End of training

all_results.json

@@ -1 +1 @@
-{"eval_accuracy": 0.02}
+{"eval_accuracy": 0.9494848786972416}

config.json

@@ -1,11 +1,13 @@
 {
-  "_name_or_path": "bert-base-chinese",
+  "_name_or_path": "hfl/chinese-roberta-wwm-ext",
   "architectures": [
     "BertForMultipleChoice"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
   "directionality": "bidi",
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -16,6 +18,7 @@
   "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
+  "output_past": true,
   "pad_token_id": 0,
   "pooler_fc_size": 768,
   "pooler_num_attention_heads": 12,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b393b363e0474986dd2150e8e1ab781133b5c1f6438c26f4d2159edaf205903
+oid sha256:cc33334cb78faceadf51ee82b548c670539725a7256af6b2a487c07f4e465ad4
 size 409142065

tokenizer.json

@@ -6,16 +6,7 @@
     "strategy": "LongestFirst",
     "stride": 0
   },
-  "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,
@@ -68,7 +59,7 @@
     "clean_text": true,
     "handle_chinese_chars": true,
     "strip_accents": null,
-    "lowercase": false
+    "lowercase": true
   },
   "pre_tokenizer": {
     "type": "BertPreTokenizer"

tokenizer_config.json

@@ -1,9 +1,9 @@
 {
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": false,
+  "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,