Card: resuming with the released code (--ignore-data-fingerprints; sparse optimizer state refused)

README.md

@@ -71,9 +71,10 @@ torchrun --standalone --nproc-per-node=1 olmo-core/src/scripts/train/ladder/coun
   --count-k 8 --count-max-order 6 --count-num-orders 6
 ```
 
-Evaluation loads model weights only. Resuming training also restores the trainer state, which records
-a fingerprint of the original data paths; the released code rejects a resume when your data paths
-differ.
+Evaluation loads model weights only. Resuming training also restores the optimizer and trainer state.
+The trainer state records a fingerprint of the data paths the model was trained on, and the code
+refuses to resume on data whose fingerprint differs; when your tokenized data is the same corpus at
+different paths, pass `--ignore-data-fingerprints`.
 
 ## Related