Upload train.py

train.py

@@ -0,0 +1,90 @@
+import os
+
+os.environ["HF_HOME"] = "/home/jovyan/work/learn-ml/huggingface"
+
+import torch
+from torch.utils.data import DataLoader
+
+from transformers import AdamW, AutoTokenizer, AutoModelForSequenceClassification, DataCollatorWithPadding, get_scheduler
+from datasets import load_dataset, load_metric
+from accelerate import Accelerator
+
+from tqdm.auto import tqdm
+
+
+
+checkpoint = 'bert-base-uncased'
+tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+model = AutoModelForSequenceClassification.from_pretrained(checkpoint, num_labels=2)
+
+
+raw_datasets = load_dataset("glue", "mrpc")
+
+
+
+def tokenize_function(example):
+    return tokenizer(example["sentence1"], example["sentence2"], truncation=True)
+
+tokenized_dataset = raw_datasets.map(tokenize_function, batched=True)
+
+
+data_collator = DataCollatorWithPadding(tokenizer=tokenizer)
+
+
+samples = tokenized_dataset["train"][:8]
+samples = {k: v for k,v in samples.items() if k not in ["idx", "sentence1", "sentence2"]}
+print([len(x) for x in samples["input_ids"]])
+
+
+tokenized_dataset = tokenized_dataset.remove_columns(["sentence1","sentence2","idx"])
+tokenized_dataset = tokenized_dataset.rename_column("label", "labels")
+tokenized_dataset.set_format("torch")
+tokenized_dataset.column_names["train"]
+
+
+train_dataloader = DataLoader(
+    tokenized_dataset["train"], shuffle=True, batch_size=8, collate_fn=data_collator,
+)
+
+eval_dataloader = DataLoader(
+    tokenized_dataset["validation"], batch_size=8, collate_fn=data_collator,
+)
+
+
+
+accelerator = Accelerator()
+
+model = AutoModelForSequenceClassification.from_pretrained(checkpoint, num_labels=2)
+
+optimizer = AdamW(model.parameters(), lr=3e-5)
+
+
+train_dataloader, eval_dataloader, model, optimizer = accelerator.prepare(train_dataloader, eval_dataloader, model, optimizer)
+
+num_epochs = 3
+num_training_steps = num_epochs * len(train_dataloader)
+lr_scheduler = get_scheduler(
+    "linear",
+    optimizer=optimizer,
+    num_warmup_steps=0,
+    num_training_steps=num_training_steps,
+)
+
+print(num_training_steps)
+
+
+progress_bar = tqdm(range(num_training_steps))
+
+
+model.train()
+
+for epoch in range(num_epochs):
+    for batch in train_dataloader:
+        outputs = model(**batch)
+        loss = outputs.loss
+        accelerator.backward(loss)
+        
+        optimizer.step()
+        lr_scheduler.step()
+        optimizer.zero_grad()
+        progress_bar.update(1)