Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_name_or_path": "dmis-lab/biobert-large-cased-v1.1-squad",
   "architectures": [
     "BertForQuestionAnswering"
   ],
@@ -8,19 +8,19 @@
   "gradient_checkpointing": false,
   "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,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.29.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 58996
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53713e4fbca84bdce8b5a5a632facefc4bdcaf9c836300b0af65c903e465fe0d
-size 430957037
+oid sha256:862dedfab0f830693df52c9a1f37fe0d1e1d9a691e64cc7163c74058e64c2997
+size 1453145069

tokenizer_config.json

@@ -1,9 +1,11 @@
 {
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": false,
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:985cd7a11a2d24d18346efa07792ca92548dcf3b4ca9bbac657ccc2cd31faafe
+oid sha256:6089a85f1880e003b1e5c90e6b452bf0b37c7f82e7126a9b94825ac662549a07
 size 3899