bert-base-cased-finetuned-mnli Open Source Text Classification Model - Free to Use, Complete Natural Language Inference Tasks

Bert Base Cased Finetuned Mnli

Developed by gchhablani

A text classification model fine-tuned on the GLUE MNLI dataset based on bert-base-cased, designed for natural language inference tasks

Text Classification

Transformers

EnglishOpen Source License:Apache-2.0 #Natural Language Inference #High-precision Text Classification #GLUE Benchmark Optimization

Downloads 84

Release Time : 3/2/2022

Model Overview

This model is a fine-tuned version of bert-base-cased specifically for the MNLI (Multi-Genre Natural Language Inference) task, primarily used to determine the logical relationship between two sentences (entailment/contradiction/neutral)

Model Features

High Accuracy

Achieves 84.1% accuracy on the MNLI validation set

Designed for Comparative Studies

Specifically designed for performance comparison studies with FNet models

Standard BERT Architecture

Based on the widely validated bert-base-cased architecture with reliable performance benchmarks

Model Capabilities

Natural Language Inference

Text Classification

Sentence Relationship Judgment

Use Cases

Academic Research

Model Architecture Comparison

Used to compare the performance of different architectures like BERT and FNet on NLI tasks

Provides benchmark performance data (84.1% accuracy)

Practical Applications

Text Logical Relationship Judgment

Determines the logical relationship between two texts (entailment/contradiction/neutral)

Can be used in question-answering systems, text moderation, and other scenarios

🚀 bert-base-cased-finetuned-mnli

This model is a fine - tuned version of [bert - base - cased](https://huggingface.co/bert - base - cased) on the GLUE MNLI dataset, aiming to compare with [google/fnet - base](https://huggingface.co/google/fnet - base) and achieve good accuracy on text classification tasks.

🚀 Quick Start

This model is a fine - tuned version of [bert - base - cased](https://huggingface.co/bert - base - cased) on the GLUE MNLI dataset. It achieves the following results on the evaluation set:

Loss: 0.5721
Accuracy: 0.8410

The model was fine - tuned to compare [google/fnet - base](https://huggingface.co/google/fnet - base) as introduced in this paper against [bert - base - cased](https://huggingface.co/bert - base - cased).

📚 Documentation

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

📦 Installation

This model is trained using the [run_glue](https://github.com/huggingface/transformers/blob/master/examples/pytorch/text - classification/run_glue.py) script. The following command was used:

#!/usr/bin/bash

python ../run_glue.py \\n  --model_name_or_path bert-base-cased \\n  --task_name mnli \\n  --do_train \\n  --do_eval \\n  --max_seq_length 512 \\n  --per_device_train_batch_size 16 \\n  --learning_rate 2e-5 \\n  --num_train_epochs 3 \\n  --output_dir bert-base-cased-finetuned-mnli \\n  --push_to_hub \\n  --hub_strategy all_checkpoints \\n  --logging_strategy epoch \\n  --save_strategy epoch \\n  --evaluation_strategy epoch \\n

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e - 05
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
lr_scheduler_type: linear
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5323	1.0	24544	0.4431	0.8302
0.3447	2.0	49088	0.4725	0.8353
0.2267	3.0	73632	0.5887	0.8368

Framework versions

Transformers 4.11.0.dev0
Pytorch 1.9.0
Datasets 1.12.1
Tokenizers 0.10.3

📄 License

This model is licensed under the Apache - 2.0 license.

📊 Model Index

Property	Details
Model Name	bert - base - cased - finetuned - mnli
Task	Text Classification
Dataset	GLUE MNLI
Metric	Accuracy
Value	0.8410292921074044

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご