File size: 1,689 Bytes
2c2a89b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 |
from datasets import load_dataset
dataset = load_dataset("yelp_review_full")
dataset["train"][100]
#creating the dataset
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("bert-base-cased")
def tokenize_function(examples):
return tokenizer(examples["text"], padding="max_length", truncation=True)
#mapping the values:
tokenized_datasets = dataset.map(tokenize_function, batched=True)
#small Datasets:
small_train_dataset = tokenized_datasets["train"].shuffle(seed=42).select(range(1000))
small_eval_dataset = tokenized_datasets["test"].shuffle(seed=42).select(range(1000))
#Loading pretrained Model:
from transformers import AutoModelForSequenceClassification
model = AutoModelForSequenceClassification.from_pretrained("bert-base-cased", num_labels=5)
###
from transformers import TrainingArguments
training_args = TrainingArguments(output_dir="test_trainer")
#Evaluate
def compute_metrics(eval_pred):
logits, labels = eval_pred
predictions = np.argmax(logits, axis=-1)
return metric.compute(predictions=predictions, references=labels)
#Training Argumnents and importing Trainer:
from transformers import TrainingArguments, Trainer
training_args = TrainingArguments(output_dir="test_trainer", evaluation_strategy="epoch")
#Defining Hyperparameters for Trainer:
trainer = Trainer(
model=model,
args=training_args,
train_dataset=small_train_dataset,
eval_dataset=small_eval_dataset,
compute_metrics=compute_metrics,
)
#Execute the training:
trainer.train()
#Predictions:
predictions = trainer.predict(small_eval_dataset)
print(predictions.predictions.shape,predictions.label_ids.shape)
print(predictions)
|