Hugging Face's logo

hmbert-64k
/
flair-hipe-2022-newseye-sv

Token Classification
Flair
PyTorch
TensorBoard
Swedish
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
3512774
•
1 Parent(s): e776b33

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 20:51:03,901 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-25 20:51:03,902 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 20:51:03,902 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-25 20:51:03,903 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 20:51:03,903 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-25 20:51:03,903 Train: 1085 sentences
55
+ 2023-10-25 20:51:03,903 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-25 20:51:03,903 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-25 20:51:03,903 Training Params:
58
+ 2023-10-25 20:51:03,903 - learning_rate: "3e-05"
59
+ 2023-10-25 20:51:03,903 - mini_batch_size: "4"
60
+ 2023-10-25 20:51:03,903 - max_epochs: "10"
61
+ 2023-10-25 20:51:03,903 - shuffle: "True"
62
+ 2023-10-25 20:51:03,903 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-25 20:51:03,903 Plugins:
64
+ 2023-10-25 20:51:03,903 - TensorboardLogger
65
+ 2023-10-25 20:51:03,903 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-25 20:51:03,903 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-25 20:51:03,903 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-25 20:51:03,903 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-25 20:51:03,903 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-25 20:51:03,903 Computation:
71
+ 2023-10-25 20:51:03,903 - compute on device: cuda:0
72
+ 2023-10-25 20:51:03,903 - embedding storage: none
73
+ 2023-10-25 20:51:03,903 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-25 20:51:03,904 Model training base path: "hmbench-newseye/sv-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
75
+ 2023-10-25 20:51:03,904 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-25 20:51:03,904 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-25 20:51:03,904 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-25 20:51:05,373 epoch 1 - iter 27/272 - loss 3.35810402 - time (sec): 1.47 - samples/sec: 3492.66 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-25 20:51:06,887 epoch 1 - iter 54/272 - loss 2.62664709 - time (sec): 2.98 - samples/sec: 3401.67 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-25 20:51:08,380 epoch 1 - iter 81/272 - loss 1.99702193 - time (sec): 4.48 - samples/sec: 3374.69 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-25 20:51:09,943 epoch 1 - iter 108/272 - loss 1.58713504 - time (sec): 6.04 - samples/sec: 3404.72 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-25 20:51:11,444 epoch 1 - iter 135/272 - loss 1.36358638 - time (sec): 7.54 - samples/sec: 3368.62 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-25 20:51:12,949 epoch 1 - iter 162/272 - loss 1.18146019 - time (sec): 9.04 - samples/sec: 3376.99 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-25 20:51:14,393 epoch 1 - iter 189/272 - loss 1.06467820 - time (sec): 10.49 - samples/sec: 3358.79 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-25 20:51:15,843 epoch 1 - iter 216/272 - loss 0.96906368 - time (sec): 11.94 - samples/sec: 3321.01 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-25 20:51:17,363 epoch 1 - iter 243/272 - loss 0.86325291 - time (sec): 13.46 - samples/sec: 3386.37 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-25 20:51:18,899 epoch 1 - iter 270/272 - loss 0.78237789 - time (sec): 14.99 - samples/sec: 3458.33 - lr: 0.000030 - momentum: 0.000000
88
+ 2023-10-25 20:51:19,005 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-25 20:51:19,005 EPOCH 1 done: loss 0.7808 - lr: 0.000030
90
+ 2023-10-25 20:51:20,097 DEV : loss 0.15305721759796143 - f1-score (micro avg) 0.6386
91
+ 2023-10-25 20:51:20,104 saving best model
92
+ 2023-10-25 20:51:20,577 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-25 20:51:22,089 epoch 2 - iter 27/272 - loss 0.13098364 - time (sec): 1.51 - samples/sec: 4032.22 - lr: 0.000030 - momentum: 0.000000
94
+ 2023-10-25 20:51:23,680 epoch 2 - iter 54/272 - loss 0.13797292 - time (sec): 3.10 - samples/sec: 3676.76 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-25 20:51:25,272 epoch 2 - iter 81/272 - loss 0.13466499 - time (sec): 4.69 - samples/sec: 3567.20 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-25 20:51:26,739 epoch 2 - iter 108/272 - loss 0.14329642 - time (sec): 6.16 - samples/sec: 3503.40 - lr: 0.000029 - momentum: 0.000000
97
+ 2023-10-25 20:51:28,334 epoch 2 - iter 135/272 - loss 0.14715212 - time (sec): 7.76 - samples/sec: 3406.31 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-25 20:51:29,837 epoch 2 - iter 162/272 - loss 0.14527168 - time (sec): 9.26 - samples/sec: 3439.37 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-25 20:51:31,271 epoch 2 - iter 189/272 - loss 0.14428601 - time (sec): 10.69 - samples/sec: 3391.13 - lr: 0.000028 - momentum: 0.000000
100
+ 2023-10-25 20:51:32,731 epoch 2 - iter 216/272 - loss 0.14094961 - time (sec): 12.15 - samples/sec: 3376.93 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-25 20:51:34,209 epoch 2 - iter 243/272 - loss 0.13825777 - time (sec): 13.63 - samples/sec: 3412.68 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-25 20:51:35,720 epoch 2 - iter 270/272 - loss 0.13406289 - time (sec): 15.14 - samples/sec: 3420.90 - lr: 0.000027 - momentum: 0.000000
103
+ 2023-10-25 20:51:35,822 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-25 20:51:35,823 EPOCH 2 done: loss 0.1336 - lr: 0.000027
105
+ 2023-10-25 20:51:37,026 DEV : loss 0.10869525372982025 - f1-score (micro avg) 0.7612
106
+ 2023-10-25 20:51:37,032 saving best model
107
+ 2023-10-25 20:51:37,679 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-25 20:51:39,125 epoch 3 - iter 27/272 - loss 0.06125906 - time (sec): 1.44 - samples/sec: 3180.36 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-25 20:51:40,638 epoch 3 - iter 54/272 - loss 0.05737341 - time (sec): 2.96 - samples/sec: 3829.78 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-25 20:51:42,149 epoch 3 - iter 81/272 - loss 0.06197287 - time (sec): 4.47 - samples/sec: 3671.03 - lr: 0.000026 - momentum: 0.000000
111
+ 2023-10-25 20:51:43,609 epoch 3 - iter 108/272 - loss 0.06482587 - time (sec): 5.93 - samples/sec: 3526.11 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-25 20:51:45,141 epoch 3 - iter 135/272 - loss 0.06852388 - time (sec): 7.46 - samples/sec: 3507.27 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-25 20:51:46,621 epoch 3 - iter 162/272 - loss 0.06845236 - time (sec): 8.94 - samples/sec: 3533.20 - lr: 0.000025 - momentum: 0.000000
114
+ 2023-10-25 20:51:48,120 epoch 3 - iter 189/272 - loss 0.06756303 - time (sec): 10.44 - samples/sec: 3460.60 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-25 20:51:49,609 epoch 3 - iter 216/272 - loss 0.06827772 - time (sec): 11.93 - samples/sec: 3469.25 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-25 20:51:51,080 epoch 3 - iter 243/272 - loss 0.07019403 - time (sec): 13.40 - samples/sec: 3441.78 - lr: 0.000024 - momentum: 0.000000
117
+ 2023-10-25 20:51:52,526 epoch 3 - iter 270/272 - loss 0.06889892 - time (sec): 14.85 - samples/sec: 3470.59 - lr: 0.000023 - momentum: 0.000000
118
+ 2023-10-25 20:51:52,642 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-25 20:51:52,642 EPOCH 3 done: loss 0.0684 - lr: 0.000023
120
+ 2023-10-25 20:51:53,815 DEV : loss 0.11325477808713913 - f1-score (micro avg) 0.8008
121
+ 2023-10-25 20:51:53,821 saving best model
122
+ 2023-10-25 20:51:54,495 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-25 20:51:55,964 epoch 4 - iter 27/272 - loss 0.03659584 - time (sec): 1.46 - samples/sec: 3878.96 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-25 20:51:57,465 epoch 4 - iter 54/272 - loss 0.03315229 - time (sec): 2.96 - samples/sec: 3655.01 - lr: 0.000023 - momentum: 0.000000
125
+ 2023-10-25 20:51:58,859 epoch 4 - iter 81/272 - loss 0.03745032 - time (sec): 4.36 - samples/sec: 3462.26 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-25 20:52:00,314 epoch 4 - iter 108/272 - loss 0.03711163 - time (sec): 5.81 - samples/sec: 3479.09 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-25 20:52:01,742 epoch 4 - iter 135/272 - loss 0.03775119 - time (sec): 7.24 - samples/sec: 3466.86 - lr: 0.000022 - momentum: 0.000000
128
+ 2023-10-25 20:52:03,327 epoch 4 - iter 162/272 - loss 0.04244654 - time (sec): 8.83 - samples/sec: 3400.80 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-25 20:52:04,794 epoch 4 - iter 189/272 - loss 0.04115573 - time (sec): 10.29 - samples/sec: 3389.24 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-25 20:52:06,428 epoch 4 - iter 216/272 - loss 0.04090003 - time (sec): 11.93 - samples/sec: 3466.71 - lr: 0.000021 - momentum: 0.000000
131
+ 2023-10-25 20:52:07,981 epoch 4 - iter 243/272 - loss 0.04016434 - time (sec): 13.48 - samples/sec: 3404.78 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-25 20:52:09,573 epoch 4 - iter 270/272 - loss 0.03989968 - time (sec): 15.07 - samples/sec: 3430.88 - lr: 0.000020 - momentum: 0.000000
133
+ 2023-10-25 20:52:09,677 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-25 20:52:09,677 EPOCH 4 done: loss 0.0397 - lr: 0.000020
135
+ 2023-10-25 20:52:10,943 DEV : loss 0.1432153433561325 - f1-score (micro avg) 0.7927
136
+ 2023-10-25 20:52:10,950 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-25 20:52:12,397 epoch 5 - iter 27/272 - loss 0.03498180 - time (sec): 1.45 - samples/sec: 3105.70 - lr: 0.000020 - momentum: 0.000000
138
+ 2023-10-25 20:52:13,883 epoch 5 - iter 54/272 - loss 0.03139512 - time (sec): 2.93 - samples/sec: 3136.88 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-25 20:52:15,479 epoch 5 - iter 81/272 - loss 0.02686437 - time (sec): 4.53 - samples/sec: 3278.40 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-25 20:52:17,076 epoch 5 - iter 108/272 - loss 0.02614851 - time (sec): 6.13 - samples/sec: 3313.61 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-25 20:52:18,602 epoch 5 - iter 135/272 - loss 0.02762334 - time (sec): 7.65 - samples/sec: 3288.24 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-25 20:52:20,123 epoch 5 - iter 162/272 - loss 0.02604272 - time (sec): 9.17 - samples/sec: 3385.64 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-25 20:52:21,652 epoch 5 - iter 189/272 - loss 0.02439411 - time (sec): 10.70 - samples/sec: 3327.17 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-25 20:52:23,621 epoch 5 - iter 216/272 - loss 0.02376852 - time (sec): 12.67 - samples/sec: 3258.47 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-25 20:52:25,077 epoch 5 - iter 243/272 - loss 0.02352355 - time (sec): 14.13 - samples/sec: 3289.41 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-25 20:52:26,579 epoch 5 - iter 270/272 - loss 0.02408055 - time (sec): 15.63 - samples/sec: 3309.97 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-25 20:52:26,689 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-25 20:52:26,689 EPOCH 5 done: loss 0.0244 - lr: 0.000017
149
+ 2023-10-25 20:52:27,848 DEV : loss 0.16343659162521362 - f1-score (micro avg) 0.8102
150
+ 2023-10-25 20:52:27,855 saving best model
151
+ 2023-10-25 20:52:28,577 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-25 20:52:30,124 epoch 6 - iter 27/272 - loss 0.02652120 - time (sec): 1.52 - samples/sec: 3067.11 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-25 20:52:31,621 epoch 6 - iter 54/272 - loss 0.02631961 - time (sec): 3.02 - samples/sec: 3218.86 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-25 20:52:33,096 epoch 6 - iter 81/272 - loss 0.02198692 - time (sec): 4.49 - samples/sec: 3280.48 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-25 20:52:34,602 epoch 6 - iter 108/272 - loss 0.02473048 - time (sec): 6.00 - samples/sec: 3337.97 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-25 20:52:36,070 epoch 6 - iter 135/272 - loss 0.02285927 - time (sec): 7.47 - samples/sec: 3371.24 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-25 20:52:37,555 epoch 6 - iter 162/272 - loss 0.02122821 - time (sec): 8.95 - samples/sec: 3473.57 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-25 20:52:39,056 epoch 6 - iter 189/272 - loss 0.01959515 - time (sec): 10.45 - samples/sec: 3470.46 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-25 20:52:40,504 epoch 6 - iter 216/272 - loss 0.01869554 - time (sec): 11.90 - samples/sec: 3465.89 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-25 20:52:41,945 epoch 6 - iter 243/272 - loss 0.01895320 - time (sec): 13.34 - samples/sec: 3492.28 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-25 20:52:43,365 epoch 6 - iter 270/272 - loss 0.01873867 - time (sec): 14.76 - samples/sec: 3507.21 - lr: 0.000013 - momentum: 0.000000
162
+ 2023-10-25 20:52:43,462 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-25 20:52:43,463 EPOCH 6 done: loss 0.0187 - lr: 0.000013
164
+ 2023-10-25 20:52:44,733 DEV : loss 0.16893555223941803 - f1-score (micro avg) 0.8324
165
+ 2023-10-25 20:52:44,741 saving best model
166
+ 2023-10-25 20:52:45,405 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-25 20:52:46,859 epoch 7 - iter 27/272 - loss 0.01570413 - time (sec): 1.45 - samples/sec: 3659.52 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-25 20:52:48,351 epoch 7 - iter 54/272 - loss 0.01635881 - time (sec): 2.94 - samples/sec: 3551.57 - lr: 0.000013 - momentum: 0.000000
169
+ 2023-10-25 20:52:49,917 epoch 7 - iter 81/272 - loss 0.01833799 - time (sec): 4.51 - samples/sec: 3370.52 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-25 20:52:51,376 epoch 7 - iter 108/272 - loss 0.01488772 - time (sec): 5.97 - samples/sec: 3387.92 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-25 20:52:52,826 epoch 7 - iter 135/272 - loss 0.01593043 - time (sec): 7.42 - samples/sec: 3335.88 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-25 20:52:54,341 epoch 7 - iter 162/272 - loss 0.01519486 - time (sec): 8.93 - samples/sec: 3367.70 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-25 20:52:55,849 epoch 7 - iter 189/272 - loss 0.01473941 - time (sec): 10.44 - samples/sec: 3372.45 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-25 20:52:57,397 epoch 7 - iter 216/272 - loss 0.01429210 - time (sec): 11.99 - samples/sec: 3440.67 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-25 20:52:58,888 epoch 7 - iter 243/272 - loss 0.01324011 - time (sec): 13.48 - samples/sec: 3476.27 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-25 20:53:00,322 epoch 7 - iter 270/272 - loss 0.01365909 - time (sec): 14.91 - samples/sec: 3480.96 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-25 20:53:00,416 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-25 20:53:00,416 EPOCH 7 done: loss 0.0136 - lr: 0.000010
179
+ 2023-10-25 20:53:01,585 DEV : loss 0.1673850566148758 - f1-score (micro avg) 0.844
180
+ 2023-10-25 20:53:01,592 saving best model
181
+ 2023-10-25 20:53:02,278 ----------------------------------------------------------------------------------------------------
182
+ 2023-10-25 20:53:03,801 epoch 8 - iter 27/272 - loss 0.02161960 - time (sec): 1.52 - samples/sec: 3618.74 - lr: 0.000010 - momentum: 0.000000
183
+ 2023-10-25 20:53:05,303 epoch 8 - iter 54/272 - loss 0.01680960 - time (sec): 3.02 - samples/sec: 3491.96 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-25 20:53:06,784 epoch 8 - iter 81/272 - loss 0.01355752 - time (sec): 4.50 - samples/sec: 3448.46 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-25 20:53:08,258 epoch 8 - iter 108/272 - loss 0.01579221 - time (sec): 5.98 - samples/sec: 3470.08 - lr: 0.000009 - momentum: 0.000000
186
+ 2023-10-25 20:53:09,700 epoch 8 - iter 135/272 - loss 0.01480401 - time (sec): 7.42 - samples/sec: 3427.25 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-25 20:53:11,218 epoch 8 - iter 162/272 - loss 0.01266974 - time (sec): 8.94 - samples/sec: 3464.35 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-25 20:53:12,725 epoch 8 - iter 189/272 - loss 0.01141429 - time (sec): 10.44 - samples/sec: 3449.79 - lr: 0.000008 - momentum: 0.000000
189
+ 2023-10-25 20:53:14,150 epoch 8 - iter 216/272 - loss 0.01178960 - time (sec): 11.87 - samples/sec: 3379.00 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-25 20:53:15,670 epoch 8 - iter 243/272 - loss 0.01123156 - time (sec): 13.39 - samples/sec: 3428.57 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-25 20:53:17,154 epoch 8 - iter 270/272 - loss 0.01148940 - time (sec): 14.87 - samples/sec: 3482.11 - lr: 0.000007 - momentum: 0.000000
192
+ 2023-10-25 20:53:17,258 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-25 20:53:17,259 EPOCH 8 done: loss 0.0115 - lr: 0.000007
194
+ 2023-10-25 20:53:18,828 DEV : loss 0.18429012596607208 - f1-score (micro avg) 0.8429
195
+ 2023-10-25 20:53:18,834 ----------------------------------------------------------------------------------------------------
196
+ 2023-10-25 20:53:20,345 epoch 9 - iter 27/272 - loss 0.00096616 - time (sec): 1.51 - samples/sec: 3279.68 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-25 20:53:21,821 epoch 9 - iter 54/272 - loss 0.00315849 - time (sec): 2.99 - samples/sec: 3323.41 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-25 20:53:23,292 epoch 9 - iter 81/272 - loss 0.00292424 - time (sec): 4.46 - samples/sec: 3273.48 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-25 20:53:24,820 epoch 9 - iter 108/272 - loss 0.00436173 - time (sec): 5.98 - samples/sec: 3396.22 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-25 20:53:26,273 epoch 9 - iter 135/272 - loss 0.00392677 - time (sec): 7.44 - samples/sec: 3513.87 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-25 20:53:27,649 epoch 9 - iter 162/272 - loss 0.00622840 - time (sec): 8.81 - samples/sec: 3541.40 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-25 20:53:29,173 epoch 9 - iter 189/272 - loss 0.00621295 - time (sec): 10.34 - samples/sec: 3498.94 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-25 20:53:30,573 epoch 9 - iter 216/272 - loss 0.00596192 - time (sec): 11.74 - samples/sec: 3536.20 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-25 20:53:32,055 epoch 9 - iter 243/272 - loss 0.00724204 - time (sec): 13.22 - samples/sec: 3575.10 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-25 20:53:33,437 epoch 9 - iter 270/272 - loss 0.00728933 - time (sec): 14.60 - samples/sec: 3541.52 - lr: 0.000003 - momentum: 0.000000
206
+ 2023-10-25 20:53:33,536 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-25 20:53:33,536 EPOCH 9 done: loss 0.0073 - lr: 0.000003
208
+ 2023-10-25 20:53:34,754 DEV : loss 0.18683403730392456 - f1-score (micro avg) 0.846
209
+ 2023-10-25 20:53:34,761 saving best model
210
+ 2023-10-25 20:53:35,249 ----------------------------------------------------------------------------------------------------
211
+ 2023-10-25 20:53:36,695 epoch 10 - iter 27/272 - loss 0.00555682 - time (sec): 1.44 - samples/sec: 3069.63 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-25 20:53:38,153 epoch 10 - iter 54/272 - loss 0.00691251 - time (sec): 2.90 - samples/sec: 3140.72 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-25 20:53:39,581 epoch 10 - iter 81/272 - loss 0.00559490 - time (sec): 4.33 - samples/sec: 3363.79 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-25 20:53:41,065 epoch 10 - iter 108/272 - loss 0.00408773 - time (sec): 5.81 - samples/sec: 3510.61 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-25 20:53:42,390 epoch 10 - iter 135/272 - loss 0.00363612 - time (sec): 7.14 - samples/sec: 3426.84 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-25 20:53:43,826 epoch 10 - iter 162/272 - loss 0.00590384 - time (sec): 8.57 - samples/sec: 3439.31 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-25 20:53:45,205 epoch 10 - iter 189/272 - loss 0.00552531 - time (sec): 9.95 - samples/sec: 3489.58 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-25 20:53:46,692 epoch 10 - iter 216/272 - loss 0.00564306 - time (sec): 11.44 - samples/sec: 3572.62 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-25 20:53:48,035 epoch 10 - iter 243/272 - loss 0.00641529 - time (sec): 12.78 - samples/sec: 3538.99 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-25 20:53:49,469 epoch 10 - iter 270/272 - loss 0.00576979 - time (sec): 14.22 - samples/sec: 3623.00 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-25 20:53:49,580 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-25 20:53:49,580 EPOCH 10 done: loss 0.0057 - lr: 0.000000
223
+ 2023-10-25 20:53:50,777 DEV : loss 0.18572133779525757 - f1-score (micro avg) 0.845
224
+ 2023-10-25 20:53:51,215 ----------------------------------------------------------------------------------------------------
225
+ 2023-10-25 20:53:51,216 Loading model from best epoch ...
226
+ 2023-10-25 20:53:53,027 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
227
+ 2023-10-25 20:53:55,007
228
+ Results:
229
+ - F-score (micro) 0.7975
230
+ - F-score (macro) 0.7465
231
+ - Accuracy 0.682
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ LOC 0.8160 0.8814 0.8475 312
237
+ PER 0.7137 0.8750 0.7862 208
238
+ ORG 0.5510 0.4909 0.5192 55
239
+ HumanProd 0.7692 0.9091 0.8333 22
240
+
241
+ micro avg 0.7556 0.8442 0.7975 597
242
+ macro avg 0.7125 0.7891 0.7465 597
243
+ weighted avg 0.7542 0.8442 0.7953 597
244
+
245
+ 2023-10-25 20:53:55,007 ----------------------------------------------------------------------------------------------------