 done: loss 2.1586 - lr: 0.000029
91
+ 2024-03-26 10:16:07,099 DEV : loss 0.8691769242286682 - f1-score (micro avg) 0.3937
92
+ 2024-03-26 10:16:07,100 saving best model
93
+ 2024-03-26 10:16:07,381 ----------------------------------------------------------------------------------------------------
94
+ 2024-03-26 10:16:08,612 epoch 2 - iter 4/48 - loss 1.18353349 - time (sec): 1.23 - samples/sec: 1924.87 - lr: 0.000030 - momentum: 0.000000
95
+ 2024-03-26 10:16:10,851 epoch 2 - iter 8/48 - loss 0.99048634 - time (sec): 3.47 - samples/sec: 1572.73 - lr: 0.000030 - momentum: 0.000000
96
+ 2024-03-26 10:16:12,631 epoch 2 - iter 12/48 - loss 0.94829107 - time (sec): 5.25 - samples/sec: 1623.34 - lr: 0.000029 - momentum: 0.000000
97
+ 2024-03-26 10:16:15,015 epoch 2 - iter 16/48 - loss 0.86335015 - time (sec): 7.63 - samples/sec: 1478.02 - lr: 0.000029 - momentum: 0.000000
98
+ 2024-03-26 10:16:18,426 epoch 2 - iter 20/48 - loss 0.78901466 - time (sec): 11.04 - samples/sec: 1335.95 - lr: 0.000029 - momentum: 0.000000
99
+ 2024-03-26 10:16:19,906 epoch 2 - iter 24/48 - loss 0.77282323 - time (sec): 12.52 - samples/sec: 1392.74 - lr: 0.000028 - momentum: 0.000000
100
+ 2024-03-26 10:16:22,559 epoch 2 - iter 28/48 - loss 0.74398129 - time (sec): 15.18 - samples/sec: 1364.18 - lr: 0.000028 - momentum: 0.000000
101
+ 2024-03-26 10:16:25,258 epoch 2 - iter 32/48 - loss 0.71068818 - time (sec): 17.88 - samples/sec: 1365.43 - lr: 0.000028 - momentum: 0.000000
102
+ 2024-03-26 10:16:27,337 epoch 2 - iter 36/48 - loss 0.69857610 - time (sec): 19.96 - samples/sec: 1355.18 - lr: 0.000028 - momentum: 0.000000
103
+ 2024-03-26 10:16:29,805 epoch 2 - iter 40/48 - loss 0.67325179 - time (sec): 22.42 - samples/sec: 1346.07 - lr: 0.000027 - momentum: 0.000000
104
+ 2024-03-26 10:16:30,853 epoch 2 - iter 44/48 - loss 0.66012014 - time (sec): 23.47 - samples/sec: 1381.45 - lr: 0.000027 - momentum: 0.000000
105
+ 2024-03-26 10:16:32,008 epoch 2 - iter 48/48 - loss 0.64582622 - time (sec): 24.63 - samples/sec: 1399.82 - lr: 0.000027 - momentum: 0.000000
106
+ 2024-03-26 10:16:32,008 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 10:16:32,008 EPOCH 2 done: loss 0.6458 - lr: 0.000027
108
+ 2024-03-26 10:16:32,902 DEV : loss 0.3441326320171356 - f1-score (micro avg) 0.7893
109
+ 2024-03-26 10:16:32,904 saving best model
110
+ 2024-03-26 10:16:33,379 ----------------------------------------------------------------------------------------------------
111
+ 2024-03-26 10:16:35,456 epoch 3 - iter 4/48 - loss 0.38138387 - time (sec): 2.08 - samples/sec: 1183.00 - lr: 0.000026 - momentum: 0.000000
112
+ 2024-03-26 10:16:37,001 epoch 3 - iter 8/48 - loss 0.33198739 - time (sec): 3.62 - samples/sec: 1323.41 - lr: 0.000026 - momentum: 0.000000
113
+ 2024-03-26 10:16:39,563 epoch 3 - iter 12/48 - loss 0.33511209 - time (sec): 6.18 - samples/sec: 1258.61 - lr: 0.000026 - momentum: 0.000000
114
+ 2024-03-26 10:16:41,567 epoch 3 - iter 16/48 - loss 0.33306197 - time (sec): 8.19 - samples/sec: 1302.69 - lr: 0.000026 - momentum: 0.000000
115
+ 2024-03-26 10:16:43,445 epoch 3 - iter 20/48 - loss 0.33037874 - time (sec): 10.06 - samples/sec: 1375.67 - lr: 0.000025 - momentum: 0.000000
116
+ 2024-03-26 10:16:45,656 epoch 3 - iter 24/48 - loss 0.32391011 - time (sec): 12.27 - samples/sec: 1392.80 - lr: 0.000025 - momentum: 0.000000
117
+ 2024-03-26 10:16:48,105 epoch 3 - iter 28/48 - loss 0.31328468 - time (sec): 14.72 - samples/sec: 1354.65 - lr: 0.000025 - momentum: 0.000000
118
+ 2024-03-26 10:16:50,640 epoch 3 - iter 32/48 - loss 0.30770160 - time (sec): 17.26 - samples/sec: 1332.24 - lr: 0.000025 - momentum: 0.000000
119
+ 2024-03-26 10:16:52,737 epoch 3 - iter 36/48 - loss 0.30585269 - time (sec): 19.36 - samples/sec: 1337.44 - lr: 0.000024 - momentum: 0.000000
120
+ 2024-03-26 10:16:55,028 epoch 3 - iter 40/48 - loss 0.30995459 - time (sec): 21.65 - samples/sec: 1353.84 - lr: 0.000024 - momentum: 0.000000
121
+ 2024-03-26 10:16:57,547 epoch 3 - iter 44/48 - loss 0.30188412 - time (sec): 24.17 - samples/sec: 1336.95 - lr: 0.000024 - momentum: 0.000000
122
+ 2024-03-26 10:16:59,044 epoch 3 - iter 48/48 - loss 0.30424410 - time (sec): 25.66 - samples/sec: 1343.29 - lr: 0.000023 - momentum: 0.000000
123
+ 2024-03-26 10:16:59,044 ----------------------------------------------------------------------------------------------------
124
+ 2024-03-26 10:16:59,044 EPOCH 3 done: loss 0.3042 - lr: 0.000023
125
+ 2024-03-26 10:16:59,951 DEV : loss 0.24834905564785004 - f1-score (micro avg) 0.8417
126
+ 2024-03-26 10:16:59,952 saving best model
127
+ 2024-03-26 10:17:00,388 ----------------------------------------------------------------------------------------------------
128
+ 2024-03-26 10:17:03,381 epoch 4 - iter 4/48 - loss 0.16357798 - time (sec): 2.99 - samples/sec: 1218.46 - lr: 0.000023 - momentum: 0.000000
129
+ 2024-03-26 10:17:04,675 epoch 4 - iter 8/48 - loss 0.19203458 - time (sec): 4.28 - samples/sec: 1372.52 - lr: 0.000023 - momentum: 0.000000
130
+ 2024-03-26 10:17:06,741 epoch 4 - iter 12/48 - loss 0.20034927 - time (sec): 6.35 - samples/sec: 1452.34 - lr: 0.000023 - momentum: 0.000000
131
+ 2024-03-26 10:17:09,275 epoch 4 - iter 16/48 - loss 0.19820873 - time (sec): 8.88 - samples/sec: 1371.25 - lr: 0.000022 - momentum: 0.000000
132
+ 2024-03-26 10:17:10,256 epoch 4 - iter 20/48 - loss 0.19764534 - time (sec): 9.87 - samples/sec: 1455.96 - lr: 0.000022 - momentum: 0.000000
133
+ 2024-03-26 10:17:11,638 epoch 4 - iter 24/48 - loss 0.20056094 - time (sec): 11.25 - samples/sec: 1502.68 - lr: 0.000022 - momentum: 0.000000
134
+ 2024-03-26 10:17:14,733 epoch 4 - iter 28/48 - loss 0.19142315 - time (sec): 14.34 - samples/sec: 1407.17 - lr: 0.000022 - momentum: 0.000000
135
+ 2024-03-26 10:17:17,197 epoch 4 - iter 32/48 - loss 0.20173939 - time (sec): 16.81 - samples/sec: 1399.26 - lr: 0.000021 - momentum: 0.000000
136
+ 2024-03-26 10:17:18,705 epoch 4 - iter 36/48 - loss 0.20107167 - time (sec): 18.32 - samples/sec: 1434.77 - lr: 0.000021 - momentum: 0.000000
137
+ 2024-03-26 10:17:20,679 epoch 4 - iter 40/48 - loss 0.19651999 - time (sec): 20.29 - samples/sec: 1449.07 - lr: 0.000021 - momentum: 0.000000
138
+ 2024-03-26 10:17:22,559 epoch 4 - iter 44/48 - loss 0.19276541 - time (sec): 22.17 - samples/sec: 1463.05 - lr: 0.000020 - momentum: 0.000000
139
+ 2024-03-26 10:17:23,594 epoch 4 - iter 48/48 - loss 0.19451533 - time (sec): 23.20 - samples/sec: 1485.60 - lr: 0.000020 - momentum: 0.000000
140
+ 2024-03-26 10:17:23,594 ----------------------------------------------------------------------------------------------------
141
+ 2024-03-26 10:17:23,594 EPOCH 4 done: loss 0.1945 - lr: 0.000020
142
+ 2024-03-26 10:17:24,489 DEV : loss 0.21226930618286133 - f1-score (micro avg) 0.8725
143
+ 2024-03-26 10:17:24,490 saving best model
144
+ 2024-03-26 10:17:24,914 ----------------------------------------------------------------------------------------------------
145
+ 2024-03-26 10:17:25,970 epoch 5 - iter 4/48 - loss 0.22900511 - time (sec): 1.05 - samples/sec: 2412.52 - lr: 0.000020 - momentum: 0.000000
146
+ 2024-03-26 10:17:27,831 epoch 5 - iter 8/48 - loss 0.20745093 - time (sec): 2.92 - samples/sec: 1777.12 - lr: 0.000020 - momentum: 0.000000
147
+ 2024-03-26 10:17:29,928 epoch 5 - iter 12/48 - loss 0.19394759 - time (sec): 5.01 - samples/sec: 1596.67 - lr: 0.000019 - momentum: 0.000000
148
+ 2024-03-26 10:17:32,188 epoch 5 - iter 16/48 - loss 0.17919168 - time (sec): 7.27 - samples/sec: 1525.06 - lr: 0.000019 - momentum: 0.000000
149
+ 2024-03-26 10:17:34,431 epoch 5 - iter 20/48 - loss 0.17309969 - time (sec): 9.52 - samples/sec: 1438.12 - lr: 0.000019 - momentum: 0.000000
150
+ 2024-03-26 10:17:36,589 epoch 5 - iter 24/48 - loss 0.16467634 - time (sec): 11.67 - samples/sec: 1455.52 - lr: 0.000018 - momentum: 0.000000
151
+ 2024-03-26 10:17:38,184 epoch 5 - iter 28/48 - loss 0.16079508 - time (sec): 13.27 - samples/sec: 1483.39 - lr: 0.000018 - momentum: 0.000000
152
+ 2024-03-26 10:17:40,278 epoch 5 - iter 32/48 - loss 0.15041135 - time (sec): 15.36 - samples/sec: 1503.84 - lr: 0.000018 - momentum: 0.000000
153
+ 2024-03-26 10:17:41,672 epoch 5 - iter 36/48 - loss 0.14767635 - time (sec): 16.76 - samples/sec: 1527.72 - lr: 0.000018 - momentum: 0.000000
154
+ 2024-03-26 10:17:44,219 epoch 5 - iter 40/48 - loss 0.14147108 - time (sec): 19.30 - samples/sec: 1493.43 - lr: 0.000017 - momentum: 0.000000
155
+ 2024-03-26 10:17:47,159 epoch 5 - iter 44/48 - loss 0.13978631 - time (sec): 22.24 - samples/sec: 1439.87 - lr: 0.000017 - momentum: 0.000000
156
+ 2024-03-26 10:17:48,665 epoch 5 - iter 48/48 - loss 0.14191100 - time (sec): 23.75 - samples/sec: 1451.53 - lr: 0.000017 - momentum: 0.000000
157
+ 2024-03-26 10:17:48,665 ----------------------------------------------------------------------------------------------------
158
+ 2024-03-26 10:17:48,665 EPOCH 5 done: loss 0.1419 - lr: 0.000017
159
+ 2024-03-26 10:17:49,581 DEV : loss 0.17432889342308044 - f1-score (micro avg) 0.8924
160
+ 2024-03-26 10:17:49,583 saving best model
161
+ 2024-03-26 10:17:50,029 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 10:17:51,893 epoch 6 - iter 4/48 - loss 0.14473226 - time (sec): 1.86 - samples/sec: 1578.61 - lr: 0.000017 - momentum: 0.000000
163
+ 2024-03-26 10:17:53,612 epoch 6 - iter 8/48 - loss 0.12456982 - time (sec): 3.58 - samples/sec: 1618.91 - lr: 0.000016 - momentum: 0.000000
164
+ 2024-03-26 10:17:55,912 epoch 6 - iter 12/48 - loss 0.12108378 - time (sec): 5.88 - samples/sec: 1499.33 - lr: 0.000016 - momentum: 0.000000
165
+ 2024-03-26 10:17:57,476 epoch 6 - iter 16/48 - loss 0.11264219 - time (sec): 7.44 - samples/sec: 1522.01 - lr: 0.000016 - momentum: 0.000000
166
+ 2024-03-26 10:18:00,033 epoch 6 - iter 20/48 - loss 0.10247223 - time (sec): 10.00 - samples/sec: 1436.35 - lr: 0.000015 - momentum: 0.000000
167
+ 2024-03-26 10:18:02,087 epoch 6 - iter 24/48 - loss 0.10312786 - time (sec): 12.06 - samples/sec: 1450.74 - lr: 0.000015 - momentum: 0.000000
168
+ 2024-03-26 10:18:04,714 epoch 6 - iter 28/48 - loss 0.10393896 - time (sec): 14.68 - samples/sec: 1425.71 - lr: 0.000015 - momentum: 0.000000
169
+ 2024-03-26 10:18:06,764 epoch 6 - iter 32/48 - loss 0.10212557 - time (sec): 16.73 - samples/sec: 1404.50 - lr: 0.000015 - momentum: 0.000000
170
+ 2024-03-26 10:18:07,864 epoch 6 - iter 36/48 - loss 0.10345036 - time (sec): 17.83 - samples/sec: 1454.68 - lr: 0.000014 - momentum: 0.000000
171
+ 2024-03-26 10:18:10,059 epoch 6 - iter 40/48 - loss 0.10498644 - time (sec): 20.03 - samples/sec: 1443.81 - lr: 0.000014 - momentum: 0.000000
172
+ 2024-03-26 10:18:11,667 epoch 6 - iter 44/48 - loss 0.10975459 - time (sec): 21.64 - samples/sec: 1467.53 - lr: 0.000014 - momentum: 0.000000
173
+ 2024-03-26 10:18:13,439 epoch 6 - iter 48/48 - loss 0.10750133 - time (sec): 23.41 - samples/sec: 1472.63 - lr: 0.000014 - momentum: 0.000000
174
+ 2024-03-26 10:18:13,440 ----------------------------------------------------------------------------------------------------
175
+ 2024-03-26 10:18:13,440 EPOCH 6 done: loss 0.1075 - lr: 0.000014
176
+ 2024-03-26 10:18:14,342 DEV : loss 0.16816526651382446 - f1-score (micro avg) 0.8996
177
+ 2024-03-26 10:18:14,344 saving best model
178
+ 2024-03-26 10:18:14,755 ----------------------------------------------------------------------------------------------------
179
+ 2024-03-26 10:18:16,361 epoch 7 - iter 4/48 - loss 0.09156530 - time (sec): 1.61 - samples/sec: 1743.14 - lr: 0.000013 - momentum: 0.000000
180
+ 2024-03-26 10:18:18,453 epoch 7 - iter 8/48 - loss 0.07762594 - time (sec): 3.70 - samples/sec: 1655.21 - lr: 0.000013 - momentum: 0.000000
181
+ 2024-03-26 10:18:20,673 epoch 7 - iter 12/48 - loss 0.07628831 - time (sec): 5.92 - samples/sec: 1488.77 - lr: 0.000013 - momentum: 0.000000
182
+ 2024-03-26 10:18:21,840 epoch 7 - iter 16/48 - loss 0.08639863 - time (sec): 7.08 - samples/sec: 1588.88 - lr: 0.000012 - momentum: 0.000000
183
+ 2024-03-26 10:18:23,946 epoch 7 - iter 20/48 - loss 0.08684581 - time (sec): 9.19 - samples/sec: 1560.88 - lr: 0.000012 - momentum: 0.000000
184
+ 2024-03-26 10:18:25,446 epoch 7 - iter 24/48 - loss 0.08404483 - time (sec): 10.69 - samples/sec: 1610.09 - lr: 0.000012 - momentum: 0.000000
185
+ 2024-03-26 10:18:27,540 epoch 7 - iter 28/48 - loss 0.08184808 - time (sec): 12.78 - samples/sec: 1570.22 - lr: 0.000012 - momentum: 0.000000
186
+ 2024-03-26 10:18:30,297 epoch 7 - iter 32/48 - loss 0.08200584 - time (sec): 15.54 - samples/sec: 1498.51 - lr: 0.000011 - momentum: 0.000000
187
+ 2024-03-26 10:18:32,241 epoch 7 - iter 36/48 - loss 0.08034921 - time (sec): 17.49 - samples/sec: 1500.73 - lr: 0.000011 - momentum: 0.000000
188
+ 2024-03-26 10:18:33,354 epoch 7 - iter 40/48 - loss 0.08407326 - time (sec): 18.60 - samples/sec: 1532.40 - lr: 0.000011 - momentum: 0.000000
189
+ 2024-03-26 10:18:35,939 epoch 7 - iter 44/48 - loss 0.08503551 - time (sec): 21.18 - samples/sec: 1513.53 - lr: 0.000010 - momentum: 0.000000
190
+ 2024-03-26 10:18:37,041 epoch 7 - iter 48/48 - loss 0.08657468 - time (sec): 22.28 - samples/sec: 1546.88 - lr: 0.000010 - momentum: 0.000000
191
+ 2024-03-26 10:18:37,041 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 10:18:37,041 EPOCH 7 done: loss 0.0866 - lr: 0.000010
193
+ 2024-03-26 10:18:37,939 DEV : loss 0.18013019859790802 - f1-score (micro avg) 0.9053
194
+ 2024-03-26 10:18:37,940 saving best model
195
+ 2024-03-26 10:18:38,380 ----------------------------------------------------------------------------------------------------
196
+ 2024-03-26 10:18:40,490 epoch 8 - iter 4/48 - loss 0.05940590 - time (sec): 2.11 - samples/sec: 1314.77 - lr: 0.000010 - momentum: 0.000000
197
+ 2024-03-26 10:18:43,093 epoch 8 - iter 8/48 - loss 0.05066426 - time (sec): 4.71 - samples/sec: 1281.95 - lr: 0.000010 - momentum: 0.000000
198
+ 2024-03-26 10:18:44,741 epoch 8 - iter 12/48 - loss 0.05202001 - time (sec): 6.36 - samples/sec: 1333.67 - lr: 0.000009 - momentum: 0.000000
199
+ 2024-03-26 10:18:47,332 epoch 8 - iter 16/48 - loss 0.06461025 - time (sec): 8.95 - samples/sec: 1286.28 - lr: 0.000009 - momentum: 0.000000
200
+ 2024-03-26 10:18:48,957 epoch 8 - iter 20/48 - loss 0.06519928 - time (sec): 10.57 - samples/sec: 1343.58 - lr: 0.000009 - momentum: 0.000000
201
+ 2024-03-26 10:18:50,408 epoch 8 - iter 24/48 - loss 0.07047337 - time (sec): 12.03 - samples/sec: 1413.48 - lr: 0.000009 - momentum: 0.000000
202
+ 2024-03-26 10:18:52,258 epoch 8 - iter 28/48 - loss 0.07587165 - time (sec): 13.88 - samples/sec: 1437.19 - lr: 0.000008 - momentum: 0.000000
203
+ 2024-03-26 10:18:54,884 epoch 8 - iter 32/48 - loss 0.07553527 - time (sec): 16.50 - samples/sec: 1423.63 - lr: 0.000008 - momentum: 0.000000
204
+ 2024-03-26 10:18:57,265 epoch 8 - iter 36/48 - loss 0.07533218 - time (sec): 18.88 - samples/sec: 1415.70 - lr: 0.000008 - momentum: 0.000000
205
+ 2024-03-26 10:18:59,444 epoch 8 - iter 40/48 - loss 0.07539987 - time (sec): 21.06 - samples/sec: 1396.95 - lr: 0.000007 - momentum: 0.000000
206
+ 2024-03-26 10:19:01,664 epoch 8 - iter 44/48 - loss 0.07328438 - time (sec): 23.28 - samples/sec: 1387.55 - lr: 0.000007 - momentum: 0.000000
207
+ 2024-03-26 10:19:03,207 epoch 8 - iter 48/48 - loss 0.07364478 - time (sec): 24.83 - samples/sec: 1388.59 - lr: 0.000007 - momentum: 0.000000
208
+ 2024-03-26 10:19:03,208 ----------------------------------------------------------------------------------------------------
209
+ 2024-03-26 10:19:03,208 EPOCH 8 done: loss 0.0736 - lr: 0.000007
210
+ 2024-03-26 10:19:04,106 DEV : loss 0.16676065325737 - f1-score (micro avg) 0.9158
211
+ 2024-03-26 10:19:04,107 saving best model
212
+ 2024-03-26 10:19:04,540 ----------------------------------------------------------------------------------------------------
213
+ 2024-03-26 10:19:06,396 epoch 9 - iter 4/48 - loss 0.07456918 - time (sec): 1.85 - samples/sec: 1557.74 - lr: 0.000007 - momentum: 0.000000
214
+ 2024-03-26 10:19:09,537 epoch 9 - iter 8/48 - loss 0.07242803 - time (sec): 4.99 - samples/sec: 1260.29 - lr: 0.000006 - momentum: 0.000000
215
+ 2024-03-26 10:19:11,171 epoch 9 - iter 12/48 - loss 0.06181526 - time (sec): 6.63 - samples/sec: 1304.71 - lr: 0.000006 - momentum: 0.000000
216
+ 2024-03-26 10:19:13,041 epoch 9 - iter 16/48 - loss 0.06839209 - time (sec): 8.50 - samples/sec: 1345.05 - lr: 0.000006 - momentum: 0.000000
217
+ 2024-03-26 10:19:15,912 epoch 9 - iter 20/48 - loss 0.06071099 - time (sec): 11.37 - samples/sec: 1306.30 - lr: 0.000006 - momentum: 0.000000
218
+ 2024-03-26 10:19:17,437 epoch 9 - iter 24/48 - loss 0.06069450 - time (sec): 12.90 - samples/sec: 1353.07 - lr: 0.000005 - momentum: 0.000000
219
+ 2024-03-26 10:19:19,370 epoch 9 - iter 28/48 - loss 0.06366137 - time (sec): 14.83 - samples/sec: 1377.70 - lr: 0.000005 - momentum: 0.000000
220
+ 2024-03-26 10:19:21,689 epoch 9 - iter 32/48 - loss 0.06159224 - time (sec): 17.15 - samples/sec: 1354.78 - lr: 0.000005 - momentum: 0.000000
221
+ 2024-03-26 10:19:22,986 epoch 9 - iter 36/48 - loss 0.06577623 - time (sec): 18.44 - samples/sec: 1385.96 - lr: 0.000004 - momentum: 0.000000
222
+ 2024-03-26 10:19:26,188 epoch 9 - iter 40/48 - loss 0.06302902 - time (sec): 21.65 - samples/sec: 1336.88 - lr: 0.000004 - momentum: 0.000000
223
+ 2024-03-26 10:19:28,302 epoch 9 - iter 44/48 - loss 0.06043263 - time (sec): 23.76 - samples/sec: 1359.42 - lr: 0.000004 - momentum: 0.000000
224
+ 2024-03-26 10:19:29,289 epoch 9 - iter 48/48 - loss 0.06250231 - time (sec): 24.75 - samples/sec: 1393.01 - lr: 0.000004 - momentum: 0.000000
225
+ 2024-03-26 10:19:29,289 ----------------------------------------------------------------------------------------------------
226
+ 2024-03-26 10:19:29,289 EPOCH 9 done: loss 0.0625 - lr: 0.000004
227
+ 2024-03-26 10:19:30,191 DEV : loss 0.15200284123420715 - f1-score (micro avg) 0.925
228
+ 2024-03-26 10:19:30,192 saving best model
229
+ 2024-03-26 10:19:30,613 ----------------------------------------------------------------------------------------------------
230
+ 2024-03-26 10:19:32,484 epoch 10 - iter 4/48 - loss 0.06632142 - time (sec): 1.87 - samples/sec: 1382.85 - lr: 0.000003 - momentum: 0.000000
231
+ 2024-03-26 10:19:35,257 epoch 10 - iter 8/48 - loss 0.04726173 - time (sec): 4.64 - samples/sec: 1246.33 - lr: 0.000003 - momentum: 0.000000
232
+ 2024-03-26 10:19:37,284 epoch 10 - iter 12/48 - loss 0.05495615 - time (sec): 6.67 - samples/sec: 1306.57 - lr: 0.000003 - momentum: 0.000000
233
+ 2024-03-26 10:19:39,304 epoch 10 - iter 16/48 - loss 0.05438606 - time (sec): 8.69 - samples/sec: 1400.10 - lr: 0.000002 - momentum: 0.000000
234
+ 2024-03-26 10:19:40,170 epoch 10 - iter 20/48 - loss 0.05397075 - time (sec): 9.56 - samples/sec: 1477.42 - lr: 0.000002 - momentum: 0.000000
235
+ 2024-03-26 10:19:41,853 epoch 10 - iter 24/48 - loss 0.05286287 - time (sec): 11.24 - samples/sec: 1505.12 - lr: 0.000002 - momentum: 0.000000
236
+ 2024-03-26 10:19:42,787 epoch 10 - iter 28/48 - loss 0.05312673 - time (sec): 12.17 - samples/sec: 1569.84 - lr: 0.000002 - momentum: 0.000000
237
+ 2024-03-26 10:19:45,100 epoch 10 - iter 32/48 - loss 0.05163266 - time (sec): 14.48 - samples/sec: 1535.96 - lr: 0.000001 - momentum: 0.000000
238
+ 2024-03-26 10:19:47,587 epoch 10 - iter 36/48 - loss 0.05428024 - time (sec): 16.97 - samples/sec: 1502.19 - lr: 0.000001 - momentum: 0.000000
239
+ 2024-03-26 10:19:49,469 epoch 10 - iter 40/48 - loss 0.05721031 - time (sec): 18.85 - samples/sec: 1496.49 - lr: 0.000001 - momentum: 0.000000
240
+ 2024-03-26 10:19:52,039 epoch 10 - iter 44/48 - loss 0.05600849 - time (sec): 21.42 - samples/sec: 1484.28 - lr: 0.000001 - momentum: 0.000000
241
+ 2024-03-26 10:19:53,639 epoch 10 - iter 48/48 - loss 0.05587015 - time (sec): 23.02 - samples/sec: 1497.23 - lr: 0.000000 - momentum: 0.000000
242
+ 2024-03-26 10:19:53,639 ----------------------------------------------------------------------------------------------------
243
+ 2024-03-26 10:19:53,639 EPOCH 10 done: loss 0.0559 - lr: 0.000000
244
+ 2024-03-26 10:19:54,542 DEV : loss 0.15424026548862457 - f1-score (micro avg) 0.9273
245
+ 2024-03-26 10:19:54,543 saving best model
246
+ 2024-03-26 10:19:55,253 ----------------------------------------------------------------------------------------------------
247
+ 2024-03-26 10:19:55,253 Loading model from best epoch ...
248
+ 2024-03-26 10:19:56,194 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
249
+ 2024-03-26 10:19:56,949
250
+ Results:
251
+ - F-score (micro) 0.9048
252
+ - F-score (macro) 0.6876
253
+ - Accuracy 0.8284
254
+
255
+ By class:
256
+ precision recall f1-score support
257
+
258
+ Unternehmen 0.9102 0.8759 0.8927 266
259
+ Auslagerung 0.8682 0.8996 0.8836 249
260
+ Ort 0.9635 0.9851 0.9742 134
261
+ Software 0.0000 0.0000 0.0000 0
262
+
263
+ micro avg 0.9020 0.9076 0.9048 649
264
+ macro avg 0.6855 0.6902 0.6876 649
265
+ weighted avg 0.9051 0.9076 0.9060 649
266
+
267
+ 2024-03-26 10:19:56,949 ----------------------------------------------------------------------------------------------------