Training in progress, epoch 1

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,254 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PHONEIMEI",
+    "2": "I-PHONEIMEI",
+    "3": "B-JOBAREA",
+    "4": "B-FIRSTNAME",
+    "5": "I-FIRSTNAME",
+    "6": "B-VEHICLEVIN",
+    "7": "I-VEHICLEVIN",
+    "8": "B-AGE",
+    "9": "B-GENDER",
+    "10": "I-GENDER",
+    "11": "B-HEIGHT",
+    "12": "I-HEIGHT",
+    "13": "B-BUILDINGNUMBER",
+    "14": "I-BUILDINGNUMBER",
+    "15": "B-MASKEDNUMBER",
+    "16": "I-MASKEDNUMBER",
+    "17": "B-PASSWORD",
+    "18": "I-PASSWORD",
+    "19": "B-DOB",
+    "20": "I-DOB",
+    "21": "B-IPV6",
+    "22": "I-IPV6",
+    "23": "B-NEARBYGPSCOORDINATE",
+    "24": "I-NEARBYGPSCOORDINATE",
+    "25": "B-USERAGENT",
+    "26": "I-USERAGENT",
+    "27": "B-TIME",
+    "28": "I-TIME",
+    "29": "B-JOBTITLE",
+    "30": "I-JOBTITLE",
+    "31": "B-COUNTY",
+    "32": "B-EMAIL",
+    "33": "I-EMAIL",
+    "34": "B-ACCOUNTNUMBER",
+    "35": "I-ACCOUNTNUMBER",
+    "36": "B-PIN",
+    "37": "I-PIN",
+    "38": "B-EYECOLOR",
+    "39": "I-EYECOLOR",
+    "40": "B-LASTNAME",
+    "41": "I-LASTNAME",
+    "42": "I-JOBAREA",
+    "43": "B-IPV4",
+    "44": "I-IPV4",
+    "45": "B-DATE",
+    "46": "I-DATE",
+    "47": "B-STREET",
+    "48": "I-STREET",
+    "49": "B-CITY",
+    "50": "I-CITY",
+    "51": "B-PREFIX",
+    "52": "I-PREFIX",
+    "53": "B-CREDITCARDISSUER",
+    "54": "B-CREDITCARDNUMBER",
+    "55": "I-CREDITCARDNUMBER",
+    "56": "I-CREDITCARDISSUER",
+    "57": "B-MIDDLENAME",
+    "58": "B-STATE",
+    "59": "I-STATE",
+    "60": "B-VEHICLEVRM",
+    "61": "I-VEHICLEVRM",
+    "62": "B-ORDINALDIRECTION",
+    "63": "B-SEX",
+    "64": "B-JOBTYPE",
+    "65": "I-JOBTYPE",
+    "66": "B-CURRENCYCODE",
+    "67": "I-CURRENCYCODE",
+    "68": "B-CURRENCYSYMBOL",
+    "69": "I-AMOUNT",
+    "70": "B-ACCOUNTNAME",
+    "71": "I-ACCOUNTNAME",
+    "72": "B-BITCOINADDRESS",
+    "73": "I-BITCOINADDRESS",
+    "74": "B-LITECOINADDRESS",
+    "75": "I-LITECOINADDRESS",
+    "76": "B-PHONENUMBER",
+    "77": "I-PHONENUMBER",
+    "78": "B-MAC",
+    "79": "I-MAC",
+    "80": "B-CURRENCY",
+    "81": "B-IBAN",
+    "82": "I-IBAN",
+    "83": "B-COMPANYNAME",
+    "84": "I-COMPANYNAME",
+    "85": "B-CURRENCYNAME",
+    "86": "I-CURRENCYNAME",
+    "87": "I-CURRENCYSYMBOL",
+    "88": "B-ZIPCODE",
+    "89": "I-ZIPCODE",
+    "90": "B-SSN",
+    "91": "I-SSN",
+    "92": "B-AMOUNT",
+    "93": "I-CURRENCY",
+    "94": "B-URL",
+    "95": "I-URL",
+    "96": "B-IP",
+    "97": "I-IP",
+    "98": "B-SECONDARYADDRESS",
+    "99": "I-SECONDARYADDRESS",
+    "100": "B-USERNAME",
+    "101": "I-USERNAME",
+    "102": "B-ETHEREUMADDRESS",
+    "103": "I-ETHEREUMADDRESS",
+    "104": "B-CREDITCARDCVV",
+    "105": "I-CREDITCARDCVV",
+    "106": "I-COUNTY",
+    "107": "I-AGE",
+    "108": "I-MIDDLENAME",
+    "109": "B-BIC",
+    "110": "I-BIC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ACCOUNTNAME": 70,
+    "B-ACCOUNTNUMBER": 34,
+    "B-AGE": 8,
+    "B-AMOUNT": 92,
+    "B-BIC": 109,
+    "B-BITCOINADDRESS": 72,
+    "B-BUILDINGNUMBER": 13,
+    "B-CITY": 49,
+    "B-COMPANYNAME": 83,
+    "B-COUNTY": 31,
+    "B-CREDITCARDCVV": 104,
+    "B-CREDITCARDISSUER": 53,
+    "B-CREDITCARDNUMBER": 54,
+    "B-CURRENCY": 80,
+    "B-CURRENCYCODE": 66,
+    "B-CURRENCYNAME": 85,
+    "B-CURRENCYSYMBOL": 68,
+    "B-DATE": 45,
+    "B-DOB": 19,
+    "B-EMAIL": 32,
+    "B-ETHEREUMADDRESS": 102,
+    "B-EYECOLOR": 38,
+    "B-FIRSTNAME": 4,
+    "B-GENDER": 9,
+    "B-HEIGHT": 11,
+    "B-IBAN": 81,
+    "B-IP": 96,
+    "B-IPV4": 43,
+    "B-IPV6": 21,
+    "B-JOBAREA": 3,
+    "B-JOBTITLE": 29,
+    "B-JOBTYPE": 64,
+    "B-LASTNAME": 40,
+    "B-LITECOINADDRESS": 74,
+    "B-MAC": 78,
+    "B-MASKEDNUMBER": 15,
+    "B-MIDDLENAME": 57,
+    "B-NEARBYGPSCOORDINATE": 23,
+    "B-ORDINALDIRECTION": 62,
+    "B-PASSWORD": 17,
+    "B-PHONEIMEI": 1,
+    "B-PHONENUMBER": 76,
+    "B-PIN": 36,
+    "B-PREFIX": 51,
+    "B-SECONDARYADDRESS": 98,
+    "B-SEX": 63,
+    "B-SSN": 90,
+    "B-STATE": 58,
+    "B-STREET": 47,
+    "B-TIME": 27,
+    "B-URL": 94,
+    "B-USERAGENT": 25,
+    "B-USERNAME": 100,
+    "B-VEHICLEVIN": 6,
+    "B-VEHICLEVRM": 60,
+    "B-ZIPCODE": 88,
+    "I-ACCOUNTNAME": 71,
+    "I-ACCOUNTNUMBER": 35,
+    "I-AGE": 107,
+    "I-AMOUNT": 69,
+    "I-BIC": 110,
+    "I-BITCOINADDRESS": 73,
+    "I-BUILDINGNUMBER": 14,
+    "I-CITY": 50,
+    "I-COMPANYNAME": 84,
+    "I-COUNTY": 106,
+    "I-CREDITCARDCVV": 105,
+    "I-CREDITCARDISSUER": 56,
+    "I-CREDITCARDNUMBER": 55,
+    "I-CURRENCY": 93,
+    "I-CURRENCYCODE": 67,
+    "I-CURRENCYNAME": 86,
+    "I-CURRENCYSYMBOL": 87,
+    "I-DATE": 46,
+    "I-DOB": 20,
+    "I-EMAIL": 33,
+    "I-ETHEREUMADDRESS": 103,
+    "I-EYECOLOR": 39,
+    "I-FIRSTNAME": 5,
+    "I-GENDER": 10,
+    "I-HEIGHT": 12,
+    "I-IBAN": 82,
+    "I-IP": 97,
+    "I-IPV4": 44,
+    "I-IPV6": 22,
+    "I-JOBAREA": 42,
+    "I-JOBTITLE": 30,
+    "I-JOBTYPE": 65,
+    "I-LASTNAME": 41,
+    "I-LITECOINADDRESS": 75,
+    "I-MAC": 79,
+    "I-MASKEDNUMBER": 16,
+    "I-MIDDLENAME": 108,
+    "I-NEARBYGPSCOORDINATE": 24,
+    "I-PASSWORD": 18,
+    "I-PHONEIMEI": 2,
+    "I-PHONENUMBER": 77,
+    "I-PIN": 37,
+    "I-PREFIX": 52,
+    "I-SECONDARYADDRESS": 99,
+    "I-SSN": 91,
+    "I-STATE": 59,
+    "I-STREET": 48,
+    "I-TIME": 28,
+    "I-URL": 95,
+    "I-USERAGENT": 26,
+    "I-USERNAME": 101,
+    "I-VEHICLEVIN": 7,
+    "I-VEHICLEVRM": 61,
+    "I-ZIPCODE": 89,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a76ec2026bbcc19dc0b0bcb95019c6fbd09b7d2abc8c5aba2d7e5b537b6050
+size 1110223661

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
+size 17082660

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "FacebookAI/xlm-roberta-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced730cc5c5efd3865bd4e24cb15c3305d398a3d2e21f902d9074befae35f0c1
+size 3515