End of training

README.md

@@ -0,0 +1,53 @@
+---
+license: apache-2.0
+base_model: google-bert/bert-large-uncased
+tags:
+- generated_from_trainer
+model-index:
+- name: Bert_large_NER_PII_062024
+  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. -->
+
+# Bert_large_NER_PII_062024
+
+This model is a fine-tuned version of [google-bert/bert-large-uncased](https://huggingface.co/google-bert/bert-large-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: 5
+
+### 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 +1,114 @@
+{
+  "_name_or_path": "google-bert/bert-large-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": 1024,
+  "id2label": {
+    "0": "ACCOUNTNAME",
+    "1": "ACCOUNTNUMBER",
+    "2": "COINADDRESS",
+    "3": "ADDRESS",
+    "4": "AGE",
+    "5": "BIC",
+    "6": "CREDITCARDISSUER",
+    "7": "CREDITCARDNUMBER",
+    "8": "CURRENCY",
+    "9": "DATE",
+    "10": "EMAIL",
+    "11": "COLOR",
+    "12": "GENDER",
+    "13": "GEO",
+    "14": "HEIGHT",
+    "15": "JOB",
+    "16": "MAC",
+    "17": "MISC",
+    "18": "USERNAME",
+    "19": "NAME",
+    "20": "NEARBYGPSCOORDINATE",
+    "21": "ORDINALDIRECTION",
+    "22": "ORG",
+    "23": "PASSWORD",
+    "24": "PHONEIMEI",
+    "25": "PHONENUMBER",
+    "26": "PREFIX",
+    "27": "SSN",
+    "28": "STREET",
+    "29": "TIME",
+    "30": "URL",
+    "31": "VEHICLEVIN",
+    "32": "VEHICLEVRM",
+    "33": "ZIPCODE",
+    "34": "IP",
+    "35": "NUM",
+    "36": "BLOODTYPE",
+    "37": "WEIGHTS",
+    "38": "DOB",
+    "39": "GPE",
+    "40": "IBAN",
+    "41": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "ACCOUNTNAME": 0,
+    "ACCOUNTNUMBER": 1,
+    "ADDRESS": 3,
+    "AGE": 4,
+    "BIC": 5,
+    "BLOODTYPE": 36,
+    "COINADDRESS": 2,
+    "COLOR": 11,
+    "CREDITCARDISSUER": 6,
+    "CREDITCARDNUMBER": 7,
+    "CURRENCY": 8,
+    "DATE": 9,
+    "DOB": 38,
+    "EMAIL": 10,
+    "GENDER": 12,
+    "GEO": 13,
+    "GPE": 39,
+    "HEIGHT": 14,
+    "IBAN": 40,
+    "IP": 34,
+    "JOB": 15,
+    "MAC": 16,
+    "MISC": 17,
+    "NAME": 19,
+    "NEARBYGPSCOORDINATE": 20,
+    "NUM": 35,
+    "O": 41,
+    "ORDINALDIRECTION": 21,
+    "ORG": 22,
+    "PASSWORD": 23,
+    "PHONEIMEI": 24,
+    "PHONENUMBER": 25,
+    "PREFIX": 26,
+    "SSN": 27,
+    "STREET": 28,
+    "TIME": 29,
+    "URL": 30,
+    "USERNAME": 18,
+    "VEHICLEVIN": 31,
+    "VEHICLEVRM": 32,
+    "WEIGHTS": 37,
+    "ZIPCODE": 33
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "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 sha256:5350ea3dcec13bb4b2163cac153fcedc4b6f10d01d75f22408980064c7af96e1
+size 1336588168

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 sha256:11496af66bcfec9c19cea824d5210001e0a372f8b32a02a027566ea79be08ff4
+size 4603