mirror of
https://github.com/wassname/multifit.git
synced 2026-09-10 12:12:50 +08:00
QRNN mldoc results for de, en and es
This commit is contained in:
Marcin
@@ -20,3 +20,67 @@ epoch train_loss valid_loss accuracy
|
||||
9 2.405682 2.448580 0.558674
|
||||
10 2.339395 2.428111 0.562502
|
||||
```
|
||||
|
||||
### MLDocs
|
||||
```
|
||||
python -m ulmfit cls --dataset-path data/mldoc/de-1 --cuda-id=0 --base-lm-path data-filtered/data/wiki/de-100/models/sp30k/qrnn_nl4.m --lang=de --name 'nl4' - train 20 --bs 40 --cls-max-len 700
|
||||
|
||||
Max vocab: 30000
|
||||
Cache dir: /home/marcin/github/n-waves/ulmfit-multilingual/data/mldoc/de-1/models/sp30k
|
||||
Model dir: /home/marcin/github/n-waves/ulmfit-multilingual/data/mldoc/de-1/models/sp30k/qrnn_nl4.m
|
||||
Loading validation /home/marcin/github/n-waves/ulmfit-multilingual/data/mldoc/de-1/de.dev.csv
|
||||
Running tokenization...
|
||||
Saving tokenized: cls.trn 13500, cls.val 1500
|
||||
Running tokenization...
|
||||
Saving tokenized: cls.trn 1000, cls.val 1000
|
||||
Size of vocabulary: 30000
|
||||
First 20 words in vocab: ['xxunk', 'xxpad', 'xxbos', 'xxfld', 'xxmaj', 'xxup', 'xxrep', 'xxwrep', '<unk>', '▁', '▁.', '▁,', '▁der', '▁die', '▁und', '▁in', "▁&'", 'en', 's', '-']
|
||||
Training args: {'clip': 0.12, 'alpha': 2, 'beta': 1, 'drop_mult': 0.3} dps: {'output_p': 0.25, 'hidden_p': 0.1, 'input_p': 0.2, 'embed_p': 0.02, 'weight_p': 0.15}
|
||||
Loading pretrained model
|
||||
Unknown tokens 0, first 100: []
|
||||
Training lm from: [PosixPath('/home/marcin/github/n-waves/ulmfit-multilingual/data-filtered/data/wiki/de-100/models/sp30k/qrnn_nl4.m/lm_best'), PosixPath('/home/marcin/github/n-waves/ulmfit-multilingual/data-filtered/data/wiki/de-100/models/sp30k/qrnn_nl4.m/../itos')]
|
||||
epoch train_loss valid_loss accuracy
|
||||
1 3.450698 2.601732 0.527671
|
||||
epoch train_loss valid_loss accuracy
|
||||
1 2.888087 2.477170 0.542949
|
||||
2 2.621279 2.300024 0.568743
|
||||
3 2.313220 2.120824 0.592728
|
||||
4 2.176746 1.973596 0.613343
|
||||
5 2.114441 1.857317 0.628628
|
||||
6 2.022593 1.765069 0.642017
|
||||
7 1.936942 1.696150 0.651549
|
||||
8 1.860200 1.622848 0.661923
|
||||
9 1.795039 1.549579 0.673416
|
||||
10 1.740739 1.500053 0.681305
|
||||
11 1.695835 1.448141 0.689201
|
||||
12 1.605702 1.402924 0.697096
|
||||
13 1.582328 1.354327 0.706123
|
||||
14 1.548034 1.316290 0.712870
|
||||
15 1.496170 1.282155 0.719413
|
||||
16 1.514243 1.255556 0.724801
|
||||
17 1.482411 1.236461 0.728380
|
||||
18 1.458308 1.223498 0.730708
|
||||
19 1.422691 1.218288 0.731713
|
||||
20 1.380592 1.217068 0.731893
|
||||
/home/marcin/github/n-waves/ulmfit-multilingual/data/mldoc/de-1/models/sp30k
|
||||
Saving info /home/marcin/github/n-waves/ulmfit-multilingual/data/mldoc/de-1/models/sp30k/qrnn_nl4.m/info.json
|
||||
Starting classifier training
|
||||
epoch train_loss valid_loss accuracy
|
||||
1 0.529402 0.376163 0.900000
|
||||
Better model found at epoch 1 with val_loss value: 0.3761630356311798.
|
||||
epoch train_loss valid_loss accuracy
|
||||
1 0.290838 0.252989 0.916000
|
||||
Better model found at epoch 1 with val_loss value: 0.25298893451690674.
|
||||
epoch train_loss valid_loss accuracy
|
||||
1 0.184352 0.204892 0.941000
|
||||
Better model found at epoch 1 with val_loss value: 0.20489171147346497.
|
||||
epoch train_loss valid_loss accuracy
|
||||
1 0.113328 0.204136 0.947000
|
||||
Better model found at epoch 1 with val_loss value: 0.20413607358932495.
|
||||
2 0.106220 0.200674 0.949000
|
||||
Better model found at epoch 2 with val_loss value: 0.20067360997200012.
|
||||
Saving models at /home/marcin/github/n-waves/ulmfit-multilingual/data/mldoc/de-1/models/sp30k/qrnn_nl4.m
|
||||
Loss and accuracy using (cls_best): [0.15208693, tensor(0.9532)]
|
||||
0.15208692848682404
|
||||
0.953249990940094
|
||||
```
|
||||
|
||||
@@ -42,3 +42,67 @@ epoch train_loss valid_loss accuracy
|
||||
9 2.933140 2.733279 0.488346
|
||||
10 2.964397 2.720861 0.490423
|
||||
```
|
||||
|
||||
### MLDocs
|
||||
```
|
||||
python -m ulmfit cls --dataset-path data/mldoc/en-1 --cuda-id=0 --base-lm-path data-filtered/data/wiki/wikitext-103/models/sp30k/qrnn_nl4.m --lang=en --name 'nl4' - train 20 --bs 40 --cls-max-len 700
|
||||
|
||||
Max vocab: 30000
|
||||
Cache dir: /home/marcin/github/n-waves/ulmfit-multilingual/data/mldoc/en-1/models/sp30k
|
||||
Model dir: /home/marcin/github/n-waves/ulmfit-multilingual/data/mldoc/en-1/models/sp30k/qrnn_nl4.m
|
||||
Loading validation /home/marcin/github/n-waves/ulmfit-multilingual/data/mldoc/en-1/en.dev.csv
|
||||
Running tokenization...
|
||||
Saving tokenized: cls.trn 13500, cls.val 1500
|
||||
Running tokenization...
|
||||
Saving tokenized: cls.trn 1000, cls.val 1000
|
||||
Size of vocabulary: 30000
|
||||
First 20 words in vocab: ['xxunk', 'xxpad', 'xxbos', 'xxfld', 'xxmaj', 'xxup', 'xxrep', 'xxwrep', '<unk>', '▁', '▁the', '▁,', '▁.', 's', '▁of', '▁and', '▁in', '▁to', '▁a', 'ed']
|
||||
Training args: {'clip': 0.12, 'alpha': 2, 'beta': 1, 'drop_mult': 0.3} dps: {'output_p': 0.25, 'hidden_p': 0.1, 'input_p': 0.2, 'embed_p': 0.02, 'weight_p': 0.15}
|
||||
Loading pretrained model
|
||||
Unknown tokens 0, first 100: []
|
||||
Training lm from: [PosixPath('/home/marcin/github/n-waves/ulmfit-multilingual/data-filtered/data/wiki/wikitext-103/models/sp30k/qrnn_nl4.m/lm_best'), PosixPath('/home/marcin/github/n-waves/ulmfit-multilingual/data-filtered/data/wiki/wikitext-103/models/sp30k/qrnn_nl4.m/.
|
||||
./itos')]
|
||||
epoch train_loss valid_loss accuracy
|
||||
1 4.459886 3.692770 0.364677
|
||||
epoch train_loss valid_loss accuracy
|
||||
1 3.962907 3.560222 0.379027
|
||||
2 3.673292 3.378484 0.402066
|
||||
3 3.460093 3.191662 0.424295
|
||||
4 3.296515 3.030681 0.442995
|
||||
5 3.161650 2.891829 0.459052
|
||||
6 3.022674 2.776469 0.473280
|
||||
7 2.974365 2.686321 0.484403
|
||||
8 2.869587 2.593854 0.496297
|
||||
9 2.785321 2.509093 0.506853
|
||||
10 2.677728 2.440328 0.516178
|
||||
11 2.641243 2.371950 0.525810
|
||||
12 2.652385 2.320008 0.533105
|
||||
13 2.547195 2.261057 0.542046
|
||||
14 2.491570 2.216933 0.548810
|
||||
15 2.454437 2.179364 0.555077
|
||||
16 2.414449 2.147612 0.559972
|
||||
17 2.358593 2.125351 0.563405
|
||||
18 2.362696 2.111580 0.565614
|
||||
19 2.341626 2.104268 0.566749
|
||||
20 2.342680 2.102918 0.566966
|
||||
/home/marcin/github/n-waves/ulmfit-multilingual/data/mldoc/en-1/models/sp30k
|
||||
Saving info /home/marcin/github/n-waves/ulmfit-multilingual/data/mldoc/en-1/models/sp30k/qrnn_nl4.m/info.json
|
||||
Starting classifier training
|
||||
epoch train_loss valid_loss accuracy
|
||||
1 0.622379 0.422002 0.882000
|
||||
Better model found at epoch 1 with val_loss value: 0.42200201749801636.
|
||||
epoch train_loss valid_loss accuracy
|
||||
1 0.313018 0.275563 0.908000
|
||||
Better model found at epoch 1 with val_loss value: 0.27556276321411133.
|
||||
epoch train_loss valid_loss accuracy
|
||||
1 0.241521 0.174606 0.933000
|
||||
Better model found at epoch 1 with val_loss value: 0.1746061146259308.
|
||||
epoch train_loss valid_loss accuracy
|
||||
1 0.125556 0.170286 0.940000
|
||||
Better model found at epoch 1 with val_loss value: 0.17028628289699554.
|
||||
2 0.107322 0.181366 0.939000
|
||||
Saving models at /home/marcin/github/n-waves/ulmfit-multilingual/data/mldoc/en-1/models/sp30k/qrnn_nl4.m
|
||||
Loss and accuracy using (cls_best): [0.18917121, tensor(0.9388)]
|
||||
0.1891712099313736
|
||||
0.9387500286102295
|
||||
```
|
||||
|
||||
@@ -23,3 +23,66 @@ epoch train_loss valid_loss accuracy
|
||||
9 2.635299 3.166430 0.410160
|
||||
10 2.656724 3.145599 0.413176
|
||||
```
|
||||
|
||||
### MLDocs
|
||||
```
|
||||
python -m ulmfit cls --dataset-path data/mldoc/es-1 --cuda-id=0 --base-lm-path data-filtered/data/wiki/es-100/models/sp30k/qrnn_nl4.m --lang=es --name 'nl4' - train 20 --bs 40 --cls-max-len 700
|
||||
|
||||
Max vocab: 30000
|
||||
Cache dir: /home/marcin/github/n-waves/ulmfit-multilingual/data/mldoc/es-1/models/sp30k
|
||||
Model dir: /home/marcin/github/n-waves/ulmfit-multilingual/data/mldoc/es-1/models/sp30k/qrnn_nl4.m
|
||||
Loading validation /home/marcin/github/n-waves/ulmfit-multilingual/data/mldoc/es-1/es.dev.csv
|
||||
Running tokenization...
|
||||
Saving tokenized: cls.trn 13013, cls.val 1445
|
||||
Running tokenization...
|
||||
Saving tokenized: cls.trn 1000, cls.val 1000
|
||||
Size of vocabulary: 30000
|
||||
First 20 words in vocab: ['xxunk', 'xxpad', 'xxbos', 'xxfld', 'xxmaj', 'xxup', 'xxrep', 'xxwrep', '<unk>', '▁', '▁de', '▁,', '▁.', '▁la', '▁el', '▁en', '▁y', 's', '▁a', "▁&'"]
|
||||
Training args: {'clip': 0.12, 'alpha': 2, 'beta': 1, 'drop_mult': 0.3} dps: {'output_p': 0.25, 'hidden_p': 0.1, 'input_p': 0.2, 'embed_p': 0.02, 'weight_p': 0.15}
|
||||
Loading pretrained model
|
||||
Unknown tokens 0, first 100: []
|
||||
Training lm from: [PosixPath('/home/marcin/github/n-waves/ulmfit-multilingual/data-filtered/data/wiki/es-100/models/sp30k/qrnn_nl4.m/lm_best'), PosixPath('/home/marcin/github/n-waves/ulmfit-multilingual/data-filtered/data/wiki/es-100/models/sp30k/qrnn_nl4.m/../itos')]
|
||||
epoch train_loss valid_loss accuracy
|
||||
1 3.352874 2.367255 0.514858
|
||||
epoch train_loss valid_loss accuracy
|
||||
1 2.796090 2.203233 0.536513
|
||||
2 2.515840 1.970145 0.576640
|
||||
3 2.198857 1.774013 0.610990
|
||||
4 2.035614 1.633484 0.633450
|
||||
5 1.944539 1.535505 0.649110
|
||||
6 1.848854 1.451618 0.661764
|
||||
7 1.788579 1.382675 0.673166
|
||||
8 1.675414 1.320675 0.683617
|
||||
9 1.614536 1.264944 0.694086
|
||||
10 1.618723 1.215493 0.702936
|
||||
11 1.504875 1.164356 0.712921
|
||||
12 1.411316 1.126858 0.721374
|
||||
13 1.421174 1.079897 0.731196
|
||||
14 1.352116 1.044965 0.738148
|
||||
15 1.318876 1.013755 0.745312
|
||||
16 1.268569 0.986391 0.751383
|
||||
17 1.273424 0.971129 0.754643
|
||||
18 1.256196 0.960661 0.757439
|
||||
19 1.233202 0.955790 0.758405
|
||||
20 1.230536 0.955070 0.758496
|
||||
/home/marcin/github/n-waves/ulmfit-multilingual/data/mldoc/es-1/models/sp30k
|
||||
Saving info /home/marcin/github/n-waves/ulmfit-multilingual/data/mldoc/es-1/models/sp30k/qrnn_nl4.m/info.json
|
||||
Starting classifier training
|
||||
epoch train_loss valid_loss accuracy
|
||||
1 0.739119 0.438338 0.867000
|
||||
Better model found at epoch 1 with val_loss value: 0.438338041305542.
|
||||
epoch train_loss valid_loss accuracy
|
||||
1 0.425376 0.207067 0.950000
|
||||
Better model found at epoch 1 with val_loss value: 0.20706671476364136.
|
||||
epoch train_loss valid_loss accuracy
|
||||
1 0.311269 0.172416 0.956000
|
||||
Better model found at epoch 1 with val_loss value: 0.17241604626178741.
|
||||
epoch train_loss valid_loss accuracy
|
||||
1 0.226164 0.166543 0.958000
|
||||
Better model found at epoch 1 with val_loss value: 0.1665433794260025.
|
||||
2 0.199775 0.167683 0.956000
|
||||
Saving models at /home/marcin/github/n-waves/ulmfit-multilingual/data/mldoc/es-1/models/sp30k/qrnn_nl4.m
|
||||
Loss and accuracy using (cls_best): [0.18184493, tensor(0.9448)]
|
||||
0.18184493482112885
|
||||
0.9447500109672546
|
||||
```
|
||||
|
||||
Reference in New Issue
Block a user