metadata

license: mit
base_model: cardiffnlp/twitter-roberta-base-sentiment-latest
language:
  - en
library_name: transformers
tags:
  - Roberta
  - Sentiment Analysis
widget:
  - text: This product is great!

🌟 Fine-tuned RoBERTa for Sentiment Analysis on Reviews 🌟

This is a fine-tuned version of cardiffnlp/twitter-roberta-base-sentiment-latest on the Amazon Reviews dataset for sentiment analysis.

📜 Model Details

🆕 Model Name: AnkitAI/reviews-roberta-base-sentiment-analysis
🔗 Base Model: cardiffnlp/twitter-roberta-base-sentiment-latest
📊 Dataset: Amazon Reviews
⚙️ Fine-tuning: This model was fine-tuned for sentiment analysis with a classification head for binary sentiment classification (positive and negative).

🏋️ Training

The model was trained using the following parameters:

🔧 Learning Rate: 2e-5
📦 Batch Size: 16
⏳ Epochs: 3
⚖️ Weight Decay: 0.01
📅 Evaluation Strategy: Epoch

🏋️ Training Details

📉 Eval Loss: 0.1049
⏱️ Eval Runtime: 3177.538 seconds
📈 Eval Samples/Second: 226.591
🌀 Eval Steps/Second: 7.081
🔄 Epoch: 3.0
🏃 Train Runtime: 110070.6349 seconds
📊 Train Samples/Second: 78.495
🌀 Train Steps/Second: 2.453
📉 Train Loss: 0.0858

🚀 Usage

You can use this model directly with the Hugging Face transformers library:

from transformers import RobertaForSequenceClassification, RobertaTokenizer

model_name = "AnkitAI/reviews-roberta-base-sentiment-analysis"
model = RobertaForSequenceClassification.from_pretrained(model_name)
tokenizer = RobertaTokenizer.from_pretrained(model_name)

# Example usage
inputs = tokenizer("This product is great!", return_tensors="pt")
outputs = model(**inputs) # 1 for positive, 0 for negative

# Get sentiment
logits = outputs.logits
print(logits)

Note: LABEL_1 indicates positive sentiment and LABEL_0 indicates negative sentiment.

📜 License

This model is licensed under the MIT License.