Downloads · 30 days
0
DRU-RE-class-weighted-loss-run
hadikhamoud/DRU-RE-class-weighted-loss-run
DRU-RE-class-weighted-loss-run is a machine learning model from hadikhamoud. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Full artifacts for the DRU-RE class-weighted-loss run.
Access
Public
Updated Jul 9, 2026
Repo size
7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt4 GB · 44%
At a glance
- Access
- Public
- Created
- Jul 9, 2026
- Updated
- Jul 9, 2026
- SHA
- 134e0fa7
Model card
From the Hugging Face model README
DRU-RE Class-Weighted Loss Run
Full artifacts for the DRU-RE class-weighted-loss run.
Run type
Class-weighted loss.
- Weighted sampler:
False - Class-weighted loss:
True - Base model:
U4RASD/NeoAraBERT - Max length:
512
Important files
model/pytorch_model.binmodel/tokenizer/config filesconfigs/artifacts/final_eval_metrics_after_best_reload.jsonartifacts/predictions.txtartifacts/submission.zip
Best checkpoint
outputs/DRU-RE-class-weighted-loss/checkpoints/checkpoint-2000
Best metric
0.30192284616872145
- Created
- Jul 9, 2026
- Updated
- Jul 9, 2026