Add checkpoint provenance and usage metadata

README.md

@@ -9,12 +9,12 @@ tags:
 
 # WRM_adaptive-all125
 
-Final EMA-enabled checkpoint for `WRM_adaptive` trained on the local
+Complete checkpoint series for `WRM_adaptive` trained on the local
 `WRM_grasp_cylinder_different_sizes_lero_tightness` LeRobot dataset.
 
 - GPULab job: `920957a7-7b2a-4e3f-89c6-ab0e5f151af8`
-- Training step: `100000`
-- Checkpoint: `last.pt`
+- Training steps: `10000` through `100000`, every `10000` steps
+- Checkpoints: ten numbered milestones plus final EMA-enabled `last.pt`
 - SHA-256: `faed996bdc4efc1f9a432e59177c9d5dc5229939ea15bd7faaf376ef5ef91214`
 - Source configuration: `resolved_config.yaml`
 - Metrics: `metrics.jsonl`