End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3204
-- F1: 0.9255
+- Loss: 0.3529
+- F1: 0.9331
 
 ## Model description
 
@@ -43,15 +43,17 @@ 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
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 1.1756        | 1.0   | 626  | 0.8871          | 0.8085 |
-| 0.4121        | 2.0   | 1252 | 0.4035          | 0.9140 |
-| 0.2018        | 3.0   | 1878 | 0.3204          | 0.9255 |
+| 0.1452        | 1.0   | 626  | 0.3403          | 0.9167 |
+| 0.0633        | 2.0   | 1252 | 0.3507          | 0.9227 |
+| 0.0432        | 3.0   | 1878 | 0.3498          | 0.9297 |
+| 0.0183        | 4.0   | 2504 | 0.3560          | 0.9311 |
+| 0.0065        | 5.0   | 3130 | 0.3529          | 0.9331 |
 
 
 ### Framework versions

logs/events.out.tfevents.1705178091.bakuretsopc.9783.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9c256ea1702d3f711b377416e10c5deb1b63b3133b108fd4e7c0279121a0a8c
-size 13713
+oid sha256:4e5e2d219f24111af964da54c80989676f68ad8121fa432c6220a93fb6635580
+size 14067