# SST2 classification with BertForSequenceClassification

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsst2-classification-with-bertforsequenceclassification%2F21114%3E%5C
**Category:** 🤗Transformers\
**Created:** [August 1, 2022, 5:32pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsst2-classification-with-bertforsequenceclassification%2F21114 "2022-08-01T17:32:12Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![kwonmha](https://avatars.discourse-cdn.com/v4/letter/k/ecccb3/32.png) [@kwonmha](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fkwonmha)%5C
**Post date:** [August 1, 2022, 5:32pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsst2-classification-with-bertforsequenceclassification%2F21114%2F1 "2022-08-01T17:32:13Z")

</div>

I’m working on sentence classification with pretrained BERT.  
I used BertForSequenceClassification class but it doesn’t look being trained.  
Can someone let me know what’s wrong with this code?

```auto
import numpy as np
from sklearn.metrics import f1_score, precision_recall_fscore_support
import torch
from torch import nn
import torch.nn.functional as F
from torch.optim import AdamW
from torch.utils.data import DataLoader, Dataset
from torchtext.datasets import SST2
from tqdm import tqdm
from transformers import AutoTokenizer, AutoModel, BertForSequenceClassification

LR = 0.0005
EPOCHS = 5
BATCH_SIZE = 128

device = torch.device("cuda:" + "0" if torch.cuda.is_available() else "cpu")

model_name = "bert-base-uncased"
tokenizer = AutoTokenizer.from_pretrained(model_name)
base_model = BertForSequenceClassification.from_pretrained(model_name)
max_input_length = 128

model = base_model.to(device)
criterion = nn.CrossEntropyLoss().to(device)
optimizer = AdamW(model.parameters(), lr=LR)

train_datapipe = SST2(split="train")
valid_datapipe = SST2(split="dev")
# Transform the raw dataset using non-batched API (i.e apply transformation line by line)
def collate_batch(batch):
    ids, types, masks, label_list = [], [], [], []
    for text, label in batch:
        tokenized = tokenizer(text,
                              padding="max_length", max_length=max_input_length,
                              truncation=True, return_tensors="pt")
        ids.append(tokenized['input_ids'])
        types.append(tokenized['token_type_ids'])
        masks.append(tokenized['attention_mask'])
        label_list.append(label)

    input_data = {
        "input_ids": torch.squeeze(torch.stack(ids)).to(device),
        "token_type_ids": torch.squeeze(torch.stack(types)).to(device),
        "attention_mask": torch.squeeze(torch.stack(masks)).to(device)
    }
    label_list = torch.tensor(label_list, dtype=torch.int64)
    return input_data, label_list

train_dataloader = DataLoader(train_datapipe, shuffle=True, batch_size=BATCH_SIZE, collate_fn=collate_batch)
valid_dataloader = DataLoader(valid_datapipe, batch_size=BATCH_SIZE, collate_fn=collate_batch)

# print("total instances: ", len(train_dataloader))
for epoch in range(EPOCHS):
    model.train()
    train_loss = []
    all_labels = []
    all_outs = []

    for i, (input_data, label) in enumerate(tqdm(train_dataloader)):
        model.zero_grad()
        output = model(**input_data).logits
        label = label.to(device)
        loss = criterion(output, label)
        loss.backward()
        optimizer.step()

        loss_value = loss.item()
        train_loss.append(loss_value)

        label = label.cpu().numpy()
        all_labels.extend(label)
        predicted_labels = torch.argmax(output, dim=-1).cpu().numpy()
        all_outs.extend(predicted_labels)

    # calc metric
    train_loss = np.mean(train_loss)
    print(train_loss)
    print(precision_recall_fscore_support(all_labels, all_outs))
    print("-" * 30)

    model.eval()
    val_loss = []
    val_accuracy = []
    with torch.no_grad():
        for i, (input_data, label) in enumerate(tqdm(valid_dataloader)):
            output = model(**input_data).logits
            label = label.to(device)
            loss = criterion(output, label)

            loss_value = loss.item()
            val_loss.append(loss_value)

            predicted_labels = torch.argmax(output, dim=-1)
            accuracy = (predicted_labels == label).cpu().numpy().mean() * 100
            val_accuracy.append(accuracy)

        print(np.mean(val_loss))
        print("accuracy:", np.mean(val_accuracy))
        print("=" * 30)

    # save

```
