File size: 45,808 Bytes
d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 190c9ce c0396a3 d572bbd 190c9ce c0396a3 190c9ce c0396a3 190c9ce d572bbd c0396a3 d572bbd c0396a3 190c9ce c0396a3 190c9ce c0396a3 190c9ce c0396a3 190c9ce c0396a3 190c9ce c0396a3 190c9ce c0396a3 190c9ce c0396a3 190c9ce c0396a3 190c9ce c0396a3 190c9ce c0396a3 190c9ce d572bbd 190c9ce d572bbd c0396a3 d572bbd c0396a3 5007ef5 c0396a3 5007ef5 c0396a3 d572bbd 5007ef5 c0396a3 d572bbd c0396a3 5007ef5 c0396a3 5007ef5 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd c0396a3 d572bbd | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 | {
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# EasyTranslate: Transformer-Based English-Chinese Translation System\n",
"\n",
"## Production Entry Point — Person C Integration\n",
"\n",
"This notebook serves as the primary entry point for the EasyTranslate project.\n",
"It handles:\n",
"- Environment detection (local vs Google Colab)\n",
"- Repository cloning and dependency installation\n",
"- Data loading and preprocessing\n",
"- Model construction and training\n",
"- Evaluation and cloud storage synchronization\n",
"\n",
"---"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1. Environment Detection & Setup\n",
"\n",
"Detect whether we are running in Google Colab or locally, and configure accordingly."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import sys\n",
"import subprocess\n",
"import importlib\n",
"import json\n",
"import shutil\n",
"from pathlib import Path\n",
"\n",
"IN_COLAB = False\n",
"try:\n",
" import google.colab\n",
" IN_COLAB = True\n",
"except ImportError:\n",
" pass\n",
"\n",
"print(f\"Running in Google Colab: {IN_COLAB}\")\n",
"print(f\"Python version: {sys.version}\")\n",
"print(f\"Working directory: {os.getcwd()}\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2. Repository Setup\n",
"\n",
"Clone the latest code from the repository. In Colab, this pulls fresh code each runtime.\n",
"Locally, it ensures the working directory is correct."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# ── 仓库地址配置 ─────────────────────────────────────────────────────────────\n",
"# import os; os.environ[\"EASYTRANSLATE_REPO_URL\"] = \"https://github.com/your-org/your-repo.git\"\n",
"REPO_URL = os.environ.get(\n",
" \"EASYTRANSLATE_REPO_URL\",\n",
" \"https://huggingface.co/sdfjliom/UCAS-EasyTranslate\",\n",
")\n",
"_DEFAULT_COLAB_DIR = Path(\"/content/UCAS-EasyTranslate\")\n",
"\n",
"\n",
"def _is_repo_root(path: Path) -> bool:\n",
" return (path / \"src\" / \"easytranslate\").exists() and (path / \"setup.py\").exists()\n",
"\n",
"\n",
"def _find_repo_root(start_path: Path):\n",
" p = start_path.resolve()\n",
" for candidate in [p] + list(p.parents):\n",
" if _is_repo_root(candidate):\n",
" return candidate\n",
" return None\n",
"\n",
"\n",
"resolved_repo = None\n",
"\n",
"if IN_COLAB:\n",
" if _is_repo_root(_DEFAULT_COLAB_DIR):\n",
" resolved_repo = _DEFAULT_COLAB_DIR\n",
" else:\n",
" print(f\"Cloning repository from: {REPO_URL}\")\n",
" try:\n",
" subprocess.run(\n",
" [\"git\", \"lfs\", \"install\"], check=False,\n",
" stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL,\n",
" )\n",
" subprocess.run(\n",
" [\"git\", \"clone\", \"--depth\", \"1\", REPO_URL, str(_DEFAULT_COLAB_DIR)],\n",
" check=True,\n",
" stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True,\n",
" )\n",
" resolved_repo = _DEFAULT_COLAB_DIR\n",
" print(f\"Cloned to: {_DEFAULT_COLAB_DIR}\")\n",
" except subprocess.CalledProcessError as e:\n",
" print(f\"Clone failed:\\n{e.stdout}\")\n",
"\n",
" # Fallback: search Drive or current dir\n",
" if resolved_repo is None:\n",
" for candidate in [\n",
" Path.cwd(),\n",
" Path(\"/content\"),\n",
" Path(\"/content/drive/MyDrive/UCAS-EasyTranslate\"),\n",
" Path(\"/content/drive/MyDrive/Colab Notebooks/UCAS-EasyTranslate\"),\n",
" ]:\n",
" root = _find_repo_root(candidate)\n",
" if root:\n",
" resolved_repo = root\n",
" print(f\"Found existing repo at: {resolved_repo}\")\n",
" break\n",
"\n",
" if resolved_repo is None:\n",
" raise FileNotFoundError(\n",
" \"Cannot locate UCAS-EasyTranslate repository.\\n\"\n",
" \"Options:\\n\"\n",
" \" (1) Set EASYTRANSLATE_REPO_URL to a publicly accessible git URL.\\n\"\n",
" \" (2) Manually clone to /content/UCAS-EasyTranslate.\\n\"\n",
" \" (3) Place repo in Google Drive and mount Drive first.\"\n",
" )\n",
"else:\n",
" resolved_repo = _find_repo_root(Path.cwd()) or Path.cwd()\n",
" print(f\"Using local repository at: {resolved_repo}\")\n",
"\n",
"# Always keep REPO_DIR in sync with wherever the repo actually is\n",
"REPO_DIR = Path(resolved_repo)\n",
"os.chdir(REPO_DIR)\n",
"sys.path.insert(0, str(REPO_DIR / \"src\"))\n",
"print(f\"Repository directory: {REPO_DIR}\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 3. Dependency Installation\n",
"\n",
"Install all required packages. In Colab, PyTorch is pre-installed."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"if IN_COLAB:\n",
" # 1. Only install packages that Colab does NOT ship.\n",
" # Do NOT touch torch/numpy/pandas — Colab's preinstalled versions are fine.\n",
" %pip install -q --upgrade pip setuptools wheel\n",
"\n",
" # Core HuggingFace packages (Colab may have older versions)\n",
" %pip install -q \"transformers>=4.36.0,<4.45.0\" \\\n",
" \"datasets>=2.16.0,<3.0.0\" \\\n",
" \"tokenizers>=0.15.0,<0.20.0\" \\\n",
" \"sentencepiece>=0.2.0\" \\\n",
" \"accelerate>=0.25.0,<0.35.0\" \\\n",
" \"peft>=0.7.0,<0.12.0\"\n",
"\n",
" # Evaluation / config packages\n",
" %pip install -q \"sacrebleu>=2.4.0\" \\\n",
" \"omegaconf>=2.3.0,<3.0.0\" \\\n",
" \"rich>=13.0.0\"\n",
"\n",
" # 2. Install project code without re-resolving heavy dependencies.\n",
" # (torch, numpy, etc. are already present from Colab runtime.)\n",
" %pip install -q --no-deps -e .\n",
"\n",
" print(\"All packages installed successfully.\")\n",
"else:\n",
" %pip install -q --upgrade pip setuptools wheel\n",
" %pip install -q -r requirements.txt\n",
" %pip install -q -e .\n",
" print(\"Dependencies installed successfully.\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 4. GPU Verification\n",
"\n",
"Verify GPU availability and display hardware information."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import torch\n",
"\n",
"print(f\"PyTorch version: {torch.__version__}\")\n",
"print(f\"CUDA available: {torch.cuda.is_available()}\")\n",
"\n",
"if torch.cuda.is_available():\n",
" print(f\"CUDA version: {torch.version.cuda}\")\n",
" print(f\"GPU count: {torch.cuda.device_count()}\")\n",
" for i in range(torch.cuda.device_count()):\n",
" print(f\" GPU {i}: {torch.cuda.get_device_name(i)}\")\n",
" props = torch.cuda.get_device_properties(i)\n",
" print(f\" Memory: {props.total_memory / 1024**3:.1f} GB\")\n",
" print(f\" Compute Capability: {props.major}.{props.minor}\")\n",
"else:\n",
" print(\"WARNING: No GPU detected. Training will be very slow on CPU.\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 5. Google Drive Mount (Colab Only)\n",
"\n",
"Mount Google Drive for persistent storage of checkpoints and results."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"DRIVE_MOUNTED = False\n",
"DRIVE_BASE = \"/content/drive/MyDrive/EasyTranslate\"\n",
"\n",
"if IN_COLAB:\n",
" from google.colab import drive\n",
" drive.mount(\"/content/drive\")\n",
" DRIVE_MOUNTED = os.path.exists(\"/content/drive\")\n",
" if DRIVE_MOUNTED:\n",
" os.makedirs(DRIVE_BASE, exist_ok=True)\n",
" print(f\"Google Drive mounted. Base path: {DRIVE_BASE}\")\n",
" else:\n",
" print(\"WARNING: Google Drive mount failed\")\n",
"else:\n",
" print(\"Not in Colab, skipping Google Drive mount\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 6. Configuration Loading\n",
"\n",
"Load and display the project configuration."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import torch\n",
"import numpy as np\n",
"\n",
"print(f\"NumPy version : {np.__version__}\")\n",
"print(f\"PyTorch version: {torch.__version__}\")\n",
"\n",
"from easytranslate.utils.config import load_config, config_to_dict\n",
"from easytranslate.utils.seed import set_seed\n",
"from easytranslate.utils.logging import setup_logging\n",
"\n",
"config = load_config(\"configs/default_config.yaml\")\n",
"config_dict = config_to_dict(config)\n",
"\n",
"exp_cfg = config_dict.get(\"experiment\", {})\n",
"seed = exp_cfg.get(\"seed\", 42)\n",
"set_seed(seed)\n",
"\n",
"log_cfg = config_dict.get(\"logging\", {})\n",
"setup_logging(\n",
" log_dir=log_cfg.get(\"log_dir\", \"logs/\"),\n",
" log_file=\"easytranslate.log\",\n",
")\n",
"\n",
"# ── Colab runtime overrides ───────────────────────────────────────────────────\n",
"if IN_COLAB:\n",
" train_cfg = config_dict.setdefault(\"training\", {})\n",
"\n",
" # Mixed precision: use bf16 on Ampere+ GPUs, fp16 otherwise, none on CPU\n",
" if torch.cuda.is_available():\n",
" gpu_cap = torch.cuda.get_device_capability(0)\n",
" if gpu_cap[0] >= 8: # A100/A10 → bf16\n",
" train_cfg[\"fp16\"] = False\n",
" train_cfg[\"bf16\"] = True\n",
" else: # T4/P100/V100 → fp16\n",
" train_cfg[\"fp16\"] = True\n",
" train_cfg[\"bf16\"] = False\n",
" else:\n",
" train_cfg[\"fp16\"] = False\n",
" train_cfg[\"bf16\"] = False\n",
"\n",
" # Reduce epochs for a Colab demo run\n",
" train_cfg.setdefault(\"epochs\", 10)\n",
"\n",
" # Colab-friendly batch / gradient accumulation settings\n",
" train_cfg.setdefault(\"batch_size\", 32)\n",
" train_cfg.setdefault(\"gradient_accumulation_steps\", 4)\n",
"\n",
"print(f\"Configuration loaded. Experiment seed: {seed}\")\n",
"print(f\"Model type : {config_dict['model']['type']}\")\n",
"print(f\"Training : epochs={config_dict['training']['epochs']}, \"\n",
" f\"fp16={config_dict['training']['fp16']}, \"\n",
" f\"bf16={config_dict['training']['bf16']}\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 7. Data Loading & Preprocessing\n",
"\n",
"Load the WMT19 zh-en dataset, train the BPE tokenizer, and prepare DataLoaders."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from easytranslate.data import (\n",
" TranslationDataset,\n",
" TranslationCollator,\n",
" DynamicBatchSampler,\n",
" build_tokenizer,\n",
" load_wmt_dataset,\n",
" preprocess_pipeline,\n",
")\n",
"from torch.utils.data import DataLoader\n",
"\n",
"data_cfg = config_dict.get(\"data\", {})\n",
"preproc_cfg = data_cfg.get(\"preprocessing\", {})\n",
"loader_cfg = data_cfg.get(\"dataloader\", {})\n",
"\n",
"# ── Cap dataset sizes for Colab to avoid RAM/time issues ─────────────────────\n",
"MAX_TRAIN_SAMPLES = 200_000 if IN_COLAB else None # None → use full dataset\n",
"MAX_VAL_SAMPLES = 5_000 if IN_COLAB else None\n",
"\n",
"print(\"Loading WMT19 zh-en dataset (this may take several minutes on first run)...\")\n",
"raw_dataset = load_wmt_dataset(\n",
" year=data_cfg.get(\"wmt\", {}).get(\"year\", \"19\"),\n",
" language_pair=data_cfg.get(\"wmt\", {}).get(\"language_pair\", \"zh-en\"),\n",
" src_lang=\"en\",\n",
" tgt_lang=\"zh\",\n",
")\n",
"\n",
"train_raw = raw_dataset[\"train\"]\n",
"\n",
"# Prefer \"validation\", fall back to \"dev\", then use a small slice of train\n",
"_val_split_name = next(\n",
" (k for k in (\"validation\", \"dev\", \"valid\") if k in raw_dataset),\n",
" None,\n",
")\n",
"val_raw = raw_dataset[_val_split_name] if _val_split_name else train_raw\n",
"\n",
"print(f\"Raw training samples : {len(train_raw['src'])}\")\n",
"print(f\"Raw validation samples: {len(val_raw['src'])} \"\n",
" f\"(split='{_val_split_name or 'train (fallback)'}')\")\n",
"\n",
"# Apply sample caps BEFORE preprocessing to save time\n",
"train_src_raw = train_raw[\"src\"][:MAX_TRAIN_SAMPLES] if MAX_TRAIN_SAMPLES else list(train_raw[\"src\"])\n",
"train_tgt_raw = train_raw[\"tgt\"][:MAX_TRAIN_SAMPLES] if MAX_TRAIN_SAMPLES else list(train_raw[\"tgt\"])\n",
"val_src_raw = val_raw[\"src\"][:MAX_VAL_SAMPLES] if MAX_VAL_SAMPLES else list(val_raw[\"src\"])\n",
"val_tgt_raw = val_raw[\"tgt\"][:MAX_VAL_SAMPLES] if MAX_VAL_SAMPLES else list(val_raw[\"tgt\"])\n",
"\n",
"print(f\"\\nPreprocessing training data ({len(train_src_raw)} samples)...\")\n",
"train_src, train_tgt = preprocess_pipeline(\n",
" train_src_raw, train_tgt_raw,\n",
" max_src_len=preproc_cfg.get(\"max_src_len\", 256),\n",
" max_tgt_len=preproc_cfg.get(\"max_tgt_len\", 256),\n",
" filter_by_length_enabled=preproc_cfg.get(\"filter_by_length\", True),\n",
" length_ratio_threshold=preproc_cfg.get(\"length_ratio_threshold\", 3.0),\n",
")\n",
"print(f\"Preprocessed training samples : {len(train_src)}\")\n",
"\n",
"print(f\"Preprocessing validation data ({len(val_src_raw)} samples)...\")\n",
"val_src, val_tgt = preprocess_pipeline(\n",
" val_src_raw, val_tgt_raw,\n",
" max_src_len=preproc_cfg.get(\"max_src_len\", 256),\n",
" max_tgt_len=preproc_cfg.get(\"max_tgt_len\", 256),\n",
" filter_by_length_enabled=preproc_cfg.get(\"filter_by_length\", True),\n",
" length_ratio_threshold=preproc_cfg.get(\"length_ratio_threshold\", 3.0),\n",
")\n",
"print(f\"Preprocessed validation samples: {len(val_src)}\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 8. Tokenizer Training\n",
"\n",
"Train a byte-level BPE tokenizer on the combined source and target texts."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"tok_cfg = config_dict.get(\"tokenizer\", {})\n",
"\n",
"print(\"Building tokenizer...\")\n",
"all_train_texts = train_src + train_tgt\n",
"tokenizer = build_tokenizer(tok_cfg, train_texts=all_train_texts)\n",
"\n",
"print(f\"Tokenizer vocabulary size: {tokenizer.vocab_size}\")\n",
"print(f\"Special tokens: PAD={tokenizer.pad_token_id}, BOS={tokenizer.bos_token_id}, EOS={tokenizer.eos_token_id}\")\n",
"\n",
"test_encode = tokenizer.encode(\"Hello world\", add_special_tokens=True)\n",
"test_decode = tokenizer.decode(test_encode)\n",
"print(f\"Encode test: {test_encode[:10]}...\")\n",
"print(f\"Decode test: {test_decode[:50]}...\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 9. Dataset & DataLoader Construction\n",
"\n",
"Build PyTorch datasets and dataloaders with dynamic batching."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"max_src_len = preproc_cfg.get(\"max_src_len\", 256)\n",
"max_tgt_len = preproc_cfg.get(\"max_tgt_len\", 256)\n",
"\n",
"train_dataset = TranslationDataset(\n",
" train_src, train_tgt,\n",
" tokenizer=tokenizer,\n",
" max_src_len=max_src_len,\n",
" max_tgt_len=max_tgt_len,\n",
")\n",
"val_dataset = TranslationDataset(\n",
" val_src, val_tgt,\n",
" tokenizer=tokenizer,\n",
" max_src_len=max_src_len,\n",
" max_tgt_len=max_tgt_len,\n",
")\n",
"\n",
"collator = TranslationCollator(\n",
" pad_token_id=tokenizer.pad_token_id,\n",
" label_pad_token_id=-100,\n",
")\n",
"\n",
"loader_cfg = config_dict.get(\"data\", {}).get(\"dataloader\", {})\n",
"batch_size = loader_cfg.get(\"batch_size\", 32)\n",
"# 2 workers on GPU Colab; 0 on CPU (no multiprocessing overhead)\n",
"num_workers = 2 if IN_COLAB and torch.cuda.is_available() else 0\n",
"# Disable dynamic batching on Colab: computing exact token lengths for 200k\n",
"# sentences requires a full tokenizer pass and can take 30+ minutes.\n",
"use_dynamic = loader_cfg.get(\"dynamic_batching\", True) and not IN_COLAB\n",
"\n",
"if use_dynamic:\n",
" max_tokens = loader_cfg.get(\"max_tokens_per_batch\", 8192)\n",
" print(\"Computing sequence lengths for dynamic batching (approximate)...\")\n",
"\n",
" def _approx_len(src_text: str, tgt_text: str) -> int:\n",
" \"\"\"Fast character-based length estimate — no tokenizer call needed.\"\"\"\n",
" def _tok_est(t: str) -> int:\n",
" cjk = sum(1 for c in t if \"\\u4e00\" <= c <= \"\\u9fff\")\n",
" return (len(t) - cjk) // 4 + cjk + 2 # rough BPE estimate\n",
" return max(_tok_est(src_text), _tok_est(tgt_text))\n",
"\n",
" train_lengths = [_approx_len(s, t) for s, t in zip(train_src, train_tgt)]\n",
" train_sampler = DynamicBatchSampler(\n",
" train_lengths,\n",
" max_tokens_per_batch=max_tokens,\n",
" shuffle=True,\n",
" )\n",
" train_loader = DataLoader(\n",
" train_dataset,\n",
" batch_sampler=train_sampler,\n",
" collate_fn=collator,\n",
" num_workers=num_workers,\n",
" pin_memory=torch.cuda.is_available(),\n",
" )\n",
"else:\n",
" if IN_COLAB and loader_cfg.get(\"dynamic_batching\", True):\n",
" print(\"Note: dynamic batching disabled on Colab (would require full tokenizer pass on all samples).\")\n",
" train_loader = DataLoader(\n",
" train_dataset,\n",
" batch_size=batch_size,\n",
" shuffle=True,\n",
" collate_fn=collator,\n",
" num_workers=num_workers,\n",
" pin_memory=torch.cuda.is_available(),\n",
" )\n",
"\n",
"val_loader = DataLoader(\n",
" val_dataset,\n",
" batch_size=batch_size,\n",
" shuffle=False,\n",
" collate_fn=collator,\n",
" num_workers=num_workers,\n",
" pin_memory=torch.cuda.is_available(),\n",
")\n",
"\n",
"print(f\"Training batches : ~{len(train_loader)}\")\n",
"print(f\"Validation batches: {len(val_loader)}\")\n",
"\n",
"sample_batch = next(iter(train_loader))\n",
"print(\"Sample batch shapes:\")\n",
"for k, v in sample_batch.items():\n",
" if isinstance(v, torch.Tensor):\n",
" print(f\" {k}: {list(v.shape)}\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 10. Model Construction\n",
"\n",
"Build the Transformer model based on configuration."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from easytranslate.model import TransformerTranslationModel\n",
"\n",
"model_cfg = config_dict.get(\"model\", {})\n",
"model_type = model_cfg.get(\"type\", \"transformer_scratch\")\n",
"\n",
"if model_type == \"transformer_scratch\":\n",
" tf_cfg = dict(model_cfg.get(\"transformer\", {}))\n",
"\n",
" # ── Colab quick-run: smaller model to fit in Colab RAM/VRAM ──────────────\n",
" # Default full model: d_model=512, 6 enc/dec layers (~75 M params)\n",
" # Colab quick model: d_model=256, 3 enc/dec layers (~12 M params)\n",
" # Set COLAB_FULL_MODEL=1 in env to skip this override.\n",
" if IN_COLAB and not os.environ.get(\"COLAB_FULL_MODEL\"):\n",
" tf_cfg.setdefault(\"d_model\", 256)\n",
" tf_cfg.setdefault(\"nhead\", 4)\n",
" tf_cfg.setdefault(\"num_encoder_layers\", 3)\n",
" tf_cfg.setdefault(\"num_decoder_layers\", 3)\n",
" tf_cfg.setdefault(\"dim_feedforward\", 1024)\n",
" print(\"Colab mode: using compact model (d_model=256, 3 layers).\")\n",
" print(\"To use the full model, run: import os; os.environ['COLAB_FULL_MODEL']='1'\")\n",
"\n",
" model = TransformerTranslationModel(\n",
" src_vocab_size=tokenizer.vocab_size,\n",
" tgt_vocab_size=tokenizer.vocab_size,\n",
" d_model=tf_cfg.get(\"d_model\", 512),\n",
" nhead=tf_cfg.get(\"nhead\", 8),\n",
" num_encoder_layers=tf_cfg.get(\"num_encoder_layers\", 6),\n",
" num_decoder_layers=tf_cfg.get(\"num_decoder_layers\", 6),\n",
" dim_feedforward=tf_cfg.get(\"dim_feedforward\", 2048),\n",
" dropout=tf_cfg.get(\"dropout\", 0.1),\n",
" activation=tf_cfg.get(\"activation\", \"gelu\"),\n",
" max_seq_len=tf_cfg.get(\"max_seq_len\", 512),\n",
" use_flash_attention=tf_cfg.get(\"use_flash_attention\", True),\n",
" use_rotary_embedding=tf_cfg.get(\"use_rotary_embedding\", True),\n",
" pre_norm=tf_cfg.get(\"pre_norm\", True),\n",
" pad_id=tokenizer.pad_token_id,\n",
" share_embedding=False,\n",
" )\n",
" print(\"Built Transformer from scratch\")\n",
"\n",
"elif model_type in (\"finetune_nllb\", \"finetune_mbart\"):\n",
" from easytranslate.model.finetune import load_pretrained_model, setup_lora\n",
" pt_cfg = model_cfg.get(\"pretrained\", {})\n",
" model, hf_tokenizer = load_pretrained_model(\n",
" model_name=pt_cfg.get(\"model_name\", \"facebook/nllb-200-distilled-600M\"),\n",
" src_lang=pt_cfg.get(\"src_lang\", \"eng_Latn\"),\n",
" tgt_lang=pt_cfg.get(\"tgt_lang\", \"zho_Hans\"),\n",
" )\n",
" if pt_cfg.get(\"use_lora\", True):\n",
" lora_cfg = pt_cfg.get(\"lora\", {})\n",
" model = setup_lora(\n",
" model,\n",
" r=lora_cfg.get(\"r\", 16),\n",
" alpha=lora_cfg.get(\"alpha\", 32),\n",
" dropout=lora_cfg.get(\"dropout\", 0.05),\n",
" target_modules=lora_cfg.get(\"target_modules\", [\"q_proj\", \"v_proj\"]),\n",
" )\n",
" print(f\"Loaded pretrained model: {pt_cfg.get('model_name')}\")\n",
"\n",
"else:\n",
" raise ValueError(f\"Unknown model type: {model_type}\")\n",
"\n",
"total_params = sum(p.numel() for p in model.parameters())\n",
"trainable_params = sum(p.numel() for p in model.parameters() if p.requires_grad)\n",
"print(f\"Total parameters : {total_params:,}\")\n",
"print(f\"Trainable parameters : {trainable_params:,}\")\n",
"print(f\"Trainable ratio : {100 * trainable_params / total_params:.2f}%\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 11. Quick Forward Pass Test\n",
"\n",
"Verify the model can perform a forward pass with correct output dimensions."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
"model = model.to(device)\n",
"model.eval()\n",
"\n",
"test_batch = next(iter(train_loader))\n",
"test_src = test_batch[\"src_ids\"][:2].to(device)\n",
"test_tgt = test_batch[\"tgt_input_ids\"][:2].to(device)\n",
"test_src_mask = test_batch[\"src_padding_mask\"][:2].to(device)\n",
"test_tgt_mask = test_batch[\"tgt_padding_mask\"][:2].to(device)\n",
"\n",
"with torch.no_grad():\n",
" logits = model(test_src, test_tgt, test_src_mask, test_tgt_mask)\n",
"\n",
"print(f\"Input src shape: {list(test_src.shape)}\")\n",
"print(f\"Input tgt shape: {list(test_tgt.shape)}\")\n",
"print(f\"Output logits shape: {list(logits.shape)}\")\n",
"print(f\"Expected output shape: [B, T, vocab_size] = [{test_tgt.size(0)}, {test_tgt.size(1)}, {tokenizer.vocab_size}]\")\n",
"assert logits.size(-1) == tokenizer.vocab_size, f\"Vocab size mismatch: {logits.size(-1)} vs {tokenizer.vocab_size}\"\n",
"print(\"Forward pass test PASSED\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 12. Training Execution\n",
"\n",
"This cell DEFINES the training setup but does NOT execute training automatically.\n",
"To start training, run the cell below this one."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# sacrebleu is now installed in the dependency cell above.\n",
"# This cell just verifies it is importable before we initialize the Trainer.\n",
"try:\n",
" importlib.import_module(\"sacrebleu\")\n",
" print(\"sacrebleu OK\")\n",
"except ImportError:\n",
" print(\"sacrebleu missing — installing now...\")\n",
" subprocess.run([sys.executable, \"-m\", \"pip\", \"install\", \"-q\", \"sacrebleu>=2.4.0\"], check=True)\n",
"\n",
"from easytranslate.training import Trainer\n",
"from easytranslate.evaluation import Evaluator\n",
"\n",
"evaluator = Evaluator(\n",
" model=model,\n",
" tokenizer=tokenizer,\n",
" config=config_dict,\n",
")\n",
"\n",
"trainer = Trainer(\n",
" model=model,\n",
" train_loader=train_loader,\n",
" val_loader=val_loader,\n",
" config=config_dict,\n",
" evaluator=evaluator,\n",
")\n",
"\n",
"# Output / plot directories live inside the repo\n",
"OUTPUT_DIR = REPO_DIR / \"outputs\"\n",
"PLOTS_DIR = OUTPUT_DIR / \"plots\"\n",
"OUTPUT_DIR.mkdir(parents=True, exist_ok=True)\n",
"PLOTS_DIR.mkdir(parents=True, exist_ok=True)\n",
"\n",
"print(\"Trainer initialized successfully\")\n",
"print(f\" Device : {trainer.device}\")\n",
"print(f\" FP16 / BF16 : {trainer.fp16} / {trainer.bf16}\")\n",
"print(f\" Gradient accumulation steps: {trainer.gradient_accumulation_steps}\")\n",
"print(f\" Number of epochs : {trainer.num_epochs}\")\n",
"print(f\" Checkpoint directory : {trainer.checkpoint_dir}\")\n",
"print(f\" Output directory : {OUTPUT_DIR}\")\n",
"print()\n",
"print(\">>> Run the NEXT cell to start training.\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 13. Start Training\n",
"\n",
"**Run this cell to begin training.** This will execute the full training loop.\n",
"Training progress will be displayed via tqdm progress bars."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"START_TRAINING = True\n",
"\n",
"if START_TRAINING:\n",
" print(\"=\" * 60)\n",
" print(\" Starting Training...\")\n",
" print(\"=\" * 60)\n",
" trainer.train()\n",
"else:\n",
" print(\"Training skipped. Set START_TRAINING = True to begin.\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 14. Evaluation on Test Set\n",
"\n",
"After training completes, evaluate the best model on the validation set."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"EVAL_RESULTS = {}\n",
"\n",
"best_ckpt = trainer.checkpoint_dir / \"best_model.pt\"\n",
"\n",
"if best_ckpt.exists():\n",
" print(f\"Loading best model from {best_ckpt}\")\n",
" checkpoint = torch.load(best_ckpt, map_location=device, weights_only=True)\n",
" model.load_state_dict(checkpoint[\"model_state_dict\"])\n",
" model = model.to(device)\n",
" model.eval()\n",
"\n",
" evaluator = Evaluator(model=model, tokenizer=tokenizer, config=config_dict)\n",
"\n",
" print(\"Running evaluation on validation set...\")\n",
" EVAL_RESULTS = evaluator.evaluate(\n",
" val_loader,\n",
" src_texts=val_src,\n",
" ref_texts=val_tgt,\n",
" )\n",
"\n",
" print(\"\\n\" + \"=\" * 60)\n",
" print(\" Evaluation Results\")\n",
" print(\"=\" * 60)\n",
" for metric, score in EVAL_RESULTS.items():\n",
" if isinstance(score, (int, float)):\n",
" print(f\" {metric:>12s}: {score:.4f}\")\n",
"\n",
" eval_path = OUTPUT_DIR / \"evaluation_results.json\"\n",
" with open(eval_path, \"w\", encoding=\"utf-8\") as f:\n",
" json.dump(EVAL_RESULTS, f, indent=2, ensure_ascii=False)\n",
" print(f\"\\nSaved evaluation results → {eval_path}\")\n",
"else:\n",
" print(\"No best_model.pt found. Run training first (Cell 13).\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 15. Translation Demo\n",
"\n",
"Test the trained model with some example translations."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"test_sentences = [\n",
" \"Hello, how are you today?\",\n",
" \"Machine translation is an important field of natural language processing.\",\n",
" \"The weather is beautiful and I want to go for a walk.\",\n",
" \"Deep learning has revolutionized artificial intelligence research.\",\n",
"]\n",
"\n",
"TRANSLATION_RESULTS = []\n",
"\n",
"if best_ckpt.exists():\n",
" print(\"Translating example sentences...\")\n",
" print(\"-\" * 60)\n",
" for sentence in test_sentences:\n",
" translation = evaluator.translate_single(sentence)\n",
" TRANSLATION_RESULTS.append({\"source_en\": sentence, \"target_zh\": translation})\n",
" print(f\"[EN] {sentence}\")\n",
" print(f\"[ZH] {translation}\")\n",
" print()\n",
"\n",
" translation_path = OUTPUT_DIR / \"translation_examples.json\"\n",
" with open(translation_path, \"w\", encoding=\"utf-8\") as f:\n",
" json.dump(TRANSLATION_RESULTS, f, indent=2, ensure_ascii=False)\n",
" print(f\"Saved translation examples → {translation_path}\")\n",
"else:\n",
" print(\"No trained model checkpoint available. Run training first (Cell 13).\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 16. Cloud Storage Synchronization\n",
"\n",
"Sync all training artifacts (checkpoints, logs, summaries) to Google Drive."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from easytranslate.utils.cloud_storage import sync_all_to_drive\n",
"\n",
"# Use trainer.log_dir if available, otherwise fall back to a sensible default\n",
"_log_dir = getattr(trainer, \"log_dir\", REPO_DIR / \"logs\")\n",
"\n",
"if IN_COLAB and DRIVE_MOUNTED:\n",
" print(\"Syncing training artifacts to Google Drive...\")\n",
" sync_results = sync_all_to_drive(\n",
" checkpoint_dir=str(trainer.checkpoint_dir),\n",
" log_dir=str(_log_dir),\n",
" drive_base_path=DRIVE_BASE,\n",
" )\n",
"\n",
" drive_outputs_dir = Path(DRIVE_BASE) / \"outputs\"\n",
" drive_outputs_dir.mkdir(parents=True, exist_ok=True)\n",
"\n",
" for artifact_file in [\n",
" OUTPUT_DIR / \"evaluation_results.json\",\n",
" OUTPUT_DIR / \"translation_examples.json\",\n",
" OUTPUT_DIR / \"training_report.json\",\n",
" ]:\n",
" if artifact_file.exists():\n",
" shutil.copy2(artifact_file, drive_outputs_dir / artifact_file.name)\n",
" print(f\" Copied {artifact_file.name} → Drive\")\n",
"\n",
" if PLOTS_DIR.exists():\n",
" drive_plots_dir = drive_outputs_dir / \"plots\"\n",
" drive_plots_dir.mkdir(parents=True, exist_ok=True)\n",
" for png_file in PLOTS_DIR.glob(\"*.png\"):\n",
" shutil.copy2(png_file, drive_plots_dir / png_file.name)\n",
" print(f\" Copied plot {png_file.name} → Drive\")\n",
"\n",
" print(f\"\\nSync complete. Drive base: {DRIVE_BASE}\")\n",
" print(f\"Sync details: {sync_results}\")\n",
"\n",
"elif not IN_COLAB:\n",
" print(\"Running locally. Artifacts are already on disk:\")\n",
" print(f\" Checkpoints : {trainer.checkpoint_dir}\")\n",
" print(f\" Logs : {_log_dir}\")\n",
" print(f\" Outputs : {OUTPUT_DIR}\")\n",
"else:\n",
" print(\"Google Drive not mounted. Artifacts saved locally only.\")\n",
" print(\"Mount Drive (Cell 5) and re-run this cell to sync results.\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 17. Training Summary\n",
"\n",
"Display the final training summary including loss curves and best metrics."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"TRAINING_SUMMARY = {}\n",
"summary_path = trainer.checkpoint_dir / \"training_summary.json\"\n",
"\n",
"if summary_path.exists():\n",
" with open(summary_path, \"r\", encoding=\"utf-8\") as f:\n",
" TRAINING_SUMMARY = json.load(f)\n",
"\n",
" print(\"=\" * 60)\n",
" print(\" Training Summary\")\n",
" print(\"=\" * 60)\n",
" print(f\" Best epoch : {TRAINING_SUMMARY.get('best_epoch', 'N/A')}\")\n",
" print(f\" Best metric : {TRAINING_SUMMARY.get('metric_name', 'N/A')} = \"\n",
" f\"{TRAINING_SUMMARY.get('best_metric', 'N/A')}\")\n",
" print(f\" Total steps : {TRAINING_SUMMARY.get('total_steps', 'N/A')}\")\n",
"\n",
" losses = TRAINING_SUMMARY.get(\"train_loss_history\", [])\n",
" if losses:\n",
" print(f\" Initial loss: {losses[0]:.4f}\")\n",
" print(f\" Final loss : {losses[-1]:.4f}\")\n",
" print(f\" Reduction : {losses[0] - losses[-1]:.4f}\")\n",
"\n",
" # Merge all results into one report file\n",
" report = {\n",
" \"training_summary\": TRAINING_SUMMARY,\n",
" \"evaluation_results\": EVAL_RESULTS,\n",
" \"translation_examples\": TRANSLATION_RESULTS,\n",
" }\n",
" report_path = OUTPUT_DIR / \"training_report.json\"\n",
" with open(report_path, \"w\", encoding=\"utf-8\") as f:\n",
" json.dump(report, f, indent=2, ensure_ascii=False)\n",
" print(f\"\\nMerged report saved → {report_path}\")\n",
"else:\n",
" print(\"Training summary not yet available. Complete training first.\")\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import matplotlib.pyplot as plt\n",
"\n",
"PLOTS_DIR.mkdir(parents=True, exist_ok=True)\n",
"\n",
"if not TRAINING_SUMMARY:\n",
" print(\"No training summary found. Run training and summary cells first.\")\n",
"else:\n",
" train_losses = TRAINING_SUMMARY.get(\"train_loss_history\", [])\n",
" val_history = TRAINING_SUMMARY.get(\"val_metrics_history\", [])\n",
"\n",
" # 1) Train Loss Curve\n",
" if train_losses:\n",
" epochs = list(range(1, len(train_losses) + 1))\n",
" plt.figure(figsize=(8, 5))\n",
" plt.plot(epochs, train_losses, marker=\"o\", linewidth=2)\n",
" plt.title(\"Training Loss by Epoch\")\n",
" plt.xlabel(\"Epoch\")\n",
" plt.ylabel(\"Loss\")\n",
" plt.grid(alpha=0.3)\n",
" loss_plot_path = PLOTS_DIR / \"train_loss_curve.png\"\n",
" plt.tight_layout()\n",
" plt.savefig(loss_plot_path, dpi=180)\n",
" plt.show()\n",
" print(f\"Saved plot: {loss_plot_path}\")\n",
"\n",
" # 2) Validation Metrics Curves\n",
" if val_history:\n",
" metric_keys = sorted({k for m in val_history for k in m.keys() if isinstance(m.get(k), (int, float))})\n",
" metric_keys = [k for k in metric_keys if k != \"val_loss\"]\n",
"\n",
" if metric_keys:\n",
" n = len(metric_keys)\n",
" rows = (n + 1) // 2\n",
" plt.figure(figsize=(12, max(4, rows * 3.5)))\n",
" for i, key in enumerate(metric_keys, start=1):\n",
" vals = [m.get(key, None) for m in val_history]\n",
" xs = [idx + 1 for idx, v in enumerate(vals) if v is not None]\n",
" ys = [v for v in vals if v is not None]\n",
" if not ys:\n",
" continue\n",
" plt.subplot(rows, 2, i)\n",
" plt.plot(xs, ys, marker=\"o\", linewidth=1.8)\n",
" plt.title(key)\n",
" plt.xlabel(\"Epoch\")\n",
" plt.ylabel(key)\n",
" plt.grid(alpha=0.3)\n",
"\n",
" metrics_plot_path = PLOTS_DIR / \"validation_metrics_curves.png\"\n",
" plt.tight_layout()\n",
" plt.savefig(metrics_plot_path, dpi=180)\n",
" plt.show()\n",
" print(f\"Saved plot: {metrics_plot_path}\")\n",
"\n",
" # 3) Final Evaluation Bar Chart\n",
" if \"EVAL_RESULTS\" in globals() and EVAL_RESULTS:\n",
" scalar_items = {k: v for k, v in EVAL_RESULTS.items() if isinstance(v, (int, float))}\n",
" if scalar_items:\n",
" names = list(scalar_items.keys())\n",
" values = [scalar_items[k] for k in names]\n",
" plt.figure(figsize=(10, 5))\n",
" bars = plt.bar(names, values)\n",
" plt.title(\"Final Evaluation Metrics\")\n",
" plt.ylabel(\"Score\")\n",
" plt.xticks(rotation=30)\n",
" plt.grid(axis=\"y\", alpha=0.25)\n",
" for bar, val in zip(bars, values):\n",
" plt.text(bar.get_x() + bar.get_width() / 2, bar.get_height(), f\"{val:.3f}\", ha=\"center\", va=\"bottom\", fontsize=9)\n",
" eval_plot_path = PLOTS_DIR / \"final_evaluation_metrics.png\"\n",
" plt.tight_layout()\n",
" plt.savefig(eval_plot_path, dpi=180)\n",
" plt.show()\n",
" print(f\"Saved plot: {eval_plot_path}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"---\n",
"\n",
"## Appendix: Module Architecture Overview\n",
"\n",
"```\n",
"EasyTranslate System Architecture\n",
"=================================\n",
"\n",
"Entry Point: EasyTranslate_Production.ipynb (this notebook)\n",
" |\n",
" +-- Environment Detection (Colab vs Local)\n",
" +-- Repository Cloning (git clone/pull)\n",
" +-- Dependency Installation\n",
" |\n",
" +-- Configuration Layer [utils/config.py]\n",
" | +-- load_config() : YAML -> OmegaConf DictConfig\n",
" | +-- merge_configs() : CLI overrides merge\n",
" | +-- config_from_cli() : Full config pipeline\n",
" |\n",
" +-- Data Layer [data/] — Person A\n",
" | +-- load_wmt_dataset() : HuggingFace datasets loader\n",
" | +-- preprocess_pipeline() : Clean + filter + deduplicate\n",
" | +-- build_tokenizer() : BPE / pretrained tokenizer\n",
" | +-- TranslationDataset() : PyTorch Dataset\n",
" | +-- TranslationCollator() : Padding + mask generation\n",
" | +-- DynamicBatchSampler() : Token-budget batching\n",
" |\n",
" +-- Model Layer [model/] — Person B\n",
" | +-- TransformerTranslationModel() : Full Enc-Dec model\n",
" | +-- TransformerEncoder() : N-layer encoder\n",
" | +-- TransformerDecoder() : N-layer decoder\n",
" | +-- FlashMultiHeadAttention() : Flash Attention 2\n",
" | +-- RotaryPositionalEmbedding() : RoPE encoding\n",
" | +-- load_pretrained_model() : NLLB/mBART loader\n",
" | +-- setup_lora() : LoRA configuration\n",
" |\n",
" +-- Training Layer [training/] — Person C\n",
" | +-- Trainer() : Full training controller\n",
" | | +-- _train_one_epoch() : Mixed precision loop\n",
" | | +-- _validate() : Validation loop\n",
" | | +-- _save_checkpoint() : Checkpoint persistence\n",
" | | +-- _load_checkpoint() : Resume training\n",
" | | +-- _should_early_stop() : Early stopping logic\n",
" | | +-- _setup_distributed() : DDP/DeepSpeed setup\n",
" | +-- LabelSmoothedCrossEntropyLoss() : Label smoothing loss\n",
" | +-- build_optimizer() : AdamW with param groups\n",
" | +-- build_scheduler() : Cosine/InverseSqrt/LR\n",
" |\n",
" +-- Evaluation Layer [evaluation/] — Person D\n",
" | +-- Evaluator() : Unified evaluation interface\n",
" | +-- greedy_decode() : Greedy decoding\n",
" | +-- beam_search_decode() : Beam search decoding\n",
" | +-- sample_decode() : Sampling (temp/top-k/top-p)\n",
" | +-- compute_bleu() : SacreBLEU metric\n",
" | +-- compute_comet() : COMET neural metric\n",
" | +-- compute_chrf() : chrF++ metric\n",
" |\n",
" +-- Cloud Storage [utils/cloud_storage.py] — Person C\n",
" +-- is_colab_environment() : Environment detection\n",
" +-- mount_google_drive() : Drive authentication\n",
" +-- sync_checkpoints_to_drive() : Checkpoint backup\n",
" +-- sync_logs_to_drive() : Log backup\n",
" +-- sync_all_to_drive() : Full sync pipeline\n",
"```\n",
"\n",
"## Module Interface Contracts\n",
"\n",
"### Tokenizer Interface (Person A -> B, C, D)\n",
"```python\n",
"tokenizer.encode(text: str) -> list[int]\n",
"tokenizer.decode(ids: list[int]) -> str\n",
"tokenizer.vocab_size -> int\n",
"tokenizer.pad_token_id -> int\n",
"tokenizer.bos_token_id -> int\n",
"tokenizer.eos_token_id -> int\n",
"```\n",
"\n",
"### Model Interface (Person B -> C, D)\n",
"```python\n",
"# Training forward pass\n",
"logits = model(src_ids, tgt_input_ids, src_padding_mask, tgt_padding_mask)\n",
"# logits: [B, T, vocab_size]\n",
"\n",
"# Inference\n",
"encoder_output = model.encode(src_ids, src_padding_mask)\n",
"next_logits = model.decode_step(tgt_input_ids, encoder_output, src_padding_mask)\n",
"```\n",
"\n",
"### Batch Format (Person A -> C)\n",
"```python\n",
"batch = {\n",
" \"src_ids\": Tensor[B, S],\n",
" \"tgt_input_ids\": Tensor[B, T],\n",
" \"labels\": Tensor[B, T],\n",
" \"src_padding_mask\": BoolTensor[B, S],\n",
" \"tgt_padding_mask\": BoolTensor[B, T],\n",
"}\n",
"```\n",
"\n",
"### Evaluation Interface (Person D -> C, E)\n",
"```python\n",
"evaluator = Evaluator(model, tokenizer, config)\n",
"results = evaluator.evaluate(dataloader)\n",
"# results: {\"bleu\": 25.6, \"comet\": 0.82, \"chrf\": 45.3, \"ter\": 55.2}\n",
"```"
]
}
],
"metadata": {
"colab": {
"include_colab_link": true,
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"name": "python",
"version": "3.10.0"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
|