Training in progress, step 256

config.json

@@ -0,0 +1,100 @@
+{
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "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": "B-SURNAME",
+    "1": "I-CREDITCARDNUMBER",
+    "2": "I-SURNAME",
+    "3": "I-EMAIL",
+    "4": "B-GIVENNAME",
+    "5": "B-CREDITCARDNUMBER",
+    "6": "I-CITY",
+    "7": "O",
+    "8": "I-BUILDINGNUM",
+    "9": "I-GIVENNAME",
+    "10": "B-BUILDINGNUM",
+    "11": "I-TELEPHONENUM",
+    "12": "B-PASSWORD",
+    "13": "B-USERNAME",
+    "14": "I-ZIPCODE",
+    "15": "I-DRIVERLICENSENUM",
+    "16": "B-TELEPHONENUM",
+    "17": "B-ZIPCODE",
+    "18": "B-IDCARDNUM",
+    "19": "I-SOCIALNUM",
+    "20": "B-CITY",
+    "21": "I-USERNAME",
+    "22": "B-TAXNUM",
+    "23": "B-DATEOFBIRTH",
+    "24": "I-DATEOFBIRTH",
+    "25": "I-IDCARDNUM",
+    "26": "B-DRIVERLICENSENUM",
+    "27": "I-TAXNUM",
+    "28": "B-ACCOUNTNUM",
+    "29": "B-SOCIALNUM",
+    "30": "I-ACCOUNTNUM",
+    "31": "B-STREET",
+    "32": "I-PASSWORD",
+    "33": "I-STREET",
+    "34": "B-EMAIL"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ACCOUNTNUM": 28,
+    "B-BUILDINGNUM": 10,
+    "B-CITY": 20,
+    "B-CREDITCARDNUMBER": 5,
+    "B-DATEOFBIRTH": 23,
+    "B-DRIVERLICENSENUM": 26,
+    "B-EMAIL": 34,
+    "B-GIVENNAME": 4,
+    "B-IDCARDNUM": 18,
+    "B-PASSWORD": 12,
+    "B-SOCIALNUM": 29,
+    "B-STREET": 31,
+    "B-SURNAME": 0,
+    "B-TAXNUM": 22,
+    "B-TELEPHONENUM": 16,
+    "B-USERNAME": 13,
+    "B-ZIPCODE": 17,
+    "I-ACCOUNTNUM": 30,
+    "I-BUILDINGNUM": 8,
+    "I-CITY": 6,
+    "I-CREDITCARDNUMBER": 1,
+    "I-DATEOFBIRTH": 24,
+    "I-DRIVERLICENSENUM": 15,
+    "I-EMAIL": 3,
+    "I-GIVENNAME": 9,
+    "I-IDCARDNUM": 25,
+    "I-PASSWORD": 32,
+    "I-SOCIALNUM": 19,
+    "I-STREET": 33,
+    "I-SURNAME": 2,
+    "I-TAXNUM": 27,
+    "I-TELEPHONENUM": 11,
+    "I-USERNAME": 21,
+    "I-ZIPCODE": 14,
+    "O": 7
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6b9c181d653d8f3187801dc7dd36f45bf9c3b03f2e49a3f051ec80f004b7c4d
+size 496351756

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_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51007d5226bd91af094c414389ea5496a531c6050b8ed3181602bf3e92816076
+size 5841