Training in progress, epoch 0

config.json

@@ -1,12 +1,11 @@
 {
-  "_name_or_path": "michiyasunaga/BioLinkBERT-base",
+  "_name_or_path": "IVN-RIN/bioBIT",
   "architectures": [
     "BertForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
   "finetuning_task": "ner",
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -33,5 +32,5 @@
   "transformers_version": "4.44.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 28895
+  "vocab_size": 31102
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cee4c9d2ee855e2447078221c042736fb39db8199c683b551ecb6786938a563
-size 430601004
+oid sha256:ce13e72e198846567fbbb4f6037c4fe76f663a7b4bec5ee7dc6cd7c8f2e2595f
+size 437380924

tb/events.out.tfevents.1725539834.da2ff10c1388.1139.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd15781ef1cd34e30d741e354e5e56d64d899f841e4fb95a4e7cd7ccf789d212
+size 5787

tokenizer_config.json

@@ -8,7 +8,7 @@
       "single_word": false,
       "special": true
     },
-    "1": {
+    "101": {
       "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "2": {
+    "102": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "3": {
+    "103": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,7 +32,7 @@
       "single_word": false,
       "special": true
     },
-    "4": {
+    "104": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -44,14 +44,16 @@
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
+  "max_len": 512,
+  "model_max_length": 512,
   "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
+  "truncation": true,
   "unk_token": "[UNK]"
 }