Views
No views yet
jiosephlee/Intern-S1-mini-lm for binary assay-transfer
prediction (transfer vs. nontransfer) over paired assay records.eval/validation/overall/binary_macro_f1.| Metric | Value |
|---|---|
| binary_macro_f1 | 0.7207 |
| binary_accuracy | 0.7225 |
| soft_mae | 0.2619 |
| transfer_precision | 0.7646 |
| Concept | macro_f1 | accuracy | soft_mae |
|---|---|---|---|
| oral_exposure | 0.7895 | 0.7900 | 0.2213 |
| Fg | 0.7814 | 0.7825 | 0.2092 |
| Fa | 0.7020 | 0.7050 | 0.2566 |
| oral_bioavailability | 0.6657 | 0.6675 | 0.2962 |
| Fh | 0.6640 | 0.6675 | 0.3262 |
oral_exposure and Fg carry the
average, while Fh and oral_bioavailability sit near 0.66.binary_macro_f1 — 0.516 (step 0), 0.442, 0.605, 0.616,
0.660, 0.701, 0.707, 0.707, 0.721 (step 400), 0.714 (step 450). The metric
was plateauing but had not clearly converged when training was stopped.jiosephlee/Intern-S1-mini-lm @ fcb667c380ae01f57693a45b4b5c2d331052a107assay_transfer_raw_pair_v6_intern, prompt/completion format, packedtransfer, nontransfer),
format CE weight 0.1intern-s1-mini_assay-transfer-raw-pair-v6-soft-a100 (2026-07-19).
Full selection metrics are in metric.json.enable_thinking=False). Answers are the option markers (A) / (B).
Match this at inference time or accuracy will not reproduce.