Hugging Face's logo

stefan-it
/
flair-co-funer-gbert_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
3
stefan-it commited on
Commit
6787202
•
1 Parent(s): 5dde822

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +264 -0
training.log ADDED
@@ -0,0 +1,264 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-03-26 10:36:55,380 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 10:36:55,380 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 10:36:55,380 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 10:36:55,380 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 10:36:55,380 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 10:36:55,380 Train: 758 sentences
54
+ 2024-03-26 10:36:55,380 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 10:36:55,380 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 10:36:55,380 Training Params:
57
+ 2024-03-26 10:36:55,380 - learning_rate: "5e-05"
58
+ 2024-03-26 10:36:55,380 - mini_batch_size: "16"
59
+ 2024-03-26 10:36:55,380 - max_epochs: "10"
60
+ 2024-03-26 10:36:55,380 - shuffle: "True"
61
+ 2024-03-26 10:36:55,380 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 10:36:55,380 Plugins:
63
+ 2024-03-26 10:36:55,380 - TensorboardLogger
64
+ 2024-03-26 10:36:55,380 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 10:36:55,380 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 10:36:55,380 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 10:36:55,381 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 10:36:55,381 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 10:36:55,381 Computation:
70
+ 2024-03-26 10:36:55,381 - compute on device: cuda:0
71
+ 2024-03-26 10:36:55,381 - embedding storage: none
72
+ 2024-03-26 10:36:55,381 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 10:36:55,381 Model training base path: "flair-co-funer-gbert_base-bs16-e10-lr5e-05-5"
74
+ 2024-03-26 10:36:55,381 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 10:36:55,381 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 10:36:55,381 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 10:36:56,864 epoch 1 - iter 4/48 - loss 3.41712450 - time (sec): 1.48 - samples/sec: 1767.86 - lr: 0.000003 - momentum: 0.000000
78
+ 2024-03-26 10:36:59,558 epoch 1 - iter 8/48 - loss 3.30550701 - time (sec): 4.18 - samples/sec: 1457.18 - lr: 0.000007 - momentum: 0.000000
79
+ 2024-03-26 10:37:01,556 epoch 1 - iter 12/48 - loss 3.11276198 - time (sec): 6.18 - samples/sec: 1442.32 - lr: 0.000011 - momentum: 0.000000
80
+ 2024-03-26 10:37:03,119 epoch 1 - iter 16/48 - loss 2.93344677 - time (sec): 7.74 - samples/sec: 1554.77 - lr: 0.000016 - momentum: 0.000000
81
+ 2024-03-26 10:37:05,277 epoch 1 - iter 20/48 - loss 2.80431032 - time (sec): 9.90 - samples/sec: 1523.66 - lr: 0.000020 - momentum: 0.000000
82
+ 2024-03-26 10:37:08,013 epoch 1 - iter 24/48 - loss 2.64390469 - time (sec): 12.63 - samples/sec: 1460.49 - lr: 0.000024 - momentum: 0.000000
83
+ 2024-03-26 10:37:09,640 epoch 1 - iter 28/48 - loss 2.54268009 - time (sec): 14.26 - samples/sec: 1471.84 - lr: 0.000028 - momentum: 0.000000
84
+ 2024-03-26 10:37:11,739 epoch 1 - iter 32/48 - loss 2.42723358 - time (sec): 16.36 - samples/sec: 1469.56 - lr: 0.000032 - momentum: 0.000000
85
+ 2024-03-26 10:37:13,294 epoch 1 - iter 36/48 - loss 2.34158912 - time (sec): 17.91 - samples/sec: 1490.48 - lr: 0.000036 - momentum: 0.000000
86
+ 2024-03-26 10:37:16,074 epoch 1 - iter 40/48 - loss 2.22848020 - time (sec): 20.69 - samples/sec: 1445.11 - lr: 0.000041 - momentum: 0.000000
87
+ 2024-03-26 10:37:17,271 epoch 1 - iter 44/48 - loss 2.14480099 - time (sec): 21.89 - samples/sec: 1468.37 - lr: 0.000045 - momentum: 0.000000
88
+ 2024-03-26 10:37:19,115 epoch 1 - iter 48/48 - loss 2.07037211 - time (sec): 23.73 - samples/sec: 1452.45 - lr: 0.000049 - momentum: 0.000000
89
+ 2024-03-26 10:37:19,115 ----------------------------------------------------------------------------------------------------
90
+ 2024-03-26 10:37:19,115 EPOCH 1 done: loss 2.0704 - lr: 0.000049
91
+ 2024-03-26 10:37:19,956 DEV : loss 0.6493859887123108 - f1-score (micro avg) 0.564
92
+ 2024-03-26 10:37:19,957 saving best model
93
+ 2024-03-26 10:37:20,233 ----------------------------------------------------------------------------------------------------
94
+ 2024-03-26 10:37:22,941 epoch 2 - iter 4/48 - loss 0.84156051 - time (sec): 2.71 - samples/sec: 1275.46 - lr: 0.000050 - momentum: 0.000000
95
+ 2024-03-26 10:37:24,799 epoch 2 - iter 8/48 - loss 0.75611975 - time (sec): 4.57 - samples/sec: 1342.20 - lr: 0.000049 - momentum: 0.000000
96
+ 2024-03-26 10:37:26,706 epoch 2 - iter 12/48 - loss 0.70152889 - time (sec): 6.47 - samples/sec: 1378.50 - lr: 0.000049 - momentum: 0.000000
97
+ 2024-03-26 10:37:29,377 epoch 2 - iter 16/48 - loss 0.63918245 - time (sec): 9.14 - samples/sec: 1384.10 - lr: 0.000048 - momentum: 0.000000
98
+ 2024-03-26 10:37:30,760 epoch 2 - iter 20/48 - loss 0.61223041 - time (sec): 10.53 - samples/sec: 1423.25 - lr: 0.000048 - momentum: 0.000000
99
+ 2024-03-26 10:37:33,570 epoch 2 - iter 24/48 - loss 0.57388306 - time (sec): 13.34 - samples/sec: 1342.10 - lr: 0.000047 - momentum: 0.000000
100
+ 2024-03-26 10:37:35,164 epoch 2 - iter 28/48 - loss 0.56507286 - time (sec): 14.93 - samples/sec: 1377.14 - lr: 0.000047 - momentum: 0.000000
101
+ 2024-03-26 10:37:37,161 epoch 2 - iter 32/48 - loss 0.53839004 - time (sec): 16.93 - samples/sec: 1371.66 - lr: 0.000046 - momentum: 0.000000
102
+ 2024-03-26 10:37:38,917 epoch 2 - iter 36/48 - loss 0.52438575 - time (sec): 18.68 - samples/sec: 1402.87 - lr: 0.000046 - momentum: 0.000000
103
+ 2024-03-26 10:37:41,274 epoch 2 - iter 40/48 - loss 0.52133054 - time (sec): 21.04 - samples/sec: 1391.24 - lr: 0.000046 - momentum: 0.000000
104
+ 2024-03-26 10:37:43,472 epoch 2 - iter 44/48 - loss 0.50072737 - time (sec): 23.24 - samples/sec: 1395.75 - lr: 0.000045 - momentum: 0.000000
105
+ 2024-03-26 10:37:44,737 epoch 2 - iter 48/48 - loss 0.49378757 - time (sec): 24.50 - samples/sec: 1406.83 - lr: 0.000045 - momentum: 0.000000
106
+ 2024-03-26 10:37:44,737 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 10:37:44,737 EPOCH 2 done: loss 0.4938 - lr: 0.000045
108
+ 2024-03-26 10:37:45,651 DEV : loss 0.310893714427948 - f1-score (micro avg) 0.8016
109
+ 2024-03-26 10:37:45,652 saving best model
110
+ 2024-03-26 10:37:46,074 ----------------------------------------------------------------------------------------------------
111
+ 2024-03-26 10:37:47,167 epoch 3 - iter 4/48 - loss 0.37154852 - time (sec): 1.09 - samples/sec: 2044.79 - lr: 0.000044 - momentum: 0.000000
112
+ 2024-03-26 10:37:49,047 epoch 3 - iter 8/48 - loss 0.33711733 - time (sec): 2.97 - samples/sec: 1658.61 - lr: 0.000044 - momentum: 0.000000
113
+ 2024-03-26 10:37:51,260 epoch 3 - iter 12/48 - loss 0.28932422 - time (sec): 5.18 - samples/sec: 1653.93 - lr: 0.000043 - momentum: 0.000000
114
+ 2024-03-26 10:37:53,202 epoch 3 - iter 16/48 - loss 0.28633748 - time (sec): 7.13 - samples/sec: 1596.39 - lr: 0.000043 - momentum: 0.000000
115
+ 2024-03-26 10:37:55,059 epoch 3 - iter 20/48 - loss 0.27913705 - time (sec): 8.98 - samples/sec: 1578.21 - lr: 0.000042 - momentum: 0.000000
116
+ 2024-03-26 10:37:57,010 epoch 3 - iter 24/48 - loss 0.26059395 - time (sec): 10.93 - samples/sec: 1533.08 - lr: 0.000042 - momentum: 0.000000
117
+ 2024-03-26 10:38:00,186 epoch 3 - iter 28/48 - loss 0.25295504 - time (sec): 14.11 - samples/sec: 1418.68 - lr: 0.000041 - momentum: 0.000000
118
+ 2024-03-26 10:38:01,694 epoch 3 - iter 32/48 - loss 0.25146753 - time (sec): 15.62 - samples/sec: 1442.21 - lr: 0.000041 - momentum: 0.000000
119
+ 2024-03-26 10:38:04,977 epoch 3 - iter 36/48 - loss 0.24244393 - time (sec): 18.90 - samples/sec: 1372.36 - lr: 0.000040 - momentum: 0.000000
120
+ 2024-03-26 10:38:07,342 epoch 3 - iter 40/48 - loss 0.24145860 - time (sec): 21.27 - samples/sec: 1375.99 - lr: 0.000040 - momentum: 0.000000
121
+ 2024-03-26 10:38:09,465 epoch 3 - iter 44/48 - loss 0.23400580 - time (sec): 23.39 - samples/sec: 1371.91 - lr: 0.000040 - momentum: 0.000000
122
+ 2024-03-26 10:38:11,039 epoch 3 - iter 48/48 - loss 0.23350999 - time (sec): 24.96 - samples/sec: 1380.91 - lr: 0.000039 - momentum: 0.000000
123
+ 2024-03-26 10:38:11,040 ----------------------------------------------------------------------------------------------------
124
+ 2024-03-26 10:38:11,040 EPOCH 3 done: loss 0.2335 - lr: 0.000039
125
+ 2024-03-26 10:38:11,953 DEV : loss 0.21961775422096252 - f1-score (micro avg) 0.8646
126
+ 2024-03-26 10:38:11,956 saving best model
127
+ 2024-03-26 10:38:12,413 ----------------------------------------------------------------------------------------------------
128
+ 2024-03-26 10:38:15,349 epoch 4 - iter 4/48 - loss 0.11178389 - time (sec): 2.94 - samples/sec: 1270.33 - lr: 0.000039 - momentum: 0.000000
129
+ 2024-03-26 10:38:16,770 epoch 4 - iter 8/48 - loss 0.15959377 - time (sec): 4.36 - samples/sec: 1427.58 - lr: 0.000038 - momentum: 0.000000
130
+ 2024-03-26 10:38:19,288 epoch 4 - iter 12/48 - loss 0.14526371 - time (sec): 6.87 - samples/sec: 1352.93 - lr: 0.000038 - momentum: 0.000000
131
+ 2024-03-26 10:38:21,940 epoch 4 - iter 16/48 - loss 0.13863715 - time (sec): 9.53 - samples/sec: 1332.79 - lr: 0.000037 - momentum: 0.000000
132
+ 2024-03-26 10:38:24,289 epoch 4 - iter 20/48 - loss 0.13644773 - time (sec): 11.88 - samples/sec: 1328.86 - lr: 0.000037 - momentum: 0.000000
133
+ 2024-03-26 10:38:25,802 epoch 4 - iter 24/48 - loss 0.13315323 - time (sec): 13.39 - samples/sec: 1361.75 - lr: 0.000036 - momentum: 0.000000
134
+ 2024-03-26 10:38:28,174 epoch 4 - iter 28/48 - loss 0.13662912 - time (sec): 15.76 - samples/sec: 1347.85 - lr: 0.000036 - momentum: 0.000000
135
+ 2024-03-26 10:38:31,132 epoch 4 - iter 32/48 - loss 0.13820914 - time (sec): 18.72 - samples/sec: 1338.84 - lr: 0.000035 - momentum: 0.000000
136
+ 2024-03-26 10:38:32,760 epoch 4 - iter 36/48 - loss 0.13989528 - time (sec): 20.35 - samples/sec: 1364.17 - lr: 0.000035 - momentum: 0.000000
137
+ 2024-03-26 10:38:33,738 epoch 4 - iter 40/48 - loss 0.14123434 - time (sec): 21.32 - samples/sec: 1408.22 - lr: 0.000034 - momentum: 0.000000
138
+ 2024-03-26 10:38:35,172 epoch 4 - iter 44/48 - loss 0.14171929 - time (sec): 22.76 - samples/sec: 1429.49 - lr: 0.000034 - momentum: 0.000000
139
+ 2024-03-26 10:38:36,037 epoch 4 - iter 48/48 - loss 0.14499606 - time (sec): 23.62 - samples/sec: 1459.24 - lr: 0.000034 - momentum: 0.000000
140
+ 2024-03-26 10:38:36,037 ----------------------------------------------------------------------------------------------------
141
+ 2024-03-26 10:38:36,037 EPOCH 4 done: loss 0.1450 - lr: 0.000034
142
+ 2024-03-26 10:38:36,936 DEV : loss 0.17372402548789978 - f1-score (micro avg) 0.8824
143
+ 2024-03-26 10:38:36,937 saving best model
144
+ 2024-03-26 10:38:37,400 ----------------------------------------------------------------------------------------------------
145
+ 2024-03-26 10:38:39,228 epoch 5 - iter 4/48 - loss 0.11557882 - time (sec): 1.83 - samples/sec: 1572.79 - lr: 0.000033 - momentum: 0.000000
146
+ 2024-03-26 10:38:41,094 epoch 5 - iter 8/48 - loss 0.10611197 - time (sec): 3.69 - samples/sec: 1680.57 - lr: 0.000033 - momentum: 0.000000
147
+ 2024-03-26 10:38:44,190 epoch 5 - iter 12/48 - loss 0.10115099 - time (sec): 6.79 - samples/sec: 1417.38 - lr: 0.000032 - momentum: 0.000000
148
+ 2024-03-26 10:38:45,507 epoch 5 - iter 16/48 - loss 0.09543635 - time (sec): 8.11 - samples/sec: 1467.07 - lr: 0.000032 - momentum: 0.000000
149
+ 2024-03-26 10:38:47,777 epoch 5 - iter 20/48 - loss 0.10616568 - time (sec): 10.38 - samples/sec: 1452.41 - lr: 0.000031 - momentum: 0.000000
150
+ 2024-03-26 10:38:49,914 epoch 5 - iter 24/48 - loss 0.10632050 - time (sec): 12.51 - samples/sec: 1420.72 - lr: 0.000031 - momentum: 0.000000
151
+ 2024-03-26 10:38:51,273 epoch 5 - iter 28/48 - loss 0.11163431 - time (sec): 13.87 - samples/sec: 1462.87 - lr: 0.000030 - momentum: 0.000000
152
+ 2024-03-26 10:38:52,647 epoch 5 - iter 32/48 - loss 0.10968299 - time (sec): 15.24 - samples/sec: 1495.40 - lr: 0.000030 - momentum: 0.000000
153
+ 2024-03-26 10:38:54,770 epoch 5 - iter 36/48 - loss 0.10937174 - time (sec): 17.37 - samples/sec: 1486.88 - lr: 0.000029 - momentum: 0.000000
154
+ 2024-03-26 10:38:56,596 epoch 5 - iter 40/48 - loss 0.10686080 - time (sec): 19.19 - samples/sec: 1485.28 - lr: 0.000029 - momentum: 0.000000
155
+ 2024-03-26 10:38:58,601 epoch 5 - iter 44/48 - loss 0.10461473 - time (sec): 21.20 - samples/sec: 1497.50 - lr: 0.000029 - momentum: 0.000000
156
+ 2024-03-26 10:39:00,720 epoch 5 - iter 48/48 - loss 0.10179425 - time (sec): 23.32 - samples/sec: 1478.37 - lr: 0.000028 - momentum: 0.000000
157
+ 2024-03-26 10:39:00,720 ----------------------------------------------------------------------------------------------------
158
+ 2024-03-26 10:39:00,720 EPOCH 5 done: loss 0.1018 - lr: 0.000028
159
+ 2024-03-26 10:39:01,632 DEV : loss 0.16379894316196442 - f1-score (micro avg) 0.9141
160
+ 2024-03-26 10:39:01,634 saving best model
161
+ 2024-03-26 10:39:02,097 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 10:39:03,985 epoch 6 - iter 4/48 - loss 0.07769285 - time (sec): 1.89 - samples/sec: 1454.25 - lr: 0.000028 - momentum: 0.000000
163
+ 2024-03-26 10:39:06,726 epoch 6 - iter 8/48 - loss 0.08570342 - time (sec): 4.63 - samples/sec: 1373.36 - lr: 0.000027 - momentum: 0.000000
164
+ 2024-03-26 10:39:08,623 epoch 6 - iter 12/48 - loss 0.08876232 - time (sec): 6.53 - samples/sec: 1383.74 - lr: 0.000027 - momentum: 0.000000
165
+ 2024-03-26 10:39:10,116 epoch 6 - iter 16/48 - loss 0.09668307 - time (sec): 8.02 - samples/sec: 1442.87 - lr: 0.000026 - momentum: 0.000000
166
+ 2024-03-26 10:39:12,810 epoch 6 - iter 20/48 - loss 0.08905650 - time (sec): 10.71 - samples/sec: 1361.19 - lr: 0.000026 - momentum: 0.000000
167
+ 2024-03-26 10:39:15,472 epoch 6 - iter 24/48 - loss 0.08339932 - time (sec): 13.37 - samples/sec: 1335.82 - lr: 0.000025 - momentum: 0.000000
168
+ 2024-03-26 10:39:17,935 epoch 6 - iter 28/48 - loss 0.08114834 - time (sec): 15.84 - samples/sec: 1310.16 - lr: 0.000025 - momentum: 0.000000
169
+ 2024-03-26 10:39:19,317 epoch 6 - iter 32/48 - loss 0.08579822 - time (sec): 17.22 - samples/sec: 1353.90 - lr: 0.000024 - momentum: 0.000000
170
+ 2024-03-26 10:39:21,182 epoch 6 - iter 36/48 - loss 0.08363678 - time (sec): 19.08 - samples/sec: 1364.59 - lr: 0.000024 - momentum: 0.000000
171
+ 2024-03-26 10:39:22,159 epoch 6 - iter 40/48 - loss 0.08249491 - time (sec): 20.06 - samples/sec: 1406.18 - lr: 0.000023 - momentum: 0.000000
172
+ 2024-03-26 10:39:24,684 epoch 6 - iter 44/48 - loss 0.08028768 - time (sec): 22.59 - samples/sec: 1377.56 - lr: 0.000023 - momentum: 0.000000
173
+ 2024-03-26 10:39:27,467 epoch 6 - iter 48/48 - loss 0.07561607 - time (sec): 25.37 - samples/sec: 1358.80 - lr: 0.000023 - momentum: 0.000000
174
+ 2024-03-26 10:39:27,467 ----------------------------------------------------------------------------------------------------
175
+ 2024-03-26 10:39:27,467 EPOCH 6 done: loss 0.0756 - lr: 0.000023
176
+ 2024-03-26 10:39:28,391 DEV : loss 0.17018161714076996 - f1-score (micro avg) 0.9144
177
+ 2024-03-26 10:39:28,393 saving best model
178
+ 2024-03-26 10:39:28,838 ----------------------------------------------------------------------------------------------------
179
+ 2024-03-26 10:39:30,970 epoch 7 - iter 4/48 - loss 0.04673555 - time (sec): 2.13 - samples/sec: 1364.98 - lr: 0.000022 - momentum: 0.000000
180
+ 2024-03-26 10:39:32,661 epoch 7 - iter 8/48 - loss 0.03746202 - time (sec): 3.82 - samples/sec: 1394.26 - lr: 0.000022 - momentum: 0.000000
181
+ 2024-03-26 10:39:34,072 epoch 7 - iter 12/48 - loss 0.06529114 - time (sec): 5.23 - samples/sec: 1450.34 - lr: 0.000021 - momentum: 0.000000
182
+ 2024-03-26 10:39:35,942 epoch 7 - iter 16/48 - loss 0.06061829 - time (sec): 7.10 - samples/sec: 1494.60 - lr: 0.000021 - momentum: 0.000000
183
+ 2024-03-26 10:39:38,206 epoch 7 - iter 20/48 - loss 0.07124102 - time (sec): 9.37 - samples/sec: 1547.16 - lr: 0.000020 - momentum: 0.000000
184
+ 2024-03-26 10:39:39,544 epoch 7 - iter 24/48 - loss 0.06873248 - time (sec): 10.70 - samples/sec: 1591.52 - lr: 0.000020 - momentum: 0.000000
185
+ 2024-03-26 10:39:41,775 epoch 7 - iter 28/48 - loss 0.06853416 - time (sec): 12.94 - samples/sec: 1541.81 - lr: 0.000019 - momentum: 0.000000
186
+ 2024-03-26 10:39:43,642 epoch 7 - iter 32/48 - loss 0.07055726 - time (sec): 14.80 - samples/sec: 1538.00 - lr: 0.000019 - momentum: 0.000000
187
+ 2024-03-26 10:39:45,621 epoch 7 - iter 36/48 - loss 0.06861420 - time (sec): 16.78 - samples/sec: 1506.13 - lr: 0.000018 - momentum: 0.000000
188
+ 2024-03-26 10:39:48,400 epoch 7 - iter 40/48 - loss 0.06533710 - time (sec): 19.56 - samples/sec: 1488.91 - lr: 0.000018 - momentum: 0.000000
189
+ 2024-03-26 10:39:49,885 epoch 7 - iter 44/48 - loss 0.06656295 - time (sec): 21.05 - samples/sec: 1504.70 - lr: 0.000017 - momentum: 0.000000
190
+ 2024-03-26 10:39:52,021 epoch 7 - iter 48/48 - loss 0.06424803 - time (sec): 23.18 - samples/sec: 1486.96 - lr: 0.000017 - momentum: 0.000000
191
+ 2024-03-26 10:39:52,022 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 10:39:52,022 EPOCH 7 done: loss 0.0642 - lr: 0.000017
193
+ 2024-03-26 10:39:52,932 DEV : loss 0.1654868870973587 - f1-score (micro avg) 0.9095
194
+ 2024-03-26 10:39:52,933 ----------------------------------------------------------------------------------------------------
195
+ 2024-03-26 10:39:55,154 epoch 8 - iter 4/48 - loss 0.06653426 - time (sec): 2.22 - samples/sec: 1256.02 - lr: 0.000017 - momentum: 0.000000
196
+ 2024-03-26 10:39:56,784 epoch 8 - iter 8/48 - loss 0.04319502 - time (sec): 3.85 - samples/sec: 1411.85 - lr: 0.000016 - momentum: 0.000000
197
+ 2024-03-26 10:39:59,684 epoch 8 - iter 12/48 - loss 0.03983315 - time (sec): 6.75 - samples/sec: 1333.27 - lr: 0.000016 - momentum: 0.000000
198
+ 2024-03-26 10:40:02,126 epoch 8 - iter 16/48 - loss 0.04241048 - time (sec): 9.19 - samples/sec: 1336.49 - lr: 0.000015 - momentum: 0.000000
199
+ 2024-03-26 10:40:03,567 epoch 8 - iter 20/48 - loss 0.04059736 - time (sec): 10.63 - samples/sec: 1397.09 - lr: 0.000015 - momentum: 0.000000
200
+ 2024-03-26 10:40:04,980 epoch 8 - iter 24/48 - loss 0.04101332 - time (sec): 12.05 - samples/sec: 1468.84 - lr: 0.000014 - momentum: 0.000000
201
+ 2024-03-26 10:40:06,293 epoch 8 - iter 28/48 - loss 0.04210901 - time (sec): 13.36 - samples/sec: 1530.54 - lr: 0.000014 - momentum: 0.000000
202
+ 2024-03-26 10:40:08,464 epoch 8 - iter 32/48 - loss 0.04396617 - time (sec): 15.53 - samples/sec: 1491.79 - lr: 0.000013 - momentum: 0.000000
203
+ 2024-03-26 10:40:11,006 epoch 8 - iter 36/48 - loss 0.04284574 - time (sec): 18.07 - samples/sec: 1448.75 - lr: 0.000013 - momentum: 0.000000
204
+ 2024-03-26 10:40:12,954 epoch 8 - iter 40/48 - loss 0.04451235 - time (sec): 20.02 - samples/sec: 1457.82 - lr: 0.000012 - momentum: 0.000000
205
+ 2024-03-26 10:40:15,093 epoch 8 - iter 44/48 - loss 0.04479140 - time (sec): 22.16 - samples/sec: 1441.49 - lr: 0.000012 - momentum: 0.000000
206
+ 2024-03-26 10:40:16,705 epoch 8 - iter 48/48 - loss 0.04470571 - time (sec): 23.77 - samples/sec: 1450.16 - lr: 0.000011 - momentum: 0.000000
207
+ 2024-03-26 10:40:16,705 ----------------------------------------------------------------------------------------------------
208
+ 2024-03-26 10:40:16,706 EPOCH 8 done: loss 0.0447 - lr: 0.000011
209
+ 2024-03-26 10:40:17,642 DEV : loss 0.17140652239322662 - f1-score (micro avg) 0.9257
210
+ 2024-03-26 10:40:17,645 saving best model
211
+ 2024-03-26 10:40:18,111 ----------------------------------------------------------------------------------------------------
212
+ 2024-03-26 10:40:20,797 epoch 9 - iter 4/48 - loss 0.04078747 - time (sec): 2.68 - samples/sec: 1304.22 - lr: 0.000011 - momentum: 0.000000
213
+ 2024-03-26 10:40:22,848 epoch 9 - iter 8/48 - loss 0.03301752 - time (sec): 4.74 - samples/sec: 1348.89 - lr: 0.000011 - momentum: 0.000000
214
+ 2024-03-26 10:40:25,677 epoch 9 - iter 12/48 - loss 0.03173569 - time (sec): 7.56 - samples/sec: 1286.16 - lr: 0.000010 - momentum: 0.000000
215
+ 2024-03-26 10:40:28,786 epoch 9 - iter 16/48 - loss 0.04109295 - time (sec): 10.67 - samples/sec: 1259.69 - lr: 0.000010 - momentum: 0.000000
216
+ 2024-03-26 10:40:29,666 epoch 9 - iter 20/48 - loss 0.03908105 - time (sec): 11.55 - samples/sec: 1348.30 - lr: 0.000009 - momentum: 0.000000
217
+ 2024-03-26 10:40:31,545 epoch 9 - iter 24/48 - loss 0.03741410 - time (sec): 13.43 - samples/sec: 1341.99 - lr: 0.000009 - momentum: 0.000000
218
+ 2024-03-26 10:40:33,546 epoch 9 - iter 28/48 - loss 0.03622658 - time (sec): 15.43 - samples/sec: 1356.79 - lr: 0.000008 - momentum: 0.000000
219
+ 2024-03-26 10:40:34,549 epoch 9 - iter 32/48 - loss 0.03646885 - time (sec): 16.44 - samples/sec: 1421.34 - lr: 0.000008 - momentum: 0.000000
220
+ 2024-03-26 10:40:35,671 epoch 9 - iter 36/48 - loss 0.03612594 - time (sec): 17.56 - samples/sec: 1475.54 - lr: 0.000007 - momentum: 0.000000
221
+ 2024-03-26 10:40:36,982 epoch 9 - iter 40/48 - loss 0.03451051 - time (sec): 18.87 - samples/sec: 1503.18 - lr: 0.000007 - momentum: 0.000000
222
+ 2024-03-26 10:40:40,049 epoch 9 - iter 44/48 - loss 0.03646728 - time (sec): 21.94 - samples/sec: 1470.50 - lr: 0.000006 - momentum: 0.000000
223
+ 2024-03-26 10:40:41,531 epoch 9 - iter 48/48 - loss 0.03497459 - time (sec): 23.42 - samples/sec: 1472.04 - lr: 0.000006 - momentum: 0.000000
224
+ 2024-03-26 10:40:41,531 ----------------------------------------------------------------------------------------------------
225
+ 2024-03-26 10:40:41,531 EPOCH 9 done: loss 0.0350 - lr: 0.000006
226
+ 2024-03-26 10:40:42,444 DEV : loss 0.16576962172985077 - f1-score (micro avg) 0.925
227
+ 2024-03-26 10:40:42,445 ----------------------------------------------------------------------------------------------------
228
+ 2024-03-26 10:40:45,297 epoch 10 - iter 4/48 - loss 0.03088687 - time (sec): 2.85 - samples/sec: 1302.19 - lr: 0.000006 - momentum: 0.000000
229
+ 2024-03-26 10:40:47,272 epoch 10 - iter 8/48 - loss 0.02766641 - time (sec): 4.83 - samples/sec: 1339.02 - lr: 0.000005 - momentum: 0.000000
230
+ 2024-03-26 10:40:49,489 epoch 10 - iter 12/48 - loss 0.02730376 - time (sec): 7.04 - samples/sec: 1291.19 - lr: 0.000005 - momentum: 0.000000
231
+ 2024-03-26 10:40:51,950 epoch 10 - iter 16/48 - loss 0.02553547 - time (sec): 9.50 - samples/sec: 1256.53 - lr: 0.000004 - momentum: 0.000000
232
+ 2024-03-26 10:40:54,523 epoch 10 - iter 20/48 - loss 0.02589611 - time (sec): 12.08 - samples/sec: 1260.53 - lr: 0.000004 - momentum: 0.000000
233
+ 2024-03-26 10:40:55,941 epoch 10 - iter 24/48 - loss 0.02442989 - time (sec): 13.50 - samples/sec: 1321.62 - lr: 0.000003 - momentum: 0.000000
234
+ 2024-03-26 10:40:56,819 epoch 10 - iter 28/48 - loss 0.02520649 - time (sec): 14.37 - samples/sec: 1393.58 - lr: 0.000003 - momentum: 0.000000
235
+ 2024-03-26 10:40:58,765 epoch 10 - iter 32/48 - loss 0.02875749 - time (sec): 16.32 - samples/sec: 1413.35 - lr: 0.000002 - momentum: 0.000000
236
+ 2024-03-26 10:41:01,047 epoch 10 - iter 36/48 - loss 0.02872012 - time (sec): 18.60 - samples/sec: 1390.78 - lr: 0.000002 - momentum: 0.000000
237
+ 2024-03-26 10:41:02,698 epoch 10 - iter 40/48 - loss 0.03056764 - time (sec): 20.25 - samples/sec: 1418.07 - lr: 0.000001 - momentum: 0.000000
238
+ 2024-03-26 10:41:05,857 epoch 10 - iter 44/48 - loss 0.02996567 - time (sec): 23.41 - samples/sec: 1399.92 - lr: 0.000001 - momentum: 0.000000
239
+ 2024-03-26 10:41:06,575 epoch 10 - iter 48/48 - loss 0.02995887 - time (sec): 24.13 - samples/sec: 1428.65 - lr: 0.000000 - momentum: 0.000000
240
+ 2024-03-26 10:41:06,575 ----------------------------------------------------------------------------------------------------
241
+ 2024-03-26 10:41:06,575 EPOCH 10 done: loss 0.0300 - lr: 0.000000
242
+ 2024-03-26 10:41:07,493 DEV : loss 0.1686474084854126 - f1-score (micro avg) 0.9228
243
+ 2024-03-26 10:41:07,785 ----------------------------------------------------------------------------------------------------
244
+ 2024-03-26 10:41:07,786 Loading model from best epoch ...
245
+ 2024-03-26 10:41:08,728 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
246
+ 2024-03-26 10:41:09,591
247
+ Results:
248
+ - F-score (micro) 0.898
249
+ - F-score (macro) 0.683
250
+ - Accuracy 0.8172
251
+
252
+ By class:
253
+ precision recall f1-score support
254
+
255
+ Unternehmen 0.9141 0.8797 0.8966 266
256
+ Auslagerung 0.8327 0.8996 0.8649 249
257
+ Ort 0.9565 0.9851 0.9706 134
258
+ Software 0.0000 0.0000 0.0000 0
259
+
260
+ micro avg 0.8872 0.9091 0.8980 649
261
+ macro avg 0.6758 0.6911 0.6830 649
262
+ weighted avg 0.8916 0.9091 0.8997 649
263
+
264
+ 2024-03-26 10:41:09,591 ----------------------------------------------------------------------------------------------------