Hugging Face's logo

stefan-it
/
hmbench-icdar-nl-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2

Token Classification
Flair
PyTorch
TensorBoard
Dutch
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
602b13b
•
1 Parent(s): f877f80

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.1697560912.bce904bcef33.2251.7 +3 -0
  5. test.tsv +0 -0
  6. training.log +237 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e52b6c3bb6edb42d3ba4395e77f94eb1c940059be0d283b671902ee66f0c11fe
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 16:42:47 0.0000 0.4293 0.0861 0.8237 0.7335 0.7760 0.6379
3
+ 2 16:43:44 0.0000 0.0871 0.0810 0.8752 0.7459 0.8054 0.6786
4
+ 3 16:44:40 0.0000 0.0636 0.0715 0.8654 0.8502 0.8577 0.7613
5
+ 4 16:45:39 0.0000 0.0443 0.0782 0.8596 0.8409 0.8501 0.7530
6
+ 5 16:46:35 0.0000 0.0319 0.1117 0.8875 0.8068 0.8452 0.7403
7
+ 6 16:47:30 0.0000 0.0237 0.1222 0.8964 0.7779 0.8330 0.7254
8
+ 7 16:48:27 0.0000 0.0181 0.1510 0.8968 0.8079 0.8500 0.7498
9
+ 8 16:49:23 0.0000 0.0122 0.1497 0.8841 0.8275 0.8549 0.7564
10
+ 9 16:50:19 0.0000 0.0092 0.1451 0.8869 0.8347 0.8600 0.7644
11
+ 10 16:51:16 0.0000 0.0060 0.1616 0.8918 0.8089 0.8483 0.7457
runs/events.out.tfevents.1697560912.bce904bcef33.2251.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30440a95b9bfc9128036ba445213e13f0fcbadb6544197d9d8374cc1ed339b04
3
+ size 407048
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,237 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 16:41:52,149 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 16:41:52,150 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 16:41:52,150 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 16:41:52,150 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 16:41:52,150 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 16:41:52,150 Train: 5777 sentences
51
+ 2023-10-17 16:41:52,150 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 16:41:52,150 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 16:41:52,151 Training Params:
54
+ 2023-10-17 16:41:52,151 - learning_rate: "5e-05"
55
+ 2023-10-17 16:41:52,151 - mini_batch_size: "8"
56
+ 2023-10-17 16:41:52,151 - max_epochs: "10"
57
+ 2023-10-17 16:41:52,151 - shuffle: "True"
58
+ 2023-10-17 16:41:52,151 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 16:41:52,151 Plugins:
60
+ 2023-10-17 16:41:52,151 - TensorboardLogger
61
+ 2023-10-17 16:41:52,151 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 16:41:52,151 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 16:41:52,151 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 16:41:52,151 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 16:41:52,151 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 16:41:52,151 Computation:
67
+ 2023-10-17 16:41:52,151 - compute on device: cuda:0
68
+ 2023-10-17 16:41:52,151 - embedding storage: none
69
+ 2023-10-17 16:41:52,151 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 16:41:52,151 Model training base path: "hmbench-icdar/nl-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2"
71
+ 2023-10-17 16:41:52,151 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 16:41:52,151 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 16:41:52,151 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 16:41:57,409 epoch 1 - iter 72/723 - loss 2.67948568 - time (sec): 5.26 - samples/sec: 3471.16 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 16:42:02,493 epoch 1 - iter 144/723 - loss 1.51756626 - time (sec): 10.34 - samples/sec: 3447.49 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 16:42:07,700 epoch 1 - iter 216/723 - loss 1.11928765 - time (sec): 15.55 - samples/sec: 3369.59 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 16:42:12,879 epoch 1 - iter 288/723 - loss 0.88170380 - time (sec): 20.73 - samples/sec: 3381.28 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 16:42:18,297 epoch 1 - iter 360/723 - loss 0.72889095 - time (sec): 26.14 - samples/sec: 3383.00 - lr: 0.000025 - momentum: 0.000000
79
+ 2023-10-17 16:42:23,461 epoch 1 - iter 432/723 - loss 0.63408298 - time (sec): 31.31 - samples/sec: 3377.27 - lr: 0.000030 - momentum: 0.000000
80
+ 2023-10-17 16:42:28,807 epoch 1 - iter 504/723 - loss 0.56269758 - time (sec): 36.66 - samples/sec: 3371.19 - lr: 0.000035 - momentum: 0.000000
81
+ 2023-10-17 16:42:34,061 epoch 1 - iter 576/723 - loss 0.50491815 - time (sec): 41.91 - samples/sec: 3371.37 - lr: 0.000040 - momentum: 0.000000
82
+ 2023-10-17 16:42:39,152 epoch 1 - iter 648/723 - loss 0.46295023 - time (sec): 47.00 - samples/sec: 3365.62 - lr: 0.000045 - momentum: 0.000000
83
+ 2023-10-17 16:42:44,485 epoch 1 - iter 720/723 - loss 0.43008419 - time (sec): 52.33 - samples/sec: 3358.72 - lr: 0.000050 - momentum: 0.000000
84
+ 2023-10-17 16:42:44,669 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 16:42:44,669 EPOCH 1 done: loss 0.4293 - lr: 0.000050
86
+ 2023-10-17 16:42:47,493 DEV : loss 0.08612097054719925 - f1-score (micro avg) 0.776
87
+ 2023-10-17 16:42:47,510 saving best model
88
+ 2023-10-17 16:42:47,882 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 16:42:52,928 epoch 2 - iter 72/723 - loss 0.12284217 - time (sec): 5.04 - samples/sec: 3280.92 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 16:42:57,952 epoch 2 - iter 144/723 - loss 0.10772593 - time (sec): 10.07 - samples/sec: 3328.33 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 16:43:03,507 epoch 2 - iter 216/723 - loss 0.09967815 - time (sec): 15.62 - samples/sec: 3264.64 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 16:43:08,830 epoch 2 - iter 288/723 - loss 0.09421738 - time (sec): 20.95 - samples/sec: 3291.54 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 16:43:13,997 epoch 2 - iter 360/723 - loss 0.09235624 - time (sec): 26.11 - samples/sec: 3291.59 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 16:43:19,442 epoch 2 - iter 432/723 - loss 0.08878323 - time (sec): 31.56 - samples/sec: 3332.33 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 16:43:24,817 epoch 2 - iter 504/723 - loss 0.08735342 - time (sec): 36.93 - samples/sec: 3331.92 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 16:43:29,935 epoch 2 - iter 576/723 - loss 0.08589435 - time (sec): 42.05 - samples/sec: 3329.59 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 16:43:35,289 epoch 2 - iter 648/723 - loss 0.08630544 - time (sec): 47.41 - samples/sec: 3336.84 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 16:43:40,514 epoch 2 - iter 720/723 - loss 0.08713654 - time (sec): 52.63 - samples/sec: 3339.30 - lr: 0.000044 - momentum: 0.000000
99
+ 2023-10-17 16:43:40,687 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 16:43:40,687 EPOCH 2 done: loss 0.0871 - lr: 0.000044
101
+ 2023-10-17 16:43:44,409 DEV : loss 0.08103517442941666 - f1-score (micro avg) 0.8054
102
+ 2023-10-17 16:43:44,429 saving best model
103
+ 2023-10-17 16:43:44,868 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 16:43:50,145 epoch 3 - iter 72/723 - loss 0.07033316 - time (sec): 5.27 - samples/sec: 3451.58 - lr: 0.000044 - momentum: 0.000000
105
+ 2023-10-17 16:43:55,281 epoch 3 - iter 144/723 - loss 0.06506614 - time (sec): 10.41 - samples/sec: 3398.46 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 16:44:00,931 epoch 3 - iter 216/723 - loss 0.06638678 - time (sec): 16.06 - samples/sec: 3389.15 - lr: 0.000043 - momentum: 0.000000
107
+ 2023-10-17 16:44:05,935 epoch 3 - iter 288/723 - loss 0.07045554 - time (sec): 21.06 - samples/sec: 3384.34 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 16:44:10,944 epoch 3 - iter 360/723 - loss 0.06881606 - time (sec): 26.07 - samples/sec: 3402.69 - lr: 0.000042 - momentum: 0.000000
109
+ 2023-10-17 16:44:16,239 epoch 3 - iter 432/723 - loss 0.06465933 - time (sec): 31.37 - samples/sec: 3410.62 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 16:44:21,124 epoch 3 - iter 504/723 - loss 0.06471377 - time (sec): 36.25 - samples/sec: 3404.19 - lr: 0.000041 - momentum: 0.000000
111
+ 2023-10-17 16:44:25,967 epoch 3 - iter 576/723 - loss 0.06437747 - time (sec): 41.10 - samples/sec: 3402.79 - lr: 0.000040 - momentum: 0.000000
112
+ 2023-10-17 16:44:31,384 epoch 3 - iter 648/723 - loss 0.06355648 - time (sec): 46.51 - samples/sec: 3391.68 - lr: 0.000039 - momentum: 0.000000
113
+ 2023-10-17 16:44:37,004 epoch 3 - iter 720/723 - loss 0.06347931 - time (sec): 52.13 - samples/sec: 3367.06 - lr: 0.000039 - momentum: 0.000000
114
+ 2023-10-17 16:44:37,239 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 16:44:37,240 EPOCH 3 done: loss 0.0636 - lr: 0.000039
116
+ 2023-10-17 16:44:40,614 DEV : loss 0.07145461440086365 - f1-score (micro avg) 0.8577
117
+ 2023-10-17 16:44:40,640 saving best model
118
+ 2023-10-17 16:44:41,173 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 16:44:46,600 epoch 4 - iter 72/723 - loss 0.03837137 - time (sec): 5.42 - samples/sec: 3284.40 - lr: 0.000038 - momentum: 0.000000
120
+ 2023-10-17 16:44:51,561 epoch 4 - iter 144/723 - loss 0.04438266 - time (sec): 10.38 - samples/sec: 3356.50 - lr: 0.000038 - momentum: 0.000000
121
+ 2023-10-17 16:44:56,563 epoch 4 - iter 216/723 - loss 0.03974982 - time (sec): 15.39 - samples/sec: 3354.19 - lr: 0.000037 - momentum: 0.000000
122
+ 2023-10-17 16:45:01,861 epoch 4 - iter 288/723 - loss 0.04252196 - time (sec): 20.68 - samples/sec: 3321.95 - lr: 0.000037 - momentum: 0.000000
123
+ 2023-10-17 16:45:07,950 epoch 4 - iter 360/723 - loss 0.04602468 - time (sec): 26.77 - samples/sec: 3239.10 - lr: 0.000036 - momentum: 0.000000
124
+ 2023-10-17 16:45:13,411 epoch 4 - iter 432/723 - loss 0.04676170 - time (sec): 32.24 - samples/sec: 3256.34 - lr: 0.000036 - momentum: 0.000000
125
+ 2023-10-17 16:45:18,763 epoch 4 - iter 504/723 - loss 0.04634358 - time (sec): 37.59 - samples/sec: 3265.53 - lr: 0.000035 - momentum: 0.000000
126
+ 2023-10-17 16:45:24,271 epoch 4 - iter 576/723 - loss 0.04532936 - time (sec): 43.10 - samples/sec: 3258.66 - lr: 0.000034 - momentum: 0.000000
127
+ 2023-10-17 16:45:29,844 epoch 4 - iter 648/723 - loss 0.04480859 - time (sec): 48.67 - samples/sec: 3247.61 - lr: 0.000034 - momentum: 0.000000
128
+ 2023-10-17 16:45:35,543 epoch 4 - iter 720/723 - loss 0.04434037 - time (sec): 54.37 - samples/sec: 3232.47 - lr: 0.000033 - momentum: 0.000000
129
+ 2023-10-17 16:45:35,705 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 16:45:35,706 EPOCH 4 done: loss 0.0443 - lr: 0.000033
131
+ 2023-10-17 16:45:39,119 DEV : loss 0.07815779000520706 - f1-score (micro avg) 0.8501
132
+ 2023-10-17 16:45:39,139 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-17 16:45:44,291 epoch 5 - iter 72/723 - loss 0.04048703 - time (sec): 5.15 - samples/sec: 3193.52 - lr: 0.000033 - momentum: 0.000000
134
+ 2023-10-17 16:45:49,767 epoch 5 - iter 144/723 - loss 0.03381670 - time (sec): 10.63 - samples/sec: 3201.78 - lr: 0.000032 - momentum: 0.000000
135
+ 2023-10-17 16:45:55,062 epoch 5 - iter 216/723 - loss 0.03374095 - time (sec): 15.92 - samples/sec: 3244.20 - lr: 0.000032 - momentum: 0.000000
136
+ 2023-10-17 16:45:59,942 epoch 5 - iter 288/723 - loss 0.03223050 - time (sec): 20.80 - samples/sec: 3260.69 - lr: 0.000031 - momentum: 0.000000
137
+ 2023-10-17 16:46:05,326 epoch 5 - iter 360/723 - loss 0.03202958 - time (sec): 26.19 - samples/sec: 3286.68 - lr: 0.000031 - momentum: 0.000000
138
+ 2023-10-17 16:46:10,429 epoch 5 - iter 432/723 - loss 0.03258311 - time (sec): 31.29 - samples/sec: 3309.95 - lr: 0.000030 - momentum: 0.000000
139
+ 2023-10-17 16:46:16,275 epoch 5 - iter 504/723 - loss 0.03307126 - time (sec): 37.13 - samples/sec: 3297.61 - lr: 0.000029 - momentum: 0.000000
140
+ 2023-10-17 16:46:22,011 epoch 5 - iter 576/723 - loss 0.03267137 - time (sec): 42.87 - samples/sec: 3298.91 - lr: 0.000029 - momentum: 0.000000
141
+ 2023-10-17 16:46:27,202 epoch 5 - iter 648/723 - loss 0.03133181 - time (sec): 48.06 - samples/sec: 3310.60 - lr: 0.000028 - momentum: 0.000000
142
+ 2023-10-17 16:46:32,072 epoch 5 - iter 720/723 - loss 0.03197385 - time (sec): 52.93 - samples/sec: 3316.95 - lr: 0.000028 - momentum: 0.000000
143
+ 2023-10-17 16:46:32,273 ----------------------------------------------------------------------------------------------------
144
+ 2023-10-17 16:46:32,274 EPOCH 5 done: loss 0.0319 - lr: 0.000028
145
+ 2023-10-17 16:46:35,912 DEV : loss 0.11172021180391312 - f1-score (micro avg) 0.8452
146
+ 2023-10-17 16:46:35,934 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-17 16:46:41,523 epoch 6 - iter 72/723 - loss 0.03952585 - time (sec): 5.59 - samples/sec: 3291.70 - lr: 0.000027 - momentum: 0.000000
148
+ 2023-10-17 16:46:46,742 epoch 6 - iter 144/723 - loss 0.02804880 - time (sec): 10.81 - samples/sec: 3289.62 - lr: 0.000027 - momentum: 0.000000
149
+ 2023-10-17 16:46:51,600 epoch 6 - iter 216/723 - loss 0.02574703 - time (sec): 15.66 - samples/sec: 3376.62 - lr: 0.000026 - momentum: 0.000000
150
+ 2023-10-17 16:46:56,779 epoch 6 - iter 288/723 - loss 0.02448115 - time (sec): 20.84 - samples/sec: 3372.80 - lr: 0.000026 - momentum: 0.000000
151
+ 2023-10-17 16:47:02,195 epoch 6 - iter 360/723 - loss 0.02459804 - time (sec): 26.26 - samples/sec: 3368.51 - lr: 0.000025 - momentum: 0.000000
152
+ 2023-10-17 16:47:07,405 epoch 6 - iter 432/723 - loss 0.02437003 - time (sec): 31.47 - samples/sec: 3392.17 - lr: 0.000024 - momentum: 0.000000
153
+ 2023-10-17 16:47:12,596 epoch 6 - iter 504/723 - loss 0.02308042 - time (sec): 36.66 - samples/sec: 3401.30 - lr: 0.000024 - momentum: 0.000000
154
+ 2023-10-17 16:47:17,452 epoch 6 - iter 576/723 - loss 0.02316493 - time (sec): 41.52 - samples/sec: 3399.71 - lr: 0.000023 - momentum: 0.000000
155
+ 2023-10-17 16:47:22,336 epoch 6 - iter 648/723 - loss 0.02348809 - time (sec): 46.40 - samples/sec: 3405.70 - lr: 0.000023 - momentum: 0.000000
156
+ 2023-10-17 16:47:27,338 epoch 6 - iter 720/723 - loss 0.02377909 - time (sec): 51.40 - samples/sec: 3414.88 - lr: 0.000022 - momentum: 0.000000
157
+ 2023-10-17 16:47:27,650 ----------------------------------------------------------------------------------------------------
158
+ 2023-10-17 16:47:27,650 EPOCH 6 done: loss 0.0237 - lr: 0.000022
159
+ 2023-10-17 16:47:30,926 DEV : loss 0.12220776081085205 - f1-score (micro avg) 0.833
160
+ 2023-10-17 16:47:30,943 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-17 16:47:36,396 epoch 7 - iter 72/723 - loss 0.01650496 - time (sec): 5.45 - samples/sec: 3376.92 - lr: 0.000022 - momentum: 0.000000
162
+ 2023-10-17 16:47:41,778 epoch 7 - iter 144/723 - loss 0.01360068 - time (sec): 10.83 - samples/sec: 3342.96 - lr: 0.000021 - momentum: 0.000000
163
+ 2023-10-17 16:47:46,812 epoch 7 - iter 216/723 - loss 0.01452251 - time (sec): 15.87 - samples/sec: 3352.48 - lr: 0.000021 - momentum: 0.000000
164
+ 2023-10-17 16:47:52,178 epoch 7 - iter 288/723 - loss 0.01645838 - time (sec): 21.23 - samples/sec: 3344.16 - lr: 0.000020 - momentum: 0.000000
165
+ 2023-10-17 16:47:57,861 epoch 7 - iter 360/723 - loss 0.01755396 - time (sec): 26.92 - samples/sec: 3306.69 - lr: 0.000019 - momentum: 0.000000
166
+ 2023-10-17 16:48:02,996 epoch 7 - iter 432/723 - loss 0.01683966 - time (sec): 32.05 - samples/sec: 3308.57 - lr: 0.000019 - momentum: 0.000000
167
+ 2023-10-17 16:48:08,362 epoch 7 - iter 504/723 - loss 0.01804620 - time (sec): 37.42 - samples/sec: 3283.71 - lr: 0.000018 - momentum: 0.000000
168
+ 2023-10-17 16:48:13,422 epoch 7 - iter 576/723 - loss 0.01858647 - time (sec): 42.48 - samples/sec: 3299.04 - lr: 0.000018 - momentum: 0.000000
169
+ 2023-10-17 16:48:18,612 epoch 7 - iter 648/723 - loss 0.01818199 - time (sec): 47.67 - samples/sec: 3299.05 - lr: 0.000017 - momentum: 0.000000
170
+ 2023-10-17 16:48:24,115 epoch 7 - iter 720/723 - loss 0.01814035 - time (sec): 53.17 - samples/sec: 3303.18 - lr: 0.000017 - momentum: 0.000000
171
+ 2023-10-17 16:48:24,307 ----------------------------------------------------------------------------------------------------
172
+ 2023-10-17 16:48:24,307 EPOCH 7 done: loss 0.0181 - lr: 0.000017
173
+ 2023-10-17 16:48:27,588 DEV : loss 0.151025652885437 - f1-score (micro avg) 0.85
174
+ 2023-10-17 16:48:27,609 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-17 16:48:32,780 epoch 8 - iter 72/723 - loss 0.01746000 - time (sec): 5.17 - samples/sec: 3309.45 - lr: 0.000016 - momentum: 0.000000
176
+ 2023-10-17 16:48:38,022 epoch 8 - iter 144/723 - loss 0.01354879 - time (sec): 10.41 - samples/sec: 3286.96 - lr: 0.000016 - momentum: 0.000000
177
+ 2023-10-17 16:48:43,458 epoch 8 - iter 216/723 - loss 0.01322560 - time (sec): 15.85 - samples/sec: 3284.27 - lr: 0.000015 - momentum: 0.000000
178
+ 2023-10-17 16:48:48,750 epoch 8 - iter 288/723 - loss 0.01336715 - time (sec): 21.14 - samples/sec: 3279.30 - lr: 0.000014 - momentum: 0.000000
179
+ 2023-10-17 16:48:53,653 epoch 8 - iter 360/723 - loss 0.01217760 - time (sec): 26.04 - samples/sec: 3282.41 - lr: 0.000014 - momentum: 0.000000
180
+ 2023-10-17 16:48:59,111 epoch 8 - iter 432/723 - loss 0.01159660 - time (sec): 31.50 - samples/sec: 3299.90 - lr: 0.000013 - momentum: 0.000000
181
+ 2023-10-17 16:49:04,309 epoch 8 - iter 504/723 - loss 0.01175992 - time (sec): 36.70 - samples/sec: 3331.35 - lr: 0.000013 - momentum: 0.000000
182
+ 2023-10-17 16:49:09,349 epoch 8 - iter 576/723 - loss 0.01287688 - time (sec): 41.74 - samples/sec: 3342.24 - lr: 0.000012 - momentum: 0.000000
183
+ 2023-10-17 16:49:14,737 epoch 8 - iter 648/723 - loss 0.01260778 - time (sec): 47.13 - samples/sec: 3348.97 - lr: 0.000012 - momentum: 0.000000
184
+ 2023-10-17 16:49:19,940 epoch 8 - iter 720/723 - loss 0.01205049 - time (sec): 52.33 - samples/sec: 3356.47 - lr: 0.000011 - momentum: 0.000000
185
+ 2023-10-17 16:49:20,099 ----------------------------------------------------------------------------------------------------
186
+ 2023-10-17 16:49:20,099 EPOCH 8 done: loss 0.0122 - lr: 0.000011
187
+ 2023-10-17 16:49:23,733 DEV : loss 0.1497245579957962 - f1-score (micro avg) 0.8549
188
+ 2023-10-17 16:49:23,750 ----------------------------------------------------------------------------------------------------
189
+ 2023-10-17 16:49:29,107 epoch 9 - iter 72/723 - loss 0.00992020 - time (sec): 5.36 - samples/sec: 3378.53 - lr: 0.000011 - momentum: 0.000000
190
+ 2023-10-17 16:49:34,981 epoch 9 - iter 144/723 - loss 0.01528820 - time (sec): 11.23 - samples/sec: 3281.60 - lr: 0.000010 - momentum: 0.000000
191
+ 2023-10-17 16:49:39,992 epoch 9 - iter 216/723 - loss 0.01243284 - time (sec): 16.24 - samples/sec: 3325.54 - lr: 0.000009 - momentum: 0.000000
192
+ 2023-10-17 16:49:45,206 epoch 9 - iter 288/723 - loss 0.01139342 - time (sec): 21.45 - samples/sec: 3322.35 - lr: 0.000009 - momentum: 0.000000
193
+ 2023-10-17 16:49:50,460 epoch 9 - iter 360/723 - loss 0.01161949 - time (sec): 26.71 - samples/sec: 3349.14 - lr: 0.000008 - momentum: 0.000000
194
+ 2023-10-17 16:49:55,643 epoch 9 - iter 432/723 - loss 0.01045204 - time (sec): 31.89 - samples/sec: 3359.81 - lr: 0.000008 - momentum: 0.000000
195
+ 2023-10-17 16:50:00,599 epoch 9 - iter 504/723 - loss 0.01053498 - time (sec): 36.85 - samples/sec: 3364.78 - lr: 0.000007 - momentum: 0.000000
196
+ 2023-10-17 16:50:05,600 epoch 9 - iter 576/723 - loss 0.00976123 - time (sec): 41.85 - samples/sec: 3373.15 - lr: 0.000007 - momentum: 0.000000
197
+ 2023-10-17 16:50:10,861 epoch 9 - iter 648/723 - loss 0.00958225 - time (sec): 47.11 - samples/sec: 3361.92 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-17 16:50:16,284 epoch 9 - iter 720/723 - loss 0.00921964 - time (sec): 52.53 - samples/sec: 3341.67 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-17 16:50:16,459 ----------------------------------------------------------------------------------------------------
200
+ 2023-10-17 16:50:16,459 EPOCH 9 done: loss 0.0092 - lr: 0.000006
201
+ 2023-10-17 16:50:19,623 DEV : loss 0.14509357511997223 - f1-score (micro avg) 0.86
202
+ 2023-10-17 16:50:19,640 saving best model
203
+ 2023-10-17 16:50:20,094 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-17 16:50:25,413 epoch 10 - iter 72/723 - loss 0.00606283 - time (sec): 5.31 - samples/sec: 3415.52 - lr: 0.000005 - momentum: 0.000000
205
+ 2023-10-17 16:50:30,233 epoch 10 - iter 144/723 - loss 0.00442758 - time (sec): 10.13 - samples/sec: 3442.56 - lr: 0.000004 - momentum: 0.000000
206
+ 2023-10-17 16:50:34,936 epoch 10 - iter 216/723 - loss 0.00436506 - time (sec): 14.84 - samples/sec: 3380.80 - lr: 0.000004 - momentum: 0.000000
207
+ 2023-10-17 16:50:40,577 epoch 10 - iter 288/723 - loss 0.00606399 - time (sec): 20.48 - samples/sec: 3309.01 - lr: 0.000003 - momentum: 0.000000
208
+ 2023-10-17 16:50:45,896 epoch 10 - iter 360/723 - loss 0.00559111 - time (sec): 25.80 - samples/sec: 3325.33 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-17 16:50:51,535 epoch 10 - iter 432/723 - loss 0.00537624 - time (sec): 31.44 - samples/sec: 3271.64 - lr: 0.000002 - momentum: 0.000000
210
+ 2023-10-17 16:50:56,965 epoch 10 - iter 504/723 - loss 0.00564013 - time (sec): 36.87 - samples/sec: 3274.74 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-17 16:51:02,222 epoch 10 - iter 576/723 - loss 0.00556250 - time (sec): 42.12 - samples/sec: 3287.06 - lr: 0.000001 - momentum: 0.000000
212
+ 2023-10-17 16:51:07,571 epoch 10 - iter 648/723 - loss 0.00584230 - time (sec): 47.47 - samples/sec: 3304.77 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-17 16:51:13,133 epoch 10 - iter 720/723 - loss 0.00597101 - time (sec): 53.03 - samples/sec: 3312.61 - lr: 0.000000 - momentum: 0.000000
214
+ 2023-10-17 16:51:13,317 ----------------------------------------------------------------------------------------------------
215
+ 2023-10-17 16:51:13,317 EPOCH 10 done: loss 0.0060 - lr: 0.000000
216
+ 2023-10-17 16:51:16,735 DEV : loss 0.1616183966398239 - f1-score (micro avg) 0.8483
217
+ 2023-10-17 16:51:17,091 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-17 16:51:17,092 Loading model from best epoch ...
219
+ 2023-10-17 16:51:18,421 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
220
+ 2023-10-17 16:51:21,216
221
+ Results:
222
+ - F-score (micro) 0.8458
223
+ - F-score (macro) 0.7427
224
+ - Accuracy 0.746
225
+
226
+ By class:
227
+ precision recall f1-score support
228
+
229
+ PER 0.8531 0.8195 0.8360 482
230
+ LOC 0.9417 0.8821 0.9109 458
231
+ ORG 0.5000 0.4638 0.4812 69
232
+
233
+ micro avg 0.8692 0.8236 0.8458 1009
234
+ macro avg 0.7650 0.7218 0.7427 1009
235
+ weighted avg 0.8692 0.8236 0.8457 1009
236
+
237
+ 2023-10-17 16:51:21,216 ----------------------------------------------------------------------------------------------------