Fine-tuned KABERT on new Persian Excel dataset (review/label; 0/1/2)

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:447594881a01dc820757d2ce5f316dadcecaca5223304242813d37199db1ad7e
+oid sha256:436d731b1ef2439701d9aa48776df00f0a47d40559b6dbd39cdc49988e1902a2
 size 656180175

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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.json

@@ -7,7 +7,9 @@
     "stride": 0
   },
   "padding": {
-    "strategy": "BatchLongest",
+    "strategy": {
+      "Fixed": 192
+    },
     "direction": "Right",
     "pad_to_multiple_of": null,
     "pad_id": 0,

tokenizer_config.json

@@ -47,12 +47,19 @@
   "do_lower_case": true,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
+  "max_length": 192,
   "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": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }