Hugging Face's logo

stefan-it
/
hmbench-topres19th-en-hmbert-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2

Token Classification
Flair
PyTorch
English
sequence-tagger-model
Model card Files Community
stefan-it commited on
Commit
977b2c5
•
1 Parent(s): 86140d8

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. test.tsv +0 -0
  5. training.log +240 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1d72fe7f66eb01c532db304769b33c955a18b24567e391c697c0ec53da90fa1
3
+ size 443311175
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 22:05:49 0.0000 0.3208 0.0772 0.5804 0.7764 0.6643 0.5111
3
+ 2 22:06:37 0.0000 0.0773 0.0681 0.6203 0.8270 0.7089 0.5632
4
+ 3 22:07:26 0.0000 0.0508 0.0806 0.7452 0.8270 0.7840 0.6577
5
+ 4 22:08:14 0.0000 0.0373 0.0884 0.7371 0.7806 0.7582 0.6271
6
+ 5 22:09:02 0.0000 0.0239 0.1016 0.7602 0.7890 0.7743 0.6493
7
+ 6 22:09:49 0.0000 0.0182 0.1044 0.7965 0.7764 0.7863 0.6619
8
+ 7 22:10:37 0.0000 0.0109 0.1095 0.7950 0.8017 0.7983 0.6786
9
+ 8 22:11:25 0.0000 0.0082 0.1185 0.7677 0.8228 0.7943 0.6655
10
+ 9 22:12:12 0.0000 0.0049 0.1191 0.7746 0.7975 0.7859 0.6585
11
+ 10 22:13:00 0.0000 0.0029 0.1210 0.7815 0.7848 0.7832 0.6572
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-16 22:05:02,568 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-16 22:05:02,569 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
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): 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
+ 2023-10-16 22:05:02,569 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-16 22:05:02,569 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
+ 2023-10-16 22:05:02,569 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-16 22:05:02,569 Train: 6183 sentences
55
+ 2023-10-16 22:05:02,569 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-16 22:05:02,569 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-16 22:05:02,569 Training Params:
58
+ 2023-10-16 22:05:02,569 - learning_rate: "5e-05"
59
+ 2023-10-16 22:05:02,569 - mini_batch_size: "8"
60
+ 2023-10-16 22:05:02,569 - max_epochs: "10"
61
+ 2023-10-16 22:05:02,569 - shuffle: "True"
62
+ 2023-10-16 22:05:02,569 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-16 22:05:02,569 Plugins:
64
+ 2023-10-16 22:05:02,569 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-16 22:05:02,569 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-16 22:05:02,570 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-16 22:05:02,570 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-16 22:05:02,570 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-16 22:05:02,570 Computation:
70
+ 2023-10-16 22:05:02,570 - compute on device: cuda:0
71
+ 2023-10-16 22:05:02,570 - embedding storage: none
72
+ 2023-10-16 22:05:02,570 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-16 22:05:02,570 Model training base path: "hmbench-topres19th/en-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2"
74
+ 2023-10-16 22:05:02,570 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-16 22:05:02,570 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-16 22:05:07,108 epoch 1 - iter 77/773 - loss 2.07744315 - time (sec): 4.54 - samples/sec: 2610.32 - lr: 0.000005 - momentum: 0.000000
77
+ 2023-10-16 22:05:11,553 epoch 1 - iter 154/773 - loss 1.17743079 - time (sec): 8.98 - samples/sec: 2642.75 - lr: 0.000010 - momentum: 0.000000
78
+ 2023-10-16 22:05:16,195 epoch 1 - iter 231/773 - loss 0.80857450 - time (sec): 13.62 - samples/sec: 2721.79 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-16 22:05:20,634 epoch 1 - iter 308/773 - loss 0.64594888 - time (sec): 18.06 - samples/sec: 2721.06 - lr: 0.000020 - momentum: 0.000000
80
+ 2023-10-16 22:05:25,021 epoch 1 - iter 385/773 - loss 0.54443571 - time (sec): 22.45 - samples/sec: 2715.07 - lr: 0.000025 - momentum: 0.000000
81
+ 2023-10-16 22:05:29,309 epoch 1 - iter 462/773 - loss 0.47012773 - time (sec): 26.74 - samples/sec: 2734.10 - lr: 0.000030 - momentum: 0.000000
82
+ 2023-10-16 22:05:33,752 epoch 1 - iter 539/773 - loss 0.41651204 - time (sec): 31.18 - samples/sec: 2757.19 - lr: 0.000035 - momentum: 0.000000
83
+ 2023-10-16 22:05:38,386 epoch 1 - iter 616/773 - loss 0.37671127 - time (sec): 35.82 - samples/sec: 2773.34 - lr: 0.000040 - momentum: 0.000000
84
+ 2023-10-16 22:05:43,095 epoch 1 - iter 693/773 - loss 0.34712982 - time (sec): 40.52 - samples/sec: 2743.12 - lr: 0.000045 - momentum: 0.000000
85
+ 2023-10-16 22:05:47,514 epoch 1 - iter 770/773 - loss 0.32154236 - time (sec): 44.94 - samples/sec: 2757.20 - lr: 0.000050 - momentum: 0.000000
86
+ 2023-10-16 22:05:47,670 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-16 22:05:47,670 EPOCH 1 done: loss 0.3208 - lr: 0.000050
88
+ 2023-10-16 22:05:49,710 DEV : loss 0.0772036612033844 - f1-score (micro avg) 0.6643
89
+ 2023-10-16 22:05:49,722 saving best model
90
+ 2023-10-16 22:05:50,064 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-16 22:05:54,575 epoch 2 - iter 77/773 - loss 0.07753873 - time (sec): 4.51 - samples/sec: 2686.50 - lr: 0.000049 - momentum: 0.000000
92
+ 2023-10-16 22:05:58,993 epoch 2 - iter 154/773 - loss 0.08814964 - time (sec): 8.93 - samples/sec: 2682.41 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-16 22:06:03,719 epoch 2 - iter 231/773 - loss 0.08367414 - time (sec): 13.65 - samples/sec: 2695.54 - lr: 0.000048 - momentum: 0.000000
94
+ 2023-10-16 22:06:08,199 epoch 2 - iter 308/773 - loss 0.08164912 - time (sec): 18.13 - samples/sec: 2694.67 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-16 22:06:12,828 epoch 2 - iter 385/773 - loss 0.08321751 - time (sec): 22.76 - samples/sec: 2705.47 - lr: 0.000047 - momentum: 0.000000
96
+ 2023-10-16 22:06:17,450 epoch 2 - iter 462/773 - loss 0.08271449 - time (sec): 27.38 - samples/sec: 2672.02 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-16 22:06:22,030 epoch 2 - iter 539/773 - loss 0.08056035 - time (sec): 31.96 - samples/sec: 2676.73 - lr: 0.000046 - momentum: 0.000000
98
+ 2023-10-16 22:06:26,558 epoch 2 - iter 616/773 - loss 0.08048201 - time (sec): 36.49 - samples/sec: 2680.20 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-16 22:06:31,001 epoch 2 - iter 693/773 - loss 0.07801088 - time (sec): 40.94 - samples/sec: 2693.49 - lr: 0.000045 - momentum: 0.000000
100
+ 2023-10-16 22:06:35,711 epoch 2 - iter 770/773 - loss 0.07752429 - time (sec): 45.65 - samples/sec: 2713.00 - lr: 0.000044 - momentum: 0.000000
101
+ 2023-10-16 22:06:35,870 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-16 22:06:35,870 EPOCH 2 done: loss 0.0773 - lr: 0.000044
103
+ 2023-10-16 22:06:37,935 DEV : loss 0.06809011846780777 - f1-score (micro avg) 0.7089
104
+ 2023-10-16 22:06:37,947 saving best model
105
+ 2023-10-16 22:06:38,714 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-16 22:06:43,428 epoch 3 - iter 77/773 - loss 0.05164133 - time (sec): 4.71 - samples/sec: 2719.74 - lr: 0.000044 - momentum: 0.000000
107
+ 2023-10-16 22:06:47,856 epoch 3 - iter 154/773 - loss 0.05614533 - time (sec): 9.14 - samples/sec: 2744.96 - lr: 0.000043 - momentum: 0.000000
108
+ 2023-10-16 22:06:52,660 epoch 3 - iter 231/773 - loss 0.05743499 - time (sec): 13.94 - samples/sec: 2704.33 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-16 22:06:57,007 epoch 3 - iter 308/773 - loss 0.05405146 - time (sec): 18.29 - samples/sec: 2728.43 - lr: 0.000042 - momentum: 0.000000
110
+ 2023-10-16 22:07:01,583 epoch 3 - iter 385/773 - loss 0.05263408 - time (sec): 22.87 - samples/sec: 2735.35 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-16 22:07:06,253 epoch 3 - iter 462/773 - loss 0.05351123 - time (sec): 27.54 - samples/sec: 2719.53 - lr: 0.000041 - momentum: 0.000000
112
+ 2023-10-16 22:07:10,771 epoch 3 - iter 539/773 - loss 0.05305526 - time (sec): 32.05 - samples/sec: 2720.58 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-16 22:07:15,136 epoch 3 - iter 616/773 - loss 0.05227538 - time (sec): 36.42 - samples/sec: 2714.42 - lr: 0.000040 - momentum: 0.000000
114
+ 2023-10-16 22:07:19,672 epoch 3 - iter 693/773 - loss 0.05203641 - time (sec): 40.96 - samples/sec: 2731.14 - lr: 0.000039 - momentum: 0.000000
115
+ 2023-10-16 22:07:24,115 epoch 3 - iter 770/773 - loss 0.05094133 - time (sec): 45.40 - samples/sec: 2730.25 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-16 22:07:24,271 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-16 22:07:24,271 EPOCH 3 done: loss 0.0508 - lr: 0.000039
118
+ 2023-10-16 22:07:26,321 DEV : loss 0.08064333349466324 - f1-score (micro avg) 0.784
119
+ 2023-10-16 22:07:26,333 saving best model
120
+ 2023-10-16 22:07:26,782 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-16 22:07:31,371 epoch 4 - iter 77/773 - loss 0.04532304 - time (sec): 4.59 - samples/sec: 2713.19 - lr: 0.000038 - momentum: 0.000000
122
+ 2023-10-16 22:07:35,796 epoch 4 - iter 154/773 - loss 0.04515752 - time (sec): 9.01 - samples/sec: 2642.61 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-16 22:07:40,584 epoch 4 - iter 231/773 - loss 0.04011628 - time (sec): 13.80 - samples/sec: 2609.12 - lr: 0.000037 - momentum: 0.000000
124
+ 2023-10-16 22:07:45,151 epoch 4 - iter 308/773 - loss 0.03827052 - time (sec): 18.37 - samples/sec: 2625.80 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-16 22:07:49,673 epoch 4 - iter 385/773 - loss 0.03710721 - time (sec): 22.89 - samples/sec: 2663.63 - lr: 0.000036 - momentum: 0.000000
126
+ 2023-10-16 22:07:54,043 epoch 4 - iter 462/773 - loss 0.03902851 - time (sec): 27.26 - samples/sec: 2684.80 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-16 22:07:58,389 epoch 4 - iter 539/773 - loss 0.03842162 - time (sec): 31.60 - samples/sec: 2707.56 - lr: 0.000035 - momentum: 0.000000
128
+ 2023-10-16 22:08:03,155 epoch 4 - iter 616/773 - loss 0.03858095 - time (sec): 36.37 - samples/sec: 2700.81 - lr: 0.000034 - momentum: 0.000000
129
+ 2023-10-16 22:08:07,677 epoch 4 - iter 693/773 - loss 0.03732367 - time (sec): 40.89 - samples/sec: 2711.50 - lr: 0.000034 - momentum: 0.000000
130
+ 2023-10-16 22:08:12,393 epoch 4 - iter 770/773 - loss 0.03734734 - time (sec): 45.61 - samples/sec: 2716.36 - lr: 0.000033 - momentum: 0.000000
131
+ 2023-10-16 22:08:12,558 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-16 22:08:12,558 EPOCH 4 done: loss 0.0373 - lr: 0.000033
133
+ 2023-10-16 22:08:14,643 DEV : loss 0.08836734294891357 - f1-score (micro avg) 0.7582
134
+ 2023-10-16 22:08:14,656 ----------------------------------------------------------------------------------------------------
135
+ 2023-10-16 22:08:19,114 epoch 5 - iter 77/773 - loss 0.02324528 - time (sec): 4.46 - samples/sec: 2818.91 - lr: 0.000033 - momentum: 0.000000
136
+ 2023-10-16 22:08:23,457 epoch 5 - iter 154/773 - loss 0.02467072 - time (sec): 8.80 - samples/sec: 2799.12 - lr: 0.000032 - momentum: 0.000000
137
+ 2023-10-16 22:08:27,881 epoch 5 - iter 231/773 - loss 0.02448679 - time (sec): 13.22 - samples/sec: 2725.54 - lr: 0.000032 - momentum: 0.000000
138
+ 2023-10-16 22:08:32,569 epoch 5 - iter 308/773 - loss 0.02574532 - time (sec): 17.91 - samples/sec: 2746.57 - lr: 0.000031 - momentum: 0.000000
139
+ 2023-10-16 22:08:37,181 epoch 5 - iter 385/773 - loss 0.02467239 - time (sec): 22.52 - samples/sec: 2743.95 - lr: 0.000031 - momentum: 0.000000
140
+ 2023-10-16 22:08:41,801 epoch 5 - iter 462/773 - loss 0.02435955 - time (sec): 27.14 - samples/sec: 2755.55 - lr: 0.000030 - momentum: 0.000000
141
+ 2023-10-16 22:08:46,576 epoch 5 - iter 539/773 - loss 0.02374115 - time (sec): 31.92 - samples/sec: 2740.25 - lr: 0.000029 - momentum: 0.000000
142
+ 2023-10-16 22:08:51,103 epoch 5 - iter 616/773 - loss 0.02505935 - time (sec): 36.45 - samples/sec: 2737.71 - lr: 0.000029 - momentum: 0.000000
143
+ 2023-10-16 22:08:55,524 epoch 5 - iter 693/773 - loss 0.02470818 - time (sec): 40.87 - samples/sec: 2737.62 - lr: 0.000028 - momentum: 0.000000
144
+ 2023-10-16 22:08:59,942 epoch 5 - iter 770/773 - loss 0.02388204 - time (sec): 45.29 - samples/sec: 2736.97 - lr: 0.000028 - momentum: 0.000000
145
+ 2023-10-16 22:09:00,093 ----------------------------------------------------------------------------------------------------
146
+ 2023-10-16 22:09:00,094 EPOCH 5 done: loss 0.0239 - lr: 0.000028
147
+ 2023-10-16 22:09:02,150 DEV : loss 0.10162093490362167 - f1-score (micro avg) 0.7743
148
+ 2023-10-16 22:09:02,163 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-16 22:09:06,579 epoch 6 - iter 77/773 - loss 0.01159246 - time (sec): 4.42 - samples/sec: 2796.00 - lr: 0.000027 - momentum: 0.000000
150
+ 2023-10-16 22:09:11,152 epoch 6 - iter 154/773 - loss 0.01350875 - time (sec): 8.99 - samples/sec: 2651.15 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-16 22:09:15,655 epoch 6 - iter 231/773 - loss 0.01496486 - time (sec): 13.49 - samples/sec: 2665.48 - lr: 0.000026 - momentum: 0.000000
152
+ 2023-10-16 22:09:20,180 epoch 6 - iter 308/773 - loss 0.01695021 - time (sec): 18.02 - samples/sec: 2700.59 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-16 22:09:24,538 epoch 6 - iter 385/773 - loss 0.01737618 - time (sec): 22.37 - samples/sec: 2712.80 - lr: 0.000025 - momentum: 0.000000
154
+ 2023-10-16 22:09:28,871 epoch 6 - iter 462/773 - loss 0.01752556 - time (sec): 26.71 - samples/sec: 2719.44 - lr: 0.000024 - momentum: 0.000000
155
+ 2023-10-16 22:09:33,395 epoch 6 - iter 539/773 - loss 0.01769065 - time (sec): 31.23 - samples/sec: 2719.13 - lr: 0.000024 - momentum: 0.000000
156
+ 2023-10-16 22:09:38,097 epoch 6 - iter 616/773 - loss 0.01836114 - time (sec): 35.93 - samples/sec: 2717.44 - lr: 0.000023 - momentum: 0.000000
157
+ 2023-10-16 22:09:42,421 epoch 6 - iter 693/773 - loss 0.01786052 - time (sec): 40.26 - samples/sec: 2719.08 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-16 22:09:47,260 epoch 6 - iter 770/773 - loss 0.01820946 - time (sec): 45.10 - samples/sec: 2742.13 - lr: 0.000022 - momentum: 0.000000
159
+ 2023-10-16 22:09:47,448 ----------------------------------------------------------------------------------------------------
160
+ 2023-10-16 22:09:47,448 EPOCH 6 done: loss 0.0182 - lr: 0.000022
161
+ 2023-10-16 22:09:49,464 DEV : loss 0.10438579320907593 - f1-score (micro avg) 0.7863
162
+ 2023-10-16 22:09:49,476 saving best model
163
+ 2023-10-16 22:09:49,941 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-16 22:09:54,815 epoch 7 - iter 77/773 - loss 0.01326801 - time (sec): 4.87 - samples/sec: 2596.22 - lr: 0.000022 - momentum: 0.000000
165
+ 2023-10-16 22:09:59,436 epoch 7 - iter 154/773 - loss 0.01133806 - time (sec): 9.49 - samples/sec: 2698.66 - lr: 0.000021 - momentum: 0.000000
166
+ 2023-10-16 22:10:03,998 epoch 7 - iter 231/773 - loss 0.01166043 - time (sec): 14.05 - samples/sec: 2696.24 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-16 22:10:08,505 epoch 7 - iter 308/773 - loss 0.01086055 - time (sec): 18.56 - samples/sec: 2685.92 - lr: 0.000020 - momentum: 0.000000
168
+ 2023-10-16 22:10:13,116 epoch 7 - iter 385/773 - loss 0.01053431 - time (sec): 23.17 - samples/sec: 2692.16 - lr: 0.000019 - momentum: 0.000000
169
+ 2023-10-16 22:10:17,458 epoch 7 - iter 462/773 - loss 0.01175421 - time (sec): 27.51 - samples/sec: 2700.81 - lr: 0.000019 - momentum: 0.000000
170
+ 2023-10-16 22:10:21,786 epoch 7 - iter 539/773 - loss 0.01094026 - time (sec): 31.84 - samples/sec: 2713.28 - lr: 0.000018 - momentum: 0.000000
171
+ 2023-10-16 22:10:26,348 epoch 7 - iter 616/773 - loss 0.01147580 - time (sec): 36.40 - samples/sec: 2708.94 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-16 22:10:30,934 epoch 7 - iter 693/773 - loss 0.01097587 - time (sec): 40.99 - samples/sec: 2718.33 - lr: 0.000017 - momentum: 0.000000
173
+ 2023-10-16 22:10:35,494 epoch 7 - iter 770/773 - loss 0.01075542 - time (sec): 45.55 - samples/sec: 2719.57 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-16 22:10:35,663 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-16 22:10:35,663 EPOCH 7 done: loss 0.0109 - lr: 0.000017
176
+ 2023-10-16 22:10:37,719 DEV : loss 0.10951930284500122 - f1-score (micro avg) 0.7983
177
+ 2023-10-16 22:10:37,731 saving best model
178
+ 2023-10-16 22:10:38,198 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-16 22:10:42,724 epoch 8 - iter 77/773 - loss 0.00728149 - time (sec): 4.52 - samples/sec: 2766.74 - lr: 0.000016 - momentum: 0.000000
180
+ 2023-10-16 22:10:47,351 epoch 8 - iter 154/773 - loss 0.00617068 - time (sec): 9.15 - samples/sec: 2771.20 - lr: 0.000016 - momentum: 0.000000
181
+ 2023-10-16 22:10:51,639 epoch 8 - iter 231/773 - loss 0.00654267 - time (sec): 13.44 - samples/sec: 2812.34 - lr: 0.000015 - momentum: 0.000000
182
+ 2023-10-16 22:10:56,231 epoch 8 - iter 308/773 - loss 0.00737351 - time (sec): 18.03 - samples/sec: 2828.58 - lr: 0.000014 - momentum: 0.000000
183
+ 2023-10-16 22:11:00,609 epoch 8 - iter 385/773 - loss 0.00732684 - time (sec): 22.41 - samples/sec: 2793.63 - lr: 0.000014 - momentum: 0.000000
184
+ 2023-10-16 22:11:05,075 epoch 8 - iter 462/773 - loss 0.00803301 - time (sec): 26.88 - samples/sec: 2785.65 - lr: 0.000013 - momentum: 0.000000
185
+ 2023-10-16 22:11:09,435 epoch 8 - iter 539/773 - loss 0.00840404 - time (sec): 31.24 - samples/sec: 2780.54 - lr: 0.000013 - momentum: 0.000000
186
+ 2023-10-16 22:11:13,860 epoch 8 - iter 616/773 - loss 0.00808847 - time (sec): 35.66 - samples/sec: 2772.46 - lr: 0.000012 - momentum: 0.000000
187
+ 2023-10-16 22:11:18,291 epoch 8 - iter 693/773 - loss 0.00861262 - time (sec): 40.09 - samples/sec: 2766.77 - lr: 0.000012 - momentum: 0.000000
188
+ 2023-10-16 22:11:23,147 epoch 8 - iter 770/773 - loss 0.00822302 - time (sec): 44.95 - samples/sec: 2756.21 - lr: 0.000011 - momentum: 0.000000
189
+ 2023-10-16 22:11:23,327 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-16 22:11:23,327 EPOCH 8 done: loss 0.0082 - lr: 0.000011
191
+ 2023-10-16 22:11:25,361 DEV : loss 0.11846552044153214 - f1-score (micro avg) 0.7943
192
+ 2023-10-16 22:11:25,374 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-16 22:11:30,050 epoch 9 - iter 77/773 - loss 0.00433896 - time (sec): 4.67 - samples/sec: 2677.26 - lr: 0.000011 - momentum: 0.000000
194
+ 2023-10-16 22:11:34,429 epoch 9 - iter 154/773 - loss 0.00498112 - time (sec): 9.05 - samples/sec: 2697.81 - lr: 0.000010 - momentum: 0.000000
195
+ 2023-10-16 22:11:38,833 epoch 9 - iter 231/773 - loss 0.00373937 - time (sec): 13.46 - samples/sec: 2717.39 - lr: 0.000009 - momentum: 0.000000
196
+ 2023-10-16 22:11:43,181 epoch 9 - iter 308/773 - loss 0.00412343 - time (sec): 17.81 - samples/sec: 2732.31 - lr: 0.000009 - momentum: 0.000000
197
+ 2023-10-16 22:11:47,729 epoch 9 - iter 385/773 - loss 0.00375047 - time (sec): 22.35 - samples/sec: 2718.05 - lr: 0.000008 - momentum: 0.000000
198
+ 2023-10-16 22:11:52,475 epoch 9 - iter 462/773 - loss 0.00369782 - time (sec): 27.10 - samples/sec: 2717.22 - lr: 0.000008 - momentum: 0.000000
199
+ 2023-10-16 22:11:56,947 epoch 9 - iter 539/773 - loss 0.00383622 - time (sec): 31.57 - samples/sec: 2733.87 - lr: 0.000007 - momentum: 0.000000
200
+ 2023-10-16 22:12:01,471 epoch 9 - iter 616/773 - loss 0.00413650 - time (sec): 36.10 - samples/sec: 2732.35 - lr: 0.000007 - momentum: 0.000000
201
+ 2023-10-16 22:12:05,987 epoch 9 - iter 693/773 - loss 0.00456700 - time (sec): 40.61 - samples/sec: 2740.68 - lr: 0.000006 - momentum: 0.000000
202
+ 2023-10-16 22:12:10,465 epoch 9 - iter 770/773 - loss 0.00488437 - time (sec): 45.09 - samples/sec: 2749.39 - lr: 0.000006 - momentum: 0.000000
203
+ 2023-10-16 22:12:10,633 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-16 22:12:10,634 EPOCH 9 done: loss 0.0049 - lr: 0.000006
205
+ 2023-10-16 22:12:12,648 DEV : loss 0.11912991851568222 - f1-score (micro avg) 0.7859
206
+ 2023-10-16 22:12:12,661 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-16 22:12:17,152 epoch 10 - iter 77/773 - loss 0.00307045 - time (sec): 4.49 - samples/sec: 2767.84 - lr: 0.000005 - momentum: 0.000000
208
+ 2023-10-16 22:12:21,594 epoch 10 - iter 154/773 - loss 0.00429958 - time (sec): 8.93 - samples/sec: 2791.36 - lr: 0.000005 - momentum: 0.000000
209
+ 2023-10-16 22:12:26,080 epoch 10 - iter 231/773 - loss 0.00374969 - time (sec): 13.42 - samples/sec: 2745.64 - lr: 0.000004 - momentum: 0.000000
210
+ 2023-10-16 22:12:30,759 epoch 10 - iter 308/773 - loss 0.00293141 - time (sec): 18.10 - samples/sec: 2763.47 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-16 22:12:35,215 epoch 10 - iter 385/773 - loss 0.00303829 - time (sec): 22.55 - samples/sec: 2752.65 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-16 22:12:39,757 epoch 10 - iter 462/773 - loss 0.00299411 - time (sec): 27.09 - samples/sec: 2766.56 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-16 22:12:44,528 epoch 10 - iter 539/773 - loss 0.00315115 - time (sec): 31.87 - samples/sec: 2730.07 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-16 22:12:48,932 epoch 10 - iter 616/773 - loss 0.00309341 - time (sec): 36.27 - samples/sec: 2742.38 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-16 22:12:53,383 epoch 10 - iter 693/773 - loss 0.00291500 - time (sec): 40.72 - samples/sec: 2734.97 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-16 22:12:57,938 epoch 10 - iter 770/773 - loss 0.00293636 - time (sec): 45.28 - samples/sec: 2730.69 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-16 22:12:58,116 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-16 22:12:58,116 EPOCH 10 done: loss 0.0029 - lr: 0.000000
219
+ 2023-10-16 22:13:00,131 DEV : loss 0.12098120898008347 - f1-score (micro avg) 0.7832
220
+ 2023-10-16 22:13:00,473 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-16 22:13:00,475 Loading model from best epoch ...
222
+ 2023-10-16 22:13:01,959 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
+ 2023-10-16 22:13:07,934
224
+ Results:
225
+ - F-score (micro) 0.8009
226
+ - F-score (macro) 0.6968
227
+ - Accuracy 0.6881
228
+
229
+ By class:
230
+ precision recall f1-score support
231
+
232
+ LOC 0.8549 0.8531 0.8540 946
233
+ BUILDING 0.6000 0.4703 0.5273 185
234
+ STREET 0.7222 0.6964 0.7091 56
235
+
236
+ micro avg 0.8163 0.7860 0.8009 1187
237
+ macro avg 0.7257 0.6733 0.6968 1187
238
+ weighted avg 0.8089 0.7860 0.7962 1187
239
+
240
+ 2023-10-16 22:13:07,935 ----------------------------------------------------------------------------------------------------