Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
dense
Generated from Trainer
dataset_size:86450
loss:DenoisingAutoEncoderLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use SwarajSolanke-turtle/make-model-mapping-TSDAE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use SwarajSolanke-turtle/make-model-mapping-TSDAE with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("SwarajSolanke-turtle/make-model-mapping-TSDAE") sentences = [ "mini", "mini contryman e electric 1", "tata safari xm diesel 1956", "daewoo cielo glx petrol 1498" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
adding tsdae_script
Browse files- tsda.ipynb +1015 -0
tsda.ipynb
ADDED
|
@@ -0,0 +1,1015 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cells": [
|
| 3 |
+
{
|
| 4 |
+
"cell_type": "markdown",
|
| 5 |
+
"id": "intro",
|
| 6 |
+
"metadata": {},
|
| 7 |
+
"source": [
|
| 8 |
+
"# TSDAE fine-tuning on the FW vehicle master\n",
|
| 9 |
+
"\n",
|
| 10 |
+
"Domain-adapts a sentence encoder to insurer vehicle strings built from `Make`, `Model`, `Variant`, `Fuel`, `CC`\n",
|
| 11 |
+
"out of `data/FW_cleaned_data_new_base_15.csv`.\n",
|
| 12 |
+
"\n",
|
| 13 |
+
"Same TSDAE recipe as `TSDAE_script.ipynb`, with two substitutions:\n",
|
| 14 |
+
"\n",
|
| 15 |
+
"| | `TSDAE_script.ipynb` | this notebook |\n",
|
| 16 |
+
"|---|---|---|\n",
|
| 17 |
+
"| corpus | `wiki1m-for-simcse` | vehicle strings from the base-15 CSV |\n",
|
| 18 |
+
"| evaluator | STS-B (generic semantic similarity) | triplets of same-vehicle vs different-vehicle strings |\n",
|
| 19 |
+
"\n",
|
| 20 |
+
"STS-B is dropped because it scores general English sentence similarity and says nothing about whether\n",
|
| 21 |
+
"`maruti swift vxi petrol 1197` lands near its sibling variants. The triplet evaluator below measures exactly that,\n",
|
| 22 |
+
"which is the property the downstream mapping step depends on."
|
| 23 |
+
]
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"cell_type": "code",
|
| 27 |
+
"execution_count": 2,
|
| 28 |
+
"id": "install",
|
| 29 |
+
"metadata": {},
|
| 30 |
+
"outputs": [
|
| 31 |
+
{
|
| 32 |
+
"name": "stdout",
|
| 33 |
+
"output_type": "stream",
|
| 34 |
+
"text": [
|
| 35 |
+
"/home/ubuntu/Motor_Mapping/.venv/bin/python: No module named uv\n",
|
| 36 |
+
"Note: you may need to restart the kernel to use updated packages.\n"
|
| 37 |
+
]
|
| 38 |
+
}
|
| 39 |
+
],
|
| 40 |
+
"source": [
|
| 41 |
+
"# This venv has only pandas/numpy. Install the training stack once (~3 GB with CUDA torch):\n",
|
| 42 |
+
"%uv pip install \"sentence-transformers>=3.0\" nltk accelerate"
|
| 43 |
+
]
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"cell_type": "code",
|
| 47 |
+
"execution_count": 18,
|
| 48 |
+
"id": "imports",
|
| 49 |
+
"metadata": {},
|
| 50 |
+
"outputs": [
|
| 51 |
+
{
|
| 52 |
+
"name": "stderr",
|
| 53 |
+
"output_type": "stream",
|
| 54 |
+
"text": [
|
| 55 |
+
"/home/ubuntu/Motor_Mapping/.venv/lib/python3.12/site-packages/nltk/downloader.py:1076: UserWarning: NLTK will not authorize the non-private download directory '/home/ubuntu/nltk_data': it (or an ancestor) is world- or group-writable, so another local user could plant files there. Choose a private location such as ~/nltk_data.\n",
|
| 56 |
+
" for msg in self.incr_download(info_or_id, download_dir, force):\n"
|
| 57 |
+
]
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"data": {
|
| 61 |
+
"text/plain": [
|
| 62 |
+
"True"
|
| 63 |
+
]
|
| 64 |
+
},
|
| 65 |
+
"execution_count": 18,
|
| 66 |
+
"metadata": {},
|
| 67 |
+
"output_type": "execute_result"
|
| 68 |
+
}
|
| 69 |
+
],
|
| 70 |
+
"source": [
|
| 71 |
+
"import random\n",
|
| 72 |
+
"from collections import defaultdict\n",
|
| 73 |
+
"\n",
|
| 74 |
+
"import nltk\n",
|
| 75 |
+
"import pandas as pd\n",
|
| 76 |
+
"from datasets import Dataset\n",
|
| 77 |
+
"from nltk import word_tokenize\n",
|
| 78 |
+
"from nltk.tokenize.treebank import TreebankWordDetokenizer\n",
|
| 79 |
+
"from sentence_transformers import (\n",
|
| 80 |
+
" SentenceTransformer,\n",
|
| 81 |
+
" SentenceTransformerTrainer,\n",
|
| 82 |
+
" SentenceTransformerTrainingArguments,\n",
|
| 83 |
+
" losses,\n",
|
| 84 |
+
" models,\n",
|
| 85 |
+
" util,\n",
|
| 86 |
+
")\n",
|
| 87 |
+
"# from sentence_transformers.evaluation import TripletEvaluator\n",
|
| 88 |
+
"from sentence_transformers.sentence_transformer.evaluation import TripletEvaluator\n",
|
| 89 |
+
"nltk.download(\"punkt_tab\", quiet=True)"
|
| 90 |
+
]
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"cell_type": "markdown",
|
| 94 |
+
"id": "config-md",
|
| 95 |
+
"metadata": {},
|
| 96 |
+
"source": [
|
| 97 |
+
"## Config\n",
|
| 98 |
+
"\n",
|
| 99 |
+
"Two values differ from the wiki1m script because vehicle strings are short (~6 tokens, not ~25):\n",
|
| 100 |
+
"\n",
|
| 101 |
+
"- `MAX_SEQ_LENGTH = 32` instead of 75 β no string comes close to 75 tokens, so the extra padding is wasted compute.\n",
|
| 102 |
+
"- `DEL_RATIO = 0.4` instead of 0.6 β deleting 60% of a 6-token string leaves 2 tokens, which usually destroys the\n",
|
| 103 |
+
" make/model identity and gives the decoder nothing to reconstruct from. 0.4 keeps ~4 tokens."
|
| 104 |
+
]
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"cell_type": "code",
|
| 108 |
+
"execution_count": 19,
|
| 109 |
+
"id": "config",
|
| 110 |
+
"metadata": {},
|
| 111 |
+
"outputs": [],
|
| 112 |
+
"source": [
|
| 113 |
+
"CSV_PATH = \"/home/ubuntu/Motor_Mapping/MotorMapping/cleaning_data/data/FW_cleaned_data_new_base_15.csv\"\n",
|
| 114 |
+
"OUTPUT_DIR = \"/home/ubuntu/Motor_Mapping/MotorMapping/cleaning_data/models/tsdae-fw\"\n",
|
| 115 |
+
"\n",
|
| 116 |
+
"MODEL_NAME = \"google-bert/bert-base-uncased\"\n",
|
| 117 |
+
"MAX_SEQ_LENGTH = 32\n",
|
| 118 |
+
"TRAIN_BATCH_SIZE = 64\n",
|
| 119 |
+
"NUM_EPOCHS = 10\n",
|
| 120 |
+
"LEARNING_RATE = 1e-5 # 3e-5\n",
|
| 121 |
+
"DEL_RATIO = 0.3\n",
|
| 122 |
+
"TEST_SIZE = 0.02\n",
|
| 123 |
+
"N_EVAL_TRIPLETS = 2000\n",
|
| 124 |
+
"SEED = 46\n",
|
| 125 |
+
"\n",
|
| 126 |
+
"random.seed(SEED)"
|
| 127 |
+
]
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"cell_type": "markdown",
|
| 131 |
+
"id": "corpus-md",
|
| 132 |
+
"metadata": {},
|
| 133 |
+
"source": [
|
| 134 |
+
"## Build the corpus\n",
|
| 135 |
+
"\n",
|
| 136 |
+
"One string per row: `make model variant fuel cc`, lowercased, with `CC` as an integer and empty/zero fields dropped.\n",
|
| 137 |
+
"Deduplicated, because the 153k rows contain the same vehicle string many times over (once per insurer) and TSDAE\n",
|
| 138 |
+
"gains nothing from seeing an identical string repeatedly."
|
| 139 |
+
]
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"cell_type": "code",
|
| 143 |
+
"execution_count": 20,
|
| 144 |
+
"id": "corpus",
|
| 145 |
+
"metadata": {},
|
| 146 |
+
"outputs": [
|
| 147 |
+
{
|
| 148 |
+
"name": "stdout",
|
| 149 |
+
"output_type": "stream",
|
| 150 |
+
"text": [
|
| 151 |
+
"rows: 153,738 unique strings: 88,215\n",
|
| 152 |
+
"\n",
|
| 153 |
+
" ac six vintage six royal roadstar petrol 1995\n",
|
| 154 |
+
" alfa romeo 156 gta std petrol 3179\n",
|
| 155 |
+
" alfa romeo alfa romeo alfa 159 3.2 jts v6 ti petrol 3195\n",
|
| 156 |
+
" alfa romeo giulia sprint 1600 gta petrol 1570\n",
|
| 157 |
+
" alfa romeo vintage alfa romeo petrol 1110\n",
|
| 158 |
+
" alfa romeo vintage alfa romeo petrol 1570\n",
|
| 159 |
+
" alfa romeo vintage alfa romeo petrol 1750\n",
|
| 160 |
+
" alfa romeo vintage romeo petrol 1100\n",
|
| 161 |
+
"\n",
|
| 162 |
+
"count 5000.000000\n",
|
| 163 |
+
"mean 7.820600\n",
|
| 164 |
+
"std 1.801961\n",
|
| 165 |
+
"min 3.000000\n",
|
| 166 |
+
"25% 7.000000\n",
|
| 167 |
+
"50% 8.000000\n",
|
| 168 |
+
"75% 9.000000\n",
|
| 169 |
+
"max 17.000000\n",
|
| 170 |
+
"dtype: float64\n"
|
| 171 |
+
]
|
| 172 |
+
}
|
| 173 |
+
],
|
| 174 |
+
"source": [
|
| 175 |
+
"FEATURE_COLS = [\"Make\", \"Model\", \"Variant\", \"Fuel\", \"CC\"]\n",
|
| 176 |
+
"GROUP_COLS = [\"MAKE\", \"NEW_MODELS\"]\n",
|
| 177 |
+
"NUMERIC_COLS = {\"CC\", \"NEW_CC\", \"SC\"}\n",
|
| 178 |
+
"\n",
|
| 179 |
+
"df = pd.read_csv(CSV_PATH, usecols=FEATURE_COLS + GROUP_COLS, low_memory=False)\n",
|
| 180 |
+
"\n",
|
| 181 |
+
"\n",
|
| 182 |
+
"def build_text(frame, cols=FEATURE_COLS):\n",
|
| 183 |
+
" parts = []\n",
|
| 184 |
+
" for col in cols:\n",
|
| 185 |
+
" if col in NUMERIC_COLS:\n",
|
| 186 |
+
" s = pd.to_numeric(frame[col], errors=\"coerce\").fillna(0).astype(int).astype(str)\n",
|
| 187 |
+
" s = s.replace(\"0\", \"\")\n",
|
| 188 |
+
" else:\n",
|
| 189 |
+
" s = frame[col].fillna(\"\").astype(str).str.lower().str.strip()\n",
|
| 190 |
+
" parts.append(s)\n",
|
| 191 |
+
" text = parts[0]\n",
|
| 192 |
+
" for s in parts[1:]:\n",
|
| 193 |
+
" text = text.str.cat(s, sep=\" \")\n",
|
| 194 |
+
" return text.str.replace(r\"\\s+\", \" \", regex=True).str.strip()\n",
|
| 195 |
+
"\n",
|
| 196 |
+
"\n",
|
| 197 |
+
"df[\"text\"] = build_text(df)\n",
|
| 198 |
+
"corpus = sorted({t for t in df[\"text\"] if t})\n",
|
| 199 |
+
"\n",
|
| 200 |
+
"print(f\"rows: {len(df):,} unique strings: {len(corpus):,}\")\n",
|
| 201 |
+
"print()\n",
|
| 202 |
+
"for t in corpus[:8]:\n",
|
| 203 |
+
" print(\" \", t)\n",
|
| 204 |
+
"print()\n",
|
| 205 |
+
"print(pd.Series([len(word_tokenize(t)) for t in corpus[:5000]]).describe())"
|
| 206 |
+
]
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"cell_type": "markdown",
|
| 210 |
+
"id": "noise-md",
|
| 211 |
+
"metadata": {},
|
| 212 |
+
"source": [
|
| 213 |
+
"## Add deletion noise\n",
|
| 214 |
+
"\n",
|
| 215 |
+
"TSDAE's objective: reconstruct the original string from a corrupted copy, forcing the pooled `[CLS]` vector to carry\n",
|
| 216 |
+
"the whole meaning. `delete_noise` keeps each token with probability `1 - DEL_RATIO`, and always keeps at least one\n",
|
| 217 |
+
"token β on strings this short an unguarded sampling run can delete everything, and an empty input teaches nothing.\n",
|
| 218 |
+
"\n",
|
| 219 |
+
"`DenoisingAutoEncoderLoss` reads the columns positionally as `(damaged, original)`, so `select_columns` pins that order."
|
| 220 |
+
]
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"cell_type": "code",
|
| 224 |
+
"execution_count": 21,
|
| 225 |
+
"id": "noise",
|
| 226 |
+
"metadata": {},
|
| 227 |
+
"outputs": [
|
| 228 |
+
{
|
| 229 |
+
"name": "stderr",
|
| 230 |
+
"output_type": "stream",
|
| 231 |
+
"text": [
|
| 232 |
+
"Map: 100%|ββββββββββ| 88215/88215 [00:05<00:00, 15160.07 examples/s]"
|
| 233 |
+
]
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"name": "stdout",
|
| 237 |
+
"output_type": "stream",
|
| 238 |
+
"text": [
|
| 239 |
+
"Dataset({\n",
|
| 240 |
+
" features: ['damaged', 'original'],\n",
|
| 241 |
+
" num_rows: 86450\n",
|
| 242 |
+
"})\n",
|
| 243 |
+
" '1.5 petrol 1482' <- 'hyundai alcazar 1.5 executive mt petrol 1482'\n",
|
| 244 |
+
" 'mahindra. 300 1.5 w8 tone diesel 1497' <- 'mahindra. xuv 300 1.5 w8 dual tone diesel 1497'\n",
|
| 245 |
+
" 'mahindra scorpio vlx mhawk bs iv airbag diesel 2179' <- 'mahindra scorpio vlx 2.2 mhawk bs iv airbag diesel 2179'\n",
|
| 246 |
+
" 'kia carens clavis o bsvi diesel' <- 'kia carens clavis htk plus (o) bsvi diesel 1493'\n",
|
| 247 |
+
" 'nissan kicks 1.3 pre (o) petrol 1298' <- 'nissan motors kicks 1.3 turbo xv pre (o) bsvi petrol 1298'\n"
|
| 248 |
+
]
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"name": "stderr",
|
| 252 |
+
"output_type": "stream",
|
| 253 |
+
"text": [
|
| 254 |
+
"\n"
|
| 255 |
+
]
|
| 256 |
+
}
|
| 257 |
+
],
|
| 258 |
+
"source": [
|
| 259 |
+
"detokenizer = TreebankWordDetokenizer()\n",
|
| 260 |
+
"\n",
|
| 261 |
+
"\n",
|
| 262 |
+
"def delete_noise(text, del_ratio=DEL_RATIO):\n",
|
| 263 |
+
" words = word_tokenize(text)\n",
|
| 264 |
+
" if not words:\n",
|
| 265 |
+
" return text\n",
|
| 266 |
+
" kept = [w for w in words if random.random() >= del_ratio]\n",
|
| 267 |
+
" if not kept:\n",
|
| 268 |
+
" kept = [random.choice(words)]\n",
|
| 269 |
+
" return detokenizer.detokenize(kept)\n",
|
| 270 |
+
"\n",
|
| 271 |
+
"\n",
|
| 272 |
+
"def noise_batch(batch):\n",
|
| 273 |
+
" return {\"damaged\": [delete_noise(t) for t in batch[\"original\"]]}\n",
|
| 274 |
+
"\n",
|
| 275 |
+
"\n",
|
| 276 |
+
"dataset = Dataset.from_dict({\"original\": corpus})\n",
|
| 277 |
+
"dataset = dataset.map(noise_batch, batched=True, batch_size=2000)\n",
|
| 278 |
+
"dataset = dataset.select_columns([\"damaged\", \"original\"])\n",
|
| 279 |
+
"\n",
|
| 280 |
+
"split = dataset.train_test_split(test_size=TEST_SIZE, seed=SEED)\n",
|
| 281 |
+
"train_dataset, eval_dataset = split[\"train\"], split[\"test\"]\n",
|
| 282 |
+
"\n",
|
| 283 |
+
"print(train_dataset)\n",
|
| 284 |
+
"for i in range(5):\n",
|
| 285 |
+
" row = train_dataset[i]\n",
|
| 286 |
+
" print(f\" {row['damaged']!r:<45} <- {row['original']!r}\")"
|
| 287 |
+
]
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"cell_type": "markdown",
|
| 291 |
+
"id": "model-md",
|
| 292 |
+
"metadata": {},
|
| 293 |
+
"source": [
|
| 294 |
+
"## Model and loss\n",
|
| 295 |
+
"\n",
|
| 296 |
+
"CLS pooling and a tied encoder/decoder, per the TSDAE paper. `decoder_name_or_path` takes the model *name*, not the\n",
|
| 297 |
+
"`SentenceTransformer` object."
|
| 298 |
+
]
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"cell_type": "code",
|
| 302 |
+
"execution_count": 22,
|
| 303 |
+
"id": "model",
|
| 304 |
+
"metadata": {},
|
| 305 |
+
"outputs": [
|
| 306 |
+
{
|
| 307 |
+
"name": "stderr",
|
| 308 |
+
"output_type": "stream",
|
| 309 |
+
"text": [
|
| 310 |
+
"Loading weights: 100%|ββββββββββ| 199/199 [00:00<00:00, 3305.71it/s]\n",
|
| 311 |
+
"[transformers] \u001b[1mBertModel LOAD REPORT\u001b[0m from: google-bert/bert-base-uncased\n",
|
| 312 |
+
"Key | Status | | \n",
|
| 313 |
+
"-------------------------------------------+------------+--+-\n",
|
| 314 |
+
"cls.seq_relationship.bias | UNEXPECTED | | \n",
|
| 315 |
+
"cls.predictions.transform.LayerNorm.bias | UNEXPECTED | | \n",
|
| 316 |
+
"cls.predictions.transform.dense.weight | UNEXPECTED | | \n",
|
| 317 |
+
"cls.predictions.transform.dense.bias | UNEXPECTED | | \n",
|
| 318 |
+
"cls.seq_relationship.weight | UNEXPECTED | | \n",
|
| 319 |
+
"cls.predictions.transform.LayerNorm.weight | UNEXPECTED | | \n",
|
| 320 |
+
"cls.predictions.bias | UNEXPECTED | | \n",
|
| 321 |
+
"\n",
|
| 322 |
+
"Notes:\n",
|
| 323 |
+
"- UNEXPECTED:\tcan be ignored when loading from different task/architecture; not ok if you expect identical arch.\n",
|
| 324 |
+
"/tmp/ipykernel_117871/364354980.py:2: FutureWarning: The `get_word_embedding_dimension` method has been renamed to `get_embedding_dimension`.\n",
|
| 325 |
+
" pooling_model = models.Pooling(word_embedding_model.get_word_embedding_dimension(), \"cls\")\n",
|
| 326 |
+
"When tie_encoder_decoder=True, the decoder_name_or_path will be invalid.\n",
|
| 327 |
+
"Loading weights: 100%|ββββββββββ| 202/202 [00:00<00:00, 3428.92it/s]\n",
|
| 328 |
+
"[transformers] \u001b[1mBertLMHeadModel LOAD REPORT\u001b[0m from: google-bert/bert-base-uncased\n",
|
| 329 |
+
"Key | Status | \n",
|
| 330 |
+
"-------------------------------------------------------------------+------------+-\n",
|
| 331 |
+
"bert.pooler.dense.bias | UNEXPECTED | \n",
|
| 332 |
+
"bert.pooler.dense.weight | UNEXPECTED | \n",
|
| 333 |
+
"cls.seq_relationship.bias | UNEXPECTED | \n",
|
| 334 |
+
"cls.seq_relationship.weight | UNEXPECTED | \n",
|
| 335 |
+
"bert.encoder.layer.{0...11}.crossattention.self.key.bias | MISSING | \n",
|
| 336 |
+
"bert.encoder.layer.{0...11}.crossattention.output.LayerNorm.bias | MISSING | \n",
|
| 337 |
+
"bert.encoder.layer.{0...11}.crossattention.output.LayerNorm.weight | MISSING | \n",
|
| 338 |
+
"bert.encoder.layer.{0...11}.crossattention.self.value.weight | MISSING | \n",
|
| 339 |
+
"bert.encoder.layer.{0...11}.crossattention.self.query.weight | MISSING | \n",
|
| 340 |
+
"bert.encoder.layer.{0...11}.crossattention.output.dense.bias | MISSING | \n",
|
| 341 |
+
"bert.encoder.layer.{0...11}.crossattention.self.query.bias | MISSING | \n",
|
| 342 |
+
"bert.encoder.layer.{0...11}.crossattention.output.dense.weight | MISSING | \n",
|
| 343 |
+
"bert.encoder.layer.{0...11}.crossattention.self.value.bias | MISSING | \n",
|
| 344 |
+
"bert.encoder.layer.{0...11}.crossattention.self.key.weight | MISSING | \n",
|
| 345 |
+
"\n",
|
| 346 |
+
"Notes:\n",
|
| 347 |
+
"- UNEXPECTED:\tcan be ignored when loading from different task/architecture; not ok if you expect identical arch.\n",
|
| 348 |
+
"- MISSING:\tthose params were newly initialized because missing from the checkpoint. Consider training on your downstream task.\n"
|
| 349 |
+
]
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"name": "stdout",
|
| 353 |
+
"output_type": "stream",
|
| 354 |
+
"text": [
|
| 355 |
+
"SentenceTransformer(\n",
|
| 356 |
+
" (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})\n",
|
| 357 |
+
" (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'cls', 'include_prompt': True})\n",
|
| 358 |
+
")\n"
|
| 359 |
+
]
|
| 360 |
+
}
|
| 361 |
+
],
|
| 362 |
+
"source": [
|
| 363 |
+
"word_embedding_model = models.Transformer(MODEL_NAME, max_seq_length=MAX_SEQ_LENGTH)\n",
|
| 364 |
+
"pooling_model = models.Pooling(word_embedding_model.get_word_embedding_dimension(), \"cls\")\n",
|
| 365 |
+
"model = SentenceTransformer(modules=[word_embedding_model, pooling_model])\n",
|
| 366 |
+
"\n",
|
| 367 |
+
"train_loss = losses.DenoisingAutoEncoderLoss(\n",
|
| 368 |
+
" model,\n",
|
| 369 |
+
" decoder_name_or_path=MODEL_NAME,\n",
|
| 370 |
+
" tie_encoder_decoder=True,\n",
|
| 371 |
+
")\n",
|
| 372 |
+
"\n",
|
| 373 |
+
"print(model)"
|
| 374 |
+
]
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"cell_type": "markdown",
|
| 378 |
+
"id": "eval-md",
|
| 379 |
+
"metadata": {},
|
| 380 |
+
"source": [
|
| 381 |
+
"## Domain evaluator\n",
|
| 382 |
+
"\n",
|
| 383 |
+
"Triplets are derived from columns the CSV already has, so no hand labelling is needed:\n",
|
| 384 |
+
"\n",
|
| 385 |
+
"- **group** = `MAKE` + `NEW_MODELS` + `Fuel` β the canonical vehicle, from the cleaned columns.\n",
|
| 386 |
+
"- **anchor / positive** = two different raw strings in the same group (same vehicle, different insurer wording).\n",
|
| 387 |
+
"- **negative** = a string from a *different* group under the *same* make β a hard negative, since `maruti swift` and\n",
|
| 388 |
+
" `maruti dzire` share tokens and are the pairs the mapper actually confuses.\n",
|
| 389 |
+
"\n",
|
| 390 |
+
"The reported accuracy is the fraction of triplets where the anchor sits closer to its positive than to its negative.\n",
|
| 391 |
+
"Note this is measured on strings the unsupervised training also sees; the grouping is never shown to the model, so it\n",
|
| 392 |
+
"scores embedding geometry rather than generalization to unseen strings."
|
| 393 |
+
]
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"cell_type": "code",
|
| 397 |
+
"execution_count": 23,
|
| 398 |
+
"id": "evaluator",
|
| 399 |
+
"metadata": {},
|
| 400 |
+
"outputs": [
|
| 401 |
+
{
|
| 402 |
+
"name": "stdout",
|
| 403 |
+
"output_type": "stream",
|
| 404 |
+
"text": [
|
| 405 |
+
"groups :0 premier | padmini | petrol\n",
|
| 406 |
+
"1 mahindra | economy | diesel\n",
|
| 407 |
+
"2 mahindra | forester | diesel\n",
|
| 408 |
+
"3 toyota | land cruiser | diesel\n",
|
| 409 |
+
"4 mahindra | forester | diesel\n",
|
| 410 |
+
" ... \n",
|
| 411 |
+
"153733 citroen | c3 aircross | petrol\n",
|
| 412 |
+
"153734 mahindra | scorpio | diesel\n",
|
| 413 |
+
"153735 tata | safari | diesel\n",
|
| 414 |
+
"153736 bmw | xm | petrol\n",
|
| 415 |
+
"153737 tesla | model y | electric\n",
|
| 416 |
+
"Length: 153738, dtype: str\n",
|
| 417 |
+
"grouped:group\n",
|
| 418 |
+
"ac | vintage | petrol [ac six vintage six royal roadstar petrol 1995]\n",
|
| 419 |
+
"alfa | 156 gta | petrol [alfa romeo 156 gta std petrol 3179]\n",
|
| 420 |
+
"alfa | alfa romeo | petrol [alfa romeo alfa romeo alfa 159 3.2 jts v6 ti ...\n",
|
| 421 |
+
"alfa | giulia sprint | petrol [alfa romeo giulia sprint 1600 gta petrol 1570]\n",
|
| 422 |
+
"alfa | vintage | petrol [alfa romeo vintage alfa romeo petrol 1570, al...\n",
|
| 423 |
+
" ... \n",
|
| 424 |
+
"wolseley | 16/20 | petrol [wolseley 16/20 saloon petrol 1140]\n",
|
| 425 |
+
"wolseley | vintage | petrol [wolseley vintage 12 hp petrol 1260, wolseley ...\n",
|
| 426 |
+
"wuling | almaz rs | hybrid [wuling almaz rs 2.0 pro hybrid hybrid 1999]\n",
|
| 427 |
+
"yamaha | yzf r15 | petrol [yamaha yzf r15 yzf r15 bs-iv petrol 155]\n",
|
| 428 |
+
"zotye | rx 6400 | diesel [zotye auto rx 6400 1.3 l diesel 1527]\n",
|
| 429 |
+
"Name: text, Length: 3671, dtype: object\n",
|
| 430 |
+
"dev_evaluator :<sentence_transformers.sentence_transformer.evaluation.triplet.TripletEvaluator object at 0x7d53e2333c80>\n",
|
| 431 |
+
"groups with >=2 strings: 2,392 triplets: 2,000\n",
|
| 432 |
+
"\n",
|
| 433 |
+
"anchor: standard herald vintage station wagon petrol 1100\n",
|
| 434 |
+
"positive: standard herald vintage vintage petrol 800\n",
|
| 435 |
+
"negative: standard standard super 10 petrol 1340\n",
|
| 436 |
+
"\n",
|
| 437 |
+
"anchor: mahindra reva electric vehicles e 20 t 2 48v electric 1\n",
|
| 438 |
+
"positive: mahindra reva e 20 t 2 electric 1\n",
|
| 439 |
+
"negative: mahindra electric mobility limited treo treo sft electric 1\n",
|
| 440 |
+
"\n",
|
| 441 |
+
"anchor: audi a5 2.0 tdi cabriolet diesel 1968\n",
|
| 442 |
+
"positive: audi a5 cabriolet 2.0 tdi diesel 1984\n",
|
| 443 |
+
"negative: audi rs q8 4.0 tfsi quattro petrol 3998\n",
|
| 444 |
+
"\n"
|
| 445 |
+
]
|
| 446 |
+
}
|
| 447 |
+
],
|
| 448 |
+
"source": [
|
| 449 |
+
"group_key = (\n",
|
| 450 |
+
" df[\"MAKE\"].fillna(\"\").astype(str).str.lower().str.strip()\n",
|
| 451 |
+
" + \" | \"\n",
|
| 452 |
+
" + df[\"NEW_MODELS\"].fillna(\"\").astype(str).str.lower().str.strip()\n",
|
| 453 |
+
" + \" | \"\n",
|
| 454 |
+
" + df[\"Fuel\"].fillna(\"\").astype(str).str.lower().str.strip()\n",
|
| 455 |
+
")\n",
|
| 456 |
+
"print(f\"groups :{group_key}\")\n",
|
| 457 |
+
"\n",
|
| 458 |
+
"df[\"group\"] = group_key\n",
|
| 459 |
+
"\n",
|
| 460 |
+
"grouped = df[df[\"text\"] != \"\"].groupby(\"group\")[\"text\"].apply(lambda s: list(dict.fromkeys(s)))\n",
|
| 461 |
+
"print(f\"grouped:{grouped}\")\n",
|
| 462 |
+
"grouped = grouped[grouped.map(len) >= 2]\n",
|
| 463 |
+
"\n",
|
| 464 |
+
"by_make = defaultdict(list)\n",
|
| 465 |
+
"for g in grouped.index:\n",
|
| 466 |
+
" by_make[g.split(\" | \")[0]].append(g)\n",
|
| 467 |
+
"\n",
|
| 468 |
+
"rng = random.Random(SEED)\n",
|
| 469 |
+
"group_names = list(grouped.index)\n",
|
| 470 |
+
"rng.shuffle(group_names)\n",
|
| 471 |
+
"\n",
|
| 472 |
+
"anchors, positives, negatives = [], [], []\n",
|
| 473 |
+
"for g in group_names:\n",
|
| 474 |
+
" if len(anchors) >= N_EVAL_TRIPLETS:\n",
|
| 475 |
+
" break\n",
|
| 476 |
+
" a, p = rng.sample(grouped[g], 2)\n",
|
| 477 |
+
" same_make = [x for x in by_make[g.split(\" | \")[0]] if x != g]\n",
|
| 478 |
+
" pool = same_make or [x for x in group_names if x != g]\n",
|
| 479 |
+
" anchors.append(a)\n",
|
| 480 |
+
" positives.append(p)\n",
|
| 481 |
+
" negatives.append(rng.choice(grouped[rng.choice(pool)]))\n",
|
| 482 |
+
"\n",
|
| 483 |
+
"dev_evaluator = TripletEvaluator(\n",
|
| 484 |
+
" anchors=anchors,\n",
|
| 485 |
+
" positives=positives,\n",
|
| 486 |
+
" negatives=negatives,\n",
|
| 487 |
+
" name=\"fw-variant-dev\",\n",
|
| 488 |
+
")\n",
|
| 489 |
+
"\n",
|
| 490 |
+
"\n",
|
| 491 |
+
"print(f\"dev_evaluator :{dev_evaluator}\")\n",
|
| 492 |
+
"\n",
|
| 493 |
+
"print(f\"groups with >=2 strings: {len(grouped):,} triplets: {len(anchors):,}\\n\")\n",
|
| 494 |
+
"for i in range(3):\n",
|
| 495 |
+
" print(f\"anchor: {anchors[i]}\")\n",
|
| 496 |
+
" print(f\"positive: {positives[i]}\")\n",
|
| 497 |
+
" print(f\"negative: {negatives[i]}\\n\")"
|
| 498 |
+
]
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"cell_type": "code",
|
| 502 |
+
"execution_count": 24,
|
| 503 |
+
"id": "baseline",
|
| 504 |
+
"metadata": {},
|
| 505 |
+
"outputs": [
|
| 506 |
+
{
|
| 507 |
+
"name": "stdout",
|
| 508 |
+
"output_type": "stream",
|
| 509 |
+
"text": [
|
| 510 |
+
"{'fw-variant-dev_cosine_accuracy': 0.8845000267028809}\n"
|
| 511 |
+
]
|
| 512 |
+
}
|
| 513 |
+
],
|
| 514 |
+
"source": [
|
| 515 |
+
"# Baseline before any training β compare against the post-training number below.\n",
|
| 516 |
+
"print(dev_evaluator(model))"
|
| 517 |
+
]
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"cell_type": "code",
|
| 521 |
+
"execution_count": 25,
|
| 522 |
+
"id": "args",
|
| 523 |
+
"metadata": {},
|
| 524 |
+
"outputs": [
|
| 525 |
+
{
|
| 526 |
+
"name": "stderr",
|
| 527 |
+
"output_type": "stream",
|
| 528 |
+
"text": [
|
| 529 |
+
"The `warmup_ratio` argument is deprecated in Transformers v5+, and will also be removed from Sentence Transformers once support for Transformers v4 is dropped. Since you're using Transformers v5+, please use `warmup_steps` (as a float) to specify the warmup ratio instead.\n"
|
| 530 |
+
]
|
| 531 |
+
}
|
| 532 |
+
],
|
| 533 |
+
"source": [
|
| 534 |
+
"args = SentenceTransformerTrainingArguments(\n",
|
| 535 |
+
" output_dir=OUTPUT_DIR,\n",
|
| 536 |
+
" num_train_epochs=NUM_EPOCHS,\n",
|
| 537 |
+
" per_device_train_batch_size=TRAIN_BATCH_SIZE,\n",
|
| 538 |
+
" per_device_eval_batch_size=TRAIN_BATCH_SIZE,\n",
|
| 539 |
+
" learning_rate=LEARNING_RATE,\n",
|
| 540 |
+
" weight_decay=0.0,\n",
|
| 541 |
+
" warmup_ratio=0.1,\n",
|
| 542 |
+
" bf16=True,\n",
|
| 543 |
+
" fp16=False,\n",
|
| 544 |
+
" eval_strategy=\"steps\",\n",
|
| 545 |
+
" eval_steps=500,\n",
|
| 546 |
+
" save_steps=1000,\n",
|
| 547 |
+
" save_total_limit=2,\n",
|
| 548 |
+
" logging_steps=50,\n",
|
| 549 |
+
" seed=SEED,\n",
|
| 550 |
+
" run_name=\"tsdae_new-fw\",\n",
|
| 551 |
+
")"
|
| 552 |
+
]
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"cell_type": "code",
|
| 556 |
+
"execution_count": 26,
|
| 557 |
+
"id": "trainer",
|
| 558 |
+
"metadata": {},
|
| 559 |
+
"outputs": [
|
| 560 |
+
{
|
| 561 |
+
"name": "stderr",
|
| 562 |
+
"output_type": "stream",
|
| 563 |
+
"text": [
|
| 564 |
+
" \r"
|
| 565 |
+
]
|
| 566 |
+
}
|
| 567 |
+
],
|
| 568 |
+
"source": [
|
| 569 |
+
"trainer = SentenceTransformerTrainer(\n",
|
| 570 |
+
" model=model,\n",
|
| 571 |
+
" args=args,\n",
|
| 572 |
+
" train_dataset=train_dataset,\n",
|
| 573 |
+
" eval_dataset=eval_dataset,\n",
|
| 574 |
+
" loss=train_loss,\n",
|
| 575 |
+
" evaluator=dev_evaluator,\n",
|
| 576 |
+
")"
|
| 577 |
+
]
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"cell_type": "code",
|
| 581 |
+
"execution_count": 27,
|
| 582 |
+
"id": "train",
|
| 583 |
+
"metadata": {},
|
| 584 |
+
"outputs": [
|
| 585 |
+
{
|
| 586 |
+
"data": {
|
| 587 |
+
"text/html": [
|
| 588 |
+
"\n",
|
| 589 |
+
" <div>\n",
|
| 590 |
+
" \n",
|
| 591 |
+
" <progress value='13510' max='13510' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
|
| 592 |
+
" [13510/13510 38:36, Epoch 10/10]\n",
|
| 593 |
+
" </div>\n",
|
| 594 |
+
" <table border=\"1\" class=\"dataframe\">\n",
|
| 595 |
+
" <thead>\n",
|
| 596 |
+
" <tr style=\"text-align: left;\">\n",
|
| 597 |
+
" <th>Step</th>\n",
|
| 598 |
+
" <th>Training Loss</th>\n",
|
| 599 |
+
" <th>Validation Loss</th>\n",
|
| 600 |
+
" <th>Fw-variant-dev Cosine Accuracy</th>\n",
|
| 601 |
+
" </tr>\n",
|
| 602 |
+
" </thead>\n",
|
| 603 |
+
" <tbody>\n",
|
| 604 |
+
" <tr>\n",
|
| 605 |
+
" <td>500</td>\n",
|
| 606 |
+
" <td>3.519659</td>\n",
|
| 607 |
+
" <td>3.315504</td>\n",
|
| 608 |
+
" <td>0.888500</td>\n",
|
| 609 |
+
" </tr>\n",
|
| 610 |
+
" <tr>\n",
|
| 611 |
+
" <td>1000</td>\n",
|
| 612 |
+
" <td>1.906371</td>\n",
|
| 613 |
+
" <td>1.835182</td>\n",
|
| 614 |
+
" <td>0.968000</td>\n",
|
| 615 |
+
" </tr>\n",
|
| 616 |
+
" <tr>\n",
|
| 617 |
+
" <td>1500</td>\n",
|
| 618 |
+
" <td>1.264665</td>\n",
|
| 619 |
+
" <td>1.237239</td>\n",
|
| 620 |
+
" <td>0.967000</td>\n",
|
| 621 |
+
" </tr>\n",
|
| 622 |
+
" <tr>\n",
|
| 623 |
+
" <td>2000</td>\n",
|
| 624 |
+
" <td>1.035154</td>\n",
|
| 625 |
+
" <td>0.979282</td>\n",
|
| 626 |
+
" <td>0.968000</td>\n",
|
| 627 |
+
" </tr>\n",
|
| 628 |
+
" <tr>\n",
|
| 629 |
+
" <td>2500</td>\n",
|
| 630 |
+
" <td>0.904463</td>\n",
|
| 631 |
+
" <td>0.855952</td>\n",
|
| 632 |
+
" <td>0.963500</td>\n",
|
| 633 |
+
" </tr>\n",
|
| 634 |
+
" <tr>\n",
|
| 635 |
+
" <td>3000</td>\n",
|
| 636 |
+
" <td>0.766660</td>\n",
|
| 637 |
+
" <td>0.772152</td>\n",
|
| 638 |
+
" <td>0.964500</td>\n",
|
| 639 |
+
" </tr>\n",
|
| 640 |
+
" <tr>\n",
|
| 641 |
+
" <td>3500</td>\n",
|
| 642 |
+
" <td>0.737115</td>\n",
|
| 643 |
+
" <td>0.723460</td>\n",
|
| 644 |
+
" <td>0.965000</td>\n",
|
| 645 |
+
" </tr>\n",
|
| 646 |
+
" <tr>\n",
|
| 647 |
+
" <td>4000</td>\n",
|
| 648 |
+
" <td>0.697386</td>\n",
|
| 649 |
+
" <td>0.687482</td>\n",
|
| 650 |
+
" <td>0.966000</td>\n",
|
| 651 |
+
" </tr>\n",
|
| 652 |
+
" <tr>\n",
|
| 653 |
+
" <td>4500</td>\n",
|
| 654 |
+
" <td>0.622651</td>\n",
|
| 655 |
+
" <td>0.657369</td>\n",
|
| 656 |
+
" <td>0.964000</td>\n",
|
| 657 |
+
" </tr>\n",
|
| 658 |
+
" <tr>\n",
|
| 659 |
+
" <td>5000</td>\n",
|
| 660 |
+
" <td>0.617842</td>\n",
|
| 661 |
+
" <td>0.635764</td>\n",
|
| 662 |
+
" <td>0.964500</td>\n",
|
| 663 |
+
" </tr>\n",
|
| 664 |
+
" <tr>\n",
|
| 665 |
+
" <td>5500</td>\n",
|
| 666 |
+
" <td>0.561297</td>\n",
|
| 667 |
+
" <td>0.606327</td>\n",
|
| 668 |
+
" <td>0.965000</td>\n",
|
| 669 |
+
" </tr>\n",
|
| 670 |
+
" <tr>\n",
|
| 671 |
+
" <td>6000</td>\n",
|
| 672 |
+
" <td>0.545678</td>\n",
|
| 673 |
+
" <td>0.599327</td>\n",
|
| 674 |
+
" <td>0.967500</td>\n",
|
| 675 |
+
" </tr>\n",
|
| 676 |
+
" <tr>\n",
|
| 677 |
+
" <td>6500</td>\n",
|
| 678 |
+
" <td>0.542860</td>\n",
|
| 679 |
+
" <td>0.576558</td>\n",
|
| 680 |
+
" <td>0.964500</td>\n",
|
| 681 |
+
" </tr>\n",
|
| 682 |
+
" <tr>\n",
|
| 683 |
+
" <td>7000</td>\n",
|
| 684 |
+
" <td>0.491351</td>\n",
|
| 685 |
+
" <td>0.570122</td>\n",
|
| 686 |
+
" <td>0.965500</td>\n",
|
| 687 |
+
" </tr>\n",
|
| 688 |
+
" <tr>\n",
|
| 689 |
+
" <td>7500</td>\n",
|
| 690 |
+
" <td>0.478219</td>\n",
|
| 691 |
+
" <td>0.564613</td>\n",
|
| 692 |
+
" <td>0.964000</td>\n",
|
| 693 |
+
" </tr>\n",
|
| 694 |
+
" <tr>\n",
|
| 695 |
+
" <td>8000</td>\n",
|
| 696 |
+
" <td>0.481421</td>\n",
|
| 697 |
+
" <td>0.548468</td>\n",
|
| 698 |
+
" <td>0.967500</td>\n",
|
| 699 |
+
" </tr>\n",
|
| 700 |
+
" <tr>\n",
|
| 701 |
+
" <td>8500</td>\n",
|
| 702 |
+
" <td>0.452666</td>\n",
|
| 703 |
+
" <td>0.542519</td>\n",
|
| 704 |
+
" <td>0.965500</td>\n",
|
| 705 |
+
" </tr>\n",
|
| 706 |
+
" <tr>\n",
|
| 707 |
+
" <td>9000</td>\n",
|
| 708 |
+
" <td>0.447252</td>\n",
|
| 709 |
+
" <td>0.534722</td>\n",
|
| 710 |
+
" <td>0.965500</td>\n",
|
| 711 |
+
" </tr>\n",
|
| 712 |
+
" <tr>\n",
|
| 713 |
+
" <td>9500</td>\n",
|
| 714 |
+
" <td>0.416157</td>\n",
|
| 715 |
+
" <td>0.526371</td>\n",
|
| 716 |
+
" <td>0.967000</td>\n",
|
| 717 |
+
" </tr>\n",
|
| 718 |
+
" <tr>\n",
|
| 719 |
+
" <td>10000</td>\n",
|
| 720 |
+
" <td>0.419636</td>\n",
|
| 721 |
+
" <td>0.521664</td>\n",
|
| 722 |
+
" <td>0.966500</td>\n",
|
| 723 |
+
" </tr>\n",
|
| 724 |
+
" <tr>\n",
|
| 725 |
+
" <td>10500</td>\n",
|
| 726 |
+
" <td>0.421646</td>\n",
|
| 727 |
+
" <td>0.519755</td>\n",
|
| 728 |
+
" <td>0.967000</td>\n",
|
| 729 |
+
" </tr>\n",
|
| 730 |
+
" <tr>\n",
|
| 731 |
+
" <td>11000</td>\n",
|
| 732 |
+
" <td>0.379481</td>\n",
|
| 733 |
+
" <td>0.511343</td>\n",
|
| 734 |
+
" <td>0.966500</td>\n",
|
| 735 |
+
" </tr>\n",
|
| 736 |
+
" <tr>\n",
|
| 737 |
+
" <td>11500</td>\n",
|
| 738 |
+
" <td>0.377998</td>\n",
|
| 739 |
+
" <td>0.507382</td>\n",
|
| 740 |
+
" <td>0.967000</td>\n",
|
| 741 |
+
" </tr>\n",
|
| 742 |
+
" <tr>\n",
|
| 743 |
+
" <td>12000</td>\n",
|
| 744 |
+
" <td>0.371554</td>\n",
|
| 745 |
+
" <td>0.505013</td>\n",
|
| 746 |
+
" <td>0.965500</td>\n",
|
| 747 |
+
" </tr>\n",
|
| 748 |
+
" <tr>\n",
|
| 749 |
+
" <td>12500</td>\n",
|
| 750 |
+
" <td>0.364893</td>\n",
|
| 751 |
+
" <td>0.500249</td>\n",
|
| 752 |
+
" <td>0.966000</td>\n",
|
| 753 |
+
" </tr>\n",
|
| 754 |
+
" <tr>\n",
|
| 755 |
+
" <td>13000</td>\n",
|
| 756 |
+
" <td>0.362321</td>\n",
|
| 757 |
+
" <td>0.498431</td>\n",
|
| 758 |
+
" <td>0.966500</td>\n",
|
| 759 |
+
" </tr>\n",
|
| 760 |
+
" <tr>\n",
|
| 761 |
+
" <td>13500</td>\n",
|
| 762 |
+
" <td>0.370435</td>\n",
|
| 763 |
+
" <td>0.497299</td>\n",
|
| 764 |
+
" <td>0.965500</td>\n",
|
| 765 |
+
" </tr>\n",
|
| 766 |
+
" <tr>\n",
|
| 767 |
+
" <td>13510</td>\n",
|
| 768 |
+
" <td>0.370435</td>\n",
|
| 769 |
+
" <td>0.497360</td>\n",
|
| 770 |
+
" <td>0.966000</td>\n",
|
| 771 |
+
" </tr>\n",
|
| 772 |
+
" </tbody>\n",
|
| 773 |
+
"</table><p>"
|
| 774 |
+
],
|
| 775 |
+
"text/plain": [
|
| 776 |
+
"<IPython.core.display.HTML object>"
|
| 777 |
+
]
|
| 778 |
+
},
|
| 779 |
+
"metadata": {},
|
| 780 |
+
"output_type": "display_data"
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"name": "stderr",
|
| 784 |
+
"output_type": "stream",
|
| 785 |
+
"text": [
|
| 786 |
+
"Writing model shards: 100%|ββββββββββ| 1/1 [00:00<00:00, 1.71it/s]\n",
|
| 787 |
+
"Writing model shards: 100%|ββββββββββ| 1/1 [00:00<00:00, 2.25it/s]\n",
|
| 788 |
+
"Writing model shards: 100%|ββββββββββ| 1/1 [00:00<00:00, 2.10it/s]\n",
|
| 789 |
+
"Writing model shards: 100%|ββββββββββ| 1/1 [00:00<00:00, 2.10it/s]\n",
|
| 790 |
+
"Writing model shards: 100%|ββββββββββ| 1/1 [00:00<00:00, 2.17it/s]\n",
|
| 791 |
+
"Writing model shards: 100%|ββββββββββ| 1/1 [00:00<00:00, 2.20it/s]\n",
|
| 792 |
+
"Writing model shards: 100%|ββββββββββ| 1/1 [00:00<00:00, 2.18it/s]\n",
|
| 793 |
+
"Writing model shards: 100%|ββββββββββ| 1/1 [00:00<00:00, 2.15it/s]\n",
|
| 794 |
+
"Writing model shards: 100%|ββββββββββ| 1/1 [00:00<00:00, 2.17it/s]\n",
|
| 795 |
+
"Writing model shards: 100%|ββββββββββ| 1/1 [00:00<00:00, 2.17it/s]\n",
|
| 796 |
+
"Writing model shards: 100%|ββββββββββ| 1/1 [00:00<00:00, 2.19it/s]\n",
|
| 797 |
+
"Writing model shards: 100%|ββββββββββ| 1/1 [00:00<00:00, 2.20it/s]\n",
|
| 798 |
+
"Writing model shards: 100%|ββββββββββ| 1/1 [00:00<00:00, 2.13it/s]\n",
|
| 799 |
+
"Writing model shards: 100%|ββββββββββ| 1/1 [00:00<00:00, 2.20it/s]\n"
|
| 800 |
+
]
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"data": {
|
| 804 |
+
"text/plain": [
|
| 805 |
+
"TrainOutput(global_step=13510, training_loss=0.860432569968268, metrics={'train_runtime': 2316.8877, 'train_samples_per_second': 373.13, 'train_steps_per_second': 5.831, 'total_flos': 0.0, 'train_loss': 0.860432569968268, 'epoch': 10.0})"
|
| 806 |
+
]
|
| 807 |
+
},
|
| 808 |
+
"execution_count": 27,
|
| 809 |
+
"metadata": {},
|
| 810 |
+
"output_type": "execute_result"
|
| 811 |
+
}
|
| 812 |
+
],
|
| 813 |
+
"source": [
|
| 814 |
+
"trainer.train()"
|
| 815 |
+
]
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"cell_type": "code",
|
| 819 |
+
"execution_count": 28,
|
| 820 |
+
"id": "post-eval",
|
| 821 |
+
"metadata": {},
|
| 822 |
+
"outputs": [
|
| 823 |
+
{
|
| 824 |
+
"name": "stdout",
|
| 825 |
+
"output_type": "stream",
|
| 826 |
+
"text": [
|
| 827 |
+
"{'fw-variant-dev_cosine_accuracy': 0.9660000205039978}\n"
|
| 828 |
+
]
|
| 829 |
+
}
|
| 830 |
+
],
|
| 831 |
+
"source": [
|
| 832 |
+
"print(dev_evaluator(model))"
|
| 833 |
+
]
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"cell_type": "code",
|
| 837 |
+
"execution_count": 29,
|
| 838 |
+
"id": "save",
|
| 839 |
+
"metadata": {},
|
| 840 |
+
"outputs": [
|
| 841 |
+
{
|
| 842 |
+
"name": "stderr",
|
| 843 |
+
"output_type": "stream",
|
| 844 |
+
"text": [
|
| 845 |
+
"Writing model shards: 0%| | 0/1 [00:00<?, ?it/s]"
|
| 846 |
+
]
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"name": "stderr",
|
| 850 |
+
"output_type": "stream",
|
| 851 |
+
"text": [
|
| 852 |
+
"Writing model shards: 100%|ββββββββββ| 1/1 [00:02<00:00, 2.75s/it]"
|
| 853 |
+
]
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"name": "stdout",
|
| 857 |
+
"output_type": "stream",
|
| 858 |
+
"text": [
|
| 859 |
+
"/home/ubuntu/Motor_Mapping/MotorMapping/cleaning_data/models/tsdae-fw/final\n"
|
| 860 |
+
]
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"name": "stderr",
|
| 864 |
+
"output_type": "stream",
|
| 865 |
+
"text": [
|
| 866 |
+
"\n"
|
| 867 |
+
]
|
| 868 |
+
}
|
| 869 |
+
],
|
| 870 |
+
"source": [
|
| 871 |
+
"final_output_dir = f\"{OUTPUT_DIR}/final\"\n",
|
| 872 |
+
"model.save(final_output_dir)\n",
|
| 873 |
+
"print(final_output_dir)"
|
| 874 |
+
]
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"cell_type": "markdown",
|
| 878 |
+
"id": "nn-md",
|
| 879 |
+
"metadata": {},
|
| 880 |
+
"source": [
|
| 881 |
+
"## Sanity check: nearest neighbours\n",
|
| 882 |
+
"\n",
|
| 883 |
+
"The triplet accuracy is one number; this shows what the embedding space actually looks like for the mapping task.\n",
|
| 884 |
+
"Swap in strings from insurer files you care about."
|
| 885 |
+
]
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"cell_type": "code",
|
| 889 |
+
"execution_count": null,
|
| 890 |
+
"id": "nn",
|
| 891 |
+
"metadata": {},
|
| 892 |
+
"outputs": [
|
| 893 |
+
{
|
| 894 |
+
"name": "stderr",
|
| 895 |
+
"output_type": "stream",
|
| 896 |
+
"text": [
|
| 897 |
+
"Batches: 100%|ββββββββββ| 345/345 [00:11<00:00, 31.25it/s]\n"
|
| 898 |
+
]
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"name": "stdout",
|
| 902 |
+
"output_type": "stream",
|
| 903 |
+
"text": [
|
| 904 |
+
"\n",
|
| 905 |
+
"query: maruti swift vxi petrol 1197\n",
|
| 906 |
+
" 1.000 maruti swift vxi petrol 1197\n",
|
| 907 |
+
" 0.999 maruti suzuki swift vxi petrol 1197\n",
|
| 908 |
+
" 0.998 maruti swift vxi cng 1197\n",
|
| 909 |
+
" 0.998 maruti swift vxi (o) petrol 1197\n",
|
| 910 |
+
" 0.998 maruti swift vxi amt petrol 1197\n",
|
| 911 |
+
"\n",
|
| 912 |
+
"query: hyundai i20 asta diesel 1396\n",
|
| 913 |
+
" 0.999 hyundai i20 asta 1.4 diesel 1396\n",
|
| 914 |
+
" 0.998 hyundai i20 1.4 asta diesel 1396\n",
|
| 915 |
+
" 0.998 hyundai i20 asta 1.4 crdi diesel 1396\n",
|
| 916 |
+
" 0.997 hyundai i20 asta 1.4 dsl diesel 1396\n",
|
| 917 |
+
" 0.997 hyundai i20 1.4 asta petrol 1396\n",
|
| 918 |
+
"\n",
|
| 919 |
+
"query: mahindra xuv500 w8 diesel 2179\n",
|
| 920 |
+
" 1.000 mahindra xuv500 w8 diesel 2179\n",
|
| 921 |
+
" 0.998 mahindra and mahindra xuv500 w8 diesel 2179\n",
|
| 922 |
+
" 0.998 mahindra xuv500 w7 diesel 2179\n",
|
| 923 |
+
" 0.998 mahindra xuv500 w8 at diesel 2179\n",
|
| 924 |
+
" 0.998 mahindra xuv500 w9 diesel 2179\n",
|
| 925 |
+
"\n",
|
| 926 |
+
"query: hyundai swift \n",
|
| 927 |
+
" 0.994 hyundai kona premium\n",
|
| 928 |
+
" 0.993 maruti suzuki swift 1.3 diesel 1248\n",
|
| 929 |
+
" 0.993 maruti swift sp petrol 1197\n",
|
| 930 |
+
" 0.993 maruti swift range extender diesel 1197\n",
|
| 931 |
+
" 0.993 maruti swift lxi petrol 1197\n"
|
| 932 |
+
]
|
| 933 |
+
}
|
| 934 |
+
],
|
| 935 |
+
"source": [
|
| 936 |
+
"corpus_embeddings = model.encode(\n",
|
| 937 |
+
" corpus,\n",
|
| 938 |
+
" batch_size=256,\n",
|
| 939 |
+
" convert_to_tensor=True,\n",
|
| 940 |
+
" normalize_embeddings=True,\n",
|
| 941 |
+
" show_progress_bar=True,\n",
|
| 942 |
+
")\n",
|
| 943 |
+
"\n",
|
| 944 |
+
"\n",
|
| 945 |
+
"def nearest(query, k=5):\n",
|
| 946 |
+
" q = model.encode([query], convert_to_tensor=True, normalize_embeddings=True)\n",
|
| 947 |
+
" hits = util.semantic_search(q, corpus_embeddings, top_k=k)[0]\n",
|
| 948 |
+
" print(f\"\\nquery: {query}\")\n",
|
| 949 |
+
" for h in hits:\n",
|
| 950 |
+
" print(f\" {h['score']:.3f} {corpus[h['corpus_id']]}\")\n",
|
| 951 |
+
"\n",
|
| 952 |
+
"\n",
|
| 953 |
+
"for q in [\n",
|
| 954 |
+
" \"maruti swift vxi petrol 1197\",\n",
|
| 955 |
+
" \"hyundai i20 asta diesel 1396\",\n",
|
| 956 |
+
" \"mahindra xuv500 w8 diesel 2179\",\n",
|
| 957 |
+
" \"mahindra and mahindra land cruiser 4500\",\n",
|
| 958 |
+
" \n",
|
| 959 |
+
"]:\n",
|
| 960 |
+
" nearest(q)"
|
| 961 |
+
]
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"cell_type": "code",
|
| 965 |
+
"execution_count": 32,
|
| 966 |
+
"id": "push",
|
| 967 |
+
"metadata": {},
|
| 968 |
+
"outputs": [
|
| 969 |
+
{
|
| 970 |
+
"name": "stderr",
|
| 971 |
+
"output_type": "stream",
|
| 972 |
+
"text": [
|
| 973 |
+
"Writing model shards: 100%|ββββββββββ| 1/1 [00:00<00:00, 2.49it/s]\n"
|
| 974 |
+
]
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"data": {
|
| 978 |
+
"text/plain": [
|
| 979 |
+
"'https://huggingface.co/SwarajSolanke-turtle/bert-base-uncased-tsdae-fw/commit/6b9f55f41f80391366307318786e577072b80866'"
|
| 980 |
+
]
|
| 981 |
+
},
|
| 982 |
+
"execution_count": 32,
|
| 983 |
+
"metadata": {},
|
| 984 |
+
"output_type": "execute_result"
|
| 985 |
+
}
|
| 986 |
+
],
|
| 987 |
+
"source": [
|
| 988 |
+
"# Optional: push to the Hugging Face Hub (run `hf auth login` first).\n",
|
| 989 |
+
"repo_id = f\"{MODEL_NAME.split('/')[-1]}-tsdae-fw\"\n",
|
| 990 |
+
"model.push_to_hub(repo_id)"
|
| 991 |
+
]
|
| 992 |
+
}
|
| 993 |
+
],
|
| 994 |
+
"metadata": {
|
| 995 |
+
"kernelspec": {
|
| 996 |
+
"display_name": "Motor_Mapping (3.12.0)",
|
| 997 |
+
"language": "python",
|
| 998 |
+
"name": "python3"
|
| 999 |
+
},
|
| 1000 |
+
"language_info": {
|
| 1001 |
+
"codemirror_mode": {
|
| 1002 |
+
"name": "ipython",
|
| 1003 |
+
"version": 3
|
| 1004 |
+
},
|
| 1005 |
+
"file_extension": ".py",
|
| 1006 |
+
"mimetype": "text/x-python",
|
| 1007 |
+
"name": "python",
|
| 1008 |
+
"nbconvert_exporter": "python",
|
| 1009 |
+
"pygments_lexer": "ipython3",
|
| 1010 |
+
"version": "3.12.0"
|
| 1011 |
+
}
|
| 1012 |
+
},
|
| 1013 |
+
"nbformat": 4,
|
| 1014 |
+
"nbformat_minor": 5
|
| 1015 |
+
}
|