Hugging Face's logo

stefan-it
/
hmbench-icdar-fr-hmbert-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1

Token Classification
Flair
PyTorch
French
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
f2e9927
•
1 Parent(s): e316c13

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 +239 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae870ec13f9f569359375798b8005d2f5ab287daab65f53eb49d127b04148f7a
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 21:38:26 0.0000 0.3542 0.0948 0.6737 0.7195 0.6958 0.5521
3
+ 2 21:39:30 0.0000 0.1033 0.0821 0.6747 0.7557 0.7129 0.5724
4
+ 3 21:40:33 0.0000 0.0722 0.1086 0.7298 0.7885 0.7580 0.6296
5
+ 4 21:41:37 0.0000 0.0499 0.1160 0.7773 0.7579 0.7675 0.6399
6
+ 5 21:42:41 0.0000 0.0408 0.1376 0.7489 0.7692 0.7589 0.6302
7
+ 6 21:43:44 0.0000 0.0288 0.1792 0.7459 0.7670 0.7563 0.6266
8
+ 7 21:44:48 0.0000 0.0217 0.1996 0.7380 0.7647 0.7511 0.6219
9
+ 8 21:45:51 0.0000 0.0157 0.2106 0.7318 0.7715 0.7511 0.6194
10
+ 9 21:46:54 0.0000 0.0107 0.2214 0.7366 0.7624 0.7493 0.6189
11
+ 10 21:47:57 0.0000 0.0072 0.2267 0.7393 0.7636 0.7513 0.6198
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-13 21:37:23,966 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 21:37:23,967 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 21:37:23,967 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 21:37:23,967 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 21:37:23,967 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 21:37:23,967 Train: 7936 sentences
55
+ 2023-10-13 21:37:23,967 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 21:37:23,967 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 21:37:23,967 Training Params:
58
+ 2023-10-13 21:37:23,967 - learning_rate: "5e-05"
59
+ 2023-10-13 21:37:23,968 - mini_batch_size: "8"
60
+ 2023-10-13 21:37:23,968 - max_epochs: "10"
61
+ 2023-10-13 21:37:23,968 - shuffle: "True"
62
+ 2023-10-13 21:37:23,968 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 21:37:23,968 Plugins:
64
+ 2023-10-13 21:37:23,968 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 21:37:23,968 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 21:37:23,968 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 21:37:23,968 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 21:37:23,968 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 21:37:23,968 Computation:
70
+ 2023-10-13 21:37:23,968 - compute on device: cuda:0
71
+ 2023-10-13 21:37:23,968 - embedding storage: none
72
+ 2023-10-13 21:37:23,968 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 21:37:23,968 Model training base path: "hmbench-icdar/fr-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
74
+ 2023-10-13 21:37:23,968 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 21:37:23,968 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 21:37:29,890 epoch 1 - iter 99/992 - loss 1.91261312 - time (sec): 5.92 - samples/sec: 2715.74 - lr: 0.000005 - momentum: 0.000000
77
+ 2023-10-13 21:37:35,908 epoch 1 - iter 198/992 - loss 1.13445665 - time (sec): 11.94 - samples/sec: 2727.88 - lr: 0.000010 - momentum: 0.000000
78
+ 2023-10-13 21:37:41,742 epoch 1 - iter 297/992 - loss 0.83788670 - time (sec): 17.77 - samples/sec: 2767.01 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-13 21:37:47,441 epoch 1 - iter 396/992 - loss 0.67694574 - time (sec): 23.47 - samples/sec: 2781.96 - lr: 0.000020 - momentum: 0.000000
80
+ 2023-10-13 21:37:53,157 epoch 1 - iter 495/992 - loss 0.57510064 - time (sec): 29.19 - samples/sec: 2789.19 - lr: 0.000025 - momentum: 0.000000
81
+ 2023-10-13 21:37:58,914 epoch 1 - iter 594/992 - loss 0.50275111 - time (sec): 34.95 - samples/sec: 2791.76 - lr: 0.000030 - momentum: 0.000000
82
+ 2023-10-13 21:38:04,772 epoch 1 - iter 693/992 - loss 0.44880423 - time (sec): 40.80 - samples/sec: 2810.61 - lr: 0.000035 - momentum: 0.000000
83
+ 2023-10-13 21:38:11,079 epoch 1 - iter 792/992 - loss 0.40684356 - time (sec): 47.11 - samples/sec: 2805.49 - lr: 0.000040 - momentum: 0.000000
84
+ 2023-10-13 21:38:16,874 epoch 1 - iter 891/992 - loss 0.37820026 - time (sec): 52.90 - samples/sec: 2799.25 - lr: 0.000045 - momentum: 0.000000
85
+ 2023-10-13 21:38:22,677 epoch 1 - iter 990/992 - loss 0.35457753 - time (sec): 58.71 - samples/sec: 2789.75 - lr: 0.000050 - momentum: 0.000000
86
+ 2023-10-13 21:38:22,786 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 21:38:22,786 EPOCH 1 done: loss 0.3542 - lr: 0.000050
88
+ 2023-10-13 21:38:26,277 DEV : loss 0.09475447982549667 - f1-score (micro avg) 0.6958
89
+ 2023-10-13 21:38:26,298 saving best model
90
+ 2023-10-13 21:38:26,721 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 21:38:32,814 epoch 2 - iter 99/992 - loss 0.12012769 - time (sec): 6.09 - samples/sec: 2833.35 - lr: 0.000049 - momentum: 0.000000
92
+ 2023-10-13 21:38:38,526 epoch 2 - iter 198/992 - loss 0.11631000 - time (sec): 11.80 - samples/sec: 2746.93 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-13 21:38:44,938 epoch 2 - iter 297/992 - loss 0.11145763 - time (sec): 18.22 - samples/sec: 2735.81 - lr: 0.000048 - momentum: 0.000000
94
+ 2023-10-13 21:38:50,662 epoch 2 - iter 396/992 - loss 0.10881005 - time (sec): 23.94 - samples/sec: 2704.74 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-13 21:38:56,694 epoch 2 - iter 495/992 - loss 0.10846778 - time (sec): 29.97 - samples/sec: 2740.68 - lr: 0.000047 - momentum: 0.000000
96
+ 2023-10-13 21:39:02,441 epoch 2 - iter 594/992 - loss 0.10567866 - time (sec): 35.72 - samples/sec: 2746.65 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-13 21:39:08,610 epoch 2 - iter 693/992 - loss 0.10559153 - time (sec): 41.89 - samples/sec: 2735.81 - lr: 0.000046 - momentum: 0.000000
98
+ 2023-10-13 21:39:14,672 epoch 2 - iter 792/992 - loss 0.10488835 - time (sec): 47.95 - samples/sec: 2722.53 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-13 21:39:20,740 epoch 2 - iter 891/992 - loss 0.10442316 - time (sec): 54.02 - samples/sec: 2727.03 - lr: 0.000045 - momentum: 0.000000
100
+ 2023-10-13 21:39:26,803 epoch 2 - iter 990/992 - loss 0.10329774 - time (sec): 60.08 - samples/sec: 2725.62 - lr: 0.000044 - momentum: 0.000000
101
+ 2023-10-13 21:39:26,916 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 21:39:26,916 EPOCH 2 done: loss 0.1033 - lr: 0.000044
103
+ 2023-10-13 21:39:30,341 DEV : loss 0.08205121755599976 - f1-score (micro avg) 0.7129
104
+ 2023-10-13 21:39:30,361 saving best model
105
+ 2023-10-13 21:39:30,861 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 21:39:36,742 epoch 3 - iter 99/992 - loss 0.07082610 - time (sec): 5.87 - samples/sec: 2789.48 - lr: 0.000044 - momentum: 0.000000
107
+ 2023-10-13 21:39:42,620 epoch 3 - iter 198/992 - loss 0.06839682 - time (sec): 11.75 - samples/sec: 2713.38 - lr: 0.000043 - momentum: 0.000000
108
+ 2023-10-13 21:39:48,758 epoch 3 - iter 297/992 - loss 0.06531227 - time (sec): 17.89 - samples/sec: 2763.77 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-13 21:39:54,864 epoch 3 - iter 396/992 - loss 0.06974993 - time (sec): 23.99 - samples/sec: 2777.66 - lr: 0.000042 - momentum: 0.000000
110
+ 2023-10-13 21:40:00,891 epoch 3 - iter 495/992 - loss 0.07037521 - time (sec): 30.02 - samples/sec: 2759.70 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-13 21:40:06,636 epoch 3 - iter 594/992 - loss 0.07072352 - time (sec): 35.77 - samples/sec: 2768.83 - lr: 0.000041 - momentum: 0.000000
112
+ 2023-10-13 21:40:12,505 epoch 3 - iter 693/992 - loss 0.07026764 - time (sec): 41.64 - samples/sec: 2761.90 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-13 21:40:18,247 epoch 3 - iter 792/992 - loss 0.07260697 - time (sec): 47.38 - samples/sec: 2775.98 - lr: 0.000040 - momentum: 0.000000
114
+ 2023-10-13 21:40:24,041 epoch 3 - iter 891/992 - loss 0.07256251 - time (sec): 53.17 - samples/sec: 2778.82 - lr: 0.000039 - momentum: 0.000000
115
+ 2023-10-13 21:40:29,699 epoch 3 - iter 990/992 - loss 0.07225091 - time (sec): 58.83 - samples/sec: 2780.17 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-13 21:40:29,815 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 21:40:29,815 EPOCH 3 done: loss 0.0722 - lr: 0.000039
118
+ 2023-10-13 21:40:33,902 DEV : loss 0.10864556580781937 - f1-score (micro avg) 0.758
119
+ 2023-10-13 21:40:33,939 saving best model
120
+ 2023-10-13 21:40:34,466 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 21:40:40,380 epoch 4 - iter 99/992 - loss 0.05150709 - time (sec): 5.91 - samples/sec: 2796.73 - lr: 0.000038 - momentum: 0.000000
122
+ 2023-10-13 21:40:46,332 epoch 4 - iter 198/992 - loss 0.04958120 - time (sec): 11.86 - samples/sec: 2802.33 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-13 21:40:51,999 epoch 4 - iter 297/992 - loss 0.05125257 - time (sec): 17.53 - samples/sec: 2798.55 - lr: 0.000037 - momentum: 0.000000
124
+ 2023-10-13 21:40:57,854 epoch 4 - iter 396/992 - loss 0.04922105 - time (sec): 23.39 - samples/sec: 2782.53 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-13 21:41:03,725 epoch 4 - iter 495/992 - loss 0.04834639 - time (sec): 29.26 - samples/sec: 2783.19 - lr: 0.000036 - momentum: 0.000000
126
+ 2023-10-13 21:41:09,534 epoch 4 - iter 594/992 - loss 0.04924934 - time (sec): 35.07 - samples/sec: 2786.12 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-13 21:41:15,489 epoch 4 - iter 693/992 - loss 0.04948734 - time (sec): 41.02 - samples/sec: 2778.64 - lr: 0.000035 - momentum: 0.000000
128
+ 2023-10-13 21:41:21,333 epoch 4 - iter 792/992 - loss 0.04908108 - time (sec): 46.87 - samples/sec: 2773.09 - lr: 0.000034 - momentum: 0.000000
129
+ 2023-10-13 21:41:27,452 epoch 4 - iter 891/992 - loss 0.04886483 - time (sec): 52.98 - samples/sec: 2765.98 - lr: 0.000034 - momentum: 0.000000
130
+ 2023-10-13 21:41:33,681 epoch 4 - iter 990/992 - loss 0.04998705 - time (sec): 59.21 - samples/sec: 2765.34 - lr: 0.000033 - momentum: 0.000000
131
+ 2023-10-13 21:41:33,794 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 21:41:33,794 EPOCH 4 done: loss 0.0499 - lr: 0.000033
133
+ 2023-10-13 21:41:37,201 DEV : loss 0.11597025394439697 - f1-score (micro avg) 0.7675
134
+ 2023-10-13 21:41:37,222 saving best model
135
+ 2023-10-13 21:41:37,774 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-13 21:41:43,640 epoch 5 - iter 99/992 - loss 0.04977178 - time (sec): 5.86 - samples/sec: 2838.67 - lr: 0.000033 - momentum: 0.000000
137
+ 2023-10-13 21:41:49,509 epoch 5 - iter 198/992 - loss 0.04238345 - time (sec): 11.73 - samples/sec: 2809.15 - lr: 0.000032 - momentum: 0.000000
138
+ 2023-10-13 21:41:55,313 epoch 5 - iter 297/992 - loss 0.04044960 - time (sec): 17.53 - samples/sec: 2809.68 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-13 21:42:01,758 epoch 5 - iter 396/992 - loss 0.03908575 - time (sec): 23.98 - samples/sec: 2780.41 - lr: 0.000031 - momentum: 0.000000
140
+ 2023-10-13 21:42:07,657 epoch 5 - iter 495/992 - loss 0.03930276 - time (sec): 29.88 - samples/sec: 2784.79 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-13 21:42:13,458 epoch 5 - iter 594/992 - loss 0.03815672 - time (sec): 35.68 - samples/sec: 2781.01 - lr: 0.000030 - momentum: 0.000000
142
+ 2023-10-13 21:42:19,292 epoch 5 - iter 693/992 - loss 0.03945281 - time (sec): 41.51 - samples/sec: 2772.88 - lr: 0.000029 - momentum: 0.000000
143
+ 2023-10-13 21:42:24,988 epoch 5 - iter 792/992 - loss 0.03857818 - time (sec): 47.21 - samples/sec: 2787.22 - lr: 0.000029 - momentum: 0.000000
144
+ 2023-10-13 21:42:31,007 epoch 5 - iter 891/992 - loss 0.03988100 - time (sec): 53.23 - samples/sec: 2781.52 - lr: 0.000028 - momentum: 0.000000
145
+ 2023-10-13 21:42:36,766 epoch 5 - iter 990/992 - loss 0.04081192 - time (sec): 58.99 - samples/sec: 2773.33 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-13 21:42:36,903 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-13 21:42:36,903 EPOCH 5 done: loss 0.0408 - lr: 0.000028
148
+ 2023-10-13 21:42:41,542 DEV : loss 0.13763324916362762 - f1-score (micro avg) 0.7589
149
+ 2023-10-13 21:42:41,580 ----------------------------------------------------------------------------------------------------
150
+ 2023-10-13 21:42:47,750 epoch 6 - iter 99/992 - loss 0.02422172 - time (sec): 6.17 - samples/sec: 2688.98 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-13 21:42:53,863 epoch 6 - iter 198/992 - loss 0.02863550 - time (sec): 12.28 - samples/sec: 2753.55 - lr: 0.000027 - momentum: 0.000000
152
+ 2023-10-13 21:42:59,675 epoch 6 - iter 297/992 - loss 0.02988685 - time (sec): 18.09 - samples/sec: 2746.20 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-13 21:43:05,663 epoch 6 - iter 396/992 - loss 0.02833903 - time (sec): 24.08 - samples/sec: 2722.44 - lr: 0.000026 - momentum: 0.000000
154
+ 2023-10-13 21:43:11,508 epoch 6 - iter 495/992 - loss 0.02786454 - time (sec): 29.93 - samples/sec: 2737.83 - lr: 0.000025 - momentum: 0.000000
155
+ 2023-10-13 21:43:17,288 epoch 6 - iter 594/992 - loss 0.02866839 - time (sec): 35.71 - samples/sec: 2755.15 - lr: 0.000024 - momentum: 0.000000
156
+ 2023-10-13 21:43:23,408 epoch 6 - iter 693/992 - loss 0.02806587 - time (sec): 41.83 - samples/sec: 2753.01 - lr: 0.000024 - momentum: 0.000000
157
+ 2023-10-13 21:43:29,273 epoch 6 - iter 792/992 - loss 0.02884132 - time (sec): 47.69 - samples/sec: 2755.88 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-13 21:43:35,118 epoch 6 - iter 891/992 - loss 0.02883868 - time (sec): 53.54 - samples/sec: 2753.63 - lr: 0.000023 - momentum: 0.000000
159
+ 2023-10-13 21:43:41,138 epoch 6 - iter 990/992 - loss 0.02863755 - time (sec): 59.56 - samples/sec: 2748.21 - lr: 0.000022 - momentum: 0.000000
160
+ 2023-10-13 21:43:41,250 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-13 21:43:41,250 EPOCH 6 done: loss 0.0288 - lr: 0.000022
162
+ 2023-10-13 21:43:44,796 DEV : loss 0.17916934192180634 - f1-score (micro avg) 0.7563
163
+ 2023-10-13 21:43:44,821 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-13 21:43:50,755 epoch 7 - iter 99/992 - loss 0.01996214 - time (sec): 5.93 - samples/sec: 2590.21 - lr: 0.000022 - momentum: 0.000000
165
+ 2023-10-13 21:43:57,458 epoch 7 - iter 198/992 - loss 0.02277291 - time (sec): 12.63 - samples/sec: 2548.91 - lr: 0.000021 - momentum: 0.000000
166
+ 2023-10-13 21:44:03,311 epoch 7 - iter 297/992 - loss 0.02180867 - time (sec): 18.49 - samples/sec: 2584.45 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-13 21:44:09,225 epoch 7 - iter 396/992 - loss 0.02147002 - time (sec): 24.40 - samples/sec: 2621.14 - lr: 0.000020 - momentum: 0.000000
168
+ 2023-10-13 21:44:15,345 epoch 7 - iter 495/992 - loss 0.02147281 - time (sec): 30.52 - samples/sec: 2658.70 - lr: 0.000019 - momentum: 0.000000
169
+ 2023-10-13 21:44:21,676 epoch 7 - iter 594/992 - loss 0.02278340 - time (sec): 36.85 - samples/sec: 2672.02 - lr: 0.000019 - momentum: 0.000000
170
+ 2023-10-13 21:44:27,314 epoch 7 - iter 693/992 - loss 0.02302071 - time (sec): 42.49 - samples/sec: 2675.36 - lr: 0.000018 - momentum: 0.000000
171
+ 2023-10-13 21:44:33,289 epoch 7 - iter 792/992 - loss 0.02238297 - time (sec): 48.47 - samples/sec: 2696.36 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-13 21:44:38,932 epoch 7 - iter 891/992 - loss 0.02194504 - time (sec): 54.11 - samples/sec: 2717.35 - lr: 0.000017 - momentum: 0.000000
173
+ 2023-10-13 21:44:44,806 epoch 7 - iter 990/992 - loss 0.02178032 - time (sec): 59.98 - samples/sec: 2727.36 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-13 21:44:44,942 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-13 21:44:44,942 EPOCH 7 done: loss 0.0217 - lr: 0.000017
176
+ 2023-10-13 21:44:48,386 DEV : loss 0.19963695108890533 - f1-score (micro avg) 0.7511
177
+ 2023-10-13 21:44:48,411 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-13 21:44:54,512 epoch 8 - iter 99/992 - loss 0.00802566 - time (sec): 6.10 - samples/sec: 2678.43 - lr: 0.000016 - momentum: 0.000000
179
+ 2023-10-13 21:45:00,449 epoch 8 - iter 198/992 - loss 0.01380324 - time (sec): 12.04 - samples/sec: 2738.01 - lr: 0.000016 - momentum: 0.000000
180
+ 2023-10-13 21:45:06,122 epoch 8 - iter 297/992 - loss 0.01227669 - time (sec): 17.71 - samples/sec: 2757.67 - lr: 0.000015 - momentum: 0.000000
181
+ 2023-10-13 21:45:12,518 epoch 8 - iter 396/992 - loss 0.01400552 - time (sec): 24.11 - samples/sec: 2729.93 - lr: 0.000014 - momentum: 0.000000
182
+ 2023-10-13 21:45:18,333 epoch 8 - iter 495/992 - loss 0.01475903 - time (sec): 29.92 - samples/sec: 2736.32 - lr: 0.000014 - momentum: 0.000000
183
+ 2023-10-13 21:45:23,984 epoch 8 - iter 594/992 - loss 0.01530820 - time (sec): 35.57 - samples/sec: 2735.01 - lr: 0.000013 - momentum: 0.000000
184
+ 2023-10-13 21:45:30,069 epoch 8 - iter 693/992 - loss 0.01589983 - time (sec): 41.66 - samples/sec: 2736.91 - lr: 0.000013 - momentum: 0.000000
185
+ 2023-10-13 21:45:36,359 epoch 8 - iter 792/992 - loss 0.01603725 - time (sec): 47.95 - samples/sec: 2744.42 - lr: 0.000012 - momentum: 0.000000
186
+ 2023-10-13 21:45:42,042 epoch 8 - iter 891/992 - loss 0.01533557 - time (sec): 53.63 - samples/sec: 2749.62 - lr: 0.000012 - momentum: 0.000000
187
+ 2023-10-13 21:45:47,922 epoch 8 - iter 990/992 - loss 0.01568211 - time (sec): 59.51 - samples/sec: 2751.39 - lr: 0.000011 - momentum: 0.000000
188
+ 2023-10-13 21:45:48,031 ----------------------------------------------------------------------------------------------------
189
+ 2023-10-13 21:45:48,031 EPOCH 8 done: loss 0.0157 - lr: 0.000011
190
+ 2023-10-13 21:45:51,538 DEV : loss 0.2106373906135559 - f1-score (micro avg) 0.7511
191
+ 2023-10-13 21:45:51,560 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-13 21:45:57,529 epoch 9 - iter 99/992 - loss 0.00887012 - time (sec): 5.97 - samples/sec: 2806.18 - lr: 0.000011 - momentum: 0.000000
193
+ 2023-10-13 21:46:03,489 epoch 9 - iter 198/992 - loss 0.00899000 - time (sec): 11.93 - samples/sec: 2748.69 - lr: 0.000010 - momentum: 0.000000
194
+ 2023-10-13 21:46:09,616 epoch 9 - iter 297/992 - loss 0.00742884 - time (sec): 18.05 - samples/sec: 2694.16 - lr: 0.000009 - momentum: 0.000000
195
+ 2023-10-13 21:46:15,833 epoch 9 - iter 396/992 - loss 0.00794530 - time (sec): 24.27 - samples/sec: 2710.07 - lr: 0.000009 - momentum: 0.000000
196
+ 2023-10-13 21:46:21,629 epoch 9 - iter 495/992 - loss 0.00848285 - time (sec): 30.07 - samples/sec: 2744.72 - lr: 0.000008 - momentum: 0.000000
197
+ 2023-10-13 21:46:27,363 epoch 9 - iter 594/992 - loss 0.00917051 - time (sec): 35.80 - samples/sec: 2739.94 - lr: 0.000008 - momentum: 0.000000
198
+ 2023-10-13 21:46:32,985 epoch 9 - iter 693/992 - loss 0.00939071 - time (sec): 41.42 - samples/sec: 2755.95 - lr: 0.000007 - momentum: 0.000000
199
+ 2023-10-13 21:46:38,976 epoch 9 - iter 792/992 - loss 0.01010125 - time (sec): 47.41 - samples/sec: 2762.85 - lr: 0.000007 - momentum: 0.000000
200
+ 2023-10-13 21:46:45,090 epoch 9 - iter 891/992 - loss 0.01075447 - time (sec): 53.53 - samples/sec: 2761.88 - lr: 0.000006 - momentum: 0.000000
201
+ 2023-10-13 21:46:50,883 epoch 9 - iter 990/992 - loss 0.01068750 - time (sec): 59.32 - samples/sec: 2757.49 - lr: 0.000006 - momentum: 0.000000
202
+ 2023-10-13 21:46:51,018 ----------------------------------------------------------------------------------------------------
203
+ 2023-10-13 21:46:51,018 EPOCH 9 done: loss 0.0107 - lr: 0.000006
204
+ 2023-10-13 21:46:54,559 DEV : loss 0.22137963771820068 - f1-score (micro avg) 0.7493
205
+ 2023-10-13 21:46:54,581 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-13 21:47:00,669 epoch 10 - iter 99/992 - loss 0.00885115 - time (sec): 6.09 - samples/sec: 2800.45 - lr: 0.000005 - momentum: 0.000000
207
+ 2023-10-13 21:47:06,567 epoch 10 - iter 198/992 - loss 0.00701261 - time (sec): 11.98 - samples/sec: 2734.37 - lr: 0.000004 - momentum: 0.000000
208
+ 2023-10-13 21:47:12,490 epoch 10 - iter 297/992 - loss 0.00709994 - time (sec): 17.91 - samples/sec: 2725.21 - lr: 0.000004 - momentum: 0.000000
209
+ 2023-10-13 21:47:19,212 epoch 10 - iter 396/992 - loss 0.00713180 - time (sec): 24.63 - samples/sec: 2657.26 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-13 21:47:24,800 epoch 10 - iter 495/992 - loss 0.00712523 - time (sec): 30.22 - samples/sec: 2696.43 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-13 21:47:30,657 epoch 10 - iter 594/992 - loss 0.00752130 - time (sec): 36.07 - samples/sec: 2715.70 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-13 21:47:36,606 epoch 10 - iter 693/992 - loss 0.00756143 - time (sec): 42.02 - samples/sec: 2720.45 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-13 21:47:42,502 epoch 10 - iter 792/992 - loss 0.00745144 - time (sec): 47.92 - samples/sec: 2732.37 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-13 21:47:48,499 epoch 10 - iter 891/992 - loss 0.00734368 - time (sec): 53.92 - samples/sec: 2744.99 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-13 21:47:54,258 epoch 10 - iter 990/992 - loss 0.00723729 - time (sec): 59.68 - samples/sec: 2742.25 - lr: 0.000000 - momentum: 0.000000
216
+ 2023-10-13 21:47:54,381 ----------------------------------------------------------------------------------------------------
217
+ 2023-10-13 21:47:54,381 EPOCH 10 done: loss 0.0072 - lr: 0.000000
218
+ 2023-10-13 21:47:57,909 DEV : loss 0.22665657103061676 - f1-score (micro avg) 0.7513
219
+ 2023-10-13 21:47:58,383 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-13 21:47:58,384 Loading model from best epoch ...
221
+ 2023-10-13 21:47:59,826 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
222
+ 2023-10-13 21:48:03,320
223
+ Results:
224
+ - F-score (micro) 0.7736
225
+ - F-score (macro) 0.6613
226
+ - Accuracy 0.6522
227
+
228
+ By class:
229
+ precision recall f1-score support
230
+
231
+ LOC 0.7826 0.8794 0.8282 655
232
+ PER 0.8556 0.6906 0.7643 223
233
+ ORG 0.5968 0.2913 0.3915 127
234
+
235
+ micro avg 0.7843 0.7632 0.7736 1005
236
+ macro avg 0.7450 0.6204 0.6613 1005
237
+ weighted avg 0.7753 0.7632 0.7588 1005
238
+
239
+ 2023-10-13 21:48:03,320 ----------------------------------------------------------------------------------------------------