File size: 1,573 Bytes
8225a4d 4d59358 b2f107f 730ad9d 8225a4d 730ad9d 4d59358 786fe91 |
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 |
# -*- coding: utf-8 -*-
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()
#gr.Interface(
# fn=trainer.train,
# inputs=None,
# outputs="training",
# title="test",
#).launch() |