martian786/agnews-roberta-seed42-fulltext-25pct

AG News RoBERTa Full-Text Seed 42 25pct

This model is a fine-tuned roberta-base sequence classifier for the AG News four-class classification task.

Model details

• —Base model: roberta-base
• —Dataset: AG News
• —Task: four-class news classification
• —Language: English
• —Random seed: 42
• —Training representation: full text
• —Training fraction: 0.25
• —Training examples: 28500
• —Validation examples: 6,000
• —Test examples: 7600
• —Maximum sequence length: 128 RoBERTa tokens

Labels

Evaluation on AG News test set

Per-class F1

Training setup

• —Learning rate: 2e-5
• —Epochs: 3
• —Train batch size: 16
• —Eval batch size: 32
• —Weight decay: 0.01
• —Warmup ratio: 0.1
• —Validation split: 5% stratified split from the original AG News training set
• —Training pool after validation holdout: 114,000 examples

Loading example

repo_id = "martian786/agnews-roberta-seed42-fulltext-25pct"

Use AutoTokenizer.from_pretrained(repo_id) and AutoModelForSequenceClassification.from_pretrained(repo_id).

Limitations

This model was fine-tuned on AG News and is intended for controlled academic comparison rather than production deployment.