Training in progress epoch 0

README.md

@@ -1,4 +1,5 @@
 ---
+license: apache-2.0
 tags:
 - generated_from_keras_callback
 model-index:
@@ -11,10 +12,9 @@ probably proofread and complete it, then remove this comment. -->
 
 # Xzt/bert-finetuned-ner
 
-This model was trained from scratch on an unknown dataset.
+This model is a fine-tuned version of [hfl/chinese-bert-wwm-ext](https://huggingface.co/hfl/chinese-bert-wwm-ext) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.1187
-- Validation Loss: 0.0612
+- Train Loss: 0.0622
 - Epoch: 0
 
 ## Model description
@@ -34,14 +34,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 3510, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
-- training_precision: mixed_float16
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 7039, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- training_precision: float32
 
 ### Training results
 
-| Train Loss | Validation Loss | Epoch |
-|:----------:|:---------------:|:-----:|
-| 0.1187     | 0.0612          | 0     |
+| Train Loss | Epoch |
+|:----------:|:-----:|
+| 0.0622     | 0     |
 
 
 ### Framework versions

config.json

@@ -1,36 +1,24 @@
 {
-  "_name_or_path": "./bert-base-cased-model",
+  "_name_or_path": "hfl/chinese-bert-wwm-ext",
   "architectures": [
     "BertForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "directionality": "bidi",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "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"
+    "1": "B-loc",
+    "2": "I-loc"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "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",
+    "B-loc": "1",
+    "I-loc": "2",
     "O": "0"
   },
   "layer_norm_eps": 1e-12,
@@ -38,10 +26,16 @@
   "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
+  "output_past": true,
   "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",
   "transformers_version": "4.18.0",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 21128
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c627269de06d8ca4304e485a47eabd99fee3155f6923ec55f32296620daeb668
-size 431179820
+oid sha256:c1d2ef774a3fcdc7d9626f7c5117db295bb624aae813efb1c9261156080b21c7
+size 406990868

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "./bert-base-cased-tokenizer", "tokenizer_class": "BertTokenizer"}
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "C:\\Users\\小周天/.cache\\huggingface\\transformers\\8183382ed1d3dbb68e827ee934b131f7a2fded38f6b5d6e94cf29c9e363e7cde.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "./save_chinese_model", "tokenizer_class": "BertTokenizer"}