Hugging Face's logo

stefan-it
/
flair-co-funer-german_dbmdz_bert_base-bs16-e10-lr5e-05-5

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
e19750b
•
1 Parent(s): f1c4f32

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 16:25:03,464 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 16:25:03,464 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 16:25:03,464 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 16:25:03,464 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 16:25:03,464 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 16:25:03,464 Train: 758 sentences
54
+ 2024-03-26 16:25:03,464 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 16:25:03,464 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 16:25:03,464 Training Params:
57
+ 2024-03-26 16:25:03,464 - learning_rate: "5e-05"
58
+ 2024-03-26 16:25:03,464 - mini_batch_size: "16"
59
+ 2024-03-26 16:25:03,464 - max_epochs: "10"
60
+ 2024-03-26 16:25:03,464 - shuffle: "True"
61
+ 2024-03-26 16:25:03,464 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 16:25:03,464 Plugins:
63
+ 2024-03-26 16:25:03,464 - TensorboardLogger
64
+ 2024-03-26 16:25:03,464 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 16:25:03,464 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 16:25:03,464 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 16:25:03,464 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 16:25:03,464 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 16:25:03,465 Computation:
70
+ 2024-03-26 16:25:03,465 - compute on device: cuda:0
71
+ 2024-03-26 16:25:03,465 - embedding storage: none
72
+ 2024-03-26 16:25:03,465 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 16:25:03,465 Model training base path: "flair-co-funer-german_dbmdz_bert_base-bs16-e10-lr5e-05-5"
74
+ 2024-03-26 16:25:03,465 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 16:25:03,465 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 16:25:03,465 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 16:25:04,936 epoch 1 - iter 4/48 - loss 3.32824977 - time (sec): 1.47 - samples/sec: 1782.07 - lr: 0.000003 - momentum: 0.000000
78
+ 2024-03-26 16:25:07,626 epoch 1 - iter 8/48 - loss 3.23808475 - time (sec): 4.16 - samples/sec: 1462.56 - lr: 0.000007 - momentum: 0.000000
79
+ 2024-03-26 16:25:09,455 epoch 1 - iter 12/48 - loss 3.10768286 - time (sec): 5.99 - samples/sec: 1487.04 - lr: 0.000011 - momentum: 0.000000
80
+ 2024-03-26 16:25:11,000 epoch 1 - iter 16/48 - loss 2.93068015 - time (sec): 7.54 - samples/sec: 1596.58 - lr: 0.000016 - momentum: 0.000000
81
+ 2024-03-26 16:25:13,124 epoch 1 - iter 20/48 - loss 2.77783855 - time (sec): 9.66 - samples/sec: 1561.09 - lr: 0.000020 - momentum: 0.000000
82
+ 2024-03-26 16:25:15,829 epoch 1 - iter 24/48 - loss 2.60744422 - time (sec): 12.36 - samples/sec: 1492.15 - lr: 0.000024 - momentum: 0.000000
83
+ 2024-03-26 16:25:17,441 epoch 1 - iter 28/48 - loss 2.48773735 - time (sec): 13.98 - samples/sec: 1501.59 - lr: 0.000028 - momentum: 0.000000
84
+ 2024-03-26 16:25:19,517 epoch 1 - iter 32/48 - loss 2.36230783 - time (sec): 16.05 - samples/sec: 1497.52 - lr: 0.000032 - momentum: 0.000000
85
+ 2024-03-26 16:25:21,053 epoch 1 - iter 36/48 - loss 2.25916147 - time (sec): 17.59 - samples/sec: 1518.01 - lr: 0.000036 - momentum: 0.000000
86
+ 2024-03-26 16:25:23,825 epoch 1 - iter 40/48 - loss 2.12584608 - time (sec): 20.36 - samples/sec: 1468.80 - lr: 0.000041 - momentum: 0.000000
87
+ 2024-03-26 16:25:25,011 epoch 1 - iter 44/48 - loss 2.03282822 - time (sec): 21.55 - samples/sec: 1491.81 - lr: 0.000045 - momentum: 0.000000
88
+ 2024-03-26 16:25:26,833 epoch 1 - iter 48/48 - loss 1.94896514 - time (sec): 23.37 - samples/sec: 1475.16 - lr: 0.000049 - momentum: 0.000000
89
+ 2024-03-26 16:25:26,834 ----------------------------------------------------------------------------------------------------
90
+ 2024-03-26 16:25:26,834 EPOCH 1 done: loss 1.9490 - lr: 0.000049
91
+ 2024-03-26 16:25:27,831 DEV : loss 0.5537716746330261 - f1-score (micro avg) 0.617
92
+ 2024-03-26 16:25:27,832 saving best model
93
+ 2024-03-26 16:25:28,134 ----------------------------------------------------------------------------------------------------
94
+ 2024-03-26 16:25:30,836 epoch 2 - iter 4/48 - loss 0.60539991 - time (sec): 2.70 - samples/sec: 1277.98 - lr: 0.000050 - momentum: 0.000000
95
+ 2024-03-26 16:25:32,689 epoch 2 - iter 8/48 - loss 0.58912879 - time (sec): 4.55 - samples/sec: 1345.54 - lr: 0.000049 - momentum: 0.000000
96
+ 2024-03-26 16:25:34,585 epoch 2 - iter 12/48 - loss 0.55105161 - time (sec): 6.45 - samples/sec: 1382.99 - lr: 0.000049 - momentum: 0.000000
97
+ 2024-03-26 16:25:37,257 epoch 2 - iter 16/48 - loss 0.50129401 - time (sec): 9.12 - samples/sec: 1387.23 - lr: 0.000048 - momentum: 0.000000
98
+ 2024-03-26 16:25:38,639 epoch 2 - iter 20/48 - loss 0.48407514 - time (sec): 10.50 - samples/sec: 1426.22 - lr: 0.000048 - momentum: 0.000000
99
+ 2024-03-26 16:25:41,459 epoch 2 - iter 24/48 - loss 0.45190843 - time (sec): 13.32 - samples/sec: 1343.23 - lr: 0.000047 - momentum: 0.000000
100
+ 2024-03-26 16:25:43,068 epoch 2 - iter 28/48 - loss 0.45024089 - time (sec): 14.93 - samples/sec: 1376.78 - lr: 0.000047 - momentum: 0.000000
101
+ 2024-03-26 16:25:45,085 epoch 2 - iter 32/48 - loss 0.42875986 - time (sec): 16.95 - samples/sec: 1369.76 - lr: 0.000046 - momentum: 0.000000
102
+ 2024-03-26 16:25:46,851 epoch 2 - iter 36/48 - loss 0.42459097 - time (sec): 18.72 - samples/sec: 1400.34 - lr: 0.000046 - momentum: 0.000000
103
+ 2024-03-26 16:25:49,222 epoch 2 - iter 40/48 - loss 0.42355452 - time (sec): 21.09 - samples/sec: 1388.11 - lr: 0.000046 - momentum: 0.000000
104
+ 2024-03-26 16:25:51,421 epoch 2 - iter 44/48 - loss 0.40750888 - time (sec): 23.29 - samples/sec: 1392.82 - lr: 0.000045 - momentum: 0.000000
105
+ 2024-03-26 16:25:52,678 epoch 2 - iter 48/48 - loss 0.40362786 - time (sec): 24.54 - samples/sec: 1404.48 - lr: 0.000045 - momentum: 0.000000
106
+ 2024-03-26 16:25:52,679 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 16:25:52,679 EPOCH 2 done: loss 0.4036 - lr: 0.000045
108
+ 2024-03-26 16:25:53,588 DEV : loss 0.30737343430519104 - f1-score (micro avg) 0.7935
109
+ 2024-03-26 16:25:53,589 saving best model
110
+ 2024-03-26 16:25:54,032 ----------------------------------------------------------------------------------------------------
111
+ 2024-03-26 16:25:55,124 epoch 3 - iter 4/48 - loss 0.31144244 - time (sec): 1.09 - samples/sec: 2047.76 - lr: 0.000044 - momentum: 0.000000
112
+ 2024-03-26 16:25:56,997 epoch 3 - iter 8/48 - loss 0.27506545 - time (sec): 2.96 - samples/sec: 1663.42 - lr: 0.000044 - momentum: 0.000000
113
+ 2024-03-26 16:25:59,194 epoch 3 - iter 12/48 - loss 0.24414820 - time (sec): 5.16 - samples/sec: 1661.85 - lr: 0.000043 - momentum: 0.000000
114
+ 2024-03-26 16:26:01,135 epoch 3 - iter 16/48 - loss 0.24252002 - time (sec): 7.10 - samples/sec: 1602.13 - lr: 0.000043 - momentum: 0.000000
115
+ 2024-03-26 16:26:02,975 epoch 3 - iter 20/48 - loss 0.23661584 - time (sec): 8.94 - samples/sec: 1585.75 - lr: 0.000042 - momentum: 0.000000
116
+ 2024-03-26 16:26:04,912 epoch 3 - iter 24/48 - loss 0.22527637 - time (sec): 10.88 - samples/sec: 1541.12 - lr: 0.000042 - momentum: 0.000000
117
+ 2024-03-26 16:26:08,066 epoch 3 - iter 28/48 - loss 0.22345440 - time (sec): 14.03 - samples/sec: 1426.58 - lr: 0.000041 - momentum: 0.000000
118
+ 2024-03-26 16:26:09,562 epoch 3 - iter 32/48 - loss 0.22304620 - time (sec): 15.53 - samples/sec: 1450.64 - lr: 0.000041 - momentum: 0.000000
119
+ 2024-03-26 16:26:12,824 epoch 3 - iter 36/48 - loss 0.21388734 - time (sec): 18.79 - samples/sec: 1380.50 - lr: 0.000040 - momentum: 0.000000
120
+ 2024-03-26 16:26:15,178 epoch 3 - iter 40/48 - loss 0.21228601 - time (sec): 21.14 - samples/sec: 1384.00 - lr: 0.000040 - momentum: 0.000000
121
+ 2024-03-26 16:26:17,307 epoch 3 - iter 44/48 - loss 0.20813710 - time (sec): 23.27 - samples/sec: 1378.84 - lr: 0.000040 - momentum: 0.000000
122
+ 2024-03-26 16:26:18,879 epoch 3 - iter 48/48 - loss 0.20795830 - time (sec): 24.84 - samples/sec: 1387.50 - lr: 0.000039 - momentum: 0.000000
123
+ 2024-03-26 16:26:18,880 ----------------------------------------------------------------------------------------------------
124
+ 2024-03-26 16:26:18,880 EPOCH 3 done: loss 0.2080 - lr: 0.000039
125
+ 2024-03-26 16:26:19,767 DEV : loss 0.20917974412441254 - f1-score (micro avg) 0.8622
126
+ 2024-03-26 16:26:19,768 saving best model
127
+ 2024-03-26 16:26:20,218 ----------------------------------------------------------------------------------------------------
128
+ 2024-03-26 16:26:23,167 epoch 4 - iter 4/48 - loss 0.11024253 - time (sec): 2.95 - samples/sec: 1265.46 - lr: 0.000039 - momentum: 0.000000
129
+ 2024-03-26 16:26:24,592 epoch 4 - iter 8/48 - loss 0.14888858 - time (sec): 4.37 - samples/sec: 1422.46 - lr: 0.000038 - momentum: 0.000000
130
+ 2024-03-26 16:26:27,106 epoch 4 - iter 12/48 - loss 0.13354107 - time (sec): 6.89 - samples/sec: 1350.58 - lr: 0.000038 - momentum: 0.000000
131
+ 2024-03-26 16:26:29,757 epoch 4 - iter 16/48 - loss 0.13064756 - time (sec): 9.54 - samples/sec: 1331.26 - lr: 0.000037 - momentum: 0.000000
132
+ 2024-03-26 16:26:32,007 epoch 4 - iter 20/48 - loss 0.12953050 - time (sec): 11.79 - samples/sec: 1338.92 - lr: 0.000037 - momentum: 0.000000
133
+ 2024-03-26 16:26:33,506 epoch 4 - iter 24/48 - loss 0.12864352 - time (sec): 13.29 - samples/sec: 1372.20 - lr: 0.000036 - momentum: 0.000000
134
+ 2024-03-26 16:26:35,865 epoch 4 - iter 28/48 - loss 0.13077801 - time (sec): 15.65 - samples/sec: 1357.74 - lr: 0.000036 - momentum: 0.000000
135
+ 2024-03-26 16:26:38,806 epoch 4 - iter 32/48 - loss 0.12972820 - time (sec): 18.59 - samples/sec: 1348.34 - lr: 0.000035 - momentum: 0.000000
136
+ 2024-03-26 16:26:40,434 epoch 4 - iter 36/48 - loss 0.13193083 - time (sec): 20.21 - samples/sec: 1373.12 - lr: 0.000035 - momentum: 0.000000
137
+ 2024-03-26 16:26:41,417 epoch 4 - iter 40/48 - loss 0.13372377 - time (sec): 21.20 - samples/sec: 1416.72 - lr: 0.000034 - momentum: 0.000000
138
+ 2024-03-26 16:26:42,850 epoch 4 - iter 44/48 - loss 0.13328906 - time (sec): 22.63 - samples/sec: 1437.61 - lr: 0.000034 - momentum: 0.000000
139
+ 2024-03-26 16:26:43,721 epoch 4 - iter 48/48 - loss 0.13705591 - time (sec): 23.50 - samples/sec: 1466.83 - lr: 0.000034 - momentum: 0.000000
140
+ 2024-03-26 16:26:43,722 ----------------------------------------------------------------------------------------------------
141
+ 2024-03-26 16:26:43,722 EPOCH 4 done: loss 0.1371 - lr: 0.000034
142
+ 2024-03-26 16:26:44,639 DEV : loss 0.16365402936935425 - f1-score (micro avg) 0.8996
143
+ 2024-03-26 16:26:44,641 saving best model
144
+ 2024-03-26 16:26:45,095 ----------------------------------------------------------------------------------------------------
145
+ 2024-03-26 16:26:46,933 epoch 5 - iter 4/48 - loss 0.10828925 - time (sec): 1.84 - samples/sec: 1564.62 - lr: 0.000033 - momentum: 0.000000
146
+ 2024-03-26 16:26:48,892 epoch 5 - iter 8/48 - loss 0.09388716 - time (sec): 3.79 - samples/sec: 1635.11 - lr: 0.000033 - momentum: 0.000000
147
+ 2024-03-26 16:26:51,983 epoch 5 - iter 12/48 - loss 0.09384839 - time (sec): 6.89 - samples/sec: 1397.31 - lr: 0.000032 - momentum: 0.000000
148
+ 2024-03-26 16:26:53,291 epoch 5 - iter 16/48 - loss 0.08935375 - time (sec): 8.19 - samples/sec: 1451.29 - lr: 0.000032 - momentum: 0.000000
149
+ 2024-03-26 16:26:55,546 epoch 5 - iter 20/48 - loss 0.09852740 - time (sec): 10.45 - samples/sec: 1442.15 - lr: 0.000031 - momentum: 0.000000
150
+ 2024-03-26 16:26:57,672 epoch 5 - iter 24/48 - loss 0.09806534 - time (sec): 12.57 - samples/sec: 1413.65 - lr: 0.000031 - momentum: 0.000000
151
+ 2024-03-26 16:26:59,025 epoch 5 - iter 28/48 - loss 0.10178698 - time (sec): 13.93 - samples/sec: 1456.91 - lr: 0.000030 - momentum: 0.000000
152
+ 2024-03-26 16:27:00,395 epoch 5 - iter 32/48 - loss 0.10298381 - time (sec): 15.30 - samples/sec: 1490.20 - lr: 0.000030 - momentum: 0.000000
153
+ 2024-03-26 16:27:02,503 epoch 5 - iter 36/48 - loss 0.10207738 - time (sec): 17.41 - samples/sec: 1483.62 - lr: 0.000029 - momentum: 0.000000
154
+ 2024-03-26 16:27:04,306 epoch 5 - iter 40/48 - loss 0.09992158 - time (sec): 19.21 - samples/sec: 1484.13 - lr: 0.000029 - momentum: 0.000000
155
+ 2024-03-26 16:27:06,289 epoch 5 - iter 44/48 - loss 0.09681532 - time (sec): 21.19 - samples/sec: 1497.99 - lr: 0.000029 - momentum: 0.000000
156
+ 2024-03-26 16:27:08,398 epoch 5 - iter 48/48 - loss 0.09501719 - time (sec): 23.30 - samples/sec: 1479.46 - lr: 0.000028 - momentum: 0.000000
157
+ 2024-03-26 16:27:08,398 ----------------------------------------------------------------------------------------------------
158
+ 2024-03-26 16:27:08,398 EPOCH 5 done: loss 0.0950 - lr: 0.000028
159
+ 2024-03-26 16:27:09,314 DEV : loss 0.1693895161151886 - f1-score (micro avg) 0.9204
160
+ 2024-03-26 16:27:09,315 saving best model
161
+ 2024-03-26 16:27:09,766 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 16:27:11,657 epoch 6 - iter 4/48 - loss 0.06697839 - time (sec): 1.89 - samples/sec: 1452.00 - lr: 0.000028 - momentum: 0.000000
163
+ 2024-03-26 16:27:14,401 epoch 6 - iter 8/48 - loss 0.07318846 - time (sec): 4.64 - samples/sec: 1371.23 - lr: 0.000027 - momentum: 0.000000
164
+ 2024-03-26 16:27:16,302 epoch 6 - iter 12/48 - loss 0.08598918 - time (sec): 6.54 - samples/sec: 1381.59 - lr: 0.000027 - momentum: 0.000000
165
+ 2024-03-26 16:27:17,790 epoch 6 - iter 16/48 - loss 0.09267531 - time (sec): 8.02 - samples/sec: 1442.01 - lr: 0.000026 - momentum: 0.000000
166
+ 2024-03-26 16:27:20,498 epoch 6 - iter 20/48 - loss 0.08577303 - time (sec): 10.73 - samples/sec: 1358.61 - lr: 0.000026 - momentum: 0.000000
167
+ 2024-03-26 16:27:23,169 epoch 6 - iter 24/48 - loss 0.07766058 - time (sec): 13.40 - samples/sec: 1332.98 - lr: 0.000025 - momentum: 0.000000
168
+ 2024-03-26 16:27:25,638 epoch 6 - iter 28/48 - loss 0.07425913 - time (sec): 15.87 - samples/sec: 1307.33 - lr: 0.000025 - momentum: 0.000000
169
+ 2024-03-26 16:27:27,031 epoch 6 - iter 32/48 - loss 0.07850212 - time (sec): 17.27 - samples/sec: 1350.35 - lr: 0.000024 - momentum: 0.000000
170
+ 2024-03-26 16:27:28,900 epoch 6 - iter 36/48 - loss 0.07649915 - time (sec): 19.13 - samples/sec: 1361.08 - lr: 0.000024 - momentum: 0.000000
171
+ 2024-03-26 16:27:29,888 epoch 6 - iter 40/48 - loss 0.07646863 - time (sec): 20.12 - samples/sec: 1401.99 - lr: 0.000023 - momentum: 0.000000
172
+ 2024-03-26 16:27:32,413 epoch 6 - iter 44/48 - loss 0.07566080 - time (sec): 22.65 - samples/sec: 1373.90 - lr: 0.000023 - momentum: 0.000000
173
+ 2024-03-26 16:27:35,195 epoch 6 - iter 48/48 - loss 0.07178153 - time (sec): 25.43 - samples/sec: 1355.63 - lr: 0.000023 - momentum: 0.000000
174
+ 2024-03-26 16:27:35,195 ----------------------------------------------------------------------------------------------------
175
+ 2024-03-26 16:27:35,195 EPOCH 6 done: loss 0.0718 - lr: 0.000023
176
+ 2024-03-26 16:27:36,169 DEV : loss 0.1729598194360733 - f1-score (micro avg) 0.9172
177
+ 2024-03-26 16:27:36,170 ----------------------------------------------------------------------------------------------------
178
+ 2024-03-26 16:27:38,315 epoch 7 - iter 4/48 - loss 0.04416839 - time (sec): 2.14 - samples/sec: 1356.50 - lr: 0.000022 - momentum: 0.000000
179
+ 2024-03-26 16:27:40,011 epoch 7 - iter 8/48 - loss 0.04150596 - time (sec): 3.84 - samples/sec: 1387.57 - lr: 0.000022 - momentum: 0.000000
180
+ 2024-03-26 16:27:41,439 epoch 7 - iter 12/48 - loss 0.06633125 - time (sec): 5.27 - samples/sec: 1440.70 - lr: 0.000021 - momentum: 0.000000
181
+ 2024-03-26 16:27:43,305 epoch 7 - iter 16/48 - loss 0.06072375 - time (sec): 7.13 - samples/sec: 1487.89 - lr: 0.000021 - momentum: 0.000000
182
+ 2024-03-26 16:27:45,577 epoch 7 - iter 20/48 - loss 0.06340498 - time (sec): 9.41 - samples/sec: 1540.62 - lr: 0.000020 - momentum: 0.000000
183
+ 2024-03-26 16:27:46,922 epoch 7 - iter 24/48 - loss 0.06004659 - time (sec): 10.75 - samples/sec: 1584.60 - lr: 0.000020 - momentum: 0.000000
184
+ 2024-03-26 16:27:49,151 epoch 7 - iter 28/48 - loss 0.05903152 - time (sec): 12.98 - samples/sec: 1536.61 - lr: 0.000019 - momentum: 0.000000
185
+ 2024-03-26 16:27:51,000 epoch 7 - iter 32/48 - loss 0.05980556 - time (sec): 14.83 - samples/sec: 1535.31 - lr: 0.000019 - momentum: 0.000000
186
+ 2024-03-26 16:27:52,954 epoch 7 - iter 36/48 - loss 0.05848180 - time (sec): 16.78 - samples/sec: 1506.02 - lr: 0.000018 - momentum: 0.000000
187
+ 2024-03-26 16:27:55,707 epoch 7 - iter 40/48 - loss 0.05540713 - time (sec): 19.54 - samples/sec: 1490.81 - lr: 0.000018 - momentum: 0.000000
188
+ 2024-03-26 16:27:57,182 epoch 7 - iter 44/48 - loss 0.05614680 - time (sec): 21.01 - samples/sec: 1507.20 - lr: 0.000017 - momentum: 0.000000
189
+ 2024-03-26 16:27:59,304 epoch 7 - iter 48/48 - loss 0.05380332 - time (sec): 23.13 - samples/sec: 1490.10 - lr: 0.000017 - momentum: 0.000000
190
+ 2024-03-26 16:27:59,305 ----------------------------------------------------------------------------------------------------
191
+ 2024-03-26 16:27:59,305 EPOCH 7 done: loss 0.0538 - lr: 0.000017
192
+ 2024-03-26 16:28:00,225 DEV : loss 0.1722007542848587 - f1-score (micro avg) 0.9193
193
+ 2024-03-26 16:28:00,228 ----------------------------------------------------------------------------------------------------
194
+ 2024-03-26 16:28:02,446 epoch 8 - iter 4/48 - loss 0.06117107 - time (sec): 2.22 - samples/sec: 1257.30 - lr: 0.000017 - momentum: 0.000000
195
+ 2024-03-26 16:28:03,987 epoch 8 - iter 8/48 - loss 0.03882310 - time (sec): 3.76 - samples/sec: 1445.96 - lr: 0.000016 - momentum: 0.000000
196
+ 2024-03-26 16:28:06,886 epoch 8 - iter 12/48 - loss 0.03967183 - time (sec): 6.66 - samples/sec: 1351.66 - lr: 0.000016 - momentum: 0.000000
197
+ 2024-03-26 16:28:09,327 epoch 8 - iter 16/48 - loss 0.04049592 - time (sec): 9.10 - samples/sec: 1350.28 - lr: 0.000015 - momentum: 0.000000
198
+ 2024-03-26 16:28:10,767 epoch 8 - iter 20/48 - loss 0.03913119 - time (sec): 10.54 - samples/sec: 1409.65 - lr: 0.000015 - momentum: 0.000000
199
+ 2024-03-26 16:28:12,189 epoch 8 - iter 24/48 - loss 0.03900572 - time (sec): 11.96 - samples/sec: 1479.33 - lr: 0.000014 - momentum: 0.000000
200
+ 2024-03-26 16:28:13,504 epoch 8 - iter 28/48 - loss 0.03950225 - time (sec): 13.28 - samples/sec: 1540.14 - lr: 0.000014 - momentum: 0.000000
201
+ 2024-03-26 16:28:15,673 epoch 8 - iter 32/48 - loss 0.04050648 - time (sec): 15.44 - samples/sec: 1499.98 - lr: 0.000013 - momentum: 0.000000
202
+ 2024-03-26 16:28:18,203 epoch 8 - iter 36/48 - loss 0.03880663 - time (sec): 17.97 - samples/sec: 1456.62 - lr: 0.000013 - momentum: 0.000000
203
+ 2024-03-26 16:28:20,139 epoch 8 - iter 40/48 - loss 0.04105555 - time (sec): 19.91 - samples/sec: 1465.82 - lr: 0.000012 - momentum: 0.000000
204
+ 2024-03-26 16:28:22,258 epoch 8 - iter 44/48 - loss 0.04231408 - time (sec): 22.03 - samples/sec: 1449.96 - lr: 0.000012 - momentum: 0.000000
205
+ 2024-03-26 16:28:23,854 epoch 8 - iter 48/48 - loss 0.04275838 - time (sec): 23.63 - samples/sec: 1459.13 - lr: 0.000011 - momentum: 0.000000
206
+ 2024-03-26 16:28:23,854 ----------------------------------------------------------------------------------------------------
207
+ 2024-03-26 16:28:23,854 EPOCH 8 done: loss 0.0428 - lr: 0.000011
208
+ 2024-03-26 16:28:24,749 DEV : loss 0.17764846980571747 - f1-score (micro avg) 0.9284
209
+ 2024-03-26 16:28:24,750 saving best model
210
+ 2024-03-26 16:28:25,207 ----------------------------------------------------------------------------------------------------
211
+ 2024-03-26 16:28:27,882 epoch 9 - iter 4/48 - loss 0.03206140 - time (sec): 2.67 - samples/sec: 1309.34 - lr: 0.000011 - momentum: 0.000000
212
+ 2024-03-26 16:28:30,013 epoch 9 - iter 8/48 - loss 0.02525687 - time (sec): 4.80 - samples/sec: 1329.48 - lr: 0.000011 - momentum: 0.000000
213
+ 2024-03-26 16:28:32,839 epoch 9 - iter 12/48 - loss 0.02697326 - time (sec): 7.63 - samples/sec: 1274.94 - lr: 0.000010 - momentum: 0.000000
214
+ 2024-03-26 16:28:35,931 epoch 9 - iter 16/48 - loss 0.03951301 - time (sec): 10.72 - samples/sec: 1253.98 - lr: 0.000010 - momentum: 0.000000
215
+ 2024-03-26 16:28:36,806 epoch 9 - iter 20/48 - loss 0.03757066 - time (sec): 11.60 - samples/sec: 1343.17 - lr: 0.000009 - momentum: 0.000000
216
+ 2024-03-26 16:28:38,674 epoch 9 - iter 24/48 - loss 0.03542734 - time (sec): 13.46 - samples/sec: 1338.78 - lr: 0.000009 - momentum: 0.000000
217
+ 2024-03-26 16:28:40,680 epoch 9 - iter 28/48 - loss 0.03450097 - time (sec): 15.47 - samples/sec: 1353.50 - lr: 0.000008 - momentum: 0.000000
218
+ 2024-03-26 16:28:41,671 epoch 9 - iter 32/48 - loss 0.03470330 - time (sec): 16.46 - samples/sec: 1419.13 - lr: 0.000008 - momentum: 0.000000
219
+ 2024-03-26 16:28:42,790 epoch 9 - iter 36/48 - loss 0.03393823 - time (sec): 17.58 - samples/sec: 1473.64 - lr: 0.000007 - momentum: 0.000000
220
+ 2024-03-26 16:28:44,096 epoch 9 - iter 40/48 - loss 0.03250121 - time (sec): 18.89 - samples/sec: 1501.70 - lr: 0.000007 - momentum: 0.000000
221
+ 2024-03-26 16:28:47,163 epoch 9 - iter 44/48 - loss 0.03527278 - time (sec): 21.95 - samples/sec: 1469.28 - lr: 0.000006 - momentum: 0.000000
222
+ 2024-03-26 16:28:48,657 epoch 9 - iter 48/48 - loss 0.03398332 - time (sec): 23.45 - samples/sec: 1470.18 - lr: 0.000006 - momentum: 0.000000
223
+ 2024-03-26 16:28:48,657 ----------------------------------------------------------------------------------------------------
224
+ 2024-03-26 16:28:48,657 EPOCH 9 done: loss 0.0340 - lr: 0.000006
225
+ 2024-03-26 16:28:49,585 DEV : loss 0.16971871256828308 - f1-score (micro avg) 0.9306
226
+ 2024-03-26 16:28:49,586 saving best model
227
+ 2024-03-26 16:28:50,041 ----------------------------------------------------------------------------------------------------
228
+ 2024-03-26 16:28:52,881 epoch 10 - iter 4/48 - loss 0.02296023 - time (sec): 2.84 - samples/sec: 1307.68 - lr: 0.000006 - momentum: 0.000000
229
+ 2024-03-26 16:28:54,853 epoch 10 - iter 8/48 - loss 0.02058276 - time (sec): 4.81 - samples/sec: 1343.16 - lr: 0.000005 - momentum: 0.000000
230
+ 2024-03-26 16:28:57,040 epoch 10 - iter 12/48 - loss 0.02147638 - time (sec): 7.00 - samples/sec: 1299.47 - lr: 0.000005 - momentum: 0.000000
231
+ 2024-03-26 16:28:59,505 epoch 10 - iter 16/48 - loss 0.01902792 - time (sec): 9.46 - samples/sec: 1261.98 - lr: 0.000004 - momentum: 0.000000
232
+ 2024-03-26 16:29:02,073 epoch 10 - iter 20/48 - loss 0.02142494 - time (sec): 12.03 - samples/sec: 1265.33 - lr: 0.000004 - momentum: 0.000000
233
+ 2024-03-26 16:29:03,490 epoch 10 - iter 24/48 - loss 0.02105055 - time (sec): 13.45 - samples/sec: 1326.26 - lr: 0.000003 - momentum: 0.000000
234
+ 2024-03-26 16:29:04,374 epoch 10 - iter 28/48 - loss 0.02280153 - time (sec): 14.33 - samples/sec: 1397.59 - lr: 0.000003 - momentum: 0.000000
235
+ 2024-03-26 16:29:06,306 epoch 10 - iter 32/48 - loss 0.02588816 - time (sec): 16.26 - samples/sec: 1418.12 - lr: 0.000002 - momentum: 0.000000
236
+ 2024-03-26 16:29:08,582 epoch 10 - iter 36/48 - loss 0.02595188 - time (sec): 18.54 - samples/sec: 1395.33 - lr: 0.000002 - momentum: 0.000000
237
+ 2024-03-26 16:29:10,247 epoch 10 - iter 40/48 - loss 0.02708344 - time (sec): 20.21 - samples/sec: 1421.38 - lr: 0.000001 - momentum: 0.000000
238
+ 2024-03-26 16:29:13,421 epoch 10 - iter 44/48 - loss 0.02656335 - time (sec): 23.38 - samples/sec: 1401.83 - lr: 0.000001 - momentum: 0.000000
239
+ 2024-03-26 16:29:14,149 epoch 10 - iter 48/48 - loss 0.02702381 - time (sec): 24.11 - samples/sec: 1429.95 - lr: 0.000000 - momentum: 0.000000
240
+ 2024-03-26 16:29:14,149 ----------------------------------------------------------------------------------------------------
241
+ 2024-03-26 16:29:14,149 EPOCH 10 done: loss 0.0270 - lr: 0.000000
242
+ 2024-03-26 16:29:15,071 DEV : loss 0.1795857846736908 - f1-score (micro avg) 0.9329
243
+ 2024-03-26 16:29:15,072 saving best model
244
+ 2024-03-26 16:29:15,821 ----------------------------------------------------------------------------------------------------
245
+ 2024-03-26 16:29:15,822 Loading model from best epoch ...
246
+ 2024-03-26 16:29:16,714 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 16:29:17,467
248
+ Results:
249
+ - F-score (micro) 0.908
250
+ - F-score (macro) 0.6898
251
+ - Accuracy 0.8361
252
+
253
+ By class:
254
+ precision recall f1-score support
255
+
256
+ Unternehmen 0.8876 0.8910 0.8893 266
257
+ Auslagerung 0.8769 0.9157 0.8959 249
258
+ Ort 0.9635 0.9851 0.9742 134
259
+ Software 0.0000 0.0000 0.0000 0
260
+
261
+ micro avg 0.8964 0.9199 0.9080 649
262
+ macro avg 0.6820 0.6979 0.6898 649
263
+ weighted avg 0.8992 0.9199 0.9093 649
264
+
265
+ 2024-03-26 16:29:17,467 ----------------------------------------------------------------------------------------------------