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 +1,74 @@
+{
+  "_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": "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-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": "4.40.2",
+  "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:d313eeecf0be282ab87ee72863aab4c309cc5c8103b9e6d050b8f3adf3fd1310
+size 2235497956

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 sha256:3a2eef4970a9735cf82d8d44fe437e4d04d97accf33f17364202012f51ec5f31
+size 5048