RoBERTa-base fine-tuned on GLUE RTE (bitfit)

This checkpoint is one learning experiment comparing Full Fine-Tuning, BitFit, adapters, and LoRA on GLUE Recognizing Textual Entailment (RTE). It uses seed 42 and selects the highest validation epoch.

Metric	Value
Best validation accuracy	0.7292
Best epoch	6
Trainable parameters	694,274
Total parameters	124,647,170

Method

bitfit. See the project README for the exact shared training configuration. This is an educational experiment, not a benchmark-level performance claim.

Load

from transformers import pipeline
classifier = pipeline("text-classification", model="Anirudh7003/roberta-base-rte-bitfit")

Downloads last month: 7

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for Anirudh7003/roberta-base-rte-bitfit

Base model

FacebookAI/roberta-base

Finetuned

(2400)

this model