update new model

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "bert-base-multilingual-uncased",
+  "architectures": [
+    "PunctuationPredictionModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "finetuning_task": "punctuation_prediction",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 105882
+}

eval_results.txt

@@ -0,0 +1,12 @@
+              precision    recall  f1-score   support
+
+      PERIOD     0.5637    0.5281    0.5453     29643
+       COMMA     0.5599    0.3249    0.4111     21231
+       COLON     0.0000    0.0000    0.0000      1153
+       QMARK     0.5656    0.6168    0.5901      5271
+      EXCLAM     0.4764    0.4733    0.4749      9167
+   SEMICOLON     0.0000    0.0000    0.0000        43
+
+   micro avg     0.5486    0.4532    0.4963     66508
+   macro avg     0.3609    0.3238    0.3369     66508
+weighted avg     0.5404    0.4532    0.4865     66508

model_config.json

@@ -0,0 +1 @@
+{"bert_model": "bert-base-multilingual-uncased", "do_lower": true, "max_seq_length": 190, "num_labels": 10, "label_map": {"1": "O", "2": "PERIOD", "3": "COMMA", "4": "COLON", "5": "QMARK", "6": "EXCLAM", "7": "SEMICOLON", "8": "[CLS]", "9": "[SEP]"}}

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "additional_special_tokens": ["<NUM>", "<URL>", "<EMAIL>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "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, "special_tokens_map_file": null, "tokenizer_file": "/root/.cache/huggingface/transformers/857db185d48b92f3e6141ef5092d8d5dbebab7eef1bacc6c9eaf85cf23807641.73ad1f9fd9f94089672128003fb4a687b64b73b2bfb8d08766bbc71feec8cd96", "name_or_path": "bert-base-multilingual-uncased", "tokenizer_class": "BertTokenizer"}