zhiguoxu
/

bert-base-chinese-finetuned-split

@@ -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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0149
 - F1: 1.0
 ## Model description
@@ -36,8 +36,8 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 26
-- eval_batch_size: 26
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -47,26 +47,26 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 3.3649        | 1.0   | 1    | 1.5647          | 0.0    |
-| 1.6645        | 2.0   | 2    | 0.7201          | 0.0    |
-| 0.8002        | 3.0   | 3    | 0.5081          | 0.0    |
-| 0.5252        | 4.0   | 4    | 0.3935          | 0.0    |
-| 0.4039        | 5.0   | 5    | 0.3012          | 0.0    |
-| 0.331         | 6.0   | 6    | 0.2515          | 0.0    |
-| 0.2797        | 7.0   | 7    | 0.2132          | 0.1538 |
-| 0.2396        | 8.0   | 8    | 0.1771          | 0.4    |
-| 0.2098        | 9.0   | 9    | 0.1444          | 0.5882 |
-| 0.1802        | 10.0  | 10   | 0.1197          | 0.8372 |
-| 0.1413        | 11.0  | 11   | 0.0972          | 0.8372 |
-| 0.1195        | 12.0  | 12   | 0.0741          | 0.9333 |
-| 0.0962        | 13.0  | 13   | 0.0551          | 0.9565 |
-| 0.0774        | 14.0  | 14   | 0.0413          | 1.0    |
-| 0.0641        | 15.0  | 15   | 0.0323          | 1.0    |
-| 0.0517        | 16.0  | 16   | 0.0256          | 1.0    |
-| 0.0425        | 17.0  | 17   | 0.0211          | 1.0    |
-| 0.035         | 18.0  | 18   | 0.0184          | 1.0    |
-| 0.031         | 19.0  | 19   | 0.0161          | 1.0    |
-| 0.0295        | 20.0  | 20   | 0.0149          | 1.0    |
 ### Framework versions

 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: 0.0177
 - F1: 1.0
 ## Model description
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
+- train_batch_size: 27
+- eval_batch_size: 27
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
+| 3.8485        | 1.0   | 1    | 1.9458          | 0.0    |
+| 2.0072        | 2.0   | 2    | 0.8351          | 0.0    |
+| 0.8935        | 3.0   | 3    | 0.4898          | 0.0    |
+| 0.5205        | 4.0   | 4    | 0.3869          | 0.0    |
+| 0.4011        | 5.0   | 5    | 0.2898          | 0.0    |
+| 0.3135        | 6.0   | 6    | 0.2673          | 0.0769 |
+| 0.291         | 7.0   | 7    | 0.2318          | 0.2143 |
+| 0.2611        | 8.0   | 8    | 0.1855          | 0.0769 |
+| 0.2101        | 9.0   | 9    | 0.1557          | 0.2759 |
+| 0.1809        | 10.0  | 10   | 0.1254          | 0.5714 |
+| 0.1661        | 11.0  | 11   | 0.1004          | 0.8636 |
+| 0.1307        | 12.0  | 12   | 0.0840          | 0.96   |
+| 0.1081        | 13.0  | 13   | 0.0696          | 0.96   |
+| 0.0942        | 14.0  | 14   | 0.0540          | 0.96   |
+| 0.071         | 15.0  | 15   | 0.0407          | 0.9796 |
+| 0.0659        | 16.0  | 16   | 0.0318          | 0.9796 |
+| 0.0492        | 17.0  | 17   | 0.0256          | 0.9796 |
+| 0.0426        | 18.0  | 18   | 0.0214          | 1.0    |
+| 0.0407        | 19.0  | 19   | 0.0189          | 1.0    |
+| 0.0354        | 20.0  | 20   | 0.0177          | 1.0    |
 ### Framework versions