Model save

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Twitter/twhin-bert-large](https://huggingface.co/Twitter/twhin-bert-large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7381
+- Loss: 1.7971
 
 ## Model description
 
@@ -46,11 +46,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.2972        | 1.0   | 232  | 2.1153          |
-| 2.0961        | 2.0   | 464  | 1.9547          |
-| 1.9033        | 3.0   | 696  | 1.8463          |
-| 1.9754        | 4.0   | 928  | 1.7398          |
-| 1.8714        | 5.0   | 1160 | 1.7381          |
+| 2.3413        | 1.0   | 232  | 2.1186          |
+| 2.0911        | 2.0   | 464  | 2.0398          |
+| 2.0235        | 3.0   | 696  | 1.8352          |
+| 1.8738        | 4.0   | 928  | 1.7995          |
+| 1.6975        | 5.0   | 1160 | 1.7971          |
 
 
 ### Framework versions

runs/Aug07_07-58-39_1c570df269c6/events.out.tfevents.1723017520.1c570df269c6.19657.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f630a31d3e4ca4012e7db00aa52c2dd1367d7c9b0e44b2a2ed7bb4e3c1b5bb19
-size 30385
+oid sha256:3936254892d4551204cf878cefc6e11366818401af70ab482406db8799380bc8
+size 31010