Jakub
67061cf373
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.
13 lines
927 B
JSON
13 lines
927 B
JSON
{
|
|
"source_archive": "aya_300k_benchmarky_20261024_215708.tar.gz",
|
|
"sha256": "b45e431cbc63bc73ef953f8aa3837695ccec43783e3da2dfccb0d99f7d1fe79c",
|
|
"compressed_bytes": 349555561,
|
|
"scope": "Hruska Aya 300k learning-rate selection and evaluation of selected LR 0.00010; Titan excluded",
|
|
"base_model": "slovak-nlp/mistral-sk-7b",
|
|
"base_model_revision": "089497ae0d72018e9591895c54f774bf0b4a83a4",
|
|
"selection_criterion": "lowest final validation loss among the six completed 300k runs",
|
|
"intended_next_stage": "planned training on the full Aya dataset on Perun; not executed in this experiment",
|
|
"data_reproducibility_limit": "No source dataset revision, data-file checksum, or held-out sample IDs were included in this archive",
|
|
"curation": "Model weights, checkpoints, trainer_state.json, duplicated inference caches and full parquet details excluded from the Git subset. Original archive retained separately."
|
|
}
|