from datasets import load_dataset
from transformers import AutoTokenizer, DataCollatorWithPadding

raw_datasets = load_dataset("glue", "sst2")
checkpoint = "ChiJuiChen/Bert-Lab4"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)


def tokenize_function(example):
    return tokenizer(example["sentence"], truncation=True)


tokenized_datasets = raw_datasets.map(tokenize_function, batched=True)

small_train_dataset = tokenized_datasets["train"].shuffle(seed=42).select(range(100))
small_eval_dataset = tokenized_datasets["validation"].shuffle(seed=42).select(range(100))

data_collator = DataCollatorWithPadding(tokenizer=tokenizer)

from transformers import TrainingArguments

training_args = TrainingArguments(output_dir="ChiJuiChen/Bert-Lab4",
                                  evaluation_strategy="epoch",
                                  hub_model_id="ChiJuiChen/Bert-Lab4")

from transformers import AutoModelForSequenceClassification
model = AutoModelForSequenceClassification.from_pretrained(checkpoint, num_labels=2)

from transformers import Trainer
trainer = Trainer(
    model,
    training_args,
    train_dataset=small_train_dataset, # if using cpu
    eval_dataset=small_eval_dataset, # if using cpu
    data_collator=data_collator,
    tokenizer=tokenizer,
    compute_metrics=compute_metrics,
)

# Evaluation
predictions = trainer.predict(small_eval_dataset)
print(predictions.predictions.shape, predictions.label_ids.shape)
preds = np.argmax(predictions.predictions, axis=-1)

import evaluate
metric = evaluate.load("glue", "sst2")
metric.compute(predictions=preds, references=predictions.label_ids)

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	13	0.6383	0.59
No log	2.0	26	0.5867	0.71
No log	3.0	39	0.5647	0.73

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2