Create train.py

train.py

@@ -0,0 +1,48 @@
+# Import necessary libraries
+from datasets import load_dataset
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer, TrainingArguments
+
+# Load your dataset (assuming you uploaded it to Hugging Face)
+dataset = load_dataset("your_dataset_name")
+
+# Load pre-trained mBERT tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained('bert-base-multilingual-cased')
+model = AutoModelForSequenceClassification.from_pretrained('bert-base-multilingual-cased', num_labels=2)
+
+# Tokenize the dataset (adjust based on your dataset's structure)
+def tokenize_function(examples):
+    return tokenizer(examples['Text'], padding="max_length", truncation=True)
+
+# Tokenize the datasets
+tokenized_datasets = dataset.map(tokenize_function, batched=True)
+
+# Split into train and test datasets (if not already split)
+train_dataset = tokenized_datasets['train']
+test_dataset = tokenized_datasets['test']
+
+# Define training arguments
+training_args = TrainingArguments(
+    output_dir='./results',          # output directory for model checkpoints
+    evaluation_strategy="epoch",     # evaluate after each epoch
+    learning_rate=2e-5,              # learning rate
+    per_device_train_batch_size=16,  # batch size for training
+    per_device_eval_batch_size=64,   # batch size for evaluation
+    num_train_epochs=3,              # number of epochs
+    weight_decay=0.01,               # strength of weight decay
+    logging_dir='./logs',            # directory to store logs
+)
+
+# Initialize Trainer
+trainer = Trainer(
+    model=model,                         # the model to be trained
+    args=training_args,                  # training arguments
+    train_dataset=train_dataset,         # training dataset
+    eval_dataset=test_dataset            # evaluation dataset
+)
+
+# Train the model
+trainer.train()
+
+# Save the model to Hugging Face Model Hub
+model.push_to_hub("your_model_name")
+tokenizer.push_to_hub("your_model_name")