GPT2 throw error Using pad_token, but it is not set yet

最新推荐文章于 2024-05-25 12:08:34 发布

乐清sss

最新推荐文章于 2024-05-25 12:08:34 发布

阅读量5k

点赞数 5

分类专栏： Pytorch transformers 文章标签：自然语言处理

本文链接：https://blog.csdn.net/sunyueqinghit/article/details/107025600

版权

Pytorch 同时被 2 个专栏收录

9 篇文章 1 订阅

订阅专栏

transformers

2 篇文章 0 订阅

订阅专栏

今天使用GPT2遇到的ERROR，看了一下源码，问题在这：
pytorch_transformers.tokenization_utils

class PreTrainedTokenizer(object):
......

@property
    def pad_token(self):
        """ Padding token (string). Log an error if used while not having been set. """
        if self._pad_token is None:
            logger.error("Using pad_token, but it is not set yet.")
        return self._pad_token

在这里插入图片描述 transformers里有一个issue是这个问题：#2648
这个人是在run_lm_finetuning.py里遇到的，julien-c修改了相关代码push到了分支6b4c3ee
按道理这个问题不应该再出现了，但我是使用AutoModelWithLMHead遇到的，可以看一下GPT2Config：

  {
  "_num_labels": 2,
  "activation_function": "gelu_new",
  "architectures": [
    "GPT2LMHeadModel"
  ],
  "attn_pdrop": 0.1,
  "bos_token_id": 50256,
  "decoder_start_token_id": null,
  "do_sample": false,
  "early_stopping": false,
  "embd_pdrop": 0.1,
  "eos_token_id": 50256,
  "finetuning_task": null,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1"
  },
  "initializer_range": 0.02,
  "is_decoder": false,
  "is_encoder_decoder": false,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1
  },
  "layer_norm_epsilon": 1e-05,
  "length_penalty": 1.0,
  "max_length": 20,
  "min_length": 0,
  "model_type": "gpt2",
  "n_ctx": 1024,
  "n_embd": 768,
  "n_head": 12,
  "n_layer": 12,
  "n_positions": 1024,
  "no_repeat_ngram_size": 0,
  "num_beams": 1,
  "num_return_sequences": 1,
  "output_attentions": false,
  "output_hidden_states": false,
  "output_past": true,
  "pad_token_id": null,
  "prefix": null,
  "pruned_heads": {},
  "repetition_penalty": 1.0,
  "resid_pdrop": 0.1,
  "summary_activation": null,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "task_specific_params": {
    "text-generation": {
      "do_sample": true,
      "max_length": 50
    }
  },
  "temperature": 1.0,
  "top_k": 50,
  "top_p": 1.0,
  "torchscript": false,
  "use_bfloat16": false,
  "vocab_size": 50257
}

问题应该出在：“pad_token_id”: null,
解决方案是在tokenizer初始化后添加一行代码，pad_token可以指定为eos_token或者你想要的其他的符号。

    tokenizer = AutoTokenizer.from_pretrained(model_name)
    
    ### ERROR - transformers.tokenization_utils -   Using pad_token, but it is not set yet.
    tokenizer.pad_token = tokenizer.eos_token

    model = AutoModelWithLMHead.from_pretrained(model_name)