Add finetune evaluation script

ptuning/evaluate_finetune.sh

@@ -0,0 +1,18 @@
+CHECKPOINT=adgen-chatglm-6b-ft-1e-4
+STEP=3000
+
+CUDA_VISIBLE_DEVICES=0 python3 main.py \
+    --do_predict \
+    --validation_file AdvertiseGen/dev.json \
+    --test_file AdvertiseGen/dev.json \
+    --overwrite_cache \
+    --prompt_column content \
+    --response_column summary \
+    --model_name_or_path ./output/$CHECKPOINT/checkpoint-$STEP  \
+    --output_dir ./output/$CHECKPOINT \
+    --overwrite_output_dir \
+    --max_source_length 256 \
+    --max_target_length 256 \
+    --per_device_eval_batch_size 1 \
+    --predict_with_generate \
+    --fp16_full_eval