Training in progress, step 18500

.ipynb_checkpoints/eval-checkpoint.py

@@ -49,7 +49,7 @@ def log_results(result: Dataset, args: Dict[str, str]):
 def normalize_text(text: str) -> str:
     """DO ADAPT FOR YOUR USE CASE. this function normalizes the target text."""
 
-    chars_to_ignore_regex = '[,?.!\-\;\:"“%‘”�—’…–]'  # noqa: W605 IMPORTANT: this should correspond to the chars that were ignored during training
+    chars_to_ignore_regex = '[!"%,.:;?\\_|©«¬»،؛؟‒–—’“”„…‹›−☺♂�\\\\-]'  # noqa: W605 IMPORTANT: this should correspond to the chars that were ignored during training
 
     text = re.sub(chars_to_ignore_regex, "", text.lower())
 

eval.py

@@ -49,7 +49,7 @@ def log_results(result: Dataset, args: Dict[str, str]):
 def normalize_text(text: str) -> str:
     """DO ADAPT FOR YOUR USE CASE. this function normalizes the target text."""
 
-    chars_to_ignore_regex = '[,?.!\-\;\:"“%‘”�—’…–]'  # noqa: W605 IMPORTANT: this should correspond to the chars that were ignored during training
+    chars_to_ignore_regex = '[!"%,.:;?\\_|©«¬»،؛؟‒–—’“”„…‹›−☺♂�\\\\-]'  # noqa: W605 IMPORTANT: this should correspond to the chars that were ignored during training
 
     text = re.sub(chars_to_ignore_regex, "", text.lower())
 

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7e4b8c5c1118bb1baee729434aff40837550be44f11a4ddc71b3643882e4d03
+oid sha256:73b90be4276eb5faf73aa36222d89249b80ec66348e9433da7efe67d53c41e0d
 size 1262104049

runs/Jan28_17-40-32_job-0074bb36-c67f-4775-b1b6-176eb09b0ba4/events.out.tfevents.1643391738.job-0074bb36-c67f-4775-b1b6-176eb09b0ba4.843454.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77cc0c5d46b1a86d6a2fc82687ea923a2f791a1d4a4415111a5fbd72bf98c515
-size 44510
+oid sha256:5c05204e072a6a078c5880fef30fe2a2e48fea9f4c7ad611aec292154ed3f6db
+size 45634