Hugging Face's logo

stefan-it
/
hmbench-newseye-fr-hmbert_64k-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
7b5f72f
·
1 Parent(s): 7e1a818

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 16:14:52,812 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-25 16:14:52,813 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 16:14:52,814 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-25 16:14:52,814 MultiCorpus: 7142 train + 698 dev + 2570 test sentences
52
+ - NER_HIPE_2022 Corpus: 7142 train + 698 dev + 2570 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fr/with_doc_seperator
53
+ 2023-10-25 16:14:52,814 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-25 16:14:52,814 Train: 7142 sentences
55
+ 2023-10-25 16:14:52,814 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-25 16:14:52,814 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-25 16:14:52,814 Training Params:
58
+ 2023-10-25 16:14:52,814 - learning_rate: "5e-05"
59
+ 2023-10-25 16:14:52,814 - mini_batch_size: "8"
60
+ 2023-10-25 16:14:52,815 - max_epochs: "10"
61
+ 2023-10-25 16:14:52,815 - shuffle: "True"
62
+ 2023-10-25 16:14:52,815 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-25 16:14:52,815 Plugins:
64
+ 2023-10-25 16:14:52,815 - TensorboardLogger
65
+ 2023-10-25 16:14:52,815 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-25 16:14:52,815 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-25 16:14:52,815 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-25 16:14:52,815 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-25 16:14:52,815 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-25 16:14:52,815 Computation:
71
+ 2023-10-25 16:14:52,815 - compute on device: cuda:0
72
+ 2023-10-25 16:14:52,815 - embedding storage: none
73
+ 2023-10-25 16:14:52,815 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-25 16:14:52,815 Model training base path: "hmbench-newseye/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3"
75
+ 2023-10-25 16:14:52,815 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-25 16:14:52,815 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-25 16:14:52,815 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-25 16:14:58,476 epoch 1 - iter 89/893 - loss 1.75249226 - time (sec): 5.66 - samples/sec: 4225.04 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-25 16:15:04,047 epoch 1 - iter 178/893 - loss 1.12358214 - time (sec): 11.23 - samples/sec: 4331.58 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-25 16:15:09,631 epoch 1 - iter 267/893 - loss 0.85862892 - time (sec): 16.81 - samples/sec: 4346.69 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-25 16:15:15,653 epoch 1 - iter 356/893 - loss 0.68950207 - time (sec): 22.84 - samples/sec: 4359.93 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-25 16:15:21,583 epoch 1 - iter 445/893 - loss 0.59145739 - time (sec): 28.77 - samples/sec: 4287.67 - lr: 0.000025 - momentum: 0.000000
83
+ 2023-10-25 16:15:27,239 epoch 1 - iter 534/893 - loss 0.52114142 - time (sec): 34.42 - samples/sec: 4306.58 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-25 16:15:32,900 epoch 1 - iter 623/893 - loss 0.46529929 - time (sec): 40.08 - samples/sec: 4352.66 - lr: 0.000035 - momentum: 0.000000
85
+ 2023-10-25 16:15:38,561 epoch 1 - iter 712/893 - loss 0.42604012 - time (sec): 45.75 - samples/sec: 4351.79 - lr: 0.000040 - momentum: 0.000000
86
+ 2023-10-25 16:15:44,304 epoch 1 - iter 801/893 - loss 0.39523829 - time (sec): 51.49 - samples/sec: 4338.77 - lr: 0.000045 - momentum: 0.000000
87
+ 2023-10-25 16:15:49,757 epoch 1 - iter 890/893 - loss 0.37145848 - time (sec): 56.94 - samples/sec: 4358.82 - lr: 0.000050 - momentum: 0.000000
88
+ 2023-10-25 16:15:49,923 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-25 16:15:49,923 EPOCH 1 done: loss 0.3708 - lr: 0.000050
90
+ 2023-10-25 16:15:53,793 DEV : loss 0.11669864505529404 - f1-score (micro avg) 0.7017
91
+ 2023-10-25 16:15:53,817 saving best model
92
+ 2023-10-25 16:15:54,256 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-25 16:16:00,060 epoch 2 - iter 89/893 - loss 0.09474515 - time (sec): 5.80 - samples/sec: 4339.83 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-25 16:16:05,594 epoch 2 - iter 178/893 - loss 0.10318396 - time (sec): 11.34 - samples/sec: 4160.10 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-25 16:16:11,390 epoch 2 - iter 267/893 - loss 0.10509808 - time (sec): 17.13 - samples/sec: 4224.80 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-25 16:16:17,233 epoch 2 - iter 356/893 - loss 0.10228761 - time (sec): 22.97 - samples/sec: 4354.62 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-25 16:16:22,957 epoch 2 - iter 445/893 - loss 0.10257400 - time (sec): 28.70 - samples/sec: 4341.65 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-25 16:16:28,542 epoch 2 - iter 534/893 - loss 0.10603402 - time (sec): 34.28 - samples/sec: 4337.53 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-25 16:16:34,303 epoch 2 - iter 623/893 - loss 0.10506118 - time (sec): 40.05 - samples/sec: 4338.75 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-25 16:16:39,929 epoch 2 - iter 712/893 - loss 0.10425592 - time (sec): 45.67 - samples/sec: 4328.82 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-25 16:16:45,809 epoch 2 - iter 801/893 - loss 0.10345125 - time (sec): 51.55 - samples/sec: 4331.43 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-25 16:16:51,516 epoch 2 - iter 890/893 - loss 0.10408064 - time (sec): 57.26 - samples/sec: 4330.98 - lr: 0.000044 - momentum: 0.000000
103
+ 2023-10-25 16:16:51,691 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-25 16:16:51,692 EPOCH 2 done: loss 0.1040 - lr: 0.000044
105
+ 2023-10-25 16:16:55,679 DEV : loss 0.10159432888031006 - f1-score (micro avg) 0.7568
106
+ 2023-10-25 16:16:55,697 saving best model
107
+ 2023-10-25 16:16:56,349 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-25 16:17:01,901 epoch 3 - iter 89/893 - loss 0.06874626 - time (sec): 5.55 - samples/sec: 4285.04 - lr: 0.000044 - momentum: 0.000000
109
+ 2023-10-25 16:17:07,545 epoch 3 - iter 178/893 - loss 0.06298047 - time (sec): 11.19 - samples/sec: 4308.04 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-25 16:17:12,918 epoch 3 - iter 267/893 - loss 0.06537415 - time (sec): 16.57 - samples/sec: 4389.94 - lr: 0.000043 - momentum: 0.000000
111
+ 2023-10-25 16:17:18,386 epoch 3 - iter 356/893 - loss 0.06543963 - time (sec): 22.03 - samples/sec: 4360.35 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-25 16:17:23,822 epoch 3 - iter 445/893 - loss 0.06548496 - time (sec): 27.47 - samples/sec: 4365.39 - lr: 0.000042 - momentum: 0.000000
113
+ 2023-10-25 16:17:29,478 epoch 3 - iter 534/893 - loss 0.06655645 - time (sec): 33.13 - samples/sec: 4387.73 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-25 16:17:35,152 epoch 3 - iter 623/893 - loss 0.06423904 - time (sec): 38.80 - samples/sec: 4396.78 - lr: 0.000041 - momentum: 0.000000
115
+ 2023-10-25 16:17:41,870 epoch 3 - iter 712/893 - loss 0.06350497 - time (sec): 45.52 - samples/sec: 4335.38 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-25 16:17:47,437 epoch 3 - iter 801/893 - loss 0.06463976 - time (sec): 51.09 - samples/sec: 4361.36 - lr: 0.000039 - momentum: 0.000000
117
+ 2023-10-25 16:17:52,859 epoch 3 - iter 890/893 - loss 0.06360620 - time (sec): 56.51 - samples/sec: 4387.69 - lr: 0.000039 - momentum: 0.000000
118
+ 2023-10-25 16:17:53,023 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-25 16:17:53,024 EPOCH 3 done: loss 0.0636 - lr: 0.000039
120
+ 2023-10-25 16:17:57,577 DEV : loss 0.12474026530981064 - f1-score (micro avg) 0.7885
121
+ 2023-10-25 16:17:57,598 saving best model
122
+ 2023-10-25 16:17:58,246 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-25 16:18:03,755 epoch 4 - iter 89/893 - loss 0.04272137 - time (sec): 5.51 - samples/sec: 4315.01 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-25 16:18:09,537 epoch 4 - iter 178/893 - loss 0.04287044 - time (sec): 11.29 - samples/sec: 4269.15 - lr: 0.000038 - momentum: 0.000000
125
+ 2023-10-25 16:18:15,017 epoch 4 - iter 267/893 - loss 0.04645572 - time (sec): 16.77 - samples/sec: 4258.22 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-25 16:18:20,857 epoch 4 - iter 356/893 - loss 0.04425794 - time (sec): 22.61 - samples/sec: 4315.23 - lr: 0.000037 - momentum: 0.000000
127
+ 2023-10-25 16:18:26,448 epoch 4 - iter 445/893 - loss 0.04423257 - time (sec): 28.20 - samples/sec: 4314.59 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-25 16:18:32,383 epoch 4 - iter 534/893 - loss 0.04415217 - time (sec): 34.14 - samples/sec: 4309.21 - lr: 0.000036 - momentum: 0.000000
129
+ 2023-10-25 16:18:38,252 epoch 4 - iter 623/893 - loss 0.04351186 - time (sec): 40.00 - samples/sec: 4308.17 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-25 16:18:44,167 epoch 4 - iter 712/893 - loss 0.04498748 - time (sec): 45.92 - samples/sec: 4323.66 - lr: 0.000034 - momentum: 0.000000
131
+ 2023-10-25 16:18:50,010 epoch 4 - iter 801/893 - loss 0.04527081 - time (sec): 51.76 - samples/sec: 4300.32 - lr: 0.000034 - momentum: 0.000000
132
+ 2023-10-25 16:18:55,870 epoch 4 - iter 890/893 - loss 0.04646286 - time (sec): 57.62 - samples/sec: 4307.11 - lr: 0.000033 - momentum: 0.000000
133
+ 2023-10-25 16:18:56,037 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-25 16:18:56,037 EPOCH 4 done: loss 0.0466 - lr: 0.000033
135
+ 2023-10-25 16:19:00,739 DEV : loss 0.14563852548599243 - f1-score (micro avg) 0.7995
136
+ 2023-10-25 16:19:00,759 saving best model
137
+ 2023-10-25 16:19:01,394 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-25 16:19:07,059 epoch 5 - iter 89/893 - loss 0.03479555 - time (sec): 5.66 - samples/sec: 4283.20 - lr: 0.000033 - momentum: 0.000000
139
+ 2023-10-25 16:19:12,717 epoch 5 - iter 178/893 - loss 0.03717067 - time (sec): 11.32 - samples/sec: 4246.28 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-25 16:19:18,650 epoch 5 - iter 267/893 - loss 0.03548914 - time (sec): 17.25 - samples/sec: 4224.53 - lr: 0.000032 - momentum: 0.000000
141
+ 2023-10-25 16:19:24,459 epoch 5 - iter 356/893 - loss 0.03481599 - time (sec): 23.06 - samples/sec: 4207.93 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-25 16:19:30,023 epoch 5 - iter 445/893 - loss 0.03447645 - time (sec): 28.63 - samples/sec: 4210.77 - lr: 0.000031 - momentum: 0.000000
143
+ 2023-10-25 16:19:35,602 epoch 5 - iter 534/893 - loss 0.03423318 - time (sec): 34.20 - samples/sec: 4226.86 - lr: 0.000030 - momentum: 0.000000
144
+ 2023-10-25 16:19:41,616 epoch 5 - iter 623/893 - loss 0.03457306 - time (sec): 40.22 - samples/sec: 4242.80 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-25 16:19:47,303 epoch 5 - iter 712/893 - loss 0.03473284 - time (sec): 45.91 - samples/sec: 4253.72 - lr: 0.000029 - momentum: 0.000000
146
+ 2023-10-25 16:19:53,078 epoch 5 - iter 801/893 - loss 0.03473047 - time (sec): 51.68 - samples/sec: 4308.69 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-25 16:19:58,731 epoch 5 - iter 890/893 - loss 0.03463942 - time (sec): 57.33 - samples/sec: 4328.07 - lr: 0.000028 - momentum: 0.000000
148
+ 2023-10-25 16:19:58,905 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-25 16:19:58,905 EPOCH 5 done: loss 0.0348 - lr: 0.000028
150
+ 2023-10-25 16:20:03,118 DEV : loss 0.15929269790649414 - f1-score (micro avg) 0.8035
151
+ 2023-10-25 16:20:03,139 saving best model
152
+ 2023-10-25 16:20:03,805 ----------------------------------------------------------------------------------------------------
153
+ 2023-10-25 16:20:10,697 epoch 6 - iter 89/893 - loss 0.02332392 - time (sec): 6.89 - samples/sec: 3453.26 - lr: 0.000027 - momentum: 0.000000
154
+ 2023-10-25 16:20:16,378 epoch 6 - iter 178/893 - loss 0.02637640 - time (sec): 12.57 - samples/sec: 3883.46 - lr: 0.000027 - momentum: 0.000000
155
+ 2023-10-25 16:20:22,209 epoch 6 - iter 267/893 - loss 0.02903353 - time (sec): 18.40 - samples/sec: 3994.50 - lr: 0.000026 - momentum: 0.000000
156
+ 2023-10-25 16:20:28,018 epoch 6 - iter 356/893 - loss 0.02755762 - time (sec): 24.21 - samples/sec: 4059.55 - lr: 0.000026 - momentum: 0.000000
157
+ 2023-10-25 16:20:34,069 epoch 6 - iter 445/893 - loss 0.02857473 - time (sec): 30.26 - samples/sec: 4082.88 - lr: 0.000025 - momentum: 0.000000
158
+ 2023-10-25 16:20:39,839 epoch 6 - iter 534/893 - loss 0.02933559 - time (sec): 36.03 - samples/sec: 4102.15 - lr: 0.000024 - momentum: 0.000000
159
+ 2023-10-25 16:20:45,844 epoch 6 - iter 623/893 - loss 0.02930823 - time (sec): 42.04 - samples/sec: 4110.00 - lr: 0.000024 - momentum: 0.000000
160
+ 2023-10-25 16:20:51,845 epoch 6 - iter 712/893 - loss 0.02914794 - time (sec): 48.04 - samples/sec: 4138.01 - lr: 0.000023 - momentum: 0.000000
161
+ 2023-10-25 16:20:57,419 epoch 6 - iter 801/893 - loss 0.02846516 - time (sec): 53.61 - samples/sec: 4158.83 - lr: 0.000023 - momentum: 0.000000
162
+ 2023-10-25 16:21:03,414 epoch 6 - iter 890/893 - loss 0.02806324 - time (sec): 59.61 - samples/sec: 4161.26 - lr: 0.000022 - momentum: 0.000000
163
+ 2023-10-25 16:21:03,591 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-25 16:21:03,592 EPOCH 6 done: loss 0.0281 - lr: 0.000022
165
+ 2023-10-25 16:21:07,987 DEV : loss 0.17629361152648926 - f1-score (micro avg) 0.8051
166
+ 2023-10-25 16:21:08,011 saving best model
167
+ 2023-10-25 16:21:08,670 ----------------------------------------------------------------------------------------------------
168
+ 2023-10-25 16:21:14,665 epoch 7 - iter 89/893 - loss 0.01807935 - time (sec): 5.99 - samples/sec: 4333.48 - lr: 0.000022 - momentum: 0.000000
169
+ 2023-10-25 16:21:20,552 epoch 7 - iter 178/893 - loss 0.01702157 - time (sec): 11.88 - samples/sec: 4331.32 - lr: 0.000021 - momentum: 0.000000
170
+ 2023-10-25 16:21:26,365 epoch 7 - iter 267/893 - loss 0.01856450 - time (sec): 17.69 - samples/sec: 4348.20 - lr: 0.000021 - momentum: 0.000000
171
+ 2023-10-25 16:21:31,968 epoch 7 - iter 356/893 - loss 0.01843919 - time (sec): 23.30 - samples/sec: 4380.43 - lr: 0.000020 - momentum: 0.000000
172
+ 2023-10-25 16:21:37,680 epoch 7 - iter 445/893 - loss 0.01921349 - time (sec): 29.01 - samples/sec: 4339.81 - lr: 0.000019 - momentum: 0.000000
173
+ 2023-10-25 16:21:43,467 epoch 7 - iter 534/893 - loss 0.01975706 - time (sec): 34.79 - samples/sec: 4351.56 - lr: 0.000019 - momentum: 0.000000
174
+ 2023-10-25 16:21:49,103 epoch 7 - iter 623/893 - loss 0.01986136 - time (sec): 40.43 - samples/sec: 4335.92 - lr: 0.000018 - momentum: 0.000000
175
+ 2023-10-25 16:21:54,799 epoch 7 - iter 712/893 - loss 0.01928109 - time (sec): 46.13 - samples/sec: 4326.33 - lr: 0.000018 - momentum: 0.000000
176
+ 2023-10-25 16:22:00,710 epoch 7 - iter 801/893 - loss 0.01923095 - time (sec): 52.04 - samples/sec: 4317.89 - lr: 0.000017 - momentum: 0.000000
177
+ 2023-10-25 16:22:06,598 epoch 7 - iter 890/893 - loss 0.01918290 - time (sec): 57.92 - samples/sec: 4282.24 - lr: 0.000017 - momentum: 0.000000
178
+ 2023-10-25 16:22:06,777 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-25 16:22:06,777 EPOCH 7 done: loss 0.0192 - lr: 0.000017
180
+ 2023-10-25 16:22:11,585 DEV : loss 0.19473356008529663 - f1-score (micro avg) 0.8021
181
+ 2023-10-25 16:22:11,607 ----------------------------------------------------------------------------------------------------
182
+ 2023-10-25 16:22:17,531 epoch 8 - iter 89/893 - loss 0.01959540 - time (sec): 5.92 - samples/sec: 4201.88 - lr: 0.000016 - momentum: 0.000000
183
+ 2023-10-25 16:22:23,194 epoch 8 - iter 178/893 - loss 0.01512738 - time (sec): 11.59 - samples/sec: 4143.22 - lr: 0.000016 - momentum: 0.000000
184
+ 2023-10-25 16:22:29,327 epoch 8 - iter 267/893 - loss 0.01384824 - time (sec): 17.72 - samples/sec: 4215.90 - lr: 0.000015 - momentum: 0.000000
185
+ 2023-10-25 16:22:35,277 epoch 8 - iter 356/893 - loss 0.01370296 - time (sec): 23.67 - samples/sec: 4183.57 - lr: 0.000014 - momentum: 0.000000
186
+ 2023-10-25 16:22:41,312 epoch 8 - iter 445/893 - loss 0.01389069 - time (sec): 29.70 - samples/sec: 4172.18 - lr: 0.000014 - momentum: 0.000000
187
+ 2023-10-25 16:22:47,286 epoch 8 - iter 534/893 - loss 0.01477066 - time (sec): 35.68 - samples/sec: 4207.64 - lr: 0.000013 - momentum: 0.000000
188
+ 2023-10-25 16:22:53,170 epoch 8 - iter 623/893 - loss 0.01437157 - time (sec): 41.56 - samples/sec: 4202.76 - lr: 0.000013 - momentum: 0.000000
189
+ 2023-10-25 16:22:59,064 epoch 8 - iter 712/893 - loss 0.01397568 - time (sec): 47.45 - samples/sec: 4207.65 - lr: 0.000012 - momentum: 0.000000
190
+ 2023-10-25 16:23:04,767 epoch 8 - iter 801/893 - loss 0.01390187 - time (sec): 53.16 - samples/sec: 4197.45 - lr: 0.000012 - momentum: 0.000000
191
+ 2023-10-25 16:23:10,581 epoch 8 - iter 890/893 - loss 0.01427908 - time (sec): 58.97 - samples/sec: 4205.45 - lr: 0.000011 - momentum: 0.000000
192
+ 2023-10-25 16:23:10,755 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-25 16:23:10,756 EPOCH 8 done: loss 0.0143 - lr: 0.000011
194
+ 2023-10-25 16:23:15,803 DEV : loss 0.1920691877603531 - f1-score (micro avg) 0.8
195
+ 2023-10-25 16:23:15,826 ----------------------------------------------------------------------------------------------------
196
+ 2023-10-25 16:23:21,740 epoch 9 - iter 89/893 - loss 0.00910264 - time (sec): 5.91 - samples/sec: 4529.19 - lr: 0.000011 - momentum: 0.000000
197
+ 2023-10-25 16:23:27,673 epoch 9 - iter 178/893 - loss 0.01115266 - time (sec): 11.85 - samples/sec: 4385.76 - lr: 0.000010 - momentum: 0.000000
198
+ 2023-10-25 16:23:33,568 epoch 9 - iter 267/893 - loss 0.00963172 - time (sec): 17.74 - samples/sec: 4396.12 - lr: 0.000009 - momentum: 0.000000
199
+ 2023-10-25 16:23:39,305 epoch 9 - iter 356/893 - loss 0.00981929 - time (sec): 23.48 - samples/sec: 4312.64 - lr: 0.000009 - momentum: 0.000000
200
+ 2023-10-25 16:23:44,931 epoch 9 - iter 445/893 - loss 0.01013183 - time (sec): 29.10 - samples/sec: 4248.67 - lr: 0.000008 - momentum: 0.000000
201
+ 2023-10-25 16:23:50,521 epoch 9 - iter 534/893 - loss 0.01006792 - time (sec): 34.69 - samples/sec: 4230.50 - lr: 0.000008 - momentum: 0.000000
202
+ 2023-10-25 16:23:56,224 epoch 9 - iter 623/893 - loss 0.00966847 - time (sec): 40.40 - samples/sec: 4263.72 - lr: 0.000007 - momentum: 0.000000
203
+ 2023-10-25 16:24:01,897 epoch 9 - iter 712/893 - loss 0.00963917 - time (sec): 46.07 - samples/sec: 4278.88 - lr: 0.000007 - momentum: 0.000000
204
+ 2023-10-25 16:24:07,419 epoch 9 - iter 801/893 - loss 0.00953469 - time (sec): 51.59 - samples/sec: 4291.48 - lr: 0.000006 - momentum: 0.000000
205
+ 2023-10-25 16:24:13,382 epoch 9 - iter 890/893 - loss 0.00931090 - time (sec): 57.55 - samples/sec: 4310.21 - lr: 0.000006 - momentum: 0.000000
206
+ 2023-10-25 16:24:13,561 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-25 16:24:13,562 EPOCH 9 done: loss 0.0093 - lr: 0.000006
208
+ 2023-10-25 16:24:17,665 DEV : loss 0.21395151317119598 - f1-score (micro avg) 0.7989
209
+ 2023-10-25 16:24:17,686 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-25 16:24:23,693 epoch 10 - iter 89/893 - loss 0.00447968 - time (sec): 6.01 - samples/sec: 4352.32 - lr: 0.000005 - momentum: 0.000000
211
+ 2023-10-25 16:24:29,482 epoch 10 - iter 178/893 - loss 0.00644700 - time (sec): 11.79 - samples/sec: 4259.83 - lr: 0.000004 - momentum: 0.000000
212
+ 2023-10-25 16:24:35,198 epoch 10 - iter 267/893 - loss 0.00651104 - time (sec): 17.51 - samples/sec: 4319.85 - lr: 0.000004 - momentum: 0.000000
213
+ 2023-10-25 16:24:41,020 epoch 10 - iter 356/893 - loss 0.00686979 - time (sec): 23.33 - samples/sec: 4260.72 - lr: 0.000003 - momentum: 0.000000
214
+ 2023-10-25 16:24:46,929 epoch 10 - iter 445/893 - loss 0.00690950 - time (sec): 29.24 - samples/sec: 4227.17 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-25 16:24:52,949 epoch 10 - iter 534/893 - loss 0.00654009 - time (sec): 35.26 - samples/sec: 4238.85 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-25 16:24:58,798 epoch 10 - iter 623/893 - loss 0.00647660 - time (sec): 41.11 - samples/sec: 4261.62 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-25 16:25:04,630 epoch 10 - iter 712/893 - loss 0.00632372 - time (sec): 46.94 - samples/sec: 4262.36 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-25 16:25:10,334 epoch 10 - iter 801/893 - loss 0.00654215 - time (sec): 52.65 - samples/sec: 4249.10 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-25 16:25:16,167 epoch 10 - iter 890/893 - loss 0.00615978 - time (sec): 58.48 - samples/sec: 4245.00 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-25 16:25:16,341 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-25 16:25:16,341 EPOCH 10 done: loss 0.0061 - lr: 0.000000
222
+ 2023-10-25 16:25:21,059 DEV : loss 0.2173573076725006 - f1-score (micro avg) 0.8064
223
+ 2023-10-25 16:25:21,080 saving best model
224
+ 2023-10-25 16:25:22,110 ----------------------------------------------------------------------------------------------------
225
+ 2023-10-25 16:25:22,112 Loading model from best epoch ...
226
+ 2023-10-25 16:25:23,975 SequenceTagger predicts: Dictionary with 17 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd
227
+ 2023-10-25 16:25:36,200
228
+ Results:
229
+ - F-score (micro) 0.6851
230
+ - F-score (macro) 0.6194
231
+ - Accuracy 0.537
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ LOC 0.6678 0.6941 0.6807 1095
237
+ PER 0.7727 0.7658 0.7692 1012
238
+ ORG 0.4590 0.5490 0.5000 357
239
+ HumanProd 0.4138 0.7273 0.5275 33
240
+
241
+ micro avg 0.6683 0.7028 0.6851 2497
242
+ macro avg 0.5783 0.6840 0.6194 2497
243
+ weighted avg 0.6771 0.7028 0.6887 2497
244
+
245
+ 2023-10-25 16:25:36,200 ----------------------------------------------------------------------------------------------------