Giorgio Gilestro
84124de143
Clarity pass over the main text (36-item audit), Discussion rewrite and cut, acknowledgements, Souly et al. as ref 62, lettered SI panels, model section moved under Results; plus the untracked curriculum/society/compose/smol configs, runners, figures, stats and tests that the SI already cites. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Y64o8FKP7rCuXzC48pxpMm
38 lines
No EOL
742 B
JSON
38 lines
No EOL
742 B
JSON
{
|
|
"experiment": "llm_compose",
|
|
"master_seed": 3,
|
|
"git_commit": null,
|
|
"python": "3.11.7",
|
|
"libraries": {
|
|
"numpy": "2.4.6",
|
|
"scipy": "1.17.1",
|
|
"pandas": "3.0.3",
|
|
"pyarrow": "24.0.0",
|
|
"torch": "2.12.1",
|
|
"transformers": "5.16.1",
|
|
"peft": "0.20.0"
|
|
},
|
|
"rows": 122,
|
|
"results_sha256": "c9d6d1408cb87b1bf71b3f85a5f58384fe5f3678350d10a32ed5e639cb63d48d",
|
|
"layer": "2",
|
|
"tier": "llm",
|
|
"base_model": "Qwen/Qwen2.5-1.5B",
|
|
"hard": false,
|
|
"compose": {
|
|
"arms": [
|
|
"dry_cat"
|
|
],
|
|
"generations": 6,
|
|
"g": 0.1,
|
|
"k_inherit": 300,
|
|
"conf_gate": 0.85,
|
|
"epochs": 3,
|
|
"n_hard": 150,
|
|
"n_gsm8k": 150,
|
|
"n_mbpp": 100,
|
|
"lora": {
|
|
"r": 16,
|
|
"alpha": 32
|
|
}
|
|
}
|
|
} |