Xin Lai commited on
Commit
43e1e6c
·
1 Parent(s): cfaea84
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -223,6 +223,8 @@ deepspeed --master_port=24999 train_ds.py \
223
  --eval_only
224
  ```
225
 
 
 
226
 
227
  ## Inference
228
 
 
223
  --eval_only
224
  ```
225
 
226
+ Note: the v1 model is trained using both `train+val` sets, so please use the `v0` model to reproduce the validation results. (To use the v0 models, please first checkout to the legacy version repo git checkout 0e26916.)
227
+
228
 
229
  ## Inference
230