mirror of
https://github.com/hanzoai/papers.git
synced 2026-10-29 07:34:31 +00:00
62 lines
912 B
JSON
62 lines
912 B
JSON
{
|
|
"stage": "h2",
|
|
"init": {
|
|
"dir": "../runs/h2",
|
|
"stage": "a"
|
|
},
|
|
"sources": [
|
|
"rag_relevance"
|
|
],
|
|
"manifest": null,
|
|
"licenses": [
|
|
"GREEN",
|
|
"YELLOW",
|
|
"RED"
|
|
],
|
|
"lang": null,
|
|
"takes": [
|
|
{
|
|
"suite": "rag_relevance",
|
|
"rows": 24000,
|
|
"times": 1,
|
|
"balance_class": false,
|
|
"balance_lang": false
|
|
}
|
|
],
|
|
"share": 1.0,
|
|
"frozen": [
|
|
"encoder.embeddings.tok_embeddings."
|
|
],
|
|
"evidence": null,
|
|
"shared": false,
|
|
"mixed": 0.05,
|
|
"epochs": 1,
|
|
"lr_encoder": 3e-05,
|
|
"lr_head": 0.0001,
|
|
"weight_decay": 0.01,
|
|
"warmup": 0.03,
|
|
"cool": 0.2,
|
|
"decay": 1.0,
|
|
"budget": {
|
|
"ctx": 4096,
|
|
"options": 4096,
|
|
"head": 8192,
|
|
"keys": 16384,
|
|
"rows": 128,
|
|
"evidence": 16384
|
|
},
|
|
"retrieval": {
|
|
"wide": 0.2,
|
|
"whole": 0.2
|
|
},
|
|
"top_k": 32,
|
|
"max_len": 1024,
|
|
"clip": 1.0,
|
|
"seed": 1,
|
|
"eval_every": 100,
|
|
"eval_rows": 400,
|
|
"max_steps": 300,
|
|
"outer": 1.0,
|
|
"momentum": 0.0,
|
|
"round": 30.0
|
|
} |