Update README.md

README.md

@@ -51,6 +51,74 @@ More information needed
 
 ## Training procedure
 
+```
+import torch
+from datasets import load_dataset
+from transformers import (
+  AutoModelForSequenceClassification,
+  AutoTokenizer,
+  DataCollatorWithPadding,
+  TrainingArguments,
+  Trainer
+)
+
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+labr = load_dataset("labr")
+
+labels = {0,1,2,3,4}
+target_names = [
+    "Poor",
+    "Fair",
+    "Good",
+    "Very Good",
+    "Excellent"
+]
+
+id2label = {idx: label for idx, label in enumerate(target_names)}
+label2id = {label: idx for idx, label in enumerate(target_names)}
+
+
+BERT_MODEL = "google-bert/bert-base-multilingual-uncased"
+
+model = AutoModelForSequenceClassification.from_pretrained(BERT_MODEL, num_labels = len(id2label))
+tokenizer = AutoTokenizer.from_pretrained(BERT_MODEL)
+
+model.to(device)
+
+
+def preprocess_function(examples):
+    return tokenizer(examples["text"], truncation=True)
+
+tokenized_labr = labr.map(preprocess_function, batched=True)
+
+
+data_collator = DataCollatorWithPadding(tokenizer=tokenizer)
+
+training_args = TrainingArguments(
+    output_dir="Arabic-Book-Review-Sentiment-Assessment",
+    learning_rate=2e-5,
+    per_device_train_batch_size=8,
+    per_device_eval_batch_size=8,
+    num_train_epochs=1,
+    weight_decay=0.01,
+    push_to_hub=True
+)
+
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=tokenized_labr["train"],
+    eval_dataset=tokenized_labr["test"],
+    tokenizer=tokenizer,
+    data_collator=data_collator,
+)
+
+trainer.train()
+
+trainer.evaluate(tokenized_labr["test"])
+```
 
 ### Training hyperparameters