revert to gpu

generation_evaluator.py

@@ -62,7 +62,7 @@ Note that ROUGE is case insensitive, meaning that upper case letters are treated
 This metrics is a wrapper around Google Research reimplementation of ROUGE:
 https://github.com/google-research/google-research/tree/master/rouge
 
-BLEU (Bilingual Evaluation Understudy) is an algorithm for evaluating the quality of text which has been machine-translated from one natural language to another.
+**BLEU (Bilingual Evaluation Understudy)** is an algorithm for evaluating the quality of text which has been machine-translated from one natural language to another.
 Quality is considered to be the correspondence between a machine's output and that of a human: "the closer a machine translation is to a professional human translation, the better it is"
 this is the central idea behind BLEU. BLEU was one of the first metrics to claim a high correlation with human judgements of quality, and remains one of the most popular automated and inexpensive metrics.
 
@@ -133,7 +133,7 @@ CHRF:{
 ALIGNSCORE_ARGS = {
     "model": "roberta-base",
     "batch_size": 32,
-    "device": "cpu",
+    "device": "cuda",
     "ckpt_path": "https://huggingface.co/yzha/AlignScore/resolve/main/AlignScore-base.ckpt",
     "evaluation_mode": "nli_sp",
 }