Train 10k + CRF for open-pii-masking-500k-ai4privacy-augmented. F1: 0.9417

open-pii-masking-500k-ai4privacy-augmented/TokenBased-BERT/config.json

@@ -0,0 +1,112 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-AGE",
+    "1": "B-BUILDINGNUM",
+    "2": "B-CITY",
+    "3": "B-CREDITCARDNUMBER",
+    "4": "B-DATE",
+    "5": "B-DRIVERLICENSENUM",
+    "6": "B-EMAIL",
+    "7": "B-GENDER",
+    "8": "B-GIVENNAME",
+    "9": "B-IDCARDNUM",
+    "10": "B-PASSPORTNUM",
+    "11": "B-SOCIALNUM",
+    "12": "B-STREET",
+    "13": "B-SURNAME",
+    "14": "B-TAXNUM",
+    "15": "B-TELEPHONENUM",
+    "16": "B-TIME",
+    "17": "B-TITLE",
+    "18": "B-ZIPCODE",
+    "19": "I-AGE",
+    "20": "I-BUILDINGNUM",
+    "21": "I-CITY",
+    "22": "I-CREDITCARDNUMBER",
+    "23": "I-DATE",
+    "24": "I-DRIVERLICENSENUM",
+    "25": "I-EMAIL",
+    "26": "I-GENDER",
+    "27": "I-GIVENNAME",
+    "28": "I-IDCARDNUM",
+    "29": "I-PASSPORTNUM",
+    "30": "I-SOCIALNUM",
+    "31": "I-STREET",
+    "32": "I-SURNAME",
+    "33": "I-TAXNUM",
+    "34": "I-TELEPHONENUM",
+    "35": "I-TIME",
+    "36": "I-TITLE",
+    "37": "I-ZIPCODE",
+    "38": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-AGE": 0,
+    "B-BUILDINGNUM": 1,
+    "B-CITY": 2,
+    "B-CREDITCARDNUMBER": 3,
+    "B-DATE": 4,
+    "B-DRIVERLICENSENUM": 5,
+    "B-EMAIL": 6,
+    "B-GENDER": 7,
+    "B-GIVENNAME": 8,
+    "B-IDCARDNUM": 9,
+    "B-PASSPORTNUM": 10,
+    "B-SOCIALNUM": 11,
+    "B-STREET": 12,
+    "B-SURNAME": 13,
+    "B-TAXNUM": 14,
+    "B-TELEPHONENUM": 15,
+    "B-TIME": 16,
+    "B-TITLE": 17,
+    "B-ZIPCODE": 18,
+    "I-AGE": 19,
+    "I-BUILDINGNUM": 20,
+    "I-CITY": 21,
+    "I-CREDITCARDNUMBER": 22,
+    "I-DATE": 23,
+    "I-DRIVERLICENSENUM": 24,
+    "I-EMAIL": 25,
+    "I-GENDER": 26,
+    "I-GIVENNAME": 27,
+    "I-IDCARDNUM": 28,
+    "I-PASSPORTNUM": 29,
+    "I-SOCIALNUM": 30,
+    "I-STREET": 31,
+    "I-SURNAME": 32,
+    "I-TAXNUM": 33,
+    "I-TELEPHONENUM": 34,
+    "I-TIME": 35,
+    "I-TITLE": 36,
+    "I-ZIPCODE": 37,
+    "O": 38
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.56.0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 119547
+}

open-pii-masking-500k-ai4privacy-augmented/TokenBased-BERT/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9d518aa442e27d3eb0faf689de53928c6d81d7896014ce62c39c8d514a30c30
+size 711563936

open-pii-masking-500k-ai4privacy-augmented/TokenBased-BERT/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

open-pii-masking-500k-ai4privacy-augmented/TokenBased-BERT/tokenizer_config.json

@@ -0,0 +1,66 @@
+{
+  "add_prefix_space": true,
+  "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
+    }
+  },
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

open-pii-masking-500k-ai4privacy-augmented/TokenBased-BERT/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce667b56c9b23318734eb66d18bf9e457eb057539597ad8fc434e79b6d0b1001
+size 5841