Training in progress, epoch 1

config.json

@@ -1,12 +1,13 @@
 {
-  "activation": "gelu",
   "architectures": [
-    "DistilBertForTokenClassification"
+    "BertForTokenClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.3,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "B-art",
     "1": "B-eve",
@@ -27,6 +28,7 @@
     "9": "I-eve"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "B-art": "0",
     "B-eve": "1",
@@ -46,17 +48,16 @@
     "I-tim": "15",
     "O": "16"
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "output_past": true,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.50.1",
+  "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 sha256:6152f2b83a6c5d83c7f2b5541fadb95f89215d49acf4a3d2bd01bf9a4bdfa94b
-size 260828276
+oid sha256:a0091ca751a899236df7e7bd4b290cda993f77beca0327411aa7eb53b1dee96f
+size 430954348

tokenizer_config.json

@@ -51,6 +51,6 @@
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1a5afb5e68a28b88394eec330e9d43c459246e9e9b54801e00665074ec6c5df
+oid sha256:c1f9e1a821368fe9f9fe6a62958d379e4e03d6d9a7661909d63289cc189f3090
 size 5368