Hugging Face's logo

stefan-it
/
hmbench-icdar-nl-hmbert_tiny-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1

Token Classification
Flair
PyTorch
TensorBoard
Dutch
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
75ae156
•
1 Parent(s): e138d58

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.1697666900.46dc0c540dd0.3571.2 +3 -0
  5. test.tsv +0 -0
  6. training.log +241 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d3dc5421b102db1f9a158a29639635acd073da35f2a541180ac586ca943fe14
3
+ size 19045922
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 22:08:39 0.0000 1.1433 0.3696 0.0000 0.0000 0.0000 0.0000
3
+ 2 22:09:00 0.0000 0.2412 0.2479 0.6357 0.0919 0.1606 0.0879
4
+ 3 22:09:20 0.0000 0.1963 0.2340 0.6290 0.1612 0.2566 0.1486
5
+ 4 22:09:40 0.0000 0.1813 0.2118 0.5937 0.3698 0.4558 0.3036
6
+ 5 22:10:00 0.0000 0.1715 0.2095 0.6230 0.3295 0.4311 0.2811
7
+ 6 22:10:20 0.0000 0.1633 0.2053 0.5989 0.3440 0.4370 0.2868
8
+ 7 22:10:39 0.0000 0.1571 0.2020 0.5823 0.3471 0.4350 0.2874
9
+ 8 22:10:59 0.0000 0.1530 0.1938 0.5753 0.4143 0.4817 0.3282
10
+ 9 22:11:18 0.0000 0.1503 0.1969 0.5764 0.3936 0.4678 0.3157
11
+ 10 22:11:38 0.0000 0.1504 0.1977 0.5811 0.3884 0.4656 0.3133
runs/events.out.tfevents.1697666900.46dc0c540dd0.3571.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb8657bc9b20fc10650eacc8af0a5da5ca2f7be4e0aaf901042efad8551c4457
3
+ size 407048
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-18 22:08:20,553 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-18 22:08:20,553 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(32001, 128)
7
+ (position_embeddings): Embedding(512, 128)
8
+ (token_type_embeddings): Embedding(2, 128)
9
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-1): 2 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=128, out_features=128, bias=True)
18
+ (key): Linear(in_features=128, out_features=128, bias=True)
19
+ (value): Linear(in_features=128, out_features=128, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=128, out_features=128, bias=True)
24
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=128, out_features=512, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=512, out_features=128, bias=True)
34
+ (LayerNorm): LayerNorm((128,), 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=128, out_features=128, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=128, out_features=13, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-18 22:08:20,553 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-18 22:08:20,554 MultiCorpus: 5777 train + 722 dev + 723 test sentences
52
+ - NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /root/.flair/datasets/ner_icdar_europeana/nl
53
+ 2023-10-18 22:08:20,554 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-18 22:08:20,554 Train: 5777 sentences
55
+ 2023-10-18 22:08:20,554 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-18 22:08:20,554 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-18 22:08:20,554 Training Params:
58
+ 2023-10-18 22:08:20,554 - learning_rate: "3e-05"
59
+ 2023-10-18 22:08:20,554 - mini_batch_size: "8"
60
+ 2023-10-18 22:08:20,554 - max_epochs: "10"
61
+ 2023-10-18 22:08:20,554 - shuffle: "True"
62
+ 2023-10-18 22:08:20,554 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-18 22:08:20,554 Plugins:
64
+ 2023-10-18 22:08:20,554 - TensorboardLogger
65
+ 2023-10-18 22:08:20,554 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-18 22:08:20,554 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-18 22:08:20,554 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-18 22:08:20,554 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-18 22:08:20,554 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-18 22:08:20,554 Computation:
71
+ 2023-10-18 22:08:20,554 - compute on device: cuda:0
72
+ 2023-10-18 22:08:20,554 - embedding storage: none
73
+ 2023-10-18 22:08:20,554 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-18 22:08:20,554 Model training base path: "hmbench-icdar/nl-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
75
+ 2023-10-18 22:08:20,554 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-18 22:08:20,554 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-18 22:08:20,554 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-18 22:08:22,339 epoch 1 - iter 72/723 - loss 3.19628147 - time (sec): 1.78 - samples/sec: 9675.62 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-18 22:08:24,206 epoch 1 - iter 144/723 - loss 2.98886129 - time (sec): 3.65 - samples/sec: 9785.27 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-18 22:08:26,021 epoch 1 - iter 216/723 - loss 2.66211908 - time (sec): 5.47 - samples/sec: 9773.41 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-18 22:08:27,869 epoch 1 - iter 288/723 - loss 2.30691520 - time (sec): 7.31 - samples/sec: 9694.54 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-18 22:08:29,724 epoch 1 - iter 360/723 - loss 1.94819460 - time (sec): 9.17 - samples/sec: 9712.82 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-18 22:08:31,493 epoch 1 - iter 432/723 - loss 1.67747636 - time (sec): 10.94 - samples/sec: 9797.48 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-18 22:08:33,327 epoch 1 - iter 504/723 - loss 1.48735944 - time (sec): 12.77 - samples/sec: 9773.89 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-18 22:08:35,091 epoch 1 - iter 576/723 - loss 1.34523933 - time (sec): 14.54 - samples/sec: 9791.10 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-18 22:08:36,824 epoch 1 - iter 648/723 - loss 1.23775011 - time (sec): 16.27 - samples/sec: 9748.59 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-18 22:08:38,548 epoch 1 - iter 720/723 - loss 1.14588291 - time (sec): 17.99 - samples/sec: 9754.09 - lr: 0.000030 - momentum: 0.000000
88
+ 2023-10-18 22:08:38,637 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-18 22:08:38,637 EPOCH 1 done: loss 1.1433 - lr: 0.000030
90
+ 2023-10-18 22:08:39,957 DEV : loss 0.36958980560302734 - f1-score (micro avg) 0.0
91
+ 2023-10-18 22:08:39,971 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-18 22:08:41,819 epoch 2 - iter 72/723 - loss 0.27018856 - time (sec): 1.85 - samples/sec: 10070.33 - lr: 0.000030 - momentum: 0.000000
93
+ 2023-10-18 22:08:43,579 epoch 2 - iter 144/723 - loss 0.28145989 - time (sec): 3.61 - samples/sec: 9918.45 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-18 22:08:45,396 epoch 2 - iter 216/723 - loss 0.28554002 - time (sec): 5.42 - samples/sec: 9927.00 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-18 22:08:47,278 epoch 2 - iter 288/723 - loss 0.27514712 - time (sec): 7.31 - samples/sec: 9805.31 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-18 22:08:49,104 epoch 2 - iter 360/723 - loss 0.26170040 - time (sec): 9.13 - samples/sec: 9725.21 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-18 22:08:50,949 epoch 2 - iter 432/723 - loss 0.25484094 - time (sec): 10.98 - samples/sec: 9792.59 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-18 22:08:52,671 epoch 2 - iter 504/723 - loss 0.25302933 - time (sec): 12.70 - samples/sec: 9736.45 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-18 22:08:54,386 epoch 2 - iter 576/723 - loss 0.24981194 - time (sec): 14.42 - samples/sec: 9726.09 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-18 22:08:56,178 epoch 2 - iter 648/723 - loss 0.24711782 - time (sec): 16.21 - samples/sec: 9733.59 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-18 22:08:57,963 epoch 2 - iter 720/723 - loss 0.24099947 - time (sec): 17.99 - samples/sec: 9770.09 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-18 22:08:58,019 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-18 22:08:58,020 EPOCH 2 done: loss 0.2412 - lr: 0.000027
104
+ 2023-10-18 22:09:00,129 DEV : loss 0.24794618785381317 - f1-score (micro avg) 0.1606
105
+ 2023-10-18 22:09:00,145 saving best model
106
+ 2023-10-18 22:09:00,182 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-18 22:09:02,154 epoch 3 - iter 72/723 - loss 0.21367677 - time (sec): 1.97 - samples/sec: 9104.26 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-18 22:09:03,878 epoch 3 - iter 144/723 - loss 0.21394777 - time (sec): 3.70 - samples/sec: 9404.23 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-18 22:09:05,631 epoch 3 - iter 216/723 - loss 0.20709447 - time (sec): 5.45 - samples/sec: 9586.09 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-18 22:09:07,509 epoch 3 - iter 288/723 - loss 0.19573277 - time (sec): 7.33 - samples/sec: 9663.93 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-18 22:09:09,309 epoch 3 - iter 360/723 - loss 0.19576608 - time (sec): 9.13 - samples/sec: 9638.03 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-18 22:09:11,120 epoch 3 - iter 432/723 - loss 0.19557293 - time (sec): 10.94 - samples/sec: 9644.08 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-18 22:09:12,825 epoch 3 - iter 504/723 - loss 0.19629812 - time (sec): 12.64 - samples/sec: 9660.73 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-18 22:09:14,649 epoch 3 - iter 576/723 - loss 0.19836773 - time (sec): 14.47 - samples/sec: 9671.57 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-18 22:09:16,513 epoch 3 - iter 648/723 - loss 0.19587120 - time (sec): 16.33 - samples/sec: 9673.08 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-18 22:09:18,375 epoch 3 - iter 720/723 - loss 0.19640335 - time (sec): 18.19 - samples/sec: 9661.70 - lr: 0.000023 - momentum: 0.000000
117
+ 2023-10-18 22:09:18,427 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-18 22:09:18,427 EPOCH 3 done: loss 0.1963 - lr: 0.000023
119
+ 2023-10-18 22:09:20,180 DEV : loss 0.23398783802986145 - f1-score (micro avg) 0.2566
120
+ 2023-10-18 22:09:20,195 saving best model
121
+ 2023-10-18 22:09:20,231 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-18 22:09:22,057 epoch 4 - iter 72/723 - loss 0.17513429 - time (sec): 1.82 - samples/sec: 9662.51 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-18 22:09:23,842 epoch 4 - iter 144/723 - loss 0.17318933 - time (sec): 3.61 - samples/sec: 9551.33 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-18 22:09:25,544 epoch 4 - iter 216/723 - loss 0.18058374 - time (sec): 5.31 - samples/sec: 9862.22 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-18 22:09:27,220 epoch 4 - iter 288/723 - loss 0.17700677 - time (sec): 6.99 - samples/sec: 10223.72 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-18 22:09:28,987 epoch 4 - iter 360/723 - loss 0.17605842 - time (sec): 8.75 - samples/sec: 10119.42 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-18 22:09:30,862 epoch 4 - iter 432/723 - loss 0.18006832 - time (sec): 10.63 - samples/sec: 10053.19 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-18 22:09:32,700 epoch 4 - iter 504/723 - loss 0.17871246 - time (sec): 12.47 - samples/sec: 10026.68 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-18 22:09:34,452 epoch 4 - iter 576/723 - loss 0.17713673 - time (sec): 14.22 - samples/sec: 10011.82 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-18 22:09:36,217 epoch 4 - iter 648/723 - loss 0.17726623 - time (sec): 15.98 - samples/sec: 9931.35 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-18 22:09:37,995 epoch 4 - iter 720/723 - loss 0.18135238 - time (sec): 17.76 - samples/sec: 9890.23 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-18 22:09:38,053 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-18 22:09:38,053 EPOCH 4 done: loss 0.1813 - lr: 0.000020
134
+ 2023-10-18 22:09:40,150 DEV : loss 0.21179497241973877 - f1-score (micro avg) 0.4558
135
+ 2023-10-18 22:09:40,164 saving best model
136
+ 2023-10-18 22:09:40,198 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-18 22:09:42,041 epoch 5 - iter 72/723 - loss 0.19369549 - time (sec): 1.84 - samples/sec: 9869.29 - lr: 0.000020 - momentum: 0.000000
138
+ 2023-10-18 22:09:43,801 epoch 5 - iter 144/723 - loss 0.18409304 - time (sec): 3.60 - samples/sec: 9974.14 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-18 22:09:45,514 epoch 5 - iter 216/723 - loss 0.18004779 - time (sec): 5.32 - samples/sec: 9724.56 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-18 22:09:47,330 epoch 5 - iter 288/723 - loss 0.17894839 - time (sec): 7.13 - samples/sec: 9574.37 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-18 22:09:49,078 epoch 5 - iter 360/723 - loss 0.17522117 - time (sec): 8.88 - samples/sec: 9572.50 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-18 22:09:50,902 epoch 5 - iter 432/723 - loss 0.17234762 - time (sec): 10.70 - samples/sec: 9692.67 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-18 22:09:52,702 epoch 5 - iter 504/723 - loss 0.17119392 - time (sec): 12.50 - samples/sec: 9721.98 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-18 22:09:54,427 epoch 5 - iter 576/723 - loss 0.17011314 - time (sec): 14.23 - samples/sec: 9782.07 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-18 22:09:56,281 epoch 5 - iter 648/723 - loss 0.17258346 - time (sec): 16.08 - samples/sec: 9755.92 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-18 22:09:58,160 epoch 5 - iter 720/723 - loss 0.17140290 - time (sec): 17.96 - samples/sec: 9775.89 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-18 22:09:58,222 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-18 22:09:58,223 EPOCH 5 done: loss 0.1715 - lr: 0.000017
149
+ 2023-10-18 22:09:59,986 DEV : loss 0.20946592092514038 - f1-score (micro avg) 0.4311
150
+ 2023-10-18 22:10:00,001 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-18 22:10:01,737 epoch 6 - iter 72/723 - loss 0.15932427 - time (sec): 1.74 - samples/sec: 9819.08 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-18 22:10:03,525 epoch 6 - iter 144/723 - loss 0.16318147 - time (sec): 3.52 - samples/sec: 9748.74 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-18 22:10:05,353 epoch 6 - iter 216/723 - loss 0.17376298 - time (sec): 5.35 - samples/sec: 9741.66 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-18 22:10:07,055 epoch 6 - iter 288/723 - loss 0.17504093 - time (sec): 7.05 - samples/sec: 9699.27 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-18 22:10:08,797 epoch 6 - iter 360/723 - loss 0.16835316 - time (sec): 8.79 - samples/sec: 9839.54 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-18 22:10:10,614 epoch 6 - iter 432/723 - loss 0.16479689 - time (sec): 10.61 - samples/sec: 9759.78 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-18 22:10:12,459 epoch 6 - iter 504/723 - loss 0.16660146 - time (sec): 12.46 - samples/sec: 9848.56 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-18 22:10:14,270 epoch 6 - iter 576/723 - loss 0.16492361 - time (sec): 14.27 - samples/sec: 9864.81 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-18 22:10:16,409 epoch 6 - iter 648/723 - loss 0.16587764 - time (sec): 16.41 - samples/sec: 9696.86 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-18 22:10:18,149 epoch 6 - iter 720/723 - loss 0.16381985 - time (sec): 18.15 - samples/sec: 9670.91 - lr: 0.000013 - momentum: 0.000000
161
+ 2023-10-18 22:10:18,222 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-18 22:10:18,222 EPOCH 6 done: loss 0.1633 - lr: 0.000013
163
+ 2023-10-18 22:10:19,990 DEV : loss 0.20532798767089844 - f1-score (micro avg) 0.437
164
+ 2023-10-18 22:10:20,004 ----------------------------------------------------------------------------------------------------
165
+ 2023-10-18 22:10:21,747 epoch 7 - iter 72/723 - loss 0.15945249 - time (sec): 1.74 - samples/sec: 9697.69 - lr: 0.000013 - momentum: 0.000000
166
+ 2023-10-18 22:10:23,545 epoch 7 - iter 144/723 - loss 0.15900563 - time (sec): 3.54 - samples/sec: 9956.07 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-18 22:10:25,277 epoch 7 - iter 216/723 - loss 0.15756915 - time (sec): 5.27 - samples/sec: 9983.42 - lr: 0.000012 - momentum: 0.000000
168
+ 2023-10-18 22:10:27,035 epoch 7 - iter 288/723 - loss 0.16114798 - time (sec): 7.03 - samples/sec: 9914.44 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-18 22:10:28,803 epoch 7 - iter 360/723 - loss 0.15938604 - time (sec): 8.80 - samples/sec: 9841.78 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-18 22:10:30,596 epoch 7 - iter 432/723 - loss 0.15944278 - time (sec): 10.59 - samples/sec: 9940.46 - lr: 0.000011 - momentum: 0.000000
171
+ 2023-10-18 22:10:32,312 epoch 7 - iter 504/723 - loss 0.15758147 - time (sec): 12.31 - samples/sec: 9961.91 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-18 22:10:34,029 epoch 7 - iter 576/723 - loss 0.15825257 - time (sec): 14.02 - samples/sec: 9904.92 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-18 22:10:35,849 epoch 7 - iter 648/723 - loss 0.15932809 - time (sec): 15.84 - samples/sec: 9917.65 - lr: 0.000010 - momentum: 0.000000
174
+ 2023-10-18 22:10:37,706 epoch 7 - iter 720/723 - loss 0.15736768 - time (sec): 17.70 - samples/sec: 9919.43 - lr: 0.000010 - momentum: 0.000000
175
+ 2023-10-18 22:10:37,771 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-18 22:10:37,772 EPOCH 7 done: loss 0.1571 - lr: 0.000010
177
+ 2023-10-18 22:10:39,536 DEV : loss 0.20203644037246704 - f1-score (micro avg) 0.435
178
+ 2023-10-18 22:10:39,551 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-18 22:10:41,250 epoch 8 - iter 72/723 - loss 0.14938503 - time (sec): 1.70 - samples/sec: 9489.78 - lr: 0.000010 - momentum: 0.000000
180
+ 2023-10-18 22:10:43,030 epoch 8 - iter 144/723 - loss 0.17061855 - time (sec): 3.48 - samples/sec: 9818.98 - lr: 0.000009 - momentum: 0.000000
181
+ 2023-10-18 22:10:44,814 epoch 8 - iter 216/723 - loss 0.15925070 - time (sec): 5.26 - samples/sec: 10070.94 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-18 22:10:46,559 epoch 8 - iter 288/723 - loss 0.15425474 - time (sec): 7.01 - samples/sec: 10052.28 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-18 22:10:48,290 epoch 8 - iter 360/723 - loss 0.15406306 - time (sec): 8.74 - samples/sec: 10093.66 - lr: 0.000008 - momentum: 0.000000
184
+ 2023-10-18 22:10:50,448 epoch 8 - iter 432/723 - loss 0.14990555 - time (sec): 10.90 - samples/sec: 9787.11 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-18 22:10:52,136 epoch 8 - iter 504/723 - loss 0.14942113 - time (sec): 12.59 - samples/sec: 9789.64 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-18 22:10:53,938 epoch 8 - iter 576/723 - loss 0.14926547 - time (sec): 14.39 - samples/sec: 9816.21 - lr: 0.000007 - momentum: 0.000000
187
+ 2023-10-18 22:10:55,695 epoch 8 - iter 648/723 - loss 0.15071738 - time (sec): 16.14 - samples/sec: 9794.35 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-18 22:10:57,488 epoch 8 - iter 720/723 - loss 0.15325254 - time (sec): 17.94 - samples/sec: 9801.83 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-18 22:10:57,544 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-18 22:10:57,544 EPOCH 8 done: loss 0.1530 - lr: 0.000007
191
+ 2023-10-18 22:10:59,325 DEV : loss 0.1937786489725113 - f1-score (micro avg) 0.4817
192
+ 2023-10-18 22:10:59,340 saving best model
193
+ 2023-10-18 22:10:59,377 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-18 22:11:01,186 epoch 9 - iter 72/723 - loss 0.13945487 - time (sec): 1.81 - samples/sec: 10785.70 - lr: 0.000006 - momentum: 0.000000
195
+ 2023-10-18 22:11:02,934 epoch 9 - iter 144/723 - loss 0.13316947 - time (sec): 3.56 - samples/sec: 10339.76 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-18 22:11:04,648 epoch 9 - iter 216/723 - loss 0.13722754 - time (sec): 5.27 - samples/sec: 10152.37 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-18 22:11:06,400 epoch 9 - iter 288/723 - loss 0.14328557 - time (sec): 7.02 - samples/sec: 10075.44 - lr: 0.000005 - momentum: 0.000000
198
+ 2023-10-18 22:11:08,177 epoch 9 - iter 360/723 - loss 0.14615266 - time (sec): 8.80 - samples/sec: 10049.16 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-18 22:11:09,894 epoch 9 - iter 432/723 - loss 0.14984252 - time (sec): 10.52 - samples/sec: 9960.70 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-18 22:11:11,597 epoch 9 - iter 504/723 - loss 0.15143593 - time (sec): 12.22 - samples/sec: 9905.91 - lr: 0.000004 - momentum: 0.000000
201
+ 2023-10-18 22:11:13,468 epoch 9 - iter 576/723 - loss 0.15073005 - time (sec): 14.09 - samples/sec: 9992.68 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-18 22:11:15,257 epoch 9 - iter 648/723 - loss 0.15148546 - time (sec): 15.88 - samples/sec: 9978.29 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-18 22:11:16,977 epoch 9 - iter 720/723 - loss 0.15040735 - time (sec): 17.60 - samples/sec: 9978.12 - lr: 0.000003 - momentum: 0.000000
204
+ 2023-10-18 22:11:17,043 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-18 22:11:17,043 EPOCH 9 done: loss 0.1503 - lr: 0.000003
206
+ 2023-10-18 22:11:18,810 DEV : loss 0.1968904435634613 - f1-score (micro avg) 0.4678
207
+ 2023-10-18 22:11:18,825 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-18 22:11:20,567 epoch 10 - iter 72/723 - loss 0.13221108 - time (sec): 1.74 - samples/sec: 9813.73 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-18 22:11:22,334 epoch 10 - iter 144/723 - loss 0.15218809 - time (sec): 3.51 - samples/sec: 9666.30 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-18 22:11:24,466 epoch 10 - iter 216/723 - loss 0.14769919 - time (sec): 5.64 - samples/sec: 9253.33 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-18 22:11:26,295 epoch 10 - iter 288/723 - loss 0.15037349 - time (sec): 7.47 - samples/sec: 9296.52 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-18 22:11:28,116 epoch 10 - iter 360/723 - loss 0.15714138 - time (sec): 9.29 - samples/sec: 9508.97 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-18 22:11:29,886 epoch 10 - iter 432/723 - loss 0.15652764 - time (sec): 11.06 - samples/sec: 9531.39 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-18 22:11:31,644 epoch 10 - iter 504/723 - loss 0.15303564 - time (sec): 12.82 - samples/sec: 9644.01 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-18 22:11:33,414 epoch 10 - iter 576/723 - loss 0.15136324 - time (sec): 14.59 - samples/sec: 9663.06 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-18 22:11:35,141 epoch 10 - iter 648/723 - loss 0.14914005 - time (sec): 16.32 - samples/sec: 9668.13 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-18 22:11:36,887 epoch 10 - iter 720/723 - loss 0.15021989 - time (sec): 18.06 - samples/sec: 9722.40 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-18 22:11:36,951 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-18 22:11:36,951 EPOCH 10 done: loss 0.1504 - lr: 0.000000
220
+ 2023-10-18 22:11:38,720 DEV : loss 0.19765476882457733 - f1-score (micro avg) 0.4656
221
+ 2023-10-18 22:11:38,766 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-18 22:11:38,766 Loading model from best epoch ...
223
+ 2023-10-18 22:11:38,851 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG
224
+ 2023-10-18 22:11:40,203
225
+ Results:
226
+ - F-score (micro) 0.4758
227
+ - F-score (macro) 0.3261
228
+ - Accuracy 0.3258
229
+
230
+ By class:
231
+ precision recall f1-score support
232
+
233
+ LOC 0.5020 0.5611 0.5299 458
234
+ PER 0.6822 0.3340 0.4485 482
235
+ ORG 0.0000 0.0000 0.0000 69
236
+
237
+ micro avg 0.5588 0.4143 0.4758 1009
238
+ macro avg 0.3947 0.2984 0.3261 1009
239
+ weighted avg 0.5537 0.4143 0.4548 1009
240
+
241
+ 2023-10-18 22:11:40,203 ----------------------------------------------------------------------------------------------------