Hugging Face's logo

stefan-it
/
flair-co-funer-gbert_base-bs16-e10-lr5e-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
eb9a1f8
•
1 Parent(s): eff798d

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 09:31:31,802 ----------------------------------------------------------------------------------------------------
2
+ 2024-03-26 09:31:31,803 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 09:31:31,803 ----------------------------------------------------------------------------------------------------
51
+ 2024-03-26 09:31:31,803 Corpus: 758 train + 94 dev + 96 test sentences
52
+ 2024-03-26 09:31:31,803 ----------------------------------------------------------------------------------------------------
53
+ 2024-03-26 09:31:31,803 Train: 758 sentences
54
+ 2024-03-26 09:31:31,803 (train_with_dev=False, train_with_test=False)
55
+ 2024-03-26 09:31:31,803 ----------------------------------------------------------------------------------------------------
56
+ 2024-03-26 09:31:31,803 Training Params:
57
+ 2024-03-26 09:31:31,803 - learning_rate: "5e-05"
58
+ 2024-03-26 09:31:31,803 - mini_batch_size: "16"
59
+ 2024-03-26 09:31:31,803 - max_epochs: "10"
60
+ 2024-03-26 09:31:31,803 - shuffle: "True"
61
+ 2024-03-26 09:31:31,803 ----------------------------------------------------------------------------------------------------
62
+ 2024-03-26 09:31:31,803 Plugins:
63
+ 2024-03-26 09:31:31,803 - TensorboardLogger
64
+ 2024-03-26 09:31:31,803 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2024-03-26 09:31:31,803 ----------------------------------------------------------------------------------------------------
66
+ 2024-03-26 09:31:31,803 Final evaluation on model from best epoch (best-model.pt)
67
+ 2024-03-26 09:31:31,803 - metric: "('micro avg', 'f1-score')"
68
+ 2024-03-26 09:31:31,803 ----------------------------------------------------------------------------------------------------
69
+ 2024-03-26 09:31:31,803 Computation:
70
+ 2024-03-26 09:31:31,803 - compute on device: cuda:0
71
+ 2024-03-26 09:31:31,803 - embedding storage: none
72
+ 2024-03-26 09:31:31,803 ----------------------------------------------------------------------------------------------------
73
+ 2024-03-26 09:31:31,803 Model training base path: "flair-co-funer-gbert_base-bs16-e10-lr5e-05-1"
74
+ 2024-03-26 09:31:31,803 ----------------------------------------------------------------------------------------------------
75
+ 2024-03-26 09:31:31,803 ----------------------------------------------------------------------------------------------------
76
+ 2024-03-26 09:31:31,803 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2024-03-26 09:31:33,778 epoch 1 - iter 4/48 - loss 3.13464684 - time (sec): 1.97 - samples/sec: 1375.34 - lr: 0.000003 - momentum: 0.000000
78
+ 2024-03-26 09:31:35,058 epoch 1 - iter 8/48 - loss 3.04063711 - time (sec): 3.25 - samples/sec: 1655.82 - lr: 0.000007 - momentum: 0.000000
79
+ 2024-03-26 09:31:37,983 epoch 1 - iter 12/48 - loss 2.87498959 - time (sec): 6.18 - samples/sec: 1408.24 - lr: 0.000011 - momentum: 0.000000
80
+ 2024-03-26 09:31:41,134 epoch 1 - iter 16/48 - loss 2.71452658 - time (sec): 9.33 - samples/sec: 1306.73 - lr: 0.000016 - momentum: 0.000000
81
+ 2024-03-26 09:31:43,588 epoch 1 - iter 20/48 - loss 2.54396549 - time (sec): 11.78 - samples/sec: 1305.27 - lr: 0.000020 - momentum: 0.000000
82
+ 2024-03-26 09:31:45,279 epoch 1 - iter 24/48 - loss 2.41159667 - time (sec): 13.48 - samples/sec: 1353.38 - lr: 0.000024 - momentum: 0.000000
83
+ 2024-03-26 09:31:46,852 epoch 1 - iter 28/48 - loss 2.30256979 - time (sec): 15.05 - samples/sec: 1375.61 - lr: 0.000028 - momentum: 0.000000
84
+ 2024-03-26 09:31:48,927 epoch 1 - iter 32/48 - loss 2.20655569 - time (sec): 17.12 - samples/sec: 1380.31 - lr: 0.000032 - momentum: 0.000000
85
+ 2024-03-26 09:31:49,904 epoch 1 - iter 36/48 - loss 2.12627397 - time (sec): 18.10 - samples/sec: 1439.10 - lr: 0.000036 - momentum: 0.000000
86
+ 2024-03-26 09:31:51,838 epoch 1 - iter 40/48 - loss 2.02856966 - time (sec): 20.03 - samples/sec: 1453.30 - lr: 0.000041 - momentum: 0.000000
87
+ 2024-03-26 09:31:53,824 epoch 1 - iter 44/48 - loss 1.93943712 - time (sec): 22.02 - samples/sec: 1438.68 - lr: 0.000045 - momentum: 0.000000
88
+ 2024-03-26 09:31:55,285 epoch 1 - iter 48/48 - loss 1.84110524 - time (sec): 23.48 - samples/sec: 1468.03 - lr: 0.000049 - momentum: 0.000000
89
+ 2024-03-26 09:31:55,285 ----------------------------------------------------------------------------------------------------
90
+ 2024-03-26 09:31:55,286 EPOCH 1 done: loss 1.8411 - lr: 0.000049
91
+ 2024-03-26 09:31:56,090 DEV : loss 0.5449312925338745 - f1-score (micro avg) 0.6421
92
+ 2024-03-26 09:31:56,091 saving best model
93
+ 2024-03-26 09:31:56,350 ----------------------------------------------------------------------------------------------------
94
+ 2024-03-26 09:31:58,809 epoch 2 - iter 4/48 - loss 0.63065975 - time (sec): 2.46 - samples/sec: 1262.10 - lr: 0.000050 - momentum: 0.000000
95
+ 2024-03-26 09:32:00,855 epoch 2 - iter 8/48 - loss 0.61141871 - time (sec): 4.50 - samples/sec: 1467.84 - lr: 0.000049 - momentum: 0.000000
96
+ 2024-03-26 09:32:03,090 epoch 2 - iter 12/48 - loss 0.58530365 - time (sec): 6.74 - samples/sec: 1373.84 - lr: 0.000049 - momentum: 0.000000
97
+ 2024-03-26 09:32:05,122 epoch 2 - iter 16/48 - loss 0.56230651 - time (sec): 8.77 - samples/sec: 1358.57 - lr: 0.000048 - momentum: 0.000000
98
+ 2024-03-26 09:32:07,226 epoch 2 - iter 20/48 - loss 0.54060094 - time (sec): 10.88 - samples/sec: 1378.87 - lr: 0.000048 - momentum: 0.000000
99
+ 2024-03-26 09:32:10,380 epoch 2 - iter 24/48 - loss 0.49961752 - time (sec): 14.03 - samples/sec: 1318.89 - lr: 0.000047 - momentum: 0.000000
100
+ 2024-03-26 09:32:12,732 epoch 2 - iter 28/48 - loss 0.48484578 - time (sec): 16.38 - samples/sec: 1314.96 - lr: 0.000047 - momentum: 0.000000
101
+ 2024-03-26 09:32:14,439 epoch 2 - iter 32/48 - loss 0.47215469 - time (sec): 18.09 - samples/sec: 1333.85 - lr: 0.000046 - momentum: 0.000000
102
+ 2024-03-26 09:32:15,461 epoch 2 - iter 36/48 - loss 0.46303288 - time (sec): 19.11 - samples/sec: 1384.22 - lr: 0.000046 - momentum: 0.000000
103
+ 2024-03-26 09:32:17,319 epoch 2 - iter 40/48 - loss 0.45128966 - time (sec): 20.97 - samples/sec: 1402.01 - lr: 0.000046 - momentum: 0.000000
104
+ 2024-03-26 09:32:19,328 epoch 2 - iter 44/48 - loss 0.44327526 - time (sec): 22.98 - samples/sec: 1397.39 - lr: 0.000045 - momentum: 0.000000
105
+ 2024-03-26 09:32:20,773 epoch 2 - iter 48/48 - loss 0.43448719 - time (sec): 24.42 - samples/sec: 1411.53 - lr: 0.000045 - momentum: 0.000000
106
+ 2024-03-26 09:32:20,773 ----------------------------------------------------------------------------------------------------
107
+ 2024-03-26 09:32:20,773 EPOCH 2 done: loss 0.4345 - lr: 0.000045
108
+ 2024-03-26 09:32:21,662 DEV : loss 0.2701604962348938 - f1-score (micro avg) 0.812
109
+ 2024-03-26 09:32:21,663 saving best model
110
+ 2024-03-26 09:32:22,173 ----------------------------------------------------------------------------------------------------
111
+ 2024-03-26 09:32:24,643 epoch 3 - iter 4/48 - loss 0.31097284 - time (sec): 2.47 - samples/sec: 1236.92 - lr: 0.000044 - momentum: 0.000000
112
+ 2024-03-26 09:32:26,455 epoch 3 - iter 8/48 - loss 0.27100056 - time (sec): 4.28 - samples/sec: 1371.11 - lr: 0.000044 - momentum: 0.000000
113
+ 2024-03-26 09:32:28,248 epoch 3 - iter 12/48 - loss 0.27588384 - time (sec): 6.07 - samples/sec: 1447.17 - lr: 0.000043 - momentum: 0.000000
114
+ 2024-03-26 09:32:30,630 epoch 3 - iter 16/48 - loss 0.25168783 - time (sec): 8.45 - samples/sec: 1444.54 - lr: 0.000043 - momentum: 0.000000
115
+ 2024-03-26 09:32:32,057 epoch 3 - iter 20/48 - loss 0.26133874 - time (sec): 9.88 - samples/sec: 1497.43 - lr: 0.000042 - momentum: 0.000000
116
+ 2024-03-26 09:32:34,963 epoch 3 - iter 24/48 - loss 0.24628684 - time (sec): 12.79 - samples/sec: 1478.89 - lr: 0.000042 - momentum: 0.000000
117
+ 2024-03-26 09:32:35,719 epoch 3 - iter 28/48 - loss 0.23985620 - time (sec): 13.54 - samples/sec: 1553.61 - lr: 0.000041 - momentum: 0.000000
118
+ 2024-03-26 09:32:38,236 epoch 3 - iter 32/48 - loss 0.22794958 - time (sec): 16.06 - samples/sec: 1495.88 - lr: 0.000041 - momentum: 0.000000
119
+ 2024-03-26 09:32:40,224 epoch 3 - iter 36/48 - loss 0.21907449 - time (sec): 18.05 - samples/sec: 1488.15 - lr: 0.000040 - momentum: 0.000000
120
+ 2024-03-26 09:32:42,104 epoch 3 - iter 40/48 - loss 0.21907616 - time (sec): 19.93 - samples/sec: 1476.48 - lr: 0.000040 - momentum: 0.000000
121
+ 2024-03-26 09:32:44,222 epoch 3 - iter 44/48 - loss 0.21043578 - time (sec): 22.05 - samples/sec: 1479.42 - lr: 0.000040 - momentum: 0.000000
122
+ 2024-03-26 09:32:45,439 epoch 3 - iter 48/48 - loss 0.20906826 - time (sec): 23.26 - samples/sec: 1481.82 - lr: 0.000039 - momentum: 0.000000
123
+ 2024-03-26 09:32:45,439 ----------------------------------------------------------------------------------------------------
124
+ 2024-03-26 09:32:45,439 EPOCH 3 done: loss 0.2091 - lr: 0.000039
125
+ 2024-03-26 09:32:46,322 DEV : loss 0.2270229309797287 - f1-score (micro avg) 0.8544
126
+ 2024-03-26 09:32:46,323 saving best model
127
+ 2024-03-26 09:32:46,755 ----------------------------------------------------------------------------------------------------
128
+ 2024-03-26 09:32:48,235 epoch 4 - iter 4/48 - loss 0.16865347 - time (sec): 1.48 - samples/sec: 1844.61 - lr: 0.000039 - momentum: 0.000000
129
+ 2024-03-26 09:32:50,630 epoch 4 - iter 8/48 - loss 0.16492162 - time (sec): 3.87 - samples/sec: 1481.26 - lr: 0.000038 - momentum: 0.000000
130
+ 2024-03-26 09:32:52,697 epoch 4 - iter 12/48 - loss 0.16216988 - time (sec): 5.94 - samples/sec: 1470.92 - lr: 0.000038 - momentum: 0.000000
131
+ 2024-03-26 09:32:54,836 epoch 4 - iter 16/48 - loss 0.14441421 - time (sec): 8.08 - samples/sec: 1481.99 - lr: 0.000037 - momentum: 0.000000
132
+ 2024-03-26 09:32:57,827 epoch 4 - iter 20/48 - loss 0.13635337 - time (sec): 11.07 - samples/sec: 1399.22 - lr: 0.000037 - momentum: 0.000000
133
+ 2024-03-26 09:32:59,236 epoch 4 - iter 24/48 - loss 0.13563064 - time (sec): 12.48 - samples/sec: 1444.20 - lr: 0.000036 - momentum: 0.000000
134
+ 2024-03-26 09:33:00,732 epoch 4 - iter 28/48 - loss 0.13427894 - time (sec): 13.98 - samples/sec: 1483.96 - lr: 0.000036 - momentum: 0.000000
135
+ 2024-03-26 09:33:03,174 epoch 4 - iter 32/48 - loss 0.13956275 - time (sec): 16.42 - samples/sec: 1476.35 - lr: 0.000035 - momentum: 0.000000
136
+ 2024-03-26 09:33:04,151 epoch 4 - iter 36/48 - loss 0.13898618 - time (sec): 17.39 - samples/sec: 1527.52 - lr: 0.000035 - momentum: 0.000000
137
+ 2024-03-26 09:33:06,496 epoch 4 - iter 40/48 - loss 0.13510467 - time (sec): 19.74 - samples/sec: 1479.50 - lr: 0.000034 - momentum: 0.000000
138
+ 2024-03-26 09:33:08,262 epoch 4 - iter 44/48 - loss 0.13614949 - time (sec): 21.51 - samples/sec: 1500.31 - lr: 0.000034 - momentum: 0.000000
139
+ 2024-03-26 09:33:09,593 epoch 4 - iter 48/48 - loss 0.13528628 - time (sec): 22.84 - samples/sec: 1509.49 - lr: 0.000034 - momentum: 0.000000
140
+ 2024-03-26 09:33:09,593 ----------------------------------------------------------------------------------------------------
141
+ 2024-03-26 09:33:09,593 EPOCH 4 done: loss 0.1353 - lr: 0.000034
142
+ 2024-03-26 09:33:10,485 DEV : loss 0.17390906810760498 - f1-score (micro avg) 0.8874
143
+ 2024-03-26 09:33:10,486 saving best model
144
+ 2024-03-26 09:33:10,918 ----------------------------------------------------------------------------------------------------
145
+ 2024-03-26 09:33:12,819 epoch 5 - iter 4/48 - loss 0.10556470 - time (sec): 1.90 - samples/sec: 1468.92 - lr: 0.000033 - momentum: 0.000000
146
+ 2024-03-26 09:33:15,231 epoch 5 - iter 8/48 - loss 0.09265636 - time (sec): 4.31 - samples/sec: 1377.48 - lr: 0.000033 - momentum: 0.000000
147
+ 2024-03-26 09:33:17,165 epoch 5 - iter 12/48 - loss 0.09936621 - time (sec): 6.24 - samples/sec: 1372.04 - lr: 0.000032 - momentum: 0.000000
148
+ 2024-03-26 09:33:19,146 epoch 5 - iter 16/48 - loss 0.10301987 - time (sec): 8.23 - samples/sec: 1404.36 - lr: 0.000032 - momentum: 0.000000
149
+ 2024-03-26 09:33:21,038 epoch 5 - iter 20/48 - loss 0.10466271 - time (sec): 10.12 - samples/sec: 1414.52 - lr: 0.000031 - momentum: 0.000000
150
+ 2024-03-26 09:33:22,531 epoch 5 - iter 24/48 - loss 0.11156514 - time (sec): 11.61 - samples/sec: 1464.98 - lr: 0.000031 - momentum: 0.000000
151
+ 2024-03-26 09:33:24,700 epoch 5 - iter 28/48 - loss 0.11115749 - time (sec): 13.78 - samples/sec: 1461.94 - lr: 0.000030 - momentum: 0.000000
152
+ 2024-03-26 09:33:27,280 epoch 5 - iter 32/48 - loss 0.10915818 - time (sec): 16.36 - samples/sec: 1447.00 - lr: 0.000030 - momentum: 0.000000
153
+ 2024-03-26 09:33:29,609 epoch 5 - iter 36/48 - loss 0.10469563 - time (sec): 18.69 - samples/sec: 1452.08 - lr: 0.000029 - momentum: 0.000000
154
+ 2024-03-26 09:33:30,483 epoch 5 - iter 40/48 - loss 0.10615079 - time (sec): 19.56 - samples/sec: 1495.65 - lr: 0.000029 - momentum: 0.000000
155
+ 2024-03-26 09:33:33,063 epoch 5 - iter 44/48 - loss 0.10402087 - time (sec): 22.14 - samples/sec: 1462.55 - lr: 0.000029 - momentum: 0.000000
156
+ 2024-03-26 09:33:34,511 epoch 5 - iter 48/48 - loss 0.10402272 - time (sec): 23.59 - samples/sec: 1461.29 - lr: 0.000028 - momentum: 0.000000
157
+ 2024-03-26 09:33:34,511 ----------------------------------------------------------------------------------------------------
158
+ 2024-03-26 09:33:34,511 EPOCH 5 done: loss 0.1040 - lr: 0.000028
159
+ 2024-03-26 09:33:35,399 DEV : loss 0.16777649521827698 - f1-score (micro avg) 0.9018
160
+ 2024-03-26 09:33:35,400 saving best model
161
+ 2024-03-26 09:33:35,831 ----------------------------------------------------------------------------------------------------
162
+ 2024-03-26 09:33:37,818 epoch 6 - iter 4/48 - loss 0.04935121 - time (sec): 1.98 - samples/sec: 1332.68 - lr: 0.000028 - momentum: 0.000000
163
+ 2024-03-26 09:33:39,894 epoch 6 - iter 8/48 - loss 0.07739319 - time (sec): 4.06 - samples/sec: 1362.42 - lr: 0.000027 - momentum: 0.000000
164
+ 2024-03-26 09:33:41,679 epoch 6 - iter 12/48 - loss 0.07870801 - time (sec): 5.85 - samples/sec: 1478.51 - lr: 0.000027 - momentum: 0.000000
165
+ 2024-03-26 09:33:43,866 epoch 6 - iter 16/48 - loss 0.07730179 - time (sec): 8.03 - samples/sec: 1430.42 - lr: 0.000026 - momentum: 0.000000
166
+ 2024-03-26 09:33:45,592 epoch 6 - iter 20/48 - loss 0.08151266 - time (sec): 9.76 - samples/sec: 1438.08 - lr: 0.000026 - momentum: 0.000000
167
+ 2024-03-26 09:33:48,008 epoch 6 - iter 24/48 - loss 0.07871227 - time (sec): 12.17 - samples/sec: 1414.34 - lr: 0.000025 - momentum: 0.000000
168
+ 2024-03-26 09:33:49,815 epoch 6 - iter 28/48 - loss 0.08023292 - time (sec): 13.98 - samples/sec: 1414.68 - lr: 0.000025 - momentum: 0.000000
169
+ 2024-03-26 09:33:52,231 epoch 6 - iter 32/48 - loss 0.07986238 - time (sec): 16.40 - samples/sec: 1393.96 - lr: 0.000024 - momentum: 0.000000
170
+ 2024-03-26 09:33:55,591 epoch 6 - iter 36/48 - loss 0.07669859 - time (sec): 19.76 - samples/sec: 1349.74 - lr: 0.000024 - momentum: 0.000000
171
+ 2024-03-26 09:33:57,177 epoch 6 - iter 40/48 - loss 0.07499192 - time (sec): 21.34 - samples/sec: 1384.54 - lr: 0.000023 - momentum: 0.000000
172
+ 2024-03-26 09:33:58,970 epoch 6 - iter 44/48 - loss 0.07360792 - time (sec): 23.14 - samples/sec: 1388.05 - lr: 0.000023 - momentum: 0.000000
173
+ 2024-03-26 09:34:00,234 epoch 6 - iter 48/48 - loss 0.07617279 - time (sec): 24.40 - samples/sec: 1412.75 - lr: 0.000023 - momentum: 0.000000
174
+ 2024-03-26 09:34:00,235 ----------------------------------------------------------------------------------------------------
175
+ 2024-03-26 09:34:00,235 EPOCH 6 done: loss 0.0762 - lr: 0.000023
176
+ 2024-03-26 09:34:01,134 DEV : loss 0.16763538122177124 - f1-score (micro avg) 0.9099
177
+ 2024-03-26 09:34:01,134 saving best model
178
+ 2024-03-26 09:34:01,569 ----------------------------------------------------------------------------------------------------
179
+ 2024-03-26 09:34:03,193 epoch 7 - iter 4/48 - loss 0.09393644 - time (sec): 1.62 - samples/sec: 1694.32 - lr: 0.000022 - momentum: 0.000000
180
+ 2024-03-26 09:34:05,334 epoch 7 - iter 8/48 - loss 0.07306259 - time (sec): 3.76 - samples/sec: 1429.27 - lr: 0.000022 - momentum: 0.000000
181
+ 2024-03-26 09:34:07,604 epoch 7 - iter 12/48 - loss 0.07212888 - time (sec): 6.03 - samples/sec: 1376.15 - lr: 0.000021 - momentum: 0.000000
182
+ 2024-03-26 09:34:10,146 epoch 7 - iter 16/48 - loss 0.06332659 - time (sec): 8.58 - samples/sec: 1345.98 - lr: 0.000021 - momentum: 0.000000
183
+ 2024-03-26 09:34:12,382 epoch 7 - iter 20/48 - loss 0.06418990 - time (sec): 10.81 - samples/sec: 1351.94 - lr: 0.000020 - momentum: 0.000000
184
+ 2024-03-26 09:34:13,717 epoch 7 - iter 24/48 - loss 0.06067116 - time (sec): 12.15 - samples/sec: 1408.53 - lr: 0.000020 - momentum: 0.000000
185
+ 2024-03-26 09:34:15,098 epoch 7 - iter 28/48 - loss 0.06052551 - time (sec): 13.53 - samples/sec: 1474.63 - lr: 0.000019 - momentum: 0.000000
186
+ 2024-03-26 09:34:17,052 epoch 7 - iter 32/48 - loss 0.05922220 - time (sec): 15.48 - samples/sec: 1465.11 - lr: 0.000019 - momentum: 0.000000
187
+ 2024-03-26 09:34:19,180 epoch 7 - iter 36/48 - loss 0.05681445 - time (sec): 17.61 - samples/sec: 1454.57 - lr: 0.000018 - momentum: 0.000000
188
+ 2024-03-26 09:34:21,604 epoch 7 - iter 40/48 - loss 0.05828898 - time (sec): 20.03 - samples/sec: 1434.70 - lr: 0.000018 - momentum: 0.000000
189
+ 2024-03-26 09:34:23,409 epoch 7 - iter 44/48 - loss 0.05798258 - time (sec): 21.84 - samples/sec: 1451.65 - lr: 0.000017 - momentum: 0.000000
190
+ 2024-03-26 09:34:25,294 epoch 7 - iter 48/48 - loss 0.05651592 - time (sec): 23.72 - samples/sec: 1453.11 - lr: 0.000017 - momentum: 0.000000
191
+ 2024-03-26 09:34:25,294 ----------------------------------------------------------------------------------------------------
192
+ 2024-03-26 09:34:25,294 EPOCH 7 done: loss 0.0565 - lr: 0.000017
193
+ 2024-03-26 09:34:26,192 DEV : loss 0.16629981994628906 - f1-score (micro avg) 0.9159
194
+ 2024-03-26 09:34:26,193 saving best model
195
+ 2024-03-26 09:34:26,624 ----------------------------------------------------------------------------------------------------
196
+ 2024-03-26 09:34:28,581 epoch 8 - iter 4/48 - loss 0.05104273 - time (sec): 1.95 - samples/sec: 1383.16 - lr: 0.000017 - momentum: 0.000000
197
+ 2024-03-26 09:34:31,363 epoch 8 - iter 8/48 - loss 0.03876510 - time (sec): 4.74 - samples/sec: 1172.92 - lr: 0.000016 - momentum: 0.000000
198
+ 2024-03-26 09:34:32,635 epoch 8 - iter 12/48 - loss 0.04249942 - time (sec): 6.01 - samples/sec: 1328.57 - lr: 0.000016 - momentum: 0.000000
199
+ 2024-03-26 09:34:35,040 epoch 8 - iter 16/48 - loss 0.05026022 - time (sec): 8.41 - samples/sec: 1337.94 - lr: 0.000015 - momentum: 0.000000
200
+ 2024-03-26 09:34:37,549 epoch 8 - iter 20/48 - loss 0.04212980 - time (sec): 10.92 - samples/sec: 1379.56 - lr: 0.000015 - momentum: 0.000000
201
+ 2024-03-26 09:34:38,829 epoch 8 - iter 24/48 - loss 0.04271362 - time (sec): 12.20 - samples/sec: 1458.44 - lr: 0.000014 - momentum: 0.000000
202
+ 2024-03-26 09:34:42,077 epoch 8 - iter 28/48 - loss 0.04376621 - time (sec): 15.45 - samples/sec: 1412.35 - lr: 0.000014 - momentum: 0.000000
203
+ 2024-03-26 09:34:44,069 epoch 8 - iter 32/48 - loss 0.04516094 - time (sec): 17.44 - samples/sec: 1413.41 - lr: 0.000013 - momentum: 0.000000
204
+ 2024-03-26 09:34:45,121 epoch 8 - iter 36/48 - loss 0.04602552 - time (sec): 18.49 - samples/sec: 1451.86 - lr: 0.000013 - momentum: 0.000000
205
+ 2024-03-26 09:34:46,782 epoch 8 - iter 40/48 - loss 0.04504686 - time (sec): 20.16 - samples/sec: 1450.07 - lr: 0.000012 - momentum: 0.000000
206
+ 2024-03-26 09:34:48,353 epoch 8 - iter 44/48 - loss 0.04621049 - time (sec): 21.73 - samples/sec: 1470.63 - lr: 0.000012 - momentum: 0.000000
207
+ 2024-03-26 09:34:50,296 epoch 8 - iter 48/48 - loss 0.04680647 - time (sec): 23.67 - samples/sec: 1456.41 - lr: 0.000011 - momentum: 0.000000
208
+ 2024-03-26 09:34:50,296 ----------------------------------------------------------------------------------------------------
209
+ 2024-03-26 09:34:50,296 EPOCH 8 done: loss 0.0468 - lr: 0.000011
210
+ 2024-03-26 09:34:51,194 DEV : loss 0.1683352291584015 - f1-score (micro avg) 0.9131
211
+ 2024-03-26 09:34:51,196 ----------------------------------------------------------------------------------------------------
212
+ 2024-03-26 09:34:53,032 epoch 9 - iter 4/48 - loss 0.03239823 - time (sec): 1.84 - samples/sec: 1458.83 - lr: 0.000011 - momentum: 0.000000
213
+ 2024-03-26 09:34:56,183 epoch 9 - iter 8/48 - loss 0.02376028 - time (sec): 4.99 - samples/sec: 1252.19 - lr: 0.000011 - momentum: 0.000000
214
+ 2024-03-26 09:34:57,833 epoch 9 - iter 12/48 - loss 0.02807453 - time (sec): 6.64 - samples/sec: 1309.51 - lr: 0.000010 - momentum: 0.000000
215
+ 2024-03-26 09:35:00,070 epoch 9 - iter 16/48 - loss 0.02893077 - time (sec): 8.87 - samples/sec: 1298.35 - lr: 0.000010 - momentum: 0.000000
216
+ 2024-03-26 09:35:02,333 epoch 9 - iter 20/48 - loss 0.03399391 - time (sec): 11.14 - samples/sec: 1328.52 - lr: 0.000009 - momentum: 0.000000
217
+ 2024-03-26 09:35:04,499 epoch 9 - iter 24/48 - loss 0.03527515 - time (sec): 13.30 - samples/sec: 1344.48 - lr: 0.000009 - momentum: 0.000000
218
+ 2024-03-26 09:35:06,861 epoch 9 - iter 28/48 - loss 0.03279158 - time (sec): 15.66 - samples/sec: 1337.95 - lr: 0.000008 - momentum: 0.000000
219
+ 2024-03-26 09:35:09,187 epoch 9 - iter 32/48 - loss 0.03328617 - time (sec): 17.99 - samples/sec: 1334.74 - lr: 0.000008 - momentum: 0.000000
220
+ 2024-03-26 09:35:10,978 epoch 9 - iter 36/48 - loss 0.03552305 - time (sec): 19.78 - samples/sec: 1353.32 - lr: 0.000007 - momentum: 0.000000
221
+ 2024-03-26 09:35:13,150 epoch 9 - iter 40/48 - loss 0.03717142 - time (sec): 21.95 - samples/sec: 1343.11 - lr: 0.000007 - momentum: 0.000000
222
+ 2024-03-26 09:35:15,278 epoch 9 - iter 44/48 - loss 0.03618859 - time (sec): 24.08 - samples/sec: 1353.80 - lr: 0.000006 - momentum: 0.000000
223
+ 2024-03-26 09:35:16,026 epoch 9 - iter 48/48 - loss 0.03659229 - time (sec): 24.83 - samples/sec: 1388.29 - lr: 0.000006 - momentum: 0.000000
224
+ 2024-03-26 09:35:16,027 ----------------------------------------------------------------------------------------------------
225
+ 2024-03-26 09:35:16,027 EPOCH 9 done: loss 0.0366 - lr: 0.000006
226
+ 2024-03-26 09:35:16,937 DEV : loss 0.16806438565254211 - f1-score (micro avg) 0.9207
227
+ 2024-03-26 09:35:16,938 saving best model
228
+ 2024-03-26 09:35:17,369 ----------------------------------------------------------------------------------------------------
229
+ 2024-03-26 09:35:19,113 epoch 10 - iter 4/48 - loss 0.01938598 - time (sec): 1.74 - samples/sec: 1508.81 - lr: 0.000006 - momentum: 0.000000
230
+ 2024-03-26 09:35:21,045 epoch 10 - iter 8/48 - loss 0.02258557 - time (sec): 3.67 - samples/sec: 1507.88 - lr: 0.000005 - momentum: 0.000000
231
+ 2024-03-26 09:35:23,658 epoch 10 - iter 12/48 - loss 0.02730836 - time (sec): 6.29 - samples/sec: 1387.97 - lr: 0.000005 - momentum: 0.000000
232
+ 2024-03-26 09:35:25,570 epoch 10 - iter 16/48 - loss 0.03125997 - time (sec): 8.20 - samples/sec: 1399.21 - lr: 0.000004 - momentum: 0.000000
233
+ 2024-03-26 09:35:27,402 epoch 10 - iter 20/48 - loss 0.03153887 - time (sec): 10.03 - samples/sec: 1442.05 - lr: 0.000004 - momentum: 0.000000
234
+ 2024-03-26 09:35:29,043 epoch 10 - iter 24/48 - loss 0.03612120 - time (sec): 11.67 - samples/sec: 1452.94 - lr: 0.000003 - momentum: 0.000000
235
+ 2024-03-26 09:35:30,786 epoch 10 - iter 28/48 - loss 0.03445545 - time (sec): 13.42 - samples/sec: 1474.83 - lr: 0.000003 - momentum: 0.000000
236
+ 2024-03-26 09:35:31,976 epoch 10 - iter 32/48 - loss 0.03355325 - time (sec): 14.61 - samples/sec: 1507.95 - lr: 0.000002 - momentum: 0.000000
237
+ 2024-03-26 09:35:34,947 epoch 10 - iter 36/48 - loss 0.03055986 - time (sec): 17.58 - samples/sec: 1457.31 - lr: 0.000002 - momentum: 0.000000
238
+ 2024-03-26 09:35:37,702 epoch 10 - iter 40/48 - loss 0.03283648 - time (sec): 20.33 - samples/sec: 1430.36 - lr: 0.000001 - momentum: 0.000000
239
+ 2024-03-26 09:35:40,457 epoch 10 - iter 44/48 - loss 0.03091020 - time (sec): 23.09 - samples/sec: 1398.36 - lr: 0.000001 - momentum: 0.000000
240
+ 2024-03-26 09:35:42,052 epoch 10 - iter 48/48 - loss 0.03004462 - time (sec): 24.68 - samples/sec: 1396.65 - lr: 0.000000 - momentum: 0.000000
241
+ 2024-03-26 09:35:42,053 ----------------------------------------------------------------------------------------------------
242
+ 2024-03-26 09:35:42,053 EPOCH 10 done: loss 0.0300 - lr: 0.000000
243
+ 2024-03-26 09:35:42,972 DEV : loss 0.1705980747938156 - f1-score (micro avg) 0.9214
244
+ 2024-03-26 09:35:42,974 saving best model
245
+ 2024-03-26 09:35:43,689 ----------------------------------------------------------------------------------------------------
246
+ 2024-03-26 09:35:43,689 Loading model from best epoch ...
247
+ 2024-03-26 09:35:44,576 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 09:35:45,419
249
+ Results:
250
+ - F-score (micro) 0.9
251
+ - F-score (macro) 0.6847
252
+ - Accuracy 0.8239
253
+
254
+ By class:
255
+ precision recall f1-score support
256
+
257
+ Unternehmen 0.9046 0.8910 0.8977 266
258
+ Auslagerung 0.8333 0.9036 0.8671 249
259
+ Ort 0.9635 0.9851 0.9742 134
260
+ Software 0.0000 0.0000 0.0000 0
261
+
262
+ micro avg 0.8852 0.9153 0.9000 649
263
+ macro avg 0.6754 0.6949 0.6847 649
264
+ weighted avg 0.8894 0.9153 0.9017 649
265
+
266
+ 2024-03-26 09:35:45,419 ----------------------------------------------------------------------------------------------------