helen9975 commited on
Commit
f7b825b
·
verified ·
1 Parent(s): 10131f7

Update model card

Browse files
Files changed (1) hide show
  1. README.md +7 -2
README.md CHANGED
@@ -10,8 +10,13 @@ base_model: lerobot/pi05_base
10
  bimanual YAM. Checkpoints are merged into a full `model.safetensors`, so each loads like a normal
11
  checkpoint, and live in `merged/<step>/`.
12
 
13
- **Status: training is still running, and no checkpoint has been uploaded yet. The first one planned
14
- is step 34,610, halfway through the run.**
 
 
 
 
 
15
 
16
  **Evaluation: not yet evaluated, in simulation or on a robot.**
17
 
 
10
  bimanual YAM. Checkpoints are merged into a full `model.safetensors`, so each loads like a normal
11
  checkpoint, and live in `merged/<step>/`.
12
 
13
+ **Status: training is still running.** Uploaded so far:
14
+
15
+ | Folder | Step | Share of the run | Held-out loss near this step |
16
+ |---|---|---|---|
17
+ | `merged/020766/` | 20,766 | 30% | 0.047–0.053 (steps 20,000–21,000) |
18
+
19
+ Step 34,610 (halfway) is planned next. Held-out loss is noisy because each eval uses few samples.
20
 
21
  **Evaluation: not yet evaluated, in simulation or on a robot.**
22