model improved

config.json

@@ -3,113 +3,114 @@
     "BertForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "B-AUX",
-    "1": "I-PRON",
-    "2": "B-PUNCT",
-    "3": "I-NUM",
-    "4": "I-INTJ",
-    "5": "I-PUNCT",
-    "6": "SCONJ",
-    "7": "B-NOUN",
+    "0": "ADJ",
+    "1": "ADP",
+    "2": "ADV",
+    "3": "AUX",
+    "4": "B-ADJ",
+    "5": "B-ADP",
+    "6": "B-ADV",
+    "7": "B-AUX",
     "8": "B-CCONJ",
-    "9": "I-NOUN",
-    "10": "B-ADP",
-    "11": "I-DET",
-    "12": "NOUN",
-    "13": "B-PROPN",
-    "14": "ADJ",
-    "15": "B-INTJ",
-    "16": "B-X",
-    "17": "B-VERB",
-    "18": "SYM",
-    "19": "I-ADP",
-    "20": "B-ADJ",
-    "21": "I-PROPN",
-    "22": "B-PART",
-    "23": "I-PART",
-    "24": "B-NUM",
-    "25": "CCONJ",
-    "26": "I-VERB",
-    "27": "VERB",
-    "28": "I-X",
-    "29": "X",
-    "30": "I-ADJ",
-    "31": "PUNCT",
-    "32": "I-SYM",
-    "33": "B-ADV",
-    "34": "B-SCONJ",
-    "35": "PART",
-    "36": "NUM",
-    "37": "ADP",
-    "38": "B-PRON",
-    "39": "I-SCONJ",
-    "40": "PROPN",
-    "41": "I-CCONJ",
+    "9": "B-DET",
+    "10": "B-INTJ",
+    "11": "B-NOUN",
+    "12": "B-NUM",
+    "13": "B-PART",
+    "14": "B-PRON",
+    "15": "B-PROPN",
+    "16": "B-PUNCT",
+    "17": "B-SCONJ",
+    "18": "B-SYM",
+    "19": "B-VERB",
+    "20": "B-X",
+    "21": "CCONJ",
+    "22": "I-ADJ",
+    "23": "I-ADP",
+    "24": "I-ADV",
+    "25": "I-AUX",
+    "26": "I-CCONJ",
+    "27": "I-DET",
+    "28": "I-INTJ",
+    "29": "I-NOUN",
+    "30": "I-NUM",
+    "31": "I-PART",
+    "32": "I-PRON",
+    "33": "I-PROPN",
+    "34": "I-PUNCT",
+    "35": "I-SCONJ",
+    "36": "I-SYM",
+    "37": "I-VERB",
+    "38": "I-X",
+    "39": "NOUN",
+    "40": "NUM",
+    "41": "PART",
     "42": "PRON",
-    "43": "ADV",
-    "44": "B-SYM",
-    "45": "I-ADV",
-    "46": "AUX",
-    "47": "B-DET",
-    "48": "I-AUX"
+    "43": "PROPN",
+    "44": "PUNCT",
+    "45": "SCONJ",
+    "46": "SYM",
+    "47": "VERB",
+    "48": "X"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "ADJ": 14,
-    "ADP": 37,
-    "ADV": 43,
-    "AUX": 46,
-    "B-ADJ": 20,
-    "B-ADP": 10,
-    "B-ADV": 33,
-    "B-AUX": 0,
+    "ADJ": 0,
+    "ADP": 1,
+    "ADV": 2,
+    "AUX": 3,
+    "B-ADJ": 4,
+    "B-ADP": 5,
+    "B-ADV": 6,
+    "B-AUX": 7,
     "B-CCONJ": 8,
-    "B-DET": 47,
-    "B-INTJ": 15,
-    "B-NOUN": 7,
-    "B-NUM": 24,
-    "B-PART": 22,
-    "B-PRON": 38,
-    "B-PROPN": 13,
-    "B-PUNCT": 2,
-    "B-SCONJ": 34,
-    "B-SYM": 44,
-    "B-VERB": 17,
-    "B-X": 16,
-    "CCONJ": 25,
-    "I-ADJ": 30,
-    "I-ADP": 19,
-    "I-ADV": 45,
-    "I-AUX": 48,
-    "I-CCONJ": 41,
-    "I-DET": 11,
-    "I-INTJ": 4,
-    "I-NOUN": 9,
-    "I-NUM": 3,
-    "I-PART": 23,
-    "I-PRON": 1,
-    "I-PROPN": 21,
-    "I-PUNCT": 5,
-    "I-SCONJ": 39,
-    "I-SYM": 32,
-    "I-VERB": 26,
-    "I-X": 28,
-    "NOUN": 12,
-    "NUM": 36,
-    "PART": 35,
+    "B-DET": 9,
+    "B-INTJ": 10,
+    "B-NOUN": 11,
+    "B-NUM": 12,
+    "B-PART": 13,
+    "B-PRON": 14,
+    "B-PROPN": 15,
+    "B-PUNCT": 16,
+    "B-SCONJ": 17,
+    "B-SYM": 18,
+    "B-VERB": 19,
+    "B-X": 20,
+    "CCONJ": 21,
+    "I-ADJ": 22,
+    "I-ADP": 23,
+    "I-ADV": 24,
+    "I-AUX": 25,
+    "I-CCONJ": 26,
+    "I-DET": 27,
+    "I-INTJ": 28,
+    "I-NOUN": 29,
+    "I-NUM": 30,
+    "I-PART": 31,
+    "I-PRON": 32,
+    "I-PROPN": 33,
+    "I-PUNCT": 34,
+    "I-SCONJ": 35,
+    "I-SYM": 36,
+    "I-VERB": 37,
+    "I-X": 38,
+    "NOUN": 39,
+    "NUM": 40,
+    "PART": 41,
     "PRON": 42,
-    "PROPN": 40,
-    "PUNCT": 31,
-    "SCONJ": 6,
-    "SYM": 18,
-    "VERB": 27,
-    "X": 29
+    "PROPN": 43,
+    "PUNCT": 44,
+    "SCONJ": 45,
+    "SYM": 46,
+    "VERB": 47,
+    "X": 48
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
@@ -120,7 +121,7 @@
   "position_embedding_type": "absolute",
   "tokenizer_class": "BertTokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.7.0",
+  "transformers_version": "4.19.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 6291

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd1b1d3cc78fb698eaa3ef04291824e29a0d31fab419fe78b68943bbbf3e0387
-size 361366224
+oid sha256:9b8258f7c475fca7980396ebbade0cc300f773d94e4f109d2b482fe3344dab49
+size 361353229

supar.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08982b52f4d011e1fcd47bba2dd72d9f11ab928b1b587b43f94644912a33b8ae
-size 411801351
+oid sha256:57617003c4704ff1e4e5ce70a0c7cd20764ff0ef2ebdc8cde125fe355435ccf7
+size 411800936

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "do_word_tokenize": true, "do_subword_tokenize": true, "word_tokenizer_type": "basic", "subword_tokenizer_type": "character", "never_split": ["[PAD]", "[UNK]", "[CLS]", "[SEP]", "[MASK]"], "mecab_kwargs": null, "do_basic_tokenize": true, "tokenizer_class": "BertTokenizer"}
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "do_word_tokenize": true, "do_subword_tokenize": true, "word_tokenizer_type": "basic", "subword_tokenizer_type": "character", "never_split": ["[PAD]", "[UNK]", "[CLS]", "[SEP]", "[MASK]"], "mecab_kwargs": null, "do_basic_tokenize": true, "tokenizer_class": "BertTokenizerFast"}