End of training

README.md

@@ -0,0 +1,52 @@
+---
+license: mit
+base_model: dbmdz/bert-base-italian-xxl-cased
+tags:
+- generated_from_trainer
+model-index:
+- name: Italin_NER_XXL
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Italin_NER_XXL
+
+This model is a fine-tuned version of [dbmdz/bert-base-italian-xxl-cased](https://huggingface.co/dbmdz/bert-base-italian-xxl-cased) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 8
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,239 @@
+{
+  "_name_or_path": "dbmdz/bert-base-italian-xxl-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-INDIRIZZO",
+    "2": "I-INDIRIZZO",
+    "3": "B-VALUTA",
+    "4": "I-VALUTA",
+    "5": "B-CVV",
+    "6": "I-CVV",
+    "7": "B-NUMERO_CONTO",
+    "8": "I-NUMERO_CONTO",
+    "9": "B-BIC",
+    "10": "I-BIC",
+    "11": "B-IBAN",
+    "12": "I-IBAN",
+    "13": "B-STATO",
+    "14": "I-STATO",
+    "15": "B-NOME",
+    "16": "I-NOME",
+    "17": "B-COGNOME",
+    "18": "I-COGNOME",
+    "19": "B-CODICE_POSTALE",
+    "20": "I-CODICE_POSTALE",
+    "21": "B-IP",
+    "22": "I-IP",
+    "23": "B-ORARIO",
+    "24": "I-ORARIO",
+    "25": "B-URL",
+    "26": "I-URL",
+    "27": "B-LUOGO",
+    "28": "I-LUOGO",
+    "29": "B-IMPORTO",
+    "30": "I-IMPORTO",
+    "31": "B-EMAIL",
+    "32": "I-EMAIL",
+    "33": "B-PASSWORD",
+    "34": "I-PASSWORD",
+    "35": "B-NUMERO_CARTA",
+    "36": "I-NUMERO_CARTA",
+    "37": "B-TARGA_VEICOLO",
+    "38": "I-TARGA_VEICOLO",
+    "39": "B-DATA_NASCITA",
+    "40": "I-DATA_NASCITA",
+    "41": "B-DATA_MORTE",
+    "42": "I-DATA_MORTE",
+    "43": "B-RAGIONE_SOCIALE",
+    "44": "I-RAGIONE_SOCIALE",
+    "45": "B-ETA",
+    "46": "I-ETA",
+    "47": "B-DATA",
+    "48": "I-DATA",
+    "49": "B-PROFESSIONE",
+    "50": "I-PROFESSIONE",
+    "51": "B-PIN",
+    "52": "I-PIN",
+    "53": "B-NUMERO_TELEFONO",
+    "54": "I-NUMERO_TELEFONO",
+    "55": "B-FOGLIO",
+    "56": "I-FOGLIO",
+    "57": "B-PARTICELLA",
+    "58": "I-PARTICELLA",
+    "59": "B-CARTELLA_CLINICA",
+    "60": "I-CARTELLA_CLINICA",
+    "61": "B-MALATTIA",
+    "62": "I-MALATTIA",
+    "63": "B-MEDICINA",
+    "64": "I-MEDICINA",
+    "65": "B-CODICE_FISCALE",
+    "66": "I-CODICE_FISCALE",
+    "67": "B-NUMERO_DOCUMENTO",
+    "68": "I-NUMERO_DOCUMENTO",
+    "69": "B-STORIA_CLINICA",
+    "70": "I-STORIA_CLINICA",
+    "71": "B-AVV_NOTAIO",
+    "72": "I-AVV_NOTAIO",
+    "73": "B-P_IVA",
+    "74": "I-P_IVA",
+    "75": "B-LEGGE",
+    "76": "I-LEGGE",
+    "77": "B-TASSO_MUTUO",
+    "78": "I-TASSO_MUTUO",
+    "79": "B-N_SENTENZA",
+    "80": "I-N_SENTENZA",
+    "81": "B-MAPPALE",
+    "82": "I-MAPPALE",
+    "83": "B-SUBALTERNO",
+    "84": "I-SUBALTERNO",
+    "85": "B-REGIME_PATRIMONIALE",
+    "86": "I-REGIME_PATRIMONIALE",
+    "87": "B-STATO_CIVILE",
+    "88": "I-STATO_CIVILE",
+    "89": "B-BANCA",
+    "90": "I-BANCA",
+    "91": "B-BRAND",
+    "92": "I-BRAND",
+    "93": "B-NUM_ASSEGNO_BANCARIO",
+    "94": "I-NUM_ASSEGNO_BANCARIO",
+    "95": "B-IMEI",
+    "96": "I-IMEI",
+    "97": "B-N_LICENZA",
+    "98": "I-N_LICENZA",
+    "99": "B-IPV6_1",
+    "100": "I-IPV6_1",
+    "101": "B-MAC",
+    "102": "I-MAC",
+    "103": "B-USER_AGENT",
+    "104": "I-USER_AGENT"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-AVV_NOTAIO": 71,
+    "B-BANCA": 89,
+    "B-BIC": 9,
+    "B-BRAND": 91,
+    "B-CARTELLA_CLINICA": 59,
+    "B-CODICE_FISCALE": 65,
+    "B-CODICE_POSTALE": 19,
+    "B-COGNOME": 17,
+    "B-CVV": 5,
+    "B-DATA": 47,
+    "B-DATA_MORTE": 41,
+    "B-DATA_NASCITA": 39,
+    "B-EMAIL": 31,
+    "B-ETA": 45,
+    "B-FOGLIO": 55,
+    "B-IBAN": 11,
+    "B-IMEI": 95,
+    "B-IMPORTO": 29,
+    "B-INDIRIZZO": 1,
+    "B-IP": 21,
+    "B-IPV6_1": 99,
+    "B-LEGGE": 75,
+    "B-LUOGO": 27,
+    "B-MAC": 101,
+    "B-MALATTIA": 61,
+    "B-MAPPALE": 81,
+    "B-MEDICINA": 63,
+    "B-NOME": 15,
+    "B-NUMERO_CARTA": 35,
+    "B-NUMERO_CONTO": 7,
+    "B-NUMERO_DOCUMENTO": 67,
+    "B-NUMERO_TELEFONO": 53,
+    "B-NUM_ASSEGNO_BANCARIO": 93,
+    "B-N_LICENZA": 97,
+    "B-N_SENTENZA": 79,
+    "B-ORARIO": 23,
+    "B-PARTICELLA": 57,
+    "B-PASSWORD": 33,
+    "B-PIN": 51,
+    "B-PROFESSIONE": 49,
+    "B-P_IVA": 73,
+    "B-RAGIONE_SOCIALE": 43,
+    "B-REGIME_PATRIMONIALE": 85,
+    "B-STATO": 13,
+    "B-STATO_CIVILE": 87,
+    "B-STORIA_CLINICA": 69,
+    "B-SUBALTERNO": 83,
+    "B-TARGA_VEICOLO": 37,
+    "B-TASSO_MUTUO": 77,
+    "B-URL": 25,
+    "B-USER_AGENT": 103,
+    "B-VALUTA": 3,
+    "I-AVV_NOTAIO": 72,
+    "I-BANCA": 90,
+    "I-BIC": 10,
+    "I-BRAND": 92,
+    "I-CARTELLA_CLINICA": 60,
+    "I-CODICE_FISCALE": 66,
+    "I-CODICE_POSTALE": 20,
+    "I-COGNOME": 18,
+    "I-CVV": 6,
+    "I-DATA": 48,
+    "I-DATA_MORTE": 42,
+    "I-DATA_NASCITA": 40,
+    "I-EMAIL": 32,
+    "I-ETA": 46,
+    "I-FOGLIO": 56,
+    "I-IBAN": 12,
+    "I-IMEI": 96,
+    "I-IMPORTO": 30,
+    "I-INDIRIZZO": 2,
+    "I-IP": 22,
+    "I-IPV6_1": 100,
+    "I-LEGGE": 76,
+    "I-LUOGO": 28,
+    "I-MAC": 102,
+    "I-MALATTIA": 62,
+    "I-MAPPALE": 82,
+    "I-MEDICINA": 64,
+    "I-NOME": 16,
+    "I-NUMERO_CARTA": 36,
+    "I-NUMERO_CONTO": 8,
+    "I-NUMERO_DOCUMENTO": 68,
+    "I-NUMERO_TELEFONO": 54,
+    "I-NUM_ASSEGNO_BANCARIO": 94,
+    "I-N_LICENZA": 98,
+    "I-N_SENTENZA": 80,
+    "I-ORARIO": 24,
+    "I-PARTICELLA": 58,
+    "I-PASSWORD": 34,
+    "I-PIN": 52,
+    "I-PROFESSIONE": 50,
+    "I-P_IVA": 74,
+    "I-RAGIONE_SOCIALE": 44,
+    "I-REGIME_PATRIMONIALE": 86,
+    "I-STATO": 14,
+    "I-STATO_CIVILE": 88,
+    "I-STORIA_CLINICA": 70,
+    "I-SUBALTERNO": 84,
+    "I-TARGA_VEICOLO": 38,
+    "I-TASSO_MUTUO": 78,
+    "I-URL": 26,
+    "I-USER_AGENT": 104,
+    "I-VALUTA": 4,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32102
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db9c598b74073536ab4c8803fdf88bf56ac5a886f7eb91d6517d2277fc18d88d
+size 440766692

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 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f695280a4a75b9011dbde72764310ed5b0c701bb8d872a73d3325acb43de37d4
+size 4664