Hugging Face's logo

stefan-it
/
hmbench-newseye-fr-hmbert_tiny-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
5c72760
•
1 Parent(s): d54b424

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. runs/events.out.tfevents.1697744530.46dc0c540dd0.4731.2 +3 -0
  5. test.tsv +0 -0
  6. training.log +246 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a05d9cd5deb673f8798a209a7cfb9b6fdac5656ab18242db7c14d182fcbdec6d
3
+ size 19048098
dev.tsv ADDED
The diff for this file is too large to render. See raw diff
 
loss.tsv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ EPOCH TIMESTAMP LEARNING_RATE TRAIN_LOSS DEV_LOSS DEV_PRECISION DEV_RECALL DEV_F1 DEV_ACCURACY
2
+ 1 19:42:34 0.0000 1.4633 0.3700 0.0000 0.0000 0.0000 0.0000
3
+ 2 19:42:59 0.0000 0.4686 0.2753 0.3388 0.2259 0.2710 0.1626
4
+ 3 19:43:25 0.0000 0.3827 0.2444 0.3817 0.3796 0.3806 0.2514
5
+ 4 19:43:50 0.0000 0.3444 0.2286 0.4302 0.4109 0.4203 0.2838
6
+ 5 19:44:14 0.0000 0.3164 0.2194 0.4159 0.4272 0.4215 0.2873
7
+ 6 19:44:40 0.0000 0.2976 0.2139 0.4469 0.4463 0.4466 0.3080
8
+ 7 19:45:06 0.0000 0.2855 0.2066 0.4510 0.4762 0.4633 0.3223
9
+ 8 19:45:31 0.0000 0.2736 0.2065 0.4722 0.4857 0.4789 0.3346
10
+ 9 19:45:57 0.0000 0.2649 0.2024 0.4603 0.5048 0.4815 0.3373
11
+ 10 19:46:23 0.0000 0.2634 0.2016 0.4617 0.5007 0.4804 0.3367
runs/events.out.tfevents.1697744530.46dc0c540dd0.4731.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa60ea5ba57f0b68a50caa2b680a4d0060d5544e4290dfc3069f80cdd61956fc
3
+ size 502461
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-19 19:42:10,225 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-19 19:42:10,226 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(32001, 128)
7
+ (position_embeddings): Embedding(512, 128)
8
+ (token_type_embeddings): Embedding(2, 128)
9
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-1): 2 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=128, out_features=128, bias=True)
18
+ (key): Linear(in_features=128, out_features=128, bias=True)
19
+ (value): Linear(in_features=128, out_features=128, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=128, out_features=128, bias=True)
24
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=128, out_features=512, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=512, out_features=128, bias=True)
34
+ (LayerNorm): LayerNorm((128,), 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=128, out_features=128, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=128, out_features=17, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-19 19:42:10,226 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-19 19:42:10,226 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
+ 2023-10-19 19:42:10,226 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-19 19:42:10,226 Train: 7142 sentences
55
+ 2023-10-19 19:42:10,226 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-19 19:42:10,226 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-19 19:42:10,226 Training Params:
58
+ 2023-10-19 19:42:10,226 - learning_rate: "3e-05"
59
+ 2023-10-19 19:42:10,226 - mini_batch_size: "8"
60
+ 2023-10-19 19:42:10,226 - max_epochs: "10"
61
+ 2023-10-19 19:42:10,226 - shuffle: "True"
62
+ 2023-10-19 19:42:10,226 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-19 19:42:10,226 Plugins:
64
+ 2023-10-19 19:42:10,226 - TensorboardLogger
65
+ 2023-10-19 19:42:10,226 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-19 19:42:10,227 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-19 19:42:10,227 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-19 19:42:10,227 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-19 19:42:10,227 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-19 19:42:10,227 Computation:
71
+ 2023-10-19 19:42:10,227 - compute on device: cuda:0
72
+ 2023-10-19 19:42:10,227 - embedding storage: none
73
+ 2023-10-19 19:42:10,227 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-19 19:42:10,227 Model training base path: "hmbench-newseye/fr-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
75
+ 2023-10-19 19:42:10,227 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-19 19:42:10,227 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-19 19:42:10,227 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-19 19:42:12,499 epoch 1 - iter 89/893 - loss 3.42294852 - time (sec): 2.27 - samples/sec: 11786.11 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-19 19:42:14,750 epoch 1 - iter 178/893 - loss 3.24973616 - time (sec): 4.52 - samples/sec: 11380.29 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-19 19:42:17,036 epoch 1 - iter 267/893 - loss 2.92472187 - time (sec): 6.81 - samples/sec: 11321.04 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-19 19:42:19,445 epoch 1 - iter 356/893 - loss 2.58407417 - time (sec): 9.22 - samples/sec: 10852.87 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-19 19:42:21,815 epoch 1 - iter 445/893 - loss 2.24270513 - time (sec): 11.59 - samples/sec: 10780.32 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-19 19:42:24,038 epoch 1 - iter 534/893 - loss 1.99303527 - time (sec): 13.81 - samples/sec: 10815.88 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-19 19:42:26,284 epoch 1 - iter 623/893 - loss 1.81063405 - time (sec): 16.06 - samples/sec: 10852.24 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-19 19:42:28,688 epoch 1 - iter 712/893 - loss 1.66666224 - time (sec): 18.46 - samples/sec: 10870.25 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-19 19:42:30,952 epoch 1 - iter 801/893 - loss 1.55222766 - time (sec): 20.72 - samples/sec: 10924.19 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-19 19:42:33,153 epoch 1 - iter 890/893 - loss 1.46483452 - time (sec): 22.93 - samples/sec: 10827.74 - lr: 0.000030 - momentum: 0.000000
88
+ 2023-10-19 19:42:33,225 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-19 19:42:33,225 EPOCH 1 done: loss 1.4633 - lr: 0.000030
90
+ 2023-10-19 19:42:34,670 DEV : loss 0.37004899978637695 - f1-score (micro avg) 0.0
91
+ 2023-10-19 19:42:34,685 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-19 19:42:36,937 epoch 2 - iter 89/893 - loss 0.56991310 - time (sec): 2.25 - samples/sec: 10827.79 - lr: 0.000030 - momentum: 0.000000
93
+ 2023-10-19 19:42:39,232 epoch 2 - iter 178/893 - loss 0.51829563 - time (sec): 4.55 - samples/sec: 10988.57 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-19 19:42:41,570 epoch 2 - iter 267/893 - loss 0.51918911 - time (sec): 6.88 - samples/sec: 10943.58 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-19 19:42:43,885 epoch 2 - iter 356/893 - loss 0.50708102 - time (sec): 9.20 - samples/sec: 10975.86 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-19 19:42:46,150 epoch 2 - iter 445/893 - loss 0.49813056 - time (sec): 11.47 - samples/sec: 10761.12 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-19 19:42:48,412 epoch 2 - iter 534/893 - loss 0.48552781 - time (sec): 13.73 - samples/sec: 10827.25 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-19 19:42:50,698 epoch 2 - iter 623/893 - loss 0.48075918 - time (sec): 16.01 - samples/sec: 10836.03 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-19 19:42:52,988 epoch 2 - iter 712/893 - loss 0.48102198 - time (sec): 18.30 - samples/sec: 10908.04 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-19 19:42:55,169 epoch 2 - iter 801/893 - loss 0.47517621 - time (sec): 20.48 - samples/sec: 10910.74 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-19 19:42:57,403 epoch 2 - iter 890/893 - loss 0.46873055 - time (sec): 22.72 - samples/sec: 10918.99 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-19 19:42:57,476 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-19 19:42:57,476 EPOCH 2 done: loss 0.4686 - lr: 0.000027
104
+ 2023-10-19 19:42:59,798 DEV : loss 0.27531182765960693 - f1-score (micro avg) 0.271
105
+ 2023-10-19 19:42:59,812 saving best model
106
+ 2023-10-19 19:42:59,842 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-19 19:43:02,214 epoch 3 - iter 89/893 - loss 0.38596650 - time (sec): 2.37 - samples/sec: 9927.69 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-19 19:43:04,319 epoch 3 - iter 178/893 - loss 0.39477050 - time (sec): 4.48 - samples/sec: 10631.79 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-19 19:43:06,573 epoch 3 - iter 267/893 - loss 0.40926338 - time (sec): 6.73 - samples/sec: 10676.77 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-19 19:43:08,797 epoch 3 - iter 356/893 - loss 0.39975922 - time (sec): 8.95 - samples/sec: 10767.85 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-19 19:43:11,077 epoch 3 - iter 445/893 - loss 0.39903730 - time (sec): 11.23 - samples/sec: 10745.31 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-19 19:43:13,421 epoch 3 - iter 534/893 - loss 0.39669463 - time (sec): 13.58 - samples/sec: 10844.31 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-19 19:43:15,674 epoch 3 - iter 623/893 - loss 0.39311498 - time (sec): 15.83 - samples/sec: 10812.31 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-19 19:43:17,971 epoch 3 - iter 712/893 - loss 0.39258502 - time (sec): 18.13 - samples/sec: 10856.97 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-19 19:43:20,300 epoch 3 - iter 801/893 - loss 0.38428342 - time (sec): 20.46 - samples/sec: 10923.44 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-19 19:43:22,576 epoch 3 - iter 890/893 - loss 0.38254796 - time (sec): 22.73 - samples/sec: 10905.73 - lr: 0.000023 - momentum: 0.000000
117
+ 2023-10-19 19:43:22,657 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-19 19:43:22,657 EPOCH 3 done: loss 0.3827 - lr: 0.000023
119
+ 2023-10-19 19:43:25,008 DEV : loss 0.24437254667282104 - f1-score (micro avg) 0.3806
120
+ 2023-10-19 19:43:25,023 saving best model
121
+ 2023-10-19 19:43:25,061 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-19 19:43:27,203 epoch 4 - iter 89/893 - loss 0.38266866 - time (sec): 2.14 - samples/sec: 10963.05 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-19 19:43:29,424 epoch 4 - iter 178/893 - loss 0.36491384 - time (sec): 4.36 - samples/sec: 11065.18 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-19 19:43:31,745 epoch 4 - iter 267/893 - loss 0.36615042 - time (sec): 6.68 - samples/sec: 11134.67 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-19 19:43:34,104 epoch 4 - iter 356/893 - loss 0.36528656 - time (sec): 9.04 - samples/sec: 10703.86 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-19 19:43:36,429 epoch 4 - iter 445/893 - loss 0.35886848 - time (sec): 11.37 - samples/sec: 10649.20 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-19 19:43:38,724 epoch 4 - iter 534/893 - loss 0.35993741 - time (sec): 13.66 - samples/sec: 10697.14 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-19 19:43:41,003 epoch 4 - iter 623/893 - loss 0.35205696 - time (sec): 15.94 - samples/sec: 10784.30 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-19 19:43:43,250 epoch 4 - iter 712/893 - loss 0.35119897 - time (sec): 18.19 - samples/sec: 10840.13 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-19 19:43:45,525 epoch 4 - iter 801/893 - loss 0.34686215 - time (sec): 20.46 - samples/sec: 10881.75 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-19 19:43:47,797 epoch 4 - iter 890/893 - loss 0.34408543 - time (sec): 22.74 - samples/sec: 10913.42 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-19 19:43:47,875 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-19 19:43:47,875 EPOCH 4 done: loss 0.3444 - lr: 0.000020
134
+ 2023-10-19 19:43:50,697 DEV : loss 0.22855891287326813 - f1-score (micro avg) 0.4203
135
+ 2023-10-19 19:43:50,711 saving best model
136
+ 2023-10-19 19:43:50,743 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-19 19:43:52,824 epoch 5 - iter 89/893 - loss 0.31466381 - time (sec): 2.08 - samples/sec: 12234.69 - lr: 0.000020 - momentum: 0.000000
138
+ 2023-10-19 19:43:54,783 epoch 5 - iter 178/893 - loss 0.33259770 - time (sec): 4.04 - samples/sec: 12497.44 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-19 19:43:56,784 epoch 5 - iter 267/893 - loss 0.33327894 - time (sec): 6.04 - samples/sec: 12653.96 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-19 19:43:58,841 epoch 5 - iter 356/893 - loss 0.33596139 - time (sec): 8.10 - samples/sec: 12185.75 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-19 19:44:01,139 epoch 5 - iter 445/893 - loss 0.33259103 - time (sec): 10.39 - samples/sec: 11893.74 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-19 19:44:03,346 epoch 5 - iter 534/893 - loss 0.32763605 - time (sec): 12.60 - samples/sec: 11795.05 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-19 19:44:05,585 epoch 5 - iter 623/893 - loss 0.32488129 - time (sec): 14.84 - samples/sec: 11686.67 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-19 19:44:07,797 epoch 5 - iter 712/893 - loss 0.32110686 - time (sec): 17.05 - samples/sec: 11715.43 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-19 19:44:10,044 epoch 5 - iter 801/893 - loss 0.32002079 - time (sec): 19.30 - samples/sec: 11627.50 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-19 19:44:12,284 epoch 5 - iter 890/893 - loss 0.31595157 - time (sec): 21.54 - samples/sec: 11524.77 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-19 19:44:12,355 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-19 19:44:12,356 EPOCH 5 done: loss 0.3164 - lr: 0.000017
149
+ 2023-10-19 19:44:14,717 DEV : loss 0.21935363113880157 - f1-score (micro avg) 0.4215
150
+ 2023-10-19 19:44:14,733 saving best model
151
+ 2023-10-19 19:44:14,768 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-19 19:44:17,085 epoch 6 - iter 89/893 - loss 0.29676919 - time (sec): 2.32 - samples/sec: 10650.34 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-19 19:44:19,366 epoch 6 - iter 178/893 - loss 0.28651342 - time (sec): 4.60 - samples/sec: 10997.91 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-19 19:44:21,619 epoch 6 - iter 267/893 - loss 0.29160014 - time (sec): 6.85 - samples/sec: 11104.38 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-19 19:44:24,327 epoch 6 - iter 356/893 - loss 0.29690307 - time (sec): 9.56 - samples/sec: 10517.72 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-19 19:44:26,566 epoch 6 - iter 445/893 - loss 0.29916859 - time (sec): 11.80 - samples/sec: 10723.48 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-19 19:44:28,793 epoch 6 - iter 534/893 - loss 0.29847625 - time (sec): 14.02 - samples/sec: 10754.82 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-19 19:44:31,010 epoch 6 - iter 623/893 - loss 0.29921952 - time (sec): 16.24 - samples/sec: 10726.73 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-19 19:44:33,255 epoch 6 - iter 712/893 - loss 0.29877886 - time (sec): 18.49 - samples/sec: 10749.20 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-19 19:44:35,494 epoch 6 - iter 801/893 - loss 0.29509483 - time (sec): 20.73 - samples/sec: 10769.45 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-19 19:44:37,767 epoch 6 - iter 890/893 - loss 0.29708723 - time (sec): 23.00 - samples/sec: 10793.38 - lr: 0.000013 - momentum: 0.000000
162
+ 2023-10-19 19:44:37,841 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-19 19:44:37,841 EPOCH 6 done: loss 0.2976 - lr: 0.000013
164
+ 2023-10-19 19:44:40,209 DEV : loss 0.21392673254013062 - f1-score (micro avg) 0.4466
165
+ 2023-10-19 19:44:40,224 saving best model
166
+ 2023-10-19 19:44:40,259 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-19 19:44:42,366 epoch 7 - iter 89/893 - loss 0.28381710 - time (sec): 2.11 - samples/sec: 10978.42 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-19 19:44:44,619 epoch 7 - iter 178/893 - loss 0.28769399 - time (sec): 4.36 - samples/sec: 11038.25 - lr: 0.000013 - momentum: 0.000000
169
+ 2023-10-19 19:44:46,970 epoch 7 - iter 267/893 - loss 0.27591167 - time (sec): 6.71 - samples/sec: 10940.40 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-19 19:44:49,224 epoch 7 - iter 356/893 - loss 0.28249607 - time (sec): 8.96 - samples/sec: 10912.64 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-19 19:44:51,474 epoch 7 - iter 445/893 - loss 0.28466695 - time (sec): 11.21 - samples/sec: 10979.50 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-19 19:44:53,826 epoch 7 - iter 534/893 - loss 0.28087036 - time (sec): 13.57 - samples/sec: 10976.81 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-19 19:44:56,168 epoch 7 - iter 623/893 - loss 0.28248157 - time (sec): 15.91 - samples/sec: 10935.88 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-19 19:44:58,432 epoch 7 - iter 712/893 - loss 0.28429254 - time (sec): 18.17 - samples/sec: 10891.84 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-19 19:45:00,735 epoch 7 - iter 801/893 - loss 0.28458619 - time (sec): 20.47 - samples/sec: 10864.55 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-19 19:45:03,071 epoch 7 - iter 890/893 - loss 0.28601360 - time (sec): 22.81 - samples/sec: 10877.94 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-19 19:45:03,142 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-19 19:45:03,142 EPOCH 7 done: loss 0.2855 - lr: 0.000010
179
+ 2023-10-19 19:45:06,007 DEV : loss 0.20663976669311523 - f1-score (micro avg) 0.4633
180
+ 2023-10-19 19:45:06,021 saving best model
181
+ 2023-10-19 19:45:06,054 ----------------------------------------------------------------------------------------------------
182
+ 2023-10-19 19:45:08,190 epoch 8 - iter 89/893 - loss 0.29246080 - time (sec): 2.13 - samples/sec: 11859.54 - lr: 0.000010 - momentum: 0.000000
183
+ 2023-10-19 19:45:10,454 epoch 8 - iter 178/893 - loss 0.29078851 - time (sec): 4.40 - samples/sec: 11412.92 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-19 19:45:12,810 epoch 8 - iter 267/893 - loss 0.28731471 - time (sec): 6.76 - samples/sec: 10883.87 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-19 19:45:15,164 epoch 8 - iter 356/893 - loss 0.27721438 - time (sec): 9.11 - samples/sec: 10866.31 - lr: 0.000009 - momentum: 0.000000
186
+ 2023-10-19 19:45:17,447 epoch 8 - iter 445/893 - loss 0.27802466 - time (sec): 11.39 - samples/sec: 10804.34 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-19 19:45:19,738 epoch 8 - iter 534/893 - loss 0.27408626 - time (sec): 13.68 - samples/sec: 10978.00 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-19 19:45:21,951 epoch 8 - iter 623/893 - loss 0.27492437 - time (sec): 15.90 - samples/sec: 10899.44 - lr: 0.000008 - momentum: 0.000000
189
+ 2023-10-19 19:45:24,239 epoch 8 - iter 712/893 - loss 0.27135379 - time (sec): 18.18 - samples/sec: 10916.13 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-19 19:45:26,479 epoch 8 - iter 801/893 - loss 0.27250084 - time (sec): 20.42 - samples/sec: 10985.45 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-19 19:45:28,773 epoch 8 - iter 890/893 - loss 0.27431573 - time (sec): 22.72 - samples/sec: 10904.35 - lr: 0.000007 - momentum: 0.000000
192
+ 2023-10-19 19:45:28,850 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-19 19:45:28,850 EPOCH 8 done: loss 0.2736 - lr: 0.000007
194
+ 2023-10-19 19:45:31,203 DEV : loss 0.2064720094203949 - f1-score (micro avg) 0.4789
195
+ 2023-10-19 19:45:31,217 saving best model
196
+ 2023-10-19 19:45:31,253 ----------------------------------------------------------------------------------------------------
197
+ 2023-10-19 19:45:33,960 epoch 9 - iter 89/893 - loss 0.26816572 - time (sec): 2.71 - samples/sec: 8997.54 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-19 19:45:36,213 epoch 9 - iter 178/893 - loss 0.28006657 - time (sec): 4.96 - samples/sec: 9839.05 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-19 19:45:38,341 epoch 9 - iter 267/893 - loss 0.26771406 - time (sec): 7.09 - samples/sec: 10273.57 - lr: 0.000006 - momentum: 0.000000
200
+ 2023-10-19 19:45:40,606 epoch 9 - iter 356/893 - loss 0.27004687 - time (sec): 9.35 - samples/sec: 10530.02 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-19 19:45:42,932 epoch 9 - iter 445/893 - loss 0.26765570 - time (sec): 11.68 - samples/sec: 10486.10 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-19 19:45:45,279 epoch 9 - iter 534/893 - loss 0.26724294 - time (sec): 14.03 - samples/sec: 10598.37 - lr: 0.000005 - momentum: 0.000000
203
+ 2023-10-19 19:45:47,526 epoch 9 - iter 623/893 - loss 0.26654924 - time (sec): 16.27 - samples/sec: 10579.28 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-19 19:45:49,904 epoch 9 - iter 712/893 - loss 0.26579743 - time (sec): 18.65 - samples/sec: 10618.05 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-19 19:45:52,282 epoch 9 - iter 801/893 - loss 0.26907596 - time (sec): 21.03 - samples/sec: 10590.61 - lr: 0.000004 - momentum: 0.000000
206
+ 2023-10-19 19:45:54,610 epoch 9 - iter 890/893 - loss 0.26503635 - time (sec): 23.36 - samples/sec: 10613.49 - lr: 0.000003 - momentum: 0.000000
207
+ 2023-10-19 19:45:54,686 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-19 19:45:54,687 EPOCH 9 done: loss 0.2649 - lr: 0.000003
209
+ 2023-10-19 19:45:57,052 DEV : loss 0.20236296951770782 - f1-score (micro avg) 0.4815
210
+ 2023-10-19 19:45:57,067 saving best model
211
+ 2023-10-19 19:45:57,103 ----------------------------------------------------------------------------------------------------
212
+ 2023-10-19 19:45:59,463 epoch 10 - iter 89/893 - loss 0.27750107 - time (sec): 2.36 - samples/sec: 10578.50 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-19 19:46:01,785 epoch 10 - iter 178/893 - loss 0.27064008 - time (sec): 4.68 - samples/sec: 10750.61 - lr: 0.000003 - momentum: 0.000000
214
+ 2023-10-19 19:46:04,150 epoch 10 - iter 267/893 - loss 0.27340003 - time (sec): 7.05 - samples/sec: 10784.09 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-19 19:46:06,451 epoch 10 - iter 356/893 - loss 0.26540687 - time (sec): 9.35 - samples/sec: 10629.43 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-19 19:46:08,741 epoch 10 - iter 445/893 - loss 0.26753954 - time (sec): 11.64 - samples/sec: 10585.41 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-19 19:46:11,090 epoch 10 - iter 534/893 - loss 0.26905903 - time (sec): 13.99 - samples/sec: 10577.08 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-19 19:46:13,346 epoch 10 - iter 623/893 - loss 0.26904401 - time (sec): 16.24 - samples/sec: 10644.31 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-19 19:46:15,712 epoch 10 - iter 712/893 - loss 0.26416451 - time (sec): 18.61 - samples/sec: 10650.66 - lr: 0.000001 - momentum: 0.000000
220
+ 2023-10-19 19:46:17,960 epoch 10 - iter 801/893 - loss 0.26399106 - time (sec): 20.86 - samples/sec: 10656.47 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-19 19:46:20,248 epoch 10 - iter 890/893 - loss 0.26342787 - time (sec): 23.15 - samples/sec: 10724.28 - lr: 0.000000 - momentum: 0.000000
222
+ 2023-10-19 19:46:20,316 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-19 19:46:20,316 EPOCH 10 done: loss 0.2634 - lr: 0.000000
224
+ 2023-10-19 19:46:23,177 DEV : loss 0.20162628591060638 - f1-score (micro avg) 0.4804
225
+ 2023-10-19 19:46:23,221 ----------------------------------------------------------------------------------------------------
226
+ 2023-10-19 19:46:23,222 Loading model from best epoch ...
227
+ 2023-10-19 19:46:23,309 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
228
+ 2023-10-19 19:46:27,910
229
+ Results:
230
+ - F-score (micro) 0.3717
231
+ - F-score (macro) 0.2097
232
+ - Accuracy 0.2385
233
+
234
+ By class:
235
+ precision recall f1-score support
236
+
237
+ LOC 0.3806 0.4776 0.4237 1095
238
+ PER 0.3604 0.4348 0.3941 1012
239
+ ORG 0.0431 0.0140 0.0211 357
240
+ HumanProd 0.0000 0.0000 0.0000 33
241
+
242
+ micro avg 0.3571 0.3877 0.3717 2497
243
+ macro avg 0.1960 0.2316 0.2097 2497
244
+ weighted avg 0.3191 0.3877 0.3485 2497
245
+
246
+ 2023-10-19 19:46:27,910 ----------------------------------------------------------------------------------------------------