metadata
language: en
license: apache-2.0
base_model: roberta-base
tags:
- text-classification
- sentiment
datasets:
- surrey-nlp/BESSTIE-CW-26
metrics:
- f1
- accuracy
roberta-base-sentiment
Fine-tuned roberta-base on the
BESSTIE-CW-26
dataset for binary sentiment classification.
Training
- Base model:
roberta-base - Task:
sentiment(binary) - Epochs: 2
- Batch size: 4
- Learning rate: 2e-5
- Weight decay: 0.01
- Max sequence length: 64
- Seed: 65 (best of {42, 65, 131})
- Optimizer: AdamW (Trainer default)
Test results
- macro-F1: 0.8932
Usage
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("vyshnav112233/roberta-base-sentiment")
tokenizer = AutoTokenizer.from_pretrained("vyshnav112233/roberta-base-sentiment")
inputs = tokenizer("your sentence here", return_tensors="pt", truncation=True, max_length=64)
logits = model(**inputs).logits