Deepanika
/

editlens-roberta-large-repro

ai-text-detection

Model card Files Files and versions

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

EditLens RoBERTa-large reproduction

Reproduction of the RoBERTa-large EditLens training config from https://github.com/pangramlabs/EditLens (commit 05a588f).

Training

Data: pangram/editlens_iclr, score_col=cosine_score, 4 buckets, thresholds [0.03, 0.15]
lr=3e-5, batch=24, 1 epoch, constant schedule, bf16, full fine-tune
Single A6000, 22 min wall-clock
Deviations from repo defaults: num_proc 32→8; TrainingArguments compat-patched to drop warmup_ratio (unsupported on transformers 5.17.0; value was 0.0, the framework default, so no behavioral change)

Downloads last month: 8

Safetensors

Model size

0.4B params

Tensor type

F32

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Deepanika/editlens-roberta-large-repro

Base model

FacebookAI/roberta-large

Finetuned

(437)

this model