Training in progress, epoch 1

added_tokens.json

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

config.json

@@ -0,0 +1,117 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-PERSON",
+    "1": "I-PERSON",
+    "2": "O",
+    "3": "B-ORGANIZATION",
+    "4": "I-ORGANIZATION",
+    "5": "B-AGE",
+    "6": "I-AGE",
+    "7": "B-CITY",
+    "8": "I-CITY",
+    "9": "B-STATE",
+    "10": "B-PAN_CARD",
+    "11": "I-PAN_CARD",
+    "12": "B-AADHAR_CARD",
+    "13": "I-AADHAR_CARD",
+    "14": "B-CREDITCARDNUMBER",
+    "15": "I-CREDITCARDNUMBER",
+    "16": "B-EXPIRYDATE",
+    "17": "I-EXPIRYDATE",
+    "18": "B-SECONDARYADDRESS",
+    "19": "I-SECONDARYADDRESS",
+    "20": "B-EMAIL",
+    "21": "I-EMAIL",
+    "22": "B-TIME",
+    "23": "I-TIME",
+    "24": "B-DATE",
+    "25": "I-DATE",
+    "26": "B-COUNTRY",
+    "27": "B-URL",
+    "28": "I-URL",
+    "29": "I-STATE",
+    "30": "B-CREDITCARDCVV",
+    "31": "B-PINCODE",
+    "32": "I-PINCODE",
+    "33": "B-PHONENUMBER",
+    "34": "I-PHONENUMBER",
+    "35": "B-DATEOFBIRTH",
+    "36": "I-DATEOFBIRTH",
+    "37": "I-COUNTRY",
+    "38": "I-CREDITCARDCVV"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-AADHAR_CARD": 12,
+    "B-AGE": 5,
+    "B-CITY": 7,
+    "B-COUNTRY": 26,
+    "B-CREDITCARDCVV": 30,
+    "B-CREDITCARDNUMBER": 14,
+    "B-DATE": 24,
+    "B-DATEOFBIRTH": 35,
+    "B-EMAIL": 20,
+    "B-EXPIRYDATE": 16,
+    "B-ORGANIZATION": 3,
+    "B-PAN_CARD": 10,
+    "B-PERSON": 0,
+    "B-PHONENUMBER": 33,
+    "B-PINCODE": 31,
+    "B-SECONDARYADDRESS": 18,
+    "B-STATE": 9,
+    "B-TIME": 22,
+    "B-URL": 27,
+    "I-AADHAR_CARD": 13,
+    "I-AGE": 6,
+    "I-CITY": 8,
+    "I-COUNTRY": 37,
+    "I-CREDITCARDCVV": 38,
+    "I-CREDITCARDNUMBER": 15,
+    "I-DATE": 25,
+    "I-DATEOFBIRTH": 36,
+    "I-EMAIL": 21,
+    "I-EXPIRYDATE": 17,
+    "I-ORGANIZATION": 4,
+    "I-PAN_CARD": 11,
+    "I-PERSON": 1,
+    "I-PHONENUMBER": 34,
+    "I-PINCODE": 32,
+    "I-SECONDARYADDRESS": 19,
+    "I-STATE": 29,
+    "I-TIME": 23,
+    "I-URL": 28,
+    "O": 2
+  },
+  "layer_norm_eps": 1e-07,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d09e8681e1781714128f58b24b0134b47d1726822da050fe7d7118a1a26625b
+size 735470556

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 +1,58 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "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:bd4441d28fa21a7e3e82851ae2ade7ff1f7f2a775fe7fbe4f1e7085b71336e11
+size 5048