akhdanre
/
TIF_E41211115_lstm-quiz-generator
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat: done adding dataset

This commit is contained in:
akhdanre 2025-04-29 20:11:56 +07:00
parent 2e558c0384
commit 6318d222e7
12 changed files with 8873 additions and 19883 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

162
NER_SRL/adjst_model_lstm.ipynb
View File

File diff suppressed because one or more lines are too long

9411
NER_SRL/lstm_ner_srl.ipynb
View File

File diff suppressed because one or more lines are too long

BIN
NER_SRL/multi_task_lstm_ner_srl_model_tf.keras
View File

Binary file not shown.

BIN
NER_SRL/tag2idx_srl.pkl
View File

Binary file not shown.

BIN
NER_SRL/word2idx.pkl
View File

Binary file not shown.

93
QC/convert_dts.py
View File

@ -1,24 +1,31 @@
import json
import csv
from pathlib import Path
import json
import csv
from pathlib import Path
# Daftar label NER yang valid (bisa disesuaikan)
VALID_NER_LABELS = {
"O",
"B-LOC", "I-LOC",
"B-PER", "I-PER",
"B-ORG", "I-ORG",
"B-DATE", "I-DATE",
"B-TIME", "I-TIME",
"B-EVENT", "I-EVENT"
}
def json_to_tsv(json_path: str | Path, tsv_path: str | Path) -> None:
"""
Konversi data JSON (field: tokens, ner, srl, …) → TSV token\tNER\tSRL.
Kalimat duplikat (urutan tokens persis sama) otomatis dilewati.
Jika ada record yang tokens, ner, dan srl tidak sama panjang, akan diberi info error lengkap.
Jika ada record yang tokens, ner, dan srl tidak sama panjang, atau ada label NER tidak valid, akan diberi info error lengkap.
"""
# ---------------------------------------------------------------------
# 1. Baca semua record dari JSON
# ---------------------------------------------------------------------
with open(json_path, encoding="utf-8") as f:
records = json.load(f)
# ---------------------------------------------------------------------
# 2. Tulis ke TSV, sambil mendeteksi duplikat
# ---------------------------------------------------------------------
seen_sentences: set[tuple[str, ...]] = set() # simpan tuple tokens unik
seen_sentences: set[tuple[str, ...]] = set()
with open(tsv_path, "w", encoding="utf-8", newline="") as f_out:
writer = csv.writer(f_out, delimiter="\t", lineterminator="\n")
@ -28,7 +35,6 @@ def json_to_tsv(json_path: str | Path, tsv_path: str | Path) -> None:
ner_tags = rec.get("ner")
srl_tags = rec.get("srl")
# -- cek panjang sama
if not (len(tokens) == len(ner_tags) == len(srl_tags)):
raise ValueError(
f"❌ Panjang tidak sama di record index {idx}:\n"
@ -37,24 +43,79 @@ def json_to_tsv(json_path: str | Path, tsv_path: str | Path) -> None:
f" srl ({len(srl_tags)}): {srl_tags}\n"
)
# -- cek duplikat kalimat
key = tuple(tokens) # tuple hash-able
if key in seen_sentences: # sudah pernah ditulis → skip
# Validasi label NER
for i, ner_label in enumerate(ner_tags):
if ner_label not in VALID_NER_LABELS:
raise ValueError(
f"❌ Label NER tidak valid di record index {idx}, token ke-{i} ('{tokens[i]}'):\n"
f" ner_label: {ner_label}\n"
f" value: {tokens}"
)
key = tuple(tokens)
if key in seen_sentences:
continue
seen_sentences.add(key)
# -- tulis baris token, NER, SRL
for tok, ner, srl in zip(tokens, ner_tags, srl_tags):
writer.writerow([tok, ner, srl])
# -- baris kosong pemisah antar-kalimat
writer.writerow([])
print(f"✔️ TSV selesai, simpan di: {tsv_path}")
# def json_to_tsv(json_path: str | Path, tsv_path: str | Path) -> None:
# """
# Konversi data JSON (field: tokens, ner, srl, …) → TSV token\tNER\tSRL.
# Kalimat duplikat (urutan tokens persis sama) otomatis dilewati.
# Jika ada record yang tokens, ner, dan srl tidak sama panjang, akan diberi info error lengkap.
# """
# # ---------------------------------------------------------------------
# # 1. Baca semua record dari JSON
# # ---------------------------------------------------------------------
# with open(json_path, encoding="utf-8") as f:
# records = json.load(f)
# # ---------------------------------------------------------------------
# # 2. Tulis ke TSV, sambil mendeteksi duplikat
# # ---------------------------------------------------------------------
# seen_sentences: set[tuple[str, ...]] = set() # simpan tuple tokens unik
# with open(tsv_path, "w", encoding="utf-8", newline="") as f_out:
# writer = csv.writer(f_out, delimiter="\t", lineterminator="\n")
# for idx, rec in enumerate(records):
# tokens = rec.get("tokens")
# ner_tags = rec.get("ner")
# srl_tags = rec.get("srl")
# # -- cek panjang sama
# if not (len(tokens) == len(ner_tags) == len(srl_tags)):
# raise ValueError(
# f"❌ Panjang tidak sama di record index {idx}:\n"
# f" tokens ({len(tokens)}): {tokens}\n"
# f" ner ({len(ner_tags)}): {ner_tags}\n"
# f" srl ({len(srl_tags)}): {srl_tags}\n"
# )
# # -- cek duplikat kalimat
# key = tuple(tokens) # tuple hash-able
# if key in seen_sentences: # sudah pernah ditulis → skip
# continue
# seen_sentences.add(key)
# # -- tulis baris token, NER, SRL
# for tok, ner, srl in zip(tokens, ner_tags, srl_tags):
# writer.writerow([tok, ner, srl])
# # -- baris kosong pemisah antar-kalimat
# writer.writerow([])
# print(f"✔️ TSV selesai, simpan di: {tsv_path}")
# ---------------------------------------------------------------------------
# CONTOH PEMAKAIAN
# ---------------------------------------------------------------------------
if __name__ == "__main__":
json_to_tsv("QC/normalized_dataset.json", "QC/new_LNS.tsv")
json_to_tsv("QC/normalize_dataset.json", "QC/new_LNS.tsv")

14587
QC/new_LNS.tsv
View File

File diff suppressed because it is too large Load Diff

BIN
QC/new_model_lstm_qg.keras
View File

Binary file not shown.

769
QC/normalize_dataset.json
View File

@ -683,9 +683,9 @@
},
{
"tokens": ["Afrika", "dijuluki", "sebagai", "Benua", "Hitam", "."],
"ner": ["B-LOC", "O", "O", "O", "O"],
"srl": ["ARG1", "V", "ARG1", "ARG1", "O"],
"question": ["Apa", "julukan", "untuk", "Benua", "Afrika", "?"],
"ner": ["B-LOC", "O", "O", "O", "O", "O"],
"srl": ["ARG1", "V", "ARGM-PRD", "ARG2", "ARG2", "O"],
"question": ["Apa", "julukan", "untuk", "Afrika", "?"],
"answer": ["Benua", "Hitam"],
"type": "ftb"
},
@ -4928,7 +4928,7 @@
"O",
"O",
"O",
"V",
"O",
"O",
"O",
"O",
@ -5000,7 +5000,7 @@
"Indian",
"."
],
"ner": ["O", "O", "O", "O", "O", "O", "V", "B-ORG", "I-ORG", "I-ORG", "O"],
"ner": ["O", "O", "O", "O", "O", "O", "O", "B-ORG", "I-ORG", "I-ORG", "O"],
"srl": [
"ARG1",
"ARG1",
@ -5053,24 +5053,24 @@
"ner": [
"B-ORG",
"I-ORG",
"ARGM-NEG",
"V",
"ARG1",
"ARGM-MNR",
"ARG1",
"ARG1",
"V",
"ARG1",
"ARGM-CAU",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"B-ORG",
"I-ORG",
"ARGM-MNR",
"V",
"ARG1",
"ARGM-MNR",
"ARG1",
"ARGM-MNR",
"ARG1",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O"
],
"srl": [
@ -5607,7 +5607,7 @@
"biru",
"."
],
"ner": ["O", "O", "O", "O", "V", "O", "O", "O"],
"ner": ["O", "O", "O", "O", "O", "O", "O", "O"],
"srl": ["ARGM-EX", "ARG1", "ARG1", "ARGM-CAU", "V", "ARG2", "ARG2", "O"],
"question": [],
"answer": [],
@ -5692,25 +5692,25 @@
"ner": [
"O",
"O",
"ARGM-TMP",
"ARGM-TMP",
"ARGM-TMP",
"O",
"ARGM-MNR",
"O",
"O",
"V",
"ARGM-LOC",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"B-LOC",
"I-LOC",
"O",
"V",
"ARG1",
"ARG1",
"ARG1",
"ARG1",
"O",
"ARG1",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O"
],
@ -5836,18 +5836,7 @@
"Ural",
"."
],
"ner": [
"O",
"ARGM-MOD",
"V",
"ARGM-CAU",
"ARG1",
"ARG1",
"O",
"B-LOC",
"I-LOC",
"O"
],
"ner": ["O", "O", "O", "O", "O", "O", "O", "B-LOC", "I-LOC", "O"],
"srl": [
"ARG1",
"ARGM-MOD",
@ -6112,7 +6101,7 @@
"O",
"B-LOC",
"I-LOC",
"V",
"O",
"O",
"O",
"O",
@ -6933,15 +6922,15 @@
"O",
"ARG1",
"V",
"ARG1",
"ARG1",
"ARG1",
"ARG1",
"ARG1",
"ARG2",
"ARG2",
"ARG2",
"ARG2",
"ARG2",
"ARGM-LOC",
"ARGM-TMP",
"ARGM-TMP",
"O",
"R-ARG2",
"ARGM-MNR",
"ARGM-MNR",
"O",
@ -6952,7 +6941,6 @@
"O",
"O",
"O",
"ARGM-MNR",
"ARGM-LOC",
"ARGM-LOC",
"O"
@ -7217,7 +7205,7 @@
"bergelombang",
"."
],
"ner": ["O", "O", "O", "V", "O", "O", "O", "O", "O"],
"ner": ["O", "O", "O", "O", "O", "O", "O", "O", "O"],
"srl": ["ARG1", "ARG1", "O", "V", "ARGM-MNR", "ARG1", "O", "ARG1", "O"],
"question": [],
"answer": [],
@ -7252,20 +7240,20 @@
"O",
"O",
"O",
"V",
"ARG1",
"ARG1",
"ARG1",
"O",
"V",
"ARG1",
"ARG1",
"ARG1",
"O",
"ARG1",
"O",
"ARGM-MNR",
"ARG1",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O"
],
"srl": [
@ -7338,23 +7326,23 @@
"O",
"B-LOC",
"I-LOC",
"V",
"ARG1",
"ARG1",
"ARG1",
"O",
"ARG1",
"ARG1",
"O",
"ARG1",
"O",
"ARG1",
"O",
"V",
"ARG1",
"ARGM-TMP",
"ARGM-TMP",
"ARGM-TMP",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O"
],
"srl": [
@ -7465,13 +7453,14 @@
"O",
"O",
"O",
"O",
"O"
],
"srl": [
"ARG1",
"ARG1",
"ARG0",
"ARG0",
"ARGM-NEG",
"ARGM-MOD",
"ARGM-ADV",
"V",
"ARG1",
"O",
@ -8490,91 +8479,7 @@
"answer": ["sangat", "pendek", "tetapi", "memanjang", "ke", "belakang"],
"type": "ftb"
},
{
"tokens": [
"Volume",
"otaknya",
"sekitar",
"900",
"cc",
",",
"di",
"antara",
"otak",
"kera",
"(",
"600",
"cc",
")",
"dan",
"otak",
"manusia",
"modern",
"(",
"1.200-1.400",
"cc",
")",
"."
],
"ner": [
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O"
],
"srl": [
"ARG1",
"ARG1",
"ARG1",
"ARG1",
"ARG1",
"O",
"ARGM-LOC",
"ARGM-LOC",
"ARGM-LOC",
"ARGM-LOC",
"O",
"ARGM-LOC",
"ARGM-LOC",
"O",
"O",
"ARGM-LOC",
"ARGM-LOC",
"ARGM-LOC",
"O",
"ARGM-LOC",
"ARGM-LOC",
"O"
],
"question": [
"Berapakah",
"volume",
"otak",
"Pithecanthropus",
"erectus",
"?"
],
"answer": ["sekitar", "900", "cc"],
"type": "ftb"
},
{
"tokens": [
"Tulang",
@ -8753,6 +8658,7 @@
"O",
"O",
"O",
"O",
"O"
],
"srl": [
@ -8784,6 +8690,7 @@
"answer": ["telah", "mencapai", "usia", "dewasa"],
"type": "ftb"
},
{
"tokens": [
"Selain",
@ -8955,6 +8862,7 @@
"B-PER",
"O",
"O",
"O",
"O"
],
"srl": [
@ -8964,12 +8872,12 @@
"ARG1",
"ARG1",
"ARGM-TMP",
"ARG1",
"ARG1",
"ARGM-TMP",
"ARGM-TMP",
"ARG0",
"ARG0",
"R-ARG0",
"ARGM-TMP",
"ARGM-PRP",
"V",
"ARG1",
"ARG1",
@ -9779,6 +9687,7 @@
"O",
"O",
"O",
"O",
"O"
],
"srl": [
@ -9803,6 +9712,7 @@
"ARG1",
"ARG1",
"ARG1",
"ARG1",
"O"
],
"question": [
@ -11088,144 +10998,7 @@
"answer": ["bertambahnya", "kapasitas", "otak"],
"type": "ftb"
},
{
"tokens": [
"Homo",
"sapiens",
"mempunyai",
"kapasitas",
"otak",
"yang",
"jauh",
"lebih",
"besar",
"(",
"rata-rata",
"1.400",
"cc",
")",
",",
"dengan",
"atap",
"tengkorak",
"yang",
"jauh",
"lebih",
"bundar",
"dan",
"lebih",
"tinggi",
"dibandingkan",
"dengan",
"Homo",
"erectus",
"yang",
"mempunyai",
"tengkorak",
"panjang",
"dan",
"rendah",
",",
"dengan",
"kapasitas",
"otak",
"1.000",
"cc",
"."
],
"ner": [
"B-EVENT",
"I-EVENT",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"B-DATE",
"I-DATE",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"B-EVENT",
"I-EVENT",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"B-DATE",
"I-DATE",
"O"
],
"srl": [
"ARG0",
"ARG0",
"V",
"ARG1",
"ARG1",
"R-ARG1",
"ARGM-MNR",
"ARGM-MNR",
"ARG1",
"O",
"ARG1",
"ARG1",
"ARG1",
"O",
"O",
"ARGM-MNR",
"ARG1",
"ARG1",
"R-ARG1",
"ARGM-MNR",
"ARGM-MNR",
"ARG1",
"O",
"ARGM-MNR",
"ARG1",
"ARGM-COM",
"ARGM-COM",
"ARG2",
"ARG2",
"R-ARG2",
"V",
"ARG1",
"ARG1",
"O",
"ARG1",
"O",
"ARGM-MNR",
"ARG1",
"ARG1",
"ARG1",
"ARG1",
"O"
],
"question": ["Berapa", "kapasitas", "otak", "Homo", "sapiens", "?"],
"answer": ["1.400", "cc"],
"type": "ftb"
},
{
"tokens": [
"Segi-segi",
@ -11438,6 +11211,7 @@
"I-DATE",
"I-DATE",
"I-DATE",
"O",
"O"
],
"srl": [
@ -11464,6 +11238,7 @@
"ARGM-TMP",
"ARGM-TMP",
"ARGM-TMP",
"O",
"O"
],
"question": [
@ -11481,192 +11256,7 @@
"answer": ["45.000", "tahun", "yang", "lalu"],
"type": "ftb"
},
{
"tokens": [
"Dalam",
"perkembangannya",
",",
"kehidupan",
"manusia",
"modern",
"ini",
"dapat",
"dikelompokkan",
"dalam",
"tiga",
"tahap",
",",
"yaitu",
"(",
"i",
")",
"kehidupan",
"manusia",
"modern",
"awal",
"yang",
"kehadirannya",
"hingga",
"akhir",
"zaman",
"es",
"(",
"sekitar",
"12.000",
"tahun",
"lalu",
")",
",",
"kemudian",
"dilanjutkan",
"oleh",
"(",
"ii",
")",
"kehidupan",
"manusia",
"modern",
"yang",
"lebih",
"belakangan",
",",
"dan",
"berdasarkan",
"karakter",
"fisiknya",
"dikenal",
"sebagai",
"ras",
"Austromelanesoid",
"."
],
"ner": [
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"B-TIME",
"I-TIME",
"O",
"O",
"B-DATE",
"I-DATE",
"I-DATE",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"B-PER",
"O"
],
"srl": [
"ARGM-TMP",
"ARGM-TMP",
"O",
"ARG1",
"ARG1",
"ARG1",
"ARG1",
"ARGM-MOD",
"V",
"ARGM-LOC",
"ARGM-EXT",
"ARGM-LOC",
"O",
"ARGM-ADV",
"O",
"O",
"O",
"ARG1",
"ARG1",
"ARG1",
"ARG1",
"R-ARG1",
"ARG1",
"ARGM-TMP",
"ARGM-TMP",
"ARGM-TMP",
"ARGM-TMP",
"O",
"ARGM-TMP",
"ARGM-TMP",
"ARGM-TMP",
"ARGM-TMP",
"O",
"O",
"ARGM-TMP",
"V",
"ARG0",
"O",
"O",
"ARG1",
"ARG1",
"ARG1",
"R-ARG1",
"ARGM-MNR",
"ARG1",
"O",
"O",
"ARGM-CAU",
"ARG1",
"ARG1",
"V",
"ARGM-PRD",
"ARG2",
"ARG2",
"O"
],
"question": [
"Apa",
"nama",
"ras",
"kehidupan",
"manusia",
"modern",
"yang",
"lebih",
"belakangan",
"?"
],
"answer": ["Austromelanesoid"],
"type": "ftb"
},
{
"tokens": [
"(",
@ -12287,8 +11877,8 @@
"O",
"O",
"O",
"V",
"V",
"O",
"O",
"O",
"B-PER",
"O",
@ -12442,5 +12032,190 @@
"question": [],
"answer": [],
"type": "none"
},
{
"tokens": [
"Temuan",
"Wajak",
"menunjukkan",
"pada",
"kita",
"bahwa",
"sekitar",
"40.000",
"tahun",
"yang",
"lalu",
"Indonesia",
"sudah",
"didiami",
"oleh",
"Homo",
"sapiens",
"yang",
"rasnya",
"sukar",
"dicocokkan",
"dengan",
"ras-ras",
"pokok",
"yang",
"terdapat",
"sekarang",
","
],
"ner": [
"O",
"B-LOC",
"O",
"O",
"O",
"O",
"O",
"B-DATE",
"I-DATE",
"I-DATE",
"I-DATE",
"B-LOC",
"O",
"O",
"O",
"B-EVENT",
"I-EVENT",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O",
"O"
],
"srl": [
"ARG0",
"ARG0",
"V",
"ARGM-REC",
"ARGM-REC",
"O",
"ARGM-TMP",
"ARGM-TMP",
"ARGM-TMP",
"ARGM-TMP",
"ARGM-TMP",
"ARGM-LOC",
"ARGM-MOD",
"V",
"ARGM-CAU",
"ARG1",
"ARG1",
"R-ARG1",
"ARG1",
"ARG1",
"V",
"ARGM-COM",
"ARG2",
"ARG2",
"R-ARG2",
"V",
"ARGM-TMP",
"O"
],
"question": [
"Sejak",
"kapan",
"Indonesia",
"sudah",
"didiami",
"oleh",
"Homo",
"sapiens",
"?"
],
"answer": ["sekitar", "40.000", "tahun", "yang", "lalu"],
"type": "ftb"
},
{
"tokens": [
"sehingga",
"manusia",
"Wajak",
"dapat",
"dianggap",
"sebagai",
"suatu",
"ras",
"tersendiri",
"."
],
"ner": ["O", "O", "B-LOC", "O", "O", "O", "O", "O", "O", "O"],
"srl": [
"ARGM-ADV",
"ARG1",
"ARG1",
"ARGM-MOD",
"V",
"ARGM-PRD",
"ARG2",
"ARG2",
"ARG2",
"O"
],
"question": ["Apa", "klasifikasi", "manusia", "Wajak", "?"],
"answer": ["ras", "tersendiri"],
"type": "ftb"
},
{
"tokens": [
"Manusia",
"Wajak",
"tidak",
"langsung",
"berevolusi",
"dari",
"Pithecanthropus",
",",
"tetapi",
"mungkin",
"tahapan",
"Homo",
"neanderthalensis"
],
"ner": [
"O",
"B-LOC",
"O",
"O",
"O",
"O",
"B-EVENT",
"O",
"O",
"O",
"O",
"B-EVENT",
"I-EVENT"
],
"srl": [
"ARG0",
"ARG0",
"ARGM-NEG",
"ARGM-MNR",
"V",
"ARGM-SRC",
"ARG2",
"O",
"ARGM-ADV",
"ARGM-MOD",
"ARG1",
"ARG1",
"ARG1"
],
"question": ["Dari", "mana", "manusia", "Wajak", "berevolusi", "?"],
"answer": ["mungkin", "tahapan", "Homo", "neanderthalensis"],
"type": "ftb"
}
]

84
QC/qg_train.ipynb
View File

@ -10,18 +10,18 @@
"name": "stderr",
"output_type": "stream",
"text": [
"2025-04-29 15:10:04.089483: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
"2025-04-29 15:10:04.096411: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n",
"2025-04-29 15:10:04.155120: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n",
"2025-04-29 15:10:04.201581: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
"2025-04-29 19:13:19.968628: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
"2025-04-29 19:13:19.975821: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n",
"2025-04-29 19:13:20.061422: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n",
"2025-04-29 19:13:20.109564: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
"WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
"E0000 00:00:1745914204.252337 250474 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
"E0000 00:00:1745914204.265450 250474 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
"W0000 00:00:1745914204.374986 250474 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"W0000 00:00:1745914204.375008 250474 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"W0000 00:00:1745914204.375009 250474 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"W0000 00:00:1745914204.375010 250474 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"2025-04-29 15:10:04.389010: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
"E0000 00:00:1745928800.155971 272184 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
"E0000 00:00:1745928800.168166 272184 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
"W0000 00:00:1745928800.263286 272184 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"W0000 00:00:1745928800.263312 272184 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"W0000 00:00:1745928800.263313 272184 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"W0000 00:00:1745928800.263314 272184 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"2025-04-29 19:13:20.274608: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
"To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
]
}
@ -51,7 +51,7 @@
},
{
"cell_type": "code",
"execution_count": 16,
"execution_count": 12,
"id": "50118278",
"metadata": {},
"outputs": [
@ -60,9 +60,9 @@
"output_type": "stream",
"text": [
"\n",
" Jumlah data valid: 261 / 261\n",
" Jumlah data valid: 287 / 287\n",
" Jumlah data tidak valid: 0\n",
"Counter({'ftb': 180, 'tof': 45, 'none': 36})\n"
"Counter({'ftb': 202, 'tof': 45, 'none': 40})\n"
]
}
],
@ -157,7 +157,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"{'none', 'tof', 'ftb'}\n"
"{'ftb', 'tof', 'none'}\n"
]
}
],
@ -208,7 +208,7 @@
"name": "stderr",
"output_type": "stream",
"text": [
"2025-04-29 15:10:06.654453: E external/local_xla/xla/stream_executor/cuda/cuda_platform.cc:51] failed call to cuInit: INTERNAL: CUDA error: Failed call to cuInit: UNKNOWN ERROR (303)\n"
"2025-04-29 19:13:22.481835: E external/local_xla/xla/stream_executor/cuda/cuda_platform.cc:51] failed call to cuInit: INTERNAL: CUDA error: Failed call to cuInit: UNKNOWN ERROR (303)\n"
]
},
{
@ -239,13 +239,13 @@
"│ srl_input │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ - │\n",
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">InputLayer</span>) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ embedding │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">74,496</span> │ tok_input[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
"│ embedding │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">126,080</span> │ tok_input[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Embedding</span>) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ embedding_1 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">352</span> │ ner_input[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Embedding</span>) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ embedding_2 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">272</span> │ srl_input[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
"│ embedding_2 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">432</span> │ srl_input[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Embedding</span>) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ concatenate │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">160</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ embedding[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>], │\n",
@ -256,10 +256,10 @@
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ get_item (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">GetItem</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ lstm[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ question_output │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">339</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">87,123</span> │ lstm[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
"│ question_output │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">473</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">121,561</span> │ lstm[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">TimeDistributed</span>) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ answer_output │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">234</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">60,138</span> │ lstm[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
"│ answer_output │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">383</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">98,431</span> │ lstm[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">TimeDistributed</span>) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ type_output (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">771</span> │ get_item[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
@ -279,13 +279,13 @@
"│ srl_input │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n",
"│ (\u001b[38;5;33mInputLayer\u001b[0m) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ embedding │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m74,496\u001b[0m │ tok_input[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ embedding │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m126,080\u001b[0m │ tok_input[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mEmbedding\u001b[0m) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ embedding_1 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m) │ \u001b[38;5;34m352\u001b[0m │ ner_input[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mEmbedding\u001b[0m) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ embedding_2 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m) │ \u001b[38;5;34m272\u001b[0m │ srl_input[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ embedding_2 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m) │ \u001b[38;5;34m432\u001b[0m │ srl_input[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mEmbedding\u001b[0m) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ concatenate │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m160\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ embedding[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m], │\n",
@ -296,10 +296,10 @@
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ get_item (\u001b[38;5;33mGetItem\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ lstm[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ question_output │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m339\u001b[0m) │ \u001b[38;5;34m87,123\u001b[0m │ lstm[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ question_output │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m473\u001b[0m) │ \u001b[38;5;34m121,561\u001b[0m │ lstm[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mTimeDistributed\u001b[0m) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ answer_output │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m234\u001b[0m) │ \u001b[38;5;34m60,138\u001b[0m │ lstm[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ answer_output │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m383\u001b[0m) │ \u001b[38;5;34m98,431\u001b[0m │ lstm[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mTimeDistributed\u001b[0m) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ type_output (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m3\u001b[0m) │ \u001b[38;5;34m771\u001b[0m │ get_item[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
@ -312,11 +312,11 @@
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">650,160</span> (2.48 MB)\n",
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">774,635</span> (2.95 MB)\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m650,160\u001b[0m (2.48 MB)\n"
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m774,635\u001b[0m (2.95 MB)\n"
]
},
"metadata": {},
@ -325,11 +325,11 @@
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">650,160</span> (2.48 MB)\n",
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">774,635</span> (2.95 MB)\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m650,160\u001b[0m (2.48 MB)\n"
"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m774,635\u001b[0m (2.95 MB)\n"
]
},
"metadata": {},
@ -353,27 +353,23 @@
"output_type": "stream",
"text": [
"Epoch 1/30\n",
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 139ms/step - answer_output_accuracy: 0.4569 - answer_output_loss: 5.3719 - loss: 12.2246 - question_output_accuracy: 0.3854 - question_output_loss: 5.7392 - type_output_accuracy: 0.5172 - type_output_loss: 1.0955 - val_answer_output_accuracy: 0.9382 - val_answer_output_loss: 4.7459 - val_loss: 10.9338 - val_question_output_accuracy: 0.7618 - val_question_output_loss: 5.0968 - val_type_output_accuracy: 0.5294 - val_type_output_loss: 1.0911\n",
"\u001b[1m7/7\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 101ms/step - answer_output_accuracy: 0.5626 - answer_output_loss: 5.7629 - loss: 12.9112 - question_output_accuracy: 0.3867 - question_output_loss: 6.0185 - type_output_accuracy: 0.5290 - type_output_loss: 1.0943 - val_answer_output_accuracy: 0.9261 - val_answer_output_loss: 3.9036 - val_loss: 9.5865 - val_question_output_accuracy: 0.7500 - val_question_output_loss: 4.5947 - val_type_output_accuracy: 0.5652 - val_type_output_loss: 1.0883\n",
"Epoch 2/30\n",
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - answer_output_accuracy: 0.9030 - answer_output_loss: 4.0847 - loss: 9.6638 - question_output_accuracy: 0.6989 - question_output_loss: 4.4100 - type_output_accuracy: 0.6659 - type_output_loss: 1.0841 - val_answer_output_accuracy: 0.9382 - val_answer_output_loss: 2.0126 - val_loss: 5.3872 - val_question_output_accuracy: 0.7618 - val_question_output_loss: 2.2876 - val_type_output_accuracy: 0.5294 - val_type_output_loss: 1.0870\n",
"\u001b[1m7/7\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - answer_output_accuracy: 0.8791 - answer_output_loss: 2.9526 - loss: 7.7800 - question_output_accuracy: 0.6837 - question_output_loss: 3.7162 - type_output_accuracy: 0.7148 - type_output_loss: 1.0672 - val_answer_output_accuracy: 0.9261 - val_answer_output_loss: 1.1139 - val_loss: 4.1230 - val_question_output_accuracy: 0.7500 - val_question_output_loss: 1.9489 - val_type_output_accuracy: 0.5652 - val_type_output_loss: 1.0601\n",
"Epoch 3/30\n",
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - answer_output_accuracy: 0.9058 - answer_output_loss: 1.7045 - loss: 4.9716 - question_output_accuracy: 0.7067 - question_output_loss: 2.1690 - type_output_accuracy: 0.6298 - type_output_loss: 1.0735 - val_answer_output_accuracy: 0.9382 - val_answer_output_loss: 0.9609 - val_loss: 3.8103 - val_question_output_accuracy: 0.7618 - val_question_output_loss: 1.7718 - val_type_output_accuracy: 0.5294 - val_type_output_loss: 1.0775\n",
"\u001b[1m7/7\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - answer_output_accuracy: 0.8726 - answer_output_loss: 1.2047 - loss: 4.4213 - question_output_accuracy: 0.6797 - question_output_loss: 2.2016 - type_output_accuracy: 0.7251 - type_output_loss: 1.0092 - val_answer_output_accuracy: 0.9261 - val_answer_output_loss: 0.7679 - val_loss: 3.7423 - val_question_output_accuracy: 0.7500 - val_question_output_loss: 1.9604 - val_type_output_accuracy: 0.5652 - val_type_output_loss: 1.0140\n",
"Epoch 4/30\n",
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - answer_output_accuracy: 0.9007 - answer_output_loss: 1.0111 - loss: 4.1452 - question_output_accuracy: 0.7096 - question_output_loss: 2.0851 - type_output_accuracy: 0.6441 - type_output_loss: 1.0523 - val_answer_output_accuracy: 0.9382 - val_answer_output_loss: 0.6963 - val_loss: 3.5772 - val_question_output_accuracy: 0.7618 - val_question_output_loss: 1.8231 - val_type_output_accuracy: 0.5294 - val_type_output_loss: 1.0579\n",
"\u001b[1m7/7\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - answer_output_accuracy: 0.8633 - answer_output_loss: 1.1478 - loss: 4.4374 - question_output_accuracy: 0.6639 - question_output_loss: 2.3671 - type_output_accuracy: 0.7490 - type_output_loss: 0.9088 - val_answer_output_accuracy: 0.9261 - val_answer_output_loss: 0.7059 - val_loss: 3.6255 - val_question_output_accuracy: 0.7500 - val_question_output_loss: 1.9356 - val_type_output_accuracy: 0.5652 - val_type_output_loss: 0.9840\n",
"Epoch 5/30\n",
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - answer_output_accuracy: 0.9116 - answer_output_loss: 0.7749 - loss: 3.9569 - question_output_accuracy: 0.6975 - question_output_loss: 2.1718 - type_output_accuracy: 0.6141 - type_output_loss: 1.0181 - val_answer_output_accuracy: 0.9382 - val_answer_output_loss: 0.6098 - val_loss: 3.3674 - val_question_output_accuracy: 0.7618 - val_question_output_loss: 1.7225 - val_type_output_accuracy: 0.5294 - val_type_output_loss: 1.0351\n",
"\u001b[1m7/7\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - answer_output_accuracy: 0.8783 - answer_output_loss: 1.0187 - loss: 4.0230 - question_output_accuracy: 0.6760 - question_output_loss: 2.1959 - type_output_accuracy: 0.7563 - type_output_loss: 0.8131 - val_answer_output_accuracy: 0.9261 - val_answer_output_loss: 0.6848 - val_loss: 3.5743 - val_question_output_accuracy: 0.7500 - val_question_output_loss: 1.9039 - val_type_output_accuracy: 0.5652 - val_type_output_loss: 0.9857\n",
"Epoch 6/30\n",
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - answer_output_accuracy: 0.9042 - answer_output_loss: 0.7511 - loss: 3.6901 - question_output_accuracy: 0.6980 - question_output_loss: 1.9691 - type_output_accuracy: 0.6667 - type_output_loss: 0.9625 - val_answer_output_accuracy: 0.9382 - val_answer_output_loss: 0.5729 - val_loss: 3.3592 - val_question_output_accuracy: 0.7618 - val_question_output_loss: 1.7692 - val_type_output_accuracy: 0.5294 - val_type_output_loss: 1.0171\n",
"\u001b[1m7/7\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - answer_output_accuracy: 0.8800 - answer_output_loss: 0.9845 - loss: 3.8171 - question_output_accuracy: 0.6878 - question_output_loss: 2.0357 - type_output_accuracy: 0.7328 - type_output_loss: 0.7942 - val_answer_output_accuracy: 0.9261 - val_answer_output_loss: 0.6742 - val_loss: 3.5592 - val_question_output_accuracy: 0.7500 - val_question_output_loss: 1.8777 - val_type_output_accuracy: 0.5652 - val_type_output_loss: 1.0074\n",
"Epoch 7/30\n",
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - answer_output_accuracy: 0.9067 - answer_output_loss: 0.7140 - loss: 3.5808 - question_output_accuracy: 0.7004 - question_output_loss: 1.9338 - type_output_accuracy: 0.6701 - type_output_loss: 0.9270 - val_answer_output_accuracy: 0.9382 - val_answer_output_loss: 0.5537 - val_loss: 3.2816 - val_question_output_accuracy: 0.7618 - val_question_output_loss: 1.7182 - val_type_output_accuracy: 0.5294 - val_type_output_loss: 1.0097\n",
"\u001b[1m7/7\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - answer_output_accuracy: 0.8768 - answer_output_loss: 0.9756 - loss: 3.8569 - question_output_accuracy: 0.6743 - question_output_loss: 2.0795 - type_output_accuracy: 0.7030 - type_output_loss: 0.8039 - val_answer_output_accuracy: 0.9261 - val_answer_output_loss: 0.6769 - val_loss: 3.5671 - val_question_output_accuracy: 0.7500 - val_question_output_loss: 1.8631 - val_type_output_accuracy: 0.5652 - val_type_output_loss: 1.0272\n",
"Epoch 8/30\n",
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - answer_output_accuracy: 0.9001 - answer_output_loss: 0.7540 - loss: 3.4527 - question_output_accuracy: 0.7065 - question_output_loss: 1.8054 - type_output_accuracy: 0.6714 - type_output_loss: 0.8939 - val_answer_output_accuracy: 0.9382 - val_answer_output_loss: 0.5429 - val_loss: 3.2578 - val_question_output_accuracy: 0.7618 - val_question_output_loss: 1.7000 - val_type_output_accuracy: 0.5294 - val_type_output_loss: 1.0149\n",
"\u001b[1m7/7\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - answer_output_accuracy: 0.8814 - answer_output_loss: 0.9217 - loss: 3.7726 - question_output_accuracy: 0.6798 - question_output_loss: 2.0253 - type_output_accuracy: 0.6785 - type_output_loss: 0.8194 - val_answer_output_accuracy: 0.9261 - val_answer_output_loss: 0.6900 - val_loss: 3.5722 - val_question_output_accuracy: 0.7500 - val_question_output_loss: 1.8469 - val_type_output_accuracy: 0.5652 - val_type_output_loss: 1.0354\n",
"Epoch 9/30\n",
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - answer_output_accuracy: 0.8970 - answer_output_loss: 0.7761 - loss: 3.4633 - question_output_accuracy: 0.6954 - question_output_loss: 1.8261 - type_output_accuracy: 0.6680 - type_output_loss: 0.8589 - val_answer_output_accuracy: 0.9382 - val_answer_output_loss: 0.5371 - val_loss: 3.2677 - val_question_output_accuracy: 0.7618 - val_question_output_loss: 1.7034 - val_type_output_accuracy: 0.5294 - val_type_output_loss: 1.0272\n",
"Epoch 10/30\n",
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - answer_output_accuracy: 0.9095 - answer_output_loss: 0.6652 - loss: 3.3243 - question_output_accuracy: 0.7002 - question_output_loss: 1.7973 - type_output_accuracy: 0.6541 - type_output_loss: 0.8676 - val_answer_output_accuracy: 0.9382 - val_answer_output_loss: 0.5337 - val_loss: 3.2687 - val_question_output_accuracy: 0.7618 - val_question_output_loss: 1.6956 - val_type_output_accuracy: 0.5294 - val_type_output_loss: 1.0394\n",
"Epoch 11/30\n",
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - answer_output_accuracy: 0.9106 - answer_output_loss: 0.6445 - loss: 3.2512 - question_output_accuracy: 0.7075 - question_output_loss: 1.7406 - type_output_accuracy: 0.6467 - type_output_loss: 0.8649 - val_answer_output_accuracy: 0.9382 - val_answer_output_loss: 0.5335 - val_loss: 3.2597 - val_question_output_accuracy: 0.7618 - val_question_output_loss: 1.6769 - val_type_output_accuracy: 0.5294 - val_type_output_loss: 1.0493\n"
"\u001b[1m7/7\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - answer_output_accuracy: 0.8703 - answer_output_loss: 0.9799 - loss: 3.6985 - question_output_accuracy: 0.6843 - question_output_loss: 1.9755 - type_output_accuracy: 0.7160 - type_output_loss: 0.7474 - val_answer_output_accuracy: 0.9261 - val_answer_output_loss: 0.6958 - val_loss: 3.5849 - val_question_output_accuracy: 0.7500 - val_question_output_loss: 1.8401 - val_type_output_accuracy: 0.5652 - val_type_output_loss: 1.0490\n"
]
}
],
@ -454,7 +450,7 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 7,
"id": "06fd86c7",
"metadata": {},
"outputs": [
@ -462,12 +458,12 @@
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step\n",
"\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 236ms/step\n",
"\n",
"=== Akurasi Detail ===\n",
"Question Accuracy (Token-level): 0.0000\n",
"Answer Accuracy (Token-level) : 0.0000\n",
"Type Accuracy (Class-level) : 0.61\n"
"Type Accuracy (Class-level) : 0.68\n"
]
}
],

BIN
QC/tokenizers.pkl
View File

Binary file not shown.

3650
dataset/dataset_ner_srl.tsv
View File

File diff suppressed because it is too large Load Diff