Hugging Face's logo

stefan-it
/
hmbench-hipe2020-fr-hmbert-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1

Token Classification
Flair
PyTorch
French
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
0d5f111
·
1 Parent(s): f4263cc

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 +244 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac98257a8e451f1e1a2d0c049dc87c3f95296ecd50c34f4449c601afa6f8f9b7
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 15:07:08 0.0000 0.6428 0.1463 0.6813 0.7199 0.7001 0.5724
3
+ 2 15:08:08 0.0000 0.1252 0.1044 0.7545 0.8099 0.7812 0.6686
4
+ 3 15:09:10 0.0000 0.0703 0.1147 0.7858 0.7944 0.7901 0.6856
5
+ 4 15:10:12 0.0000 0.0455 0.1425 0.7976 0.8328 0.8148 0.7152
6
+ 5 15:11:14 0.0000 0.0341 0.1662 0.8015 0.8396 0.8201 0.7176
7
+ 6 15:12:16 0.0000 0.0271 0.1780 0.8198 0.8362 0.8279 0.7337
8
+ 7 15:13:18 0.0000 0.0171 0.1946 0.8084 0.8408 0.8243 0.7303
9
+ 8 15:14:19 0.0000 0.0141 0.2088 0.8148 0.8368 0.8257 0.7305
10
+ 9 15:15:19 0.0000 0.0107 0.2110 0.8200 0.8402 0.8300 0.7383
11
+ 10 15:16:22 0.0000 0.0081 0.2104 0.8078 0.8402 0.8237 0.7295
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-13 15:06:11,843 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 15:06:11,844 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 15:06:11,844 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 15:06:11,844 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 15:06:11,844 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 15:06:11,844 Train: 5901 sentences
55
+ 2023-10-13 15:06:11,844 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 15:06:11,844 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 15:06:11,845 Training Params:
58
+ 2023-10-13 15:06:11,845 - learning_rate: "3e-05"
59
+ 2023-10-13 15:06:11,845 - mini_batch_size: "8"
60
+ 2023-10-13 15:06:11,845 - max_epochs: "10"
61
+ 2023-10-13 15:06:11,845 - shuffle: "True"
62
+ 2023-10-13 15:06:11,845 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 15:06:11,845 Plugins:
64
+ 2023-10-13 15:06:11,845 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 15:06:11,845 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 15:06:11,845 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 15:06:11,845 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 15:06:11,845 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 15:06:11,845 Computation:
70
+ 2023-10-13 15:06:11,845 - compute on device: cuda:0
71
+ 2023-10-13 15:06:11,845 - embedding storage: none
72
+ 2023-10-13 15:06:11,845 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 15:06:11,845 Model training base path: "hmbench-hipe2020/fr-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
74
+ 2023-10-13 15:06:11,845 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 15:06:11,845 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 15:06:17,981 epoch 1 - iter 73/738 - loss 3.00595806 - time (sec): 6.13 - samples/sec: 2718.25 - lr: 0.000003 - momentum: 0.000000
77
+ 2023-10-13 15:06:22,822 epoch 1 - iter 146/738 - loss 2.01431217 - time (sec): 10.98 - samples/sec: 3002.22 - lr: 0.000006 - momentum: 0.000000
78
+ 2023-10-13 15:06:28,408 epoch 1 - iter 219/738 - loss 1.47513576 - time (sec): 16.56 - samples/sec: 3131.01 - lr: 0.000009 - momentum: 0.000000
79
+ 2023-10-13 15:06:32,838 epoch 1 - iter 292/738 - loss 1.22557139 - time (sec): 20.99 - samples/sec: 3197.17 - lr: 0.000012 - momentum: 0.000000
80
+ 2023-10-13 15:06:37,475 epoch 1 - iter 365/738 - loss 1.05610101 - time (sec): 25.63 - samples/sec: 3240.87 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-13 15:06:42,108 epoch 1 - iter 438/738 - loss 0.93629240 - time (sec): 30.26 - samples/sec: 3255.61 - lr: 0.000018 - momentum: 0.000000
82
+ 2023-10-13 15:06:46,475 epoch 1 - iter 511/738 - loss 0.84807635 - time (sec): 34.63 - samples/sec: 3283.97 - lr: 0.000021 - momentum: 0.000000
83
+ 2023-10-13 15:06:51,169 epoch 1 - iter 584/738 - loss 0.77373600 - time (sec): 39.32 - samples/sec: 3278.82 - lr: 0.000024 - momentum: 0.000000
84
+ 2023-10-13 15:06:56,762 epoch 1 - iter 657/738 - loss 0.69819945 - time (sec): 44.92 - samples/sec: 3299.98 - lr: 0.000027 - momentum: 0.000000
85
+ 2023-10-13 15:07:01,779 epoch 1 - iter 730/738 - loss 0.64790807 - time (sec): 49.93 - samples/sec: 3302.06 - lr: 0.000030 - momentum: 0.000000
86
+ 2023-10-13 15:07:02,220 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 15:07:02,220 EPOCH 1 done: loss 0.6428 - lr: 0.000030
88
+ 2023-10-13 15:07:08,107 DEV : loss 0.14631909132003784 - f1-score (micro avg) 0.7001
89
+ 2023-10-13 15:07:08,134 saving best model
90
+ 2023-10-13 15:07:08,525 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 15:07:14,091 epoch 2 - iter 73/738 - loss 0.16706915 - time (sec): 5.56 - samples/sec: 3041.31 - lr: 0.000030 - momentum: 0.000000
92
+ 2023-10-13 15:07:18,341 epoch 2 - iter 146/738 - loss 0.14761739 - time (sec): 9.81 - samples/sec: 3167.97 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-13 15:07:23,052 epoch 2 - iter 219/738 - loss 0.14448689 - time (sec): 14.53 - samples/sec: 3195.29 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-13 15:07:27,919 epoch 2 - iter 292/738 - loss 0.14158495 - time (sec): 19.39 - samples/sec: 3231.27 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-13 15:07:32,228 epoch 2 - iter 365/738 - loss 0.13700805 - time (sec): 23.70 - samples/sec: 3290.03 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-13 15:07:38,405 epoch 2 - iter 438/738 - loss 0.13803403 - time (sec): 29.88 - samples/sec: 3339.44 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-13 15:07:43,280 epoch 2 - iter 511/738 - loss 0.13381098 - time (sec): 34.75 - samples/sec: 3339.59 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-13 15:07:48,287 epoch 2 - iter 584/738 - loss 0.13192888 - time (sec): 39.76 - samples/sec: 3331.69 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-13 15:07:53,037 epoch 2 - iter 657/738 - loss 0.12867654 - time (sec): 44.51 - samples/sec: 3348.07 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-13 15:07:57,470 epoch 2 - iter 730/738 - loss 0.12546326 - time (sec): 48.94 - samples/sec: 3365.74 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-13 15:07:57,943 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 15:07:57,943 EPOCH 2 done: loss 0.1252 - lr: 0.000027
103
+ 2023-10-13 15:08:08,895 DEV : loss 0.10444298386573792 - f1-score (micro avg) 0.7812
104
+ 2023-10-13 15:08:08,935 saving best model
105
+ 2023-10-13 15:08:09,490 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 15:08:14,272 epoch 3 - iter 73/738 - loss 0.07135036 - time (sec): 4.78 - samples/sec: 3180.23 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-13 15:08:18,952 epoch 3 - iter 146/738 - loss 0.06016871 - time (sec): 9.46 - samples/sec: 3299.03 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-13 15:08:23,756 epoch 3 - iter 219/738 - loss 0.06731171 - time (sec): 14.26 - samples/sec: 3388.02 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-13 15:08:28,852 epoch 3 - iter 292/738 - loss 0.06774648 - time (sec): 19.36 - samples/sec: 3379.36 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-13 15:08:33,951 epoch 3 - iter 365/738 - loss 0.07186902 - time (sec): 24.46 - samples/sec: 3390.49 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-13 15:08:38,497 epoch 3 - iter 438/738 - loss 0.07329844 - time (sec): 29.00 - samples/sec: 3374.13 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-13 15:08:43,281 epoch 3 - iter 511/738 - loss 0.07169878 - time (sec): 33.79 - samples/sec: 3383.78 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-13 15:08:48,666 epoch 3 - iter 584/738 - loss 0.07135414 - time (sec): 39.17 - samples/sec: 3352.61 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-13 15:08:53,320 epoch 3 - iter 657/738 - loss 0.07090972 - time (sec): 43.83 - samples/sec: 3371.01 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-13 15:08:58,624 epoch 3 - iter 730/738 - loss 0.07063718 - time (sec): 49.13 - samples/sec: 3355.13 - lr: 0.000023 - momentum: 0.000000
116
+ 2023-10-13 15:08:59,067 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 15:08:59,067 EPOCH 3 done: loss 0.0703 - lr: 0.000023
118
+ 2023-10-13 15:09:10,781 DEV : loss 0.11466138809919357 - f1-score (micro avg) 0.7901
119
+ 2023-10-13 15:09:10,815 saving best model
120
+ 2023-10-13 15:09:11,367 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 15:09:16,072 epoch 4 - iter 73/738 - loss 0.04052283 - time (sec): 4.70 - samples/sec: 3351.70 - lr: 0.000023 - momentum: 0.000000
122
+ 2023-10-13 15:09:21,227 epoch 4 - iter 146/738 - loss 0.04104392 - time (sec): 9.86 - samples/sec: 3391.42 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-13 15:09:26,698 epoch 4 - iter 219/738 - loss 0.04349424 - time (sec): 15.33 - samples/sec: 3397.14 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-13 15:09:31,305 epoch 4 - iter 292/738 - loss 0.04220332 - time (sec): 19.93 - samples/sec: 3382.12 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-13 15:09:35,929 epoch 4 - iter 365/738 - loss 0.04287845 - time (sec): 24.56 - samples/sec: 3378.03 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-13 15:09:40,356 epoch 4 - iter 438/738 - loss 0.04241677 - time (sec): 28.98 - samples/sec: 3364.05 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-13 15:09:45,522 epoch 4 - iter 511/738 - loss 0.04273484 - time (sec): 34.15 - samples/sec: 3370.50 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-13 15:09:50,179 epoch 4 - iter 584/738 - loss 0.04336454 - time (sec): 38.81 - samples/sec: 3360.30 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-13 15:09:55,539 epoch 4 - iter 657/738 - loss 0.04399407 - time (sec): 44.17 - samples/sec: 3357.73 - lr: 0.000020 - momentum: 0.000000
130
+ 2023-10-13 15:10:00,301 epoch 4 - iter 730/738 - loss 0.04575017 - time (sec): 48.93 - samples/sec: 3370.96 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-13 15:10:00,739 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 15:10:00,740 EPOCH 4 done: loss 0.0455 - lr: 0.000020
133
+ 2023-10-13 15:10:12,198 DEV : loss 0.1425015777349472 - f1-score (micro avg) 0.8148
134
+ 2023-10-13 15:10:12,235 saving best model
135
+ 2023-10-13 15:10:12,842 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-13 15:10:17,689 epoch 5 - iter 73/738 - loss 0.03811823 - time (sec): 4.84 - samples/sec: 3173.32 - lr: 0.000020 - momentum: 0.000000
137
+ 2023-10-13 15:10:22,809 epoch 5 - iter 146/738 - loss 0.03085581 - time (sec): 9.96 - samples/sec: 3137.72 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-13 15:10:27,945 epoch 5 - iter 219/738 - loss 0.03743163 - time (sec): 15.10 - samples/sec: 3218.04 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-13 15:10:32,662 epoch 5 - iter 292/738 - loss 0.03362175 - time (sec): 19.82 - samples/sec: 3227.76 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-13 15:10:37,919 epoch 5 - iter 365/738 - loss 0.03326265 - time (sec): 25.07 - samples/sec: 3248.42 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-13 15:10:43,093 epoch 5 - iter 438/738 - loss 0.03370392 - time (sec): 30.25 - samples/sec: 3253.05 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-13 15:10:47,701 epoch 5 - iter 511/738 - loss 0.03447331 - time (sec): 34.85 - samples/sec: 3266.99 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-13 15:10:52,511 epoch 5 - iter 584/738 - loss 0.03383997 - time (sec): 39.66 - samples/sec: 3275.72 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-13 15:10:57,968 epoch 5 - iter 657/738 - loss 0.03331943 - time (sec): 45.12 - samples/sec: 3288.68 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-13 15:11:02,727 epoch 5 - iter 730/738 - loss 0.03414638 - time (sec): 49.88 - samples/sec: 3307.94 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-13 15:11:03,167 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-13 15:11:03,167 EPOCH 5 done: loss 0.0341 - lr: 0.000017
148
+ 2023-10-13 15:11:14,225 DEV : loss 0.16617898643016815 - f1-score (micro avg) 0.8201
149
+ 2023-10-13 15:11:14,254 saving best model
150
+ 2023-10-13 15:11:14,766 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-13 15:11:19,314 epoch 6 - iter 73/738 - loss 0.03653394 - time (sec): 4.54 - samples/sec: 3289.33 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-13 15:11:24,335 epoch 6 - iter 146/738 - loss 0.02834807 - time (sec): 9.56 - samples/sec: 3172.23 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-13 15:11:29,927 epoch 6 - iter 219/738 - loss 0.02694544 - time (sec): 15.15 - samples/sec: 3243.68 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-13 15:11:34,905 epoch 6 - iter 292/738 - loss 0.02900938 - time (sec): 20.13 - samples/sec: 3232.05 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-13 15:11:39,564 epoch 6 - iter 365/738 - loss 0.02925216 - time (sec): 24.79 - samples/sec: 3266.97 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-13 15:11:44,927 epoch 6 - iter 438/738 - loss 0.02862355 - time (sec): 30.15 - samples/sec: 3284.34 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-13 15:11:49,476 epoch 6 - iter 511/738 - loss 0.02801253 - time (sec): 34.70 - samples/sec: 3289.74 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-13 15:11:54,293 epoch 6 - iter 584/738 - loss 0.02697259 - time (sec): 39.52 - samples/sec: 3292.93 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-13 15:11:59,783 epoch 6 - iter 657/738 - loss 0.02638200 - time (sec): 45.01 - samples/sec: 3312.23 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-13 15:12:04,543 epoch 6 - iter 730/738 - loss 0.02702535 - time (sec): 49.77 - samples/sec: 3311.87 - lr: 0.000013 - momentum: 0.000000
161
+ 2023-10-13 15:12:05,010 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-13 15:12:05,011 EPOCH 6 done: loss 0.0271 - lr: 0.000013
163
+ 2023-10-13 15:12:16,088 DEV : loss 0.17802561819553375 - f1-score (micro avg) 0.8279
164
+ 2023-10-13 15:12:16,116 saving best model
165
+ 2023-10-13 15:12:16,626 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-13 15:12:21,328 epoch 7 - iter 73/738 - loss 0.02201187 - time (sec): 4.70 - samples/sec: 3237.82 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-13 15:12:26,848 epoch 7 - iter 146/738 - loss 0.01959250 - time (sec): 10.22 - samples/sec: 3292.24 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-13 15:12:31,310 epoch 7 - iter 219/738 - loss 0.01698476 - time (sec): 14.68 - samples/sec: 3318.25 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-13 15:12:36,512 epoch 7 - iter 292/738 - loss 0.01780977 - time (sec): 19.88 - samples/sec: 3258.64 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-13 15:12:41,639 epoch 7 - iter 365/738 - loss 0.01729180 - time (sec): 25.01 - samples/sec: 3270.72 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-13 15:12:46,745 epoch 7 - iter 438/738 - loss 0.01848562 - time (sec): 30.11 - samples/sec: 3315.54 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-13 15:12:52,092 epoch 7 - iter 511/738 - loss 0.01773880 - time (sec): 35.46 - samples/sec: 3309.93 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-13 15:12:57,414 epoch 7 - iter 584/738 - loss 0.01697287 - time (sec): 40.78 - samples/sec: 3290.74 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-13 15:13:02,062 epoch 7 - iter 657/738 - loss 0.01729116 - time (sec): 45.43 - samples/sec: 3278.94 - lr: 0.000010 - momentum: 0.000000
175
+ 2023-10-13 15:13:06,934 epoch 7 - iter 730/738 - loss 0.01695416 - time (sec): 50.30 - samples/sec: 3271.06 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-13 15:13:07,414 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-13 15:13:07,414 EPOCH 7 done: loss 0.0171 - lr: 0.000010
178
+ 2023-10-13 15:13:18,417 DEV : loss 0.1945790946483612 - f1-score (micro avg) 0.8243
179
+ 2023-10-13 15:13:18,444 ----------------------------------------------------------------------------------------------------
180
+ 2023-10-13 15:13:23,184 epoch 8 - iter 73/738 - loss 0.01028889 - time (sec): 4.74 - samples/sec: 3410.19 - lr: 0.000010 - momentum: 0.000000
181
+ 2023-10-13 15:13:27,830 epoch 8 - iter 146/738 - loss 0.01125169 - time (sec): 9.38 - samples/sec: 3402.58 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-13 15:13:32,888 epoch 8 - iter 219/738 - loss 0.01185173 - time (sec): 14.44 - samples/sec: 3435.18 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-13 15:13:37,825 epoch 8 - iter 292/738 - loss 0.01232791 - time (sec): 19.38 - samples/sec: 3373.16 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-13 15:13:42,461 epoch 8 - iter 365/738 - loss 0.01366262 - time (sec): 24.02 - samples/sec: 3372.28 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-13 15:13:47,566 epoch 8 - iter 438/738 - loss 0.01654620 - time (sec): 29.12 - samples/sec: 3339.24 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-13 15:13:52,187 epoch 8 - iter 511/738 - loss 0.01569334 - time (sec): 33.74 - samples/sec: 3335.61 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-13 15:13:57,753 epoch 8 - iter 584/738 - loss 0.01574651 - time (sec): 39.31 - samples/sec: 3330.91 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-13 15:14:02,442 epoch 8 - iter 657/738 - loss 0.01505006 - time (sec): 44.00 - samples/sec: 3337.63 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-13 15:14:07,726 epoch 8 - iter 730/738 - loss 0.01414673 - time (sec): 49.28 - samples/sec: 3345.74 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-13 15:14:08,175 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-13 15:14:08,175 EPOCH 8 done: loss 0.0141 - lr: 0.000007
192
+ 2023-10-13 15:14:19,189 DEV : loss 0.208764910697937 - f1-score (micro avg) 0.8257
193
+ 2023-10-13 15:14:19,216 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-13 15:14:24,185 epoch 9 - iter 73/738 - loss 0.01390651 - time (sec): 4.97 - samples/sec: 3487.39 - lr: 0.000006 - momentum: 0.000000
195
+ 2023-10-13 15:14:28,985 epoch 9 - iter 146/738 - loss 0.01196049 - time (sec): 9.77 - samples/sec: 3443.85 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-13 15:14:33,824 epoch 9 - iter 219/738 - loss 0.01250429 - time (sec): 14.61 - samples/sec: 3380.42 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-13 15:14:38,723 epoch 9 - iter 292/738 - loss 0.01082105 - time (sec): 19.51 - samples/sec: 3355.41 - lr: 0.000005 - momentum: 0.000000
198
+ 2023-10-13 15:14:43,628 epoch 9 - iter 365/738 - loss 0.01081319 - time (sec): 24.41 - samples/sec: 3341.46 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-13 15:14:48,215 epoch 9 - iter 438/738 - loss 0.01107780 - time (sec): 29.00 - samples/sec: 3343.77 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-13 15:14:53,022 epoch 9 - iter 511/738 - loss 0.01096276 - time (sec): 33.80 - samples/sec: 3377.28 - lr: 0.000004 - momentum: 0.000000
201
+ 2023-10-13 15:14:58,322 epoch 9 - iter 584/738 - loss 0.01113887 - time (sec): 39.11 - samples/sec: 3358.91 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-13 15:15:03,199 epoch 9 - iter 657/738 - loss 0.01099575 - time (sec): 43.98 - samples/sec: 3363.25 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-13 15:15:07,995 epoch 9 - iter 730/738 - loss 0.01087907 - time (sec): 48.78 - samples/sec: 3369.09 - lr: 0.000003 - momentum: 0.000000
204
+ 2023-10-13 15:15:08,627 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-13 15:15:08,627 EPOCH 9 done: loss 0.0107 - lr: 0.000003
206
+ 2023-10-13 15:15:19,652 DEV : loss 0.21101868152618408 - f1-score (micro avg) 0.83
207
+ 2023-10-13 15:15:19,682 saving best model
208
+ 2023-10-13 15:15:20,194 ----------------------------------------------------------------------------------------------------
209
+ 2023-10-13 15:15:25,141 epoch 10 - iter 73/738 - loss 0.00803248 - time (sec): 4.94 - samples/sec: 3261.82 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-13 15:15:31,005 epoch 10 - iter 146/738 - loss 0.00805600 - time (sec): 10.81 - samples/sec: 3277.85 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-13 15:15:36,594 epoch 10 - iter 219/738 - loss 0.00898068 - time (sec): 16.40 - samples/sec: 3134.89 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-13 15:15:41,054 epoch 10 - iter 292/738 - loss 0.00813472 - time (sec): 20.86 - samples/sec: 3202.98 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-13 15:15:45,471 epoch 10 - iter 365/738 - loss 0.00754629 - time (sec): 25.27 - samples/sec: 3253.82 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-13 15:15:49,965 epoch 10 - iter 438/738 - loss 0.00782211 - time (sec): 29.77 - samples/sec: 3272.23 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-13 15:15:55,145 epoch 10 - iter 511/738 - loss 0.00825368 - time (sec): 34.95 - samples/sec: 3287.64 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-13 15:16:00,172 epoch 10 - iter 584/738 - loss 0.00879952 - time (sec): 39.97 - samples/sec: 3277.10 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-13 15:16:05,095 epoch 10 - iter 657/738 - loss 0.00821806 - time (sec): 44.90 - samples/sec: 3273.46 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-13 15:16:10,579 epoch 10 - iter 730/738 - loss 0.00815587 - time (sec): 50.38 - samples/sec: 3275.14 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-13 15:16:11,019 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-13 15:16:11,019 EPOCH 10 done: loss 0.0081 - lr: 0.000000
221
+ 2023-10-13 15:16:22,129 DEV : loss 0.21044372022151947 - f1-score (micro avg) 0.8237
222
+ 2023-10-13 15:16:22,555 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-13 15:16:22,556 Loading model from best epoch ...
224
+ 2023-10-13 15:16:24,438 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
225
+ 2023-10-13 15:16:30,319
226
+ Results:
227
+ - F-score (micro) 0.7963
228
+ - F-score (macro) 0.6911
229
+ - Accuracy 0.6835
230
+
231
+ By class:
232
+ precision recall f1-score support
233
+
234
+ loc 0.8486 0.8951 0.8712 858
235
+ pers 0.7409 0.7933 0.7662 537
236
+ org 0.5840 0.5530 0.5681 132
237
+ time 0.5231 0.6296 0.5714 54
238
+ prod 0.7451 0.6230 0.6786 61
239
+
240
+ micro avg 0.7780 0.8155 0.7963 1642
241
+ macro avg 0.6883 0.6988 0.6911 1642
242
+ weighted avg 0.7776 0.8155 0.7955 1642
243
+
244
+ 2023-10-13 15:16:30,319 ----------------------------------------------------------------------------------------------------