Training in progress, epoch 1

.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

config.json

@@ -0,0 +1,92 @@
+{
+  "_name_or_path": "Kudod/roberta-large-ner-ghtk-gam-data-standard-3090-30Aug-1",
+  "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": "O",
+    "1": "S\u1ea3n ph\u1ea9m",
+    "2": "\u0110\u1ecba ch\u1ec9 nh\u1eadn h\u00e0ng",
+    "3": "S\u1ed1 l\u01b0\u1ee3ng s\u1ea3n ph\u1ea9m",
+    "4": "\u0110\u1eb7c \u0111i\u1ec3m kh\u00e1c c\u1ee7a da",
+    "5": "\u0110\u01a1n v\u1ecb s\u1ea3n ph\u1ea9m",
+    "6": "D\u00e1ng ng\u01b0\u1eddi",
+    "7": "Phong c\u00e1ch mua s\u1eafm",
+    "8": "M\u00e0u s\u1eafc s\u1ea3n ph\u1ea9m",
+    "9": "M\u00e0u da",
+    "10": "Th\u1eddi gian nh\u1eadn h\u00e0ng",
+    "11": "C\u00e2n n\u1eb7ng kh\u00e1ch h\u00e0ng",
+    "12": "Ch\u1ea5t t\u00f3c",
+    "13": "Phong c\u00e1ch th\u1eddi trang",
+    "14": "Phong c\u00e1ch nh\u00e0 c\u1eeda",
+    "15": "Cung m\u1ec7nh",
+    "16": "Cung ho\u00e0ng \u0111\u1ea1o",
+    "17": "Lo\u1ea1i da",
+    "18": "\u0110\u1ed9 tu\u1ed5i kh\u00e1ch h\u00e0ng",
+    "19": "S\u1ed1 \u0111i\u1ec7n tho\u1ea1i nh\u1eadn h\u00e0ng",
+    "20": "Gi\u00e1 s\u1ea3n ph\u1ea9m",
+    "21": "D\u00e1ng khu\u00f4n m\u1eb7t",
+    "22": "\u0110\u1ed9 d\u00e0i t\u00f3c",
+    "23": "M\u1eadt \u0111\u1ed9 t\u00f3c",
+    "24": "Chi\u1ec1u cao kh\u00e1ch h\u00e0ng",
+    "25": "M\u00e3 s\u1ea3n ph\u1ea9m",
+    "26": "Kh\u1ed1i l\u01b0\u1ee3ng s\u1ea3n ph\u1ea9m",
+    "27": "S\u1ed1 \u0111o v\u00f2ng",
+    "28": "Chi\u1ec1u d\u00e0i s\u1ea3n ph\u1ea9m",
+    "29": "Chi\u1ec1u r\u1ed9ng s\u1ea3n ph\u1ea9m"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Chi\u1ec1u cao kh\u00e1ch h\u00e0ng": 24,
+    "Chi\u1ec1u d\u00e0i s\u1ea3n ph\u1ea9m": 28,
+    "Chi\u1ec1u r\u1ed9ng s\u1ea3n ph\u1ea9m": 29,
+    "Ch\u1ea5t t\u00f3c": 12,
+    "Cung ho\u00e0ng \u0111\u1ea1o": 16,
+    "Cung m\u1ec7nh": 15,
+    "C\u00e2n n\u1eb7ng kh\u00e1ch h\u00e0ng": 11,
+    "D\u00e1ng khu\u00f4n m\u1eb7t": 21,
+    "D\u00e1ng ng\u01b0\u1eddi": 6,
+    "Gi\u00e1 s\u1ea3n ph\u1ea9m": 20,
+    "Kh\u1ed1i l\u01b0\u1ee3ng s\u1ea3n ph\u1ea9m": 26,
+    "Lo\u1ea1i da": 17,
+    "M\u00e0u da": 9,
+    "M\u00e0u s\u1eafc s\u1ea3n ph\u1ea9m": 8,
+    "M\u00e3 s\u1ea3n ph\u1ea9m": 25,
+    "M\u1eadt \u0111\u1ed9 t\u00f3c": 23,
+    "O": 0,
+    "Phong c\u00e1ch mua s\u1eafm": 7,
+    "Phong c\u00e1ch nh\u00e0 c\u1eeda": 14,
+    "Phong c\u00e1ch th\u1eddi trang": 13,
+    "S\u1ea3n ph\u1ea9m": 1,
+    "S\u1ed1 l\u01b0\u1ee3ng s\u1ea3n ph\u1ea9m": 3,
+    "S\u1ed1 \u0111i\u1ec7n tho\u1ea1i nh\u1eadn h\u00e0ng": 19,
+    "S\u1ed1 \u0111o v\u00f2ng": 27,
+    "Th\u1eddi gian nh\u1eadn h\u00e0ng": 10,
+    "\u0110\u01a1n v\u1ecb s\u1ea3n ph\u1ea9m": 5,
+    "\u0110\u1eb7c \u0111i\u1ec3m kh\u00e1c c\u1ee7a da": 4,
+    "\u0110\u1ecba ch\u1ec9 nh\u1eadn h\u00e0ng": 2,
+    "\u0110\u1ed9 d\u00e0i t\u00f3c": 22,
+    "\u0110\u1ed9 tu\u1ed5i kh\u00e1ch h\u00e0ng": 18
+  },
+  "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": "4.44.2",
+  "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:b9e6b5ed8dbd7c2d5b6aa1028c9312cd39e09adfb3632f65e701fa1b596c586d
+size 2235534864

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94cd5ebfadbb8e9954373d20e84f0b18c5eb631e24ff494da1c134c073c521bc
+size 5176