Japanese Sentiment Analysis

🚀 Japanese Sentiment Analysis

A model trained from scratch on the chABSA dataset for Japanese sentence sentiment analysis.

🚀 Quick Start

This model was trained from scratch on the chABSA dataset. It achieves the following results on the evaluation set:

• Loss: 0.0001
• Accuracy: 1.0
• F1: 1.0

✨ Features

Model description

The model is trained for Japanese sentence sentiments.

Intended uses & limitations

The model was trained on the chABSA Japanese dataset. DATASET link: https://www.kaggle.com/datasets/takahirokubo0/chabsa

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

💻 Usage Examples

Basic Usage

You can use cURL to access this model. Here is an example using the Python API:

from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("jarvisx17/japanese-sentiment-analysis")

model = AutoModelForSequenceClassification.from_pretrained("jarvisx17/japanese-sentiment-analysis")

inputs = tokenizer("I love AutoNLP", return_tensors="pt")

outputs = model(**inputs)

📚 Documentation

Training results

[No specific content provided in the original, so this section remains as a placeholder for potential future addition]

Framework versions

• Transformers 4.24.0
• Pytorch 1.12.1+cu113
• Datasets 2.7.0
• Tokenizers 0.13.2

Dependencies

• !pip install fugashi
• !pip install unidic_lite