Hugging Face's logo

stefan-it
/
hmbench-ajmc-en-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3

Token Classification
Flair
PyTorch
TensorBoard
English
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
5aa271d
•
1 Parent(s): 73dfc0c

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +246 -0
training.log ADDED
@@ -0,0 +1,246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-23 18:19:41,179 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-23 18:19:41,180 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=25, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-23 18:19:41,181 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-23 18:19:41,181 MultiCorpus: 1214 train + 266 dev + 251 test sentences
52
+ - NER_HIPE_2022 Corpus: 1214 train + 266 dev + 251 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/en/with_doc_seperator
53
+ 2023-10-23 18:19:41,181 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-23 18:19:41,181 Train: 1214 sentences
55
+ 2023-10-23 18:19:41,181 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-23 18:19:41,181 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-23 18:19:41,181 Training Params:
58
+ 2023-10-23 18:19:41,181 - learning_rate: "3e-05"
59
+ 2023-10-23 18:19:41,181 - mini_batch_size: "8"
60
+ 2023-10-23 18:19:41,181 - max_epochs: "10"
61
+ 2023-10-23 18:19:41,181 - shuffle: "True"
62
+ 2023-10-23 18:19:41,181 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-23 18:19:41,181 Plugins:
64
+ 2023-10-23 18:19:41,181 - TensorboardLogger
65
+ 2023-10-23 18:19:41,181 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-23 18:19:41,181 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-23 18:19:41,181 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-23 18:19:41,181 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-23 18:19:41,181 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-23 18:19:41,182 Computation:
71
+ 2023-10-23 18:19:41,182 - compute on device: cuda:0
72
+ 2023-10-23 18:19:41,182 - embedding storage: none
73
+ 2023-10-23 18:19:41,182 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-23 18:19:41,182 Model training base path: "hmbench-ajmc/en-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3"
75
+ 2023-10-23 18:19:41,182 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-23 18:19:41,182 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-23 18:19:41,182 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-23 18:19:41,949 epoch 1 - iter 15/152 - loss 3.11385143 - time (sec): 0.77 - samples/sec: 3973.24 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-23 18:19:42,708 epoch 1 - iter 30/152 - loss 2.66819735 - time (sec): 1.53 - samples/sec: 3873.24 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-23 18:19:43,469 epoch 1 - iter 45/152 - loss 2.03026616 - time (sec): 2.29 - samples/sec: 3895.80 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-23 18:19:44,229 epoch 1 - iter 60/152 - loss 1.70709060 - time (sec): 3.05 - samples/sec: 3932.94 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-23 18:19:44,983 epoch 1 - iter 75/152 - loss 1.46041251 - time (sec): 3.80 - samples/sec: 3963.43 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-23 18:19:45,749 epoch 1 - iter 90/152 - loss 1.28362004 - time (sec): 4.57 - samples/sec: 3980.01 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-23 18:19:46,529 epoch 1 - iter 105/152 - loss 1.14421153 - time (sec): 5.35 - samples/sec: 3984.53 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-23 18:19:47,287 epoch 1 - iter 120/152 - loss 1.04230113 - time (sec): 6.10 - samples/sec: 3989.91 - lr: 0.000023 - momentum: 0.000000
86
+ 2023-10-23 18:19:48,056 epoch 1 - iter 135/152 - loss 0.94143217 - time (sec): 6.87 - samples/sec: 4014.79 - lr: 0.000026 - momentum: 0.000000
87
+ 2023-10-23 18:19:48,811 epoch 1 - iter 150/152 - loss 0.87310563 - time (sec): 7.63 - samples/sec: 4009.45 - lr: 0.000029 - momentum: 0.000000
88
+ 2023-10-23 18:19:48,918 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-23 18:19:48,918 EPOCH 1 done: loss 0.8644 - lr: 0.000029
90
+ 2023-10-23 18:19:49,725 DEV : loss 0.19825053215026855 - f1-score (micro avg) 0.5945
91
+ 2023-10-23 18:19:49,733 saving best model
92
+ 2023-10-23 18:19:50,168 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-23 18:19:50,956 epoch 2 - iter 15/152 - loss 0.20761390 - time (sec): 0.79 - samples/sec: 3941.37 - lr: 0.000030 - momentum: 0.000000
94
+ 2023-10-23 18:19:51,725 epoch 2 - iter 30/152 - loss 0.17537014 - time (sec): 1.56 - samples/sec: 4053.34 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-23 18:19:52,510 epoch 2 - iter 45/152 - loss 0.16433025 - time (sec): 2.34 - samples/sec: 3933.86 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-23 18:19:53,280 epoch 2 - iter 60/152 - loss 0.16227219 - time (sec): 3.11 - samples/sec: 3925.61 - lr: 0.000029 - momentum: 0.000000
97
+ 2023-10-23 18:19:54,051 epoch 2 - iter 75/152 - loss 0.15897537 - time (sec): 3.88 - samples/sec: 3896.99 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-23 18:19:54,821 epoch 2 - iter 90/152 - loss 0.15189330 - time (sec): 4.65 - samples/sec: 3916.47 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-23 18:19:55,588 epoch 2 - iter 105/152 - loss 0.15322637 - time (sec): 5.42 - samples/sec: 3864.70 - lr: 0.000028 - momentum: 0.000000
100
+ 2023-10-23 18:19:56,352 epoch 2 - iter 120/152 - loss 0.15144396 - time (sec): 6.18 - samples/sec: 3911.47 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-23 18:19:57,182 epoch 2 - iter 135/152 - loss 0.14911332 - time (sec): 7.01 - samples/sec: 3892.71 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-23 18:19:57,954 epoch 2 - iter 150/152 - loss 0.14321232 - time (sec): 7.78 - samples/sec: 3934.72 - lr: 0.000027 - momentum: 0.000000
103
+ 2023-10-23 18:19:58,052 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-23 18:19:58,052 EPOCH 2 done: loss 0.1424 - lr: 0.000027
105
+ 2023-10-23 18:19:58,905 DEV : loss 0.14702850580215454 - f1-score (micro avg) 0.7924
106
+ 2023-10-23 18:19:58,913 saving best model
107
+ 2023-10-23 18:19:59,472 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-23 18:20:00,334 epoch 3 - iter 15/152 - loss 0.06391830 - time (sec): 0.86 - samples/sec: 3370.68 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-23 18:20:01,135 epoch 3 - iter 30/152 - loss 0.06920391 - time (sec): 1.66 - samples/sec: 3759.95 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-23 18:20:01,975 epoch 3 - iter 45/152 - loss 0.08444799 - time (sec): 2.50 - samples/sec: 3780.32 - lr: 0.000026 - momentum: 0.000000
111
+ 2023-10-23 18:20:02,847 epoch 3 - iter 60/152 - loss 0.08218897 - time (sec): 3.37 - samples/sec: 3685.87 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-23 18:20:03,565 epoch 3 - iter 75/152 - loss 0.07841224 - time (sec): 4.09 - samples/sec: 3839.98 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-23 18:20:04,310 epoch 3 - iter 90/152 - loss 0.07548322 - time (sec): 4.84 - samples/sec: 3852.36 - lr: 0.000025 - momentum: 0.000000
114
+ 2023-10-23 18:20:05,182 epoch 3 - iter 105/152 - loss 0.07717780 - time (sec): 5.71 - samples/sec: 3766.44 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-23 18:20:06,039 epoch 3 - iter 120/152 - loss 0.07553394 - time (sec): 6.57 - samples/sec: 3780.26 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-23 18:20:06,888 epoch 3 - iter 135/152 - loss 0.07497682 - time (sec): 7.41 - samples/sec: 3727.66 - lr: 0.000024 - momentum: 0.000000
117
+ 2023-10-23 18:20:07,685 epoch 3 - iter 150/152 - loss 0.08015255 - time (sec): 8.21 - samples/sec: 3735.74 - lr: 0.000023 - momentum: 0.000000
118
+ 2023-10-23 18:20:07,797 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-23 18:20:07,797 EPOCH 3 done: loss 0.0807 - lr: 0.000023
120
+ 2023-10-23 18:20:08,644 DEV : loss 0.14846408367156982 - f1-score (micro avg) 0.7875
121
+ 2023-10-23 18:20:08,651 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-23 18:20:09,522 epoch 4 - iter 15/152 - loss 0.04146583 - time (sec): 0.87 - samples/sec: 3878.14 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-23 18:20:10,377 epoch 4 - iter 30/152 - loss 0.04382436 - time (sec): 1.72 - samples/sec: 3770.97 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-23 18:20:11,250 epoch 4 - iter 45/152 - loss 0.05477412 - time (sec): 2.60 - samples/sec: 3588.03 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-23 18:20:12,105 epoch 4 - iter 60/152 - loss 0.04640008 - time (sec): 3.45 - samples/sec: 3617.40 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-23 18:20:12,965 epoch 4 - iter 75/152 - loss 0.04581229 - time (sec): 4.31 - samples/sec: 3590.01 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-23 18:20:13,844 epoch 4 - iter 90/152 - loss 0.05157112 - time (sec): 5.19 - samples/sec: 3570.66 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-23 18:20:14,678 epoch 4 - iter 105/152 - loss 0.06028727 - time (sec): 6.02 - samples/sec: 3591.59 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-23 18:20:15,526 epoch 4 - iter 120/152 - loss 0.05892637 - time (sec): 6.87 - samples/sec: 3587.02 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-23 18:20:16,402 epoch 4 - iter 135/152 - loss 0.05678927 - time (sec): 7.75 - samples/sec: 3571.03 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-23 18:20:17,271 epoch 4 - iter 150/152 - loss 0.05572967 - time (sec): 8.62 - samples/sec: 3548.65 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-23 18:20:17,386 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-23 18:20:17,386 EPOCH 4 done: loss 0.0552 - lr: 0.000020
134
+ 2023-10-23 18:20:18,253 DEV : loss 0.1560734659433365 - f1-score (micro avg) 0.8216
135
+ 2023-10-23 18:20:18,260 saving best model
136
+ 2023-10-23 18:20:18,829 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-23 18:20:19,661 epoch 5 - iter 15/152 - loss 0.01895573 - time (sec): 0.83 - samples/sec: 3785.59 - lr: 0.000020 - momentum: 0.000000
138
+ 2023-10-23 18:20:20,531 epoch 5 - iter 30/152 - loss 0.03738480 - time (sec): 1.70 - samples/sec: 3588.93 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-23 18:20:21,386 epoch 5 - iter 45/152 - loss 0.04663379 - time (sec): 2.56 - samples/sec: 3658.12 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-23 18:20:22,235 epoch 5 - iter 60/152 - loss 0.04280235 - time (sec): 3.40 - samples/sec: 3627.69 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-23 18:20:23,086 epoch 5 - iter 75/152 - loss 0.04025851 - time (sec): 4.25 - samples/sec: 3688.14 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-23 18:20:23,909 epoch 5 - iter 90/152 - loss 0.03707620 - time (sec): 5.08 - samples/sec: 3678.00 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-23 18:20:24,760 epoch 5 - iter 105/152 - loss 0.03528057 - time (sec): 5.93 - samples/sec: 3658.21 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-23 18:20:25,609 epoch 5 - iter 120/152 - loss 0.03517572 - time (sec): 6.78 - samples/sec: 3647.27 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-23 18:20:26,467 epoch 5 - iter 135/152 - loss 0.03659409 - time (sec): 7.64 - samples/sec: 3614.77 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-23 18:20:27,329 epoch 5 - iter 150/152 - loss 0.03748552 - time (sec): 8.50 - samples/sec: 3591.66 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-23 18:20:27,433 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-23 18:20:27,433 EPOCH 5 done: loss 0.0388 - lr: 0.000017
149
+ 2023-10-23 18:20:28,329 DEV : loss 0.17505785822868347 - f1-score (micro avg) 0.82
150
+ 2023-10-23 18:20:28,337 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-23 18:20:29,209 epoch 6 - iter 15/152 - loss 0.07671918 - time (sec): 0.87 - samples/sec: 3587.02 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-23 18:20:30,069 epoch 6 - iter 30/152 - loss 0.04659880 - time (sec): 1.73 - samples/sec: 3469.36 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-23 18:20:30,926 epoch 6 - iter 45/152 - loss 0.04527842 - time (sec): 2.59 - samples/sec: 3568.63 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-23 18:20:31,782 epoch 6 - iter 60/152 - loss 0.03656474 - time (sec): 3.44 - samples/sec: 3532.81 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-23 18:20:32,631 epoch 6 - iter 75/152 - loss 0.03768485 - time (sec): 4.29 - samples/sec: 3528.16 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-23 18:20:33,496 epoch 6 - iter 90/152 - loss 0.03359681 - time (sec): 5.16 - samples/sec: 3495.68 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-23 18:20:34,370 epoch 6 - iter 105/152 - loss 0.03221236 - time (sec): 6.03 - samples/sec: 3500.09 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-23 18:20:35,205 epoch 6 - iter 120/152 - loss 0.03110637 - time (sec): 6.87 - samples/sec: 3552.19 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-23 18:20:36,059 epoch 6 - iter 135/152 - loss 0.03086084 - time (sec): 7.72 - samples/sec: 3549.93 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-23 18:20:36,922 epoch 6 - iter 150/152 - loss 0.02867945 - time (sec): 8.58 - samples/sec: 3575.30 - lr: 0.000013 - momentum: 0.000000
161
+ 2023-10-23 18:20:37,023 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-23 18:20:37,023 EPOCH 6 done: loss 0.0286 - lr: 0.000013
163
+ 2023-10-23 18:20:37,897 DEV : loss 0.213690847158432 - f1-score (micro avg) 0.8042
164
+ 2023-10-23 18:20:37,904 ----------------------------------------------------------------------------------------------------
165
+ 2023-10-23 18:20:38,775 epoch 7 - iter 15/152 - loss 0.01848948 - time (sec): 0.87 - samples/sec: 3605.57 - lr: 0.000013 - momentum: 0.000000
166
+ 2023-10-23 18:20:39,649 epoch 7 - iter 30/152 - loss 0.02345417 - time (sec): 1.74 - samples/sec: 3534.13 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-23 18:20:40,466 epoch 7 - iter 45/152 - loss 0.01960782 - time (sec): 2.56 - samples/sec: 3630.78 - lr: 0.000012 - momentum: 0.000000
168
+ 2023-10-23 18:20:41,328 epoch 7 - iter 60/152 - loss 0.01659578 - time (sec): 3.42 - samples/sec: 3677.30 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-23 18:20:42,192 epoch 7 - iter 75/152 - loss 0.01802838 - time (sec): 4.29 - samples/sec: 3632.53 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-23 18:20:43,067 epoch 7 - iter 90/152 - loss 0.01609284 - time (sec): 5.16 - samples/sec: 3606.92 - lr: 0.000011 - momentum: 0.000000
171
+ 2023-10-23 18:20:44,104 epoch 7 - iter 105/152 - loss 0.01693181 - time (sec): 6.20 - samples/sec: 3481.38 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-23 18:20:44,980 epoch 7 - iter 120/152 - loss 0.02051780 - time (sec): 7.07 - samples/sec: 3447.07 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-23 18:20:45,850 epoch 7 - iter 135/152 - loss 0.02240269 - time (sec): 7.94 - samples/sec: 3500.08 - lr: 0.000010 - momentum: 0.000000
174
+ 2023-10-23 18:20:46,714 epoch 7 - iter 150/152 - loss 0.02191603 - time (sec): 8.81 - samples/sec: 3484.81 - lr: 0.000010 - momentum: 0.000000
175
+ 2023-10-23 18:20:46,830 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-23 18:20:46,830 EPOCH 7 done: loss 0.0217 - lr: 0.000010
177
+ 2023-10-23 18:20:47,711 DEV : loss 0.20538194477558136 - f1-score (micro avg) 0.8298
178
+ 2023-10-23 18:20:47,719 saving best model
179
+ 2023-10-23 18:20:48,300 ----------------------------------------------------------------------------------------------------
180
+ 2023-10-23 18:20:49,154 epoch 8 - iter 15/152 - loss 0.03230665 - time (sec): 0.85 - samples/sec: 3154.08 - lr: 0.000010 - momentum: 0.000000
181
+ 2023-10-23 18:20:50,029 epoch 8 - iter 30/152 - loss 0.01668591 - time (sec): 1.73 - samples/sec: 3357.08 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-23 18:20:50,884 epoch 8 - iter 45/152 - loss 0.02251894 - time (sec): 2.58 - samples/sec: 3437.65 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-23 18:20:51,762 epoch 8 - iter 60/152 - loss 0.02137099 - time (sec): 3.46 - samples/sec: 3363.13 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-23 18:20:52,597 epoch 8 - iter 75/152 - loss 0.02250062 - time (sec): 4.30 - samples/sec: 3544.67 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-23 18:20:53,453 epoch 8 - iter 90/152 - loss 0.02719262 - time (sec): 5.15 - samples/sec: 3585.35 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-23 18:20:54,321 epoch 8 - iter 105/152 - loss 0.02531438 - time (sec): 6.02 - samples/sec: 3569.07 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-23 18:20:55,174 epoch 8 - iter 120/152 - loss 0.02258369 - time (sec): 6.87 - samples/sec: 3641.91 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-23 18:20:56,042 epoch 8 - iter 135/152 - loss 0.02136133 - time (sec): 7.74 - samples/sec: 3617.28 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-23 18:20:56,897 epoch 8 - iter 150/152 - loss 0.01996947 - time (sec): 8.60 - samples/sec: 3568.50 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-23 18:20:57,011 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-23 18:20:57,012 EPOCH 8 done: loss 0.0199 - lr: 0.000007
192
+ 2023-10-23 18:20:57,869 DEV : loss 0.21447792649269104 - f1-score (micro avg) 0.8333
193
+ 2023-10-23 18:20:57,877 saving best model
194
+ 2023-10-23 18:20:58,441 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-23 18:20:59,283 epoch 9 - iter 15/152 - loss 0.01725436 - time (sec): 0.84 - samples/sec: 3938.89 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-23 18:21:00,148 epoch 9 - iter 30/152 - loss 0.01283757 - time (sec): 1.70 - samples/sec: 3671.09 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-23 18:21:00,986 epoch 9 - iter 45/152 - loss 0.01772803 - time (sec): 2.54 - samples/sec: 3708.49 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-23 18:21:01,843 epoch 9 - iter 60/152 - loss 0.01848425 - time (sec): 3.40 - samples/sec: 3532.67 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-23 18:21:02,696 epoch 9 - iter 75/152 - loss 0.01580778 - time (sec): 4.25 - samples/sec: 3604.89 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-23 18:21:03,553 epoch 9 - iter 90/152 - loss 0.01408170 - time (sec): 5.11 - samples/sec: 3579.45 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-23 18:21:04,389 epoch 9 - iter 105/152 - loss 0.01445924 - time (sec): 5.95 - samples/sec: 3594.29 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-23 18:21:05,258 epoch 9 - iter 120/152 - loss 0.01571336 - time (sec): 6.82 - samples/sec: 3577.20 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-23 18:21:06,133 epoch 9 - iter 135/152 - loss 0.01439284 - time (sec): 7.69 - samples/sec: 3576.32 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-23 18:21:07,008 epoch 9 - iter 150/152 - loss 0.01446179 - time (sec): 8.57 - samples/sec: 3577.22 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-23 18:21:07,117 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-23 18:21:07,117 EPOCH 9 done: loss 0.0143 - lr: 0.000004
207
+ 2023-10-23 18:21:08,043 DEV : loss 0.20278561115264893 - f1-score (micro avg) 0.844
208
+ 2023-10-23 18:21:08,053 saving best model
209
+ 2023-10-23 18:21:08,617 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-23 18:21:09,456 epoch 10 - iter 15/152 - loss 0.01131616 - time (sec): 0.84 - samples/sec: 3627.17 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-23 18:21:10,257 epoch 10 - iter 30/152 - loss 0.01668086 - time (sec): 1.64 - samples/sec: 3740.30 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-23 18:21:11,029 epoch 10 - iter 45/152 - loss 0.01181820 - time (sec): 2.41 - samples/sec: 3876.25 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-23 18:21:11,812 epoch 10 - iter 60/152 - loss 0.01505051 - time (sec): 3.19 - samples/sec: 3823.97 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-23 18:21:12,607 epoch 10 - iter 75/152 - loss 0.01291314 - time (sec): 3.99 - samples/sec: 3857.98 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-23 18:21:13,388 epoch 10 - iter 90/152 - loss 0.01284814 - time (sec): 4.77 - samples/sec: 3864.82 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-23 18:21:14,161 epoch 10 - iter 105/152 - loss 0.01282451 - time (sec): 5.54 - samples/sec: 3862.61 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-23 18:21:14,948 epoch 10 - iter 120/152 - loss 0.01439910 - time (sec): 6.33 - samples/sec: 3912.19 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-23 18:21:15,731 epoch 10 - iter 135/152 - loss 0.01333481 - time (sec): 7.11 - samples/sec: 3882.82 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-23 18:21:16,498 epoch 10 - iter 150/152 - loss 0.01248508 - time (sec): 7.88 - samples/sec: 3884.03 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-23 18:21:16,596 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-23 18:21:16,596 EPOCH 10 done: loss 0.0123 - lr: 0.000000
222
+ 2023-10-23 18:21:17,550 DEV : loss 0.20392796397209167 - f1-score (micro avg) 0.8443
223
+ 2023-10-23 18:21:17,559 saving best model
224
+ 2023-10-23 18:21:18,564 ----------------------------------------------------------------------------------------------------
225
+ 2023-10-23 18:21:18,566 Loading model from best epoch ...
226
+ 2023-10-23 18:21:20,461 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-date, B-date, E-date, I-date, S-object, B-object, E-object, I-object
227
+ 2023-10-23 18:21:21,342
228
+ Results:
229
+ - F-score (micro) 0.8076
230
+ - F-score (macro) 0.6245
231
+ - Accuracy 0.6882
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ scope 0.7669 0.8278 0.7962 151
237
+ pers 0.7807 0.9271 0.8476 96
238
+ work 0.7664 0.8632 0.8119 95
239
+ loc 0.6667 0.6667 0.6667 3
240
+ date 0.0000 0.0000 0.0000 3
241
+
242
+ micro avg 0.7641 0.8563 0.8076 348
243
+ macro avg 0.5961 0.6569 0.6245 348
244
+ weighted avg 0.7631 0.8563 0.8067 348
245
+
246
+ 2023-10-23 18:21:21,342 ----------------------------------------------------------------------------------------------------