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
..
audit_summary.json	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
family_prompt_summary.csv	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
family_summary.csv	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
input_length_budget_boundary_rows.csv	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
input_length_diagnostics_per_task.csv	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
input_length_diagnostics_summary.json	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
log_truncation_evidence.json	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
per_task_metrics.csv	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
results_2026-10-22T21-55-04.268099.json	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
three_prompt_summary.csv	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00
truncation_audit_per_task.csv	Add Aya 300k learning-rate study and benchmark results	2026-10-25 00:33:24 +02:00