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
32 lines
No EOL
625 B
JSON
32 lines
No EOL
625 B
JSON
{
|
|
"experiment": "llm_moe_hard_seeds_smol",
|
|
"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": 126,
|
|
"results_sha256": "38eb9f8ca0b52d9d2c17a385f33612a0d14fb622066e524eb5aff8d85d1fe0f1",
|
|
"layer": "2",
|
|
"tier": "llm",
|
|
"base_model": "HuggingFaceTB/SmolLM2-1.7B-Instruct",
|
|
"hard": true,
|
|
"seeds": [
|
|
1,
|
|
2,
|
|
3
|
|
],
|
|
"operators": [
|
|
"soup",
|
|
"ties",
|
|
"moe_oracle",
|
|
"moe_learned"
|
|
]
|
|
} |