End of training

README.md

@@ -15,7 +15,7 @@ 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: 0.3522
+- Loss: 0.1214
 
 ## Model description
 
@@ -46,14 +46,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.771         | 1.0   | 10   | 0.5336          |
-| 0.4083        | 2.0   | 20   | 0.4325          |
-| 0.1741        | 3.0   | 30   | 0.3522          |
+| No log        | 1.0   | 7    | 0.4115          |
+| 0.7297        | 2.0   | 14   | 0.1834          |
+| 0.1589        | 3.0   | 21   | 0.1214          |
 
 
 ### Framework versions
 
 - Transformers 4.51.3
 - Pytorch 2.6.0+cu124
-- Datasets 3.5.0
+- Datasets 3.5.1
 - Tokenizers 0.21.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b33885fcb154ca92da667a528fc83c524ce2ebf6953f1674fe4b3959a339e1a7
+oid sha256:e34c5d8c614ce7fa572059c52f4e62e9b3b7dec6a85d8b05a58af0db33856817
 size 406746908