Hugging Face's logo

stefan-it
/
hmbench-topres19th-en-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3

Token Classification
Flair
PyTorch
TensorBoard
English
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
3725154
•
1 Parent(s): 0a14f39

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +240 -0
training.log ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-25 11:23:45,120 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-25 11:23:45,121 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(64001, 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=13, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-25 11:23:45,122 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-25 11:23:45,122 MultiCorpus: 6183 train + 680 dev + 2113 test sentences
52
+ - NER_HIPE_2022 Corpus: 6183 train + 680 dev + 2113 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/topres19th/en/with_doc_seperator
53
+ 2023-10-25 11:23:45,122 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-25 11:23:45,122 Train: 6183 sentences
55
+ 2023-10-25 11:23:45,122 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-25 11:23:45,122 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-25 11:23:45,122 Training Params:
58
+ 2023-10-25 11:23:45,122 - learning_rate: "3e-05"
59
+ 2023-10-25 11:23:45,122 - mini_batch_size: "8"
60
+ 2023-10-25 11:23:45,122 - max_epochs: "10"
61
+ 2023-10-25 11:23:45,122 - shuffle: "True"
62
+ 2023-10-25 11:23:45,122 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-25 11:23:45,122 Plugins:
64
+ 2023-10-25 11:23:45,122 - TensorboardLogger
65
+ 2023-10-25 11:23:45,123 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-25 11:23:45,123 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-25 11:23:45,123 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-25 11:23:45,123 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-25 11:23:45,123 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-25 11:23:45,123 Computation:
71
+ 2023-10-25 11:23:45,123 - compute on device: cuda:0
72
+ 2023-10-25 11:23:45,123 - embedding storage: none
73
+ 2023-10-25 11:23:45,123 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-25 11:23:45,123 Model training base path: "hmbench-topres19th/en-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3"
75
+ 2023-10-25 11:23:45,123 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-25 11:23:45,123 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-25 11:23:45,123 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-25 11:23:50,075 epoch 1 - iter 77/773 - loss 1.91678480 - time (sec): 4.95 - samples/sec: 2874.84 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-25 11:23:54,493 epoch 1 - iter 154/773 - loss 1.15435044 - time (sec): 9.37 - samples/sec: 2781.06 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-25 11:23:58,988 epoch 1 - iter 231/773 - loss 0.83774526 - time (sec): 13.86 - samples/sec: 2790.82 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-25 11:24:03,379 epoch 1 - iter 308/773 - loss 0.66749755 - time (sec): 18.26 - samples/sec: 2784.22 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-25 11:24:08,082 epoch 1 - iter 385/773 - loss 0.56093101 - time (sec): 22.96 - samples/sec: 2754.85 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-25 11:24:12,562 epoch 1 - iter 462/773 - loss 0.49653847 - time (sec): 27.44 - samples/sec: 2714.10 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-25 11:24:16,898 epoch 1 - iter 539/773 - loss 0.44368224 - time (sec): 31.77 - samples/sec: 2725.13 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-25 11:24:21,264 epoch 1 - iter 616/773 - loss 0.39898395 - time (sec): 36.14 - samples/sec: 2742.88 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-25 11:24:25,543 epoch 1 - iter 693/773 - loss 0.36556811 - time (sec): 40.42 - samples/sec: 2757.54 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-25 11:24:29,876 epoch 1 - iter 770/773 - loss 0.33864681 - time (sec): 44.75 - samples/sec: 2765.28 - lr: 0.000030 - momentum: 0.000000
88
+ 2023-10-25 11:24:30,037 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-25 11:24:30,038 EPOCH 1 done: loss 0.3377 - lr: 0.000030
90
+ 2023-10-25 11:24:33,102 DEV : loss 0.06016210466623306 - f1-score (micro avg) 0.7285
91
+ 2023-10-25 11:24:33,119 saving best model
92
+ 2023-10-25 11:24:33,572 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-25 11:24:37,785 epoch 2 - iter 77/773 - loss 0.07630160 - time (sec): 4.21 - samples/sec: 2796.95 - lr: 0.000030 - momentum: 0.000000
94
+ 2023-10-25 11:24:42,099 epoch 2 - iter 154/773 - loss 0.07590975 - time (sec): 8.53 - samples/sec: 2887.65 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-25 11:24:46,938 epoch 2 - iter 231/773 - loss 0.07648601 - time (sec): 13.36 - samples/sec: 2844.76 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-25 11:24:51,715 epoch 2 - iter 308/773 - loss 0.07250012 - time (sec): 18.14 - samples/sec: 2818.90 - lr: 0.000029 - momentum: 0.000000
97
+ 2023-10-25 11:24:56,017 epoch 2 - iter 385/773 - loss 0.07287862 - time (sec): 22.44 - samples/sec: 2828.12 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-25 11:25:00,268 epoch 2 - iter 462/773 - loss 0.07298913 - time (sec): 26.69 - samples/sec: 2806.41 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-25 11:25:04,535 epoch 2 - iter 539/773 - loss 0.07213277 - time (sec): 30.96 - samples/sec: 2808.25 - lr: 0.000028 - momentum: 0.000000
100
+ 2023-10-25 11:25:08,906 epoch 2 - iter 616/773 - loss 0.07150224 - time (sec): 35.33 - samples/sec: 2817.08 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-25 11:25:13,090 epoch 2 - iter 693/773 - loss 0.07238655 - time (sec): 39.52 - samples/sec: 2815.06 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-25 11:25:17,354 epoch 2 - iter 770/773 - loss 0.07180071 - time (sec): 43.78 - samples/sec: 2826.40 - lr: 0.000027 - momentum: 0.000000
103
+ 2023-10-25 11:25:17,537 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-25 11:25:17,537 EPOCH 2 done: loss 0.0717 - lr: 0.000027
105
+ 2023-10-25 11:25:20,202 DEV : loss 0.04841422662138939 - f1-score (micro avg) 0.7897
106
+ 2023-10-25 11:25:20,220 saving best model
107
+ 2023-10-25 11:25:20,869 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-25 11:25:25,415 epoch 3 - iter 77/773 - loss 0.03585561 - time (sec): 4.54 - samples/sec: 2729.38 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-25 11:25:30,524 epoch 3 - iter 154/773 - loss 0.03611039 - time (sec): 9.65 - samples/sec: 2571.24 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-25 11:25:35,189 epoch 3 - iter 231/773 - loss 0.03766398 - time (sec): 14.32 - samples/sec: 2687.59 - lr: 0.000026 - momentum: 0.000000
111
+ 2023-10-25 11:25:39,730 epoch 3 - iter 308/773 - loss 0.03782797 - time (sec): 18.86 - samples/sec: 2690.26 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-25 11:25:44,174 epoch 3 - iter 385/773 - loss 0.04228608 - time (sec): 23.30 - samples/sec: 2675.69 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-25 11:25:48,714 epoch 3 - iter 462/773 - loss 0.04114786 - time (sec): 27.84 - samples/sec: 2637.81 - lr: 0.000025 - momentum: 0.000000
114
+ 2023-10-25 11:25:53,418 epoch 3 - iter 539/773 - loss 0.04108091 - time (sec): 32.54 - samples/sec: 2655.14 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-25 11:25:57,981 epoch 3 - iter 616/773 - loss 0.04075527 - time (sec): 37.11 - samples/sec: 2660.94 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-25 11:26:02,262 epoch 3 - iter 693/773 - loss 0.04114755 - time (sec): 41.39 - samples/sec: 2689.33 - lr: 0.000024 - momentum: 0.000000
117
+ 2023-10-25 11:26:06,577 epoch 3 - iter 770/773 - loss 0.04149795 - time (sec): 45.70 - samples/sec: 2712.34 - lr: 0.000023 - momentum: 0.000000
118
+ 2023-10-25 11:26:06,737 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-25 11:26:06,738 EPOCH 3 done: loss 0.0414 - lr: 0.000023
120
+ 2023-10-25 11:26:09,120 DEV : loss 0.07111605256795883 - f1-score (micro avg) 0.7925
121
+ 2023-10-25 11:26:09,138 saving best model
122
+ 2023-10-25 11:26:09,841 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-25 11:26:14,547 epoch 4 - iter 77/773 - loss 0.01773509 - time (sec): 4.70 - samples/sec: 2731.17 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-25 11:26:19,254 epoch 4 - iter 154/773 - loss 0.02615240 - time (sec): 9.41 - samples/sec: 2734.92 - lr: 0.000023 - momentum: 0.000000
125
+ 2023-10-25 11:26:23,788 epoch 4 - iter 231/773 - loss 0.02603226 - time (sec): 13.95 - samples/sec: 2756.74 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-25 11:26:28,325 epoch 4 - iter 308/773 - loss 0.02587723 - time (sec): 18.48 - samples/sec: 2747.31 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-25 11:26:32,834 epoch 4 - iter 385/773 - loss 0.02487878 - time (sec): 22.99 - samples/sec: 2755.18 - lr: 0.000022 - momentum: 0.000000
128
+ 2023-10-25 11:26:37,187 epoch 4 - iter 462/773 - loss 0.02646341 - time (sec): 27.34 - samples/sec: 2773.65 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-25 11:26:41,447 epoch 4 - iter 539/773 - loss 0.02772075 - time (sec): 31.60 - samples/sec: 2769.18 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-25 11:26:45,981 epoch 4 - iter 616/773 - loss 0.02778736 - time (sec): 36.14 - samples/sec: 2743.29 - lr: 0.000021 - momentum: 0.000000
131
+ 2023-10-25 11:26:50,560 epoch 4 - iter 693/773 - loss 0.02887018 - time (sec): 40.72 - samples/sec: 2717.05 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-25 11:26:55,041 epoch 4 - iter 770/773 - loss 0.02903954 - time (sec): 45.20 - samples/sec: 2737.37 - lr: 0.000020 - momentum: 0.000000
133
+ 2023-10-25 11:26:55,221 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-25 11:26:55,222 EPOCH 4 done: loss 0.0291 - lr: 0.000020
135
+ 2023-10-25 11:26:57,921 DEV : loss 0.08298607915639877 - f1-score (micro avg) 0.7716
136
+ 2023-10-25 11:26:57,937 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-25 11:27:02,328 epoch 5 - iter 77/773 - loss 0.02702620 - time (sec): 4.39 - samples/sec: 2672.32 - lr: 0.000020 - momentum: 0.000000
138
+ 2023-10-25 11:27:06,657 epoch 5 - iter 154/773 - loss 0.02292715 - time (sec): 8.72 - samples/sec: 2750.18 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-25 11:27:11,263 epoch 5 - iter 231/773 - loss 0.02016044 - time (sec): 13.32 - samples/sec: 2754.22 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-25 11:27:15,785 epoch 5 - iter 308/773 - loss 0.02010956 - time (sec): 17.85 - samples/sec: 2752.40 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-25 11:27:20,238 epoch 5 - iter 385/773 - loss 0.02039984 - time (sec): 22.30 - samples/sec: 2718.24 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-25 11:27:24,677 epoch 5 - iter 462/773 - loss 0.02190141 - time (sec): 26.74 - samples/sec: 2745.65 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-25 11:27:28,819 epoch 5 - iter 539/773 - loss 0.02138656 - time (sec): 30.88 - samples/sec: 2776.01 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-25 11:27:32,991 epoch 5 - iter 616/773 - loss 0.02090922 - time (sec): 35.05 - samples/sec: 2800.73 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-25 11:27:37,188 epoch 5 - iter 693/773 - loss 0.02083139 - time (sec): 39.25 - samples/sec: 2813.48 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-25 11:27:41,590 epoch 5 - iter 770/773 - loss 0.01980612 - time (sec): 43.65 - samples/sec: 2839.77 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-25 11:27:41,748 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-25 11:27:41,748 EPOCH 5 done: loss 0.0198 - lr: 0.000017
149
+ 2023-10-25 11:27:44,317 DEV : loss 0.10546855628490448 - f1-score (micro avg) 0.7653
150
+ 2023-10-25 11:27:44,335 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-25 11:27:48,611 epoch 6 - iter 77/773 - loss 0.01097830 - time (sec): 4.27 - samples/sec: 2852.95 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-25 11:27:53,219 epoch 6 - iter 154/773 - loss 0.01069205 - time (sec): 8.88 - samples/sec: 2781.94 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-25 11:27:57,904 epoch 6 - iter 231/773 - loss 0.00999344 - time (sec): 13.57 - samples/sec: 2751.47 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-25 11:28:02,448 epoch 6 - iter 308/773 - loss 0.01106499 - time (sec): 18.11 - samples/sec: 2721.28 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-25 11:28:07,185 epoch 6 - iter 385/773 - loss 0.01289234 - time (sec): 22.85 - samples/sec: 2769.63 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-25 11:28:11,711 epoch 6 - iter 462/773 - loss 0.01300909 - time (sec): 27.38 - samples/sec: 2767.91 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-25 11:28:16,226 epoch 6 - iter 539/773 - loss 0.01390742 - time (sec): 31.89 - samples/sec: 2740.14 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-25 11:28:20,802 epoch 6 - iter 616/773 - loss 0.01367765 - time (sec): 36.47 - samples/sec: 2730.90 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-25 11:28:25,371 epoch 6 - iter 693/773 - loss 0.01407704 - time (sec): 41.03 - samples/sec: 2718.67 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-25 11:28:29,956 epoch 6 - iter 770/773 - loss 0.01382031 - time (sec): 45.62 - samples/sec: 2714.49 - lr: 0.000013 - momentum: 0.000000
161
+ 2023-10-25 11:28:30,128 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-25 11:28:30,128 EPOCH 6 done: loss 0.0138 - lr: 0.000013
163
+ 2023-10-25 11:28:33,108 DEV : loss 0.1092146635055542 - f1-score (micro avg) 0.7919
164
+ 2023-10-25 11:28:33,124 ----------------------------------------------------------------------------------------------------
165
+ 2023-10-25 11:28:37,466 epoch 7 - iter 77/773 - loss 0.00808285 - time (sec): 4.34 - samples/sec: 2808.41 - lr: 0.000013 - momentum: 0.000000
166
+ 2023-10-25 11:28:41,713 epoch 7 - iter 154/773 - loss 0.01054920 - time (sec): 8.59 - samples/sec: 2892.61 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-25 11:28:45,847 epoch 7 - iter 231/773 - loss 0.00910599 - time (sec): 12.72 - samples/sec: 2943.80 - lr: 0.000012 - momentum: 0.000000
168
+ 2023-10-25 11:28:50,141 epoch 7 - iter 308/773 - loss 0.00849477 - time (sec): 17.02 - samples/sec: 2918.19 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-25 11:28:54,420 epoch 7 - iter 385/773 - loss 0.00844130 - time (sec): 21.29 - samples/sec: 2882.76 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-25 11:28:58,725 epoch 7 - iter 462/773 - loss 0.00830111 - time (sec): 25.60 - samples/sec: 2908.43 - lr: 0.000011 - momentum: 0.000000
171
+ 2023-10-25 11:29:03,175 epoch 7 - iter 539/773 - loss 0.01004841 - time (sec): 30.05 - samples/sec: 2876.33 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-25 11:29:07,818 epoch 7 - iter 616/773 - loss 0.00946287 - time (sec): 34.69 - samples/sec: 2831.29 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-25 11:29:12,320 epoch 7 - iter 693/773 - loss 0.00905604 - time (sec): 39.19 - samples/sec: 2834.21 - lr: 0.000010 - momentum: 0.000000
174
+ 2023-10-25 11:29:16,815 epoch 7 - iter 770/773 - loss 0.00934767 - time (sec): 43.69 - samples/sec: 2835.04 - lr: 0.000010 - momentum: 0.000000
175
+ 2023-10-25 11:29:16,982 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-25 11:29:16,983 EPOCH 7 done: loss 0.0093 - lr: 0.000010
177
+ 2023-10-25 11:29:19,518 DEV : loss 0.1093023419380188 - f1-score (micro avg) 0.7848
178
+ 2023-10-25 11:29:19,537 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-25 11:29:23,811 epoch 8 - iter 77/773 - loss 0.00671671 - time (sec): 4.27 - samples/sec: 2797.82 - lr: 0.000010 - momentum: 0.000000
180
+ 2023-10-25 11:29:28,182 epoch 8 - iter 154/773 - loss 0.00697096 - time (sec): 8.64 - samples/sec: 2893.67 - lr: 0.000009 - momentum: 0.000000
181
+ 2023-10-25 11:29:32,549 epoch 8 - iter 231/773 - loss 0.00623998 - time (sec): 13.01 - samples/sec: 2896.37 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-25 11:29:36,864 epoch 8 - iter 308/773 - loss 0.00599104 - time (sec): 17.33 - samples/sec: 2900.18 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-25 11:29:41,202 epoch 8 - iter 385/773 - loss 0.00649897 - time (sec): 21.66 - samples/sec: 2890.66 - lr: 0.000008 - momentum: 0.000000
184
+ 2023-10-25 11:29:45,564 epoch 8 - iter 462/773 - loss 0.00718124 - time (sec): 26.03 - samples/sec: 2848.14 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-25 11:29:49,995 epoch 8 - iter 539/773 - loss 0.00668630 - time (sec): 30.46 - samples/sec: 2846.89 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-25 11:29:54,430 epoch 8 - iter 616/773 - loss 0.00648273 - time (sec): 34.89 - samples/sec: 2835.96 - lr: 0.000007 - momentum: 0.000000
187
+ 2023-10-25 11:29:58,956 epoch 8 - iter 693/773 - loss 0.00657413 - time (sec): 39.42 - samples/sec: 2819.74 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-25 11:30:03,306 epoch 8 - iter 770/773 - loss 0.00648703 - time (sec): 43.77 - samples/sec: 2824.90 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-25 11:30:03,477 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-25 11:30:03,477 EPOCH 8 done: loss 0.0065 - lr: 0.000007
191
+ 2023-10-25 11:30:06,018 DEV : loss 0.12693718075752258 - f1-score (micro avg) 0.7553
192
+ 2023-10-25 11:30:06,034 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-25 11:30:10,578 epoch 9 - iter 77/773 - loss 0.00163409 - time (sec): 4.54 - samples/sec: 2700.63 - lr: 0.000006 - momentum: 0.000000
194
+ 2023-10-25 11:30:15,192 epoch 9 - iter 154/773 - loss 0.00370643 - time (sec): 9.16 - samples/sec: 2665.87 - lr: 0.000006 - momentum: 0.000000
195
+ 2023-10-25 11:30:20,010 epoch 9 - iter 231/773 - loss 0.00354968 - time (sec): 13.97 - samples/sec: 2615.36 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-25 11:30:24,754 epoch 9 - iter 308/773 - loss 0.00327572 - time (sec): 18.72 - samples/sec: 2612.04 - lr: 0.000005 - momentum: 0.000000
197
+ 2023-10-25 11:30:29,255 epoch 9 - iter 385/773 - loss 0.00341277 - time (sec): 23.22 - samples/sec: 2684.08 - lr: 0.000005 - momentum: 0.000000
198
+ 2023-10-25 11:30:33,495 epoch 9 - iter 462/773 - loss 0.00316797 - time (sec): 27.46 - samples/sec: 2715.67 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-25 11:30:37,782 epoch 9 - iter 539/773 - loss 0.00347581 - time (sec): 31.75 - samples/sec: 2734.77 - lr: 0.000004 - momentum: 0.000000
200
+ 2023-10-25 11:30:42,176 epoch 9 - iter 616/773 - loss 0.00395273 - time (sec): 36.14 - samples/sec: 2760.41 - lr: 0.000004 - momentum: 0.000000
201
+ 2023-10-25 11:30:46,387 epoch 9 - iter 693/773 - loss 0.00399888 - time (sec): 40.35 - samples/sec: 2786.00 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-25 11:30:50,631 epoch 9 - iter 770/773 - loss 0.00454743 - time (sec): 44.59 - samples/sec: 2777.36 - lr: 0.000003 - momentum: 0.000000
203
+ 2023-10-25 11:30:50,808 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-25 11:30:50,808 EPOCH 9 done: loss 0.0045 - lr: 0.000003
205
+ 2023-10-25 11:30:53,316 DEV : loss 0.12672311067581177 - f1-score (micro avg) 0.7758
206
+ 2023-10-25 11:30:53,337 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-25 11:30:58,434 epoch 10 - iter 77/773 - loss 0.00097966 - time (sec): 5.10 - samples/sec: 2687.48 - lr: 0.000003 - momentum: 0.000000
208
+ 2023-10-25 11:31:03,219 epoch 10 - iter 154/773 - loss 0.00096282 - time (sec): 9.88 - samples/sec: 2580.96 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-25 11:31:07,705 epoch 10 - iter 231/773 - loss 0.00100765 - time (sec): 14.37 - samples/sec: 2665.67 - lr: 0.000002 - momentum: 0.000000
210
+ 2023-10-25 11:31:12,108 epoch 10 - iter 308/773 - loss 0.00103783 - time (sec): 18.77 - samples/sec: 2699.24 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-25 11:31:16,706 epoch 10 - iter 385/773 - loss 0.00112711 - time (sec): 23.37 - samples/sec: 2721.46 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-25 11:31:21,631 epoch 10 - iter 462/773 - loss 0.00170921 - time (sec): 28.29 - samples/sec: 2684.80 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-25 11:31:25,883 epoch 10 - iter 539/773 - loss 0.00217353 - time (sec): 32.54 - samples/sec: 2697.81 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-25 11:31:30,157 epoch 10 - iter 616/773 - loss 0.00225198 - time (sec): 36.82 - samples/sec: 2708.18 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-25 11:31:34,532 epoch 10 - iter 693/773 - loss 0.00229876 - time (sec): 41.19 - samples/sec: 2717.64 - lr: 0.000000 - momentum: 0.000000
216
+ 2023-10-25 11:31:38,969 epoch 10 - iter 770/773 - loss 0.00247570 - time (sec): 45.63 - samples/sec: 2715.19 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-25 11:31:39,133 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-25 11:31:39,134 EPOCH 10 done: loss 0.0026 - lr: 0.000000
219
+ 2023-10-25 11:31:42,020 DEV : loss 0.13155733048915863 - f1-score (micro avg) 0.7645
220
+ 2023-10-25 11:31:42,974 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-25 11:31:42,975 Loading model from best epoch ...
222
+ 2023-10-25 11:31:44,802 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-BUILDING, B-BUILDING, E-BUILDING, I-BUILDING, S-STREET, B-STREET, E-STREET, I-STREET
223
+ 2023-10-25 11:31:53,488
224
+ Results:
225
+ - F-score (micro) 0.7909
226
+ - F-score (macro) 0.693
227
+ - Accuracy 0.67
228
+
229
+ By class:
230
+ precision recall f1-score support
231
+
232
+ LOC 0.8082 0.8552 0.8310 946
233
+ BUILDING 0.6884 0.5135 0.5882 185
234
+ STREET 0.7805 0.5714 0.6598 56
235
+
236
+ micro avg 0.7932 0.7885 0.7909 1187
237
+ macro avg 0.7590 0.6467 0.6930 1187
238
+ weighted avg 0.7882 0.7885 0.7851 1187
239
+
240
+ 2023-10-25 11:31:53,489 ----------------------------------------------------------------------------------------------------