Index libero-all-suites/init_variants/ffn_magnitude

README.md

@@ -9,7 +9,7 @@ tags:
 
 # LoopWAM final checkpoints
 
-Final trained policy weights from the LoopWAM experiments. This repository contains **24 checkpoints**, separated by training data scope. Both original and repeated 4/4 runs are retained. All production checkpoints are from completed ten-epoch runs with global batch 128 and training seed 42.
+Final trained policy weights from the LoopWAM experiments. This repository contains **25 checkpoints**, separated by training data scope. Both original and repeated 4/4 runs are retained. All production checkpoints are from completed ten-epoch runs with global batch 128 and training seed 42.
 
 ## October 9 additions: all-loop KV
 
@@ -81,8 +81,9 @@ Dense-S12 / Dense-S30 trained on all four suites with the same data, normalizati
 | [libero-all-suites/init_variants/core16_21](libero-all-suites/init_variants/core16_21) | v0 init `core16_21` | 4/4 | 584,536,135 | Training only; evaluation not run |
 | [libero-all-suites/init_variants/no_video_pretraining](libero-all-suites/init_variants/no_video_pretraining) | v0 init `no_video_pretraining` (no Wan video pretraining) | 4/4 | 584,536,135 | Training only; evaluation not run |
 | [libero-all-suites/init_variants/core_random](libero-all-suites/init_variants/core_random) | v0 init `core_random` | 4/4 | 584,536,135 | 82.20% (4,932/6,000; 4 suites x seeds 42/43/44) |
+| [libero-all-suites/init_variants/ffn_magnitude](libero-all-suites/init_variants/ffn_magnitude) | v0 init `ffn_magnitude` | 4/4 | 584,536,135 | 92.12% (5,527/6,000; 4 suites x seeds 42/43/44) |
 
-v0 (video 4 / action 4) retrained on all four suites with the same data, normalization, schedule and precision as `libero-all-suites/v0-video4-action4` (21,700 updates, global batch 128, seed 42) on two B200 GPUs; only the student initialization differs (see each directory's README and `init_variant_manifest.json`). Not evaluated. `init_variants/no_video_pretraining` starts without any Wan video pretraining and was trained on two H100s (2 GPUs x microbatch 8 x accumulation 8). `init_variants/core_random` was trained on two H100s (2 GPUs x microbatch 8 x accumulation 8) and scored 82.20% on the matched 6,000-episode four-suite evaluation.
+v0 (video 4 / action 4) retrained on all four suites with the same data, normalization, schedule and precision as `libero-all-suites/v0-video4-action4` (21,700 updates, global batch 128, seed 42) on two B200 GPUs; only the student initialization differs (see each directory's README and `init_variant_manifest.json`). Not evaluated. `init_variants/no_video_pretraining` starts without any Wan video pretraining and was trained on two H100s (2 GPUs x microbatch 8 x accumulation 8). `init_variants/core_random` was trained on two H100s (2 GPUs x microbatch 8 x accumulation 8) and scored 82.20% on the matched 6,000-episode four-suite evaluation. `init_variants/ffn_magnitude` was trained on two H100s (2 GPUs x microbatch 8 x accumulation 8) and scored 92.12% on the matched 6,000-episode four-suite evaluation.
 
 ## October 26 addition: full-suite aligned 4/2
 
@@ -101,6 +102,7 @@ Aligned (late) 4/2 v0 trained on all four suites with the same data, normalizati
 | [libero-all-suites/init_variants/core16_21](libero-all-suites/init_variants/core16_21) | v0 init `core16_21` | 4/4 | 584,536,135 | Training only; evaluation not run |
 | [libero-all-suites/init_variants/no_video_pretraining](libero-all-suites/init_variants/no_video_pretraining) | v0 init `no_video_pretraining` (no Wan video pretraining) | 4/4 | 584,536,135 | Training only; evaluation not run |
 | [libero-all-suites/init_variants/core_random](libero-all-suites/init_variants/core_random) | v0 init `core_random` | 4/4 | 584,536,135 | 82.20% (4,932/6,000; 4 suites x seeds 42/43/44) |
+| [libero-all-suites/init_variants/ffn_magnitude](libero-all-suites/init_variants/ffn_magnitude) | v0 init `ffn_magnitude` | 4/4 | 584,536,135 | 92.12% (5,527/6,000; 4 suites x seeds 42/43/44) |
 | [libero-all-suites/dense-s30](libero-all-suites/dense-s30) | dense_s30 | 1/1 | 1,416,114,247 | Training only; evaluation not run |
 | [libero-all-suites/dense-s12](libero-all-suites/dense-s12) | dense_s12 | 1/1 | 584,536,135 | Training only; evaluation not run |
 | [libero-all-suites/v0-video1-action4](libero-all-suites/v0-video1-action4) | v0 aligned | 1/4 | 584536135 | Not evaluated (training only) |

checkpoint_index.json

@@ -740,7 +740,55 @@
       "microbatch": 8,
       "gradient_accumulation": 8,
       "created_utc": "2026-10-28T19:11:24.475905+00:00"
+    },
+    {
+      "id": "v0_ffn_magnitude_full_libero_h100",
+      "repo_path": "libero-all-suites/init_variants/ffn_magnitude",
+      "training_path": "/groups/yshang/an221229/checkpoints/LoopWAM_NT/v0_init_variants/ffn_magnitude/train",
+      "source_sha256": "455bc19ea8027c18cff4be95a2135124b238dd192a06ab2fcd76660be64443e2",
+      "source_bytes": 7015840727,
+      "export_sha256": "a71026b87c5b6384311e8290d2eb6735ef0bd10b116fc485f329749092980d78",
+      "export_bytes": 2338914443,
+      "step": 21700,
+      "format": "loopwam-s-v1",
+      "optimizer_included": false,
+      "version": "v0",
+      "video_loops": 4,
+      "action_loops": 4,
+      "loop_alignment": "late",
+      "parameters": 584536135,
+      "init_variant": "ffn_magnitude",
+      "initialization_sha256": "c73dea22295a8b0c5de98536c862f6920438f0b51daf44690105bdc4a558d9bf",
+      "initialization_mode": "wan_init_variant_ffn_magnitude_fresh_optimizer",
+      "dataset_scope": "full_libero",
+      "epochs": 10,
+      "global_batch": 128,
+      "training_seed": 42,
+      "evaluation_status": "matched_libero_6000_h100",
+      "success_rate": 0.9211666666666667,
+      "successes": 5527,
+      "episodes": 6000,
+      "per_suite_success_rate": {
+        "libero_spatial": 0.958,
+        "libero_object": 0.9826666666666667,
+        "libero_goal": 0.9293333333333333,
+        "libero_10": 0.8146666666666667
+      },
+      "training_seconds": 79544.43194627948,
+      "resume_starts": 0,
+      "tensor_equality_verified": true,
+      "native_loader_verified": true,
+      "source_revision": "4ebf38a3c65aa5cc9d6c07d94c52f91c51551b57",
+      "compatible_code_revision": "4ebf38a3c65aa5cc9d6c07d94c52f91c51551b57",
+      "code_branch": "v0-init-variants",
+      "normalization_sha256": "d5ad351eb3272f416d34082e8af5483ba1118ceca355a37d9f268fdb269fb3e4",
+      "fairness_check_passed": true,
+      "gpu": "NVIDIA H100 80GB HBM3",
+      "world_size": 2,
+      "microbatch": 8,
+      "gradient_accumulation": 8,
+      "created_utc": "2026-10-28T19:14:54.782633+00:00"
     }
   ],
-  "updated_utc": "2026-10-28T19:17:16.281578+00:00"
+  "updated_utc": "2026-10-28T19:18:44.471588+00:00"
 }