Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1afd738da8e061209b4fb5f71085049db473642ef078b204b749307c1f08e958
+oid sha256:784d4b73a75d3f656f1e78aa407449a5fcfa9bb9662064b2c530f68e20f0ac19
 size 711452684

tokenizer_config.json

@@ -8,7 +8,7 @@
       "single_word": false,
       "special": true
     },
-    "1": {
+    "100": {
       "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "2": {
+    "101": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "3": {
+    "102": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,7 +32,7 @@
       "single_word": false,
       "special": true
     },
-    "4": {
+    "103": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -43,19 +43,15 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": false,
-  "do_subword_tokenize": true,
-  "do_word_tokenize": true,
-  "jumanpp_kwargs": null,
   "mask_token": "[MASK]",
-  "mecab_kwargs": null,
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "subword_tokenizer_type": "wordpiece",
-  "sudachi_kwargs": null,
-  "tokenizer_class": "BertJapaneseTokenizer",
-  "unk_token": "[UNK]",
-  "word_tokenizer_type": "mecab"
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }