deberta3_pii

README.md

@@ -0,0 +1,68 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-small
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: deBert-finetuned-ner-v1
+  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. -->
+
+# deBert-finetuned-ner-v1
+
+This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0010
+- Precision: 0.9674
+- Recall: 0.9784
+- F1: 0.9728
+- Accuracy: 0.9997
+
+## 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: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.037         | 1.0   | 950  | 0.0017          | 0.9350    | 0.9664 | 0.9505 | 0.9995   |
+| 0.0013        | 2.0   | 1900 | 0.0011          | 0.9644    | 0.9758 | 0.9701 | 0.9996   |
+| 0.0006        | 3.0   | 2850 | 0.0010          | 0.9674    | 0.9784 | 0.9728 | 0.9997   |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.2

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,65 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-small",
+  "architectures": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "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-07,
+  "max_position_embeddings": 1024,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e25bfd6927e6d0660db35f3ca01fb0f35335c88198147266340e8248e7952d6e
+size 565269844

runs/Mar22_12-35-39_915a02c27372/events.out.tfevents.1711110949.915a02c27372.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46ea17aa12ce179a42676aa76fa089294b758320e05c16971ed6d86c9b497ed2
+size 8209

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d7f97394d075d51ad93d87e0a50bc8e70f4d2a892cfca0ec69647d7dfa19e01
+size 4920