b10401015
/

hw1-2-question_answering-bert-base-chinese-finetuned

@@ -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: 1.0376
 ## Model description
@@ -40,15 +40,14 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
 ### Training results
-| Training Loss | Epoch | Step  | Validation Loss |
-|:-------------:|:-----:|:-----:|:---------------:|
-| 0.7744        | 1.0   | 3456  | 0.7555          |
-| 0.3747        | 2.0   | 6912  | 0.7105          |
-| 0.1813        | 3.0   | 10368 | 1.0376          |
 ### 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: 0.7718
 ## Model description
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 2
 ### Training results
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.7585        | 1.0   | 3456 | 0.7009          |
+| 0.3201        | 2.0   | 6912 | 0.7718          |
 ### Framework versions

runs/Sep18_14-30-51_aa1dab4d7cf8/events.out.tfevents.1726669864.aa1dab4d7cf8.907.1 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddaa51660f89b29ffb3432357f541feb089d7a5751740b2ced5368301809eb3e
-size 8173

 version https://git-lfs.github.com/spec/v1
+oid sha256:b88578ab93b7ba2894cce91fd3bbcedf2c2d435ae6f356f7bb2b952598ffdfce
+size 8798