Hugging Face's logo

stefan-it
/
hmbench-newseye-sv-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2

Token Classification
Flair
PyTorch
TensorBoard
Swedish
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
c76b9ec
•
1 Parent(s): 570c99d

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +243 -0
training.log ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-25 20:57:20,509 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-25 20:57:20,511 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 20:57:20,511 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-25 20:57:20,511 MultiCorpus: 1085 train + 148 dev + 364 test sentences
52
+ - NER_HIPE_2022 Corpus: 1085 train + 148 dev + 364 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/sv/with_doc_seperator
53
+ 2023-10-25 20:57:20,511 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-25 20:57:20,511 Train: 1085 sentences
55
+ 2023-10-25 20:57:20,511 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-25 20:57:20,511 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-25 20:57:20,511 Training Params:
58
+ 2023-10-25 20:57:20,511 - learning_rate: "3e-05"
59
+ 2023-10-25 20:57:20,512 - mini_batch_size: "8"
60
+ 2023-10-25 20:57:20,512 - max_epochs: "10"
61
+ 2023-10-25 20:57:20,512 - shuffle: "True"
62
+ 2023-10-25 20:57:20,512 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-25 20:57:20,512 Plugins:
64
+ 2023-10-25 20:57:20,512 - TensorboardLogger
65
+ 2023-10-25 20:57:20,512 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-25 20:57:20,512 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-25 20:57:20,512 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-25 20:57:20,512 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-25 20:57:20,512 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-25 20:57:20,512 Computation:
71
+ 2023-10-25 20:57:20,512 - compute on device: cuda:0
72
+ 2023-10-25 20:57:20,512 - embedding storage: none
73
+ 2023-10-25 20:57:20,512 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-25 20:57:20,512 Model training base path: "hmbench-newseye/sv-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2"
75
+ 2023-10-25 20:57:20,512 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-25 20:57:20,513 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-25 20:57:20,513 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-25 20:57:21,498 epoch 1 - iter 13/136 - loss 2.92990884 - time (sec): 0.98 - samples/sec: 5127.53 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-25 20:57:22,541 epoch 1 - iter 26/136 - loss 2.55165335 - time (sec): 2.03 - samples/sec: 5026.31 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-25 20:57:23,554 epoch 1 - iter 39/136 - loss 2.04744423 - time (sec): 3.04 - samples/sec: 4980.68 - lr: 0.000008 - momentum: 0.000000
81
+ 2023-10-25 20:57:24,655 epoch 1 - iter 52/136 - loss 1.61339578 - time (sec): 4.14 - samples/sec: 5099.28 - lr: 0.000011 - momentum: 0.000000
82
+ 2023-10-25 20:57:25,631 epoch 1 - iter 65/136 - loss 1.42349176 - time (sec): 5.12 - samples/sec: 5012.82 - lr: 0.000014 - momentum: 0.000000
83
+ 2023-10-25 20:57:26,638 epoch 1 - iter 78/136 - loss 1.27186349 - time (sec): 6.12 - samples/sec: 4920.72 - lr: 0.000017 - momentum: 0.000000
84
+ 2023-10-25 20:57:27,850 epoch 1 - iter 91/136 - loss 1.11113718 - time (sec): 7.34 - samples/sec: 4941.45 - lr: 0.000020 - momentum: 0.000000
85
+ 2023-10-25 20:57:28,832 epoch 1 - iter 104/136 - loss 1.02098309 - time (sec): 8.32 - samples/sec: 4908.84 - lr: 0.000023 - momentum: 0.000000
86
+ 2023-10-25 20:57:29,872 epoch 1 - iter 117/136 - loss 0.93707203 - time (sec): 9.36 - samples/sec: 4859.80 - lr: 0.000026 - momentum: 0.000000
87
+ 2023-10-25 20:57:30,903 epoch 1 - iter 130/136 - loss 0.87769480 - time (sec): 10.39 - samples/sec: 4840.00 - lr: 0.000028 - momentum: 0.000000
88
+ 2023-10-25 20:57:31,283 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-25 20:57:31,284 EPOCH 1 done: loss 0.8541 - lr: 0.000028
90
+ 2023-10-25 20:57:32,387 DEV : loss 0.16994501650333405 - f1-score (micro avg) 0.613
91
+ 2023-10-25 20:57:32,398 saving best model
92
+ 2023-10-25 20:57:32,931 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-25 20:57:33,928 epoch 2 - iter 13/136 - loss 0.20415905 - time (sec): 0.99 - samples/sec: 4751.30 - lr: 0.000030 - momentum: 0.000000
94
+ 2023-10-25 20:57:34,874 epoch 2 - iter 26/136 - loss 0.18777881 - time (sec): 1.94 - samples/sec: 4792.72 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-25 20:57:35,900 epoch 2 - iter 39/136 - loss 0.17721837 - time (sec): 2.97 - samples/sec: 4904.96 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-25 20:57:37,005 epoch 2 - iter 52/136 - loss 0.16931145 - time (sec): 4.07 - samples/sec: 4744.31 - lr: 0.000029 - momentum: 0.000000
97
+ 2023-10-25 20:57:38,017 epoch 2 - iter 65/136 - loss 0.17210883 - time (sec): 5.08 - samples/sec: 4810.67 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-25 20:57:39,068 epoch 2 - iter 78/136 - loss 0.15995899 - time (sec): 6.13 - samples/sec: 4901.43 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-25 20:57:40,018 epoch 2 - iter 91/136 - loss 0.15946327 - time (sec): 7.08 - samples/sec: 4902.65 - lr: 0.000028 - momentum: 0.000000
100
+ 2023-10-25 20:57:40,921 epoch 2 - iter 104/136 - loss 0.15402756 - time (sec): 7.99 - samples/sec: 4948.05 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-25 20:57:42,007 epoch 2 - iter 117/136 - loss 0.14965945 - time (sec): 9.07 - samples/sec: 4961.57 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-25 20:57:42,936 epoch 2 - iter 130/136 - loss 0.14655700 - time (sec): 10.00 - samples/sec: 5015.06 - lr: 0.000027 - momentum: 0.000000
103
+ 2023-10-25 20:57:43,313 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-25 20:57:43,313 EPOCH 2 done: loss 0.1453 - lr: 0.000027
105
+ 2023-10-25 20:57:44,548 DEV : loss 0.10967841744422913 - f1-score (micro avg) 0.7458
106
+ 2023-10-25 20:57:44,554 saving best model
107
+ 2023-10-25 20:57:45,287 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-25 20:57:46,242 epoch 3 - iter 13/136 - loss 0.07746010 - time (sec): 0.95 - samples/sec: 5501.51 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-25 20:57:47,192 epoch 3 - iter 26/136 - loss 0.07658585 - time (sec): 1.90 - samples/sec: 5289.55 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-25 20:57:48,252 epoch 3 - iter 39/136 - loss 0.07212515 - time (sec): 2.96 - samples/sec: 5179.41 - lr: 0.000026 - momentum: 0.000000
111
+ 2023-10-25 20:57:49,294 epoch 3 - iter 52/136 - loss 0.07599664 - time (sec): 4.00 - samples/sec: 5037.24 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-25 20:57:50,176 epoch 3 - iter 65/136 - loss 0.07909179 - time (sec): 4.89 - samples/sec: 5020.73 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-25 20:57:51,247 epoch 3 - iter 78/136 - loss 0.08230846 - time (sec): 5.96 - samples/sec: 4937.25 - lr: 0.000025 - momentum: 0.000000
114
+ 2023-10-25 20:57:52,192 epoch 3 - iter 91/136 - loss 0.08233746 - time (sec): 6.90 - samples/sec: 5016.99 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-25 20:57:53,266 epoch 3 - iter 104/136 - loss 0.08114831 - time (sec): 7.98 - samples/sec: 4936.38 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-25 20:57:54,376 epoch 3 - iter 117/136 - loss 0.08185953 - time (sec): 9.09 - samples/sec: 4904.42 - lr: 0.000024 - momentum: 0.000000
117
+ 2023-10-25 20:57:55,366 epoch 3 - iter 130/136 - loss 0.07910712 - time (sec): 10.08 - samples/sec: 4914.93 - lr: 0.000024 - momentum: 0.000000
118
+ 2023-10-25 20:57:55,881 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-25 20:57:55,882 EPOCH 3 done: loss 0.0776 - lr: 0.000024
120
+ 2023-10-25 20:57:57,053 DEV : loss 0.0935666635632515 - f1-score (micro avg) 0.8015
121
+ 2023-10-25 20:57:57,059 saving best model
122
+ 2023-10-25 20:57:58,210 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-25 20:57:59,243 epoch 4 - iter 13/136 - loss 0.06733069 - time (sec): 1.03 - samples/sec: 5627.57 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-25 20:58:00,107 epoch 4 - iter 26/136 - loss 0.05352415 - time (sec): 1.90 - samples/sec: 5440.88 - lr: 0.000023 - momentum: 0.000000
125
+ 2023-10-25 20:58:01,167 epoch 4 - iter 39/136 - loss 0.04727758 - time (sec): 2.96 - samples/sec: 5014.87 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-25 20:58:02,233 epoch 4 - iter 52/136 - loss 0.04394289 - time (sec): 4.02 - samples/sec: 5086.01 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-25 20:58:03,417 epoch 4 - iter 65/136 - loss 0.04532334 - time (sec): 5.21 - samples/sec: 4877.50 - lr: 0.000022 - momentum: 0.000000
128
+ 2023-10-25 20:58:04,380 epoch 4 - iter 78/136 - loss 0.04726676 - time (sec): 6.17 - samples/sec: 4857.29 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-25 20:58:05,436 epoch 4 - iter 91/136 - loss 0.04783662 - time (sec): 7.22 - samples/sec: 4788.09 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-25 20:58:06,326 epoch 4 - iter 104/136 - loss 0.04641077 - time (sec): 8.11 - samples/sec: 4836.17 - lr: 0.000021 - momentum: 0.000000
131
+ 2023-10-25 20:58:07,338 epoch 4 - iter 117/136 - loss 0.04569068 - time (sec): 9.13 - samples/sec: 4885.19 - lr: 0.000021 - momentum: 0.000000
132
+ 2023-10-25 20:58:08,264 epoch 4 - iter 130/136 - loss 0.04531045 - time (sec): 10.05 - samples/sec: 4925.63 - lr: 0.000020 - momentum: 0.000000
133
+ 2023-10-25 20:58:08,714 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-25 20:58:08,714 EPOCH 4 done: loss 0.0448 - lr: 0.000020
135
+ 2023-10-25 20:58:09,861 DEV : loss 0.1180381178855896 - f1-score (micro avg) 0.8165
136
+ 2023-10-25 20:58:09,867 saving best model
137
+ 2023-10-25 20:58:10,587 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-25 20:58:11,495 epoch 5 - iter 13/136 - loss 0.03999052 - time (sec): 0.91 - samples/sec: 4746.95 - lr: 0.000020 - momentum: 0.000000
139
+ 2023-10-25 20:58:12,564 epoch 5 - iter 26/136 - loss 0.03877379 - time (sec): 1.98 - samples/sec: 5143.91 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-25 20:58:13,366 epoch 5 - iter 39/136 - loss 0.04104911 - time (sec): 2.78 - samples/sec: 4969.15 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-25 20:58:14,396 epoch 5 - iter 52/136 - loss 0.03582605 - time (sec): 3.81 - samples/sec: 4918.58 - lr: 0.000019 - momentum: 0.000000
142
+ 2023-10-25 20:58:15,284 epoch 5 - iter 65/136 - loss 0.03311757 - time (sec): 4.70 - samples/sec: 4947.49 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-25 20:58:16,438 epoch 5 - iter 78/136 - loss 0.03365822 - time (sec): 5.85 - samples/sec: 4889.46 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-25 20:58:17,429 epoch 5 - iter 91/136 - loss 0.03140306 - time (sec): 6.84 - samples/sec: 4859.76 - lr: 0.000018 - momentum: 0.000000
145
+ 2023-10-25 20:58:18,539 epoch 5 - iter 104/136 - loss 0.03087682 - time (sec): 7.95 - samples/sec: 4846.31 - lr: 0.000018 - momentum: 0.000000
146
+ 2023-10-25 20:58:19,430 epoch 5 - iter 117/136 - loss 0.02923008 - time (sec): 8.84 - samples/sec: 4879.53 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-25 20:58:20,456 epoch 5 - iter 130/136 - loss 0.03015711 - time (sec): 9.87 - samples/sec: 4978.43 - lr: 0.000017 - momentum: 0.000000
148
+ 2023-10-25 20:58:20,973 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-25 20:58:20,974 EPOCH 5 done: loss 0.0295 - lr: 0.000017
150
+ 2023-10-25 20:58:22,150 DEV : loss 0.11727390438318253 - f1-score (micro avg) 0.8088
151
+ 2023-10-25 20:58:22,156 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-25 20:58:23,485 epoch 6 - iter 13/136 - loss 0.01807270 - time (sec): 1.33 - samples/sec: 4027.12 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-25 20:58:24,422 epoch 6 - iter 26/136 - loss 0.01886995 - time (sec): 2.26 - samples/sec: 4455.37 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-25 20:58:25,465 epoch 6 - iter 39/136 - loss 0.02451372 - time (sec): 3.31 - samples/sec: 4665.73 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-25 20:58:26,479 epoch 6 - iter 52/136 - loss 0.02065873 - time (sec): 4.32 - samples/sec: 4746.12 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-25 20:58:27,522 epoch 6 - iter 65/136 - loss 0.02021702 - time (sec): 5.36 - samples/sec: 4808.08 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-25 20:58:28,600 epoch 6 - iter 78/136 - loss 0.01893068 - time (sec): 6.44 - samples/sec: 4809.68 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-25 20:58:29,580 epoch 6 - iter 91/136 - loss 0.01805364 - time (sec): 7.42 - samples/sec: 4847.49 - lr: 0.000015 - momentum: 0.000000
159
+ 2023-10-25 20:58:30,512 epoch 6 - iter 104/136 - loss 0.01718406 - time (sec): 8.35 - samples/sec: 4876.08 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-25 20:58:31,575 epoch 6 - iter 117/136 - loss 0.01675969 - time (sec): 9.42 - samples/sec: 4846.20 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-25 20:58:32,611 epoch 6 - iter 130/136 - loss 0.01889550 - time (sec): 10.45 - samples/sec: 4803.09 - lr: 0.000014 - momentum: 0.000000
162
+ 2023-10-25 20:58:32,983 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-25 20:58:32,984 EPOCH 6 done: loss 0.0187 - lr: 0.000014
164
+ 2023-10-25 20:58:34,198 DEV : loss 0.1490204632282257 - f1-score (micro avg) 0.803
165
+ 2023-10-25 20:58:34,204 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-25 20:58:35,206 epoch 7 - iter 13/136 - loss 0.01586148 - time (sec): 1.00 - samples/sec: 4925.95 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-25 20:58:36,177 epoch 7 - iter 26/136 - loss 0.01681382 - time (sec): 1.97 - samples/sec: 4906.10 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-25 20:58:37,190 epoch 7 - iter 39/136 - loss 0.01778000 - time (sec): 2.99 - samples/sec: 5193.78 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-25 20:58:38,194 epoch 7 - iter 52/136 - loss 0.01659602 - time (sec): 3.99 - samples/sec: 5214.42 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-25 20:58:39,216 epoch 7 - iter 65/136 - loss 0.01555708 - time (sec): 5.01 - samples/sec: 5276.45 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-25 20:58:40,258 epoch 7 - iter 78/136 - loss 0.01558607 - time (sec): 6.05 - samples/sec: 5305.58 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-25 20:58:41,101 epoch 7 - iter 91/136 - loss 0.01578396 - time (sec): 6.90 - samples/sec: 5234.84 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-25 20:58:42,219 epoch 7 - iter 104/136 - loss 0.01483323 - time (sec): 8.01 - samples/sec: 5201.77 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-25 20:58:43,132 epoch 7 - iter 117/136 - loss 0.01536701 - time (sec): 8.93 - samples/sec: 5193.89 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-25 20:58:44,007 epoch 7 - iter 130/136 - loss 0.01644397 - time (sec): 9.80 - samples/sec: 5080.17 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-25 20:58:44,444 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-25 20:58:44,445 EPOCH 7 done: loss 0.0162 - lr: 0.000010
178
+ 2023-10-25 20:58:45,626 DEV : loss 0.14709986746311188 - f1-score (micro avg) 0.8096
179
+ 2023-10-25 20:58:45,632 ----------------------------------------------------------------------------------------------------
180
+ 2023-10-25 20:58:46,673 epoch 8 - iter 13/136 - loss 0.01048661 - time (sec): 1.04 - samples/sec: 5216.80 - lr: 0.000010 - momentum: 0.000000
181
+ 2023-10-25 20:58:47,884 epoch 8 - iter 26/136 - loss 0.00918910 - time (sec): 2.25 - samples/sec: 4798.99 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-25 20:58:48,876 epoch 8 - iter 39/136 - loss 0.00801765 - time (sec): 3.24 - samples/sec: 4835.38 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-25 20:58:49,811 epoch 8 - iter 52/136 - loss 0.00951333 - time (sec): 4.18 - samples/sec: 4941.81 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-25 20:58:50,861 epoch 8 - iter 65/136 - loss 0.00958210 - time (sec): 5.23 - samples/sec: 5002.81 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-25 20:58:51,749 epoch 8 - iter 78/136 - loss 0.01103231 - time (sec): 6.12 - samples/sec: 4905.51 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-25 20:58:52,774 epoch 8 - iter 91/136 - loss 0.01146889 - time (sec): 7.14 - samples/sec: 4902.71 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-25 20:58:53,756 epoch 8 - iter 104/136 - loss 0.01148418 - time (sec): 8.12 - samples/sec: 4894.10 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-25 20:58:54,740 epoch 8 - iter 117/136 - loss 0.01250022 - time (sec): 9.11 - samples/sec: 4937.33 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-25 20:58:55,742 epoch 8 - iter 130/136 - loss 0.01246305 - time (sec): 10.11 - samples/sec: 4930.91 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-25 20:58:56,172 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-25 20:58:56,172 EPOCH 8 done: loss 0.0130 - lr: 0.000007
192
+ 2023-10-25 20:58:57,358 DEV : loss 0.16205309331417084 - f1-score (micro avg) 0.8183
193
+ 2023-10-25 20:58:57,364 saving best model
194
+ 2023-10-25 20:58:58,100 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-25 20:58:59,189 epoch 9 - iter 13/136 - loss 0.00483657 - time (sec): 1.09 - samples/sec: 5339.49 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-25 20:59:00,097 epoch 9 - iter 26/136 - loss 0.00526744 - time (sec): 1.99 - samples/sec: 4947.19 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-25 20:59:01,077 epoch 9 - iter 39/136 - loss 0.00787094 - time (sec): 2.97 - samples/sec: 5056.61 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-25 20:59:02,123 epoch 9 - iter 52/136 - loss 0.01159497 - time (sec): 4.02 - samples/sec: 5193.06 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-25 20:59:03,041 epoch 9 - iter 65/136 - loss 0.01128801 - time (sec): 4.94 - samples/sec: 5167.89 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-25 20:59:04,110 epoch 9 - iter 78/136 - loss 0.01095419 - time (sec): 6.01 - samples/sec: 5110.67 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-25 20:59:05,047 epoch 9 - iter 91/136 - loss 0.01033969 - time (sec): 6.94 - samples/sec: 5006.06 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-25 20:59:05,926 epoch 9 - iter 104/136 - loss 0.01030358 - time (sec): 7.82 - samples/sec: 5022.70 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-25 20:59:06,884 epoch 9 - iter 117/136 - loss 0.01015395 - time (sec): 8.78 - samples/sec: 5070.38 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-25 20:59:07,853 epoch 9 - iter 130/136 - loss 0.00984376 - time (sec): 9.75 - samples/sec: 5102.10 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-25 20:59:08,267 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-25 20:59:08,267 EPOCH 9 done: loss 0.0099 - lr: 0.000004
207
+ 2023-10-25 20:59:09,517 DEV : loss 0.17475153505802155 - f1-score (micro avg) 0.8117
208
+ 2023-10-25 20:59:09,524 ----------------------------------------------------------------------------------------------------
209
+ 2023-10-25 20:59:10,421 epoch 10 - iter 13/136 - loss 0.01947312 - time (sec): 0.90 - samples/sec: 4741.61 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-25 20:59:11,667 epoch 10 - iter 26/136 - loss 0.01091648 - time (sec): 2.14 - samples/sec: 4142.73 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-25 20:59:12,604 epoch 10 - iter 39/136 - loss 0.00996893 - time (sec): 3.08 - samples/sec: 4426.47 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-25 20:59:13,600 epoch 10 - iter 52/136 - loss 0.00856799 - time (sec): 4.07 - samples/sec: 4501.11 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-25 20:59:14,760 epoch 10 - iter 65/136 - loss 0.00788452 - time (sec): 5.23 - samples/sec: 4662.51 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-25 20:59:15,743 epoch 10 - iter 78/136 - loss 0.00803522 - time (sec): 6.22 - samples/sec: 4773.14 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-25 20:59:16,609 epoch 10 - iter 91/136 - loss 0.00759162 - time (sec): 7.08 - samples/sec: 4782.21 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-25 20:59:17,630 epoch 10 - iter 104/136 - loss 0.00729881 - time (sec): 8.10 - samples/sec: 4884.75 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-25 20:59:18,560 epoch 10 - iter 117/136 - loss 0.00781195 - time (sec): 9.03 - samples/sec: 4889.68 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-25 20:59:19,677 epoch 10 - iter 130/136 - loss 0.00830425 - time (sec): 10.15 - samples/sec: 4910.15 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-25 20:59:20,151 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-25 20:59:20,152 EPOCH 10 done: loss 0.0080 - lr: 0.000000
221
+ 2023-10-25 20:59:21,449 DEV : loss 0.17531758546829224 - f1-score (micro avg) 0.8147
222
+ 2023-10-25 20:59:21,950 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-25 20:59:21,951 Loading model from best epoch ...
224
+ 2023-10-25 20:59:23,863 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd, S-ORG, B-ORG, E-ORG, I-ORG
225
+ 2023-10-25 20:59:25,930
226
+ Results:
227
+ - F-score (micro) 0.7987
228
+ - F-score (macro) 0.7473
229
+ - Accuracy 0.6811
230
+
231
+ By class:
232
+ precision recall f1-score support
233
+
234
+ LOC 0.7989 0.8910 0.8424 312
235
+ PER 0.7328 0.8702 0.7956 208
236
+ ORG 0.5556 0.4545 0.5000 55
237
+ HumanProd 0.8000 0.9091 0.8511 22
238
+
239
+ micro avg 0.7579 0.8442 0.7987 597
240
+ macro avg 0.7218 0.7812 0.7473 597
241
+ weighted avg 0.7535 0.8442 0.7949 597
242
+
243
+ 2023-10-25 20:59:25,930 ----------------------------------------------------------------------------------------------------