Training in progress, step 5780

config.json

@@ -0,0 +1,101 @@
+{
+  "_name_or_path": "NlpHUST/ner-vietnamese-electra-base",
+  "architectures": [
+    "ElectraForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "finetuning_task": "ner",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "I-LOCATION",
+    "1": "I-DISEASE",
+    "2": "B-AGE",
+    "3": "I-ROLE",
+    "4": "B-ROLE",
+    "5": "I-DATETIME",
+    "6": "B-TRANSPORTATION",
+    "7": "O",
+    "8": "B-DISEASE",
+    "9": "I-PHONE",
+    "10": "B-GENDER",
+    "11": "I-PRODUCT",
+    "12": "I-QUANTITY",
+    "13": "B-DATETIME",
+    "14": "B-QUANTITY",
+    "15": "I-EMAIL",
+    "16": "B-EMAIL",
+    "17": "B-LAW",
+    "18": "I-GENDER",
+    "19": "I-AGE",
+    "20": "I-ORGANIZATION",
+    "21": "I-EVENT",
+    "22": "B-PRODUCT",
+    "23": "I-LAW",
+    "24": "I-URL",
+    "25": "B-LOCATION",
+    "26": "B-EVENT",
+    "27": "B-URL",
+    "28": "I-TRANSPORTATION",
+    "29": "B-PERSON",
+    "30": "B-PHONE",
+    "31": "B-ORGANIZATION",
+    "32": "I-PERSON"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-AGE": 2,
+    "B-DATETIME": 13,
+    "B-DISEASE": 8,
+    "B-EMAIL": 16,
+    "B-EVENT": 26,
+    "B-GENDER": 10,
+    "B-LAW": 17,
+    "B-LOCATION": 25,
+    "B-ORGANIZATION": 31,
+    "B-PERSON": 29,
+    "B-PHONE": 30,
+    "B-PRODUCT": 22,
+    "B-QUANTITY": 14,
+    "B-ROLE": 4,
+    "B-TRANSPORTATION": 6,
+    "B-URL": 27,
+    "I-AGE": 19,
+    "I-DATETIME": 5,
+    "I-DISEASE": 1,
+    "I-EMAIL": 15,
+    "I-EVENT": 21,
+    "I-GENDER": 18,
+    "I-LAW": 23,
+    "I-LOCATION": 0,
+    "I-ORGANIZATION": 20,
+    "I-PERSON": 32,
+    "I-PHONE": 9,
+    "I-PRODUCT": 11,
+    "I-QUANTITY": 12,
+    "I-ROLE": 3,
+    "I-TRANSPORTATION": 28,
+    "I-URL": 24,
+    "O": 7
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 62000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dfb176bcd5b58b996fe0220ec808c897fe301648fc379e8c4c146b3fc8491e0
+size 532392452

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_length": 256,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "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:d89c6f407e1c9c36def48115a0e1d0fb47811eba563849ebe6b78eaad11d007f
+size 5112