TEST Open-source AI Model - Fine-tuned Based on BERT, with Nearly 94% Training Accuracy to Support Diverse Applications

TEST

Developed by joe5campbell

A model fine-tuned based on bert-base-uncased, with a training accuracy of 93.75% and validation accuracy of 50%

Large Language Model

Transformers

Open Source License:Apache-2.0 #BERT fine-tuning #Text classification #Low-resource adaptation

Downloads 14

Release Time : 3/2/2022

Model Overview

This model is a fine-tuned version based on bert-base-uncased, primarily used for text classification tasks.

Model Features

High training accuracy

Achieves 93.75% accuracy on the training set

Based on BERT architecture

Uses bert-base-uncased as the base model for fine-tuning

Model Capabilities

Text classification

Natural language understanding

Use Cases

Text analysis

Sentiment analysis

Can be used to analyze the sentiment tendency of text

Topic classification

Can be used to classify text content

🚀 TEST

This is a fine - tuned model based on [bert - base - uncased](https://huggingface.co/bert - base - uncased), achieving certain results on the evaluation set.

🚀 Quick Start

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

Train Loss: 0.4904
Train Accuracy: 0.9375
Validation Loss: 0.7016
Validation Accuracy: 0.5
Epoch: 1

📚 Documentation

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

optimizer: {'name': 'Adam', 'clipnorm': 1.0, 'learning_rate': 3e - 05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e - 08, 'amsgrad': False}
training_precision: float32