Hugging Face's logo

stefan-it
/
hmbench-topres19th-en-hmbert_tiny-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1

Token Classification
Flair
PyTorch
TensorBoard
English
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
a957f14
·
1 Parent(s): e0a8d72

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.1697793508.46dc0c540dd0.5704.3 +3 -0
  5. test.tsv +0 -0
  6. training.log +245 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9627ce2787a97155cd0110b4945f7c9a55ecfda59f920cd0cbd0ae0672920d95
3
+ size 19045986
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 09:18:47 0.0000 0.9579 0.1307 0.0000 0.0000 0.0000 0.0000
3
+ 2 09:19:06 0.0000 0.1796 0.0881 0.6345 0.3882 0.4817 0.3297
4
+ 3 09:19:24 0.0000 0.1467 0.0795 0.6324 0.5443 0.5850 0.4329
5
+ 4 09:19:43 0.0000 0.1299 0.0781 0.6862 0.5443 0.6071 0.4607
6
+ 5 09:20:02 0.0000 0.1169 0.0753 0.6439 0.5570 0.5973 0.4536
7
+ 6 09:20:20 0.0000 0.1098 0.0746 0.6351 0.5949 0.6144 0.4747
8
+ 7 09:20:39 0.0000 0.1037 0.0766 0.6282 0.6203 0.6242 0.4836
9
+ 8 09:20:57 0.0000 0.0973 0.0794 0.6574 0.5992 0.6269 0.4863
10
+ 9 09:21:15 0.0000 0.0943 0.0802 0.6774 0.6203 0.6476 0.5034
11
+ 10 09:21:34 0.0000 0.0933 0.0814 0.6758 0.6245 0.6491 0.5051
runs/events.out.tfevents.1697793508.46dc0c540dd0.5704.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c674d53abb83609d6cb56982ae40f1db6d09176d83b9c0b0729a7234acb5600
3
+ size 434848
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-20 09:18:28,284 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-20 09:18:28,285 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(32001, 128)
7
+ (position_embeddings): Embedding(512, 128)
8
+ (token_type_embeddings): Embedding(2, 128)
9
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-1): 2 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=128, out_features=128, bias=True)
18
+ (key): Linear(in_features=128, out_features=128, bias=True)
19
+ (value): Linear(in_features=128, out_features=128, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=128, out_features=128, bias=True)
24
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=128, out_features=512, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=512, out_features=128, bias=True)
34
+ (LayerNorm): LayerNorm((128,), 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=128, out_features=128, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=128, out_features=13, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-20 09:18:28,285 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-20 09:18:28,285 MultiCorpus: 6183 train + 680 dev + 2113 test sentences
52
+ - NER_HIPE_2022 Corpus: 6183 train + 680 dev + 2113 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/topres19th/en/with_doc_seperator
53
+ 2023-10-20 09:18:28,285 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-20 09:18:28,285 Train: 6183 sentences
55
+ 2023-10-20 09:18:28,285 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-20 09:18:28,285 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-20 09:18:28,285 Training Params:
58
+ 2023-10-20 09:18:28,285 - learning_rate: "5e-05"
59
+ 2023-10-20 09:18:28,285 - mini_batch_size: "8"
60
+ 2023-10-20 09:18:28,285 - max_epochs: "10"
61
+ 2023-10-20 09:18:28,285 - shuffle: "True"
62
+ 2023-10-20 09:18:28,285 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-20 09:18:28,285 Plugins:
64
+ 2023-10-20 09:18:28,285 - TensorboardLogger
65
+ 2023-10-20 09:18:28,285 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-20 09:18:28,285 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-20 09:18:28,285 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-20 09:18:28,285 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-20 09:18:28,285 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-20 09:18:28,285 Computation:
71
+ 2023-10-20 09:18:28,285 - compute on device: cuda:0
72
+ 2023-10-20 09:18:28,285 - embedding storage: none
73
+ 2023-10-20 09:18:28,285 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-20 09:18:28,285 Model training base path: "hmbench-topres19th/en-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
75
+ 2023-10-20 09:18:28,285 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-20 09:18:28,286 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-20 09:18:28,286 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-20 09:18:30,058 epoch 1 - iter 77/773 - loss 3.29697785 - time (sec): 1.77 - samples/sec: 7168.00 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-20 09:18:31,992 epoch 1 - iter 154/773 - loss 2.98890475 - time (sec): 3.71 - samples/sec: 6576.90 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-20 09:18:33,803 epoch 1 - iter 231/773 - loss 2.52454647 - time (sec): 5.52 - samples/sec: 6624.09 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-20 09:18:35,611 epoch 1 - iter 308/773 - loss 2.02302739 - time (sec): 7.32 - samples/sec: 6736.79 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-20 09:18:37,338 epoch 1 - iter 385/773 - loss 1.67463555 - time (sec): 9.05 - samples/sec: 6790.49 - lr: 0.000025 - momentum: 0.000000
83
+ 2023-10-20 09:18:39,053 epoch 1 - iter 462/773 - loss 1.45168116 - time (sec): 10.77 - samples/sec: 6786.86 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-20 09:18:40,795 epoch 1 - iter 539/773 - loss 1.27870844 - time (sec): 12.51 - samples/sec: 6856.46 - lr: 0.000035 - momentum: 0.000000
85
+ 2023-10-20 09:18:42,569 epoch 1 - iter 616/773 - loss 1.14349474 - time (sec): 14.28 - samples/sec: 6915.75 - lr: 0.000040 - momentum: 0.000000
86
+ 2023-10-20 09:18:44,300 epoch 1 - iter 693/773 - loss 1.04649070 - time (sec): 16.01 - samples/sec: 6911.30 - lr: 0.000045 - momentum: 0.000000
87
+ 2023-10-20 09:18:46,008 epoch 1 - iter 770/773 - loss 0.96192728 - time (sec): 17.72 - samples/sec: 6982.19 - lr: 0.000050 - momentum: 0.000000
88
+ 2023-10-20 09:18:46,078 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-20 09:18:46,078 EPOCH 1 done: loss 0.9579 - lr: 0.000050
90
+ 2023-10-20 09:18:47,081 DEV : loss 0.13065889477729797 - f1-score (micro avg) 0.0
91
+ 2023-10-20 09:18:47,093 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-20 09:18:48,821 epoch 2 - iter 77/773 - loss 0.21812324 - time (sec): 1.73 - samples/sec: 7194.59 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-20 09:18:50,518 epoch 2 - iter 154/773 - loss 0.20906091 - time (sec): 3.42 - samples/sec: 7000.84 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-20 09:18:52,209 epoch 2 - iter 231/773 - loss 0.20993493 - time (sec): 5.12 - samples/sec: 6931.96 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-20 09:18:54,042 epoch 2 - iter 308/773 - loss 0.19690084 - time (sec): 6.95 - samples/sec: 6958.80 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-20 09:18:55,800 epoch 2 - iter 385/773 - loss 0.19499084 - time (sec): 8.71 - samples/sec: 7026.30 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-20 09:18:57,611 epoch 2 - iter 462/773 - loss 0.19104238 - time (sec): 10.52 - samples/sec: 6931.75 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-20 09:18:59,427 epoch 2 - iter 539/773 - loss 0.18943072 - time (sec): 12.33 - samples/sec: 6878.89 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-20 09:19:01,231 epoch 2 - iter 616/773 - loss 0.18586711 - time (sec): 14.14 - samples/sec: 6897.61 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-20 09:19:03,004 epoch 2 - iter 693/773 - loss 0.18459343 - time (sec): 15.91 - samples/sec: 6903.21 - lr: 0.000045 - momentum: 0.000000
101
+ 2023-10-20 09:19:04,772 epoch 2 - iter 770/773 - loss 0.18021271 - time (sec): 17.68 - samples/sec: 6991.26 - lr: 0.000044 - momentum: 0.000000
102
+ 2023-10-20 09:19:04,847 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-20 09:19:04,848 EPOCH 2 done: loss 0.1796 - lr: 0.000044
104
+ 2023-10-20 09:19:06,215 DEV : loss 0.08806052803993225 - f1-score (micro avg) 0.4817
105
+ 2023-10-20 09:19:06,227 saving best model
106
+ 2023-10-20 09:19:06,256 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-20 09:19:08,034 epoch 3 - iter 77/773 - loss 0.16021178 - time (sec): 1.78 - samples/sec: 6437.36 - lr: 0.000044 - momentum: 0.000000
108
+ 2023-10-20 09:19:09,769 epoch 3 - iter 154/773 - loss 0.14807212 - time (sec): 3.51 - samples/sec: 6858.33 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-20 09:19:11,509 epoch 3 - iter 231/773 - loss 0.14019763 - time (sec): 5.25 - samples/sec: 6941.49 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-20 09:19:13,236 epoch 3 - iter 308/773 - loss 0.14847424 - time (sec): 6.98 - samples/sec: 7082.25 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-20 09:19:14,934 epoch 3 - iter 385/773 - loss 0.14709744 - time (sec): 8.68 - samples/sec: 7070.55 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-20 09:19:16,681 epoch 3 - iter 462/773 - loss 0.14818828 - time (sec): 10.42 - samples/sec: 7183.86 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-20 09:19:18,432 epoch 3 - iter 539/773 - loss 0.14929835 - time (sec): 12.18 - samples/sec: 7178.10 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-20 09:19:20,162 epoch 3 - iter 616/773 - loss 0.14786552 - time (sec): 13.91 - samples/sec: 7189.40 - lr: 0.000040 - momentum: 0.000000
115
+ 2023-10-20 09:19:21,899 epoch 3 - iter 693/773 - loss 0.14779447 - time (sec): 15.64 - samples/sec: 7105.63 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-20 09:19:23,605 epoch 3 - iter 770/773 - loss 0.14693652 - time (sec): 17.35 - samples/sec: 7129.47 - lr: 0.000039 - momentum: 0.000000
117
+ 2023-10-20 09:19:23,676 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-20 09:19:23,676 EPOCH 3 done: loss 0.1467 - lr: 0.000039
119
+ 2023-10-20 09:19:24,745 DEV : loss 0.07945284247398376 - f1-score (micro avg) 0.585
120
+ 2023-10-20 09:19:24,756 saving best model
121
+ 2023-10-20 09:19:24,790 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-20 09:19:26,577 epoch 4 - iter 77/773 - loss 0.13996426 - time (sec): 1.79 - samples/sec: 7057.97 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-20 09:19:28,330 epoch 4 - iter 154/773 - loss 0.13144568 - time (sec): 3.54 - samples/sec: 7020.35 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-20 09:19:30,061 epoch 4 - iter 231/773 - loss 0.13656365 - time (sec): 5.27 - samples/sec: 6788.28 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-20 09:19:31,745 epoch 4 - iter 308/773 - loss 0.13712233 - time (sec): 6.95 - samples/sec: 6967.80 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-20 09:19:33,517 epoch 4 - iter 385/773 - loss 0.13771739 - time (sec): 8.73 - samples/sec: 6955.05 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-20 09:19:35,269 epoch 4 - iter 462/773 - loss 0.13408346 - time (sec): 10.48 - samples/sec: 6958.02 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-20 09:19:37,000 epoch 4 - iter 539/773 - loss 0.13073922 - time (sec): 12.21 - samples/sec: 7056.03 - lr: 0.000035 - momentum: 0.000000
129
+ 2023-10-20 09:19:38,795 epoch 4 - iter 616/773 - loss 0.13003178 - time (sec): 14.00 - samples/sec: 7078.88 - lr: 0.000034 - momentum: 0.000000
130
+ 2023-10-20 09:19:40,490 epoch 4 - iter 693/773 - loss 0.13006617 - time (sec): 15.70 - samples/sec: 7082.33 - lr: 0.000034 - momentum: 0.000000
131
+ 2023-10-20 09:19:42,234 epoch 4 - iter 770/773 - loss 0.12994693 - time (sec): 17.44 - samples/sec: 7100.14 - lr: 0.000033 - momentum: 0.000000
132
+ 2023-10-20 09:19:42,298 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-20 09:19:42,298 EPOCH 4 done: loss 0.1299 - lr: 0.000033
134
+ 2023-10-20 09:19:43,375 DEV : loss 0.07809021323919296 - f1-score (micro avg) 0.6071
135
+ 2023-10-20 09:19:43,386 saving best model
136
+ 2023-10-20 09:19:43,425 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-20 09:19:45,188 epoch 5 - iter 77/773 - loss 0.11117031 - time (sec): 1.76 - samples/sec: 6996.81 - lr: 0.000033 - momentum: 0.000000
138
+ 2023-10-20 09:19:46,900 epoch 5 - iter 154/773 - loss 0.11764714 - time (sec): 3.47 - samples/sec: 6894.04 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-20 09:19:48,635 epoch 5 - iter 231/773 - loss 0.11991202 - time (sec): 5.21 - samples/sec: 6905.69 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-20 09:19:50,432 epoch 5 - iter 308/773 - loss 0.11700014 - time (sec): 7.01 - samples/sec: 7024.72 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-20 09:19:52,197 epoch 5 - iter 385/773 - loss 0.11617792 - time (sec): 8.77 - samples/sec: 7091.97 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-20 09:19:53,901 epoch 5 - iter 462/773 - loss 0.11525526 - time (sec): 10.48 - samples/sec: 7097.11 - lr: 0.000030 - momentum: 0.000000
143
+ 2023-10-20 09:19:55,632 epoch 5 - iter 539/773 - loss 0.11333040 - time (sec): 12.21 - samples/sec: 7074.53 - lr: 0.000029 - momentum: 0.000000
144
+ 2023-10-20 09:19:57,353 epoch 5 - iter 616/773 - loss 0.11550300 - time (sec): 13.93 - samples/sec: 7091.84 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-20 09:19:59,064 epoch 5 - iter 693/773 - loss 0.11629394 - time (sec): 15.64 - samples/sec: 7154.16 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-20 09:20:00,821 epoch 5 - iter 770/773 - loss 0.11699897 - time (sec): 17.40 - samples/sec: 7117.38 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-20 09:20:00,890 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-20 09:20:00,890 EPOCH 5 done: loss 0.1169 - lr: 0.000028
149
+ 2023-10-20 09:20:01,993 DEV : loss 0.07527422904968262 - f1-score (micro avg) 0.5973
150
+ 2023-10-20 09:20:02,004 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-20 09:20:03,679 epoch 6 - iter 77/773 - loss 0.09373771 - time (sec): 1.67 - samples/sec: 7129.91 - lr: 0.000027 - momentum: 0.000000
152
+ 2023-10-20 09:20:05,341 epoch 6 - iter 154/773 - loss 0.10168393 - time (sec): 3.34 - samples/sec: 7107.39 - lr: 0.000027 - momentum: 0.000000
153
+ 2023-10-20 09:20:07,029 epoch 6 - iter 231/773 - loss 0.11169160 - time (sec): 5.02 - samples/sec: 7123.67 - lr: 0.000026 - momentum: 0.000000
154
+ 2023-10-20 09:20:08,763 epoch 6 - iter 308/773 - loss 0.11308050 - time (sec): 6.76 - samples/sec: 7205.74 - lr: 0.000026 - momentum: 0.000000
155
+ 2023-10-20 09:20:10,476 epoch 6 - iter 385/773 - loss 0.11734393 - time (sec): 8.47 - samples/sec: 7119.05 - lr: 0.000025 - momentum: 0.000000
156
+ 2023-10-20 09:20:12,242 epoch 6 - iter 462/773 - loss 0.11359539 - time (sec): 10.24 - samples/sec: 7161.69 - lr: 0.000024 - momentum: 0.000000
157
+ 2023-10-20 09:20:13,952 epoch 6 - iter 539/773 - loss 0.11053055 - time (sec): 11.95 - samples/sec: 7179.03 - lr: 0.000024 - momentum: 0.000000
158
+ 2023-10-20 09:20:15,718 epoch 6 - iter 616/773 - loss 0.10958303 - time (sec): 13.71 - samples/sec: 7213.13 - lr: 0.000023 - momentum: 0.000000
159
+ 2023-10-20 09:20:17,429 epoch 6 - iter 693/773 - loss 0.10856611 - time (sec): 15.42 - samples/sec: 7165.92 - lr: 0.000023 - momentum: 0.000000
160
+ 2023-10-20 09:20:19,168 epoch 6 - iter 770/773 - loss 0.10997793 - time (sec): 17.16 - samples/sec: 7211.89 - lr: 0.000022 - momentum: 0.000000
161
+ 2023-10-20 09:20:19,240 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-20 09:20:19,241 EPOCH 6 done: loss 0.1098 - lr: 0.000022
163
+ 2023-10-20 09:20:20,340 DEV : loss 0.07457771897315979 - f1-score (micro avg) 0.6144
164
+ 2023-10-20 09:20:20,354 saving best model
165
+ 2023-10-20 09:20:20,394 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-20 09:20:22,182 epoch 7 - iter 77/773 - loss 0.10104822 - time (sec): 1.79 - samples/sec: 7514.85 - lr: 0.000022 - momentum: 0.000000
167
+ 2023-10-20 09:20:23,898 epoch 7 - iter 154/773 - loss 0.09821556 - time (sec): 3.50 - samples/sec: 7100.36 - lr: 0.000021 - momentum: 0.000000
168
+ 2023-10-20 09:20:25,626 epoch 7 - iter 231/773 - loss 0.09548090 - time (sec): 5.23 - samples/sec: 7242.33 - lr: 0.000021 - momentum: 0.000000
169
+ 2023-10-20 09:20:27,321 epoch 7 - iter 308/773 - loss 0.10355270 - time (sec): 6.93 - samples/sec: 7143.99 - lr: 0.000020 - momentum: 0.000000
170
+ 2023-10-20 09:20:29,117 epoch 7 - iter 385/773 - loss 0.10438038 - time (sec): 8.72 - samples/sec: 7124.85 - lr: 0.000019 - momentum: 0.000000
171
+ 2023-10-20 09:20:30,854 epoch 7 - iter 462/773 - loss 0.10313345 - time (sec): 10.46 - samples/sec: 7148.72 - lr: 0.000019 - momentum: 0.000000
172
+ 2023-10-20 09:20:32,639 epoch 7 - iter 539/773 - loss 0.10557270 - time (sec): 12.24 - samples/sec: 7134.59 - lr: 0.000018 - momentum: 0.000000
173
+ 2023-10-20 09:20:34,316 epoch 7 - iter 616/773 - loss 0.10463863 - time (sec): 13.92 - samples/sec: 7183.24 - lr: 0.000018 - momentum: 0.000000
174
+ 2023-10-20 09:20:36,084 epoch 7 - iter 693/773 - loss 0.10402035 - time (sec): 15.69 - samples/sec: 7119.43 - lr: 0.000017 - momentum: 0.000000
175
+ 2023-10-20 09:20:37,828 epoch 7 - iter 770/773 - loss 0.10392693 - time (sec): 17.43 - samples/sec: 7102.19 - lr: 0.000017 - momentum: 0.000000
176
+ 2023-10-20 09:20:37,899 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-20 09:20:37,899 EPOCH 7 done: loss 0.1037 - lr: 0.000017
178
+ 2023-10-20 09:20:39,024 DEV : loss 0.07657597213983536 - f1-score (micro avg) 0.6242
179
+ 2023-10-20 09:20:39,037 saving best model
180
+ 2023-10-20 09:20:39,075 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-20 09:20:40,803 epoch 8 - iter 77/773 - loss 0.08347295 - time (sec): 1.73 - samples/sec: 7045.81 - lr: 0.000016 - momentum: 0.000000
182
+ 2023-10-20 09:20:42,539 epoch 8 - iter 154/773 - loss 0.10176786 - time (sec): 3.46 - samples/sec: 7193.34 - lr: 0.000016 - momentum: 0.000000
183
+ 2023-10-20 09:20:44,261 epoch 8 - iter 231/773 - loss 0.10219115 - time (sec): 5.19 - samples/sec: 7117.05 - lr: 0.000015 - momentum: 0.000000
184
+ 2023-10-20 09:20:45,993 epoch 8 - iter 308/773 - loss 0.09661994 - time (sec): 6.92 - samples/sec: 7120.96 - lr: 0.000014 - momentum: 0.000000
185
+ 2023-10-20 09:20:47,714 epoch 8 - iter 385/773 - loss 0.09443349 - time (sec): 8.64 - samples/sec: 7214.99 - lr: 0.000014 - momentum: 0.000000
186
+ 2023-10-20 09:20:49,480 epoch 8 - iter 462/773 - loss 0.09714750 - time (sec): 10.40 - samples/sec: 7273.85 - lr: 0.000013 - momentum: 0.000000
187
+ 2023-10-20 09:20:51,177 epoch 8 - iter 539/773 - loss 0.09639649 - time (sec): 12.10 - samples/sec: 7201.04 - lr: 0.000013 - momentum: 0.000000
188
+ 2023-10-20 09:20:52,899 epoch 8 - iter 616/773 - loss 0.09879490 - time (sec): 13.82 - samples/sec: 7136.22 - lr: 0.000012 - momentum: 0.000000
189
+ 2023-10-20 09:20:54,622 epoch 8 - iter 693/773 - loss 0.09745774 - time (sec): 15.55 - samples/sec: 7128.81 - lr: 0.000012 - momentum: 0.000000
190
+ 2023-10-20 09:20:56,382 epoch 8 - iter 770/773 - loss 0.09749713 - time (sec): 17.31 - samples/sec: 7163.01 - lr: 0.000011 - momentum: 0.000000
191
+ 2023-10-20 09:20:56,439 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-20 09:20:56,439 EPOCH 8 done: loss 0.0973 - lr: 0.000011
193
+ 2023-10-20 09:20:57,540 DEV : loss 0.07944915443658829 - f1-score (micro avg) 0.6269
194
+ 2023-10-20 09:20:57,552 saving best model
195
+ 2023-10-20 09:20:57,590 ----------------------------------------------------------------------------------------------------
196
+ 2023-10-20 09:20:59,260 epoch 9 - iter 77/773 - loss 0.09459646 - time (sec): 1.67 - samples/sec: 7330.85 - lr: 0.000011 - momentum: 0.000000
197
+ 2023-10-20 09:21:00,859 epoch 9 - iter 154/773 - loss 0.09513909 - time (sec): 3.27 - samples/sec: 7555.16 - lr: 0.000010 - momentum: 0.000000
198
+ 2023-10-20 09:21:02,459 epoch 9 - iter 231/773 - loss 0.08891959 - time (sec): 4.87 - samples/sec: 7837.97 - lr: 0.000009 - momentum: 0.000000
199
+ 2023-10-20 09:21:04,135 epoch 9 - iter 308/773 - loss 0.09023339 - time (sec): 6.54 - samples/sec: 7649.30 - lr: 0.000009 - momentum: 0.000000
200
+ 2023-10-20 09:21:05,867 epoch 9 - iter 385/773 - loss 0.09340261 - time (sec): 8.28 - samples/sec: 7652.07 - lr: 0.000008 - momentum: 0.000000
201
+ 2023-10-20 09:21:07,610 epoch 9 - iter 462/773 - loss 0.09643093 - time (sec): 10.02 - samples/sec: 7510.55 - lr: 0.000008 - momentum: 0.000000
202
+ 2023-10-20 09:21:09,362 epoch 9 - iter 539/773 - loss 0.09664935 - time (sec): 11.77 - samples/sec: 7470.84 - lr: 0.000007 - momentum: 0.000000
203
+ 2023-10-20 09:21:11,036 epoch 9 - iter 616/773 - loss 0.09738019 - time (sec): 13.45 - samples/sec: 7447.59 - lr: 0.000007 - momentum: 0.000000
204
+ 2023-10-20 09:21:12,730 epoch 9 - iter 693/773 - loss 0.09569268 - time (sec): 15.14 - samples/sec: 7368.56 - lr: 0.000006 - momentum: 0.000000
205
+ 2023-10-20 09:21:14,449 epoch 9 - iter 770/773 - loss 0.09441439 - time (sec): 16.86 - samples/sec: 7348.71 - lr: 0.000006 - momentum: 0.000000
206
+ 2023-10-20 09:21:14,509 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-20 09:21:14,509 EPOCH 9 done: loss 0.0943 - lr: 0.000006
208
+ 2023-10-20 09:21:15,576 DEV : loss 0.08020081371068954 - f1-score (micro avg) 0.6476
209
+ 2023-10-20 09:21:15,587 saving best model
210
+ 2023-10-20 09:21:15,626 ----------------------------------------------------------------------------------------------------
211
+ 2023-10-20 09:21:17,352 epoch 10 - iter 77/773 - loss 0.10683426 - time (sec): 1.73 - samples/sec: 6965.15 - lr: 0.000005 - momentum: 0.000000
212
+ 2023-10-20 09:21:19,118 epoch 10 - iter 154/773 - loss 0.09922985 - time (sec): 3.49 - samples/sec: 7124.64 - lr: 0.000005 - momentum: 0.000000
213
+ 2023-10-20 09:21:20,969 epoch 10 - iter 231/773 - loss 0.09606770 - time (sec): 5.34 - samples/sec: 7135.38 - lr: 0.000004 - momentum: 0.000000
214
+ 2023-10-20 09:21:22,727 epoch 10 - iter 308/773 - loss 0.09168936 - time (sec): 7.10 - samples/sec: 7163.36 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-20 09:21:24,454 epoch 10 - iter 385/773 - loss 0.09319490 - time (sec): 8.83 - samples/sec: 7145.89 - lr: 0.000003 - momentum: 0.000000
216
+ 2023-10-20 09:21:26,193 epoch 10 - iter 462/773 - loss 0.09108964 - time (sec): 10.57 - samples/sec: 7122.69 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-20 09:21:27,920 epoch 10 - iter 539/773 - loss 0.08863410 - time (sec): 12.29 - samples/sec: 7160.35 - lr: 0.000002 - momentum: 0.000000
218
+ 2023-10-20 09:21:29,676 epoch 10 - iter 616/773 - loss 0.08839821 - time (sec): 14.05 - samples/sec: 7084.18 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-20 09:21:31,407 epoch 10 - iter 693/773 - loss 0.09194621 - time (sec): 15.78 - samples/sec: 7085.52 - lr: 0.000001 - momentum: 0.000000
220
+ 2023-10-20 09:21:33,142 epoch 10 - iter 770/773 - loss 0.09345324 - time (sec): 17.52 - samples/sec: 7078.58 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-20 09:21:33,207 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-20 09:21:33,207 EPOCH 10 done: loss 0.0933 - lr: 0.000000
223
+ 2023-10-20 09:21:34,289 DEV : loss 0.08138395845890045 - f1-score (micro avg) 0.6491
224
+ 2023-10-20 09:21:34,302 saving best model
225
+ 2023-10-20 09:21:34,370 ----------------------------------------------------------------------------------------------------
226
+ 2023-10-20 09:21:34,371 Loading model from best epoch ...
227
+ 2023-10-20 09:21:34,443 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-BUILDING, B-BUILDING, E-BUILDING, I-BUILDING, S-STREET, B-STREET, E-STREET, I-STREET
228
+ 2023-10-20 09:21:37,354
229
+ Results:
230
+ - F-score (micro) 0.5866
231
+ - F-score (macro) 0.3173
232
+ - Accuracy 0.4314
233
+
234
+ By class:
235
+ precision recall f1-score support
236
+
237
+ LOC 0.6274 0.6818 0.6535 946
238
+ BUILDING 0.3400 0.0919 0.1447 185
239
+ STREET 0.5556 0.0893 0.1538 56
240
+
241
+ micro avg 0.6136 0.5619 0.5866 1187
242
+ macro avg 0.5077 0.2877 0.3173 1187
243
+ weighted avg 0.5792 0.5619 0.5506 1187
244
+
245
+ 2023-10-20 09:21:37,354 ----------------------------------------------------------------------------------------------------