Hugging Face's logo

stefan-it
/
hmbench-topres19th-en-hmbert-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5

Token Classification
Flair
PyTorch
English
sequence-tagger-model
Model card Files Community
stefan-it commited on
Commit
a722b28
·
1 Parent(s): 03b28b2

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 sha256:5965b72e4cb2c5bf3a0e800edd586fdc2dcaff3750d86e2b1c65f420f3cbed83
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 00:11:33 0.0000 0.3293 0.0597 0.7119 0.7300 0.7208 0.5864
3
+ 2 00:12:21 0.0000 0.0805 0.0636 0.7164 0.8312 0.7695 0.6314
4
+ 3 00:13:09 0.0000 0.0491 0.0740 0.6899 0.8354 0.7557 0.6168
5
+ 4 00:13:57 0.0000 0.0369 0.0950 0.7835 0.7637 0.7735 0.6464
6
+ 5 00:14:44 0.0000 0.0267 0.0898 0.7452 0.8143 0.7782 0.6498
7
+ 6 00:15:32 0.0000 0.0182 0.1050 0.7610 0.8059 0.7828 0.6609
8
+ 7 00:16:20 0.0000 0.0129 0.1137 0.7316 0.8397 0.7819 0.6568
9
+ 8 00:17:08 0.0000 0.0104 0.1139 0.7358 0.8228 0.7769 0.6522
10
+ 9 00:17:56 0.0000 0.0065 0.1205 0.7683 0.7975 0.7826 0.6632
11
+ 10 00:18:43 0.0000 0.0046 0.1188 0.7500 0.8101 0.7789 0.6575
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 00:10:46,564 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 00:10:46,565 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
+ 2023-10-17 00:10:46,565 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-17 00:10:46,565 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
+ 2023-10-17 00:10:46,565 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-17 00:10:46,565 Train: 6183 sentences
55
+ 2023-10-17 00:10:46,565 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-17 00:10:46,565 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-17 00:10:46,565 Training Params:
58
+ 2023-10-17 00:10:46,565 - learning_rate: "5e-05"
59
+ 2023-10-17 00:10:46,565 - mini_batch_size: "8"
60
+ 2023-10-17 00:10:46,565 - max_epochs: "10"
61
+ 2023-10-17 00:10:46,565 - shuffle: "True"
62
+ 2023-10-17 00:10:46,566 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 00:10:46,566 Plugins:
64
+ 2023-10-17 00:10:46,566 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-17 00:10:46,566 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 00:10:46,566 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-17 00:10:46,566 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-17 00:10:46,566 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-17 00:10:46,566 Computation:
70
+ 2023-10-17 00:10:46,566 - compute on device: cuda:0
71
+ 2023-10-17 00:10:46,566 - embedding storage: none
72
+ 2023-10-17 00:10:46,566 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 00:10:46,566 Model training base path: "hmbench-topres19th/en-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
74
+ 2023-10-17 00:10:46,566 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-17 00:10:46,566 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-17 00:10:51,045 epoch 1 - iter 77/773 - loss 2.01913050 - time (sec): 4.48 - samples/sec: 2875.44 - lr: 0.000005 - momentum: 0.000000
77
+ 2023-10-17 00:10:55,420 epoch 1 - iter 154/773 - loss 1.15152095 - time (sec): 8.85 - samples/sec: 2881.70 - lr: 0.000010 - momentum: 0.000000
78
+ 2023-10-17 00:10:59,884 epoch 1 - iter 231/773 - loss 0.83359397 - time (sec): 13.32 - samples/sec: 2834.07 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-17 00:11:04,318 epoch 1 - iter 308/773 - loss 0.66484530 - time (sec): 17.75 - samples/sec: 2812.38 - lr: 0.000020 - momentum: 0.000000
80
+ 2023-10-17 00:11:08,928 epoch 1 - iter 385/773 - loss 0.55488029 - time (sec): 22.36 - samples/sec: 2796.56 - lr: 0.000025 - momentum: 0.000000
81
+ 2023-10-17 00:11:13,398 epoch 1 - iter 462/773 - loss 0.48513473 - time (sec): 26.83 - samples/sec: 2767.76 - lr: 0.000030 - momentum: 0.000000
82
+ 2023-10-17 00:11:17,743 epoch 1 - iter 539/773 - loss 0.43220579 - time (sec): 31.18 - samples/sec: 2767.71 - lr: 0.000035 - momentum: 0.000000
83
+ 2023-10-17 00:11:22,171 epoch 1 - iter 616/773 - loss 0.39217814 - time (sec): 35.60 - samples/sec: 2766.34 - lr: 0.000040 - momentum: 0.000000
84
+ 2023-10-17 00:11:26,934 epoch 1 - iter 693/773 - loss 0.35818872 - time (sec): 40.37 - samples/sec: 2755.31 - lr: 0.000045 - momentum: 0.000000
85
+ 2023-10-17 00:11:31,429 epoch 1 - iter 770/773 - loss 0.33013406 - time (sec): 44.86 - samples/sec: 2762.25 - lr: 0.000050 - momentum: 0.000000
86
+ 2023-10-17 00:11:31,575 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-17 00:11:31,575 EPOCH 1 done: loss 0.3293 - lr: 0.000050
88
+ 2023-10-17 00:11:33,573 DEV : loss 0.059652842581272125 - f1-score (micro avg) 0.7208
89
+ 2023-10-17 00:11:33,596 saving best model
90
+ 2023-10-17 00:11:33,936 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-17 00:11:38,685 epoch 2 - iter 77/773 - loss 0.08267678 - time (sec): 4.75 - samples/sec: 2784.77 - lr: 0.000049 - momentum: 0.000000
92
+ 2023-10-17 00:11:43,311 epoch 2 - iter 154/773 - loss 0.08055208 - time (sec): 9.37 - samples/sec: 2754.52 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-17 00:11:47,825 epoch 2 - iter 231/773 - loss 0.08052395 - time (sec): 13.89 - samples/sec: 2743.62 - lr: 0.000048 - momentum: 0.000000
94
+ 2023-10-17 00:11:52,184 epoch 2 - iter 308/773 - loss 0.08357330 - time (sec): 18.25 - samples/sec: 2741.61 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-17 00:11:56,640 epoch 2 - iter 385/773 - loss 0.08382211 - time (sec): 22.70 - samples/sec: 2709.61 - lr: 0.000047 - momentum: 0.000000
96
+ 2023-10-17 00:12:01,104 epoch 2 - iter 462/773 - loss 0.08414725 - time (sec): 27.17 - samples/sec: 2725.32 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-17 00:12:05,611 epoch 2 - iter 539/773 - loss 0.08425195 - time (sec): 31.67 - samples/sec: 2738.14 - lr: 0.000046 - momentum: 0.000000
98
+ 2023-10-17 00:12:10,421 epoch 2 - iter 616/773 - loss 0.08124072 - time (sec): 36.48 - samples/sec: 2732.40 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-17 00:12:14,839 epoch 2 - iter 693/773 - loss 0.08111029 - time (sec): 40.90 - samples/sec: 2724.98 - lr: 0.000045 - momentum: 0.000000
100
+ 2023-10-17 00:12:19,329 epoch 2 - iter 770/773 - loss 0.08051640 - time (sec): 45.39 - samples/sec: 2731.34 - lr: 0.000044 - momentum: 0.000000
101
+ 2023-10-17 00:12:19,473 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-17 00:12:19,473 EPOCH 2 done: loss 0.0805 - lr: 0.000044
103
+ 2023-10-17 00:12:21,618 DEV : loss 0.06363236904144287 - f1-score (micro avg) 0.7695
104
+ 2023-10-17 00:12:21,632 saving best model
105
+ 2023-10-17 00:12:22,081 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-17 00:12:26,590 epoch 3 - iter 77/773 - loss 0.04146028 - time (sec): 4.51 - samples/sec: 2835.22 - lr: 0.000044 - momentum: 0.000000
107
+ 2023-10-17 00:12:31,330 epoch 3 - iter 154/773 - loss 0.05242848 - time (sec): 9.25 - samples/sec: 2794.38 - lr: 0.000043 - momentum: 0.000000
108
+ 2023-10-17 00:12:36,075 epoch 3 - iter 231/773 - loss 0.05020704 - time (sec): 13.99 - samples/sec: 2799.71 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-17 00:12:40,485 epoch 3 - iter 308/773 - loss 0.04913742 - time (sec): 18.40 - samples/sec: 2761.24 - lr: 0.000042 - momentum: 0.000000
110
+ 2023-10-17 00:12:45,283 epoch 3 - iter 385/773 - loss 0.04825767 - time (sec): 23.20 - samples/sec: 2709.09 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-17 00:12:49,681 epoch 3 - iter 462/773 - loss 0.04909420 - time (sec): 27.60 - samples/sec: 2706.36 - lr: 0.000041 - momentum: 0.000000
112
+ 2023-10-17 00:12:54,373 epoch 3 - iter 539/773 - loss 0.05056346 - time (sec): 32.29 - samples/sec: 2716.55 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-17 00:12:58,913 epoch 3 - iter 616/773 - loss 0.04920383 - time (sec): 36.83 - samples/sec: 2711.79 - lr: 0.000040 - momentum: 0.000000
114
+ 2023-10-17 00:13:03,233 epoch 3 - iter 693/773 - loss 0.04950107 - time (sec): 41.15 - samples/sec: 2708.02 - lr: 0.000039 - momentum: 0.000000
115
+ 2023-10-17 00:13:07,711 epoch 3 - iter 770/773 - loss 0.04922958 - time (sec): 45.63 - samples/sec: 2714.93 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-17 00:13:07,859 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-17 00:13:07,859 EPOCH 3 done: loss 0.0491 - lr: 0.000039
118
+ 2023-10-17 00:13:09,920 DEV : loss 0.07400500774383545 - f1-score (micro avg) 0.7557
119
+ 2023-10-17 00:13:09,933 ----------------------------------------------------------------------------------------------------
120
+ 2023-10-17 00:13:14,277 epoch 4 - iter 77/773 - loss 0.03358044 - time (sec): 4.34 - samples/sec: 2682.63 - lr: 0.000038 - momentum: 0.000000
121
+ 2023-10-17 00:13:18,839 epoch 4 - iter 154/773 - loss 0.03101342 - time (sec): 8.91 - samples/sec: 2657.51 - lr: 0.000038 - momentum: 0.000000
122
+ 2023-10-17 00:13:23,406 epoch 4 - iter 231/773 - loss 0.04019504 - time (sec): 13.47 - samples/sec: 2696.83 - lr: 0.000037 - momentum: 0.000000
123
+ 2023-10-17 00:13:27,935 epoch 4 - iter 308/773 - loss 0.03771869 - time (sec): 18.00 - samples/sec: 2698.58 - lr: 0.000037 - momentum: 0.000000
124
+ 2023-10-17 00:13:32,515 epoch 4 - iter 385/773 - loss 0.03809639 - time (sec): 22.58 - samples/sec: 2693.07 - lr: 0.000036 - momentum: 0.000000
125
+ 2023-10-17 00:13:36,925 epoch 4 - iter 462/773 - loss 0.03778033 - time (sec): 26.99 - samples/sec: 2697.29 - lr: 0.000036 - momentum: 0.000000
126
+ 2023-10-17 00:13:41,472 epoch 4 - iter 539/773 - loss 0.03704712 - time (sec): 31.54 - samples/sec: 2709.38 - lr: 0.000035 - momentum: 0.000000
127
+ 2023-10-17 00:13:45,999 epoch 4 - iter 616/773 - loss 0.03811842 - time (sec): 36.07 - samples/sec: 2708.41 - lr: 0.000034 - momentum: 0.000000
128
+ 2023-10-17 00:13:50,448 epoch 4 - iter 693/773 - loss 0.03785183 - time (sec): 40.51 - samples/sec: 2725.89 - lr: 0.000034 - momentum: 0.000000
129
+ 2023-10-17 00:13:55,203 epoch 4 - iter 770/773 - loss 0.03661737 - time (sec): 45.27 - samples/sec: 2732.01 - lr: 0.000033 - momentum: 0.000000
130
+ 2023-10-17 00:13:55,384 ----------------------------------------------------------------------------------------------------
131
+ 2023-10-17 00:13:55,384 EPOCH 4 done: loss 0.0369 - lr: 0.000033
132
+ 2023-10-17 00:13:57,425 DEV : loss 0.094989113509655 - f1-score (micro avg) 0.7735
133
+ 2023-10-17 00:13:57,438 saving best model
134
+ 2023-10-17 00:13:57,905 ----------------------------------------------------------------------------------------------------
135
+ 2023-10-17 00:14:02,360 epoch 5 - iter 77/773 - loss 0.03472163 - time (sec): 4.45 - samples/sec: 2784.21 - lr: 0.000033 - momentum: 0.000000
136
+ 2023-10-17 00:14:06,806 epoch 5 - iter 154/773 - loss 0.03021440 - time (sec): 8.89 - samples/sec: 2742.09 - lr: 0.000032 - momentum: 0.000000
137
+ 2023-10-17 00:14:11,196 epoch 5 - iter 231/773 - loss 0.02772660 - time (sec): 13.28 - samples/sec: 2772.06 - lr: 0.000032 - momentum: 0.000000
138
+ 2023-10-17 00:14:15,511 epoch 5 - iter 308/773 - loss 0.02631770 - time (sec): 17.60 - samples/sec: 2794.08 - lr: 0.000031 - momentum: 0.000000
139
+ 2023-10-17 00:14:20,117 epoch 5 - iter 385/773 - loss 0.02565861 - time (sec): 22.20 - samples/sec: 2794.33 - lr: 0.000031 - momentum: 0.000000
140
+ 2023-10-17 00:14:24,603 epoch 5 - iter 462/773 - loss 0.02740935 - time (sec): 26.69 - samples/sec: 2773.42 - lr: 0.000030 - momentum: 0.000000
141
+ 2023-10-17 00:14:29,099 epoch 5 - iter 539/773 - loss 0.02750473 - time (sec): 31.19 - samples/sec: 2807.62 - lr: 0.000029 - momentum: 0.000000
142
+ 2023-10-17 00:14:33,457 epoch 5 - iter 616/773 - loss 0.02705987 - time (sec): 35.54 - samples/sec: 2797.03 - lr: 0.000029 - momentum: 0.000000
143
+ 2023-10-17 00:14:37,868 epoch 5 - iter 693/773 - loss 0.02728248 - time (sec): 39.96 - samples/sec: 2796.81 - lr: 0.000028 - momentum: 0.000000
144
+ 2023-10-17 00:14:42,389 epoch 5 - iter 770/773 - loss 0.02673116 - time (sec): 44.48 - samples/sec: 2787.57 - lr: 0.000028 - momentum: 0.000000
145
+ 2023-10-17 00:14:42,531 ----------------------------------------------------------------------------------------------------
146
+ 2023-10-17 00:14:42,532 EPOCH 5 done: loss 0.0267 - lr: 0.000028
147
+ 2023-10-17 00:14:44,574 DEV : loss 0.08982112258672714 - f1-score (micro avg) 0.7782
148
+ 2023-10-17 00:14:44,587 saving best model
149
+ 2023-10-17 00:14:45,034 ----------------------------------------------------------------------------------------------------
150
+ 2023-10-17 00:14:49,458 epoch 6 - iter 77/773 - loss 0.01860363 - time (sec): 4.42 - samples/sec: 2848.08 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-17 00:14:54,100 epoch 6 - iter 154/773 - loss 0.02010732 - time (sec): 9.06 - samples/sec: 2800.03 - lr: 0.000027 - momentum: 0.000000
152
+ 2023-10-17 00:14:58,610 epoch 6 - iter 231/773 - loss 0.02089781 - time (sec): 13.57 - samples/sec: 2737.15 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-17 00:15:02,982 epoch 6 - iter 308/773 - loss 0.02145581 - time (sec): 17.95 - samples/sec: 2766.88 - lr: 0.000026 - momentum: 0.000000
154
+ 2023-10-17 00:15:07,619 epoch 6 - iter 385/773 - loss 0.02124064 - time (sec): 22.58 - samples/sec: 2763.84 - lr: 0.000025 - momentum: 0.000000
155
+ 2023-10-17 00:15:12,187 epoch 6 - iter 462/773 - loss 0.02044592 - time (sec): 27.15 - samples/sec: 2735.29 - lr: 0.000024 - momentum: 0.000000
156
+ 2023-10-17 00:15:16,805 epoch 6 - iter 539/773 - loss 0.01854573 - time (sec): 31.77 - samples/sec: 2735.71 - lr: 0.000024 - momentum: 0.000000
157
+ 2023-10-17 00:15:21,104 epoch 6 - iter 616/773 - loss 0.01837402 - time (sec): 36.07 - samples/sec: 2709.40 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-17 00:15:25,786 epoch 6 - iter 693/773 - loss 0.01805303 - time (sec): 40.75 - samples/sec: 2715.50 - lr: 0.000023 - momentum: 0.000000
159
+ 2023-10-17 00:15:30,367 epoch 6 - iter 770/773 - loss 0.01812580 - time (sec): 45.33 - samples/sec: 2734.73 - lr: 0.000022 - momentum: 0.000000
160
+ 2023-10-17 00:15:30,515 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-17 00:15:30,515 EPOCH 6 done: loss 0.0182 - lr: 0.000022
162
+ 2023-10-17 00:15:32,896 DEV : loss 0.10503190755844116 - f1-score (micro avg) 0.7828
163
+ 2023-10-17 00:15:32,909 saving best model
164
+ 2023-10-17 00:15:33,359 ----------------------------------------------------------------------------------------------------
165
+ 2023-10-17 00:15:37,736 epoch 7 - iter 77/773 - loss 0.01183332 - time (sec): 4.38 - samples/sec: 2641.89 - lr: 0.000022 - momentum: 0.000000
166
+ 2023-10-17 00:15:42,135 epoch 7 - iter 154/773 - loss 0.01209373 - time (sec): 8.78 - samples/sec: 2648.17 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-17 00:15:46,560 epoch 7 - iter 231/773 - loss 0.01195452 - time (sec): 13.20 - samples/sec: 2661.44 - lr: 0.000021 - momentum: 0.000000
168
+ 2023-10-17 00:15:51,297 epoch 7 - iter 308/773 - loss 0.01287340 - time (sec): 17.94 - samples/sec: 2678.24 - lr: 0.000020 - momentum: 0.000000
169
+ 2023-10-17 00:15:56,031 epoch 7 - iter 385/773 - loss 0.01293459 - time (sec): 22.67 - samples/sec: 2684.40 - lr: 0.000019 - momentum: 0.000000
170
+ 2023-10-17 00:16:00,860 epoch 7 - iter 462/773 - loss 0.01236694 - time (sec): 27.50 - samples/sec: 2680.71 - lr: 0.000019 - momentum: 0.000000
171
+ 2023-10-17 00:16:05,350 epoch 7 - iter 539/773 - loss 0.01324423 - time (sec): 31.99 - samples/sec: 2716.70 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-17 00:16:09,729 epoch 7 - iter 616/773 - loss 0.01303248 - time (sec): 36.37 - samples/sec: 2732.97 - lr: 0.000018 - momentum: 0.000000
173
+ 2023-10-17 00:16:14,130 epoch 7 - iter 693/773 - loss 0.01280785 - time (sec): 40.77 - samples/sec: 2728.98 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-17 00:16:18,632 epoch 7 - iter 770/773 - loss 0.01284700 - time (sec): 45.27 - samples/sec: 2736.07 - lr: 0.000017 - momentum: 0.000000
175
+ 2023-10-17 00:16:18,807 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-17 00:16:18,807 EPOCH 7 done: loss 0.0129 - lr: 0.000017
177
+ 2023-10-17 00:16:20,898 DEV : loss 0.11371700465679169 - f1-score (micro avg) 0.7819
178
+ 2023-10-17 00:16:20,911 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-17 00:16:25,476 epoch 8 - iter 77/773 - loss 0.01156935 - time (sec): 4.56 - samples/sec: 2709.97 - lr: 0.000016 - momentum: 0.000000
180
+ 2023-10-17 00:16:30,132 epoch 8 - iter 154/773 - loss 0.01249568 - time (sec): 9.22 - samples/sec: 2800.97 - lr: 0.000016 - momentum: 0.000000
181
+ 2023-10-17 00:16:34,605 epoch 8 - iter 231/773 - loss 0.01229927 - time (sec): 13.69 - samples/sec: 2766.08 - lr: 0.000015 - momentum: 0.000000
182
+ 2023-10-17 00:16:39,121 epoch 8 - iter 308/773 - loss 0.01066091 - time (sec): 18.21 - samples/sec: 2785.15 - lr: 0.000014 - momentum: 0.000000
183
+ 2023-10-17 00:16:43,831 epoch 8 - iter 385/773 - loss 0.00972507 - time (sec): 22.92 - samples/sec: 2770.43 - lr: 0.000014 - momentum: 0.000000
184
+ 2023-10-17 00:16:48,553 epoch 8 - iter 462/773 - loss 0.00980739 - time (sec): 27.64 - samples/sec: 2766.62 - lr: 0.000013 - momentum: 0.000000
185
+ 2023-10-17 00:16:53,046 epoch 8 - iter 539/773 - loss 0.01020468 - time (sec): 32.13 - samples/sec: 2739.83 - lr: 0.000013 - momentum: 0.000000
186
+ 2023-10-17 00:16:57,396 epoch 8 - iter 616/773 - loss 0.01063618 - time (sec): 36.48 - samples/sec: 2725.94 - lr: 0.000012 - momentum: 0.000000
187
+ 2023-10-17 00:17:01,933 epoch 8 - iter 693/773 - loss 0.01072864 - time (sec): 41.02 - samples/sec: 2734.32 - lr: 0.000012 - momentum: 0.000000
188
+ 2023-10-17 00:17:06,292 epoch 8 - iter 770/773 - loss 0.01043384 - time (sec): 45.38 - samples/sec: 2729.16 - lr: 0.000011 - momentum: 0.000000
189
+ 2023-10-17 00:17:06,450 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-17 00:17:06,450 EPOCH 8 done: loss 0.0104 - lr: 0.000011
191
+ 2023-10-17 00:17:08,525 DEV : loss 0.11392305791378021 - f1-score (micro avg) 0.7769
192
+ 2023-10-17 00:17:08,537 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-17 00:17:12,969 epoch 9 - iter 77/773 - loss 0.00904434 - time (sec): 4.43 - samples/sec: 2761.63 - lr: 0.000011 - momentum: 0.000000
194
+ 2023-10-17 00:17:17,472 epoch 9 - iter 154/773 - loss 0.00780158 - time (sec): 8.93 - samples/sec: 2828.74 - lr: 0.000010 - momentum: 0.000000
195
+ 2023-10-17 00:17:22,301 epoch 9 - iter 231/773 - loss 0.00701070 - time (sec): 13.76 - samples/sec: 2789.60 - lr: 0.000009 - momentum: 0.000000
196
+ 2023-10-17 00:17:26,710 epoch 9 - iter 308/773 - loss 0.00763945 - time (sec): 18.17 - samples/sec: 2774.88 - lr: 0.000009 - momentum: 0.000000
197
+ 2023-10-17 00:17:31,242 epoch 9 - iter 385/773 - loss 0.00690755 - time (sec): 22.70 - samples/sec: 2761.91 - lr: 0.000008 - momentum: 0.000000
198
+ 2023-10-17 00:17:35,850 epoch 9 - iter 462/773 - loss 0.00645291 - time (sec): 27.31 - samples/sec: 2743.64 - lr: 0.000008 - momentum: 0.000000
199
+ 2023-10-17 00:17:40,446 epoch 9 - iter 539/773 - loss 0.00573275 - time (sec): 31.91 - samples/sec: 2708.02 - lr: 0.000007 - momentum: 0.000000
200
+ 2023-10-17 00:17:44,926 epoch 9 - iter 616/773 - loss 0.00611407 - time (sec): 36.39 - samples/sec: 2725.77 - lr: 0.000007 - momentum: 0.000000
201
+ 2023-10-17 00:17:49,539 epoch 9 - iter 693/773 - loss 0.00629245 - time (sec): 41.00 - samples/sec: 2723.65 - lr: 0.000006 - momentum: 0.000000
202
+ 2023-10-17 00:17:53,916 epoch 9 - iter 770/773 - loss 0.00650414 - time (sec): 45.38 - samples/sec: 2726.62 - lr: 0.000006 - momentum: 0.000000
203
+ 2023-10-17 00:17:54,091 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-17 00:17:54,091 EPOCH 9 done: loss 0.0065 - lr: 0.000006
205
+ 2023-10-17 00:17:56,158 DEV : loss 0.12053602188825607 - f1-score (micro avg) 0.7826
206
+ 2023-10-17 00:17:56,171 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-17 00:18:00,927 epoch 10 - iter 77/773 - loss 0.00599831 - time (sec): 4.75 - samples/sec: 2645.45 - lr: 0.000005 - momentum: 0.000000
208
+ 2023-10-17 00:18:05,488 epoch 10 - iter 154/773 - loss 0.00506362 - time (sec): 9.32 - samples/sec: 2681.78 - lr: 0.000005 - momentum: 0.000000
209
+ 2023-10-17 00:18:09,735 epoch 10 - iter 231/773 - loss 0.00564116 - time (sec): 13.56 - samples/sec: 2681.17 - lr: 0.000004 - momentum: 0.000000
210
+ 2023-10-17 00:18:14,369 epoch 10 - iter 308/773 - loss 0.00511353 - time (sec): 18.20 - samples/sec: 2704.55 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-17 00:18:18,980 epoch 10 - iter 385/773 - loss 0.00477008 - time (sec): 22.81 - samples/sec: 2745.02 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-17 00:18:23,547 epoch 10 - iter 462/773 - loss 0.00429130 - time (sec): 27.38 - samples/sec: 2766.04 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-17 00:18:28,025 epoch 10 - iter 539/773 - loss 0.00437021 - time (sec): 31.85 - samples/sec: 2763.06 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-17 00:18:32,366 epoch 10 - iter 616/773 - loss 0.00440371 - time (sec): 36.19 - samples/sec: 2751.71 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-17 00:18:36,768 epoch 10 - iter 693/773 - loss 0.00478785 - time (sec): 40.60 - samples/sec: 2756.28 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-17 00:18:41,261 epoch 10 - iter 770/773 - loss 0.00462015 - time (sec): 45.09 - samples/sec: 2746.82 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-17 00:18:41,417 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-17 00:18:41,417 EPOCH 10 done: loss 0.0046 - lr: 0.000000
219
+ 2023-10-17 00:18:43,468 DEV : loss 0.11875911056995392 - f1-score (micro avg) 0.7789
220
+ 2023-10-17 00:18:43,819 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-17 00:18:43,821 Loading model from best epoch ...
222
+ 2023-10-17 00:18:45,650 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
+ 2023-10-17 00:18:51,351
224
+ Results:
225
+ - F-score (micro) 0.8017
226
+ - F-score (macro) 0.7056
227
+ - Accuracy 0.6963
228
+
229
+ By class:
230
+ precision recall f1-score support
231
+
232
+ LOC 0.8471 0.8436 0.8453 946
233
+ BUILDING 0.6049 0.6703 0.6359 185
234
+ STREET 0.6667 0.6071 0.6355 56
235
+
236
+ micro avg 0.7980 0.8054 0.8017 1187
237
+ macro avg 0.7062 0.7070 0.7056 1187
238
+ weighted avg 0.8009 0.8054 0.8028 1187
239
+
240
+ 2023-10-17 00:18:51,351 ----------------------------------------------------------------------------------------------------