Hugging Face's logo

stefan-it
/
hmbench-hipe2020-fr-hmbert-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2

Token Classification
Flair
PyTorch
French
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
349f79d
·
1 Parent(s): d084b09

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 +246 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b5e99d73aa688872870fba4e51f15f802ae5e51e060cb41c7bb5c9cbad0e7dd
3
+ size 443335879
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 16:08:27 0.0000 0.5581 0.1429 0.6525 0.7583 0.7015 0.5680
3
+ 2 16:09:29 0.0000 0.1233 0.1049 0.7381 0.7749 0.7561 0.6352
4
+ 3 16:10:30 0.0000 0.0696 0.1244 0.7958 0.7858 0.7908 0.6833
5
+ 4 16:11:32 0.0000 0.0504 0.1623 0.7580 0.8270 0.7910 0.6863
6
+ 5 16:12:34 0.0000 0.0356 0.1621 0.7948 0.8076 0.8011 0.7029
7
+ 6 16:13:37 0.0000 0.0276 0.1762 0.8010 0.8253 0.8130 0.7095
8
+ 7 16:14:38 0.0000 0.0182 0.1849 0.8282 0.8310 0.8296 0.7328
9
+ 8 16:15:40 0.0000 0.0135 0.2090 0.8135 0.8368 0.8250 0.7269
10
+ 9 16:16:41 0.0000 0.0083 0.2079 0.8224 0.8379 0.8301 0.7363
11
+ 10 16:17:43 0.0000 0.0049 0.2119 0.8230 0.8414 0.8321 0.7397
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-13 16:07:31,904 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 16:07:31,905 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=21, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-13 16:07:31,905 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 16:07:31,905 MultiCorpus: 5901 train + 1287 dev + 1505 test sentences
52
+ - NER_HIPE_2022 Corpus: 5901 train + 1287 dev + 1505 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/fr/with_doc_seperator
53
+ 2023-10-13 16:07:31,905 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 16:07:31,905 Train: 5901 sentences
55
+ 2023-10-13 16:07:31,905 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 16:07:31,905 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 16:07:31,905 Training Params:
58
+ 2023-10-13 16:07:31,905 - learning_rate: "5e-05"
59
+ 2023-10-13 16:07:31,905 - mini_batch_size: "8"
60
+ 2023-10-13 16:07:31,905 - max_epochs: "10"
61
+ 2023-10-13 16:07:31,905 - shuffle: "True"
62
+ 2023-10-13 16:07:31,906 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 16:07:31,906 Plugins:
64
+ 2023-10-13 16:07:31,906 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 16:07:31,906 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 16:07:31,906 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 16:07:31,906 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 16:07:31,906 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 16:07:31,906 Computation:
70
+ 2023-10-13 16:07:31,906 - compute on device: cuda:0
71
+ 2023-10-13 16:07:31,906 - embedding storage: none
72
+ 2023-10-13 16:07:31,906 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 16:07:31,906 Model training base path: "hmbench-hipe2020/fr-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2"
74
+ 2023-10-13 16:07:31,906 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 16:07:31,906 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 16:07:37,143 epoch 1 - iter 73/738 - loss 2.76598445 - time (sec): 5.24 - samples/sec: 3360.36 - lr: 0.000005 - momentum: 0.000000
77
+ 2023-10-13 16:07:42,169 epoch 1 - iter 146/738 - loss 1.66719703 - time (sec): 10.26 - samples/sec: 3487.80 - lr: 0.000010 - momentum: 0.000000
78
+ 2023-10-13 16:07:47,178 epoch 1 - iter 219/738 - loss 1.27255728 - time (sec): 15.27 - samples/sec: 3386.07 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-13 16:07:52,113 epoch 1 - iter 292/738 - loss 1.03524511 - time (sec): 20.21 - samples/sec: 3381.44 - lr: 0.000020 - momentum: 0.000000
80
+ 2023-10-13 16:07:57,063 epoch 1 - iter 365/738 - loss 0.89357834 - time (sec): 25.16 - samples/sec: 3379.11 - lr: 0.000025 - momentum: 0.000000
81
+ 2023-10-13 16:08:01,878 epoch 1 - iter 438/738 - loss 0.78652245 - time (sec): 29.97 - samples/sec: 3393.22 - lr: 0.000030 - momentum: 0.000000
82
+ 2023-10-13 16:08:06,712 epoch 1 - iter 511/738 - loss 0.71094911 - time (sec): 34.80 - samples/sec: 3385.50 - lr: 0.000035 - momentum: 0.000000
83
+ 2023-10-13 16:08:11,369 epoch 1 - iter 584/738 - loss 0.65439322 - time (sec): 39.46 - samples/sec: 3354.63 - lr: 0.000039 - momentum: 0.000000
84
+ 2023-10-13 16:08:16,348 epoch 1 - iter 657/738 - loss 0.60420483 - time (sec): 44.44 - samples/sec: 3343.22 - lr: 0.000044 - momentum: 0.000000
85
+ 2023-10-13 16:08:21,114 epoch 1 - iter 730/738 - loss 0.56171741 - time (sec): 49.21 - samples/sec: 3351.84 - lr: 0.000049 - momentum: 0.000000
86
+ 2023-10-13 16:08:21,588 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 16:08:21,588 EPOCH 1 done: loss 0.5581 - lr: 0.000049
88
+ 2023-10-13 16:08:27,352 DEV : loss 0.14290109276771545 - f1-score (micro avg) 0.7015
89
+ 2023-10-13 16:08:27,384 saving best model
90
+ 2023-10-13 16:08:27,872 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 16:08:32,167 epoch 2 - iter 73/738 - loss 0.12716274 - time (sec): 4.29 - samples/sec: 3521.57 - lr: 0.000049 - momentum: 0.000000
92
+ 2023-10-13 16:08:36,924 epoch 2 - iter 146/738 - loss 0.13405283 - time (sec): 9.05 - samples/sec: 3459.97 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-13 16:08:41,641 epoch 2 - iter 219/738 - loss 0.13759252 - time (sec): 13.77 - samples/sec: 3447.39 - lr: 0.000048 - momentum: 0.000000
94
+ 2023-10-13 16:08:47,028 epoch 2 - iter 292/738 - loss 0.13374106 - time (sec): 19.15 - samples/sec: 3295.50 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-13 16:08:51,691 epoch 2 - iter 365/738 - loss 0.13472976 - time (sec): 23.82 - samples/sec: 3300.76 - lr: 0.000047 - momentum: 0.000000
96
+ 2023-10-13 16:08:56,701 epoch 2 - iter 438/738 - loss 0.13143665 - time (sec): 28.83 - samples/sec: 3311.21 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-13 16:09:02,238 epoch 2 - iter 511/738 - loss 0.12819648 - time (sec): 34.37 - samples/sec: 3312.44 - lr: 0.000046 - momentum: 0.000000
98
+ 2023-10-13 16:09:07,051 epoch 2 - iter 584/738 - loss 0.12305117 - time (sec): 39.18 - samples/sec: 3321.56 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-13 16:09:12,066 epoch 2 - iter 657/738 - loss 0.12315101 - time (sec): 44.19 - samples/sec: 3333.00 - lr: 0.000045 - momentum: 0.000000
100
+ 2023-10-13 16:09:17,367 epoch 2 - iter 730/738 - loss 0.12343880 - time (sec): 49.49 - samples/sec: 3328.11 - lr: 0.000045 - momentum: 0.000000
101
+ 2023-10-13 16:09:17,866 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 16:09:17,866 EPOCH 2 done: loss 0.1233 - lr: 0.000045
103
+ 2023-10-13 16:09:28,983 DEV : loss 0.10492947697639465 - f1-score (micro avg) 0.7561
104
+ 2023-10-13 16:09:29,013 saving best model
105
+ 2023-10-13 16:09:29,530 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 16:09:34,249 epoch 3 - iter 73/738 - loss 0.05692245 - time (sec): 4.72 - samples/sec: 3271.85 - lr: 0.000044 - momentum: 0.000000
107
+ 2023-10-13 16:09:39,076 epoch 3 - iter 146/738 - loss 0.06379593 - time (sec): 9.54 - samples/sec: 3360.48 - lr: 0.000043 - momentum: 0.000000
108
+ 2023-10-13 16:09:43,953 epoch 3 - iter 219/738 - loss 0.07184299 - time (sec): 14.42 - samples/sec: 3352.39 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-13 16:09:48,396 epoch 3 - iter 292/738 - loss 0.07056935 - time (sec): 18.86 - samples/sec: 3355.15 - lr: 0.000042 - momentum: 0.000000
110
+ 2023-10-13 16:09:53,905 epoch 3 - iter 365/738 - loss 0.06945011 - time (sec): 24.37 - samples/sec: 3322.09 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-13 16:09:59,137 epoch 3 - iter 438/738 - loss 0.06940866 - time (sec): 29.60 - samples/sec: 3357.23 - lr: 0.000041 - momentum: 0.000000
112
+ 2023-10-13 16:10:04,013 epoch 3 - iter 511/738 - loss 0.06696551 - time (sec): 34.48 - samples/sec: 3346.45 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-13 16:10:08,915 epoch 3 - iter 584/738 - loss 0.06853341 - time (sec): 39.38 - samples/sec: 3359.17 - lr: 0.000040 - momentum: 0.000000
114
+ 2023-10-13 16:10:14,120 epoch 3 - iter 657/738 - loss 0.06811819 - time (sec): 44.59 - samples/sec: 3350.17 - lr: 0.000040 - momentum: 0.000000
115
+ 2023-10-13 16:10:18,824 epoch 3 - iter 730/738 - loss 0.06952438 - time (sec): 49.29 - samples/sec: 3343.34 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-13 16:10:19,287 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 16:10:19,287 EPOCH 3 done: loss 0.0696 - lr: 0.000039
118
+ 2023-10-13 16:10:30,446 DEV : loss 0.12435939162969589 - f1-score (micro avg) 0.7908
119
+ 2023-10-13 16:10:30,475 saving best model
120
+ 2023-10-13 16:10:31,010 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 16:10:35,777 epoch 4 - iter 73/738 - loss 0.04217679 - time (sec): 4.76 - samples/sec: 3176.63 - lr: 0.000038 - momentum: 0.000000
122
+ 2023-10-13 16:10:40,427 epoch 4 - iter 146/738 - loss 0.04322531 - time (sec): 9.41 - samples/sec: 3274.46 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-13 16:10:45,415 epoch 4 - iter 219/738 - loss 0.04486914 - time (sec): 14.40 - samples/sec: 3287.51 - lr: 0.000037 - momentum: 0.000000
124
+ 2023-10-13 16:10:50,035 epoch 4 - iter 292/738 - loss 0.04509778 - time (sec): 19.02 - samples/sec: 3300.10 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-13 16:10:55,060 epoch 4 - iter 365/738 - loss 0.04617630 - time (sec): 24.05 - samples/sec: 3306.06 - lr: 0.000036 - momentum: 0.000000
126
+ 2023-10-13 16:11:00,379 epoch 4 - iter 438/738 - loss 0.04564721 - time (sec): 29.37 - samples/sec: 3297.33 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-13 16:11:06,000 epoch 4 - iter 511/738 - loss 0.04566072 - time (sec): 34.99 - samples/sec: 3301.63 - lr: 0.000035 - momentum: 0.000000
128
+ 2023-10-13 16:11:10,755 epoch 4 - iter 584/738 - loss 0.04718094 - time (sec): 39.74 - samples/sec: 3320.12 - lr: 0.000035 - momentum: 0.000000
129
+ 2023-10-13 16:11:15,857 epoch 4 - iter 657/738 - loss 0.04928165 - time (sec): 44.84 - samples/sec: 3317.33 - lr: 0.000034 - momentum: 0.000000
130
+ 2023-10-13 16:11:20,524 epoch 4 - iter 730/738 - loss 0.05030015 - time (sec): 49.51 - samples/sec: 3328.40 - lr: 0.000033 - momentum: 0.000000
131
+ 2023-10-13 16:11:21,012 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 16:11:21,012 EPOCH 4 done: loss 0.0504 - lr: 0.000033
133
+ 2023-10-13 16:11:32,198 DEV : loss 0.16232198476791382 - f1-score (micro avg) 0.791
134
+ 2023-10-13 16:11:32,230 saving best model
135
+ 2023-10-13 16:11:32,738 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-13 16:11:37,904 epoch 5 - iter 73/738 - loss 0.04547528 - time (sec): 5.16 - samples/sec: 3187.03 - lr: 0.000033 - momentum: 0.000000
137
+ 2023-10-13 16:11:42,931 epoch 5 - iter 146/738 - loss 0.03745766 - time (sec): 10.19 - samples/sec: 3241.04 - lr: 0.000032 - momentum: 0.000000
138
+ 2023-10-13 16:11:47,719 epoch 5 - iter 219/738 - loss 0.04018018 - time (sec): 14.98 - samples/sec: 3334.49 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-13 16:11:52,545 epoch 5 - iter 292/738 - loss 0.03642262 - time (sec): 19.80 - samples/sec: 3334.28 - lr: 0.000031 - momentum: 0.000000
140
+ 2023-10-13 16:11:57,388 epoch 5 - iter 365/738 - loss 0.03525492 - time (sec): 24.65 - samples/sec: 3330.64 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-13 16:12:02,106 epoch 5 - iter 438/738 - loss 0.03546021 - time (sec): 29.36 - samples/sec: 3321.27 - lr: 0.000030 - momentum: 0.000000
142
+ 2023-10-13 16:12:07,137 epoch 5 - iter 511/738 - loss 0.03493695 - time (sec): 34.39 - samples/sec: 3306.29 - lr: 0.000030 - momentum: 0.000000
143
+ 2023-10-13 16:12:12,773 epoch 5 - iter 584/738 - loss 0.03563392 - time (sec): 40.03 - samples/sec: 3286.64 - lr: 0.000029 - momentum: 0.000000
144
+ 2023-10-13 16:12:18,509 epoch 5 - iter 657/738 - loss 0.03533050 - time (sec): 45.77 - samples/sec: 3273.26 - lr: 0.000028 - momentum: 0.000000
145
+ 2023-10-13 16:12:23,151 epoch 5 - iter 730/738 - loss 0.03550563 - time (sec): 50.41 - samples/sec: 3266.32 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-13 16:12:23,713 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-13 16:12:23,713 EPOCH 5 done: loss 0.0356 - lr: 0.000028
148
+ 2023-10-13 16:12:34,872 DEV : loss 0.16207054257392883 - f1-score (micro avg) 0.8011
149
+ 2023-10-13 16:12:34,902 saving best model
150
+ 2023-10-13 16:12:35,395 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-13 16:12:39,937 epoch 6 - iter 73/738 - loss 0.03186713 - time (sec): 4.54 - samples/sec: 3270.44 - lr: 0.000027 - momentum: 0.000000
152
+ 2023-10-13 16:12:45,514 epoch 6 - iter 146/738 - loss 0.02345574 - time (sec): 10.11 - samples/sec: 3355.66 - lr: 0.000027 - momentum: 0.000000
153
+ 2023-10-13 16:12:50,577 epoch 6 - iter 219/738 - loss 0.02552735 - time (sec): 15.18 - samples/sec: 3347.83 - lr: 0.000026 - momentum: 0.000000
154
+ 2023-10-13 16:12:55,260 epoch 6 - iter 292/738 - loss 0.02690248 - time (sec): 19.86 - samples/sec: 3336.26 - lr: 0.000026 - momentum: 0.000000
155
+ 2023-10-13 16:13:01,206 epoch 6 - iter 365/738 - loss 0.02701658 - time (sec): 25.81 - samples/sec: 3272.23 - lr: 0.000025 - momentum: 0.000000
156
+ 2023-10-13 16:13:06,100 epoch 6 - iter 438/738 - loss 0.02755494 - time (sec): 30.70 - samples/sec: 3300.44 - lr: 0.000025 - momentum: 0.000000
157
+ 2023-10-13 16:13:10,632 epoch 6 - iter 511/738 - loss 0.02727897 - time (sec): 35.23 - samples/sec: 3311.23 - lr: 0.000024 - momentum: 0.000000
158
+ 2023-10-13 16:13:15,741 epoch 6 - iter 584/738 - loss 0.02651565 - time (sec): 40.34 - samples/sec: 3301.92 - lr: 0.000023 - momentum: 0.000000
159
+ 2023-10-13 16:13:20,645 epoch 6 - iter 657/738 - loss 0.02669398 - time (sec): 45.25 - samples/sec: 3290.08 - lr: 0.000023 - momentum: 0.000000
160
+ 2023-10-13 16:13:25,644 epoch 6 - iter 730/738 - loss 0.02762465 - time (sec): 50.24 - samples/sec: 3280.08 - lr: 0.000022 - momentum: 0.000000
161
+ 2023-10-13 16:13:26,124 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-13 16:13:26,124 EPOCH 6 done: loss 0.0276 - lr: 0.000022
163
+ 2023-10-13 16:13:37,376 DEV : loss 0.17623859643936157 - f1-score (micro avg) 0.813
164
+ 2023-10-13 16:13:37,409 saving best model
165
+ 2023-10-13 16:13:37,915 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-13 16:13:43,425 epoch 7 - iter 73/738 - loss 0.02042456 - time (sec): 5.51 - samples/sec: 3090.32 - lr: 0.000022 - momentum: 0.000000
167
+ 2023-10-13 16:13:47,723 epoch 7 - iter 146/738 - loss 0.01755039 - time (sec): 9.81 - samples/sec: 3246.41 - lr: 0.000021 - momentum: 0.000000
168
+ 2023-10-13 16:13:53,127 epoch 7 - iter 219/738 - loss 0.01705598 - time (sec): 15.21 - samples/sec: 3310.24 - lr: 0.000021 - momentum: 0.000000
169
+ 2023-10-13 16:13:58,575 epoch 7 - iter 292/738 - loss 0.01623354 - time (sec): 20.66 - samples/sec: 3333.59 - lr: 0.000020 - momentum: 0.000000
170
+ 2023-10-13 16:14:03,036 epoch 7 - iter 365/738 - loss 0.01564171 - time (sec): 25.12 - samples/sec: 3331.51 - lr: 0.000020 - momentum: 0.000000
171
+ 2023-10-13 16:14:07,628 epoch 7 - iter 438/738 - loss 0.01656402 - time (sec): 29.71 - samples/sec: 3334.05 - lr: 0.000019 - momentum: 0.000000
172
+ 2023-10-13 16:14:12,209 epoch 7 - iter 511/738 - loss 0.01804093 - time (sec): 34.29 - samples/sec: 3354.90 - lr: 0.000018 - momentum: 0.000000
173
+ 2023-10-13 16:14:16,920 epoch 7 - iter 584/738 - loss 0.01843500 - time (sec): 39.00 - samples/sec: 3345.53 - lr: 0.000018 - momentum: 0.000000
174
+ 2023-10-13 16:14:21,848 epoch 7 - iter 657/738 - loss 0.01777761 - time (sec): 43.93 - samples/sec: 3333.64 - lr: 0.000017 - momentum: 0.000000
175
+ 2023-10-13 16:14:27,303 epoch 7 - iter 730/738 - loss 0.01822353 - time (sec): 49.39 - samples/sec: 3337.85 - lr: 0.000017 - momentum: 0.000000
176
+ 2023-10-13 16:14:27,768 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-13 16:14:27,768 EPOCH 7 done: loss 0.0182 - lr: 0.000017
178
+ 2023-10-13 16:14:38,887 DEV : loss 0.18489772081375122 - f1-score (micro avg) 0.8296
179
+ 2023-10-13 16:14:38,917 saving best model
180
+ 2023-10-13 16:14:39,522 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-13 16:14:44,322 epoch 8 - iter 73/738 - loss 0.02158221 - time (sec): 4.80 - samples/sec: 3479.64 - lr: 0.000016 - momentum: 0.000000
182
+ 2023-10-13 16:14:49,508 epoch 8 - iter 146/738 - loss 0.01696772 - time (sec): 9.98 - samples/sec: 3370.64 - lr: 0.000016 - momentum: 0.000000
183
+ 2023-10-13 16:14:55,059 epoch 8 - iter 219/738 - loss 0.01617594 - time (sec): 15.53 - samples/sec: 3401.07 - lr: 0.000015 - momentum: 0.000000
184
+ 2023-10-13 16:14:59,771 epoch 8 - iter 292/738 - loss 0.01777930 - time (sec): 20.24 - samples/sec: 3343.21 - lr: 0.000015 - momentum: 0.000000
185
+ 2023-10-13 16:15:04,316 epoch 8 - iter 365/738 - loss 0.01630697 - time (sec): 24.79 - samples/sec: 3323.60 - lr: 0.000014 - momentum: 0.000000
186
+ 2023-10-13 16:15:09,176 epoch 8 - iter 438/738 - loss 0.01597156 - time (sec): 29.65 - samples/sec: 3324.09 - lr: 0.000013 - momentum: 0.000000
187
+ 2023-10-13 16:15:14,012 epoch 8 - iter 511/738 - loss 0.01492589 - time (sec): 34.49 - samples/sec: 3327.04 - lr: 0.000013 - momentum: 0.000000
188
+ 2023-10-13 16:15:18,408 epoch 8 - iter 584/738 - loss 0.01525583 - time (sec): 38.88 - samples/sec: 3326.93 - lr: 0.000012 - momentum: 0.000000
189
+ 2023-10-13 16:15:23,227 epoch 8 - iter 657/738 - loss 0.01427343 - time (sec): 43.70 - samples/sec: 3323.76 - lr: 0.000012 - momentum: 0.000000
190
+ 2023-10-13 16:15:28,712 epoch 8 - iter 730/738 - loss 0.01360292 - time (sec): 49.18 - samples/sec: 3348.93 - lr: 0.000011 - momentum: 0.000000
191
+ 2023-10-13 16:15:29,203 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-13 16:15:29,203 EPOCH 8 done: loss 0.0135 - lr: 0.000011
193
+ 2023-10-13 16:15:40,324 DEV : loss 0.20899920165538788 - f1-score (micro avg) 0.825
194
+ 2023-10-13 16:15:40,355 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-13 16:15:45,276 epoch 9 - iter 73/738 - loss 0.00737419 - time (sec): 4.92 - samples/sec: 3151.24 - lr: 0.000011 - momentum: 0.000000
196
+ 2023-10-13 16:15:50,322 epoch 9 - iter 146/738 - loss 0.00639227 - time (sec): 9.97 - samples/sec: 3242.90 - lr: 0.000010 - momentum: 0.000000
197
+ 2023-10-13 16:15:54,891 epoch 9 - iter 219/738 - loss 0.00609163 - time (sec): 14.54 - samples/sec: 3323.28 - lr: 0.000010 - momentum: 0.000000
198
+ 2023-10-13 16:15:59,713 epoch 9 - iter 292/738 - loss 0.00710336 - time (sec): 19.36 - samples/sec: 3348.37 - lr: 0.000009 - momentum: 0.000000
199
+ 2023-10-13 16:16:05,038 epoch 9 - iter 365/738 - loss 0.00870007 - time (sec): 24.68 - samples/sec: 3353.92 - lr: 0.000008 - momentum: 0.000000
200
+ 2023-10-13 16:16:09,730 epoch 9 - iter 438/738 - loss 0.00815323 - time (sec): 29.37 - samples/sec: 3345.31 - lr: 0.000008 - momentum: 0.000000
201
+ 2023-10-13 16:16:14,960 epoch 9 - iter 511/738 - loss 0.00770538 - time (sec): 34.60 - samples/sec: 3328.70 - lr: 0.000007 - momentum: 0.000000
202
+ 2023-10-13 16:16:19,571 epoch 9 - iter 584/738 - loss 0.00789209 - time (sec): 39.21 - samples/sec: 3320.50 - lr: 0.000007 - momentum: 0.000000
203
+ 2023-10-13 16:16:24,295 epoch 9 - iter 657/738 - loss 0.00748613 - time (sec): 43.94 - samples/sec: 3337.76 - lr: 0.000006 - momentum: 0.000000
204
+ 2023-10-13 16:16:29,662 epoch 9 - iter 730/738 - loss 0.00819185 - time (sec): 49.31 - samples/sec: 3338.75 - lr: 0.000006 - momentum: 0.000000
205
+ 2023-10-13 16:16:30,264 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-13 16:16:30,264 EPOCH 9 done: loss 0.0083 - lr: 0.000006
207
+ 2023-10-13 16:16:41,419 DEV : loss 0.20789538323879242 - f1-score (micro avg) 0.8301
208
+ 2023-10-13 16:16:41,457 saving best model
209
+ 2023-10-13 16:16:41,968 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-13 16:16:47,776 epoch 10 - iter 73/738 - loss 0.00953757 - time (sec): 5.80 - samples/sec: 3035.36 - lr: 0.000005 - momentum: 0.000000
211
+ 2023-10-13 16:16:52,458 epoch 10 - iter 146/738 - loss 0.00607430 - time (sec): 10.48 - samples/sec: 3196.87 - lr: 0.000004 - momentum: 0.000000
212
+ 2023-10-13 16:16:56,727 epoch 10 - iter 219/738 - loss 0.00711998 - time (sec): 14.75 - samples/sec: 3318.90 - lr: 0.000004 - momentum: 0.000000
213
+ 2023-10-13 16:17:01,617 epoch 10 - iter 292/738 - loss 0.00638173 - time (sec): 19.64 - samples/sec: 3324.20 - lr: 0.000003 - momentum: 0.000000
214
+ 2023-10-13 16:17:06,558 epoch 10 - iter 365/738 - loss 0.00593203 - time (sec): 24.59 - samples/sec: 3308.48 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-13 16:17:12,087 epoch 10 - iter 438/738 - loss 0.00538934 - time (sec): 30.11 - samples/sec: 3322.99 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-13 16:17:16,645 epoch 10 - iter 511/738 - loss 0.00527968 - time (sec): 34.67 - samples/sec: 3309.72 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-13 16:17:22,018 epoch 10 - iter 584/738 - loss 0.00510774 - time (sec): 40.04 - samples/sec: 3290.48 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-13 16:17:27,000 epoch 10 - iter 657/738 - loss 0.00530120 - time (sec): 45.03 - samples/sec: 3292.97 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-13 16:17:32,035 epoch 10 - iter 730/738 - loss 0.00491710 - time (sec): 50.06 - samples/sec: 3294.31 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-13 16:17:32,457 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-13 16:17:32,458 EPOCH 10 done: loss 0.0049 - lr: 0.000000
222
+ 2023-10-13 16:17:43,618 DEV : loss 0.21186788380146027 - f1-score (micro avg) 0.8321
223
+ 2023-10-13 16:17:43,651 saving best model
224
+ 2023-10-13 16:17:44,637 ----------------------------------------------------------------------------------------------------
225
+ 2023-10-13 16:17:44,638 Loading model from best epoch ...
226
+ 2023-10-13 16:17:46,067 SequenceTagger predicts: Dictionary with 21 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, S-time, B-time, E-time, I-time, S-prod, B-prod, E-prod, I-prod
227
+ 2023-10-13 16:17:51,903
228
+ Results:
229
+ - F-score (micro) 0.7943
230
+ - F-score (macro) 0.6995
231
+ - Accuracy 0.6824
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ loc 0.8442 0.8776 0.8606 858
237
+ pers 0.7558 0.7952 0.7750 537
238
+ org 0.5603 0.5985 0.5788 132
239
+ time 0.5538 0.6667 0.6050 54
240
+ prod 0.7222 0.6393 0.6783 61
241
+
242
+ micro avg 0.7769 0.8124 0.7943 1642
243
+ macro avg 0.6873 0.7155 0.6995 1642
244
+ weighted avg 0.7784 0.8124 0.7947 1642
245
+
246
+ 2023-10-13 16:17:51,904 ----------------------------------------------------------------------------------------------------