End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+base_model: FacebookAI/xlm-roberta-large
+tags:
+- generated_from_trainer
+model-index:
+- name: XLM_roberta_large_NER_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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/tuevu_smu/huggingface/runs/l7js02lb)
+# XLM_roberta_large_NER_PII
+
+This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) 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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.0.dev0
+- Pytorch 1.13.1
+- Datasets 2.18.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,106 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "ACCOUNTNAME",
+    "1": "IBAN",
+    "2": "COINADDRESS",
+    "3": "ADDRESS",
+    "4": "AGE",
+    "5": "BIC",
+    "6": "CREDITCARDISSUER",
+    "7": "CREDITCARDNUMBER",
+    "8": "CURRENCY",
+    "9": "DATE",
+    "10": "EMAIL",
+    "11": "EYECOLOR",
+    "12": "GENDER",
+    "13": "GEO",
+    "14": "HEIGHT",
+    "15": "JOB",
+    "16": "MAC",
+    "17": "MISC",
+    "18": "USERNAME",
+    "19": "NAME",
+    "20": "NEARBYGPSCOORDINATE",
+    "21": "ORDINALDIRECTION",
+    "22": "ORG",
+    "23": "PASSWORD",
+    "24": "PHONEIMEI",
+    "25": "PHONENUMBER",
+    "26": "PREFIX",
+    "27": "SSN",
+    "28": "STREET",
+    "29": "TIME",
+    "30": "URL",
+    "31": "VEHICLEVIN",
+    "32": "VEHICLEVRM",
+    "33": "ZIPCODE",
+    "34": "IP",
+    "35": "NUM",
+    "36": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "ACCOUNTNAME": 0,
+    "ADDRESS": 3,
+    "AGE": 4,
+    "BIC": 5,
+    "COINADDRESS": 2,
+    "CREDITCARDISSUER": 6,
+    "CREDITCARDNUMBER": 7,
+    "CURRENCY": 8,
+    "DATE": 9,
+    "EMAIL": 10,
+    "EYECOLOR": 11,
+    "GENDER": 12,
+    "GEO": 13,
+    "HEIGHT": 14,
+    "IBAN": 1,
+    "IP": 34,
+    "JOB": 15,
+    "MAC": 16,
+    "MISC": 17,
+    "NAME": 19,
+    "NEARBYGPSCOORDINATE": 20,
+    "NUM": 35,
+    "O": 36,
+    "ORDINALDIRECTION": 21,
+    "ORG": 22,
+    "PASSWORD": 23,
+    "PHONEIMEI": 24,
+    "PHONENUMBER": 25,
+    "PREFIX": 26,
+    "SSN": 27,
+    "STREET": 28,
+    "TIME": 29,
+    "URL": 30,
+    "USERNAME": 18,
+    "VEHICLEVIN": 31,
+    "VEHICLEVRM": 32,
+    "ZIPCODE": 33
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1061fb47d83900ec9eb883c33c5bde809d9b4406737d625a2e38024904bdbc68
+size 2235563564

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
+size 17082832

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05fa0f272f34f15e50f532e88f80e7d985b36ab2dce3be29dd552f49955f4f46
+size 4603