Hugging Face's logo

stefan-it
/
hmbench-icdar-fr-hmbert-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2

Token Classification
Flair
PyTorch
French
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
d72aeda
·
1 Parent(s): e6febab

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. test.tsv +0 -0
  5. training.log +240 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcdf4667b9c6d79d131e40d2b3c8566faed108df2efcee65eda03b8aa12a533b
3
+ size 443311111
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 22:22:33 0.0000 0.4368 0.0990 0.6863 0.7127 0.6992 0.5536
3
+ 2 22:23:36 0.0000 0.1012 0.0944 0.7114 0.7862 0.7469 0.6123
4
+ 3 22:24:40 0.0000 0.0697 0.1071 0.7128 0.7862 0.7477 0.6150
5
+ 4 22:25:43 0.0000 0.0491 0.1333 0.7327 0.7658 0.7489 0.6160
6
+ 5 22:26:46 0.0000 0.0386 0.1475 0.7371 0.8054 0.7697 0.6438
7
+ 6 22:27:48 0.0000 0.0294 0.1888 0.7141 0.7771 0.7443 0.6123
8
+ 7 22:28:51 0.0000 0.0221 0.1875 0.7405 0.7907 0.7648 0.6366
9
+ 8 22:29:54 0.0000 0.0160 0.1971 0.7327 0.7907 0.7606 0.6297
10
+ 9 22:30:57 0.0000 0.0116 0.2116 0.7465 0.7828 0.7642 0.6349
11
+ 10 22:31:59 0.0000 0.0089 0.2155 0.7442 0.7964 0.7694 0.6423
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-13 22:21:32,062 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 22:21:32,063 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
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): 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=13, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-13 22:21:32,063 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 22:21:32,063 MultiCorpus: 7936 train + 992 dev + 992 test sentences
52
+ - NER_ICDAR_EUROPEANA Corpus: 7936 train + 992 dev + 992 test sentences - /root/.flair/datasets/ner_icdar_europeana/fr
53
+ 2023-10-13 22:21:32,063 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 22:21:32,063 Train: 7936 sentences
55
+ 2023-10-13 22:21:32,063 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 22:21:32,063 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 22:21:32,064 Training Params:
58
+ 2023-10-13 22:21:32,064 - learning_rate: "3e-05"
59
+ 2023-10-13 22:21:32,064 - mini_batch_size: "8"
60
+ 2023-10-13 22:21:32,064 - max_epochs: "10"
61
+ 2023-10-13 22:21:32,064 - shuffle: "True"
62
+ 2023-10-13 22:21:32,064 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 22:21:32,064 Plugins:
64
+ 2023-10-13 22:21:32,064 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 22:21:32,064 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 22:21:32,064 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 22:21:32,064 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 22:21:32,064 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 22:21:32,064 Computation:
70
+ 2023-10-13 22:21:32,064 - compute on device: cuda:0
71
+ 2023-10-13 22:21:32,064 - embedding storage: none
72
+ 2023-10-13 22:21:32,064 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 22:21:32,064 Model training base path: "hmbench-icdar/fr-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2"
74
+ 2023-10-13 22:21:32,064 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 22:21:32,064 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 22:21:38,226 epoch 1 - iter 99/992 - loss 2.33299355 - time (sec): 6.16 - samples/sec: 2821.27 - lr: 0.000003 - momentum: 0.000000
77
+ 2023-10-13 22:21:43,899 epoch 1 - iter 198/992 - loss 1.45654399 - time (sec): 11.83 - samples/sec: 2803.24 - lr: 0.000006 - momentum: 0.000000
78
+ 2023-10-13 22:21:49,704 epoch 1 - iter 297/992 - loss 1.08734806 - time (sec): 17.64 - samples/sec: 2777.39 - lr: 0.000009 - momentum: 0.000000
79
+ 2023-10-13 22:21:55,475 epoch 1 - iter 396/992 - loss 0.87857029 - time (sec): 23.41 - samples/sec: 2773.46 - lr: 0.000012 - momentum: 0.000000
80
+ 2023-10-13 22:22:01,199 epoch 1 - iter 495/992 - loss 0.74066449 - time (sec): 29.13 - samples/sec: 2783.19 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-13 22:22:07,235 epoch 1 - iter 594/992 - loss 0.64158469 - time (sec): 35.17 - samples/sec: 2778.31 - lr: 0.000018 - momentum: 0.000000
82
+ 2023-10-13 22:22:12,920 epoch 1 - iter 693/992 - loss 0.57302135 - time (sec): 40.86 - samples/sec: 2782.79 - lr: 0.000021 - momentum: 0.000000
83
+ 2023-10-13 22:22:18,655 epoch 1 - iter 792/992 - loss 0.51792287 - time (sec): 46.59 - samples/sec: 2794.99 - lr: 0.000024 - momentum: 0.000000
84
+ 2023-10-13 22:22:24,750 epoch 1 - iter 891/992 - loss 0.47364366 - time (sec): 52.68 - samples/sec: 2790.38 - lr: 0.000027 - momentum: 0.000000
85
+ 2023-10-13 22:22:30,602 epoch 1 - iter 990/992 - loss 0.43807375 - time (sec): 58.54 - samples/sec: 2793.01 - lr: 0.000030 - momentum: 0.000000
86
+ 2023-10-13 22:22:30,750 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 22:22:30,750 EPOCH 1 done: loss 0.4368 - lr: 0.000030
88
+ 2023-10-13 22:22:33,919 DEV : loss 0.09895769506692886 - f1-score (micro avg) 0.6992
89
+ 2023-10-13 22:22:33,940 saving best model
90
+ 2023-10-13 22:22:34,356 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 22:22:40,079 epoch 2 - iter 99/992 - loss 0.10440393 - time (sec): 5.72 - samples/sec: 2716.33 - lr: 0.000030 - momentum: 0.000000
92
+ 2023-10-13 22:22:45,944 epoch 2 - iter 198/992 - loss 0.10904220 - time (sec): 11.59 - samples/sec: 2709.89 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-13 22:22:52,058 epoch 2 - iter 297/992 - loss 0.10445266 - time (sec): 17.70 - samples/sec: 2738.80 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-13 22:22:57,812 epoch 2 - iter 396/992 - loss 0.10543564 - time (sec): 23.45 - samples/sec: 2776.19 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-13 22:23:03,822 epoch 2 - iter 495/992 - loss 0.10401639 - time (sec): 29.46 - samples/sec: 2761.40 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-13 22:23:09,512 epoch 2 - iter 594/992 - loss 0.10324383 - time (sec): 35.16 - samples/sec: 2769.06 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-13 22:23:15,203 epoch 2 - iter 693/992 - loss 0.10117912 - time (sec): 40.85 - samples/sec: 2773.98 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-13 22:23:21,294 epoch 2 - iter 792/992 - loss 0.10187508 - time (sec): 46.94 - samples/sec: 2770.45 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-13 22:23:27,242 epoch 2 - iter 891/992 - loss 0.10186016 - time (sec): 52.89 - samples/sec: 2763.64 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-13 22:23:33,244 epoch 2 - iter 990/992 - loss 0.10129833 - time (sec): 58.89 - samples/sec: 2778.25 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-13 22:23:33,369 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 22:23:33,370 EPOCH 2 done: loss 0.1012 - lr: 0.000027
103
+ 2023-10-13 22:23:36,856 DEV : loss 0.09443922340869904 - f1-score (micro avg) 0.7469
104
+ 2023-10-13 22:23:36,889 saving best model
105
+ 2023-10-13 22:23:37,421 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 22:23:44,041 epoch 3 - iter 99/992 - loss 0.07835091 - time (sec): 6.62 - samples/sec: 2418.55 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-13 22:23:49,988 epoch 3 - iter 198/992 - loss 0.07452825 - time (sec): 12.57 - samples/sec: 2565.06 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-13 22:23:55,653 epoch 3 - iter 297/992 - loss 0.06912775 - time (sec): 18.23 - samples/sec: 2646.29 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-13 22:24:01,450 epoch 3 - iter 396/992 - loss 0.07019004 - time (sec): 24.03 - samples/sec: 2688.30 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-13 22:24:07,403 epoch 3 - iter 495/992 - loss 0.06908856 - time (sec): 29.98 - samples/sec: 2698.01 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-13 22:24:13,363 epoch 3 - iter 594/992 - loss 0.06956091 - time (sec): 35.94 - samples/sec: 2710.32 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-13 22:24:19,337 epoch 3 - iter 693/992 - loss 0.07164602 - time (sec): 41.91 - samples/sec: 2708.74 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-13 22:24:25,264 epoch 3 - iter 792/992 - loss 0.07204638 - time (sec): 47.84 - samples/sec: 2726.73 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-13 22:24:31,199 epoch 3 - iter 891/992 - loss 0.07025467 - time (sec): 53.78 - samples/sec: 2740.60 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-13 22:24:37,045 epoch 3 - iter 990/992 - loss 0.06972650 - time (sec): 59.62 - samples/sec: 2746.36 - lr: 0.000023 - momentum: 0.000000
116
+ 2023-10-13 22:24:37,147 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 22:24:37,147 EPOCH 3 done: loss 0.0697 - lr: 0.000023
118
+ 2023-10-13 22:24:40,552 DEV : loss 0.10710007697343826 - f1-score (micro avg) 0.7477
119
+ 2023-10-13 22:24:40,575 saving best model
120
+ 2023-10-13 22:24:41,077 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 22:24:46,925 epoch 4 - iter 99/992 - loss 0.04664656 - time (sec): 5.84 - samples/sec: 2741.14 - lr: 0.000023 - momentum: 0.000000
122
+ 2023-10-13 22:24:53,063 epoch 4 - iter 198/992 - loss 0.04715979 - time (sec): 11.98 - samples/sec: 2768.98 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-13 22:24:59,015 epoch 4 - iter 297/992 - loss 0.04504200 - time (sec): 17.93 - samples/sec: 2753.00 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-13 22:25:04,781 epoch 4 - iter 396/992 - loss 0.04552468 - time (sec): 23.70 - samples/sec: 2777.07 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-13 22:25:10,615 epoch 4 - iter 495/992 - loss 0.04550867 - time (sec): 29.53 - samples/sec: 2791.41 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-13 22:25:16,451 epoch 4 - iter 594/992 - loss 0.04745191 - time (sec): 35.37 - samples/sec: 2789.76 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-13 22:25:22,220 epoch 4 - iter 693/992 - loss 0.04806225 - time (sec): 41.14 - samples/sec: 2786.19 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-13 22:25:28,218 epoch 4 - iter 792/992 - loss 0.04807101 - time (sec): 47.14 - samples/sec: 2781.22 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-13 22:25:33,783 epoch 4 - iter 891/992 - loss 0.04884662 - time (sec): 52.70 - samples/sec: 2795.26 - lr: 0.000020 - momentum: 0.000000
130
+ 2023-10-13 22:25:39,847 epoch 4 - iter 990/992 - loss 0.04904023 - time (sec): 58.77 - samples/sec: 2783.19 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-13 22:25:39,971 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 22:25:39,972 EPOCH 4 done: loss 0.0491 - lr: 0.000020
133
+ 2023-10-13 22:25:43,378 DEV : loss 0.1333416849374771 - f1-score (micro avg) 0.7489
134
+ 2023-10-13 22:25:43,398 saving best model
135
+ 2023-10-13 22:25:44,266 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-13 22:25:50,041 epoch 5 - iter 99/992 - loss 0.03508164 - time (sec): 5.77 - samples/sec: 2761.94 - lr: 0.000020 - momentum: 0.000000
137
+ 2023-10-13 22:25:55,794 epoch 5 - iter 198/992 - loss 0.03490154 - time (sec): 11.52 - samples/sec: 2811.59 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-13 22:26:01,520 epoch 5 - iter 297/992 - loss 0.03554118 - time (sec): 17.25 - samples/sec: 2835.25 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-13 22:26:07,492 epoch 5 - iter 396/992 - loss 0.03723271 - time (sec): 23.22 - samples/sec: 2830.39 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-13 22:26:13,620 epoch 5 - iter 495/992 - loss 0.03770116 - time (sec): 29.35 - samples/sec: 2814.86 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-13 22:26:19,504 epoch 5 - iter 594/992 - loss 0.03766517 - time (sec): 35.23 - samples/sec: 2797.30 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-13 22:26:25,285 epoch 5 - iter 693/992 - loss 0.03805744 - time (sec): 41.01 - samples/sec: 2792.03 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-13 22:26:31,050 epoch 5 - iter 792/992 - loss 0.03684000 - time (sec): 46.78 - samples/sec: 2788.99 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-13 22:26:37,088 epoch 5 - iter 891/992 - loss 0.03834438 - time (sec): 52.82 - samples/sec: 2790.28 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-13 22:26:42,739 epoch 5 - iter 990/992 - loss 0.03863747 - time (sec): 58.47 - samples/sec: 2796.55 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-13 22:26:42,895 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-13 22:26:42,895 EPOCH 5 done: loss 0.0386 - lr: 0.000017
148
+ 2023-10-13 22:26:46,395 DEV : loss 0.1474953144788742 - f1-score (micro avg) 0.7697
149
+ 2023-10-13 22:26:46,416 saving best model
150
+ 2023-10-13 22:26:46,900 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-13 22:26:52,655 epoch 6 - iter 99/992 - loss 0.03066144 - time (sec): 5.75 - samples/sec: 2870.08 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-13 22:26:58,650 epoch 6 - iter 198/992 - loss 0.02576809 - time (sec): 11.75 - samples/sec: 2842.92 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-13 22:27:04,479 epoch 6 - iter 297/992 - loss 0.02640387 - time (sec): 17.58 - samples/sec: 2865.75 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-13 22:27:10,420 epoch 6 - iter 396/992 - loss 0.02662851 - time (sec): 23.52 - samples/sec: 2839.78 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-13 22:27:16,188 epoch 6 - iter 495/992 - loss 0.02679061 - time (sec): 29.28 - samples/sec: 2812.92 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-13 22:27:22,018 epoch 6 - iter 594/992 - loss 0.02779911 - time (sec): 35.12 - samples/sec: 2804.97 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-13 22:27:27,615 epoch 6 - iter 693/992 - loss 0.02793110 - time (sec): 40.71 - samples/sec: 2789.84 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-13 22:27:33,725 epoch 6 - iter 792/992 - loss 0.02849861 - time (sec): 46.82 - samples/sec: 2800.86 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-13 22:27:39,500 epoch 6 - iter 891/992 - loss 0.03003150 - time (sec): 52.60 - samples/sec: 2796.36 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-13 22:27:45,315 epoch 6 - iter 990/992 - loss 0.02931730 - time (sec): 58.41 - samples/sec: 2799.63 - lr: 0.000013 - momentum: 0.000000
161
+ 2023-10-13 22:27:45,439 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-13 22:27:45,439 EPOCH 6 done: loss 0.0294 - lr: 0.000013
163
+ 2023-10-13 22:27:48,830 DEV : loss 0.18882010877132416 - f1-score (micro avg) 0.7443
164
+ 2023-10-13 22:27:48,850 ----------------------------------------------------------------------------------------------------
165
+ 2023-10-13 22:27:54,585 epoch 7 - iter 99/992 - loss 0.01843936 - time (sec): 5.73 - samples/sec: 2830.51 - lr: 0.000013 - momentum: 0.000000
166
+ 2023-10-13 22:28:00,478 epoch 7 - iter 198/992 - loss 0.01884112 - time (sec): 11.63 - samples/sec: 2775.82 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-13 22:28:07,139 epoch 7 - iter 297/992 - loss 0.02033178 - time (sec): 18.29 - samples/sec: 2712.51 - lr: 0.000012 - momentum: 0.000000
168
+ 2023-10-13 22:28:13,151 epoch 7 - iter 396/992 - loss 0.02087243 - time (sec): 24.30 - samples/sec: 2732.06 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-13 22:28:19,012 epoch 7 - iter 495/992 - loss 0.02087418 - time (sec): 30.16 - samples/sec: 2747.66 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-13 22:28:24,686 epoch 7 - iter 594/992 - loss 0.02171817 - time (sec): 35.83 - samples/sec: 2751.03 - lr: 0.000011 - momentum: 0.000000
171
+ 2023-10-13 22:28:30,346 epoch 7 - iter 693/992 - loss 0.02240224 - time (sec): 41.49 - samples/sec: 2767.35 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-13 22:28:36,072 epoch 7 - iter 792/992 - loss 0.02183838 - time (sec): 47.22 - samples/sec: 2779.85 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-13 22:28:41,868 epoch 7 - iter 891/992 - loss 0.02200465 - time (sec): 53.02 - samples/sec: 2773.88 - lr: 0.000010 - momentum: 0.000000
174
+ 2023-10-13 22:28:47,905 epoch 7 - iter 990/992 - loss 0.02214401 - time (sec): 59.05 - samples/sec: 2773.37 - lr: 0.000010 - momentum: 0.000000
175
+ 2023-10-13 22:28:48,003 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-13 22:28:48,003 EPOCH 7 done: loss 0.0221 - lr: 0.000010
177
+ 2023-10-13 22:28:51,462 DEV : loss 0.18745747208595276 - f1-score (micro avg) 0.7648
178
+ 2023-10-13 22:28:51,483 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-13 22:28:57,625 epoch 8 - iter 99/992 - loss 0.01733595 - time (sec): 6.14 - samples/sec: 2687.32 - lr: 0.000010 - momentum: 0.000000
180
+ 2023-10-13 22:29:03,732 epoch 8 - iter 198/992 - loss 0.01451052 - time (sec): 12.25 - samples/sec: 2732.96 - lr: 0.000009 - momentum: 0.000000
181
+ 2023-10-13 22:29:09,698 epoch 8 - iter 297/992 - loss 0.01458980 - time (sec): 18.21 - samples/sec: 2747.88 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-13 22:29:15,627 epoch 8 - iter 396/992 - loss 0.01434329 - time (sec): 24.14 - samples/sec: 2786.27 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-13 22:29:21,451 epoch 8 - iter 495/992 - loss 0.01589815 - time (sec): 29.97 - samples/sec: 2787.43 - lr: 0.000008 - momentum: 0.000000
184
+ 2023-10-13 22:29:27,300 epoch 8 - iter 594/992 - loss 0.01547773 - time (sec): 35.82 - samples/sec: 2772.84 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-13 22:29:33,240 epoch 8 - iter 693/992 - loss 0.01546711 - time (sec): 41.76 - samples/sec: 2752.58 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-13 22:29:39,317 epoch 8 - iter 792/992 - loss 0.01554967 - time (sec): 47.83 - samples/sec: 2748.23 - lr: 0.000007 - momentum: 0.000000
187
+ 2023-10-13 22:29:45,154 epoch 8 - iter 891/992 - loss 0.01624295 - time (sec): 53.67 - samples/sec: 2751.29 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-13 22:29:51,001 epoch 8 - iter 990/992 - loss 0.01584456 - time (sec): 59.52 - samples/sec: 2752.74 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-13 22:29:51,101 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-13 22:29:51,101 EPOCH 8 done: loss 0.0160 - lr: 0.000007
191
+ 2023-10-13 22:29:54,567 DEV : loss 0.19708073139190674 - f1-score (micro avg) 0.7606
192
+ 2023-10-13 22:29:54,588 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-13 22:30:00,193 epoch 9 - iter 99/992 - loss 0.00851250 - time (sec): 5.60 - samples/sec: 2638.38 - lr: 0.000006 - momentum: 0.000000
194
+ 2023-10-13 22:30:05,871 epoch 9 - iter 198/992 - loss 0.01387637 - time (sec): 11.28 - samples/sec: 2720.77 - lr: 0.000006 - momentum: 0.000000
195
+ 2023-10-13 22:30:11,835 epoch 9 - iter 297/992 - loss 0.01335263 - time (sec): 17.25 - samples/sec: 2715.07 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-13 22:30:17,685 epoch 9 - iter 396/992 - loss 0.01153281 - time (sec): 23.10 - samples/sec: 2735.71 - lr: 0.000005 - momentum: 0.000000
197
+ 2023-10-13 22:30:23,804 epoch 9 - iter 495/992 - loss 0.01105092 - time (sec): 29.21 - samples/sec: 2740.26 - lr: 0.000005 - momentum: 0.000000
198
+ 2023-10-13 22:30:29,756 epoch 9 - iter 594/992 - loss 0.01139772 - time (sec): 35.17 - samples/sec: 2748.28 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-13 22:30:35,469 epoch 9 - iter 693/992 - loss 0.01125951 - time (sec): 40.88 - samples/sec: 2762.21 - lr: 0.000004 - momentum: 0.000000
200
+ 2023-10-13 22:30:41,410 epoch 9 - iter 792/992 - loss 0.01144688 - time (sec): 46.82 - samples/sec: 2773.64 - lr: 0.000004 - momentum: 0.000000
201
+ 2023-10-13 22:30:47,347 epoch 9 - iter 891/992 - loss 0.01171083 - time (sec): 52.76 - samples/sec: 2778.18 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-13 22:30:53,864 epoch 9 - iter 990/992 - loss 0.01160068 - time (sec): 59.27 - samples/sec: 2759.87 - lr: 0.000003 - momentum: 0.000000
203
+ 2023-10-13 22:30:53,972 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-13 22:30:53,972 EPOCH 9 done: loss 0.0116 - lr: 0.000003
205
+ 2023-10-13 22:30:57,399 DEV : loss 0.21158859133720398 - f1-score (micro avg) 0.7642
206
+ 2023-10-13 22:30:57,420 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-13 22:31:03,143 epoch 10 - iter 99/992 - loss 0.01294454 - time (sec): 5.72 - samples/sec: 2871.83 - lr: 0.000003 - momentum: 0.000000
208
+ 2023-10-13 22:31:09,337 epoch 10 - iter 198/992 - loss 0.01174616 - time (sec): 11.92 - samples/sec: 2875.49 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-13 22:31:14,913 epoch 10 - iter 297/992 - loss 0.01070740 - time (sec): 17.49 - samples/sec: 2844.70 - lr: 0.000002 - momentum: 0.000000
210
+ 2023-10-13 22:31:20,657 epoch 10 - iter 396/992 - loss 0.01045205 - time (sec): 23.24 - samples/sec: 2850.69 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-13 22:31:26,862 epoch 10 - iter 495/992 - loss 0.01098101 - time (sec): 29.44 - samples/sec: 2830.26 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-13 22:31:32,596 epoch 10 - iter 594/992 - loss 0.01073008 - time (sec): 35.18 - samples/sec: 2824.57 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-13 22:31:38,266 epoch 10 - iter 693/992 - loss 0.01015657 - time (sec): 40.85 - samples/sec: 2806.63 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-13 22:31:44,347 epoch 10 - iter 792/992 - loss 0.00973608 - time (sec): 46.93 - samples/sec: 2792.56 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-13 22:31:50,396 epoch 10 - iter 891/992 - loss 0.00928079 - time (sec): 52.98 - samples/sec: 2788.54 - lr: 0.000000 - momentum: 0.000000
216
+ 2023-10-13 22:31:56,043 epoch 10 - iter 990/992 - loss 0.00889257 - time (sec): 58.62 - samples/sec: 2792.15 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-13 22:31:56,156 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-13 22:31:56,156 EPOCH 10 done: loss 0.0089 - lr: 0.000000
219
+ 2023-10-13 22:31:59,648 DEV : loss 0.21550461649894714 - f1-score (micro avg) 0.7694
220
+ 2023-10-13 22:32:00,091 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-13 22:32:00,092 Loading model from best epoch ...
222
+ 2023-10-13 22:32:01,548 SequenceTagger predicts: Dictionary with 13 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
223
+ 2023-10-13 22:32:04,837
224
+ Results:
225
+ - F-score (micro) 0.7902
226
+ - F-score (macro) 0.7068
227
+ - Accuracy 0.6763
228
+
229
+ By class:
230
+ precision recall f1-score support
231
+
232
+ LOC 0.8268 0.8748 0.8501 655
233
+ PER 0.7026 0.8475 0.7683 223
234
+ ORG 0.5259 0.4803 0.5021 127
235
+
236
+ micro avg 0.7635 0.8189 0.7902 1005
237
+ macro avg 0.6851 0.7342 0.7068 1005
238
+ weighted avg 0.7612 0.8189 0.7880 1005
239
+
240
+ 2023-10-13 22:32:04,837 ----------------------------------------------------------------------------------------------------