File size: 13,153 Bytes
26d475a 1cf0c70 26d475a 1cf0c70 26d475a 1cf0c70 26d475a 1cf0c70 26d475a eab759c 26d475a eab759c 26d475a f759a95 26d475a 1cf0c70 21982ea 9bc7615 df2ee29 a692f9c 9f309e4 9ecbaf0 1870fd6 5a79254 f759a95 26d475a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "b12ae8a3-9e08-402c-894c-31697fad6c56",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "eab00695e2b240ffb58ab998c85c0e7d",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from huggingface_hub import notebook_login\n",
"\n",
"notebook_login()"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "160c80c1-0ca4-45df-8171-87cd3c88a223",
"metadata": {},
"outputs": [],
"source": [
"\n",
"from transformers import (\n",
" AutoTokenizer,\n",
" DataCollatorWithPadding,\n",
" Trainer,\n",
" TrainingArguments,\n",
")\n",
"from utils import ConsistentSentenceRegressor, get_metrics, load_dataset"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "25800588-5d42-4524-9dc6-a6a0c180b8b0",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" text label\n",
"512 カーキ色の服を着た男性が、口元にリンゴを当てています。[SEP]カーキ色の服を着た男性が、口... 0.0\n",
"513 男性がグラウンドでボールを投げています。[SEP]白い髯を生やした男性がボールを投げています。 0.5\n",
"514 椅子に座った子供が、手づかみで食事をしています。[SEP]椅子に座った子供が手づかみで、食事... 1.0\n",
"515 プロペラ機が何台も駐機しています。[SEP]プロペラ機が何台も連なって飛んでいます。 0.0\n",
"516 消火栓から水が勢いよく噴き出しています。[SEP]水が噴き出している消火栓の水を浴びるように... 0.5\n",
"517 冷蔵庫のないキッチンにナイフとフォークが置かれています。[SEP]冷蔵庫の置かれたキッチンに... 0.0\n",
"518 うみでサーフィンをしているひとがいます。[SEP]黒いウェットスーツを着た人がサーフボードに... 0.5\n",
"519 池から白い鳥が飛び立っています。[SEP]森にある水の上を鳥が飛んでいます。 0.5\n",
"520 丈夫なビーチパラソルが立っています。[SEP]ビーチパラソルの支柱が折れ曲がっています。 0.0\n",
"521 白髪の男性が少女から花束を受け取っています。[SEP]花束を持った男性の前に多くの子供たちが... 0.5\n",
" text label\n",
"0 赤いひとつの傘に、二人の人が入っています。[SEP]歩道を歩く通行人が傘をさして歩いています。 0.5\n",
"1 川を小さなボートが進んで行きます。[SEP]川を豪華客船が進んでいきます。 0.0\n",
"2 ゲレンデのこぶでスキージャンプしています。[SEP]雪上でモーグルを楽しむ水色のウェアを着た女性。 0.5\n",
"3 黒いお皿に乗っているピザをカットしています。[SEP]黒い皿の上にピザが盛られています。 1.0\n",
"4 女性が目を細めて携帯電話で話をしています。[SEP]目を細めた女性が携帯電話で話をしています。 1.0\n",
"5 バナナやパパイヤなどの果物が売られている。[SEP]台の上にはバナナなどの青果が並べられています。 0.5\n",
"6 ヘッドライトを点灯させた白いバスが駐車場に止まっています。[SEP]ライトを点灯させているバ... 1.0\n",
"7 水面の上に、カイトサーフィンの凧が揚がっています。[SEP]海の上に水上スポーツ用の凧が揚が... 0.5\n",
"8 ホットドッグを野外で食べている人たちです。[SEP]家の中でホットドッグを食べている。 0.0\n",
"9 草が生い茂っている所に、3頭のゾウがいます。[SEP]草むらの中に三頭のゾウが立っているとこ... 0.5\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "f20c88d0f96c4c06a9a0ddf835e544e3",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Map: 0%| | 0/19561 [00:00<?, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Asking to pad to max_length but no maximum length is provided and the model has no predefined maximum length. Default to no padding.\n",
"Asking to truncate to max_length but no maximum length is provided and the model has no predefined maximum length. Default to no truncation.\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "97591288ca9d40fd91e7737b41828f63",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Map: 0%| | 0/512 [00:00<?, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"tokenizer = AutoTokenizer.from_pretrained(\"line-corporation/line-distilbert-base-japanese\")\n",
"dataset = load_dataset('train-v1.1.json')\n",
"tokenized_dataset = dataset.map(\n",
" lambda examples: tokenizer(examples[\"text\"], padding='max_length', truncation=True), batched=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6bc83d4c-378c-4313-b641-8ead0c02f715",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"WARNING:root:XRT configuration not detected. Defaulting to preview PJRT runtime. To silence this warning and continue using PJRT, explicitly set PJRT_DEVICE to a supported device or configure XRT. To disable default device selection, set PJRT_SELECT_DEFAULT_DEVICE=0\n",
"WARNING:root:For more information about the status of PJRT, see https://github.com/pytorch/xla/blob/master/docs/pjrt.md\n",
"WARNING:root:Defaulting to PJRT_DEVICE=CPU\n"
]
},
{
"data": {
"text/html": [
"\n",
" <div>\n",
" \n",
" <progress value='7971' max='30600' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
" [ 7971/30600 16:14 < 46:07, 8.18 it/s, Epoch 26.05/100]\n",
" </div>\n",
" <table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: left;\">\n",
" <th>Epoch</th>\n",
" <th>Training Loss</th>\n",
" <th>Validation Loss</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <td>1</td>\n",
" <td>No log</td>\n",
" <td>0.085583</td>\n",
" </tr>\n",
" <tr>\n",
" <td>2</td>\n",
" <td>0.104100</td>\n",
" <td>0.081926</td>\n",
" </tr>\n",
" <tr>\n",
" <td>3</td>\n",
" <td>0.104100</td>\n",
" <td>0.079540</td>\n",
" </tr>\n",
" <tr>\n",
" <td>4</td>\n",
" <td>0.091900</td>\n",
" <td>0.078066</td>\n",
" </tr>\n",
" <tr>\n",
" <td>5</td>\n",
" <td>0.087600</td>\n",
" <td>0.076963</td>\n",
" </tr>\n",
" <tr>\n",
" <td>6</td>\n",
" <td>0.087600</td>\n",
" <td>0.075823</td>\n",
" </tr>\n",
" <tr>\n",
" <td>7</td>\n",
" <td>0.084500</td>\n",
" <td>0.075087</td>\n",
" </tr>\n",
" <tr>\n",
" <td>8</td>\n",
" <td>0.084500</td>\n",
" <td>0.075002</td>\n",
" </tr>\n",
" <tr>\n",
" <td>9</td>\n",
" <td>0.083000</td>\n",
" <td>0.073672</td>\n",
" </tr>\n",
" <tr>\n",
" <td>10</td>\n",
" <td>0.080900</td>\n",
" <td>0.073238</td>\n",
" </tr>\n",
" <tr>\n",
" <td>11</td>\n",
" <td>0.080900</td>\n",
" <td>0.072717</td>\n",
" </tr>\n",
" <tr>\n",
" <td>12</td>\n",
" <td>0.080200</td>\n",
" <td>0.072234</td>\n",
" </tr>\n",
" <tr>\n",
" <td>13</td>\n",
" <td>0.080200</td>\n",
" <td>0.071684</td>\n",
" </tr>\n",
" <tr>\n",
" <td>14</td>\n",
" <td>0.079700</td>\n",
" <td>0.072137</td>\n",
" </tr>\n",
" <tr>\n",
" <td>15</td>\n",
" <td>0.078000</td>\n",
" <td>0.071143</td>\n",
" </tr>\n",
" <tr>\n",
" <td>16</td>\n",
" <td>0.078000</td>\n",
" <td>0.070724</td>\n",
" </tr>\n",
" <tr>\n",
" <td>17</td>\n",
" <td>0.076500</td>\n",
" <td>0.070303</td>\n",
" </tr>\n",
" <tr>\n",
" <td>18</td>\n",
" <td>0.077400</td>\n",
" <td>0.069888</td>\n",
" </tr>\n",
" <tr>\n",
" <td>19</td>\n",
" <td>0.077400</td>\n",
" <td>0.069760</td>\n",
" </tr>\n",
" <tr>\n",
" <td>20</td>\n",
" <td>0.076200</td>\n",
" <td>0.069610</td>\n",
" </tr>\n",
" <tr>\n",
" <td>21</td>\n",
" <td>0.076200</td>\n",
" <td>0.069183</td>\n",
" </tr>\n",
" <tr>\n",
" <td>22</td>\n",
" <td>0.075600</td>\n",
" <td>0.069061</td>\n",
" </tr>\n",
" <tr>\n",
" <td>23</td>\n",
" <td>0.075600</td>\n",
" <td>0.068791</td>\n",
" </tr>\n",
" <tr>\n",
" <td>24</td>\n",
" <td>0.075600</td>\n",
" <td>0.068658</td>\n",
" </tr>\n",
" <tr>\n",
" <td>25</td>\n",
" <td>0.075000</td>\n",
" <td>0.068027</td>\n",
" </tr>\n",
" <tr>\n",
" <td>26</td>\n",
" <td>0.075000</td>\n",
" <td>0.068032</td>\n",
" </tr>\n",
" </tbody>\n",
"</table><p>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"model = ConsistentSentenceRegressor(\n",
" freeze_bert=True)\n",
"\n",
"training_args = TrainingArguments(\n",
" output_dir=\".\",\n",
" learning_rate=1e-5,\n",
" per_device_train_batch_size=64,\n",
" num_train_epochs=100,\n",
" weight_decay=0.02,\n",
" evaluation_strategy=\"epoch\",\n",
" eval_accumulation_steps=1,\n",
" save_strategy=\"epoch\",\n",
" load_best_model_at_end=True,\n",
" push_to_hub=True,\n",
")\n",
"\n",
"data_collator = DataCollatorWithPadding(tokenizer=tokenizer)\n",
"trainer = Trainer(\n",
" model=model,\n",
" args=training_args,\n",
" train_dataset=tokenized_dataset[\"train\"],\n",
" eval_dataset=tokenized_dataset[\"test\"],\n",
" tokenizer=tokenizer,\n",
" data_collator=data_collator,\n",
")\n",
"\n",
"trainer.train()\n",
"trainer.push_to_hub('factual-consistency-regression-ja')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a6eb93f7-5a38-49a2-be0d-e42267e23a0a",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "3638c8d8-fc85-4caf-83a4-4fd2ad6fb95d",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"environment": {
"kernel": "python3",
"name": "pytorch-gpu.2-0.m112",
"type": "gcloud",
"uri": "gcr.io/deeplearning-platform-release/pytorch-gpu.2-0:m112"
},
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|