Hugging Face's logo

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

Token Classification
Flair
PyTorch
Dutch
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
89cf804
·
1 Parent(s): 17e7a25

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 sha256:1477615a3e43b31b0174d6aede9e38bb05ca9b3d79457c2ce6d301ba99a51dee
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 10:20:22 0.0000 0.3283 0.1316 0.6916 0.6601 0.6755 0.5187
3
+ 2 10:21:26 0.0000 0.0985 0.1147 0.7358 0.7769 0.7558 0.6169
4
+ 3 10:22:30 0.0000 0.0627 0.0884 0.8508 0.7366 0.7896 0.6626
5
+ 4 10:23:36 0.0000 0.0455 0.0871 0.8562 0.7934 0.8236 0.7111
6
+ 5 10:24:42 0.0000 0.0328 0.1185 0.8386 0.7624 0.7987 0.6802
7
+ 6 10:25:48 0.0000 0.0244 0.1726 0.8953 0.7066 0.7898 0.6590
8
+ 7 10:26:51 0.0000 0.0189 0.1648 0.8550 0.7800 0.8158 0.6984
9
+ 8 10:27:54 0.0000 0.0128 0.1723 0.8511 0.7913 0.8201 0.7040
10
+ 9 10:28:56 0.0000 0.0087 0.1810 0.8423 0.8058 0.8237 0.7084
11
+ 10 10:30:00 0.0000 0.0063 0.1870 0.8615 0.7841 0.8210 0.7047
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-14 10:19:19,794 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-14 10:19:19,795 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
+ 2023-10-14 10:19:19,795 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-14 10:19:19,795 MultiCorpus: 5777 train + 722 dev + 723 test sentences
52
+ - NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /root/.flair/datasets/ner_icdar_europeana/nl
53
+ 2023-10-14 10:19:19,795 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-14 10:19:19,795 Train: 5777 sentences
55
+ 2023-10-14 10:19:19,795 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-14 10:19:19,795 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-14 10:19:19,795 Training Params:
58
+ 2023-10-14 10:19:19,795 - learning_rate: "5e-05"
59
+ 2023-10-14 10:19:19,795 - mini_batch_size: "8"
60
+ 2023-10-14 10:19:19,795 - max_epochs: "10"
61
+ 2023-10-14 10:19:19,795 - shuffle: "True"
62
+ 2023-10-14 10:19:19,795 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-14 10:19:19,795 Plugins:
64
+ 2023-10-14 10:19:19,795 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-14 10:19:19,795 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-14 10:19:19,795 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-14 10:19:19,795 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-14 10:19:19,795 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-14 10:19:19,795 Computation:
70
+ 2023-10-14 10:19:19,796 - compute on device: cuda:0
71
+ 2023-10-14 10:19:19,796 - embedding storage: none
72
+ 2023-10-14 10:19:19,796 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-14 10:19:19,796 Model training base path: "hmbench-icdar/nl-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3"
74
+ 2023-10-14 10:19:19,796 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-14 10:19:19,796 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-14 10:19:25,609 epoch 1 - iter 72/723 - loss 1.72327249 - time (sec): 5.81 - samples/sec: 2983.38 - lr: 0.000005 - momentum: 0.000000
77
+ 2023-10-14 10:19:31,228 epoch 1 - iter 144/723 - loss 1.00146801 - time (sec): 11.43 - samples/sec: 3045.82 - lr: 0.000010 - momentum: 0.000000
78
+ 2023-10-14 10:19:36,758 epoch 1 - iter 216/723 - loss 0.73554490 - time (sec): 16.96 - samples/sec: 3059.06 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-14 10:19:42,581 epoch 1 - iter 288/723 - loss 0.60215162 - time (sec): 22.78 - samples/sec: 3047.48 - lr: 0.000020 - momentum: 0.000000
80
+ 2023-10-14 10:19:48,999 epoch 1 - iter 360/723 - loss 0.50523257 - time (sec): 29.20 - samples/sec: 3045.82 - lr: 0.000025 - momentum: 0.000000
81
+ 2023-10-14 10:19:55,159 epoch 1 - iter 432/723 - loss 0.45270535 - time (sec): 35.36 - samples/sec: 2992.60 - lr: 0.000030 - momentum: 0.000000
82
+ 2023-10-14 10:20:00,904 epoch 1 - iter 504/723 - loss 0.41268390 - time (sec): 41.11 - samples/sec: 2980.35 - lr: 0.000035 - momentum: 0.000000
83
+ 2023-10-14 10:20:07,154 epoch 1 - iter 576/723 - loss 0.37700903 - time (sec): 47.36 - samples/sec: 2966.93 - lr: 0.000040 - momentum: 0.000000
84
+ 2023-10-14 10:20:13,057 epoch 1 - iter 648/723 - loss 0.34991301 - time (sec): 53.26 - samples/sec: 2976.79 - lr: 0.000045 - momentum: 0.000000
85
+ 2023-10-14 10:20:18,955 epoch 1 - iter 720/723 - loss 0.32824400 - time (sec): 59.16 - samples/sec: 2973.43 - lr: 0.000050 - momentum: 0.000000
86
+ 2023-10-14 10:20:19,104 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-14 10:20:19,104 EPOCH 1 done: loss 0.3283 - lr: 0.000050
88
+ 2023-10-14 10:20:22,627 DEV : loss 0.1315712332725525 - f1-score (micro avg) 0.6755
89
+ 2023-10-14 10:20:22,650 saving best model
90
+ 2023-10-14 10:20:23,102 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-14 10:20:29,239 epoch 2 - iter 72/723 - loss 0.12632996 - time (sec): 6.13 - samples/sec: 2913.10 - lr: 0.000049 - momentum: 0.000000
92
+ 2023-10-14 10:20:35,225 epoch 2 - iter 144/723 - loss 0.11494873 - time (sec): 12.12 - samples/sec: 2893.63 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-14 10:20:40,755 epoch 2 - iter 216/723 - loss 0.11125540 - time (sec): 17.65 - samples/sec: 2962.74 - lr: 0.000048 - momentum: 0.000000
94
+ 2023-10-14 10:20:46,994 epoch 2 - iter 288/723 - loss 0.10970521 - time (sec): 23.89 - samples/sec: 2965.22 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-14 10:20:53,342 epoch 2 - iter 360/723 - loss 0.10475284 - time (sec): 30.24 - samples/sec: 2955.70 - lr: 0.000047 - momentum: 0.000000
96
+ 2023-10-14 10:20:59,111 epoch 2 - iter 432/723 - loss 0.10224698 - time (sec): 36.01 - samples/sec: 2961.87 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-14 10:21:04,544 epoch 2 - iter 504/723 - loss 0.10046143 - time (sec): 41.44 - samples/sec: 2974.07 - lr: 0.000046 - momentum: 0.000000
98
+ 2023-10-14 10:21:10,196 epoch 2 - iter 576/723 - loss 0.09752484 - time (sec): 47.09 - samples/sec: 2995.32 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-14 10:21:16,127 epoch 2 - iter 648/723 - loss 0.09941523 - time (sec): 53.02 - samples/sec: 2991.38 - lr: 0.000045 - momentum: 0.000000
100
+ 2023-10-14 10:21:21,791 epoch 2 - iter 720/723 - loss 0.09855220 - time (sec): 58.69 - samples/sec: 2994.78 - lr: 0.000044 - momentum: 0.000000
101
+ 2023-10-14 10:21:21,952 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-14 10:21:21,952 EPOCH 2 done: loss 0.0985 - lr: 0.000044
103
+ 2023-10-14 10:21:26,345 DEV : loss 0.11473622173070908 - f1-score (micro avg) 0.7558
104
+ 2023-10-14 10:21:26,361 saving best model
105
+ 2023-10-14 10:21:26,963 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-14 10:21:32,825 epoch 3 - iter 72/723 - loss 0.07907433 - time (sec): 5.86 - samples/sec: 2993.20 - lr: 0.000044 - momentum: 0.000000
107
+ 2023-10-14 10:21:38,751 epoch 3 - iter 144/723 - loss 0.07464467 - time (sec): 11.78 - samples/sec: 2959.55 - lr: 0.000043 - momentum: 0.000000
108
+ 2023-10-14 10:21:44,800 epoch 3 - iter 216/723 - loss 0.06887957 - time (sec): 17.83 - samples/sec: 2967.64 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-14 10:21:51,036 epoch 3 - iter 288/723 - loss 0.06980865 - time (sec): 24.07 - samples/sec: 2938.66 - lr: 0.000042 - momentum: 0.000000
110
+ 2023-10-14 10:21:57,209 epoch 3 - iter 360/723 - loss 0.06595517 - time (sec): 30.24 - samples/sec: 2912.85 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-14 10:22:02,975 epoch 3 - iter 432/723 - loss 0.06369977 - time (sec): 36.01 - samples/sec: 2932.84 - lr: 0.000041 - momentum: 0.000000
112
+ 2023-10-14 10:22:09,498 epoch 3 - iter 504/723 - loss 0.06320356 - time (sec): 42.53 - samples/sec: 2916.78 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-14 10:22:15,167 epoch 3 - iter 576/723 - loss 0.06249681 - time (sec): 48.20 - samples/sec: 2918.13 - lr: 0.000040 - momentum: 0.000000
114
+ 2023-10-14 10:22:21,126 epoch 3 - iter 648/723 - loss 0.06292183 - time (sec): 54.16 - samples/sec: 2926.70 - lr: 0.000039 - momentum: 0.000000
115
+ 2023-10-14 10:22:27,060 epoch 3 - iter 720/723 - loss 0.06275594 - time (sec): 60.09 - samples/sec: 2924.25 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-14 10:22:27,243 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-14 10:22:27,244 EPOCH 3 done: loss 0.0627 - lr: 0.000039
118
+ 2023-10-14 10:22:30,796 DEV : loss 0.08838976919651031 - f1-score (micro avg) 0.7896
119
+ 2023-10-14 10:22:30,815 saving best model
120
+ 2023-10-14 10:22:31,393 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-14 10:22:37,402 epoch 4 - iter 72/723 - loss 0.04342449 - time (sec): 6.00 - samples/sec: 2874.63 - lr: 0.000038 - momentum: 0.000000
122
+ 2023-10-14 10:22:43,827 epoch 4 - iter 144/723 - loss 0.04558890 - time (sec): 12.43 - samples/sec: 2795.95 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-14 10:22:50,441 epoch 4 - iter 216/723 - loss 0.04282584 - time (sec): 19.04 - samples/sec: 2683.29 - lr: 0.000037 - momentum: 0.000000
124
+ 2023-10-14 10:22:56,600 epoch 4 - iter 288/723 - loss 0.04327687 - time (sec): 25.20 - samples/sec: 2751.68 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-14 10:23:02,680 epoch 4 - iter 360/723 - loss 0.04398015 - time (sec): 31.28 - samples/sec: 2781.27 - lr: 0.000036 - momentum: 0.000000
126
+ 2023-10-14 10:23:09,050 epoch 4 - iter 432/723 - loss 0.04594075 - time (sec): 37.65 - samples/sec: 2802.25 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-14 10:23:15,185 epoch 4 - iter 504/723 - loss 0.04565317 - time (sec): 43.79 - samples/sec: 2831.76 - lr: 0.000035 - momentum: 0.000000
128
+ 2023-10-14 10:23:20,960 epoch 4 - iter 576/723 - loss 0.04572753 - time (sec): 49.56 - samples/sec: 2833.82 - lr: 0.000034 - momentum: 0.000000
129
+ 2023-10-14 10:23:26,585 epoch 4 - iter 648/723 - loss 0.04471750 - time (sec): 55.19 - samples/sec: 2854.56 - lr: 0.000034 - momentum: 0.000000
130
+ 2023-10-14 10:23:32,857 epoch 4 - iter 720/723 - loss 0.04552874 - time (sec): 61.46 - samples/sec: 2861.20 - lr: 0.000033 - momentum: 0.000000
131
+ 2023-10-14 10:23:33,032 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-14 10:23:33,032 EPOCH 4 done: loss 0.0455 - lr: 0.000033
133
+ 2023-10-14 10:23:36,576 DEV : loss 0.08705586940050125 - f1-score (micro avg) 0.8236
134
+ 2023-10-14 10:23:36,597 saving best model
135
+ 2023-10-14 10:23:37,122 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-14 10:23:43,697 epoch 5 - iter 72/723 - loss 0.03314608 - time (sec): 6.57 - samples/sec: 2845.13 - lr: 0.000033 - momentum: 0.000000
137
+ 2023-10-14 10:23:49,408 epoch 5 - iter 144/723 - loss 0.02748621 - time (sec): 12.28 - samples/sec: 2921.11 - lr: 0.000032 - momentum: 0.000000
138
+ 2023-10-14 10:23:55,570 epoch 5 - iter 216/723 - loss 0.02779545 - time (sec): 18.45 - samples/sec: 2927.77 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-14 10:24:01,691 epoch 5 - iter 288/723 - loss 0.02991449 - time (sec): 24.57 - samples/sec: 2917.20 - lr: 0.000031 - momentum: 0.000000
140
+ 2023-10-14 10:24:07,775 epoch 5 - iter 360/723 - loss 0.03006041 - time (sec): 30.65 - samples/sec: 2908.32 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-14 10:24:13,849 epoch 5 - iter 432/723 - loss 0.03092723 - time (sec): 36.72 - samples/sec: 2904.76 - lr: 0.000030 - momentum: 0.000000
142
+ 2023-10-14 10:24:19,930 epoch 5 - iter 504/723 - loss 0.03033433 - time (sec): 42.81 - samples/sec: 2882.81 - lr: 0.000029 - momentum: 0.000000
143
+ 2023-10-14 10:24:25,916 epoch 5 - iter 576/723 - loss 0.03189491 - time (sec): 48.79 - samples/sec: 2887.10 - lr: 0.000029 - momentum: 0.000000
144
+ 2023-10-14 10:24:31,822 epoch 5 - iter 648/723 - loss 0.03147341 - time (sec): 54.70 - samples/sec: 2897.07 - lr: 0.000028 - momentum: 0.000000
145
+ 2023-10-14 10:24:38,005 epoch 5 - iter 720/723 - loss 0.03282684 - time (sec): 60.88 - samples/sec: 2885.40 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-14 10:24:38,183 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-14 10:24:38,184 EPOCH 5 done: loss 0.0328 - lr: 0.000028
148
+ 2023-10-14 10:24:42,528 DEV : loss 0.11852852255105972 - f1-score (micro avg) 0.7987
149
+ 2023-10-14 10:24:42,545 ----------------------------------------------------------------------------------------------------
150
+ 2023-10-14 10:24:48,512 epoch 6 - iter 72/723 - loss 0.02109962 - time (sec): 5.97 - samples/sec: 2932.99 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-14 10:24:55,286 epoch 6 - iter 144/723 - loss 0.02464690 - time (sec): 12.74 - samples/sec: 2851.35 - lr: 0.000027 - momentum: 0.000000
152
+ 2023-10-14 10:25:01,278 epoch 6 - iter 216/723 - loss 0.02651401 - time (sec): 18.73 - samples/sec: 2861.92 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-14 10:25:07,586 epoch 6 - iter 288/723 - loss 0.02500530 - time (sec): 25.04 - samples/sec: 2837.34 - lr: 0.000026 - momentum: 0.000000
154
+ 2023-10-14 10:25:13,880 epoch 6 - iter 360/723 - loss 0.02550617 - time (sec): 31.33 - samples/sec: 2820.00 - lr: 0.000025 - momentum: 0.000000
155
+ 2023-10-14 10:25:20,227 epoch 6 - iter 432/723 - loss 0.02588593 - time (sec): 37.68 - samples/sec: 2835.76 - lr: 0.000024 - momentum: 0.000000
156
+ 2023-10-14 10:25:26,637 epoch 6 - iter 504/723 - loss 0.02626521 - time (sec): 44.09 - samples/sec: 2816.25 - lr: 0.000024 - momentum: 0.000000
157
+ 2023-10-14 10:25:32,350 epoch 6 - iter 576/723 - loss 0.02545341 - time (sec): 49.80 - samples/sec: 2826.59 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-14 10:25:38,211 epoch 6 - iter 648/723 - loss 0.02546137 - time (sec): 55.67 - samples/sec: 2824.80 - lr: 0.000023 - momentum: 0.000000
159
+ 2023-10-14 10:25:44,480 epoch 6 - iter 720/723 - loss 0.02448943 - time (sec): 61.93 - samples/sec: 2834.22 - lr: 0.000022 - momentum: 0.000000
160
+ 2023-10-14 10:25:44,752 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-14 10:25:44,752 EPOCH 6 done: loss 0.0244 - lr: 0.000022
162
+ 2023-10-14 10:25:48,334 DEV : loss 0.1726008951663971 - f1-score (micro avg) 0.7898
163
+ 2023-10-14 10:25:48,364 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-14 10:25:54,132 epoch 7 - iter 72/723 - loss 0.01010894 - time (sec): 5.77 - samples/sec: 3009.11 - lr: 0.000022 - momentum: 0.000000
165
+ 2023-10-14 10:26:00,546 epoch 7 - iter 144/723 - loss 0.01397475 - time (sec): 12.18 - samples/sec: 2880.79 - lr: 0.000021 - momentum: 0.000000
166
+ 2023-10-14 10:26:06,233 epoch 7 - iter 216/723 - loss 0.01737460 - time (sec): 17.87 - samples/sec: 2927.54 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-14 10:26:12,698 epoch 7 - iter 288/723 - loss 0.01805427 - time (sec): 24.33 - samples/sec: 2887.43 - lr: 0.000020 - momentum: 0.000000
168
+ 2023-10-14 10:26:18,352 epoch 7 - iter 360/723 - loss 0.01744268 - time (sec): 29.99 - samples/sec: 2920.78 - lr: 0.000019 - momentum: 0.000000
169
+ 2023-10-14 10:26:24,396 epoch 7 - iter 432/723 - loss 0.01990357 - time (sec): 36.03 - samples/sec: 2932.22 - lr: 0.000019 - momentum: 0.000000
170
+ 2023-10-14 10:26:30,242 epoch 7 - iter 504/723 - loss 0.01939631 - time (sec): 41.88 - samples/sec: 2936.64 - lr: 0.000018 - momentum: 0.000000
171
+ 2023-10-14 10:26:35,761 epoch 7 - iter 576/723 - loss 0.01925559 - time (sec): 47.40 - samples/sec: 2951.69 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-14 10:26:41,965 epoch 7 - iter 648/723 - loss 0.01913244 - time (sec): 53.60 - samples/sec: 2949.86 - lr: 0.000017 - momentum: 0.000000
173
+ 2023-10-14 10:26:48,111 epoch 7 - iter 720/723 - loss 0.01890120 - time (sec): 59.75 - samples/sec: 2942.22 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-14 10:26:48,270 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-14 10:26:48,271 EPOCH 7 done: loss 0.0189 - lr: 0.000017
176
+ 2023-10-14 10:26:51,780 DEV : loss 0.16478076577186584 - f1-score (micro avg) 0.8158
177
+ 2023-10-14 10:26:51,797 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-14 10:26:57,786 epoch 8 - iter 72/723 - loss 0.01381860 - time (sec): 5.99 - samples/sec: 3020.38 - lr: 0.000016 - momentum: 0.000000
179
+ 2023-10-14 10:27:03,369 epoch 8 - iter 144/723 - loss 0.01061469 - time (sec): 11.57 - samples/sec: 3040.23 - lr: 0.000016 - momentum: 0.000000
180
+ 2023-10-14 10:27:10,268 epoch 8 - iter 216/723 - loss 0.01332653 - time (sec): 18.47 - samples/sec: 2967.68 - lr: 0.000015 - momentum: 0.000000
181
+ 2023-10-14 10:27:15,337 epoch 8 - iter 288/723 - loss 0.01314284 - time (sec): 23.54 - samples/sec: 2952.54 - lr: 0.000014 - momentum: 0.000000
182
+ 2023-10-14 10:27:21,493 epoch 8 - iter 360/723 - loss 0.01343682 - time (sec): 29.70 - samples/sec: 2971.85 - lr: 0.000014 - momentum: 0.000000
183
+ 2023-10-14 10:27:27,555 epoch 8 - iter 432/723 - loss 0.01231511 - time (sec): 35.76 - samples/sec: 2984.09 - lr: 0.000013 - momentum: 0.000000
184
+ 2023-10-14 10:27:32,976 epoch 8 - iter 504/723 - loss 0.01164514 - time (sec): 41.18 - samples/sec: 3007.06 - lr: 0.000013 - momentum: 0.000000
185
+ 2023-10-14 10:27:38,634 epoch 8 - iter 576/723 - loss 0.01222536 - time (sec): 46.84 - samples/sec: 3010.30 - lr: 0.000012 - momentum: 0.000000
186
+ 2023-10-14 10:27:44,572 epoch 8 - iter 648/723 - loss 0.01264218 - time (sec): 52.77 - samples/sec: 3011.91 - lr: 0.000012 - momentum: 0.000000
187
+ 2023-10-14 10:27:50,263 epoch 8 - iter 720/723 - loss 0.01283067 - time (sec): 58.47 - samples/sec: 3006.26 - lr: 0.000011 - momentum: 0.000000
188
+ 2023-10-14 10:27:50,446 ----------------------------------------------------------------------------------------------------
189
+ 2023-10-14 10:27:50,446 EPOCH 8 done: loss 0.0128 - lr: 0.000011
190
+ 2023-10-14 10:27:54,343 DEV : loss 0.17232058942317963 - f1-score (micro avg) 0.8201
191
+ 2023-10-14 10:27:54,359 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-14 10:28:00,250 epoch 9 - iter 72/723 - loss 0.00704046 - time (sec): 5.89 - samples/sec: 3061.31 - lr: 0.000011 - momentum: 0.000000
193
+ 2023-10-14 10:28:06,250 epoch 9 - iter 144/723 - loss 0.00659264 - time (sec): 11.89 - samples/sec: 2995.37 - lr: 0.000010 - momentum: 0.000000
194
+ 2023-10-14 10:28:11,950 epoch 9 - iter 216/723 - loss 0.00659604 - time (sec): 17.59 - samples/sec: 2989.48 - lr: 0.000009 - momentum: 0.000000
195
+ 2023-10-14 10:28:18,181 epoch 9 - iter 288/723 - loss 0.00665508 - time (sec): 23.82 - samples/sec: 2980.52 - lr: 0.000009 - momentum: 0.000000
196
+ 2023-10-14 10:28:23,869 epoch 9 - iter 360/723 - loss 0.00733282 - time (sec): 29.51 - samples/sec: 2978.60 - lr: 0.000008 - momentum: 0.000000
197
+ 2023-10-14 10:28:30,360 epoch 9 - iter 432/723 - loss 0.00781952 - time (sec): 36.00 - samples/sec: 2974.28 - lr: 0.000008 - momentum: 0.000000
198
+ 2023-10-14 10:28:35,920 epoch 9 - iter 504/723 - loss 0.00773609 - time (sec): 41.56 - samples/sec: 2971.56 - lr: 0.000007 - momentum: 0.000000
199
+ 2023-10-14 10:28:41,901 epoch 9 - iter 576/723 - loss 0.00869847 - time (sec): 47.54 - samples/sec: 2978.58 - lr: 0.000007 - momentum: 0.000000
200
+ 2023-10-14 10:28:47,424 epoch 9 - iter 648/723 - loss 0.00883473 - time (sec): 53.06 - samples/sec: 2988.14 - lr: 0.000006 - momentum: 0.000000
201
+ 2023-10-14 10:28:53,233 epoch 9 - iter 720/723 - loss 0.00872089 - time (sec): 58.87 - samples/sec: 2987.10 - lr: 0.000006 - momentum: 0.000000
202
+ 2023-10-14 10:28:53,391 ----------------------------------------------------------------------------------------------------
203
+ 2023-10-14 10:28:53,391 EPOCH 9 done: loss 0.0087 - lr: 0.000006
204
+ 2023-10-14 10:28:56,879 DEV : loss 0.18103523552417755 - f1-score (micro avg) 0.8237
205
+ 2023-10-14 10:28:56,896 saving best model
206
+ 2023-10-14 10:28:57,500 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-14 10:29:03,133 epoch 10 - iter 72/723 - loss 0.00332405 - time (sec): 5.63 - samples/sec: 2958.13 - lr: 0.000005 - momentum: 0.000000
208
+ 2023-10-14 10:29:09,814 epoch 10 - iter 144/723 - loss 0.00473766 - time (sec): 12.31 - samples/sec: 2881.86 - lr: 0.000004 - momentum: 0.000000
209
+ 2023-10-14 10:29:15,600 epoch 10 - iter 216/723 - loss 0.00599232 - time (sec): 18.10 - samples/sec: 2940.03 - lr: 0.000004 - momentum: 0.000000
210
+ 2023-10-14 10:29:21,108 epoch 10 - iter 288/723 - loss 0.00549493 - time (sec): 23.61 - samples/sec: 2957.54 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-14 10:29:27,547 epoch 10 - iter 360/723 - loss 0.00683243 - time (sec): 30.04 - samples/sec: 2937.64 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-14 10:29:33,142 epoch 10 - iter 432/723 - loss 0.00611410 - time (sec): 35.64 - samples/sec: 2958.49 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-14 10:29:39,216 epoch 10 - iter 504/723 - loss 0.00646123 - time (sec): 41.71 - samples/sec: 2972.85 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-14 10:29:45,089 epoch 10 - iter 576/723 - loss 0.00655367 - time (sec): 47.59 - samples/sec: 2969.83 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-14 10:29:50,720 epoch 10 - iter 648/723 - loss 0.00634156 - time (sec): 53.22 - samples/sec: 2971.21 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-14 10:29:56,807 epoch 10 - iter 720/723 - loss 0.00633108 - time (sec): 59.31 - samples/sec: 2958.84 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-14 10:29:57,135 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-14 10:29:57,136 EPOCH 10 done: loss 0.0063 - lr: 0.000000
219
+ 2023-10-14 10:30:00,608 DEV : loss 0.18696151673793793 - f1-score (micro avg) 0.821
220
+ 2023-10-14 10:30:01,006 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-14 10:30:01,007 Loading model from best epoch ...
222
+ 2023-10-14 10:30:02,647 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
223
+ 2023-10-14 10:30:05,788
224
+ Results:
225
+ - F-score (micro) 0.815
226
+ - F-score (macro) 0.7275
227
+ - Accuracy 0.6978
228
+
229
+ By class:
230
+ precision recall f1-score support
231
+
232
+ PER 0.8004 0.8402 0.8198 482
233
+ LOC 0.8892 0.8231 0.8549 458
234
+ ORG 0.5410 0.4783 0.5077 69
235
+
236
+ micro avg 0.8224 0.8077 0.8150 1009
237
+ macro avg 0.7435 0.7139 0.7275 1009
238
+ weighted avg 0.8229 0.8077 0.8144 1009
239
+
240
+ 2023-10-14 10:30:05,789 ----------------------------------------------------------------------------------------------------