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 +1,174 @@
+{
+  "_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": "O",
+    "1": "Ph\u01b0\u01a1ng th\u1ee9c ho\u1ea1t \u0111\u1ed9ng",
+    "2": "Lo\u1ea1i thi\u1ebft b\u1ecb an to\u00e0n",
+    "3": "Lo\u1ea1i \u0111\u00e8n",
+    "4": "Lo\u1ea1i \u0111\u1ed3 ch\u0103m s\u00f3c s\u1ee9c kh\u1ecfe m\u1eb9",
+    "5": "Lo\u1ea1i hoa",
+    "6": "Nh\u00f3m tu\u1ed5i",
+    "7": "Lo\u1ea1i trang thi\u1ebft b\u1ecb th\u1ec3 thao",
+    "8": "Lo\u1ea1i v\u1eadt d\u1ee5ng h\u1ed3 c\u00e1",
+    "9": "Lo\u1ea1i voucher & d\u1ecbch v\u1ee5",
+    "10": "Chi\u1ec1u cao",
+    "11": "Lo\u1ea1i tr\u00f2 ch\u01a1i",
+    "12": "Lo\u1ea1i thi\u1ebft b\u1ecb \u00e2m thanh",
+    "13": "Lo\u1ea1i b\u1ed9 \u0111\u1ed3 b\u00e0n \u0103n",
+    "14": "Lo\u1ea1i \u0111\u1ed3 d\u00f9ng ph\u00f2ng kh\u00e1ch",
+    "15": "Lo\u1ea1i thi\u1ebft b\u1ecb \u0111i\u1ec7n gia d\u1ee5ng",
+    "16": "Chi\u1ec1u d\u00e0i",
+    "17": "Lo\u1ea1i gi\u00e0y d\u00e9p",
+    "18": "Lo\u1ea1i \u0111\u1ed3 d\u00f9ng ph\u00f2ng t\u1eafm",
+    "19": "Th\u1ec3 t\u00edch",
+    "20": "Lo\u1ea1i thi\u1ebft b\u1ecb y t\u1ebf",
+    "21": "Gi\u1edbi t\u00ednh",
+    "22": "Phong c\u00e1ch",
+    "23": "Lo\u1ea1i ph\u1ee5 ki\u1ec7n \u0111i\u1ec7n t\u1eed",
+    "24": "Lo\u1ea1i \u0111\u1ed3 v\u1eadt s\u01b0u t\u1ea7m",
+    "25": "M\u00f9i h\u01b0\u01a1ng",
+    "26": "Ch\u1ee9c n\u0103ng h\u1ed7 tr\u1ee3 s\u1ee9c kh\u1ecfe",
+    "27": "T\u00ecnh tr\u1ea1ng",
+    "28": "C\u1ed5 \u00e1o",
+    "29": "C\u00e2n n\u1eb7ng",
+    "30": "M\u1eabu xe t\u01b0\u01a1ng th\u00edch",
+    "31": "Lo\u1ea1i \u0111\u1ed3 gia d\u1ee5ng b\u1ebfp",
+    "32": "Lo\u1ea1i \u1ed1p",
+    "33": "H\u01b0\u01a1ng v\u1ecb",
+    "34": "Lo\u1ea1i tr\u00e1i c\u00e2y",
+    "35": "Th\u00e0nh Ph\u1ea7n Ho\u1ea1t T\u00ednh",
+    "36": "Lo\u1ea1i \u0111\u1ed3 ch\u01a1i",
+    "37": "Dung t\u00edch",
+    "38": "Xu\u1ea5t x\u1ee9",
+    "39": "T\u00edch h\u1ee3p ph\u1ee5 ki\u1ec7n",
+    "40": "Lo\u1ea1i \u0111\u1ed3 d\u00f9ng ph\u00f2ng ng\u1ee7",
+    "41": "Lo\u1ea1i d\u1ee5ng c\u1ee5 & thi\u1ebft b\u1ecb s\u1eeda ch\u1eefa",
+    "42": "Lo\u1ea1i v\u1eadt d\u1ee5ng l\u00e0m v\u01b0\u1eddn",
+    "43": "Ch\u1ee9c n\u0103ng l\u00e0m \u0111\u1eb9p",
+    "44": "Lo\u1ea1i \u0111\u1ed3 d\u00f9ng ch\u0103m s\u00f3c b\u00e9",
+    "45": "Tr\u1ecdng l\u01b0\u1ee3ng",
+    "46": "Thi\u1ebft b\u1ecb t\u01b0\u01a1ng th\u00edch",
+    "47": "H\u00ecnh th\u1ee9c s\u1ea3n ph\u1ea9m",
+    "48": "Lo\u1ea1i thi\u1ebft b\u1ecb v\u00e0 d\u1ee5ng c\u1ee5 l\u00e0m \u0111\u1eb9p",
+    "49": "Lo\u1ea1i trang ph\u1ee5c",
+    "50": "Th\u00e0nh ph\u1ea7n",
+    "51": "Ch\u1ea5t li\u1ec7u",
+    "52": "Lo\u1ea1i \u0111\u1ed3 d\u00f9ng v\u0103n ph\u00f2ng ph\u1ea9m",
+    "53": "Lo\u1ea1i ph\u1ee5 ki\u1ec7n nh\u00e0 b\u1ebfp",
+    "54": "Lo\u1ea1i thi\u1ebft b\u1ecb v\u00e0 linh ki\u1ec7n \u0111i\u1ec7n t\u1eed",
+    "55": "Lo\u1ea1i trang s\u1ee9c / ph\u1ee5 ki\u1ec7n",
+    "56": "Size",
+    "57": "Lo\u1ea1i th\u1ee9c \u0103n ch\u1ebf bi\u1ebfn s\u1eb5n",
+    "58": "Th\u1ec3 lo\u1ea1i s\u00e1ch truy\u1ec7n",
+    "59": "Lo\u1ea1i v\u1eadt d\u1ee5ng ch\u0103m s\u00f3c c\u00e1 nh\u00e2n",
+    "60": "T\u00ednh n\u0103ng",
+    "61": "Th\u01b0\u01a1ng hi\u1ec7u",
+    "62": "Ki\u1ec3u \u0111\u00f3ng g\u00f3i",
+    "63": "Lo\u1ea1i thu\u1ed1c & th\u1ef1c ph\u1ea9m ch\u1ee9c n\u0103ng",
+    "64": "Lo\u1ea1i ph\u1ee5 ki\u1ec7n / linh ki\u1ec7n xe",
+    "65": "Lo\u1ea1i v\u1eadt d\u1ee5ng trong nh\u00e0 kh\u00e1c",
+    "66": "M\u00e0u s\u1eafc",
+    "67": "Lo\u1ea1i th\u1ef1c ph\u1ea9m",
+    "68": "Lo\u1ea1i gi\u1ed1ng",
+    "69": "M\u1eabu",
+    "70": "Lo\u1ea1i s\u1ea3n ph\u1ea9m l\u00e0m \u0111\u1eb9p"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Chi\u1ec1u cao": 10,
+    "Chi\u1ec1u d\u00e0i": 16,
+    "Ch\u1ea5t li\u1ec7u": 51,
+    "Ch\u1ee9c n\u0103ng h\u1ed7 tr\u1ee3 s\u1ee9c kh\u1ecfe": 26,
+    "Ch\u1ee9c n\u0103ng l\u00e0m \u0111\u1eb9p": 43,
+    "C\u00e2n n\u1eb7ng": 29,
+    "C\u1ed5 \u00e1o": 28,
+    "Dung t\u00edch": 37,
+    "Gi\u1edbi t\u00ednh": 21,
+    "H\u00ecnh th\u1ee9c s\u1ea3n ph\u1ea9m": 47,
+    "H\u01b0\u01a1ng v\u1ecb": 33,
+    "Ki\u1ec3u \u0111\u00f3ng g\u00f3i": 62,
+    "Lo\u1ea1i b\u1ed9 \u0111\u1ed3 b\u00e0n \u0103n": 13,
+    "Lo\u1ea1i d\u1ee5ng c\u1ee5 & thi\u1ebft b\u1ecb s\u1eeda ch\u1eefa": 41,
+    "Lo\u1ea1i gi\u00e0y d\u00e9p": 17,
+    "Lo\u1ea1i gi\u1ed1ng": 68,
+    "Lo\u1ea1i hoa": 5,
+    "Lo\u1ea1i ph\u1ee5 ki\u1ec7n / linh ki\u1ec7n xe": 64,
+    "Lo\u1ea1i ph\u1ee5 ki\u1ec7n nh\u00e0 b\u1ebfp": 53,
+    "Lo\u1ea1i ph\u1ee5 ki\u1ec7n \u0111i\u1ec7n t\u1eed": 23,
+    "Lo\u1ea1i s\u1ea3n ph\u1ea9m l\u00e0m \u0111\u1eb9p": 70,
+    "Lo\u1ea1i thi\u1ebft b\u1ecb an to\u00e0n": 2,
+    "Lo\u1ea1i thi\u1ebft b\u1ecb v\u00e0 d\u1ee5ng c\u1ee5 l\u00e0m \u0111\u1eb9p": 48,
+    "Lo\u1ea1i thi\u1ebft b\u1ecb v\u00e0 linh ki\u1ec7n \u0111i\u1ec7n t\u1eed": 54,
+    "Lo\u1ea1i thi\u1ebft b\u1ecb y t\u1ebf": 20,
+    "Lo\u1ea1i thi\u1ebft b\u1ecb \u00e2m thanh": 12,
+    "Lo\u1ea1i thi\u1ebft b\u1ecb \u0111i\u1ec7n gia d\u1ee5ng": 15,
+    "Lo\u1ea1i thu\u1ed1c & th\u1ef1c ph\u1ea9m ch\u1ee9c n\u0103ng": 63,
+    "Lo\u1ea1i th\u1ee9c \u0103n ch\u1ebf bi\u1ebfn s\u1eb5n": 57,
+    "Lo\u1ea1i th\u1ef1c ph\u1ea9m": 67,
+    "Lo\u1ea1i trang ph\u1ee5c": 49,
+    "Lo\u1ea1i trang s\u1ee9c / ph\u1ee5 ki\u1ec7n": 55,
+    "Lo\u1ea1i trang thi\u1ebft b\u1ecb th\u1ec3 thao": 7,
+    "Lo\u1ea1i tr\u00e1i c\u00e2y": 34,
+    "Lo\u1ea1i tr\u00f2 ch\u01a1i": 11,
+    "Lo\u1ea1i voucher & d\u1ecbch v\u1ee5": 9,
+    "Lo\u1ea1i v\u1eadt d\u1ee5ng ch\u0103m s\u00f3c c\u00e1 nh\u00e2n": 59,
+    "Lo\u1ea1i v\u1eadt d\u1ee5ng h\u1ed3 c\u00e1": 8,
+    "Lo\u1ea1i v\u1eadt d\u1ee5ng l\u00e0m v\u01b0\u1eddn": 42,
+    "Lo\u1ea1i v\u1eadt d\u1ee5ng trong nh\u00e0 kh\u00e1c": 65,
+    "Lo\u1ea1i \u0111\u00e8n": 3,
+    "Lo\u1ea1i \u0111\u1ed3 ch\u0103m s\u00f3c s\u1ee9c kh\u1ecfe m\u1eb9": 4,
+    "Lo\u1ea1i \u0111\u1ed3 ch\u01a1i": 36,
+    "Lo\u1ea1i \u0111\u1ed3 d\u00f9ng ch\u0103m s\u00f3c b\u00e9": 44,
+    "Lo\u1ea1i \u0111\u1ed3 d\u00f9ng ph\u00f2ng kh\u00e1ch": 14,
+    "Lo\u1ea1i \u0111\u1ed3 d\u00f9ng ph\u00f2ng ng\u1ee7": 40,
+    "Lo\u1ea1i \u0111\u1ed3 d\u00f9ng ph\u00f2ng t\u1eafm": 18,
+    "Lo\u1ea1i \u0111\u1ed3 d\u00f9ng v\u0103n ph\u00f2ng ph\u1ea9m": 52,
+    "Lo\u1ea1i \u0111\u1ed3 gia d\u1ee5ng b\u1ebfp": 31,
+    "Lo\u1ea1i \u0111\u1ed3 v\u1eadt s\u01b0u t\u1ea7m": 24,
+    "Lo\u1ea1i \u1ed1p": 32,
+    "M\u00e0u s\u1eafc": 66,
+    "M\u00f9i h\u01b0\u01a1ng": 25,
+    "M\u1eabu": 69,
+    "M\u1eabu xe t\u01b0\u01a1ng th\u00edch": 30,
+    "Nh\u00f3m tu\u1ed5i": 6,
+    "O": 0,
+    "Phong c\u00e1ch": 22,
+    "Ph\u01b0\u01a1ng th\u1ee9c ho\u1ea1t \u0111\u1ed9ng": 1,
+    "Size": 56,
+    "Thi\u1ebft b\u1ecb t\u01b0\u01a1ng th\u00edch": 46,
+    "Th\u00e0nh Ph\u1ea7n Ho\u1ea1t T\u00ednh": 35,
+    "Th\u00e0nh ph\u1ea7n": 50,
+    "Th\u01b0\u01a1ng hi\u1ec7u": 61,
+    "Th\u1ec3 lo\u1ea1i s\u00e1ch truy\u1ec7n": 58,
+    "Th\u1ec3 t\u00edch": 19,
+    "Tr\u1ecdng l\u01b0\u1ee3ng": 45,
+    "T\u00ecnh tr\u1ea1ng": 27,
+    "T\u00edch h\u1ee3p ph\u1ee5 ki\u1ec7n": 39,
+    "T\u00ednh n\u0103ng": 60,
+    "Xu\u1ea5t x\u1ee9": 38
+  },
+  "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 sha256:4c713cecaad417d83c2d251c84e4a68b620dabdc487dc3756248543e4e07c8a9
+size 2235702964

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 sha256:8c799331196ab4aa8c224d982166cf96ae0f99e5c7ebf63e074ad0e199c64c73
+size 5304