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-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.3158
+- Loss: 1.9471
 
 ## Model description
 
@@ -40,15 +40,22 @@ 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: 3.0
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.6877        | 1.0   | 66   | 2.5071          |
-| 2.4714        | 2.0   | 132  | 2.3436          |
-| 2.3531        | 3.0   | 198  | 2.2612          |
+| 2.6813        | 1.0   | 66   | 2.4897          |
+| 2.4377        | 2.0   | 132  | 2.2871          |
+| 2.2739        | 3.0   | 198  | 2.1468          |
+| 2.1432        | 4.0   | 264  | 2.1158          |
+| 2.058         | 5.0   | 330  | 2.0199          |
+| 2.0181        | 6.0   | 396  | 1.9629          |
+| 1.9669        | 7.0   | 462  | 2.0044          |
+| 1.9437        | 8.0   | 528  | 2.0210          |
+| 1.9289        | 9.0   | 594  | 1.8997          |
+| 1.9102        | 10.0  | 660  | 1.9474          |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc9d7585755aa9cb620009ee5637addc7f6cc469ceb86942c4121f10f0e2e664
+oid sha256:44f8677a36ad335fe2de5b1ac75015cc62aa4180e07e570bc21cc4a1c0f0680e
 size 669924786