Hugging Face's logo

stefan-it
/
hmbench-letemps-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
a9bf069
·
1 Parent(s): b85d75d

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 +240 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeff8c281c9bfdbeca78ee28c1a0be613ab8e236e6e659533ac809cf5efe6935
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 19:36:11 0.0000 0.3115 0.1074 0.5316 0.7517 0.6227 0.4604
3
+ 2 19:38:10 0.0000 0.0822 0.1011 0.5915 0.7174 0.6484 0.4834
4
+ 3 19:40:09 0.0000 0.0580 0.1736 0.5340 0.7906 0.6375 0.4779
5
+ 4 19:42:06 0.0000 0.0399 0.2393 0.5616 0.7769 0.6519 0.4917
6
+ 5 19:44:03 0.0000 0.0288 0.3242 0.5483 0.7723 0.6413 0.4818
7
+ 6 19:46:00 0.0000 0.0195 0.3273 0.5626 0.7609 0.6469 0.4865
8
+ 7 19:47:57 0.0000 0.0142 0.3470 0.5557 0.7929 0.6535 0.4929
9
+ 8 19:49:55 0.0000 0.0110 0.3828 0.5618 0.7952 0.6585 0.4986
10
+ 9 19:51:54 0.0000 0.0065 0.4086 0.5416 0.8112 0.6496 0.4890
11
+ 10 19:53:52 0.0000 0.0046 0.4026 0.5582 0.7849 0.6524 0.4918
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-14 19:34:13,664 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-14 19:34:13,665 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
+ 2023-10-14 19:34:13,665 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-14 19:34:13,665 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
+ 2023-10-14 19:34:13,665 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-14 19:34:13,665 Train: 14465 sentences
55
+ 2023-10-14 19:34:13,665 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-14 19:34:13,665 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-14 19:34:13,665 Training Params:
58
+ 2023-10-14 19:34:13,665 - learning_rate: "3e-05"
59
+ 2023-10-14 19:34:13,665 - mini_batch_size: "8"
60
+ 2023-10-14 19:34:13,665 - max_epochs: "10"
61
+ 2023-10-14 19:34:13,665 - shuffle: "True"
62
+ 2023-10-14 19:34:13,666 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-14 19:34:13,666 Plugins:
64
+ 2023-10-14 19:34:13,666 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-14 19:34:13,666 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-14 19:34:13,666 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-14 19:34:13,666 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-14 19:34:13,666 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-14 19:34:13,666 Computation:
70
+ 2023-10-14 19:34:13,666 - compute on device: cuda:0
71
+ 2023-10-14 19:34:13,666 - embedding storage: none
72
+ 2023-10-14 19:34:13,666 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-14 19:34:13,666 Model training base path: "hmbench-letemps/fr-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
74
+ 2023-10-14 19:34:13,666 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-14 19:34:13,666 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-14 19:34:24,866 epoch 1 - iter 180/1809 - loss 1.87339049 - time (sec): 11.20 - samples/sec: 3416.59 - lr: 0.000003 - momentum: 0.000000
77
+ 2023-10-14 19:34:36,164 epoch 1 - iter 360/1809 - loss 1.06251129 - time (sec): 22.50 - samples/sec: 3376.96 - lr: 0.000006 - momentum: 0.000000
78
+ 2023-10-14 19:34:47,458 epoch 1 - iter 540/1809 - loss 0.77046509 - time (sec): 33.79 - samples/sec: 3359.59 - lr: 0.000009 - momentum: 0.000000
79
+ 2023-10-14 19:34:58,728 epoch 1 - iter 720/1809 - loss 0.60884730 - time (sec): 45.06 - samples/sec: 3383.44 - lr: 0.000012 - momentum: 0.000000
80
+ 2023-10-14 19:35:09,821 epoch 1 - iter 900/1809 - loss 0.51478582 - time (sec): 56.15 - samples/sec: 3381.75 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-14 19:35:20,824 epoch 1 - iter 1080/1809 - loss 0.45038851 - time (sec): 67.16 - samples/sec: 3386.76 - lr: 0.000018 - momentum: 0.000000
82
+ 2023-10-14 19:35:31,910 epoch 1 - iter 1260/1809 - loss 0.40226510 - time (sec): 78.24 - samples/sec: 3377.71 - lr: 0.000021 - momentum: 0.000000
83
+ 2023-10-14 19:35:43,094 epoch 1 - iter 1440/1809 - loss 0.36377365 - time (sec): 89.43 - samples/sec: 3397.83 - lr: 0.000024 - momentum: 0.000000
84
+ 2023-10-14 19:35:54,127 epoch 1 - iter 1620/1809 - loss 0.33618725 - time (sec): 100.46 - samples/sec: 3394.46 - lr: 0.000027 - momentum: 0.000000
85
+ 2023-10-14 19:36:05,245 epoch 1 - iter 1800/1809 - loss 0.31254600 - time (sec): 111.58 - samples/sec: 3390.41 - lr: 0.000030 - momentum: 0.000000
86
+ 2023-10-14 19:36:05,747 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-14 19:36:05,748 EPOCH 1 done: loss 0.3115 - lr: 0.000030
88
+ 2023-10-14 19:36:11,319 DEV : loss 0.1074068620800972 - f1-score (micro avg) 0.6227
89
+ 2023-10-14 19:36:11,359 saving best model
90
+ 2023-10-14 19:36:11,761 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-14 19:36:23,545 epoch 2 - iter 180/1809 - loss 0.08399045 - time (sec): 11.78 - samples/sec: 3227.45 - lr: 0.000030 - momentum: 0.000000
92
+ 2023-10-14 19:36:35,128 epoch 2 - iter 360/1809 - loss 0.08189791 - time (sec): 23.37 - samples/sec: 3255.60 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-14 19:36:46,819 epoch 2 - iter 540/1809 - loss 0.08429012 - time (sec): 35.06 - samples/sec: 3269.66 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-14 19:36:57,832 epoch 2 - iter 720/1809 - loss 0.08515928 - time (sec): 46.07 - samples/sec: 3290.94 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-14 19:37:08,723 epoch 2 - iter 900/1809 - loss 0.08559861 - time (sec): 56.96 - samples/sec: 3309.87 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-14 19:37:20,230 epoch 2 - iter 1080/1809 - loss 0.08401278 - time (sec): 68.47 - samples/sec: 3319.10 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-14 19:37:31,469 epoch 2 - iter 1260/1809 - loss 0.08491285 - time (sec): 79.71 - samples/sec: 3330.62 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-14 19:37:42,280 epoch 2 - iter 1440/1809 - loss 0.08263217 - time (sec): 90.52 - samples/sec: 3343.72 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-14 19:37:53,300 epoch 2 - iter 1620/1809 - loss 0.08200069 - time (sec): 101.54 - samples/sec: 3356.23 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-14 19:38:04,107 epoch 2 - iter 1800/1809 - loss 0.08208246 - time (sec): 112.34 - samples/sec: 3365.44 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-14 19:38:04,597 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-14 19:38:04,597 EPOCH 2 done: loss 0.0822 - lr: 0.000027
103
+ 2023-10-14 19:38:10,890 DEV : loss 0.10114093124866486 - f1-score (micro avg) 0.6484
104
+ 2023-10-14 19:38:10,920 saving best model
105
+ 2023-10-14 19:38:11,500 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-14 19:38:22,010 epoch 3 - iter 180/1809 - loss 0.05838759 - time (sec): 10.51 - samples/sec: 3366.01 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-14 19:38:33,197 epoch 3 - iter 360/1809 - loss 0.05874179 - time (sec): 21.70 - samples/sec: 3385.52 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-14 19:38:44,444 epoch 3 - iter 540/1809 - loss 0.05854957 - time (sec): 32.94 - samples/sec: 3374.75 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-14 19:38:55,688 epoch 3 - iter 720/1809 - loss 0.05766306 - time (sec): 44.19 - samples/sec: 3401.61 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-14 19:39:06,774 epoch 3 - iter 900/1809 - loss 0.05644867 - time (sec): 55.27 - samples/sec: 3397.78 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-14 19:39:18,191 epoch 3 - iter 1080/1809 - loss 0.05882154 - time (sec): 66.69 - samples/sec: 3399.07 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-14 19:39:29,277 epoch 3 - iter 1260/1809 - loss 0.05771495 - time (sec): 77.78 - samples/sec: 3409.11 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-14 19:39:40,304 epoch 3 - iter 1440/1809 - loss 0.05784555 - time (sec): 88.80 - samples/sec: 3408.50 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-14 19:39:51,247 epoch 3 - iter 1620/1809 - loss 0.05830648 - time (sec): 99.75 - samples/sec: 3407.59 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-14 19:40:02,524 epoch 3 - iter 1800/1809 - loss 0.05809712 - time (sec): 111.02 - samples/sec: 3408.39 - lr: 0.000023 - momentum: 0.000000
116
+ 2023-10-14 19:40:03,015 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-14 19:40:03,016 EPOCH 3 done: loss 0.0580 - lr: 0.000023
118
+ 2023-10-14 19:40:09,518 DEV : loss 0.1736098974943161 - f1-score (micro avg) 0.6375
119
+ 2023-10-14 19:40:09,550 ----------------------------------------------------------------------------------------------------
120
+ 2023-10-14 19:40:20,934 epoch 4 - iter 180/1809 - loss 0.03691108 - time (sec): 11.38 - samples/sec: 3440.28 - lr: 0.000023 - momentum: 0.000000
121
+ 2023-10-14 19:40:31,862 epoch 4 - iter 360/1809 - loss 0.04056818 - time (sec): 22.31 - samples/sec: 3422.32 - lr: 0.000023 - momentum: 0.000000
122
+ 2023-10-14 19:40:42,991 epoch 4 - iter 540/1809 - loss 0.03990955 - time (sec): 33.44 - samples/sec: 3403.48 - lr: 0.000022 - momentum: 0.000000
123
+ 2023-10-14 19:40:53,744 epoch 4 - iter 720/1809 - loss 0.03930742 - time (sec): 44.19 - samples/sec: 3401.04 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-14 19:41:04,742 epoch 4 - iter 900/1809 - loss 0.03878415 - time (sec): 55.19 - samples/sec: 3419.03 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-14 19:41:15,576 epoch 4 - iter 1080/1809 - loss 0.03901667 - time (sec): 66.02 - samples/sec: 3423.98 - lr: 0.000021 - momentum: 0.000000
126
+ 2023-10-14 19:41:26,903 epoch 4 - iter 1260/1809 - loss 0.03923070 - time (sec): 77.35 - samples/sec: 3417.32 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-14 19:41:37,923 epoch 4 - iter 1440/1809 - loss 0.03883106 - time (sec): 88.37 - samples/sec: 3425.27 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-14 19:41:48,896 epoch 4 - iter 1620/1809 - loss 0.03987697 - time (sec): 99.34 - samples/sec: 3426.90 - lr: 0.000020 - momentum: 0.000000
129
+ 2023-10-14 19:42:00,001 epoch 4 - iter 1800/1809 - loss 0.03999749 - time (sec): 110.45 - samples/sec: 3422.64 - lr: 0.000020 - momentum: 0.000000
130
+ 2023-10-14 19:42:00,575 ----------------------------------------------------------------------------------------------------
131
+ 2023-10-14 19:42:00,575 EPOCH 4 done: loss 0.0399 - lr: 0.000020
132
+ 2023-10-14 19:42:06,152 DEV : loss 0.23925307393074036 - f1-score (micro avg) 0.6519
133
+ 2023-10-14 19:42:06,183 saving best model
134
+ 2023-10-14 19:42:06,655 ----------------------------------------------------------------------------------------------------
135
+ 2023-10-14 19:42:18,792 epoch 5 - iter 180/1809 - loss 0.02627690 - time (sec): 12.13 - samples/sec: 3239.69 - lr: 0.000020 - momentum: 0.000000
136
+ 2023-10-14 19:42:29,688 epoch 5 - iter 360/1809 - loss 0.02735443 - time (sec): 23.03 - samples/sec: 3336.57 - lr: 0.000019 - momentum: 0.000000
137
+ 2023-10-14 19:42:40,686 epoch 5 - iter 540/1809 - loss 0.02869184 - time (sec): 34.03 - samples/sec: 3376.77 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-14 19:42:51,517 epoch 5 - iter 720/1809 - loss 0.02921413 - time (sec): 44.86 - samples/sec: 3377.93 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-14 19:43:02,583 epoch 5 - iter 900/1809 - loss 0.02806718 - time (sec): 55.92 - samples/sec: 3405.91 - lr: 0.000018 - momentum: 0.000000
140
+ 2023-10-14 19:43:13,617 epoch 5 - iter 1080/1809 - loss 0.02805195 - time (sec): 66.96 - samples/sec: 3418.51 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-14 19:43:24,754 epoch 5 - iter 1260/1809 - loss 0.02890258 - time (sec): 78.09 - samples/sec: 3420.80 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-14 19:43:35,724 epoch 5 - iter 1440/1809 - loss 0.02875453 - time (sec): 89.06 - samples/sec: 3414.02 - lr: 0.000017 - momentum: 0.000000
143
+ 2023-10-14 19:43:46,503 epoch 5 - iter 1620/1809 - loss 0.02827331 - time (sec): 99.84 - samples/sec: 3424.55 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-14 19:43:57,328 epoch 5 - iter 1800/1809 - loss 0.02888219 - time (sec): 110.67 - samples/sec: 3418.00 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-14 19:43:57,818 ----------------------------------------------------------------------------------------------------
146
+ 2023-10-14 19:43:57,818 EPOCH 5 done: loss 0.0288 - lr: 0.000017
147
+ 2023-10-14 19:44:03,397 DEV : loss 0.3241709768772125 - f1-score (micro avg) 0.6413
148
+ 2023-10-14 19:44:03,430 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-14 19:44:14,543 epoch 6 - iter 180/1809 - loss 0.01726600 - time (sec): 11.11 - samples/sec: 3401.18 - lr: 0.000016 - momentum: 0.000000
150
+ 2023-10-14 19:44:25,391 epoch 6 - iter 360/1809 - loss 0.02130409 - time (sec): 21.96 - samples/sec: 3418.16 - lr: 0.000016 - momentum: 0.000000
151
+ 2023-10-14 19:44:36,249 epoch 6 - iter 540/1809 - loss 0.01945479 - time (sec): 32.82 - samples/sec: 3401.46 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-14 19:44:47,162 epoch 6 - iter 720/1809 - loss 0.01798882 - time (sec): 43.73 - samples/sec: 3412.71 - lr: 0.000015 - momentum: 0.000000
153
+ 2023-10-14 19:44:58,270 epoch 6 - iter 900/1809 - loss 0.01805154 - time (sec): 54.84 - samples/sec: 3425.09 - lr: 0.000015 - momentum: 0.000000
154
+ 2023-10-14 19:45:10,066 epoch 6 - iter 1080/1809 - loss 0.01928162 - time (sec): 66.64 - samples/sec: 3389.98 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-14 19:45:21,094 epoch 6 - iter 1260/1809 - loss 0.01948046 - time (sec): 77.66 - samples/sec: 3392.34 - lr: 0.000014 - momentum: 0.000000
156
+ 2023-10-14 19:45:32,425 epoch 6 - iter 1440/1809 - loss 0.01954946 - time (sec): 88.99 - samples/sec: 3404.88 - lr: 0.000014 - momentum: 0.000000
157
+ 2023-10-14 19:45:43,426 epoch 6 - iter 1620/1809 - loss 0.01979056 - time (sec): 100.00 - samples/sec: 3398.79 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-14 19:45:54,379 epoch 6 - iter 1800/1809 - loss 0.01952738 - time (sec): 110.95 - samples/sec: 3408.26 - lr: 0.000013 - momentum: 0.000000
159
+ 2023-10-14 19:45:54,891 ----------------------------------------------------------------------------------------------------
160
+ 2023-10-14 19:45:54,891 EPOCH 6 done: loss 0.0195 - lr: 0.000013
161
+ 2023-10-14 19:46:00,459 DEV : loss 0.32730063796043396 - f1-score (micro avg) 0.6469
162
+ 2023-10-14 19:46:00,489 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-14 19:46:11,510 epoch 7 - iter 180/1809 - loss 0.01375259 - time (sec): 11.02 - samples/sec: 3507.41 - lr: 0.000013 - momentum: 0.000000
164
+ 2023-10-14 19:46:22,844 epoch 7 - iter 360/1809 - loss 0.01337537 - time (sec): 22.35 - samples/sec: 3435.97 - lr: 0.000013 - momentum: 0.000000
165
+ 2023-10-14 19:46:33,788 epoch 7 - iter 540/1809 - loss 0.01292578 - time (sec): 33.30 - samples/sec: 3437.99 - lr: 0.000012 - momentum: 0.000000
166
+ 2023-10-14 19:46:44,656 epoch 7 - iter 720/1809 - loss 0.01256781 - time (sec): 44.17 - samples/sec: 3454.85 - lr: 0.000012 - momentum: 0.000000
167
+ 2023-10-14 19:46:55,743 epoch 7 - iter 900/1809 - loss 0.01292955 - time (sec): 55.25 - samples/sec: 3441.61 - lr: 0.000012 - momentum: 0.000000
168
+ 2023-10-14 19:47:06,590 epoch 7 - iter 1080/1809 - loss 0.01366189 - time (sec): 66.10 - samples/sec: 3444.85 - lr: 0.000011 - momentum: 0.000000
169
+ 2023-10-14 19:47:17,485 epoch 7 - iter 1260/1809 - loss 0.01294217 - time (sec): 76.99 - samples/sec: 3446.87 - lr: 0.000011 - momentum: 0.000000
170
+ 2023-10-14 19:47:28,684 epoch 7 - iter 1440/1809 - loss 0.01355941 - time (sec): 88.19 - samples/sec: 3438.84 - lr: 0.000011 - momentum: 0.000000
171
+ 2023-10-14 19:47:39,588 epoch 7 - iter 1620/1809 - loss 0.01404239 - time (sec): 99.10 - samples/sec: 3436.68 - lr: 0.000010 - momentum: 0.000000
172
+ 2023-10-14 19:47:50,401 epoch 7 - iter 1800/1809 - loss 0.01415717 - time (sec): 109.91 - samples/sec: 3440.60 - lr: 0.000010 - momentum: 0.000000
173
+ 2023-10-14 19:47:50,880 ----------------------------------------------------------------------------------------------------
174
+ 2023-10-14 19:47:50,881 EPOCH 7 done: loss 0.0142 - lr: 0.000010
175
+ 2023-10-14 19:47:57,159 DEV : loss 0.34697893261909485 - f1-score (micro avg) 0.6535
176
+ 2023-10-14 19:47:57,189 saving best model
177
+ 2023-10-14 19:47:57,664 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-14 19:48:08,704 epoch 8 - iter 180/1809 - loss 0.00926758 - time (sec): 11.04 - samples/sec: 3339.97 - lr: 0.000010 - momentum: 0.000000
179
+ 2023-10-14 19:48:19,824 epoch 8 - iter 360/1809 - loss 0.01045925 - time (sec): 22.16 - samples/sec: 3378.57 - lr: 0.000009 - momentum: 0.000000
180
+ 2023-10-14 19:48:30,922 epoch 8 - iter 540/1809 - loss 0.01079154 - time (sec): 33.25 - samples/sec: 3412.90 - lr: 0.000009 - momentum: 0.000000
181
+ 2023-10-14 19:48:42,001 epoch 8 - iter 720/1809 - loss 0.01092862 - time (sec): 44.33 - samples/sec: 3412.23 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-14 19:48:52,717 epoch 8 - iter 900/1809 - loss 0.01101834 - time (sec): 55.05 - samples/sec: 3423.63 - lr: 0.000008 - momentum: 0.000000
183
+ 2023-10-14 19:49:03,432 epoch 8 - iter 1080/1809 - loss 0.01138095 - time (sec): 65.76 - samples/sec: 3406.13 - lr: 0.000008 - momentum: 0.000000
184
+ 2023-10-14 19:49:14,961 epoch 8 - iter 1260/1809 - loss 0.01254336 - time (sec): 77.29 - samples/sec: 3406.95 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-14 19:49:25,998 epoch 8 - iter 1440/1809 - loss 0.01162416 - time (sec): 88.33 - samples/sec: 3404.01 - lr: 0.000007 - momentum: 0.000000
186
+ 2023-10-14 19:49:37,131 epoch 8 - iter 1620/1809 - loss 0.01113848 - time (sec): 99.46 - samples/sec: 3411.17 - lr: 0.000007 - momentum: 0.000000
187
+ 2023-10-14 19:49:48,424 epoch 8 - iter 1800/1809 - loss 0.01102466 - time (sec): 110.76 - samples/sec: 3410.53 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-14 19:49:49,050 ----------------------------------------------------------------------------------------------------
189
+ 2023-10-14 19:49:49,050 EPOCH 8 done: loss 0.0110 - lr: 0.000007
190
+ 2023-10-14 19:49:55,515 DEV : loss 0.3827722668647766 - f1-score (micro avg) 0.6585
191
+ 2023-10-14 19:49:55,558 saving best model
192
+ 2023-10-14 19:49:56,097 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-14 19:50:08,129 epoch 9 - iter 180/1809 - loss 0.00799016 - time (sec): 12.03 - samples/sec: 3140.21 - lr: 0.000006 - momentum: 0.000000
194
+ 2023-10-14 19:50:19,453 epoch 9 - iter 360/1809 - loss 0.00806244 - time (sec): 23.35 - samples/sec: 3293.32 - lr: 0.000006 - momentum: 0.000000
195
+ 2023-10-14 19:50:30,505 epoch 9 - iter 540/1809 - loss 0.00701912 - time (sec): 34.41 - samples/sec: 3346.83 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-14 19:50:41,490 epoch 9 - iter 720/1809 - loss 0.00725727 - time (sec): 45.39 - samples/sec: 3343.45 - lr: 0.000005 - momentum: 0.000000
197
+ 2023-10-14 19:50:52,341 epoch 9 - iter 900/1809 - loss 0.00639063 - time (sec): 56.24 - samples/sec: 3362.52 - lr: 0.000005 - momentum: 0.000000
198
+ 2023-10-14 19:51:03,204 epoch 9 - iter 1080/1809 - loss 0.00665483 - time (sec): 67.11 - samples/sec: 3375.42 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-14 19:51:14,164 epoch 9 - iter 1260/1809 - loss 0.00668153 - time (sec): 78.06 - samples/sec: 3373.14 - lr: 0.000004 - momentum: 0.000000
200
+ 2023-10-14 19:51:25,278 epoch 9 - iter 1440/1809 - loss 0.00657144 - time (sec): 89.18 - samples/sec: 3373.75 - lr: 0.000004 - momentum: 0.000000
201
+ 2023-10-14 19:51:36,498 epoch 9 - iter 1620/1809 - loss 0.00673205 - time (sec): 100.40 - samples/sec: 3381.01 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-14 19:51:47,624 epoch 9 - iter 1800/1809 - loss 0.00652186 - time (sec): 111.52 - samples/sec: 3393.26 - lr: 0.000003 - momentum: 0.000000
203
+ 2023-10-14 19:51:48,165 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-14 19:51:48,166 EPOCH 9 done: loss 0.0065 - lr: 0.000003
205
+ 2023-10-14 19:51:54,459 DEV : loss 0.40861621499061584 - f1-score (micro avg) 0.6496
206
+ 2023-10-14 19:51:54,491 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-14 19:52:05,476 epoch 10 - iter 180/1809 - loss 0.00347599 - time (sec): 10.98 - samples/sec: 3484.27 - lr: 0.000003 - momentum: 0.000000
208
+ 2023-10-14 19:52:16,545 epoch 10 - iter 360/1809 - loss 0.00318849 - time (sec): 22.05 - samples/sec: 3488.76 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-14 19:52:27,552 epoch 10 - iter 540/1809 - loss 0.00415644 - time (sec): 33.06 - samples/sec: 3444.26 - lr: 0.000002 - momentum: 0.000000
210
+ 2023-10-14 19:52:38,746 epoch 10 - iter 720/1809 - loss 0.00401066 - time (sec): 44.25 - samples/sec: 3429.51 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-14 19:52:50,230 epoch 10 - iter 900/1809 - loss 0.00421623 - time (sec): 55.74 - samples/sec: 3410.38 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-14 19:53:01,536 epoch 10 - iter 1080/1809 - loss 0.00490989 - time (sec): 67.04 - samples/sec: 3402.50 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-14 19:53:12,373 epoch 10 - iter 1260/1809 - loss 0.00503163 - time (sec): 77.88 - samples/sec: 3395.85 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-14 19:53:23,229 epoch 10 - iter 1440/1809 - loss 0.00494148 - time (sec): 88.74 - samples/sec: 3381.82 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-14 19:53:34,347 epoch 10 - iter 1620/1809 - loss 0.00474586 - time (sec): 99.86 - samples/sec: 3392.70 - lr: 0.000000 - momentum: 0.000000
216
+ 2023-10-14 19:53:45,922 epoch 10 - iter 1800/1809 - loss 0.00460738 - time (sec): 111.43 - samples/sec: 3394.00 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-14 19:53:46,432 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-14 19:53:46,432 EPOCH 10 done: loss 0.0046 - lr: 0.000000
219
+ 2023-10-14 19:53:52,077 DEV : loss 0.40256527066230774 - f1-score (micro avg) 0.6524
220
+ 2023-10-14 19:53:52,610 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-14 19:53:52,611 Loading model from best epoch ...
222
+ 2023-10-14 19:53:55,979 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
223
+ 2023-10-14 19:54:03,479
224
+ Results:
225
+ - F-score (micro) 0.6649
226
+ - F-score (macro) 0.5416
227
+ - Accuracy 0.5127
228
+
229
+ By class:
230
+ precision recall f1-score support
231
+
232
+ loc 0.6498 0.8037 0.7186 591
233
+ pers 0.5723 0.7647 0.6547 357
234
+ org 0.2639 0.2405 0.2517 79
235
+
236
+ micro avg 0.5992 0.7468 0.6649 1027
237
+ macro avg 0.4953 0.6030 0.5416 1027
238
+ weighted avg 0.5932 0.7468 0.6605 1027
239
+
240
+ 2023-10-14 19:54:03,479 ----------------------------------------------------------------------------------------------------