Correct way to create a Dataset from a csv file

Beginners
15

The script now works with a modification by Yasmin Moslem. I post it below in case others have a simil;ar issue:

import datasets
from transformers import AutoTokenizer
from datasets import load_dataset
from transformers import DataCollatorForSeq2Seq
from transformers import AutoModelForSeq2SeqLM, Seq2SeqTrainingArguments, Seq2SeqTrainer
from random import randrange

luganda_dataset = load_dataset("csv", data_files="Luganda.csv")
luganda_dataset = luganda_dataset["train"].map(lambda ex, i: {"id": i, "translation": dict(ex)}, remove_columns=["en", "lg"], features=datasets.Features({"id": datasets.Value("string"), "translation": datasets
.Translation(languages=["en", "lg"])}), with_indices=True,)
luganda_dataset = luganda_dataset.train_test_split(test_size=0.2)
tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-en-lg")
source_lang = "en"
target_lang = "lg"
prefix = "translate English to Luganda: "

def preprocess_function(examples):
    inputs = []
    targets = []
    for example in examples["translation"]:
        if example[source_lang] is not None and example[target_lang] is not None and \
        len(example[source_lang].strip()) > 3 and len(example[target_lang].strip()) > 3:
            inputs.append(prefix + example[source_lang].strip())
            targets.append(example[target_lang].strip())
        else:
            "There is an issue with this segment:"
            print("Source:", example[source_lang])
            print("Target:", example[target_lang])
            random_num = randrange(10000)
            print("Replaced with", random_num)
            inputs.append(prefix + str(random_num))
            targets.append(str(random_num))
    model_inputs = tokenizer(inputs, max_length=128, truncation=True)
    with tokenizer.as_target_tokenizer():
        labels = tokenizer(targets, max_length=128, truncation=True)
        model_inputs["labels"] = labels["input_ids"]
    return model_inputs

print(luganda_dataset.map)
tokenized_luganda = luganda_dataset.map(preprocess_function, batched=True)
model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-en-lg")
data_collator = DataCollatorForSeq2Seq(tokenizer=tokenizer, model=model)

training_args = Seq2SeqTrainingArguments(
    output_dir="./results",
    evaluation_strategy="epoch",
    learning_rate=2e-5,
    per_device_train_batch_size=16,
    per_device_eval_batch_size=16,
    weight_decay=0.01,
    save_total_limit=3,
    num_train_epochs=10,
    fp16=True,
)

trainer = Seq2SeqTrainer(
    model=model,
    args=training_args,
    train_dataset=tokenized_luganda["train"],
    eval_dataset=tokenized_luganda["test"],
    tokenizer=tokenizer,
    data_collator=data_collator,
)

trainer.train()