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. |
||
|---|---|---|
| .. | ||
| adapter_config.json | ||
| all_results.json | ||
| eval_results.json | ||
| train_results.json | ||
| TRAINING_COMPLETE | ||
| training_eval_loss.png | ||
| training_loss.png | ||