Hugging Face's logo

stefan-it
/
flair-co-funer-gbert_base-bs16-e10-lr3e-05-1

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
4e0c761
•
1 Parent(s): 33a269e

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +265 -0
training.log ADDED
@@ -0,0 +1,265 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-03-26 09:27:01,310 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 09:27:01,311 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 09:27:01,311 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 09:27:01,311 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 09:27:01,311 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 09:27:01,311 Train: 758 sentences
54
+ 2024-03-26 09:27:01,311 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 09:27:01,311 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 09:27:01,311 Training Params:
57
+ 2024-03-26 09:27:01,311 - learning_rate: "3e-05"
58
+ 2024-03-26 09:27:01,311 - mini_batch_size: "16"
59
+ 2024-03-26 09:27:01,311 - max_epochs: "10"
60
+ 2024-03-26 09:27:01,311 - shuffle: "True"
61
+ 2024-03-26 09:27:01,311 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 09:27:01,311 Plugins:
63
+ 2024-03-26 09:27:01,311 - TensorboardLogger
64
+ 2024-03-26 09:27:01,311 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 09:27:01,311 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 09:27:01,311 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 09:27:01,311 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 09:27:01,311 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 09:27:01,311 Computation:
70
+ 2024-03-26 09:27:01,311 - compute on device: cuda:0
71
+ 2024-03-26 09:27:01,311 - embedding storage: none
72
+ 2024-03-26 09:27:01,311 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 09:27:01,311 Model training base path: "flair-co-funer-gbert_base-bs16-e10-lr3e-05-1"
74
+ 2024-03-26 09:27:01,311 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 09:27:01,311 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 09:27:01,311 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 09:27:03,347 epoch 1 - iter 4/48 - loss 3.13979079 - time (sec): 2.04 - samples/sec: 1333.70 - lr: 0.000002 - momentum: 0.000000
78
+ 2024-03-26 09:27:04,595 epoch 1 - iter 8/48 - loss 3.07798066 - time (sec): 3.28 - samples/sec: 1641.38 - lr: 0.000004 - momentum: 0.000000
79
+ 2024-03-26 09:27:07,585 epoch 1 - iter 12/48 - loss 2.97060594 - time (sec): 6.27 - samples/sec: 1387.12 - lr: 0.000007 - momentum: 0.000000
80
+ 2024-03-26 09:27:10,667 epoch 1 - iter 16/48 - loss 2.84417408 - time (sec): 9.36 - samples/sec: 1303.32 - lr: 0.000009 - momentum: 0.000000
81
+ 2024-03-26 09:27:13,058 epoch 1 - iter 20/48 - loss 2.69619801 - time (sec): 11.75 - samples/sec: 1309.52 - lr: 0.000012 - momentum: 0.000000
82
+ 2024-03-26 09:27:14,710 epoch 1 - iter 24/48 - loss 2.56981828 - time (sec): 13.40 - samples/sec: 1361.09 - lr: 0.000014 - momentum: 0.000000
83
+ 2024-03-26 09:27:16,246 epoch 1 - iter 28/48 - loss 2.46547501 - time (sec): 14.93 - samples/sec: 1386.12 - lr: 0.000017 - momentum: 0.000000
84
+ 2024-03-26 09:27:18,263 epoch 1 - iter 32/48 - loss 2.38026327 - time (sec): 16.95 - samples/sec: 1394.34 - lr: 0.000019 - momentum: 0.000000
85
+ 2024-03-26 09:27:19,211 epoch 1 - iter 36/48 - loss 2.31027246 - time (sec): 17.90 - samples/sec: 1455.28 - lr: 0.000022 - momentum: 0.000000
86
+ 2024-03-26 09:27:21,097 epoch 1 - iter 40/48 - loss 2.22806839 - time (sec): 19.79 - samples/sec: 1471.58 - lr: 0.000024 - momentum: 0.000000
87
+ 2024-03-26 09:27:23,034 epoch 1 - iter 44/48 - loss 2.14894110 - time (sec): 21.72 - samples/sec: 1458.43 - lr: 0.000027 - momentum: 0.000000
88
+ 2024-03-26 09:27:24,473 epoch 1 - iter 48/48 - loss 2.06114686 - time (sec): 23.16 - samples/sec: 1488.32 - lr: 0.000029 - momentum: 0.000000
89
+ 2024-03-26 09:27:24,473 ----------------------------------------------------------------------------------------------------
90
+ 2024-03-26 09:27:24,473 EPOCH 1 done: loss 2.0611 - lr: 0.000029
91
+ 2024-03-26 09:27:25,252 DEV : loss 0.7669001817703247 - f1-score (micro avg) 0.4977
92
+ 2024-03-26 09:27:25,253 saving best model
93
+ 2024-03-26 09:27:25,535 ----------------------------------------------------------------------------------------------------
94
+ 2024-03-26 09:27:27,913 epoch 2 - iter 4/48 - loss 0.98267064 - time (sec): 2.38 - samples/sec: 1304.60 - lr: 0.000030 - momentum: 0.000000
95
+ 2024-03-26 09:27:29,885 epoch 2 - iter 8/48 - loss 0.93150894 - time (sec): 4.35 - samples/sec: 1520.10 - lr: 0.000030 - momentum: 0.000000
96
+ 2024-03-26 09:27:32,046 epoch 2 - iter 12/48 - loss 0.87529358 - time (sec): 6.51 - samples/sec: 1422.15 - lr: 0.000029 - momentum: 0.000000
97
+ 2024-03-26 09:27:34,007 epoch 2 - iter 16/48 - loss 0.83035092 - time (sec): 8.47 - samples/sec: 1406.57 - lr: 0.000029 - momentum: 0.000000
98
+ 2024-03-26 09:27:36,039 epoch 2 - iter 20/48 - loss 0.78760978 - time (sec): 10.50 - samples/sec: 1427.73 - lr: 0.000029 - momentum: 0.000000
99
+ 2024-03-26 09:27:39,079 epoch 2 - iter 24/48 - loss 0.72756319 - time (sec): 13.54 - samples/sec: 1366.20 - lr: 0.000028 - momentum: 0.000000
100
+ 2024-03-26 09:27:41,351 epoch 2 - iter 28/48 - loss 0.70243644 - time (sec): 15.82 - samples/sec: 1362.01 - lr: 0.000028 - momentum: 0.000000
101
+ 2024-03-26 09:27:43,002 epoch 2 - iter 32/48 - loss 0.67807443 - time (sec): 17.47 - samples/sec: 1381.36 - lr: 0.000028 - momentum: 0.000000
102
+ 2024-03-26 09:27:43,988 epoch 2 - iter 36/48 - loss 0.66044671 - time (sec): 18.45 - samples/sec: 1433.59 - lr: 0.000028 - momentum: 0.000000
103
+ 2024-03-26 09:27:45,779 epoch 2 - iter 40/48 - loss 0.64116783 - time (sec): 20.24 - samples/sec: 1452.19 - lr: 0.000027 - momentum: 0.000000
104
+ 2024-03-26 09:27:47,724 epoch 2 - iter 44/48 - loss 0.62573228 - time (sec): 22.19 - samples/sec: 1447.07 - lr: 0.000027 - momentum: 0.000000
105
+ 2024-03-26 09:27:49,127 epoch 2 - iter 48/48 - loss 0.61188841 - time (sec): 23.59 - samples/sec: 1461.18 - lr: 0.000027 - momentum: 0.000000
106
+ 2024-03-26 09:27:49,128 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 09:27:49,128 EPOCH 2 done: loss 0.6119 - lr: 0.000027
108
+ 2024-03-26 09:27:50,059 DEV : loss 0.3239489793777466 - f1-score (micro avg) 0.7699
109
+ 2024-03-26 09:27:50,060 saving best model
110
+ 2024-03-26 09:27:50,511 ----------------------------------------------------------------------------------------------------
111
+ 2024-03-26 09:27:52,924 epoch 3 - iter 4/48 - loss 0.42826350 - time (sec): 2.41 - samples/sec: 1265.71 - lr: 0.000026 - momentum: 0.000000
112
+ 2024-03-26 09:27:54,703 epoch 3 - iter 8/48 - loss 0.38023174 - time (sec): 4.19 - samples/sec: 1400.36 - lr: 0.000026 - momentum: 0.000000
113
+ 2024-03-26 09:27:56,459 epoch 3 - iter 12/48 - loss 0.38279022 - time (sec): 5.95 - samples/sec: 1477.77 - lr: 0.000026 - momentum: 0.000000
114
+ 2024-03-26 09:27:58,856 epoch 3 - iter 16/48 - loss 0.35668301 - time (sec): 8.34 - samples/sec: 1463.88 - lr: 0.000026 - momentum: 0.000000
115
+ 2024-03-26 09:28:00,266 epoch 3 - iter 20/48 - loss 0.36344288 - time (sec): 9.75 - samples/sec: 1517.17 - lr: 0.000025 - momentum: 0.000000
116
+ 2024-03-26 09:28:03,119 epoch 3 - iter 24/48 - loss 0.34539125 - time (sec): 12.61 - samples/sec: 1500.12 - lr: 0.000025 - momentum: 0.000000
117
+ 2024-03-26 09:28:03,860 epoch 3 - iter 28/48 - loss 0.33533201 - time (sec): 13.35 - samples/sec: 1576.47 - lr: 0.000025 - momentum: 0.000000
118
+ 2024-03-26 09:28:06,336 epoch 3 - iter 32/48 - loss 0.32173533 - time (sec): 15.82 - samples/sec: 1518.36 - lr: 0.000025 - momentum: 0.000000
119
+ 2024-03-26 09:28:08,290 epoch 3 - iter 36/48 - loss 0.31315603 - time (sec): 17.78 - samples/sec: 1510.87 - lr: 0.000024 - momentum: 0.000000
120
+ 2024-03-26 09:28:10,135 epoch 3 - iter 40/48 - loss 0.31183643 - time (sec): 19.62 - samples/sec: 1499.51 - lr: 0.000024 - momentum: 0.000000
121
+ 2024-03-26 09:28:12,217 epoch 3 - iter 44/48 - loss 0.30012530 - time (sec): 21.70 - samples/sec: 1502.79 - lr: 0.000024 - momentum: 0.000000
122
+ 2024-03-26 09:28:13,416 epoch 3 - iter 48/48 - loss 0.29678680 - time (sec): 22.90 - samples/sec: 1505.13 - lr: 0.000023 - momentum: 0.000000
123
+ 2024-03-26 09:28:13,416 ----------------------------------------------------------------------------------------------------
124
+ 2024-03-26 09:28:13,416 EPOCH 3 done: loss 0.2968 - lr: 0.000023
125
+ 2024-03-26 09:28:14,287 DEV : loss 0.26448285579681396 - f1-score (micro avg) 0.8403
126
+ 2024-03-26 09:28:14,288 saving best model
127
+ 2024-03-26 09:28:14,759 ----------------------------------------------------------------------------------------------------
128
+ 2024-03-26 09:28:16,204 epoch 4 - iter 4/48 - loss 0.26363306 - time (sec): 1.44 - samples/sec: 1890.48 - lr: 0.000023 - momentum: 0.000000
129
+ 2024-03-26 09:28:18,545 epoch 4 - iter 8/48 - loss 0.23484258 - time (sec): 3.78 - samples/sec: 1516.61 - lr: 0.000023 - momentum: 0.000000
130
+ 2024-03-26 09:28:20,589 epoch 4 - iter 12/48 - loss 0.23169066 - time (sec): 5.83 - samples/sec: 1499.47 - lr: 0.000023 - momentum: 0.000000
131
+ 2024-03-26 09:28:22,699 epoch 4 - iter 16/48 - loss 0.20987272 - time (sec): 7.94 - samples/sec: 1508.53 - lr: 0.000022 - momentum: 0.000000
132
+ 2024-03-26 09:28:25,648 epoch 4 - iter 20/48 - loss 0.19941139 - time (sec): 10.89 - samples/sec: 1422.78 - lr: 0.000022 - momentum: 0.000000
133
+ 2024-03-26 09:28:27,042 epoch 4 - iter 24/48 - loss 0.19827921 - time (sec): 12.28 - samples/sec: 1467.58 - lr: 0.000022 - momentum: 0.000000
134
+ 2024-03-26 09:28:28,520 epoch 4 - iter 28/48 - loss 0.19424885 - time (sec): 13.76 - samples/sec: 1507.39 - lr: 0.000022 - momentum: 0.000000
135
+ 2024-03-26 09:28:30,929 epoch 4 - iter 32/48 - loss 0.20143061 - time (sec): 16.17 - samples/sec: 1499.19 - lr: 0.000021 - momentum: 0.000000
136
+ 2024-03-26 09:28:31,889 epoch 4 - iter 36/48 - loss 0.20123336 - time (sec): 17.13 - samples/sec: 1551.30 - lr: 0.000021 - momentum: 0.000000
137
+ 2024-03-26 09:28:34,211 epoch 4 - iter 40/48 - loss 0.19568585 - time (sec): 19.45 - samples/sec: 1501.59 - lr: 0.000021 - momentum: 0.000000
138
+ 2024-03-26 09:28:35,958 epoch 4 - iter 44/48 - loss 0.19592911 - time (sec): 21.20 - samples/sec: 1522.21 - lr: 0.000020 - momentum: 0.000000
139
+ 2024-03-26 09:28:37,276 epoch 4 - iter 48/48 - loss 0.19413849 - time (sec): 22.51 - samples/sec: 1531.11 - lr: 0.000020 - momentum: 0.000000
140
+ 2024-03-26 09:28:37,276 ----------------------------------------------------------------------------------------------------
141
+ 2024-03-26 09:28:37,276 EPOCH 4 done: loss 0.1941 - lr: 0.000020
142
+ 2024-03-26 09:28:38,202 DEV : loss 0.20181307196617126 - f1-score (micro avg) 0.8661
143
+ 2024-03-26 09:28:38,205 saving best model
144
+ 2024-03-26 09:28:38,648 ----------------------------------------------------------------------------------------------------
145
+ 2024-03-26 09:28:40,513 epoch 5 - iter 4/48 - loss 0.18286346 - time (sec): 1.86 - samples/sec: 1496.88 - lr: 0.000020 - momentum: 0.000000
146
+ 2024-03-26 09:28:42,881 epoch 5 - iter 8/48 - loss 0.15386085 - time (sec): 4.23 - samples/sec: 1403.07 - lr: 0.000020 - momentum: 0.000000
147
+ 2024-03-26 09:28:44,784 epoch 5 - iter 12/48 - loss 0.15581086 - time (sec): 6.13 - samples/sec: 1396.58 - lr: 0.000019 - momentum: 0.000000
148
+ 2024-03-26 09:28:46,735 epoch 5 - iter 16/48 - loss 0.15172544 - time (sec): 8.09 - samples/sec: 1428.78 - lr: 0.000019 - momentum: 0.000000
149
+ 2024-03-26 09:28:48,592 epoch 5 - iter 20/48 - loss 0.15213150 - time (sec): 9.94 - samples/sec: 1439.35 - lr: 0.000019 - momentum: 0.000000
150
+ 2024-03-26 09:28:50,059 epoch 5 - iter 24/48 - loss 0.15722917 - time (sec): 11.41 - samples/sec: 1490.75 - lr: 0.000018 - momentum: 0.000000
151
+ 2024-03-26 09:28:52,196 epoch 5 - iter 28/48 - loss 0.15699606 - time (sec): 13.55 - samples/sec: 1487.07 - lr: 0.000018 - momentum: 0.000000
152
+ 2024-03-26 09:28:54,740 epoch 5 - iter 32/48 - loss 0.15384884 - time (sec): 16.09 - samples/sec: 1471.23 - lr: 0.000018 - momentum: 0.000000
153
+ 2024-03-26 09:28:57,055 epoch 5 - iter 36/48 - loss 0.14632635 - time (sec): 18.41 - samples/sec: 1474.42 - lr: 0.000018 - momentum: 0.000000
154
+ 2024-03-26 09:28:57,924 epoch 5 - iter 40/48 - loss 0.14743954 - time (sec): 19.27 - samples/sec: 1518.00 - lr: 0.000017 - momentum: 0.000000
155
+ 2024-03-26 09:29:00,487 epoch 5 - iter 44/48 - loss 0.14301882 - time (sec): 21.84 - samples/sec: 1482.96 - lr: 0.000017 - momentum: 0.000000
156
+ 2024-03-26 09:29:01,928 epoch 5 - iter 48/48 - loss 0.14207733 - time (sec): 23.28 - samples/sec: 1480.88 - lr: 0.000017 - momentum: 0.000000
157
+ 2024-03-26 09:29:01,928 ----------------------------------------------------------------------------------------------------
158
+ 2024-03-26 09:29:01,928 EPOCH 5 done: loss 0.1421 - lr: 0.000017
159
+ 2024-03-26 09:29:02,798 DEV : loss 0.1995552033185959 - f1-score (micro avg) 0.8842
160
+ 2024-03-26 09:29:02,799 saving best model
161
+ 2024-03-26 09:29:03,271 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 09:29:05,224 epoch 6 - iter 4/48 - loss 0.08497267 - time (sec): 1.95 - samples/sec: 1354.85 - lr: 0.000017 - momentum: 0.000000
163
+ 2024-03-26 09:29:07,333 epoch 6 - iter 8/48 - loss 0.11241659 - time (sec): 4.06 - samples/sec: 1362.26 - lr: 0.000016 - momentum: 0.000000
164
+ 2024-03-26 09:29:09,110 epoch 6 - iter 12/48 - loss 0.11714498 - time (sec): 5.84 - samples/sec: 1480.36 - lr: 0.000016 - momentum: 0.000000
165
+ 2024-03-26 09:29:11,290 epoch 6 - iter 16/48 - loss 0.11620269 - time (sec): 8.02 - samples/sec: 1433.00 - lr: 0.000016 - momentum: 0.000000
166
+ 2024-03-26 09:29:13,011 epoch 6 - iter 20/48 - loss 0.11740035 - time (sec): 9.74 - samples/sec: 1440.89 - lr: 0.000015 - momentum: 0.000000
167
+ 2024-03-26 09:29:15,416 epoch 6 - iter 24/48 - loss 0.11484259 - time (sec): 12.14 - samples/sec: 1417.97 - lr: 0.000015 - momentum: 0.000000
168
+ 2024-03-26 09:29:17,210 epoch 6 - iter 28/48 - loss 0.11528236 - time (sec): 13.94 - samples/sec: 1419.07 - lr: 0.000015 - momentum: 0.000000
169
+ 2024-03-26 09:29:19,622 epoch 6 - iter 32/48 - loss 0.11521092 - time (sec): 16.35 - samples/sec: 1398.04 - lr: 0.000015 - momentum: 0.000000
170
+ 2024-03-26 09:29:22,955 epoch 6 - iter 36/48 - loss 0.11033813 - time (sec): 19.68 - samples/sec: 1354.87 - lr: 0.000014 - momentum: 0.000000
171
+ 2024-03-26 09:29:24,519 epoch 6 - iter 40/48 - loss 0.10826951 - time (sec): 21.25 - samples/sec: 1390.87 - lr: 0.000014 - momentum: 0.000000
172
+ 2024-03-26 09:29:26,292 epoch 6 - iter 44/48 - loss 0.10638058 - time (sec): 23.02 - samples/sec: 1395.11 - lr: 0.000014 - momentum: 0.000000
173
+ 2024-03-26 09:29:27,541 epoch 6 - iter 48/48 - loss 0.10980662 - time (sec): 24.27 - samples/sec: 1420.44 - lr: 0.000014 - momentum: 0.000000
174
+ 2024-03-26 09:29:27,541 ----------------------------------------------------------------------------------------------------
175
+ 2024-03-26 09:29:27,541 EPOCH 6 done: loss 0.1098 - lr: 0.000014
176
+ 2024-03-26 09:29:28,421 DEV : loss 0.190290629863739 - f1-score (micro avg) 0.89
177
+ 2024-03-26 09:29:28,422 saving best model
178
+ 2024-03-26 09:29:28,868 ----------------------------------------------------------------------------------------------------
179
+ 2024-03-26 09:29:30,475 epoch 7 - iter 4/48 - loss 0.13132601 - time (sec): 1.60 - samples/sec: 1712.33 - lr: 0.000013 - momentum: 0.000000
180
+ 2024-03-26 09:29:32,500 epoch 7 - iter 8/48 - loss 0.10894840 - time (sec): 3.63 - samples/sec: 1481.78 - lr: 0.000013 - momentum: 0.000000
181
+ 2024-03-26 09:29:34,756 epoch 7 - iter 12/48 - loss 0.11116772 - time (sec): 5.89 - samples/sec: 1410.62 - lr: 0.000013 - momentum: 0.000000
182
+ 2024-03-26 09:29:37,286 epoch 7 - iter 16/48 - loss 0.10061780 - time (sec): 8.42 - samples/sec: 1371.43 - lr: 0.000012 - momentum: 0.000000
183
+ 2024-03-26 09:29:39,521 epoch 7 - iter 20/48 - loss 0.10057925 - time (sec): 10.65 - samples/sec: 1372.26 - lr: 0.000012 - momentum: 0.000000
184
+ 2024-03-26 09:29:40,854 epoch 7 - iter 24/48 - loss 0.09594952 - time (sec): 11.98 - samples/sec: 1427.56 - lr: 0.000012 - momentum: 0.000000
185
+ 2024-03-26 09:29:42,237 epoch 7 - iter 28/48 - loss 0.09355689 - time (sec): 13.37 - samples/sec: 1492.28 - lr: 0.000012 - momentum: 0.000000
186
+ 2024-03-26 09:29:44,188 epoch 7 - iter 32/48 - loss 0.08991898 - time (sec): 15.32 - samples/sec: 1480.72 - lr: 0.000011 - momentum: 0.000000
187
+ 2024-03-26 09:29:46,307 epoch 7 - iter 36/48 - loss 0.08734474 - time (sec): 17.44 - samples/sec: 1468.87 - lr: 0.000011 - momentum: 0.000000
188
+ 2024-03-26 09:29:48,727 epoch 7 - iter 40/48 - loss 0.08720038 - time (sec): 19.86 - samples/sec: 1447.45 - lr: 0.000011 - momentum: 0.000000
189
+ 2024-03-26 09:29:50,527 epoch 7 - iter 44/48 - loss 0.08727137 - time (sec): 21.66 - samples/sec: 1463.81 - lr: 0.000010 - momentum: 0.000000
190
+ 2024-03-26 09:29:52,412 epoch 7 - iter 48/48 - loss 0.08649088 - time (sec): 23.54 - samples/sec: 1464.31 - lr: 0.000010 - momentum: 0.000000
191
+ 2024-03-26 09:29:52,412 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 09:29:52,412 EPOCH 7 done: loss 0.0865 - lr: 0.000010
193
+ 2024-03-26 09:29:53,341 DEV : loss 0.17982175946235657 - f1-score (micro avg) 0.9045
194
+ 2024-03-26 09:29:53,343 saving best model
195
+ 2024-03-26 09:29:53,800 ----------------------------------------------------------------------------------------------------
196
+ 2024-03-26 09:29:55,741 epoch 8 - iter 4/48 - loss 0.09321231 - time (sec): 1.94 - samples/sec: 1393.95 - lr: 0.000010 - momentum: 0.000000
197
+ 2024-03-26 09:29:58,488 epoch 8 - iter 8/48 - loss 0.07249940 - time (sec): 4.69 - samples/sec: 1185.45 - lr: 0.000010 - momentum: 0.000000
198
+ 2024-03-26 09:29:59,746 epoch 8 - iter 12/48 - loss 0.07664782 - time (sec): 5.94 - samples/sec: 1342.92 - lr: 0.000009 - momentum: 0.000000
199
+ 2024-03-26 09:30:02,133 epoch 8 - iter 16/48 - loss 0.08386172 - time (sec): 8.33 - samples/sec: 1351.18 - lr: 0.000009 - momentum: 0.000000
200
+ 2024-03-26 09:30:04,610 epoch 8 - iter 20/48 - loss 0.07359994 - time (sec): 10.81 - samples/sec: 1394.07 - lr: 0.000009 - momentum: 0.000000
201
+ 2024-03-26 09:30:05,883 epoch 8 - iter 24/48 - loss 0.07537128 - time (sec): 12.08 - samples/sec: 1473.14 - lr: 0.000009 - momentum: 0.000000
202
+ 2024-03-26 09:30:09,106 epoch 8 - iter 28/48 - loss 0.07450515 - time (sec): 15.30 - samples/sec: 1425.76 - lr: 0.000008 - momentum: 0.000000
203
+ 2024-03-26 09:30:11,077 epoch 8 - iter 32/48 - loss 0.07698629 - time (sec): 17.28 - samples/sec: 1427.11 - lr: 0.000008 - momentum: 0.000000
204
+ 2024-03-26 09:30:12,123 epoch 8 - iter 36/48 - loss 0.07680939 - time (sec): 18.32 - samples/sec: 1465.62 - lr: 0.000008 - momentum: 0.000000
205
+ 2024-03-26 09:30:13,773 epoch 8 - iter 40/48 - loss 0.07577223 - time (sec): 19.97 - samples/sec: 1463.42 - lr: 0.000007 - momentum: 0.000000
206
+ 2024-03-26 09:30:15,328 epoch 8 - iter 44/48 - loss 0.07498246 - time (sec): 21.53 - samples/sec: 1484.35 - lr: 0.000007 - momentum: 0.000000
207
+ 2024-03-26 09:30:17,249 epoch 8 - iter 48/48 - loss 0.07557714 - time (sec): 23.45 - samples/sec: 1470.17 - lr: 0.000007 - momentum: 0.000000
208
+ 2024-03-26 09:30:17,249 ----------------------------------------------------------------------------------------------------
209
+ 2024-03-26 09:30:17,249 EPOCH 8 done: loss 0.0756 - lr: 0.000007
210
+ 2024-03-26 09:30:18,149 DEV : loss 0.17024415731430054 - f1-score (micro avg) 0.918
211
+ 2024-03-26 09:30:18,151 saving best model
212
+ 2024-03-26 09:30:18,606 ----------------------------------------------------------------------------------------------------
213
+ 2024-03-26 09:30:20,426 epoch 9 - iter 4/48 - loss 0.05767140 - time (sec): 1.82 - samples/sec: 1473.96 - lr: 0.000007 - momentum: 0.000000
214
+ 2024-03-26 09:30:23,553 epoch 9 - iter 8/48 - loss 0.04154401 - time (sec): 4.94 - samples/sec: 1262.98 - lr: 0.000006 - momentum: 0.000000
215
+ 2024-03-26 09:30:25,189 epoch 9 - iter 12/48 - loss 0.05035534 - time (sec): 6.58 - samples/sec: 1320.70 - lr: 0.000006 - momentum: 0.000000
216
+ 2024-03-26 09:30:27,408 epoch 9 - iter 16/48 - loss 0.05450684 - time (sec): 8.80 - samples/sec: 1309.29 - lr: 0.000006 - momentum: 0.000000
217
+ 2024-03-26 09:30:29,653 epoch 9 - iter 20/48 - loss 0.05915286 - time (sec): 11.04 - samples/sec: 1339.63 - lr: 0.000006 - momentum: 0.000000
218
+ 2024-03-26 09:30:31,806 epoch 9 - iter 24/48 - loss 0.06294200 - time (sec): 13.20 - samples/sec: 1355.11 - lr: 0.000005 - momentum: 0.000000
219
+ 2024-03-26 09:30:34,148 epoch 9 - iter 28/48 - loss 0.06112591 - time (sec): 15.54 - samples/sec: 1348.70 - lr: 0.000005 - momentum: 0.000000
220
+ 2024-03-26 09:30:36,453 epoch 9 - iter 32/48 - loss 0.06079575 - time (sec): 17.84 - samples/sec: 1345.68 - lr: 0.000005 - momentum: 0.000000
221
+ 2024-03-26 09:30:38,226 epoch 9 - iter 36/48 - loss 0.06342821 - time (sec): 19.62 - samples/sec: 1364.71 - lr: 0.000004 - momentum: 0.000000
222
+ 2024-03-26 09:30:40,379 epoch 9 - iter 40/48 - loss 0.06494860 - time (sec): 21.77 - samples/sec: 1354.37 - lr: 0.000004 - momentum: 0.000000
223
+ 2024-03-26 09:30:42,484 epoch 9 - iter 44/48 - loss 0.06451464 - time (sec): 23.88 - samples/sec: 1365.50 - lr: 0.000004 - momentum: 0.000000
224
+ 2024-03-26 09:30:43,220 epoch 9 - iter 48/48 - loss 0.06516833 - time (sec): 24.61 - samples/sec: 1400.60 - lr: 0.000004 - momentum: 0.000000
225
+ 2024-03-26 09:30:43,221 ----------------------------------------------------------------------------------------------------
226
+ 2024-03-26 09:30:43,221 EPOCH 9 done: loss 0.0652 - lr: 0.000004
227
+ 2024-03-26 09:30:44,109 DEV : loss 0.16860732436180115 - f1-score (micro avg) 0.9142
228
+ 2024-03-26 09:30:44,110 ----------------------------------------------------------------------------------------------------
229
+ 2024-03-26 09:30:45,829 epoch 10 - iter 4/48 - loss 0.04146833 - time (sec): 1.72 - samples/sec: 1529.39 - lr: 0.000003 - momentum: 0.000000
230
+ 2024-03-26 09:30:47,751 epoch 10 - iter 8/48 - loss 0.04228870 - time (sec): 3.64 - samples/sec: 1521.79 - lr: 0.000003 - momentum: 0.000000
231
+ 2024-03-26 09:30:50,430 epoch 10 - iter 12/48 - loss 0.04638348 - time (sec): 6.32 - samples/sec: 1380.80 - lr: 0.000003 - momentum: 0.000000
232
+ 2024-03-26 09:30:52,334 epoch 10 - iter 16/48 - loss 0.05569483 - time (sec): 8.22 - samples/sec: 1395.05 - lr: 0.000002 - momentum: 0.000000
233
+ 2024-03-26 09:30:54,151 epoch 10 - iter 20/48 - loss 0.05880033 - time (sec): 10.04 - samples/sec: 1440.66 - lr: 0.000002 - momentum: 0.000000
234
+ 2024-03-26 09:30:55,784 epoch 10 - iter 24/48 - loss 0.06605991 - time (sec): 11.67 - samples/sec: 1452.74 - lr: 0.000002 - momentum: 0.000000
235
+ 2024-03-26 09:30:57,517 epoch 10 - iter 28/48 - loss 0.06374936 - time (sec): 13.41 - samples/sec: 1475.79 - lr: 0.000002 - momentum: 0.000000
236
+ 2024-03-26 09:30:58,700 epoch 10 - iter 32/48 - loss 0.06224483 - time (sec): 14.59 - samples/sec: 1509.54 - lr: 0.000001 - momentum: 0.000000
237
+ 2024-03-26 09:31:01,656 epoch 10 - iter 36/48 - loss 0.05697960 - time (sec): 17.55 - samples/sec: 1459.85 - lr: 0.000001 - momentum: 0.000000
238
+ 2024-03-26 09:31:04,421 epoch 10 - iter 40/48 - loss 0.06062508 - time (sec): 20.31 - samples/sec: 1431.81 - lr: 0.000001 - momentum: 0.000000
239
+ 2024-03-26 09:31:07,187 epoch 10 - iter 44/48 - loss 0.05774779 - time (sec): 23.08 - samples/sec: 1398.91 - lr: 0.000001 - momentum: 0.000000
240
+ 2024-03-26 09:31:08,778 epoch 10 - iter 48/48 - loss 0.05640631 - time (sec): 24.67 - samples/sec: 1397.47 - lr: 0.000000 - momentum: 0.000000
241
+ 2024-03-26 09:31:08,778 ----------------------------------------------------------------------------------------------------
242
+ 2024-03-26 09:31:08,778 EPOCH 10 done: loss 0.0564 - lr: 0.000000
243
+ 2024-03-26 09:31:09,670 DEV : loss 0.16845521330833435 - f1-score (micro avg) 0.9144
244
+ 2024-03-26 09:31:09,951 ----------------------------------------------------------------------------------------------------
245
+ 2024-03-26 09:31:09,951 Loading model from best epoch ...
246
+ 2024-03-26 09:31:10,857 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
247
+ 2024-03-26 09:31:11,602
248
+ Results:
249
+ - F-score (micro) 0.8904
250
+ - F-score (macro) 0.6781
251
+ - Accuracy 0.808
252
+
253
+ By class:
254
+ precision recall f1-score support
255
+
256
+ Unternehmen 0.8927 0.8759 0.8843 266
257
+ Auslagerung 0.8333 0.8835 0.8577 249
258
+ Ort 0.9565 0.9851 0.9706 134
259
+ Software 0.0000 0.0000 0.0000 0
260
+
261
+ micro avg 0.8797 0.9014 0.8904 649
262
+ macro avg 0.6706 0.6861 0.6781 649
263
+ weighted avg 0.8831 0.9014 0.8919 649
264
+
265
+ 2024-03-26 09:31:11,602 ----------------------------------------------------------------------------------------------------