Train 10k + CRF for financial-pii-ready-augmented. F1: 1.0000

financial-pii-ready-augmented/TokenBased-BERT/config.json

@@ -0,0 +1,68 @@
+{
+  "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-ADDRESS",
+    "1": "B-COMPANY",
+    "2": "B-CREDIT_CARD",
+    "3": "B-EMAIL",
+    "4": "B-NAME",
+    "5": "B-PHONE",
+    "6": "B-SSN/CCCD",
+    "7": "B-URL",
+    "8": "I-ADDRESS",
+    "9": "I-COMPANY",
+    "10": "I-CREDIT_CARD",
+    "11": "I-EMAIL",
+    "12": "I-NAME",
+    "13": "I-PHONE",
+    "14": "I-SSN/CCCD",
+    "15": "I-URL",
+    "16": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ADDRESS": 0,
+    "B-COMPANY": 1,
+    "B-CREDIT_CARD": 2,
+    "B-EMAIL": 3,
+    "B-NAME": 4,
+    "B-PHONE": 5,
+    "B-SSN/CCCD": 6,
+    "B-URL": 7,
+    "I-ADDRESS": 8,
+    "I-COMPANY": 9,
+    "I-CREDIT_CARD": 10,
+    "I-EMAIL": 11,
+    "I-NAME": 12,
+    "I-PHONE": 13,
+    "I-SSN/CCCD": 14,
+    "I-URL": 15,
+    "O": 16
+  },
+  "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
+}

financial-pii-ready-augmented/TokenBased-BERT/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60a7f06c2be407ecf4b58db5d6c0a803098b401d2c76edfe47d6e4d3aab3b327
+size 711491160

financial-pii-ready-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
+  }
+}

financial-pii-ready-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]"
+}

financial-pii-ready-augmented/TokenBased-BERT/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6fb71ffd9fc5e758c4dc68deaf5f26da5220baae99ae91d7494cafa9c233790
+size 5777