End of training

README.md

@@ -1,6 +1,5 @@
 ---
-license: apache-2.0
-base_model: bert-base-cased
+base_model: bert-base-chinese
 tags:
 - generated_from_trainer
 metrics:
@@ -18,13 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # berttest2
 
-This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
+This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2938
-- Precision: 0.4447
-- Recall: 0.3059
-- F1: 0.3625
-- Accuracy: 0.9212
+- Loss: 0.0206
+- Precision: 0.9610
+- Recall: 0.9653
+- F1: 0.9631
+- Accuracy: 0.9956
 
 ## Model description
 
@@ -55,9 +54,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.3339        | 1.0   | 2609 | 0.3198          | 0.4350    | 0.2483 | 0.3161 | 0.9150   |
-| 0.3034        | 2.0   | 5218 | 0.2974          | 0.4494    | 0.2851 | 0.3489 | 0.9203   |
-| 0.2879        | 3.0   | 7827 | 0.2938          | 0.4447    | 0.3059 | 0.3625 | 0.9212   |
+| 0.028         | 1.0   | 2609 | 0.0225          | 0.9385    | 0.9350 | 0.9368 | 0.9932   |
+| 0.011         | 2.0   | 5218 | 0.0182          | 0.9542    | 0.9592 | 0.9567 | 0.9951   |
+| 0.0044        | 3.0   | 7827 | 0.0206          | 0.9610    | 0.9653 | 0.9631 | 0.9956   |
 
 
 ### Framework versions