Correct method to start incremental training with new data?

[Ak-sky]

Hi I have been trying to setup a Hindi-English NMT model with a deep multi-layer (wmt16_gnmt_4_layer.json) RNN which is unidirectional and uses LSTM as a recurrent unit. And the translations from Hindi to English are pretty ok with "num_train_steps": 340000 and now I want to improve the quality of the translation to a certain good level with the help of adding new corpus from another source.

I want to make sure, the steps that I will follow to start the incremental training is correct - -Generating preprocessing data (not the vocab) using the wmt shell script from nmt repo. -Vocabulary to be used from the previous preprocessed data. -copying the checkpoint, translate.ckpt-340000.data-00000-of-00001, translate.ckpt-340000.index, translate.ckpt-340000.meta to the new out_dir -Using the dev/test set from the previous preprocessed data -Modifying the "num_train_steps" as 350000 in json file.(wmt16_gnmt_4_layer.json)

-Starting the training using below command -- sudo python -m nmt.nmt
--src=hi
--tgt=en
--override_loaded_hparams=true
--hparams_path=/home/atladmin/nmt/nmt/standard_hparams/wmt16_gnmt_4_layer.json
--out_dir=/home/atladmin/nmt_ckpt
--vocab_prefix=/home/atladmin/nmt_new/vocab.bpe.32000
--train_prefix=/home/atladmin/nmt_new/train.tok.clean.bpe.32000
--dev_prefix=/home/atladmin/nmt_new/dev.tok.bpe.32000
--test_prefix=/home/atladmin/nmt_new/test.tok.bpe.32000 \ > nmt_hindi_log.txt &

Please do let me know if the above mentioned steps can be used for incremental training for the new corpus.

Please provide your suggestions and correct me if I am wrong. Thanks!

[pliu19]

Hi there, may I know whether your way works?