Hugging Face's logo

stefan-it
/
autotrain-flair-mobie-gbert_base-bs16-e10-lr3e-05-3

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files
xet
Metrics Community
2
stefan-it commited on
Commit
5d1f60b
·
1 Parent(s): 94f13bc

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +260 -0
training.log ADDED
@@ -0,0 +1,260 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-19 01:11:50,079 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-19 01:11:50,080 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=81, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-19 01:11:50,080 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-19 01:11:50,080 Corpus: 6900 train + 1576 dev + 1833 test sentences
52
+ 2023-10-19 01:11:50,080 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-19 01:11:50,081 Train: 6900 sentences
54
+ 2023-10-19 01:11:50,081 (train_with_dev=False, train_with_test=False)
55
+ 2023-10-19 01:11:50,081 ----------------------------------------------------------------------------------------------------
56
+ 2023-10-19 01:11:50,081 Training Params:
57
+ 2023-10-19 01:11:50,081 - learning_rate: "3e-05"
58
+ 2023-10-19 01:11:50,081 - mini_batch_size: "16"
59
+ 2023-10-19 01:11:50,081 - max_epochs: "10"
60
+ 2023-10-19 01:11:50,081 - shuffle: "True"
61
+ 2023-10-19 01:11:50,081 ----------------------------------------------------------------------------------------------------
62
+ 2023-10-19 01:11:50,081 Plugins:
63
+ 2023-10-19 01:11:50,081 - TensorboardLogger
64
+ 2023-10-19 01:11:50,081 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-19 01:11:50,081 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-19 01:11:50,081 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-19 01:11:50,081 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-19 01:11:50,081 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-19 01:11:50,081 Computation:
70
+ 2023-10-19 01:11:50,081 - compute on device: cuda:0
71
+ 2023-10-19 01:11:50,082 - embedding storage: none
72
+ 2023-10-19 01:11:50,082 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-19 01:11:50,082 Model training base path: "autotrain-flair-mobie-gbert_base-bs16-e10-lr3e-05-3"
74
+ 2023-10-19 01:11:50,082 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-19 01:11:50,082 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-19 01:11:50,082 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2023-10-19 01:12:04,567 epoch 1 - iter 43/432 - loss 4.48039409 - time (sec): 14.48 - samples/sec: 428.48 - lr: 0.000003 - momentum: 0.000000
78
+ 2023-10-19 01:12:19,172 epoch 1 - iter 86/432 - loss 3.60384065 - time (sec): 29.09 - samples/sec: 419.78 - lr: 0.000006 - momentum: 0.000000
79
+ 2023-10-19 01:12:34,227 epoch 1 - iter 129/432 - loss 3.00100989 - time (sec): 44.14 - samples/sec: 420.06 - lr: 0.000009 - momentum: 0.000000
80
+ 2023-10-19 01:12:48,856 epoch 1 - iter 172/432 - loss 2.67529242 - time (sec): 58.77 - samples/sec: 419.88 - lr: 0.000012 - momentum: 0.000000
81
+ 2023-10-19 01:13:03,508 epoch 1 - iter 215/432 - loss 2.41800710 - time (sec): 73.43 - samples/sec: 420.32 - lr: 0.000015 - momentum: 0.000000
82
+ 2023-10-19 01:13:18,780 epoch 1 - iter 258/432 - loss 2.20845718 - time (sec): 88.70 - samples/sec: 417.62 - lr: 0.000018 - momentum: 0.000000
83
+ 2023-10-19 01:13:33,474 epoch 1 - iter 301/432 - loss 2.03382086 - time (sec): 103.39 - samples/sec: 419.31 - lr: 0.000021 - momentum: 0.000000
84
+ 2023-10-19 01:13:48,681 epoch 1 - iter 344/432 - loss 1.89777717 - time (sec): 118.60 - samples/sec: 415.73 - lr: 0.000024 - momentum: 0.000000
85
+ 2023-10-19 01:14:03,153 epoch 1 - iter 387/432 - loss 1.77824460 - time (sec): 133.07 - samples/sec: 417.50 - lr: 0.000027 - momentum: 0.000000
86
+ 2023-10-19 01:14:17,180 epoch 1 - iter 430/432 - loss 1.66845790 - time (sec): 147.10 - samples/sec: 419.34 - lr: 0.000030 - momentum: 0.000000
87
+ 2023-10-19 01:14:17,812 ----------------------------------------------------------------------------------------------------
88
+ 2023-10-19 01:14:17,813 EPOCH 1 done: loss 1.6662 - lr: 0.000030
89
+ 2023-10-19 01:14:31,290 DEV : loss 0.5518006086349487 - f1-score (micro avg) 0.633
90
+ 2023-10-19 01:14:31,318 saving best model
91
+ 2023-10-19 01:14:31,797 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-19 01:14:46,715 epoch 2 - iter 43/432 - loss 0.58848912 - time (sec): 14.92 - samples/sec: 418.67 - lr: 0.000030 - momentum: 0.000000
93
+ 2023-10-19 01:15:01,216 epoch 2 - iter 86/432 - loss 0.57906599 - time (sec): 29.42 - samples/sec: 416.84 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-19 01:15:16,263 epoch 2 - iter 129/432 - loss 0.55687926 - time (sec): 44.46 - samples/sec: 415.80 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-19 01:15:31,483 epoch 2 - iter 172/432 - loss 0.54911765 - time (sec): 59.68 - samples/sec: 418.70 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-19 01:15:47,092 epoch 2 - iter 215/432 - loss 0.53928280 - time (sec): 75.29 - samples/sec: 413.74 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-19 01:16:02,710 epoch 2 - iter 258/432 - loss 0.52556553 - time (sec): 90.91 - samples/sec: 413.06 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-19 01:16:16,574 epoch 2 - iter 301/432 - loss 0.51270046 - time (sec): 104.77 - samples/sec: 415.26 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-19 01:16:31,736 epoch 2 - iter 344/432 - loss 0.49960162 - time (sec): 119.94 - samples/sec: 414.74 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-19 01:16:47,479 epoch 2 - iter 387/432 - loss 0.48792945 - time (sec): 135.68 - samples/sec: 409.73 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-19 01:17:02,658 epoch 2 - iter 430/432 - loss 0.47759296 - time (sec): 150.86 - samples/sec: 408.74 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-19 01:17:03,329 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-19 01:17:03,329 EPOCH 2 done: loss 0.4774 - lr: 0.000027
104
+ 2023-10-19 01:17:16,639 DEV : loss 0.3671756088733673 - f1-score (micro avg) 0.7689
105
+ 2023-10-19 01:17:16,662 saving best model
106
+ 2023-10-19 01:17:17,961 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-19 01:17:33,883 epoch 3 - iter 43/432 - loss 0.30082443 - time (sec): 15.92 - samples/sec: 383.21 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-19 01:17:48,498 epoch 3 - iter 86/432 - loss 0.31439609 - time (sec): 30.54 - samples/sec: 398.31 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-19 01:18:04,454 epoch 3 - iter 129/432 - loss 0.30878822 - time (sec): 46.49 - samples/sec: 395.42 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-19 01:18:20,430 epoch 3 - iter 172/432 - loss 0.30542878 - time (sec): 62.47 - samples/sec: 388.42 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-19 01:18:35,450 epoch 3 - iter 215/432 - loss 0.30005019 - time (sec): 77.49 - samples/sec: 392.10 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-19 01:18:50,219 epoch 3 - iter 258/432 - loss 0.30250277 - time (sec): 92.26 - samples/sec: 398.49 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-19 01:19:05,708 epoch 3 - iter 301/432 - loss 0.30560660 - time (sec): 107.75 - samples/sec: 397.21 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-19 01:19:20,037 epoch 3 - iter 344/432 - loss 0.30515807 - time (sec): 122.07 - samples/sec: 402.40 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-19 01:19:34,892 epoch 3 - iter 387/432 - loss 0.30122812 - time (sec): 136.93 - samples/sec: 403.45 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-19 01:19:50,610 epoch 3 - iter 430/432 - loss 0.29729232 - time (sec): 152.65 - samples/sec: 403.63 - lr: 0.000023 - momentum: 0.000000
117
+ 2023-10-19 01:19:51,120 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-19 01:19:51,120 EPOCH 3 done: loss 0.2972 - lr: 0.000023
119
+ 2023-10-19 01:20:04,739 DEV : loss 0.3239019811153412 - f1-score (micro avg) 0.8084
120
+ 2023-10-19 01:20:04,763 saving best model
121
+ 2023-10-19 01:20:06,054 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-19 01:20:20,480 epoch 4 - iter 43/432 - loss 0.21669863 - time (sec): 14.42 - samples/sec: 428.02 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-19 01:20:35,146 epoch 4 - iter 86/432 - loss 0.20451815 - time (sec): 29.09 - samples/sec: 426.60 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-19 01:20:50,293 epoch 4 - iter 129/432 - loss 0.21364175 - time (sec): 44.24 - samples/sec: 421.20 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-19 01:21:05,859 epoch 4 - iter 172/432 - loss 0.21881045 - time (sec): 59.80 - samples/sec: 415.69 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-19 01:21:21,185 epoch 4 - iter 215/432 - loss 0.22071577 - time (sec): 75.13 - samples/sec: 408.92 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-19 01:21:35,428 epoch 4 - iter 258/432 - loss 0.21878871 - time (sec): 89.37 - samples/sec: 411.30 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-19 01:21:50,207 epoch 4 - iter 301/432 - loss 0.21383356 - time (sec): 104.15 - samples/sec: 410.97 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-19 01:22:04,657 epoch 4 - iter 344/432 - loss 0.21198471 - time (sec): 118.60 - samples/sec: 417.17 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-19 01:22:20,290 epoch 4 - iter 387/432 - loss 0.21285777 - time (sec): 134.24 - samples/sec: 411.41 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-19 01:22:35,747 epoch 4 - iter 430/432 - loss 0.21143223 - time (sec): 149.69 - samples/sec: 411.26 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-19 01:22:36,321 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-19 01:22:36,322 EPOCH 4 done: loss 0.2117 - lr: 0.000020
134
+ 2023-10-19 01:22:49,686 DEV : loss 0.30530545115470886 - f1-score (micro avg) 0.8194
135
+ 2023-10-19 01:22:49,710 saving best model
136
+ 2023-10-19 01:22:51,003 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-19 01:23:05,732 epoch 5 - iter 43/432 - loss 0.15718174 - time (sec): 14.73 - samples/sec: 394.91 - lr: 0.000020 - momentum: 0.000000
138
+ 2023-10-19 01:23:20,374 epoch 5 - iter 86/432 - loss 0.15300782 - time (sec): 29.37 - samples/sec: 406.10 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-19 01:23:34,910 epoch 5 - iter 129/432 - loss 0.15938683 - time (sec): 43.91 - samples/sec: 417.94 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-19 01:23:48,967 epoch 5 - iter 172/432 - loss 0.15808067 - time (sec): 57.96 - samples/sec: 426.26 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-19 01:24:03,719 epoch 5 - iter 215/432 - loss 0.16506791 - time (sec): 72.71 - samples/sec: 424.28 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-19 01:24:19,437 epoch 5 - iter 258/432 - loss 0.16346937 - time (sec): 88.43 - samples/sec: 417.81 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-19 01:24:34,321 epoch 5 - iter 301/432 - loss 0.16131309 - time (sec): 103.32 - samples/sec: 416.84 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-19 01:24:49,426 epoch 5 - iter 344/432 - loss 0.16170570 - time (sec): 118.42 - samples/sec: 415.27 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-19 01:25:03,964 epoch 5 - iter 387/432 - loss 0.16232398 - time (sec): 132.96 - samples/sec: 417.96 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-19 01:25:19,256 epoch 5 - iter 430/432 - loss 0.16167487 - time (sec): 148.25 - samples/sec: 416.09 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-19 01:25:19,736 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-19 01:25:19,736 EPOCH 5 done: loss 0.1620 - lr: 0.000017
149
+ 2023-10-19 01:25:32,940 DEV : loss 0.321034699678421 - f1-score (micro avg) 0.8198
150
+ 2023-10-19 01:25:32,965 saving best model
151
+ 2023-10-19 01:25:34,290 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-19 01:25:50,079 epoch 6 - iter 43/432 - loss 0.11198163 - time (sec): 15.79 - samples/sec: 387.46 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-19 01:26:05,066 epoch 6 - iter 86/432 - loss 0.11365943 - time (sec): 30.77 - samples/sec: 396.18 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-19 01:26:20,043 epoch 6 - iter 129/432 - loss 0.11579195 - time (sec): 45.75 - samples/sec: 408.71 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-19 01:26:34,245 epoch 6 - iter 172/432 - loss 0.12052255 - time (sec): 59.95 - samples/sec: 415.39 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-19 01:26:48,584 epoch 6 - iter 215/432 - loss 0.12402843 - time (sec): 74.29 - samples/sec: 417.44 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-19 01:27:03,787 epoch 6 - iter 258/432 - loss 0.12002060 - time (sec): 89.50 - samples/sec: 414.34 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-19 01:27:19,177 epoch 6 - iter 301/432 - loss 0.12019028 - time (sec): 104.89 - samples/sec: 411.10 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-19 01:27:34,518 epoch 6 - iter 344/432 - loss 0.12027080 - time (sec): 120.23 - samples/sec: 412.59 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-19 01:27:50,024 epoch 6 - iter 387/432 - loss 0.12168734 - time (sec): 135.73 - samples/sec: 409.94 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-19 01:28:04,990 epoch 6 - iter 430/432 - loss 0.12485490 - time (sec): 150.70 - samples/sec: 409.14 - lr: 0.000013 - momentum: 0.000000
162
+ 2023-10-19 01:28:05,672 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-19 01:28:05,673 EPOCH 6 done: loss 0.1248 - lr: 0.000013
164
+ 2023-10-19 01:28:18,762 DEV : loss 0.33496347069740295 - f1-score (micro avg) 0.8301
165
+ 2023-10-19 01:28:18,786 saving best model
166
+ 2023-10-19 01:28:20,656 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-19 01:28:36,296 epoch 7 - iter 43/432 - loss 0.09890459 - time (sec): 15.64 - samples/sec: 398.70 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-19 01:28:50,948 epoch 7 - iter 86/432 - loss 0.09672663 - time (sec): 30.29 - samples/sec: 424.23 - lr: 0.000013 - momentum: 0.000000
169
+ 2023-10-19 01:29:05,164 epoch 7 - iter 129/432 - loss 0.10195590 - time (sec): 44.51 - samples/sec: 420.61 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-19 01:29:20,590 epoch 7 - iter 172/432 - loss 0.10025118 - time (sec): 59.93 - samples/sec: 414.40 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-19 01:29:36,554 epoch 7 - iter 215/432 - loss 0.10219041 - time (sec): 75.90 - samples/sec: 409.06 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-19 01:29:52,459 epoch 7 - iter 258/432 - loss 0.10239845 - time (sec): 91.80 - samples/sec: 402.76 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-19 01:30:07,118 epoch 7 - iter 301/432 - loss 0.10348027 - time (sec): 106.46 - samples/sec: 404.05 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-19 01:30:21,327 epoch 7 - iter 344/432 - loss 0.10248971 - time (sec): 120.67 - samples/sec: 406.93 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-19 01:30:36,374 epoch 7 - iter 387/432 - loss 0.10201551 - time (sec): 135.72 - samples/sec: 407.72 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-19 01:30:51,938 epoch 7 - iter 430/432 - loss 0.10240589 - time (sec): 151.28 - samples/sec: 407.48 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-19 01:30:52,652 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-19 01:30:52,653 EPOCH 7 done: loss 0.1023 - lr: 0.000010
179
+ 2023-10-19 01:31:05,779 DEV : loss 0.3334580063819885 - f1-score (micro avg) 0.841
180
+ 2023-10-19 01:31:05,803 saving best model
181
+ 2023-10-19 01:31:07,095 ----------------------------------------------------------------------------------------------------
182
+ 2023-10-19 01:31:21,749 epoch 8 - iter 43/432 - loss 0.07715346 - time (sec): 14.65 - samples/sec: 397.05 - lr: 0.000010 - momentum: 0.000000
183
+ 2023-10-19 01:31:36,808 epoch 8 - iter 86/432 - loss 0.08026845 - time (sec): 29.71 - samples/sec: 406.77 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-19 01:31:51,972 epoch 8 - iter 129/432 - loss 0.07932378 - time (sec): 44.88 - samples/sec: 418.29 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-19 01:32:06,196 epoch 8 - iter 172/432 - loss 0.07970603 - time (sec): 59.10 - samples/sec: 418.22 - lr: 0.000009 - momentum: 0.000000
186
+ 2023-10-19 01:32:22,269 epoch 8 - iter 215/432 - loss 0.08310639 - time (sec): 75.17 - samples/sec: 411.59 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-19 01:32:38,561 epoch 8 - iter 258/432 - loss 0.08405516 - time (sec): 91.46 - samples/sec: 410.16 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-19 01:32:55,145 epoch 8 - iter 301/432 - loss 0.08440344 - time (sec): 108.05 - samples/sec: 405.80 - lr: 0.000008 - momentum: 0.000000
189
+ 2023-10-19 01:33:09,512 epoch 8 - iter 344/432 - loss 0.08349681 - time (sec): 122.42 - samples/sec: 408.17 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-19 01:33:23,875 epoch 8 - iter 387/432 - loss 0.08301177 - time (sec): 136.78 - samples/sec: 408.43 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-19 01:33:38,932 epoch 8 - iter 430/432 - loss 0.08343770 - time (sec): 151.84 - samples/sec: 405.83 - lr: 0.000007 - momentum: 0.000000
192
+ 2023-10-19 01:33:39,452 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-19 01:33:39,452 EPOCH 8 done: loss 0.0833 - lr: 0.000007
194
+ 2023-10-19 01:33:53,260 DEV : loss 0.353408545255661 - f1-score (micro avg) 0.8389
195
+ 2023-10-19 01:33:53,290 ----------------------------------------------------------------------------------------------------
196
+ 2023-10-19 01:34:07,214 epoch 9 - iter 43/432 - loss 0.06833600 - time (sec): 13.92 - samples/sec: 438.65 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-19 01:34:21,380 epoch 9 - iter 86/432 - loss 0.05877407 - time (sec): 28.09 - samples/sec: 445.31 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-19 01:34:35,471 epoch 9 - iter 129/432 - loss 0.05787196 - time (sec): 42.18 - samples/sec: 437.56 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-19 01:34:50,284 epoch 9 - iter 172/432 - loss 0.06129648 - time (sec): 56.99 - samples/sec: 435.62 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-19 01:35:05,160 epoch 9 - iter 215/432 - loss 0.06250295 - time (sec): 71.87 - samples/sec: 432.52 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-19 01:35:20,325 epoch 9 - iter 258/432 - loss 0.06541137 - time (sec): 87.03 - samples/sec: 428.16 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-19 01:35:35,910 epoch 9 - iter 301/432 - loss 0.06884328 - time (sec): 102.62 - samples/sec: 422.22 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-19 01:35:50,902 epoch 9 - iter 344/432 - loss 0.07066233 - time (sec): 117.61 - samples/sec: 419.43 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-19 01:36:06,777 epoch 9 - iter 387/432 - loss 0.07187549 - time (sec): 133.49 - samples/sec: 414.04 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-19 01:36:21,720 epoch 9 - iter 430/432 - loss 0.07149832 - time (sec): 148.43 - samples/sec: 415.86 - lr: 0.000003 - momentum: 0.000000
206
+ 2023-10-19 01:36:22,264 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-19 01:36:22,264 EPOCH 9 done: loss 0.0716 - lr: 0.000003
208
+ 2023-10-19 01:36:35,557 DEV : loss 0.3648279905319214 - f1-score (micro avg) 0.8495
209
+ 2023-10-19 01:36:35,582 saving best model
210
+ 2023-10-19 01:36:36,891 ----------------------------------------------------------------------------------------------------
211
+ 2023-10-19 01:36:52,640 epoch 10 - iter 43/432 - loss 0.04889939 - time (sec): 15.75 - samples/sec: 402.72 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-19 01:37:07,560 epoch 10 - iter 86/432 - loss 0.05311027 - time (sec): 30.67 - samples/sec: 413.88 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-19 01:37:21,347 epoch 10 - iter 129/432 - loss 0.05478559 - time (sec): 44.45 - samples/sec: 418.04 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-19 01:37:36,295 epoch 10 - iter 172/432 - loss 0.05290573 - time (sec): 59.40 - samples/sec: 418.92 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-19 01:37:50,899 epoch 10 - iter 215/432 - loss 0.05619202 - time (sec): 74.01 - samples/sec: 417.36 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-19 01:38:05,622 epoch 10 - iter 258/432 - loss 0.05730337 - time (sec): 88.73 - samples/sec: 415.93 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-19 01:38:20,801 epoch 10 - iter 301/432 - loss 0.05650763 - time (sec): 103.91 - samples/sec: 416.31 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-19 01:38:36,560 epoch 10 - iter 344/432 - loss 0.05713604 - time (sec): 119.67 - samples/sec: 412.30 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-19 01:38:50,599 epoch 10 - iter 387/432 - loss 0.05915272 - time (sec): 133.71 - samples/sec: 416.97 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-19 01:39:06,390 epoch 10 - iter 430/432 - loss 0.05855833 - time (sec): 149.50 - samples/sec: 412.06 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-19 01:39:06,987 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-19 01:39:06,987 EPOCH 10 done: loss 0.0588 - lr: 0.000000
223
+ 2023-10-19 01:39:20,265 DEV : loss 0.3677222728729248 - f1-score (micro avg) 0.848
224
+ 2023-10-19 01:39:20,773 ----------------------------------------------------------------------------------------------------
225
+ 2023-10-19 01:39:20,775 Loading model from best epoch ...
226
+ 2023-10-19 01:39:23,129 SequenceTagger predicts: Dictionary with 81 tags: O, S-location-route, B-location-route, E-location-route, I-location-route, S-location-stop, B-location-stop, E-location-stop, I-location-stop, S-trigger, B-trigger, E-trigger, I-trigger, S-organization-company, B-organization-company, E-organization-company, I-organization-company, S-location-city, B-location-city, E-location-city, I-location-city, S-location, B-location, E-location, I-location, S-event-cause, B-event-cause, E-event-cause, I-event-cause, S-location-street, B-location-street, E-location-street, I-location-street, S-time, B-time, E-time, I-time, S-date, B-date, E-date, I-date, S-number, B-number, E-number, I-number, S-duration, B-duration, E-duration, I-duration, S-organization
227
+ 2023-10-19 01:39:41,029
228
+ Results:
229
+ - F-score (micro) 0.7588
230
+ - F-score (macro) 0.5671
231
+ - Accuracy 0.6563
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ trigger 0.7137 0.5954 0.6492 833
237
+ location-stop 0.8420 0.8288 0.8353 765
238
+ location 0.8053 0.8271 0.8160 665
239
+ location-city 0.7987 0.8834 0.8389 566
240
+ date 0.8773 0.8350 0.8557 394
241
+ location-street 0.9366 0.8808 0.9079 386
242
+ time 0.7766 0.8828 0.8263 256
243
+ location-route 0.8025 0.6866 0.7400 284
244
+ organization-company 0.7936 0.6865 0.7362 252
245
+ number 0.6632 0.8456 0.7434 149
246
+ distance 0.9824 1.0000 0.9911 167
247
+ duration 0.3205 0.3067 0.3135 163
248
+ event-cause 0.0000 0.0000 0.0000 0
249
+ disaster-type 0.7826 0.2609 0.3913 69
250
+ organization 0.4839 0.5357 0.5085 28
251
+ person 0.4737 0.9000 0.6207 10
252
+ set 0.0000 0.0000 0.0000 0
253
+ org-position 0.0000 0.0000 0.0000 1
254
+ money 0.0000 0.0000 0.0000 0
255
+
256
+ micro avg 0.7504 0.7674 0.7588 4988
257
+ macro avg 0.5817 0.5766 0.5671 4988
258
+ weighted avg 0.7914 0.7674 0.7752 4988
259
+
260
+ 2023-10-19 01:39:41,029 ----------------------------------------------------------------------------------------------------