t5-political-evaluator / batch_political_base.sh
pere's picture
small
e577c11
raw
history blame
4.45 kB
#!/bin/bash
PROJECT_DIR=${HOME}"/models/t5-political-evaluator"
export PYTHONPATH=${PROJECT_DIR}
#INITIAL_CHECKPOINT_PATH=\"gs://nb-t5x-us-central2/norwegian_NCC_plus_English_t5x_base/checkpoint_1500000\"
#TRAIN_STEPS=1505000
FINETUNE_STEPS=5000
MODEL_BUCKET_DIR="gs://nb-t5x-us-central2/finetuned/"
EVAL_PREFIX="ul2test/eval_political_"
CHECKPOINT_BUCKET_DIR="gs://nb-t5x-us-central2/"
CHECKPOINT_LIST=("exp1-t5-base-ul2-engvoc" "exp2-t5-base-ul2-scandvoc" "exp3-t5-base-span-engvoc" "exp4-t5-base-span-scandvoc" "exp5-t5-base-ul2-scandvoc-full" "exp6-t5-base-span-scandvoc-full" "exp7-t5-base-ul2-511-scandvoc" "exp8-t5-base-span-511-scandvoc" "exp9-t5-base-ul2-mt5voc" "exp10-t5-base-span-mt5voc" "exp11-t5-base-ul2-511-scandvoc-full" "exp12-t5-base-span-511-scandvoc-full" "exp13-t5-base-ul2-mt5voc-full" "exp14-t5-base-span-mt5voc-full" "exp15-t5-base-ul2-511-scandvoc-full-scratch" "exp16-t5-base-span-511-scandvoc-full-scratch" "exp17-t5-small-ul2-mt5voc-scratch" "exp18-t5-small-span-mt5voc-scratch" "exp19-t5-small-ul2-mt5voc" "exp20-t5-small-span-mt5voc" "exp21-t5-small-ul2-mt5voc-full" "exp22-t5-small-span-mt5voc-full")
PRETUNE_START_LIST=(100000 200000 300000 400000 500000 1000000 1100000 1184000 1200000 1204000 1284000 1300000 1384000 1400000 1484000 1500000)
VERSION_LIST=("1" "2" "3" "4" "5")
index=$(($1 + 0))
if [ $index -lt 1 ] || [ $index -gt ${#CHECKPOINT_LIST[@]} ] || [ $# -ne 1 ]; then
echo "Error: You need to provide the number of the checkpoints below as a parameter."
for i in "${!CHECKPOINT_LIST[@]}"; do
echo "$((i+1)). ${CHECKPOINT_LIST[i]}"
done
exit 1
fi
for v in "${VERSION_LIST[@]}"; do
for s in "${PRETUNE_START_LIST[@]}"; do
INITIAL_CHECKPOINT_PATH="${CHECKPOINT_BUCKET_DIR}${CHECKPOINT_LIST[$((index-1))]}/checkpoint_${s}"
TRAIN_STEPS=$((s+FINETUNE_STEPS))
if [[ "$INITIAL_CHECKPOINT_PATH" == *"engvoc"* ]]; then
GIN_FILE="finetune_classification_base.gin"
MIXTURE_OR_TASK_NAME="parliament_max300"
elif [[ "$INITIAL_CHECKPOINT_PATH" == *"scandvoc"* ]]; then
GIN_FILE="finetune_classification_base_scand.gin"
MIXTURE_OR_TASK_NAME="parliament_max300_scand"
else
if [[ "$INITIAL_CHECKPOINT_PATH" == *"small"* ]]; then
GIN_FILE="finetune_classification_small_mt5.gin"
else
GIN_FILE="finetune_classification_base_mt5.gin"
fi
MIXTURE_OR_TASK_NAME="parliament_max300_mt5"
fi
MODEL_DIR="${MODEL_BUCKET_DIR}${EVAL_PREFIX}v${v}_${CHECKPOINT_LIST[$((index-1))]}_${s}"
command="python3 ../../t5x/t5x/train.py --gin_search_paths=\"./\" --gin.TRAIN_STEPS=${TRAIN_STEPS} --gin_file=${GIN_FILE} --gin.INITIAL_CHECKPOINT_PATH=\\\"${INITIAL_CHECKPOINT_PATH}\\\" --gin.MIXTURE_OR_TASK_NAME=\\\"${MIXTURE_OR_TASK_NAME}\\\" --gin.MODEL_DIR=\\\"${MODEL_DIR}\\\""
echo "${command}"
# Uncomment the next line to run the command:
eval "${command}"
done
done
#python3 ../../t5x/t5x/train.py --gin_search_paths="./" --gin.TRAIN_STEPS=${TRAIN_STEPS} --gin_file="finetune_translate_base.gin" --gin.INITIAL_CHECKPOINT_PATH=${INITIAL_CHECKPOINT_PATH} --gin.MIXTURE_OR_TASK_NAME=\"translate_long\" --gin.MODEL_DIR=\"gs://nb-t5x-us-central2/finetuned/nynorsk_NCC_base_v1\" &&
#python3 ../../t5x/t5x/train.py --gin_search_paths="./" --gin.TRAIN_STEPS=${TRAIN_STEPS} --gin_file="finetune_translate_base.gin" --gin.INITIAL_CHECKPOINT_PATH=${INITIAL_CHECKPOINT_PATH} --gin.MIXTURE_OR_TASK_NAME=\"translate_long\" --gin.MODEL_DIR=\"gs://nb-t5x-us-central2/finetuned/nynorsk_NCC_base_v2\" &&
#python3 ../../t5x/t5x/train.py --gin_search_paths="./" --gin.TRAIN_STEPS=${TRAIN_STEPS} --gin_file="finetune_translate_base.gin" --gin.INITIAL_CHECKPOINT_PATH=${INITIAL_CHECKPOINT_PATH} --gin.MIXTURE_OR_TASK_NAME=\"translate_long\" --gin.MODEL_DIR=\"gs://nb-t5x-us-central2/finetuned/nynorsk_NCC_base_v3\" &&
#python3 ../../t5x/t5x/train.py --gin_search_paths="./" --gin.TRAIN_STEPS=${TRAIN_STEPS} --gin_file="finetune_translate_base.gin" --gin.INITIAL_CHECKPOINT_PATH=${INITIAL_CHECKPOINT_PATH} --gin.MIXTURE_OR_TASK_NAME=\"translate_long\" --gin.MODEL_DIR=\"gs://nb-t5x-us-central2/finetuned/nynorsk_NCC_base_v4\" &&
#python3 ../../t5x/t5x/train.py --gin_search_paths="./" --gin.TRAIN_STEPS=${TRAIN_STEPS} --gin_file="finetune_translate_base.gin" --gin.INITIAL_CHECKPOINT_PATH=${INITIAL_CHECKPOINT_PATH} --gin.MIXTURE_OR_TASK_NAME=\"translate_long\" --gin.MODEL_DIR=\"gs://nb-t5x-us-central2/finetuned/nynorsk_NCC_base_v5\"