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
49 lines
No EOL
934 B
JSON
49 lines
No EOL
934 B
JSON
{
|
|
"experiment": "llm_curriculum_v5",
|
|
"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": 235,
|
|
"results_sha256": "291a074fe83cc1c282346197177afa78a69d48d8e4dbfcff29f165b4e1720744",
|
|
"layer": "2",
|
|
"tier": "llm",
|
|
"base_model": "Qwen/Qwen2.5-1.5B",
|
|
"hard": false,
|
|
"curriculum": {
|
|
"families": [
|
|
"mnli",
|
|
"arc",
|
|
"hellaswag",
|
|
"squad",
|
|
"boolq",
|
|
"winogrande"
|
|
],
|
|
"lineages": 3,
|
|
"generations": 6,
|
|
"arms": [
|
|
"isolated"
|
|
],
|
|
"baselines": [
|
|
"sequential",
|
|
"single_shot_merge",
|
|
"joint"
|
|
],
|
|
"n_new": 300,
|
|
"n_replay": 150,
|
|
"operator": "linear",
|
|
"ancestor_depth": 3,
|
|
"lora": {
|
|
"r": 16,
|
|
"alpha": 32
|
|
}
|
|
}
|
|
} |