Training in progress, epoch 1

config.json

@@ -1,13 +1,14 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "dslim/bert-base-NER",
+  "_num_labels": 9,
   "architectures": [
-    "DistilBertForTokenClassification"
+    "BertForTokenClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "B-Product",
     "1": "I-Product",
@@ -25,6 +26,7 @@
     "13": "I-ModelNo"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "B-Country": 4,
     "B-HSCode": 6,
@@ -41,16 +43,17 @@
     "I-Product": 1,
     "I-Trademark": 3
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
   "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": "4.33.2",
-  "vocab_size": 30522
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db1586b3871f5c1d3e37e425f40f8bb7af5a5e8d45b8991950033fe026c6baea
-size 265529381
+oid sha256:453b673d06f8a293b5d6c4a7ae693960656e7274c08133d0edc81941bad65404
+size 430989481

tokenizer_config.json

@@ -1,13 +1,16 @@
 {
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": false,
   "mask_token": "[MASK]",
+  "max_len": 512,
   "model_max_length": 512,
+  "never_split": null,
   "pad_token": "[PAD]",
   "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 sha256:4324291a10f195d1ccad012a0b4dee94d24d99c562e5b7fb0e532767eb5bda1c
+oid sha256:caf42b6ce8541412a3418b0ab307072d8b8ce0f6baa0c757d63d94c5509b8074
 size 4027