Q_UNUSED ( name ) 的用法

通过const char* source_name = obs_source_get_name(source);可以获得吗

代码出现问题：(style_tune) C:\Users\28996\Desktop\AI\persona_contrastive_finetuning>python Contrastive_Training_LM.py INFO:accelerate.utils.modeling:We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). trainable params: 1,572,864 || all params: 1,838,401,536 || trainable%: 0.0856 训练集样本示例: {'anchor_input_ids': [56568, 118919, 116122, 11319], 'positive_input_ids': [116122, 20412, 107340, 9370, 100357, 102323, 3837, 109202, 104078, 103975, 100675, 101940, 100912, 105054, 6313], 'negative_input_ids': [100323, 104307, 99245, 9370, 106059, 104060, 3837, 104530, 115604, 99329, 11319]} 验证集样本示例: {'anchor_input_ids': [56568, 118919, 116122, 11319], 'positive_input_ids': [116122, 20412, 107340, 9370, 100357, 102323, 3837, 109202, 104078, 103975, 100675, 101940, 100912, 105054, 6313], 'negative_input_ids': [100323, 104307, 99245, 9370, 106059, 104060, 3837, 104530, 115604, 99329, 11319]} Trainer.tokenizer is now deprecated. You should use `Trainer.processing_class = processing_class` instead. INFO:__main__:GPU内存使用: 已分配 2.93GB, 保留 4.13GB 可训练参数列表: - base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight - base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight - base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight - base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight - base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight 0%| | 0/3 [00:00<?, ?it/s]You're using a Qwen2TokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding. Trainer.tokenizer is now deprecated. You should use Trainer.processing_class instead. Trainer.tokenizer is now deprecated. You should use Trainer.processing_class instead. INFO:__main__:GPU内存使用: 已分配 4.00GB, 保留 4.21GB Could not estimate the number of tokens of the input, floating-point operations will not be computed Trainer.tokenizer is now deprecated. You should use Trainer.processing_class instead. Trainer.tokenizer is now deprecated. You should use Trainer.processing_class instead. INFO:__main__:GPU内存使用: 已分配 4.02GB, 保留 4.22GB 33%|████████████████████████████ | 1/3 [00:03<00:06, 3.25s/it]Trainer.tokenizer is now deprecated. You should use Trainer.processing_class instead. Trainer.tokenizer is now deprecated. You should use Trainer.processing_class instead. INFO:__main__:GPU内存使用: 已分配 4.01GB, 保留 4.25GB Trainer.tokenizer is now deprecated. You should use Trainer.processing_class instead. Trainer.tokenizer is now deprecated. You should use Trainer.processing_class instead. INFO:__main__:GPU内存使用: 已分配 4.02GB, 保留 4.26GB 67%|████████████████████████████████████████████████████████ | 2/3 [00:06<00:02, 2.98s/it]Trainer.tokenizer is now deprecated. You should use Trainer.processing_class instead. Trainer.tokenizer is now deprecated. You should use Trainer.processing_class instead. INFO:__main__:GPU内存使用: 已分配 4.01GB, 保留 4.25GB Trainer.tokenizer is now deprecated. You should use Trainer.processing_class instead. Trainer.tokenizer is now deprecated. You should use Trainer.processing_class instead. INFO:__main__:GPU内存使用: 已分配 4.02GB, 保留 4.26GB {'train_runtime': 9.034, 'train_samples_per_second': 0.664, 'train_steps_per_second': 0.332, 'train_loss': 1.0772175788879395, 'epoch': 3.0} 100%|████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:09<00:00, 3.01s/it] Traceback (most recent call last): File "C:\Users\28996\Desktop\AI\persona_contrastive_finetuning\Contrastive_Training_LM.py", line 356, in <module> eval_results = trainer.evaluate() File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\transformers\trainer.py", line 4076, in evaluate output = eval_loop( File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\transformers\trainer.py", line 4270, in evaluation_loop losses, logits, labels = self.prediction_step(model, inputs, prediction_loss_only, ignore_keys=ignore_keys) File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\transformers\trainer.py", line 4496, in prediction_step outputs = model(**inputs) File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(*args, **kwargs) File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\accelerate\utils\operations.py", line 818, in forward return model_forward(*args, **kwargs) File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\accelerate\utils\operations.py", line 806, in __call__ return convert_to_fp32(self.model_forward(*args, **kwargs)) File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\torch\amp\autocast_mode.py", line 44, in decorate_autocast return func(*args, **kwargs) File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\peft\peft_model.py", line 1719, in forward return self.base_model( File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(*args, **kwargs) File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\peft\tuners\tuners_utils.py", line 197, in forward return self.model.forward(*args, **kwargs) File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\transformers\models\qwen2\modeling_qwen2.py", line 816, in forward outputs = self.model( File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(*args, **kwargs) File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\transformers\models\qwen2\modeling_qwen2.py", line 521, in forward raise ValueError("You must specify exactly one of input_ids or inputs_embeds") ValueError: You must specify exactly one of input_ids or inputs_embeds (style_tune) C:\Users\28996\Desktop\AI\persona_contrastive_finetuning>python Contrastive_Training_LM.py Traceback (most recent call last): File "C:\Users\28996\Desktop\AI\persona_contrastive_finetuning\Contrastive_Training_LM.py", line 57, in <module> class ContrastiveTrainer(Trainer): File "C:\Users\28996\Desktop\AI\persona_contrastive_finetuning\Contrastive_Training_LM.py", line 63, in ContrastiveTrainer eval_dataset: Optional[Dataset] = None, NameError: name 'Dataset' is not defined 原代码如下：import torch import torch.nn as nn import torch.nn.functional as F from transformers import ( AutoModelForCausalLM, AutoTokenizer, TrainingArguments, Trainer, PreTrainedTokenizerBase, BitsAndBytesConfig ) from transformers.tokenization_utils_base import PreTrainedTokenizerBase from transformers.utils import PaddingStrategy from datasets import load_dataset from typing import Any, Dict, List, Optional, Tuple, Union import logging from dataclasses import dataclass import os import gc from peft import LoraConfig, get_peft_model, prepare_model_for_kbit_training @dataclass class EvalDataCollator: """评估专用的数据收集器""" tokenizer: PreTrainedTokenizerBase padding: Union[bool, str, PaddingStrategy] = True max_length: Optional[int] = None pad_to_multiple_of: Optional[int] = None return_tensors: str = "pt" def __call__(self, features: List[Dict[str, Any]]) -> Dict[str, torch.Tensor]: # 评估时只使用正样本（用于语言建模评估） positive_features = [{"input_ids": f["positive_input_ids"]} for f in features] # 对正样本进行填充 batch_positive = self.tokenizer.pad( positive_features, padding=self.padding, max_length=self.max_length, pad_to_multiple_of=self.pad_to_multiple_of, return_tensors=self.return_tensors, ) # 创建注意力掩码 attention_mask = (batch_positive["input_ids"] != self.tokenizer.pad_token_id).int() # 创建标签（用于语言建模） labels = batch_positive["input_ids"].clone() labels[labels == self.tokenizer.pad_token_id] = -100 return { "input_ids": batch_positive["input_ids"], "attention_mask": attention_mask, "labels": labels } class ContrastiveTrainer(Trainer): """内存优化的训练器""" # ... [保持其他方法不变] ... def evaluate( self, eval_dataset: Optional[Dataset] = None, ignore_keys: Optional[List[str]] = None, metric_key_prefix: str = "eval", ) -> Dict[str, float]: """重写评估方法以使用专用的数据收集器""" # 创建评估专用的数据收集器 eval_data_collator = EvalDataCollator( tokenizer=self.tokenizer, max_length=256, padding="max_length" ) # 临时保存原始数据收集器 original_collator = self.data_collator try: # 使用评估专用的数据收集器 self.data_collator = eval_data_collator # 调用父类的评估方法 return super().evaluate( eval_dataset=eval_dataset, ignore_keys=ignore_keys, metric_key_prefix=metric_key_prefix ) finally: # 恢复原始数据收集器 self.data_collator = original_collator # 设置日志 logging.basicConfig(level=logging.INFO) logger = logging.getLogger(__name__) # 内存优化工具函数 def clear_memory(): """清除Python和CUDA缓存""" gc.collect() if torch.cuda.is_available(): torch.cuda.empty_cache() torch.cuda.reset_peak_memory_stats() def print_memory_usage(): """打印当前内存使用情况""" if torch.cuda.is_available(): allocated = torch.cuda.memory_allocated() / (1024 ** 3) reserved = torch.cuda.memory_reserved() / (1024 ** 3) logger.info(f"GPU内存使用: 已分配 {allocated:.2f}GB, 保留 {reserved:.2f}GB") else: logger.info("未检测到GPU") def tokenize_function(examples, tokenizer, max_length=256): """将文本转换为token IDs""" tokenized = {} # 对每个字段进行分词 for key in ['anchor', 'positive', 'negative']: if key in examples: # 使用分词器处理文本 result = tokenizer( examples[key], max_length=max_length, truncation=True, padding=False, return_tensors=None ) tokenized[f"{key}_input_ids"] = result["input_ids"] return tokenized @dataclass class ContrastiveDataCollator: """内存优化的数据收集器""" tokenizer: PreTrainedTokenizerBase padding: Union[bool, str, PaddingStrategy] = True max_length: Optional[int] = None pad_to_multiple_of: Optional[int] = None return_tensors: str = "pt" def __call__(self, features: List[Dict[str, Any]]) -> Dict[str, torch.Tensor]: # 分离出三元组的各个部分 anchor_features = [{"input_ids": f["anchor_input_ids"]} for f in features] positive_features = [{"input_ids": f["positive_input_ids"]} for f in features] negative_features = [{"input_ids": f["negative_input_ids"]} for f in features] # 对每个部分分别进行填充 batch_anchor = self.tokenizer.pad( anchor_features, padding=self.padding, max_length=self.max_length, pad_to_multiple_of=self.pad_to_multiple_of, return_tensors=self.return_tensors, ) batch_positive = self.tokenizer.pad( positive_features, padding=self.padding, max_length=self.max_length, pad_to_multiple_of=self.pad_to_multiple_of, return_tensors=self.return_tensors, ) batch_negative = self.tokenizer.pad( negative_features, padding=self.padding, max_length=self.max_length, pad_to_multiple_of=self.pad_to_multiple_of, return_tensors=self.return_tensors, ) # 创建注意力掩码 def create_attention_mask(input_ids): return (input_ids != self.tokenizer.pad_token_id).int() # 释放中间变量内存 del anchor_features, positive_features, negative_features clear_memory() return { "anchor_input_ids": batch_anchor["input_ids"], "anchor_attention_mask": create_attention_mask(batch_anchor["input_ids"]), "positive_input_ids": batch_positive["input_ids"], "positive_attention_mask": create_attention_mask(batch_positive["input_ids"]), "negative_input_ids": batch_negative["input_ids"], "negative_attention_mask": create_attention_mask(batch_negative["input_ids"]), } class ContrastiveTrainer(Trainer): """内存优化的训练器""" def __init__(self, tokenizer=None, *args, contrastive_config=None, **kwargs): # 首先调用父类初始化 super().__init__(*args, **kwargs) # 关键修复：设置tokenizer self.tokenizer = tokenizer if contrastive_config is None: contrastive_config = {} # 设置默认值 self.temperature = contrastive_config.get("temperature", 0.07) self.margin = contrastive_config.get("margin", 0.3) self.contrastive_weight = contrastive_config.get("weight", 0.8) self.repr_layer = contrastive_config.get("repr_layer", -1) # 验证必要参数 if not hasattr(self.model.config, "output_hidden_states") or not self.model.config.output_hidden_states: raise ValueError("模型必须设置output_hidden_states=True") self.cross_entropy = nn.CrossEntropyLoss() def compute_contrastive_loss(self, anchor_emb, pos_emb, neg_emb): """计算对比损失""" # 计算余弦相似度 pos_sim = F.cosine_similarity(anchor_emb, pos_emb) neg_sim = F.cosine_similarity(anchor_emb, neg_emb) # 计算InfoNCE损失 numerator = torch.exp(pos_sim / self.temperature) denominator = numerator + torch.exp(neg_sim / self.temperature) info_nce_loss = -torch.log(numerator / (denominator + 1e-8)).mean() # 计算三元组损失 triplet_loss = F.relu(neg_sim - pos_sim + self.margin).mean() return info_nce_loss + triplet_loss def get_sequence_representation(self, outputs, attention_mask): """获取序列表示（内存优化版）""" # 只获取需要的隐藏状态层 hidden_states = outputs.hidden_states[self.repr_layer] # 获取每个序列的最后一个非填充token seq_lengths = attention_mask.sum(dim=1) - 1 batch_indices = torch.arange(hidden_states.size(0)) # 返回对应位置的隐藏状态 return hidden_states[batch_indices, seq_lengths] def compute_loss(self, model, inputs, return_outputs=False): """内存优化的损失计算""" # 确保模型处于训练模式 model.train() # 提取输入 anchor_ids = inputs["anchor_input_ids"] anchor_mask = inputs["anchor_attention_mask"] positive_ids = inputs["positive_input_ids"] positive_mask = inputs["positive_attention_mask"] negative_ids = inputs["negative_input_ids"] negative_mask = inputs["negative_attention_mask"] # 前向传播获取隐藏状态 def get_embeddings(input_ids, attention_mask): outputs = model( input_ids=input_ids, attention_mask=attention_mask, output_hidden_states=True, return_dict=True ) return self.get_sequence_representation(outputs, attention_mask) # 获取三元组的嵌入表示 anchor_emb = get_embeddings(anchor_ids, anchor_mask) pos_emb = get_embeddings(positive_ids, positive_mask) neg_emb = get_embeddings(negative_ids, negative_mask) # 计算对比损失 cl_loss = self.compute_contrastive_loss(anchor_emb, pos_emb, neg_emb) cl_loss = cl_loss * self.contrastive_weight # 关键修复：确保tokenizer已设置 if self.tokenizer is None: raise ValueError("Tokenizer未设置！") # 计算语言建模损失 lm_labels = positive_ids.clone() # 关键修复：使用tokenizer的pad_token_id pad_token_id = self.tokenizer.pad_token_id lm_labels[lm_labels == pad_token_id] = -100 # 计算语言建模损失 lm_outputs = model( input_ids=positive_ids, attention_mask=positive_mask, labels=lm_labels ) lm_loss = lm_outputs.loss # 总损失 = LM损失 + 对比损失 total_loss = lm_loss + cl_loss # 记录内存使用 print_memory_usage() return (total_loss, lm_outputs) if return_outputs else total_loss # ================ 主程序 ================ # if __name__ == "__main__": # 配置量化以减少内存使用 bnb_config = BitsAndBytesConfig( load_in_4bit=True, # 使用4位量化 bnb_4bit_quant_type="nf4", # 使用NF4量化类型 bnb_4bit_use_double_quant=True, # 双重量化 bnb_4bit_compute_dtype=torch.float16 # 计算使用FP16 ) # 加载模型和分词器（使用量化） model = AutoModelForCausalLM.from_pretrained( "model/Qwen/Qwen1.5-1.8B", quantization_config=bnb_config, # 应用量化配置 device_map="auto", # 自动选择设备 output_hidden_states=True, # 必须设置以获取隐藏状态 return_dict_in_generate=True, use_cache=False # 禁用缓存以节省内存 ) tokenizer = AutoTokenizer.from_pretrained("model/Qwen/Qwen1.5-1.8B") tokenizer.pad_token = tokenizer.eos_token # 设置填充token # 为量化模型添加LoRA适配器 lora_config = LoraConfig( r=8, lora_alpha=32, target_modules=["q_proj", "v_proj"], # 针对Qwen1.5-1.8B模型 lora_dropout=0.05, bias="none", task_type="CAUSAL_LM" ) # 关键修复：准备模型用于k位训练 model = prepare_model_for_kbit_training(model, use_gradient_checkpointing=True) # 添加LoRA适配器 model = get_peft_model(model, lora_config) # 关键修复：显式启用LoRA参数的梯度 for param in model.parameters(): if param.requires_grad: param.requires_grad = True model.print_trainable_parameters() # 打印可训练参数数量 # 加载数据集 def load_and_tokenize_dataset(file_path, tokenizer): """加载数据集并进行分词处理""" # 加载原始数据集 dataset_dict = load_dataset('json', data_files=file_path) raw_dataset = dataset_dict['train'] # 应用分词函数 tokenized_dataset = raw_dataset.map( lambda ex: tokenize_function(ex, tokenizer, max_length=256), batched=True, batch_size=8, # 减小批处理大小 remove_columns=['anchor', 'positive', 'negative'] ) return tokenized_dataset train_dataset = load_and_tokenize_dataset('data/processed/train_style_triplets.json', tokenizer) val_dataset = load_and_tokenize_dataset('data/processed/val_style_triplets.json', tokenizer) # 验证数据集格式 print("训练集样本示例:", train_dataset[0]) print("验证集样本示例:", val_dataset[0]) # 训练参数配置（内存优化） training_args = TrainingArguments( output_dir="./model/lora_adapter", per_device_train_batch_size=1, # 减小批量大小 gradient_accumulation_steps=8, # 增加梯度累积步数 num_train_epochs=3, learning_rate=2e-4, logging_steps=10, # 更频繁的日志记录以监控内存 save_steps=500, fp16=True, report_to="none", remove_unused_columns=False, gradient_checkpointing=True, # 启用梯度检查点 optim="adafactor", # 使用内存更少的优化器 ) # 对比学习配置 contrastive_config = { "temperature": 0.07, "margin": 0.3, "weight": 0.8, "repr_layer": -1 } # 初始化数据收集器 data_collator = ContrastiveDataCollator( tokenizer=tokenizer, max_length=256, # 减少最大长度 padding="max_length" ) # 初始化训练器 - 关键修复：传递tokenizer trainer = ContrastiveTrainer( model=model, args=training_args, tokenizer=tokenizer, # 传递tokenizer data_collator=data_collator, train_dataset=train_dataset, eval_dataset=val_dataset, contrastive_config=contrastive_config ) # 开始训练前打印内存状态 print_memory_usage() # 关键修复：验证可训练参数 print("可训练参数列表:") for name, param in model.named_parameters(): if param.requires_grad: print(f"- {name}") # 开始训练 trainer.train() # 保存LoRA适配器 model.save_pretrained("./model/lora_adapter") # 评估模型 try: eval_results = trainer.evaluate() print("评估结果:", eval_results) except Exception as e: print(f"评估过程中发生错误: {e}") import traceback traceback.print_exc()