Training in progress, epoch 1

config.json

@@ -0,0 +1,77 @@
+{
+  "_name_or_path": "google-bert/bert-large-cased-whole-word-masking",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Email",
+    "1": "O",
+    "2": "S\u0110T",
+    "3": "M\u00e3 \u0111\u01a1n",
+    "4": "Ti\u1ec1n",
+    "5": "Ph\u01b0\u01a1ng th\u1ee9c thanh to\u00e1n",
+    "6": "Gi\u1edd",
+    "7": "Ng\u00e0y tr\u1eebu t\u01b0\u1ee3ng",
+    "8": "\u0110\u01a1n v\u1ecb \u0111o",
+    "9": "CCCD - CMT",
+    "10": "STK",
+    "11": "Ng\u00e2n h\u00e0ng",
+    "12": "Ca",
+    "13": "S\u1ea3n ph\u1ea9m c\u1ee5 th\u1ec3",
+    "14": "Ng\u00e0y",
+    "15": "T\u00ean ng\u01b0\u1eddi",
+    "16": "Kh\u1ed1i l\u01b0\u1ee3ng",
+    "17": "\u0110\u1ecba ch\u1ec9 c\u1ee5 th\u1ec3",
+    "18": "S\u0110T tr\u1eebu t\u01b0\u1ee3ng",
+    "19": "\u0110\u1ecba ch\u1ec9 tr\u1eebu t\u01b0\u1ee3ng",
+    "20": "S\u1ea3n ph\u1ea9m tr\u1eebu t\u01b0\u1ee3ng"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "CCCD - CMT": 9,
+    "Ca": 12,
+    "Email": 0,
+    "Gi\u1edd": 6,
+    "Kh\u1ed1i l\u01b0\u1ee3ng": 16,
+    "M\u00e3 \u0111\u01a1n": 3,
+    "Ng\u00e0y": 14,
+    "Ng\u00e0y tr\u1eebu t\u01b0\u1ee3ng": 7,
+    "Ng\u00e2n h\u00e0ng": 11,
+    "O": 1,
+    "Ph\u01b0\u01a1ng th\u1ee9c thanh to\u00e1n": 5,
+    "STK": 10,
+    "S\u0110T": 2,
+    "S\u0110T tr\u1eebu t\u01b0\u1ee3ng": 18,
+    "S\u1ea3n ph\u1ea9m c\u1ee5 th\u1ec3": 13,
+    "S\u1ea3n ph\u1ea9m tr\u1eebu t\u01b0\u1ee3ng": 20,
+    "Ti\u1ec1n": 4,
+    "T\u00ean ng\u01b0\u1eddi": 15,
+    "\u0110\u01a1n v\u1ecb \u0111o": 8,
+    "\u0110\u1ecba ch\u1ec9 c\u1ee5 th\u1ec3": 17,
+    "\u0110\u1ecba ch\u1ec9 tr\u1eebu t\u01b0\u1ee3ng": 19
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "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:ce72e52af2548bc2afb4786aa0f007667d1877efa4fd9df6ce507dac78bf2f1f
+size 1330251572

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 +1,55 @@
+{
+  "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,
+  "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 sha256:355fbcedfb344e4e4df51e188b90fcb3e5e257a2164e5e5b352bed5a69665ece
+size 5048