wuyang/llm-atlas
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

research: publish AttnRes forward training study

Browse Source
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
Download Patch File Download Diff File Expand all files Collapse all files
experiments/k3/attnres_forward/results/gates/step-zero.json
+21 -11
View File
@@ -1,5 +1,5 @@
{
"canonical_sha256_without_self": "00db0569d2fd00599383ecdc50578c52df784a937a96dd69576f1366e88b0dcb",
"canonical_sha256_without_self": "9a0716bc496d39b9447b79aba0aec42ca4c953cbabe30e3aa349c1bba0701c5f",
"environment": {
"cublas_workspace_config": ":4096:8",
"cuda": "12.8",
@@ -21,7 +21,8 @@
"initial_mixer_hash": true,
"initial_public_hash": true,
"logits_sha256": true,
"loss_nats": true
"loss_nats": true,
"loss_tensor_sha256": true
},
"passed": true,
"payload": {
@@ -1254,7 +1255,8 @@
"initial_mixer_hash": "c5a06c218c4501b16fcccee115aa8c79d5dceade78b38bbb547e4f5b2202516d",
"initial_public_hash": "73bbe569e1a47981386ebaf59ca891174746bf81897fe5403676ad6d50423c58",
"logits_sha256": "6b44486d93c29a13dc0b961117cc2d22f26c81dc519346ac45b1bb0fefa29939",
"loss_nats": 5.516995429992676
"loss_nats": 5.516995429992676,
"loss_tensor_sha256": "c4e1d45c137a73ad6249c2db3ff5e29c849310d4f71f3182c41d27ff6b9fcb6a"
},
"pre_reduction_uniform_weight_gate": true,
"pre_reduction_uniform_weight_max_abs_error": 0.0,
@@ -1267,7 +1269,8 @@
"initial_mixer_hash": true,
"initial_public_hash": true,
"logits_sha256": true,
"loss_nats": true
"loss_nats": true,
"loss_tensor_sha256": true
},
"passed": true,
"payload": {
@@ -2500,7 +2503,8 @@
"initial_mixer_hash": "c5a06c218c4501b16fcccee115aa8c79d5dceade78b38bbb547e4f5b2202516d",
"initial_public_hash": "73bbe569e1a47981386ebaf59ca891174746bf81897fe5403676ad6d50423c58",
"logits_sha256": "6b44486d93c29a13dc0b961117cc2d22f26c81dc519346ac45b1bb0fefa29939",
"loss_nats": 5.516995429992676
"loss_nats": 5.516995429992676,
"loss_tensor_sha256": "c4e1d45c137a73ad6249c2db3ff5e29c849310d4f71f3182c41d27ff6b9fcb6a"
},
"pre_reduction_uniform_weight_gate": true,
"pre_reduction_uniform_weight_max_abs_error": 0.0,
@@ -2562,7 +2566,8 @@
"initial_mixer_hash": true,
"initial_public_hash": true,
"logits_sha256": true,
"loss_nats": true
"loss_nats": true,
"loss_tensor_sha256": true
},
"passed": true,
"payload": {
@@ -3795,7 +3800,8 @@
"initial_mixer_hash": "c5a06c218c4501b16fcccee115aa8c79d5dceade78b38bbb547e4f5b2202516d",
"initial_public_hash": "73bbe569e1a47981386ebaf59ca891174746bf81897fe5403676ad6d50423c58",
"logits_sha256": "6b44486d93c29a13dc0b961117cc2d22f26c81dc519346ac45b1bb0fefa29939",
"loss_nats": 5.516995429992676
"loss_nats": 5.516995429992676,
"loss_tensor_sha256": "c4e1d45c137a73ad6249c2db3ff5e29c849310d4f71f3182c41d27ff6b9fcb6a"
},
"pre_reduction_uniform_weight_gate": true,
"pre_reduction_uniform_weight_max_abs_error": 0.0,
@@ -3857,7 +3863,8 @@
"initial_mixer_hash": true,
"initial_public_hash": true,
"logits_sha256": true,
"loss_nats": true
"loss_nats": true,
"loss_tensor_sha256": true
},
"passed": true,
"payload": {
@@ -5090,7 +5097,8 @@
"initial_mixer_hash": "c5a06c218c4501b16fcccee115aa8c79d5dceade78b38bbb547e4f5b2202516d",
"initial_public_hash": "73bbe569e1a47981386ebaf59ca891174746bf81897fe5403676ad6d50423c58",
"logits_sha256": "6b44486d93c29a13dc0b961117cc2d22f26c81dc519346ac45b1bb0fefa29939",
"loss_nats": 5.516995429992676
"loss_nats": 5.516995429992676,
"loss_tensor_sha256": "c4e1d45c137a73ad6249c2db3ff5e29c849310d4f71f3182c41d27ff6b9fcb6a"
},
"pre_reduction_uniform_weight_gate": true,
"pre_reduction_uniform_weight_max_abs_error": 0.0,
@@ -5128,7 +5136,8 @@
"initial_mixer_hash": true,
"initial_public_hash": true,
"logits_sha256": true,
"loss_nats": true
"loss_nats": true,
"loss_tensor_sha256": true
},
"passed": true,
"payload": {
@@ -6361,7 +6370,8 @@
"initial_mixer_hash": "c5a06c218c4501b16fcccee115aa8c79d5dceade78b38bbb547e4f5b2202516d",
"initial_public_hash": "73bbe569e1a47981386ebaf59ca891174746bf81897fe5403676ad6d50423c58",
"logits_sha256": "6b44486d93c29a13dc0b961117cc2d22f26c81dc519346ac45b1bb0fefa29939",
"loss_nats": 5.516995429992676
"loss_nats": 5.516995429992676,
"loss_tensor_sha256": "c4e1d45c137a73ad6249c2db3ff5e29c849310d4f71f3182c41d27ff6b9fcb6a"
},
"pre_reduction_uniform_weight_gate": true,
"pre_reduction_uniform_weight_max_abs_error": 0.0,