diff --git a/results/logs/qrnn-de.md b/results/logs/qrnn-de.md new file mode 100644 index 0000000..9addcd1 --- /dev/null +++ b/results/logs/qrnn-de.md @@ -0,0 +1,22 @@ +# QRNN DE +## SP30k nl +### LM +``` +python -m ulmfit lm --dataset-path data/wiki/de-100 --bidir=False --qrnn=True --nl 4 --tokenizer='sp' --max-vocab 30000 --lang de --name 'nl4' --cuda-id=0 - train 10 --drop-mult=0 --bs=50 + +Size of vocabulary: 30000 +First 20 words in vocab: ['xxunk', 'xxpad', 'xxbos', 'xxfld', 'xxmaj', 'xxup', 'xxrep', 'xxwrep', '', '▁', '▁.', '▁,', '▁der', '▁die', '▁und', '▁in', "▁&'", 'en', 's', '-'] +Training args: {'clip': 0.12, 'alpha': 2, 'beta': 1, 'drop_mult': 0} dps: {'output_p': 0.25, 'hidden_p': 0.1, 'input_p': 0.2, 'embed_p': 0.02, 'weight_p': 0.15} +Training lm from random weights +epoch train_loss valid_loss accuracy +1 2.790653 2.867094 0.511392 +2 2.742032 2.843288 0.510885 +3 2.696114 2.833874 0.512062 +4 2.671780 2.786312 0.516448 +5 2.611292 2.725993 0.522723 +6 2.542737 2.655713 0.530968 +7 2.572076 2.582141 0.539928 +8 2.465960 2.509654 0.549987 +9 2.405682 2.448580 0.558674 +10 2.339395 2.428111 0.562502 +``` diff --git a/results/logs/qrnn-en.md b/results/logs/qrnn-en.md new file mode 100644 index 0000000..06d1247 --- /dev/null +++ b/results/logs/qrnn-en.md @@ -0,0 +1,44 @@ +# QRNN EN +## SP30k nl 4 +### LM + +``` +python -m ulmfit lm --dataset-path data/wiki/wikitext-103 --bidir=False --qrnn=True --nl 4 --tokenizer='sp' --max-vocab 30000 --lang en --name 'nl4' --cuda-id=1 - train 10 --drop-mult=0 --bs=50 + +Size of vocabulary: 30000 +First 20 words in vocab: ['xxunk', 'xxpad', 'xxbos', 'xxfld', 'xxmaj', 'xxup', 'xxrep', 'xxwrep', '', '▁', '▁the', '▁,', '▁.', 's', '▁of', '▁and', '▁in', '▁to', '▁a', 'ed'] +Training args: {'clip': 0.12, 'alpha': 2, 'beta': 1, 'drop_mult': 0.5} dps: {'output_p': 0.25, 'hidden_p': 0.1, 'input_p': 0.2, 'embed_p': 0.02, 'weight_p': 0.15} +Training lm from random weights +epoch train_loss valid_loss accuracy +1 3.184221 3.256314 0.438527 +2 3.084555 3.241498 0.435628 +3 3.099060 3.258447 0.435060 +4 3.119621 3.220939 0.437597 +5 3.073662 3.165012 0.445108 +6 2.938047 3.086962 0.452921 +7 2.920506 2.998151 0.462940 +8 2.920506 2.899240 0.474378 +9 2.862836 2.835098 0.485305 +10 2.891070 2.810929 0.489867 +``` + +### LM, BS=128, drop-mult=0.5 +``` +python -m ulmfit lm --dataset-path data/wiki/wikitext-103 --bidir=False --qrnn=True --nl 4 --tokenizer='sp' --max-vocab 30000 --lang en --name 'nl4-bs128' --cuda-id=1 - train 10 --drop-mult=0.5 --bs=128 + +Size of vocabulary: 30000 +First 20 words in vocab: ['xxunk', 'xxpad', 'xxbos', 'xxfld', 'xxmaj', 'xxup', 'xxrep', 'xxwrep', '', '▁', '▁the', '▁,', '▁.', 's', '▁of', '▁and', '▁in', '▁to', '▁a', 'ed'] +Training args: {'clip': 0.12, 'alpha': 2, 'beta': 1, 'drop_mult': 0.5} dps: {'output_p': 0.25, 'hidden_p': 0.1, 'input_p': 0.2, 'embed_p': 0.02, 'weight_p': 0.15} +Training lm from random weights +epoch train_loss valid_loss accuracy +1 3.413345 3.280860 0.433011 +2 3.219606 3.129479 0.444172 +3 3.136091 3.094905 0.448493 +4 3.145281 3.033001 0.452830 +5 3.100366 2.980189 0.458984 +6 3.062894 2.923044 0.464841 +7 3.001627 2.834753 0.475316 +8 2.979051 2.792044 0.480915 +9 2.933140 2.733279 0.488346 +10 2.964397 2.720861 0.490423 +``` diff --git a/results/logs/qrnn-es.md b/results/logs/qrnn-es.md new file mode 100644 index 0000000..c103458 --- /dev/null +++ b/results/logs/qrnn-es.md @@ -0,0 +1,25 @@ +# QRNN ES + +## SP30k nl 4 +### LM +``` +python -m ulmfit lm --dataset-path data/wiki/es-100 --bidir=False --qrnn=True --nl 4 --tokenizer='sp' --max-vocab 30000 --lang es --name 'nl4' --cuda-id=0 - train 10 --drop-mult=0 --bs=50 + +Wiki text was split to 161509 articles +Wiki text was split to 78 articles +Size of vocabulary: 30000 +First 20 words in vocab: ['xxunk', 'xxpad', 'xxbos', 'xxfld', 'xxmaj', 'xxup', 'xxrep', 'xxwrep', '', '▁', '▁de', '▁,', '▁.', '▁la', '▁el', '▁en', '▁y', 's', '▁a', "▁&'"] +Training args: {'clip': 0.12, 'drop_mult': 0} dps: {'output_p': 0.25, 'hidden_p': 0.1, 'input_p': 0.2, 'embed_p': 0.02, 'weight_p': 0.15} +Training lm from random weights +epoch train_loss valid_loss accuracy +1 3.067289 3.640350 0.357276 +2 2.958243 3.619773 0.358111 +3 3.033412 3.587700 0.359495 +4 2.933573 3.525202 0.367685 +5 2.904549 3.467990 0.372583 +6 2.798806 3.409506 0.380045 +7 2.733132 3.303108 0.391922 +8 2.675272 3.224150 0.401143 +9 2.635299 3.166430 0.410160 +10 2.656724 3.145599 0.413176 +``` diff --git a/results/logs/qrnn-ru.md b/results/logs/qrnn-ru.md new file mode 100644 index 0000000..36ae8d4 --- /dev/null +++ b/results/logs/qrnn-ru.md @@ -0,0 +1,24 @@ +# QRNN RU +## SP30k nl4 +### LM +``` +python -m ulmfit lm --dataset-path data/wiki/ru-100 --bidir=False --qrnn=True --nl 4 --tokenizer='sp' --max-vocab 30000 --lang ru --name 'nl4' --cuda-id=0 - train 10 --drop-mult=0 --bs=50 + +Wiki text was split to 193047 articles +Wiki text was split to 460 articles +Size of vocabulary: 30000 +First 20 words in vocab: ['xxunk', 'xxpad', 'xxbos', 'xxfld', 'xxmaj', 'xxup', 'xxrep', 'xxwrep', '', '▁', '▁,', '▁.', '▁в', 'а', '▁и', 'е', 'и', 'й', '▁на', '▁с'] +Training args: {'clip': 0.12, 'drop_mult': 0} dps: {'output_p': 0.25, 'hidden_p': 0.1, 'input_p': 0.2, 'embed_p': 0.02, 'weight_p': 0.15} +Training lm from random weights +epoch train_loss valid_loss accuracy +1 3.273207 3.350111 0.429702 +2 3.169897 3.274238 0.433682 +3 3.162197 3.247077 0.435900 +4 3.131630 3.168798 0.445252 +5 3.042942 3.096774 0.453532 +6 2.950550 3.002989 0.465113 +7 2.833593 2.902871 0.478954 +8 2.829737 2.805592 0.492138 +9 2.746991 2.733609 0.503711 +10 2.687201 2.708546 0.508050 +```