Update README.md

README.md

@@ -54,7 +54,7 @@ The model should not be used for any purpose other than generating impressions f
 ### Recommendations
 
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+Users should be aware of the limitations and potential biases of the model when using the generated impressions for clinical decision-making. Further information is needed to provide specific recommendations.
 
 ## How to Get Started with the Model
 
@@ -69,6 +69,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
 from transformers import SummarizationPipeline
 
 summarizer = SummarizationPipeline(model=model, tokenizer=tokenizer)
+
 output= summarizer("heart size normal mediastinal hilar contours remain stable small right pneumothorax remains unchanged surgical lung staples overlying
     left upper lobe seen linear pattern consistent prior upper lobe resection soft tissue osseous structures appear unremarkable nasogastric
     endotracheal tubes remain satisfactory position atelectatic changes right lower lung field remain unchanged prior study")
@@ -77,9 +78,8 @@ output= summarizer("heart size normal mediastinal hilar contours remain stable s
 ## Training Details
 
 ### Training Data
--Data Source: The training data was a custom dataset of 70,000 radiology reports. 
--Data Cleaning: The data was cleaned to remove any personal or confidential information. The data was also tokenized and normalized.
--Data Split: The training data was split into a training set and a validation set. The training set consisted of 63,000 radiology reports, and the validation set consisted of 7,000 radiology reports.
+The training data was a custom dataset of 70,000 radiology reports.The data was cleaned to remove any personal or confidential information. The data was also tokenized and normalized.
+The training data was split into a training set and a validation set. The training set consisted of 63,000 radiology reports, and the validation set consisted of 7,000 radiology reports.
 
 
 
@@ -91,16 +91,16 @@ The model was trained using the Hugging Face Transformers library: https://huggi
 #### Training Hyperparameters
 
 - **Training regime:**
--evaluation_strategy="epoch",
--learning_rate=5.6e-5,
--per_device_train_batch_size=batch_size //4,
--per_device_eval_batch_size=batch_size //4,
--weight_decay=0.01,
--save_total_limit=3,
--num_train_epochs=num_train_epochs,
--predict_with_generate=True,
--logging_steps=logging_steps,
--push_to_hub=False,
+-[evaluation_strategy="epoch"],
+-[learning_rate=5.6e-5],
+-[per_device_train_batch_size=batch_size //4],
+-[per_device_eval_batch_size=batch_size //4,]
+-[weight_decay=0.01],
+-[save_total_limit=3],
+-[num_train_epochs=num_train_epochs //4],
+-[predict_with_generate=True //4],
+-[logging_steps=logging_steps],
+-[push_to_hub=False]
 
 
 
@@ -113,10 +113,10 @@ The testing data consisted of 10,000 radiology reports.
 
 #### Factors
 The following factors were evaluated:
--ROUGE-1
--ROUGE-2
--ROUGE-L
--ROUGELSUM
+[-ROUGE-1]
+[-ROUGE-2]
+[-ROUGE-L]
+[-ROUGELSUM]
 
 #### Metrics
 The following metrics were used to evaluate the model: