Training in progress, epoch 1

config.json

@@ -1,13 +1,15 @@
 {
-  "_name_or_path": "dslim/distilbert-NER",
-  "activation": "gelu",
+  "_name_or_path": "dslim/bert-large-NER",
   "architectures": [
-    "DistilBertForTokenClassification"
+    "BertForTokenClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "eos_token_ids": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
   "id2label": {
     "0": "O",
     "1": "B-PER",
@@ -20,6 +22,7 @@
     "8": "I-MISC"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 4096,
   "label2id": {
     "B-LOC": 5,
     "B-MISC": 7,
@@ -31,17 +34,22 @@
     "I-PER": 2,
     "O": 0
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "output_past": true,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "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": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c1261e8f7ca8d81238384c2eaae01edac4d004c419bd0a86c1e637f8441e237
-size 260803668
+oid sha256:f91cd20714cb9668e96a183ea314d7a882531ec288095aaead8db82400d495e0
+size 1330202364

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e08409fa69a4a99665de29223988dce134bc21801796a0fa9b55da37e56a12df
+oid sha256:1c918981c67aa306963e9ecdc488dce3db8793211d7d601d816e505d8670908b
 size 5112