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 +1,82 @@
+{
+  "_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": "Ti\u1ec1n c\u1ee5 th\u1ec3",
+    "2": "M\u00e3 \u0111\u01a1n",
+    "3": "S\u1ed1 c\u00f4ng",
+    "4": "Th\u00e1ng c\u1ee5 th\u1ec3",
+    "5": "V\u1ecb tr\u00ed",
+    "6": "S\u1ed1 \u0111i\u1ec3m",
+    "7": "C\u00f4ng",
+    "8": "L\u01b0\u01a1ng",
+    "9": "Ti\u1ec1n tr\u1eebu t\u01b0\u1ee3ng",
+    "10": "S\u1ed1 \u0111\u01a1n",
+    "11": "Th\u00e1ng tr\u1eebu t\u01b0\u1ee3ng",
+    "12": "Th\u1ee9",
+    "13": "Ph\u1ee5 c\u1ea5p",
+    "14": "S\u1ed1 gi\u1edd",
+    "15": "Kho\u1ea3ng th\u1eddi gian",
+    "16": "Th\u00f4ng tin CTT",
+    "17": "Kho",
+    "18": "Gi\u1edd",
+    "19": "N\u0103m c\u1ee5 th\u1ec3",
+    "20": "H\u00ecnh th\u1ee9c l\u00e0m vi\u1ec7c",
+    "21": "Gi\u1ea5y t\u1edd",
+    "22": "\u0110\u1ee3t",
+    "23": "T\u1ef7 l\u1ec7",
+    "24": "M\u00e3 s\u1ed1 thu\u1ebf"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "C\u00f4ng": 7,
+    "Gi\u1ea5y t\u1edd": 21,
+    "Gi\u1edd": 18,
+    "H\u00ecnh th\u1ee9c l\u00e0m vi\u1ec7c": 20,
+    "Kho": 17,
+    "Kho\u1ea3ng th\u1eddi gian": 15,
+    "L\u01b0\u01a1ng": 8,
+    "M\u00e3 s\u1ed1 thu\u1ebf": 24,
+    "M\u00e3 \u0111\u01a1n": 2,
+    "N\u0103m c\u1ee5 th\u1ec3": 19,
+    "O": 0,
+    "Ph\u1ee5 c\u1ea5p": 13,
+    "S\u1ed1 c\u00f4ng": 3,
+    "S\u1ed1 gi\u1edd": 14,
+    "S\u1ed1 \u0111i\u1ec3m": 6,
+    "S\u1ed1 \u0111\u01a1n": 10,
+    "Th\u00e1ng c\u1ee5 th\u1ec3": 4,
+    "Th\u00e1ng tr\u1eebu t\u01b0\u1ee3ng": 11,
+    "Th\u00f4ng tin CTT": 16,
+    "Th\u1ee9": 12,
+    "Ti\u1ec1n c\u1ee5 th\u1ec3": 1,
+    "Ti\u1ec1n tr\u1eebu t\u01b0\u1ee3ng": 9,
+    "T\u1ef7 l\u1ec7": 23,
+    "V\u1ecb tr\u00ed": 5,
+    "\u0110\u1ee3t": 22
+  },
+  "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": "4.46.3",
+  "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:b13f16c428bceb41a540dbde3d1c78f6af0e89485d646e4ba6143f52bd3871ae
+size 2235514364

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": false,
+  "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 sha256:01c8f358d467001c8a968119ca4df6e85a2b1ae2ca84009b47fbabf0a3596e79
+size 5368