vuiseng9
/

bert-base-squadv1-block-pruning-hybrid-filled-lt

Question Answering

Inference Endpoints

Model card Files Files and versions Community

Chua, Vui Seng commited on Jan 9, 2022

Commit

37ca5f0

·

1 Parent(s): c83a9d5

Update eval batch size

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -53,9 +53,9 @@ nohup python run_qa.py  \
     --optimize_model_before_eval \
     --optimized_checkpoint /path/to/clone/bert-base-squadv1-block-pruning-hybrid-filled-lt  \
     --do_eval  \
-    --per_device_eval_batch_size 16  \
     --max_seq_length 384  \
     --doc_stride 128  \
     --overwrite_output_dir \
     --output_dir $OUTDIR 2>&1 | tee $OUTDIR/run.log &
-```

     --optimize_model_before_eval \
     --optimized_checkpoint /path/to/clone/bert-base-squadv1-block-pruning-hybrid-filled-lt  \
     --do_eval  \
+    --per_device_eval_batch_size 128  \
     --max_seq_length 384  \
     --doc_stride 128  \
     --overwrite_output_dir \
     --output_dir $OUTDIR 2>&1 | tee $OUTDIR/run.log &
+```