Hugging Face's logo

stefan-it
/
hmbench-newseye-fi-hmbert_64k-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5

Token Classification
Flair
PyTorch
TensorBoard
Finnish
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
c6942d3
·
1 Parent(s): 0d6a10c

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +245 -0
training.log ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-25 21:30:08,203 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-25 21:30:08,204 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(64001, 768)
7
+ (position_embeddings): Embedding(512, 768)
8
+ (token_type_embeddings): Embedding(2, 768)
9
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=768, out_features=768, bias=True)
18
+ (key): Linear(in_features=768, out_features=768, bias=True)
19
+ (value): Linear(in_features=768, out_features=768, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=768, out_features=768, bias=True)
24
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
34
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
35
+ (dropout): Dropout(p=0.1, inplace=False)
36
+ )
37
+ )
38
+ )
39
+ )
40
+ (pooler): BertPooler(
41
+ (dense): Linear(in_features=768, out_features=768, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=768, out_features=17, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-25 21:30:08,204 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-25 21:30:08,204 MultiCorpus: 1166 train + 165 dev + 415 test sentences
52
+ - NER_HIPE_2022 Corpus: 1166 train + 165 dev + 415 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fi/with_doc_seperator
53
+ 2023-10-25 21:30:08,204 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-25 21:30:08,204 Train: 1166 sentences
55
+ 2023-10-25 21:30:08,204 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-25 21:30:08,204 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-25 21:30:08,204 Training Params:
58
+ 2023-10-25 21:30:08,204 - learning_rate: "3e-05"
59
+ 2023-10-25 21:30:08,204 - mini_batch_size: "4"
60
+ 2023-10-25 21:30:08,204 - max_epochs: "10"
61
+ 2023-10-25 21:30:08,204 - shuffle: "True"
62
+ 2023-10-25 21:30:08,204 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-25 21:30:08,204 Plugins:
64
+ 2023-10-25 21:30:08,205 - TensorboardLogger
65
+ 2023-10-25 21:30:08,205 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-25 21:30:08,205 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-25 21:30:08,205 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-25 21:30:08,205 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-25 21:30:08,205 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-25 21:30:08,205 Computation:
71
+ 2023-10-25 21:30:08,205 - compute on device: cuda:0
72
+ 2023-10-25 21:30:08,205 - embedding storage: none
73
+ 2023-10-25 21:30:08,205 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-25 21:30:08,205 Model training base path: "hmbench-newseye/fi-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5"
75
+ 2023-10-25 21:30:08,205 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-25 21:30:08,205 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-25 21:30:08,205 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-25 21:30:09,606 epoch 1 - iter 29/292 - loss 2.59371458 - time (sec): 1.40 - samples/sec: 2896.33 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-25 21:30:10,850 epoch 1 - iter 58/292 - loss 1.95964027 - time (sec): 2.64 - samples/sec: 2959.98 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-25 21:30:12,193 epoch 1 - iter 87/292 - loss 1.55409749 - time (sec): 3.99 - samples/sec: 3138.14 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-25 21:30:13,533 epoch 1 - iter 116/292 - loss 1.29448959 - time (sec): 5.33 - samples/sec: 3211.67 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-25 21:30:14,805 epoch 1 - iter 145/292 - loss 1.10125147 - time (sec): 6.60 - samples/sec: 3291.64 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-25 21:30:16,127 epoch 1 - iter 174/292 - loss 0.98629607 - time (sec): 7.92 - samples/sec: 3235.22 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-25 21:30:17,493 epoch 1 - iter 203/292 - loss 0.86851694 - time (sec): 9.29 - samples/sec: 3310.48 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-25 21:30:18,859 epoch 1 - iter 232/292 - loss 0.77881535 - time (sec): 10.65 - samples/sec: 3357.49 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-25 21:30:20,169 epoch 1 - iter 261/292 - loss 0.72190147 - time (sec): 11.96 - samples/sec: 3368.38 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-25 21:30:21,437 epoch 1 - iter 290/292 - loss 0.68367522 - time (sec): 13.23 - samples/sec: 3341.39 - lr: 0.000030 - momentum: 0.000000
88
+ 2023-10-25 21:30:21,516 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-25 21:30:21,516 EPOCH 1 done: loss 0.6826 - lr: 0.000030
90
+ 2023-10-25 21:30:22,184 DEV : loss 0.1497330218553543 - f1-score (micro avg) 0.5972
91
+ 2023-10-25 21:30:22,188 saving best model
92
+ 2023-10-25 21:30:22,530 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-25 21:30:23,819 epoch 2 - iter 29/292 - loss 0.17252226 - time (sec): 1.29 - samples/sec: 3461.31 - lr: 0.000030 - momentum: 0.000000
94
+ 2023-10-25 21:30:25,115 epoch 2 - iter 58/292 - loss 0.19611204 - time (sec): 2.58 - samples/sec: 3403.61 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-25 21:30:26,423 epoch 2 - iter 87/292 - loss 0.18751975 - time (sec): 3.89 - samples/sec: 3340.71 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-25 21:30:27,769 epoch 2 - iter 116/292 - loss 0.17497620 - time (sec): 5.24 - samples/sec: 3374.72 - lr: 0.000029 - momentum: 0.000000
97
+ 2023-10-25 21:30:29,058 epoch 2 - iter 145/292 - loss 0.16837296 - time (sec): 6.53 - samples/sec: 3335.07 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-25 21:30:30,367 epoch 2 - iter 174/292 - loss 0.16678211 - time (sec): 7.84 - samples/sec: 3347.37 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-25 21:30:31,620 epoch 2 - iter 203/292 - loss 0.16469283 - time (sec): 9.09 - samples/sec: 3342.18 - lr: 0.000028 - momentum: 0.000000
100
+ 2023-10-25 21:30:32,877 epoch 2 - iter 232/292 - loss 0.16617154 - time (sec): 10.35 - samples/sec: 3360.39 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-25 21:30:34,211 epoch 2 - iter 261/292 - loss 0.16625252 - time (sec): 11.68 - samples/sec: 3367.96 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-25 21:30:35,519 epoch 2 - iter 290/292 - loss 0.16032533 - time (sec): 12.99 - samples/sec: 3391.30 - lr: 0.000027 - momentum: 0.000000
103
+ 2023-10-25 21:30:35,604 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-25 21:30:35,604 EPOCH 2 done: loss 0.1595 - lr: 0.000027
105
+ 2023-10-25 21:30:36,510 DEV : loss 0.12749069929122925 - f1-score (micro avg) 0.6216
106
+ 2023-10-25 21:30:36,514 saving best model
107
+ 2023-10-25 21:30:37,133 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-25 21:30:38,576 epoch 3 - iter 29/292 - loss 0.09022188 - time (sec): 1.44 - samples/sec: 4060.31 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-25 21:30:39,893 epoch 3 - iter 58/292 - loss 0.10087929 - time (sec): 2.76 - samples/sec: 3781.78 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-25 21:30:41,160 epoch 3 - iter 87/292 - loss 0.10208490 - time (sec): 4.03 - samples/sec: 3635.44 - lr: 0.000026 - momentum: 0.000000
111
+ 2023-10-25 21:30:42,449 epoch 3 - iter 116/292 - loss 0.10105352 - time (sec): 5.31 - samples/sec: 3517.62 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-25 21:30:43,751 epoch 3 - iter 145/292 - loss 0.10094429 - time (sec): 6.62 - samples/sec: 3495.48 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-25 21:30:45,016 epoch 3 - iter 174/292 - loss 0.09645934 - time (sec): 7.88 - samples/sec: 3441.59 - lr: 0.000025 - momentum: 0.000000
114
+ 2023-10-25 21:30:46,488 epoch 3 - iter 203/292 - loss 0.09398874 - time (sec): 9.35 - samples/sec: 3382.73 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-25 21:30:47,737 epoch 3 - iter 232/292 - loss 0.09314091 - time (sec): 10.60 - samples/sec: 3308.62 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-25 21:30:49,070 epoch 3 - iter 261/292 - loss 0.09176423 - time (sec): 11.93 - samples/sec: 3358.99 - lr: 0.000024 - momentum: 0.000000
117
+ 2023-10-25 21:30:50,363 epoch 3 - iter 290/292 - loss 0.09054539 - time (sec): 13.23 - samples/sec: 3342.94 - lr: 0.000023 - momentum: 0.000000
118
+ 2023-10-25 21:30:50,450 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-25 21:30:50,450 EPOCH 3 done: loss 0.0913 - lr: 0.000023
120
+ 2023-10-25 21:30:51,361 DEV : loss 0.11841346323490143 - f1-score (micro avg) 0.7118
121
+ 2023-10-25 21:30:51,365 saving best model
122
+ 2023-10-25 21:30:52,005 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-25 21:30:53,266 epoch 4 - iter 29/292 - loss 0.06571735 - time (sec): 1.26 - samples/sec: 3370.24 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-25 21:30:54,598 epoch 4 - iter 58/292 - loss 0.05780459 - time (sec): 2.59 - samples/sec: 3250.20 - lr: 0.000023 - momentum: 0.000000
125
+ 2023-10-25 21:30:55,965 epoch 4 - iter 87/292 - loss 0.05216866 - time (sec): 3.96 - samples/sec: 3297.12 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-25 21:30:57,257 epoch 4 - iter 116/292 - loss 0.04928450 - time (sec): 5.25 - samples/sec: 3238.11 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-25 21:30:58,611 epoch 4 - iter 145/292 - loss 0.05174887 - time (sec): 6.60 - samples/sec: 3421.02 - lr: 0.000022 - momentum: 0.000000
128
+ 2023-10-25 21:30:59,914 epoch 4 - iter 174/292 - loss 0.05349774 - time (sec): 7.91 - samples/sec: 3465.27 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-25 21:31:01,321 epoch 4 - iter 203/292 - loss 0.05412245 - time (sec): 9.31 - samples/sec: 3411.38 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-25 21:31:02,580 epoch 4 - iter 232/292 - loss 0.05878785 - time (sec): 10.57 - samples/sec: 3383.60 - lr: 0.000021 - momentum: 0.000000
131
+ 2023-10-25 21:31:03,967 epoch 4 - iter 261/292 - loss 0.06009869 - time (sec): 11.96 - samples/sec: 3381.49 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-25 21:31:05,232 epoch 4 - iter 290/292 - loss 0.05847457 - time (sec): 13.22 - samples/sec: 3342.38 - lr: 0.000020 - momentum: 0.000000
133
+ 2023-10-25 21:31:05,312 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-25 21:31:05,312 EPOCH 4 done: loss 0.0583 - lr: 0.000020
135
+ 2023-10-25 21:31:06,226 DEV : loss 0.13698235154151917 - f1-score (micro avg) 0.7329
136
+ 2023-10-25 21:31:06,231 saving best model
137
+ 2023-10-25 21:31:06,849 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-25 21:31:08,165 epoch 5 - iter 29/292 - loss 0.03972724 - time (sec): 1.31 - samples/sec: 3464.93 - lr: 0.000020 - momentum: 0.000000
139
+ 2023-10-25 21:31:09,448 epoch 5 - iter 58/292 - loss 0.03798626 - time (sec): 2.60 - samples/sec: 3365.39 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-25 21:31:10,783 epoch 5 - iter 87/292 - loss 0.03555398 - time (sec): 3.93 - samples/sec: 3314.51 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-25 21:31:12,032 epoch 5 - iter 116/292 - loss 0.03214301 - time (sec): 5.18 - samples/sec: 3360.42 - lr: 0.000019 - momentum: 0.000000
142
+ 2023-10-25 21:31:13,311 epoch 5 - iter 145/292 - loss 0.03292483 - time (sec): 6.46 - samples/sec: 3385.15 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-25 21:31:14,600 epoch 5 - iter 174/292 - loss 0.03681121 - time (sec): 7.75 - samples/sec: 3329.04 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-25 21:31:15,983 epoch 5 - iter 203/292 - loss 0.03818340 - time (sec): 9.13 - samples/sec: 3327.67 - lr: 0.000018 - momentum: 0.000000
145
+ 2023-10-25 21:31:17,283 epoch 5 - iter 232/292 - loss 0.04048615 - time (sec): 10.43 - samples/sec: 3412.34 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-25 21:31:18,581 epoch 5 - iter 261/292 - loss 0.04033068 - time (sec): 11.73 - samples/sec: 3414.90 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-25 21:31:19,822 epoch 5 - iter 290/292 - loss 0.03959189 - time (sec): 12.97 - samples/sec: 3415.07 - lr: 0.000017 - momentum: 0.000000
148
+ 2023-10-25 21:31:19,897 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-25 21:31:19,897 EPOCH 5 done: loss 0.0395 - lr: 0.000017
150
+ 2023-10-25 21:31:20,805 DEV : loss 0.14024661481380463 - f1-score (micro avg) 0.7364
151
+ 2023-10-25 21:31:20,809 saving best model
152
+ 2023-10-25 21:31:21,435 ----------------------------------------------------------------------------------------------------
153
+ 2023-10-25 21:31:22,752 epoch 6 - iter 29/292 - loss 0.02545293 - time (sec): 1.31 - samples/sec: 3771.70 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-25 21:31:24,050 epoch 6 - iter 58/292 - loss 0.03242435 - time (sec): 2.61 - samples/sec: 3433.27 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-25 21:31:25,321 epoch 6 - iter 87/292 - loss 0.02375022 - time (sec): 3.88 - samples/sec: 3488.35 - lr: 0.000016 - momentum: 0.000000
156
+ 2023-10-25 21:31:26,643 epoch 6 - iter 116/292 - loss 0.03110057 - time (sec): 5.20 - samples/sec: 3502.60 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-25 21:31:27,915 epoch 6 - iter 145/292 - loss 0.03115742 - time (sec): 6.48 - samples/sec: 3503.77 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-25 21:31:29,157 epoch 6 - iter 174/292 - loss 0.03002770 - time (sec): 7.72 - samples/sec: 3510.24 - lr: 0.000015 - momentum: 0.000000
159
+ 2023-10-25 21:31:30,359 epoch 6 - iter 203/292 - loss 0.02977686 - time (sec): 8.92 - samples/sec: 3488.79 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-25 21:31:31,596 epoch 6 - iter 232/292 - loss 0.02910083 - time (sec): 10.16 - samples/sec: 3471.29 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-25 21:31:32,922 epoch 6 - iter 261/292 - loss 0.02814018 - time (sec): 11.48 - samples/sec: 3472.71 - lr: 0.000014 - momentum: 0.000000
162
+ 2023-10-25 21:31:34,133 epoch 6 - iter 290/292 - loss 0.02750245 - time (sec): 12.69 - samples/sec: 3462.82 - lr: 0.000013 - momentum: 0.000000
163
+ 2023-10-25 21:31:34,216 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-25 21:31:34,216 EPOCH 6 done: loss 0.0275 - lr: 0.000013
165
+ 2023-10-25 21:31:35,136 DEV : loss 0.1627625823020935 - f1-score (micro avg) 0.7527
166
+ 2023-10-25 21:31:35,140 saving best model
167
+ 2023-10-25 21:31:35,751 ----------------------------------------------------------------------------------------------------
168
+ 2023-10-25 21:31:36,998 epoch 7 - iter 29/292 - loss 0.02550245 - time (sec): 1.24 - samples/sec: 3912.23 - lr: 0.000013 - momentum: 0.000000
169
+ 2023-10-25 21:31:38,272 epoch 7 - iter 58/292 - loss 0.03222503 - time (sec): 2.52 - samples/sec: 3887.60 - lr: 0.000013 - momentum: 0.000000
170
+ 2023-10-25 21:31:39,460 epoch 7 - iter 87/292 - loss 0.03168046 - time (sec): 3.70 - samples/sec: 3733.03 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-25 21:31:40,677 epoch 7 - iter 116/292 - loss 0.02908034 - time (sec): 4.92 - samples/sec: 3612.53 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-25 21:31:41,881 epoch 7 - iter 145/292 - loss 0.02514753 - time (sec): 6.13 - samples/sec: 3542.89 - lr: 0.000012 - momentum: 0.000000
173
+ 2023-10-25 21:31:43,238 epoch 7 - iter 174/292 - loss 0.02468695 - time (sec): 7.48 - samples/sec: 3553.75 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-25 21:31:44,537 epoch 7 - iter 203/292 - loss 0.02340193 - time (sec): 8.78 - samples/sec: 3551.40 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-25 21:31:45,809 epoch 7 - iter 232/292 - loss 0.02228458 - time (sec): 10.05 - samples/sec: 3510.36 - lr: 0.000011 - momentum: 0.000000
176
+ 2023-10-25 21:31:47,167 epoch 7 - iter 261/292 - loss 0.02091578 - time (sec): 11.41 - samples/sec: 3473.34 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-25 21:31:48,521 epoch 7 - iter 290/292 - loss 0.02054549 - time (sec): 12.77 - samples/sec: 3470.06 - lr: 0.000010 - momentum: 0.000000
178
+ 2023-10-25 21:31:48,612 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-25 21:31:48,612 EPOCH 7 done: loss 0.0205 - lr: 0.000010
180
+ 2023-10-25 21:31:49,536 DEV : loss 0.18406300246715546 - f1-score (micro avg) 0.7638
181
+ 2023-10-25 21:31:49,540 saving best model
182
+ 2023-10-25 21:31:50,152 ----------------------------------------------------------------------------------------------------
183
+ 2023-10-25 21:31:51,534 epoch 8 - iter 29/292 - loss 0.01278755 - time (sec): 1.38 - samples/sec: 3174.63 - lr: 0.000010 - momentum: 0.000000
184
+ 2023-10-25 21:31:52,890 epoch 8 - iter 58/292 - loss 0.01502218 - time (sec): 2.73 - samples/sec: 3230.30 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-25 21:31:54,205 epoch 8 - iter 87/292 - loss 0.01162352 - time (sec): 4.05 - samples/sec: 3323.36 - lr: 0.000009 - momentum: 0.000000
186
+ 2023-10-25 21:31:55,489 epoch 8 - iter 116/292 - loss 0.01556603 - time (sec): 5.33 - samples/sec: 3302.90 - lr: 0.000009 - momentum: 0.000000
187
+ 2023-10-25 21:31:56,784 epoch 8 - iter 145/292 - loss 0.01579903 - time (sec): 6.63 - samples/sec: 3285.94 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-25 21:31:58,212 epoch 8 - iter 174/292 - loss 0.01669043 - time (sec): 8.06 - samples/sec: 3226.30 - lr: 0.000008 - momentum: 0.000000
189
+ 2023-10-25 21:31:59,482 epoch 8 - iter 203/292 - loss 0.01521658 - time (sec): 9.33 - samples/sec: 3184.00 - lr: 0.000008 - momentum: 0.000000
190
+ 2023-10-25 21:32:00,800 epoch 8 - iter 232/292 - loss 0.01518710 - time (sec): 10.64 - samples/sec: 3210.18 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-25 21:32:02,092 epoch 8 - iter 261/292 - loss 0.01451772 - time (sec): 11.94 - samples/sec: 3264.25 - lr: 0.000007 - momentum: 0.000000
192
+ 2023-10-25 21:32:03,464 epoch 8 - iter 290/292 - loss 0.01550935 - time (sec): 13.31 - samples/sec: 3323.97 - lr: 0.000007 - momentum: 0.000000
193
+ 2023-10-25 21:32:03,551 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-25 21:32:03,552 EPOCH 8 done: loss 0.0156 - lr: 0.000007
195
+ 2023-10-25 21:32:04,457 DEV : loss 0.18133316934108734 - f1-score (micro avg) 0.7489
196
+ 2023-10-25 21:32:04,462 ----------------------------------------------------------------------------------------------------
197
+ 2023-10-25 21:32:05,828 epoch 9 - iter 29/292 - loss 0.00469478 - time (sec): 1.36 - samples/sec: 3658.24 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-25 21:32:07,078 epoch 9 - iter 58/292 - loss 0.00939010 - time (sec): 2.61 - samples/sec: 3544.28 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-25 21:32:08,353 epoch 9 - iter 87/292 - loss 0.00915593 - time (sec): 3.89 - samples/sec: 3555.78 - lr: 0.000006 - momentum: 0.000000
200
+ 2023-10-25 21:32:09,712 epoch 9 - iter 116/292 - loss 0.01207961 - time (sec): 5.25 - samples/sec: 3529.11 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-25 21:32:11,030 epoch 9 - iter 145/292 - loss 0.01222517 - time (sec): 6.57 - samples/sec: 3493.57 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-25 21:32:12,307 epoch 9 - iter 174/292 - loss 0.01195187 - time (sec): 7.84 - samples/sec: 3478.22 - lr: 0.000005 - momentum: 0.000000
203
+ 2023-10-25 21:32:13,584 epoch 9 - iter 203/292 - loss 0.01115930 - time (sec): 9.12 - samples/sec: 3479.08 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-25 21:32:14,839 epoch 9 - iter 232/292 - loss 0.01057009 - time (sec): 10.38 - samples/sec: 3434.42 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-25 21:32:16,163 epoch 9 - iter 261/292 - loss 0.01094290 - time (sec): 11.70 - samples/sec: 3384.80 - lr: 0.000004 - momentum: 0.000000
206
+ 2023-10-25 21:32:17,540 epoch 9 - iter 290/292 - loss 0.01034591 - time (sec): 13.08 - samples/sec: 3376.60 - lr: 0.000003 - momentum: 0.000000
207
+ 2023-10-25 21:32:17,632 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-25 21:32:17,632 EPOCH 9 done: loss 0.0103 - lr: 0.000003
209
+ 2023-10-25 21:32:18,549 DEV : loss 0.1857309192419052 - f1-score (micro avg) 0.7461
210
+ 2023-10-25 21:32:18,553 ----------------------------------------------------------------------------------------------------
211
+ 2023-10-25 21:32:19,857 epoch 10 - iter 29/292 - loss 0.00833025 - time (sec): 1.30 - samples/sec: 3353.71 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-25 21:32:21,159 epoch 10 - iter 58/292 - loss 0.00620856 - time (sec): 2.60 - samples/sec: 3160.18 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-25 21:32:22,448 epoch 10 - iter 87/292 - loss 0.01250990 - time (sec): 3.89 - samples/sec: 3177.17 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-25 21:32:23,642 epoch 10 - iter 116/292 - loss 0.01078091 - time (sec): 5.09 - samples/sec: 3278.69 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-25 21:32:24,940 epoch 10 - iter 145/292 - loss 0.00880841 - time (sec): 6.39 - samples/sec: 3371.71 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-25 21:32:26,129 epoch 10 - iter 174/292 - loss 0.00884157 - time (sec): 7.57 - samples/sec: 3418.33 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-25 21:32:27,383 epoch 10 - iter 203/292 - loss 0.00866918 - time (sec): 8.83 - samples/sec: 3498.88 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-25 21:32:28,613 epoch 10 - iter 232/292 - loss 0.00812226 - time (sec): 10.06 - samples/sec: 3493.63 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-25 21:32:29,859 epoch 10 - iter 261/292 - loss 0.00777060 - time (sec): 11.30 - samples/sec: 3510.22 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-25 21:32:31,235 epoch 10 - iter 290/292 - loss 0.00767455 - time (sec): 12.68 - samples/sec: 3490.79 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-25 21:32:31,323 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-25 21:32:31,323 EPOCH 10 done: loss 0.0084 - lr: 0.000000
223
+ 2023-10-25 21:32:32,251 DEV : loss 0.1949864774942398 - f1-score (micro avg) 0.7571
224
+ 2023-10-25 21:32:32,724 ----------------------------------------------------------------------------------------------------
225
+ 2023-10-25 21:32:32,725 Loading model from best epoch ...
226
+ 2023-10-25 21:32:34,339 SequenceTagger predicts: Dictionary with 17 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, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd
227
+ 2023-10-25 21:32:35,859
228
+ Results:
229
+ - F-score (micro) 0.7648
230
+ - F-score (macro) 0.6948
231
+ - Accuracy 0.6424
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ PER 0.8187 0.8305 0.8245 348
237
+ LOC 0.6759 0.8391 0.7487 261
238
+ ORG 0.4583 0.4231 0.4400 52
239
+ HumanProd 0.7200 0.8182 0.7660 22
240
+
241
+ micro avg 0.7307 0.8023 0.7648 683
242
+ macro avg 0.6682 0.7277 0.6948 683
243
+ weighted avg 0.7335 0.8023 0.7644 683
244
+
245
+ 2023-10-25 21:32:35,859 ----------------------------------------------------------------------------------------------------