Hugging Face's logo

stefan-it
/
hmbench-letemps-fr-hmbert-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4

Token Classification
Flair
PyTorch
French
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
72adeae
•
1 Parent(s): 3280e60

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 +237 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18f06f319aa0990ffde5b703786d2848ee12bfd5f32e781e7623ac4d96847e98
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 00:06:41 0.0000 0.2318 0.1423 0.4526 0.7437 0.5628 0.4070
3
+ 2 00:09:38 0.0000 0.1036 0.1783 0.5553 0.7643 0.6432 0.4830
4
+ 3 00:12:36 0.0000 0.0842 0.2163 0.5289 0.7231 0.6109 0.4492
5
+ 4 00:15:52 0.0000 0.0641 0.2644 0.5222 0.7277 0.6080 0.4485
6
+ 5 00:18:44 0.0000 0.0473 0.3083 0.5378 0.7323 0.6202 0.4604
7
+ 6 00:21:47 0.0000 0.0341 0.2927 0.5470 0.6991 0.6138 0.4519
8
+ 7 00:24:41 0.0000 0.0255 0.3246 0.5437 0.7540 0.6318 0.4738
9
+ 8 00:27:35 0.0000 0.0170 0.3864 0.5354 0.7620 0.6289 0.4710
10
+ 9 00:30:26 0.0000 0.0108 0.3468 0.5585 0.7323 0.6337 0.4755
11
+ 10 00:33:20 0.0000 0.0066 0.4006 0.5445 0.7494 0.6307 0.4726
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,237 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-15 00:03:50,981 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-15 00:03:50,982 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
+ 2023-10-15 00:03:50,982 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-15 00:03:50,982 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
+ 2023-10-15 00:03:50,982 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-15 00:03:50,982 Train: 14465 sentences
55
+ 2023-10-15 00:03:50,982 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-15 00:03:50,982 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-15 00:03:50,982 Training Params:
58
+ 2023-10-15 00:03:50,982 - learning_rate: "5e-05"
59
+ 2023-10-15 00:03:50,982 - mini_batch_size: "4"
60
+ 2023-10-15 00:03:50,982 - max_epochs: "10"
61
+ 2023-10-15 00:03:50,982 - shuffle: "True"
62
+ 2023-10-15 00:03:50,982 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-15 00:03:50,983 Plugins:
64
+ 2023-10-15 00:03:50,983 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-15 00:03:50,983 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-15 00:03:50,983 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-15 00:03:50,983 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-15 00:03:50,983 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-15 00:03:50,983 Computation:
70
+ 2023-10-15 00:03:50,983 - compute on device: cuda:0
71
+ 2023-10-15 00:03:50,983 - embedding storage: none
72
+ 2023-10-15 00:03:50,983 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-15 00:03:50,983 Model training base path: "hmbench-letemps/fr-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4"
74
+ 2023-10-15 00:03:50,983 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-15 00:03:50,983 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-15 00:04:07,798 epoch 1 - iter 361/3617 - loss 1.14190309 - time (sec): 16.81 - samples/sec: 2251.69 - lr: 0.000005 - momentum: 0.000000
77
+ 2023-10-15 00:04:24,690 epoch 1 - iter 722/3617 - loss 0.66100745 - time (sec): 33.71 - samples/sec: 2228.99 - lr: 0.000010 - momentum: 0.000000
78
+ 2023-10-15 00:04:41,045 epoch 1 - iter 1083/3617 - loss 0.49172746 - time (sec): 50.06 - samples/sec: 2264.99 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-15 00:04:57,113 epoch 1 - iter 1444/3617 - loss 0.40440624 - time (sec): 66.13 - samples/sec: 2279.37 - lr: 0.000020 - momentum: 0.000000
80
+ 2023-10-15 00:05:13,378 epoch 1 - iter 1805/3617 - loss 0.34944834 - time (sec): 82.39 - samples/sec: 2296.50 - lr: 0.000025 - momentum: 0.000000
81
+ 2023-10-15 00:05:29,700 epoch 1 - iter 2166/3617 - loss 0.31177626 - time (sec): 98.72 - samples/sec: 2299.63 - lr: 0.000030 - momentum: 0.000000
82
+ 2023-10-15 00:05:45,946 epoch 1 - iter 2527/3617 - loss 0.28399617 - time (sec): 114.96 - samples/sec: 2296.61 - lr: 0.000035 - momentum: 0.000000
83
+ 2023-10-15 00:06:02,585 epoch 1 - iter 2888/3617 - loss 0.26224385 - time (sec): 131.60 - samples/sec: 2294.38 - lr: 0.000040 - momentum: 0.000000
84
+ 2023-10-15 00:06:19,442 epoch 1 - iter 3249/3617 - loss 0.24569678 - time (sec): 148.46 - samples/sec: 2296.71 - lr: 0.000045 - momentum: 0.000000
85
+ 2023-10-15 00:06:36,736 epoch 1 - iter 3610/3617 - loss 0.23207698 - time (sec): 165.75 - samples/sec: 2288.12 - lr: 0.000050 - momentum: 0.000000
86
+ 2023-10-15 00:06:37,043 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-15 00:06:37,044 EPOCH 1 done: loss 0.2318 - lr: 0.000050
88
+ 2023-10-15 00:06:41,816 DEV : loss 0.14234784245491028 - f1-score (micro avg) 0.5628
89
+ 2023-10-15 00:06:41,846 saving best model
90
+ 2023-10-15 00:06:42,204 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-15 00:06:58,610 epoch 2 - iter 361/3617 - loss 0.11043076 - time (sec): 16.40 - samples/sec: 2369.45 - lr: 0.000049 - momentum: 0.000000
92
+ 2023-10-15 00:07:14,868 epoch 2 - iter 722/3617 - loss 0.10307503 - time (sec): 32.66 - samples/sec: 2344.00 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-15 00:07:31,128 epoch 2 - iter 1083/3617 - loss 0.10343443 - time (sec): 48.92 - samples/sec: 2334.59 - lr: 0.000048 - momentum: 0.000000
94
+ 2023-10-15 00:07:47,512 epoch 2 - iter 1444/3617 - loss 0.10211674 - time (sec): 65.31 - samples/sec: 2343.66 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-15 00:08:03,756 epoch 2 - iter 1805/3617 - loss 0.10329026 - time (sec): 81.55 - samples/sec: 2341.87 - lr: 0.000047 - momentum: 0.000000
96
+ 2023-10-15 00:08:20,587 epoch 2 - iter 2166/3617 - loss 0.10243479 - time (sec): 98.38 - samples/sec: 2342.52 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-15 00:08:36,735 epoch 2 - iter 2527/3617 - loss 0.10394519 - time (sec): 114.53 - samples/sec: 2336.04 - lr: 0.000046 - momentum: 0.000000
98
+ 2023-10-15 00:08:55,159 epoch 2 - iter 2888/3617 - loss 0.10245744 - time (sec): 132.95 - samples/sec: 2288.97 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-15 00:09:12,663 epoch 2 - iter 3249/3617 - loss 0.10371302 - time (sec): 150.46 - samples/sec: 2274.10 - lr: 0.000045 - momentum: 0.000000
100
+ 2023-10-15 00:09:31,541 epoch 2 - iter 3610/3617 - loss 0.10357504 - time (sec): 169.34 - samples/sec: 2240.45 - lr: 0.000044 - momentum: 0.000000
101
+ 2023-10-15 00:09:31,891 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-15 00:09:31,892 EPOCH 2 done: loss 0.1036 - lr: 0.000044
103
+ 2023-10-15 00:09:38,248 DEV : loss 0.17834356427192688 - f1-score (micro avg) 0.6432
104
+ 2023-10-15 00:09:38,279 saving best model
105
+ 2023-10-15 00:09:38,784 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-15 00:09:56,999 epoch 3 - iter 361/3617 - loss 0.07560643 - time (sec): 18.21 - samples/sec: 2079.60 - lr: 0.000044 - momentum: 0.000000
107
+ 2023-10-15 00:10:13,534 epoch 3 - iter 722/3617 - loss 0.08065039 - time (sec): 34.75 - samples/sec: 2214.64 - lr: 0.000043 - momentum: 0.000000
108
+ 2023-10-15 00:10:29,627 epoch 3 - iter 1083/3617 - loss 0.08073724 - time (sec): 50.84 - samples/sec: 2235.86 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-15 00:10:46,011 epoch 3 - iter 1444/3617 - loss 0.08653947 - time (sec): 67.22 - samples/sec: 2250.71 - lr: 0.000042 - momentum: 0.000000
110
+ 2023-10-15 00:11:02,212 epoch 3 - iter 1805/3617 - loss 0.08584021 - time (sec): 83.42 - samples/sec: 2249.12 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-15 00:11:19,576 epoch 3 - iter 2166/3617 - loss 0.08541915 - time (sec): 100.79 - samples/sec: 2241.64 - lr: 0.000041 - momentum: 0.000000
112
+ 2023-10-15 00:11:36,404 epoch 3 - iter 2527/3617 - loss 0.08471573 - time (sec): 117.62 - samples/sec: 2245.13 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-15 00:11:53,556 epoch 3 - iter 2888/3617 - loss 0.08579463 - time (sec): 134.77 - samples/sec: 2241.78 - lr: 0.000040 - momentum: 0.000000
114
+ 2023-10-15 00:12:11,257 epoch 3 - iter 3249/3617 - loss 0.08564418 - time (sec): 152.47 - samples/sec: 2226.98 - lr: 0.000039 - momentum: 0.000000
115
+ 2023-10-15 00:12:30,255 epoch 3 - iter 3610/3617 - loss 0.08383490 - time (sec): 171.47 - samples/sec: 2212.68 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-15 00:12:30,615 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-15 00:12:30,615 EPOCH 3 done: loss 0.0842 - lr: 0.000039
118
+ 2023-10-15 00:12:36,289 DEV : loss 0.21627244353294373 - f1-score (micro avg) 0.6109
119
+ 2023-10-15 00:12:36,341 ----------------------------------------------------------------------------------------------------
120
+ 2023-10-15 00:12:55,272 epoch 4 - iter 361/3617 - loss 0.06671701 - time (sec): 18.93 - samples/sec: 2004.88 - lr: 0.000038 - momentum: 0.000000
121
+ 2023-10-15 00:13:15,637 epoch 4 - iter 722/3617 - loss 0.06317418 - time (sec): 39.29 - samples/sec: 1904.94 - lr: 0.000038 - momentum: 0.000000
122
+ 2023-10-15 00:13:34,686 epoch 4 - iter 1083/3617 - loss 0.06492905 - time (sec): 58.34 - samples/sec: 1969.17 - lr: 0.000037 - momentum: 0.000000
123
+ 2023-10-15 00:13:52,578 epoch 4 - iter 1444/3617 - loss 0.06403201 - time (sec): 76.24 - samples/sec: 2000.12 - lr: 0.000037 - momentum: 0.000000
124
+ 2023-10-15 00:14:11,684 epoch 4 - iter 1805/3617 - loss 0.06566880 - time (sec): 95.34 - samples/sec: 1994.66 - lr: 0.000036 - momentum: 0.000000
125
+ 2023-10-15 00:14:30,587 epoch 4 - iter 2166/3617 - loss 0.06340193 - time (sec): 114.24 - samples/sec: 1994.97 - lr: 0.000036 - momentum: 0.000000
126
+ 2023-10-15 00:14:49,596 epoch 4 - iter 2527/3617 - loss 0.06409664 - time (sec): 133.25 - samples/sec: 1995.84 - lr: 0.000035 - momentum: 0.000000
127
+ 2023-10-15 00:15:08,843 epoch 4 - iter 2888/3617 - loss 0.06400556 - time (sec): 152.50 - samples/sec: 1989.21 - lr: 0.000034 - momentum: 0.000000
128
+ 2023-10-15 00:15:27,862 epoch 4 - iter 3249/3617 - loss 0.06304313 - time (sec): 171.52 - samples/sec: 1989.02 - lr: 0.000034 - momentum: 0.000000
129
+ 2023-10-15 00:15:46,803 epoch 4 - iter 3610/3617 - loss 0.06409593 - time (sec): 190.46 - samples/sec: 1991.45 - lr: 0.000033 - momentum: 0.000000
130
+ 2023-10-15 00:15:47,168 ----------------------------------------------------------------------------------------------------
131
+ 2023-10-15 00:15:47,168 EPOCH 4 done: loss 0.0641 - lr: 0.000033
132
+ 2023-10-15 00:15:52,843 DEV : loss 0.2644401490688324 - f1-score (micro avg) 0.608
133
+ 2023-10-15 00:15:52,874 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-15 00:16:09,928 epoch 5 - iter 361/3617 - loss 0.05868204 - time (sec): 17.05 - samples/sec: 2185.12 - lr: 0.000033 - momentum: 0.000000
135
+ 2023-10-15 00:16:26,528 epoch 5 - iter 722/3617 - loss 0.05449946 - time (sec): 33.65 - samples/sec: 2261.15 - lr: 0.000032 - momentum: 0.000000
136
+ 2023-10-15 00:16:42,928 epoch 5 - iter 1083/3617 - loss 0.04942409 - time (sec): 50.05 - samples/sec: 2291.71 - lr: 0.000032 - momentum: 0.000000
137
+ 2023-10-15 00:16:59,251 epoch 5 - iter 1444/3617 - loss 0.04938677 - time (sec): 66.38 - samples/sec: 2293.76 - lr: 0.000031 - momentum: 0.000000
138
+ 2023-10-15 00:17:15,645 epoch 5 - iter 1805/3617 - loss 0.04852069 - time (sec): 82.77 - samples/sec: 2302.53 - lr: 0.000031 - momentum: 0.000000
139
+ 2023-10-15 00:17:31,936 epoch 5 - iter 2166/3617 - loss 0.04830852 - time (sec): 99.06 - samples/sec: 2312.12 - lr: 0.000030 - momentum: 0.000000
140
+ 2023-10-15 00:17:48,190 epoch 5 - iter 2527/3617 - loss 0.04877510 - time (sec): 115.31 - samples/sec: 2329.25 - lr: 0.000029 - momentum: 0.000000
141
+ 2023-10-15 00:18:04,491 epoch 5 - iter 2888/3617 - loss 0.04805849 - time (sec): 131.62 - samples/sec: 2325.19 - lr: 0.000029 - momentum: 0.000000
142
+ 2023-10-15 00:18:20,840 epoch 5 - iter 3249/3617 - loss 0.04778150 - time (sec): 147.96 - samples/sec: 2316.92 - lr: 0.000028 - momentum: 0.000000
143
+ 2023-10-15 00:18:37,081 epoch 5 - iter 3610/3617 - loss 0.04737949 - time (sec): 164.21 - samples/sec: 2309.75 - lr: 0.000028 - momentum: 0.000000
144
+ 2023-10-15 00:18:37,380 ----------------------------------------------------------------------------------------------------
145
+ 2023-10-15 00:18:37,380 EPOCH 5 done: loss 0.0473 - lr: 0.000028
146
+ 2023-10-15 00:18:44,647 DEV : loss 0.30833280086517334 - f1-score (micro avg) 0.6202
147
+ 2023-10-15 00:18:44,680 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-15 00:19:04,511 epoch 6 - iter 361/3617 - loss 0.03472543 - time (sec): 19.83 - samples/sec: 1893.54 - lr: 0.000027 - momentum: 0.000000
149
+ 2023-10-15 00:19:20,916 epoch 6 - iter 722/3617 - loss 0.03710473 - time (sec): 36.23 - samples/sec: 2099.04 - lr: 0.000027 - momentum: 0.000000
150
+ 2023-10-15 00:19:37,412 epoch 6 - iter 1083/3617 - loss 0.03705415 - time (sec): 52.73 - samples/sec: 2162.30 - lr: 0.000026 - momentum: 0.000000
151
+ 2023-10-15 00:19:54,771 epoch 6 - iter 1444/3617 - loss 0.03567499 - time (sec): 70.09 - samples/sec: 2181.21 - lr: 0.000026 - momentum: 0.000000
152
+ 2023-10-15 00:20:13,851 epoch 6 - iter 1805/3617 - loss 0.03467301 - time (sec): 89.17 - samples/sec: 2131.96 - lr: 0.000025 - momentum: 0.000000
153
+ 2023-10-15 00:20:31,490 epoch 6 - iter 2166/3617 - loss 0.03401480 - time (sec): 106.81 - samples/sec: 2132.64 - lr: 0.000024 - momentum: 0.000000
154
+ 2023-10-15 00:20:48,141 epoch 6 - iter 2527/3617 - loss 0.03417127 - time (sec): 123.46 - samples/sec: 2148.18 - lr: 0.000024 - momentum: 0.000000
155
+ 2023-10-15 00:21:04,805 epoch 6 - iter 2888/3617 - loss 0.03417472 - time (sec): 140.12 - samples/sec: 2162.24 - lr: 0.000023 - momentum: 0.000000
156
+ 2023-10-15 00:21:23,559 epoch 6 - iter 3249/3617 - loss 0.03431393 - time (sec): 158.88 - samples/sec: 2149.16 - lr: 0.000023 - momentum: 0.000000
157
+ 2023-10-15 00:21:40,415 epoch 6 - iter 3610/3617 - loss 0.03406611 - time (sec): 175.73 - samples/sec: 2157.29 - lr: 0.000022 - momentum: 0.000000
158
+ 2023-10-15 00:21:40,717 ----------------------------------------------------------------------------------------------------
159
+ 2023-10-15 00:21:40,718 EPOCH 6 done: loss 0.0341 - lr: 0.000022
160
+ 2023-10-15 00:21:47,770 DEV : loss 0.29267942905426025 - f1-score (micro avg) 0.6138
161
+ 2023-10-15 00:21:47,811 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-15 00:22:04,371 epoch 7 - iter 361/3617 - loss 0.02492550 - time (sec): 16.56 - samples/sec: 2240.71 - lr: 0.000022 - momentum: 0.000000
163
+ 2023-10-15 00:22:20,782 epoch 7 - iter 722/3617 - loss 0.02586181 - time (sec): 32.97 - samples/sec: 2232.97 - lr: 0.000021 - momentum: 0.000000
164
+ 2023-10-15 00:22:37,204 epoch 7 - iter 1083/3617 - loss 0.02579214 - time (sec): 49.39 - samples/sec: 2267.41 - lr: 0.000021 - momentum: 0.000000
165
+ 2023-10-15 00:22:54,241 epoch 7 - iter 1444/3617 - loss 0.02631518 - time (sec): 66.43 - samples/sec: 2245.58 - lr: 0.000020 - momentum: 0.000000
166
+ 2023-10-15 00:23:10,610 epoch 7 - iter 1805/3617 - loss 0.02825187 - time (sec): 82.80 - samples/sec: 2262.71 - lr: 0.000019 - momentum: 0.000000
167
+ 2023-10-15 00:23:27,120 epoch 7 - iter 2166/3617 - loss 0.02772231 - time (sec): 99.31 - samples/sec: 2272.34 - lr: 0.000019 - momentum: 0.000000
168
+ 2023-10-15 00:23:43,593 epoch 7 - iter 2527/3617 - loss 0.02743720 - time (sec): 115.78 - samples/sec: 2287.95 - lr: 0.000018 - momentum: 0.000000
169
+ 2023-10-15 00:23:59,953 epoch 7 - iter 2888/3617 - loss 0.02583311 - time (sec): 132.14 - samples/sec: 2284.62 - lr: 0.000018 - momentum: 0.000000
170
+ 2023-10-15 00:24:16,683 epoch 7 - iter 3249/3617 - loss 0.02569944 - time (sec): 148.87 - samples/sec: 2299.18 - lr: 0.000017 - momentum: 0.000000
171
+ 2023-10-15 00:24:34,095 epoch 7 - iter 3610/3617 - loss 0.02550174 - time (sec): 166.28 - samples/sec: 2281.13 - lr: 0.000017 - momentum: 0.000000
172
+ 2023-10-15 00:24:34,434 ----------------------------------------------------------------------------------------------------
173
+ 2023-10-15 00:24:34,434 EPOCH 7 done: loss 0.0255 - lr: 0.000017
174
+ 2023-10-15 00:24:41,164 DEV : loss 0.32456058263778687 - f1-score (micro avg) 0.6318
175
+ 2023-10-15 00:24:41,200 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-15 00:24:57,722 epoch 8 - iter 361/3617 - loss 0.01548764 - time (sec): 16.52 - samples/sec: 2256.70 - lr: 0.000016 - momentum: 0.000000
177
+ 2023-10-15 00:25:14,113 epoch 8 - iter 722/3617 - loss 0.01434764 - time (sec): 32.91 - samples/sec: 2300.40 - lr: 0.000016 - momentum: 0.000000
178
+ 2023-10-15 00:25:31,676 epoch 8 - iter 1083/3617 - loss 0.01437637 - time (sec): 50.47 - samples/sec: 2234.89 - lr: 0.000015 - momentum: 0.000000
179
+ 2023-10-15 00:25:49,450 epoch 8 - iter 1444/3617 - loss 0.01581867 - time (sec): 68.25 - samples/sec: 2227.74 - lr: 0.000014 - momentum: 0.000000
180
+ 2023-10-15 00:26:05,762 epoch 8 - iter 1805/3617 - loss 0.01496411 - time (sec): 84.56 - samples/sec: 2234.48 - lr: 0.000014 - momentum: 0.000000
181
+ 2023-10-15 00:26:21,684 epoch 8 - iter 2166/3617 - loss 0.01497828 - time (sec): 100.48 - samples/sec: 2256.01 - lr: 0.000013 - momentum: 0.000000
182
+ 2023-10-15 00:26:38,210 epoch 8 - iter 2527/3617 - loss 0.01610702 - time (sec): 117.01 - samples/sec: 2258.71 - lr: 0.000013 - momentum: 0.000000
183
+ 2023-10-15 00:26:55,148 epoch 8 - iter 2888/3617 - loss 0.01643447 - time (sec): 133.95 - samples/sec: 2263.00 - lr: 0.000012 - momentum: 0.000000
184
+ 2023-10-15 00:27:12,712 epoch 8 - iter 3249/3617 - loss 0.01674537 - time (sec): 151.51 - samples/sec: 2249.77 - lr: 0.000012 - momentum: 0.000000
185
+ 2023-10-15 00:27:29,206 epoch 8 - iter 3610/3617 - loss 0.01703835 - time (sec): 168.00 - samples/sec: 2256.24 - lr: 0.000011 - momentum: 0.000000
186
+ 2023-10-15 00:27:29,523 ----------------------------------------------------------------------------------------------------
187
+ 2023-10-15 00:27:29,523 EPOCH 8 done: loss 0.0170 - lr: 0.000011
188
+ 2023-10-15 00:27:35,276 DEV : loss 0.3864128291606903 - f1-score (micro avg) 0.6289
189
+ 2023-10-15 00:27:35,310 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-15 00:27:51,747 epoch 9 - iter 361/3617 - loss 0.01450096 - time (sec): 16.44 - samples/sec: 2304.81 - lr: 0.000011 - momentum: 0.000000
191
+ 2023-10-15 00:28:08,204 epoch 9 - iter 722/3617 - loss 0.01064632 - time (sec): 32.89 - samples/sec: 2320.76 - lr: 0.000010 - momentum: 0.000000
192
+ 2023-10-15 00:28:24,784 epoch 9 - iter 1083/3617 - loss 0.01026489 - time (sec): 49.47 - samples/sec: 2310.82 - lr: 0.000009 - momentum: 0.000000
193
+ 2023-10-15 00:28:41,232 epoch 9 - iter 1444/3617 - loss 0.01130151 - time (sec): 65.92 - samples/sec: 2296.54 - lr: 0.000009 - momentum: 0.000000
194
+ 2023-10-15 00:28:58,560 epoch 9 - iter 1805/3617 - loss 0.01065243 - time (sec): 83.25 - samples/sec: 2282.03 - lr: 0.000008 - momentum: 0.000000
195
+ 2023-10-15 00:29:14,860 epoch 9 - iter 2166/3617 - loss 0.01016027 - time (sec): 99.55 - samples/sec: 2288.00 - lr: 0.000008 - momentum: 0.000000
196
+ 2023-10-15 00:29:31,188 epoch 9 - iter 2527/3617 - loss 0.01022229 - time (sec): 115.88 - samples/sec: 2288.63 - lr: 0.000007 - momentum: 0.000000
197
+ 2023-10-15 00:29:47,607 epoch 9 - iter 2888/3617 - loss 0.01081834 - time (sec): 132.30 - samples/sec: 2296.70 - lr: 0.000007 - momentum: 0.000000
198
+ 2023-10-15 00:30:04,031 epoch 9 - iter 3249/3617 - loss 0.01056924 - time (sec): 148.72 - samples/sec: 2297.77 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-15 00:30:20,223 epoch 9 - iter 3610/3617 - loss 0.01077879 - time (sec): 164.91 - samples/sec: 2300.24 - lr: 0.000006 - momentum: 0.000000
200
+ 2023-10-15 00:30:20,526 ----------------------------------------------------------------------------------------------------
201
+ 2023-10-15 00:30:20,526 EPOCH 9 done: loss 0.0108 - lr: 0.000006
202
+ 2023-10-15 00:30:26,188 DEV : loss 0.3467862010002136 - f1-score (micro avg) 0.6337
203
+ 2023-10-15 00:30:26,221 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-15 00:30:43,182 epoch 10 - iter 361/3617 - loss 0.00565146 - time (sec): 16.96 - samples/sec: 2278.19 - lr: 0.000005 - momentum: 0.000000
205
+ 2023-10-15 00:30:59,790 epoch 10 - iter 722/3617 - loss 0.00592381 - time (sec): 33.57 - samples/sec: 2289.25 - lr: 0.000004 - momentum: 0.000000
206
+ 2023-10-15 00:31:16,416 epoch 10 - iter 1083/3617 - loss 0.00612734 - time (sec): 50.19 - samples/sec: 2263.89 - lr: 0.000004 - momentum: 0.000000
207
+ 2023-10-15 00:31:32,708 epoch 10 - iter 1444/3617 - loss 0.00593170 - time (sec): 66.49 - samples/sec: 2296.56 - lr: 0.000003 - momentum: 0.000000
208
+ 2023-10-15 00:31:48,980 epoch 10 - iter 1805/3617 - loss 0.00622588 - time (sec): 82.76 - samples/sec: 2295.89 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-15 00:32:05,209 epoch 10 - iter 2166/3617 - loss 0.00640911 - time (sec): 98.99 - samples/sec: 2291.44 - lr: 0.000002 - momentum: 0.000000
210
+ 2023-10-15 00:32:23,502 epoch 10 - iter 2527/3617 - loss 0.00605974 - time (sec): 117.28 - samples/sec: 2269.96 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-15 00:32:41,563 epoch 10 - iter 2888/3617 - loss 0.00603640 - time (sec): 135.34 - samples/sec: 2247.59 - lr: 0.000001 - momentum: 0.000000
212
+ 2023-10-15 00:32:57,825 epoch 10 - iter 3249/3617 - loss 0.00584887 - time (sec): 151.60 - samples/sec: 2253.59 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-15 00:33:14,082 epoch 10 - iter 3610/3617 - loss 0.00661902 - time (sec): 167.86 - samples/sec: 2258.04 - lr: 0.000000 - momentum: 0.000000
214
+ 2023-10-15 00:33:14,400 ----------------------------------------------------------------------------------------------------
215
+ 2023-10-15 00:33:14,400 EPOCH 10 done: loss 0.0066 - lr: 0.000000
216
+ 2023-10-15 00:33:20,856 DEV : loss 0.40056759119033813 - f1-score (micro avg) 0.6307
217
+ 2023-10-15 00:33:21,342 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-15 00:33:21,343 Loading model from best epoch ...
219
+ 2023-10-15 00:33:23,092 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
220
+ 2023-10-15 00:33:29,961
221
+ Results:
222
+ - F-score (micro) 0.6314
223
+ - F-score (macro) 0.4273
224
+ - Accuracy 0.4768
225
+
226
+ By class:
227
+ precision recall f1-score support
228
+
229
+ loc 0.6242 0.7868 0.6961 591
230
+ pers 0.5294 0.6555 0.5857 357
231
+ org 0.0000 0.0000 0.0000 79
232
+
233
+ micro avg 0.5889 0.6806 0.6314 1027
234
+ macro avg 0.3845 0.4808 0.4273 1027
235
+ weighted avg 0.5432 0.6806 0.6042 1027
236
+
237
+ 2023-10-15 00:33:29,961 ----------------------------------------------------------------------------------------------------