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
75 lines
No EOL
1.3 KiB
JSON
75 lines
No EOL
1.3 KiB
JSON
{
|
|
"experiment": "llm_curriculum_v5_late",
|
|
"master_seed": 1,
|
|
"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": 439,
|
|
"results_sha256": "85cbf1f211b7336d5eea2048a9385f1f97e8e2c92804ab52441544b33796ad78",
|
|
"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",
|
|
"society"
|
|
],
|
|
"baselines": [],
|
|
"n_new": 300,
|
|
"n_replay": 150,
|
|
"operator": "linear",
|
|
"ancestor_depth": null,
|
|
"lora": {
|
|
"r": 16,
|
|
"alpha": 32
|
|
},
|
|
"allow_veto": true,
|
|
"merge_until": null,
|
|
"orders": [
|
|
[
|
|
"mnli",
|
|
"arc",
|
|
"hellaswag",
|
|
"squad",
|
|
"boolq",
|
|
"winogrande"
|
|
],
|
|
[
|
|
"arc",
|
|
"hellaswag",
|
|
"squad",
|
|
"mnli",
|
|
"winogrande",
|
|
"boolq"
|
|
],
|
|
[
|
|
"hellaswag",
|
|
"squad",
|
|
"mnli",
|
|
"arc",
|
|
"boolq",
|
|
"winogrande"
|
|
]
|
|
],
|
|
"cull": null
|
|
}
|
|
} |