使用“sst2”数据集进行“情感分析”（分类）

Question

我正在尝试使用 Huggingface 库微调“distilbert-base-uncased”模型，但我遇到了此错误：

IndexError: Target -1 is out of bounds.

使用 Huggingface 数据集加载我的数据集（sst2）并对其进行标记后：

small_train_dataset = encoded_dataset["train"].shuffle(seed=42).select(range(1000))
small_eval_dataset = encoded_dataset["test"].shuffle(seed=42).select(range(1000))
full_train_dataset = encoded_dataset["train"]
full_eval_dataset = encoded_dataset["test"]

# Define the training parameters

metric_name = "accuracy"
model_name = model_checkpoint.split("/")[-1]
weight_decay = 0.01
lr = 2e-5
batch_size = 16
num_train_epochs = 5

import numpy as np

# Define a function to evaluate the model

def compute_metrics(eval_pred):
    logits, labels = eval_pred
    predictions = np.argmax(logits, axis=-1)
    return metric.compute(predictions=predictions, references=labels)

# Fine-tune the model

args = TrainingArguments(
    f"{model_name}-finetuned-{task}",
    evaluation_strategy = "steps",             
    eval_steps=10,
    save_strategy = "steps",                   
    learning_rate = lr,                   
    per_device_train_batch_size = batch_size,     
    per_device_eval_batch_size = batch_size,      
    num_train_epochs = num_train_epochs,                
    weight_decay = weight_decay,                    
    load_best_model_at_end = True,          
    metric_for_best_model = metric_name,          
    push_to_hub = False,                    
)

trainer = Trainer(
    model=model,
    args=args,
    train_dataset = small_train_dataset,           
    eval_dataset = small_eval_dataset,            
    tokenizer = tokenizer,               
    compute_metrics = compute_metrics         
)

trainer.train()

我尝试更改指标，但没有帮助。

Answer 1

问题出在数据集上，我使用encoded_dataset[“test”]进行验证，与它的名称不同，它由无监督数据组成，所有数据都带有标签-1。将其更改为encoded_dataset[“validation”]后问题得到解决。