initial release

config.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B",
+    "1": "E",
+    "2": "E2",
+    "3": "E3",
+    "4": "M",
+    "5": "S"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B": 0,
+    "E": 1,
+    "E2": 2,
+    "E3": 3,
+    "M": 4,
+    "S": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "BertTokenizer",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 26318
+}

eval_results_ner.txt

@@ -0,0 +1,8 @@
+eval_loss = 0.2782273292541504
+eval_accuracy_score = 0.9262469636974678
+eval_precision = 0.9145419977575197
+eval_recall = 0.901186530239708
+eval_f1 = 0.9078151463827728
+eval_runtime = 2.124
+eval_samples_per_second = 338.039
+epoch = 3.0

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f26c0d74c31c51ac42c98f0ea52eae0bf4353e65a71e58489fd35a03e7d9c13
+size 422760843

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "KoichiYasuoka/roberta-classical-chinese-base-char", "do_basic_tokenize": true, "never_split": null}