End of training

README.md

@@ -0,0 +1,54 @@
+---
+license: apache-2.0
+base_model: google-bert/bert-base-uncased
+tags:
+- generated_from_trainer
+model-index:
+- name: Bert_base_NER_PII65k
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/tuevu_smu/huggingface/runs/mjqe8h9n)
+# Bert_base_NER_PII65k
+
+This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.0.dev0
+- Pytorch 1.13.1
+- Datasets 2.18.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,98 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ACCOUNTNAME",
+    "1": "ACCOUNTNUMBER",
+    "2": "COINADDRESS",
+    "3": "COMPANY_NAME",
+    "4": "CREDITCARDISSUER",
+    "5": "CREDITCARDNUMBER",
+    "6": "CURRENCY",
+    "7": "DATE",
+    "8": "EMAIL",
+    "9": "GENDER",
+    "10": "GEO",
+    "11": "IBAN",
+    "12": "PASSWORD",
+    "13": "PHONEIMEI",
+    "14": "PHONE_NUMBER",
+    "15": "PREFIX",
+    "16": "SSN",
+    "17": "STREET",
+    "18": "SUFFIX",
+    "19": "USERAGENT",
+    "20": "USERNAME",
+    "21": "VEHICLEVIN",
+    "22": "VEHICLEVRM",
+    "23": "ZIPCODE",
+    "24": "ADDRESS",
+    "25": "BIC",
+    "26": "IP",
+    "27": "JOB",
+    "28": "MAC",
+    "29": "NAME",
+    "30": "NUM",
+    "31": "TIME",
+    "32": "URL",
+    "33": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ACCOUNTNAME": 0,
+    "ACCOUNTNUMBER": 1,
+    "ADDRESS": 24,
+    "BIC": 25,
+    "COINADDRESS": 2,
+    "COMPANY_NAME": 3,
+    "CREDITCARDISSUER": 4,
+    "CREDITCARDNUMBER": 5,
+    "CURRENCY": 6,
+    "DATE": 7,
+    "EMAIL": 8,
+    "GENDER": 9,
+    "GEO": 10,
+    "IBAN": 11,
+    "IP": 26,
+    "JOB": 27,
+    "MAC": 28,
+    "NAME": 29,
+    "NUM": 30,
+    "O": 33,
+    "PASSWORD": 12,
+    "PHONEIMEI": 13,
+    "PHONE_NUMBER": 14,
+    "PREFIX": 15,
+    "SSN": 16,
+    "STREET": 17,
+    "SUFFIX": 18,
+    "TIME": 31,
+    "URL": 32,
+    "USERAGENT": 19,
+    "USERNAME": 20,
+    "VEHICLEVIN": 21,
+    "VEHICLEVRM": 22,
+    "ZIPCODE": 23
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9901771cb09115e7c792b8930ef13e235934c4c698a3b0e2340e7c7b474dab23
+size 435694520

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e41e4ea4111114257b57c4e2d553c7fb60539cd5b756a7997f245502896de90
+size 4603