Use 175k steps checkpoint

README.md

@@ -37,6 +37,7 @@ python lerobot/scripts/train.py \
 
 
 The training curves may be found at https://wandb.ai/aliberts/lerobot/runs/s7elvf4r.
+The current model corresponds to the checkpoint at 175k steps.
 
 ## Evaluation
 
@@ -49,7 +50,18 @@ Here are the metrics for 500 episodes worth of evaluation. The "Theirs" column i
 
 <blank>|Ours|Theirs
 -|-|-
-Average max. overlap ratio | 0.945 | 0.957
-Success rate for 500 episodes (%) | 63.2 | 64.2
+Average max. overlap ratio | 0.955 | 0.957
+Success rate for 500 episodes (%) | 65.4 | 64.2
 
-The results of each of the individual rollouts may be found in [eval_info.json](eval_info.json).
+The results of each of the individual rollouts may be found in [eval_info.json](eval_info.json).
+It was produced with this command:
+```bash
+python lerobot/scripts/eval.py \
+    --policy.path=outputs/train/diffusion_pusht/checkpoints/175000/pretrained_model \
+    --output_dir=outputs/eval/diffusion_pusht/175000 \
+    --env.type=pusht \
+    --eval.n_episodes=500 \
+    --eval.batch_size=50 \
+    --device=cuda \
+    --use_amp=false
+```

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6b2458798c6dfad3edc0d338a1a4c78da62cc68817eb3d8bd7b395bed4ef672
+oid sha256:995d14d35db57d95c35ad9704c3d79c8612b7bc45f3877e5c46c2cdc516856a8
 size 1050862408