|
|
|
|
|
import gradio as gr |
|
from transformers import pipeline |
|
from transformers import AutoTokenizer |
|
from datasets import load_dataset |
|
from transformers import DataCollatorWithPadding |
|
|
|
raw_datasets = load_dataset("glue", "sst2") |
|
raw_datasets |
|
checkpoint = "bert-base-uncased" |
|
tokenizer = AutoTokenizer.from_pretrained(checkpoint) |
|
def tokenize_function(example): |
|
return tokenizer(example["sentence"], truncation=True) |
|
|
|
tokenized_datasets = raw_datasets.map(tokenize_function, batched=True,remove_columns=['idx','sentence']) |
|
tokenized_datasets |
|
|
|
|
|
data_collator = DataCollatorWithPadding(tokenizer=tokenizer) |
|
|
|
from transformers import TrainingArguments |
|
from transformers import AutoModelForSequenceClassification |
|
from datasets import load_metric |
|
from transformers import Trainer |
|
import numpy as np |
|
|
|
training_args = TrainingArguments("test-trainer", evaluation_strategy="epoch") |
|
model = AutoModelForSequenceClassification.from_pretrained(checkpoint, num_labels=2) |
|
|
|
def compute_metrics(eval_preds): |
|
metric = load_metric("glue", "sst2") |
|
logits, labels = eval_preds |
|
predictions = np.argmax(logits, axis=-1) |
|
return metric.compute(predictions=predictions, references=labels) |
|
|
|
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() |
|
|
|
|
|
|
|
|
|
|
|
|
