add .env gitignore

.gitignore

@@ -3,3 +3,5 @@
 __pycache__/
 
 meaningbert
+
+.env

README.md

@@ -16,11 +16,11 @@ Its goal is to assess meaning preservation between two sentences that correlate
 checks. For more details, refer to our publicly available article.
 
 > This public version of our model uses the best model trained (where in our article, we present the performance results
-> of an average of 10 models) for a more extended period (1,000 epochs instead of 250). We have observed later that the
-> model can further reduce dev loss and increase performance.
+> of an average of 10 models) for a more extended period (500 epochs instead of 250). We have observed later that the
+> model can further reduce dev loss and increase performance. Also, we have changed the data augmentation technique use
+> in the article for a more robust one.
 
 - [HuggingFace Model Card](https://huggingface.co/davebulaval/MeaningBERT)
-- [HuggingFace Metric Card]()
 
 ## Sanity Check
 

datastore/.gitignore

@@ -1 +1,2 @@
 /V1
+/V2

datastore/V2.dvc

@@ -0,0 +1,6 @@
+outs:
+- md5: 44c355ec08f57d43542c375519260f3b.dir
+  size: 438905054
+  nfiles: 7
+  hash: md5
+  path: V2

push_model_to_hub.py

@@ -1,8 +1,14 @@
 import os.path
 
+import huggingface_hub
+from dotenv import dotenv_values
 from transformers import AutoModelForSequenceClassification, AutoTokenizer
 
-model_path = os.path.join("datastore", "V1")
+secrets = dotenv_values(".env")
+
+huggingface_hub.login(token=secrets["huggingface_token"])
+
+model_path = os.path.join(".", "datastore", "V2")
 model = AutoModelForSequenceClassification.from_pretrained(model_path)
 
 model.push_to_hub("davebulaval/MeaningBERT")

requirements.txt

@@ -2,4 +2,5 @@
 
 pytorch
 tensorflow[and-cuda]
-keras
+keras
+dotenv