Training in progress, step 500

config.json

@@ -1,17 +1,14 @@
 {
-  "_name_or_path": "ckiplab/albert-base-chinese",
+  "_name_or_path": "ckiplab/bert-base-chinese",
   "architectures": [
-    "AlbertForTokenClassification"
+    "BertForTokenClassification"
   ],
-  "attention_probs_dropout_prob": 0,
-  "bos_token_id": 101,
-  "classifier_dropout_prob": 0.1,
-  "down_scale_factor": 1,
-  "embedding_size": 128,
-  "eos_token_id": 102,
-  "gap_size": 0,
-  "hidden_act": "relu",
-  "hidden_dropout_prob": 0,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
     "0": "0",
@@ -21,7 +18,6 @@
     "4": "I-BRAND"
   },
   "initializer_range": 0.02,
-  "inner_group_num": 1,
   "intermediate_size": 3072,
   "label2id": {
     "0": 0,
@@ -31,19 +27,21 @@
     "I-ITEM": 2
   },
   "layer_norm_eps": 1e-12,
-  "layers_to_keep": [],
   "max_position_embeddings": 512,
-  "model_type": "albert",
-  "net_structure_type": 0,
+  "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_groups": 1,
   "num_hidden_layers": 12,
-  "num_memory_blocks": 0,
   "pad_token_id": 0,
+  "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",
   "tokenizer_class": "BertTokenizerFast",
   "torch_dtype": "float32",
   "transformers_version": "4.29.0.dev0",
   "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 21128
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a70a36f19fe86f5cd9ce02cf4d0c8d67f05a002f7277678af894425bb05e7f74
-size 39857239
+oid sha256:72e2f0f6731826f857eac0e44be1fc9397f580defa5d870f13a53d0bedbc99c5
+size 406794033

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -54,7 +59,7 @@
     "clean_text": true,
     "handle_chinese_chars": true,
     "strip_accents": null,
-    "lowercase": false
+    "lowercase": true
   },
   "pre_tokenizer": {
     "type": "BertPreTokenizer"

tokenizer_config.json

@@ -1,9 +1,11 @@
 {
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": false,
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e69f91dd249aede855f60514e353ceb4c26aff7265de132eb94433d0cf326558
+oid sha256:5e890486c3302ca1997c48dcd9add3d9e4eaedef0818ddd6ab0b3cfc4bb45835
 size 3567