Upload folder using huggingface_hub

README.md

@@ -16,27 +16,31 @@ datasets:
 Evaluation-only checkpoints (EMA weights, fitted normalizer, resolved config, git SHA) for
 [FlowPush](https://github.com/WilliamHangXu/FlowPush): flow-matching and diffusion
 visuomotor policies on Push-T, a 1-step distilled student, and Push-F transfer policies.
-Each file is training seed 0 of the corresponding row in the repository README; evaluating
-it on the 50 test episodes reproduces that seed's number (the README reports 3-seed means).
+Each file is training seed 0 of the corresponding row in the repository README (plus the
+seed-2 teacher); scores are that seed's result on the 100-episode final holdout — † marks
+models outside the holdout list, scored on the 50-episode development set. The README
+reports 3-seed means.
 
-| file | model | success@0.95, seed 0 |
+| file | model | success@0.95 (final holdout) |
 |---|---|---|
-| `pusht_ddpm_unet_seed0.pt` | DDPM U-Net, state obs, 100 steps | 0.44 |
-| `pusht_fm_unet_seed0.pt` | flow-matching U-Net, state obs, 8 Euler steps | 0.60 |
-| `pusht_fm_unet_seed2.pt` | flow-matching U-Net, state obs — the distillation teacher | 0.60 |
-| `pusht_fm_dit_seed0.pt` | flow-matching DiT (7.8M params), state obs, 8 steps | 0.34 |
-| `pusht_fm_unet_image_seed0.pt` | flow-matching U-Net, 96×96 RGB obs, 8 steps | 0.30 |
-| `pusht_2rf_seed0.pt` | 2-rectified flow (K = 8), 1 step | 0.46 |
-| `pusht_2rf_k32_seed0.pt` | 2-rectified flow (K = 32) — parent of the 1-step students | 0.36 |
-| `pusht_1step_distilled_seed0.pt` | 1-step distilled student (trained from `pusht_2rf_k32_seed0.pt`) | 0.52 |
-| `pushf_scratch_n100_seed0.pt` | Push-F, trained from scratch on 100 demos, 8 steps | 0.66 |
-| `pushf_finetune_n100_seed0.pt` | Push-F, fine-tuned from the Push-T teacher on 100 demos (lr 1e-4), 8 steps | 0.78 |
+| `pusht_ddpm_unet_seed0.pt` | DDPM U-Net, state obs, 100 steps | 0.62 |
+| `pusht_fm_unet_seed0.pt` | flow-matching U-Net, state obs, 8 Euler steps | 0.65 |
+| `pusht_fm_unet_seed2.pt` | flow-matching U-Net, state obs — the distillation teacher | 0.61 |
+| `pusht_fm_dit_seed0.pt` | flow-matching DiT (7.8M params), state obs, 8 steps | 0.34† |
+| `pusht_fm_unet_image_seed0.pt` | flow-matching U-Net, 96×96 RGB obs, 8 steps | 0.30† |
+| `pusht_2rf_seed0.pt` | 2-rectified flow (K = 8), 1 step | 0.47 |
+| `pusht_2rf_k32_seed0.pt` | 2-rectified flow (K = 32) — parent of the 1-step students | 0.47 |
+| `pusht_1step_distilled_seed0.pt` | 1-step distilled student (trained from `pusht_2rf_k32_seed0.pt`) | 0.40 |
+| `pushf_scratch_n100_seed0.pt` | Push-F, trained from scratch on 100 demos, 8 steps | 0.70 |
+| `pushf_finetune_n100_seed0.pt` | Push-F, fine-tuned from the Push-T teacher on 100 demos (lr 1e-4), 8 steps | 0.67 |
 
 `eval_records.tgz` holds the per-episode evaluation records behind the repository's
 `results/*.csv`. All three student seeds share the single K = 32 parent above, which was
 trained from the seed-2 teacher; the repository's `results/lineage.csv` records parents and
-SHA-256 hashes. The Push-T test seeds were reused while developing the distillation recipe,
-so Part 2 comparisons are development-set results. A pre-registered final holdout
+SHA-256 hashes, and the 2-RF and student checkpoints embed their coupling manifest
+(teacher SHA-256, K, ODE steps). The original 50-episode evaluation set was consulted during
+exploratory work in Parts 2 and 3, so numbers from it are development results (marked †).
+A final holdout, pre-specified and committed before evaluation
 (100 fresh episodes, one evaluation per model; `docs/FINAL_HOLDOUT.md` in the repository)
 re-scored every released Push-T/Push-F policy: FM@8 0.617 ± 0.031, DDPM@100 0.537 ± 0.127,
 1-step student 0.427 ± 0.025 vs its K = 32 parent 0.470 — the student's development-set
@@ -48,7 +52,7 @@ of record; `eval_records.tgz` includes the `final_*.json` records.
 ```bash
 git clone https://github.com/WilliamHangXu/FlowPush.git && cd FlowPush
 uv sync && make data && make checkpoints
-uv run python evaluate.py --ckpt checkpoints/pusht_fm_unet_seed0.pt --seeds test --points euler:8
+uv run python evaluate.py --ckpt checkpoints/pusht_fm_unet_seed0.pt --seeds final --points euler:8
 # Push-F policies: add --env pushf
 ```
 

pusht_1step_distilled_seed0.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d95bafa0f2917fffaf800c712c5894d9d998a97124802b5b821b1bc6c348c6c8
-size 261596327
+oid sha256:f9d9243d54e333e90ce9afaf6c61b8c6378a078e9546829ece2ee5b27d49f347
+size 261597095

pusht_2rf_k32_seed0.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9104d164750fca82ef67d27052003def1cf6474582d5f7275e4ddcd81315f89f
-size 261594999
+oid sha256:a57dd49dc6d68b7423b95bc627812496979b4cabdbfc17bfd12940efad1eed9f
+size 261595767

pusht_2rf_seed0.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7a7323c439351208625cead9d6a0b5314eb58aaac9d405c7cf0d42befb58672
-size 261594367
+oid sha256:8634a74d93899ea9a60b043a3a6865810d85b35602a978f0e8984492bb0a50bb
+size 261595135