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
..
analyze_aya_300k_lr_all.py	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
analyze_aya_300k_lr.py	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
analyze_training_results.py	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
rerun_skbench_lr_0p00010.sh	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
run_aya_300k_lr_validation_lower.sh	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
run_aya_300k_lr_validation.sh	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
run_lmeval_aya_300k_lr_0p00010.sh	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
setup_aya_300k_lr_validation.sh	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
unpack_results_archive.py	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00