You can deploy this model and start earning money today!

mia-project-2025/
bert-base-uncased-finetuned-glue-mnli

Name: bert-base-uncased-finetuned-glue-mnli
Availability: InStock

safetensors

apache-2.0

Views

No views yet

Fine-Tuned BERT on MNLI (MultiNLI)

This repository contains a BERT-base model fine-tuned on the GLUE MultiNLI dataset.
The task is natural language inference (NLI): given a premise and a hypothesis, predict the relationship between them as one of:

entailment
contradiction
neutral

Model Details

Base Model: bert-base-uncased
Fine-tuning Method: Full fine-tuning
Task: Sequence Classification (3 classes)
Frameworks: Hugging Face Transformers, PyTorch

Training Configuration

Epochs: 4
Batch Size: 64 (train) / 64 (eval)
Learning Rate: 3e-5 (AdamW fused optimizer)
Scheduler: Linear Warmup (10%)
Other Techniques:
- Gradient checkpointing
- Gradient accumulation (steps = 2)
- Mixed precision (FP16 when GPU available)

Dataset

Name: GLUE MNLI
Train Split: ~392k examples
Evaluation Splits:
- Matched (in-domain): premise/hypothesis from the same domain
- Mismatched (cross-domain): premise/hypothesis from different domains

Results

Final Evaluation (Epoch 4)

Metric	Matched (in-domain)	Mismatched (out-of-domain)
Eval Loss	0.5139	0.4987
Accuracy	84.46%	84.46%
Precision	0.8473	0.8467
Recall	0.8446	0.8446
F1 Score	0.8453	0.8453
Train Loss	0.7036	0.7036
Train Runtime	2936.98s	2936.98s
Eval Runtime	4.7s	4.8s

Usage

python

from transformers import AutoTokenizer, AutoModelForSequenceClassification

model_name = "mia-project-2025/bert-base-uncased-finetuned-glue-mnli"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

# Example input
premise = "A soccer game with multiple males playing."
hypothesis = "Some men are playing a sport."
inputs = tokenizer(premise, hypothesis, return_tensors="pt", padding=True, truncation=True)

# Prediction
outputs = model(**inputs)
pred = outputs.logits.argmax(-1).item()
labels = ["entailment", "neutral", "contradiction"]
print("Prediction:", labels[pred])