python - AllenNLP 中可分解注意力模型的微调问题

Question

我在微调 decomposable-attention-elmo 模型时遇到问题。我已经能够下载模型:wget https://s3-us-west-2.amazonaws.com/allennlp/models/decomposable-attention-elmo-2018.02.19.tar.gz 。我正在尝试加载模型，然后使用 AllenNLP 训练命令行命令根据我的数据对其进行微调。

我还创建了一个与 SNLIDatasetReader 类似的自定义数据集读取器，并且似乎运行良好。

我创建了一个 .jsonnet 文件，类似于 here ，但我无法使其正常工作。

当我使用这个版本时:

// Configuraiton for a textual entailment model based on:
//  Parikh, Ankur P. et al. “A Decomposable Attention Model for Natural Language Inference.” EMNLP (2016).
{
  "dataset_reader": {
    "type": "custom_reader",
    "token_indexers": {
      "elmo": {
        "type": "elmo_characters"
      }
    },
    "tokenizer": {
      "end_tokens": ["@@NULL@@"]
    }
  },
  "train_data_path": "examples_train_",
  "validation_data_path": "examples_val_",
  "model": {
    "type": "from_archive",
    "archive_file": "decomposable-attention-elmo-2018.02.19.tar.gz",
    "text_field_embedder": {
      "token_embedders": {
        "elmo": {
            "type": "elmo_token_embedder",
            "do_layer_norm": false,
            "dropout": 0.2
        }
      }
    },
   },
  "data_loader": {
    "batch_sampler": {
      "type": "bucket",
      "batch_size": 64
    }
  },
  "trainer": {
    "num_epochs": 140,
    "patience": 20,
    "grad_clipping": 5.0,
    "validation_metric": "+accuracy",
    "optimizer": {
      "type": "adagrad"
    }
  }
}

我收到错误:

 File "lib/python3.6/site-packages/allennlp/common/params.py", line 423, in assert_empty
    "Extra parameters passed to {}: {}".format(class_name, self.params)
allennlp.common.checks.ConfigurationError: Extra parameters passed to Model: {'text_field_embedder': {'token_embedders': {'elmo': {'do_layer_norm': False, 'dropout': 0.2, 'type': 'elmo_token_embedder'}}}}

然后，当我取出 text_field_embedder 部分并使用此版本时:

// Configuraiton for a textual entailment model based on:
//  Parikh, Ankur P. et al. “A Decomposable Attention Model for Natural Language Inference.” EMNLP (2016).
{
  "dataset_reader": {
    "type": "fake_news",
    "token_indexers": {
      "elmo": {
        "type": "elmo_characters"
      }
    },
    "tokenizer": {
      "end_tokens": ["@@NULL@@"]
    }
  },
  "train_data_path": "examples_train_",
  "validation_data_path": "examples_val_",
  "model": {
    "type": "from_archive",
    "archive_file": "decomposable-attention-elmo-2018.02.19.tar.gz",
   },
  "data_loader": {
    "batch_sampler": {
      "type": "bucket",
      "batch_size": 64
    }
  },
  "trainer": {
    "num_epochs": 140,
    "patience": 20,
    "grad_clipping": 5.0,
    "validation_metric": "+accuracy",
    "optimizer": {
      "type": "adagrad"
    }
  }
}

我收到错误:

    raise ConfigurationError(msg)
allennlp.common.checks.ConfigurationError: key "token_embedders" is required at location "model.text_field_embedder."

这两个错误似乎是矛盾的，我不知道如何进行这种微调。

Answer 1

我们在 GitHub 上发现问题出在 @hockeybro 正在加载的模型的旧版本上。目前最新版本为https://storage.googleapis.com/allennlp-public-models/decomposable-attention-elmo-2020.04.09.tar.gz .