Hugging Face's logo

stefan-it
/
hmbench-icdar-nl-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3

Token Classification
Flair
PyTorch
TensorBoard
Dutch
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
9546cce
•
1 Parent(s): 768ee88

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.1697563682.bce904bcef33.2251.11 +3 -0
  5. test.tsv +0 -0
  6. training.log +236 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62ad8ac7117a3e6fbb28bf7efedc2a15e5c53b1df09737c63aec75f87c948175
3
+ size 440941957
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 17:28:58 0.0000 0.4040 0.0850 0.8677 0.7727 0.8175 0.6958
3
+ 2 17:29:56 0.0000 0.0854 0.1300 0.8436 0.5961 0.6985 0.5403
4
+ 3 17:30:56 0.0000 0.0622 0.0600 0.8711 0.8657 0.8684 0.7766
5
+ 4 17:31:55 0.0000 0.0420 0.0824 0.8895 0.8564 0.8726 0.7843
6
+ 5 17:32:53 0.0000 0.0318 0.1042 0.8916 0.8068 0.8471 0.7445
7
+ 6 17:33:50 0.0000 0.0252 0.1177 0.8776 0.8151 0.8452 0.7436
8
+ 7 17:34:48 0.0000 0.0174 0.1412 0.8994 0.8223 0.8591 0.7632
9
+ 8 17:35:46 0.0000 0.0125 0.1396 0.8836 0.8471 0.8650 0.7736
10
+ 9 17:36:43 0.0000 0.0078 0.1421 0.8823 0.8440 0.8627 0.7700
11
+ 10 17:37:41 0.0000 0.0055 0.1529 0.8836 0.8388 0.8606 0.7653
runs/events.out.tfevents.1697563682.bce904bcef33.2251.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b2561c0c83663e369ba3e6cf1de1e234ed243a1e09b3f69101f24b09909f4ec
3
+ size 407048
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,236 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 17:28:02,197 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 17:28:02,198 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): ElectraModel(
5
+ (embeddings): ElectraEmbeddings(
6
+ (word_embeddings): Embedding(32001, 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): ElectraEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x ElectraLayer(
15
+ (attention): ElectraAttention(
16
+ (self): ElectraSelfAttention(
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): ElectraSelfOutput(
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): ElectraIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): ElectraOutput(
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
+ )
41
+ )
42
+ (locked_dropout): LockedDropout(p=0.5)
43
+ (linear): Linear(in_features=768, out_features=13, bias=True)
44
+ (loss_function): CrossEntropyLoss()
45
+ )"
46
+ 2023-10-17 17:28:02,198 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 17:28:02,199 MultiCorpus: 5777 train + 722 dev + 723 test sentences
48
+ - NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /root/.flair/datasets/ner_icdar_europeana/nl
49
+ 2023-10-17 17:28:02,199 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 17:28:02,199 Train: 5777 sentences
51
+ 2023-10-17 17:28:02,199 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 17:28:02,199 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 17:28:02,199 Training Params:
54
+ 2023-10-17 17:28:02,199 - learning_rate: "5e-05"
55
+ 2023-10-17 17:28:02,199 - mini_batch_size: "8"
56
+ 2023-10-17 17:28:02,199 - max_epochs: "10"
57
+ 2023-10-17 17:28:02,199 - shuffle: "True"
58
+ 2023-10-17 17:28:02,199 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 17:28:02,199 Plugins:
60
+ 2023-10-17 17:28:02,199 - TensorboardLogger
61
+ 2023-10-17 17:28:02,199 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 17:28:02,199 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 17:28:02,199 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 17:28:02,199 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 17:28:02,199 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 17:28:02,199 Computation:
67
+ 2023-10-17 17:28:02,199 - compute on device: cuda:0
68
+ 2023-10-17 17:28:02,199 - embedding storage: none
69
+ 2023-10-17 17:28:02,199 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 17:28:02,199 Model training base path: "hmbench-icdar/nl-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3"
71
+ 2023-10-17 17:28:02,199 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 17:28:02,199 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 17:28:02,199 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 17:28:07,437 epoch 1 - iter 72/723 - loss 2.62229683 - time (sec): 5.24 - samples/sec: 3280.94 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 17:28:12,712 epoch 1 - iter 144/723 - loss 1.53564932 - time (sec): 10.51 - samples/sec: 3238.36 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 17:28:17,693 epoch 1 - iter 216/723 - loss 1.07363928 - time (sec): 15.49 - samples/sec: 3338.32 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 17:28:23,105 epoch 1 - iter 288/723 - loss 0.84654223 - time (sec): 20.90 - samples/sec: 3324.64 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 17:28:28,670 epoch 1 - iter 360/723 - loss 0.69584770 - time (sec): 26.47 - samples/sec: 3332.68 - lr: 0.000025 - momentum: 0.000000
79
+ 2023-10-17 17:28:33,963 epoch 1 - iter 432/723 - loss 0.59690308 - time (sec): 31.76 - samples/sec: 3353.05 - lr: 0.000030 - momentum: 0.000000
80
+ 2023-10-17 17:28:39,179 epoch 1 - iter 504/723 - loss 0.52741417 - time (sec): 36.98 - samples/sec: 3347.54 - lr: 0.000035 - momentum: 0.000000
81
+ 2023-10-17 17:28:44,472 epoch 1 - iter 576/723 - loss 0.47603842 - time (sec): 42.27 - samples/sec: 3345.25 - lr: 0.000040 - momentum: 0.000000
82
+ 2023-10-17 17:28:49,270 epoch 1 - iter 648/723 - loss 0.44069521 - time (sec): 47.07 - samples/sec: 3335.95 - lr: 0.000045 - momentum: 0.000000
83
+ 2023-10-17 17:28:54,524 epoch 1 - iter 720/723 - loss 0.40554441 - time (sec): 52.32 - samples/sec: 3352.88 - lr: 0.000050 - momentum: 0.000000
84
+ 2023-10-17 17:28:54,815 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 17:28:54,815 EPOCH 1 done: loss 0.4040 - lr: 0.000050
86
+ 2023-10-17 17:28:58,191 DEV : loss 0.08499432355165482 - f1-score (micro avg) 0.8175
87
+ 2023-10-17 17:28:58,207 saving best model
88
+ 2023-10-17 17:28:58,558 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 17:29:03,714 epoch 2 - iter 72/723 - loss 0.08166951 - time (sec): 5.16 - samples/sec: 3366.35 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 17:29:09,042 epoch 2 - iter 144/723 - loss 0.09238710 - time (sec): 10.48 - samples/sec: 3318.53 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 17:29:14,060 epoch 2 - iter 216/723 - loss 0.09656663 - time (sec): 15.50 - samples/sec: 3340.45 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 17:29:19,239 epoch 2 - iter 288/723 - loss 0.09515758 - time (sec): 20.68 - samples/sec: 3340.74 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 17:29:24,949 epoch 2 - iter 360/723 - loss 0.09351682 - time (sec): 26.39 - samples/sec: 3330.41 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 17:29:31,143 epoch 2 - iter 432/723 - loss 0.09171543 - time (sec): 32.58 - samples/sec: 3302.14 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 17:29:36,313 epoch 2 - iter 504/723 - loss 0.08991783 - time (sec): 37.75 - samples/sec: 3317.34 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 17:29:41,332 epoch 2 - iter 576/723 - loss 0.08743025 - time (sec): 42.77 - samples/sec: 3322.67 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 17:29:46,509 epoch 2 - iter 648/723 - loss 0.08684948 - time (sec): 47.95 - samples/sec: 3308.97 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 17:29:52,156 epoch 2 - iter 720/723 - loss 0.08531715 - time (sec): 53.60 - samples/sec: 3275.07 - lr: 0.000044 - momentum: 0.000000
99
+ 2023-10-17 17:29:52,352 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 17:29:52,352 EPOCH 2 done: loss 0.0854 - lr: 0.000044
101
+ 2023-10-17 17:29:56,717 DEV : loss 0.12996011972427368 - f1-score (micro avg) 0.6985
102
+ 2023-10-17 17:29:56,733 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-17 17:30:02,368 epoch 3 - iter 72/723 - loss 0.07263265 - time (sec): 5.63 - samples/sec: 3086.04 - lr: 0.000044 - momentum: 0.000000
104
+ 2023-10-17 17:30:08,080 epoch 3 - iter 144/723 - loss 0.06576995 - time (sec): 11.34 - samples/sec: 3162.51 - lr: 0.000043 - momentum: 0.000000
105
+ 2023-10-17 17:30:13,506 epoch 3 - iter 216/723 - loss 0.06486849 - time (sec): 16.77 - samples/sec: 3233.55 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 17:30:18,957 epoch 3 - iter 288/723 - loss 0.05999593 - time (sec): 22.22 - samples/sec: 3239.41 - lr: 0.000042 - momentum: 0.000000
107
+ 2023-10-17 17:30:24,068 epoch 3 - iter 360/723 - loss 0.05991573 - time (sec): 27.33 - samples/sec: 3235.14 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 17:30:29,685 epoch 3 - iter 432/723 - loss 0.06066152 - time (sec): 32.95 - samples/sec: 3234.13 - lr: 0.000041 - momentum: 0.000000
109
+ 2023-10-17 17:30:35,555 epoch 3 - iter 504/723 - loss 0.06270855 - time (sec): 38.82 - samples/sec: 3207.12 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 17:30:40,841 epoch 3 - iter 576/723 - loss 0.06209895 - time (sec): 44.11 - samples/sec: 3200.17 - lr: 0.000040 - momentum: 0.000000
111
+ 2023-10-17 17:30:46,401 epoch 3 - iter 648/723 - loss 0.06130730 - time (sec): 49.67 - samples/sec: 3186.94 - lr: 0.000039 - momentum: 0.000000
112
+ 2023-10-17 17:30:52,184 epoch 3 - iter 720/723 - loss 0.06221705 - time (sec): 55.45 - samples/sec: 3172.81 - lr: 0.000039 - momentum: 0.000000
113
+ 2023-10-17 17:30:52,371 ----------------------------------------------------------------------------------------------------
114
+ 2023-10-17 17:30:52,371 EPOCH 3 done: loss 0.0622 - lr: 0.000039
115
+ 2023-10-17 17:30:56,033 DEV : loss 0.06001274287700653 - f1-score (micro avg) 0.8684
116
+ 2023-10-17 17:30:56,053 saving best model
117
+ 2023-10-17 17:30:56,585 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-17 17:31:01,784 epoch 4 - iter 72/723 - loss 0.03813632 - time (sec): 5.20 - samples/sec: 3213.96 - lr: 0.000038 - momentum: 0.000000
119
+ 2023-10-17 17:31:07,908 epoch 4 - iter 144/723 - loss 0.03747693 - time (sec): 11.32 - samples/sec: 3060.36 - lr: 0.000038 - momentum: 0.000000
120
+ 2023-10-17 17:31:13,233 epoch 4 - iter 216/723 - loss 0.03936375 - time (sec): 16.64 - samples/sec: 3109.39 - lr: 0.000037 - momentum: 0.000000
121
+ 2023-10-17 17:31:18,623 epoch 4 - iter 288/723 - loss 0.04307423 - time (sec): 22.03 - samples/sec: 3142.16 - lr: 0.000037 - momentum: 0.000000
122
+ 2023-10-17 17:31:23,678 epoch 4 - iter 360/723 - loss 0.04236315 - time (sec): 27.09 - samples/sec: 3185.58 - lr: 0.000036 - momentum: 0.000000
123
+ 2023-10-17 17:31:29,478 epoch 4 - iter 432/723 - loss 0.04209825 - time (sec): 32.89 - samples/sec: 3158.73 - lr: 0.000036 - momentum: 0.000000
124
+ 2023-10-17 17:31:34,915 epoch 4 - iter 504/723 - loss 0.04200339 - time (sec): 38.33 - samples/sec: 3176.76 - lr: 0.000035 - momentum: 0.000000
125
+ 2023-10-17 17:31:40,837 epoch 4 - iter 576/723 - loss 0.04275515 - time (sec): 44.25 - samples/sec: 3185.87 - lr: 0.000034 - momentum: 0.000000
126
+ 2023-10-17 17:31:46,159 epoch 4 - iter 648/723 - loss 0.04212727 - time (sec): 49.57 - samples/sec: 3186.36 - lr: 0.000034 - momentum: 0.000000
127
+ 2023-10-17 17:31:51,490 epoch 4 - iter 720/723 - loss 0.04197729 - time (sec): 54.90 - samples/sec: 3201.14 - lr: 0.000033 - momentum: 0.000000
128
+ 2023-10-17 17:31:51,670 ----------------------------------------------------------------------------------------------------
129
+ 2023-10-17 17:31:51,671 EPOCH 4 done: loss 0.0420 - lr: 0.000033
130
+ 2023-10-17 17:31:55,071 DEV : loss 0.0824296697974205 - f1-score (micro avg) 0.8726
131
+ 2023-10-17 17:31:55,090 saving best model
132
+ 2023-10-17 17:31:55,766 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-17 17:32:01,345 epoch 5 - iter 72/723 - loss 0.02976008 - time (sec): 5.58 - samples/sec: 3219.59 - lr: 0.000033 - momentum: 0.000000
134
+ 2023-10-17 17:32:06,577 epoch 5 - iter 144/723 - loss 0.02756584 - time (sec): 10.81 - samples/sec: 3239.64 - lr: 0.000032 - momentum: 0.000000
135
+ 2023-10-17 17:32:12,023 epoch 5 - iter 216/723 - loss 0.03103086 - time (sec): 16.26 - samples/sec: 3261.33 - lr: 0.000032 - momentum: 0.000000
136
+ 2023-10-17 17:32:17,738 epoch 5 - iter 288/723 - loss 0.02922852 - time (sec): 21.97 - samples/sec: 3237.78 - lr: 0.000031 - momentum: 0.000000
137
+ 2023-10-17 17:32:23,061 epoch 5 - iter 360/723 - loss 0.02855856 - time (sec): 27.29 - samples/sec: 3222.87 - lr: 0.000031 - momentum: 0.000000
138
+ 2023-10-17 17:32:28,710 epoch 5 - iter 432/723 - loss 0.03052075 - time (sec): 32.94 - samples/sec: 3218.79 - lr: 0.000030 - momentum: 0.000000
139
+ 2023-10-17 17:32:34,177 epoch 5 - iter 504/723 - loss 0.03129817 - time (sec): 38.41 - samples/sec: 3228.96 - lr: 0.000029 - momentum: 0.000000
140
+ 2023-10-17 17:32:39,137 epoch 5 - iter 576/723 - loss 0.03242960 - time (sec): 43.37 - samples/sec: 3246.68 - lr: 0.000029 - momentum: 0.000000
141
+ 2023-10-17 17:32:44,212 epoch 5 - iter 648/723 - loss 0.03218350 - time (sec): 48.44 - samples/sec: 3259.18 - lr: 0.000028 - momentum: 0.000000
142
+ 2023-10-17 17:32:49,585 epoch 5 - iter 720/723 - loss 0.03177889 - time (sec): 53.82 - samples/sec: 3264.47 - lr: 0.000028 - momentum: 0.000000
143
+ 2023-10-17 17:32:49,775 ----------------------------------------------------------------------------------------------------
144
+ 2023-10-17 17:32:49,775 EPOCH 5 done: loss 0.0318 - lr: 0.000028
145
+ 2023-10-17 17:32:53,581 DEV : loss 0.10424862802028656 - f1-score (micro avg) 0.8471
146
+ 2023-10-17 17:32:53,601 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-17 17:32:58,963 epoch 6 - iter 72/723 - loss 0.02973653 - time (sec): 5.36 - samples/sec: 3496.63 - lr: 0.000027 - momentum: 0.000000
148
+ 2023-10-17 17:33:04,263 epoch 6 - iter 144/723 - loss 0.02285847 - time (sec): 10.66 - samples/sec: 3353.33 - lr: 0.000027 - momentum: 0.000000
149
+ 2023-10-17 17:33:09,929 epoch 6 - iter 216/723 - loss 0.02429447 - time (sec): 16.33 - samples/sec: 3326.30 - lr: 0.000026 - momentum: 0.000000
150
+ 2023-10-17 17:33:15,711 epoch 6 - iter 288/723 - loss 0.02499962 - time (sec): 22.11 - samples/sec: 3282.73 - lr: 0.000026 - momentum: 0.000000
151
+ 2023-10-17 17:33:20,942 epoch 6 - iter 360/723 - loss 0.02571431 - time (sec): 27.34 - samples/sec: 3278.43 - lr: 0.000025 - momentum: 0.000000
152
+ 2023-10-17 17:33:26,294 epoch 6 - iter 432/723 - loss 0.02517103 - time (sec): 32.69 - samples/sec: 3294.69 - lr: 0.000024 - momentum: 0.000000
153
+ 2023-10-17 17:33:31,447 epoch 6 - iter 504/723 - loss 0.02605168 - time (sec): 37.84 - samples/sec: 3287.99 - lr: 0.000024 - momentum: 0.000000
154
+ 2023-10-17 17:33:36,580 epoch 6 - iter 576/723 - loss 0.02631389 - time (sec): 42.98 - samples/sec: 3304.30 - lr: 0.000023 - momentum: 0.000000
155
+ 2023-10-17 17:33:41,733 epoch 6 - iter 648/723 - loss 0.02543096 - time (sec): 48.13 - samples/sec: 3295.75 - lr: 0.000023 - momentum: 0.000000
156
+ 2023-10-17 17:33:46,823 epoch 6 - iter 720/723 - loss 0.02521898 - time (sec): 53.22 - samples/sec: 3302.40 - lr: 0.000022 - momentum: 0.000000
157
+ 2023-10-17 17:33:47,018 ----------------------------------------------------------------------------------------------------
158
+ 2023-10-17 17:33:47,018 EPOCH 6 done: loss 0.0252 - lr: 0.000022
159
+ 2023-10-17 17:33:50,373 DEV : loss 0.11773881316184998 - f1-score (micro avg) 0.8452
160
+ 2023-10-17 17:33:50,391 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-17 17:33:55,498 epoch 7 - iter 72/723 - loss 0.01211954 - time (sec): 5.11 - samples/sec: 3363.93 - lr: 0.000022 - momentum: 0.000000
162
+ 2023-10-17 17:34:00,867 epoch 7 - iter 144/723 - loss 0.01732599 - time (sec): 10.47 - samples/sec: 3294.18 - lr: 0.000021 - momentum: 0.000000
163
+ 2023-10-17 17:34:06,234 epoch 7 - iter 216/723 - loss 0.01866389 - time (sec): 15.84 - samples/sec: 3299.82 - lr: 0.000021 - momentum: 0.000000
164
+ 2023-10-17 17:34:11,575 epoch 7 - iter 288/723 - loss 0.02100187 - time (sec): 21.18 - samples/sec: 3323.79 - lr: 0.000020 - momentum: 0.000000
165
+ 2023-10-17 17:34:17,437 epoch 7 - iter 360/723 - loss 0.01933756 - time (sec): 27.04 - samples/sec: 3241.66 - lr: 0.000019 - momentum: 0.000000
166
+ 2023-10-17 17:34:22,923 epoch 7 - iter 432/723 - loss 0.01996565 - time (sec): 32.53 - samples/sec: 3262.22 - lr: 0.000019 - momentum: 0.000000
167
+ 2023-10-17 17:34:28,273 epoch 7 - iter 504/723 - loss 0.01973901 - time (sec): 37.88 - samples/sec: 3284.32 - lr: 0.000018 - momentum: 0.000000
168
+ 2023-10-17 17:34:33,625 epoch 7 - iter 576/723 - loss 0.01903934 - time (sec): 43.23 - samples/sec: 3274.98 - lr: 0.000018 - momentum: 0.000000
169
+ 2023-10-17 17:34:38,898 epoch 7 - iter 648/723 - loss 0.01808703 - time (sec): 48.51 - samples/sec: 3262.65 - lr: 0.000017 - momentum: 0.000000
170
+ 2023-10-17 17:34:44,431 epoch 7 - iter 720/723 - loss 0.01730273 - time (sec): 54.04 - samples/sec: 3245.34 - lr: 0.000017 - momentum: 0.000000
171
+ 2023-10-17 17:34:44,838 ----------------------------------------------------------------------------------------------------
172
+ 2023-10-17 17:34:44,838 EPOCH 7 done: loss 0.0174 - lr: 0.000017
173
+ 2023-10-17 17:34:48,262 DEV : loss 0.1411609798669815 - f1-score (micro avg) 0.8591
174
+ 2023-10-17 17:34:48,280 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-17 17:34:53,518 epoch 8 - iter 72/723 - loss 0.01428987 - time (sec): 5.24 - samples/sec: 3189.97 - lr: 0.000016 - momentum: 0.000000
176
+ 2023-10-17 17:34:59,013 epoch 8 - iter 144/723 - loss 0.00959426 - time (sec): 10.73 - samples/sec: 3163.77 - lr: 0.000016 - momentum: 0.000000
177
+ 2023-10-17 17:35:04,311 epoch 8 - iter 216/723 - loss 0.01074675 - time (sec): 16.03 - samples/sec: 3194.32 - lr: 0.000015 - momentum: 0.000000
178
+ 2023-10-17 17:35:09,779 epoch 8 - iter 288/723 - loss 0.01082205 - time (sec): 21.50 - samples/sec: 3207.07 - lr: 0.000014 - momentum: 0.000000
179
+ 2023-10-17 17:35:15,456 epoch 8 - iter 360/723 - loss 0.01174131 - time (sec): 27.17 - samples/sec: 3185.76 - lr: 0.000014 - momentum: 0.000000
180
+ 2023-10-17 17:35:20,762 epoch 8 - iter 432/723 - loss 0.01179153 - time (sec): 32.48 - samples/sec: 3199.23 - lr: 0.000013 - momentum: 0.000000
181
+ 2023-10-17 17:35:26,144 epoch 8 - iter 504/723 - loss 0.01159015 - time (sec): 37.86 - samples/sec: 3218.57 - lr: 0.000013 - momentum: 0.000000
182
+ 2023-10-17 17:35:31,465 epoch 8 - iter 576/723 - loss 0.01238696 - time (sec): 43.18 - samples/sec: 3231.32 - lr: 0.000012 - momentum: 0.000000
183
+ 2023-10-17 17:35:37,327 epoch 8 - iter 648/723 - loss 0.01238150 - time (sec): 49.05 - samples/sec: 3242.41 - lr: 0.000012 - momentum: 0.000000
184
+ 2023-10-17 17:35:42,459 epoch 8 - iter 720/723 - loss 0.01243442 - time (sec): 54.18 - samples/sec: 3241.49 - lr: 0.000011 - momentum: 0.000000
185
+ 2023-10-17 17:35:42,643 ----------------------------------------------------------------------------------------------------
186
+ 2023-10-17 17:35:42,643 EPOCH 8 done: loss 0.0125 - lr: 0.000011
187
+ 2023-10-17 17:35:46,562 DEV : loss 0.13958391547203064 - f1-score (micro avg) 0.865
188
+ 2023-10-17 17:35:46,583 ----------------------------------------------------------------------------------------------------
189
+ 2023-10-17 17:35:51,843 epoch 9 - iter 72/723 - loss 0.00536784 - time (sec): 5.26 - samples/sec: 3259.05 - lr: 0.000011 - momentum: 0.000000
190
+ 2023-10-17 17:35:57,193 epoch 9 - iter 144/723 - loss 0.00538410 - time (sec): 10.61 - samples/sec: 3301.20 - lr: 0.000010 - momentum: 0.000000
191
+ 2023-10-17 17:36:02,650 epoch 9 - iter 216/723 - loss 0.00537525 - time (sec): 16.07 - samples/sec: 3268.19 - lr: 0.000009 - momentum: 0.000000
192
+ 2023-10-17 17:36:08,285 epoch 9 - iter 288/723 - loss 0.00698419 - time (sec): 21.70 - samples/sec: 3267.87 - lr: 0.000009 - momentum: 0.000000
193
+ 2023-10-17 17:36:14,022 epoch 9 - iter 360/723 - loss 0.00741743 - time (sec): 27.44 - samples/sec: 3253.34 - lr: 0.000008 - momentum: 0.000000
194
+ 2023-10-17 17:36:19,237 epoch 9 - iter 432/723 - loss 0.00850564 - time (sec): 32.65 - samples/sec: 3272.18 - lr: 0.000008 - momentum: 0.000000
195
+ 2023-10-17 17:36:24,435 epoch 9 - iter 504/723 - loss 0.00834734 - time (sec): 37.85 - samples/sec: 3261.14 - lr: 0.000007 - momentum: 0.000000
196
+ 2023-10-17 17:36:29,366 epoch 9 - iter 576/723 - loss 0.00779422 - time (sec): 42.78 - samples/sec: 3263.01 - lr: 0.000007 - momentum: 0.000000
197
+ 2023-10-17 17:36:34,772 epoch 9 - iter 648/723 - loss 0.00761217 - time (sec): 48.19 - samples/sec: 3279.14 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-17 17:36:40,289 epoch 9 - iter 720/723 - loss 0.00782569 - time (sec): 53.70 - samples/sec: 3271.12 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-17 17:36:40,464 ----------------------------------------------------------------------------------------------------
200
+ 2023-10-17 17:36:40,464 EPOCH 9 done: loss 0.0078 - lr: 0.000006
201
+ 2023-10-17 17:36:43,871 DEV : loss 0.1421152502298355 - f1-score (micro avg) 0.8627
202
+ 2023-10-17 17:36:43,891 ----------------------------------------------------------------------------------------------------
203
+ 2023-10-17 17:36:49,280 epoch 10 - iter 72/723 - loss 0.01028871 - time (sec): 5.39 - samples/sec: 3344.29 - lr: 0.000005 - momentum: 0.000000
204
+ 2023-10-17 17:36:54,336 epoch 10 - iter 144/723 - loss 0.00650322 - time (sec): 10.44 - samples/sec: 3325.81 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-17 17:37:00,082 epoch 10 - iter 216/723 - loss 0.00664087 - time (sec): 16.19 - samples/sec: 3281.14 - lr: 0.000004 - momentum: 0.000000
206
+ 2023-10-17 17:37:05,727 epoch 10 - iter 288/723 - loss 0.00546743 - time (sec): 21.83 - samples/sec: 3259.82 - lr: 0.000003 - momentum: 0.000000
207
+ 2023-10-17 17:37:11,027 epoch 10 - iter 360/723 - loss 0.00555269 - time (sec): 27.13 - samples/sec: 3271.40 - lr: 0.000003 - momentum: 0.000000
208
+ 2023-10-17 17:37:16,744 epoch 10 - iter 432/723 - loss 0.00516482 - time (sec): 32.85 - samples/sec: 3237.38 - lr: 0.000002 - momentum: 0.000000
209
+ 2023-10-17 17:37:21,902 epoch 10 - iter 504/723 - loss 0.00532677 - time (sec): 38.01 - samples/sec: 3248.19 - lr: 0.000002 - momentum: 0.000000
210
+ 2023-10-17 17:37:27,390 epoch 10 - iter 576/723 - loss 0.00486427 - time (sec): 43.50 - samples/sec: 3241.67 - lr: 0.000001 - momentum: 0.000000
211
+ 2023-10-17 17:37:32,975 epoch 10 - iter 648/723 - loss 0.00551894 - time (sec): 49.08 - samples/sec: 3237.10 - lr: 0.000001 - momentum: 0.000000
212
+ 2023-10-17 17:37:38,248 epoch 10 - iter 720/723 - loss 0.00553918 - time (sec): 54.36 - samples/sec: 3235.06 - lr: 0.000000 - momentum: 0.000000
213
+ 2023-10-17 17:37:38,400 ----------------------------------------------------------------------------------------------------
214
+ 2023-10-17 17:37:38,401 EPOCH 10 done: loss 0.0055 - lr: 0.000000
215
+ 2023-10-17 17:37:41,831 DEV : loss 0.15293623507022858 - f1-score (micro avg) 0.8606
216
+ 2023-10-17 17:37:42,249 ----------------------------------------------------------------------------------------------------
217
+ 2023-10-17 17:37:42,251 Loading model from best epoch ...
218
+ 2023-10-17 17:37:44,011 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG
219
+ 2023-10-17 17:37:47,497
220
+ Results:
221
+ - F-score (micro) 0.86
222
+ - F-score (macro) 0.7669
223
+ - Accuracy 0.765
224
+
225
+ By class:
226
+ precision recall f1-score support
227
+
228
+ PER 0.8685 0.8361 0.8520 482
229
+ LOC 0.9177 0.9258 0.9217 458
230
+ ORG 0.4937 0.5652 0.5270 69
231
+
232
+ micro avg 0.8617 0.8583 0.8600 1009
233
+ macro avg 0.7600 0.7757 0.7669 1009
234
+ weighted avg 0.8652 0.8583 0.8614 1009
235
+
236
+ 2023-10-17 17:37:47,497 ----------------------------------------------------------------------------------------------------