End of training

README.md

@@ -1,5 +1,6 @@
 ---
 library_name: transformers
+license: apache-2.0
 base_model: bert-base-chinese
 tags:
 - generated_from_trainer
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 0.0156
+- Loss: 0.0099
 
 ## Model description
 
@@ -34,29 +35,36 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- 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: 6
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 7    | 0.3058          |
-| 0.6093        | 2.0   | 14   | 0.0692          |
-| 0.0904        | 3.0   | 21   | 0.0277          |
-| 0.0904        | 4.0   | 28   | 0.0386          |
-| 0.0343        | 5.0   | 35   | 0.0174          |
-| 0.0126        | 6.0   | 42   | 0.0156          |
+| No log        | 1.0   | 3    | 0.5742          |
+| No log        | 2.0   | 6    | 0.3245          |
+| No log        | 3.0   | 9    | 0.1796          |
+| 0.4633        | 4.0   | 12   | 0.0784          |
+| 0.4633        | 5.0   | 15   | 0.0439          |
+| 0.4633        | 6.0   | 18   | 0.0265          |
+| 0.0749        | 7.0   | 21   | 0.0163          |
+| 0.0749        | 8.0   | 24   | 0.0121          |
+| 0.0749        | 9.0   | 27   | 0.0104          |
+| 0.0183        | 10.0  | 30   | 0.0099          |
 
 
 ### Framework versions
 
-- Transformers 4.51.3
-- Pytorch 2.6.0+cu124
-- Datasets 3.5.1
-- Tokenizers 0.21.1
+- Transformers 4.57.3
+- Pytorch 2.9.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.1