Training in progress, epoch 1

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "answerdotai/ModernBERT-base",
   "architectures": [
-    "ModernBertForTokenClassification"
+    "DualModernBertForTokenClassification"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
@@ -21,34 +21,34 @@
   "hidden_activation": "gelu",
   "hidden_size": 768,
   "id2label": {
-    "B-address": 4,
-    "B-certificate": 24,
-    "B-date": 14,
-    "B-degree": 22,
-    "B-duration": 16,
-    "B-email": 6,
-    "B-individual_skill": 26,
-    "B-job_role": 20,
-    "B-language": 10,
-    "B-location": 12,
-    "B-name": 2,
-    "B-organization": 18,
-    "B-phone_number": 8,
-    "I-address": 5,
-    "I-certificate": 25,
-    "I-date": 15,
-    "I-degree": 23,
-    "I-duration": 17,
-    "I-email": 7,
-    "I-individual_skill": 27,
-    "I-job_role": 21,
-    "I-language": 11,
-    "I-location": 13,
-    "I-name": 3,
-    "I-organization": 19,
-    "I-phone_number": 9,
+    "B-address": 3,
+    "B-certificate": 23,
+    "B-date": 13,
+    "B-degree": 21,
+    "B-duration": 15,
+    "B-email": 5,
+    "B-individual_skill": 25,
+    "B-job_role": 19,
+    "B-language": 9,
+    "B-location": 11,
+    "B-name": 1,
+    "B-organization": 17,
+    "B-phone_number": 7,
+    "I-address": 4,
+    "I-certificate": 24,
+    "I-date": 14,
+    "I-degree": 22,
+    "I-duration": 16,
+    "I-email": 6,
+    "I-individual_skill": 26,
+    "I-job_role": 20,
+    "I-language": 10,
+    "I-location": 12,
+    "I-name": 2,
+    "I-organization": 18,
+    "I-phone_number": 8,
     "O": 0,
-    "O-section": 1,
+    "O-section": 27,
     "education_description": 33,
     "education_information": 32,
     "employment_description": 31,
@@ -60,34 +60,34 @@
   "initializer_range": 0.02,
   "intermediate_size": 1152,
   "label2id": {
-    "B-address": 4,
-    "B-certificate": 24,
-    "B-date": 14,
-    "B-degree": 22,
-    "B-duration": 16,
-    "B-email": 6,
-    "B-individual_skill": 26,
-    "B-job_role": 20,
-    "B-language": 10,
-    "B-location": 12,
-    "B-name": 2,
-    "B-organization": 18,
-    "B-phone_number": 8,
-    "I-address": 5,
-    "I-certificate": 25,
-    "I-date": 15,
-    "I-degree": 23,
-    "I-duration": 17,
-    "I-email": 7,
-    "I-individual_skill": 27,
-    "I-job_role": 21,
-    "I-language": 11,
-    "I-location": 13,
-    "I-name": 3,
-    "I-organization": 19,
-    "I-phone_number": 9,
+    "B-address": 3,
+    "B-certificate": 23,
+    "B-date": 13,
+    "B-degree": 21,
+    "B-duration": 15,
+    "B-email": 5,
+    "B-individual_skill": 25,
+    "B-job_role": 19,
+    "B-language": 9,
+    "B-location": 11,
+    "B-name": 1,
+    "B-organization": 17,
+    "B-phone_number": 7,
+    "I-address": 4,
+    "I-certificate": 24,
+    "I-date": 14,
+    "I-degree": 22,
+    "I-duration": 16,
+    "I-email": 6,
+    "I-individual_skill": 26,
+    "I-job_role": 20,
+    "I-language": 10,
+    "I-location": 12,
+    "I-name": 2,
+    "I-organization": 18,
+    "I-phone_number": 8,
     "O": 0,
-    "O-section": 1,
+    "O-section": 27,
     "education_description": 33,
     "education_information": 32,
     "employment_description": 31,
@@ -108,12 +108,12 @@
   "num_hidden_layers": 22,
   "pad_token_id": 50283,
   "position_embedding_type": "absolute",
-  "reference_compile": true,
+  "reference_compile": false,
   "repad_logits_with_grad": false,
   "sep_token_id": 50282,
   "sparse_pred_ignore_index": -100,
   "sparse_prediction": false,
   "torch_dtype": "float32",
   "transformers_version": "4.49.0",
-  "vocab_size": 50368
+  "vocab_size": 50369
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc8c0ffcf9ad7dc750538afa94b4d801bdb43b5c9220b45d82bea85c06d08f13
-size 598538224
+oid sha256:66635a1f764636bd9920b9e811936d4c59f7682d68ef81acac1d60d10a2c5855
+size 598541296

tokenizer.json

@@ -1051,6 +1051,15 @@
       "rstrip": false,
       "normalized": true,
       "special": false
+    },
+    {
+      "id": 50368,
+      "content": "[SECTION]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true,
+      "special": false
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -927,6 +927,14 @@
       "rstrip": false,
       "single_word": false,
       "special": false
+    },
+    "50368": {
+      "content": "[SECTION]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
   "clean_up_tokenization_spaces": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfef2ff16862d2106d2ea0b4ab2757dc787c873fdc7a6605d876abf5165d4fbf
+oid sha256:44b8732a07251e11935ffb1a06a24458ae0ee2a86b015a29f0fce4c8356e4570
 size 5304