透過訓練進行微調

Python 的 LLM 入門

Jasmin Ludolf

Senior Data Science Content Developer, DataCamp

Training Arguments

from transformers import Trainer, 
TrainingArguments

training_args = TrainingArguments(

  output_dir="./finetuned",

  evaluation_strategy="epoch",

  num_train_epochs=3,

  learning_rate=2e-5,







)
  • TrainingArguments(): 自訂訓練設定
  • 參數請見文件
  • 數值依用途、資料集、速度而定
  • output_dir: 輸出目錄
  • eval_strategy: 何時評估，「epoch」、「steps」或「none」
  • num_train_epochs: 訓練輪數
  • learning_rate: 最佳化器的學習率
Python 的 LLM 入門

Training Arguments

from transformers import Trainer, 
TrainingArguments

training_args = TrainingArguments(
  output_dir="./finetuned",
  evaluation_strategy="epoch",
  num_train_epochs=3,
  learning_rate=2e-5,

  per_device_train_batch_size=8,
  per_device_eval_batch_size=8,

  weight_decay=0.01,

)
  • per_device_train_batch_size 與 per_device_eval_batch_size 設定批次大小
  • weight_decay: 套用於最佳化器以避免過度擬合
Python 的 LLM 入門

Trainer 類別

from transformers import Trainer, 
TrainingArguments

training_args = TrainingArguments(...)

trainer = Trainer(

    model=model,

    args=training_args,

    train_dataset=tokenized_training_data,

    eval_dataset=tokenized_test_data,

    tokenizer=tokenizer

)


trainer.train()
  • model: 要微調的模型
  • args: 訓練參數
  • train_dataset: 用於訓練的資料
  • eval_dataset: 用於評估的資料
  • tokenizer: 標記器

訓練迴圈次數：資料集大小、num_train_epochs、per_device_train_batch_size、per_device_eval_batch_size

Python 的 LLM 入門

Trainer 輸出

{'eval_loss': 0.398524671792984, 'eval_runtime': 33.3145, 'eval_samples_per_second': 46.916, 
'eval_steps_per_second': 5.883, 'epoch': 1.0}
{'eval_loss': 0.1745782047510147, 'eval_runtime': 33.5202, 'eval_samples_per_second': 46.629, 
'eval_steps_per_second': 5.847, 'epoch': 2.0}
{'loss': 0.4272, 'grad_norm': 15.558795928955078, 'learning_rate': 2.993197278911565e-06, 
'epoch': 2.5510204081632653}
{'eval_loss': 0.12216147780418396, 'eval_runtime': 33.2238, 'eval_samples_per_second': 47.045, 
'eval_steps_per_second': 5.899, 'epoch': 3.0}
{'train_runtime': 673.0528, 'train_samples_per_second': 6.967, 'train_steps_per_second': 0.874, 
'train_loss': 0.40028538347101533, 'epoch': 3.0}
TrainOutput(global_step=588, training_loss=0.40028538347101533, metrics={'train_runtime': 673.0528, 
'train_samples_per_second': 6.967, 'train_steps_per_second': 0.874, 
'train_loss': 0.40028538347101533, 'epoch': 3.0})
Python 的 LLM 入門

使用微調後的模型

new_data = ["This is movie was disappointing!", "This is the best movie ever!"]


new_input = tokenizer(new_data, return_tensors="pt", padding=True, truncation=True, max_length=64)


with torch.no_grad():
    outputs = model(**new_input)


predicted_labels = torch.argmax(outputs.logits, dim=1).tolist()

label_map = {0: "NEGATIVE", 1: "POSITIVE"}
for i, predicted_label in enumerate(predicted_labels):
    sentiment = label_map[predicted_label]
    print(f"\nInput Text {i + 1}: {new_data[i]}")
    print(f"Predicted Label: {sentiment}")
Python 的 LLM 入門

微調結果

Input Text 1: This is movie was disappointing!
Predicted Sentiment: NEGATIVE

Input Text 2: This is the best movie ever!
Predicted Sentiment: POSITIVE
Python 的 LLM 入門

儲存模型與 tokenizer

model.save_pretrained("my_finetuned_files")

 

tokenizer.save_pretrained("my_finetuned_files")

 

# Loading a saved model
model = AutoModelForSequenceClassification.from_pretrained("my_finetuned_files")
tokenizer = AutoTokenizer.from_pretrained("my_finetuned_files")
Python 的 LLM 入門

一起來練習吧！

Python 的 LLM 入門

Preparing Video For Download...