Update README.md

examples/textual_inversion/README.md

@@ -49,7 +49,7 @@ accelerate launch textual_inversion.py \
   --placeholder_token="<cat-toy>" --initializer_token="toy" \
   --resolution=512 \
   --train_batch_size=1 \
-  --gradient_accumulation_steps=2 \
+  --gradient_accumulation_steps=4 \
   --max_train_steps=3000 \
   --learning_rate=5.0e-04 --scale_lr \
   --lr_scheduler="constant" \
@@ -79,4 +79,4 @@ with autocast("cuda"):
     image = pipe(prompt, num_inference_steps=50, guidance_scale=7.5)["sample"][0]
 
 image.save("cat-backpack.png")
-```
\ No newline at end of file
+```