bert-cased

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [hung200504/bert-21](https://huggingface.co/hung200504/bert-21) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.4374
+- Loss: 11.8463
 
 ## Model description
 
@@ -34,7 +34,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
+- learning_rate: 3e-07
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -46,17 +46,17 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 10.4103       | 0.09  | 5    | 10.6941         |
-| 9.1193        | 0.18  | 10   | 9.3831          |
-| 7.5499        | 0.27  | 15   | 8.3303          |
-| 6.6925        | 0.36  | 20   | 7.5582          |
-| 6.1016        | 0.45  | 25   | 7.0295          |
-| 5.6815        | 0.55  | 30   | 6.7212          |
-| 4.8923        | 0.64  | 35   | 6.5725          |
-| 4.78          | 0.73  | 40   | 6.5496          |
-| 5.0663        | 0.82  | 45   | 6.5124          |
-| 4.8708        | 0.91  | 50   | 6.4650          |
-| 4.832         | 1.0   | 55   | 6.4374          |
+| 10.907        | 0.09  | 5    | 11.9207         |
+| 11.0539       | 0.18  | 10   | 11.9068         |
+| 10.685        | 0.27  | 15   | 11.8944         |
+| 10.843        | 0.36  | 20   | 11.8840         |
+| 10.8607       | 0.45  | 25   | 11.8741         |
+| 10.9156       | 0.55  | 30   | 11.8658         |
+| 10.2342       | 0.64  | 35   | 11.8593         |
+| 10.8976       | 0.73  | 40   | 11.8541         |
+| 10.4814       | 0.82  | 45   | 11.8501         |
+| 10.4101       | 0.91  | 50   | 11.8476         |
+| 10.2016       | 1.0   | 55   | 11.8463         |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:304c69428185c473723503cab7599242d2305c166301f7ccfd6a4821df0890fa
+oid sha256:d1e1aca68dfa149485721a2faa5895ba69f274f4df117c59598f5e628739e199
 size 430953062

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cf4c87b82581e8fa9a3a122b3cb86709bc6805e8dcd45f6c70cc00edb6e9005
+oid sha256:b14ab8c21d1947772dde0d11a98ff2919001753f884f0ead1293e00daece1213
 size 4472