Spaces:
Paused
Paused
File size: 29,453 Bytes
2f5127c |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Tune GPT2 to generate positive reviews\n",
"> Optimise GPT2 to produce positive IMDB movie reviews using a BERT sentiment classifier as a reward function."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<div style=\"text-align: center\">\n",
"<img src='https://huggingface.co/datasets/trl-lib/documentation-images/resolve/main/gpt2_bert_training.png' width='600'>\n",
"<p style=\"text-align: center;\"> <b>Figure:</b> Experiment setup to tune GPT2. The yellow arrows are outside the scope of this notebook, but the trained models are available through Hugging Face. </p>\n",
"</div>\n",
"\n",
"\n",
"In this notebook we fine-tune GPT2 (small) to generate positive movie reviews based on the IMDB dataset. The model gets the start of a real review and is tasked to produce positive continuations. To reward positive continuations we use a BERT classifier to analyse the sentiment of the produced sentences and use the classifier's outputs as rewards signals for PPO training."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Setup experiment"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Import dependencies"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%load_ext autoreload\n",
"%autoreload 2"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%pip install transformers trl wandb"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import torch\n",
"from tqdm import tqdm\n",
"import pandas as pd\n",
"\n",
"tqdm.pandas()\n",
"\n",
"from transformers import pipeline, AutoTokenizer\n",
"from datasets import load_dataset\n",
"\n",
"from trl import PPOTrainer, PPOConfig, AutoModelForCausalLMWithValueHead\n",
"from trl.core import LengthSampler"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Configuration"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"config = PPOConfig(\n",
" model_name=\"lvwerra/gpt2-imdb\",\n",
" learning_rate=1.41e-5,\n",
" log_with=\"wandb\",\n",
")\n",
"\n",
"sent_kwargs = {\"top_k\": None, \"function_to_apply\": \"none\", \"batch_size\": 16}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import wandb\n",
"\n",
"wandb.init()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You can see that we load a GPT2 model called `gpt2_imdb`. This model was additionally fine-tuned on the IMDB dataset for 1 epoch with the huggingface [script](https://github.com/huggingface/transformers/blob/main/examples/legacy/run_language_modeling.py) (no special settings). The other parameters are mostly taken from the original paper [\"Fine-Tuning Language Models from Human Preferences\"](\n",
"https://huggingface.co/papers/1909.08593). This model as well as the BERT model is available in the Huggingface model zoo [here](https://huggingface.co/models). The following code should automatically download the models."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Load data and models"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### Load IMDB dataset\n",
"The IMDB dataset contains 50k movie review annotated with \"positive\"/\"negative\" feedback indicating the sentiment. We load the IMDB dataset into a DataFrame and filter for comments that are at least 200 characters. Then we tokenize each text and cut it to random size with the `LengthSampler`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def build_dataset(\n",
" config,\n",
" dataset_name=\"stanfordnlp/imdb\",\n",
" input_min_text_length=2,\n",
" input_max_text_length=8,\n",
"):\n",
" \"\"\"\n",
" Build dataset for training. This builds the dataset from `load_dataset`, one should\n",
" customize this function to train the model on its own dataset.\n",
"\n",
" Args:\n",
" dataset_name (`str`):\n",
" The name of the dataset to be loaded.\n",
"\n",
" Returns:\n",
" dataloader (`torch.utils.data.DataLoader`):\n",
" The dataloader for the dataset.\n",
" \"\"\"\n",
" tokenizer = AutoTokenizer.from_pretrained(config.model_name)\n",
" tokenizer.pad_token = tokenizer.eos_token\n",
" # load imdb with datasets\n",
" ds = load_dataset(dataset_name, split=\"train\")\n",
" ds = ds.rename_columns({\"text\": \"review\"})\n",
" ds = ds.filter(lambda x: len(x[\"review\"]) > 200, batched=False)\n",
"\n",
" input_size = LengthSampler(input_min_text_length, input_max_text_length)\n",
"\n",
" def tokenize(sample):\n",
" sample[\"input_ids\"] = tokenizer.encode(sample[\"review\"])[: input_size()]\n",
" sample[\"query\"] = tokenizer.decode(sample[\"input_ids\"])\n",
" return sample\n",
"\n",
" ds = ds.map(tokenize, batched=False)\n",
" ds.set_format(type=\"torch\")\n",
" return ds"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"dataset = build_dataset(config)\n",
"\n",
"\n",
"def collator(data):\n",
" return dict((key, [d[key] for d in data]) for key in data[0])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Load pre-trained GPT2 language models"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We load the GPT2 model with a value head and the tokenizer. We load the model twice; the first model is optimized while the second model serves as a reference to calculate the KL-divergence from the starting point. This serves as an additional reward signal in the PPO training to make sure the optimized model does not deviate too much from the original language model."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"model = AutoModelForCausalLMWithValueHead.from_pretrained(config.model_name)\n",
"ref_model = AutoModelForCausalLMWithValueHead.from_pretrained(config.model_name)\n",
"tokenizer = AutoTokenizer.from_pretrained(config.model_name)\n",
"\n",
"tokenizer.pad_token = tokenizer.eos_token"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### Initialize PPOTrainer\n",
"The `PPOTrainer` takes care of device placement and optimization later on:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ppo_trainer = PPOTrainer(\n",
" config, model, ref_model, tokenizer, dataset=dataset, data_collator=collator\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Load BERT classifier\n",
"We load a BERT classifier fine-tuned on the IMDB dataset."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"device = ppo_trainer.accelerator.device\n",
"if ppo_trainer.accelerator.num_processes == 1:\n",
" device = 0 if torch.cuda.is_available() else \"cpu\" # to avoid a `pipeline` bug\n",
"sentiment_pipe = pipeline(\n",
" \"sentiment-analysis\", model=\"lvwerra/distilbert-imdb\", device=device\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The model outputs are the logits for the negative and positive class. We will use the logits for positive class as a reward signal for the language model."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[{'label': 'NEGATIVE', 'score': 2.335048198699951},\n",
" {'label': 'POSITIVE', 'score': -2.726576328277588}]"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"text = \"this movie was really bad!!\"\n",
"sentiment_pipe(text, **sent_kwargs)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[{'label': 'POSITIVE', 'score': 2.557040214538574},\n",
" {'label': 'NEGATIVE', 'score': -2.294790267944336}]"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"text = \"this movie was really good!!\"\n",
"sentiment_pipe(text, **sent_kwargs)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Generation settings\n",
"For the response generation we just use sampling and make sure top-k and nucleus sampling are turned off as well as a minimal length."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"gen_kwargs = {\n",
" \"min_length\": -1,\n",
" \"top_k\": 0.0,\n",
" \"top_p\": 1.0,\n",
" \"do_sample\": True,\n",
" \"pad_token_id\": tokenizer.eos_token_id,\n",
"}"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Optimize model"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Training loop"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The training loop consists of the following main steps:\n",
"1. Get the query responses from the policy network (GPT-2)\n",
"2. Get sentiments for query/responses from BERT\n",
"3. Optimize policy with PPO using the (query, response, reward) triplet\n",
"\n",
"**Training time**\n",
"\n",
"This step takes **~2h** on a V100 GPU with the above specified settings."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"output_min_length = 4\n",
"output_max_length = 16\n",
"output_length_sampler = LengthSampler(output_min_length, output_max_length)\n",
"\n",
"\n",
"generation_kwargs = {\n",
" \"min_length\": -1,\n",
" \"top_k\": 0.0,\n",
" \"top_p\": 1.0,\n",
" \"do_sample\": True,\n",
" \"pad_token_id\": tokenizer.eos_token_id,\n",
"}\n",
"\n",
"\n",
"for epoch, batch in enumerate(tqdm(ppo_trainer.dataloader)):\n",
" query_tensors = batch[\"input_ids\"]\n",
"\n",
" #### Get response from gpt2\n",
" response_tensors = []\n",
" for query in query_tensors:\n",
" gen_len = output_length_sampler()\n",
" generation_kwargs[\"max_new_tokens\"] = gen_len\n",
" query_response = ppo_trainer.generate(query, **generation_kwargs).squeeze()\n",
" response_len = len(query_response) - len(query)\n",
" response_tensors.append(query_response[-response_len:])\n",
" batch[\"response\"] = [tokenizer.decode(r.squeeze()) for r in response_tensors]\n",
"\n",
" #### Compute sentiment score\n",
" texts = [q + r for q, r in zip(batch[\"query\"], batch[\"response\"])]\n",
" pipe_outputs = sentiment_pipe(texts, **sent_kwargs)\n",
" positive_scores = [\n",
" item[\"score\"]\n",
" for output in pipe_outputs\n",
" for item in output\n",
" if item[\"label\"] == \"POSITIVE\"\n",
" ]\n",
" rewards = [torch.tensor(score) for score in positive_scores]\n",
"\n",
" #### Run PPO step\n",
" stats = ppo_trainer.step(query_tensors, response_tensors, rewards)\n",
" ppo_trainer.log_stats(stats, batch, rewards)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Training progress\n",
"If you are tracking the training progress with Weights&Biases you should see a plot similar to the one below. Check out the interactive sample report on wandb.ai: [link](https://wandb.ai/huggingface/trl/runs/w9l3110g).\n",
"\n",
"<div style=\"text-align: center\">\n",
"<img src='https://huggingface.co/datasets/trl-internal-testing/example-images/resolve/main/images/gpt2_tuning_progress.png' width='800'>\n",
"<p style=\"text-align: center;\"> <b>Figure:</b> Reward mean and distribution evolution during training. </p>\n",
"</div>\n",
"\n",
"One can observe how the model starts to generate more positive outputs after a few optimisation steps.\n",
"\n",
"> Note: Investigating the KL-divergence will probably show that at this point the model has not converged to the target KL-divergence, yet. To get there would require longer training or starting with a higher initial coefficient."
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Model inspection\n",
"Let's inspect some examples from the IMDB dataset. We can use `ref_model` to compare the tuned model `model` against the model before optimisation."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>query</th>\n",
" <th>response (before)</th>\n",
" <th>response (after)</th>\n",
" <th>rewards (before)</th>\n",
" <th>rewards (after)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>I rented Zero Day</td>\n",
" <td>4 for my sister. To my surprise, the Wii caug...</td>\n",
" <td>. It is a pleasure. It is a huge leap 68 years...</td>\n",
" <td>1.736068</td>\n",
" <td>2.423731</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>The only</td>\n",
" <td>distro of her</td>\n",
" <td>special compliments is the</td>\n",
" <td>0.150852</td>\n",
" <td>0.190159</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>I've read a few</td>\n",
" <td>news reports about Mr. Mueller's activities b...</td>\n",
" <td>novels and I never watch this. It has a reall...</td>\n",
" <td>-1.417962</td>\n",
" <td>2.831814</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>This is the second British Rank film</td>\n",
" <td>, and I wouldn't be surprised anymore if it</td>\n",
" <td>that I have enjoyed, achieving it in both the</td>\n",
" <td>0.835876</td>\n",
" <td>2.205628</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>A classic</td>\n",
" <td>classic.<br /><br />And only this one will ha...</td>\n",
" <td>. It's a movie with a fine cast. As the beginn...</td>\n",
" <td>2.113075</td>\n",
" <td>2.739168</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>This has to be one of the</td>\n",
" <td>worst with the differences being that for the</td>\n",
" <td>best thriller films I've seen in recent</td>\n",
" <td>-2.705339</td>\n",
" <td>2.730615</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>Happy Go Lovely is a waste</td>\n",
" <td>. Not only are extremely</td>\n",
" <td>of time, giving a</td>\n",
" <td>-2.429504</td>\n",
" <td>-2.934672</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>Wow, I just</td>\n",
" <td>can't make fun of it</td>\n",
" <td>feek it! This show</td>\n",
" <td>-2.201666</td>\n",
" <td>-0.106085</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>This movie makes several mistakes.</td>\n",
" <td>Despite being a great comedic diversion it es...</td>\n",
" <td>It's cool, wonderful - it held me into a very ...</td>\n",
" <td>-1.232380</td>\n",
" <td>2.707638</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>Branagh and Fish</td>\n",
" <td>burne, Drake is played</td>\n",
" <td>is a great show. Beautiful</td>\n",
" <td>0.776819</td>\n",
" <td>2.808996</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>I might have given this movie a</td>\n",
" <td>rating of *11 when I heard that!), but it was...</td>\n",
" <td>great performance. It was truly a great movie...</td>\n",
" <td>0.276380</td>\n",
" <td>2.743328</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>Really, really bad</td>\n",
" <td>with feel like there is no end to the</td>\n",
" <td>. This movie is incredibly good, with the</td>\n",
" <td>-2.639503</td>\n",
" <td>-1.568827</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>What another reviewer called lack of</td>\n",
" <td>judgment, connecting into her own harsh obser...</td>\n",
" <td>suspense. Rogers and Rooney rate this as exce...</td>\n",
" <td>-1.079707</td>\n",
" <td>2.696888</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>This is simply one</td>\n",
" <td>more problem of Steve</td>\n",
" <td>of the best choice</td>\n",
" <td>-1.445436</td>\n",
" <td>2.662699</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>\"Perhaps we can arrange a meet</td>\n",
" <td>-and-greet.<br /><br />Teleg</td>\n",
" <td>with spent, classic music and dance, and come...</td>\n",
" <td>0.258479</td>\n",
" <td>1.876662</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>Richard Willaims is</td>\n",
" <td>nice enough; the little black guy plays quite</td>\n",
" <td>beautifully hands on in his own spin, and</td>\n",
" <td>0.796508</td>\n",
" <td>2.820259</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" query \\\n",
"0 I rented Zero Day \n",
"1 The only \n",
"2 I've read a few \n",
"3 This is the second British Rank film \n",
"4 A classic \n",
"5 This has to be one of the \n",
"6 Happy Go Lovely is a waste \n",
"7 Wow, I just \n",
"8 This movie makes several mistakes. \n",
"9 Branagh and Fish \n",
"10 I might have given this movie a \n",
"11 Really, really bad \n",
"12 What another reviewer called lack of \n",
"13 This is simply one \n",
"14 \"Perhaps we can arrange a meet \n",
"15 Richard Willaims is \n",
"\n",
" response (before) \\\n",
"0 4 for my sister. To my surprise, the Wii caug... \n",
"1 distro of her \n",
"2 news reports about Mr. Mueller's activities b... \n",
"3 , and I wouldn't be surprised anymore if it \n",
"4 classic.<br /><br />And only this one will ha... \n",
"5 worst with the differences being that for the \n",
"6 . Not only are extremely \n",
"7 can't make fun of it \n",
"8 Despite being a great comedic diversion it es... \n",
"9 burne, Drake is played \n",
"10 rating of *11 when I heard that!), but it was... \n",
"11 with feel like there is no end to the \n",
"12 judgment, connecting into her own harsh obser... \n",
"13 more problem of Steve \n",
"14 -and-greet.<br /><br />Teleg \n",
"15 nice enough; the little black guy plays quite \n",
"\n",
" response (after) rewards (before) \\\n",
"0 . It is a pleasure. It is a huge leap 68 years... 1.736068 \n",
"1 special compliments is the 0.150852 \n",
"2 novels and I never watch this. It has a reall... -1.417962 \n",
"3 that I have enjoyed, achieving it in both the 0.835876 \n",
"4 . It's a movie with a fine cast. As the beginn... 2.113075 \n",
"5 best thriller films I've seen in recent -2.705339 \n",
"6 of time, giving a -2.429504 \n",
"7 feek it! This show -2.201666 \n",
"8 It's cool, wonderful - it held me into a very ... -1.232380 \n",
"9 is a great show. Beautiful 0.776819 \n",
"10 great performance. It was truly a great movie... 0.276380 \n",
"11 . This movie is incredibly good, with the -2.639503 \n",
"12 suspense. Rogers and Rooney rate this as exce... -1.079707 \n",
"13 of the best choice -1.445436 \n",
"14 with spent, classic music and dance, and come... 0.258479 \n",
"15 beautifully hands on in his own spin, and 0.796508 \n",
"\n",
" rewards (after) \n",
"0 2.423731 \n",
"1 0.190159 \n",
"2 2.831814 \n",
"3 2.205628 \n",
"4 2.739168 \n",
"5 2.730615 \n",
"6 -2.934672 \n",
"7 -0.106085 \n",
"8 2.707638 \n",
"9 2.808996 \n",
"10 2.743328 \n",
"11 -1.568827 \n",
"12 2.696888 \n",
"13 2.662699 \n",
"14 1.876662 \n",
"15 2.820259 "
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#### get a batch from the dataset\n",
"bs = 16\n",
"game_data = dict()\n",
"dataset.set_format(\"pandas\")\n",
"df_batch = dataset[:].sample(bs)\n",
"game_data[\"query\"] = df_batch[\"query\"].tolist()\n",
"query_tensors = df_batch[\"input_ids\"].tolist()\n",
"\n",
"response_tensors_ref, response_tensors = [], []\n",
"\n",
"#### get response from gpt2 and gpt2_ref\n",
"for i in range(bs):\n",
" query = torch.tensor(query_tensors[i]).to(device)\n",
"\n",
" gen_len = output_length_sampler()\n",
" query_response = ref_model.generate(\n",
" query.unsqueeze(0), max_new_tokens=gen_len, **gen_kwargs\n",
" ).squeeze()\n",
" response_len = len(query_response) - len(query)\n",
" response_tensors_ref.append(query_response[-response_len:])\n",
"\n",
" query_response = model.generate(\n",
" query.unsqueeze(0), max_new_tokens=gen_len, **gen_kwargs\n",
" ).squeeze()\n",
" response_len = len(query_response) - len(query)\n",
" response_tensors.append(query_response[-response_len:])\n",
"\n",
"#### decode responses\n",
"game_data[\"response (before)\"] = [\n",
" tokenizer.decode(response_tensors_ref[i]) for i in range(bs)\n",
"]\n",
"game_data[\"response (after)\"] = [\n",
" tokenizer.decode(response_tensors[i]) for i in range(bs)\n",
"]\n",
"\n",
"#### sentiment analysis of query/response pairs before/after\n",
"texts = [q + r for q, r in zip(game_data[\"query\"], game_data[\"response (before)\"])]\n",
"pipe_outputs = sentiment_pipe(texts, **sent_kwargs)\n",
"positive_scores = [\n",
" item[\"score\"]\n",
" for output in pipe_outputs\n",
" for item in output\n",
" if item[\"label\"] == \"POSITIVE\"\n",
"]\n",
"game_data[\"rewards (before)\"] = positive_scores\n",
"\n",
"texts = [q + r for q, r in zip(game_data[\"query\"], game_data[\"response (after)\"])]\n",
"pipe_outputs = sentiment_pipe(texts, **sent_kwargs)\n",
"positive_scores = [\n",
" item[\"score\"]\n",
" for output in pipe_outputs\n",
" for item in output\n",
" if item[\"label\"] == \"POSITIVE\"\n",
"]\n",
"game_data[\"rewards (after)\"] = positive_scores\n",
"\n",
"# store results in a dataframe\n",
"df_results = pd.DataFrame(game_data)\n",
"df_results"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Looking at the reward mean/median of the generated sequences we observe a significant difference."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"mean:\n"
]
},
{
"data": {
"text/plain": [
"rewards (before) -0.512965\n",
"rewards (after) 1.676750\n",
"dtype: float64"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"median:\n"
]
},
{
"data": {
"text/plain": [
"rewards (before) -0.464427\n",
"rewards (after) 2.679794\n",
"dtype: float64"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"print(\"mean:\")\n",
"display(df_results[[\"rewards (before)\", \"rewards (after)\"]].mean())\n",
"print()\n",
"print(\"median:\")\n",
"display(df_results[[\"rewards (before)\", \"rewards (after)\"]].median())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Save model\n",
"Finally, we save the model and push it to the Hugging Face for later usage."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"('gpt2-imdb-pos-v2/tokenizer_config.json',\n",
" 'gpt2-imdb-pos-v2/special_tokens_map.json',\n",
" 'gpt2-imdb-pos-v2/vocab.json',\n",
" 'gpt2-imdb-pos-v2/merges.txt',\n",
" 'gpt2-imdb-pos-v2/added_tokens.json',\n",
" 'gpt2-imdb-pos-v2/tokenizer.json')"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.save_pretrained(\"gpt2-imdb-pos-v2\", push_to_hub=True)\n",
"tokenizer.save_pretrained(\"gpt2-imdb-pos-v2\", push_to_hub=True)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "env",
"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": "3.11.9"
},
"vscode": {
"interpreter": {
"hash": "4c8ff454cd947027f86954d72bf940c689a97dcc494eb53cfe4813862c6065fe"
}
}
},
"nbformat": 4,
"nbformat_minor": 4
}
|