End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: hfl/chinese-macbert-base
+base_model: bert-base-chinese
 tags:
 - generated_from_trainer
 model-index:
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # classification_2
 
-This model is a fine-tuned version of [hfl/chinese-macbert-base](https://huggingface.co/hfl/chinese-macbert-base) on the None dataset.
+This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2281
+- Loss: 0.0260
 
 ## Model description
 
@@ -35,26 +35,36 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 2e-05
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 3
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.5343        | 1.0   | 20   | 0.3772          |
-| 0.0912        | 2.0   | 40   | 0.6497          |
-| 0.0095        | 3.0   | 60   | 0.2281          |
+| No log        | 1.0   | 3    | 0.6182          |
+| No log        | 2.0   | 6    | 0.5323          |
+| No log        | 3.0   | 9    | 0.3020          |
+| 0.602         | 4.0   | 12   | 0.1746          |
+| 0.602         | 5.0   | 15   | 0.1003          |
+| 0.602         | 6.0   | 18   | 0.0594          |
+| 0.1176        | 7.0   | 21   | 0.0400          |
+| 0.1176        | 8.0   | 24   | 0.0310          |
+| 0.1176        | 9.0   | 27   | 0.0273          |
+| 0.0277        | 10.0  | 30   | 0.0260          |
 
 
 ### Framework versions
 
-- Transformers 4.51.3
-- Pytorch 2.6.0+cu124
-- Datasets 3.5.0
-- Tokenizers 0.21.1
+- Transformers 4.57.3
+- Pytorch 2.9.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.1