Hugging Face's logo

stefan-it
/
flair-co-funer-gbert_base-bs16-e10-lr5e-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
e85e689
•
1 Parent(s): 83d54d5

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 10:20:21,938 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 10:20:21,938 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 10:20:21,938 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 10:20:21,938 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 10:20:21,938 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 10:20:21,938 Train: 758 sentences
54
+ 2024-03-26 10:20:21,938 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 10:20:21,938 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 10:20:21,938 Training Params:
57
+ 2024-03-26 10:20:21,938 - learning_rate: "5e-05"
58
+ 2024-03-26 10:20:21,938 - mini_batch_size: "16"
59
+ 2024-03-26 10:20:21,938 - max_epochs: "10"
60
+ 2024-03-26 10:20:21,938 - shuffle: "True"
61
+ 2024-03-26 10:20:21,938 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 10:20:21,938 Plugins:
63
+ 2024-03-26 10:20:21,938 - TensorboardLogger
64
+ 2024-03-26 10:20:21,939 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 10:20:21,939 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 10:20:21,939 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 10:20:21,939 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 10:20:21,939 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 10:20:21,939 Computation:
70
+ 2024-03-26 10:20:21,939 - compute on device: cuda:0
71
+ 2024-03-26 10:20:21,939 - embedding storage: none
72
+ 2024-03-26 10:20:21,939 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 10:20:21,939 Model training base path: "flair-co-funer-gbert_base-bs16-e10-lr5e-05-4"
74
+ 2024-03-26 10:20:21,939 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 10:20:21,939 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 10:20:21,939 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 10:20:23,389 epoch 1 - iter 4/48 - loss 3.33143156 - time (sec): 1.45 - samples/sec: 1800.62 - lr: 0.000003 - momentum: 0.000000
78
+ 2024-03-26 10:20:25,188 epoch 1 - iter 8/48 - loss 3.24253277 - time (sec): 3.25 - samples/sec: 1576.87 - lr: 0.000007 - momentum: 0.000000
79
+ 2024-03-26 10:20:26,510 epoch 1 - iter 12/48 - loss 3.09296223 - time (sec): 4.57 - samples/sec: 1597.62 - lr: 0.000011 - momentum: 0.000000
80
+ 2024-03-26 10:20:29,021 epoch 1 - iter 16/48 - loss 2.83159528 - time (sec): 7.08 - samples/sec: 1510.67 - lr: 0.000016 - momentum: 0.000000
81
+ 2024-03-26 10:20:31,108 epoch 1 - iter 20/48 - loss 2.68393125 - time (sec): 9.17 - samples/sec: 1493.92 - lr: 0.000020 - momentum: 0.000000
82
+ 2024-03-26 10:20:33,765 epoch 1 - iter 24/48 - loss 2.52199527 - time (sec): 11.83 - samples/sec: 1431.14 - lr: 0.000024 - momentum: 0.000000
83
+ 2024-03-26 10:20:36,248 epoch 1 - iter 28/48 - loss 2.39681153 - time (sec): 14.31 - samples/sec: 1417.79 - lr: 0.000028 - momentum: 0.000000
84
+ 2024-03-26 10:20:38,112 epoch 1 - iter 32/48 - loss 2.30150701 - time (sec): 16.17 - samples/sec: 1414.35 - lr: 0.000032 - momentum: 0.000000
85
+ 2024-03-26 10:20:38,990 epoch 1 - iter 36/48 - loss 2.22901668 - time (sec): 17.05 - samples/sec: 1465.06 - lr: 0.000036 - momentum: 0.000000
86
+ 2024-03-26 10:20:40,843 epoch 1 - iter 40/48 - loss 2.11985964 - time (sec): 18.90 - samples/sec: 1473.35 - lr: 0.000041 - momentum: 0.000000
87
+ 2024-03-26 10:20:42,869 epoch 1 - iter 44/48 - loss 1.99600231 - time (sec): 20.93 - samples/sec: 1492.07 - lr: 0.000045 - momentum: 0.000000
88
+ 2024-03-26 10:20:44,580 epoch 1 - iter 48/48 - loss 1.90143416 - time (sec): 22.64 - samples/sec: 1522.55 - lr: 0.000049 - momentum: 0.000000
89
+ 2024-03-26 10:20:44,580 ----------------------------------------------------------------------------------------------------
90
+ 2024-03-26 10:20:44,580 EPOCH 1 done: loss 1.9014 - lr: 0.000049
91
+ 2024-03-26 10:20:45,388 DEV : loss 0.5843583941459656 - f1-score (micro avg) 0.6105
92
+ 2024-03-26 10:20:45,389 saving best model
93
+ 2024-03-26 10:20:45,671 ----------------------------------------------------------------------------------------------------
94
+ 2024-03-26 10:20:46,897 epoch 2 - iter 4/48 - loss 0.87169473 - time (sec): 1.23 - samples/sec: 1931.82 - lr: 0.000050 - momentum: 0.000000
95
+ 2024-03-26 10:20:49,128 epoch 2 - iter 8/48 - loss 0.67248507 - time (sec): 3.46 - samples/sec: 1578.54 - lr: 0.000049 - momentum: 0.000000
96
+ 2024-03-26 10:20:50,900 epoch 2 - iter 12/48 - loss 0.64179862 - time (sec): 5.23 - samples/sec: 1629.89 - lr: 0.000049 - momentum: 0.000000
97
+ 2024-03-26 10:20:53,272 epoch 2 - iter 16/48 - loss 0.57875086 - time (sec): 7.60 - samples/sec: 1484.27 - lr: 0.000048 - momentum: 0.000000
98
+ 2024-03-26 10:20:56,664 epoch 2 - iter 20/48 - loss 0.52549505 - time (sec): 10.99 - samples/sec: 1342.28 - lr: 0.000048 - momentum: 0.000000
99
+ 2024-03-26 10:20:58,142 epoch 2 - iter 24/48 - loss 0.52600785 - time (sec): 12.47 - samples/sec: 1398.75 - lr: 0.000047 - momentum: 0.000000
100
+ 2024-03-26 10:21:00,781 epoch 2 - iter 28/48 - loss 0.51174459 - time (sec): 15.11 - samples/sec: 1370.32 - lr: 0.000047 - momentum: 0.000000
101
+ 2024-03-26 10:21:03,461 epoch 2 - iter 32/48 - loss 0.49143427 - time (sec): 17.79 - samples/sec: 1372.11 - lr: 0.000046 - momentum: 0.000000
102
+ 2024-03-26 10:21:05,537 epoch 2 - iter 36/48 - loss 0.48842538 - time (sec): 19.87 - samples/sec: 1361.31 - lr: 0.000046 - momentum: 0.000000
103
+ 2024-03-26 10:21:08,002 epoch 2 - iter 40/48 - loss 0.47106482 - time (sec): 22.33 - samples/sec: 1351.68 - lr: 0.000046 - momentum: 0.000000
104
+ 2024-03-26 10:21:09,051 epoch 2 - iter 44/48 - loss 0.46284650 - time (sec): 23.38 - samples/sec: 1386.82 - lr: 0.000045 - momentum: 0.000000
105
+ 2024-03-26 10:21:10,205 epoch 2 - iter 48/48 - loss 0.45432071 - time (sec): 24.53 - samples/sec: 1405.07 - lr: 0.000045 - momentum: 0.000000
106
+ 2024-03-26 10:21:10,206 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 10:21:10,206 EPOCH 2 done: loss 0.4543 - lr: 0.000045
108
+ 2024-03-26 10:21:11,095 DEV : loss 0.27210864424705505 - f1-score (micro avg) 0.8439
109
+ 2024-03-26 10:21:11,096 saving best model
110
+ 2024-03-26 10:21:11,525 ----------------------------------------------------------------------------------------------------
111
+ 2024-03-26 10:21:13,505 epoch 3 - iter 4/48 - loss 0.28056207 - time (sec): 1.98 - samples/sec: 1240.70 - lr: 0.000044 - momentum: 0.000000
112
+ 2024-03-26 10:21:15,052 epoch 3 - iter 8/48 - loss 0.23255003 - time (sec): 3.53 - samples/sec: 1358.59 - lr: 0.000044 - momentum: 0.000000
113
+ 2024-03-26 10:21:17,622 epoch 3 - iter 12/48 - loss 0.23329462 - time (sec): 6.10 - samples/sec: 1276.30 - lr: 0.000043 - momentum: 0.000000
114
+ 2024-03-26 10:21:19,629 epoch 3 - iter 16/48 - loss 0.23716737 - time (sec): 8.10 - samples/sec: 1316.13 - lr: 0.000043 - momentum: 0.000000
115
+ 2024-03-26 10:21:21,510 epoch 3 - iter 20/48 - loss 0.23579224 - time (sec): 9.98 - samples/sec: 1386.82 - lr: 0.000042 - momentum: 0.000000
116
+ 2024-03-26 10:21:23,730 epoch 3 - iter 24/48 - loss 0.23278104 - time (sec): 12.20 - samples/sec: 1400.92 - lr: 0.000042 - momentum: 0.000000
117
+ 2024-03-26 10:21:26,190 epoch 3 - iter 28/48 - loss 0.22345605 - time (sec): 14.66 - samples/sec: 1360.25 - lr: 0.000041 - momentum: 0.000000
118
+ 2024-03-26 10:21:28,736 epoch 3 - iter 32/48 - loss 0.21820840 - time (sec): 17.21 - samples/sec: 1336.04 - lr: 0.000041 - momentum: 0.000000
119
+ 2024-03-26 10:21:30,845 epoch 3 - iter 36/48 - loss 0.21675927 - time (sec): 19.32 - samples/sec: 1340.02 - lr: 0.000040 - momentum: 0.000000
120
+ 2024-03-26 10:21:33,145 epoch 3 - iter 40/48 - loss 0.22341811 - time (sec): 21.62 - samples/sec: 1355.58 - lr: 0.000040 - momentum: 0.000000
121
+ 2024-03-26 10:21:35,667 epoch 3 - iter 44/48 - loss 0.21735862 - time (sec): 24.14 - samples/sec: 1338.36 - lr: 0.000040 - momentum: 0.000000
122
+ 2024-03-26 10:21:37,169 epoch 3 - iter 48/48 - loss 0.21861097 - time (sec): 25.64 - samples/sec: 1344.30 - lr: 0.000039 - momentum: 0.000000
123
+ 2024-03-26 10:21:37,170 ----------------------------------------------------------------------------------------------------
124
+ 2024-03-26 10:21:37,170 EPOCH 3 done: loss 0.2186 - lr: 0.000039
125
+ 2024-03-26 10:21:38,088 DEV : loss 0.1997971087694168 - f1-score (micro avg) 0.8749
126
+ 2024-03-26 10:21:38,089 saving best model
127
+ 2024-03-26 10:21:38,536 ----------------------------------------------------------------------------------------------------
128
+ 2024-03-26 10:21:41,519 epoch 4 - iter 4/48 - loss 0.09551912 - time (sec): 2.98 - samples/sec: 1223.05 - lr: 0.000039 - momentum: 0.000000
129
+ 2024-03-26 10:21:42,899 epoch 4 - iter 8/48 - loss 0.11646094 - time (sec): 4.36 - samples/sec: 1348.52 - lr: 0.000038 - momentum: 0.000000
130
+ 2024-03-26 10:21:44,963 epoch 4 - iter 12/48 - loss 0.12918594 - time (sec): 6.42 - samples/sec: 1435.71 - lr: 0.000038 - momentum: 0.000000
131
+ 2024-03-26 10:21:47,488 epoch 4 - iter 16/48 - loss 0.13063851 - time (sec): 8.95 - samples/sec: 1361.30 - lr: 0.000037 - momentum: 0.000000
132
+ 2024-03-26 10:21:48,468 epoch 4 - iter 20/48 - loss 0.12827349 - time (sec): 9.93 - samples/sec: 1446.70 - lr: 0.000037 - momentum: 0.000000
133
+ 2024-03-26 10:21:49,848 epoch 4 - iter 24/48 - loss 0.13092356 - time (sec): 11.31 - samples/sec: 1494.57 - lr: 0.000036 - momentum: 0.000000
134
+ 2024-03-26 10:21:52,936 epoch 4 - iter 28/48 - loss 0.12716420 - time (sec): 14.40 - samples/sec: 1401.82 - lr: 0.000036 - momentum: 0.000000
135
+ 2024-03-26 10:21:55,392 epoch 4 - iter 32/48 - loss 0.13483254 - time (sec): 16.85 - samples/sec: 1395.38 - lr: 0.000035 - momentum: 0.000000
136
+ 2024-03-26 10:21:56,884 epoch 4 - iter 36/48 - loss 0.13516354 - time (sec): 18.35 - samples/sec: 1432.40 - lr: 0.000035 - momentum: 0.000000
137
+ 2024-03-26 10:21:58,842 epoch 4 - iter 40/48 - loss 0.13302960 - time (sec): 20.30 - samples/sec: 1448.04 - lr: 0.000034 - momentum: 0.000000
138
+ 2024-03-26 10:22:00,728 epoch 4 - iter 44/48 - loss 0.13158699 - time (sec): 22.19 - samples/sec: 1461.65 - lr: 0.000034 - momentum: 0.000000
139
+ 2024-03-26 10:22:01,761 epoch 4 - iter 48/48 - loss 0.13451918 - time (sec): 23.22 - samples/sec: 1484.41 - lr: 0.000034 - momentum: 0.000000
140
+ 2024-03-26 10:22:01,761 ----------------------------------------------------------------------------------------------------
141
+ 2024-03-26 10:22:01,761 EPOCH 4 done: loss 0.1345 - lr: 0.000034
142
+ 2024-03-26 10:22:02,660 DEV : loss 0.1830204278230667 - f1-score (micro avg) 0.8992
143
+ 2024-03-26 10:22:02,661 saving best model
144
+ 2024-03-26 10:22:03,103 ----------------------------------------------------------------------------------------------------
145
+ 2024-03-26 10:22:04,153 epoch 5 - iter 4/48 - loss 0.15872146 - time (sec): 1.05 - samples/sec: 2426.35 - lr: 0.000033 - momentum: 0.000000
146
+ 2024-03-26 10:22:06,022 epoch 5 - iter 8/48 - loss 0.14255133 - time (sec): 2.92 - samples/sec: 1776.12 - lr: 0.000033 - momentum: 0.000000
147
+ 2024-03-26 10:22:08,118 epoch 5 - iter 12/48 - loss 0.12951855 - time (sec): 5.01 - samples/sec: 1596.60 - lr: 0.000032 - momentum: 0.000000
148
+ 2024-03-26 10:22:10,380 epoch 5 - iter 16/48 - loss 0.12352511 - time (sec): 7.27 - samples/sec: 1524.70 - lr: 0.000032 - momentum: 0.000000
149
+ 2024-03-26 10:22:12,623 epoch 5 - iter 20/48 - loss 0.11945075 - time (sec): 9.52 - samples/sec: 1437.80 - lr: 0.000031 - momentum: 0.000000
150
+ 2024-03-26 10:22:14,779 epoch 5 - iter 24/48 - loss 0.11337964 - time (sec): 11.67 - samples/sec: 1455.39 - lr: 0.000031 - momentum: 0.000000
151
+ 2024-03-26 10:22:16,378 epoch 5 - iter 28/48 - loss 0.11046502 - time (sec): 13.27 - samples/sec: 1482.93 - lr: 0.000030 - momentum: 0.000000
152
+ 2024-03-26 10:22:18,466 epoch 5 - iter 32/48 - loss 0.10254048 - time (sec): 15.36 - samples/sec: 1503.92 - lr: 0.000030 - momentum: 0.000000
153
+ 2024-03-26 10:22:19,855 epoch 5 - iter 36/48 - loss 0.09999268 - time (sec): 16.75 - samples/sec: 1528.35 - lr: 0.000029 - momentum: 0.000000
154
+ 2024-03-26 10:22:22,382 epoch 5 - iter 40/48 - loss 0.09503797 - time (sec): 19.28 - samples/sec: 1495.46 - lr: 0.000029 - momentum: 0.000000
155
+ 2024-03-26 10:22:25,295 epoch 5 - iter 44/48 - loss 0.09353316 - time (sec): 22.19 - samples/sec: 1443.35 - lr: 0.000029 - momentum: 0.000000
156
+ 2024-03-26 10:22:26,793 epoch 5 - iter 48/48 - loss 0.09494866 - time (sec): 23.69 - samples/sec: 1455.28 - lr: 0.000028 - momentum: 0.000000
157
+ 2024-03-26 10:22:26,793 ----------------------------------------------------------------------------------------------------
158
+ 2024-03-26 10:22:26,793 EPOCH 5 done: loss 0.0949 - lr: 0.000028
159
+ 2024-03-26 10:22:27,682 DEV : loss 0.15144632756710052 - f1-score (micro avg) 0.9025
160
+ 2024-03-26 10:22:27,683 saving best model
161
+ 2024-03-26 10:22:28,118 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 10:22:29,963 epoch 6 - iter 4/48 - loss 0.10851113 - time (sec): 1.84 - samples/sec: 1594.45 - lr: 0.000028 - momentum: 0.000000
163
+ 2024-03-26 10:22:31,670 epoch 6 - iter 8/48 - loss 0.09307528 - time (sec): 3.55 - samples/sec: 1633.20 - lr: 0.000027 - momentum: 0.000000
164
+ 2024-03-26 10:22:33,956 epoch 6 - iter 12/48 - loss 0.08665395 - time (sec): 5.84 - samples/sec: 1511.12 - lr: 0.000027 - momentum: 0.000000
165
+ 2024-03-26 10:22:35,512 epoch 6 - iter 16/48 - loss 0.08378454 - time (sec): 7.39 - samples/sec: 1533.01 - lr: 0.000026 - momentum: 0.000000
166
+ 2024-03-26 10:22:38,049 epoch 6 - iter 20/48 - loss 0.07627659 - time (sec): 9.93 - samples/sec: 1446.92 - lr: 0.000026 - momentum: 0.000000
167
+ 2024-03-26 10:22:40,084 epoch 6 - iter 24/48 - loss 0.07713601 - time (sec): 11.96 - samples/sec: 1461.94 - lr: 0.000025 - momentum: 0.000000
168
+ 2024-03-26 10:22:42,691 epoch 6 - iter 28/48 - loss 0.07848976 - time (sec): 14.57 - samples/sec: 1436.72 - lr: 0.000025 - momentum: 0.000000
169
+ 2024-03-26 10:22:44,719 epoch 6 - iter 32/48 - loss 0.07641593 - time (sec): 16.60 - samples/sec: 1415.80 - lr: 0.000024 - momentum: 0.000000
170
+ 2024-03-26 10:22:45,816 epoch 6 - iter 36/48 - loss 0.07605365 - time (sec): 17.70 - samples/sec: 1465.91 - lr: 0.000024 - momentum: 0.000000
171
+ 2024-03-26 10:22:47,991 epoch 6 - iter 40/48 - loss 0.07646544 - time (sec): 19.87 - samples/sec: 1455.23 - lr: 0.000023 - momentum: 0.000000
172
+ 2024-03-26 10:22:49,584 epoch 6 - iter 44/48 - loss 0.08001823 - time (sec): 21.46 - samples/sec: 1479.31 - lr: 0.000023 - momentum: 0.000000
173
+ 2024-03-26 10:22:51,349 epoch 6 - iter 48/48 - loss 0.07755461 - time (sec): 23.23 - samples/sec: 1484.01 - lr: 0.000023 - momentum: 0.000000
174
+ 2024-03-26 10:22:51,349 ----------------------------------------------------------------------------------------------------
175
+ 2024-03-26 10:22:51,349 EPOCH 6 done: loss 0.0776 - lr: 0.000023
176
+ 2024-03-26 10:22:52,261 DEV : loss 0.1642305999994278 - f1-score (micro avg) 0.9209
177
+ 2024-03-26 10:22:52,262 saving best model
178
+ 2024-03-26 10:22:52,690 ----------------------------------------------------------------------------------------------------
179
+ 2024-03-26 10:22:54,223 epoch 7 - iter 4/48 - loss 0.05032160 - time (sec): 1.53 - samples/sec: 1827.49 - lr: 0.000022 - momentum: 0.000000
180
+ 2024-03-26 10:22:56,327 epoch 7 - iter 8/48 - loss 0.04567333 - time (sec): 3.64 - samples/sec: 1683.33 - lr: 0.000022 - momentum: 0.000000
181
+ 2024-03-26 10:22:58,559 epoch 7 - iter 12/48 - loss 0.04588195 - time (sec): 5.87 - samples/sec: 1501.40 - lr: 0.000021 - momentum: 0.000000
182
+ 2024-03-26 10:22:59,732 epoch 7 - iter 16/48 - loss 0.05196772 - time (sec): 7.04 - samples/sec: 1598.72 - lr: 0.000021 - momentum: 0.000000
183
+ 2024-03-26 10:23:01,851 epoch 7 - iter 20/48 - loss 0.05230221 - time (sec): 9.16 - samples/sec: 1566.06 - lr: 0.000020 - momentum: 0.000000
184
+ 2024-03-26 10:23:03,370 epoch 7 - iter 24/48 - loss 0.05050299 - time (sec): 10.68 - samples/sec: 1611.85 - lr: 0.000020 - momentum: 0.000000
185
+ 2024-03-26 10:23:05,473 epoch 7 - iter 28/48 - loss 0.05048660 - time (sec): 12.78 - samples/sec: 1570.56 - lr: 0.000019 - momentum: 0.000000
186
+ 2024-03-26 10:23:08,249 epoch 7 - iter 32/48 - loss 0.05200003 - time (sec): 15.56 - samples/sec: 1497.01 - lr: 0.000019 - momentum: 0.000000
187
+ 2024-03-26 10:23:10,207 epoch 7 - iter 36/48 - loss 0.05120253 - time (sec): 17.52 - samples/sec: 1498.16 - lr: 0.000018 - momentum: 0.000000
188
+ 2024-03-26 10:23:11,324 epoch 7 - iter 40/48 - loss 0.05496877 - time (sec): 18.63 - samples/sec: 1529.53 - lr: 0.000018 - momentum: 0.000000
189
+ 2024-03-26 10:23:13,921 epoch 7 - iter 44/48 - loss 0.05649099 - time (sec): 21.23 - samples/sec: 1510.23 - lr: 0.000017 - momentum: 0.000000
190
+ 2024-03-26 10:23:15,025 epoch 7 - iter 48/48 - loss 0.05715487 - time (sec): 22.33 - samples/sec: 1543.52 - lr: 0.000017 - momentum: 0.000000
191
+ 2024-03-26 10:23:15,025 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 10:23:15,025 EPOCH 7 done: loss 0.0572 - lr: 0.000017
193
+ 2024-03-26 10:23:15,918 DEV : loss 0.16066581010818481 - f1-score (micro avg) 0.9321
194
+ 2024-03-26 10:23:15,919 saving best model
195
+ 2024-03-26 10:23:16,376 ----------------------------------------------------------------------------------------------------
196
+ 2024-03-26 10:23:18,477 epoch 8 - iter 4/48 - loss 0.03381401 - time (sec): 2.10 - samples/sec: 1320.91 - lr: 0.000017 - momentum: 0.000000
197
+ 2024-03-26 10:23:21,156 epoch 8 - iter 8/48 - loss 0.03430206 - time (sec): 4.78 - samples/sec: 1264.11 - lr: 0.000016 - momentum: 0.000000
198
+ 2024-03-26 10:23:22,808 epoch 8 - iter 12/48 - loss 0.03362778 - time (sec): 6.43 - samples/sec: 1318.90 - lr: 0.000016 - momentum: 0.000000
199
+ 2024-03-26 10:23:25,407 epoch 8 - iter 16/48 - loss 0.04013356 - time (sec): 9.03 - samples/sec: 1275.00 - lr: 0.000015 - momentum: 0.000000
200
+ 2024-03-26 10:23:27,037 epoch 8 - iter 20/48 - loss 0.04031454 - time (sec): 10.66 - samples/sec: 1332.95 - lr: 0.000015 - momentum: 0.000000
201
+ 2024-03-26 10:23:28,493 epoch 8 - iter 24/48 - loss 0.04286096 - time (sec): 12.12 - samples/sec: 1403.05 - lr: 0.000014 - momentum: 0.000000
202
+ 2024-03-26 10:23:30,353 epoch 8 - iter 28/48 - loss 0.04539810 - time (sec): 13.97 - samples/sec: 1427.05 - lr: 0.000014 - momentum: 0.000000
203
+ 2024-03-26 10:23:32,986 epoch 8 - iter 32/48 - loss 0.04655029 - time (sec): 16.61 - samples/sec: 1414.48 - lr: 0.000013 - momentum: 0.000000
204
+ 2024-03-26 10:23:35,375 epoch 8 - iter 36/48 - loss 0.04613594 - time (sec): 19.00 - samples/sec: 1407.20 - lr: 0.000013 - momentum: 0.000000
205
+ 2024-03-26 10:23:37,561 epoch 8 - iter 40/48 - loss 0.04545780 - time (sec): 21.18 - samples/sec: 1389.03 - lr: 0.000012 - momentum: 0.000000
206
+ 2024-03-26 10:23:39,791 epoch 8 - iter 44/48 - loss 0.04427927 - time (sec): 23.41 - samples/sec: 1379.75 - lr: 0.000012 - momentum: 0.000000
207
+ 2024-03-26 10:23:41,345 epoch 8 - iter 48/48 - loss 0.04501008 - time (sec): 24.97 - samples/sec: 1380.70 - lr: 0.000011 - momentum: 0.000000
208
+ 2024-03-26 10:23:41,345 ----------------------------------------------------------------------------------------------------
209
+ 2024-03-26 10:23:41,346 EPOCH 8 done: loss 0.0450 - lr: 0.000011
210
+ 2024-03-26 10:23:42,258 DEV : loss 0.15505997836589813 - f1-score (micro avg) 0.9301
211
+ 2024-03-26 10:23:42,259 ----------------------------------------------------------------------------------------------------
212
+ 2024-03-26 10:23:44,109 epoch 9 - iter 4/48 - loss 0.04194533 - time (sec): 1.85 - samples/sec: 1561.57 - lr: 0.000011 - momentum: 0.000000
213
+ 2024-03-26 10:23:47,244 epoch 9 - iter 8/48 - loss 0.03637572 - time (sec): 4.98 - samples/sec: 1262.88 - lr: 0.000011 - momentum: 0.000000
214
+ 2024-03-26 10:23:48,869 epoch 9 - iter 12/48 - loss 0.03048679 - time (sec): 6.61 - samples/sec: 1308.50 - lr: 0.000010 - momentum: 0.000000
215
+ 2024-03-26 10:23:50,738 epoch 9 - iter 16/48 - loss 0.03637230 - time (sec): 8.48 - samples/sec: 1348.29 - lr: 0.000010 - momentum: 0.000000
216
+ 2024-03-26 10:23:53,600 epoch 9 - iter 20/48 - loss 0.03169081 - time (sec): 11.34 - samples/sec: 1309.60 - lr: 0.000009 - momentum: 0.000000
217
+ 2024-03-26 10:23:55,125 epoch 9 - iter 24/48 - loss 0.03128243 - time (sec): 12.87 - samples/sec: 1356.14 - lr: 0.000009 - momentum: 0.000000
218
+ 2024-03-26 10:23:57,053 epoch 9 - iter 28/48 - loss 0.03451015 - time (sec): 14.79 - samples/sec: 1380.89 - lr: 0.000008 - momentum: 0.000000
219
+ 2024-03-26 10:23:59,368 epoch 9 - iter 32/48 - loss 0.03338486 - time (sec): 17.11 - samples/sec: 1357.83 - lr: 0.000008 - momentum: 0.000000
220
+ 2024-03-26 10:24:00,662 epoch 9 - iter 36/48 - loss 0.03742122 - time (sec): 18.40 - samples/sec: 1389.10 - lr: 0.000007 - momentum: 0.000000
221
+ 2024-03-26 10:24:03,850 epoch 9 - iter 40/48 - loss 0.03719738 - time (sec): 21.59 - samples/sec: 1340.32 - lr: 0.000007 - momentum: 0.000000
222
+ 2024-03-26 10:24:05,961 epoch 9 - iter 44/48 - loss 0.03525908 - time (sec): 23.70 - samples/sec: 1362.76 - lr: 0.000006 - momentum: 0.000000
223
+ 2024-03-26 10:24:06,946 epoch 9 - iter 48/48 - loss 0.03580414 - time (sec): 24.69 - samples/sec: 1396.37 - lr: 0.000006 - momentum: 0.000000
224
+ 2024-03-26 10:24:06,946 ----------------------------------------------------------------------------------------------------
225
+ 2024-03-26 10:24:06,946 EPOCH 9 done: loss 0.0358 - lr: 0.000006
226
+ 2024-03-26 10:24:07,845 DEV : loss 0.15631996095180511 - f1-score (micro avg) 0.9391
227
+ 2024-03-26 10:24:07,847 saving best model
228
+ 2024-03-26 10:24:08,273 ----------------------------------------------------------------------------------------------------
229
+ 2024-03-26 10:24:10,138 epoch 10 - iter 4/48 - loss 0.04267402 - time (sec): 1.86 - samples/sec: 1387.06 - lr: 0.000006 - momentum: 0.000000
230
+ 2024-03-26 10:24:12,900 epoch 10 - iter 8/48 - loss 0.02765691 - time (sec): 4.63 - samples/sec: 1250.69 - lr: 0.000005 - momentum: 0.000000
231
+ 2024-03-26 10:24:14,919 epoch 10 - iter 12/48 - loss 0.03229017 - time (sec): 6.64 - samples/sec: 1311.33 - lr: 0.000005 - momentum: 0.000000
232
+ 2024-03-26 10:24:16,936 epoch 10 - iter 16/48 - loss 0.02870081 - time (sec): 8.66 - samples/sec: 1404.55 - lr: 0.000004 - momentum: 0.000000
233
+ 2024-03-26 10:24:17,802 epoch 10 - iter 20/48 - loss 0.02796793 - time (sec): 9.53 - samples/sec: 1481.67 - lr: 0.000004 - momentum: 0.000000
234
+ 2024-03-26 10:24:19,480 epoch 10 - iter 24/48 - loss 0.02776836 - time (sec): 11.21 - samples/sec: 1509.57 - lr: 0.000003 - momentum: 0.000000
235
+ 2024-03-26 10:24:20,416 epoch 10 - iter 28/48 - loss 0.02689986 - time (sec): 12.14 - samples/sec: 1573.80 - lr: 0.000003 - momentum: 0.000000
236
+ 2024-03-26 10:24:22,721 epoch 10 - iter 32/48 - loss 0.02474031 - time (sec): 14.45 - samples/sec: 1540.01 - lr: 0.000002 - momentum: 0.000000
237
+ 2024-03-26 10:24:25,204 epoch 10 - iter 36/48 - loss 0.02836269 - time (sec): 16.93 - samples/sec: 1505.96 - lr: 0.000002 - momentum: 0.000000
238
+ 2024-03-26 10:24:27,087 epoch 10 - iter 40/48 - loss 0.02902092 - time (sec): 18.81 - samples/sec: 1499.79 - lr: 0.000001 - momentum: 0.000000
239
+ 2024-03-26 10:24:29,653 epoch 10 - iter 44/48 - loss 0.02860789 - time (sec): 21.38 - samples/sec: 1487.45 - lr: 0.000001 - momentum: 0.000000
240
+ 2024-03-26 10:24:31,253 epoch 10 - iter 48/48 - loss 0.02837633 - time (sec): 22.98 - samples/sec: 1500.21 - lr: 0.000000 - momentum: 0.000000
241
+ 2024-03-26 10:24:31,253 ----------------------------------------------------------------------------------------------------
242
+ 2024-03-26 10:24:31,253 EPOCH 10 done: loss 0.0284 - lr: 0.000000
243
+ 2024-03-26 10:24:32,155 DEV : loss 0.16044245660305023 - f1-score (micro avg) 0.9489
244
+ 2024-03-26 10:24:32,156 saving best model
245
+ 2024-03-26 10:24:32,848 ----------------------------------------------------------------------------------------------------
246
+ 2024-03-26 10:24:32,849 Loading model from best epoch ...
247
+ 2024-03-26 10:24:33,749 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 10:24:34,587
249
+ Results:
250
+ - F-score (micro) 0.9038
251
+ - F-score (macro) 0.6866
252
+ - Accuracy 0.8268
253
+
254
+ By class:
255
+ precision recall f1-score support
256
+
257
+ Unternehmen 0.9109 0.8835 0.8969 266
258
+ Auslagerung 0.8555 0.9036 0.8789 249
259
+ Ort 0.9565 0.9851 0.9706 134
260
+ Software 0.0000 0.0000 0.0000 0
261
+
262
+ micro avg 0.8956 0.9122 0.9038 649
263
+ macro avg 0.6807 0.6930 0.6866 649
264
+ weighted avg 0.8991 0.9122 0.9052 649
265
+
266
+ 2024-03-26 10:24:34,587 ----------------------------------------------------------------------------------------------------