Training in progress, epoch 1

config.json

@@ -1,52 +1,52 @@
-{
-  "add_cross_attention": false,
-  "architectures": [
-    "BertForTokenClassification"
-  ],
-  "attention_probs_dropout_prob": 0.3,
-  "bos_token_id": null,
-  "classifier_dropout": null,
-  "dtype": "float32",
-  "eos_token_id": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.3,
-  "hidden_size": 768,
-  "id2label": {
-    "0": "O",
-    "1": "B-PER",
-    "2": "I-PER",
-    "3": "B-ORG",
-    "4": "I-ORG",
-    "5": "B-LOC",
-    "6": "I-LOC",
-    "7": "B-MISC",
-    "8": "I-MISC"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "is_decoder": false,
-  "label2id": {
-    "B-LOC": 5,
-    "B-MISC": 7,
-    "B-ORG": 3,
-    "B-PER": 1,
-    "I-LOC": 6,
-    "I-MISC": 8,
-    "I-ORG": 4,
-    "I-PER": 2,
-    "O": 0
-  },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
-  "tie_word_embeddings": true,
-  "transformers_version": "5.0.0",
-  "type_vocab_size": 2,
-  "use_cache": false,
-  "vocab_size": 28996
-}
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.3,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.3,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.4",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 28996
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e61dea82a39c247d497b26ecbd7eba6087dc6f4c22d0aae9f24a23b594cb28b9
+oid sha256:a1651fea32692fb2e7c3240cfa2b8dbb516842991848cdeff84fef7b4621b6c0
 size 430929716

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0eedbd656df25542bf5eb27d41b9fa5e4f0159fb3f0477a3621e4a4afd9f500
-size 5201
+oid sha256:ee01e16b8da66d8e146dc41eed8ff3272f5a7c6b0374373c09c3918b92635b38
+size 5265