Fix example command in README

README.md

@@ -28,16 +28,16 @@ The only difference is that there are a few new training arguments specific to H
 [Here](https://github.com/huggingface/optimum-habana/blob/main/examples/image-classification/run_image_classification.py) is an image classification example script to fine-tune a model. You can run it with Swin with the following command:
 ```bash
 python run_image_classification.py \
-    --model_name_or_path microsoft/swin-base-patch4-window7-224 \
+    --model_name_or_path microsoft/swin-base-patch4-window7-224-in22k \
     --dataset_name cifar10 \
     --output_dir /tmp/outputs/ \
     --remove_unused_columns False \
     --do_train \
     --do_eval \
-    --learning_rate 2e-5 \
+    --learning_rate 3e-5 \
     --num_train_epochs 5 \
-    --per_device_train_batch_size 32 \
-    --per_device_eval_batch_size 32 \
+    --per_device_train_batch_size 64 \
+    --per_device_eval_batch_size 64 \
     --evaluation_strategy epoch \
     --save_strategy epoch \
     --load_best_model_at_end True \
@@ -46,7 +46,8 @@ python run_image_classification.py \
     --use_habana \
     --use_lazy_mode \
     --gaudi_config_name Habana/swin \
-    --throughput_warmup_steps 2
+    --throughput_warmup_steps 2 \
+    --ignore_mismatched_sizes
 ```
 
 Check the [documentation](https://huggingface.co/docs/optimum/habana/index) out for more advanced usage and examples.