small updates

app.py

@@ -14,7 +14,7 @@ from io import BytesIO
 #model = AlbertModel.from_pretrained('albert-' + model_size + '-v2')
 
 # For baseline 'sentence-transformers/paraphrase-albert-base-v2'
-model_name = 'output/training_OnlineConstrativeLoss-2023-03-14_00-40-03'
+model_name = 'output/training_OnlineConstrativeLoss-2023-03-14_01-24-44'
 
 similarity_threshold = 0.9
 

quick_evaluate.py

@@ -12,7 +12,7 @@ from sentence_transformers import SentenceTransformer
 model_name = 'output/training_OnlineConstrativeLoss-2023-03-10_11-17-15'
 model_name = 'output/training_OnlineConstrativeLoss-2023-03-11_00-24-35'
 model_name = 'output/training_OnlineConstrativeLoss-2023-03-11_01-00-19'
-model_name='output/training_OnlineConstrativeLoss-2023-03-12_00-42-41'
+model_name='output/training_OnlineConstrativeLoss-2023-03-14_01-24-44'
 model_sbert = SentenceTransformer(model_name)
 
 def get_sbert_embedding(input_text):

train.py

@@ -25,8 +25,8 @@ logger = logging.getLogger(__name__)
 
 #As base model, we use DistilBERT-base that was pre-trained on NLI and STSb data
 model = SentenceTransformer('sentence-transformers/paraphrase-albert-base-v2')
-num_epochs = 10
-train_batch_size = 10
+num_epochs = 12
+train_batch_size = 14
 
 #As distance metric, we use cosine distance (cosine_distance = 1-cosine_similarity)
 distance_metric = losses.SiameseDistanceMetric.COSINE_DISTANCE