syssec-utd/pylingual-shared-segmentation-v2

Universal (all-version) PyLingual segmentation backbone for the shared-backbone + per-version LoRA study, trained on Python 3.6-3.15. last-checkpoint/ holds the latest resumable Trainer checkpoint while training runs; the repo root holds the final model.

• Data: syssec-utd/pylingual-shared-encoded-v2 universal/segmentation at revision 87be6f40c315dc8d136d0df6690470edb021becd (100000 source files, 3120145 encoded rows, tokenizer.json sha256 61c4f9cd711448c6f71db41e93b6cbbe9fc3d0c994f3d427b0faecfd02e954df)
• Initialization: /home/henryh/pylingual-runs-v2/universal/mlm/checkpoint
• 2 epochs, global batch 28 (28 x 1 accumulation x 1 GPU), learning rate 2e-05, weight decay 0.01, FP16, seed 20261020
• Code: https://github.com/quinntyx/pylingual branch feat-shared-backbone-lora, commit 89981ff203058329636eebd66edaa45ee24f9629

run/provenance.json records every training argument and the full data manifest.