The Trainer API

Trainer - 
1. Model

2. Training/ Validation/ Test dataset

3. Tokenizer

4. Data Collator

5. Hyperparameters

6. Metrics

 

Evaluation/ Prediction

! pip install datasets transformers[sentencepiece]

from datasets import load_dataset
from transformers import AutoTokenizer, DataCollatorWithPadding

raw_datasets = load_dataset("glue", "mrpc")
checkpoint = "bert-base-cased"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)

def tokenize_function(examples):
    return tokenizer(examples["sentence1"], examples["sentence2"], truncation=True)

tokenized_datasets = raw_datasets.map(tokenize_function, batched=True)
data_collator = DataCollatorWithPadding(tokenizer)

dataset = "glue", "mrpc" ??

checkpoint = model name

GLUE (General Language Understanding Evaluation)

MRPC (Microsoft Research Paraphrase Corpus)

from transformers import TrainingArguments

training_args = TrainingArguments("test-trainer")

 

from transformers import TrainingArguments

training_args = TrainingArguments(
    "test-trainer",
    per_device_train_batch_size=16,
    per_device_eval_batch_size=16,
    num_train_epochs=5,
    learning_rate=2e-5,
    weight_decay=0.01,
)

from transformers import Trainer

trainer = Trainer(
    model,
    training_args,
    train_dataset=tokenized_datasets["train"],
    eval_dataset=tokenized_datasets["validation"],
    data_collator=data_collator,
    tokenizer=tokenizer,
)
trainer.train()

predictions = trainer.predict(tokenized_datasets["validation"])
print(predictions.predictions.shape, predictions.label_ids.shape)

import numpy as np
from datasets import load_metric

metric = load_metric("glue", "mrpc")
preds = np.argmax(predictions.predictions, axis=-1)
metric.compute(predictions=preds, references=predictions.label_ids)

 

metric = load_metric("glue", "mrpc")

def compute_metrics(eval_preds):
    logits, labels = eval_preds
    predictions = np.argmax(logits, axis=-1)
    return metric.compute(predictions=predictions, references=labels)

 

training_args = TrainingArguments("test-trainer", evaluation_strategy="epoch")
model = AutoModelForSequenceClassification.from_pretrained(checkpoint, num_labels=2)

trainer = Trainer(
    model,
    training_args,
    train_dataset=tokenized_datasets["train"],
    eval_dataset=tokenized_datasets["validation"],
    data_collator=data_collator,
    tokenizer=tokenizer,
    compute_metrics=compute_metrics
)
trainer.train()