End of training

README.md

@@ -0,0 +1,74 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: yonigo/distilbert-base-multilingual-cased-pii
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: PII_classification_m1
+  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. -->
+
+# PII_classification_m1
+
+This model is a fine-tuned version of [yonigo/distilbert-base-multilingual-cased-pii](https://huggingface.co/yonigo/distilbert-base-multilingual-cased-pii) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5114
+- Precision: 0.2198
+- Recall: 0.2152
+- F1: 0.2175
+- Accuracy: 0.8536
+
+## 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: 3e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 8
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.5054        | 1.0   | 5036  | 0.4803          | 0.1488    | 0.1167 | 0.1308 | 0.8323   |
+| 0.4305        | 2.0   | 10072 | 0.4536          | 0.1928    | 0.1756 | 0.1838 | 0.8416   |
+| 0.3903        | 3.0   | 15108 | 0.4378          | 0.2003    | 0.1759 | 0.1873 | 0.8495   |
+| 0.3317        | 4.0   | 20144 | 0.4314          | 0.2001    | 0.1782 | 0.1885 | 0.8501   |
+| 0.2925        | 5.0   | 25180 | 0.4395          | 0.2194    | 0.2068 | 0.2130 | 0.8523   |
+| 0.2609        | 6.0   | 30216 | 0.4759          | 0.2195    | 0.2129 | 0.2162 | 0.8529   |
+| 0.2272        | 7.0   | 35252 | 0.4924          | 0.2228    | 0.2140 | 0.2183 | 0.8531   |
+| 0.2059        | 8.0   | 40288 | 0.5114          | 0.2198    | 0.2152 | 0.2175 | 0.8536   |
+
+
+### Framework versions
+
+- Transformers 4.50.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.4.1
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,122 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-EMAIL",
+    "2": "I-EMAIL",
+    "3": "B-IDCARD",
+    "4": "I-IDCARD",
+    "5": "B-SOCIALNUMBER",
+    "6": "I-SOCIALNUMBER",
+    "7": "B-TEL",
+    "8": "I-TEL",
+    "9": "B-IP",
+    "10": "I-IP",
+    "11": "B-TIME",
+    "12": "B-DRIVERLICENSE",
+    "13": "I-DRIVERLICENSE",
+    "14": "B-DATE",
+    "15": "I-DATE",
+    "16": "B-PASSPORT",
+    "17": "I-PASSPORT",
+    "18": "B-USERNAME",
+    "19": "I-USERNAME",
+    "20": "B-PASS",
+    "21": "I-PASS",
+    "22": "B-SEX",
+    "23": "I-SEX",
+    "24": "B-TITLE",
+    "25": "B-BOD",
+    "26": "I-BOD",
+    "27": "I-TITLE",
+    "28": "B-LASTNAME1",
+    "29": "I-LASTNAME1",
+    "30": "I-TIME",
+    "31": "B-GIVENNAME1",
+    "32": "I-GIVENNAME1",
+    "33": "B-COUNTRY",
+    "34": "B-BUILDING",
+    "35": "I-BUILDING",
+    "36": "B-STREET",
+    "37": "I-STREET",
+    "38": "B-CITY",
+    "39": "I-CITY",
+    "40": "B-STATE",
+    "41": "I-STATE",
+    "42": "B-POSTCODE",
+    "43": "I-POSTCODE",
+    "44": "B-SECADDRESS",
+    "45": "I-SECADDRESS",
+    "46": "I-COUNTRY"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-BOD": 25,
+    "B-BUILDING": 34,
+    "B-CITY": 38,
+    "B-COUNTRY": 33,
+    "B-DATE": 14,
+    "B-DRIVERLICENSE": 12,
+    "B-EMAIL": 1,
+    "B-GIVENNAME1": 31,
+    "B-IDCARD": 3,
+    "B-IP": 9,
+    "B-LASTNAME1": 28,
+    "B-PASS": 20,
+    "B-PASSPORT": 16,
+    "B-POSTCODE": 42,
+    "B-SECADDRESS": 44,
+    "B-SEX": 22,
+    "B-SOCIALNUMBER": 5,
+    "B-STATE": 40,
+    "B-STREET": 36,
+    "B-TEL": 7,
+    "B-TIME": 11,
+    "B-TITLE": 24,
+    "B-USERNAME": 18,
+    "I-BOD": 26,
+    "I-BUILDING": 35,
+    "I-CITY": 39,
+    "I-COUNTRY": 46,
+    "I-DATE": 15,
+    "I-DRIVERLICENSE": 13,
+    "I-EMAIL": 2,
+    "I-GIVENNAME1": 32,
+    "I-IDCARD": 4,
+    "I-IP": 10,
+    "I-LASTNAME1": 29,
+    "I-PASS": 21,
+    "I-PASSPORT": 17,
+    "I-POSTCODE": 43,
+    "I-SECADDRESS": 45,
+    "I-SEX": 23,
+    "I-SOCIALNUMBER": 6,
+    "I-STATE": 41,
+    "I-STREET": 37,
+    "I-TEL": 8,
+    "I-TIME": 30,
+    "I-TITLE": 27,
+    "I-USERNAME": 19,
+    "O": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.0",
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6efc2847d3c64568e2e636615cc9ca36eb47f6317cb530d61bd3bd78c8945645
+size 539093252

runs/Mar26_20-13-25_a8c7e18bb442/events.out.tfevents.1743020011.a8c7e18bb442.1086.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:537a6ee9b09533eadb97bc5d6b22b297290ed619079c3cf4881aa314203e44d2
+size 28246

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eebc2eb87d3a2f2fd8b2bd9e34e7438beeab0ff33d1609e20dfe9b2d49f3a8f1
+size 5368