Training in progress, epoch 1

config.json

@@ -1,10 +1,11 @@
 {
-  "_name_or_path": "google-bert/bert-large-uncased",
+  "_name_or_path": "google-bert/bert-large-cased",
   "architectures": [
     "BertForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "directionality": "bidi",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
@@ -27,10 +28,15 @@
   "num_attention_heads": 16,
   "num_hidden_layers": 24,
   "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.41.0",
   "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 sha256:2275dd353e3d1f8fa7a26f344d06aa2f56df8b56c4dae49594df1b48e8ba9280
-size 1336428268
+oid sha256:d30dcba7e825c3c5c228f9c03de4654fe8cd3e82d1b3d6df2965ecc858a86098
+size 1330177764

runs/Jul23_17-17-44_cn2363/events.out.tfevents.1721769470.cn2363.2033351.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18f12356b6697608d6b0b5319cab6ba283b2ae9cef32169bf7123e9d0e264ac8
+size 5557

tokenizer_config.json

@@ -43,7 +43,7 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcc380d6ec26c354d12d8181815640cb126f7fd89883d53c46feeb0613a3e360
+oid sha256:91b334d2742e742970282325496d38356e64cba8c732e95385b926ce118f9d5a
 size 4655