Hugging Face's logo

stefan-it
/
hmbench-topres19th-en-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1

Token Classification
Flair
PyTorch
TensorBoard
English
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
01142a8
·
1 Parent(s): c87b517

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. runs/events.out.tfevents.1697534161.4c6324b99746.1159.1 +3 -0
  5. test.tsv +0 -0
  6. training.log +239 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf0a37cd287b33a85d30396dc2f87cd397486106cf47405785eb653204fff889
3
+ size 440942021
dev.tsv ADDED
The diff for this file is too large to render. See raw diff
 
loss.tsv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ EPOCH TIMESTAMP LEARNING_RATE TRAIN_LOSS DEV_LOSS DEV_PRECISION DEV_RECALL DEV_F1 DEV_ACCURACY
2
+ 1 09:18:06 0.0000 0.2880 0.0625 0.7269 0.7300 0.7284 0.5864
3
+ 2 09:20:13 0.0000 0.0921 0.0714 0.7586 0.6498 0.7000 0.5461
4
+ 3 09:22:18 0.0000 0.0627 0.0698 0.7194 0.8439 0.7767 0.6472
5
+ 4 09:24:29 0.0000 0.0420 0.0895 0.7605 0.7637 0.7621 0.6220
6
+ 5 09:26:31 0.0000 0.0318 0.0925 0.7683 0.7975 0.7826 0.6632
7
+ 6 09:28:37 0.0000 0.0243 0.1133 0.7759 0.7890 0.7824 0.6608
8
+ 7 09:30:40 0.0000 0.0171 0.1029 0.7837 0.8101 0.7967 0.6809
9
+ 8 09:32:46 0.0000 0.0081 0.1405 0.7500 0.7848 0.7670 0.6436
10
+ 9 09:34:49 0.0000 0.0060 0.1270 0.7734 0.8354 0.8032 0.6851
11
+ 10 09:36:54 0.0000 0.0036 0.1268 0.8075 0.8143 0.8109 0.6968
runs/events.out.tfevents.1697534161.4c6324b99746.1159.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0795f18c91fdffcd8c2694f41c976ee12120265c13f194743f4381727359e48
3
+ size 864636
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 09:16:01,879 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 09:16:01,881 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): ElectraModel(
5
+ (embeddings): ElectraEmbeddings(
6
+ (word_embeddings): Embedding(32001, 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): ElectraEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x ElectraLayer(
15
+ (attention): ElectraAttention(
16
+ (self): ElectraSelfAttention(
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): ElectraSelfOutput(
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): ElectraIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): ElectraOutput(
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
+ )
41
+ )
42
+ (locked_dropout): LockedDropout(p=0.5)
43
+ (linear): Linear(in_features=768, out_features=13, bias=True)
44
+ (loss_function): CrossEntropyLoss()
45
+ )"
46
+ 2023-10-17 09:16:01,881 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 09:16:01,881 MultiCorpus: 6183 train + 680 dev + 2113 test sentences
48
+ - NER_HIPE_2022 Corpus: 6183 train + 680 dev + 2113 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/topres19th/en/with_doc_seperator
49
+ 2023-10-17 09:16:01,881 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 09:16:01,882 Train: 6183 sentences
51
+ 2023-10-17 09:16:01,882 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 09:16:01,882 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 09:16:01,882 Training Params:
54
+ 2023-10-17 09:16:01,882 - learning_rate: "5e-05"
55
+ 2023-10-17 09:16:01,882 - mini_batch_size: "4"
56
+ 2023-10-17 09:16:01,882 - max_epochs: "10"
57
+ 2023-10-17 09:16:01,882 - shuffle: "True"
58
+ 2023-10-17 09:16:01,882 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 09:16:01,882 Plugins:
60
+ 2023-10-17 09:16:01,882 - TensorboardLogger
61
+ 2023-10-17 09:16:01,882 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 09:16:01,882 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 09:16:01,882 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 09:16:01,882 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 09:16:01,883 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 09:16:01,883 Computation:
67
+ 2023-10-17 09:16:01,883 - compute on device: cuda:0
68
+ 2023-10-17 09:16:01,883 - embedding storage: none
69
+ 2023-10-17 09:16:01,883 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 09:16:01,883 Model training base path: "hmbench-topres19th/en-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
71
+ 2023-10-17 09:16:01,883 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 09:16:01,883 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 09:16:01,883 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 09:16:13,984 epoch 1 - iter 154/1546 - loss 1.62924967 - time (sec): 12.10 - samples/sec: 1062.47 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 09:16:25,906 epoch 1 - iter 308/1546 - loss 0.93248566 - time (sec): 24.02 - samples/sec: 1044.33 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 09:16:37,922 epoch 1 - iter 462/1546 - loss 0.66723251 - time (sec): 36.04 - samples/sec: 1038.33 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 09:16:49,947 epoch 1 - iter 616/1546 - loss 0.52961124 - time (sec): 48.06 - samples/sec: 1048.97 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 09:17:01,946 epoch 1 - iter 770/1546 - loss 0.44851569 - time (sec): 60.06 - samples/sec: 1042.97 - lr: 0.000025 - momentum: 0.000000
79
+ 2023-10-17 09:17:14,007 epoch 1 - iter 924/1546 - loss 0.39387565 - time (sec): 72.12 - samples/sec: 1038.88 - lr: 0.000030 - momentum: 0.000000
80
+ 2023-10-17 09:17:26,317 epoch 1 - iter 1078/1546 - loss 0.35997284 - time (sec): 84.43 - samples/sec: 1027.07 - lr: 0.000035 - momentum: 0.000000
81
+ 2023-10-17 09:17:39,074 epoch 1 - iter 1232/1546 - loss 0.33539440 - time (sec): 97.19 - samples/sec: 1016.65 - lr: 0.000040 - momentum: 0.000000
82
+ 2023-10-17 09:17:51,486 epoch 1 - iter 1386/1546 - loss 0.30892754 - time (sec): 109.60 - samples/sec: 1018.04 - lr: 0.000045 - momentum: 0.000000
83
+ 2023-10-17 09:18:03,504 epoch 1 - iter 1540/1546 - loss 0.28846921 - time (sec): 121.62 - samples/sec: 1019.55 - lr: 0.000050 - momentum: 0.000000
84
+ 2023-10-17 09:18:03,959 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 09:18:03,959 EPOCH 1 done: loss 0.2880 - lr: 0.000050
86
+ 2023-10-17 09:18:06,548 DEV : loss 0.062463369220495224 - f1-score (micro avg) 0.7284
87
+ 2023-10-17 09:18:06,576 saving best model
88
+ 2023-10-17 09:18:07,127 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 09:18:19,061 epoch 2 - iter 154/1546 - loss 0.11824926 - time (sec): 11.93 - samples/sec: 990.45 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 09:18:31,040 epoch 2 - iter 308/1546 - loss 0.09859653 - time (sec): 23.91 - samples/sec: 1010.34 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 09:18:43,141 epoch 2 - iter 462/1546 - loss 0.09381658 - time (sec): 36.01 - samples/sec: 1046.89 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 09:18:55,259 epoch 2 - iter 616/1546 - loss 0.09522061 - time (sec): 48.13 - samples/sec: 1041.58 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 09:19:07,386 epoch 2 - iter 770/1546 - loss 0.09398797 - time (sec): 60.26 - samples/sec: 1041.37 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 09:19:19,779 epoch 2 - iter 924/1546 - loss 0.09339793 - time (sec): 72.65 - samples/sec: 1031.34 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 09:19:32,797 epoch 2 - iter 1078/1546 - loss 0.09259153 - time (sec): 85.67 - samples/sec: 1020.93 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 09:19:44,967 epoch 2 - iter 1232/1546 - loss 0.09239772 - time (sec): 97.84 - samples/sec: 1027.57 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 09:19:57,504 epoch 2 - iter 1386/1546 - loss 0.09117852 - time (sec): 110.37 - samples/sec: 1016.56 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 09:20:10,053 epoch 2 - iter 1540/1546 - loss 0.09196043 - time (sec): 122.92 - samples/sec: 1008.94 - lr: 0.000044 - momentum: 0.000000
99
+ 2023-10-17 09:20:10,529 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 09:20:10,529 EPOCH 2 done: loss 0.0921 - lr: 0.000044
101
+ 2023-10-17 09:20:13,490 DEV : loss 0.07139772176742554 - f1-score (micro avg) 0.7
102
+ 2023-10-17 09:20:13,524 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-17 09:20:25,161 epoch 3 - iter 154/1546 - loss 0.05594334 - time (sec): 11.63 - samples/sec: 1004.75 - lr: 0.000044 - momentum: 0.000000
104
+ 2023-10-17 09:20:37,872 epoch 3 - iter 308/1546 - loss 0.06152451 - time (sec): 24.35 - samples/sec: 1019.88 - lr: 0.000043 - momentum: 0.000000
105
+ 2023-10-17 09:20:50,458 epoch 3 - iter 462/1546 - loss 0.05868671 - time (sec): 36.93 - samples/sec: 1033.95 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 09:21:02,558 epoch 3 - iter 616/1546 - loss 0.05626465 - time (sec): 49.03 - samples/sec: 1031.87 - lr: 0.000042 - momentum: 0.000000
107
+ 2023-10-17 09:21:14,660 epoch 3 - iter 770/1546 - loss 0.05831441 - time (sec): 61.13 - samples/sec: 1021.45 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 09:21:26,729 epoch 3 - iter 924/1546 - loss 0.05999687 - time (sec): 73.20 - samples/sec: 1025.56 - lr: 0.000041 - momentum: 0.000000
109
+ 2023-10-17 09:21:38,836 epoch 3 - iter 1078/1546 - loss 0.06078623 - time (sec): 85.31 - samples/sec: 1021.69 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 09:21:51,064 epoch 3 - iter 1232/1546 - loss 0.06071517 - time (sec): 97.54 - samples/sec: 1020.41 - lr: 0.000040 - momentum: 0.000000
111
+ 2023-10-17 09:22:03,166 epoch 3 - iter 1386/1546 - loss 0.06341036 - time (sec): 109.64 - samples/sec: 1006.31 - lr: 0.000039 - momentum: 0.000000
112
+ 2023-10-17 09:22:15,420 epoch 3 - iter 1540/1546 - loss 0.06258378 - time (sec): 121.89 - samples/sec: 1016.44 - lr: 0.000039 - momentum: 0.000000
113
+ 2023-10-17 09:22:15,882 ----------------------------------------------------------------------------------------------------
114
+ 2023-10-17 09:22:15,882 EPOCH 3 done: loss 0.0627 - lr: 0.000039
115
+ 2023-10-17 09:22:18,763 DEV : loss 0.06976697593927383 - f1-score (micro avg) 0.7767
116
+ 2023-10-17 09:22:18,792 saving best model
117
+ 2023-10-17 09:22:20,230 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-17 09:22:32,554 epoch 4 - iter 154/1546 - loss 0.04523365 - time (sec): 12.32 - samples/sec: 1043.60 - lr: 0.000038 - momentum: 0.000000
119
+ 2023-10-17 09:22:45,142 epoch 4 - iter 308/1546 - loss 0.03926806 - time (sec): 24.91 - samples/sec: 984.68 - lr: 0.000038 - momentum: 0.000000
120
+ 2023-10-17 09:22:57,852 epoch 4 - iter 462/1546 - loss 0.04050801 - time (sec): 37.62 - samples/sec: 997.23 - lr: 0.000037 - momentum: 0.000000
121
+ 2023-10-17 09:23:10,024 epoch 4 - iter 616/1546 - loss 0.03878561 - time (sec): 49.79 - samples/sec: 1004.29 - lr: 0.000037 - momentum: 0.000000
122
+ 2023-10-17 09:23:22,388 epoch 4 - iter 770/1546 - loss 0.03865470 - time (sec): 62.15 - samples/sec: 1004.24 - lr: 0.000036 - momentum: 0.000000
123
+ 2023-10-17 09:23:35,333 epoch 4 - iter 924/1546 - loss 0.04069375 - time (sec): 75.10 - samples/sec: 1002.81 - lr: 0.000036 - momentum: 0.000000
124
+ 2023-10-17 09:23:47,453 epoch 4 - iter 1078/1546 - loss 0.04126939 - time (sec): 87.22 - samples/sec: 1009.12 - lr: 0.000035 - momentum: 0.000000
125
+ 2023-10-17 09:24:00,928 epoch 4 - iter 1232/1546 - loss 0.04052158 - time (sec): 100.69 - samples/sec: 990.16 - lr: 0.000034 - momentum: 0.000000
126
+ 2023-10-17 09:24:13,374 epoch 4 - iter 1386/1546 - loss 0.04157212 - time (sec): 113.14 - samples/sec: 985.57 - lr: 0.000034 - momentum: 0.000000
127
+ 2023-10-17 09:24:25,720 epoch 4 - iter 1540/1546 - loss 0.04184639 - time (sec): 125.49 - samples/sec: 987.77 - lr: 0.000033 - momentum: 0.000000
128
+ 2023-10-17 09:24:26,182 ----------------------------------------------------------------------------------------------------
129
+ 2023-10-17 09:24:26,182 EPOCH 4 done: loss 0.0420 - lr: 0.000033
130
+ 2023-10-17 09:24:29,002 DEV : loss 0.08950287848711014 - f1-score (micro avg) 0.7621
131
+ 2023-10-17 09:24:29,033 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-17 09:24:40,952 epoch 5 - iter 154/1546 - loss 0.03009039 - time (sec): 11.92 - samples/sec: 995.54 - lr: 0.000033 - momentum: 0.000000
133
+ 2023-10-17 09:24:52,812 epoch 5 - iter 308/1546 - loss 0.02873435 - time (sec): 23.78 - samples/sec: 1021.53 - lr: 0.000032 - momentum: 0.000000
134
+ 2023-10-17 09:25:04,892 epoch 5 - iter 462/1546 - loss 0.02553030 - time (sec): 35.86 - samples/sec: 1008.65 - lr: 0.000032 - momentum: 0.000000
135
+ 2023-10-17 09:25:16,887 epoch 5 - iter 616/1546 - loss 0.02718396 - time (sec): 47.85 - samples/sec: 1011.63 - lr: 0.000031 - momentum: 0.000000
136
+ 2023-10-17 09:25:28,726 epoch 5 - iter 770/1546 - loss 0.03075938 - time (sec): 59.69 - samples/sec: 1028.39 - lr: 0.000031 - momentum: 0.000000
137
+ 2023-10-17 09:25:40,497 epoch 5 - iter 924/1546 - loss 0.02980085 - time (sec): 71.46 - samples/sec: 1035.53 - lr: 0.000030 - momentum: 0.000000
138
+ 2023-10-17 09:25:52,316 epoch 5 - iter 1078/1546 - loss 0.02958354 - time (sec): 83.28 - samples/sec: 1038.68 - lr: 0.000029 - momentum: 0.000000
139
+ 2023-10-17 09:26:04,188 epoch 5 - iter 1232/1546 - loss 0.03071438 - time (sec): 95.15 - samples/sec: 1036.96 - lr: 0.000029 - momentum: 0.000000
140
+ 2023-10-17 09:26:16,141 epoch 5 - iter 1386/1546 - loss 0.03065998 - time (sec): 107.11 - samples/sec: 1044.83 - lr: 0.000028 - momentum: 0.000000
141
+ 2023-10-17 09:26:27,952 epoch 5 - iter 1540/1546 - loss 0.03163804 - time (sec): 118.92 - samples/sec: 1040.63 - lr: 0.000028 - momentum: 0.000000
142
+ 2023-10-17 09:26:28,420 ----------------------------------------------------------------------------------------------------
143
+ 2023-10-17 09:26:28,421 EPOCH 5 done: loss 0.0318 - lr: 0.000028
144
+ 2023-10-17 09:26:31,249 DEV : loss 0.09248381108045578 - f1-score (micro avg) 0.7826
145
+ 2023-10-17 09:26:31,276 saving best model
146
+ 2023-10-17 09:26:32,670 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-17 09:26:44,458 epoch 6 - iter 154/1546 - loss 0.01744772 - time (sec): 11.78 - samples/sec: 1088.41 - lr: 0.000027 - momentum: 0.000000
148
+ 2023-10-17 09:26:56,154 epoch 6 - iter 308/1546 - loss 0.01475739 - time (sec): 23.48 - samples/sec: 1096.15 - lr: 0.000027 - momentum: 0.000000
149
+ 2023-10-17 09:27:07,914 epoch 6 - iter 462/1546 - loss 0.01645344 - time (sec): 35.24 - samples/sec: 1079.04 - lr: 0.000026 - momentum: 0.000000
150
+ 2023-10-17 09:27:20,358 epoch 6 - iter 616/1546 - loss 0.01806831 - time (sec): 47.68 - samples/sec: 1060.34 - lr: 0.000026 - momentum: 0.000000
151
+ 2023-10-17 09:27:32,424 epoch 6 - iter 770/1546 - loss 0.01828414 - time (sec): 59.75 - samples/sec: 1063.31 - lr: 0.000025 - momentum: 0.000000
152
+ 2023-10-17 09:27:44,726 epoch 6 - iter 924/1546 - loss 0.01867124 - time (sec): 72.05 - samples/sec: 1042.82 - lr: 0.000024 - momentum: 0.000000
153
+ 2023-10-17 09:27:57,290 epoch 6 - iter 1078/1546 - loss 0.02286106 - time (sec): 84.62 - samples/sec: 1027.03 - lr: 0.000024 - momentum: 0.000000
154
+ 2023-10-17 09:28:09,420 epoch 6 - iter 1232/1546 - loss 0.02306730 - time (sec): 96.75 - samples/sec: 1020.36 - lr: 0.000023 - momentum: 0.000000
155
+ 2023-10-17 09:28:21,749 epoch 6 - iter 1386/1546 - loss 0.02425800 - time (sec): 109.08 - samples/sec: 1020.97 - lr: 0.000023 - momentum: 0.000000
156
+ 2023-10-17 09:28:34,208 epoch 6 - iter 1540/1546 - loss 0.02438160 - time (sec): 121.53 - samples/sec: 1019.32 - lr: 0.000022 - momentum: 0.000000
157
+ 2023-10-17 09:28:34,701 ----------------------------------------------------------------------------------------------------
158
+ 2023-10-17 09:28:34,701 EPOCH 6 done: loss 0.0243 - lr: 0.000022
159
+ 2023-10-17 09:28:37,708 DEV : loss 0.11331269890069962 - f1-score (micro avg) 0.7824
160
+ 2023-10-17 09:28:37,738 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-17 09:28:49,752 epoch 7 - iter 154/1546 - loss 0.00853625 - time (sec): 12.01 - samples/sec: 975.35 - lr: 0.000022 - momentum: 0.000000
162
+ 2023-10-17 09:29:02,437 epoch 7 - iter 308/1546 - loss 0.01700246 - time (sec): 24.70 - samples/sec: 961.02 - lr: 0.000021 - momentum: 0.000000
163
+ 2023-10-17 09:29:14,092 epoch 7 - iter 462/1546 - loss 0.01549663 - time (sec): 36.35 - samples/sec: 996.68 - lr: 0.000021 - momentum: 0.000000
164
+ 2023-10-17 09:29:25,932 epoch 7 - iter 616/1546 - loss 0.01582650 - time (sec): 48.19 - samples/sec: 1015.55 - lr: 0.000020 - momentum: 0.000000
165
+ 2023-10-17 09:29:37,848 epoch 7 - iter 770/1546 - loss 0.01646521 - time (sec): 60.11 - samples/sec: 1024.53 - lr: 0.000019 - momentum: 0.000000
166
+ 2023-10-17 09:29:49,378 epoch 7 - iter 924/1546 - loss 0.01629401 - time (sec): 71.64 - samples/sec: 1031.99 - lr: 0.000019 - momentum: 0.000000
167
+ 2023-10-17 09:30:00,738 epoch 7 - iter 1078/1546 - loss 0.01679182 - time (sec): 83.00 - samples/sec: 1035.90 - lr: 0.000018 - momentum: 0.000000
168
+ 2023-10-17 09:30:13,015 epoch 7 - iter 1232/1546 - loss 0.01625462 - time (sec): 95.27 - samples/sec: 1039.96 - lr: 0.000018 - momentum: 0.000000
169
+ 2023-10-17 09:30:24,972 epoch 7 - iter 1386/1546 - loss 0.01691603 - time (sec): 107.23 - samples/sec: 1043.25 - lr: 0.000017 - momentum: 0.000000
170
+ 2023-10-17 09:30:36,848 epoch 7 - iter 1540/1546 - loss 0.01710851 - time (sec): 119.11 - samples/sec: 1038.46 - lr: 0.000017 - momentum: 0.000000
171
+ 2023-10-17 09:30:37,317 ----------------------------------------------------------------------------------------------------
172
+ 2023-10-17 09:30:37,317 EPOCH 7 done: loss 0.0171 - lr: 0.000017
173
+ 2023-10-17 09:30:40,138 DEV : loss 0.10292882472276688 - f1-score (micro avg) 0.7967
174
+ 2023-10-17 09:30:40,166 saving best model
175
+ 2023-10-17 09:30:41,561 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-17 09:30:53,628 epoch 8 - iter 154/1546 - loss 0.00897999 - time (sec): 12.06 - samples/sec: 1026.13 - lr: 0.000016 - momentum: 0.000000
177
+ 2023-10-17 09:31:06,246 epoch 8 - iter 308/1546 - loss 0.00679301 - time (sec): 24.68 - samples/sec: 1023.58 - lr: 0.000016 - momentum: 0.000000
178
+ 2023-10-17 09:31:18,239 epoch 8 - iter 462/1546 - loss 0.00873332 - time (sec): 36.67 - samples/sec: 1018.98 - lr: 0.000015 - momentum: 0.000000
179
+ 2023-10-17 09:31:30,487 epoch 8 - iter 616/1546 - loss 0.00762723 - time (sec): 48.92 - samples/sec: 1011.60 - lr: 0.000014 - momentum: 0.000000
180
+ 2023-10-17 09:31:42,740 epoch 8 - iter 770/1546 - loss 0.00715001 - time (sec): 61.17 - samples/sec: 1005.54 - lr: 0.000014 - momentum: 0.000000
181
+ 2023-10-17 09:31:54,758 epoch 8 - iter 924/1546 - loss 0.00780939 - time (sec): 73.19 - samples/sec: 1020.03 - lr: 0.000013 - momentum: 0.000000
182
+ 2023-10-17 09:32:06,777 epoch 8 - iter 1078/1546 - loss 0.00748800 - time (sec): 85.21 - samples/sec: 1028.26 - lr: 0.000013 - momentum: 0.000000
183
+ 2023-10-17 09:32:18,870 epoch 8 - iter 1232/1546 - loss 0.00779496 - time (sec): 97.31 - samples/sec: 1022.41 - lr: 0.000012 - momentum: 0.000000
184
+ 2023-10-17 09:32:30,904 epoch 8 - iter 1386/1546 - loss 0.00808887 - time (sec): 109.34 - samples/sec: 1014.93 - lr: 0.000012 - momentum: 0.000000
185
+ 2023-10-17 09:32:42,904 epoch 8 - iter 1540/1546 - loss 0.00813670 - time (sec): 121.34 - samples/sec: 1021.43 - lr: 0.000011 - momentum: 0.000000
186
+ 2023-10-17 09:32:43,372 ----------------------------------------------------------------------------------------------------
187
+ 2023-10-17 09:32:43,372 EPOCH 8 done: loss 0.0081 - lr: 0.000011
188
+ 2023-10-17 09:32:46,130 DEV : loss 0.14049740135669708 - f1-score (micro avg) 0.767
189
+ 2023-10-17 09:32:46,160 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-17 09:32:58,264 epoch 9 - iter 154/1546 - loss 0.00309967 - time (sec): 12.10 - samples/sec: 1041.71 - lr: 0.000011 - momentum: 0.000000
191
+ 2023-10-17 09:33:10,247 epoch 9 - iter 308/1546 - loss 0.00466253 - time (sec): 24.08 - samples/sec: 1018.41 - lr: 0.000010 - momentum: 0.000000
192
+ 2023-10-17 09:33:22,003 epoch 9 - iter 462/1546 - loss 0.00679552 - time (sec): 35.84 - samples/sec: 1043.56 - lr: 0.000009 - momentum: 0.000000
193
+ 2023-10-17 09:33:33,721 epoch 9 - iter 616/1546 - loss 0.00701922 - time (sec): 47.56 - samples/sec: 1033.03 - lr: 0.000009 - momentum: 0.000000
194
+ 2023-10-17 09:33:45,568 epoch 9 - iter 770/1546 - loss 0.00656941 - time (sec): 59.41 - samples/sec: 1041.79 - lr: 0.000008 - momentum: 0.000000
195
+ 2023-10-17 09:33:58,097 epoch 9 - iter 924/1546 - loss 0.00655801 - time (sec): 71.94 - samples/sec: 1028.82 - lr: 0.000008 - momentum: 0.000000
196
+ 2023-10-17 09:34:10,150 epoch 9 - iter 1078/1546 - loss 0.00604590 - time (sec): 83.99 - samples/sec: 1034.54 - lr: 0.000007 - momentum: 0.000000
197
+ 2023-10-17 09:34:22,061 epoch 9 - iter 1232/1546 - loss 0.00650962 - time (sec): 95.90 - samples/sec: 1032.50 - lr: 0.000007 - momentum: 0.000000
198
+ 2023-10-17 09:34:34,171 epoch 9 - iter 1386/1546 - loss 0.00605757 - time (sec): 108.01 - samples/sec: 1039.92 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-17 09:34:46,499 epoch 9 - iter 1540/1546 - loss 0.00602743 - time (sec): 120.34 - samples/sec: 1028.93 - lr: 0.000006 - momentum: 0.000000
200
+ 2023-10-17 09:34:46,985 ----------------------------------------------------------------------------------------------------
201
+ 2023-10-17 09:34:46,985 EPOCH 9 done: loss 0.0060 - lr: 0.000006
202
+ 2023-10-17 09:34:49,926 DEV : loss 0.12698261439800262 - f1-score (micro avg) 0.8032
203
+ 2023-10-17 09:34:49,956 saving best model
204
+ 2023-10-17 09:34:51,408 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-17 09:35:04,024 epoch 10 - iter 154/1546 - loss 0.00737061 - time (sec): 12.61 - samples/sec: 992.85 - lr: 0.000005 - momentum: 0.000000
206
+ 2023-10-17 09:35:16,144 epoch 10 - iter 308/1546 - loss 0.00570858 - time (sec): 24.73 - samples/sec: 1002.41 - lr: 0.000004 - momentum: 0.000000
207
+ 2023-10-17 09:35:28,174 epoch 10 - iter 462/1546 - loss 0.00405368 - time (sec): 36.76 - samples/sec: 1029.47 - lr: 0.000004 - momentum: 0.000000
208
+ 2023-10-17 09:35:39,730 epoch 10 - iter 616/1546 - loss 0.00351886 - time (sec): 48.32 - samples/sec: 1040.18 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-17 09:35:51,440 epoch 10 - iter 770/1546 - loss 0.00343175 - time (sec): 60.03 - samples/sec: 1041.22 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-17 09:36:03,143 epoch 10 - iter 924/1546 - loss 0.00370004 - time (sec): 71.73 - samples/sec: 1034.86 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-17 09:36:14,990 epoch 10 - iter 1078/1546 - loss 0.00352942 - time (sec): 83.58 - samples/sec: 1041.32 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-17 09:36:26,661 epoch 10 - iter 1232/1546 - loss 0.00371630 - time (sec): 95.25 - samples/sec: 1037.65 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-17 09:36:38,732 epoch 10 - iter 1386/1546 - loss 0.00370365 - time (sec): 107.32 - samples/sec: 1038.39 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-17 09:36:51,551 epoch 10 - iter 1540/1546 - loss 0.00357901 - time (sec): 120.14 - samples/sec: 1030.81 - lr: 0.000000 - momentum: 0.000000
215
+ 2023-10-17 09:36:52,006 ----------------------------------------------------------------------------------------------------
216
+ 2023-10-17 09:36:52,006 EPOCH 10 done: loss 0.0036 - lr: 0.000000
217
+ 2023-10-17 09:36:54,823 DEV : loss 0.12681032717227936 - f1-score (micro avg) 0.8109
218
+ 2023-10-17 09:36:54,853 saving best model
219
+ 2023-10-17 09:36:56,978 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-17 09:36:56,980 Loading model from best epoch ...
221
+ 2023-10-17 09:36:59,153 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
222
+ 2023-10-17 09:37:07,160
223
+ Results:
224
+ - F-score (micro) 0.8205
225
+ - F-score (macro) 0.7279
226
+ - Accuracy 0.7179
227
+
228
+ By class:
229
+ precision recall f1-score support
230
+
231
+ LOC 0.8723 0.8594 0.8658 946
232
+ BUILDING 0.6404 0.6162 0.6281 185
233
+ STREET 0.6667 0.7143 0.6897 56
234
+
235
+ micro avg 0.8265 0.8147 0.8205 1187
236
+ macro avg 0.7265 0.7300 0.7279 1187
237
+ weighted avg 0.8265 0.8147 0.8205 1187
238
+
239
+ 2023-10-17 09:37:07,160 ----------------------------------------------------------------------------------------------------