feat: adjust on the dataset
This commit is contained in:
parent
f0f6f412bb
commit
6851390ea2
|
|
@ -3,5 +3,8 @@ myenv
|
|||
*keras*
|
||||
**/*keras*
|
||||
|
||||
|
||||
*h5*
|
||||
**/*h5*
|
||||
# Abaikan semua file dengan ekstensi .pkl
|
||||
*.pkl
|
||||
|
|
|
|||
Binary file not shown.
|
Before Width: | Height: | Size: 65 KiB After Width: | Height: | Size: 62 KiB |
File diff suppressed because one or more lines are too long
Binary file not shown.
|
Before Width: | Height: | Size: 54 KiB After Width: | Height: | Size: 54 KiB |
Binary file not shown.
Binary file not shown.
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,3 @@
|
|||
[
|
||||
"B-PER"
|
||||
]
|
||||
|
|
@ -2,7 +2,7 @@
|
|||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 51,
|
||||
"execution_count": 20,
|
||||
"id": "9bf2159a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
|
|
@ -31,28 +31,96 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 52,
|
||||
"execution_count": 21,
|
||||
"id": "50118278",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# # Load raw data\n",
|
||||
"# with open(\"qg_dataset.json\", encoding=\"utf-8\") as f:\n",
|
||||
"# raw_data = json.load(f)\n",
|
||||
"\n",
|
||||
"# # Validasi lengkap\n",
|
||||
"# required_keys = {\"tokens\", \"ner\", \"srl\", \"question\", \"answer\", \"type\"}\n",
|
||||
"# valid_data = []\n",
|
||||
"# invalid_data = []\n",
|
||||
"\n",
|
||||
"# for idx, item in enumerate(raw_data):\n",
|
||||
"# error_messages = []\n",
|
||||
"\n",
|
||||
"# if not isinstance(item, dict):\n",
|
||||
"# error_messages.append(\"bukan dictionary\")\n",
|
||||
"\n",
|
||||
"# missing_keys = required_keys - item.keys()\n",
|
||||
"# if missing_keys:\n",
|
||||
"# error_messages.append(f\"missing keys: {missing_keys}\")\n",
|
||||
"\n",
|
||||
"# if not error_messages:\n",
|
||||
"# # Cek tipe data dan None\n",
|
||||
"# if (not isinstance(item[\"tokens\"], list) or\n",
|
||||
"# not isinstance(item[\"ner\"], list) or\n",
|
||||
"# not isinstance(item[\"srl\"], list) or\n",
|
||||
"# not isinstance(item[\"question\"], list) or\n",
|
||||
"# not isinstance(item[\"answer\"], list) or\n",
|
||||
"# not isinstance(item[\"type\"], str)):\n",
|
||||
"# error_messages.append(\"field type tidak sesuai\")\n",
|
||||
" \n",
|
||||
"# if error_messages:\n",
|
||||
"# print(f\"\\n Index {idx} | Masalah: {', '.join(error_messages)}\")\n",
|
||||
"# print(json.dumps(item, indent=2, ensure_ascii=False))\n",
|
||||
"# invalid_data.append(item)\n",
|
||||
"# continue\n",
|
||||
"\n",
|
||||
"# valid_data.append(item)\n",
|
||||
"\n",
|
||||
"# # Statistik\n",
|
||||
"# print(f\"\\n Jumlah data valid: {len(valid_data)} / {len(raw_data)}\")\n",
|
||||
"# print(f\" Jumlah data tidak valid: {len(invalid_data)}\")\n",
|
||||
"\n",
|
||||
"# # Proses data valid\n",
|
||||
"# tokens = [[t.lower().strip() for t in item[\"tokens\"]] for item in valid_data]\n",
|
||||
"# ner_tags = [item[\"ner\"] for item in valid_data]\n",
|
||||
"# srl_tags = [item[\"srl\"] for item in valid_data]\n",
|
||||
"# questions = [[token.lower().strip() for token in item[\"question\"]] for item in valid_data]\n",
|
||||
"# answers = [[token.lower().strip() for token in item[\"answer\"]] for item in valid_data]\n",
|
||||
"# types = [item[\"type\"] for item in valid_data]\n",
|
||||
"\n",
|
||||
"# type_counts = Counter(types)\n",
|
||||
"\n",
|
||||
"# print(type_counts)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 22,
|
||||
"id": "970867e2",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
" Jumlah data valid: 70 / 70\n",
|
||||
" Jumlah data tidak valid: 0\n",
|
||||
"Counter({'tof': 30, 'isian': 30, 'opsi': 10})\n"
|
||||
"Jumlah data valid: 396 / 397\n",
|
||||
"Jumlah data tidak valid: 1\n",
|
||||
"\n",
|
||||
"Distribusi Tipe Soal:\n",
|
||||
"- isian: 390\n",
|
||||
"- opsi: 4\n",
|
||||
"- true_false: 2\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import json\n",
|
||||
"from collections import Counter\n",
|
||||
"\n",
|
||||
"# Load raw data\n",
|
||||
"with open(\"qg_dataset.json\", encoding=\"utf-8\") as f:\n",
|
||||
"with open(\"../../dataset/dev_dataset_qg.json\", encoding=\"utf-8\") as f:\n",
|
||||
" raw_data = json.load(f)\n",
|
||||
"\n",
|
||||
"# Validasi lengkap\n",
|
||||
"required_keys = {\"tokens\", \"ner\", \"srl\", \"question\", \"answer\", \"type\"}\n",
|
||||
"required_keys = {\"tokens\", \"ner\", \"srl\", \"quiz_possibility\"}\n",
|
||||
"valid_data = []\n",
|
||||
"invalid_data = []\n",
|
||||
"\n",
|
||||
|
|
@ -61,23 +129,48 @@
|
|||
"\n",
|
||||
" if not isinstance(item, dict):\n",
|
||||
" error_messages.append(\"bukan dictionary\")\n",
|
||||
" invalid_data.append(item)\n",
|
||||
" continue\n",
|
||||
"\n",
|
||||
" missing_keys = required_keys - item.keys()\n",
|
||||
" if missing_keys:\n",
|
||||
" error_messages.append(f\"missing keys: {missing_keys}\")\n",
|
||||
"\n",
|
||||
" if not error_messages:\n",
|
||||
" # Cek tipe data dan None\n",
|
||||
" # Cek tipe data utama\n",
|
||||
" if (not isinstance(item[\"tokens\"], list) or\n",
|
||||
" not isinstance(item[\"ner\"], list) or\n",
|
||||
" not isinstance(item[\"srl\"], list) or\n",
|
||||
" not isinstance(item[\"question\"], list) or\n",
|
||||
" not isinstance(item[\"answer\"], list) or\n",
|
||||
" not isinstance(item[\"type\"], str)):\n",
|
||||
" error_messages.append(\"field type tidak sesuai\")\n",
|
||||
" \n",
|
||||
" not isinstance(item[\"quiz_possibility\"], list)):\n",
|
||||
" error_messages.append(\"field type tidak sesuai di level utama\")\n",
|
||||
"\n",
|
||||
" # Validasi quiz_possibility\n",
|
||||
" if not error_messages:\n",
|
||||
" if not item[\"quiz_possibility\"]:\n",
|
||||
" error_messages.append(\"quiz_possibility kosong\")\n",
|
||||
" else:\n",
|
||||
" quiz_item = item[\"quiz_possibility\"][0]\n",
|
||||
"\n",
|
||||
" # Validasi kunci di dalam quiz_possibility[0]\n",
|
||||
" expected_quiz_keys = {\"type\", \"question\", \"answer\"}\n",
|
||||
" missing_quiz_keys = expected_quiz_keys - quiz_item.keys()\n",
|
||||
"\n",
|
||||
" if missing_quiz_keys:\n",
|
||||
" error_messages.append(f\"missing keys di quiz_possibility[0]: {missing_quiz_keys}\")\n",
|
||||
" else:\n",
|
||||
" # Cek tipe data di quiz_possibility[0]\n",
|
||||
" if (not isinstance(quiz_item[\"type\"], str) or\n",
|
||||
" not isinstance(quiz_item[\"question\"], list) or\n",
|
||||
" not isinstance(quiz_item[\"answer\"], list)):\n",
|
||||
" error_messages.append(\"field type tidak sesuai di quiz_possibility[0]\")\n",
|
||||
" else:\n",
|
||||
" # Flatten ke struktur lama untuk konsistensi\n",
|
||||
" item[\"type\"] = quiz_item[\"type\"]\n",
|
||||
" item[\"question\"] = quiz_item[\"question\"]\n",
|
||||
" item[\"answer\"] = quiz_item[\"answer\"]\n",
|
||||
"\n",
|
||||
" if error_messages:\n",
|
||||
" print(f\"\\n Index {idx} | Masalah: {', '.join(error_messages)}\")\n",
|
||||
" print(f\"\\nIndex {idx} | Masalah: {', '.join(error_messages)}\")\n",
|
||||
" print(json.dumps(item, indent=2, ensure_ascii=False))\n",
|
||||
" invalid_data.append(item)\n",
|
||||
" continue\n",
|
||||
|
|
@ -85,8 +178,8 @@
|
|||
" valid_data.append(item)\n",
|
||||
"\n",
|
||||
"# Statistik\n",
|
||||
"print(f\"\\n Jumlah data valid: {len(valid_data)} / {len(raw_data)}\")\n",
|
||||
"print(f\" Jumlah data tidak valid: {len(invalid_data)}\")\n",
|
||||
"print(f\"\\nJumlah data valid: {len(valid_data)} / {len(raw_data)}\")\n",
|
||||
"print(f\"Jumlah data tidak valid: {len(invalid_data)}\")\n",
|
||||
"\n",
|
||||
"# Proses data valid\n",
|
||||
"tokens = [[t.lower().strip() for t in item[\"tokens\"]] for item in valid_data]\n",
|
||||
|
|
@ -94,16 +187,26 @@
|
|||
"srl_tags = [item[\"srl\"] for item in valid_data]\n",
|
||||
"questions = [[token.lower().strip() for token in item[\"question\"]] for item in valid_data]\n",
|
||||
"answers = [[token.lower().strip() for token in item[\"answer\"]] for item in valid_data]\n",
|
||||
"types = [item[\"type\"] for item in valid_data]\n",
|
||||
"types = [item[\"type\"].lower().strip() for item in valid_data] # Konsistensi lowercase untuk tipe\n",
|
||||
"\n",
|
||||
"# Statistik tipe soal\n",
|
||||
"type_counts = Counter(types)\n",
|
||||
"print(\"\\nDistribusi Tipe Soal:\")\n",
|
||||
"for t, count in type_counts.items():\n",
|
||||
" print(f\"- {t}: {count}\")\n",
|
||||
"\n",
|
||||
"print(type_counts)\n"
|
||||
"# (Opsional) Simpan data valid\n",
|
||||
"with open(\"cleaned_qg_dataset.json\", \"w\", encoding=\"utf-8\") as f:\n",
|
||||
" json.dump(valid_data, f, ensure_ascii=False, indent=2)\n",
|
||||
"\n",
|
||||
"# (Opsional) Simpan data tidak valid untuk analisa\n",
|
||||
"with open(\"invalid_qg_dataset.json\", \"w\", encoding=\"utf-8\") as f:\n",
|
||||
" json.dump(invalid_data, f, ensure_ascii=False, indent=2)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 53,
|
||||
"execution_count": 23,
|
||||
"id": "4e3a0088",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
|
|
@ -129,7 +232,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 54,
|
||||
"execution_count": 24,
|
||||
"id": "555f9e22",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
|
|
@ -137,7 +240,7 @@
|
|||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{'isian', 'tof', 'opsi'}\n"
|
||||
"{'opsi', 'isian', 'true_false'}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -164,7 +267,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 55,
|
||||
"execution_count": 25,
|
||||
"id": "f530cfe7",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
|
|
@ -180,18 +283,18 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 56,
|
||||
"execution_count": 26,
|
||||
"id": "255e2a9a",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"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\">Model: \"functional_5\"</span>\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\">Model: \"functional_1\"</span>\n",
|
||||
"</pre>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"\u001b[1mModel: \"functional_5\"\u001b[0m\n"
|
||||
"\u001b[1mModel: \"functional_1\"\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
|
|
@ -212,31 +315,31 @@
|
|||
"│ 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_15 │ (<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\">41,600</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_3 │ (<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\">116,992</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_16 │ (<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> │ ner_input[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
|
||||
"│ embedding_4 │ (<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\">704</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_17 │ (<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_5 │ (<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\">336</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_5 │ (<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_15[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">…</span> │\n",
|
||||
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Concatenate</span>) │ │ │ embedding_16[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">…</span> │\n",
|
||||
"│ │ │ │ embedding_17[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">…</span> │\n",
|
||||
"│ concatenate_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\">160</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ embedding_3[<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\">Concatenate</span>) │ │ │ embedding_4[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>… │\n",
|
||||
"│ │ │ │ embedding_5[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
|
||||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||||
"│ lstm_5 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">LSTM</span>) │ (<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\">256</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">427,008</span> │ concatenate_5[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]… │\n",
|
||||
"│ lstm_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">LSTM</span>) │ (<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\">256</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">427,008</span> │ concatenate_1[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]… │\n",
|
||||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||||
"│ get_item_5 │ (<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_5[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
|
||||
"│ get_item_1 │ (<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_1[<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\">GetItem</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\">272</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">69,904</span> │ lstm_5[<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\">479</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">123,103</span> │ lstm_1[<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\">60</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">15,420</span> │ lstm_5[<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\">308</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">79,156</span> │ lstm_1[<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_5[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\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\">4</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">1,028</span> │ get_item_1[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
|
||||
"└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n",
|
||||
"</pre>\n"
|
||||
],
|
||||
|
|
@ -253,31 +356,31 @@
|
|||
"│ 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_15 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m41,600\u001b[0m │ tok_input[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
||||
"│ embedding_3 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m116,992\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_16 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m) │ \u001b[38;5;34m272\u001b[0m │ ner_input[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
||||
"│ embedding_4 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m) │ \u001b[38;5;34m704\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_17 │ (\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_5 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m) │ \u001b[38;5;34m336\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_5 │ (\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_15[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m…\u001b[0m │\n",
|
||||
"│ (\u001b[38;5;33mConcatenate\u001b[0m) │ │ │ embedding_16[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m…\u001b[0m │\n",
|
||||
"│ │ │ │ embedding_17[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m…\u001b[0m │\n",
|
||||
"│ concatenate_1 │ (\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_3[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m… │\n",
|
||||
"│ (\u001b[38;5;33mConcatenate\u001b[0m) │ │ │ embedding_4[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m… │\n",
|
||||
"│ │ │ │ embedding_5[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
||||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||||
"│ lstm_5 (\u001b[38;5;33mLSTM\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m427,008\u001b[0m │ concatenate_5[\u001b[38;5;34m0\u001b[0m]… │\n",
|
||||
"│ lstm_1 (\u001b[38;5;33mLSTM\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m427,008\u001b[0m │ concatenate_1[\u001b[38;5;34m0\u001b[0m]… │\n",
|
||||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||||
"│ get_item_5 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ lstm_5[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
||||
"│ get_item_1 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ lstm_1[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
||||
"│ (\u001b[38;5;33mGetItem\u001b[0m) │ │ │ │\n",
|
||||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||||
"│ question_output │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m272\u001b[0m) │ \u001b[38;5;34m69,904\u001b[0m │ lstm_5[\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;34m479\u001b[0m) │ \u001b[38;5;34m123,103\u001b[0m │ lstm_1[\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;34m60\u001b[0m) │ \u001b[38;5;34m15,420\u001b[0m │ lstm_5[\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;34m308\u001b[0m) │ \u001b[38;5;34m79,156\u001b[0m │ lstm_1[\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_5[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
||||
"│ type_output (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m) │ \u001b[38;5;34m1,028\u001b[0m │ get_item_1[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
||||
"└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n"
|
||||
]
|
||||
},
|
||||
|
|
@ -287,11 +390,11 @@
|
|||
{
|
||||
"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\">555,247</span> (2.12 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\">748,327</span> (2.85 MB)\n",
|
||||
"</pre>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m555,247\u001b[0m (2.12 MB)\n"
|
||||
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m748,327\u001b[0m (2.85 MB)\n"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
|
|
@ -300,11 +403,11 @@
|
|||
{
|
||||
"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\">555,247</span> (2.12 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\">748,327</span> (2.85 MB)\n",
|
||||
"</pre>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m555,247\u001b[0m (2.12 MB)\n"
|
||||
"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m748,327\u001b[0m (2.85 MB)\n"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
|
|
@ -328,61 +431,65 @@
|
|||
"output_type": "stream",
|
||||
"text": [
|
||||
"Epoch 1/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 3s/step - answer_output_accuracy: 0.0030 - answer_output_loss: 4.1163 - loss: 10.8193 - question_output_accuracy: 0.0030 - question_output_loss: 5.6031 - type_output_accuracy: 0.2000 - type_output_loss: 1.0999 - val_answer_output_accuracy: 0.8833 - val_answer_output_loss: 4.0123 - val_loss: 10.6706 - val_question_output_accuracy: 0.6000 - val_question_output_loss: 5.5595 - val_type_output_accuracy: 0.1667 - val_type_output_loss: 1.0987\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 176ms/step - answer_output_accuracy: 0.4544 - answer_output_loss: 5.6455 - loss: 13.1436 - question_output_accuracy: 0.3565 - question_output_loss: 6.1017 - type_output_accuracy: 0.6386 - type_output_loss: 1.3766 - val_answer_output_accuracy: 0.9141 - val_answer_output_loss: 5.0547 - val_loss: 12.0109 - val_question_output_accuracy: 0.6844 - val_question_output_loss: 5.6110 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 1.3453\n",
|
||||
"Epoch 2/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 95ms/step - answer_output_accuracy: 0.8800 - answer_output_loss: 4.0174 - loss: 10.6778 - question_output_accuracy: 0.5640 - question_output_loss: 5.5631 - type_output_accuracy: 0.4200 - type_output_loss: 1.0973 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 3.8939 - val_loss: 10.4860 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 5.4945 - val_type_output_accuracy: 0.3333 - val_type_output_loss: 1.0976\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - answer_output_accuracy: 0.9145 - answer_output_loss: 4.3849 - loss: 10.8584 - question_output_accuracy: 0.6760 - question_output_loss: 5.0255 - type_output_accuracy: 0.9758 - type_output_loss: 1.3371 - val_answer_output_accuracy: 0.9141 - val_answer_output_loss: 2.1055 - val_loss: 6.1782 - val_question_output_accuracy: 0.6844 - val_question_output_loss: 2.7704 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 1.3023\n",
|
||||
"Epoch 3/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 91ms/step - answer_output_accuracy: 0.9370 - answer_output_loss: 3.9075 - loss: 10.5064 - question_output_accuracy: 0.5870 - question_output_loss: 5.5043 - type_output_accuracy: 0.6200 - type_output_loss: 1.0946 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 3.7157 - val_loss: 10.1938 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 5.3815 - val_type_output_accuracy: 0.3333 - val_type_output_loss: 1.0965\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - answer_output_accuracy: 0.9095 - answer_output_loss: 1.7129 - loss: 5.4664 - question_output_accuracy: 0.6777 - question_output_loss: 2.4346 - type_output_accuracy: 0.9795 - type_output_loss: 1.2889 - val_answer_output_accuracy: 0.9141 - val_answer_output_loss: 1.0023 - val_loss: 4.2358 - val_question_output_accuracy: 0.6844 - val_question_output_loss: 2.0019 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 1.2316\n",
|
||||
"Epoch 4/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 90ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 3.7435 - loss: 10.2381 - question_output_accuracy: 0.5890 - question_output_loss: 5.4027 - type_output_accuracy: 0.6200 - type_output_loss: 1.0919 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 3.4257 - val_loss: 9.7085 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 5.1873 - val_type_output_accuracy: 0.3333 - val_type_output_loss: 1.0955\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - answer_output_accuracy: 0.9140 - answer_output_loss: 0.9210 - loss: 4.2240 - question_output_accuracy: 0.6804 - question_output_loss: 2.1028 - type_output_accuracy: 0.9812 - type_output_loss: 1.2037 - val_answer_output_accuracy: 0.9141 - val_answer_output_loss: 0.7526 - val_loss: 4.0127 - val_question_output_accuracy: 0.6844 - val_question_output_loss: 2.1652 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 1.0949\n",
|
||||
"Epoch 5/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 90ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 3.4788 - loss: 9.7970 - question_output_accuracy: 0.5850 - question_output_loss: 5.2288 - type_output_accuracy: 0.6600 - type_output_loss: 1.0894 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 2.9617 - val_loss: 8.9146 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 4.8585 - val_type_output_accuracy: 0.3333 - val_type_output_loss: 1.0944\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step - answer_output_accuracy: 0.9131 - answer_output_loss: 0.7388 - loss: 4.0409 - question_output_accuracy: 0.6753 - question_output_loss: 2.2497 - type_output_accuracy: 0.9832 - type_output_loss: 1.0455 - val_answer_output_accuracy: 0.9141 - val_answer_output_loss: 0.6789 - val_loss: 3.6821 - val_question_output_accuracy: 0.6844 - val_question_output_loss: 2.1028 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.9003\n",
|
||||
"Epoch 6/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 95ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 3.0565 - loss: 9.0790 - question_output_accuracy: 0.5850 - question_output_loss: 4.9355 - type_output_accuracy: 0.6600 - type_output_loss: 1.0869 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 2.3649 - val_loss: 7.8024 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 4.3441 - val_type_output_accuracy: 0.3333 - val_type_output_loss: 1.0933\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step - answer_output_accuracy: 0.9190 - answer_output_loss: 0.6585 - loss: 3.5809 - question_output_accuracy: 0.6788 - question_output_loss: 2.0865 - type_output_accuracy: 0.9797 - type_output_loss: 0.8341 - val_answer_output_accuracy: 0.9141 - val_answer_output_loss: 0.6491 - val_loss: 3.3418 - val_question_output_accuracy: 0.6844 - val_question_output_loss: 2.0148 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.6779\n",
|
||||
"Epoch 7/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 95ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 2.5004 - loss: 8.0585 - question_output_accuracy: 0.5850 - question_output_loss: 4.4735 - type_output_accuracy: 0.6600 - type_output_loss: 1.0845 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 1.8898 - val_loss: 6.6823 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 3.7005 - val_type_output_accuracy: 0.3333 - val_type_output_loss: 1.0920\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - answer_output_accuracy: 0.9165 - answer_output_loss: 0.6312 - loss: 3.2776 - question_output_accuracy: 0.6763 - question_output_loss: 2.0259 - type_output_accuracy: 0.9695 - type_output_loss: 0.6233 - val_answer_output_accuracy: 0.9141 - val_answer_output_loss: 0.6313 - val_loss: 3.1431 - val_question_output_accuracy: 0.6844 - val_question_output_loss: 2.0432 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.4687\n",
|
||||
"Epoch 8/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 88ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 2.0239 - loss: 6.9823 - question_output_accuracy: 0.5850 - question_output_loss: 3.8764 - type_output_accuracy: 0.6600 - type_output_loss: 1.0821 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 1.5873 - val_loss: 5.7713 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 3.0934 - val_type_output_accuracy: 0.3333 - val_type_output_loss: 1.0906\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step - answer_output_accuracy: 0.9148 - answer_output_loss: 0.6209 - loss: 3.0631 - question_output_accuracy: 0.6762 - question_output_loss: 2.0136 - type_output_accuracy: 0.9708 - type_output_loss: 0.4301 - val_answer_output_accuracy: 0.9141 - val_answer_output_loss: 0.6193 - val_loss: 2.9071 - val_question_output_accuracy: 0.6844 - val_question_output_loss: 1.9849 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.3029\n",
|
||||
"Epoch 9/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 93ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 1.6939 - loss: 6.0594 - question_output_accuracy: 0.5850 - question_output_loss: 3.2857 - type_output_accuracy: 0.6600 - type_output_loss: 1.0798 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 1.3585 - val_loss: 5.0778 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 2.6303 - val_type_output_accuracy: 0.3333 - val_type_output_loss: 1.0890\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - answer_output_accuracy: 0.9155 - answer_output_loss: 0.6067 - loss: 2.7923 - question_output_accuracy: 0.6799 - question_output_loss: 1.9057 - type_output_accuracy: 0.9747 - type_output_loss: 0.2789 - val_answer_output_accuracy: 0.9141 - val_answer_output_loss: 0.6109 - val_loss: 2.7805 - val_question_output_accuracy: 0.6844 - val_question_output_loss: 1.9768 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.1928\n",
|
||||
"Epoch 10/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 97ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 1.4268 - loss: 5.3244 - question_output_accuracy: 0.5850 - question_output_loss: 2.8203 - type_output_accuracy: 0.6600 - type_output_loss: 1.0774 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 1.1559 - val_loss: 4.5630 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 2.3200 - val_type_output_accuracy: 0.3333 - val_type_output_loss: 1.0871\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - answer_output_accuracy: 0.9160 - answer_output_loss: 0.5715 - loss: 2.6738 - question_output_accuracy: 0.6770 - question_output_loss: 1.9091 - type_output_accuracy: 0.9784 - type_output_loss: 0.1873 - val_answer_output_accuracy: 0.9141 - val_answer_output_loss: 0.6033 - val_loss: 2.6801 - val_question_output_accuracy: 0.6844 - val_question_output_loss: 1.9506 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.1262\n",
|
||||
"Epoch 11/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 93ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 1.1880 - loss: 4.7795 - question_output_accuracy: 0.5850 - question_output_loss: 2.5167 - type_output_accuracy: 0.6600 - type_output_loss: 1.0748 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 0.9716 - val_loss: 4.2001 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 2.1437 - val_type_output_accuracy: 0.3333 - val_type_output_loss: 1.0848\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - answer_output_accuracy: 0.9159 - answer_output_loss: 0.5691 - loss: 2.5854 - question_output_accuracy: 0.6791 - question_output_loss: 1.8621 - type_output_accuracy: 0.9743 - type_output_loss: 0.1495 - val_answer_output_accuracy: 0.9141 - val_answer_output_loss: 0.5962 - val_loss: 2.5971 - val_question_output_accuracy: 0.7031 - val_question_output_loss: 1.9119 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0890\n",
|
||||
"Epoch 12/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 95ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 0.9857 - loss: 4.4356 - question_output_accuracy: 0.5850 - question_output_loss: 2.3778 - type_output_accuracy: 0.6600 - type_output_loss: 1.0721 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 0.8171 - val_loss: 3.9799 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 2.0807 - val_type_output_accuracy: 0.3333 - val_type_output_loss: 1.0822\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - answer_output_accuracy: 0.9151 - answer_output_loss: 0.5528 - loss: 2.4857 - question_output_accuracy: 0.6954 - question_output_loss: 1.8064 - type_output_accuracy: 0.9765 - type_output_loss: 0.1240 - val_answer_output_accuracy: 0.9141 - val_answer_output_loss: 0.5907 - val_loss: 2.5231 - val_question_output_accuracy: 0.7031 - val_question_output_loss: 1.8654 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0670\n",
|
||||
"Epoch 13/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 92ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 0.8280 - loss: 4.2715 - question_output_accuracy: 0.5850 - question_output_loss: 2.3745 - type_output_accuracy: 0.6600 - type_output_loss: 1.0690 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 0.6995 - val_loss: 3.8760 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 2.0974 - val_type_output_accuracy: 0.3333 - val_type_output_loss: 1.0790\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - answer_output_accuracy: 0.9116 - answer_output_loss: 0.5741 - loss: 2.4910 - question_output_accuracy: 0.6913 - question_output_loss: 1.7912 - type_output_accuracy: 0.9721 - type_output_loss: 0.1279 - val_answer_output_accuracy: 0.9141 - val_answer_output_loss: 0.5874 - val_loss: 2.4624 - val_question_output_accuracy: 0.7031 - val_question_output_loss: 1.8207 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0543\n",
|
||||
"Epoch 14/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 91ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 0.7110 - loss: 4.2264 - question_output_accuracy: 0.5850 - question_output_loss: 2.4498 - type_output_accuracy: 0.6400 - type_output_loss: 1.0656 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 0.6143 - val_loss: 3.8415 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 2.1518 - val_type_output_accuracy: 0.5000 - val_type_output_loss: 1.0754\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step - answer_output_accuracy: 0.9142 - answer_output_loss: 0.5370 - loss: 2.4278 - question_output_accuracy: 0.6900 - question_output_loss: 1.7686 - type_output_accuracy: 0.9730 - type_output_loss: 0.1186 - val_answer_output_accuracy: 0.9141 - val_answer_output_loss: 0.5837 - val_loss: 2.4136 - val_question_output_accuracy: 0.7031 - val_question_output_loss: 1.7833 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0466\n",
|
||||
"Epoch 15/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 95ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 0.6254 - loss: 4.2353 - question_output_accuracy: 0.5850 - question_output_loss: 2.5482 - type_output_accuracy: 0.6000 - type_output_loss: 1.0617 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 0.5529 - val_loss: 3.8335 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 2.2091 - val_type_output_accuracy: 0.5000 - val_type_output_loss: 1.0714\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - answer_output_accuracy: 0.9160 - answer_output_loss: 0.5186 - loss: 2.3183 - question_output_accuracy: 0.6898 - question_output_loss: 1.7028 - type_output_accuracy: 0.9784 - type_output_loss: 0.1001 - val_answer_output_accuracy: 0.9141 - val_answer_output_loss: 0.5794 - val_loss: 2.3714 - val_question_output_accuracy: 0.7109 - val_question_output_loss: 1.7506 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0414\n",
|
||||
"Epoch 16/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 94ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 0.5623 - loss: 4.2530 - question_output_accuracy: 0.5850 - question_output_loss: 2.6334 - type_output_accuracy: 0.6000 - type_output_loss: 1.0573 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 0.5083 - val_loss: 3.8255 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 2.2502 - val_type_output_accuracy: 0.5000 - val_type_output_loss: 1.0670\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - answer_output_accuracy: 0.9171 - answer_output_loss: 0.5077 - loss: 2.2275 - question_output_accuracy: 0.7036 - question_output_loss: 1.6393 - type_output_accuracy: 0.9791 - type_output_loss: 0.0876 - val_answer_output_accuracy: 0.9141 - val_answer_output_loss: 0.5748 - val_loss: 2.3340 - val_question_output_accuracy: 0.7172 - val_question_output_loss: 1.7214 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0379\n",
|
||||
"Epoch 17/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 96ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 0.5150 - loss: 4.2561 - question_output_accuracy: 0.5850 - question_output_loss: 2.6886 - type_output_accuracy: 0.6000 - type_output_loss: 1.0525 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 0.4752 - val_loss: 3.8053 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 2.2678 - val_type_output_accuracy: 0.5000 - val_type_output_loss: 1.0623\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - answer_output_accuracy: 0.9137 - answer_output_loss: 0.5248 - loss: 2.2290 - question_output_accuracy: 0.7070 - question_output_loss: 1.6285 - type_output_accuracy: 0.9828 - type_output_loss: 0.0771 - val_answer_output_accuracy: 0.9219 - val_answer_output_loss: 0.5716 - val_loss: 2.3017 - val_question_output_accuracy: 0.7172 - val_question_output_loss: 1.6946 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0355\n",
|
||||
"Epoch 18/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 104ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 0.4790 - loss: 4.2357 - question_output_accuracy: 0.5850 - question_output_loss: 2.7094 - type_output_accuracy: 0.6000 - type_output_loss: 1.0473 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 0.4503 - val_loss: 3.7689 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 2.2612 - val_type_output_accuracy: 0.5000 - val_type_output_loss: 1.0573\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - answer_output_accuracy: 0.9233 - answer_output_loss: 0.5080 - loss: 2.2392 - question_output_accuracy: 0.7059 - question_output_loss: 1.6139 - type_output_accuracy: 0.9678 - type_output_loss: 0.1205 - val_answer_output_accuracy: 0.9219 - val_answer_output_loss: 0.5676 - val_loss: 2.2777 - val_question_output_accuracy: 0.7219 - val_question_output_loss: 1.6760 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0341\n",
|
||||
"Epoch 19/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 94ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 0.4511 - loss: 4.1904 - question_output_accuracy: 0.5850 - question_output_loss: 2.6974 - type_output_accuracy: 0.5600 - type_output_loss: 1.0419 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 0.4313 - val_loss: 3.7162 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 2.2327 - val_type_output_accuracy: 0.5000 - val_type_output_loss: 1.0523\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step - answer_output_accuracy: 0.9221 - answer_output_loss: 0.5038 - loss: 2.1188 - question_output_accuracy: 0.7131 - question_output_loss: 1.5706 - type_output_accuracy: 0.9854 - type_output_loss: 0.0616 - val_answer_output_accuracy: 0.9219 - val_answer_output_loss: 0.5639 - val_loss: 2.2545 - val_question_output_accuracy: 0.7203 - val_question_output_loss: 1.6580 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0326\n",
|
||||
"Epoch 20/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 94ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 0.4293 - loss: 4.1218 - question_output_accuracy: 0.5850 - question_output_loss: 2.6564 - type_output_accuracy: 0.5600 - type_output_loss: 1.0361 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 0.4164 - val_loss: 3.6494 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 2.1859 - val_type_output_accuracy: 0.5000 - val_type_output_loss: 1.0471\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - answer_output_accuracy: 0.9175 - answer_output_loss: 0.5233 - loss: 2.1645 - question_output_accuracy: 0.7128 - question_output_loss: 1.5526 - type_output_accuracy: 0.9775 - type_output_loss: 0.0858 - val_answer_output_accuracy: 0.9219 - val_answer_output_loss: 0.5603 - val_loss: 2.2376 - val_question_output_accuracy: 0.7234 - val_question_output_loss: 1.6450 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0323\n",
|
||||
"Epoch 21/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 93ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 0.4118 - loss: 4.0332 - question_output_accuracy: 0.5850 - question_output_loss: 2.5912 - type_output_accuracy: 0.5600 - type_output_loss: 1.0302 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 0.4046 - val_loss: 3.5722 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 2.1256 - val_type_output_accuracy: 0.5000 - val_type_output_loss: 1.0420\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - answer_output_accuracy: 0.9193 - answer_output_loss: 0.5090 - loss: 2.1288 - question_output_accuracy: 0.7118 - question_output_loss: 1.5447 - type_output_accuracy: 0.9828 - type_output_loss: 0.0644 - val_answer_output_accuracy: 0.9219 - val_answer_output_loss: 0.5568 - val_loss: 2.2206 - val_question_output_accuracy: 0.7219 - val_question_output_loss: 1.6317 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0321\n",
|
||||
"Epoch 22/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 95ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 0.3975 - loss: 3.9297 - question_output_accuracy: 0.5850 - question_output_loss: 2.5080 - type_output_accuracy: 0.5600 - type_output_loss: 1.0242 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 0.3951 - val_loss: 3.4909 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 2.0587 - val_type_output_accuracy: 0.5000 - val_type_output_loss: 1.0370\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - answer_output_accuracy: 0.9204 - answer_output_loss: 0.4971 - loss: 2.0726 - question_output_accuracy: 0.7128 - question_output_loss: 1.5100 - type_output_accuracy: 0.9817 - type_output_loss: 0.0626 - val_answer_output_accuracy: 0.9219 - val_answer_output_loss: 0.5535 - val_loss: 2.2055 - val_question_output_accuracy: 0.7359 - val_question_output_loss: 1.6200 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0320\n",
|
||||
"Epoch 23/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 94ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 0.3858 - loss: 3.8184 - question_output_accuracy: 0.5850 - question_output_loss: 2.4147 - type_output_accuracy: 0.5600 - type_output_loss: 1.0180 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 0.3875 - val_loss: 3.4143 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 1.9948 - val_type_output_accuracy: 0.5000 - val_type_output_loss: 1.0321\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step - answer_output_accuracy: 0.9191 - answer_output_loss: 0.5003 - loss: 2.1218 - question_output_accuracy: 0.7108 - question_output_loss: 1.5310 - type_output_accuracy: 0.9762 - type_output_loss: 0.0771 - val_answer_output_accuracy: 0.9219 - val_answer_output_loss: 0.5517 - val_loss: 2.1920 - val_question_output_accuracy: 0.7234 - val_question_output_loss: 1.6081 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0322\n",
|
||||
"Epoch 24/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 91ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 0.3759 - loss: 3.7097 - question_output_accuracy: 0.5850 - question_output_loss: 2.3222 - type_output_accuracy: 0.5600 - type_output_loss: 1.0116 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 0.3812 - val_loss: 3.3557 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 1.9473 - val_type_output_accuracy: 0.5000 - val_type_output_loss: 1.0273\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step - answer_output_accuracy: 0.9220 - answer_output_loss: 0.4808 - loss: 2.0044 - question_output_accuracy: 0.7175 - question_output_loss: 1.4722 - type_output_accuracy: 0.9810 - type_output_loss: 0.0608 - val_answer_output_accuracy: 0.9219 - val_answer_output_loss: 0.5494 - val_loss: 2.1723 - val_question_output_accuracy: 0.7312 - val_question_output_loss: 1.5905 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0323\n",
|
||||
"Epoch 25/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 95ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 0.3674 - loss: 3.6180 - question_output_accuracy: 0.5850 - question_output_loss: 2.2455 - type_output_accuracy: 0.5600 - type_output_loss: 1.0051 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 0.3759 - val_loss: 3.3316 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 1.9330 - val_type_output_accuracy: 0.5000 - val_type_output_loss: 1.0227\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step - answer_output_accuracy: 0.9183 - answer_output_loss: 0.4965 - loss: 2.0500 - question_output_accuracy: 0.7174 - question_output_loss: 1.4835 - type_output_accuracy: 0.9775 - type_output_loss: 0.0676 - val_answer_output_accuracy: 0.9219 - val_answer_output_loss: 0.5473 - val_loss: 2.1609 - val_question_output_accuracy: 0.7328 - val_question_output_loss: 1.5810 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0326\n",
|
||||
"Epoch 26/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 96ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 0.3600 - loss: 3.5615 - question_output_accuracy: 0.5850 - question_output_loss: 2.2030 - type_output_accuracy: 0.5400 - type_output_loss: 0.9985 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 0.3715 - val_loss: 3.3519 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 1.9622 - val_type_output_accuracy: 0.5000 - val_type_output_loss: 1.0183\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step - answer_output_accuracy: 0.9236 - answer_output_loss: 0.4672 - loss: 1.9620 - question_output_accuracy: 0.7220 - question_output_loss: 1.4313 - type_output_accuracy: 0.9780 - type_output_loss: 0.0672 - val_answer_output_accuracy: 0.9219 - val_answer_output_loss: 0.5454 - val_loss: 2.1488 - val_question_output_accuracy: 0.7344 - val_question_output_loss: 1.5705 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0328\n",
|
||||
"Epoch 27/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 90ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 0.3534 - loss: 3.5516 - question_output_accuracy: 0.5850 - question_output_loss: 2.2064 - type_output_accuracy: 0.5400 - type_output_loss: 0.9917 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 0.3677 - val_loss: 3.4014 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 2.0195 - val_type_output_accuracy: 0.5000 - val_type_output_loss: 1.0141\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 70ms/step - answer_output_accuracy: 0.9219 - answer_output_loss: 0.4671 - loss: 1.9415 - question_output_accuracy: 0.7288 - question_output_loss: 1.4130 - type_output_accuracy: 0.9765 - type_output_loss: 0.0605 - val_answer_output_accuracy: 0.9219 - val_answer_output_loss: 0.5440 - val_loss: 2.1382 - val_question_output_accuracy: 0.7359 - val_question_output_loss: 1.5615 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0327\n",
|
||||
"Epoch 28/30\n",
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 96ms/step - answer_output_accuracy: 0.9380 - answer_output_loss: 0.3474 - loss: 3.5737 - question_output_accuracy: 0.5850 - question_output_loss: 2.2414 - type_output_accuracy: 0.5400 - type_output_loss: 0.9848 - val_answer_output_accuracy: 0.9250 - val_answer_output_loss: 0.3645 - val_loss: 3.4429 - val_question_output_accuracy: 0.6250 - val_question_output_loss: 2.0682 - val_type_output_accuracy: 0.5000 - val_type_output_loss: 1.0102\n"
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step - answer_output_accuracy: 0.9212 - answer_output_loss: 0.4676 - loss: 1.9277 - question_output_accuracy: 0.7271 - question_output_loss: 1.4106 - type_output_accuracy: 0.9823 - type_output_loss: 0.0526 - val_answer_output_accuracy: 0.9219 - val_answer_output_loss: 0.5435 - val_loss: 2.1317 - val_question_output_accuracy: 0.7422 - val_question_output_loss: 1.5559 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0323\n",
|
||||
"Epoch 29/30\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step - answer_output_accuracy: 0.9228 - answer_output_loss: 0.4658 - loss: 1.8773 - question_output_accuracy: 0.7397 - question_output_loss: 1.3683 - type_output_accuracy: 0.9823 - type_output_loss: 0.0487 - val_answer_output_accuracy: 0.9219 - val_answer_output_loss: 0.5428 - val_loss: 2.1239 - val_question_output_accuracy: 0.7437 - val_question_output_loss: 1.5493 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0319\n",
|
||||
"Epoch 30/30\n",
|
||||
"\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step - answer_output_accuracy: 0.9207 - answer_output_loss: 0.4658 - loss: 1.9146 - question_output_accuracy: 0.7355 - question_output_loss: 1.3799 - type_output_accuracy: 0.9795 - type_output_loss: 0.0563 - val_answer_output_accuracy: 0.9219 - val_answer_output_loss: 0.5421 - val_loss: 2.1174 - val_question_output_accuracy: 0.7437 - val_question_output_loss: 1.5436 - val_type_output_accuracy: 1.0000 - val_type_output_loss: 0.0317\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -463,7 +570,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 57,
|
||||
"execution_count": 27,
|
||||
"id": "06fd86c7",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
|
|
@ -471,12 +578,12 @@
|
|||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 239ms/step\n",
|
||||
"\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 137ms/step\n",
|
||||
"\n",
|
||||
"=== Akurasi Detail ===\n",
|
||||
"Question Accuracy (Token-level): 0.0000\n",
|
||||
"Answer Accuracy (Token-level) : 0.0000\n",
|
||||
"Type Accuracy (Class-level) : 0.29\n"
|
||||
"Question Accuracy (Token-level): 0.1519\n",
|
||||
"Answer Accuracy (Token-level) : 0.0638\n",
|
||||
"Type Accuracy (Class-level) : 1.00\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -519,7 +626,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 58,
|
||||
"execution_count": 28,
|
||||
"id": "b17b6470",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
|
|
@ -548,7 +655,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 59,
|
||||
"execution_count": 29,
|
||||
"id": "d5ed106c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
|
|
@ -561,7 +668,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 60,
|
||||
"execution_count": 30,
|
||||
"id": "aa3860de",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
|
|
|
|||
|
|
@ -6,10 +6,10 @@ import numpy as np
|
|||
|
||||
def infer_from_input(input_data, maxlen=50):
|
||||
|
||||
with open("QC/tokenizers.pkl", "rb") as f:
|
||||
with open("tokenizers.pkl", "rb") as f:
|
||||
tokenizers = pickle.load(f)
|
||||
|
||||
model = load_model("QC/new_model_lstm_qg.keras")
|
||||
model = load_model("new_model_lstm_qg.keras")
|
||||
|
||||
tok_token = tokenizers["token"]
|
||||
tok_ner = tokenizers["ner"]
|
||||
|
|
@ -62,9 +62,37 @@ if __name__ == "__main__":
|
|||
|
||||
# Example input
|
||||
input_data = {
|
||||
"tokens": ["Nama", "lengkap", "saya", "adalah", "Bayu", "Prabowo", "."],
|
||||
"ner": ["O", "O", "O", "O", "B-PER", "I-PER", "O"],
|
||||
"srl": ["ARG1", "ARG1", "ARG2", "V", "ARG0", "ARG0", "O"],
|
||||
"tokens": [
|
||||
"Mars",
|
||||
"disebut",
|
||||
"juga",
|
||||
"sebagai",
|
||||
"planet",
|
||||
"merah",
|
||||
"karena",
|
||||
"permukaannya",
|
||||
"banyak",
|
||||
"mengandung",
|
||||
"zat",
|
||||
"besi",
|
||||
".",
|
||||
],
|
||||
"ner": ["B-LOC", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O"],
|
||||
"srl": [
|
||||
"ARG0",
|
||||
"V",
|
||||
"O",
|
||||
"O",
|
||||
"ARG1",
|
||||
"ARG1",
|
||||
"ARGM-CAU",
|
||||
"ARG1",
|
||||
"ARGM-MNR",
|
||||
"ARGM-MNR",
|
||||
"ARG1",
|
||||
"ARG1",
|
||||
"O",
|
||||
],
|
||||
}
|
||||
|
||||
# input_data = {
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
Binary file not shown.
|
Before Width: | Height: | Size: 50 KiB After Width: | Height: | Size: 50 KiB |
Loading…
Reference in New Issue