按要求创建了文件夹，但是不知道tmd到底是什么文件在这个文件夹里面

my-bert-model/config.json

@@ -0,0 +1,23 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

my-bert-model/modeling_bert.py

@@ -0,0 +1,95 @@
+from typing import List, Optional, Tuple, Union
+import torch
+import torch.utils.checkpoint
+from torch import nn
+from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
+from transformers import BertPreTrainedModel, BertModel
+from transformers.modeling_outputs import SequenceClassifierOutput
+
+
+class BertForSequenceClassification(BertPreTrainedModel):
+    def __init__(self, config):
+        super().__init__(config)
+        self.num_labels = config.num_labels
+        self.config = config
+
+        self.bert = BertModel(config)
+        classifier_dropout = (
+            config.classifier_dropout if config.classifier_dropout is not None else config.hidden_dropout_prob
+        )
+        self.dropout = nn.Dropout(classifier_dropout)
+        self.classifier = nn.Linear(config.hidden_size, config.num_labels)
+
+        # Initialize weights and apply final processing
+        self.post_init()
+
+    def forward(
+        self,
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple[torch.Tensor], SequenceClassifierOutput]:
+        r"""
+        labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
+            Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
+            config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
+            `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
+        """
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+        outputs = self.bert(
+            input_ids,
+            attention_mask=attention_mask,
+            token_type_ids=token_type_ids,
+            position_ids=position_ids,
+            head_mask=head_mask,
+            inputs_embeds=inputs_embeds,
+            output_attentions=output_attentions,
+            output_hidden_states=output_hidden_states,
+            return_dict=return_dict,
+        )
+
+        pooled_output = outputs[1]
+
+        pooled_output = self.dropout(pooled_output)
+        logits = self.classifier(pooled_output)
+
+        loss = None
+        if labels is not None:
+            if self.config.problem_type is None:
+                if self.num_labels == 1:
+                    self.config.problem_type = "regression"
+                elif self.num_labels > 1 and (labels.dtype == torch.long or labels.dtype == torch.int):
+                    self.config.problem_type = "single_label_classification"
+                else:
+                    self.config.problem_type = "multi_label_classification"
+
+            if self.config.problem_type == "regression":
+                loss_fct = MSELoss()
+                if self.num_labels == 1:
+                    loss = loss_fct(logits.squeeze(), labels.squeeze())
+                else:
+                    loss = loss_fct(logits, labels)
+            elif self.config.problem_type == "single_label_classification":
+                loss_fct = CrossEntropyLoss()
+                loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
+            elif self.config.problem_type == "multi_label_classification":
+                loss_fct = BCEWithLogitsLoss()
+                loss = loss_fct(logits, labels)
+        if not return_dict:
+            output = (logits,) + outputs[2:]
+            return ((loss,) + output) if loss is not None else output
+
+        return SequenceClassifierOutput(
+            loss=loss,
+            logits=logits,
+            hidden_states=outputs.hidden_states,
+            attentions=outputs.attentions,
+        )

my-bert-model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097417381d6c7230bd9e3557456d726de6e83245ec8b24f529f60198a67b203a
+size 440473133

my-bert-model/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "model_max_length": 512}

my-bert-model/utils_data.py

@@ -0,0 +1,45 @@
+from torch.utils.data import Dataset
+import torch
+import pandas as pd
+
+def load_data(args, split):
+    df = pd.read_csv(f"{args.data_root}/{split}.csv")
+    texts = df['text'].values.tolist()
+    labels = df['target'].values.tolist()
+    return texts, labels
+
+class MyDataset(Dataset):
+    def __init__(self, data, tokenizer, max_length, is_test):
+        self.tokenizer = tokenizer
+        self.max_length = max_length
+        self.texts = data[0]
+        self.labels = data[1]
+        self.is_test = is_test
+            
+    def __len__(self):
+        """returns the length of dataframe"""
+        return len(self.texts)
+
+    def __getitem__(self, index):
+        """return the input ids, attention masks and target ids"""
+        text = str(self.texts[index])
+        source = self.tokenizer.batch_encode_plus(
+            [text],
+            max_length=self.max_length,
+            pad_to_max_length=True,
+            truncation=True,
+            padding="max_length",
+            return_tensors="pt",
+        )
+        source_ids = source["input_ids"].squeeze()
+        source_mask = source["attention_mask"].squeeze()
+        data_sample = {
+            "input_ids": source_ids,
+            "attention_mask": source_mask,
+        }
+        if not self.is_test:
+            label = self.labels[index]
+            target_ids = torch.tensor(label).squeeze()
+            data_sample["labels"] = target_ids 
+        return data_sample
+