Update app.py

app.py

@@ -20,115 +20,6 @@ optimizer = AdamW(model.parameters(), lr=1e-5)
 
 global_data = None
 
-def load_data(file):
-    global global_data
-    df = pd.read_csv(file)
-    inputs = tokenizer(df['text'].tolist(), padding=True, truncation=True, return_tensors="pt")  # Mã hóa văn bản
-    labels = torch.tensor(df['label'].tolist()).long()  # Đảm bảo tên cột là 'label'
-    global_data = TensorDataset(inputs['input_ids'], inputs['attention_mask'], labels)
-
-    print(global_data)
-
-def get_dataloader(start, end, batch_size=8):
-    global global_data
-    subset = torch.utils.data.Subset(global_data, range(start, end))
-    return DataLoader(subset, batch_size=batch_size)
-
-@spaces.GPU(duration=20)
-def train_batch(dataloader):
-    model.train()
-    start_time = time.time()
-
-    for step, batch in enumerate(dataloader):
-        input_ids, attention_mask, labels = batch
-        input_ids, attention_mask, labels = input_ids.to(device), attention_mask.to(device), labels.to(device)
-
-        optimizer.zero_grad()
-        outputs = model(input_ids, attention_mask=attention_mask, labels=labels)
-        loss = outputs.loss
-        loss.backward()
-        optimizer.step()
-
-        elapsed_time = time.time() - start_time
-        if elapsed_time > 10: 
-            print('Save checkpoint')
-            if not os.path.exists('./checkpoint'):
-                os.makedirs('./checkpoint')
-            torch.save(model.state_dict(), "./checkpoint/model.pt")
-            
-            return False, "Checkpoint saved. Training paused."
-
-    return True, "Batch training completed."
-
-Hugging Face's logo
-Hugging Face
-Search models, datasets, users...
-Models
-Datasets
-Spaces
-Posts
-Docs
-Solutions
-Pricing
-
-
-
-Hugging Face is way more fun with friends and colleagues! 🤗 Join an organization
-Spaces:
-
-ShynBui
-/
-train_for_fun
-
-private
-
-Logs
-App
-Files
-Community
-Settings
-train_for_fun
-/
-app.py
-
-ShynBui's picture
-ShynBui
-Update app.py
-07a2715
-verified
-15 minutes ago
-raw
-
-Copy download link
-history
-blame
-edit
-delete
-No virus
-
-3.25 kB
-import time
-import torch
-from transformers import BertForSequenceClassification, AdamW
-from torch.utils.data import DataLoader, TensorDataset
-from transformers import BertTokenizer
-import gradio as gr
-import pandas as pd
-import os
-import spaces
-from spaces.zero.gradio import HTMLError
-
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-print(device)
-
-model = BertForSequenceClassification.from_pretrained('bert-base-uncased')
-tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
-model.to(device)
-
-optimizer = AdamW(model.parameters(), lr=1e-5)
-
-global_data = None
-
 def load_data(file):
     global global_data
     df = pd.read_csv(file)