Training in progress, step 256

config.json

@@ -0,0 +1,103 @@
+{
+  "architectures": [
+    "ElectraForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "B-CREDITCARDNUMBER",
+    "1": "B-CITY",
+    "2": "B-DRIVERLICENSENUM",
+    "3": "B-TAXNUM",
+    "4": "I-USERNAME",
+    "5": "B-BUILDINGNUM",
+    "6": "B-ACCOUNTNUM",
+    "7": "I-PASSWORD",
+    "8": "B-SOCIALNUM",
+    "9": "I-CREDITCARDNUMBER",
+    "10": "B-EMAIL",
+    "11": "I-CITY",
+    "12": "I-STREET",
+    "13": "B-SURNAME",
+    "14": "I-BUILDINGNUM",
+    "15": "B-ZIPCODE",
+    "16": "I-IDCARDNUM",
+    "17": "I-GIVENNAME",
+    "18": "I-TAXNUM",
+    "19": "I-SOCIALNUM",
+    "20": "I-ACCOUNTNUM",
+    "21": "I-DATEOFBIRTH",
+    "22": "B-DATEOFBIRTH",
+    "23": "I-TELEPHONENUM",
+    "24": "B-TELEPHONENUM",
+    "25": "B-USERNAME",
+    "26": "I-DRIVERLICENSENUM",
+    "27": "O",
+    "28": "B-STREET",
+    "29": "I-ZIPCODE",
+    "30": "B-IDCARDNUM",
+    "31": "B-GIVENNAME",
+    "32": "B-PASSWORD",
+    "33": "I-EMAIL",
+    "34": "I-SURNAME"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "B-ACCOUNTNUM": 6,
+    "B-BUILDINGNUM": 5,
+    "B-CITY": 1,
+    "B-CREDITCARDNUMBER": 0,
+    "B-DATEOFBIRTH": 22,
+    "B-DRIVERLICENSENUM": 2,
+    "B-EMAIL": 10,
+    "B-GIVENNAME": 31,
+    "B-IDCARDNUM": 30,
+    "B-PASSWORD": 32,
+    "B-SOCIALNUM": 8,
+    "B-STREET": 28,
+    "B-SURNAME": 13,
+    "B-TAXNUM": 3,
+    "B-TELEPHONENUM": 24,
+    "B-USERNAME": 25,
+    "B-ZIPCODE": 15,
+    "I-ACCOUNTNUM": 20,
+    "I-BUILDINGNUM": 14,
+    "I-CITY": 11,
+    "I-CREDITCARDNUMBER": 9,
+    "I-DATEOFBIRTH": 21,
+    "I-DRIVERLICENSENUM": 26,
+    "I-EMAIL": 33,
+    "I-GIVENNAME": 17,
+    "I-IDCARDNUM": 16,
+    "I-PASSWORD": 7,
+    "I-SOCIALNUM": 19,
+    "I-STREET": 12,
+    "I-SURNAME": 34,
+    "I-TAXNUM": 18,
+    "I-TELEPHONENUM": 23,
+    "I-USERNAME": 4,
+    "I-ZIPCODE": 29,
+    "O": 27
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.4",
+  "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 sha256:7003012b369478de78b541b77fb1c7e87cdb225d8ac71492afc564dfbd1e9d40
+size 53991756

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 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93e00b7b9d0530fc53c81b9cc33c7ab31668ef80159375a39b673d23f48327b6
+size 5841