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
779 B
JSON
38 lines
No EOL
779 B
JSON
{
|
|
"experiment": "llm_compose_gate",
|
|
"master_seed": 1,
|
|
"git_commit": "e4804adabcdce6d928c5e6b1e85429b2a6acf2fe",
|
|
"python": "3.14.7",
|
|
"libraries": {
|
|
"numpy": "2.5.0",
|
|
"scipy": "1.18.0",
|
|
"pandas": "3.0.3",
|
|
"pyarrow": "24.0.0",
|
|
"torch": "2.12.1",
|
|
"transformers": "5.16.1",
|
|
"peft": "0.20.0"
|
|
},
|
|
"rows": 14,
|
|
"results_sha256": "cc1c6f5ac13eda7c26eecb563b3fcd22b034027dfec432e80cb071a71bf2a7c6",
|
|
"layer": "2",
|
|
"tier": "llm",
|
|
"base_model": "Qwen/Qwen2.5-1.5B",
|
|
"hard": false,
|
|
"compose": {
|
|
"arms": [
|
|
"dry"
|
|
],
|
|
"generations": 0,
|
|
"g": 0.1,
|
|
"k_inherit": 300,
|
|
"conf_gate": 0.85,
|
|
"epochs": 3,
|
|
"n_hard": 120,
|
|
"n_gsm8k": 100,
|
|
"n_mbpp": 80,
|
|
"lora": {
|
|
"r": 16,
|
|
"alpha": 32
|
|
}
|
|
}
|
|
} |