med2425/bge-resume-fit

Resume Job Fit Classifier

A cross-encoder model for predicting whether a resume is a fit for a job description.

Model Description

Fine-tuned BAAI/bge-m3 as a cross-encoder classifier on resume and job description pairs.

The model takes a resume and a job description as input and predicts one of three classes: Good Fit, No Fit, or Potential Fit.

Dataset

Trained on cnamuangtoun/resume-job-description-fit.

• Train: 5,059 pairs (90% of original train split, stratified)
• Eval: 625 pairs (10% of original train split, stratified)
• Test: 1,759 pairs (original test split)

Label distribution: No Fit = 50%, Good Fit = 25%, Potential Fit = 25%

Training Details

• Base model: BAAI/bge-m3 (570M params, supports up to 8192 tokens)
• Max sequence length: 8192 tokens (resume: 4096, JD: 4000)
• Optimizer: AdamW with layer-wise learning rates — bottom layers get LR/10, top layers get full LR, classifier head gets full LR
• Learning rate: 8e-6 with cosine scheduler and 15% warmup
• Batch size: 1 per device, gradient accumulation steps: 32 (effective batch: 32)
• Epochs: 40 max, early stopping with patience 6 (best checkpoint at step 3200, epoch ~21)
• Loss: weighted CrossEntropyLoss to handle class imbalance
• WeightedRandomSampler to oversample minority classes during training
• Label smoothing: 0.1
• Dropout: 0.3 classifier, 0.15 hidden layers
• Hardware: NVIDIA RTX 4090 (24GB VRAM)
• Training time: ~3 hours

Results

Metric	Eval	Test
Accuracy	78.08%	54.58%
Macro F1	76.54%	51.91%
F1 Good Fit	76.31%	44.32%
F1 No Fit	82.35%	66.05%
F1 Potential Fit	70.95%	45.35%

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
import numpy as np

model = AutoModelForSequenceClassification.from_pretrained("med2425/bge-resume-fit")
tokenizer = AutoTokenizer.from_pretrained("med2425/bge-resume-fit")

model.eval()
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

resume = """
John Smith
Senior ML Engineer with 6 years experience.
Skills: Python, PyTorch, TensorFlow, NLP, AWS, Docker.
Built NLP pipelines processing 10M documents/day at TechCorp (2020-Present).
Fine-tuned BERT models achieving 94% accuracy on document classification.
B.Sc. Computer Science, State University 2018.
"""

jd = """
Senior Machine Learning Engineer
Requirements: 5+ years ML experience, strong Python,
PyTorch or TensorFlow, NLP experience, production deployment on AWS/GCP/Azure,
Bachelor in Computer Science or related field.
"""

inputs = tokenizer(resume, jd, return_tensors="pt", truncation=True, max_length=8192).to(device)

with torch.no_grad():
    probs = torch.softmax(model(**inputs).logits, dim=-1).squeeze().tolist()

id2label = {0: "Good Fit", 1: "No Fit", 2: "Potential Fit"}
for i, p in enumerate(probs):
    print(f"{id2label[i]}: {p:.2%}")
print(f"Prediction: {id2label[np.argmax(probs)]}")

Note: Use full-length realistic resumes and job descriptions for best results. The model was trained on resumes averaging 700 words and JDs averaging 400 words. Very short inputs may produce unreliable predictions.