Bert-Lab4

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5647
• Accuracy: 0.73

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

We use 100 data from the glue/sst2, since we train on Colab. https://drive.google.com/file/d/1Ej0-bDkfXmlNPynypS-xDbEEGK9hI06l/view?usp=sharing

How to use

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