Hugging Face's logo

stefan-it
/
hmbench-letemps-fr-hmbert_tiny-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
217c8cc
•
1 Parent(s): 8ed1d8a

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.1697679569.46dc0c540dd0.3802.15 +3 -0
  5. test.tsv +0 -0
  6. training.log +243 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b70ee55e2d0a6f5849c013dfae2538d3efc98ff4feae73946ec19ea4bf8aaa9
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 01:40:14 0.0000 0.7123 0.1734 0.2495 0.2643 0.2567 0.1518
3
+ 2 01:41:00 0.0000 0.1743 0.1575 0.3788 0.4039 0.3909 0.2505
4
+ 3 01:41:45 0.0000 0.1433 0.1513 0.3792 0.5515 0.4494 0.3011
5
+ 4 01:42:32 0.0000 0.1279 0.1521 0.4061 0.5343 0.4615 0.3095
6
+ 5 01:43:18 0.0000 0.1156 0.1627 0.4052 0.5915 0.4809 0.3258
7
+ 6 01:44:04 0.0000 0.1067 0.1653 0.4061 0.6213 0.4912 0.3364
8
+ 7 01:44:50 0.0000 0.0993 0.1655 0.4206 0.5847 0.4892 0.3346
9
+ 8 01:45:36 0.0000 0.0932 0.1720 0.4136 0.5618 0.4765 0.3226
10
+ 9 01:46:23 0.0000 0.0901 0.1773 0.4225 0.5767 0.4877 0.3329
11
+ 10 01:47:09 0.0000 0.0872 0.1790 0.4192 0.5847 0.4883 0.3336
runs/events.out.tfevents.1697679569.46dc0c540dd0.3802.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6cdb16a866a707d61145fed2c18e9ce6396c23941d1edb80a8c29c1deaa0d8e
3
+ size 1018100
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-19 01:39:29,579 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-19 01:39:29,579 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
+ 2023-10-19 01:39:29,579 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-19 01:39:29,579 MultiCorpus: 14465 train + 1392 dev + 2432 test sentences
52
+ - NER_HIPE_2022 Corpus: 14465 train + 1392 dev + 2432 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/letemps/fr/with_doc_seperator
53
+ 2023-10-19 01:39:29,579 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-19 01:39:29,579 Train: 14465 sentences
55
+ 2023-10-19 01:39:29,579 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-19 01:39:29,579 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-19 01:39:29,579 Training Params:
58
+ 2023-10-19 01:39:29,579 - learning_rate: "5e-05"
59
+ 2023-10-19 01:39:29,579 - mini_batch_size: "8"
60
+ 2023-10-19 01:39:29,579 - max_epochs: "10"
61
+ 2023-10-19 01:39:29,579 - shuffle: "True"
62
+ 2023-10-19 01:39:29,579 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-19 01:39:29,579 Plugins:
64
+ 2023-10-19 01:39:29,579 - TensorboardLogger
65
+ 2023-10-19 01:39:29,579 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-19 01:39:29,579 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-19 01:39:29,579 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-19 01:39:29,580 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-19 01:39:29,580 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-19 01:39:29,580 Computation:
71
+ 2023-10-19 01:39:29,580 - compute on device: cuda:0
72
+ 2023-10-19 01:39:29,580 - embedding storage: none
73
+ 2023-10-19 01:39:29,580 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-19 01:39:29,580 Model training base path: "hmbench-letemps/fr-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4"
75
+ 2023-10-19 01:39:29,580 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-19 01:39:29,580 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-19 01:39:29,580 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-19 01:39:33,832 epoch 1 - iter 180/1809 - loss 3.04420001 - time (sec): 4.25 - samples/sec: 8449.13 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-19 01:39:38,091 epoch 1 - iter 360/1809 - loss 2.39412590 - time (sec): 8.51 - samples/sec: 8808.44 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-19 01:39:42,356 epoch 1 - iter 540/1809 - loss 1.77159067 - time (sec): 12.78 - samples/sec: 8796.59 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-19 01:39:46,100 epoch 1 - iter 720/1809 - loss 1.42634419 - time (sec): 16.52 - samples/sec: 9015.97 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-19 01:39:50,344 epoch 1 - iter 900/1809 - loss 1.20167935 - time (sec): 20.76 - samples/sec: 8957.73 - lr: 0.000025 - momentum: 0.000000
83
+ 2023-10-19 01:39:54,490 epoch 1 - iter 1080/1809 - loss 1.05023629 - time (sec): 24.91 - samples/sec: 8952.71 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-19 01:39:58,642 epoch 1 - iter 1260/1809 - loss 0.93612850 - time (sec): 29.06 - samples/sec: 8963.79 - lr: 0.000035 - momentum: 0.000000
85
+ 2023-10-19 01:40:02,969 epoch 1 - iter 1440/1809 - loss 0.84232437 - time (sec): 33.39 - samples/sec: 8992.63 - lr: 0.000040 - momentum: 0.000000
86
+ 2023-10-19 01:40:07,213 epoch 1 - iter 1620/1809 - loss 0.77253770 - time (sec): 37.63 - samples/sec: 9018.41 - lr: 0.000045 - momentum: 0.000000
87
+ 2023-10-19 01:40:11,486 epoch 1 - iter 1800/1809 - loss 0.71434367 - time (sec): 41.91 - samples/sec: 9027.00 - lr: 0.000050 - momentum: 0.000000
88
+ 2023-10-19 01:40:11,680 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-19 01:40:11,680 EPOCH 1 done: loss 0.7123 - lr: 0.000050
90
+ 2023-10-19 01:40:13,974 DEV : loss 0.1734248250722885 - f1-score (micro avg) 0.2567
91
+ 2023-10-19 01:40:14,001 saving best model
92
+ 2023-10-19 01:40:14,031 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-19 01:40:18,185 epoch 2 - iter 180/1809 - loss 0.18923941 - time (sec): 4.15 - samples/sec: 8812.17 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-19 01:40:22,280 epoch 2 - iter 360/1809 - loss 0.18939649 - time (sec): 8.25 - samples/sec: 9004.44 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-19 01:40:26,415 epoch 2 - iter 540/1809 - loss 0.18224811 - time (sec): 12.38 - samples/sec: 8996.02 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-19 01:40:30,684 epoch 2 - iter 720/1809 - loss 0.18220968 - time (sec): 16.65 - samples/sec: 8914.54 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-19 01:40:34,851 epoch 2 - iter 900/1809 - loss 0.17987747 - time (sec): 20.82 - samples/sec: 8996.08 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-19 01:40:39,029 epoch 2 - iter 1080/1809 - loss 0.17778650 - time (sec): 25.00 - samples/sec: 8991.05 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-19 01:40:43,266 epoch 2 - iter 1260/1809 - loss 0.17945407 - time (sec): 29.23 - samples/sec: 8983.41 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-19 01:40:47,530 epoch 2 - iter 1440/1809 - loss 0.17784107 - time (sec): 33.50 - samples/sec: 8984.65 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-19 01:40:51,796 epoch 2 - iter 1620/1809 - loss 0.17638771 - time (sec): 37.76 - samples/sec: 8998.48 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-19 01:40:56,105 epoch 2 - iter 1800/1809 - loss 0.17432110 - time (sec): 42.07 - samples/sec: 8996.09 - lr: 0.000044 - momentum: 0.000000
103
+ 2023-10-19 01:40:56,301 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-19 01:40:56,301 EPOCH 2 done: loss 0.1743 - lr: 0.000044
105
+ 2023-10-19 01:41:00,145 DEV : loss 0.1575053483247757 - f1-score (micro avg) 0.3909
106
+ 2023-10-19 01:41:00,172 saving best model
107
+ 2023-10-19 01:41:00,205 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-19 01:41:04,473 epoch 3 - iter 180/1809 - loss 0.13892889 - time (sec): 4.27 - samples/sec: 9002.32 - lr: 0.000044 - momentum: 0.000000
109
+ 2023-10-19 01:41:08,737 epoch 3 - iter 360/1809 - loss 0.15265984 - time (sec): 8.53 - samples/sec: 8808.50 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-19 01:41:12,982 epoch 3 - iter 540/1809 - loss 0.15372864 - time (sec): 12.78 - samples/sec: 8997.56 - lr: 0.000043 - momentum: 0.000000
111
+ 2023-10-19 01:41:17,185 epoch 3 - iter 720/1809 - loss 0.15378802 - time (sec): 16.98 - samples/sec: 8940.43 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-19 01:41:21,362 epoch 3 - iter 900/1809 - loss 0.15097206 - time (sec): 21.16 - samples/sec: 8941.18 - lr: 0.000042 - momentum: 0.000000
113
+ 2023-10-19 01:41:25,569 epoch 3 - iter 1080/1809 - loss 0.15094211 - time (sec): 25.36 - samples/sec: 8897.63 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-19 01:41:29,834 epoch 3 - iter 1260/1809 - loss 0.14776592 - time (sec): 29.63 - samples/sec: 8891.75 - lr: 0.000041 - momentum: 0.000000
115
+ 2023-10-19 01:41:34,104 epoch 3 - iter 1440/1809 - loss 0.14536958 - time (sec): 33.90 - samples/sec: 8905.02 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-19 01:41:38,337 epoch 3 - iter 1620/1809 - loss 0.14321631 - time (sec): 38.13 - samples/sec: 8956.50 - lr: 0.000039 - momentum: 0.000000
117
+ 2023-10-19 01:41:42,473 epoch 3 - iter 1800/1809 - loss 0.14343704 - time (sec): 42.27 - samples/sec: 8954.16 - lr: 0.000039 - momentum: 0.000000
118
+ 2023-10-19 01:41:42,668 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-19 01:41:42,668 EPOCH 3 done: loss 0.1433 - lr: 0.000039
120
+ 2023-10-19 01:41:45,857 DEV : loss 0.15128640830516815 - f1-score (micro avg) 0.4494
121
+ 2023-10-19 01:41:45,885 saving best model
122
+ 2023-10-19 01:41:45,918 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-19 01:41:50,115 epoch 4 - iter 180/1809 - loss 0.12278635 - time (sec): 4.20 - samples/sec: 8956.04 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-19 01:41:54,414 epoch 4 - iter 360/1809 - loss 0.12152527 - time (sec): 8.50 - samples/sec: 8859.92 - lr: 0.000038 - momentum: 0.000000
125
+ 2023-10-19 01:41:58,551 epoch 4 - iter 540/1809 - loss 0.12629146 - time (sec): 12.63 - samples/sec: 9036.33 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-19 01:42:02,773 epoch 4 - iter 720/1809 - loss 0.12649074 - time (sec): 16.85 - samples/sec: 8996.97 - lr: 0.000037 - momentum: 0.000000
127
+ 2023-10-19 01:42:07,022 epoch 4 - iter 900/1809 - loss 0.12832559 - time (sec): 21.10 - samples/sec: 8923.83 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-19 01:42:11,302 epoch 4 - iter 1080/1809 - loss 0.12966244 - time (sec): 25.38 - samples/sec: 8937.72 - lr: 0.000036 - momentum: 0.000000
129
+ 2023-10-19 01:42:15,650 epoch 4 - iter 1260/1809 - loss 0.12766548 - time (sec): 29.73 - samples/sec: 8928.73 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-19 01:42:19,882 epoch 4 - iter 1440/1809 - loss 0.12653062 - time (sec): 33.96 - samples/sec: 8911.98 - lr: 0.000034 - momentum: 0.000000
131
+ 2023-10-19 01:42:24,121 epoch 4 - iter 1620/1809 - loss 0.12617595 - time (sec): 38.20 - samples/sec: 8930.45 - lr: 0.000034 - momentum: 0.000000
132
+ 2023-10-19 01:42:28,266 epoch 4 - iter 1800/1809 - loss 0.12779140 - time (sec): 42.35 - samples/sec: 8932.38 - lr: 0.000033 - momentum: 0.000000
133
+ 2023-10-19 01:42:28,457 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-19 01:42:28,457 EPOCH 4 done: loss 0.1279 - lr: 0.000033
135
+ 2023-10-19 01:42:32,317 DEV : loss 0.15212927758693695 - f1-score (micro avg) 0.4615
136
+ 2023-10-19 01:42:32,344 saving best model
137
+ 2023-10-19 01:42:32,377 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-19 01:42:36,505 epoch 5 - iter 180/1809 - loss 0.11457552 - time (sec): 4.13 - samples/sec: 9118.90 - lr: 0.000033 - momentum: 0.000000
139
+ 2023-10-19 01:42:40,688 epoch 5 - iter 360/1809 - loss 0.11115056 - time (sec): 8.31 - samples/sec: 8979.27 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-19 01:42:44,935 epoch 5 - iter 540/1809 - loss 0.11379745 - time (sec): 12.56 - samples/sec: 8816.95 - lr: 0.000032 - momentum: 0.000000
141
+ 2023-10-19 01:42:49,154 epoch 5 - iter 720/1809 - loss 0.11718434 - time (sec): 16.78 - samples/sec: 8852.26 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-19 01:42:53,432 epoch 5 - iter 900/1809 - loss 0.11789862 - time (sec): 21.05 - samples/sec: 8870.04 - lr: 0.000031 - momentum: 0.000000
143
+ 2023-10-19 01:42:57,602 epoch 5 - iter 1080/1809 - loss 0.11519563 - time (sec): 25.22 - samples/sec: 8864.53 - lr: 0.000030 - momentum: 0.000000
144
+ 2023-10-19 01:43:01,826 epoch 5 - iter 1260/1809 - loss 0.11691779 - time (sec): 29.45 - samples/sec: 8916.53 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-19 01:43:06,125 epoch 5 - iter 1440/1809 - loss 0.11649889 - time (sec): 33.75 - samples/sec: 8926.80 - lr: 0.000029 - momentum: 0.000000
146
+ 2023-10-19 01:43:10,343 epoch 5 - iter 1620/1809 - loss 0.11628702 - time (sec): 37.97 - samples/sec: 8950.98 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-19 01:43:14,626 epoch 5 - iter 1800/1809 - loss 0.11539962 - time (sec): 42.25 - samples/sec: 8949.63 - lr: 0.000028 - momentum: 0.000000
148
+ 2023-10-19 01:43:14,827 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-19 01:43:14,828 EPOCH 5 done: loss 0.1156 - lr: 0.000028
150
+ 2023-10-19 01:43:18,024 DEV : loss 0.16273775696754456 - f1-score (micro avg) 0.4809
151
+ 2023-10-19 01:43:18,052 saving best model
152
+ 2023-10-19 01:43:18,091 ----------------------------------------------------------------------------------------------------
153
+ 2023-10-19 01:43:22,287 epoch 6 - iter 180/1809 - loss 0.11369687 - time (sec): 4.20 - samples/sec: 8885.91 - lr: 0.000027 - momentum: 0.000000
154
+ 2023-10-19 01:43:26,419 epoch 6 - iter 360/1809 - loss 0.10397102 - time (sec): 8.33 - samples/sec: 9027.87 - lr: 0.000027 - momentum: 0.000000
155
+ 2023-10-19 01:43:30,641 epoch 6 - iter 540/1809 - loss 0.10451339 - time (sec): 12.55 - samples/sec: 9069.09 - lr: 0.000026 - momentum: 0.000000
156
+ 2023-10-19 01:43:34,859 epoch 6 - iter 720/1809 - loss 0.10415941 - time (sec): 16.77 - samples/sec: 8952.01 - lr: 0.000026 - momentum: 0.000000
157
+ 2023-10-19 01:43:39,120 epoch 6 - iter 900/1809 - loss 0.10131086 - time (sec): 21.03 - samples/sec: 8826.73 - lr: 0.000025 - momentum: 0.000000
158
+ 2023-10-19 01:43:43,415 epoch 6 - iter 1080/1809 - loss 0.10388199 - time (sec): 25.32 - samples/sec: 8864.36 - lr: 0.000024 - momentum: 0.000000
159
+ 2023-10-19 01:43:47,760 epoch 6 - iter 1260/1809 - loss 0.10374079 - time (sec): 29.67 - samples/sec: 8853.19 - lr: 0.000024 - momentum: 0.000000
160
+ 2023-10-19 01:43:52,647 epoch 6 - iter 1440/1809 - loss 0.10431911 - time (sec): 34.55 - samples/sec: 8709.60 - lr: 0.000023 - momentum: 0.000000
161
+ 2023-10-19 01:43:56,907 epoch 6 - iter 1620/1809 - loss 0.10493723 - time (sec): 38.82 - samples/sec: 8752.08 - lr: 0.000023 - momentum: 0.000000
162
+ 2023-10-19 01:44:01,350 epoch 6 - iter 1800/1809 - loss 0.10667085 - time (sec): 43.26 - samples/sec: 8747.02 - lr: 0.000022 - momentum: 0.000000
163
+ 2023-10-19 01:44:01,560 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-19 01:44:01,561 EPOCH 6 done: loss 0.1067 - lr: 0.000022
165
+ 2023-10-19 01:44:04,766 DEV : loss 0.16526678204536438 - f1-score (micro avg) 0.4912
166
+ 2023-10-19 01:44:04,794 saving best model
167
+ 2023-10-19 01:44:04,827 ----------------------------------------------------------------------------------------------------
168
+ 2023-10-19 01:44:09,069 epoch 7 - iter 180/1809 - loss 0.10175065 - time (sec): 4.24 - samples/sec: 8932.79 - lr: 0.000022 - momentum: 0.000000
169
+ 2023-10-19 01:44:13,227 epoch 7 - iter 360/1809 - loss 0.10175187 - time (sec): 8.40 - samples/sec: 8883.86 - lr: 0.000021 - momentum: 0.000000
170
+ 2023-10-19 01:44:17,449 epoch 7 - iter 540/1809 - loss 0.09763149 - time (sec): 12.62 - samples/sec: 8957.13 - lr: 0.000021 - momentum: 0.000000
171
+ 2023-10-19 01:44:21,487 epoch 7 - iter 720/1809 - loss 0.09845246 - time (sec): 16.66 - samples/sec: 9087.13 - lr: 0.000020 - momentum: 0.000000
172
+ 2023-10-19 01:44:25,705 epoch 7 - iter 900/1809 - loss 0.09992038 - time (sec): 20.88 - samples/sec: 9068.53 - lr: 0.000019 - momentum: 0.000000
173
+ 2023-10-19 01:44:30,014 epoch 7 - iter 1080/1809 - loss 0.09902913 - time (sec): 25.19 - samples/sec: 9064.18 - lr: 0.000019 - momentum: 0.000000
174
+ 2023-10-19 01:44:34,276 epoch 7 - iter 1260/1809 - loss 0.09771706 - time (sec): 29.45 - samples/sec: 9032.63 - lr: 0.000018 - momentum: 0.000000
175
+ 2023-10-19 01:44:38,551 epoch 7 - iter 1440/1809 - loss 0.09670512 - time (sec): 33.72 - samples/sec: 9023.43 - lr: 0.000018 - momentum: 0.000000
176
+ 2023-10-19 01:44:42,761 epoch 7 - iter 1620/1809 - loss 0.09868533 - time (sec): 37.93 - samples/sec: 8987.96 - lr: 0.000017 - momentum: 0.000000
177
+ 2023-10-19 01:44:47,125 epoch 7 - iter 1800/1809 - loss 0.09925492 - time (sec): 42.30 - samples/sec: 8948.09 - lr: 0.000017 - momentum: 0.000000
178
+ 2023-10-19 01:44:47,325 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-19 01:44:47,325 EPOCH 7 done: loss 0.0993 - lr: 0.000017
180
+ 2023-10-19 01:44:50,521 DEV : loss 0.1655406653881073 - f1-score (micro avg) 0.4892
181
+ 2023-10-19 01:44:50,549 ----------------------------------------------------------------------------------------------------
182
+ 2023-10-19 01:44:54,538 epoch 8 - iter 180/1809 - loss 0.08987194 - time (sec): 3.99 - samples/sec: 9767.08 - lr: 0.000016 - momentum: 0.000000
183
+ 2023-10-19 01:44:58,907 epoch 8 - iter 360/1809 - loss 0.09430654 - time (sec): 8.36 - samples/sec: 9250.17 - lr: 0.000016 - momentum: 0.000000
184
+ 2023-10-19 01:45:03,904 epoch 8 - iter 540/1809 - loss 0.09522618 - time (sec): 13.35 - samples/sec: 8738.18 - lr: 0.000015 - momentum: 0.000000
185
+ 2023-10-19 01:45:08,121 epoch 8 - iter 720/1809 - loss 0.09554787 - time (sec): 17.57 - samples/sec: 8738.51 - lr: 0.000014 - momentum: 0.000000
186
+ 2023-10-19 01:45:12,567 epoch 8 - iter 900/1809 - loss 0.09292183 - time (sec): 22.02 - samples/sec: 8720.10 - lr: 0.000014 - momentum: 0.000000
187
+ 2023-10-19 01:45:16,729 epoch 8 - iter 1080/1809 - loss 0.09283442 - time (sec): 26.18 - samples/sec: 8714.94 - lr: 0.000013 - momentum: 0.000000
188
+ 2023-10-19 01:45:21,011 epoch 8 - iter 1260/1809 - loss 0.09407078 - time (sec): 30.46 - samples/sec: 8697.93 - lr: 0.000013 - momentum: 0.000000
189
+ 2023-10-19 01:45:25,184 epoch 8 - iter 1440/1809 - loss 0.09382524 - time (sec): 34.63 - samples/sec: 8724.49 - lr: 0.000012 - momentum: 0.000000
190
+ 2023-10-19 01:45:29,432 epoch 8 - iter 1620/1809 - loss 0.09358378 - time (sec): 38.88 - samples/sec: 8747.52 - lr: 0.000012 - momentum: 0.000000
191
+ 2023-10-19 01:45:33,540 epoch 8 - iter 1800/1809 - loss 0.09294724 - time (sec): 42.99 - samples/sec: 8797.83 - lr: 0.000011 - momentum: 0.000000
192
+ 2023-10-19 01:45:33,719 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-19 01:45:33,720 EPOCH 8 done: loss 0.0932 - lr: 0.000011
194
+ 2023-10-19 01:45:36,937 DEV : loss 0.17200641334056854 - f1-score (micro avg) 0.4765
195
+ 2023-10-19 01:45:36,966 ----------------------------------------------------------------------------------------------------
196
+ 2023-10-19 01:45:41,335 epoch 9 - iter 180/1809 - loss 0.09874270 - time (sec): 4.37 - samples/sec: 9050.22 - lr: 0.000011 - momentum: 0.000000
197
+ 2023-10-19 01:45:45,582 epoch 9 - iter 360/1809 - loss 0.08796417 - time (sec): 8.62 - samples/sec: 9016.35 - lr: 0.000010 - momentum: 0.000000
198
+ 2023-10-19 01:45:49,799 epoch 9 - iter 540/1809 - loss 0.09019361 - time (sec): 12.83 - samples/sec: 9061.73 - lr: 0.000009 - momentum: 0.000000
199
+ 2023-10-19 01:45:53,991 epoch 9 - iter 720/1809 - loss 0.08746996 - time (sec): 17.02 - samples/sec: 8957.76 - lr: 0.000009 - momentum: 0.000000
200
+ 2023-10-19 01:45:58,253 epoch 9 - iter 900/1809 - loss 0.08620817 - time (sec): 21.29 - samples/sec: 9022.78 - lr: 0.000008 - momentum: 0.000000
201
+ 2023-10-19 01:46:02,447 epoch 9 - iter 1080/1809 - loss 0.08880201 - time (sec): 25.48 - samples/sec: 8990.05 - lr: 0.000008 - momentum: 0.000000
202
+ 2023-10-19 01:46:06,595 epoch 9 - iter 1260/1809 - loss 0.08994610 - time (sec): 29.63 - samples/sec: 8976.71 - lr: 0.000007 - momentum: 0.000000
203
+ 2023-10-19 01:46:10,821 epoch 9 - iter 1440/1809 - loss 0.08980005 - time (sec): 33.85 - samples/sec: 9007.29 - lr: 0.000007 - momentum: 0.000000
204
+ 2023-10-19 01:46:15,046 epoch 9 - iter 1620/1809 - loss 0.09016965 - time (sec): 38.08 - samples/sec: 8966.36 - lr: 0.000006 - momentum: 0.000000
205
+ 2023-10-19 01:46:19,235 epoch 9 - iter 1800/1809 - loss 0.09005114 - time (sec): 42.27 - samples/sec: 8941.44 - lr: 0.000006 - momentum: 0.000000
206
+ 2023-10-19 01:46:19,432 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-19 01:46:19,432 EPOCH 9 done: loss 0.0901 - lr: 0.000006
208
+ 2023-10-19 01:46:23,260 DEV : loss 0.1773018091917038 - f1-score (micro avg) 0.4877
209
+ 2023-10-19 01:46:23,288 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-19 01:46:27,362 epoch 10 - iter 180/1809 - loss 0.08558466 - time (sec): 4.07 - samples/sec: 8868.97 - lr: 0.000005 - momentum: 0.000000
211
+ 2023-10-19 01:46:31,568 epoch 10 - iter 360/1809 - loss 0.08733092 - time (sec): 8.28 - samples/sec: 9040.72 - lr: 0.000004 - momentum: 0.000000
212
+ 2023-10-19 01:46:35,723 epoch 10 - iter 540/1809 - loss 0.08811151 - time (sec): 12.43 - samples/sec: 9006.82 - lr: 0.000004 - momentum: 0.000000
213
+ 2023-10-19 01:46:40,017 epoch 10 - iter 720/1809 - loss 0.08584389 - time (sec): 16.73 - samples/sec: 8953.08 - lr: 0.000003 - momentum: 0.000000
214
+ 2023-10-19 01:46:44,293 epoch 10 - iter 900/1809 - loss 0.08722287 - time (sec): 21.00 - samples/sec: 8968.51 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-19 01:46:48,559 epoch 10 - iter 1080/1809 - loss 0.08921336 - time (sec): 25.27 - samples/sec: 8984.04 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-19 01:46:52,844 epoch 10 - iter 1260/1809 - loss 0.08817541 - time (sec): 29.56 - samples/sec: 8989.90 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-19 01:46:57,060 epoch 10 - iter 1440/1809 - loss 0.08719774 - time (sec): 33.77 - samples/sec: 8989.84 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-19 01:47:01,289 epoch 10 - iter 1620/1809 - loss 0.08762114 - time (sec): 38.00 - samples/sec: 8944.19 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-19 01:47:05,579 epoch 10 - iter 1800/1809 - loss 0.08713337 - time (sec): 42.29 - samples/sec: 8947.54 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-19 01:47:05,770 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-19 01:47:05,770 EPOCH 10 done: loss 0.0872 - lr: 0.000000
222
+ 2023-10-19 01:47:08,983 DEV : loss 0.17904870212078094 - f1-score (micro avg) 0.4883
223
+ 2023-10-19 01:47:09,043 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-19 01:47:09,043 Loading model from best epoch ...
225
+ 2023-10-19 01:47:09,124 SequenceTagger predicts: Dictionary with 13 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org
226
+ 2023-10-19 01:47:13,241
227
+ Results:
228
+ - F-score (micro) 0.5203
229
+ - F-score (macro) 0.3446
230
+ - Accuracy 0.3646
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ loc 0.4966 0.7343 0.5925 591
236
+ pers 0.3922 0.5042 0.4412 357
237
+ org 0.0000 0.0000 0.0000 79
238
+
239
+ micro avg 0.4606 0.5979 0.5203 1027
240
+ macro avg 0.2962 0.4129 0.3446 1027
241
+ weighted avg 0.4221 0.5979 0.4943 1027
242
+
243
+ 2023-10-19 01:47:13,241 ----------------------------------------------------------------------------------------------------