Training in progress epoch 0

.gitignore

@@ -0,0 +1,2 @@
+step_*
+epoch_*

config.json

@@ -1,21 +1,24 @@
 {
-  "_name_or_path": "bert-base-chinese",
+  "_name_or_path": "hfl/chinese-roberta-wwm-ext-large",
   "architectures": [
     "BertForQuestionAnswering"
   ],
   "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,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "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 sha256:365152893bec30a1d6aef29c747d8429c88f502def5b9b9795701336201ae6f1
-size 406782566
+oid sha256:8322799f8192a73f5309ce410e4c1b4314d73a886d2ca2d27368358dccb75866
+size 1298033766

tokenizer.json

@@ -59,7 +59,7 @@
     "clean_text": true,
     "handle_chinese_chars": true,
     "strip_accents": null,
-    "lowercase": false
+    "lowercase": true
   },
   "pre_tokenizer": {
     "type": "BertPreTokenizer"

tokenizer_config.json

@@ -44,9 +44,9 @@
   "additional_special_tokens": [],
   "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,