End of training

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-bert/bert-base-chinese](https://huggingface.co/google-bert/bert-base-chinese) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2579
-- Accuracy: 0.9416
+- Loss: 0.3173
+- Accuracy: 0.9393
 
 ## Model description
 
@@ -50,15 +50,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 54   | 0.3100          | 0.9077   |
-| 0.0507        | 2.0   | 108  | 0.2642          | 0.9416   |
-| 0.0507        | 3.0   | 162  | 0.2298          | 0.9393   |
-| 0.0311        | 4.0   | 216  | 0.2579          | 0.9416   |
+| No log        | 1.0   | 54   | 0.3855          | 0.9206   |
+| 0.0226        | 2.0   | 108  | 0.3115          | 0.9381   |
+| 0.0226        | 3.0   | 162  | 0.2941          | 0.9369   |
+| 0.0105        | 4.0   | 216  | 0.3173          | 0.9393   |
 
 
 ### Framework versions
 
-- Transformers 4.57.1
-- Pytorch 2.8.0+cu126
+- Transformers 5.0.0
+- Pytorch 2.9.0+cu126
 - Datasets 4.0.0
-- Tokenizers 0.22.1
+- Tokenizers 0.22.2

config.json

@@ -1,16 +1,20 @@
 {
+  "add_cross_attention": false,
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
   "classifier_dropout": null,
   "directionality": "bidi",
   "dtype": "float32",
+  "eos_token_id": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
+  "is_decoder": false,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
@@ -22,10 +26,10 @@
   "pooler_num_fc_layers": 3,
   "pooler_size_per_head": 128,
   "pooler_type": "first_token_transform",
-  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "transformers_version": "4.57.1",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
   "type_vocab_size": 2,
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 21128
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2291b813fdd768aa6fccd47dc557c274791f73663da8366f685caa40b8f6e7ed
-size 409100240
+oid sha256:773b26caec7e382763c3e2feeb34fdc9256043c3af2e72d1541b9e1178e4278c
+size 409100216

tokenizer_config.json

@@ -1,50 +1,8 @@
 {
-  "added_tokens_decoder": {
-    "0": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "100": {
-      "content": "[UNK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "101": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "102": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "clean_up_tokenization_spaces": false,
+  "backend": "tokenizers",
   "cls_token": "[CLS]",
   "do_lower_case": false,
-  "extra_special_tokens": {},
+  "is_local": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbf193e48072a40edb8e04734d050dffa225c3be49bc3056c5c43ce38db02b9e
-size 5841
+oid sha256:9140d4a7c2541afa3314690cc4c6c3ac050eb2aec25f705690482b82ebdf26dc
+size 5201