Training in progress, epoch 1

config.json

@@ -1,10 +1,11 @@
 {
-  "_name_or_path": "emilyalsentzer/Bio_ClinicalBERT",
+  "_name_or_path": "bert-base-cased",
   "architectures": [
     "BertForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aecea909f28a83280d13f3f37cb6b6b7c2fab48fef6fc34b0643eedb297e2c55
+oid sha256:c70216e14904f504787ed1a82550a49dfd509d13bb684fe99f53cf31d49c6884
 size 430911284

runs/Sep12_06-41-32_194165fd9d08/events.out.tfevents.1726123295.194165fd9d08.723.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f5d20f30cae6a42c1a321c563861fafbe2491c9d6a4af1bb6a24592b0c1491f
+size 5732

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -54,7 +59,7 @@
     "clean_text": true,
     "handle_chinese_chars": true,
     "strip_accents": null,
-    "lowercase": true
+    "lowercase": false
   },
   "pre_tokenizer": {
     "type": "BertPreTokenizer"

tokenizer_config.json

@@ -43,11 +43,9 @@
   },
   "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,
-  "never_split": null,
+  "model_max_length": 512,
   "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 sha256:746442736b26f71f72c23cbbd0d0c0ffcee0a17cfa8ac6d498395879889cb114
+oid sha256:c1bf463753cc6cd9d5269b323696fb1f2fd280f36e722756c170e4d1f592fbcf
 size 5176