Upload fine-tuned PII detection model

README.md

@@ -0,0 +1,72 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+model-index:
+- name: pii_bert_model
+  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_bert_model
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1020
+- Precision: 0.9748
+- Recall: 0.9744
+- F1: 0.9745
+
+## 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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- 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     |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
+| 0.1362        | 1.0   | 150  | 0.1090          | 0.9663    | 0.9642 | 0.9645 |
+| 0.0974        | 2.0   | 300  | 0.1192          | 0.9632    | 0.9619 | 0.9620 |
+| 0.0736        | 3.0   | 450  | 0.0867          | 0.9696    | 0.9693 | 0.9693 |
+| 0.0605        | 4.0   | 600  | 0.1111          | 0.9696    | 0.9682 | 0.9685 |
+| 0.0445        | 5.0   | 750  | 0.0895          | 0.9729    | 0.9726 | 0.9726 |
+| 0.0343        | 6.0   | 900  | 0.0952          | 0.9727    | 0.9719 | 0.9721 |
+| 0.023         | 7.0   | 1050 | 0.0991          | 0.9745    | 0.9740 | 0.9741 |
+| 0.0179        | 8.0   | 1200 | 0.1020          | 0.9748    | 0.9744 | 0.9745 |
+
+
+### Framework versions
+
+- Transformers 4.50.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,99 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-EMAIL",
+    "4": "I-EMAIL",
+    "5": "B-PHONE",
+    "6": "I-PHONE",
+    "7": "B-LOC",
+    "8": "I-LOC",
+    "9": "B-DATE",
+    "10": "I-DATE",
+    "11": "B-SSN",
+    "12": "I-SSN",
+    "13": "B-CC",
+    "14": "I-CC",
+    "15": "B-ID",
+    "16": "I-ID",
+    "17": "B-IP",
+    "18": "I-IP",
+    "19": "B-URL",
+    "20": "I-URL",
+    "21": "B-ORG",
+    "22": "I-ORG",
+    "23": "B-AGE",
+    "24": "I-AGE",
+    "25": "B-PASSPORT",
+    "26": "I-PASSPORT",
+    "27": "B-DRIVER",
+    "28": "I-DRIVER",
+    "29": "B-BANK",
+    "30": "I-BANK",
+    "31": "B-MEDICAL",
+    "32": "I-MEDICAL",
+    "33": "B-PLATE",
+    "34": "I-PLATE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-AGE": 23,
+    "B-BANK": 29,
+    "B-CC": 13,
+    "B-DATE": 9,
+    "B-DRIVER": 27,
+    "B-EMAIL": 3,
+    "B-ID": 15,
+    "B-IP": 17,
+    "B-LOC": 7,
+    "B-MEDICAL": 31,
+    "B-ORG": 21,
+    "B-PASSPORT": 25,
+    "B-PER": 1,
+    "B-PHONE": 5,
+    "B-PLATE": 33,
+    "B-SSN": 11,
+    "B-URL": 19,
+    "I-AGE": 24,
+    "I-BANK": 30,
+    "I-CC": 14,
+    "I-DATE": 10,
+    "I-DRIVER": 28,
+    "I-EMAIL": 4,
+    "I-ID": 16,
+    "I-IP": 18,
+    "I-LOC": 8,
+    "I-MEDICAL": 32,
+    "I-ORG": 22,
+    "I-PASSPORT": 26,
+    "I-PER": 2,
+    "I-PHONE": 6,
+    "I-PLATE": 34,
+    "I-SSN": 12,
+    "I-URL": 20,
+    "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": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

labels.json

@@ -0,0 +1,37 @@
+{
+  "O": 0,
+  "B-PER": 1,
+  "I-PER": 2,
+  "B-EMAIL": 3,
+  "I-EMAIL": 4,
+  "B-PHONE": 5,
+  "I-PHONE": 6,
+  "B-LOC": 7,
+  "I-LOC": 8,
+  "B-DATE": 9,
+  "I-DATE": 10,
+  "B-SSN": 11,
+  "I-SSN": 12,
+  "B-CC": 13,
+  "I-CC": 14,
+  "B-ID": 15,
+  "I-ID": 16,
+  "B-IP": 17,
+  "I-IP": 18,
+  "B-URL": 19,
+  "I-URL": 20,
+  "B-ORG": 21,
+  "I-ORG": 22,
+  "B-AGE": 23,
+  "I-AGE": 24,
+  "B-PASSPORT": 25,
+  "I-PASSPORT": 26,
+  "B-DRIVER": 27,
+  "I-DRIVER": 28,
+  "B-BANK": 29,
+  "I-BANK": 30,
+  "B-MEDICAL": 31,
+  "I-MEDICAL": 32,
+  "B-PLATE": 33,
+  "I-PLATE": 34
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c888c59de538cd8c98d8322ec7d96f2d704458c6bddea98b54ca5821dc97a98a
+size 435697596

runs/Apr13_04-04-42_65661a2afab4/events.out.tfevents.1744517090.65661a2afab4.289.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f5a84fefca8f5c987cf718eb443837f0734a96e0458f71de5cfa6935e6e0a5e
+size 7644

runs/Apr13_04-08-50_65661a2afab4/events.out.tfevents.1744517333.65661a2afab4.289.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db35dccd8def46102f14aebc0d5ba2982043688fc34257fcb4fddcde6589ad00
+size 11757

runs/Apr13_04-08-50_65661a2afab4/events.out.tfevents.1744517898.65661a2afab4.289.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9581be7062d4f300b6f0dc5b85d94901fd75c659c130a378a80e5c18f027a151
+size 508

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 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:338f5091ae2ec8440197a0066e8b9ed3f5a0d013f232cc3d57eda3bf3cbf593f
+size 5304