Model save

README.md

@@ -0,0 +1,66 @@
+---
+license: mit
+base_model: dslim/bert-base-NER
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: bert-ner-finetuned-pii
+  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. -->
+
+# bert-ner-finetuned-pii
+
+This model is a fine-tuned version of [dslim/bert-base-NER](https://huggingface.co/dslim/bert-base-NER) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0030
+- Precision: 0.6649
+- Recall: 0.4725
+- F1: 0.5525
+- Accuracy: 0.9992
+
+## 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: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0052        | 1.0   | 724  | 0.0030          | 0.6649    | 0.4725 | 0.5525 | 0.9992   |
+
+
+### Framework versions
+
+- Transformers 4.37.0
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "dslim/bert-base-NER",
+  "_num_labels": 9,
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-EMAIL",
+    "1": "B-ID_NUM",
+    "2": "B-NAME_STUDENT",
+    "3": "B-PHONE_NUM",
+    "4": "B-STREET_ADDRESS",
+    "5": "B-URL_PERSONAL",
+    "6": "B-USERNAME",
+    "7": "I-ID_NUM",
+    "8": "I-NAME_STUDENT",
+    "9": "I-PHONE_NUM",
+    "10": "I-STREET_ADDRESS",
+    "11": "I-URL_PERSONAL",
+    "12": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-EMAIL": 0,
+    "B-ID_NUM": 1,
+    "B-NAME_STUDENT": 2,
+    "B-PHONE_NUM": 3,
+    "B-STREET_ADDRESS": 4,
+    "B-URL_PERSONAL": 5,
+    "B-USERNAME": 6,
+    "I-ID_NUM": 7,
+    "I-NAME_STUDENT": 8,
+    "I-PHONE_NUM": 9,
+    "I-STREET_ADDRESS": 10,
+    "I-URL_PERSONAL": 11,
+    "O": 12
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d4bf18abd5132e61eb2f0b77b29395b152b873cc6ee439787848aaec531cae6
+size 430942044

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
+    },
+    "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_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 sha256:298576503da7ba1c9d5b5174a3638ea904165cab2d88646022efd4b17faeb269
+size 4728