Training in progress, epoch 1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,171 @@
+{
+  "architectures": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-ADDRESS",
+    "2": "I-ADDRESS",
+    "3": "B-API_KEY",
+    "4": "I-API_KEY",
+    "5": "B-BANK_ACCOUNT",
+    "6": "I-BANK_ACCOUNT",
+    "7": "B-CARD_CVV",
+    "8": "I-CARD_CVV",
+    "9": "B-CARD_EXPIRY",
+    "10": "I-CARD_EXPIRY",
+    "11": "B-CARD_LAST4",
+    "12": "I-CARD_LAST4",
+    "13": "B-CARD_NUMBER",
+    "14": "I-CARD_NUMBER",
+    "15": "B-DATE",
+    "16": "I-DATE",
+    "17": "B-DATE_OF_BIRTH",
+    "18": "I-DATE_OF_BIRTH",
+    "19": "B-DEVICE_SERIAL",
+    "20": "I-DEVICE_SERIAL",
+    "21": "B-DOCTOR_NAME",
+    "22": "I-DOCTOR_NAME",
+    "23": "B-DRIVER_LICENSE",
+    "24": "I-DRIVER_LICENSE",
+    "25": "B-EMAIL",
+    "26": "I-EMAIL",
+    "27": "B-EMPLOYEE_ID",
+    "28": "I-EMPLOYEE_ID",
+    "29": "B-HOSPITAL_NAME",
+    "30": "I-HOSPITAL_NAME",
+    "31": "B-IBAN",
+    "32": "I-IBAN",
+    "33": "B-INSURANCE_ID",
+    "34": "I-INSURANCE_ID",
+    "35": "B-IP_ADDRESS",
+    "36": "I-IP_ADDRESS",
+    "37": "B-ITIN",
+    "38": "I-ITIN",
+    "39": "B-LICENSE_PLATE",
+    "40": "I-LICENSE_PLATE",
+    "41": "B-MAC_ADDRESS",
+    "42": "I-MAC_ADDRESS",
+    "43": "B-MRN",
+    "44": "I-MRN",
+    "45": "B-NATIONAL_ID",
+    "46": "I-NATIONAL_ID",
+    "47": "B-PASSPORT_NUMBER",
+    "48": "I-PASSPORT_NUMBER",
+    "49": "B-PASSWORD",
+    "50": "I-PASSWORD",
+    "51": "B-PERSON_NAME",
+    "52": "I-PERSON_NAME",
+    "53": "B-PHONE",
+    "54": "I-PHONE",
+    "55": "B-ROUTING_NUMBER",
+    "56": "I-ROUTING_NUMBER",
+    "57": "B-SSN",
+    "58": "I-SSN",
+    "59": "B-SWIFT_CODE",
+    "60": "I-SWIFT_CODE",
+    "61": "B-USERNAME",
+    "62": "I-USERNAME",
+    "63": "B-VEHICLE_VIN",
+    "64": "I-VEHICLE_VIN"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ADDRESS": 1,
+    "B-API_KEY": 3,
+    "B-BANK_ACCOUNT": 5,
+    "B-CARD_CVV": 7,
+    "B-CARD_EXPIRY": 9,
+    "B-CARD_LAST4": 11,
+    "B-CARD_NUMBER": 13,
+    "B-DATE": 15,
+    "B-DATE_OF_BIRTH": 17,
+    "B-DEVICE_SERIAL": 19,
+    "B-DOCTOR_NAME": 21,
+    "B-DRIVER_LICENSE": 23,
+    "B-EMAIL": 25,
+    "B-EMPLOYEE_ID": 27,
+    "B-HOSPITAL_NAME": 29,
+    "B-IBAN": 31,
+    "B-INSURANCE_ID": 33,
+    "B-IP_ADDRESS": 35,
+    "B-ITIN": 37,
+    "B-LICENSE_PLATE": 39,
+    "B-MAC_ADDRESS": 41,
+    "B-MRN": 43,
+    "B-NATIONAL_ID": 45,
+    "B-PASSPORT_NUMBER": 47,
+    "B-PASSWORD": 49,
+    "B-PERSON_NAME": 51,
+    "B-PHONE": 53,
+    "B-ROUTING_NUMBER": 55,
+    "B-SSN": 57,
+    "B-SWIFT_CODE": 59,
+    "B-USERNAME": 61,
+    "B-VEHICLE_VIN": 63,
+    "I-ADDRESS": 2,
+    "I-API_KEY": 4,
+    "I-BANK_ACCOUNT": 6,
+    "I-CARD_CVV": 8,
+    "I-CARD_EXPIRY": 10,
+    "I-CARD_LAST4": 12,
+    "I-CARD_NUMBER": 14,
+    "I-DATE": 16,
+    "I-DATE_OF_BIRTH": 18,
+    "I-DEVICE_SERIAL": 20,
+    "I-DOCTOR_NAME": 22,
+    "I-DRIVER_LICENSE": 24,
+    "I-EMAIL": 26,
+    "I-EMPLOYEE_ID": 28,
+    "I-HOSPITAL_NAME": 30,
+    "I-IBAN": 32,
+    "I-INSURANCE_ID": 34,
+    "I-IP_ADDRESS": 36,
+    "I-ITIN": 38,
+    "I-LICENSE_PLATE": 40,
+    "I-MAC_ADDRESS": 42,
+    "I-MRN": 44,
+    "I-NATIONAL_ID": 46,
+    "I-PASSPORT_NUMBER": 48,
+    "I-PASSWORD": 50,
+    "I-PERSON_NAME": 52,
+    "I-PHONE": 54,
+    "I-ROUTING_NUMBER": 56,
+    "I-SSN": 58,
+    "I-SWIFT_CODE": 60,
+    "I-USERNAME": 62,
+    "I-VEHICLE_VIN": 64,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ac4045e5415c48a9399aa4563d803f11fc2b84a11047ce85cb157eeb7157a4d
+size 735550532

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:610df77b20e51e77e8effe6f097777f42aaf4d1caaf4b7f25e03492a13e9bb64
+size 5432