test

batch_nynorsk_NCC_base.sh → batch_political_base.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
-PROJECT_DIR=${HOME}"/models/t5-nynorsk-evaluator"
+PROJECT_DIR=${HOME}"/models/t5-political-evaluator"
 export PYTHONPATH=${PROJECT_DIR}
 #INITIAL_CHECKPOINT_PATH=\"gs://nb-t5x-us-central2/norwegian_NCC_plus_English_t5x_base/checkpoint_1500000\"
 #TRAIN_STEPS=1505000
@@ -7,7 +7,7 @@ export PYTHONPATH=${PROJECT_DIR}
 
 FINETUNE_STEPS=5000
 MODEL_BUCKET_DIR="gs://nb-t5x-us-central2/finetuned/"
-EVAL_PREFIX="ul2test/eval_nynorsk_"
+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") 
 
@@ -32,11 +32,11 @@ for v in "${VERSION_LIST[@]}"; do
 	    INITIAL_CHECKPOINT_PATH="${CHECKPOINT_BUCKET_DIR}${CHECKPOINT_LIST[$((index-1))]}/checkpoint_${s}"
 	    TRAIN_STEPS=$((s+FINETUNE_STEPS))
 	    if [[ "$INITIAL_CHECKPOINT_PATH" == *"engvoc"* ]]; then
-		GIN_FILE="finetune_translate_base.gin"
-		MIXTURE_OR_TASK_NAME="translate_long"
+		GIN_FILE="finetune_classification_base.gin"
+		MIXTURE_OR_TASK_NAME="parliament_max300"
 	    else
-		GIN_FILE="finetune_translate_base_scand.gin"
-		MIXTURE_OR_TASK_NAME="translate_long_scand"
+		GIN_FILE="finetune_classification_base_scand.gin"
+		MIXTURE_OR_TASK_NAME="parliament_max300_scand"
 	    fi
 
 	    MODEL_DIR="${MODEL_BUCKET_DIR}${EVAL_PREFIX}v${v}_${CHECKPOINT_LIST[$((index-1))]}_${s}"

finetune_translate_base_scand.gin

@@ -1,37 +0,0 @@
-from __gin__ import dynamic_registration
-import tasks
-import seqio
-
-import __main__ as train_script
-from t5.data import mixtures
-from t5x import models
-from t5x import partitioning
-from t5x import utils
-
-include "t5x/examples/t5/t5_1_1/base.gin"
-include "t5x/configs/runs/finetune.gin"
-
-MIXTURE_OR_TASK_NAME = %gin.REQUIRED
-TASK_FEATURE_LENGTHS = {"inputs": 512, "targets": 512}
-INITIAL_CHECKPOINT_PATH = %gin.REQUIRED
-TRAIN_STEPS = %gin.REQUIRED  # 1000000 pre-trained steps + 10000 fine-tuning steps.
-USE_CACHED_TASKS = False
-DROPOUT_RATE = 0.1
-RANDOM_SEED = 0
-
-#Fixing a small error
-infer_eval/utils.DatasetConfig:
-  task_feature_lengths = %TASK_FEATURE_LENGTHS
-
-#Saving every 1000 steps
-utils.SaveCheckpointConfig:
-  period = 1000
-  keep = 1  # number of checkpoints to keep
-
-# Might have to ba changed based on architecture
-# partitioning.PjitPartitioner.num_partitions = 1
-
-VOCABULARY = @seqio.SentencePieceVocabulary()
-seqio.SentencePieceVocabulary.sentencepiece_model_file = "gs://nb-t5/t5/vocabs/wikipedia/no-da-en-sv-nn-is_32000_unigram.sp.model"
-seqio.SentencePieceVocabulary.extra_ids = 100
-