transfix-train/scripts/marian-train.sh

#!/bin/bash

# arguments
# 1. root of gonito.net challenge-like filestructure
# 2. name of the model and therefore a directory that will contain the model
# 3. expected number of train epochs

# path to corpus
corpus_path="$1"
model_name="$2"
epochs="$3"

source_file="$corpus_path"/train/in.tsv
source_file_valid="$corpus_path"/test-A/in.tsv

target_file="$corpus_path"/train/expected.tsv
target_file_valid="$corpus_path"/test-A/expected.tsv

mkdir "$model_name"

~/marian/build/marian \
--type transformer \
--model "$model_name"/model.npz \
--overwrite \
--train-sets "$source_file" "$target_file" \
--max-length 200 \
--mini-batch-fit -w 10000 --maxi-batch 1000 \
--valid-freq 5000 \
--save-freq 5000 \
--disp-freq 500 \
--beam-size 6 --normalize 0.6 \
--enc-depth 6 --dec-depth 6 \
--transformer-heads 8 \
--transformer-postprocess-emb d \
--transformer-postprocess dan \
--transformer-dropout 0.1 --label-smoothing 0.1 \
--learn-rate 0.0003 --lr-warmup 16000 --lr-decay-inv-sqrt 16000 --lr-report \
--optimizer-params 0.9 0.98 1e-09 --clip-norm 5 \
--tied-embeddings-all \
--exponential-smoothing \
--log "$model_name"/train.log \
--after-epochs="$epochs" \
--vocabs "$model_name"/vocab.in.spm "$model_name"/vocab.expected.spm \
--valid-log "$model_name"/valid.log \
--valid-metrics perplexity bleu \
--valid-mini-batch 64 \
--valid-sets "$source_file_valid" "$target_file_valid" \
--valid-translation-output "$model_name"/valid.output --quiet-translation