kravmar/llm-course-hw3-lora

Model Card for Model ID

Model Details

Model Description

OuteAI/Lite-Oute-1-300M-Instruct finetuned with LoRA on cardiffnlp/tweet_eval dataset for sentiment analysis task. The model predicts class label: negative, neutral or positive.

Training Details

Training Data

cardiffnlp/tweet_eval

Prompt

System prompt:

"You are a sentiment analysis model. Your task is to classify the sentiment of the given text into one of the following categories:

positive: Indicates a favorable or optimistic sentiment. negative: Indicates an unfavorable or pessimistic sentiment. neutral: Indicates a neutral or indifferent sentiment, without any strong emotional tone.

Return ONLY the name of the sentiment class: positive, negative, or neutral. Do NOT output anything else."

Training Hyperparameters

Batch size: 8

Learning rate: 5e-4

Num epochs: 1

0.14% trained parameters

Generation example

User prompt: "Ben Smith / Smith (concussion) remains out of the lineup Thursday, Curtis #NHL #SJ"

True answer: neutral

Model output: neut