Jakub 67061cf373 Add Aya 300k learning-rate study and benchmark results ... Document six completed LR runs as preparation for full Aya training on Perun. Record selection of LR 0.00010 by lowest final validation loss, selected-model lm-eval and partial SK-bench results, reproducible provenance, and dataset-access/context-truncation limitations. Preserve existing 30k and Titan material.		2026-10-25 00:33:24 +02:00
..
custom_tasks	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
comparability_audit.json	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
lm_eval_commit.txt	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
package_versions.json	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
run_settings.txt	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
SHA256SUMS.txt	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
tasks.txt	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00