Training in progress, step 500

config.json

@@ -1,14 +1,17 @@
 {
-  "_name_or_path": "ckiplab/bert-base-chinese",
+  "_name_or_path": "ckiplab/albert-base-chinese",
   "architectures": [
-    "BertForTokenClassification"
+    "AlbertForTokenClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "directionality": "bidi",
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
+  "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,
   "hidden_size": 768,
   "id2label": {
     "0": "0",
@@ -18,6 +21,7 @@
     "4": "I-BRAND"
   },
   "initializer_range": 0.02,
+  "inner_group_num": 1,
   "intermediate_size": 3072,
   "label2id": {
     "0": 0,
@@ -27,21 +31,19 @@
     "I-ITEM": 2
   },
   "layer_norm_eps": 1e-12,
+  "layers_to_keep": [],
   "max_position_embeddings": 512,
-  "model_type": "bert",
+  "model_type": "albert",
+  "net_structure_type": 0,
   "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:d62a2f3e526daf971a0ac05bdfdaf91bda5e415b1b30bac9eca09671108a3369
-size 406794033
+oid sha256:62e68403571baaa290b0d19936f39efae0d5c517d380fc22ca099df13371e43c
+size 39857239