shantanu-tr commited on
Commit
ef188f5
·
verified ·
1 Parent(s): 29717bd

Fill training details: batch size 8, 40K steps (final checkpoint)

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -120,8 +120,8 @@ so no special flag is needed at inference.
120
  - **Dataset:** [`TrossenRoboticsCommunity/stationary-block-transfer-lerobot-v3`](https://huggingface.co/datasets/TrossenRoboticsCommunity/stationary-block-transfer-lerobot-v3) @ `v3.0`.
121
  - **Base model:** `lerobot/pi05_base`.
122
  - **Framework:** lerobot-latest (`--policy.type=pi05`).
123
- - **Batch size:** TODO.
124
- - **Total steps:** TODO (checkpoints exist at 40k/60k/80k; this record is **40k**).
125
  - **Training env / hardware:** local-5090 (run on a local RTX 5090 using the Trossen cloud pipeline).
126
 
127
  ## Outputs
 
120
  - **Dataset:** [`TrossenRoboticsCommunity/stationary-block-transfer-lerobot-v3`](https://huggingface.co/datasets/TrossenRoboticsCommunity/stationary-block-transfer-lerobot-v3) @ `v3.0`.
121
  - **Base model:** `lerobot/pi05_base`.
122
  - **Framework:** lerobot-latest (`--policy.type=pi05`).
123
+ - **Batch size:** 8.
124
+ - **Total steps:** 40,000 (this is the final checkpoint).
125
  - **Training env / hardware:** local-5090 (run on a local RTX 5090 using the Trossen cloud pipeline).
126
 
127
  ## Outputs