research: publish AttnRes forward training study

This commit is contained in:
wuyang
2026-07-30 18:41:18 +08:00
parent 7ea91caabb
commit f177fa676d
47 changed files with 192164 additions and 192 deletions
+9 -4
View File
@@ -92,10 +92,14 @@ def smoke_compare(args: argparse.Namespace) -> None:
"gradient_gate",
"environment",
)
checks = {
field: parent_result[field] == wrapper_result[field]
for field in fields
}
checks = {}
for field in fields:
parent_value = exact_structure(parent_result[field])
wrapper_value = exact_structure(wrapper_result[field])
if field == "manifest":
parent_value.pop("path", None)
wrapper_value.pop("path", None)
checks[field] = parent_value == wrapper_value
wrapper_identity = {
"protocol": wrapper_result["protocol_id"] == runner.PROTOCOL_ID,
"parent_protocol": (
@@ -185,6 +189,7 @@ def step_zero(args: argparse.Namespace) -> None:
"initial_mixer_hash": initial_mixer,
"logits_sha256": tensor_sha256(logits),
"loss_nats": loss.detach().cpu().item(),
"loss_tensor_sha256": tensor_sha256(loss),
"evaluation": exact_structure(evaluation),
"diagnostic": exact_structure(diagnostic),
}