Hugging Face's logo

stefan-it
/
hmbench-icdar-fr-hmbert_tiny-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
fe7e39d
•
1 Parent(s): 45d5fe2

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.1697666073.46dc0c540dd0.3341.19 +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:fee23266555510fad03bf060eb4fa8a816f5e7dfb0895e8bf749a2f20eb53ebd
3
+ size 19045922
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 21:54:57 0.0000 0.9704 0.2183 0.3298 0.3213 0.3255 0.2185
3
+ 2 21:55:21 0.0000 0.2748 0.1905 0.3265 0.4118 0.3642 0.2490
4
+ 3 21:55:45 0.0000 0.2337 0.1749 0.3976 0.4412 0.4182 0.2863
5
+ 4 21:56:09 0.0000 0.2099 0.1590 0.4064 0.4570 0.4302 0.2958
6
+ 5 21:56:33 0.0000 0.1918 0.1518 0.4356 0.4977 0.4646 0.3242
7
+ 6 21:56:58 0.0000 0.1799 0.1518 0.4339 0.4977 0.4636 0.3242
8
+ 7 21:57:23 0.0000 0.1710 0.1477 0.4308 0.4966 0.4614 0.3233
9
+ 8 21:57:47 0.0000 0.1653 0.1502 0.4358 0.5181 0.4734 0.3336
10
+ 9 21:58:11 0.0000 0.1599 0.1510 0.4498 0.5170 0.4811 0.3416
11
+ 10 21:58:36 0.0000 0.1566 0.1495 0.4571 0.5238 0.4881 0.3471
runs/events.out.tfevents.1697666073.46dc0c540dd0.3341.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0c5aaab010007ef44677be29514571b3bb2d07c1a0a8d1941fbf151fa0d4614
3
+ size 556612
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-18 21:54:33,271 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-18 21:54:33,272 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
+ 2023-10-18 21:54:33,272 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-18 21:54:33,272 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
+ 2023-10-18 21:54:33,272 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-18 21:54:33,272 Train: 7936 sentences
55
+ 2023-10-18 21:54:33,272 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-18 21:54:33,272 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-18 21:54:33,272 Training Params:
58
+ 2023-10-18 21:54:33,272 - learning_rate: "5e-05"
59
+ 2023-10-18 21:54:33,272 - mini_batch_size: "8"
60
+ 2023-10-18 21:54:33,272 - max_epochs: "10"
61
+ 2023-10-18 21:54:33,272 - shuffle: "True"
62
+ 2023-10-18 21:54:33,272 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-18 21:54:33,272 Plugins:
64
+ 2023-10-18 21:54:33,272 - TensorboardLogger
65
+ 2023-10-18 21:54:33,272 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-18 21:54:33,272 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-18 21:54:33,272 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-18 21:54:33,272 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-18 21:54:33,272 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-18 21:54:33,272 Computation:
71
+ 2023-10-18 21:54:33,272 - compute on device: cuda:0
72
+ 2023-10-18 21:54:33,272 - embedding storage: none
73
+ 2023-10-18 21:54:33,272 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-18 21:54:33,272 Model training base path: "hmbench-icdar/fr-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
75
+ 2023-10-18 21:54:33,273 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-18 21:54:33,273 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-18 21:54:33,273 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-18 21:54:35,500 epoch 1 - iter 99/992 - loss 3.11355291 - time (sec): 2.23 - samples/sec: 7666.30 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-18 21:54:37,678 epoch 1 - iter 198/992 - loss 2.79550926 - time (sec): 4.40 - samples/sec: 7440.64 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-18 21:54:39,905 epoch 1 - iter 297/992 - loss 2.26929089 - time (sec): 6.63 - samples/sec: 7505.99 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-18 21:54:42,204 epoch 1 - iter 396/992 - loss 1.82821963 - time (sec): 8.93 - samples/sec: 7490.72 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-18 21:54:44,416 epoch 1 - iter 495/992 - loss 1.57018564 - time (sec): 11.14 - samples/sec: 7467.81 - lr: 0.000025 - momentum: 0.000000
83
+ 2023-10-18 21:54:46,645 epoch 1 - iter 594/992 - loss 1.38359360 - time (sec): 13.37 - samples/sec: 7441.53 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-18 21:54:48,875 epoch 1 - iter 693/992 - loss 1.23623179 - time (sec): 15.60 - samples/sec: 7446.06 - lr: 0.000035 - momentum: 0.000000
85
+ 2023-10-18 21:54:51,050 epoch 1 - iter 792/992 - loss 1.12943382 - time (sec): 17.78 - samples/sec: 7407.13 - lr: 0.000040 - momentum: 0.000000
86
+ 2023-10-18 21:54:53,334 epoch 1 - iter 891/992 - loss 1.04184352 - time (sec): 20.06 - samples/sec: 7358.15 - lr: 0.000045 - momentum: 0.000000
87
+ 2023-10-18 21:54:55,537 epoch 1 - iter 990/992 - loss 0.97151767 - time (sec): 22.26 - samples/sec: 7352.94 - lr: 0.000050 - momentum: 0.000000
88
+ 2023-10-18 21:54:55,582 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-18 21:54:55,582 EPOCH 1 done: loss 0.9704 - lr: 0.000050
90
+ 2023-10-18 21:54:57,145 DEV : loss 0.21833859384059906 - f1-score (micro avg) 0.3255
91
+ 2023-10-18 21:54:57,164 saving best model
92
+ 2023-10-18 21:54:57,197 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-18 21:54:59,459 epoch 2 - iter 99/992 - loss 0.32706359 - time (sec): 2.26 - samples/sec: 7173.70 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-18 21:55:01,708 epoch 2 - iter 198/992 - loss 0.30563463 - time (sec): 4.51 - samples/sec: 7302.81 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-18 21:55:03,969 epoch 2 - iter 297/992 - loss 0.29429747 - time (sec): 6.77 - samples/sec: 7288.04 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-18 21:55:06,244 epoch 2 - iter 396/992 - loss 0.29148563 - time (sec): 9.05 - samples/sec: 7349.37 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-18 21:55:08,509 epoch 2 - iter 495/992 - loss 0.28801704 - time (sec): 11.31 - samples/sec: 7327.17 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-18 21:55:10,695 epoch 2 - iter 594/992 - loss 0.28735579 - time (sec): 13.50 - samples/sec: 7332.54 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-18 21:55:12,926 epoch 2 - iter 693/992 - loss 0.28460464 - time (sec): 15.73 - samples/sec: 7250.53 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-18 21:55:15,130 epoch 2 - iter 792/992 - loss 0.28520998 - time (sec): 17.93 - samples/sec: 7217.01 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-18 21:55:17,353 epoch 2 - iter 891/992 - loss 0.28026538 - time (sec): 20.16 - samples/sec: 7269.54 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-18 21:55:19,536 epoch 2 - iter 990/992 - loss 0.27503839 - time (sec): 22.34 - samples/sec: 7321.67 - lr: 0.000044 - momentum: 0.000000
103
+ 2023-10-18 21:55:19,584 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-18 21:55:19,584 EPOCH 2 done: loss 0.2748 - lr: 0.000044
105
+ 2023-10-18 21:55:21,774 DEV : loss 0.19050592184066772 - f1-score (micro avg) 0.3642
106
+ 2023-10-18 21:55:21,794 saving best model
107
+ 2023-10-18 21:55:21,829 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-18 21:55:24,022 epoch 3 - iter 99/992 - loss 0.24311763 - time (sec): 2.19 - samples/sec: 7302.08 - lr: 0.000044 - momentum: 0.000000
109
+ 2023-10-18 21:55:26,230 epoch 3 - iter 198/992 - loss 0.23452324 - time (sec): 4.40 - samples/sec: 7287.89 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-18 21:55:28,453 epoch 3 - iter 297/992 - loss 0.22907305 - time (sec): 6.62 - samples/sec: 7223.86 - lr: 0.000043 - momentum: 0.000000
111
+ 2023-10-18 21:55:30,594 epoch 3 - iter 396/992 - loss 0.23622014 - time (sec): 8.76 - samples/sec: 7324.50 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-18 21:55:32,575 epoch 3 - iter 495/992 - loss 0.23845281 - time (sec): 10.75 - samples/sec: 7506.47 - lr: 0.000042 - momentum: 0.000000
113
+ 2023-10-18 21:55:34,775 epoch 3 - iter 594/992 - loss 0.23683125 - time (sec): 12.95 - samples/sec: 7508.86 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-18 21:55:36,956 epoch 3 - iter 693/992 - loss 0.23617397 - time (sec): 15.13 - samples/sec: 7515.06 - lr: 0.000041 - momentum: 0.000000
115
+ 2023-10-18 21:55:39,166 epoch 3 - iter 792/992 - loss 0.23480189 - time (sec): 17.34 - samples/sec: 7516.39 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-18 21:55:41,385 epoch 3 - iter 891/992 - loss 0.23528113 - time (sec): 19.56 - samples/sec: 7487.53 - lr: 0.000039 - momentum: 0.000000
117
+ 2023-10-18 21:55:43,685 epoch 3 - iter 990/992 - loss 0.23330811 - time (sec): 21.86 - samples/sec: 7491.34 - lr: 0.000039 - momentum: 0.000000
118
+ 2023-10-18 21:55:43,736 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-18 21:55:43,736 EPOCH 3 done: loss 0.2337 - lr: 0.000039
120
+ 2023-10-18 21:55:45,582 DEV : loss 0.1749068647623062 - f1-score (micro avg) 0.4182
121
+ 2023-10-18 21:55:45,601 saving best model
122
+ 2023-10-18 21:55:45,640 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-18 21:55:47,867 epoch 4 - iter 99/992 - loss 0.23209216 - time (sec): 2.23 - samples/sec: 7316.80 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-18 21:55:50,006 epoch 4 - iter 198/992 - loss 0.21943860 - time (sec): 4.37 - samples/sec: 7335.23 - lr: 0.000038 - momentum: 0.000000
125
+ 2023-10-18 21:55:52,141 epoch 4 - iter 297/992 - loss 0.21580522 - time (sec): 6.50 - samples/sec: 7473.64 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-18 21:55:54,086 epoch 4 - iter 396/992 - loss 0.21521306 - time (sec): 8.44 - samples/sec: 7706.14 - lr: 0.000037 - momentum: 0.000000
127
+ 2023-10-18 21:55:56,286 epoch 4 - iter 495/992 - loss 0.21303400 - time (sec): 10.65 - samples/sec: 7697.26 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-18 21:55:58,585 epoch 4 - iter 594/992 - loss 0.21386872 - time (sec): 12.94 - samples/sec: 7620.66 - lr: 0.000036 - momentum: 0.000000
129
+ 2023-10-18 21:56:00,843 epoch 4 - iter 693/992 - loss 0.21292105 - time (sec): 15.20 - samples/sec: 7609.58 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-18 21:56:03,054 epoch 4 - iter 792/992 - loss 0.21167609 - time (sec): 17.41 - samples/sec: 7582.95 - lr: 0.000034 - momentum: 0.000000
131
+ 2023-10-18 21:56:05,288 epoch 4 - iter 891/992 - loss 0.21036360 - time (sec): 19.65 - samples/sec: 7539.23 - lr: 0.000034 - momentum: 0.000000
132
+ 2023-10-18 21:56:07,573 epoch 4 - iter 990/992 - loss 0.21009866 - time (sec): 21.93 - samples/sec: 7461.11 - lr: 0.000033 - momentum: 0.000000
133
+ 2023-10-18 21:56:07,624 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-18 21:56:07,625 EPOCH 4 done: loss 0.2099 - lr: 0.000033
135
+ 2023-10-18 21:56:09,454 DEV : loss 0.1589556187391281 - f1-score (micro avg) 0.4302
136
+ 2023-10-18 21:56:09,473 saving best model
137
+ 2023-10-18 21:56:09,507 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-18 21:56:11,681 epoch 5 - iter 99/992 - loss 0.21244283 - time (sec): 2.17 - samples/sec: 7120.21 - lr: 0.000033 - momentum: 0.000000
139
+ 2023-10-18 21:56:13,909 epoch 5 - iter 198/992 - loss 0.20346866 - time (sec): 4.40 - samples/sec: 7143.14 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-18 21:56:16,179 epoch 5 - iter 297/992 - loss 0.19250101 - time (sec): 6.67 - samples/sec: 7157.94 - lr: 0.000032 - momentum: 0.000000
141
+ 2023-10-18 21:56:18,394 epoch 5 - iter 396/992 - loss 0.19416248 - time (sec): 8.89 - samples/sec: 7174.94 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-18 21:56:20,709 epoch 5 - iter 495/992 - loss 0.19298598 - time (sec): 11.20 - samples/sec: 7166.12 - lr: 0.000031 - momentum: 0.000000
143
+ 2023-10-18 21:56:22,990 epoch 5 - iter 594/992 - loss 0.19140411 - time (sec): 13.48 - samples/sec: 7227.29 - lr: 0.000030 - momentum: 0.000000
144
+ 2023-10-18 21:56:25,289 epoch 5 - iter 693/992 - loss 0.19104653 - time (sec): 15.78 - samples/sec: 7234.47 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-18 21:56:27,581 epoch 5 - iter 792/992 - loss 0.19022986 - time (sec): 18.07 - samples/sec: 7240.62 - lr: 0.000029 - momentum: 0.000000
146
+ 2023-10-18 21:56:29,785 epoch 5 - iter 891/992 - loss 0.18871481 - time (sec): 20.28 - samples/sec: 7294.24 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-18 21:56:31,990 epoch 5 - iter 990/992 - loss 0.19191013 - time (sec): 22.48 - samples/sec: 7277.88 - lr: 0.000028 - momentum: 0.000000
148
+ 2023-10-18 21:56:32,037 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-18 21:56:32,037 EPOCH 5 done: loss 0.1918 - lr: 0.000028
150
+ 2023-10-18 21:56:33,887 DEV : loss 0.15180285274982452 - f1-score (micro avg) 0.4646
151
+ 2023-10-18 21:56:33,907 saving best model
152
+ 2023-10-18 21:56:33,942 ----------------------------------------------------------------------------------------------------
153
+ 2023-10-18 21:56:36,213 epoch 6 - iter 99/992 - loss 0.19371930 - time (sec): 2.27 - samples/sec: 7383.02 - lr: 0.000027 - momentum: 0.000000
154
+ 2023-10-18 21:56:38,443 epoch 6 - iter 198/992 - loss 0.19060230 - time (sec): 4.50 - samples/sec: 7462.91 - lr: 0.000027 - momentum: 0.000000
155
+ 2023-10-18 21:56:40,617 epoch 6 - iter 297/992 - loss 0.18894797 - time (sec): 6.67 - samples/sec: 7425.76 - lr: 0.000026 - momentum: 0.000000
156
+ 2023-10-18 21:56:42,855 epoch 6 - iter 396/992 - loss 0.18244944 - time (sec): 8.91 - samples/sec: 7341.36 - lr: 0.000026 - momentum: 0.000000
157
+ 2023-10-18 21:56:45,105 epoch 6 - iter 495/992 - loss 0.18110119 - time (sec): 11.16 - samples/sec: 7315.36 - lr: 0.000025 - momentum: 0.000000
158
+ 2023-10-18 21:56:47,397 epoch 6 - iter 594/992 - loss 0.17861193 - time (sec): 13.45 - samples/sec: 7316.73 - lr: 0.000024 - momentum: 0.000000
159
+ 2023-10-18 21:56:49,686 epoch 6 - iter 693/992 - loss 0.17844836 - time (sec): 15.74 - samples/sec: 7374.44 - lr: 0.000024 - momentum: 0.000000
160
+ 2023-10-18 21:56:51,924 epoch 6 - iter 792/992 - loss 0.17957471 - time (sec): 17.98 - samples/sec: 7292.61 - lr: 0.000023 - momentum: 0.000000
161
+ 2023-10-18 21:56:54,153 epoch 6 - iter 891/992 - loss 0.17926821 - time (sec): 20.21 - samples/sec: 7280.88 - lr: 0.000023 - momentum: 0.000000
162
+ 2023-10-18 21:56:56,391 epoch 6 - iter 990/992 - loss 0.17924101 - time (sec): 22.45 - samples/sec: 7286.45 - lr: 0.000022 - momentum: 0.000000
163
+ 2023-10-18 21:56:56,441 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-18 21:56:56,441 EPOCH 6 done: loss 0.1799 - lr: 0.000022
165
+ 2023-10-18 21:56:58,301 DEV : loss 0.15175634622573853 - f1-score (micro avg) 0.4636
166
+ 2023-10-18 21:56:58,320 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-18 21:57:00,560 epoch 7 - iter 99/992 - loss 0.17331896 - time (sec): 2.24 - samples/sec: 6979.09 - lr: 0.000022 - momentum: 0.000000
168
+ 2023-10-18 21:57:02,905 epoch 7 - iter 198/992 - loss 0.17621820 - time (sec): 4.58 - samples/sec: 7191.86 - lr: 0.000021 - momentum: 0.000000
169
+ 2023-10-18 21:57:05,242 epoch 7 - iter 297/992 - loss 0.17242925 - time (sec): 6.92 - samples/sec: 7159.28 - lr: 0.000021 - momentum: 0.000000
170
+ 2023-10-18 21:57:07,579 epoch 7 - iter 396/992 - loss 0.16680316 - time (sec): 9.26 - samples/sec: 7077.62 - lr: 0.000020 - momentum: 0.000000
171
+ 2023-10-18 21:57:09,886 epoch 7 - iter 495/992 - loss 0.16917314 - time (sec): 11.57 - samples/sec: 7049.19 - lr: 0.000019 - momentum: 0.000000
172
+ 2023-10-18 21:57:12,114 epoch 7 - iter 594/992 - loss 0.16845160 - time (sec): 13.79 - samples/sec: 7097.60 - lr: 0.000019 - momentum: 0.000000
173
+ 2023-10-18 21:57:14,364 epoch 7 - iter 693/992 - loss 0.16833284 - time (sec): 16.04 - samples/sec: 7120.30 - lr: 0.000018 - momentum: 0.000000
174
+ 2023-10-18 21:57:16,729 epoch 7 - iter 792/992 - loss 0.16816329 - time (sec): 18.41 - samples/sec: 7189.87 - lr: 0.000018 - momentum: 0.000000
175
+ 2023-10-18 21:57:18,914 epoch 7 - iter 891/992 - loss 0.16870231 - time (sec): 20.59 - samples/sec: 7207.37 - lr: 0.000017 - momentum: 0.000000
176
+ 2023-10-18 21:57:21,088 epoch 7 - iter 990/992 - loss 0.17120803 - time (sec): 22.77 - samples/sec: 7184.77 - lr: 0.000017 - momentum: 0.000000
177
+ 2023-10-18 21:57:21,133 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-18 21:57:21,133 EPOCH 7 done: loss 0.1710 - lr: 0.000017
179
+ 2023-10-18 21:57:23,365 DEV : loss 0.14771050214767456 - f1-score (micro avg) 0.4614
180
+ 2023-10-18 21:57:23,384 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-18 21:57:25,576 epoch 8 - iter 99/992 - loss 0.16145510 - time (sec): 2.19 - samples/sec: 8094.49 - lr: 0.000016 - momentum: 0.000000
182
+ 2023-10-18 21:57:27,798 epoch 8 - iter 198/992 - loss 0.16238181 - time (sec): 4.41 - samples/sec: 7801.61 - lr: 0.000016 - momentum: 0.000000
183
+ 2023-10-18 21:57:30,048 epoch 8 - iter 297/992 - loss 0.16042643 - time (sec): 6.66 - samples/sec: 7743.08 - lr: 0.000015 - momentum: 0.000000
184
+ 2023-10-18 21:57:32,312 epoch 8 - iter 396/992 - loss 0.16123392 - time (sec): 8.93 - samples/sec: 7716.08 - lr: 0.000014 - momentum: 0.000000
185
+ 2023-10-18 21:57:34,474 epoch 8 - iter 495/992 - loss 0.15882526 - time (sec): 11.09 - samples/sec: 7568.87 - lr: 0.000014 - momentum: 0.000000
186
+ 2023-10-18 21:57:36,702 epoch 8 - iter 594/992 - loss 0.15852308 - time (sec): 13.32 - samples/sec: 7545.54 - lr: 0.000013 - momentum: 0.000000
187
+ 2023-10-18 21:57:38,933 epoch 8 - iter 693/992 - loss 0.16090394 - time (sec): 15.55 - samples/sec: 7490.79 - lr: 0.000013 - momentum: 0.000000
188
+ 2023-10-18 21:57:41,122 epoch 8 - iter 792/992 - loss 0.16162584 - time (sec): 17.74 - samples/sec: 7465.42 - lr: 0.000012 - momentum: 0.000000
189
+ 2023-10-18 21:57:43,302 epoch 8 - iter 891/992 - loss 0.16350113 - time (sec): 19.92 - samples/sec: 7410.15 - lr: 0.000012 - momentum: 0.000000
190
+ 2023-10-18 21:57:45,570 epoch 8 - iter 990/992 - loss 0.16534095 - time (sec): 22.19 - samples/sec: 7377.71 - lr: 0.000011 - momentum: 0.000000
191
+ 2023-10-18 21:57:45,617 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-18 21:57:45,617 EPOCH 8 done: loss 0.1653 - lr: 0.000011
193
+ 2023-10-18 21:57:47,461 DEV : loss 0.15022730827331543 - f1-score (micro avg) 0.4734
194
+ 2023-10-18 21:57:47,483 saving best model
195
+ 2023-10-18 21:57:47,522 ----------------------------------------------------------------------------------------------------
196
+ 2023-10-18 21:57:49,845 epoch 9 - iter 99/992 - loss 0.15429276 - time (sec): 2.32 - samples/sec: 7144.31 - lr: 0.000011 - momentum: 0.000000
197
+ 2023-10-18 21:57:52,069 epoch 9 - iter 198/992 - loss 0.15976108 - time (sec): 4.55 - samples/sec: 7389.48 - lr: 0.000010 - momentum: 0.000000
198
+ 2023-10-18 21:57:54,419 epoch 9 - iter 297/992 - loss 0.16814053 - time (sec): 6.90 - samples/sec: 7414.35 - lr: 0.000009 - momentum: 0.000000
199
+ 2023-10-18 21:57:56,610 epoch 9 - iter 396/992 - loss 0.16893864 - time (sec): 9.09 - samples/sec: 7402.74 - lr: 0.000009 - momentum: 0.000000
200
+ 2023-10-18 21:57:58,842 epoch 9 - iter 495/992 - loss 0.16480279 - time (sec): 11.32 - samples/sec: 7368.59 - lr: 0.000008 - momentum: 0.000000
201
+ 2023-10-18 21:58:01,049 epoch 9 - iter 594/992 - loss 0.16380758 - time (sec): 13.53 - samples/sec: 7331.97 - lr: 0.000008 - momentum: 0.000000
202
+ 2023-10-18 21:58:03,242 epoch 9 - iter 693/992 - loss 0.16219906 - time (sec): 15.72 - samples/sec: 7370.67 - lr: 0.000007 - momentum: 0.000000
203
+ 2023-10-18 21:58:05,443 epoch 9 - iter 792/992 - loss 0.16449280 - time (sec): 17.92 - samples/sec: 7342.15 - lr: 0.000007 - momentum: 0.000000
204
+ 2023-10-18 21:58:07,702 epoch 9 - iter 891/992 - loss 0.16241771 - time (sec): 20.18 - samples/sec: 7314.62 - lr: 0.000006 - momentum: 0.000000
205
+ 2023-10-18 21:58:09,923 epoch 9 - iter 990/992 - loss 0.15995791 - time (sec): 22.40 - samples/sec: 7312.03 - lr: 0.000006 - momentum: 0.000000
206
+ 2023-10-18 21:58:09,963 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-18 21:58:09,964 EPOCH 9 done: loss 0.1599 - lr: 0.000006
208
+ 2023-10-18 21:58:11,791 DEV : loss 0.15096156299114227 - f1-score (micro avg) 0.4811
209
+ 2023-10-18 21:58:11,811 saving best model
210
+ 2023-10-18 21:58:11,847 ----------------------------------------------------------------------------------------------------
211
+ 2023-10-18 21:58:14,177 epoch 10 - iter 99/992 - loss 0.16010106 - time (sec): 2.33 - samples/sec: 6908.82 - lr: 0.000005 - momentum: 0.000000
212
+ 2023-10-18 21:58:16,389 epoch 10 - iter 198/992 - loss 0.14789645 - time (sec): 4.54 - samples/sec: 7237.38 - lr: 0.000004 - momentum: 0.000000
213
+ 2023-10-18 21:58:18,701 epoch 10 - iter 297/992 - loss 0.14655674 - time (sec): 6.85 - samples/sec: 7318.07 - lr: 0.000004 - momentum: 0.000000
214
+ 2023-10-18 21:58:20,992 epoch 10 - iter 396/992 - loss 0.15028578 - time (sec): 9.14 - samples/sec: 7188.41 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-18 21:58:23,161 epoch 10 - iter 495/992 - loss 0.15310770 - time (sec): 11.31 - samples/sec: 7192.41 - lr: 0.000003 - momentum: 0.000000
216
+ 2023-10-18 21:58:25,426 epoch 10 - iter 594/992 - loss 0.15629795 - time (sec): 13.58 - samples/sec: 7213.73 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-18 21:58:27,654 epoch 10 - iter 693/992 - loss 0.15763389 - time (sec): 15.81 - samples/sec: 7241.31 - lr: 0.000002 - momentum: 0.000000
218
+ 2023-10-18 21:58:29,889 epoch 10 - iter 792/992 - loss 0.15858926 - time (sec): 18.04 - samples/sec: 7295.51 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-18 21:58:32,062 epoch 10 - iter 891/992 - loss 0.15834786 - time (sec): 20.21 - samples/sec: 7287.22 - lr: 0.000001 - momentum: 0.000000
220
+ 2023-10-18 21:58:34,265 epoch 10 - iter 990/992 - loss 0.15652090 - time (sec): 22.42 - samples/sec: 7302.97 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-18 21:58:34,312 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-18 21:58:34,312 EPOCH 10 done: loss 0.1566 - lr: 0.000000
223
+ 2023-10-18 21:58:36,128 DEV : loss 0.1495286077260971 - f1-score (micro avg) 0.4881
224
+ 2023-10-18 21:58:36,146 saving best model
225
+ 2023-10-18 21:58:36,204 ----------------------------------------------------------------------------------------------------
226
+ 2023-10-18 21:58:36,204 Loading model from best epoch ...
227
+ 2023-10-18 21:58:36,283 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
228
+ 2023-10-18 21:58:37,756
229
+ Results:
230
+ - F-score (micro) 0.542
231
+ - F-score (macro) 0.3671
232
+ - Accuracy 0.4099
233
+
234
+ By class:
235
+ precision recall f1-score support
236
+
237
+ LOC 0.7039 0.6824 0.6930 655
238
+ PER 0.2770 0.5067 0.3582 223
239
+ ORG 0.1212 0.0315 0.0500 127
240
+
241
+ micro avg 0.5242 0.5612 0.5420 1005
242
+ macro avg 0.3674 0.4069 0.3671 1005
243
+ weighted avg 0.5356 0.5612 0.5375 1005
244
+
245
+ 2023-10-18 21:58:37,756 ----------------------------------------------------------------------------------------------------