diff --git a/results/bilcls_qrnn-wt-103-wd0 b/results/bilcls_qrnn-wt-103-wd0 deleted file mode 100644 index 4f2a68f..0000000 --- a/results/bilcls_qrnn-wt-103-wd0 +++ /dev/null @@ -1,26 +0,0 @@ -pretraining -0 - 8 lost, about 0.30 0.32 after 5 epochs -8 3.744213 4.021358 0.308377 0.325672 -9 3.700674 4.021499 0.308637 0.325881 -10 3.674045 4.022058 0.308656 0.325903 ---- crash--- -$ python -m ulmfit.train_clas --data_dir data --model_dir data/wiki/wikitext-103/models --pretrain_name=bilm-wt-103 --qrnn=True --name 'concat-2x' --cuda-id=0 --bs 40 --train=True --bidir=True -Dataset: imdb. Language: en. -Using QRNNs... -BiLM -Loading the pickled data... -Train size: 22500. Valid size: 2500. Test size: 25000. -loading encoder -Starting classifier training -epoch train_loss valid_loss accuracy -1 0.346874 0.276838 0.881200 -epoch train_loss valid_loss accuracy -1 0.321121 0.243946 0.901200 -epoch train_loss valid_loss accuracy -1 0.303174 0.234627 0.908400 -epoch train_loss valid_loss accuracy -1 0.295207 0.227533 0.912800 -2 0.269754 0.221328 0.914400 -Saving models at data/wiki/wikitext-103/models -accuracy: tensor(0.9144) - diff --git a/results/bilm_qrnn-wt-103-unk-wd1 b/results/bilm_qrnn-wt-103-unk-wd1 deleted file mode 100644 index dc5c8ce..0000000 --- a/results/bilm_qrnn-wt-103-unk-wd1 +++ /dev/null @@ -1,20 +0,0 @@ -(fastaiv1) n-waves@GV100:~/workspace/ulmfit-multilingual$ python -m ulmfit.pretrain_lm data/wiki/wikitext-103-unk --qrnn=True --cuda-id=0 - --name=bilm-wt-103-unk --num_epochs=10 --bs=64 --bidir=True -Batch size: 64 -Max vocab: 60000 -Using QRNNs... -Loading itos: data/wiki/wikitext-103-unk/models/itos_bilm-wt-103-unk.pkl -Size of vocabulary: 60001 -First 10 words in vocab: the, , ,, ., of, and, to, in, , a -Starting from random weights -epoch train_loss valid_loss accuracy_fwd accuracy_bwd -1 4.184118 4.113817 0.308417 0.318290 -2 4.106002 4.039978 0.312220 0.320315 -3 4.160282 4.086650 0.306327 0.314152 -4 4.136789 4.049762 0.309202 0.317373 -5 4.086520 4.001534 0.313158 0.321543 -6 4.036415 3.960494 0.318333 0.325623 -7 3.988382 3.913568 0.324409 0.330398 -8 3.937409 3.874283 0.328386 0.334786 -9 3.912215 3.856325 0.330593 0.337102 -10 3.876535 3.848783 0.331202 0.337649 \ No newline at end of file diff --git a/results/bilm_qrnn-wt-103-wd0 b/results/bilm_qrnn-wt-103-wd0 deleted file mode 100644 index 291173e..0000000 --- a/results/bilm_qrnn-wt-103-wd0 +++ /dev/null @@ -1,20 +0,0 @@ -(fastaiv1) n-waves@GV100:~/workspace/ulmfit-multilingual$ python -m ulmfit.pretrain_lm -ki/wikitext-103 --qrnn=True --cuda-id=0 --name=bilm-wt-103 --num_epochs=10 --bs=64 --bidir=True -Batch size: 64 -Max vocab: 60000 -Using QRNNs... -Loading itos: data/wiki/wikitext-103/models/itos_bilm-wt-103.pkl -Size of vocabulary: 60001 -First 10 words in vocab: the, , ,, ., of, and, to, in, , a -Starting from random weights -epoch train_loss valid_loss accuracy_fwd accuracy_bwd -1 4.141750 4.114931 0.307700 0.320260 -2 4.078711 4.061186 0.310221 0.320550 -3 4.108722 4.081286 0.308383 0.316431 -4 4.054437 4.040497 0.311229 0.319658 -5 4.014880 3.966010 0.318588 0.327607 -6 3.926770 3.897305 0.326874 0.333171 -7 3.855364 3.816452 0.335632 0.342045 -8 3.761600 3.745798 0.343413 0.350675 - -10 3.614097 3.687730 0.351651 0.358280 \ No newline at end of file diff --git a/results/lm_lstm-wt-103-wd0 b/results/lm_lstm-wt-103-wd0 deleted file mode 100644 index 41c178f..0000000 --- a/results/lm_lstm-wt-103-wd0 +++ /dev/null @@ -1,22 +0,0 @@ -(fastaiv1) pczapla@galatea ~/w/ulmfit-multilingual ❯❯❯ time python -m ulmfit.pretrain_lm data/wiki/wikitext-103 --qrnn=False --cuda-id=1 --name=wt-103 --num_epochs=10 --bs=32 -Batch size: 32 -Max vocab: 60000 -Loading itos: data/wiki/wikitext-103/models/itos_wt-103.pkl -Size of vocabulary: 60001 -First 10 words in vocab: the, , ,, ., of, and, to, in, , a -Starting from random weights -epoch train_loss valid_loss accuracy -1 4.317837 4.245714 0.309034 -2 4.347099 4.251623 0.306932 -3 4.360198 4.302850 0.302014 -4 4.329998 4.264225 0.306828 -5 4.301852 4.209807 0.311763 -6 4.218213 4.131647 0.319867 -7 4.167365 4.047796 0.327259 -8 4.095695 3.980298 0.336255 -9 4.032371 3.919622 0.343671 -10 3.983160 3.906227 0.345863 -Saving models at data/wiki/wikitext-103/models -Saving optimiser state at data/wiki/wikitext-103/models/lstm3_wt-103_state.pth -accuracy: tensor(0.3461) -python -m ulmfit.pretrain_lm data/wiki/wikitext-103 --qrnn=False --cuda-id=1 44147.64s user 16746.69s system 99% cpu 16:58:47.57 total \ No newline at end of file diff --git a/results/lm_qrnn-wt-103-unk-wd0 b/results/lm_qrnn-wt-103-unk-wd0 deleted file mode 100644 index d009387..0000000 --- a/results/lm_qrnn-wt-103-unk-wd0 +++ /dev/null @@ -1,23 +0,0 @@ -time python -m ulmfit.pretrain_lm data/wiki/wikitext-103-unk --qrnn=True --cuda-id=0 --name=wt-103 --num_epochs=10 --bs=32 -Batch size: 32 -Max vocab: 60000 -Using QRNNs... -Loading itos: data/wiki/wikitext-103-unk/models/itos_wt-103.pkl -Size of vocabulary: 60001 -First 10 words in vocab: the, , ,, ., of, and, to, in, , a -Starting from random weights -epoch train_loss valid_loss accuracy -1 4.393613 4.282537 0.305135 -2 4.394575 4.299973 0.300028 -3 4.444056 4.336682 0.295496 -4 4.414292 4.332908 0.297408 -5 4.406248 4.269964 0.302962 -6 4.327769 4.209948 0.309025 -7 4.244819 4.140769 0.315675 -8 4.210000 4.075574 0.323544 -9 4.139524 4.034881 0.328550 -10 4.150556 4.021361 0.331256 -Saving models at data/wiki/wikitext-103-unk/models -Saving optimiser state at data/wiki/wikitext-103-unk/models/qrnn3_wt-103_state.pth -accuracy: tensor(0.3312) -python -m ulmfit.pretrain_lm data/wiki/wikitext-103-unk --qrnn=True --bs=3 32119.72s user 12439.18s system 99% cpu 12:25:03.65 total \ No newline at end of file diff --git a/results/lm_qrnn-wt-103-unk-wd1 b/results/lm_qrnn-wt-103-unk-wd1 deleted file mode 100644 index 0ee4a69..0000000 --- a/results/lm_qrnn-wt-103-unk-wd1 +++ /dev/null @@ -1,24 +0,0 @@ -ime python -m ulmfit.pretrain_lm data/wiki/wikitext-103-unk --qrnn=True --cuda-id=0 --name=wt-103-wd1 --num_epochs=10 --bs=32 -Batch size: 32 -Max vocab: 60000 -Using QRNNs... -Saving vocabulary as data/wiki/wikitext-103-unk/models -Size of vocabulary: 60001 -First 10 words in vocab: the, , ,, ., of, and, to, in, , a -true_wd: True -Starting from random weights -epoch train_loss valid_loss accuracy -1 4.355600 4.271729 0.306827 -2 4.384312 4.288582 0.299482 -3 4.527577 4.366407 0.289836 -4 4.519645 4.387311 0.288076 -5 4.514816 4.371242 0.289862 -6 4.506230 4.337718 0.294208 -7 4.444272 4.295349 0.298786 -8 4.432104 4.257432 0.301785 -9 4.416849 4.242803 0.304147 -10 4.389035 4.239752 0.304871 -Saving models at data/wiki/wikitext-103-unk/models -Saving optimiser state at data/wiki/wikitext-103-unk/models/qrnn3_wt-103-wd1_state.pth -itos_fname: data/wiki/wikitext-103-unk/models/itos_wt-103-wd1.pkl -accuracy: tensor(0.2829) \ No newline at end of file diff --git a/results/lm_qrnn-wt-103-wd0 b/results/lm_qrnn-wt-103-wd0 deleted file mode 100644 index 33d243b..0000000 --- a/results/lm_qrnn-wt-103-wd0 +++ /dev/null @@ -1,20 +0,0 @@ -time python -m ulmfit.pretrain_lm data/wiki/wikitext-103 --qrnn=True --cuda-id=1 --name=wt-103 --num_epochs=10 --bs=32 ✘ 1 -Batch size: 32 -Max vocab: 60000 -Using QRNNs... -Size of vocabulary: 60001 -First 10 words in vocab: the, , ,, ., of, and, to, in, , a -Saving vocabulary as data/wiki/wikitext-103/models -epoch train_loss valid_loss accuracy -1 4.328219 4.268609 0.306414 -2 4.351323 4.282290 0.300560 -3 4.376134 4.345460 0.294145 -4 4.394314 4.319661 0.298142 -5 4.337362 4.265630 0.303437 -6 4.295763 4.199119 0.309354 -7 4.165526 4.121037 0.318062 -8 4.151789 4.060387 0.325899 -9 4.066542 4.014568 0.332732 -10 4.013142 3.997691 0.335299 -Saving models at data/wiki/wikitext-103/models -Saving optimiser state at data/wiki/wikitext-103/models/qrnn3_wt-103_state.pth \ No newline at end of file diff --git a/results/sp30k_biqrnn_bs70 b/results/sp30k_biqrnn_bs70 deleted file mode 100644 index 5c658fd..0000000 --- a/results/sp30k_biqrnn_bs70 +++ /dev/null @@ -1,13 +0,0 @@ -Starting from random weights -epoch train_loss valid_loss accuracy_fwd accuracy_bwd -1 3.669261 3.641705 0.399714 0.380689 -2 3.574335 3.547273 0.404729 0.385104 -3 3.573150 3.549644 0.403350 0.384167 -4 3.518714 3.499090 0.408166 0.389015 -5 3.477355 3.441828 0.413880 0.394777 -6 3.408005 3.366269 0.422041 0.402934 -7 3.314280 3.284519 0.431068 0.411727 -8 3.244735 3.205757 0.440180 0.421078 -9 3.170936 3.152495 0.446947 0.428045 -10 3.131996 3.138446 0.448782 0.430013 -Saving optimiser state at data/wiki/wikitext-103/models/sp30k/biqrnn_bs70.m \ No newline at end of file