Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "princeton-nlp/sup-simcse-bert-base-uncased",
+  "_name_or_path": "bert-base-cased",
   "architectures": [
     "BertForTokenClassification"
   ],
@@ -32,5 +32,5 @@
   "transformers_version": "4.40.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3f7654a7f029a55c7f8ff5480f1b231ca637314458ec1cc49894e4c5cf1f3be
-size 435599164
+oid sha256:740c9ea6cab3bebc4a0eead7d59a6873b9a61de8c37299597e02fce1894e412c
+size 430911284

runs/May19_07-51-00_868affc172b8/events.out.tfevents.1716105061.868affc172b8.460.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b67cf4dab78e122e58c6d8ae0efd9132d3d810bac086c8c1cadfc7c54b8eca3
+size 5410

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": 512,
-  "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:a06b47f92bb9a638df9ae744ba8e50bb62c6a5f834b91b7711e355574ff29c01
+oid sha256:cd85e9b26d719b6908668c43858e54ac087c3b8b4639de76d055746aeb8a548c
 size 4984