Hugging Face's logo

stefan-it
/
autotrain-flair-mobie-gbert_base-bs16-e10-lr3e-05-4

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
2
stefan-it commited on
Commit
64919c1
•
1 Parent(s): d4ec9e6

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 02:07:58,307 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-19 02:07:58,308 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 02:07:58,308 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-19 02:07:58,309 Corpus: 6900 train + 1576 dev + 1833 test sentences
52
+ 2023-10-19 02:07:58,309 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-19 02:07:58,309 Train: 6900 sentences
54
+ 2023-10-19 02:07:58,309 (train_with_dev=False, train_with_test=False)
55
+ 2023-10-19 02:07:58,309 ----------------------------------------------------------------------------------------------------
56
+ 2023-10-19 02:07:58,309 Training Params:
57
+ 2023-10-19 02:07:58,309 - learning_rate: "3e-05"
58
+ 2023-10-19 02:07:58,309 - mini_batch_size: "16"
59
+ 2023-10-19 02:07:58,309 - max_epochs: "10"
60
+ 2023-10-19 02:07:58,309 - shuffle: "True"
61
+ 2023-10-19 02:07:58,309 ----------------------------------------------------------------------------------------------------
62
+ 2023-10-19 02:07:58,309 Plugins:
63
+ 2023-10-19 02:07:58,309 - TensorboardLogger
64
+ 2023-10-19 02:07:58,309 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-19 02:07:58,309 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-19 02:07:58,309 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-19 02:07:58,309 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-19 02:07:58,309 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-19 02:07:58,309 Computation:
70
+ 2023-10-19 02:07:58,310 - compute on device: cuda:0
71
+ 2023-10-19 02:07:58,310 - embedding storage: none
72
+ 2023-10-19 02:07:58,310 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-19 02:07:58,310 Model training base path: "autotrain-flair-mobie-gbert_base-bs16-e10-lr3e-05-4"
74
+ 2023-10-19 02:07:58,310 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-19 02:07:58,310 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-19 02:07:58,310 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2023-10-19 02:08:13,517 epoch 1 - iter 43/432 - loss 4.93250462 - time (sec): 15.21 - samples/sec: 429.82 - lr: 0.000003 - momentum: 0.000000
78
+ 2023-10-19 02:08:28,839 epoch 1 - iter 86/432 - loss 3.97734066 - time (sec): 30.53 - samples/sec: 411.99 - lr: 0.000006 - momentum: 0.000000
79
+ 2023-10-19 02:08:43,873 epoch 1 - iter 129/432 - loss 3.26708172 - time (sec): 45.56 - samples/sec: 408.49 - lr: 0.000009 - momentum: 0.000000
80
+ 2023-10-19 02:08:59,143 epoch 1 - iter 172/432 - loss 2.86543349 - time (sec): 60.83 - samples/sec: 410.11 - lr: 0.000012 - momentum: 0.000000
81
+ 2023-10-19 02:09:15,576 epoch 1 - iter 215/432 - loss 2.59028422 - time (sec): 77.26 - samples/sec: 401.88 - lr: 0.000015 - momentum: 0.000000
82
+ 2023-10-19 02:09:30,082 epoch 1 - iter 258/432 - loss 2.35703794 - time (sec): 91.77 - samples/sec: 406.04 - lr: 0.000018 - momentum: 0.000000
83
+ 2023-10-19 02:09:44,936 epoch 1 - iter 301/432 - loss 2.15806965 - time (sec): 106.63 - samples/sec: 406.83 - lr: 0.000021 - momentum: 0.000000
84
+ 2023-10-19 02:09:59,763 epoch 1 - iter 344/432 - loss 2.00613180 - time (sec): 121.45 - samples/sec: 408.73 - lr: 0.000024 - momentum: 0.000000
85
+ 2023-10-19 02:10:13,958 epoch 1 - iter 387/432 - loss 1.88001586 - time (sec): 135.65 - samples/sec: 409.08 - lr: 0.000027 - momentum: 0.000000
86
+ 2023-10-19 02:10:29,196 epoch 1 - iter 430/432 - loss 1.76470516 - time (sec): 150.89 - samples/sec: 408.67 - lr: 0.000030 - momentum: 0.000000
87
+ 2023-10-19 02:10:29,817 ----------------------------------------------------------------------------------------------------
88
+ 2023-10-19 02:10:29,817 EPOCH 1 done: loss 1.7614 - lr: 0.000030
89
+ 2023-10-19 02:10:43,326 DEV : loss 0.5575976967811584 - f1-score (micro avg) 0.6297
90
+ 2023-10-19 02:10:43,351 saving best model
91
+ 2023-10-19 02:10:43,792 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-19 02:10:58,128 epoch 2 - iter 43/432 - loss 0.62560817 - time (sec): 14.33 - samples/sec: 414.75 - lr: 0.000030 - momentum: 0.000000
93
+ 2023-10-19 02:11:12,293 epoch 2 - iter 86/432 - loss 0.61003222 - time (sec): 28.50 - samples/sec: 441.84 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-19 02:11:27,392 epoch 2 - iter 129/432 - loss 0.58076243 - time (sec): 43.60 - samples/sec: 420.07 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-19 02:11:41,758 epoch 2 - iter 172/432 - loss 0.56106454 - time (sec): 57.96 - samples/sec: 421.61 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-19 02:11:56,333 epoch 2 - iter 215/432 - loss 0.54986490 - time (sec): 72.54 - samples/sec: 419.66 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-19 02:12:11,136 epoch 2 - iter 258/432 - loss 0.53748417 - time (sec): 87.34 - samples/sec: 421.39 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-19 02:12:26,691 epoch 2 - iter 301/432 - loss 0.52065632 - time (sec): 102.90 - samples/sec: 417.10 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-19 02:12:42,153 epoch 2 - iter 344/432 - loss 0.50823824 - time (sec): 118.36 - samples/sec: 411.50 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-19 02:12:58,398 epoch 2 - iter 387/432 - loss 0.49509518 - time (sec): 134.60 - samples/sec: 409.60 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-19 02:13:13,413 epoch 2 - iter 430/432 - loss 0.48286405 - time (sec): 149.62 - samples/sec: 412.11 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-19 02:13:13,985 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-19 02:13:13,986 EPOCH 2 done: loss 0.4828 - lr: 0.000027
104
+ 2023-10-19 02:13:27,322 DEV : loss 0.3526449203491211 - f1-score (micro avg) 0.7754
105
+ 2023-10-19 02:13:27,346 saving best model
106
+ 2023-10-19 02:13:28,590 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-19 02:13:43,341 epoch 3 - iter 43/432 - loss 0.31230210 - time (sec): 14.75 - samples/sec: 421.77 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-19 02:13:57,500 epoch 3 - iter 86/432 - loss 0.30333100 - time (sec): 28.91 - samples/sec: 427.74 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-19 02:14:12,357 epoch 3 - iter 129/432 - loss 0.29986924 - time (sec): 43.76 - samples/sec: 420.79 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-19 02:14:27,258 epoch 3 - iter 172/432 - loss 0.30292860 - time (sec): 58.67 - samples/sec: 422.53 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-19 02:14:42,390 epoch 3 - iter 215/432 - loss 0.30311275 - time (sec): 73.80 - samples/sec: 417.71 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-19 02:14:57,121 epoch 3 - iter 258/432 - loss 0.30056148 - time (sec): 88.53 - samples/sec: 417.74 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-19 02:15:12,777 epoch 3 - iter 301/432 - loss 0.30074375 - time (sec): 104.19 - samples/sec: 416.07 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-19 02:15:27,941 epoch 3 - iter 344/432 - loss 0.30006914 - time (sec): 119.35 - samples/sec: 414.44 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-19 02:15:43,189 epoch 3 - iter 387/432 - loss 0.29793746 - time (sec): 134.60 - samples/sec: 414.38 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-19 02:15:57,165 epoch 3 - iter 430/432 - loss 0.29556403 - time (sec): 148.57 - samples/sec: 414.85 - lr: 0.000023 - momentum: 0.000000
117
+ 2023-10-19 02:15:57,703 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-19 02:15:57,703 EPOCH 3 done: loss 0.2954 - lr: 0.000023
119
+ 2023-10-19 02:16:11,087 DEV : loss 0.30149412155151367 - f1-score (micro avg) 0.8069
120
+ 2023-10-19 02:16:11,111 saving best model
121
+ 2023-10-19 02:16:12,352 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-19 02:16:27,084 epoch 4 - iter 43/432 - loss 0.21264161 - time (sec): 14.73 - samples/sec: 411.11 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-19 02:16:43,109 epoch 4 - iter 86/432 - loss 0.22163872 - time (sec): 30.76 - samples/sec: 394.07 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-19 02:16:58,411 epoch 4 - iter 129/432 - loss 0.22101676 - time (sec): 46.06 - samples/sec: 396.91 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-19 02:17:13,941 epoch 4 - iter 172/432 - loss 0.22361025 - time (sec): 61.59 - samples/sec: 395.37 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-19 02:17:27,914 epoch 4 - iter 215/432 - loss 0.22111072 - time (sec): 75.56 - samples/sec: 402.30 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-19 02:17:43,302 epoch 4 - iter 258/432 - loss 0.21935857 - time (sec): 90.95 - samples/sec: 397.99 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-19 02:17:57,934 epoch 4 - iter 301/432 - loss 0.21595980 - time (sec): 105.58 - samples/sec: 403.99 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-19 02:18:13,452 epoch 4 - iter 344/432 - loss 0.21581270 - time (sec): 121.10 - samples/sec: 408.20 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-19 02:18:28,710 epoch 4 - iter 387/432 - loss 0.21528790 - time (sec): 136.36 - samples/sec: 406.51 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-19 02:18:43,163 epoch 4 - iter 430/432 - loss 0.21420583 - time (sec): 150.81 - samples/sec: 408.75 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-19 02:18:43,749 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-19 02:18:43,749 EPOCH 4 done: loss 0.2144 - lr: 0.000020
134
+ 2023-10-19 02:18:57,091 DEV : loss 0.3102978467941284 - f1-score (micro avg) 0.8163
135
+ 2023-10-19 02:18:57,116 saving best model
136
+ 2023-10-19 02:18:58,362 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-19 02:19:12,811 epoch 5 - iter 43/432 - loss 0.15083744 - time (sec): 14.45 - samples/sec: 412.38 - lr: 0.000020 - momentum: 0.000000
138
+ 2023-10-19 02:19:27,463 epoch 5 - iter 86/432 - loss 0.15320825 - time (sec): 29.10 - samples/sec: 418.60 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-19 02:19:42,164 epoch 5 - iter 129/432 - loss 0.15857775 - time (sec): 43.80 - samples/sec: 428.40 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-19 02:19:57,171 epoch 5 - iter 172/432 - loss 0.15560054 - time (sec): 58.81 - samples/sec: 426.51 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-19 02:20:12,653 epoch 5 - iter 215/432 - loss 0.15299635 - time (sec): 74.29 - samples/sec: 412.79 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-19 02:20:26,815 epoch 5 - iter 258/432 - loss 0.15415565 - time (sec): 88.45 - samples/sec: 413.63 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-19 02:20:41,252 epoch 5 - iter 301/432 - loss 0.15470623 - time (sec): 102.89 - samples/sec: 415.99 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-19 02:20:57,180 epoch 5 - iter 344/432 - loss 0.15738806 - time (sec): 118.82 - samples/sec: 413.47 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-19 02:21:12,778 epoch 5 - iter 387/432 - loss 0.15861707 - time (sec): 134.41 - samples/sec: 411.86 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-19 02:21:28,825 epoch 5 - iter 430/432 - loss 0.15871889 - time (sec): 150.46 - samples/sec: 409.68 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-19 02:21:29,386 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-19 02:21:29,387 EPOCH 5 done: loss 0.1591 - lr: 0.000017
149
+ 2023-10-19 02:21:42,711 DEV : loss 0.3180293142795563 - f1-score (micro avg) 0.8294
150
+ 2023-10-19 02:21:42,736 saving best model
151
+ 2023-10-19 02:21:43,978 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-19 02:21:58,649 epoch 6 - iter 43/432 - loss 0.11722725 - time (sec): 14.67 - samples/sec: 429.78 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-19 02:22:13,269 epoch 6 - iter 86/432 - loss 0.11922248 - time (sec): 29.29 - samples/sec: 428.61 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-19 02:22:29,215 epoch 6 - iter 129/432 - loss 0.11571691 - time (sec): 45.24 - samples/sec: 417.24 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-19 02:22:44,481 epoch 6 - iter 172/432 - loss 0.11512543 - time (sec): 60.50 - samples/sec: 415.94 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-19 02:22:59,365 epoch 6 - iter 215/432 - loss 0.11922747 - time (sec): 75.39 - samples/sec: 415.99 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-19 02:23:13,706 epoch 6 - iter 258/432 - loss 0.12213480 - time (sec): 89.73 - samples/sec: 412.85 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-19 02:23:28,113 epoch 6 - iter 301/432 - loss 0.12324684 - time (sec): 104.13 - samples/sec: 413.96 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-19 02:23:42,639 epoch 6 - iter 344/432 - loss 0.12430268 - time (sec): 118.66 - samples/sec: 415.94 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-19 02:23:57,051 epoch 6 - iter 387/432 - loss 0.12584428 - time (sec): 133.07 - samples/sec: 416.41 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-19 02:24:11,447 epoch 6 - iter 430/432 - loss 0.12693815 - time (sec): 147.47 - samples/sec: 418.17 - lr: 0.000013 - momentum: 0.000000
162
+ 2023-10-19 02:24:12,214 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-19 02:24:12,215 EPOCH 6 done: loss 0.1269 - lr: 0.000013
164
+ 2023-10-19 02:24:25,523 DEV : loss 0.32838910818099976 - f1-score (micro avg) 0.8206
165
+ 2023-10-19 02:24:25,547 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-19 02:24:39,692 epoch 7 - iter 43/432 - loss 0.08912504 - time (sec): 14.14 - samples/sec: 441.62 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-19 02:24:54,333 epoch 7 - iter 86/432 - loss 0.09693013 - time (sec): 28.78 - samples/sec: 423.29 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-19 02:25:09,997 epoch 7 - iter 129/432 - loss 0.09674099 - time (sec): 44.45 - samples/sec: 416.87 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-19 02:25:24,036 epoch 7 - iter 172/432 - loss 0.09757105 - time (sec): 58.49 - samples/sec: 418.36 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-19 02:25:38,207 epoch 7 - iter 215/432 - loss 0.09807207 - time (sec): 72.66 - samples/sec: 416.52 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-19 02:25:53,354 epoch 7 - iter 258/432 - loss 0.09815033 - time (sec): 87.81 - samples/sec: 414.87 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-19 02:26:08,690 epoch 7 - iter 301/432 - loss 0.09658140 - time (sec): 103.14 - samples/sec: 415.61 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-19 02:26:23,350 epoch 7 - iter 344/432 - loss 0.09822029 - time (sec): 117.80 - samples/sec: 414.25 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-19 02:26:38,076 epoch 7 - iter 387/432 - loss 0.09934983 - time (sec): 132.53 - samples/sec: 417.40 - lr: 0.000010 - momentum: 0.000000
175
+ 2023-10-19 02:26:53,511 epoch 7 - iter 430/432 - loss 0.10039982 - time (sec): 147.96 - samples/sec: 416.66 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-19 02:26:53,991 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-19 02:26:53,991 EPOCH 7 done: loss 0.1008 - lr: 0.000010
178
+ 2023-10-19 02:27:07,624 DEV : loss 0.34814995527267456 - f1-score (micro avg) 0.832
179
+ 2023-10-19 02:27:07,647 saving best model
180
+ 2023-10-19 02:27:08,914 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-19 02:27:22,666 epoch 8 - iter 43/432 - loss 0.10350894 - time (sec): 13.75 - samples/sec: 470.25 - lr: 0.000010 - momentum: 0.000000
182
+ 2023-10-19 02:27:36,004 epoch 8 - iter 86/432 - loss 0.09852409 - time (sec): 27.09 - samples/sec: 476.91 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-19 02:27:50,049 epoch 8 - iter 129/432 - loss 0.09286219 - time (sec): 41.13 - samples/sec: 465.85 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-19 02:28:03,617 epoch 8 - iter 172/432 - loss 0.08743720 - time (sec): 54.70 - samples/sec: 455.60 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-19 02:28:17,277 epoch 8 - iter 215/432 - loss 0.08573511 - time (sec): 68.36 - samples/sec: 459.17 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-19 02:28:30,969 epoch 8 - iter 258/432 - loss 0.08331380 - time (sec): 82.05 - samples/sec: 462.63 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-19 02:28:44,354 epoch 8 - iter 301/432 - loss 0.08249316 - time (sec): 95.44 - samples/sec: 457.26 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-19 02:28:58,899 epoch 8 - iter 344/432 - loss 0.08196643 - time (sec): 109.98 - samples/sec: 448.87 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-19 02:29:12,883 epoch 8 - iter 387/432 - loss 0.08297009 - time (sec): 123.97 - samples/sec: 447.78 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-19 02:29:26,795 epoch 8 - iter 430/432 - loss 0.08266864 - time (sec): 137.88 - samples/sec: 447.49 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-19 02:29:27,277 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-19 02:29:27,277 EPOCH 8 done: loss 0.0826 - lr: 0.000007
193
+ 2023-10-19 02:29:39,277 DEV : loss 0.34838762879371643 - f1-score (micro avg) 0.8366
194
+ 2023-10-19 02:29:39,301 saving best model
195
+ 2023-10-19 02:29:40,574 ----------------------------------------------------------------------------------------------------
196
+ 2023-10-19 02:29:53,319 epoch 9 - iter 43/432 - loss 0.06186272 - time (sec): 12.74 - samples/sec: 474.43 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-19 02:30:08,597 epoch 9 - iter 86/432 - loss 0.06634905 - time (sec): 28.02 - samples/sec: 422.46 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-19 02:30:22,346 epoch 9 - iter 129/432 - loss 0.07167375 - time (sec): 41.77 - samples/sec: 424.58 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-19 02:30:36,275 epoch 9 - iter 172/432 - loss 0.06969364 - time (sec): 55.70 - samples/sec: 426.04 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-19 02:30:50,140 epoch 9 - iter 215/432 - loss 0.06782716 - time (sec): 69.56 - samples/sec: 430.13 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-19 02:31:04,623 epoch 9 - iter 258/432 - loss 0.06830674 - time (sec): 84.05 - samples/sec: 428.69 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-19 02:31:18,536 epoch 9 - iter 301/432 - loss 0.06808899 - time (sec): 97.96 - samples/sec: 431.85 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-19 02:31:31,833 epoch 9 - iter 344/432 - loss 0.06544761 - time (sec): 111.26 - samples/sec: 438.17 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-19 02:31:45,008 epoch 9 - iter 387/432 - loss 0.06628105 - time (sec): 124.43 - samples/sec: 443.94 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-19 02:31:58,464 epoch 9 - iter 430/432 - loss 0.06698673 - time (sec): 137.89 - samples/sec: 446.90 - lr: 0.000003 - momentum: 0.000000
206
+ 2023-10-19 02:31:58,887 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-19 02:31:58,887 EPOCH 9 done: loss 0.0669 - lr: 0.000003
208
+ 2023-10-19 02:32:10,770 DEV : loss 0.37735414505004883 - f1-score (micro avg) 0.8355
209
+ 2023-10-19 02:32:10,795 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-19 02:32:24,493 epoch 10 - iter 43/432 - loss 0.06688660 - time (sec): 13.70 - samples/sec: 479.67 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-19 02:32:38,648 epoch 10 - iter 86/432 - loss 0.06022775 - time (sec): 27.85 - samples/sec: 445.00 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-19 02:32:52,077 epoch 10 - iter 129/432 - loss 0.05771265 - time (sec): 41.28 - samples/sec: 452.85 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-19 02:33:05,697 epoch 10 - iter 172/432 - loss 0.05574235 - time (sec): 54.90 - samples/sec: 453.57 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-19 02:33:19,731 epoch 10 - iter 215/432 - loss 0.05793529 - time (sec): 68.93 - samples/sec: 450.88 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-19 02:33:32,567 epoch 10 - iter 258/432 - loss 0.05732065 - time (sec): 81.77 - samples/sec: 451.59 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-19 02:33:45,896 epoch 10 - iter 301/432 - loss 0.05663405 - time (sec): 95.10 - samples/sec: 448.98 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-19 02:33:59,944 epoch 10 - iter 344/432 - loss 0.05723962 - time (sec): 109.15 - samples/sec: 448.98 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-19 02:34:13,929 epoch 10 - iter 387/432 - loss 0.05878775 - time (sec): 123.13 - samples/sec: 447.55 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-19 02:34:27,981 epoch 10 - iter 430/432 - loss 0.05901642 - time (sec): 137.18 - samples/sec: 449.90 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-19 02:34:28,415 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-19 02:34:28,415 EPOCH 10 done: loss 0.0589 - lr: 0.000000
222
+ 2023-10-19 02:34:40,654 DEV : loss 0.38429826498031616 - f1-score (micro avg) 0.8381
223
+ 2023-10-19 02:34:40,679 saving best model
224
+ 2023-10-19 02:34:42,621 ----------------------------------------------------------------------------------------------------
225
+ 2023-10-19 02:34:42,623 Loading model from best epoch ...
226
+ 2023-10-19 02:34:44,813 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 02:35:01,412
228
+ Results:
229
+ - F-score (micro) 0.7634
230
+ - F-score (macro) 0.5759
231
+ - Accuracy 0.6618
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ trigger 0.7056 0.6158 0.6577 833
237
+ location-stop 0.8486 0.8353 0.8419 765
238
+ location 0.7905 0.8286 0.8091 665
239
+ location-city 0.8088 0.8746 0.8404 566
240
+ date 0.8836 0.8477 0.8653 394
241
+ location-street 0.9315 0.8808 0.9055 386
242
+ time 0.7889 0.8906 0.8367 256
243
+ location-route 0.7976 0.6937 0.7420 284
244
+ organization-company 0.7946 0.7063 0.7479 252
245
+ distance 0.9940 1.0000 0.9970 167
246
+ number 0.6721 0.8255 0.7410 149
247
+ duration 0.3455 0.3497 0.3476 163
248
+ event-cause 0.0000 0.0000 0.0000 0
249
+ disaster-type 0.9375 0.4348 0.5941 69
250
+ organization 0.4706 0.5714 0.5161 28
251
+ person 0.3636 0.8000 0.5000 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 0.7503 0.7771 0.7634 4988
257
+ macro avg 0.5860 0.5871 0.5759 4988
258
+ weighted avg 0.7941 0.7771 0.7826 4988
259
+
260
+ 2023-10-19 02:35:01,413 ----------------------------------------------------------------------------------------------------